In [6]:
def play_episode(env, agent, seed=None, mode=None, render=False):
observation, _ = env.reset(seed=seed)
reward, terminated, truncated = 0., False, False
agent.reset(mode=mode)
episode_reward, elapsed_steps = 0., 0
while True:
action = agent.step(observation, reward, terminated)
if render:
env.render()
if terminated or truncated:
break
observation, reward, terminated, truncated, _ = env.step(action)
episode_reward += reward
elapsed_steps += 1
agent.close()
return episode_reward, elapsed_steps
logging.info('==== expert ====')
episode_rewards = []
for episode in range(5):
episode_reward, elapsed_steps = play_episode(env, agent, mode='expert')
episode_rewards.append(episode_reward)
logging.info('expert episode %d: reward = %.2f, steps = %d',
episode, episode_reward, elapsed_steps)
logging.info('average expert episode reward = %.2f ± %.2f',
np.mean(episode_rewards), np.std(episode_rewards))
logging.info('==== train ====')
episode_rewards = []
for episode in itertools.count():
episode_reward, elapsed_steps = play_episode(env, agent, seed=episode,
mode='train')
episode_rewards.append(episode_reward)
logging.info('train episode %d: reward = %.2f, steps = %d',
episode, episode_reward, elapsed_steps)
if np.mean(episode_rewards[-10:]) > 30:
break
plt.plot(episode_rewards)
logging.info('==== test ====')
episode_rewards = []
for episode in range(100):
episode_reward, elapsed_steps = play_episode(env, agent)
episode_rewards.append(episode_reward)
logging.info('test episode %d: reward = %.2f, steps = %d',
episode, episode_reward, elapsed_steps)
logging.info('average episode reward = %.2f ± %.2f',
np.mean(episode_rewards), np.std(episode_rewards))
00:30:40 [INFO] ==== expert ==== 00:30:51 [INFO] expert episode 0: reward = 3636.76, steps = 1000 00:31:02 [INFO] expert episode 1: reward = 3584.22, steps = 1000 00:31:14 [INFO] expert episode 2: reward = 3582.76, steps = 1000 00:31:25 [INFO] expert episode 3: reward = 3641.40, steps = 1000 00:31:36 [INFO] expert episode 4: reward = 3581.67, steps = 1000 00:31:36 [INFO] average expert episode reward = 3605.36 ± 27.58 00:31:36 [INFO] ==== train ==== 00:31:38 [INFO] train episode 0: reward = -79.14, steps = 18 00:31:40 [INFO] train episode 1: reward = -110.21, steps = 18 00:31:42 [INFO] train episode 2: reward = -101.51, steps = 18 00:31:44 [INFO] train episode 3: reward = -92.36, steps = 21 00:31:46 [INFO] train episode 4: reward = -108.00, steps = 19 00:31:47 [INFO] train episode 5: reward = -93.61, steps = 19 00:31:49 [INFO] train episode 6: reward = -74.89, steps = 19 00:31:51 [INFO] train episode 7: reward = -125.12, steps = 19 00:31:53 [INFO] train episode 8: reward = -84.82, steps = 19 00:31:55 [INFO] train episode 9: reward = -111.11, steps = 18 00:31:57 [INFO] train episode 10: reward = -89.66, steps = 18 00:31:59 [INFO] train episode 11: reward = -84.21, steps = 20 00:32:00 [INFO] train episode 12: reward = -90.54, steps = 18 00:32:02 [INFO] train episode 13: reward = -73.38, steps = 18 00:32:04 [INFO] train episode 14: reward = -99.06, steps = 18 00:32:06 [INFO] train episode 15: reward = -76.72, steps = 20 00:32:08 [INFO] train episode 16: reward = -116.54, steps = 18 00:32:10 [INFO] train episode 17: reward = -68.15, steps = 18 00:32:11 [INFO] train episode 18: reward = -119.01, steps = 17 00:32:13 [INFO] train episode 19: reward = -77.43, steps = 18 00:32:15 [INFO] train episode 20: reward = -67.85, steps = 20 00:32:17 [INFO] train episode 21: reward = -66.71, steps = 19 00:32:19 [INFO] train episode 22: reward = -96.96, steps = 20 00:32:20 [INFO] train episode 23: reward = -73.69, steps = 17 00:32:22 [INFO] train episode 24: reward = -82.73, steps = 18 00:32:24 [INFO] train episode 25: reward = -119.54, steps = 19 00:32:26 [INFO] train episode 26: reward = -83.12, steps = 19 00:32:27 [INFO] train episode 27: reward = -110.98, steps = 19 00:32:29 [INFO] train episode 28: reward = -111.10, steps = 20 00:32:31 [INFO] train episode 29: reward = -96.16, steps = 19 00:32:33 [INFO] train episode 30: reward = -68.18, steps = 19 00:32:35 [INFO] train episode 31: reward = -86.15, steps = 19 00:32:37 [INFO] train episode 32: reward = -87.55, steps = 20 00:32:39 [INFO] train episode 33: reward = -86.94, steps = 18 00:32:41 [INFO] train episode 34: reward = -98.93, steps = 20 00:32:42 [INFO] train episode 35: reward = -84.46, steps = 19 00:32:44 [INFO] train episode 36: reward = -109.62, steps = 19 00:32:46 [INFO] train episode 37: reward = -77.42, steps = 17 00:32:48 [INFO] train episode 38: reward = -84.67, steps = 19 00:32:49 [INFO] train episode 39: reward = -107.70, steps = 18 00:32:52 [INFO] train episode 40: reward = -99.60, steps = 24 00:32:54 [INFO] train episode 41: reward = -72.74, steps = 19 00:32:56 [INFO] train episode 42: reward = -127.59, steps = 28 00:32:58 [INFO] train episode 43: reward = -77.09, steps = 18 00:33:00 [INFO] train episode 44: reward = -70.73, steps = 19 00:33:02 [INFO] train episode 45: reward = -102.10, steps = 20 00:33:04 [INFO] train episode 46: reward = -127.57, steps = 20 00:33:05 [INFO] train episode 47: reward = -103.09, steps = 19 00:33:07 [INFO] train episode 48: reward = -116.48, steps = 21 00:33:09 [INFO] train episode 49: reward = -81.13, steps = 19 00:33:11 [INFO] train episode 50: reward = -102.49, steps = 19 00:33:13 [INFO] train episode 51: reward = -102.19, steps = 23 00:33:15 [INFO] train episode 52: reward = -102.18, steps = 19 00:33:17 [INFO] train episode 53: reward = -70.11, steps = 19 00:33:19 [INFO] train episode 54: reward = -93.22, steps = 18 00:33:21 [INFO] train episode 55: reward = -108.73, steps = 21 00:33:23 [INFO] train episode 56: reward = -105.17, steps = 19 00:33:25 [INFO] train episode 57: reward = -72.26, steps = 18 00:33:28 [INFO] train episode 58: reward = -120.26, steps = 33 00:33:30 [INFO] train episode 59: reward = -111.37, steps = 25 00:33:32 [INFO] train episode 60: reward = -89.61, steps = 20 00:33:34 [INFO] train episode 61: reward = -74.78, steps = 19 00:33:35 [INFO] train episode 62: reward = -85.73, steps = 12 00:33:37 [INFO] train episode 63: reward = -78.95, steps = 18 00:33:39 [INFO] train episode 64: reward = -118.64, steps = 19 00:33:41 [INFO] train episode 65: reward = -95.37, steps = 20 00:33:43 [INFO] train episode 66: reward = -97.14, steps = 20 00:33:44 [INFO] train episode 67: reward = -64.64, steps = 20 00:33:46 [INFO] train episode 68: reward = -69.37, steps = 19 00:33:48 [INFO] train episode 69: reward = -76.50, steps = 20 00:33:50 [INFO] train episode 70: reward = -92.06, steps = 24 00:33:52 [INFO] train episode 71: reward = -103.73, steps = 19 00:33:54 [INFO] train episode 72: reward = -95.87, steps = 19 00:33:56 [INFO] train episode 73: reward = -83.82, steps = 20 00:33:58 [INFO] train episode 74: reward = -93.55, steps = 20 00:34:00 [INFO] train episode 75: reward = -110.14, steps = 18 00:34:02 [INFO] train episode 76: reward = -85.88, steps = 19 00:34:03 [INFO] train episode 77: reward = -89.40, steps = 19 00:34:06 [INFO] train episode 78: reward = -138.31, steps = 28 00:34:08 [INFO] train episode 79: reward = -85.14, steps = 18 00:34:09 [INFO] train episode 80: reward = -91.14, steps = 14 00:34:11 [INFO] train episode 81: reward = -104.99, steps = 19 00:34:13 [INFO] train episode 82: reward = -123.08, steps = 18 00:34:15 [INFO] train episode 83: reward = -106.35, steps = 20 00:34:16 [INFO] train episode 84: reward = -68.89, steps = 19 00:34:18 [INFO] train episode 85: reward = -93.73, steps = 17 00:34:20 [INFO] train episode 86: reward = -68.90, steps = 19 00:34:22 [INFO] train episode 87: reward = -92.88, steps = 18 00:34:23 [INFO] train episode 88: reward = -120.13, steps = 19 00:34:25 [INFO] train episode 89: reward = -73.32, steps = 19 00:34:27 [INFO] train episode 90: reward = -92.91, steps = 19 00:34:29 [INFO] train episode 91: reward = -116.92, steps = 19 00:34:31 [INFO] train episode 92: reward = -92.28, steps = 19 00:34:33 [INFO] train episode 93: reward = -66.03, steps = 18 00:34:35 [INFO] train episode 94: reward = -129.49, steps = 21 00:34:37 [INFO] train episode 95: reward = -88.44, steps = 20 00:34:38 [INFO] train episode 96: reward = -73.53, steps = 19 00:34:40 [INFO] train episode 97: reward = -90.76, steps = 19 00:34:45 [INFO] train episode 98: reward = -80.65, steps = 18 00:34:46 [INFO] train episode 99: reward = -106.17, steps = 19 00:34:48 [INFO] train episode 100: reward = -74.56, steps = 18 00:34:50 [INFO] train episode 101: reward = -124.97, steps = 17 00:34:52 [INFO] train episode 102: reward = -73.13, steps = 21 00:34:54 [INFO] train episode 103: reward = -120.33, steps = 23 00:34:56 [INFO] train episode 104: reward = -91.96, steps = 18 00:34:58 [INFO] train episode 105: reward = -88.31, steps = 19 00:34:59 [INFO] train episode 106: reward = -80.25, steps = 19 00:35:01 [INFO] train episode 107: reward = -67.95, steps = 20 00:35:03 [INFO] train episode 108: reward = -86.37, steps = 18 00:35:05 [INFO] train episode 109: reward = -78.90, steps = 18 00:35:06 [INFO] train episode 110: reward = -73.80, steps = 18 00:35:08 [INFO] train episode 111: reward = -94.26, steps = 18 00:35:10 [INFO] train episode 112: reward = -127.86, steps = 20 00:35:12 [INFO] train episode 113: reward = -108.71, steps = 20 00:35:14 [INFO] train episode 114: reward = -92.66, steps = 18 00:35:16 [INFO] train episode 115: reward = -95.80, steps = 18 00:35:17 [INFO] train episode 116: reward = -76.48, steps = 19 00:35:19 [INFO] train episode 117: reward = -89.09, steps = 19 00:35:21 [INFO] train episode 118: reward = -101.88, steps = 20 00:35:23 [INFO] train episode 119: reward = -73.70, steps = 18 00:35:24 [INFO] train episode 120: reward = -94.50, steps = 19 00:35:26 [INFO] train episode 121: reward = -50.80, steps = 19 00:35:28 [INFO] train episode 122: reward = -90.13, steps = 18 00:35:30 [INFO] train episode 123: reward = -71.93, steps = 20 00:35:32 [INFO] train episode 124: reward = -107.20, steps = 20 00:35:34 [INFO] train episode 125: reward = -111.67, steps = 18 00:35:35 [INFO] train episode 126: reward = -96.52, steps = 19 00:35:37 [INFO] train episode 127: reward = -126.17, steps = 23 00:35:39 [INFO] train episode 128: reward = -101.27, steps = 20 00:35:41 [INFO] train episode 129: reward = -81.64, steps = 19 00:35:43 [INFO] train episode 130: reward = -95.74, steps = 21 00:35:45 [INFO] train episode 131: reward = -110.22, steps = 18 00:35:47 [INFO] train episode 132: reward = -118.17, steps = 18 00:35:48 [INFO] train episode 133: reward = -78.08, steps = 18 00:35:50 [INFO] train episode 134: reward = -85.33, steps = 19 00:35:53 [INFO] train episode 135: reward = -143.50, steps = 30 00:35:55 [INFO] train episode 136: reward = -88.60, steps = 19 00:35:56 [INFO] train episode 137: reward = -100.95, steps = 18 00:35:58 [INFO] train episode 138: reward = -120.17, steps = 18 00:36:00 [INFO] train episode 139: reward = -72.63, steps = 19 00:36:02 [INFO] train episode 140: reward = -86.22, steps = 20 00:36:04 [INFO] train episode 141: reward = -77.49, steps = 19 00:36:05 [INFO] train episode 142: reward = -86.23, steps = 17 00:36:07 [INFO] train episode 143: reward = -91.12, steps = 19 00:36:09 [INFO] train episode 144: reward = -95.69, steps = 19 00:36:11 [INFO] train episode 145: reward = -77.20, steps = 20 00:36:13 [INFO] train episode 146: reward = -67.32, steps = 19 00:36:15 [INFO] train episode 147: reward = -78.64, steps = 23 00:36:17 [INFO] train episode 148: reward = -89.77, steps = 20 00:36:19 [INFO] train episode 149: reward = -71.66, steps = 19 00:36:21 [INFO] train episode 150: reward = -96.32, steps = 19 00:36:23 [INFO] train episode 151: reward = -88.35, steps = 19 00:36:24 [INFO] train episode 152: reward = -76.34, steps = 18 00:36:27 [INFO] train episode 153: reward = -125.37, steps = 25 00:36:29 [INFO] train episode 154: reward = -87.33, steps = 17 00:36:31 [INFO] train episode 155: reward = -96.88, steps = 20 00:36:33 [INFO] train episode 156: reward = -106.17, steps = 26 00:36:35 [INFO] train episode 157: reward = -78.84, steps = 17 00:36:37 [INFO] train episode 158: reward = -126.25, steps = 19 00:36:39 [INFO] train episode 159: reward = -94.31, steps = 19 00:36:41 [INFO] train episode 160: reward = -96.24, steps = 20 00:36:43 [INFO] train episode 161: reward = -92.35, steps = 20 00:36:45 [INFO] train episode 162: reward = -99.01, steps = 20 00:36:48 [INFO] train episode 163: reward = -149.55, steps = 30 00:36:49 [INFO] train episode 164: reward = -119.34, steps = 17 00:36:51 [INFO] train episode 165: reward = -99.94, steps = 18 00:36:53 [INFO] train episode 166: reward = -48.48, steps = 18 00:36:55 [INFO] train episode 167: reward = -105.09, steps = 18 00:36:57 [INFO] train episode 168: reward = -107.82, steps = 19 00:36:59 [INFO] train episode 169: reward = -93.99, steps = 21 00:37:00 [INFO] train episode 170: reward = -75.25, steps = 17 00:37:02 [INFO] train episode 171: reward = -94.52, steps = 19 00:37:04 [INFO] train episode 172: reward = -88.56, steps = 19 00:37:06 [INFO] train episode 173: reward = -103.38, steps = 21 00:37:08 [INFO] train episode 174: reward = -84.22, steps = 19 00:37:10 [INFO] train episode 175: reward = -95.38, steps = 20 00:37:12 [INFO] train episode 176: reward = -100.47, steps = 19 00:37:14 [INFO] train episode 177: reward = -90.15, steps = 19 00:37:16 [INFO] train episode 178: reward = -71.66, steps = 19 00:37:18 [INFO] train episode 179: reward = -76.89, steps = 19 00:37:21 [INFO] train episode 180: reward = -136.09, steps = 25 00:37:23 [INFO] train episode 181: reward = -88.00, steps = 18 00:37:24 [INFO] train episode 182: reward = -103.00, steps = 18 00:37:26 [INFO] train episode 183: reward = -102.34, steps = 18 00:37:29 [INFO] train episode 184: reward = -104.66, steps = 20 00:37:30 [INFO] train episode 185: reward = -122.50, steps = 19 00:37:32 [INFO] train episode 186: reward = -82.66, steps = 18 00:37:34 [INFO] train episode 187: reward = -81.76, steps = 21 00:37:36 [INFO] train episode 188: reward = -68.35, steps = 19 00:37:38 [INFO] train episode 189: reward = -78.80, steps = 18 00:37:40 [INFO] train episode 190: reward = -109.60, steps = 17 00:37:42 [INFO] train episode 191: reward = -62.15, steps = 20 00:37:44 [INFO] train episode 192: reward = -97.61, steps = 19 00:37:47 [INFO] train episode 193: reward = -108.08, steps = 19 00:37:48 [INFO] train episode 194: reward = -116.01, steps = 19 00:37:50 [INFO] train episode 195: reward = -84.76, steps = 19 00:37:53 [INFO] train episode 196: reward = -88.13, steps = 20 00:37:55 [INFO] train episode 197: reward = -72.49, steps = 20 00:37:57 [INFO] train episode 198: reward = -143.37, steps = 19 00:37:59 [INFO] train episode 199: reward = -87.70, steps = 18 00:38:01 [INFO] train episode 200: reward = -110.97, steps = 18 00:38:03 [INFO] train episode 201: reward = -109.22, steps = 24 00:38:05 [INFO] train episode 202: reward = -98.83, steps = 18 00:38:07 [INFO] train episode 203: reward = -98.76, steps = 23 00:38:09 [INFO] train episode 204: reward = -101.23, steps = 19 00:38:11 [INFO] train episode 205: reward = -118.61, steps = 19 00:38:13 [INFO] train episode 206: reward = -101.97, steps = 20 00:38:15 [INFO] train episode 207: reward = -82.13, steps = 19 00:38:18 [INFO] train episode 208: reward = -70.02, steps = 18 00:38:20 [INFO] train episode 209: reward = -115.30, steps = 21 00:38:23 [INFO] train episode 210: reward = -131.19, steps = 23 00:38:24 [INFO] train episode 211: reward = -94.39, steps = 17 00:38:26 [INFO] train episode 212: reward = -65.64, steps = 19 00:38:28 [INFO] train episode 213: reward = -104.49, steps = 20 00:38:30 [INFO] train episode 214: reward = -102.36, steps = 19 00:38:32 [INFO] train episode 215: reward = -80.17, steps = 19 00:38:33 [INFO] train episode 216: reward = -132.09, steps = 19 00:38:35 [INFO] train episode 217: reward = -102.71, steps = 18 00:38:37 [INFO] train episode 218: reward = -91.00, steps = 18 00:38:39 [INFO] train episode 219: reward = -97.14, steps = 19 00:38:42 [INFO] train episode 220: reward = -113.37, steps = 22 00:38:44 [INFO] train episode 221: reward = -105.84, steps = 20 00:38:45 [INFO] train episode 222: reward = -97.06, steps = 19 00:38:48 [INFO] train episode 223: reward = -71.83, steps = 21 00:38:50 [INFO] train episode 224: reward = -98.88, steps = 19 00:38:52 [INFO] train episode 225: reward = -107.81, steps = 18 00:38:55 [INFO] train episode 226: reward = -108.72, steps = 29 00:38:57 [INFO] train episode 227: reward = -93.02, steps = 21 00:39:00 [INFO] train episode 228: reward = -111.14, steps = 21 00:39:03 [INFO] train episode 229: reward = -108.02, steps = 25 00:39:05 [INFO] train episode 230: reward = -71.11, steps = 17 00:39:07 [INFO] train episode 231: reward = -95.47, steps = 19 00:39:10 [INFO] train episode 232: reward = -85.53, steps = 19 00:39:12 [INFO] train episode 233: reward = -97.74, steps = 18 00:39:14 [INFO] train episode 234: reward = -105.33, steps = 19 00:39:17 [INFO] train episode 235: reward = -69.77, steps = 20 00:39:19 [INFO] train episode 236: reward = -101.60, steps = 19 00:39:21 [INFO] train episode 237: reward = -96.08, steps = 18 00:39:23 [INFO] train episode 238: reward = -110.11, steps = 19 00:39:26 [INFO] train episode 239: reward = -83.34, steps = 19 00:39:28 [INFO] train episode 240: reward = -88.50, steps = 20 00:39:31 [INFO] train episode 241: reward = -128.01, steps = 21 00:39:33 [INFO] train episode 242: reward = -90.53, steps = 19 00:39:35 [INFO] train episode 243: reward = -98.01, steps = 19 00:39:36 [INFO] train episode 244: reward = -81.08, steps = 18 00:39:39 [INFO] train episode 245: reward = -82.13, steps = 19 00:39:41 [INFO] train episode 246: reward = -92.65, steps = 18 00:39:42 [INFO] train episode 247: reward = -118.47, steps = 20 00:39:44 [INFO] train episode 248: reward = -86.65, steps = 18 00:39:46 [INFO] train episode 249: reward = -78.88, steps = 18 00:39:48 [INFO] train episode 250: reward = -87.39, steps = 18 00:39:50 [INFO] train episode 251: reward = -100.81, steps = 23 00:39:51 [INFO] train episode 252: reward = -124.19, steps = 18 00:39:53 [INFO] train episode 253: reward = -92.30, steps = 19 00:39:55 [INFO] train episode 254: reward = -77.23, steps = 19 00:39:57 [INFO] train episode 255: reward = -94.87, steps = 18 00:39:59 [INFO] train episode 256: reward = -108.53, steps = 19 00:40:01 [INFO] train episode 257: reward = -76.45, steps = 22 00:40:03 [INFO] train episode 258: reward = -63.85, steps = 19 00:40:04 [INFO] train episode 259: reward = -76.48, steps = 18 00:40:06 [INFO] train episode 260: reward = -102.44, steps = 20 00:40:08 [INFO] train episode 261: reward = -85.16, steps = 19 00:40:10 [INFO] train episode 262: reward = -84.48, steps = 19 00:40:11 [INFO] train episode 263: reward = -104.55, steps = 19 00:40:14 [INFO] train episode 264: reward = -59.47, steps = 19 00:40:15 [INFO] train episode 265: reward = -89.44, steps = 19 00:40:17 [INFO] train episode 266: reward = -76.63, steps = 19 00:40:19 [INFO] train episode 267: reward = -78.60, steps = 19 00:40:20 [INFO] train episode 268: reward = -73.98, steps = 18 00:40:22 [INFO] train episode 269: reward = -84.28, steps = 19 00:40:24 [INFO] train episode 270: reward = -110.36, steps = 18 00:40:26 [INFO] train episode 271: reward = -132.77, steps = 20 00:40:27 [INFO] train episode 272: reward = -101.51, steps = 19 00:40:29 [INFO] train episode 273: reward = -120.68, steps = 18 00:40:30 [INFO] train episode 274: reward = -80.81, steps = 9 00:40:32 [INFO] train episode 275: reward = -97.92, steps = 18 00:40:34 [INFO] train episode 276: reward = -96.51, steps = 18 00:40:36 [INFO] train episode 277: reward = -67.88, steps = 18 00:40:38 [INFO] train episode 278: reward = -95.72, steps = 21 00:40:40 [INFO] train episode 279: reward = -91.33, steps = 27 00:40:42 [INFO] train episode 280: reward = -136.09, steps = 19 00:40:44 [INFO] train episode 281: reward = -90.87, steps = 18 00:40:47 [INFO] train episode 282: reward = -112.00, steps = 25 00:40:49 [INFO] train episode 283: reward = -123.81, steps = 26 00:40:51 [INFO] train episode 284: reward = -97.62, steps = 20 00:40:53 [INFO] train episode 285: reward = -71.58, steps = 18 00:40:55 [INFO] train episode 286: reward = -94.28, steps = 20 00:40:57 [INFO] train episode 287: reward = -103.29, steps = 20 00:40:59 [INFO] train episode 288: reward = -118.17, steps = 19 00:41:01 [INFO] train episode 289: reward = -84.92, steps = 19 00:41:03 [INFO] train episode 290: reward = -90.36, steps = 19 00:41:05 [INFO] train episode 291: reward = -79.12, steps = 18 00:41:07 [INFO] train episode 292: reward = -106.17, steps = 20 00:41:09 [INFO] train episode 293: reward = -121.85, steps = 25 00:41:12 [INFO] train episode 294: reward = -117.97, steps = 19 00:41:13 [INFO] train episode 295: reward = -88.59, steps = 18 00:41:15 [INFO] train episode 296: reward = -99.74, steps = 16 00:41:17 [INFO] train episode 297: reward = -94.42, steps = 22 00:41:19 [INFO] train episode 298: reward = -87.35, steps = 19 00:41:21 [INFO] train episode 299: reward = -95.05, steps = 19 00:41:23 [INFO] train episode 300: reward = -140.69, steps = 26 00:41:25 [INFO] train episode 301: reward = -110.64, steps = 19 00:41:27 [INFO] train episode 302: reward = -106.55, steps = 18 00:41:29 [INFO] train episode 303: reward = -122.36, steps = 20 00:41:30 [INFO] train episode 304: reward = -110.63, steps = 18 00:41:32 [INFO] train episode 305: reward = -108.02, steps = 19 00:41:34 [INFO] train episode 306: reward = -86.90, steps = 19 00:41:36 [INFO] train episode 307: reward = -79.81, steps = 20 00:41:39 [INFO] train episode 308: reward = -108.20, steps = 19 00:41:41 [INFO] train episode 309: reward = -90.80, steps = 20 00:41:43 [INFO] train episode 310: reward = -86.73, steps = 19 00:41:45 [INFO] train episode 311: reward = -96.42, steps = 21 00:41:47 [INFO] train episode 312: reward = -91.87, steps = 19 00:41:49 [INFO] train episode 313: reward = -100.08, steps = 18 00:41:52 [INFO] train episode 314: reward = -108.18, steps = 20 00:41:55 [INFO] train episode 315: reward = -84.61, steps = 22 00:41:57 [INFO] train episode 316: reward = -105.22, steps = 19 00:42:01 [INFO] train episode 317: reward = -104.53, steps = 23 00:42:03 [INFO] train episode 318: reward = -92.73, steps = 19 00:42:05 [INFO] train episode 319: reward = -106.87, steps = 19 00:42:06 [INFO] train episode 320: reward = -71.37, steps = 18 00:42:08 [INFO] train episode 321: reward = -91.83, steps = 19 00:42:10 [INFO] train episode 322: reward = -97.32, steps = 18 00:42:12 [INFO] train episode 323: reward = -67.96, steps = 19 00:42:14 [INFO] train episode 324: reward = -100.93, steps = 18 00:42:16 [INFO] train episode 325: reward = -86.69, steps = 18 00:42:18 [INFO] train episode 326: reward = -109.65, steps = 20 00:42:20 [INFO] train episode 327: reward = -93.89, steps = 17 00:42:21 [INFO] train episode 328: reward = -65.68, steps = 18 00:42:23 [INFO] train episode 329: reward = -100.42, steps = 19 00:42:25 [INFO] train episode 330: reward = -109.18, steps = 20 00:42:27 [INFO] train episode 331: reward = -90.71, steps = 18 00:42:29 [INFO] train episode 332: reward = -109.66, steps = 20 00:42:31 [INFO] train episode 333: reward = -73.11, steps = 18 00:42:32 [INFO] train episode 334: reward = -93.53, steps = 20 00:42:35 [INFO] train episode 335: reward = -101.52, steps = 19 00:42:37 [INFO] train episode 336: reward = -98.63, steps = 20 00:42:39 [INFO] train episode 337: reward = -88.86, steps = 19 00:42:40 [INFO] train episode 338: reward = -97.79, steps = 17 00:42:42 [INFO] train episode 339: reward = -103.02, steps = 18 00:42:44 [INFO] train episode 340: reward = -129.47, steps = 21 00:42:46 [INFO] train episode 341: reward = -95.22, steps = 20 00:42:48 [INFO] train episode 342: reward = -130.64, steps = 21 00:42:50 [INFO] train episode 343: reward = -93.99, steps = 19 00:42:52 [INFO] train episode 344: reward = -107.38, steps = 20 00:42:54 [INFO] train episode 345: reward = -98.96, steps = 18 00:42:56 [INFO] train episode 346: reward = -65.16, steps = 20 00:42:58 [INFO] train episode 347: reward = -142.52, steps = 24 00:43:01 [INFO] train episode 348: reward = -71.89, steps = 19 00:43:03 [INFO] train episode 349: reward = -134.13, steps = 20 00:43:05 [INFO] train episode 350: reward = -77.76, steps = 18 00:43:07 [INFO] train episode 351: reward = -128.59, steps = 22 00:43:10 [INFO] train episode 352: reward = -117.13, steps = 25 00:43:11 [INFO] train episode 353: reward = -79.91, steps = 19 00:43:13 [INFO] train episode 354: reward = -101.23, steps = 18 00:43:15 [INFO] train episode 355: reward = -85.75, steps = 17 00:43:16 [INFO] train episode 356: reward = -83.04, steps = 19 00:43:18 [INFO] train episode 357: reward = -91.21, steps = 18 00:43:20 [INFO] train episode 358: reward = -96.01, steps = 20 00:43:22 [INFO] train episode 359: reward = -81.18, steps = 18 00:43:24 [INFO] train episode 360: reward = -126.79, steps = 21 00:43:26 [INFO] train episode 361: reward = -105.54, steps = 20 00:43:29 [INFO] train episode 362: reward = -101.96, steps = 25 00:43:31 [INFO] train episode 363: reward = -149.50, steps = 22 00:43:33 [INFO] train episode 364: reward = -95.66, steps = 19 00:43:35 [INFO] train episode 365: reward = -106.05, steps = 20 00:43:37 [INFO] train episode 366: reward = -101.53, steps = 24 00:43:39 [INFO] train episode 367: reward = -64.00, steps = 20 00:43:41 [INFO] train episode 368: reward = -86.49, steps = 20 00:43:42 [INFO] train episode 369: reward = -128.62, steps = 17 00:43:45 [INFO] train episode 370: reward = -69.74, steps = 19 00:43:46 [INFO] train episode 371: reward = -109.44, steps = 18 00:43:48 [INFO] train episode 372: reward = -97.72, steps = 19 00:43:50 [INFO] train episode 373: reward = -86.96, steps = 21 00:43:52 [INFO] train episode 374: reward = -103.92, steps = 19 00:43:54 [INFO] train episode 375: reward = -101.15, steps = 20 00:43:56 [INFO] train episode 376: reward = -95.67, steps = 21 00:43:58 [INFO] train episode 377: reward = -116.81, steps = 20 00:44:01 [INFO] train episode 378: reward = -100.39, steps = 19 00:44:03 [INFO] train episode 379: reward = -94.68, steps = 19 00:44:05 [INFO] train episode 380: reward = -135.96, steps = 19 00:44:07 [INFO] train episode 381: reward = -105.39, steps = 21 00:44:09 [INFO] train episode 382: reward = -84.43, steps = 20 00:44:11 [INFO] train episode 383: reward = -91.42, steps = 19 00:44:12 [INFO] train episode 384: reward = -132.57, steps = 18 00:44:14 [INFO] train episode 385: reward = -117.30, steps = 18 00:44:16 [INFO] train episode 386: reward = -105.77, steps = 17 00:44:18 [INFO] train episode 387: reward = -99.65, steps = 19 00:44:20 [INFO] train episode 388: reward = -138.23, steps = 18 00:44:22 [INFO] train episode 389: reward = -101.96, steps = 20 00:44:24 [INFO] train episode 390: reward = -88.12, steps = 20 00:44:26 [INFO] train episode 391: reward = -104.15, steps = 22 00:44:29 [INFO] train episode 392: reward = -111.68, steps = 19 00:44:31 [INFO] train episode 393: reward = -118.23, steps = 20 00:44:32 [INFO] train episode 394: reward = -92.78, steps = 17 00:44:34 [INFO] train episode 395: reward = -110.35, steps = 19 00:44:36 [INFO] train episode 396: reward = -109.91, steps = 19 00:44:39 [INFO] train episode 397: reward = -126.39, steps = 19 00:44:41 [INFO] train episode 398: reward = -86.95, steps = 19 00:44:43 [INFO] train episode 399: reward = -103.75, steps = 18 00:44:44 [INFO] train episode 400: reward = -92.04, steps = 19 00:44:46 [INFO] train episode 401: reward = -80.60, steps = 18 00:44:48 [INFO] train episode 402: reward = -95.14, steps = 21 00:44:50 [INFO] train episode 403: reward = -119.91, steps = 19 00:44:52 [INFO] train episode 404: reward = -95.65, steps = 19 00:44:54 [INFO] train episode 405: reward = -79.73, steps = 17 00:44:56 [INFO] train episode 406: reward = -98.86, steps = 20 00:44:58 [INFO] train episode 407: reward = -114.78, steps = 22 00:45:01 [INFO] train episode 408: reward = -116.12, steps = 25 00:45:03 [INFO] train episode 409: reward = -83.53, steps = 19 00:45:05 [INFO] train episode 410: reward = -71.20, steps = 19 00:45:06 [INFO] train episode 411: reward = -104.69, steps = 19 00:45:09 [INFO] train episode 412: reward = -107.98, steps = 20 00:45:11 [INFO] train episode 413: reward = -106.61, steps = 20 00:45:13 [INFO] train episode 414: reward = -73.20, steps = 18 00:45:15 [INFO] train episode 415: reward = -119.95, steps = 17 00:45:17 [INFO] train episode 416: reward = -88.45, steps = 26 00:45:19 [INFO] train episode 417: reward = -105.88, steps = 19 00:45:21 [INFO] train episode 418: reward = -130.00, steps = 19 00:45:23 [INFO] train episode 419: reward = -76.54, steps = 19 00:45:25 [INFO] train episode 420: reward = -140.43, steps = 21 00:45:27 [INFO] train episode 421: reward = -83.66, steps = 19 00:45:29 [INFO] train episode 422: reward = -91.48, steps = 20 00:45:31 [INFO] train episode 423: reward = -79.81, steps = 19 00:45:33 [INFO] train episode 424: reward = -103.17, steps = 20 00:45:35 [INFO] train episode 425: reward = -91.10, steps = 19 00:45:37 [INFO] train episode 426: reward = -73.64, steps = 20 00:45:39 [INFO] train episode 427: reward = -102.75, steps = 19 00:45:41 [INFO] train episode 428: reward = -129.37, steps = 17 00:45:43 [INFO] train episode 429: reward = -83.47, steps = 19 00:45:44 [INFO] train episode 430: reward = -112.69, steps = 20 00:45:46 [INFO] train episode 431: reward = -105.28, steps = 18 00:45:49 [INFO] train episode 432: reward = -81.35, steps = 22 00:45:51 [INFO] train episode 433: reward = -73.60, steps = 19 00:45:53 [INFO] train episode 434: reward = -94.23, steps = 21 00:45:55 [INFO] train episode 435: reward = -102.83, steps = 18 00:45:57 [INFO] train episode 436: reward = -85.78, steps = 17 00:45:58 [INFO] train episode 437: reward = -72.47, steps = 18 00:46:00 [INFO] train episode 438: reward = -91.14, steps = 19 00:46:03 [INFO] train episode 439: reward = -97.39, steps = 25 00:46:05 [INFO] train episode 440: reward = -81.63, steps = 21 00:46:07 [INFO] train episode 441: reward = -100.13, steps = 18 00:46:09 [INFO] train episode 442: reward = -107.77, steps = 20 00:46:11 [INFO] train episode 443: reward = -80.98, steps = 19 00:46:13 [INFO] train episode 444: reward = -92.40, steps = 19 00:46:15 [INFO] train episode 445: reward = -108.58, steps = 19 00:46:17 [INFO] train episode 446: reward = -124.32, steps = 20 00:46:19 [INFO] train episode 447: reward = -118.50, steps = 26 00:46:21 [INFO] train episode 448: reward = -73.04, steps = 20 00:46:23 [INFO] train episode 449: reward = -100.43, steps = 18 00:46:25 [INFO] train episode 450: reward = -108.23, steps = 19 00:46:28 [INFO] train episode 451: reward = -112.54, steps = 19 00:46:30 [INFO] train episode 452: reward = -105.67, steps = 19 00:46:32 [INFO] train episode 453: reward = -106.87, steps = 19 00:46:34 [INFO] train episode 454: reward = -65.47, steps = 20 00:46:36 [INFO] train episode 455: reward = -121.13, steps = 20 00:46:38 [INFO] train episode 456: reward = -114.83, steps = 23 00:46:40 [INFO] train episode 457: reward = -97.34, steps = 21 00:46:43 [INFO] train episode 458: reward = -99.25, steps = 19 00:46:44 [INFO] train episode 459: reward = -68.33, steps = 19 00:46:46 [INFO] train episode 460: reward = -91.92, steps = 17 00:46:48 [INFO] train episode 461: reward = -105.61, steps = 21 00:46:50 [INFO] train episode 462: reward = -103.23, steps = 17 00:46:52 [INFO] train episode 463: reward = -82.16, steps = 19 00:46:54 [INFO] train episode 464: reward = -66.14, steps = 19 00:46:55 [INFO] train episode 465: reward = -123.28, steps = 18 00:46:57 [INFO] train episode 466: reward = -109.06, steps = 19 00:46:59 [INFO] train episode 467: reward = -83.73, steps = 20 00:47:02 [INFO] train episode 468: reward = -101.78, steps = 20 00:47:04 [INFO] train episode 469: reward = -116.62, steps = 21 00:47:05 [INFO] train episode 470: reward = -61.98, steps = 19 00:47:07 [INFO] train episode 471: reward = -99.45, steps = 19 00:47:09 [INFO] train episode 472: reward = -70.89, steps = 18 00:47:11 [INFO] train episode 473: reward = -117.98, steps = 20 00:47:13 [INFO] train episode 474: reward = -138.59, steps = 26 00:47:15 [INFO] train episode 475: reward = -121.15, steps = 18 00:47:17 [INFO] train episode 476: reward = -64.98, steps = 18 00:47:19 [INFO] train episode 477: reward = -93.97, steps = 19 00:47:20 [INFO] train episode 478: reward = -70.88, steps = 15 00:47:22 [INFO] train episode 479: reward = -76.73, steps = 18 00:47:23 [INFO] train episode 480: reward = -76.73, steps = 19 00:47:25 [INFO] train episode 481: reward = -96.08, steps = 19 00:47:27 [INFO] train episode 482: reward = -73.62, steps = 19 00:47:29 [INFO] train episode 483: reward = -87.55, steps = 21 00:47:31 [INFO] train episode 484: reward = -80.02, steps = 22 00:47:33 [INFO] train episode 485: reward = -84.97, steps = 18 00:47:35 [INFO] train episode 486: reward = -82.77, steps = 18 00:47:36 [INFO] train episode 487: reward = -83.67, steps = 18 00:47:38 [INFO] train episode 488: reward = -79.57, steps = 18 00:47:40 [INFO] train episode 489: reward = -88.22, steps = 20 00:47:43 [INFO] train episode 490: reward = -95.54, steps = 23 00:47:44 [INFO] train episode 491: reward = -89.21, steps = 17 00:47:46 [INFO] train episode 492: reward = -115.84, steps = 18 00:47:48 [INFO] train episode 493: reward = -82.99, steps = 18 00:47:50 [INFO] train episode 494: reward = -124.90, steps = 21 00:47:52 [INFO] train episode 495: reward = -76.15, steps = 17 00:47:53 [INFO] train episode 496: reward = -123.87, steps = 19 00:47:55 [INFO] train episode 497: reward = -83.06, steps = 19 00:47:57 [INFO] train episode 498: reward = -132.89, steps = 20 00:47:59 [INFO] train episode 499: reward = -92.44, steps = 20 00:48:00 [INFO] train episode 500: reward = -94.73, steps = 18 00:48:02 [INFO] train episode 501: reward = -111.25, steps = 18 00:48:04 [INFO] train episode 502: reward = -116.28, steps = 18 00:48:07 [INFO] train episode 503: reward = -74.91, steps = 26 00:48:08 [INFO] train episode 504: reward = -94.12, steps = 19 00:48:11 [INFO] train episode 505: reward = -132.44, steps = 24 00:48:12 [INFO] train episode 506: reward = -106.87, steps = 20 00:48:14 [INFO] train episode 507: reward = -103.08, steps = 20 00:48:16 [INFO] train episode 508: reward = -90.31, steps = 18 00:48:18 [INFO] train episode 509: reward = -69.72, steps = 18 00:48:19 [INFO] train episode 510: reward = -92.43, steps = 18 00:48:21 [INFO] train episode 511: reward = -79.05, steps = 20 00:48:23 [INFO] train episode 512: reward = -83.63, steps = 22 00:48:25 [INFO] train episode 513: reward = -110.30, steps = 19 00:48:27 [INFO] train episode 514: reward = -114.04, steps = 19 00:48:28 [INFO] train episode 515: reward = -90.89, steps = 18 00:48:30 [INFO] train episode 516: reward = -92.16, steps = 19 00:48:33 [INFO] train episode 517: reward = -89.69, steps = 21 00:48:34 [INFO] train episode 518: reward = -88.30, steps = 17 00:48:36 [INFO] train episode 519: reward = -95.76, steps = 18 00:48:38 [INFO] train episode 520: reward = -91.03, steps = 20 00:48:41 [INFO] train episode 521: reward = -129.82, steps = 20 00:48:42 [INFO] train episode 522: reward = -103.70, steps = 18 00:48:44 [INFO] train episode 523: reward = -119.84, steps = 18 00:48:46 [INFO] train episode 524: reward = -116.21, steps = 24 00:48:48 [INFO] train episode 525: reward = -118.83, steps = 19 00:48:50 [INFO] train episode 526: reward = -84.99, steps = 19 00:48:53 [INFO] train episode 527: reward = -126.12, steps = 28 00:48:55 [INFO] train episode 528: reward = -93.72, steps = 19 00:48:57 [INFO] train episode 529: reward = -63.80, steps = 21 00:48:59 [INFO] train episode 530: reward = -98.75, steps = 18 00:49:01 [INFO] train episode 531: reward = -90.74, steps = 20 00:49:03 [INFO] train episode 532: reward = -105.24, steps = 19 00:49:05 [INFO] train episode 533: reward = -133.58, steps = 27 00:49:07 [INFO] train episode 534: reward = -64.94, steps = 19 00:49:09 [INFO] train episode 535: reward = -92.04, steps = 19 00:49:11 [INFO] train episode 536: reward = -74.89, steps = 20 00:49:13 [INFO] train episode 537: reward = -90.47, steps = 19 00:49:15 [INFO] train episode 538: reward = -113.60, steps = 22 00:49:17 [INFO] train episode 539: reward = -81.14, steps = 20 00:49:19 [INFO] train episode 540: reward = -64.94, steps = 19 00:49:21 [INFO] train episode 541: reward = -86.59, steps = 18 00:49:22 [INFO] train episode 542: reward = -97.80, steps = 18 00:49:24 [INFO] train episode 543: reward = -125.15, steps = 19 00:49:26 [INFO] train episode 544: reward = -112.35, steps = 20 00:49:28 [INFO] train episode 545: reward = -97.20, steps = 18 00:49:30 [INFO] train episode 546: reward = -118.25, steps = 19 00:49:32 [INFO] train episode 547: reward = -129.38, steps = 20 00:49:34 [INFO] train episode 548: reward = -109.10, steps = 19 00:49:36 [INFO] train episode 549: reward = -80.53, steps = 18 00:49:37 [INFO] train episode 550: reward = -111.66, steps = 19 00:49:39 [INFO] train episode 551: reward = -80.75, steps = 20 00:49:41 [INFO] train episode 552: reward = -79.01, steps = 19 00:49:43 [INFO] train episode 553: reward = -86.01, steps = 17 00:49:44 [INFO] train episode 554: reward = -75.17, steps = 19 00:49:47 [INFO] train episode 555: reward = -139.77, steps = 31 00:49:49 [INFO] train episode 556: reward = -130.75, steps = 18 00:49:51 [INFO] train episode 557: reward = -117.39, steps = 20 00:49:53 [INFO] train episode 558: reward = -95.02, steps = 18 00:49:56 [INFO] train episode 559: reward = -103.24, steps = 28 00:49:58 [INFO] train episode 560: reward = -102.58, steps = 20 00:50:00 [INFO] train episode 561: reward = -108.46, steps = 19 00:50:02 [INFO] train episode 562: reward = -80.23, steps = 19 00:50:03 [INFO] train episode 563: reward = -66.72, steps = 19 00:50:06 [INFO] train episode 564: reward = -92.52, steps = 20 00:50:07 [INFO] train episode 565: reward = -108.34, steps = 19 00:50:10 [INFO] train episode 566: reward = -120.47, steps = 27 00:50:12 [INFO] train episode 567: reward = -126.50, steps = 19 00:50:14 [INFO] train episode 568: reward = -93.93, steps = 23 00:50:16 [INFO] train episode 569: reward = -93.23, steps = 20 00:50:18 [INFO] train episode 570: reward = -102.76, steps = 20 00:50:20 [INFO] train episode 571: reward = -106.37, steps = 20 00:50:22 [INFO] train episode 572: reward = -105.15, steps = 18 00:50:24 [INFO] train episode 573: reward = -93.81, steps = 19 00:50:26 [INFO] train episode 574: reward = -69.66, steps = 19 00:50:28 [INFO] train episode 575: reward = -101.49, steps = 24 00:50:30 [INFO] train episode 576: reward = -85.88, steps = 18 00:50:32 [INFO] train episode 577: reward = -123.66, steps = 20 00:50:34 [INFO] train episode 578: reward = -108.91, steps = 18 00:50:36 [INFO] train episode 579: reward = -106.03, steps = 19 00:50:37 [INFO] train episode 580: reward = -94.42, steps = 18 00:50:39 [INFO] train episode 581: reward = -92.80, steps = 21 00:50:41 [INFO] train episode 582: reward = -84.99, steps = 19 00:50:43 [INFO] train episode 583: reward = -100.74, steps = 18 00:50:45 [INFO] train episode 584: reward = -79.11, steps = 18 00:50:47 [INFO] train episode 585: reward = -121.94, steps = 21 00:50:48 [INFO] train episode 586: reward = -77.95, steps = 17 00:50:51 [INFO] train episode 587: reward = -81.61, steps = 18 00:50:52 [INFO] train episode 588: reward = -102.41, steps = 19 00:50:54 [INFO] train episode 589: reward = -117.78, steps = 19 00:50:56 [INFO] train episode 590: reward = -94.06, steps = 20 00:50:58 [INFO] train episode 591: reward = -64.52, steps = 18 00:51:00 [INFO] train episode 592: reward = -128.46, steps = 20 00:51:02 [INFO] train episode 593: reward = -136.34, steps = 19 00:51:04 [INFO] train episode 594: reward = -95.80, steps = 29 00:51:06 [INFO] train episode 595: reward = -107.67, steps = 21 00:51:08 [INFO] train episode 596: reward = -98.24, steps = 22 00:51:10 [INFO] train episode 597: reward = -122.79, steps = 19 00:51:12 [INFO] train episode 598: reward = -91.41, steps = 20 00:51:14 [INFO] train episode 599: reward = -102.83, steps = 19 00:51:16 [INFO] train episode 600: reward = -69.15, steps = 20 00:51:18 [INFO] train episode 601: reward = -115.15, steps = 20 00:51:20 [INFO] train episode 602: reward = -85.59, steps = 20 00:51:22 [INFO] train episode 603: reward = -96.55, steps = 24 00:51:24 [INFO] train episode 604: reward = -99.16, steps = 21 00:51:25 [INFO] train episode 605: reward = -92.77, steps = 19 00:51:27 [INFO] train episode 606: reward = -99.01, steps = 18 00:51:29 [INFO] train episode 607: reward = -80.98, steps = 18 00:51:31 [INFO] train episode 608: reward = -97.03, steps = 18 00:51:33 [INFO] train episode 609: reward = -114.21, steps = 30 00:51:35 [INFO] train episode 610: reward = -80.70, steps = 19 00:51:37 [INFO] train episode 611: reward = -110.43, steps = 19 00:51:39 [INFO] train episode 612: reward = -106.40, steps = 21 00:51:42 [INFO] train episode 613: reward = -115.89, steps = 31 00:51:44 [INFO] train episode 614: reward = -115.87, steps = 20 00:51:46 [INFO] train episode 615: reward = -123.99, steps = 20 00:51:48 [INFO] train episode 616: reward = -110.58, steps = 23 00:51:50 [INFO] train episode 617: reward = -114.53, steps = 18 00:51:52 [INFO] train episode 618: reward = -150.17, steps = 26 00:51:54 [INFO] train episode 619: reward = -98.10, steps = 18 00:51:55 [INFO] train episode 620: reward = -93.49, steps = 16 00:51:57 [INFO] train episode 621: reward = -90.39, steps = 20 00:51:59 [INFO] train episode 622: reward = -98.15, steps = 20 00:52:01 [INFO] train episode 623: reward = -76.69, steps = 20 00:52:03 [INFO] train episode 624: reward = -79.81, steps = 19 00:52:05 [INFO] train episode 625: reward = -82.52, steps = 24 00:52:06 [INFO] train episode 626: reward = -78.91, steps = 13 00:52:08 [INFO] train episode 627: reward = -108.80, steps = 21 00:52:10 [INFO] train episode 628: reward = -60.51, steps = 21 00:52:12 [INFO] train episode 629: reward = -107.41, steps = 18 00:52:14 [INFO] train episode 630: reward = -120.65, steps = 22 00:52:15 [INFO] train episode 631: reward = -118.73, steps = 18 00:52:17 [INFO] train episode 632: reward = -85.15, steps = 19 00:52:19 [INFO] train episode 633: reward = -99.34, steps = 19 00:52:21 [INFO] train episode 634: reward = -89.53, steps = 22 00:52:23 [INFO] train episode 635: reward = -89.00, steps = 19 00:52:25 [INFO] train episode 636: reward = -103.65, steps = 19 00:52:27 [INFO] train episode 637: reward = -104.04, steps = 20 00:52:28 [INFO] train episode 638: reward = -86.72, steps = 19 00:52:30 [INFO] train episode 639: reward = -113.60, steps = 18 00:52:32 [INFO] train episode 640: reward = -92.39, steps = 20 00:52:33 [INFO] train episode 641: reward = -119.47, steps = 18 00:52:36 [INFO] train episode 642: reward = -78.80, steps = 20 00:52:37 [INFO] train episode 643: reward = -85.77, steps = 19 00:52:39 [INFO] train episode 644: reward = -113.80, steps = 19 00:52:41 [INFO] train episode 645: reward = -116.58, steps = 20 00:52:42 [INFO] train episode 646: reward = -94.46, steps = 18 00:52:44 [INFO] train episode 647: reward = -81.92, steps = 17 00:52:46 [INFO] train episode 648: reward = -98.59, steps = 19 00:52:47 [INFO] train episode 649: reward = -92.10, steps = 19 00:52:49 [INFO] train episode 650: reward = -83.66, steps = 20 00:52:51 [INFO] train episode 651: reward = -80.86, steps = 20 00:52:53 [INFO] train episode 652: reward = -86.66, steps = 20 00:52:55 [INFO] train episode 653: reward = -89.90, steps = 21 00:52:57 [INFO] train episode 654: reward = -86.53, steps = 19 00:52:59 [INFO] train episode 655: reward = -113.07, steps = 20 00:53:01 [INFO] train episode 656: reward = -126.94, steps = 21 00:53:02 [INFO] train episode 657: reward = -87.93, steps = 19 00:53:04 [INFO] train episode 658: reward = -110.25, steps = 19 00:53:07 [INFO] train episode 659: reward = -84.63, steps = 23 00:53:08 [INFO] train episode 660: reward = -91.48, steps = 19 00:53:10 [INFO] train episode 661: reward = -92.59, steps = 23 00:53:12 [INFO] train episode 662: reward = -90.90, steps = 19 00:53:14 [INFO] train episode 663: reward = -72.26, steps = 16 00:53:15 [INFO] train episode 664: reward = -67.95, steps = 20 00:53:17 [INFO] train episode 665: reward = -113.88, steps = 19 00:53:19 [INFO] train episode 666: reward = -84.46, steps = 20 00:53:21 [INFO] train episode 667: reward = -93.55, steps = 20 00:53:23 [INFO] train episode 668: reward = -86.10, steps = 20 00:53:25 [INFO] train episode 669: reward = -129.88, steps = 20 00:53:27 [INFO] train episode 670: reward = -66.13, steps = 20 00:53:28 [INFO] train episode 671: reward = -111.62, steps = 19 00:53:30 [INFO] train episode 672: reward = -75.97, steps = 19 00:53:32 [INFO] train episode 673: reward = -119.86, steps = 19 00:53:34 [INFO] train episode 674: reward = -84.32, steps = 21 00:53:36 [INFO] train episode 675: reward = -94.24, steps = 18 00:53:37 [INFO] train episode 676: reward = -102.27, steps = 20 00:53:39 [INFO] train episode 677: reward = -89.72, steps = 20 00:53:41 [INFO] train episode 678: reward = -102.62, steps = 19 00:53:43 [INFO] train episode 679: reward = -63.47, steps = 18 00:53:45 [INFO] train episode 680: reward = -63.95, steps = 17 00:53:47 [INFO] train episode 681: reward = -94.78, steps = 20 00:53:48 [INFO] train episode 682: reward = -87.21, steps = 19 00:53:51 [INFO] train episode 683: reward = -100.68, steps = 18 00:53:53 [INFO] train episode 684: reward = -99.17, steps = 21 00:53:56 [INFO] train episode 685: reward = -134.73, steps = 33 00:53:58 [INFO] train episode 686: reward = -106.76, steps = 19 00:54:00 [INFO] train episode 687: reward = -138.78, steps = 20 00:54:01 [INFO] train episode 688: reward = -97.82, steps = 19 00:54:03 [INFO] train episode 689: reward = -80.37, steps = 19 00:54:05 [INFO] train episode 690: reward = -69.83, steps = 19 00:54:07 [INFO] train episode 691: reward = -101.24, steps = 19 00:54:09 [INFO] train episode 692: reward = -108.33, steps = 22 00:54:11 [INFO] train episode 693: reward = -102.71, steps = 20 00:54:13 [INFO] train episode 694: reward = -101.07, steps = 20 00:54:15 [INFO] train episode 695: reward = -136.32, steps = 17 00:54:17 [INFO] train episode 696: reward = -89.38, steps = 19 00:54:18 [INFO] train episode 697: reward = -81.81, steps = 18 00:54:20 [INFO] train episode 698: reward = -84.04, steps = 19 00:54:22 [INFO] train episode 699: reward = -105.73, steps = 22 00:54:24 [INFO] train episode 700: reward = -80.51, steps = 18 00:54:26 [INFO] train episode 701: reward = -92.91, steps = 18 00:54:28 [INFO] train episode 702: reward = -102.45, steps = 18 00:54:30 [INFO] train episode 703: reward = -107.68, steps = 19 00:54:32 [INFO] train episode 704: reward = -103.46, steps = 21 00:54:34 [INFO] train episode 705: reward = -146.29, steps = 19 00:54:35 [INFO] train episode 706: reward = -92.31, steps = 18 00:54:38 [INFO] train episode 707: reward = -112.93, steps = 28 00:54:40 [INFO] train episode 708: reward = -114.54, steps = 19 00:54:42 [INFO] train episode 709: reward = -91.94, steps = 18 00:54:43 [INFO] train episode 710: reward = -98.78, steps = 19 00:54:45 [INFO] train episode 711: reward = -118.29, steps = 24 00:54:48 [INFO] train episode 712: reward = -83.68, steps = 19 00:54:50 [INFO] train episode 713: reward = -103.26, steps = 27 00:54:52 [INFO] train episode 714: reward = -84.54, steps = 20 00:54:54 [INFO] train episode 715: reward = -103.64, steps = 20 00:54:57 [INFO] train episode 716: reward = -129.13, steps = 24 00:54:59 [INFO] train episode 717: reward = -91.13, steps = 19 00:55:01 [INFO] train episode 718: reward = -159.08, steps = 26 00:55:03 [INFO] train episode 719: reward = -82.83, steps = 20 00:55:06 [INFO] train episode 720: reward = -89.91, steps = 20 00:55:07 [INFO] train episode 721: reward = -112.05, steps = 21 00:55:09 [INFO] train episode 722: reward = -154.05, steps = 19 00:55:11 [INFO] train episode 723: reward = -143.78, steps = 18 00:55:13 [INFO] train episode 724: reward = -138.08, steps = 20 00:55:15 [INFO] train episode 725: reward = -113.43, steps = 22 00:55:16 [INFO] train episode 726: reward = -109.50, steps = 18 00:55:18 [INFO] train episode 727: reward = -143.78, steps = 22 00:55:21 [INFO] train episode 728: reward = -109.27, steps = 27 00:55:23 [INFO] train episode 729: reward = -95.82, steps = 19 00:55:24 [INFO] train episode 730: reward = -101.05, steps = 20 00:55:26 [INFO] train episode 731: reward = -105.69, steps = 22 00:55:28 [INFO] train episode 732: reward = -114.93, steps = 17 00:55:30 [INFO] train episode 733: reward = -89.68, steps = 20 00:55:32 [INFO] train episode 734: reward = -140.65, steps = 25 00:55:34 [INFO] train episode 735: reward = -84.47, steps = 20 00:55:36 [INFO] train episode 736: reward = -112.34, steps = 19 00:55:38 [INFO] train episode 737: reward = -93.08, steps = 18 00:55:39 [INFO] train episode 738: reward = -75.25, steps = 16 00:55:41 [INFO] train episode 739: reward = -98.88, steps = 20 00:55:43 [INFO] train episode 740: reward = -137.31, steps = 21 00:55:45 [INFO] train episode 741: reward = -97.52, steps = 20 00:55:46 [INFO] train episode 742: reward = -75.32, steps = 19 00:55:49 [INFO] train episode 743: reward = -161.82, steps = 27 00:55:51 [INFO] train episode 744: reward = -156.18, steps = 26 00:55:53 [INFO] train episode 745: reward = -102.34, steps = 18 00:55:55 [INFO] train episode 746: reward = -81.29, steps = 20 00:55:57 [INFO] train episode 747: reward = -109.77, steps = 19 00:55:59 [INFO] train episode 748: reward = -104.36, steps = 19 00:56:01 [INFO] train episode 749: reward = -144.63, steps = 23 00:56:02 [INFO] train episode 750: reward = -86.64, steps = 19 00:56:04 [INFO] train episode 751: reward = -89.35, steps = 22 00:56:06 [INFO] train episode 752: reward = -99.04, steps = 19 00:56:08 [INFO] train episode 753: reward = -107.26, steps = 20 00:56:10 [INFO] train episode 754: reward = -88.70, steps = 19 00:56:12 [INFO] train episode 755: reward = -85.15, steps = 19 00:56:13 [INFO] train episode 756: reward = -76.68, steps = 18 00:56:15 [INFO] train episode 757: reward = -101.19, steps = 17 00:56:17 [INFO] train episode 758: reward = -140.02, steps = 21 00:56:19 [INFO] train episode 759: reward = -137.90, steps = 30 00:56:21 [INFO] train episode 760: reward = -75.23, steps = 19 00:56:23 [INFO] train episode 761: reward = -85.72, steps = 17 00:56:25 [INFO] train episode 762: reward = -108.09, steps = 18 00:56:26 [INFO] train episode 763: reward = -108.05, steps = 16 00:56:28 [INFO] train episode 764: reward = -101.15, steps = 19 00:56:30 [INFO] train episode 765: reward = -91.36, steps = 20 00:56:32 [INFO] train episode 766: reward = -98.23, steps = 20 00:56:33 [INFO] train episode 767: reward = -81.31, steps = 19 00:56:35 [INFO] train episode 768: reward = -103.25, steps = 20 00:56:37 [INFO] train episode 769: reward = -89.16, steps = 19 00:56:39 [INFO] train episode 770: reward = -70.03, steps = 19 00:56:42 [INFO] train episode 771: reward = -105.26, steps = 25 00:56:44 [INFO] train episode 772: reward = -91.91, steps = 20 00:56:47 [INFO] train episode 773: reward = -106.31, steps = 28 00:56:49 [INFO] train episode 774: reward = -91.35, steps = 22 00:56:50 [INFO] train episode 775: reward = -95.98, steps = 19 00:56:52 [INFO] train episode 776: reward = -92.67, steps = 19 00:56:56 [INFO] train episode 777: reward = -179.42, steps = 25 00:56:58 [INFO] train episode 778: reward = -107.50, steps = 20 00:57:00 [INFO] train episode 779: reward = -83.43, steps = 18 00:57:02 [INFO] train episode 780: reward = -74.49, steps = 19 00:57:04 [INFO] train episode 781: reward = -131.53, steps = 21 00:57:06 [INFO] train episode 782: reward = -77.39, steps = 19 00:57:08 [INFO] train episode 783: reward = -101.75, steps = 18 00:57:10 [INFO] train episode 784: reward = -91.25, steps = 19 00:57:12 [INFO] train episode 785: reward = -91.23, steps = 23 00:57:15 [INFO] train episode 786: reward = -147.40, steps = 31 00:57:18 [INFO] train episode 787: reward = -107.03, steps = 20 00:57:20 [INFO] train episode 788: reward = -103.58, steps = 21 00:57:22 [INFO] train episode 789: reward = -86.95, steps = 19 00:57:24 [INFO] train episode 790: reward = -88.50, steps = 19 00:57:26 [INFO] train episode 791: reward = -67.52, steps = 20 00:57:28 [INFO] train episode 792: reward = -118.94, steps = 20 00:57:30 [INFO] train episode 793: reward = -90.05, steps = 17 00:57:32 [INFO] train episode 794: reward = -113.36, steps = 19 00:57:34 [INFO] train episode 795: reward = -112.26, steps = 20 00:57:36 [INFO] train episode 796: reward = -88.03, steps = 20 00:57:39 [INFO] train episode 797: reward = -95.14, steps = 19 00:57:41 [INFO] train episode 798: reward = -94.78, steps = 18 00:57:43 [INFO] train episode 799: reward = -44.21, steps = 17 00:57:45 [INFO] train episode 800: reward = -125.31, steps = 21 00:57:47 [INFO] train episode 801: reward = -91.24, steps = 18 00:57:50 [INFO] train episode 802: reward = -76.89, steps = 23 00:57:53 [INFO] train episode 803: reward = -88.29, steps = 19 00:57:55 [INFO] train episode 804: reward = -103.18, steps = 19 00:57:57 [INFO] train episode 805: reward = -121.25, steps = 19 00:57:59 [INFO] train episode 806: reward = -111.32, steps = 19 00:58:01 [INFO] train episode 807: reward = -87.28, steps = 18 00:58:03 [INFO] train episode 808: reward = -102.42, steps = 19 00:58:04 [INFO] train episode 809: reward = -92.67, steps = 19 00:58:06 [INFO] train episode 810: reward = -84.85, steps = 19 00:58:08 [INFO] train episode 811: reward = -100.24, steps = 22 00:58:10 [INFO] train episode 812: reward = -107.98, steps = 18 00:58:13 [INFO] train episode 813: reward = -110.56, steps = 23 00:58:16 [INFO] train episode 814: reward = -89.66, steps = 24 00:58:18 [INFO] train episode 815: reward = -96.76, steps = 19 00:58:20 [INFO] train episode 816: reward = -129.60, steps = 21 00:58:22 [INFO] train episode 817: reward = -100.41, steps = 21 00:58:24 [INFO] train episode 818: reward = -112.25, steps = 23 00:58:26 [INFO] train episode 819: reward = -91.00, steps = 18 00:58:29 [INFO] train episode 820: reward = -114.39, steps = 20 00:58:31 [INFO] train episode 821: reward = -97.03, steps = 19 00:58:34 [INFO] train episode 822: reward = -77.51, steps = 20 00:58:36 [INFO] train episode 823: reward = -86.52, steps = 19 00:58:38 [INFO] train episode 824: reward = -79.13, steps = 17 00:58:42 [INFO] train episode 825: reward = -119.30, steps = 23 00:58:44 [INFO] train episode 826: reward = -101.48, steps = 19 00:58:47 [INFO] train episode 827: reward = -117.10, steps = 33 00:58:51 [INFO] train episode 828: reward = -135.82, steps = 28 00:58:52 [INFO] train episode 829: reward = -112.56, steps = 18 00:58:55 [INFO] train episode 830: reward = -61.87, steps = 19 00:58:56 [INFO] train episode 831: reward = -90.77, steps = 19 00:58:58 [INFO] train episode 832: reward = -98.95, steps = 20 00:59:00 [INFO] train episode 833: reward = -125.53, steps = 17 00:59:02 [INFO] train episode 834: reward = -121.46, steps = 20 00:59:04 [INFO] train episode 835: reward = -127.00, steps = 18 00:59:06 [INFO] train episode 836: reward = -98.54, steps = 20 00:59:08 [INFO] train episode 837: reward = -121.53, steps = 20 00:59:09 [INFO] train episode 838: reward = -89.38, steps = 18 00:59:11 [INFO] train episode 839: reward = -107.42, steps = 18 00:59:14 [INFO] train episode 840: reward = -135.42, steps = 31 00:59:16 [INFO] train episode 841: reward = -129.74, steps = 19 00:59:18 [INFO] train episode 842: reward = -109.90, steps = 18 00:59:20 [INFO] train episode 843: reward = -93.48, steps = 21 00:59:21 [INFO] train episode 844: reward = -107.74, steps = 19 00:59:23 [INFO] train episode 845: reward = -88.03, steps = 16 00:59:25 [INFO] train episode 846: reward = -106.97, steps = 20 00:59:27 [INFO] train episode 847: reward = -113.01, steps = 19 00:59:29 [INFO] train episode 848: reward = -123.66, steps = 19 00:59:30 [INFO] train episode 849: reward = -152.85, steps = 19 00:59:32 [INFO] train episode 850: reward = -110.79, steps = 20 00:59:34 [INFO] train episode 851: reward = -83.72, steps = 18 00:59:36 [INFO] train episode 852: reward = -103.81, steps = 20 00:59:37 [INFO] train episode 853: reward = -73.54, steps = 18 00:59:39 [INFO] train episode 854: reward = -102.09, steps = 20 00:59:41 [INFO] train episode 855: reward = -97.31, steps = 20 00:59:43 [INFO] train episode 856: reward = -97.69, steps = 19 00:59:45 [INFO] train episode 857: reward = -105.15, steps = 19 00:59:47 [INFO] train episode 858: reward = -111.22, steps = 19 00:59:49 [INFO] train episode 859: reward = -119.47, steps = 30 00:59:52 [INFO] train episode 860: reward = -136.60, steps = 31 00:59:54 [INFO] train episode 861: reward = -117.20, steps = 21 00:59:56 [INFO] train episode 862: reward = -104.66, steps = 20 00:59:58 [INFO] train episode 863: reward = -113.11, steps = 22 01:00:01 [INFO] train episode 864: reward = -81.83, steps = 19 01:00:03 [INFO] train episode 865: reward = -115.39, steps = 19 01:00:05 [INFO] train episode 866: reward = -116.64, steps = 27 01:00:07 [INFO] train episode 867: reward = -97.36, steps = 18 01:00:09 [INFO] train episode 868: reward = -84.38, steps = 20 01:00:11 [INFO] train episode 869: reward = -87.65, steps = 19 01:00:13 [INFO] train episode 870: reward = -126.36, steps = 22 01:00:15 [INFO] train episode 871: reward = -89.28, steps = 18 01:00:18 [INFO] train episode 872: reward = -105.59, steps = 18 01:00:20 [INFO] train episode 873: reward = -89.61, steps = 19 01:00:22 [INFO] train episode 874: reward = -110.07, steps = 18 01:00:24 [INFO] train episode 875: reward = -97.43, steps = 19 01:00:25 [INFO] train episode 876: reward = -104.12, steps = 18 01:00:27 [INFO] train episode 877: reward = -108.03, steps = 21 01:00:29 [INFO] train episode 878: reward = -106.92, steps = 20 01:00:32 [INFO] train episode 879: reward = -108.70, steps = 20 01:00:33 [INFO] train episode 880: reward = -82.39, steps = 19 01:00:35 [INFO] train episode 881: reward = -86.02, steps = 18 01:00:38 [INFO] train episode 882: reward = -107.62, steps = 19 01:00:40 [INFO] train episode 883: reward = -94.45, steps = 17 01:00:41 [INFO] train episode 884: reward = -112.25, steps = 19 01:00:43 [INFO] train episode 885: reward = -91.22, steps = 20 01:00:46 [INFO] train episode 886: reward = -106.31, steps = 20 01:00:47 [INFO] train episode 887: reward = -69.83, steps = 17 01:00:49 [INFO] train episode 888: reward = -106.14, steps = 20 01:00:51 [INFO] train episode 889: reward = -86.82, steps = 20 01:00:53 [INFO] train episode 890: reward = -110.56, steps = 19 01:00:55 [INFO] train episode 891: reward = -80.33, steps = 19 01:00:57 [INFO] train episode 892: reward = -126.83, steps = 20 01:00:59 [INFO] train episode 893: reward = -113.26, steps = 19 01:01:01 [INFO] train episode 894: reward = -98.53, steps = 19 01:01:03 [INFO] train episode 895: reward = -96.70, steps = 18 01:01:05 [INFO] train episode 896: reward = -88.08, steps = 21 01:01:06 [INFO] train episode 897: reward = -101.49, steps = 18 01:01:09 [INFO] train episode 898: reward = -148.74, steps = 23 01:01:10 [INFO] train episode 899: reward = -112.47, steps = 19 01:01:13 [INFO] train episode 900: reward = -107.53, steps = 26 01:01:16 [INFO] train episode 901: reward = -121.52, steps = 24 01:01:19 [INFO] train episode 902: reward = -123.05, steps = 27 01:01:20 [INFO] train episode 903: reward = -80.18, steps = 18 01:01:23 [INFO] train episode 904: reward = -124.18, steps = 18 01:01:25 [INFO] train episode 905: reward = -90.62, steps = 18 01:01:27 [INFO] train episode 906: reward = -104.02, steps = 19 01:01:29 [INFO] train episode 907: reward = -80.40, steps = 20 01:01:32 [INFO] train episode 908: reward = -132.40, steps = 24 01:01:34 [INFO] train episode 909: reward = -110.61, steps = 20 01:01:36 [INFO] train episode 910: reward = -94.49, steps = 19 01:01:38 [INFO] train episode 911: reward = -109.62, steps = 20 01:01:40 [INFO] train episode 912: reward = -149.81, steps = 20 01:01:42 [INFO] train episode 913: reward = -98.73, steps = 21 01:01:44 [INFO] train episode 914: reward = -87.46, steps = 24 01:01:46 [INFO] train episode 915: reward = -75.48, steps = 19 01:01:49 [INFO] train episode 916: reward = -76.75, steps = 21 01:01:51 [INFO] train episode 917: reward = -91.39, steps = 19 01:01:53 [INFO] train episode 918: reward = -104.85, steps = 19 01:01:54 [INFO] train episode 919: reward = -78.13, steps = 19 01:01:56 [INFO] train episode 920: reward = -95.30, steps = 21 01:01:58 [INFO] train episode 921: reward = -101.56, steps = 20 01:02:00 [INFO] train episode 922: reward = -133.24, steps = 20 01:02:02 [INFO] train episode 923: reward = -89.99, steps = 19 01:02:04 [INFO] train episode 924: reward = -109.85, steps = 19 01:02:06 [INFO] train episode 925: reward = -98.35, steps = 19 01:02:10 [INFO] train episode 926: reward = -225.67, steps = 39 01:02:12 [INFO] train episode 927: reward = -80.21, steps = 25 01:02:15 [INFO] train episode 928: reward = -117.22, steps = 26 01:02:17 [INFO] train episode 929: reward = -157.91, steps = 21 01:02:19 [INFO] train episode 930: reward = -84.58, steps = 21 01:02:20 [INFO] train episode 931: reward = -114.11, steps = 18 01:02:22 [INFO] train episode 932: reward = -82.90, steps = 18 01:02:24 [INFO] train episode 933: reward = -97.86, steps = 20 01:02:26 [INFO] train episode 934: reward = -112.02, steps = 19 01:02:28 [INFO] train episode 935: reward = -126.57, steps = 21 01:02:30 [INFO] train episode 936: reward = -87.37, steps = 18 01:02:31 [INFO] train episode 937: reward = -85.90, steps = 19 01:02:33 [INFO] train episode 938: reward = -101.01, steps = 23 01:02:35 [INFO] train episode 939: reward = -153.70, steps = 21 01:02:37 [INFO] train episode 940: reward = -131.85, steps = 21 01:02:40 [INFO] train episode 941: reward = -95.36, steps = 20 01:02:42 [INFO] train episode 942: reward = -80.15, steps = 18 01:02:44 [INFO] train episode 943: reward = -75.42, steps = 19 01:02:45 [INFO] train episode 944: reward = -101.46, steps = 20 01:02:47 [INFO] train episode 945: reward = -92.19, steps = 19 01:02:49 [INFO] train episode 946: reward = -135.15, steps = 19 01:02:51 [INFO] train episode 947: reward = -76.31, steps = 19 01:02:53 [INFO] train episode 948: reward = -129.15, steps = 20 01:02:55 [INFO] train episode 949: reward = -131.88, steps = 21 01:02:57 [INFO] train episode 950: reward = -80.67, steps = 17 01:02:59 [INFO] train episode 951: reward = -91.56, steps = 21 01:03:01 [INFO] train episode 952: reward = -130.22, steps = 20 01:03:03 [INFO] train episode 953: reward = -79.09, steps = 18 01:03:05 [INFO] train episode 954: reward = -123.76, steps = 21 01:03:07 [INFO] train episode 955: reward = -117.16, steps = 20 01:03:09 [INFO] train episode 956: reward = -108.66, steps = 20 01:03:11 [INFO] train episode 957: reward = -89.72, steps = 24 01:03:13 [INFO] train episode 958: reward = -85.15, steps = 18 01:03:15 [INFO] train episode 959: reward = -86.19, steps = 18 01:03:17 [INFO] train episode 960: reward = -92.39, steps = 20 01:03:19 [INFO] train episode 961: reward = -116.67, steps = 20 01:03:22 [INFO] train episode 962: reward = -122.47, steps = 23 01:03:23 [INFO] train episode 963: reward = -130.61, steps = 19 01:03:25 [INFO] train episode 964: reward = -79.43, steps = 18 01:03:27 [INFO] train episode 965: reward = -85.32, steps = 22 01:03:30 [INFO] train episode 966: reward = -152.01, steps = 23 01:03:32 [INFO] train episode 967: reward = -91.73, steps = 17 01:03:35 [INFO] train episode 968: reward = -91.99, steps = 20 01:03:37 [INFO] train episode 969: reward = -86.76, steps = 23 01:03:39 [INFO] train episode 970: reward = -137.04, steps = 17 01:03:41 [INFO] train episode 971: reward = -68.99, steps = 19 01:03:43 [INFO] train episode 972: reward = -92.21, steps = 20 01:03:44 [INFO] train episode 973: reward = -107.71, steps = 21 01:03:47 [INFO] train episode 974: reward = -152.67, steps = 20 01:03:48 [INFO] train episode 975: reward = -92.32, steps = 19 01:03:50 [INFO] train episode 976: reward = -89.43, steps = 19 01:03:53 [INFO] train episode 977: reward = -162.19, steps = 22 01:03:55 [INFO] train episode 978: reward = -113.09, steps = 20 01:03:56 [INFO] train episode 979: reward = -125.81, steps = 16 01:03:58 [INFO] train episode 980: reward = -106.18, steps = 18 01:04:01 [INFO] train episode 981: reward = -120.30, steps = 29 01:04:03 [INFO] train episode 982: reward = -73.36, steps = 16 01:04:04 [INFO] train episode 983: reward = -105.64, steps = 19 01:04:06 [INFO] train episode 984: reward = -90.92, steps = 20 01:04:09 [INFO] train episode 985: reward = -92.11, steps = 20 01:04:11 [INFO] train episode 986: reward = -119.74, steps = 19 01:04:12 [INFO] train episode 987: reward = -69.78, steps = 17 01:04:15 [INFO] train episode 988: reward = -127.16, steps = 24 01:04:17 [INFO] train episode 989: reward = -117.77, steps = 21 01:04:18 [INFO] train episode 990: reward = -118.55, steps = 20 01:04:20 [INFO] train episode 991: reward = -123.05, steps = 18 01:04:22 [INFO] train episode 992: reward = -85.55, steps = 19 01:04:25 [INFO] train episode 993: reward = -117.51, steps = 26 01:04:27 [INFO] train episode 994: reward = -116.24, steps = 20 01:04:29 [INFO] train episode 995: reward = -102.75, steps = 20 01:04:31 [INFO] train episode 996: reward = -128.41, steps = 19 01:04:33 [INFO] train episode 997: reward = -91.58, steps = 21 01:04:34 [INFO] train episode 998: reward = -77.47, steps = 19 01:04:36 [INFO] train episode 999: reward = -99.79, steps = 19 01:04:38 [INFO] train episode 1000: reward = -91.04, steps = 20 01:04:40 [INFO] train episode 1001: reward = -104.86, steps = 23 01:04:44 [INFO] train episode 1002: reward = -140.08, steps = 34 01:04:46 [INFO] train episode 1003: reward = -114.74, steps = 23 01:04:48 [INFO] train episode 1004: reward = -114.21, steps = 19 01:04:50 [INFO] train episode 1005: reward = -127.43, steps = 22 01:04:52 [INFO] train episode 1006: reward = -89.47, steps = 18 01:04:54 [INFO] train episode 1007: reward = -113.12, steps = 20 01:04:55 [INFO] train episode 1008: reward = -109.02, steps = 19 01:04:57 [INFO] train episode 1009: reward = -76.55, steps = 20 01:05:00 [INFO] train episode 1010: reward = -115.86, steps = 18 01:05:01 [INFO] train episode 1011: reward = -102.47, steps = 18 01:05:03 [INFO] train episode 1012: reward = -121.15, steps = 20 01:05:05 [INFO] train episode 1013: reward = -145.21, steps = 22 01:05:07 [INFO] train episode 1014: reward = -128.95, steps = 21 01:05:09 [INFO] train episode 1015: reward = -148.63, steps = 21 01:05:11 [INFO] train episode 1016: reward = -100.92, steps = 20 01:05:13 [INFO] train episode 1017: reward = -85.99, steps = 19 01:05:15 [INFO] train episode 1018: reward = -88.74, steps = 19 01:05:17 [INFO] train episode 1019: reward = -99.21, steps = 19 01:05:19 [INFO] train episode 1020: reward = -106.35, steps = 20 01:05:21 [INFO] train episode 1021: reward = -119.28, steps = 18 01:05:23 [INFO] train episode 1022: reward = -107.56, steps = 23 01:05:25 [INFO] train episode 1023: reward = -86.18, steps = 18 01:05:27 [INFO] train episode 1024: reward = -144.21, steps = 20 01:05:29 [INFO] train episode 1025: reward = -115.86, steps = 26 01:05:31 [INFO] train episode 1026: reward = -121.30, steps = 19 01:05:33 [INFO] train episode 1027: reward = -146.46, steps = 19 01:05:35 [INFO] train episode 1028: reward = -92.25, steps = 18 01:05:37 [INFO] train episode 1029: reward = -76.38, steps = 19 01:05:38 [INFO] train episode 1030: reward = -63.18, steps = 12 01:05:40 [INFO] train episode 1031: reward = -77.12, steps = 19 01:05:41 [INFO] train episode 1032: reward = -95.72, steps = 19 01:05:43 [INFO] train episode 1033: reward = -103.39, steps = 19 01:05:44 [INFO] train episode 1034: reward = -70.51, steps = 12 01:05:46 [INFO] train episode 1035: reward = -80.50, steps = 19 01:05:48 [INFO] train episode 1036: reward = -107.07, steps = 19 01:05:50 [INFO] train episode 1037: reward = -83.60, steps = 18 01:05:52 [INFO] train episode 1038: reward = -72.89, steps = 19 01:05:54 [INFO] train episode 1039: reward = -106.87, steps = 19 01:05:57 [INFO] train episode 1040: reward = -88.79, steps = 22 01:05:59 [INFO] train episode 1041: reward = -90.11, steps = 20 01:06:01 [INFO] train episode 1042: reward = -107.04, steps = 19 01:06:03 [INFO] train episode 1043: reward = -129.50, steps = 25 01:06:05 [INFO] train episode 1044: reward = -88.53, steps = 20 01:06:07 [INFO] train episode 1045: reward = -123.82, steps = 20 01:06:10 [INFO] train episode 1046: reward = -113.41, steps = 27 01:06:12 [INFO] train episode 1047: reward = -113.90, steps = 18 01:06:14 [INFO] train episode 1048: reward = -88.51, steps = 19 01:06:16 [INFO] train episode 1049: reward = -83.49, steps = 19 01:06:18 [INFO] train episode 1050: reward = -142.80, steps = 20 01:06:20 [INFO] train episode 1051: reward = -82.26, steps = 20 01:06:21 [INFO] train episode 1052: reward = -104.04, steps = 17 01:06:23 [INFO] train episode 1053: reward = -96.52, steps = 20 01:06:26 [INFO] train episode 1054: reward = -123.31, steps = 26 01:06:28 [INFO] train episode 1055: reward = -95.15, steps = 19 01:06:30 [INFO] train episode 1056: reward = -94.76, steps = 20 01:06:32 [INFO] train episode 1057: reward = -79.03, steps = 19 01:06:34 [INFO] train episode 1058: reward = -122.69, steps = 21 01:06:36 [INFO] train episode 1059: reward = -149.13, steps = 20 01:06:38 [INFO] train episode 1060: reward = -99.20, steps = 18 01:06:40 [INFO] train episode 1061: reward = -130.29, steps = 20 01:06:41 [INFO] train episode 1062: reward = -99.87, steps = 19 01:06:45 [INFO] train episode 1063: reward = -98.46, steps = 20 01:06:47 [INFO] train episode 1064: reward = -105.95, steps = 23 01:06:49 [INFO] train episode 1065: reward = -97.78, steps = 22 01:06:51 [INFO] train episode 1066: reward = -148.31, steps = 19 01:06:52 [INFO] train episode 1067: reward = -67.05, steps = 19 01:06:54 [INFO] train episode 1068: reward = -103.69, steps = 18 01:06:56 [INFO] train episode 1069: reward = -81.16, steps = 20 01:06:58 [INFO] train episode 1070: reward = -93.49, steps = 21 01:07:00 [INFO] train episode 1071: reward = -109.78, steps = 19 01:07:03 [INFO] train episode 1072: reward = -108.78, steps = 23 01:07:04 [INFO] train episode 1073: reward = -87.70, steps = 20 01:07:06 [INFO] train episode 1074: reward = -119.22, steps = 20 01:07:08 [INFO] train episode 1075: reward = -103.53, steps = 19 01:07:10 [INFO] train episode 1076: reward = -118.71, steps = 19 01:07:12 [INFO] train episode 1077: reward = -99.30, steps = 21 01:07:14 [INFO] train episode 1078: reward = -67.62, steps = 19 01:07:16 [INFO] train episode 1079: reward = -150.72, steps = 27 01:07:19 [INFO] train episode 1080: reward = -106.04, steps = 19 01:07:20 [INFO] train episode 1081: reward = -71.33, steps = 17 01:07:22 [INFO] train episode 1082: reward = -80.70, steps = 20 01:07:24 [INFO] train episode 1083: reward = -87.90, steps = 19 01:07:26 [INFO] train episode 1084: reward = -104.26, steps = 20 01:07:27 [INFO] train episode 1085: reward = -82.26, steps = 18 01:07:30 [INFO] train episode 1086: reward = -123.19, steps = 22 01:07:31 [INFO] train episode 1087: reward = -86.35, steps = 21 01:07:33 [INFO] train episode 1088: reward = -92.22, steps = 19 01:07:35 [INFO] train episode 1089: reward = -91.22, steps = 18 01:07:37 [INFO] train episode 1090: reward = -84.17, steps = 19 01:07:39 [INFO] train episode 1091: reward = -96.70, steps = 19 01:07:41 [INFO] train episode 1092: reward = -127.78, steps = 20 01:07:42 [INFO] train episode 1093: reward = -78.93, steps = 19 01:07:44 [INFO] train episode 1094: reward = -99.93, steps = 19 01:07:47 [INFO] train episode 1095: reward = -162.39, steps = 28 01:07:49 [INFO] train episode 1096: reward = -66.83, steps = 21 01:07:51 [INFO] train episode 1097: reward = -131.48, steps = 24 01:07:53 [INFO] train episode 1098: reward = -111.58, steps = 22 01:07:55 [INFO] train episode 1099: reward = -104.77, steps = 19 01:07:56 [INFO] train episode 1100: reward = -102.67, steps = 16 01:07:58 [INFO] train episode 1101: reward = -76.60, steps = 19 01:08:00 [INFO] train episode 1102: reward = -91.40, steps = 21 01:08:02 [INFO] train episode 1103: reward = -110.58, steps = 19 01:08:04 [INFO] train episode 1104: reward = -107.44, steps = 19 01:08:06 [INFO] train episode 1105: reward = -101.53, steps = 22 01:08:08 [INFO] train episode 1106: reward = -150.03, steps = 22 01:08:10 [INFO] train episode 1107: reward = -165.83, steps = 20 01:08:12 [INFO] train episode 1108: reward = -132.75, steps = 23 01:08:13 [INFO] train episode 1109: reward = -112.22, steps = 19 01:08:15 [INFO] train episode 1110: reward = -134.72, steps = 21 01:08:17 [INFO] train episode 1111: reward = -73.24, steps = 21 01:08:19 [INFO] train episode 1112: reward = -106.13, steps = 20 01:08:21 [INFO] train episode 1113: reward = -74.65, steps = 19 01:08:23 [INFO] train episode 1114: reward = -114.45, steps = 19 01:08:25 [INFO] train episode 1115: reward = -99.41, steps = 19 01:08:26 [INFO] train episode 1116: reward = -122.66, steps = 18 01:08:28 [INFO] train episode 1117: reward = -61.25, steps = 19 01:08:30 [INFO] train episode 1118: reward = -97.13, steps = 20 01:08:32 [INFO] train episode 1119: reward = -75.22, steps = 20 01:08:33 [INFO] train episode 1120: reward = -89.22, steps = 19 01:08:35 [INFO] train episode 1121: reward = -126.77, steps = 19 01:08:37 [INFO] train episode 1122: reward = -119.24, steps = 19 01:08:39 [INFO] train episode 1123: reward = -106.40, steps = 24 01:08:41 [INFO] train episode 1124: reward = -115.88, steps = 20 01:08:43 [INFO] train episode 1125: reward = -98.44, steps = 17 01:08:44 [INFO] train episode 1126: reward = -99.13, steps = 19 01:08:47 [INFO] train episode 1127: reward = -172.42, steps = 32 01:08:49 [INFO] train episode 1128: reward = -73.01, steps = 19 01:08:51 [INFO] train episode 1129: reward = -74.88, steps = 21 01:08:52 [INFO] train episode 1130: reward = -108.73, steps = 18 01:08:55 [INFO] train episode 1131: reward = -119.94, steps = 26 01:08:57 [INFO] train episode 1132: reward = -108.70, steps = 20 01:08:59 [INFO] train episode 1133: reward = -96.31, steps = 20 01:09:01 [INFO] train episode 1134: reward = -161.56, steps = 20 01:09:02 [INFO] train episode 1135: reward = -98.54, steps = 20 01:09:04 [INFO] train episode 1136: reward = -104.14, steps = 19 01:09:06 [INFO] train episode 1137: reward = -104.54, steps = 20 01:09:08 [INFO] train episode 1138: reward = -109.47, steps = 20 01:09:10 [INFO] train episode 1139: reward = -74.79, steps = 20 01:09:12 [INFO] train episode 1140: reward = -143.10, steps = 24 01:09:14 [INFO] train episode 1141: reward = -77.41, steps = 18 01:09:16 [INFO] train episode 1142: reward = -110.85, steps = 20 01:09:18 [INFO] train episode 1143: reward = -100.45, steps = 19 01:09:19 [INFO] train episode 1144: reward = -83.00, steps = 21 01:09:21 [INFO] train episode 1145: reward = -92.63, steps = 18 01:09:23 [INFO] train episode 1146: reward = -102.88, steps = 23 01:09:25 [INFO] train episode 1147: reward = -98.74, steps = 19 01:09:27 [INFO] train episode 1148: reward = -97.02, steps = 18 01:09:29 [INFO] train episode 1149: reward = -80.97, steps = 20 01:09:30 [INFO] train episode 1150: reward = -98.56, steps = 18 01:09:32 [INFO] train episode 1151: reward = -90.97, steps = 17 01:09:34 [INFO] train episode 1152: reward = -79.02, steps = 19 01:09:35 [INFO] train episode 1153: reward = -105.19, steps = 13 01:09:37 [INFO] train episode 1154: reward = -99.82, steps = 19 01:09:39 [INFO] train episode 1155: reward = -106.09, steps = 19 01:09:41 [INFO] train episode 1156: reward = -105.00, steps = 27 01:09:43 [INFO] train episode 1157: reward = -118.08, steps = 20 01:09:46 [INFO] train episode 1158: reward = -96.66, steps = 19 01:09:48 [INFO] train episode 1159: reward = -105.61, steps = 19 01:09:49 [INFO] train episode 1160: reward = -136.09, steps = 20 01:09:51 [INFO] train episode 1161: reward = -156.40, steps = 21 01:09:53 [INFO] train episode 1162: reward = -89.34, steps = 20 01:09:55 [INFO] train episode 1163: reward = -121.96, steps = 19 01:09:57 [INFO] train episode 1164: reward = -112.06, steps = 19 01:09:58 [INFO] train episode 1165: reward = -83.03, steps = 19 01:10:00 [INFO] train episode 1166: reward = -110.75, steps = 19 01:10:02 [INFO] train episode 1167: reward = -81.66, steps = 19 01:10:04 [INFO] train episode 1168: reward = -108.28, steps = 19 01:10:06 [INFO] train episode 1169: reward = -105.51, steps = 23 01:10:08 [INFO] train episode 1170: reward = -93.61, steps = 21 01:10:10 [INFO] train episode 1171: reward = -102.89, steps = 19 01:10:12 [INFO] train episode 1172: reward = -124.88, steps = 26 01:10:14 [INFO] train episode 1173: reward = -113.36, steps = 19 01:10:16 [INFO] train episode 1174: reward = -88.10, steps = 19 01:10:18 [INFO] train episode 1175: reward = -96.39, steps = 18 01:10:19 [INFO] train episode 1176: reward = -74.88, steps = 18 01:10:22 [INFO] train episode 1177: reward = -139.23, steps = 24 01:10:24 [INFO] train episode 1178: reward = -108.73, steps = 22 01:10:25 [INFO] train episode 1179: reward = -138.39, steps = 19 01:10:27 [INFO] train episode 1180: reward = -107.76, steps = 20 01:10:29 [INFO] train episode 1181: reward = -86.24, steps = 19 01:10:31 [INFO] train episode 1182: reward = -81.07, steps = 19 01:10:32 [INFO] train episode 1183: reward = -74.97, steps = 18 01:10:34 [INFO] train episode 1184: reward = -114.29, steps = 19 01:10:36 [INFO] train episode 1185: reward = -76.33, steps = 21 01:10:38 [INFO] train episode 1186: reward = -118.32, steps = 20 01:10:40 [INFO] train episode 1187: reward = -106.21, steps = 18 01:10:42 [INFO] train episode 1188: reward = -129.55, steps = 22 01:10:44 [INFO] train episode 1189: reward = -104.15, steps = 21 01:10:46 [INFO] train episode 1190: reward = -108.92, steps = 19 01:10:48 [INFO] train episode 1191: reward = -103.78, steps = 20 01:10:50 [INFO] train episode 1192: reward = -123.51, steps = 22 01:10:52 [INFO] train episode 1193: reward = -109.62, steps = 21 01:10:54 [INFO] train episode 1194: reward = -85.93, steps = 19 01:10:56 [INFO] train episode 1195: reward = -76.27, steps = 19 01:10:57 [INFO] train episode 1196: reward = -86.87, steps = 19 01:11:00 [INFO] train episode 1197: reward = -83.58, steps = 23 01:11:02 [INFO] train episode 1198: reward = -112.76, steps = 32 01:11:04 [INFO] train episode 1199: reward = -86.60, steps = 19 01:11:06 [INFO] train episode 1200: reward = -120.67, steps = 18 01:11:09 [INFO] train episode 1201: reward = -108.05, steps = 34 01:11:11 [INFO] train episode 1202: reward = -97.31, steps = 20 01:11:13 [INFO] train episode 1203: reward = -83.26, steps = 18 01:11:15 [INFO] train episode 1204: reward = -95.28, steps = 19 01:11:17 [INFO] train episode 1205: reward = -88.59, steps = 22 01:11:19 [INFO] train episode 1206: reward = -88.71, steps = 21 01:11:21 [INFO] train episode 1207: reward = -143.98, steps = 25 01:11:23 [INFO] train episode 1208: reward = -96.19, steps = 24 01:11:25 [INFO] train episode 1209: reward = -87.57, steps = 19 01:11:27 [INFO] train episode 1210: reward = -116.69, steps = 20 01:11:29 [INFO] train episode 1211: reward = -92.71, steps = 19 01:11:31 [INFO] train episode 1212: reward = -106.70, steps = 18 01:11:32 [INFO] train episode 1213: reward = -84.73, steps = 19 01:11:35 [INFO] train episode 1214: reward = -105.64, steps = 23 01:11:37 [INFO] train episode 1215: reward = -124.23, steps = 22 01:11:38 [INFO] train episode 1216: reward = -110.83, steps = 18 01:11:40 [INFO] train episode 1217: reward = -101.64, steps = 19 01:11:42 [INFO] train episode 1218: reward = -102.83, steps = 18 01:11:44 [INFO] train episode 1219: reward = -128.98, steps = 23 01:11:46 [INFO] train episode 1220: reward = -111.49, steps = 21 01:11:48 [INFO] train episode 1221: reward = -93.93, steps = 20 01:11:50 [INFO] train episode 1222: reward = -109.77, steps = 19 01:11:53 [INFO] train episode 1223: reward = -156.77, steps = 24 01:11:55 [INFO] train episode 1224: reward = -138.58, steps = 18 01:11:57 [INFO] train episode 1225: reward = -94.87, steps = 20 01:12:00 [INFO] train episode 1226: reward = -100.18, steps = 26 01:12:02 [INFO] train episode 1227: reward = -88.85, steps = 19 01:12:04 [INFO] train episode 1228: reward = -119.69, steps = 20 01:12:06 [INFO] train episode 1229: reward = -125.94, steps = 27 01:12:08 [INFO] train episode 1230: reward = -89.18, steps = 20 01:12:10 [INFO] train episode 1231: reward = -118.79, steps = 18 01:12:13 [INFO] train episode 1232: reward = -98.05, steps = 19 01:12:15 [INFO] train episode 1233: reward = -148.74, steps = 23 01:12:17 [INFO] train episode 1234: reward = -105.20, steps = 19 01:12:20 [INFO] train episode 1235: reward = -105.08, steps = 26 01:12:22 [INFO] train episode 1236: reward = -143.84, steps = 20 01:12:23 [INFO] train episode 1237: reward = -111.51, steps = 18 01:12:25 [INFO] train episode 1238: reward = -72.98, steps = 19 01:12:27 [INFO] train episode 1239: reward = -121.41, steps = 25 01:12:29 [INFO] train episode 1240: reward = -97.99, steps = 20 01:12:31 [INFO] train episode 1241: reward = -87.09, steps = 19 01:12:33 [INFO] train episode 1242: reward = -97.92, steps = 21 01:12:35 [INFO] train episode 1243: reward = -92.85, steps = 21 01:12:37 [INFO] train episode 1244: reward = -131.78, steps = 19 01:12:39 [INFO] train episode 1245: reward = -108.76, steps = 24 01:12:41 [INFO] train episode 1246: reward = -90.98, steps = 18 01:12:43 [INFO] train episode 1247: reward = -83.48, steps = 18 01:12:45 [INFO] train episode 1248: reward = -98.27, steps = 20 01:12:47 [INFO] train episode 1249: reward = -105.48, steps = 20 01:12:49 [INFO] train episode 1250: reward = -113.34, steps = 19 01:12:52 [INFO] train episode 1251: reward = -88.34, steps = 19 01:12:54 [INFO] train episode 1252: reward = -110.45, steps = 19 01:12:56 [INFO] train episode 1253: reward = -100.04, steps = 20 01:12:57 [INFO] train episode 1254: reward = -124.92, steps = 21 01:12:59 [INFO] train episode 1255: reward = -126.37, steps = 19 01:13:01 [INFO] train episode 1256: reward = -114.33, steps = 22 01:13:03 [INFO] train episode 1257: reward = -100.96, steps = 18 01:13:05 [INFO] train episode 1258: reward = -124.84, steps = 21 01:13:08 [INFO] train episode 1259: reward = -129.04, steps = 24 01:13:09 [INFO] train episode 1260: reward = -95.81, steps = 19 01:13:11 [INFO] train episode 1261: reward = -140.03, steps = 18 01:13:13 [INFO] train episode 1262: reward = -123.84, steps = 19 01:13:15 [INFO] train episode 1263: reward = -99.97, steps = 19 01:13:16 [INFO] train episode 1264: reward = -88.26, steps = 18 01:13:19 [INFO] train episode 1265: reward = -105.25, steps = 28 01:13:21 [INFO] train episode 1266: reward = -83.32, steps = 19 01:13:23 [INFO] train episode 1267: reward = -125.05, steps = 23 01:13:25 [INFO] train episode 1268: reward = -84.31, steps = 22 01:13:27 [INFO] train episode 1269: reward = -98.58, steps = 20 01:13:29 [INFO] train episode 1270: reward = -89.59, steps = 19 01:13:31 [INFO] train episode 1271: reward = -110.22, steps = 19 01:13:33 [INFO] train episode 1272: reward = -111.83, steps = 24 01:13:36 [INFO] train episode 1273: reward = -111.57, steps = 19 01:13:38 [INFO] train episode 1274: reward = -101.68, steps = 21 01:13:40 [INFO] train episode 1275: reward = -85.71, steps = 19 01:13:42 [INFO] train episode 1276: reward = -116.73, steps = 20 01:13:44 [INFO] train episode 1277: reward = -93.96, steps = 18 01:13:46 [INFO] train episode 1278: reward = -113.86, steps = 21 01:13:47 [INFO] train episode 1279: reward = -85.79, steps = 18 01:13:49 [INFO] train episode 1280: reward = -92.72, steps = 19 01:13:51 [INFO] train episode 1281: reward = -108.47, steps = 20 01:13:53 [INFO] train episode 1282: reward = -94.50, steps = 25 01:13:55 [INFO] train episode 1283: reward = -103.90, steps = 19 01:13:57 [INFO] train episode 1284: reward = -109.07, steps = 17 01:13:59 [INFO] train episode 1285: reward = -84.49, steps = 20 01:14:01 [INFO] train episode 1286: reward = -79.53, steps = 20 01:14:04 [INFO] train episode 1287: reward = -143.57, steps = 30 01:14:06 [INFO] train episode 1288: reward = -97.17, steps = 19 01:14:07 [INFO] train episode 1289: reward = -80.61, steps = 19 01:14:09 [INFO] train episode 1290: reward = -100.74, steps = 19 01:14:11 [INFO] train episode 1291: reward = -101.67, steps = 19 01:14:13 [INFO] train episode 1292: reward = -127.03, steps = 19 01:14:15 [INFO] train episode 1293: reward = -66.41, steps = 16 01:14:17 [INFO] train episode 1294: reward = -99.93, steps = 19 01:14:18 [INFO] train episode 1295: reward = -95.88, steps = 19 01:14:20 [INFO] train episode 1296: reward = -137.34, steps = 20 01:14:22 [INFO] train episode 1297: reward = -99.56, steps = 18 01:14:24 [INFO] train episode 1298: reward = -101.30, steps = 20 01:14:26 [INFO] train episode 1299: reward = -111.27, steps = 18 01:14:28 [INFO] train episode 1300: reward = -105.91, steps = 21 01:14:30 [INFO] train episode 1301: reward = -121.52, steps = 21 01:14:32 [INFO] train episode 1302: reward = -111.78, steps = 27 01:14:34 [INFO] train episode 1303: reward = -117.52, steps = 19 01:14:36 [INFO] train episode 1304: reward = -99.08, steps = 19 01:14:38 [INFO] train episode 1305: reward = -126.11, steps = 25 01:14:40 [INFO] train episode 1306: reward = -85.19, steps = 20 01:14:43 [INFO] train episode 1307: reward = -114.94, steps = 27 01:14:44 [INFO] train episode 1308: reward = -120.15, steps = 18 01:14:46 [INFO] train episode 1309: reward = -100.22, steps = 20 01:14:48 [INFO] train episode 1310: reward = -98.37, steps = 20 01:14:50 [INFO] train episode 1311: reward = -103.48, steps = 18 01:14:52 [INFO] train episode 1312: reward = -124.14, steps = 20 01:14:54 [INFO] train episode 1313: reward = -102.74, steps = 19 01:14:56 [INFO] train episode 1314: reward = -137.38, steps = 20 01:14:58 [INFO] train episode 1315: reward = -84.06, steps = 20 01:15:00 [INFO] train episode 1316: reward = -85.18, steps = 22 01:15:02 [INFO] train episode 1317: reward = -113.33, steps = 19 01:15:03 [INFO] train episode 1318: reward = -127.90, steps = 19 01:15:06 [INFO] train episode 1319: reward = -120.72, steps = 26 01:15:08 [INFO] train episode 1320: reward = -84.92, steps = 25 01:15:10 [INFO] train episode 1321: reward = -138.45, steps = 21 01:15:12 [INFO] train episode 1322: reward = -108.48, steps = 20 01:15:14 [INFO] train episode 1323: reward = -136.05, steps = 22 01:15:16 [INFO] train episode 1324: reward = -87.27, steps = 18 01:15:18 [INFO] train episode 1325: reward = -89.40, steps = 17 01:15:19 [INFO] train episode 1326: reward = -138.50, steps = 19 01:15:24 [INFO] train episode 1327: reward = -156.61, steps = 43 01:15:25 [INFO] train episode 1328: reward = -86.17, steps = 19 01:15:27 [INFO] train episode 1329: reward = -111.31, steps = 23 01:15:30 [INFO] train episode 1330: reward = -136.93, steps = 29 01:15:32 [INFO] train episode 1331: reward = -114.06, steps = 19 01:15:34 [INFO] train episode 1332: reward = -130.00, steps = 26 01:15:36 [INFO] train episode 1333: reward = -81.48, steps = 19 01:15:38 [INFO] train episode 1334: reward = -118.81, steps = 22 01:15:40 [INFO] train episode 1335: reward = -98.56, steps = 19 01:15:42 [INFO] train episode 1336: reward = -69.58, steps = 19 01:15:44 [INFO] train episode 1337: reward = -117.10, steps = 20 01:15:46 [INFO] train episode 1338: reward = -129.10, steps = 20 01:15:47 [INFO] train episode 1339: reward = -91.46, steps = 19 01:15:49 [INFO] train episode 1340: reward = -118.38, steps = 19 01:15:51 [INFO] train episode 1341: reward = -101.36, steps = 18 01:15:53 [INFO] train episode 1342: reward = -114.41, steps = 18 01:15:55 [INFO] train episode 1343: reward = -135.85, steps = 19 01:15:57 [INFO] train episode 1344: reward = -136.64, steps = 19 01:15:59 [INFO] train episode 1345: reward = -128.97, steps = 20 01:16:01 [INFO] train episode 1346: reward = -116.90, steps = 17 01:16:03 [INFO] train episode 1347: reward = -60.94, steps = 18 01:16:05 [INFO] train episode 1348: reward = -123.80, steps = 19 01:16:07 [INFO] train episode 1349: reward = -105.81, steps = 20 01:16:09 [INFO] train episode 1350: reward = -124.76, steps = 26 01:16:11 [INFO] train episode 1351: reward = -123.09, steps = 21 01:16:13 [INFO] train episode 1352: reward = -76.93, steps = 19 01:16:15 [INFO] train episode 1353: reward = -88.88, steps = 18 01:16:17 [INFO] train episode 1354: reward = -95.99, steps = 20 01:16:19 [INFO] train episode 1355: reward = -105.68, steps = 24 01:16:21 [INFO] train episode 1356: reward = -120.79, steps = 20 01:16:23 [INFO] train episode 1357: reward = -98.44, steps = 20 01:16:25 [INFO] train episode 1358: reward = -80.64, steps = 19 01:16:26 [INFO] train episode 1359: reward = -84.02, steps = 19 01:16:28 [INFO] train episode 1360: reward = -121.18, steps = 19 01:16:30 [INFO] train episode 1361: reward = -119.43, steps = 20 01:16:32 [INFO] train episode 1362: reward = -123.30, steps = 19 01:16:35 [INFO] train episode 1363: reward = -138.46, steps = 20 01:16:36 [INFO] train episode 1364: reward = -108.06, steps = 18 01:16:38 [INFO] train episode 1365: reward = -117.81, steps = 22 01:16:40 [INFO] train episode 1366: reward = -68.44, steps = 19 01:16:42 [INFO] train episode 1367: reward = -91.48, steps = 20 01:16:44 [INFO] train episode 1368: reward = -73.67, steps = 19 01:16:46 [INFO] train episode 1369: reward = -101.37, steps = 19 01:16:47 [INFO] train episode 1370: reward = -123.18, steps = 20 01:16:49 [INFO] train episode 1371: reward = -120.17, steps = 19 01:16:51 [INFO] train episode 1372: reward = -109.34, steps = 19 01:16:53 [INFO] train episode 1373: reward = -69.45, steps = 19 01:16:55 [INFO] train episode 1374: reward = -89.84, steps = 20 01:16:57 [INFO] train episode 1375: reward = -82.35, steps = 19 01:16:59 [INFO] train episode 1376: reward = -179.42, steps = 20 01:17:01 [INFO] train episode 1377: reward = -95.62, steps = 22 01:17:03 [INFO] train episode 1378: reward = -104.17, steps = 19 01:17:04 [INFO] train episode 1379: reward = -98.64, steps = 17 01:17:06 [INFO] train episode 1380: reward = -99.74, steps = 19 01:17:08 [INFO] train episode 1381: reward = -114.55, steps = 19 01:17:10 [INFO] train episode 1382: reward = -105.97, steps = 20 01:17:12 [INFO] train episode 1383: reward = -100.10, steps = 21 01:17:14 [INFO] train episode 1384: reward = -108.35, steps = 19 01:17:16 [INFO] train episode 1385: reward = -113.11, steps = 20 01:17:18 [INFO] train episode 1386: reward = -81.70, steps = 19 01:17:20 [INFO] train episode 1387: reward = -101.33, steps = 19 01:17:21 [INFO] train episode 1388: reward = -106.29, steps = 18 01:17:23 [INFO] train episode 1389: reward = -101.73, steps = 20 01:17:26 [INFO] train episode 1390: reward = -128.76, steps = 20 01:17:27 [INFO] train episode 1391: reward = -115.29, steps = 20 01:17:29 [INFO] train episode 1392: reward = -87.37, steps = 18 01:17:31 [INFO] train episode 1393: reward = -94.97, steps = 17 01:17:33 [INFO] train episode 1394: reward = -112.96, steps = 19 01:17:35 [INFO] train episode 1395: reward = -124.44, steps = 20 01:17:36 [INFO] train episode 1396: reward = -85.77, steps = 20 01:17:38 [INFO] train episode 1397: reward = -110.77, steps = 20 01:17:40 [INFO] train episode 1398: reward = -80.70, steps = 18 01:17:41 [INFO] train episode 1399: reward = -99.37, steps = 9 01:17:43 [INFO] train episode 1400: reward = -128.07, steps = 20 01:17:45 [INFO] train episode 1401: reward = -130.80, steps = 19 01:17:47 [INFO] train episode 1402: reward = -92.32, steps = 19 01:17:49 [INFO] train episode 1403: reward = -66.38, steps = 19 01:17:50 [INFO] train episode 1404: reward = -85.01, steps = 19 01:17:52 [INFO] train episode 1405: reward = -111.58, steps = 23 01:17:54 [INFO] train episode 1406: reward = -122.25, steps = 19 01:17:56 [INFO] train episode 1407: reward = -93.25, steps = 20 01:17:59 [INFO] train episode 1408: reward = -139.74, steps = 25 01:18:01 [INFO] train episode 1409: reward = -100.91, steps = 19 01:18:03 [INFO] train episode 1410: reward = -124.75, steps = 19 01:18:05 [INFO] train episode 1411: reward = -104.24, steps = 22 01:18:07 [INFO] train episode 1412: reward = -98.22, steps = 19 01:18:09 [INFO] train episode 1413: reward = -107.05, steps = 22 01:18:10 [INFO] train episode 1414: reward = -103.27, steps = 18 01:18:12 [INFO] train episode 1415: reward = -116.52, steps = 19 01:18:14 [INFO] train episode 1416: reward = -97.57, steps = 19 01:18:16 [INFO] train episode 1417: reward = -132.10, steps = 22 01:18:18 [INFO] train episode 1418: reward = -87.48, steps = 19 01:18:20 [INFO] train episode 1419: reward = -122.12, steps = 19 01:18:22 [INFO] train episode 1420: reward = -100.50, steps = 19 01:18:24 [INFO] train episode 1421: reward = -107.09, steps = 18 01:18:26 [INFO] train episode 1422: reward = -104.29, steps = 28 01:18:28 [INFO] train episode 1423: reward = -90.06, steps = 19 01:18:30 [INFO] train episode 1424: reward = -110.24, steps = 20 01:18:32 [INFO] train episode 1425: reward = -86.10, steps = 19 01:18:35 [INFO] train episode 1426: reward = -143.88, steps = 25 01:18:37 [INFO] train episode 1427: reward = -130.32, steps = 19 01:18:38 [INFO] train episode 1428: reward = -117.23, steps = 17 01:18:40 [INFO] train episode 1429: reward = -86.14, steps = 18 01:18:42 [INFO] train episode 1430: reward = -82.95, steps = 19 01:18:43 [INFO] train episode 1431: reward = -76.47, steps = 19 01:18:45 [INFO] train episode 1432: reward = -110.04, steps = 20 01:18:47 [INFO] train episode 1433: reward = -116.11, steps = 18 01:18:49 [INFO] train episode 1434: reward = -99.91, steps = 22 01:18:51 [INFO] train episode 1435: reward = -88.26, steps = 19 01:18:53 [INFO] train episode 1436: reward = -115.62, steps = 19 01:18:54 [INFO] train episode 1437: reward = -111.43, steps = 19 01:18:56 [INFO] train episode 1438: reward = -98.23, steps = 20 01:18:58 [INFO] train episode 1439: reward = -74.36, steps = 16 01:19:00 [INFO] train episode 1440: reward = -109.54, steps = 20 01:19:02 [INFO] train episode 1441: reward = -120.03, steps = 20 01:19:04 [INFO] train episode 1442: reward = -108.10, steps = 19 01:19:06 [INFO] train episode 1443: reward = -95.91, steps = 20 01:19:08 [INFO] train episode 1444: reward = -57.63, steps = 19 01:19:10 [INFO] train episode 1445: reward = -76.40, steps = 18 01:19:12 [INFO] train episode 1446: reward = -115.84, steps = 20 01:19:14 [INFO] train episode 1447: reward = -73.98, steps = 20 01:19:16 [INFO] train episode 1448: reward = -118.71, steps = 22 01:19:18 [INFO] train episode 1449: reward = -103.95, steps = 23 01:19:20 [INFO] train episode 1450: reward = -157.76, steps = 20 01:19:22 [INFO] train episode 1451: reward = -95.77, steps = 18 01:19:23 [INFO] train episode 1452: reward = -92.59, steps = 18 01:19:25 [INFO] train episode 1453: reward = -89.05, steps = 19 01:19:27 [INFO] train episode 1454: reward = -95.06, steps = 19 01:19:29 [INFO] train episode 1455: reward = -110.01, steps = 22 01:19:31 [INFO] train episode 1456: reward = -105.79, steps = 22 01:19:33 [INFO] train episode 1457: reward = -121.04, steps = 19 01:19:35 [INFO] train episode 1458: reward = -131.97, steps = 19 01:19:37 [INFO] train episode 1459: reward = -88.73, steps = 22 01:19:39 [INFO] train episode 1460: reward = -125.68, steps = 22 01:19:40 [INFO] train episode 1461: reward = -93.60, steps = 19 01:19:43 [INFO] train episode 1462: reward = -91.61, steps = 20 01:19:44 [INFO] train episode 1463: reward = -86.22, steps = 18 01:19:46 [INFO] train episode 1464: reward = -112.76, steps = 18 01:19:48 [INFO] train episode 1465: reward = -108.78, steps = 19 01:19:49 [INFO] train episode 1466: reward = -101.67, steps = 19 01:19:51 [INFO] train episode 1467: reward = -61.05, steps = 19 01:19:53 [INFO] train episode 1468: reward = -108.34, steps = 20 01:19:54 [INFO] train episode 1469: reward = -92.07, steps = 18 01:19:56 [INFO] train episode 1470: reward = -85.93, steps = 21 01:19:59 [INFO] train episode 1471: reward = -110.22, steps = 25 01:20:01 [INFO] train episode 1472: reward = -114.61, steps = 18 01:20:02 [INFO] train episode 1473: reward = -101.63, steps = 18 01:20:05 [INFO] train episode 1474: reward = -125.78, steps = 26 01:20:06 [INFO] train episode 1475: reward = -92.15, steps = 19 01:20:08 [INFO] train episode 1476: reward = -105.65, steps = 20 01:20:10 [INFO] train episode 1477: reward = -117.12, steps = 19 01:20:11 [INFO] train episode 1478: reward = -91.40, steps = 18 01:20:13 [INFO] train episode 1479: reward = -81.37, steps = 18 01:20:15 [INFO] train episode 1480: reward = -120.16, steps = 22 01:20:17 [INFO] train episode 1481: reward = -108.33, steps = 19 01:20:19 [INFO] train episode 1482: reward = -86.88, steps = 19 01:20:20 [INFO] train episode 1483: reward = -112.30, steps = 20 01:20:23 [INFO] train episode 1484: reward = -117.61, steps = 27 01:20:25 [INFO] train episode 1485: reward = -99.55, steps = 20 01:20:26 [INFO] train episode 1486: reward = -83.01, steps = 20 01:20:28 [INFO] train episode 1487: reward = -85.13, steps = 19 01:20:30 [INFO] train episode 1488: reward = -104.13, steps = 19 01:20:33 [INFO] train episode 1489: reward = -110.61, steps = 20 01:20:35 [INFO] train episode 1490: reward = -88.52, steps = 23 01:20:37 [INFO] train episode 1491: reward = -115.00, steps = 21 01:20:39 [INFO] train episode 1492: reward = -90.94, steps = 23 01:20:41 [INFO] train episode 1493: reward = -92.76, steps = 19 01:20:43 [INFO] train episode 1494: reward = -82.25, steps = 19 01:20:45 [INFO] train episode 1495: reward = -112.23, steps = 23 01:20:47 [INFO] train episode 1496: reward = -83.10, steps = 19 01:20:50 [INFO] train episode 1497: reward = -82.39, steps = 19 01:20:51 [INFO] train episode 1498: reward = -125.95, steps = 18 01:20:53 [INFO] train episode 1499: reward = -131.04, steps = 19 01:20:55 [INFO] train episode 1500: reward = -141.97, steps = 19 01:20:57 [INFO] train episode 1501: reward = -114.97, steps = 19 01:20:59 [INFO] train episode 1502: reward = -125.03, steps = 18 01:21:01 [INFO] train episode 1503: reward = -109.51, steps = 19 01:21:03 [INFO] train episode 1504: reward = -87.22, steps = 18 01:21:05 [INFO] train episode 1505: reward = -93.43, steps = 19 01:21:07 [INFO] train episode 1506: reward = -111.87, steps = 20 01:21:09 [INFO] train episode 1507: reward = -102.92, steps = 20 01:21:11 [INFO] train episode 1508: reward = -119.08, steps = 19 01:21:14 [INFO] train episode 1509: reward = -98.07, steps = 25 01:21:16 [INFO] train episode 1510: reward = -90.76, steps = 16 01:21:18 [INFO] train episode 1511: reward = -142.04, steps = 25 01:21:20 [INFO] train episode 1512: reward = -119.45, steps = 20 01:21:21 [INFO] train episode 1513: reward = -119.14, steps = 18 01:21:23 [INFO] train episode 1514: reward = -119.25, steps = 19 01:21:25 [INFO] train episode 1515: reward = -79.27, steps = 19 01:21:27 [INFO] train episode 1516: reward = -97.35, steps = 19 01:21:29 [INFO] train episode 1517: reward = -142.19, steps = 22 01:21:31 [INFO] train episode 1518: reward = -137.74, steps = 20 01:21:33 [INFO] train episode 1519: reward = -112.48, steps = 22 01:21:34 [INFO] train episode 1520: reward = -130.48, steps = 18 01:21:37 [INFO] train episode 1521: reward = -123.58, steps = 24 01:21:38 [INFO] train episode 1522: reward = -114.70, steps = 19 01:21:41 [INFO] train episode 1523: reward = -147.73, steps = 26 01:21:43 [INFO] train episode 1524: reward = -95.60, steps = 21 01:21:45 [INFO] train episode 1525: reward = -110.28, steps = 20 01:21:47 [INFO] train episode 1526: reward = -92.08, steps = 20 01:21:49 [INFO] train episode 1527: reward = -104.15, steps = 18 01:21:51 [INFO] train episode 1528: reward = -97.54, steps = 22 01:21:53 [INFO] train episode 1529: reward = -144.64, steps = 29 01:21:55 [INFO] train episode 1530: reward = -111.83, steps = 18 01:21:57 [INFO] train episode 1531: reward = -122.69, steps = 19 01:21:59 [INFO] train episode 1532: reward = -92.09, steps = 19 01:22:01 [INFO] train episode 1533: reward = -116.61, steps = 19 01:22:03 [INFO] train episode 1534: reward = -107.20, steps = 21 01:22:04 [INFO] train episode 1535: reward = -116.14, steps = 17 01:22:07 [INFO] train episode 1536: reward = -135.54, steps = 29 01:22:09 [INFO] train episode 1537: reward = -87.07, steps = 20 01:22:11 [INFO] train episode 1538: reward = -135.87, steps = 19 01:22:13 [INFO] train episode 1539: reward = -132.28, steps = 21 01:22:15 [INFO] train episode 1540: reward = -108.37, steps = 20 01:22:17 [INFO] train episode 1541: reward = -108.21, steps = 19 01:22:19 [INFO] train episode 1542: reward = -97.77, steps = 18 01:22:20 [INFO] train episode 1543: reward = -105.57, steps = 19 01:22:22 [INFO] train episode 1544: reward = -98.78, steps = 18 01:22:24 [INFO] train episode 1545: reward = -64.99, steps = 19 01:22:25 [INFO] train episode 1546: reward = -127.59, steps = 19 01:22:27 [INFO] train episode 1547: reward = -112.25, steps = 19 01:22:29 [INFO] train episode 1548: reward = -76.40, steps = 19 01:22:30 [INFO] train episode 1549: reward = -86.29, steps = 19 01:22:33 [INFO] train episode 1550: reward = -116.35, steps = 25 01:22:35 [INFO] train episode 1551: reward = -132.67, steps = 25 01:22:37 [INFO] train episode 1552: reward = -81.90, steps = 20 01:22:39 [INFO] train episode 1553: reward = -90.28, steps = 19 01:22:43 [INFO] train episode 1554: reward = -134.05, steps = 46 01:22:45 [INFO] train episode 1555: reward = -77.40, steps = 20 01:22:47 [INFO] train episode 1556: reward = -115.56, steps = 20 01:22:49 [INFO] train episode 1557: reward = -137.58, steps = 19 01:22:51 [INFO] train episode 1558: reward = -118.36, steps = 19 01:22:52 [INFO] train episode 1559: reward = -81.09, steps = 18 01:22:54 [INFO] train episode 1560: reward = -110.04, steps = 20 01:22:56 [INFO] train episode 1561: reward = -110.90, steps = 20 01:22:58 [INFO] train episode 1562: reward = -110.69, steps = 19 01:23:00 [INFO] train episode 1563: reward = -106.10, steps = 25 01:23:02 [INFO] train episode 1564: reward = -114.58, steps = 19 01:23:04 [INFO] train episode 1565: reward = -76.14, steps = 22 01:23:06 [INFO] train episode 1566: reward = -121.15, steps = 18 01:23:08 [INFO] train episode 1567: reward = -92.96, steps = 18 01:23:09 [INFO] train episode 1568: reward = -84.89, steps = 20 01:23:12 [INFO] train episode 1569: reward = -93.69, steps = 27 01:23:14 [INFO] train episode 1570: reward = -100.24, steps = 19 01:23:15 [INFO] train episode 1571: reward = -112.07, steps = 19 01:23:18 [INFO] train episode 1572: reward = -136.09, steps = 23 01:23:19 [INFO] train episode 1573: reward = -66.97, steps = 19 01:23:21 [INFO] train episode 1574: reward = -129.02, steps = 20 01:23:24 [INFO] train episode 1575: reward = -100.73, steps = 20 01:23:26 [INFO] train episode 1576: reward = -122.27, steps = 18 01:23:28 [INFO] train episode 1577: reward = -105.32, steps = 19 01:23:30 [INFO] train episode 1578: reward = -94.89, steps = 21 01:23:32 [INFO] train episode 1579: reward = -93.69, steps = 19 01:23:34 [INFO] train episode 1580: reward = -130.51, steps = 21 01:23:36 [INFO] train episode 1581: reward = -94.58, steps = 19 01:23:38 [INFO] train episode 1582: reward = -75.84, steps = 19 01:23:39 [INFO] train episode 1583: reward = -86.35, steps = 19 01:23:42 [INFO] train episode 1584: reward = -82.87, steps = 18 01:23:44 [INFO] train episode 1585: reward = -166.61, steps = 28 01:23:46 [INFO] train episode 1586: reward = -115.81, steps = 20 01:23:48 [INFO] train episode 1587: reward = -85.17, steps = 19 01:23:50 [INFO] train episode 1588: reward = -96.03, steps = 19 01:23:52 [INFO] train episode 1589: reward = -103.54, steps = 26 01:23:54 [INFO] train episode 1590: reward = -187.49, steps = 19 01:23:56 [INFO] train episode 1591: reward = -101.10, steps = 19 01:23:57 [INFO] train episode 1592: reward = -115.34, steps = 20 01:24:00 [INFO] train episode 1593: reward = -140.99, steps = 22 01:24:01 [INFO] train episode 1594: reward = -88.57, steps = 18 01:24:03 [INFO] train episode 1595: reward = -79.66, steps = 18 01:24:05 [INFO] train episode 1596: reward = -136.47, steps = 22 01:24:08 [INFO] train episode 1597: reward = -120.02, steps = 29 01:24:09 [INFO] train episode 1598: reward = -104.83, steps = 20 01:24:11 [INFO] train episode 1599: reward = -101.99, steps = 18 01:24:13 [INFO] train episode 1600: reward = -94.26, steps = 20 01:24:15 [INFO] train episode 1601: reward = -126.99, steps = 19 01:24:17 [INFO] train episode 1602: reward = -115.34, steps = 19 01:24:20 [INFO] train episode 1603: reward = -154.98, steps = 30 01:24:22 [INFO] train episode 1604: reward = -114.05, steps = 20 01:24:24 [INFO] train episode 1605: reward = -90.93, steps = 19 01:24:25 [INFO] train episode 1606: reward = -99.67, steps = 20 01:24:27 [INFO] train episode 1607: reward = -97.79, steps = 18 01:24:29 [INFO] train episode 1608: reward = -110.22, steps = 21 01:24:31 [INFO] train episode 1609: reward = -109.44, steps = 19 01:24:33 [INFO] train episode 1610: reward = -129.04, steps = 19 01:24:35 [INFO] train episode 1611: reward = -98.26, steps = 19 01:24:36 [INFO] train episode 1612: reward = -79.53, steps = 18 01:24:38 [INFO] train episode 1613: reward = -126.26, steps = 19 01:24:40 [INFO] train episode 1614: reward = -94.47, steps = 19 01:24:42 [INFO] train episode 1615: reward = -119.87, steps = 19 01:24:44 [INFO] train episode 1616: reward = -104.72, steps = 18 01:24:46 [INFO] train episode 1617: reward = -116.62, steps = 22 01:24:47 [INFO] train episode 1618: reward = -76.19, steps = 21 01:24:50 [INFO] train episode 1619: reward = -90.99, steps = 19 01:24:51 [INFO] train episode 1620: reward = -129.21, steps = 18 01:24:53 [INFO] train episode 1621: reward = -104.28, steps = 19 01:24:55 [INFO] train episode 1622: reward = -101.40, steps = 19 01:24:57 [INFO] train episode 1623: reward = -115.01, steps = 19 01:24:58 [INFO] train episode 1624: reward = -83.24, steps = 19 01:25:00 [INFO] train episode 1625: reward = -76.35, steps = 19 01:25:02 [INFO] train episode 1626: reward = -100.66, steps = 20 01:25:04 [INFO] train episode 1627: reward = -149.40, steps = 19 01:25:06 [INFO] train episode 1628: reward = -112.40, steps = 19 01:25:08 [INFO] train episode 1629: reward = -106.30, steps = 19 01:25:09 [INFO] train episode 1630: reward = -83.74, steps = 17 01:25:11 [INFO] train episode 1631: reward = -116.19, steps = 19 01:25:14 [INFO] train episode 1632: reward = -106.86, steps = 20 01:25:16 [INFO] train episode 1633: reward = -100.74, steps = 19 01:25:17 [INFO] train episode 1634: reward = -112.90, steps = 17 01:25:19 [INFO] train episode 1635: reward = -121.81, steps = 20 01:25:21 [INFO] train episode 1636: reward = -117.23, steps = 22 01:25:23 [INFO] train episode 1637: reward = -87.13, steps = 20 01:25:25 [INFO] train episode 1638: reward = -103.19, steps = 19 01:25:27 [INFO] train episode 1639: reward = -95.36, steps = 18 01:25:29 [INFO] train episode 1640: reward = -136.09, steps = 24 01:25:31 [INFO] train episode 1641: reward = -119.52, steps = 21 01:25:33 [INFO] train episode 1642: reward = -107.51, steps = 18 01:25:34 [INFO] train episode 1643: reward = -129.44, steps = 17 01:25:37 [INFO] train episode 1644: reward = -92.76, steps = 25 01:25:39 [INFO] train episode 1645: reward = -59.53, steps = 19 01:25:41 [INFO] train episode 1646: reward = -89.28, steps = 19 01:25:43 [INFO] train episode 1647: reward = -115.00, steps = 18 01:25:45 [INFO] train episode 1648: reward = -109.91, steps = 19 01:25:47 [INFO] train episode 1649: reward = -106.35, steps = 20 01:25:48 [INFO] train episode 1650: reward = -68.34, steps = 19 01:25:51 [INFO] train episode 1651: reward = -122.87, steps = 25 01:25:53 [INFO] train episode 1652: reward = -106.03, steps = 19 01:25:54 [INFO] train episode 1653: reward = -86.31, steps = 19 01:25:56 [INFO] train episode 1654: reward = -111.02, steps = 19 01:25:58 [INFO] train episode 1655: reward = -88.04, steps = 19 01:26:00 [INFO] train episode 1656: reward = -106.04, steps = 19 01:26:02 [INFO] train episode 1657: reward = -100.65, steps = 23 01:26:04 [INFO] train episode 1658: reward = -104.70, steps = 17 01:26:06 [INFO] train episode 1659: reward = -100.71, steps = 23 01:26:08 [INFO] train episode 1660: reward = -109.67, steps = 19 01:26:10 [INFO] train episode 1661: reward = -117.79, steps = 27 01:26:12 [INFO] train episode 1662: reward = -84.48, steps = 20 01:26:14 [INFO] train episode 1663: reward = -69.10, steps = 19 01:26:16 [INFO] train episode 1664: reward = -99.96, steps = 19 01:26:18 [INFO] train episode 1665: reward = -107.81, steps = 20 01:26:20 [INFO] train episode 1666: reward = -112.77, steps = 19 01:26:22 [INFO] train episode 1667: reward = -95.31, steps = 18 01:26:23 [INFO] train episode 1668: reward = -83.47, steps = 19 01:26:25 [INFO] train episode 1669: reward = -106.78, steps = 22 01:26:28 [INFO] train episode 1670: reward = -110.73, steps = 23 01:26:29 [INFO] train episode 1671: reward = -90.52, steps = 18 01:26:31 [INFO] train episode 1672: reward = -103.60, steps = 17 01:26:34 [INFO] train episode 1673: reward = -123.10, steps = 20 01:26:36 [INFO] train episode 1674: reward = -112.07, steps = 19 01:26:37 [INFO] train episode 1675: reward = -115.49, steps = 19 01:26:39 [INFO] train episode 1676: reward = -110.32, steps = 19 01:26:41 [INFO] train episode 1677: reward = -104.50, steps = 21 01:26:43 [INFO] train episode 1678: reward = -72.50, steps = 19 01:26:45 [INFO] train episode 1679: reward = -80.22, steps = 19 01:26:47 [INFO] train episode 1680: reward = -104.44, steps = 21 01:26:49 [INFO] train episode 1681: reward = -92.43, steps = 16 01:26:51 [INFO] train episode 1682: reward = -91.43, steps = 20 01:26:53 [INFO] train episode 1683: reward = -97.68, steps = 18 01:26:54 [INFO] train episode 1684: reward = -125.01, steps = 19 01:26:56 [INFO] train episode 1685: reward = -90.92, steps = 19 01:26:58 [INFO] train episode 1686: reward = -110.71, steps = 20 01:27:00 [INFO] train episode 1687: reward = -79.02, steps = 19 01:27:02 [INFO] train episode 1688: reward = -100.07, steps = 19 01:27:03 [INFO] train episode 1689: reward = -96.02, steps = 19 01:27:05 [INFO] train episode 1690: reward = -79.52, steps = 20 01:27:07 [INFO] train episode 1691: reward = -111.80, steps = 17 01:27:09 [INFO] train episode 1692: reward = -166.05, steps = 20 01:27:11 [INFO] train episode 1693: reward = -92.94, steps = 19 01:27:13 [INFO] train episode 1694: reward = -100.45, steps = 19 01:27:15 [INFO] train episode 1695: reward = -111.21, steps = 19 01:27:17 [INFO] train episode 1696: reward = -70.48, steps = 23 01:27:19 [INFO] train episode 1697: reward = -95.62, steps = 19 01:27:22 [INFO] train episode 1698: reward = -119.90, steps = 25 01:27:23 [INFO] train episode 1699: reward = -71.80, steps = 19 01:27:26 [INFO] train episode 1700: reward = -104.82, steps = 25 01:27:28 [INFO] train episode 1701: reward = -93.70, steps = 18 01:27:30 [INFO] train episode 1702: reward = -126.13, steps = 24 01:27:32 [INFO] train episode 1703: reward = -150.26, steps = 20 01:27:34 [INFO] train episode 1704: reward = -100.59, steps = 19 01:27:36 [INFO] train episode 1705: reward = -123.40, steps = 18 01:27:37 [INFO] train episode 1706: reward = -92.93, steps = 19 01:27:40 [INFO] train episode 1707: reward = -111.29, steps = 27 01:27:42 [INFO] train episode 1708: reward = -111.96, steps = 19 01:27:45 [INFO] train episode 1709: reward = -156.89, steps = 30 01:27:47 [INFO] train episode 1710: reward = -80.27, steps = 19 01:27:49 [INFO] train episode 1711: reward = -55.32, steps = 18 01:27:51 [INFO] train episode 1712: reward = -103.49, steps = 21 01:27:53 [INFO] train episode 1713: reward = -152.51, steps = 21 01:27:55 [INFO] train episode 1714: reward = -105.59, steps = 24 01:27:58 [INFO] train episode 1715: reward = -100.14, steps = 21 01:28:00 [INFO] train episode 1716: reward = -157.60, steps = 20 01:28:02 [INFO] train episode 1717: reward = -115.14, steps = 17 01:28:04 [INFO] train episode 1718: reward = -103.52, steps = 20 01:28:05 [INFO] train episode 1719: reward = -106.47, steps = 19 01:28:07 [INFO] train episode 1720: reward = -124.07, steps = 19 01:28:09 [INFO] train episode 1721: reward = -83.82, steps = 19 01:28:11 [INFO] train episode 1722: reward = -94.97, steps = 20 01:28:13 [INFO] train episode 1723: reward = -104.93, steps = 21 01:28:14 [INFO] train episode 1724: reward = -136.26, steps = 19 01:28:16 [INFO] train episode 1725: reward = -76.91, steps = 18 01:28:19 [INFO] train episode 1726: reward = -107.67, steps = 23 01:28:20 [INFO] train episode 1727: reward = -90.19, steps = 19 01:28:23 [INFO] train episode 1728: reward = -119.03, steps = 24 01:28:25 [INFO] train episode 1729: reward = -97.97, steps = 20 01:28:27 [INFO] train episode 1730: reward = -112.04, steps = 19 01:28:29 [INFO] train episode 1731: reward = -97.41, steps = 19 01:28:30 [INFO] train episode 1732: reward = -122.21, steps = 19 01:28:33 [INFO] train episode 1733: reward = -147.52, steps = 19 01:28:35 [INFO] train episode 1734: reward = -86.48, steps = 19 01:28:37 [INFO] train episode 1735: reward = -77.66, steps = 19 01:28:39 [INFO] train episode 1736: reward = -100.02, steps = 21 01:28:41 [INFO] train episode 1737: reward = -111.10, steps = 20 01:28:43 [INFO] train episode 1738: reward = -146.52, steps = 19 01:28:45 [INFO] train episode 1739: reward = -83.48, steps = 19 01:28:46 [INFO] train episode 1740: reward = -102.36, steps = 20 01:28:48 [INFO] train episode 1741: reward = -94.23, steps = 20 01:28:50 [INFO] train episode 1742: reward = -107.36, steps = 19 01:28:52 [INFO] train episode 1743: reward = -156.53, steps = 20 01:28:54 [INFO] train episode 1744: reward = -119.97, steps = 16 01:28:56 [INFO] train episode 1745: reward = -115.42, steps = 23 01:28:57 [INFO] train episode 1746: reward = -112.93, steps = 19 01:28:59 [INFO] train episode 1747: reward = -101.41, steps = 20 01:29:02 [INFO] train episode 1748: reward = -116.01, steps = 29 01:29:04 [INFO] train episode 1749: reward = -91.87, steps = 22 01:29:06 [INFO] train episode 1750: reward = -103.86, steps = 19 01:29:08 [INFO] train episode 1751: reward = -150.28, steps = 20 01:29:10 [INFO] train episode 1752: reward = -89.92, steps = 19 01:29:12 [INFO] train episode 1753: reward = -113.86, steps = 20 01:29:14 [INFO] train episode 1754: reward = -143.81, steps = 23 01:29:15 [INFO] train episode 1755: reward = -97.64, steps = 19 01:29:17 [INFO] train episode 1756: reward = -74.89, steps = 21 01:29:19 [INFO] train episode 1757: reward = -116.21, steps = 18 01:29:21 [INFO] train episode 1758: reward = -84.89, steps = 20 01:29:23 [INFO] train episode 1759: reward = -129.08, steps = 22 01:29:24 [INFO] train episode 1760: reward = -134.26, steps = 19 01:29:26 [INFO] train episode 1761: reward = -90.76, steps = 16 01:29:28 [INFO] train episode 1762: reward = -91.93, steps = 20 01:29:30 [INFO] train episode 1763: reward = -118.94, steps = 22 01:29:32 [INFO] train episode 1764: reward = -105.90, steps = 19 01:29:34 [INFO] train episode 1765: reward = -131.72, steps = 25 01:29:36 [INFO] train episode 1766: reward = -83.14, steps = 18 01:29:38 [INFO] train episode 1767: reward = -87.88, steps = 19 01:29:40 [INFO] train episode 1768: reward = -121.51, steps = 24 01:29:42 [INFO] train episode 1769: reward = -115.84, steps = 22 01:29:45 [INFO] train episode 1770: reward = -141.53, steps = 28 01:29:46 [INFO] train episode 1771: reward = -65.84, steps = 20 01:29:48 [INFO] train episode 1772: reward = -117.97, steps = 19 01:29:50 [INFO] train episode 1773: reward = -99.96, steps = 20 01:29:52 [INFO] train episode 1774: reward = -98.81, steps = 19 01:29:54 [INFO] train episode 1775: reward = -128.57, steps = 19 01:29:55 [INFO] train episode 1776: reward = -121.51, steps = 18 01:29:57 [INFO] train episode 1777: reward = -113.65, steps = 18 01:29:59 [INFO] train episode 1778: reward = -106.26, steps = 21 01:30:01 [INFO] train episode 1779: reward = -105.86, steps = 18 01:30:03 [INFO] train episode 1780: reward = -109.14, steps = 20 01:30:05 [INFO] train episode 1781: reward = -76.55, steps = 19 01:30:06 [INFO] train episode 1782: reward = -101.20, steps = 19 01:30:08 [INFO] train episode 1783: reward = -106.79, steps = 20 01:30:10 [INFO] train episode 1784: reward = -87.86, steps = 21 01:30:12 [INFO] train episode 1785: reward = -90.17, steps = 22 01:30:14 [INFO] train episode 1786: reward = -101.82, steps = 19 01:30:16 [INFO] train episode 1787: reward = -87.41, steps = 21 01:30:18 [INFO] train episode 1788: reward = -103.16, steps = 20 01:30:20 [INFO] train episode 1789: reward = -121.47, steps = 19 01:30:21 [INFO] train episode 1790: reward = -69.66, steps = 16 01:30:23 [INFO] train episode 1791: reward = -165.87, steps = 18 01:30:24 [INFO] train episode 1792: reward = -81.11, steps = 17 01:30:26 [INFO] train episode 1793: reward = -113.89, steps = 22 01:30:29 [INFO] train episode 1794: reward = -107.08, steps = 23 01:30:30 [INFO] train episode 1795: reward = -107.29, steps = 18 01:30:32 [INFO] train episode 1796: reward = -87.65, steps = 19 01:30:34 [INFO] train episode 1797: reward = -123.63, steps = 21 01:30:36 [INFO] train episode 1798: reward = -117.25, steps = 19 01:30:38 [INFO] train episode 1799: reward = -59.69, steps = 19 01:30:40 [INFO] train episode 1800: reward = -107.79, steps = 19 01:30:41 [INFO] train episode 1801: reward = -82.41, steps = 18 01:30:43 [INFO] train episode 1802: reward = -114.92, steps = 21 01:30:45 [INFO] train episode 1803: reward = -101.82, steps = 21 01:30:47 [INFO] train episode 1804: reward = -124.04, steps = 19 01:30:49 [INFO] train episode 1805: reward = -95.53, steps = 19 01:30:51 [INFO] train episode 1806: reward = -87.45, steps = 19 01:30:52 [INFO] train episode 1807: reward = -138.87, steps = 19 01:30:55 [INFO] train episode 1808: reward = -92.49, steps = 20 01:30:57 [INFO] train episode 1809: reward = -76.26, steps = 19 01:30:59 [INFO] train episode 1810: reward = -125.83, steps = 19 01:31:01 [INFO] train episode 1811: reward = -87.48, steps = 20 01:31:03 [INFO] train episode 1812: reward = -104.12, steps = 19 01:31:04 [INFO] train episode 1813: reward = -93.19, steps = 19 01:31:06 [INFO] train episode 1814: reward = -120.40, steps = 18 01:31:08 [INFO] train episode 1815: reward = -105.32, steps = 20 01:31:10 [INFO] train episode 1816: reward = -99.17, steps = 20 01:31:12 [INFO] train episode 1817: reward = -93.63, steps = 20 01:31:14 [INFO] train episode 1818: reward = -139.33, steps = 21 01:31:15 [INFO] train episode 1819: reward = -143.24, steps = 19 01:31:17 [INFO] train episode 1820: reward = -105.17, steps = 13 01:31:19 [INFO] train episode 1821: reward = -130.61, steps = 20 01:31:20 [INFO] train episode 1822: reward = -120.96, steps = 19 01:31:22 [INFO] train episode 1823: reward = -98.39, steps = 20 01:31:25 [INFO] train episode 1824: reward = -87.45, steps = 19 01:31:28 [INFO] train episode 1825: reward = -96.46, steps = 17 01:31:29 [INFO] train episode 1826: reward = -148.62, steps = 18 01:31:32 [INFO] train episode 1827: reward = -98.67, steps = 23 01:31:33 [INFO] train episode 1828: reward = -127.84, steps = 19 01:31:35 [INFO] train episode 1829: reward = -94.92, steps = 20 01:31:38 [INFO] train episode 1830: reward = -128.52, steps = 28 01:31:40 [INFO] train episode 1831: reward = -108.63, steps = 19 01:31:42 [INFO] train episode 1832: reward = -85.01, steps = 22 01:31:44 [INFO] train episode 1833: reward = -96.27, steps = 19 01:31:45 [INFO] train episode 1834: reward = -128.05, steps = 20 01:31:47 [INFO] train episode 1835: reward = -122.70, steps = 18 01:31:49 [INFO] train episode 1836: reward = -139.98, steps = 18 01:31:51 [INFO] train episode 1837: reward = -106.87, steps = 23 01:31:53 [INFO] train episode 1838: reward = -68.89, steps = 19 01:31:55 [INFO] train episode 1839: reward = -124.58, steps = 20 01:31:57 [INFO] train episode 1840: reward = -116.59, steps = 20 01:31:59 [INFO] train episode 1841: reward = -138.18, steps = 21 01:32:01 [INFO] train episode 1842: reward = -101.48, steps = 22 01:32:03 [INFO] train episode 1843: reward = -76.53, steps = 19 01:32:04 [INFO] train episode 1844: reward = -95.30, steps = 21 01:32:07 [INFO] train episode 1845: reward = -233.31, steps = 32 01:32:09 [INFO] train episode 1846: reward = -103.34, steps = 16 01:32:11 [INFO] train episode 1847: reward = -115.96, steps = 19 01:32:13 [INFO] train episode 1848: reward = -137.64, steps = 19 01:32:16 [INFO] train episode 1849: reward = -180.37, steps = 26 01:32:18 [INFO] train episode 1850: reward = -84.90, steps = 20 01:32:20 [INFO] train episode 1851: reward = -94.54, steps = 23 01:32:22 [INFO] train episode 1852: reward = -109.38, steps = 18 01:32:24 [INFO] train episode 1853: reward = -128.75, steps = 20 01:32:26 [INFO] train episode 1854: reward = -126.39, steps = 21 01:32:29 [INFO] train episode 1855: reward = -157.44, steps = 33 01:32:31 [INFO] train episode 1856: reward = -121.33, steps = 19 01:32:34 [INFO] train episode 1857: reward = -128.14, steps = 24 01:32:36 [INFO] train episode 1858: reward = -135.73, steps = 22 01:32:38 [INFO] train episode 1859: reward = -126.42, steps = 21 01:32:41 [INFO] train episode 1860: reward = -117.67, steps = 21 01:32:43 [INFO] train episode 1861: reward = -114.33, steps = 26 01:32:45 [INFO] train episode 1862: reward = -132.04, steps = 19 01:32:47 [INFO] train episode 1863: reward = -92.51, steps = 19 01:32:49 [INFO] train episode 1864: reward = -97.79, steps = 19 01:32:51 [INFO] train episode 1865: reward = -117.14, steps = 20 01:32:54 [INFO] train episode 1866: reward = -85.57, steps = 19 01:32:55 [INFO] train episode 1867: reward = -133.75, steps = 18 01:32:58 [INFO] train episode 1868: reward = -130.09, steps = 29 01:33:00 [INFO] train episode 1869: reward = -98.85, steps = 18 01:33:02 [INFO] train episode 1870: reward = -95.20, steps = 22 01:33:04 [INFO] train episode 1871: reward = -171.17, steps = 21 01:33:06 [INFO] train episode 1872: reward = -111.85, steps = 19 01:33:08 [INFO] train episode 1873: reward = -73.55, steps = 19 01:33:10 [INFO] train episode 1874: reward = -89.69, steps = 20 01:33:12 [INFO] train episode 1875: reward = -117.46, steps = 19 01:33:14 [INFO] train episode 1876: reward = -86.74, steps = 21 01:33:16 [INFO] train episode 1877: reward = -138.92, steps = 20 01:33:18 [INFO] train episode 1878: reward = -120.34, steps = 18 01:33:20 [INFO] train episode 1879: reward = -137.63, steps = 20 01:33:22 [INFO] train episode 1880: reward = -152.73, steps = 28 01:33:24 [INFO] train episode 1881: reward = -132.76, steps = 19 01:33:26 [INFO] train episode 1882: reward = -121.20, steps = 19 01:33:28 [INFO] train episode 1883: reward = -118.66, steps = 19 01:33:30 [INFO] train episode 1884: reward = -86.16, steps = 19 01:33:31 [INFO] train episode 1885: reward = -127.96, steps = 18 01:33:33 [INFO] train episode 1886: reward = -89.22, steps = 18 01:33:35 [INFO] train episode 1887: reward = -115.26, steps = 21 01:33:37 [INFO] train episode 1888: reward = -86.41, steps = 19 01:33:38 [INFO] train episode 1889: reward = -94.59, steps = 18 01:33:40 [INFO] train episode 1890: reward = -115.69, steps = 18 01:33:42 [INFO] train episode 1891: reward = -115.19, steps = 20 01:33:43 [INFO] train episode 1892: reward = -99.90, steps = 17 01:33:45 [INFO] train episode 1893: reward = -123.64, steps = 19 01:33:47 [INFO] train episode 1894: reward = -139.02, steps = 20 01:33:49 [INFO] train episode 1895: reward = -106.19, steps = 19 01:33:51 [INFO] train episode 1896: reward = -130.86, steps = 20 01:33:53 [INFO] train episode 1897: reward = -96.07, steps = 21 01:33:54 [INFO] train episode 1898: reward = -83.12, steps = 18 01:33:56 [INFO] train episode 1899: reward = -119.32, steps = 19 01:33:58 [INFO] train episode 1900: reward = -88.62, steps = 18 01:34:00 [INFO] train episode 1901: reward = -96.57, steps = 25 01:34:02 [INFO] train episode 1902: reward = -97.11, steps = 19 01:34:04 [INFO] train episode 1903: reward = -77.38, steps = 20 01:34:05 [INFO] train episode 1904: reward = -126.63, steps = 19 01:34:07 [INFO] train episode 1905: reward = -105.85, steps = 19 01:34:09 [INFO] train episode 1906: reward = -107.19, steps = 19 01:34:11 [INFO] train episode 1907: reward = -122.02, steps = 20 01:34:13 [INFO] train episode 1908: reward = -108.51, steps = 19 01:34:15 [INFO] train episode 1909: reward = -87.73, steps = 20 01:34:17 [INFO] train episode 1910: reward = -93.71, steps = 18 01:34:19 [INFO] train episode 1911: reward = -123.52, steps = 18 01:34:21 [INFO] train episode 1912: reward = -101.72, steps = 19 01:34:22 [INFO] train episode 1913: reward = -85.38, steps = 19 01:34:24 [INFO] train episode 1914: reward = -151.94, steps = 25 01:34:26 [INFO] train episode 1915: reward = -95.17, steps = 19 01:34:28 [INFO] train episode 1916: reward = -135.70, steps = 19 01:34:30 [INFO] train episode 1917: reward = -119.58, steps = 19 01:34:32 [INFO] train episode 1918: reward = -42.88, steps = 16 01:34:36 [INFO] train episode 1919: reward = -102.01, steps = 27 01:34:38 [INFO] train episode 1920: reward = -119.44, steps = 20 01:34:40 [INFO] train episode 1921: reward = -97.84, steps = 20 01:34:41 [INFO] train episode 1922: reward = -116.17, steps = 20 01:34:43 [INFO] train episode 1923: reward = -99.02, steps = 21 01:34:45 [INFO] train episode 1924: reward = -97.37, steps = 19 01:34:48 [INFO] train episode 1925: reward = -168.84, steps = 34 01:34:50 [INFO] train episode 1926: reward = -133.34, steps = 17 01:34:52 [INFO] train episode 1927: reward = -90.46, steps = 19 01:34:54 [INFO] train episode 1928: reward = -111.45, steps = 19 01:34:56 [INFO] train episode 1929: reward = -116.00, steps = 19 01:34:58 [INFO] train episode 1930: reward = -110.19, steps = 19 01:35:00 [INFO] train episode 1931: reward = -105.49, steps = 22 01:35:02 [INFO] train episode 1932: reward = -102.39, steps = 19 01:35:04 [INFO] train episode 1933: reward = -126.12, steps = 19 01:35:05 [INFO] train episode 1934: reward = -126.74, steps = 19 01:35:08 [INFO] train episode 1935: reward = -124.77, steps = 27 01:35:10 [INFO] train episode 1936: reward = -92.96, steps = 20 01:35:13 [INFO] train episode 1937: reward = -137.32, steps = 30 01:35:15 [INFO] train episode 1938: reward = -131.32, steps = 19 01:35:17 [INFO] train episode 1939: reward = -113.33, steps = 23 01:35:19 [INFO] train episode 1940: reward = -116.98, steps = 21 01:35:21 [INFO] train episode 1941: reward = -107.43, steps = 26 01:35:23 [INFO] train episode 1942: reward = -137.72, steps = 20 01:35:25 [INFO] train episode 1943: reward = -124.86, steps = 19 01:35:27 [INFO] train episode 1944: reward = -105.18, steps = 20 01:35:29 [INFO] train episode 1945: reward = -103.78, steps = 20 01:35:31 [INFO] train episode 1946: reward = -93.97, steps = 19 01:35:33 [INFO] train episode 1947: reward = -98.31, steps = 19 01:35:35 [INFO] train episode 1948: reward = -125.35, steps = 19 01:35:37 [INFO] train episode 1949: reward = -97.17, steps = 18 01:35:39 [INFO] train episode 1950: reward = -96.95, steps = 20 01:35:41 [INFO] train episode 1951: reward = -132.79, steps = 26 01:35:43 [INFO] train episode 1952: reward = -130.78, steps = 21 01:35:45 [INFO] train episode 1953: reward = -92.50, steps = 19 01:35:47 [INFO] train episode 1954: reward = -98.37, steps = 18 01:35:49 [INFO] train episode 1955: reward = -75.64, steps = 19 01:35:51 [INFO] train episode 1956: reward = -145.03, steps = 21 01:35:53 [INFO] train episode 1957: reward = -118.40, steps = 19 01:35:55 [INFO] train episode 1958: reward = -153.97, steps = 20 01:35:57 [INFO] train episode 1959: reward = -97.27, steps = 22 01:35:59 [INFO] train episode 1960: reward = -128.03, steps = 20 01:36:00 [INFO] train episode 1961: reward = -108.03, steps = 19 01:36:03 [INFO] train episode 1962: reward = -95.68, steps = 19 01:36:04 [INFO] train episode 1963: reward = -79.07, steps = 19 01:36:06 [INFO] train episode 1964: reward = -84.44, steps = 20 01:36:08 [INFO] train episode 1965: reward = -94.96, steps = 21 01:36:12 [INFO] train episode 1966: reward = -177.20, steps = 39 01:36:13 [INFO] train episode 1967: reward = -106.08, steps = 19 01:36:15 [INFO] train episode 1968: reward = -108.01, steps = 20 01:36:17 [INFO] train episode 1969: reward = -120.44, steps = 20 01:36:19 [INFO] train episode 1970: reward = -95.40, steps = 20 01:36:21 [INFO] train episode 1971: reward = -77.09, steps = 18 01:36:23 [INFO] train episode 1972: reward = -120.46, steps = 23 01:36:25 [INFO] train episode 1973: reward = -94.27, steps = 18 01:36:26 [INFO] train episode 1974: reward = -119.21, steps = 19 01:36:28 [INFO] train episode 1975: reward = -130.83, steps = 20 01:36:30 [INFO] train episode 1976: reward = -86.14, steps = 19 01:36:32 [INFO] train episode 1977: reward = -142.77, steps = 19 01:36:33 [INFO] train episode 1978: reward = -67.53, steps = 19 01:36:36 [INFO] train episode 1979: reward = -96.89, steps = 20 01:36:37 [INFO] train episode 1980: reward = -97.06, steps = 19 01:36:39 [INFO] train episode 1981: reward = -121.91, steps = 19 01:36:41 [INFO] train episode 1982: reward = -105.43, steps = 19 01:36:43 [INFO] train episode 1983: reward = -192.08, steps = 28 01:36:45 [INFO] train episode 1984: reward = -73.80, steps = 19 01:36:47 [INFO] train episode 1985: reward = -111.19, steps = 24 01:36:49 [INFO] train episode 1986: reward = -145.00, steps = 26 01:36:51 [INFO] train episode 1987: reward = -88.70, steps = 18 01:36:53 [INFO] train episode 1988: reward = -102.19, steps = 20 01:36:55 [INFO] train episode 1989: reward = -113.43, steps = 20 01:36:57 [INFO] train episode 1990: reward = -102.54, steps = 21 01:36:59 [INFO] train episode 1991: reward = -129.29, steps = 17 01:37:01 [INFO] train episode 1992: reward = -86.70, steps = 21 01:37:03 [INFO] train episode 1993: reward = -128.13, steps = 19 01:37:05 [INFO] train episode 1994: reward = -115.44, steps = 19 01:37:07 [INFO] train episode 1995: reward = -97.33, steps = 19 01:37:08 [INFO] train episode 1996: reward = -119.31, steps = 19 01:37:11 [INFO] train episode 1997: reward = -114.15, steps = 19 01:37:13 [INFO] train episode 1998: reward = -139.13, steps = 27 01:37:16 [INFO] train episode 1999: reward = -135.44, steps = 25 01:37:18 [INFO] train episode 2000: reward = -110.62, steps = 19 01:37:20 [INFO] train episode 2001: reward = -86.34, steps = 20 01:37:22 [INFO] train episode 2002: reward = -174.90, steps = 20 01:37:24 [INFO] train episode 2003: reward = -112.49, steps = 20 01:37:26 [INFO] train episode 2004: reward = -124.66, steps = 19 01:37:28 [INFO] train episode 2005: reward = -106.79, steps = 20 01:37:30 [INFO] train episode 2006: reward = -68.65, steps = 19 01:37:32 [INFO] train episode 2007: reward = -136.31, steps = 25 01:37:34 [INFO] train episode 2008: reward = -110.22, steps = 20 01:37:36 [INFO] train episode 2009: reward = -84.31, steps = 18 01:37:39 [INFO] train episode 2010: reward = -131.21, steps = 21 01:37:43 [INFO] train episode 2011: reward = -127.51, steps = 30 01:37:45 [INFO] train episode 2012: reward = -127.65, steps = 23 01:37:47 [INFO] train episode 2013: reward = -86.62, steps = 19 01:37:49 [INFO] train episode 2014: reward = -85.44, steps = 20 01:37:51 [INFO] train episode 2015: reward = -108.56, steps = 19 01:37:53 [INFO] train episode 2016: reward = -76.29, steps = 19 01:37:56 [INFO] train episode 2017: reward = -132.94, steps = 25 01:37:58 [INFO] train episode 2018: reward = -84.86, steps = 19 01:37:59 [INFO] train episode 2019: reward = -50.15, steps = 18 01:38:01 [INFO] train episode 2020: reward = -92.00, steps = 18 01:38:03 [INFO] train episode 2021: reward = -106.83, steps = 20 01:38:05 [INFO] train episode 2022: reward = -104.87, steps = 18 01:38:07 [INFO] train episode 2023: reward = -106.41, steps = 20 01:38:09 [INFO] train episode 2024: reward = -129.51, steps = 18 01:38:11 [INFO] train episode 2025: reward = -148.24, steps = 21 01:38:13 [INFO] train episode 2026: reward = -85.86, steps = 18 01:38:15 [INFO] train episode 2027: reward = -94.36, steps = 20 01:38:16 [INFO] train episode 2028: reward = -101.62, steps = 19 01:38:18 [INFO] train episode 2029: reward = -106.60, steps = 19 01:38:20 [INFO] train episode 2030: reward = -105.55, steps = 19 01:38:21 [INFO] train episode 2031: reward = -99.79, steps = 18 01:38:24 [INFO] train episode 2032: reward = -144.70, steps = 19 01:38:25 [INFO] train episode 2033: reward = -90.43, steps = 17 01:38:27 [INFO] train episode 2034: reward = -101.74, steps = 19 01:38:29 [INFO] train episode 2035: reward = -95.92, steps = 19 01:38:30 [INFO] train episode 2036: reward = -115.32, steps = 21 01:38:32 [INFO] train episode 2037: reward = -159.57, steps = 19 01:38:34 [INFO] train episode 2038: reward = -110.44, steps = 20 01:38:36 [INFO] train episode 2039: reward = -131.79, steps = 19 01:38:38 [INFO] train episode 2040: reward = -139.55, steps = 26 01:38:40 [INFO] train episode 2041: reward = -105.95, steps = 19 01:38:42 [INFO] train episode 2042: reward = -104.02, steps = 24 01:38:44 [INFO] train episode 2043: reward = -118.60, steps = 20 01:38:46 [INFO] train episode 2044: reward = -135.35, steps = 26 01:38:48 [INFO] train episode 2045: reward = -94.50, steps = 19 01:38:50 [INFO] train episode 2046: reward = -92.76, steps = 17 01:38:52 [INFO] train episode 2047: reward = -100.24, steps = 22 01:38:53 [INFO] train episode 2048: reward = -107.50, steps = 19 01:38:56 [INFO] train episode 2049: reward = -98.11, steps = 20 01:38:57 [INFO] train episode 2050: reward = -161.32, steps = 21 01:39:00 [INFO] train episode 2051: reward = -110.49, steps = 28 01:39:01 [INFO] train episode 2052: reward = -110.19, steps = 17 01:39:03 [INFO] train episode 2053: reward = -114.45, steps = 18 01:39:05 [INFO] train episode 2054: reward = -84.84, steps = 20 01:39:07 [INFO] train episode 2055: reward = -85.65, steps = 19 01:39:08 [INFO] train episode 2056: reward = -131.86, steps = 19 01:39:10 [INFO] train episode 2057: reward = -100.15, steps = 20 01:39:12 [INFO] train episode 2058: reward = -90.10, steps = 19 01:39:14 [INFO] train episode 2059: reward = -134.44, steps = 21 01:39:15 [INFO] train episode 2060: reward = -123.35, steps = 15 01:39:17 [INFO] train episode 2061: reward = -64.93, steps = 19 01:39:19 [INFO] train episode 2062: reward = -100.72, steps = 20 01:39:21 [INFO] train episode 2063: reward = -125.97, steps = 19 01:39:22 [INFO] train episode 2064: reward = -89.83, steps = 20 01:39:24 [INFO] train episode 2065: reward = -118.27, steps = 19 01:39:26 [INFO] train episode 2066: reward = -111.76, steps = 19 01:39:28 [INFO] train episode 2067: reward = -123.12, steps = 18 01:39:30 [INFO] train episode 2068: reward = -137.81, steps = 23 01:39:32 [INFO] train episode 2069: reward = -131.62, steps = 21 01:39:34 [INFO] train episode 2070: reward = -94.23, steps = 19 01:39:36 [INFO] train episode 2071: reward = -219.80, steps = 26 01:39:38 [INFO] train episode 2072: reward = -78.57, steps = 20 01:39:39 [INFO] train episode 2073: reward = -108.29, steps = 18 01:39:41 [INFO] train episode 2074: reward = -100.03, steps = 20 01:39:43 [INFO] train episode 2075: reward = -132.14, steps = 20 01:39:45 [INFO] train episode 2076: reward = -109.53, steps = 19 01:39:47 [INFO] train episode 2077: reward = -93.00, steps = 19 01:39:48 [INFO] train episode 2078: reward = -82.18, steps = 16 01:39:50 [INFO] train episode 2079: reward = -114.82, steps = 20 01:39:52 [INFO] train episode 2080: reward = -99.02, steps = 19 01:39:54 [INFO] train episode 2081: reward = -148.13, steps = 24 01:39:56 [INFO] train episode 2082: reward = -123.90, steps = 22 01:39:58 [INFO] train episode 2083: reward = -115.99, steps = 23 01:40:01 [INFO] train episode 2084: reward = -118.19, steps = 25 01:40:03 [INFO] train episode 2085: reward = -140.25, steps = 23 01:40:05 [INFO] train episode 2086: reward = -81.51, steps = 20 01:40:06 [INFO] train episode 2087: reward = -96.34, steps = 19 01:40:09 [INFO] train episode 2088: reward = -149.49, steps = 27 01:40:10 [INFO] train episode 2089: reward = -119.80, steps = 19 01:40:12 [INFO] train episode 2090: reward = -138.66, steps = 21 01:40:14 [INFO] train episode 2091: reward = -92.57, steps = 18 01:40:16 [INFO] train episode 2092: reward = -110.64, steps = 19 01:40:18 [INFO] train episode 2093: reward = -108.64, steps = 18 01:40:19 [INFO] train episode 2094: reward = -106.26, steps = 19 01:40:21 [INFO] train episode 2095: reward = -113.17, steps = 23 01:40:23 [INFO] train episode 2096: reward = -142.41, steps = 19 01:40:25 [INFO] train episode 2097: reward = -155.99, steps = 20 01:40:29 [INFO] train episode 2098: reward = -168.03, steps = 35 01:40:30 [INFO] train episode 2099: reward = -122.13, steps = 17 01:40:32 [INFO] train episode 2100: reward = -101.90, steps = 20 01:40:34 [INFO] train episode 2101: reward = -103.36, steps = 19 01:40:36 [INFO] train episode 2102: reward = -133.28, steps = 22 01:40:38 [INFO] train episode 2103: reward = -102.99, steps = 18 01:40:40 [INFO] train episode 2104: reward = -95.39, steps = 20 01:40:41 [INFO] train episode 2105: reward = -95.33, steps = 20 01:40:44 [INFO] train episode 2106: reward = -180.18, steps = 20 01:40:46 [INFO] train episode 2107: reward = -115.75, steps = 20 01:40:48 [INFO] train episode 2108: reward = -142.15, steps = 19 01:40:50 [INFO] train episode 2109: reward = -93.64, steps = 20 01:40:52 [INFO] train episode 2110: reward = -111.44, steps = 20 01:40:53 [INFO] train episode 2111: reward = -88.96, steps = 20 01:40:55 [INFO] train episode 2112: reward = -128.31, steps = 20 01:40:57 [INFO] train episode 2113: reward = -115.86, steps = 17 01:40:59 [INFO] train episode 2114: reward = -145.64, steps = 20 01:41:00 [INFO] train episode 2115: reward = -76.74, steps = 19 01:41:02 [INFO] train episode 2116: reward = -90.11, steps = 19 01:41:04 [INFO] train episode 2117: reward = -74.36, steps = 19 01:41:06 [INFO] train episode 2118: reward = -65.75, steps = 20 01:41:08 [INFO] train episode 2119: reward = -118.64, steps = 25 01:41:10 [INFO] train episode 2120: reward = -90.25, steps = 20 01:41:12 [INFO] train episode 2121: reward = -96.03, steps = 20 01:41:15 [INFO] train episode 2122: reward = -148.89, steps = 32 01:41:16 [INFO] train episode 2123: reward = -116.81, steps = 20 01:41:18 [INFO] train episode 2124: reward = -110.09, steps = 18 01:41:20 [INFO] train episode 2125: reward = -103.89, steps = 22 01:41:22 [INFO] train episode 2126: reward = -79.05, steps = 20 01:41:24 [INFO] train episode 2127: reward = -95.14, steps = 20 01:41:26 [INFO] train episode 2128: reward = -94.59, steps = 20 01:41:28 [INFO] train episode 2129: reward = -90.36, steps = 19 01:41:30 [INFO] train episode 2130: reward = -111.14, steps = 23 01:41:31 [INFO] train episode 2131: reward = -138.72, steps = 19 01:41:33 [INFO] train episode 2132: reward = -97.59, steps = 19 01:41:35 [INFO] train episode 2133: reward = -137.31, steps = 19 01:41:37 [INFO] train episode 2134: reward = -132.25, steps = 30 01:41:40 [INFO] train episode 2135: reward = -109.85, steps = 24 01:41:42 [INFO] train episode 2136: reward = -70.87, steps = 20 01:41:43 [INFO] train episode 2137: reward = -81.16, steps = 19 01:41:46 [INFO] train episode 2138: reward = -150.00, steps = 24 01:41:48 [INFO] train episode 2139: reward = -183.94, steps = 26 01:41:50 [INFO] train episode 2140: reward = -124.48, steps = 27 01:41:53 [INFO] train episode 2141: reward = -101.42, steps = 27 01:41:55 [INFO] train episode 2142: reward = -110.03, steps = 21 01:41:56 [INFO] train episode 2143: reward = -109.59, steps = 12 01:41:58 [INFO] train episode 2144: reward = -71.91, steps = 19 01:41:59 [INFO] train episode 2145: reward = -99.84, steps = 19 01:42:01 [INFO] train episode 2146: reward = -106.57, steps = 19 01:42:03 [INFO] train episode 2147: reward = -95.67, steps = 19 01:42:05 [INFO] train episode 2148: reward = -113.85, steps = 20 01:42:06 [INFO] train episode 2149: reward = -99.18, steps = 18 01:42:08 [INFO] train episode 2150: reward = -141.71, steps = 21 01:42:10 [INFO] train episode 2151: reward = -115.13, steps = 23 01:42:13 [INFO] train episode 2152: reward = -131.73, steps = 20 01:42:14 [INFO] train episode 2153: reward = -85.96, steps = 19 01:42:16 [INFO] train episode 2154: reward = -104.73, steps = 21 01:42:18 [INFO] train episode 2155: reward = -82.16, steps = 19 01:42:20 [INFO] train episode 2156: reward = -126.60, steps = 20 01:42:21 [INFO] train episode 2157: reward = -92.81, steps = 19 01:42:23 [INFO] train episode 2158: reward = -107.65, steps = 20 01:42:25 [INFO] train episode 2159: reward = -108.84, steps = 19 01:42:27 [INFO] train episode 2160: reward = -109.07, steps = 20 01:42:29 [INFO] train episode 2161: reward = -122.41, steps = 24 01:42:31 [INFO] train episode 2162: reward = -105.49, steps = 20 01:42:33 [INFO] train episode 2163: reward = -115.44, steps = 20 01:42:35 [INFO] train episode 2164: reward = -83.86, steps = 19 01:42:37 [INFO] train episode 2165: reward = -73.67, steps = 19 01:42:39 [INFO] train episode 2166: reward = -97.23, steps = 22 01:42:40 [INFO] train episode 2167: reward = -101.67, steps = 19 01:42:42 [INFO] train episode 2168: reward = -87.43, steps = 20 01:42:44 [INFO] train episode 2169: reward = -72.86, steps = 18 01:42:46 [INFO] train episode 2170: reward = -116.88, steps = 19 01:42:48 [INFO] train episode 2171: reward = -125.87, steps = 18 01:42:49 [INFO] train episode 2172: reward = -88.32, steps = 19 01:42:52 [INFO] train episode 2173: reward = -137.51, steps = 28 01:42:53 [INFO] train episode 2174: reward = -113.76, steps = 19 01:42:55 [INFO] train episode 2175: reward = -87.78, steps = 22 01:42:57 [INFO] train episode 2176: reward = -123.74, steps = 21 01:42:59 [INFO] train episode 2177: reward = -97.25, steps = 19 01:43:01 [INFO] train episode 2178: reward = -100.93, steps = 19 01:43:03 [INFO] train episode 2179: reward = -124.50, steps = 18 01:43:04 [INFO] train episode 2180: reward = -125.62, steps = 19 01:43:06 [INFO] train episode 2181: reward = -113.18, steps = 19 01:43:08 [INFO] train episode 2182: reward = -122.44, steps = 19 01:43:10 [INFO] train episode 2183: reward = -123.10, steps = 22 01:43:12 [INFO] train episode 2184: reward = -87.09, steps = 20 01:43:14 [INFO] train episode 2185: reward = -122.80, steps = 21 01:43:16 [INFO] train episode 2186: reward = -118.95, steps = 21 01:43:18 [INFO] train episode 2187: reward = -93.43, steps = 20 01:43:19 [INFO] train episode 2188: reward = -113.77, steps = 19 01:43:21 [INFO] train episode 2189: reward = -116.66, steps = 20 01:43:23 [INFO] train episode 2190: reward = -150.99, steps = 20 01:43:25 [INFO] train episode 2191: reward = -79.46, steps = 20 01:43:27 [INFO] train episode 2192: reward = -83.81, steps = 18 01:43:28 [INFO] train episode 2193: reward = -108.99, steps = 20 01:43:30 [INFO] train episode 2194: reward = -150.54, steps = 24 01:43:32 [INFO] train episode 2195: reward = -138.57, steps = 19 01:43:34 [INFO] train episode 2196: reward = -107.71, steps = 19 01:43:36 [INFO] train episode 2197: reward = -113.65, steps = 23 01:43:38 [INFO] train episode 2198: reward = -119.31, steps = 19 01:43:40 [INFO] train episode 2199: reward = -105.89, steps = 23 01:43:43 [INFO] train episode 2200: reward = -98.19, steps = 21 01:43:45 [INFO] train episode 2201: reward = -118.49, steps = 19 01:43:46 [INFO] train episode 2202: reward = -91.09, steps = 20 01:43:48 [INFO] train episode 2203: reward = -83.81, steps = 20 01:43:50 [INFO] train episode 2204: reward = -106.37, steps = 22 01:43:53 [INFO] train episode 2205: reward = -172.35, steps = 25 01:43:55 [INFO] train episode 2206: reward = -137.57, steps = 19 01:43:56 [INFO] train episode 2207: reward = -75.48, steps = 19 01:43:58 [INFO] train episode 2208: reward = -135.89, steps = 23 01:44:00 [INFO] train episode 2209: reward = -107.77, steps = 19 01:44:02 [INFO] train episode 2210: reward = -90.80, steps = 20 01:44:04 [INFO] train episode 2211: reward = -107.46, steps = 20 01:44:06 [INFO] train episode 2212: reward = -131.92, steps = 20 01:44:09 [INFO] train episode 2213: reward = -128.04, steps = 29 01:44:10 [INFO] train episode 2214: reward = -125.25, steps = 19 01:44:12 [INFO] train episode 2215: reward = -201.89, steps = 24 01:44:15 [INFO] train episode 2216: reward = -169.68, steps = 28 01:44:17 [INFO] train episode 2217: reward = -100.89, steps = 20 01:44:18 [INFO] train episode 2218: reward = -132.69, steps = 19 01:44:20 [INFO] train episode 2219: reward = -87.11, steps = 17 01:44:22 [INFO] train episode 2220: reward = -100.13, steps = 19 01:44:23 [INFO] train episode 2221: reward = -87.99, steps = 19 01:44:26 [INFO] train episode 2222: reward = -117.25, steps = 26 01:44:28 [INFO] train episode 2223: reward = -126.15, steps = 19 01:44:30 [INFO] train episode 2224: reward = -135.98, steps = 23 01:44:32 [INFO] train episode 2225: reward = -131.73, steps = 19 01:44:33 [INFO] train episode 2226: reward = -87.63, steps = 21 01:44:35 [INFO] train episode 2227: reward = -85.55, steps = 19 01:44:37 [INFO] train episode 2228: reward = -79.03, steps = 19 01:44:39 [INFO] train episode 2229: reward = -106.11, steps = 19 01:44:41 [INFO] train episode 2230: reward = -110.42, steps = 18 01:44:42 [INFO] train episode 2231: reward = -97.77, steps = 19 01:44:45 [INFO] train episode 2232: reward = -97.35, steps = 26 01:44:47 [INFO] train episode 2233: reward = -178.53, steps = 23 01:44:49 [INFO] train episode 2234: reward = -133.52, steps = 20 01:44:51 [INFO] train episode 2235: reward = -109.72, steps = 22 01:44:53 [INFO] train episode 2236: reward = -134.99, steps = 28 01:44:55 [INFO] train episode 2237: reward = -86.46, steps = 19 01:44:57 [INFO] train episode 2238: reward = -123.34, steps = 19 01:44:59 [INFO] train episode 2239: reward = -105.48, steps = 25 01:45:01 [INFO] train episode 2240: reward = -109.75, steps = 19 01:45:03 [INFO] train episode 2241: reward = -73.35, steps = 19 01:45:04 [INFO] train episode 2242: reward = -119.07, steps = 20 01:45:07 [INFO] train episode 2243: reward = -72.93, steps = 21 01:45:08 [INFO] train episode 2244: reward = -78.13, steps = 21 01:45:10 [INFO] train episode 2245: reward = -77.04, steps = 20 01:45:12 [INFO] train episode 2246: reward = -123.93, steps = 21 01:45:14 [INFO] train episode 2247: reward = -144.63, steps = 20 01:45:16 [INFO] train episode 2248: reward = -94.18, steps = 19 01:45:18 [INFO] train episode 2249: reward = -121.76, steps = 19 01:45:20 [INFO] train episode 2250: reward = -95.00, steps = 17 01:45:22 [INFO] train episode 2251: reward = -81.69, steps = 20 01:45:24 [INFO] train episode 2252: reward = -85.89, steps = 19 01:45:26 [INFO] train episode 2253: reward = -89.11, steps = 19 01:45:28 [INFO] train episode 2254: reward = -123.29, steps = 27 01:45:31 [INFO] train episode 2255: reward = -97.81, steps = 20 01:45:33 [INFO] train episode 2256: reward = -112.08, steps = 18 01:45:36 [INFO] train episode 2257: reward = -98.72, steps = 21 01:45:37 [INFO] train episode 2258: reward = -99.25, steps = 16 01:45:39 [INFO] train episode 2259: reward = -120.77, steps = 19 01:45:41 [INFO] train episode 2260: reward = -123.14, steps = 20 01:45:43 [INFO] train episode 2261: reward = -103.94, steps = 20 01:45:45 [INFO] train episode 2262: reward = -100.15, steps = 24 01:45:47 [INFO] train episode 2263: reward = -77.60, steps = 20 01:45:49 [INFO] train episode 2264: reward = -108.51, steps = 25 01:45:52 [INFO] train episode 2265: reward = -114.84, steps = 19 01:45:54 [INFO] train episode 2266: reward = -106.86, steps = 22 01:45:56 [INFO] train episode 2267: reward = -119.31, steps = 16 01:45:59 [INFO] train episode 2268: reward = -91.19, steps = 21 01:46:02 [INFO] train episode 2269: reward = -98.02, steps = 23 01:46:04 [INFO] train episode 2270: reward = -113.82, steps = 19 01:46:05 [INFO] train episode 2271: reward = -105.42, steps = 20 01:46:08 [INFO] train episode 2272: reward = -218.93, steps = 27 01:46:10 [INFO] train episode 2273: reward = -115.05, steps = 19 01:46:12 [INFO] train episode 2274: reward = -123.37, steps = 20 01:46:14 [INFO] train episode 2275: reward = -124.39, steps = 19 01:46:15 [INFO] train episode 2276: reward = -86.77, steps = 19 01:46:17 [INFO] train episode 2277: reward = -109.24, steps = 19 01:46:19 [INFO] train episode 2278: reward = -102.06, steps = 18 01:46:21 [INFO] train episode 2279: reward = -79.47, steps = 19 01:46:22 [INFO] train episode 2280: reward = -121.48, steps = 20 01:46:25 [INFO] train episode 2281: reward = -185.12, steps = 29 01:46:27 [INFO] train episode 2282: reward = -92.55, steps = 19 01:46:29 [INFO] train episode 2283: reward = -109.04, steps = 18 01:46:31 [INFO] train episode 2284: reward = -139.12, steps = 22 01:46:33 [INFO] train episode 2285: reward = -53.82, steps = 14 01:46:35 [INFO] train episode 2286: reward = -109.91, steps = 18 01:46:38 [INFO] train episode 2287: reward = -125.50, steps = 19 01:46:40 [INFO] train episode 2288: reward = -99.07, steps = 19 01:46:42 [INFO] train episode 2289: reward = -122.23, steps = 18 01:46:45 [INFO] train episode 2290: reward = -94.59, steps = 18 01:46:47 [INFO] train episode 2291: reward = -115.10, steps = 20 01:46:48 [INFO] train episode 2292: reward = -91.29, steps = 15 01:46:50 [INFO] train episode 2293: reward = -97.28, steps = 19 01:46:53 [INFO] train episode 2294: reward = -104.68, steps = 19 01:46:55 [INFO] train episode 2295: reward = -131.75, steps = 23 01:46:57 [INFO] train episode 2296: reward = -124.50, steps = 21 01:46:59 [INFO] train episode 2297: reward = -98.98, steps = 19 01:47:01 [INFO] train episode 2298: reward = -118.95, steps = 20 01:47:03 [INFO] train episode 2299: reward = -138.95, steps = 18 01:47:06 [INFO] train episode 2300: reward = -160.83, steps = 21 01:47:08 [INFO] train episode 2301: reward = -154.18, steps = 23 01:47:09 [INFO] train episode 2302: reward = -124.89, steps = 15 01:47:12 [INFO] train episode 2303: reward = -95.65, steps = 21 01:47:13 [INFO] train episode 2304: reward = -127.15, steps = 18 01:47:16 [INFO] train episode 2305: reward = -131.36, steps = 20 01:47:18 [INFO] train episode 2306: reward = -178.08, steps = 27 01:47:20 [INFO] train episode 2307: reward = -74.18, steps = 20 01:47:22 [INFO] train episode 2308: reward = -100.79, steps = 18 01:47:24 [INFO] train episode 2309: reward = -92.72, steps = 21 01:47:26 [INFO] train episode 2310: reward = -133.88, steps = 20 01:47:28 [INFO] train episode 2311: reward = -100.93, steps = 19 01:47:30 [INFO] train episode 2312: reward = -78.73, steps = 19 01:47:31 [INFO] train episode 2313: reward = -91.73, steps = 19 01:47:33 [INFO] train episode 2314: reward = -111.59, steps = 21 01:47:35 [INFO] train episode 2315: reward = -89.43, steps = 19 01:47:37 [INFO] train episode 2316: reward = -166.62, steps = 24 01:47:39 [INFO] train episode 2317: reward = -107.27, steps = 20 01:47:41 [INFO] train episode 2318: reward = -97.70, steps = 23 01:47:43 [INFO] train episode 2319: reward = -95.93, steps = 19 01:47:45 [INFO] train episode 2320: reward = -94.11, steps = 19 01:47:47 [INFO] train episode 2321: reward = -90.80, steps = 21 01:47:49 [INFO] train episode 2322: reward = -149.33, steps = 21 01:47:51 [INFO] train episode 2323: reward = -130.72, steps = 27 01:47:54 [INFO] train episode 2324: reward = -95.85, steps = 30 01:47:56 [INFO] train episode 2325: reward = -100.16, steps = 19 01:47:59 [INFO] train episode 2326: reward = -138.18, steps = 21 01:48:01 [INFO] train episode 2327: reward = -90.89, steps = 20 01:48:02 [INFO] train episode 2328: reward = -107.12, steps = 19 01:48:04 [INFO] train episode 2329: reward = -83.21, steps = 19 01:48:06 [INFO] train episode 2330: reward = -99.80, steps = 20 01:48:08 [INFO] train episode 2331: reward = -152.87, steps = 22 01:48:10 [INFO] train episode 2332: reward = -89.58, steps = 19 01:48:12 [INFO] train episode 2333: reward = -109.36, steps = 19 01:48:13 [INFO] train episode 2334: reward = -80.83, steps = 19 01:48:16 [INFO] train episode 2335: reward = -113.30, steps = 23 01:48:18 [INFO] train episode 2336: reward = -117.33, steps = 20 01:48:20 [INFO] train episode 2337: reward = -146.51, steps = 24 01:48:22 [INFO] train episode 2338: reward = -102.68, steps = 19 01:48:24 [INFO] train episode 2339: reward = -148.85, steps = 23 01:48:25 [INFO] train episode 2340: reward = -141.97, steps = 19 01:48:27 [INFO] train episode 2341: reward = -70.16, steps = 19 01:48:29 [INFO] train episode 2342: reward = -64.63, steps = 18 01:48:31 [INFO] train episode 2343: reward = -115.21, steps = 19 01:48:33 [INFO] train episode 2344: reward = -108.59, steps = 19 01:48:35 [INFO] train episode 2345: reward = -131.40, steps = 19 01:48:37 [INFO] train episode 2346: reward = -128.11, steps = 28 01:48:39 [INFO] train episode 2347: reward = -90.46, steps = 19 01:48:41 [INFO] train episode 2348: reward = -148.49, steps = 21 01:48:42 [INFO] train episode 2349: reward = -111.69, steps = 18 01:48:44 [INFO] train episode 2350: reward = -149.85, steps = 21 01:48:46 [INFO] train episode 2351: reward = -127.55, steps = 18 01:48:48 [INFO] train episode 2352: reward = -120.43, steps = 19 01:48:51 [INFO] train episode 2353: reward = -93.91, steps = 25 01:48:52 [INFO] train episode 2354: reward = -125.41, steps = 19 01:48:54 [INFO] train episode 2355: reward = -116.89, steps = 20 01:48:56 [INFO] train episode 2356: reward = -114.20, steps = 22 01:48:58 [INFO] train episode 2357: reward = -110.37, steps = 20 01:49:00 [INFO] train episode 2358: reward = -102.24, steps = 18 01:49:01 [INFO] train episode 2359: reward = -93.45, steps = 19 01:49:03 [INFO] train episode 2360: reward = -95.48, steps = 20 01:49:06 [INFO] train episode 2361: reward = -171.41, steps = 29 01:49:08 [INFO] train episode 2362: reward = -95.27, steps = 17 01:49:10 [INFO] train episode 2363: reward = -132.62, steps = 20 01:49:12 [INFO] train episode 2364: reward = -96.78, steps = 19 01:49:13 [INFO] train episode 2365: reward = -111.58, steps = 18 01:49:15 [INFO] train episode 2366: reward = -125.91, steps = 23 01:49:17 [INFO] train episode 2367: reward = -125.03, steps = 20 01:49:20 [INFO] train episode 2368: reward = -141.27, steps = 28 01:49:22 [INFO] train episode 2369: reward = -109.62, steps = 19 01:49:24 [INFO] train episode 2370: reward = -100.49, steps = 19 01:49:25 [INFO] train episode 2371: reward = -88.50, steps = 18 01:49:27 [INFO] train episode 2372: reward = -131.87, steps = 19 01:49:29 [INFO] train episode 2373: reward = -111.37, steps = 19 01:49:31 [INFO] train episode 2374: reward = -124.52, steps = 19 01:49:33 [INFO] train episode 2375: reward = -116.04, steps = 20 01:49:35 [INFO] train episode 2376: reward = -106.71, steps = 19 01:49:37 [INFO] train episode 2377: reward = -146.92, steps = 21 01:49:39 [INFO] train episode 2378: reward = -95.70, steps = 18 01:49:41 [INFO] train episode 2379: reward = -125.03, steps = 20 01:49:43 [INFO] train episode 2380: reward = -113.53, steps = 21 01:49:45 [INFO] train episode 2381: reward = -114.76, steps = 21 01:49:47 [INFO] train episode 2382: reward = -116.98, steps = 19 01:49:49 [INFO] train episode 2383: reward = -81.98, steps = 18 01:49:51 [INFO] train episode 2384: reward = -81.80, steps = 24 01:49:53 [INFO] train episode 2385: reward = -129.46, steps = 22 01:49:55 [INFO] train episode 2386: reward = -148.84, steps = 22 01:49:59 [INFO] train episode 2387: reward = -136.64, steps = 28 01:50:01 [INFO] train episode 2388: reward = -97.54, steps = 19 01:50:03 [INFO] train episode 2389: reward = -156.35, steps = 19 01:50:05 [INFO] train episode 2390: reward = -113.47, steps = 21 01:50:06 [INFO] train episode 2391: reward = -127.19, steps = 19 01:50:08 [INFO] train episode 2392: reward = -91.77, steps = 19 01:50:10 [INFO] train episode 2393: reward = -130.97, steps = 19 01:50:12 [INFO] train episode 2394: reward = -110.98, steps = 18 01:50:14 [INFO] train episode 2395: reward = -150.23, steps = 22 01:50:16 [INFO] train episode 2396: reward = -105.22, steps = 19 01:50:17 [INFO] train episode 2397: reward = -97.99, steps = 19 01:50:19 [INFO] train episode 2398: reward = -103.94, steps = 17 01:50:21 [INFO] train episode 2399: reward = -112.26, steps = 20 01:50:23 [INFO] train episode 2400: reward = -112.66, steps = 21 01:50:25 [INFO] train episode 2401: reward = -152.69, steps = 22 01:50:27 [INFO] train episode 2402: reward = -136.64, steps = 27 01:50:29 [INFO] train episode 2403: reward = -113.11, steps = 20 01:50:31 [INFO] train episode 2404: reward = -111.40, steps = 19 01:50:33 [INFO] train episode 2405: reward = -113.02, steps = 21 01:50:35 [INFO] train episode 2406: reward = -110.80, steps = 19 01:50:37 [INFO] train episode 2407: reward = -111.61, steps = 23 01:50:39 [INFO] train episode 2408: reward = -123.95, steps = 23 01:50:41 [INFO] train episode 2409: reward = -129.66, steps = 19 01:50:43 [INFO] train episode 2410: reward = -103.81, steps = 19 01:50:45 [INFO] train episode 2411: reward = -111.56, steps = 23 01:50:47 [INFO] train episode 2412: reward = -75.18, steps = 19 01:50:49 [INFO] train episode 2413: reward = -112.13, steps = 23 01:50:51 [INFO] train episode 2414: reward = -116.53, steps = 20 01:50:53 [INFO] train episode 2415: reward = -94.46, steps = 20 01:50:55 [INFO] train episode 2416: reward = -110.16, steps = 24 01:50:57 [INFO] train episode 2417: reward = -131.76, steps = 22 01:50:59 [INFO] train episode 2418: reward = -89.56, steps = 20 01:51:00 [INFO] train episode 2419: reward = -143.12, steps = 18 01:51:02 [INFO] train episode 2420: reward = -105.85, steps = 21 01:51:05 [INFO] train episode 2421: reward = -120.97, steps = 19 01:51:06 [INFO] train episode 2422: reward = -79.83, steps = 20 01:51:08 [INFO] train episode 2423: reward = -120.06, steps = 20 01:51:10 [INFO] train episode 2424: reward = -110.60, steps = 19 01:51:12 [INFO] train episode 2425: reward = -98.81, steps = 21 01:51:14 [INFO] train episode 2426: reward = -119.34, steps = 27 01:51:16 [INFO] train episode 2427: reward = -109.05, steps = 22 01:51:18 [INFO] train episode 2428: reward = -108.64, steps = 19 01:51:20 [INFO] train episode 2429: reward = -106.93, steps = 19 01:51:22 [INFO] train episode 2430: reward = -126.96, steps = 23 01:51:24 [INFO] train episode 2431: reward = -122.75, steps = 20 01:51:26 [INFO] train episode 2432: reward = -132.58, steps = 24 01:51:28 [INFO] train episode 2433: reward = -77.30, steps = 19 01:51:31 [INFO] train episode 2434: reward = -213.81, steps = 26 01:51:33 [INFO] train episode 2435: reward = -95.73, steps = 20 01:51:35 [INFO] train episode 2436: reward = -88.95, steps = 19 01:51:37 [INFO] train episode 2437: reward = -109.52, steps = 19 01:51:39 [INFO] train episode 2438: reward = -196.40, steps = 24 01:51:41 [INFO] train episode 2439: reward = -103.15, steps = 19 01:51:43 [INFO] train episode 2440: reward = -168.72, steps = 22 01:51:45 [INFO] train episode 2441: reward = -117.17, steps = 26 01:51:47 [INFO] train episode 2442: reward = -102.93, steps = 24 01:51:49 [INFO] train episode 2443: reward = -94.05, steps = 20 01:51:51 [INFO] train episode 2444: reward = -97.06, steps = 20 01:51:53 [INFO] train episode 2445: reward = -114.03, steps = 21 01:51:55 [INFO] train episode 2446: reward = -111.96, steps = 20 01:51:57 [INFO] train episode 2447: reward = -78.03, steps = 19 01:51:59 [INFO] train episode 2448: reward = -87.89, steps = 19 01:52:00 [INFO] train episode 2449: reward = -89.10, steps = 19 01:52:02 [INFO] train episode 2450: reward = -141.45, steps = 22 01:52:04 [INFO] train episode 2451: reward = -105.34, steps = 19 01:52:06 [INFO] train episode 2452: reward = -158.25, steps = 24 01:52:08 [INFO] train episode 2453: reward = -127.13, steps = 21 01:52:11 [INFO] train episode 2454: reward = -130.09, steps = 20 01:52:12 [INFO] train episode 2455: reward = -107.86, steps = 19 01:52:14 [INFO] train episode 2456: reward = -99.63, steps = 20 01:52:16 [INFO] train episode 2457: reward = -120.46, steps = 18 01:52:18 [INFO] train episode 2458: reward = -88.82, steps = 18 01:52:20 [INFO] train episode 2459: reward = -119.49, steps = 19 01:52:21 [INFO] train episode 2460: reward = -105.44, steps = 19 01:52:23 [INFO] train episode 2461: reward = -116.73, steps = 21 01:52:25 [INFO] train episode 2462: reward = -112.60, steps = 19 01:52:27 [INFO] train episode 2463: reward = -179.82, steps = 18 01:52:29 [INFO] train episode 2464: reward = -95.30, steps = 20 01:52:31 [INFO] train episode 2465: reward = -170.77, steps = 23 01:52:33 [INFO] train episode 2466: reward = -110.64, steps = 22 01:52:35 [INFO] train episode 2467: reward = -157.78, steps = 26 01:52:38 [INFO] train episode 2468: reward = -119.18, steps = 23 01:52:40 [INFO] train episode 2469: reward = -75.25, steps = 25 01:52:42 [INFO] train episode 2470: reward = -102.44, steps = 24 01:52:44 [INFO] train episode 2471: reward = -96.99, steps = 20 01:52:46 [INFO] train episode 2472: reward = -90.99, steps = 20 01:52:48 [INFO] train episode 2473: reward = -111.47, steps = 19 01:52:50 [INFO] train episode 2474: reward = -81.24, steps = 19 01:52:51 [INFO] train episode 2475: reward = -122.94, steps = 19 01:52:53 [INFO] train episode 2476: reward = -129.91, steps = 22 01:52:55 [INFO] train episode 2477: reward = -106.80, steps = 21 01:52:57 [INFO] train episode 2478: reward = -94.60, steps = 23 01:52:59 [INFO] train episode 2479: reward = -109.33, steps = 19 01:53:02 [INFO] train episode 2480: reward = -117.05, steps = 21 01:53:04 [INFO] train episode 2481: reward = -67.75, steps = 20 01:53:06 [INFO] train episode 2482: reward = -133.65, steps = 24 01:53:08 [INFO] train episode 2483: reward = -145.52, steps = 23 01:53:10 [INFO] train episode 2484: reward = -96.89, steps = 19 01:53:12 [INFO] train episode 2485: reward = -120.83, steps = 20 01:53:14 [INFO] train episode 2486: reward = -194.97, steps = 19 01:53:16 [INFO] train episode 2487: reward = -75.89, steps = 18 01:53:18 [INFO] train episode 2488: reward = -113.51, steps = 20 01:53:20 [INFO] train episode 2489: reward = -87.72, steps = 19 01:53:22 [INFO] train episode 2490: reward = -108.28, steps = 19 01:53:24 [INFO] train episode 2491: reward = -126.35, steps = 22 01:53:26 [INFO] train episode 2492: reward = -111.31, steps = 23 01:53:28 [INFO] train episode 2493: reward = -145.10, steps = 23 01:53:30 [INFO] train episode 2494: reward = -96.11, steps = 20 01:53:32 [INFO] train episode 2495: reward = -116.02, steps = 20 01:53:33 [INFO] train episode 2496: reward = -130.05, steps = 20 01:53:36 [INFO] train episode 2497: reward = -109.89, steps = 20 01:53:37 [INFO] train episode 2498: reward = -145.06, steps = 19 01:53:40 [INFO] train episode 2499: reward = -125.74, steps = 24 01:53:42 [INFO] train episode 2500: reward = -116.67, steps = 30 01:53:44 [INFO] train episode 2501: reward = -112.55, steps = 19 01:53:46 [INFO] train episode 2502: reward = -90.13, steps = 23 01:53:48 [INFO] train episode 2503: reward = -162.41, steps = 19 01:53:50 [INFO] train episode 2504: reward = -109.50, steps = 20 01:53:52 [INFO] train episode 2505: reward = -94.00, steps = 24 01:53:55 [INFO] train episode 2506: reward = -154.64, steps = 26 01:53:57 [INFO] train episode 2507: reward = -115.46, steps = 26 01:53:59 [INFO] train episode 2508: reward = -134.66, steps = 23 01:54:01 [INFO] train episode 2509: reward = -105.22, steps = 20 01:54:03 [INFO] train episode 2510: reward = -120.22, steps = 20 01:54:05 [INFO] train episode 2511: reward = -84.28, steps = 19 01:54:07 [INFO] train episode 2512: reward = -110.96, steps = 20 01:54:09 [INFO] train episode 2513: reward = -134.26, steps = 20 01:54:11 [INFO] train episode 2514: reward = -102.01, steps = 19 01:54:13 [INFO] train episode 2515: reward = -116.55, steps = 19 01:54:14 [INFO] train episode 2516: reward = -131.78, steps = 19 01:54:16 [INFO] train episode 2517: reward = -147.44, steps = 19 01:54:19 [INFO] train episode 2518: reward = -138.19, steps = 28 01:54:21 [INFO] train episode 2519: reward = -112.49, steps = 20 01:54:22 [INFO] train episode 2520: reward = -99.96, steps = 18 01:54:24 [INFO] train episode 2521: reward = -169.32, steps = 23 01:54:26 [INFO] train episode 2522: reward = -91.31, steps = 19 01:54:28 [INFO] train episode 2523: reward = -121.90, steps = 20 01:54:30 [INFO] train episode 2524: reward = -169.30, steps = 18 01:54:32 [INFO] train episode 2525: reward = -106.44, steps = 19 01:54:33 [INFO] train episode 2526: reward = -62.77, steps = 19 01:54:35 [INFO] train episode 2527: reward = -95.89, steps = 20 01:54:37 [INFO] train episode 2528: reward = -95.59, steps = 21 01:54:39 [INFO] train episode 2529: reward = -146.92, steps = 20 01:54:41 [INFO] train episode 2530: reward = -81.26, steps = 23 01:54:43 [INFO] train episode 2531: reward = -113.41, steps = 19 01:54:45 [INFO] train episode 2532: reward = -126.35, steps = 18 01:54:47 [INFO] train episode 2533: reward = -76.45, steps = 19 01:54:49 [INFO] train episode 2534: reward = -101.62, steps = 18 01:54:51 [INFO] train episode 2535: reward = -150.54, steps = 31 01:54:54 [INFO] train episode 2536: reward = -91.70, steps = 24 01:54:56 [INFO] train episode 2537: reward = -116.63, steps = 22 01:54:57 [INFO] train episode 2538: reward = -116.21, steps = 18 01:55:00 [INFO] train episode 2539: reward = -112.53, steps = 20 01:55:02 [INFO] train episode 2540: reward = -101.08, steps = 18 01:55:04 [INFO] train episode 2541: reward = -112.34, steps = 22 01:55:06 [INFO] train episode 2542: reward = -89.98, steps = 20 01:55:10 [INFO] train episode 2543: reward = -88.73, steps = 26 01:55:12 [INFO] train episode 2544: reward = -77.08, steps = 20 01:55:15 [INFO] train episode 2545: reward = -107.09, steps = 20 01:55:17 [INFO] train episode 2546: reward = -105.88, steps = 18 01:55:19 [INFO] train episode 2547: reward = -102.01, steps = 19 01:55:22 [INFO] train episode 2548: reward = -146.73, steps = 21 01:55:24 [INFO] train episode 2549: reward = -132.63, steps = 19 01:55:25 [INFO] train episode 2550: reward = -89.96, steps = 18 01:55:28 [INFO] train episode 2551: reward = -138.24, steps = 31 01:55:30 [INFO] train episode 2552: reward = -97.00, steps = 19 01:55:32 [INFO] train episode 2553: reward = -135.65, steps = 20 01:55:34 [INFO] train episode 2554: reward = -93.11, steps = 18 01:55:36 [INFO] train episode 2555: reward = -98.29, steps = 18 01:55:38 [INFO] train episode 2556: reward = -125.29, steps = 19 01:55:40 [INFO] train episode 2557: reward = -77.33, steps = 19 01:55:42 [INFO] train episode 2558: reward = -92.54, steps = 19 01:55:43 [INFO] train episode 2559: reward = -123.31, steps = 20 01:55:45 [INFO] train episode 2560: reward = -120.09, steps = 20 01:55:47 [INFO] train episode 2561: reward = -148.38, steps = 19 01:55:49 [INFO] train episode 2562: reward = -96.77, steps = 22 01:55:51 [INFO] train episode 2563: reward = -82.81, steps = 18 01:55:53 [INFO] train episode 2564: reward = -152.01, steps = 23 01:55:56 [INFO] train episode 2565: reward = -143.13, steps = 32 01:55:58 [INFO] train episode 2566: reward = -148.63, steps = 22 01:56:00 [INFO] train episode 2567: reward = -190.88, steps = 19 01:56:02 [INFO] train episode 2568: reward = -90.46, steps = 19 01:56:04 [INFO] train episode 2569: reward = -101.12, steps = 19 01:56:06 [INFO] train episode 2570: reward = -99.78, steps = 22 01:56:08 [INFO] train episode 2571: reward = -94.49, steps = 22 01:56:11 [INFO] train episode 2572: reward = -164.82, steps = 23 01:56:14 [INFO] train episode 2573: reward = -139.22, steps = 29 01:56:16 [INFO] train episode 2574: reward = -100.38, steps = 17 01:56:18 [INFO] train episode 2575: reward = -137.30, steps = 18 01:56:20 [INFO] train episode 2576: reward = -101.91, steps = 20 01:56:22 [INFO] train episode 2577: reward = -106.75, steps = 22 01:56:24 [INFO] train episode 2578: reward = -188.52, steps = 29 01:56:26 [INFO] train episode 2579: reward = -129.01, steps = 19 01:56:29 [INFO] train episode 2580: reward = -129.82, steps = 22 01:56:31 [INFO] train episode 2581: reward = -108.48, steps = 17 01:56:33 [INFO] train episode 2582: reward = -139.76, steps = 23 01:56:35 [INFO] train episode 2583: reward = -115.78, steps = 20 01:56:37 [INFO] train episode 2584: reward = -158.63, steps = 24 01:56:39 [INFO] train episode 2585: reward = -135.07, steps = 19 01:56:41 [INFO] train episode 2586: reward = -83.85, steps = 18 01:56:43 [INFO] train episode 2587: reward = -102.65, steps = 21 01:56:45 [INFO] train episode 2588: reward = -154.77, steps = 19 01:56:47 [INFO] train episode 2589: reward = -150.20, steps = 20 01:56:49 [INFO] train episode 2590: reward = -107.20, steps = 19 01:56:51 [INFO] train episode 2591: reward = -99.05, steps = 19 01:56:53 [INFO] train episode 2592: reward = -143.53, steps = 19 01:56:55 [INFO] train episode 2593: reward = -155.26, steps = 29 01:56:57 [INFO] train episode 2594: reward = -116.98, steps = 19 01:57:00 [INFO] train episode 2595: reward = -122.97, steps = 27 01:57:02 [INFO] train episode 2596: reward = -137.74, steps = 19 01:57:03 [INFO] train episode 2597: reward = -128.12, steps = 20 01:57:05 [INFO] train episode 2598: reward = -122.97, steps = 18 01:57:08 [INFO] train episode 2599: reward = -131.77, steps = 22 01:57:10 [INFO] train episode 2600: reward = -137.85, steps = 18 01:57:11 [INFO] train episode 2601: reward = -97.96, steps = 19 01:57:14 [INFO] train episode 2602: reward = -153.38, steps = 23 01:57:15 [INFO] train episode 2603: reward = -109.59, steps = 19 01:57:17 [INFO] train episode 2604: reward = -124.13, steps = 19 01:57:19 [INFO] train episode 2605: reward = -96.23, steps = 19 01:57:21 [INFO] train episode 2606: reward = -128.73, steps = 19 01:57:23 [INFO] train episode 2607: reward = -133.86, steps = 19 01:57:26 [INFO] train episode 2608: reward = -129.74, steps = 24 01:57:29 [INFO] train episode 2609: reward = -182.54, steps = 31 01:57:30 [INFO] train episode 2610: reward = -107.56, steps = 16 01:57:32 [INFO] train episode 2611: reward = -111.19, steps = 19 01:57:34 [INFO] train episode 2612: reward = -137.38, steps = 19 01:57:36 [INFO] train episode 2613: reward = -87.27, steps = 20 01:57:38 [INFO] train episode 2614: reward = -101.28, steps = 19 01:57:39 [INFO] train episode 2615: reward = -128.59, steps = 19 01:57:42 [INFO] train episode 2616: reward = -109.43, steps = 18 01:57:43 [INFO] train episode 2617: reward = -83.64, steps = 19 01:57:45 [INFO] train episode 2618: reward = -123.61, steps = 18 01:57:47 [INFO] train episode 2619: reward = -77.25, steps = 18 01:57:49 [INFO] train episode 2620: reward = -147.16, steps = 20 01:57:51 [INFO] train episode 2621: reward = -77.24, steps = 22 01:57:53 [INFO] train episode 2622: reward = -131.88, steps = 24 01:57:55 [INFO] train episode 2623: reward = -111.31, steps = 25 01:57:58 [INFO] train episode 2624: reward = -100.61, steps = 23 01:58:00 [INFO] train episode 2625: reward = -107.74, steps = 19 01:58:02 [INFO] train episode 2626: reward = -113.68, steps = 21 01:58:04 [INFO] train episode 2627: reward = -119.70, steps = 19 01:58:06 [INFO] train episode 2628: reward = -87.99, steps = 22 01:58:07 [INFO] train episode 2629: reward = -103.52, steps = 18 01:58:10 [INFO] train episode 2630: reward = -100.02, steps = 26 01:58:12 [INFO] train episode 2631: reward = -124.09, steps = 19 01:58:14 [INFO] train episode 2632: reward = -130.34, steps = 19 01:58:16 [INFO] train episode 2633: reward = -82.74, steps = 20 01:58:18 [INFO] train episode 2634: reward = -143.73, steps = 20 01:58:20 [INFO] train episode 2635: reward = -118.52, steps = 21 01:58:21 [INFO] train episode 2636: reward = -103.43, steps = 19 01:58:23 [INFO] train episode 2637: reward = -92.13, steps = 19 01:58:25 [INFO] train episode 2638: reward = -83.83, steps = 19 01:58:27 [INFO] train episode 2639: reward = -131.44, steps = 19 01:58:29 [INFO] train episode 2640: reward = -130.19, steps = 19 01:58:30 [INFO] train episode 2641: reward = -118.53, steps = 15 01:58:32 [INFO] train episode 2642: reward = -118.03, steps = 19 01:58:34 [INFO] train episode 2643: reward = -150.77, steps = 20 01:58:37 [INFO] train episode 2644: reward = -143.43, steps = 24 01:58:39 [INFO] train episode 2645: reward = -179.46, steps = 24 01:58:41 [INFO] train episode 2646: reward = -119.61, steps = 19 01:58:43 [INFO] train episode 2647: reward = -112.63, steps = 20 01:58:45 [INFO] train episode 2648: reward = -81.00, steps = 22 01:58:47 [INFO] train episode 2649: reward = -110.82, steps = 20 01:58:49 [INFO] train episode 2650: reward = -145.74, steps = 27 01:58:52 [INFO] train episode 2651: reward = -154.32, steps = 20 01:58:53 [INFO] train episode 2652: reward = -111.34, steps = 20 01:58:55 [INFO] train episode 2653: reward = -130.36, steps = 19 01:58:57 [INFO] train episode 2654: reward = -80.58, steps = 18 01:58:59 [INFO] train episode 2655: reward = -105.06, steps = 18 01:59:01 [INFO] train episode 2656: reward = -85.33, steps = 21 01:59:03 [INFO] train episode 2657: reward = -165.89, steps = 23 01:59:05 [INFO] train episode 2658: reward = -85.96, steps = 19 01:59:07 [INFO] train episode 2659: reward = -75.76, steps = 21 01:59:09 [INFO] train episode 2660: reward = -111.08, steps = 22 01:59:11 [INFO] train episode 2661: reward = -139.03, steps = 20 01:59:14 [INFO] train episode 2662: reward = -133.32, steps = 25 01:59:16 [INFO] train episode 2663: reward = -156.67, steps = 20 01:59:17 [INFO] train episode 2664: reward = -89.08, steps = 19 01:59:21 [INFO] train episode 2665: reward = -107.27, steps = 25 01:59:22 [INFO] train episode 2666: reward = -122.82, steps = 18 01:59:24 [INFO] train episode 2667: reward = -111.00, steps = 20 01:59:26 [INFO] train episode 2668: reward = -118.87, steps = 19 01:59:28 [INFO] train episode 2669: reward = -97.34, steps = 18 01:59:30 [INFO] train episode 2670: reward = -117.89, steps = 20 01:59:32 [INFO] train episode 2671: reward = -85.44, steps = 19 01:59:34 [INFO] train episode 2672: reward = -88.22, steps = 19 01:59:36 [INFO] train episode 2673: reward = -84.84, steps = 23 01:59:38 [INFO] train episode 2674: reward = -117.12, steps = 19 01:59:40 [INFO] train episode 2675: reward = -89.83, steps = 16 01:59:42 [INFO] train episode 2676: reward = -105.93, steps = 25 01:59:44 [INFO] train episode 2677: reward = -97.76, steps = 21 01:59:46 [INFO] train episode 2678: reward = -116.56, steps = 19 01:59:48 [INFO] train episode 2679: reward = -129.14, steps = 20 01:59:51 [INFO] train episode 2680: reward = -146.51, steps = 29 01:59:52 [INFO] train episode 2681: reward = -79.22, steps = 18 01:59:54 [INFO] train episode 2682: reward = -97.94, steps = 19 01:59:56 [INFO] train episode 2683: reward = -95.09, steps = 22 01:59:59 [INFO] train episode 2684: reward = -145.09, steps = 30 02:00:01 [INFO] train episode 2685: reward = -95.12, steps = 19 02:00:03 [INFO] train episode 2686: reward = -104.96, steps = 19 02:00:05 [INFO] train episode 2687: reward = -200.48, steps = 20 02:00:07 [INFO] train episode 2688: reward = -140.02, steps = 23 02:00:09 [INFO] train episode 2689: reward = -192.32, steps = 19 02:00:11 [INFO] train episode 2690: reward = -70.69, steps = 21 02:00:14 [INFO] train episode 2691: reward = -84.65, steps = 23 02:00:16 [INFO] train episode 2692: reward = -155.11, steps = 25 02:00:18 [INFO] train episode 2693: reward = -93.41, steps = 19 02:00:20 [INFO] train episode 2694: reward = -127.03, steps = 19 02:00:22 [INFO] train episode 2695: reward = -123.31, steps = 27 02:00:24 [INFO] train episode 2696: reward = -98.51, steps = 21 02:00:27 [INFO] train episode 2697: reward = -118.32, steps = 29 02:00:29 [INFO] train episode 2698: reward = -72.90, steps = 22 02:00:32 [INFO] train episode 2699: reward = -155.84, steps = 25 02:00:33 [INFO] train episode 2700: reward = -135.28, steps = 18 02:00:35 [INFO] train episode 2701: reward = -57.97, steps = 16 02:00:38 [INFO] train episode 2702: reward = -114.82, steps = 21 02:00:39 [INFO] train episode 2703: reward = -95.78, steps = 20 02:00:41 [INFO] train episode 2704: reward = -123.77, steps = 19 02:00:44 [INFO] train episode 2705: reward = -105.04, steps = 24 02:00:45 [INFO] train episode 2706: reward = -132.62, steps = 20 02:00:47 [INFO] train episode 2707: reward = -79.37, steps = 18 02:00:49 [INFO] train episode 2708: reward = -137.50, steps = 18 02:00:51 [INFO] train episode 2709: reward = -140.15, steps = 20 02:00:53 [INFO] train episode 2710: reward = -119.75, steps = 21 02:00:55 [INFO] train episode 2711: reward = -101.12, steps = 20 02:00:57 [INFO] train episode 2712: reward = -94.59, steps = 19 02:01:00 [INFO] train episode 2713: reward = -97.24, steps = 27 02:01:02 [INFO] train episode 2714: reward = -87.71, steps = 24 02:01:04 [INFO] train episode 2715: reward = -87.37, steps = 23 02:01:06 [INFO] train episode 2716: reward = -89.86, steps = 18 02:01:08 [INFO] train episode 2717: reward = -137.21, steps = 22 02:01:10 [INFO] train episode 2718: reward = -118.43, steps = 19 02:01:13 [INFO] train episode 2719: reward = -104.85, steps = 24 02:01:14 [INFO] train episode 2720: reward = -102.05, steps = 20 02:01:16 [INFO] train episode 2721: reward = -118.32, steps = 18 02:01:18 [INFO] train episode 2722: reward = -131.61, steps = 19 02:01:20 [INFO] train episode 2723: reward = -120.30, steps = 18 02:01:21 [INFO] train episode 2724: reward = -137.83, steps = 19 02:01:23 [INFO] train episode 2725: reward = -103.51, steps = 19 02:01:25 [INFO] train episode 2726: reward = -94.09, steps = 19 02:01:27 [INFO] train episode 2727: reward = -92.48, steps = 19 02:01:29 [INFO] train episode 2728: reward = -115.36, steps = 22 02:01:32 [INFO] train episode 2729: reward = -109.20, steps = 24 02:01:33 [INFO] train episode 2730: reward = -139.49, steps = 19 02:01:35 [INFO] train episode 2731: reward = -167.25, steps = 21 02:01:38 [INFO] train episode 2732: reward = -121.24, steps = 23 02:01:40 [INFO] train episode 2733: reward = -136.59, steps = 21 02:01:41 [INFO] train episode 2734: reward = -98.64, steps = 18 02:01:43 [INFO] train episode 2735: reward = -96.11, steps = 19 02:01:45 [INFO] train episode 2736: reward = -108.72, steps = 18 02:01:47 [INFO] train episode 2737: reward = -129.92, steps = 22 02:01:50 [INFO] train episode 2738: reward = -190.97, steps = 22 02:01:52 [INFO] train episode 2739: reward = -175.64, steps = 21 02:01:54 [INFO] train episode 2740: reward = -164.36, steps = 21 02:01:56 [INFO] train episode 2741: reward = -120.24, steps = 19 02:01:57 [INFO] train episode 2742: reward = -109.93, steps = 20 02:01:59 [INFO] train episode 2743: reward = -120.52, steps = 19 02:02:03 [INFO] train episode 2744: reward = -174.34, steps = 33 02:02:05 [INFO] train episode 2745: reward = -135.03, steps = 22 02:02:07 [INFO] train episode 2746: reward = -99.67, steps = 24 02:02:09 [INFO] train episode 2747: reward = -77.97, steps = 20 02:02:10 [INFO] train episode 2748: reward = -158.70, steps = 20 02:02:12 [INFO] train episode 2749: reward = -95.12, steps = 22 02:02:14 [INFO] train episode 2750: reward = -136.88, steps = 22 02:02:17 [INFO] train episode 2751: reward = -139.01, steps = 29 02:02:19 [INFO] train episode 2752: reward = -93.69, steps = 21 02:02:21 [INFO] train episode 2753: reward = -66.32, steps = 20 02:02:23 [INFO] train episode 2754: reward = -74.53, steps = 19 02:02:25 [INFO] train episode 2755: reward = -72.63, steps = 18 02:02:26 [INFO] train episode 2756: reward = -77.23, steps = 19 02:02:29 [INFO] train episode 2757: reward = -92.80, steps = 17 02:02:31 [INFO] train episode 2758: reward = -132.86, steps = 20 02:02:33 [INFO] train episode 2759: reward = -239.66, steps = 25 02:02:35 [INFO] train episode 2760: reward = -144.81, steps = 19 02:02:37 [INFO] train episode 2761: reward = -138.90, steps = 21 02:02:39 [INFO] train episode 2762: reward = -113.47, steps = 19 02:02:41 [INFO] train episode 2763: reward = -88.11, steps = 20 02:02:43 [INFO] train episode 2764: reward = -103.65, steps = 20 02:02:44 [INFO] train episode 2765: reward = -104.52, steps = 21 02:02:46 [INFO] train episode 2766: reward = -112.78, steps = 20 02:02:48 [INFO] train episode 2767: reward = -98.74, steps = 19 02:02:50 [INFO] train episode 2768: reward = -117.44, steps = 19 02:02:52 [INFO] train episode 2769: reward = -122.83, steps = 20 02:02:54 [INFO] train episode 2770: reward = -97.26, steps = 19 02:02:56 [INFO] train episode 2771: reward = -121.57, steps = 25 02:02:59 [INFO] train episode 2772: reward = -141.91, steps = 28 02:03:01 [INFO] train episode 2773: reward = -106.74, steps = 19 02:03:03 [INFO] train episode 2774: reward = -143.61, steps = 21 02:03:05 [INFO] train episode 2775: reward = -160.21, steps = 20 02:03:07 [INFO] train episode 2776: reward = -98.58, steps = 26 02:03:10 [INFO] train episode 2777: reward = -118.51, steps = 25 02:03:12 [INFO] train episode 2778: reward = -101.80, steps = 20 02:03:14 [INFO] train episode 2779: reward = -121.35, steps = 20 02:03:16 [INFO] train episode 2780: reward = -112.98, steps = 19 02:03:18 [INFO] train episode 2781: reward = -156.16, steps = 21 02:03:20 [INFO] train episode 2782: reward = -106.06, steps = 20 02:03:22 [INFO] train episode 2783: reward = -126.02, steps = 23 02:03:25 [INFO] train episode 2784: reward = -142.59, steps = 32 02:03:28 [INFO] train episode 2785: reward = -115.91, steps = 27 02:03:30 [INFO] train episode 2786: reward = -185.25, steps = 20 02:03:33 [INFO] train episode 2787: reward = -142.29, steps = 28 02:03:35 [INFO] train episode 2788: reward = -98.44, steps = 22 02:03:37 [INFO] train episode 2789: reward = -128.57, steps = 21 02:03:39 [INFO] train episode 2790: reward = -114.72, steps = 25 02:03:42 [INFO] train episode 2791: reward = -85.78, steps = 21 02:03:44 [INFO] train episode 2792: reward = -93.14, steps = 21 02:03:45 [INFO] train episode 2793: reward = -145.55, steps = 20 02:03:48 [INFO] train episode 2794: reward = -136.99, steps = 19 02:03:50 [INFO] train episode 2795: reward = -111.49, steps = 22 02:03:51 [INFO] train episode 2796: reward = -131.45, steps = 16 02:03:53 [INFO] train episode 2797: reward = -77.38, steps = 19 02:03:55 [INFO] train episode 2798: reward = -104.56, steps = 19 02:03:57 [INFO] train episode 2799: reward = -157.62, steps = 21 02:03:59 [INFO] train episode 2800: reward = -158.64, steps = 25 02:04:01 [INFO] train episode 2801: reward = -122.27, steps = 20 02:04:04 [INFO] train episode 2802: reward = -108.57, steps = 19 02:04:06 [INFO] train episode 2803: reward = -150.44, steps = 19 02:04:07 [INFO] train episode 2804: reward = -90.76, steps = 19 02:04:10 [INFO] train episode 2805: reward = -140.07, steps = 30 02:04:12 [INFO] train episode 2806: reward = -104.09, steps = 19 02:04:14 [INFO] train episode 2807: reward = -124.54, steps = 23 02:04:17 [INFO] train episode 2808: reward = -107.12, steps = 27 02:04:19 [INFO] train episode 2809: reward = -145.61, steps = 27 02:04:22 [INFO] train episode 2810: reward = -177.36, steps = 27 02:04:25 [INFO] train episode 2811: reward = -114.72, steps = 25 02:04:26 [INFO] train episode 2812: reward = -106.36, steps = 19 02:04:28 [INFO] train episode 2813: reward = -80.03, steps = 20 02:04:30 [INFO] train episode 2814: reward = -107.56, steps = 21 02:04:33 [INFO] train episode 2815: reward = -195.39, steps = 28 02:04:35 [INFO] train episode 2816: reward = -96.28, steps = 18 02:04:37 [INFO] train episode 2817: reward = -95.13, steps = 20 02:04:39 [INFO] train episode 2818: reward = -157.29, steps = 23 02:04:41 [INFO] train episode 2819: reward = -112.12, steps = 19 02:04:43 [INFO] train episode 2820: reward = -78.99, steps = 20 02:04:45 [INFO] train episode 2821: reward = -108.26, steps = 19 02:04:47 [INFO] train episode 2822: reward = -136.91, steps = 19 02:04:49 [INFO] train episode 2823: reward = -126.31, steps = 26 02:04:51 [INFO] train episode 2824: reward = -101.43, steps = 20 02:04:53 [INFO] train episode 2825: reward = -103.18, steps = 18 02:04:55 [INFO] train episode 2826: reward = -103.31, steps = 20 02:04:57 [INFO] train episode 2827: reward = -109.37, steps = 21 02:04:59 [INFO] train episode 2828: reward = -110.21, steps = 20 02:05:01 [INFO] train episode 2829: reward = -79.76, steps = 21 02:05:03 [INFO] train episode 2830: reward = -112.84, steps = 19 02:05:06 [INFO] train episode 2831: reward = -114.10, steps = 25 02:05:08 [INFO] train episode 2832: reward = -94.22, steps = 21 02:05:11 [INFO] train episode 2833: reward = -181.98, steps = 32 02:05:13 [INFO] train episode 2834: reward = -136.03, steps = 20 02:05:15 [INFO] train episode 2835: reward = -106.36, steps = 20 02:05:17 [INFO] train episode 2836: reward = -115.74, steps = 20 02:05:19 [INFO] train episode 2837: reward = -75.41, steps = 19 02:05:21 [INFO] train episode 2838: reward = -116.77, steps = 20 02:05:24 [INFO] train episode 2839: reward = -163.77, steps = 32 02:05:26 [INFO] train episode 2840: reward = -134.41, steps = 22 02:05:28 [INFO] train episode 2841: reward = -129.04, steps = 19 02:05:30 [INFO] train episode 2842: reward = -79.59, steps = 20 02:05:32 [INFO] train episode 2843: reward = -155.49, steps = 19 02:05:34 [INFO] train episode 2844: reward = -110.46, steps = 19 02:05:36 [INFO] train episode 2845: reward = -113.72, steps = 21 02:05:39 [INFO] train episode 2846: reward = -129.61, steps = 25 02:05:41 [INFO] train episode 2847: reward = -108.83, steps = 19 02:05:43 [INFO] train episode 2848: reward = -134.63, steps = 23 02:05:45 [INFO] train episode 2849: reward = -150.56, steps = 23 02:05:47 [INFO] train episode 2850: reward = -166.39, steps = 18 02:05:50 [INFO] train episode 2851: reward = -131.77, steps = 23 02:05:52 [INFO] train episode 2852: reward = -127.51, steps = 24 02:05:54 [INFO] train episode 2853: reward = -141.97, steps = 22 02:05:56 [INFO] train episode 2854: reward = -119.19, steps = 18 02:05:58 [INFO] train episode 2855: reward = -212.36, steps = 22 02:06:00 [INFO] train episode 2856: reward = -110.99, steps = 19 02:06:02 [INFO] train episode 2857: reward = -109.86, steps = 19 02:06:04 [INFO] train episode 2858: reward = -112.09, steps = 19 02:06:06 [INFO] train episode 2859: reward = -89.79, steps = 20 02:06:08 [INFO] train episode 2860: reward = -104.71, steps = 19 02:06:10 [INFO] train episode 2861: reward = -88.63, steps = 21 02:06:12 [INFO] train episode 2862: reward = -126.07, steps = 22 02:06:14 [INFO] train episode 2863: reward = -99.91, steps = 20 02:06:16 [INFO] train episode 2864: reward = -147.45, steps = 18 02:06:19 [INFO] train episode 2865: reward = -116.83, steps = 31 02:06:21 [INFO] train episode 2866: reward = -139.55, steps = 21 02:06:22 [INFO] train episode 2867: reward = -87.86, steps = 19 02:06:25 [INFO] train episode 2868: reward = -128.54, steps = 18 02:06:26 [INFO] train episode 2869: reward = -115.73, steps = 19 02:06:29 [INFO] train episode 2870: reward = -130.98, steps = 26 02:06:31 [INFO] train episode 2871: reward = -173.58, steps = 22 02:06:34 [INFO] train episode 2872: reward = -121.00, steps = 27 02:06:37 [INFO] train episode 2873: reward = -152.89, steps = 33 02:06:39 [INFO] train episode 2874: reward = -95.86, steps = 22 02:06:41 [INFO] train episode 2875: reward = -104.24, steps = 21 02:06:43 [INFO] train episode 2876: reward = -97.49, steps = 19 02:06:45 [INFO] train episode 2877: reward = -99.46, steps = 23 02:06:47 [INFO] train episode 2878: reward = -140.66, steps = 21 02:06:50 [INFO] train episode 2879: reward = -147.82, steps = 26 02:06:51 [INFO] train episode 2880: reward = -81.67, steps = 19 02:06:53 [INFO] train episode 2881: reward = -109.27, steps = 22 02:06:56 [INFO] train episode 2882: reward = -159.82, steps = 29 02:06:58 [INFO] train episode 2883: reward = -91.22, steps = 21 02:07:00 [INFO] train episode 2884: reward = -123.64, steps = 20 02:07:02 [INFO] train episode 2885: reward = -127.83, steps = 19 02:07:04 [INFO] train episode 2886: reward = -112.42, steps = 23 02:07:06 [INFO] train episode 2887: reward = -106.27, steps = 20 02:07:08 [INFO] train episode 2888: reward = -121.17, steps = 20 02:07:10 [INFO] train episode 2889: reward = -155.78, steps = 24 02:07:12 [INFO] train episode 2890: reward = -59.14, steps = 19 02:07:15 [INFO] train episode 2891: reward = -115.73, steps = 28 02:07:18 [INFO] train episode 2892: reward = -95.77, steps = 20 02:07:19 [INFO] train episode 2893: reward = -140.30, steps = 19 02:07:22 [INFO] train episode 2894: reward = -170.58, steps = 27 02:07:24 [INFO] train episode 2895: reward = -100.55, steps = 19 02:07:26 [INFO] train episode 2896: reward = -123.93, steps = 19 02:07:28 [INFO] train episode 2897: reward = -107.55, steps = 19 02:07:30 [INFO] train episode 2898: reward = -104.11, steps = 20 02:07:32 [INFO] train episode 2899: reward = -108.29, steps = 20 02:07:34 [INFO] train episode 2900: reward = -88.65, steps = 20 02:07:36 [INFO] train episode 2901: reward = -127.91, steps = 20 02:07:38 [INFO] train episode 2902: reward = -110.20, steps = 19 02:07:40 [INFO] train episode 2903: reward = -87.12, steps = 19 02:07:42 [INFO] train episode 2904: reward = -99.20, steps = 22 02:07:43 [INFO] train episode 2905: reward = -112.97, steps = 19 02:07:46 [INFO] train episode 2906: reward = -155.51, steps = 30 02:07:49 [INFO] train episode 2907: reward = -127.08, steps = 28 02:07:51 [INFO] train episode 2908: reward = -126.66, steps = 23 02:07:53 [INFO] train episode 2909: reward = -97.86, steps = 19 02:07:55 [INFO] train episode 2910: reward = -128.13, steps = 19 02:07:58 [INFO] train episode 2911: reward = -102.35, steps = 25 02:08:00 [INFO] train episode 2912: reward = -194.92, steps = 24 02:08:02 [INFO] train episode 2913: reward = -139.69, steps = 20 02:08:04 [INFO] train episode 2914: reward = -146.61, steps = 26 02:08:06 [INFO] train episode 2915: reward = -115.44, steps = 19 02:08:08 [INFO] train episode 2916: reward = -179.36, steps = 20 02:08:11 [INFO] train episode 2917: reward = -135.94, steps = 28 02:08:13 [INFO] train episode 2918: reward = -139.45, steps = 24 02:08:15 [INFO] train episode 2919: reward = -106.92, steps = 20 02:08:17 [INFO] train episode 2920: reward = -130.22, steps = 19 02:08:19 [INFO] train episode 2921: reward = -122.01, steps = 26 02:08:22 [INFO] train episode 2922: reward = -167.40, steps = 24 02:08:24 [INFO] train episode 2923: reward = -134.05, steps = 21 02:08:26 [INFO] train episode 2924: reward = -131.10, steps = 25 02:08:28 [INFO] train episode 2925: reward = -139.93, steps = 14 02:08:29 [INFO] train episode 2926: reward = -105.09, steps = 18 02:08:32 [INFO] train episode 2927: reward = -149.23, steps = 23 02:08:33 [INFO] train episode 2928: reward = -105.69, steps = 20 02:08:35 [INFO] train episode 2929: reward = -107.06, steps = 19 02:08:37 [INFO] train episode 2930: reward = -170.49, steps = 19 02:08:39 [INFO] train episode 2931: reward = -130.80, steps = 20 02:08:42 [INFO] train episode 2932: reward = -149.51, steps = 28 02:08:44 [INFO] train episode 2933: reward = -101.78, steps = 21 02:08:46 [INFO] train episode 2934: reward = -88.88, steps = 19 02:08:50 [INFO] train episode 2935: reward = -176.51, steps = 32 02:08:52 [INFO] train episode 2936: reward = -119.21, steps = 19 02:08:53 [INFO] train episode 2937: reward = -106.67, steps = 18 02:08:55 [INFO] train episode 2938: reward = -116.26, steps = 20 02:08:58 [INFO] train episode 2939: reward = -160.22, steps = 26 02:09:00 [INFO] train episode 2940: reward = -107.80, steps = 21 02:09:02 [INFO] train episode 2941: reward = -82.97, steps = 19 02:09:04 [INFO] train episode 2942: reward = -124.05, steps = 20 02:09:06 [INFO] train episode 2943: reward = -82.65, steps = 17 02:09:08 [INFO] train episode 2944: reward = -113.24, steps = 25 02:09:10 [INFO] train episode 2945: reward = -102.73, steps = 19 02:09:12 [INFO] train episode 2946: reward = -120.29, steps = 19 02:09:14 [INFO] train episode 2947: reward = -234.01, steps = 24 02:09:16 [INFO] train episode 2948: reward = -205.24, steps = 22 02:09:18 [INFO] train episode 2949: reward = -116.23, steps = 19 02:09:20 [INFO] train episode 2950: reward = -106.67, steps = 20 02:09:22 [INFO] train episode 2951: reward = -75.41, steps = 19 02:09:24 [INFO] train episode 2952: reward = -87.47, steps = 25 02:09:26 [INFO] train episode 2953: reward = -108.35, steps = 19 02:09:28 [INFO] train episode 2954: reward = -118.02, steps = 23 02:09:30 [INFO] train episode 2955: reward = -111.68, steps = 21 02:09:32 [INFO] train episode 2956: reward = -104.70, steps = 20 02:09:35 [INFO] train episode 2957: reward = -68.95, steps = 20 02:09:36 [INFO] train episode 2958: reward = -121.98, steps = 20 02:09:39 [INFO] train episode 2959: reward = -113.28, steps = 18 02:09:40 [INFO] train episode 2960: reward = -112.16, steps = 19 02:09:42 [INFO] train episode 2961: reward = -105.49, steps = 19 02:09:44 [INFO] train episode 2962: reward = -143.23, steps = 20 02:09:46 [INFO] train episode 2963: reward = -86.64, steps = 19 02:09:48 [INFO] train episode 2964: reward = -101.83, steps = 23 02:09:50 [INFO] train episode 2965: reward = -103.24, steps = 24 02:09:52 [INFO] train episode 2966: reward = -124.37, steps = 16 02:09:54 [INFO] train episode 2967: reward = -72.74, steps = 20 02:09:56 [INFO] train episode 2968: reward = -92.36, steps = 19 02:09:58 [INFO] train episode 2969: reward = -104.00, steps = 19 02:09:59 [INFO] train episode 2970: reward = -96.54, steps = 20 02:10:02 [INFO] train episode 2971: reward = -114.71, steps = 30 02:10:04 [INFO] train episode 2972: reward = -109.46, steps = 24 02:10:08 [INFO] train episode 2973: reward = -126.61, steps = 32 02:10:09 [INFO] train episode 2974: reward = -127.18, steps = 16 02:10:11 [INFO] train episode 2975: reward = -128.84, steps = 21 02:10:13 [INFO] train episode 2976: reward = -106.75, steps = 20 02:10:15 [INFO] train episode 2977: reward = -133.76, steps = 24 02:10:18 [INFO] train episode 2978: reward = -166.08, steps = 23 02:10:20 [INFO] train episode 2979: reward = -88.00, steps = 25 02:10:22 [INFO] train episode 2980: reward = -101.90, steps = 20 02:10:24 [INFO] train episode 2981: reward = -104.10, steps = 23 02:10:26 [INFO] train episode 2982: reward = -99.15, steps = 24 02:10:28 [INFO] train episode 2983: reward = -91.80, steps = 19 02:10:30 [INFO] train episode 2984: reward = -73.06, steps = 20 02:10:33 [INFO] train episode 2985: reward = -208.82, steps = 36 02:10:35 [INFO] train episode 2986: reward = -142.57, steps = 19 02:10:37 [INFO] train episode 2987: reward = -114.27, steps = 20 02:10:39 [INFO] train episode 2988: reward = -88.67, steps = 19 02:10:41 [INFO] train episode 2989: reward = -129.83, steps = 19 02:10:43 [INFO] train episode 2990: reward = -224.90, steps = 26 02:10:45 [INFO] train episode 2991: reward = -118.60, steps = 19 02:10:47 [INFO] train episode 2992: reward = -98.61, steps = 21 02:10:49 [INFO] train episode 2993: reward = -88.98, steps = 19 02:10:51 [INFO] train episode 2994: reward = -138.79, steps = 23 02:10:53 [INFO] train episode 2995: reward = -132.07, steps = 22 02:10:56 [INFO] train episode 2996: reward = -161.99, steps = 27 02:10:58 [INFO] train episode 2997: reward = -120.38, steps = 21 02:11:00 [INFO] train episode 2998: reward = -91.43, steps = 24 02:11:02 [INFO] train episode 2999: reward = -83.27, steps = 18 02:11:04 [INFO] train episode 3000: reward = -112.98, steps = 20 02:11:07 [INFO] train episode 3001: reward = -94.60, steps = 20 02:11:09 [INFO] train episode 3002: reward = -95.72, steps = 24 02:11:11 [INFO] train episode 3003: reward = -134.88, steps = 19 02:11:13 [INFO] train episode 3004: reward = -87.93, steps = 23 02:11:15 [INFO] train episode 3005: reward = -113.68, steps = 22 02:11:17 [INFO] train episode 3006: reward = -149.49, steps = 18 02:11:19 [INFO] train episode 3007: reward = -117.06, steps = 22 02:11:21 [INFO] train episode 3008: reward = -99.73, steps = 20 02:11:22 [INFO] train episode 3009: reward = -119.43, steps = 16 02:11:25 [INFO] train episode 3010: reward = -184.41, steps = 22 02:11:27 [INFO] train episode 3011: reward = -149.05, steps = 25 02:11:29 [INFO] train episode 3012: reward = -81.98, steps = 19 02:11:31 [INFO] train episode 3013: reward = -152.11, steps = 29 02:11:33 [INFO] train episode 3014: reward = -147.49, steps = 20 02:11:35 [INFO] train episode 3015: reward = -171.81, steps = 20 02:11:37 [INFO] train episode 3016: reward = -136.15, steps = 16 02:11:39 [INFO] train episode 3017: reward = -127.43, steps = 21 02:11:41 [INFO] train episode 3018: reward = -121.95, steps = 19 02:11:43 [INFO] train episode 3019: reward = -117.42, steps = 18 02:11:45 [INFO] train episode 3020: reward = -107.38, steps = 18 02:11:47 [INFO] train episode 3021: reward = -106.71, steps = 20 02:11:49 [INFO] train episode 3022: reward = -124.61, steps = 25 02:11:51 [INFO] train episode 3023: reward = -154.18, steps = 19 02:11:54 [INFO] train episode 3024: reward = -149.99, steps = 29 02:11:57 [INFO] train episode 3025: reward = -110.61, steps = 23 02:11:59 [INFO] train episode 3026: reward = -118.75, steps = 23 02:12:02 [INFO] train episode 3027: reward = -93.47, steps = 22 02:12:04 [INFO] train episode 3028: reward = -149.80, steps = 27 02:12:06 [INFO] train episode 3029: reward = -117.30, steps = 19 02:12:08 [INFO] train episode 3030: reward = -132.97, steps = 26 02:12:10 [INFO] train episode 3031: reward = -126.56, steps = 20 02:12:13 [INFO] train episode 3032: reward = -142.76, steps = 25 02:12:15 [INFO] train episode 3033: reward = -98.88, steps = 25 02:12:17 [INFO] train episode 3034: reward = -91.71, steps = 19 02:12:19 [INFO] train episode 3035: reward = -139.84, steps = 19 02:12:21 [INFO] train episode 3036: reward = -127.03, steps = 30 02:12:23 [INFO] train episode 3037: reward = -122.22, steps = 20 02:12:25 [INFO] train episode 3038: reward = -153.94, steps = 19 02:12:27 [INFO] train episode 3039: reward = -135.08, steps = 24 02:12:29 [INFO] train episode 3040: reward = -151.09, steps = 22 02:12:32 [INFO] train episode 3041: reward = -132.27, steps = 29 02:12:35 [INFO] train episode 3042: reward = -183.66, steps = 28 02:12:37 [INFO] train episode 3043: reward = -80.15, steps = 23 02:12:40 [INFO] train episode 3044: reward = -105.92, steps = 26 02:12:41 [INFO] train episode 3045: reward = -83.41, steps = 14 02:12:43 [INFO] train episode 3046: reward = -97.86, steps = 21 02:12:46 [INFO] train episode 3047: reward = -184.86, steps = 28 02:12:48 [INFO] train episode 3048: reward = -126.77, steps = 22 02:12:50 [INFO] train episode 3049: reward = -78.75, steps = 19 02:12:52 [INFO] train episode 3050: reward = -156.33, steps = 20 02:12:54 [INFO] train episode 3051: reward = -99.59, steps = 20 02:12:56 [INFO] train episode 3052: reward = -121.54, steps = 20 02:12:58 [INFO] train episode 3053: reward = -104.07, steps = 19 02:13:00 [INFO] train episode 3054: reward = -105.95, steps = 19 02:13:02 [INFO] train episode 3055: reward = -93.12, steps = 20 02:13:03 [INFO] train episode 3056: reward = -105.31, steps = 20 02:13:05 [INFO] train episode 3057: reward = -138.51, steps = 17 02:13:07 [INFO] train episode 3058: reward = -109.09, steps = 16 02:13:09 [INFO] train episode 3059: reward = -203.16, steps = 25 02:13:12 [INFO] train episode 3060: reward = -119.65, steps = 28 02:13:14 [INFO] train episode 3061: reward = -136.41, steps = 21 02:13:16 [INFO] train episode 3062: reward = -128.43, steps = 19 02:13:18 [INFO] train episode 3063: reward = -101.85, steps = 20 02:13:19 [INFO] train episode 3064: reward = -94.55, steps = 19 02:13:21 [INFO] train episode 3065: reward = -135.22, steps = 21 02:13:24 [INFO] train episode 3066: reward = -96.82, steps = 25 02:13:26 [INFO] train episode 3067: reward = -164.41, steps = 28 02:13:29 [INFO] train episode 3068: reward = -125.26, steps = 24 02:13:31 [INFO] train episode 3069: reward = -139.23, steps = 20 02:13:32 [INFO] train episode 3070: reward = -132.22, steps = 19 02:13:34 [INFO] train episode 3071: reward = -100.79, steps = 20 02:13:36 [INFO] train episode 3072: reward = -106.88, steps = 19 02:13:38 [INFO] train episode 3073: reward = -122.19, steps = 26 02:13:40 [INFO] train episode 3074: reward = -139.54, steps = 21 02:13:43 [INFO] train episode 3075: reward = -120.28, steps = 24 02:13:45 [INFO] train episode 3076: reward = -103.26, steps = 23 02:13:47 [INFO] train episode 3077: reward = -96.70, steps = 23 02:13:50 [INFO] train episode 3078: reward = -142.91, steps = 31 02:13:52 [INFO] train episode 3079: reward = -114.98, steps = 19 02:13:54 [INFO] train episode 3080: reward = -117.98, steps = 19 02:13:56 [INFO] train episode 3081: reward = -110.48, steps = 19 02:13:57 [INFO] train episode 3082: reward = -88.08, steps = 19 02:14:00 [INFO] train episode 3083: reward = -148.46, steps = 25 02:14:02 [INFO] train episode 3084: reward = -116.28, steps = 24 02:14:05 [INFO] train episode 3085: reward = -105.53, steps = 24 02:14:07 [INFO] train episode 3086: reward = -128.63, steps = 20 02:14:08 [INFO] train episode 3087: reward = -113.29, steps = 20 02:14:11 [INFO] train episode 3088: reward = -148.43, steps = 24 02:14:12 [INFO] train episode 3089: reward = -137.76, steps = 19 02:14:14 [INFO] train episode 3090: reward = -103.75, steps = 22 02:14:16 [INFO] train episode 3091: reward = -152.03, steps = 21 02:14:18 [INFO] train episode 3092: reward = -197.68, steps = 20 02:14:21 [INFO] train episode 3093: reward = -140.53, steps = 26 02:14:23 [INFO] train episode 3094: reward = -103.17, steps = 19 02:14:25 [INFO] train episode 3095: reward = -86.90, steps = 21 02:14:27 [INFO] train episode 3096: reward = -150.18, steps = 23 02:14:29 [INFO] train episode 3097: reward = -72.86, steps = 19 02:14:31 [INFO] train episode 3098: reward = -139.02, steps = 26 02:14:34 [INFO] train episode 3099: reward = -134.49, steps = 24 02:14:37 [INFO] train episode 3100: reward = -174.83, steps = 30 02:14:39 [INFO] train episode 3101: reward = -102.33, steps = 21 02:14:41 [INFO] train episode 3102: reward = -115.98, steps = 19 02:14:43 [INFO] train episode 3103: reward = -116.89, steps = 22 02:14:45 [INFO] train episode 3104: reward = -129.66, steps = 27 02:14:47 [INFO] train episode 3105: reward = -140.24, steps = 19 02:14:49 [INFO] train episode 3106: reward = -106.60, steps = 21 02:14:51 [INFO] train episode 3107: reward = -111.05, steps = 19 02:14:54 [INFO] train episode 3108: reward = -207.88, steps = 27 02:14:56 [INFO] train episode 3109: reward = -132.33, steps = 26 02:14:58 [INFO] train episode 3110: reward = -121.45, steps = 19 02:15:00 [INFO] train episode 3111: reward = -132.37, steps = 18 02:15:02 [INFO] train episode 3112: reward = -86.03, steps = 21 02:15:05 [INFO] train episode 3113: reward = -136.32, steps = 24 02:15:07 [INFO] train episode 3114: reward = -102.66, steps = 24 02:15:09 [INFO] train episode 3115: reward = -106.44, steps = 19 02:15:10 [INFO] train episode 3116: reward = -109.29, steps = 19 02:15:13 [INFO] train episode 3117: reward = -150.24, steps = 28 02:15:15 [INFO] train episode 3118: reward = -125.86, steps = 21 02:15:18 [INFO] train episode 3119: reward = -124.08, steps = 33 02:15:20 [INFO] train episode 3120: reward = -78.26, steps = 23 02:15:22 [INFO] train episode 3121: reward = -101.18, steps = 20 02:15:24 [INFO] train episode 3122: reward = -150.47, steps = 23 02:15:27 [INFO] train episode 3123: reward = -145.82, steps = 32 02:15:30 [INFO] train episode 3124: reward = -145.91, steps = 19 02:15:31 [INFO] train episode 3125: reward = -103.72, steps = 20 02:15:34 [INFO] train episode 3126: reward = -144.87, steps = 24 02:15:36 [INFO] train episode 3127: reward = -136.23, steps = 28 02:15:38 [INFO] train episode 3128: reward = -103.16, steps = 13 02:15:40 [INFO] train episode 3129: reward = -133.67, steps = 22 02:15:42 [INFO] train episode 3130: reward = -113.26, steps = 20 02:15:43 [INFO] train episode 3131: reward = -107.38, steps = 19 02:15:46 [INFO] train episode 3132: reward = -108.96, steps = 19 02:15:47 [INFO] train episode 3133: reward = -155.58, steps = 19 02:15:49 [INFO] train episode 3134: reward = -100.19, steps = 18 02:15:51 [INFO] train episode 3135: reward = -126.10, steps = 23 02:15:53 [INFO] train episode 3136: reward = -81.85, steps = 20 02:15:55 [INFO] train episode 3137: reward = -142.42, steps = 21 02:15:57 [INFO] train episode 3138: reward = -119.27, steps = 19 02:15:59 [INFO] train episode 3139: reward = -107.12, steps = 24 02:16:01 [INFO] train episode 3140: reward = -92.53, steps = 20 02:16:04 [INFO] train episode 3141: reward = -112.45, steps = 24 02:16:07 [INFO] train episode 3142: reward = -163.69, steps = 30 02:16:09 [INFO] train episode 3143: reward = -146.72, steps = 25 02:16:11 [INFO] train episode 3144: reward = -143.79, steps = 20 02:16:13 [INFO] train episode 3145: reward = -147.85, steps = 19 02:16:15 [INFO] train episode 3146: reward = -104.65, steps = 23 02:16:17 [INFO] train episode 3147: reward = -116.16, steps = 23 02:16:20 [INFO] train episode 3148: reward = -141.50, steps = 27 02:16:22 [INFO] train episode 3149: reward = -111.73, steps = 22 02:16:24 [INFO] train episode 3150: reward = -119.28, steps = 20 02:16:26 [INFO] train episode 3151: reward = -149.62, steps = 23 02:16:28 [INFO] train episode 3152: reward = -114.47, steps = 19 02:16:30 [INFO] train episode 3153: reward = -127.59, steps = 23 02:16:32 [INFO] train episode 3154: reward = -141.84, steps = 20 02:16:35 [INFO] train episode 3155: reward = -104.01, steps = 24 02:16:36 [INFO] train episode 3156: reward = -119.33, steps = 20 02:16:41 [INFO] train episode 3157: reward = -147.25, steps = 43 02:16:43 [INFO] train episode 3158: reward = -99.52, steps = 25 02:16:45 [INFO] train episode 3159: reward = -89.60, steps = 20 02:16:47 [INFO] train episode 3160: reward = -129.35, steps = 21 02:16:48 [INFO] train episode 3161: reward = -119.06, steps = 20 02:16:50 [INFO] train episode 3162: reward = -139.26, steps = 19 02:16:53 [INFO] train episode 3163: reward = -179.32, steps = 28 02:16:56 [INFO] train episode 3164: reward = -132.40, steps = 26 02:16:58 [INFO] train episode 3165: reward = -181.13, steps = 21 02:16:59 [INFO] train episode 3166: reward = -144.09, steps = 20 02:17:02 [INFO] train episode 3167: reward = -145.30, steps = 30 02:17:04 [INFO] train episode 3168: reward = -141.95, steps = 19 02:17:06 [INFO] train episode 3169: reward = -72.43, steps = 18 02:17:08 [INFO] train episode 3170: reward = -156.92, steps = 21 02:17:10 [INFO] train episode 3171: reward = -101.22, steps = 26 02:17:12 [INFO] train episode 3172: reward = -124.36, steps = 21 02:17:15 [INFO] train episode 3173: reward = -147.53, steps = 23 02:17:17 [INFO] train episode 3174: reward = -134.57, steps = 22 02:17:19 [INFO] train episode 3175: reward = -125.98, steps = 22 02:17:21 [INFO] train episode 3176: reward = -166.85, steps = 25 02:17:24 [INFO] train episode 3177: reward = -171.67, steps = 30 02:17:26 [INFO] train episode 3178: reward = -88.42, steps = 18 02:17:30 [INFO] train episode 3179: reward = -218.99, steps = 35 02:17:32 [INFO] train episode 3180: reward = -168.07, steps = 25 02:17:34 [INFO] train episode 3181: reward = -87.72, steps = 18 02:17:36 [INFO] train episode 3182: reward = -131.25, steps = 21 02:17:37 [INFO] train episode 3183: reward = -100.37, steps = 19 02:17:40 [INFO] train episode 3184: reward = -115.45, steps = 27 02:17:43 [INFO] train episode 3185: reward = -174.80, steps = 35 02:17:45 [INFO] train episode 3186: reward = -129.11, steps = 23 02:17:47 [INFO] train episode 3187: reward = -121.11, steps = 21 02:17:49 [INFO] train episode 3188: reward = -91.57, steps = 19 02:17:51 [INFO] train episode 3189: reward = -92.17, steps = 20 02:17:53 [INFO] train episode 3190: reward = -129.85, steps = 19 02:17:55 [INFO] train episode 3191: reward = -112.98, steps = 25 02:17:57 [INFO] train episode 3192: reward = -107.46, steps = 19 02:17:58 [INFO] train episode 3193: reward = -135.85, steps = 19 02:18:00 [INFO] train episode 3194: reward = -124.57, steps = 20 02:18:03 [INFO] train episode 3195: reward = -77.60, steps = 20 02:18:05 [INFO] train episode 3196: reward = -159.55, steps = 29 02:18:09 [INFO] train episode 3197: reward = -132.07, steps = 27 02:18:10 [INFO] train episode 3198: reward = -103.01, steps = 14 02:18:12 [INFO] train episode 3199: reward = -135.21, steps = 19 02:18:14 [INFO] train episode 3200: reward = -117.99, steps = 20 02:18:16 [INFO] train episode 3201: reward = -114.84, steps = 24 02:18:18 [INFO] train episode 3202: reward = -98.38, steps = 24 02:18:21 [INFO] train episode 3203: reward = -56.21, steps = 21 02:18:24 [INFO] train episode 3204: reward = -144.03, steps = 31 02:18:25 [INFO] train episode 3205: reward = -124.33, steps = 18 02:18:27 [INFO] train episode 3206: reward = -100.56, steps = 20 02:18:29 [INFO] train episode 3207: reward = -158.84, steps = 20 02:18:31 [INFO] train episode 3208: reward = -123.75, steps = 19 02:18:32 [INFO] train episode 3209: reward = -94.99, steps = 16 02:18:34 [INFO] train episode 3210: reward = -111.21, steps = 21 02:18:37 [INFO] train episode 3211: reward = -212.92, steps = 24 02:18:39 [INFO] train episode 3212: reward = -118.90, steps = 24 02:18:42 [INFO] train episode 3213: reward = -100.85, steps = 24 02:18:43 [INFO] train episode 3214: reward = -107.46, steps = 19 02:18:46 [INFO] train episode 3215: reward = -116.87, steps = 23 02:18:47 [INFO] train episode 3216: reward = -137.32, steps = 19 02:18:50 [INFO] train episode 3217: reward = -106.79, steps = 28 02:18:52 [INFO] train episode 3218: reward = -94.06, steps = 21 02:18:55 [INFO] train episode 3219: reward = -72.22, steps = 25 02:18:58 [INFO] train episode 3220: reward = -95.36, steps = 33 02:19:01 [INFO] train episode 3221: reward = -266.15, steps = 28 02:19:03 [INFO] train episode 3222: reward = -116.82, steps = 27 02:19:05 [INFO] train episode 3223: reward = -127.86, steps = 23 02:19:08 [INFO] train episode 3224: reward = -104.86, steps = 26 02:19:10 [INFO] train episode 3225: reward = -177.07, steps = 22 02:19:12 [INFO] train episode 3226: reward = -108.76, steps = 20 02:19:14 [INFO] train episode 3227: reward = -230.90, steps = 18 02:19:15 [INFO] train episode 3228: reward = -74.60, steps = 15 02:19:17 [INFO] train episode 3229: reward = -117.71, steps = 19 02:19:19 [INFO] train episode 3230: reward = -122.29, steps = 19 02:19:21 [INFO] train episode 3231: reward = -134.41, steps = 25 02:19:24 [INFO] train episode 3232: reward = -112.07, steps = 28 02:19:25 [INFO] train episode 3233: reward = -117.84, steps = 19 02:19:28 [INFO] train episode 3234: reward = -100.88, steps = 25 02:19:30 [INFO] train episode 3235: reward = -97.71, steps = 23 02:19:32 [INFO] train episode 3236: reward = -136.94, steps = 20 02:19:34 [INFO] train episode 3237: reward = -151.58, steps = 19 02:19:36 [INFO] train episode 3238: reward = -149.91, steps = 30 02:19:38 [INFO] train episode 3239: reward = -134.77, steps = 22 02:19:40 [INFO] train episode 3240: reward = -123.92, steps = 19 02:19:42 [INFO] train episode 3241: reward = -98.98, steps = 25 02:19:44 [INFO] train episode 3242: reward = -128.36, steps = 19 02:19:46 [INFO] train episode 3243: reward = -93.62, steps = 21 02:19:49 [INFO] train episode 3244: reward = -117.91, steps = 25 02:19:50 [INFO] train episode 3245: reward = -126.15, steps = 19 02:19:53 [INFO] train episode 3246: reward = -141.87, steps = 25 02:19:54 [INFO] train episode 3247: reward = -97.43, steps = 17 02:19:56 [INFO] train episode 3248: reward = -116.64, steps = 25 02:19:58 [INFO] train episode 3249: reward = -76.65, steps = 20 02:20:01 [INFO] train episode 3250: reward = -121.75, steps = 32 02:20:04 [INFO] train episode 3251: reward = -82.63, steps = 24 02:20:06 [INFO] train episode 3252: reward = -103.76, steps = 20 02:20:07 [INFO] train episode 3253: reward = -108.24, steps = 19 02:20:09 [INFO] train episode 3254: reward = -110.10, steps = 22 02:20:11 [INFO] train episode 3255: reward = -110.99, steps = 21 02:20:14 [INFO] train episode 3256: reward = -132.08, steps = 29 02:20:16 [INFO] train episode 3257: reward = -110.82, steps = 21 02:20:18 [INFO] train episode 3258: reward = -150.63, steps = 24 02:20:20 [INFO] train episode 3259: reward = -97.57, steps = 20 02:20:22 [INFO] train episode 3260: reward = -97.96, steps = 21 02:20:24 [INFO] train episode 3261: reward = -155.62, steps = 23 02:20:26 [INFO] train episode 3262: reward = -104.22, steps = 23 02:20:28 [INFO] train episode 3263: reward = -142.80, steps = 19 02:20:30 [INFO] train episode 3264: reward = -92.67, steps = 19 02:20:32 [INFO] train episode 3265: reward = -162.72, steps = 24 02:20:36 [INFO] train episode 3266: reward = -169.41, steps = 29 02:20:38 [INFO] train episode 3267: reward = -142.58, steps = 21 02:20:41 [INFO] train episode 3268: reward = -115.28, steps = 24 02:20:43 [INFO] train episode 3269: reward = -95.15, steps = 27 02:20:45 [INFO] train episode 3270: reward = -142.63, steps = 20 02:20:47 [INFO] train episode 3271: reward = -127.71, steps = 19 02:20:50 [INFO] train episode 3272: reward = -129.32, steps = 28 02:20:52 [INFO] train episode 3273: reward = -142.90, steps = 20 02:20:54 [INFO] train episode 3274: reward = -68.58, steps = 21 02:20:58 [INFO] train episode 3275: reward = -128.23, steps = 27 02:20:59 [INFO] train episode 3276: reward = -153.71, steps = 15 02:21:01 [INFO] train episode 3277: reward = -102.65, steps = 16 02:21:03 [INFO] train episode 3278: reward = -115.39, steps = 22 02:21:05 [INFO] train episode 3279: reward = -163.21, steps = 28 02:21:07 [INFO] train episode 3280: reward = -122.33, steps = 23 02:21:10 [INFO] train episode 3281: reward = -166.59, steps = 23 02:21:12 [INFO] train episode 3282: reward = -108.25, steps = 22 02:21:16 [INFO] train episode 3283: reward = -143.36, steps = 29 02:21:18 [INFO] train episode 3284: reward = -92.78, steps = 21 02:21:19 [INFO] train episode 3285: reward = -85.41, steps = 19 02:21:22 [INFO] train episode 3286: reward = -124.04, steps = 24 02:21:24 [INFO] train episode 3287: reward = -119.20, steps = 20 02:21:25 [INFO] train episode 3288: reward = -145.93, steps = 20 02:21:28 [INFO] train episode 3289: reward = -182.79, steps = 28 02:21:30 [INFO] train episode 3290: reward = -105.70, steps = 19 02:21:32 [INFO] train episode 3291: reward = -87.18, steps = 20 02:21:34 [INFO] train episode 3292: reward = -87.46, steps = 19 02:21:36 [INFO] train episode 3293: reward = -109.15, steps = 27 02:21:38 [INFO] train episode 3294: reward = -132.28, steps = 19 02:21:40 [INFO] train episode 3295: reward = -193.25, steps = 25 02:21:42 [INFO] train episode 3296: reward = -119.84, steps = 19 02:21:44 [INFO] train episode 3297: reward = -123.15, steps = 19 02:21:46 [INFO] train episode 3298: reward = -102.58, steps = 23 02:21:49 [INFO] train episode 3299: reward = -125.36, steps = 20 02:21:51 [INFO] train episode 3300: reward = -144.30, steps = 27 02:21:54 [INFO] train episode 3301: reward = -134.89, steps = 28 02:21:55 [INFO] train episode 3302: reward = -129.45, steps = 19 02:21:57 [INFO] train episode 3303: reward = -106.84, steps = 19 02:21:59 [INFO] train episode 3304: reward = -114.36, steps = 24 02:22:02 [INFO] train episode 3305: reward = -133.48, steps = 25 02:22:04 [INFO] train episode 3306: reward = -101.92, steps = 21 02:22:07 [INFO] train episode 3307: reward = -116.39, steps = 30 02:22:09 [INFO] train episode 3308: reward = -139.91, steps = 21 02:22:11 [INFO] train episode 3309: reward = -85.57, steps = 26 02:22:13 [INFO] train episode 3310: reward = -87.12, steps = 23 02:22:16 [INFO] train episode 3311: reward = -125.66, steps = 26 02:22:18 [INFO] train episode 3312: reward = -143.82, steps = 25 02:22:20 [INFO] train episode 3313: reward = -144.57, steps = 21 02:22:23 [INFO] train episode 3314: reward = -202.85, steps = 30 02:22:25 [INFO] train episode 3315: reward = -113.74, steps = 20 02:22:27 [INFO] train episode 3316: reward = -109.45, steps = 24 02:22:29 [INFO] train episode 3317: reward = -146.88, steps = 21 02:22:32 [INFO] train episode 3318: reward = -162.92, steps = 31 02:22:34 [INFO] train episode 3319: reward = -121.93, steps = 21 02:22:36 [INFO] train episode 3320: reward = -91.89, steps = 21 02:22:38 [INFO] train episode 3321: reward = -114.82, steps = 20 02:22:40 [INFO] train episode 3322: reward = -131.58, steps = 19 02:22:42 [INFO] train episode 3323: reward = -125.81, steps = 21 02:22:44 [INFO] train episode 3324: reward = -169.27, steps = 28 02:22:47 [INFO] train episode 3325: reward = -89.46, steps = 31 02:22:49 [INFO] train episode 3326: reward = -101.05, steps = 19 02:22:51 [INFO] train episode 3327: reward = -103.61, steps = 24 02:22:53 [INFO] train episode 3328: reward = -154.54, steps = 21 02:22:56 [INFO] train episode 3329: reward = -130.54, steps = 31 02:23:00 [INFO] train episode 3330: reward = -253.12, steps = 41 02:23:02 [INFO] train episode 3331: reward = -98.83, steps = 22 02:23:04 [INFO] train episode 3332: reward = -147.88, steps = 19 02:23:06 [INFO] train episode 3333: reward = -141.08, steps = 20 02:23:07 [INFO] train episode 3334: reward = -101.90, steps = 14 02:23:09 [INFO] train episode 3335: reward = -126.76, steps = 24 02:23:11 [INFO] train episode 3336: reward = -108.54, steps = 19 02:23:14 [INFO] train episode 3337: reward = -141.92, steps = 23 02:23:16 [INFO] train episode 3338: reward = -132.91, steps = 22 02:23:19 [INFO] train episode 3339: reward = -134.50, steps = 31 02:23:20 [INFO] train episode 3340: reward = -107.55, steps = 20 02:23:22 [INFO] train episode 3341: reward = -70.11, steps = 19 02:23:25 [INFO] train episode 3342: reward = -144.29, steps = 33 02:23:27 [INFO] train episode 3343: reward = -129.33, steps = 21 02:23:29 [INFO] train episode 3344: reward = -139.55, steps = 20 02:23:33 [INFO] train episode 3345: reward = -131.14, steps = 33 02:23:35 [INFO] train episode 3346: reward = -89.20, steps = 22 02:23:36 [INFO] train episode 3347: reward = -93.81, steps = 19 02:23:38 [INFO] train episode 3348: reward = -131.09, steps = 20 02:23:40 [INFO] train episode 3349: reward = -117.01, steps = 23 02:23:42 [INFO] train episode 3350: reward = -100.09, steps = 19 02:23:45 [INFO] train episode 3351: reward = -156.81, steps = 30 02:23:48 [INFO] train episode 3352: reward = -184.94, steps = 31 02:23:51 [INFO] train episode 3353: reward = -135.85, steps = 22 02:23:53 [INFO] train episode 3354: reward = -129.92, steps = 23 02:23:55 [INFO] train episode 3355: reward = -106.91, steps = 20 02:23:56 [INFO] train episode 3356: reward = -129.68, steps = 19 02:23:59 [INFO] train episode 3357: reward = -104.31, steps = 27 02:24:01 [INFO] train episode 3358: reward = -142.40, steps = 20 02:24:03 [INFO] train episode 3359: reward = -200.37, steps = 26 02:24:05 [INFO] train episode 3360: reward = -115.60, steps = 22 02:24:07 [INFO] train episode 3361: reward = -113.50, steps = 22 02:24:09 [INFO] train episode 3362: reward = -89.03, steps = 23 02:24:11 [INFO] train episode 3363: reward = -209.53, steps = 20 02:24:14 [INFO] train episode 3364: reward = -143.31, steps = 34 02:24:16 [INFO] train episode 3365: reward = -116.08, steps = 18 02:24:19 [INFO] train episode 3366: reward = -115.18, steps = 21 02:24:21 [INFO] train episode 3367: reward = -170.43, steps = 21 02:24:24 [INFO] train episode 3368: reward = -132.63, steps = 29 02:24:26 [INFO] train episode 3369: reward = -106.50, steps = 22 02:24:28 [INFO] train episode 3370: reward = -218.48, steps = 32 02:24:31 [INFO] train episode 3371: reward = -117.01, steps = 25 02:24:33 [INFO] train episode 3372: reward = -164.65, steps = 23 02:24:35 [INFO] train episode 3373: reward = -153.73, steps = 27 02:24:37 [INFO] train episode 3374: reward = -111.22, steps = 20 02:24:39 [INFO] train episode 3375: reward = -108.28, steps = 19 02:24:42 [INFO] train episode 3376: reward = -137.24, steps = 24 02:24:45 [INFO] train episode 3377: reward = -143.98, steps = 30 02:24:47 [INFO] train episode 3378: reward = -107.65, steps = 21 02:24:48 [INFO] train episode 3379: reward = -96.93, steps = 18 02:24:50 [INFO] train episode 3380: reward = -143.23, steps = 19 02:24:52 [INFO] train episode 3381: reward = -100.52, steps = 17 02:24:55 [INFO] train episode 3382: reward = -127.79, steps = 39 02:24:58 [INFO] train episode 3383: reward = -132.25, steps = 20 02:25:00 [INFO] train episode 3384: reward = -109.72, steps = 20 02:25:01 [INFO] train episode 3385: reward = -112.44, steps = 19 02:25:04 [INFO] train episode 3386: reward = -165.00, steps = 24 02:25:05 [INFO] train episode 3387: reward = -89.10, steps = 20 02:25:07 [INFO] train episode 3388: reward = -126.89, steps = 23 02:25:10 [INFO] train episode 3389: reward = -156.25, steps = 27 02:25:12 [INFO] train episode 3390: reward = -125.32, steps = 19 02:25:14 [INFO] train episode 3391: reward = -93.93, steps = 24 02:25:17 [INFO] train episode 3392: reward = -103.69, steps = 29 02:25:19 [INFO] train episode 3393: reward = -136.20, steps = 20 02:25:21 [INFO] train episode 3394: reward = -123.03, steps = 23 02:25:23 [INFO] train episode 3395: reward = -123.40, steps = 23 02:25:25 [INFO] train episode 3396: reward = -88.19, steps = 24 02:25:27 [INFO] train episode 3397: reward = -110.70, steps = 22 02:25:29 [INFO] train episode 3398: reward = -131.96, steps = 24 02:25:32 [INFO] train episode 3399: reward = -133.57, steps = 25 02:25:34 [INFO] train episode 3400: reward = -134.68, steps = 19 02:25:36 [INFO] train episode 3401: reward = -128.65, steps = 28 02:25:38 [INFO] train episode 3402: reward = -107.90, steps = 22 02:25:40 [INFO] train episode 3403: reward = -148.91, steps = 21 02:25:43 [INFO] train episode 3404: reward = -170.10, steps = 33 02:25:45 [INFO] train episode 3405: reward = -115.29, steps = 18 02:25:47 [INFO] train episode 3406: reward = -121.19, steps = 21 02:25:49 [INFO] train episode 3407: reward = -162.61, steps = 20 02:25:51 [INFO] train episode 3408: reward = -117.91, steps = 22 02:25:53 [INFO] train episode 3409: reward = -153.94, steps = 26 02:25:55 [INFO] train episode 3410: reward = -126.48, steps = 23 02:25:57 [INFO] train episode 3411: reward = -110.84, steps = 22 02:25:59 [INFO] train episode 3412: reward = -120.11, steps = 19 02:26:02 [INFO] train episode 3413: reward = -138.66, steps = 32 02:26:04 [INFO] train episode 3414: reward = -109.70, steps = 22 02:26:07 [INFO] train episode 3415: reward = -157.69, steps = 25 02:26:08 [INFO] train episode 3416: reward = -88.23, steps = 19 02:26:11 [INFO] train episode 3417: reward = -154.77, steps = 27 02:26:13 [INFO] train episode 3418: reward = -125.17, steps = 27 02:26:15 [INFO] train episode 3419: reward = -100.12, steps = 21 02:26:17 [INFO] train episode 3420: reward = -124.10, steps = 22 02:26:20 [INFO] train episode 3421: reward = -121.23, steps = 27 02:26:23 [INFO] train episode 3422: reward = -176.74, steps = 33 02:26:25 [INFO] train episode 3423: reward = -143.80, steps = 24 02:26:28 [INFO] train episode 3424: reward = -186.16, steps = 32 02:26:30 [INFO] train episode 3425: reward = -163.55, steps = 19 02:26:32 [INFO] train episode 3426: reward = -122.23, steps = 21 02:26:34 [INFO] train episode 3427: reward = -156.55, steps = 19 02:26:36 [INFO] train episode 3428: reward = -211.98, steps = 25 02:26:38 [INFO] train episode 3429: reward = -149.81, steps = 20 02:26:40 [INFO] train episode 3430: reward = -120.07, steps = 28 02:26:43 [INFO] train episode 3431: reward = -135.43, steps = 27 02:26:45 [INFO] train episode 3432: reward = -158.93, steps = 28 02:26:47 [INFO] train episode 3433: reward = -161.14, steps = 18 02:26:49 [INFO] train episode 3434: reward = -159.05, steps = 20 02:26:51 [INFO] train episode 3435: reward = -157.36, steps = 26 02:26:54 [INFO] train episode 3436: reward = -126.58, steps = 27 02:26:58 [INFO] train episode 3437: reward = -155.72, steps = 43 02:27:00 [INFO] train episode 3438: reward = -137.56, steps = 27 02:27:02 [INFO] train episode 3439: reward = -235.58, steps = 21 02:27:04 [INFO] train episode 3440: reward = -102.93, steps = 19 02:27:06 [INFO] train episode 3441: reward = -89.04, steps = 24 02:27:08 [INFO] train episode 3442: reward = -159.95, steps = 20 02:27:10 [INFO] train episode 3443: reward = -91.07, steps = 17 02:27:12 [INFO] train episode 3444: reward = -93.40, steps = 19 02:27:14 [INFO] train episode 3445: reward = -94.87, steps = 21 02:27:16 [INFO] train episode 3446: reward = -115.67, steps = 28 02:27:19 [INFO] train episode 3447: reward = -110.48, steps = 25 02:27:22 [INFO] train episode 3448: reward = -120.68, steps = 27 02:27:24 [INFO] train episode 3449: reward = -104.90, steps = 21 02:27:26 [INFO] train episode 3450: reward = -153.37, steps = 19 02:27:28 [INFO] train episode 3451: reward = -190.92, steps = 27 02:27:31 [INFO] train episode 3452: reward = -101.79, steps = 19 02:27:33 [INFO] train episode 3453: reward = -91.64, steps = 23 02:27:35 [INFO] train episode 3454: reward = -104.38, steps = 20 02:27:36 [INFO] train episode 3455: reward = -170.64, steps = 21 02:27:38 [INFO] train episode 3456: reward = -114.55, steps = 20 02:27:40 [INFO] train episode 3457: reward = -102.10, steps = 22 02:27:42 [INFO] train episode 3458: reward = -230.40, steps = 24 02:27:45 [INFO] train episode 3459: reward = -125.54, steps = 24 02:27:47 [INFO] train episode 3460: reward = -135.77, steps = 21 02:27:49 [INFO] train episode 3461: reward = -117.12, steps = 20 02:27:51 [INFO] train episode 3462: reward = -107.79, steps = 23 02:27:53 [INFO] train episode 3463: reward = -139.06, steps = 24 02:27:55 [INFO] train episode 3464: reward = -174.50, steps = 24 02:27:57 [INFO] train episode 3465: reward = -105.96, steps = 19 02:27:59 [INFO] train episode 3466: reward = -101.57, steps = 20 02:28:01 [INFO] train episode 3467: reward = -86.52, steps = 23 02:28:05 [INFO] train episode 3468: reward = -147.07, steps = 34 02:28:07 [INFO] train episode 3469: reward = -184.55, steps = 26 02:28:09 [INFO] train episode 3470: reward = -143.87, steps = 22 02:28:11 [INFO] train episode 3471: reward = -195.36, steps = 19 02:28:13 [INFO] train episode 3472: reward = -97.62, steps = 24 02:28:14 [INFO] train episode 3473: reward = -60.37, steps = 14 02:28:16 [INFO] train episode 3474: reward = -125.77, steps = 26 02:28:19 [INFO] train episode 3475: reward = -101.23, steps = 23 02:28:21 [INFO] train episode 3476: reward = -74.60, steps = 20 02:28:22 [INFO] train episode 3477: reward = -103.81, steps = 19 02:28:25 [INFO] train episode 3478: reward = -117.00, steps = 23 02:28:26 [INFO] train episode 3479: reward = -133.14, steps = 18 02:28:28 [INFO] train episode 3480: reward = -142.37, steps = 24 02:28:30 [INFO] train episode 3481: reward = -106.46, steps = 23 02:28:33 [INFO] train episode 3482: reward = -216.63, steps = 27 02:28:35 [INFO] train episode 3483: reward = -86.78, steps = 19 02:28:37 [INFO] train episode 3484: reward = -73.70, steps = 20 02:28:39 [INFO] train episode 3485: reward = -159.36, steps = 23 02:28:42 [INFO] train episode 3486: reward = -123.42, steps = 36 02:28:44 [INFO] train episode 3487: reward = -121.51, steps = 24 02:28:46 [INFO] train episode 3488: reward = -129.58, steps = 20 02:28:49 [INFO] train episode 3489: reward = -139.30, steps = 34 02:28:51 [INFO] train episode 3490: reward = -111.02, steps = 20 02:28:53 [INFO] train episode 3491: reward = -131.07, steps = 20 02:28:56 [INFO] train episode 3492: reward = -175.64, steps = 30 02:28:58 [INFO] train episode 3493: reward = -98.74, steps = 21 02:29:00 [INFO] train episode 3494: reward = -127.02, steps = 23 02:29:03 [INFO] train episode 3495: reward = -137.63, steps = 27 02:29:06 [INFO] train episode 3496: reward = -105.63, steps = 28 02:29:08 [INFO] train episode 3497: reward = -170.21, steps = 22 02:29:11 [INFO] train episode 3498: reward = -118.50, steps = 24 02:29:12 [INFO] train episode 3499: reward = -132.86, steps = 19 02:29:14 [INFO] train episode 3500: reward = -114.95, steps = 21 02:29:16 [INFO] train episode 3501: reward = -103.12, steps = 19 02:29:18 [INFO] train episode 3502: reward = -141.02, steps = 24 02:29:20 [INFO] train episode 3503: reward = -169.86, steps = 22 02:29:22 [INFO] train episode 3504: reward = -139.88, steps = 20 02:29:25 [INFO] train episode 3505: reward = -155.36, steps = 29 02:29:28 [INFO] train episode 3506: reward = -154.64, steps = 25 02:29:29 [INFO] train episode 3507: reward = -131.44, steps = 20 02:29:32 [INFO] train episode 3508: reward = -115.13, steps = 23 02:29:33 [INFO] train episode 3509: reward = -149.14, steps = 20 02:29:36 [INFO] train episode 3510: reward = -167.49, steps = 25 02:29:38 [INFO] train episode 3511: reward = -137.00, steps = 23 02:29:40 [INFO] train episode 3512: reward = -108.98, steps = 26 02:29:42 [INFO] train episode 3513: reward = -122.11, steps = 19 02:29:45 [INFO] train episode 3514: reward = -170.70, steps = 27 02:29:47 [INFO] train episode 3515: reward = -185.76, steps = 30 02:29:50 [INFO] train episode 3516: reward = -163.20, steps = 26 02:29:52 [INFO] train episode 3517: reward = -97.37, steps = 23 02:29:54 [INFO] train episode 3518: reward = -130.84, steps = 25 02:29:56 [INFO] train episode 3519: reward = -192.76, steps = 22 02:29:58 [INFO] train episode 3520: reward = -103.83, steps = 20 02:30:00 [INFO] train episode 3521: reward = -159.56, steps = 21 02:30:02 [INFO] train episode 3522: reward = -155.59, steps = 19 02:30:04 [INFO] train episode 3523: reward = -89.54, steps = 28 02:30:07 [INFO] train episode 3524: reward = -161.35, steps = 29 02:30:10 [INFO] train episode 3525: reward = -123.45, steps = 26 02:30:12 [INFO] train episode 3526: reward = -131.18, steps = 19 02:30:14 [INFO] train episode 3527: reward = -171.85, steps = 19 02:30:16 [INFO] train episode 3528: reward = -115.32, steps = 24 02:30:19 [INFO] train episode 3529: reward = -107.42, steps = 30 02:30:24 [INFO] train episode 3530: reward = -210.50, steps = 40 02:30:27 [INFO] train episode 3531: reward = -169.35, steps = 30 02:30:30 [INFO] train episode 3532: reward = -115.50, steps = 36 02:30:32 [INFO] train episode 3533: reward = -127.92, steps = 20 02:30:36 [INFO] train episode 3534: reward = -98.63, steps = 20 02:30:41 [INFO] train episode 3535: reward = -135.05, steps = 21 02:30:45 [INFO] train episode 3536: reward = -121.34, steps = 22 02:30:50 [INFO] train episode 3537: reward = -176.16, steps = 31 02:30:53 [INFO] train episode 3538: reward = -151.51, steps = 19 02:30:56 [INFO] train episode 3539: reward = -96.74, steps = 21 02:31:00 [INFO] train episode 3540: reward = -127.44, steps = 22 02:31:05 [INFO] train episode 3541: reward = -118.14, steps = 32 02:31:09 [INFO] train episode 3542: reward = -158.94, steps = 25 02:31:13 [INFO] train episode 3543: reward = -120.15, steps = 27 02:31:17 [INFO] train episode 3544: reward = -139.36, steps = 25 02:31:22 [INFO] train episode 3545: reward = -175.21, steps = 33 02:31:25 [INFO] train episode 3546: reward = -160.34, steps = 22 02:31:27 [INFO] train episode 3547: reward = -145.70, steps = 19 02:31:29 [INFO] train episode 3548: reward = -80.50, steps = 19 02:31:30 [INFO] train episode 3549: reward = -103.48, steps = 19 02:31:32 [INFO] train episode 3550: reward = -117.53, steps = 22 02:31:34 [INFO] train episode 3551: reward = -153.17, steps = 17 02:31:36 [INFO] train episode 3552: reward = -111.94, steps = 22 02:31:39 [INFO] train episode 3553: reward = -138.29, steps = 28 02:31:41 [INFO] train episode 3554: reward = -132.58, steps = 25 02:31:43 [INFO] train episode 3555: reward = -112.99, steps = 22 02:31:45 [INFO] train episode 3556: reward = -107.98, steps = 25 02:31:47 [INFO] train episode 3557: reward = -160.06, steps = 26 02:31:49 [INFO] train episode 3558: reward = -150.98, steps = 23 02:31:53 [INFO] train episode 3559: reward = -143.86, steps = 36 02:31:54 [INFO] train episode 3560: reward = -113.66, steps = 19 02:31:56 [INFO] train episode 3561: reward = -103.37, steps = 19 02:31:58 [INFO] train episode 3562: reward = -111.30, steps = 19 02:32:00 [INFO] train episode 3563: reward = -164.29, steps = 30 02:32:02 [INFO] train episode 3564: reward = -105.96, steps = 23 02:32:04 [INFO] train episode 3565: reward = -136.71, steps = 26 02:32:06 [INFO] train episode 3566: reward = -179.97, steps = 19 02:32:08 [INFO] train episode 3567: reward = -77.68, steps = 18 02:32:10 [INFO] train episode 3568: reward = -86.83, steps = 19 02:32:11 [INFO] train episode 3569: reward = -147.30, steps = 19 02:32:14 [INFO] train episode 3570: reward = -137.29, steps = 25 02:32:16 [INFO] train episode 3571: reward = -129.87, steps = 24 02:32:17 [INFO] train episode 3572: reward = -105.07, steps = 20 02:32:19 [INFO] train episode 3573: reward = -132.45, steps = 19 02:32:22 [INFO] train episode 3574: reward = -187.41, steps = 34 02:32:25 [INFO] train episode 3575: reward = -124.66, steps = 28 02:32:26 [INFO] train episode 3576: reward = -90.78, steps = 19 02:32:28 [INFO] train episode 3577: reward = -173.41, steps = 22 02:32:30 [INFO] train episode 3578: reward = -87.18, steps = 23 02:32:32 [INFO] train episode 3579: reward = -116.85, steps = 22 02:32:34 [INFO] train episode 3580: reward = -174.48, steps = 22 02:32:36 [INFO] train episode 3581: reward = -107.77, steps = 19 02:32:38 [INFO] train episode 3582: reward = -87.75, steps = 20 02:32:40 [INFO] train episode 3583: reward = -133.54, steps = 19 02:32:42 [INFO] train episode 3584: reward = -232.17, steps = 20 02:32:44 [INFO] train episode 3585: reward = -141.25, steps = 22 02:32:46 [INFO] train episode 3586: reward = -172.82, steps = 24 02:32:48 [INFO] train episode 3587: reward = -110.35, steps = 25 02:32:50 [INFO] train episode 3588: reward = -204.10, steps = 29 02:32:54 [INFO] train episode 3589: reward = -159.80, steps = 35 02:32:56 [INFO] train episode 3590: reward = -158.71, steps = 29 02:32:59 [INFO] train episode 3591: reward = -145.22, steps = 38 02:33:01 [INFO] train episode 3592: reward = -158.68, steps = 23 02:33:04 [INFO] train episode 3593: reward = -84.59, steps = 26 02:33:05 [INFO] train episode 3594: reward = -144.17, steps = 21 02:33:08 [INFO] train episode 3595: reward = -128.63, steps = 25 02:33:11 [INFO] train episode 3596: reward = -150.20, steps = 29 02:33:13 [INFO] train episode 3597: reward = -85.32, steps = 27 02:33:15 [INFO] train episode 3598: reward = -114.28, steps = 25 02:33:17 [INFO] train episode 3599: reward = -101.05, steps = 25 02:33:20 [INFO] train episode 3600: reward = -116.98, steps = 31 02:33:22 [INFO] train episode 3601: reward = -140.15, steps = 20 02:33:24 [INFO] train episode 3602: reward = -190.85, steps = 31 02:33:27 [INFO] train episode 3603: reward = -153.25, steps = 21 02:33:28 [INFO] train episode 3604: reward = -140.30, steps = 17 02:33:31 [INFO] train episode 3605: reward = -127.31, steps = 36 02:33:33 [INFO] train episode 3606: reward = -141.33, steps = 22 02:33:35 [INFO] train episode 3607: reward = -157.13, steps = 21 02:33:37 [INFO] train episode 3608: reward = -154.97, steps = 21 02:33:40 [INFO] train episode 3609: reward = -190.55, steps = 36 02:33:42 [INFO] train episode 3610: reward = -96.76, steps = 16 02:33:44 [INFO] train episode 3611: reward = -134.00, steps = 19 02:33:46 [INFO] train episode 3612: reward = -114.55, steps = 21 02:33:48 [INFO] train episode 3613: reward = -141.49, steps = 27 02:33:51 [INFO] train episode 3614: reward = -156.42, steps = 26 02:33:53 [INFO] train episode 3615: reward = -102.25, steps = 25 02:33:55 [INFO] train episode 3616: reward = -179.01, steps = 22 02:33:57 [INFO] train episode 3617: reward = -138.09, steps = 25 02:33:59 [INFO] train episode 3618: reward = -111.02, steps = 21 02:34:01 [INFO] train episode 3619: reward = -111.72, steps = 19 02:34:03 [INFO] train episode 3620: reward = -101.03, steps = 22 02:34:05 [INFO] train episode 3621: reward = -147.49, steps = 26 02:34:07 [INFO] train episode 3622: reward = -147.79, steps = 23 02:34:09 [INFO] train episode 3623: reward = -151.15, steps = 21 02:34:12 [INFO] train episode 3624: reward = -179.06, steps = 34 02:34:15 [INFO] train episode 3625: reward = -284.79, steps = 35 02:34:18 [INFO] train episode 3626: reward = -135.60, steps = 32 02:34:20 [INFO] train episode 3627: reward = -169.85, steps = 31 02:34:23 [INFO] train episode 3628: reward = -197.45, steps = 27 02:34:26 [INFO] train episode 3629: reward = -168.66, steps = 37 02:34:28 [INFO] train episode 3630: reward = -69.21, steps = 22 02:34:30 [INFO] train episode 3631: reward = -122.04, steps = 20 02:34:33 [INFO] train episode 3632: reward = -169.59, steps = 29 02:34:34 [INFO] train episode 3633: reward = -106.21, steps = 22 02:34:36 [INFO] train episode 3634: reward = -102.03, steps = 19 02:34:38 [INFO] train episode 3635: reward = -155.76, steps = 19 02:34:40 [INFO] train episode 3636: reward = -139.78, steps = 26 02:34:42 [INFO] train episode 3637: reward = -121.26, steps = 24 02:34:44 [INFO] train episode 3638: reward = -160.30, steps = 20 02:34:47 [INFO] train episode 3639: reward = -116.60, steps = 28 02:34:49 [INFO] train episode 3640: reward = -131.16, steps = 21 02:34:51 [INFO] train episode 3641: reward = -134.48, steps = 25 02:34:53 [INFO] train episode 3642: reward = -91.66, steps = 25 02:34:55 [INFO] train episode 3643: reward = -204.73, steps = 29 02:34:57 [INFO] train episode 3644: reward = -115.54, steps = 20 02:34:59 [INFO] train episode 3645: reward = -93.58, steps = 19 02:35:02 [INFO] train episode 3646: reward = -184.25, steps = 33 02:35:04 [INFO] train episode 3647: reward = -154.64, steps = 23 02:35:06 [INFO] train episode 3648: reward = -124.23, steps = 19 02:35:08 [INFO] train episode 3649: reward = -135.02, steps = 25 02:35:11 [INFO] train episode 3650: reward = -261.73, steps = 31 02:35:13 [INFO] train episode 3651: reward = -132.67, steps = 32 02:35:15 [INFO] train episode 3652: reward = -150.37, steps = 23 02:35:17 [INFO] train episode 3653: reward = -133.43, steps = 19 02:35:20 [INFO] train episode 3654: reward = -141.04, steps = 25 02:35:22 [INFO] train episode 3655: reward = -154.96, steps = 31 02:35:24 [INFO] train episode 3656: reward = -163.24, steps = 24 02:35:26 [INFO] train episode 3657: reward = -104.04, steps = 21 02:35:28 [INFO] train episode 3658: reward = -143.51, steps = 19 02:35:30 [INFO] train episode 3659: reward = -101.42, steps = 20 02:35:31 [INFO] train episode 3660: reward = -145.14, steps = 20 02:35:35 [INFO] train episode 3661: reward = -151.86, steps = 31 02:35:36 [INFO] train episode 3662: reward = -134.63, steps = 22 02:35:38 [INFO] train episode 3663: reward = -117.37, steps = 20 02:35:40 [INFO] train episode 3664: reward = -96.73, steps = 20 02:35:42 [INFO] train episode 3665: reward = -155.37, steps = 25 02:35:44 [INFO] train episode 3666: reward = -110.77, steps = 24 02:35:47 [INFO] train episode 3667: reward = -140.62, steps = 27 02:35:50 [INFO] train episode 3668: reward = -100.48, steps = 35 02:35:52 [INFO] train episode 3669: reward = -125.42, steps = 23 02:35:54 [INFO] train episode 3670: reward = -146.89, steps = 23 02:35:56 [INFO] train episode 3671: reward = -150.11, steps = 20 02:35:57 [INFO] train episode 3672: reward = -154.57, steps = 20 02:36:00 [INFO] train episode 3673: reward = -215.42, steps = 25 02:36:02 [INFO] train episode 3674: reward = -126.67, steps = 25 02:36:05 [INFO] train episode 3675: reward = -157.07, steps = 34 02:36:07 [INFO] train episode 3676: reward = -144.71, steps = 27 02:36:10 [INFO] train episode 3677: reward = -129.32, steps = 27 02:36:12 [INFO] train episode 3678: reward = -133.79, steps = 28 02:36:14 [INFO] train episode 3679: reward = -147.81, steps = 21 02:36:16 [INFO] train episode 3680: reward = -131.35, steps = 19 02:36:18 [INFO] train episode 3681: reward = -171.10, steps = 22 02:36:19 [INFO] train episode 3682: reward = -114.59, steps = 20 02:36:22 [INFO] train episode 3683: reward = -137.26, steps = 25 02:36:24 [INFO] train episode 3684: reward = -122.09, steps = 18 02:36:26 [INFO] train episode 3685: reward = -143.81, steps = 21 02:36:27 [INFO] train episode 3686: reward = -136.71, steps = 18 02:36:29 [INFO] train episode 3687: reward = -144.12, steps = 23 02:36:31 [INFO] train episode 3688: reward = -135.76, steps = 19 02:36:33 [INFO] train episode 3689: reward = -100.74, steps = 25 02:36:36 [INFO] train episode 3690: reward = -124.26, steps = 28 02:36:40 [INFO] train episode 3691: reward = -163.02, steps = 35 02:36:41 [INFO] train episode 3692: reward = -79.87, steps = 22 02:36:43 [INFO] train episode 3693: reward = -109.72, steps = 18 02:36:45 [INFO] train episode 3694: reward = -109.29, steps = 18 02:36:47 [INFO] train episode 3695: reward = -143.96, steps = 24 02:36:49 [INFO] train episode 3696: reward = -196.29, steps = 30 02:36:51 [INFO] train episode 3697: reward = -157.46, steps = 19 02:36:54 [INFO] train episode 3698: reward = -145.19, steps = 32 02:36:57 [INFO] train episode 3699: reward = -162.09, steps = 30 02:36:58 [INFO] train episode 3700: reward = -84.62, steps = 20 02:37:01 [INFO] train episode 3701: reward = -121.32, steps = 24 02:37:02 [INFO] train episode 3702: reward = -174.91, steps = 20 02:37:05 [INFO] train episode 3703: reward = -153.89, steps = 24 02:37:07 [INFO] train episode 3704: reward = -119.86, steps = 23 02:37:09 [INFO] train episode 3705: reward = -173.47, steps = 25 02:37:12 [INFO] train episode 3706: reward = -124.04, steps = 27 02:37:15 [INFO] train episode 3707: reward = -141.08, steps = 30 02:37:17 [INFO] train episode 3708: reward = -136.61, steps = 22 02:37:19 [INFO] train episode 3709: reward = -113.69, steps = 27 02:37:21 [INFO] train episode 3710: reward = -162.84, steps = 22 02:37:24 [INFO] train episode 3711: reward = -148.99, steps = 24 02:37:26 [INFO] train episode 3712: reward = -95.40, steps = 26 02:37:29 [INFO] train episode 3713: reward = -117.61, steps = 20 02:37:30 [INFO] train episode 3714: reward = -133.45, steps = 19 02:37:33 [INFO] train episode 3715: reward = -135.80, steps = 24 02:37:35 [INFO] train episode 3716: reward = -139.94, steps = 25 02:37:37 [INFO] train episode 3717: reward = -83.22, steps = 19 02:37:39 [INFO] train episode 3718: reward = -114.73, steps = 22 02:37:41 [INFO] train episode 3719: reward = -159.13, steps = 25 02:37:43 [INFO] train episode 3720: reward = -139.27, steps = 21 02:37:46 [INFO] train episode 3721: reward = -142.28, steps = 21 02:37:47 [INFO] train episode 3722: reward = -139.41, steps = 20 02:37:49 [INFO] train episode 3723: reward = -155.06, steps = 22 02:37:52 [INFO] train episode 3724: reward = -105.20, steps = 28 02:37:55 [INFO] train episode 3725: reward = -191.45, steps = 31 02:37:57 [INFO] train episode 3726: reward = -114.36, steps = 24 02:37:59 [INFO] train episode 3727: reward = -142.37, steps = 26 02:38:02 [INFO] train episode 3728: reward = -78.75, steps = 23 02:38:04 [INFO] train episode 3729: reward = -164.51, steps = 19 02:38:06 [INFO] train episode 3730: reward = -115.48, steps = 28 02:38:09 [INFO] train episode 3731: reward = -122.60, steps = 29 02:38:11 [INFO] train episode 3732: reward = -144.33, steps = 24 02:38:13 [INFO] train episode 3733: reward = -127.16, steps = 27 02:38:15 [INFO] train episode 3734: reward = -103.07, steps = 20 02:38:18 [INFO] train episode 3735: reward = -121.55, steps = 28 02:38:20 [INFO] train episode 3736: reward = -80.34, steps = 19 02:38:23 [INFO] train episode 3737: reward = -210.66, steps = 32 02:38:25 [INFO] train episode 3738: reward = -172.42, steps = 26 02:38:28 [INFO] train episode 3739: reward = -119.51, steps = 26 02:38:30 [INFO] train episode 3740: reward = -106.95, steps = 23 02:38:32 [INFO] train episode 3741: reward = -137.61, steps = 27 02:38:34 [INFO] train episode 3742: reward = -117.73, steps = 19 02:38:37 [INFO] train episode 3743: reward = -120.52, steps = 28 02:38:40 [INFO] train episode 3744: reward = -147.16, steps = 33 02:38:42 [INFO] train episode 3745: reward = -149.70, steps = 23 02:38:44 [INFO] train episode 3746: reward = -142.24, steps = 25 02:38:46 [INFO] train episode 3747: reward = -99.94, steps = 22 02:38:48 [INFO] train episode 3748: reward = -115.89, steps = 19 02:38:50 [INFO] train episode 3749: reward = -72.13, steps = 19 02:38:52 [INFO] train episode 3750: reward = -162.70, steps = 22 02:38:55 [INFO] train episode 3751: reward = -126.36, steps = 28 02:38:58 [INFO] train episode 3752: reward = -180.57, steps = 28 02:39:00 [INFO] train episode 3753: reward = -164.24, steps = 19 02:39:02 [INFO] train episode 3754: reward = -126.51, steps = 23 02:39:04 [INFO] train episode 3755: reward = -106.02, steps = 25 02:39:07 [INFO] train episode 3756: reward = -129.35, steps = 29 02:39:09 [INFO] train episode 3757: reward = -129.57, steps = 27 02:39:12 [INFO] train episode 3758: reward = -94.60, steps = 20 02:39:15 [INFO] train episode 3759: reward = -162.68, steps = 33 02:39:16 [INFO] train episode 3760: reward = -117.29, steps = 18 02:39:18 [INFO] train episode 3761: reward = -107.87, steps = 19 02:39:20 [INFO] train episode 3762: reward = -110.46, steps = 21 02:39:22 [INFO] train episode 3763: reward = -99.21, steps = 22 02:39:24 [INFO] train episode 3764: reward = -161.90, steps = 20 02:39:26 [INFO] train episode 3765: reward = -87.91, steps = 22 02:39:28 [INFO] train episode 3766: reward = -96.59, steps = 20 02:39:31 [INFO] train episode 3767: reward = -121.11, steps = 27 02:39:33 [INFO] train episode 3768: reward = -102.02, steps = 23 02:39:35 [INFO] train episode 3769: reward = -104.91, steps = 20 02:39:37 [INFO] train episode 3770: reward = -133.01, steps = 21 02:39:40 [INFO] train episode 3771: reward = -159.60, steps = 29 02:39:43 [INFO] train episode 3772: reward = -161.47, steps = 24 02:39:45 [INFO] train episode 3773: reward = -144.50, steps = 24 02:39:47 [INFO] train episode 3774: reward = -81.00, steps = 21 02:39:49 [INFO] train episode 3775: reward = -96.39, steps = 20 02:39:51 [INFO] train episode 3776: reward = -101.47, steps = 18 02:39:52 [INFO] train episode 3777: reward = -117.00, steps = 20 02:39:54 [INFO] train episode 3778: reward = -86.45, steps = 21 02:39:57 [INFO] train episode 3779: reward = -115.43, steps = 34 02:40:00 [INFO] train episode 3780: reward = -123.55, steps = 30 02:40:02 [INFO] train episode 3781: reward = -103.85, steps = 21 02:40:05 [INFO] train episode 3782: reward = -101.40, steps = 30 02:40:07 [INFO] train episode 3783: reward = -125.06, steps = 28 02:40:09 [INFO] train episode 3784: reward = -116.14, steps = 17 02:40:11 [INFO] train episode 3785: reward = -159.74, steps = 26 02:40:13 [INFO] train episode 3786: reward = -101.56, steps = 28 02:40:15 [INFO] train episode 3787: reward = -173.06, steps = 24 02:40:18 [INFO] train episode 3788: reward = -134.21, steps = 30 02:40:20 [INFO] train episode 3789: reward = -134.41, steps = 24 02:40:23 [INFO] train episode 3790: reward = -182.82, steps = 26 02:40:25 [INFO] train episode 3791: reward = -169.18, steps = 27 02:40:27 [INFO] train episode 3792: reward = -155.14, steps = 19 02:40:28 [INFO] train episode 3793: reward = -100.41, steps = 20 02:40:30 [INFO] train episode 3794: reward = -144.77, steps = 22 02:40:32 [INFO] train episode 3795: reward = -91.26, steps = 20 02:40:34 [INFO] train episode 3796: reward = -123.49, steps = 19 02:40:36 [INFO] train episode 3797: reward = -164.13, steps = 25 02:40:38 [INFO] train episode 3798: reward = -152.22, steps = 22 02:40:42 [INFO] train episode 3799: reward = -181.18, steps = 44 02:40:44 [INFO] train episode 3800: reward = -118.39, steps = 26 02:40:47 [INFO] train episode 3801: reward = -138.01, steps = 32 02:40:49 [INFO] train episode 3802: reward = -99.88, steps = 20 02:40:51 [INFO] train episode 3803: reward = -75.54, steps = 24 02:40:53 [INFO] train episode 3804: reward = -115.41, steps = 20 02:40:55 [INFO] train episode 3805: reward = -206.57, steps = 26 02:40:57 [INFO] train episode 3806: reward = -112.23, steps = 24 02:40:59 [INFO] train episode 3807: reward = -113.93, steps = 19 02:41:01 [INFO] train episode 3808: reward = -139.05, steps = 23 02:41:03 [INFO] train episode 3809: reward = -109.04, steps = 24 02:41:05 [INFO] train episode 3810: reward = -125.95, steps = 20 02:41:07 [INFO] train episode 3811: reward = -158.62, steps = 23 02:41:09 [INFO] train episode 3812: reward = -117.40, steps = 25 02:41:11 [INFO] train episode 3813: reward = -136.66, steps = 23 02:41:14 [INFO] train episode 3814: reward = -132.15, steps = 25 02:41:16 [INFO] train episode 3815: reward = -131.42, steps = 25 02:41:17 [INFO] train episode 3816: reward = -108.48, steps = 19 02:41:20 [INFO] train episode 3817: reward = -132.36, steps = 28 02:41:22 [INFO] train episode 3818: reward = -104.75, steps = 21 02:41:24 [INFO] train episode 3819: reward = -127.93, steps = 19 02:41:26 [INFO] train episode 3820: reward = -152.37, steps = 27 02:41:28 [INFO] train episode 3821: reward = -156.53, steps = 21 02:41:30 [INFO] train episode 3822: reward = -107.14, steps = 19 02:41:31 [INFO] train episode 3823: reward = -114.78, steps = 19 02:41:33 [INFO] train episode 3824: reward = -116.51, steps = 24 02:41:35 [INFO] train episode 3825: reward = -121.14, steps = 23 02:41:38 [INFO] train episode 3826: reward = -147.57, steps = 31 02:41:40 [INFO] train episode 3827: reward = -146.09, steps = 21 02:41:42 [INFO] train episode 3828: reward = -115.81, steps = 21 02:41:44 [INFO] train episode 3829: reward = -153.80, steps = 22 02:41:46 [INFO] train episode 3830: reward = -144.86, steps = 30 02:41:48 [INFO] train episode 3831: reward = -83.07, steps = 22 02:41:51 [INFO] train episode 3832: reward = -93.92, steps = 34 02:41:54 [INFO] train episode 3833: reward = -127.56, steps = 31 02:41:56 [INFO] train episode 3834: reward = -99.24, steps = 23 02:41:59 [INFO] train episode 3835: reward = -87.43, steps = 29 02:42:01 [INFO] train episode 3836: reward = -201.64, steps = 30 02:42:03 [INFO] train episode 3837: reward = -116.48, steps = 21 02:42:06 [INFO] train episode 3838: reward = -177.81, steps = 31 02:42:09 [INFO] train episode 3839: reward = -104.03, steps = 29 02:42:12 [INFO] train episode 3840: reward = -134.18, steps = 28 02:42:13 [INFO] train episode 3841: reward = -120.99, steps = 20 02:42:16 [INFO] train episode 3842: reward = -140.72, steps = 29 02:42:19 [INFO] train episode 3843: reward = -310.44, steps = 40 02:42:22 [INFO] train episode 3844: reward = -174.77, steps = 29 02:42:24 [INFO] train episode 3845: reward = -109.38, steps = 25 02:42:27 [INFO] train episode 3846: reward = -165.52, steps = 27 02:42:30 [INFO] train episode 3847: reward = -223.54, steps = 38 02:42:32 [INFO] train episode 3848: reward = -78.75, steps = 20 02:42:34 [INFO] train episode 3849: reward = -123.67, steps = 21 02:42:37 [INFO] train episode 3850: reward = -97.49, steps = 28 02:42:39 [INFO] train episode 3851: reward = -182.57, steps = 23 02:42:41 [INFO] train episode 3852: reward = -128.10, steps = 28 02:42:44 [INFO] train episode 3853: reward = -151.57, steps = 23 02:42:45 [INFO] train episode 3854: reward = -82.48, steps = 19 02:42:47 [INFO] train episode 3855: reward = -113.92, steps = 24 02:42:50 [INFO] train episode 3856: reward = -98.77, steps = 29 02:42:52 [INFO] train episode 3857: reward = -94.41, steps = 20 02:42:53 [INFO] train episode 3858: reward = -117.53, steps = 20 02:42:56 [INFO] train episode 3859: reward = -101.95, steps = 25 02:42:57 [INFO] train episode 3860: reward = -141.62, steps = 19 02:43:00 [INFO] train episode 3861: reward = -123.67, steps = 29 02:43:03 [INFO] train episode 3862: reward = -146.68, steps = 27 02:43:06 [INFO] train episode 3863: reward = -177.21, steps = 45 02:43:08 [INFO] train episode 3864: reward = -99.37, steps = 20 02:43:10 [INFO] train episode 3865: reward = -122.90, steps = 22 02:43:12 [INFO] train episode 3866: reward = -137.35, steps = 20 02:43:14 [INFO] train episode 3867: reward = -123.15, steps = 30 02:43:17 [INFO] train episode 3868: reward = -115.62, steps = 22 02:43:19 [INFO] train episode 3869: reward = -103.84, steps = 32 02:43:22 [INFO] train episode 3870: reward = -128.99, steps = 29 02:43:24 [INFO] train episode 3871: reward = -162.68, steps = 22 02:43:26 [INFO] train episode 3872: reward = -100.87, steps = 21 02:43:28 [INFO] train episode 3873: reward = -107.52, steps = 23 02:43:30 [INFO] train episode 3874: reward = -146.00, steps = 28 02:43:34 [INFO] train episode 3875: reward = -182.72, steps = 39 02:43:36 [INFO] train episode 3876: reward = -126.09, steps = 30 02:43:39 [INFO] train episode 3877: reward = -130.34, steps = 26 02:43:41 [INFO] train episode 3878: reward = -141.15, steps = 31 02:43:44 [INFO] train episode 3879: reward = -181.17, steps = 26 02:43:46 [INFO] train episode 3880: reward = -82.10, steps = 22 02:43:49 [INFO] train episode 3881: reward = -124.02, steps = 34 02:43:51 [INFO] train episode 3882: reward = -133.74, steps = 21 02:43:53 [INFO] train episode 3883: reward = -144.36, steps = 23 02:43:55 [INFO] train episode 3884: reward = -105.29, steps = 28 02:43:58 [INFO] train episode 3885: reward = -173.73, steps = 30 02:44:00 [INFO] train episode 3886: reward = -144.84, steps = 22 02:44:01 [INFO] train episode 3887: reward = -100.23, steps = 22 02:44:04 [INFO] train episode 3888: reward = -166.87, steps = 21 02:44:07 [INFO] train episode 3889: reward = -213.60, steps = 34 02:44:09 [INFO] train episode 3890: reward = -114.26, steps = 24 02:44:11 [INFO] train episode 3891: reward = -125.78, steps = 22 02:44:13 [INFO] train episode 3892: reward = -162.46, steps = 26 02:44:15 [INFO] train episode 3893: reward = -180.95, steps = 20 02:44:17 [INFO] train episode 3894: reward = -149.35, steps = 30 02:44:20 [INFO] train episode 3895: reward = -86.97, steps = 25 02:44:22 [INFO] train episode 3896: reward = -86.94, steps = 22 02:44:24 [INFO] train episode 3897: reward = -133.19, steps = 29 02:44:27 [INFO] train episode 3898: reward = -107.14, steps = 30 02:44:29 [INFO] train episode 3899: reward = -142.93, steps = 20 02:44:31 [INFO] train episode 3900: reward = -122.64, steps = 27 02:44:33 [INFO] train episode 3901: reward = -123.14, steps = 26 02:44:37 [INFO] train episode 3902: reward = -152.31, steps = 33 02:44:39 [INFO] train episode 3903: reward = -135.87, steps = 23 02:44:41 [INFO] train episode 3904: reward = -129.94, steps = 26 02:44:42 [INFO] train episode 3905: reward = -127.78, steps = 19 02:44:45 [INFO] train episode 3906: reward = -93.83, steps = 28 02:44:47 [INFO] train episode 3907: reward = -113.94, steps = 25 02:44:50 [INFO] train episode 3908: reward = -164.70, steps = 29 02:44:52 [INFO] train episode 3909: reward = -131.83, steps = 26 02:44:54 [INFO] train episode 3910: reward = -119.29, steps = 22 02:44:57 [INFO] train episode 3911: reward = -81.76, steps = 27 02:44:59 [INFO] train episode 3912: reward = -101.71, steps = 24 02:45:01 [INFO] train episode 3913: reward = -156.79, steps = 22 02:45:02 [INFO] train episode 3914: reward = -97.74, steps = 20 02:45:04 [INFO] train episode 3915: reward = -105.71, steps = 21 02:45:07 [INFO] train episode 3916: reward = -147.00, steps = 26 02:45:10 [INFO] train episode 3917: reward = -131.36, steps = 31 02:45:12 [INFO] train episode 3918: reward = -118.09, steps = 22 02:45:13 [INFO] train episode 3919: reward = -72.01, steps = 20 02:45:15 [INFO] train episode 3920: reward = -82.12, steps = 20 02:45:17 [INFO] train episode 3921: reward = -115.25, steps = 19 02:45:19 [INFO] train episode 3922: reward = -109.98, steps = 30 02:45:21 [INFO] train episode 3923: reward = -122.81, steps = 20 02:45:23 [INFO] train episode 3924: reward = -197.51, steps = 19 02:45:25 [INFO] train episode 3925: reward = -119.38, steps = 21 02:45:28 [INFO] train episode 3926: reward = -141.01, steps = 22 02:45:30 [INFO] train episode 3927: reward = -155.36, steps = 21 02:45:32 [INFO] train episode 3928: reward = -120.75, steps = 20 02:45:34 [INFO] train episode 3929: reward = -115.23, steps = 25 02:45:36 [INFO] train episode 3930: reward = -200.82, steps = 27 02:45:38 [INFO] train episode 3931: reward = -80.56, steps = 27 02:45:41 [INFO] train episode 3932: reward = -180.12, steps = 27 02:45:43 [INFO] train episode 3933: reward = -92.98, steps = 20 02:45:45 [INFO] train episode 3934: reward = -154.83, steps = 19 02:45:47 [INFO] train episode 3935: reward = -120.03, steps = 22 02:45:48 [INFO] train episode 3936: reward = -92.45, steps = 21 02:45:51 [INFO] train episode 3937: reward = -110.52, steps = 28 02:45:54 [INFO] train episode 3938: reward = -130.11, steps = 31 02:45:56 [INFO] train episode 3939: reward = -120.12, steps = 22 02:45:58 [INFO] train episode 3940: reward = -139.32, steps = 29 02:46:00 [INFO] train episode 3941: reward = -100.91, steps = 18 02:46:02 [INFO] train episode 3942: reward = -132.16, steps = 26 02:46:04 [INFO] train episode 3943: reward = -118.66, steps = 20 02:46:06 [INFO] train episode 3944: reward = -109.32, steps = 22 02:46:08 [INFO] train episode 3945: reward = -138.92, steps = 24 02:46:11 [INFO] train episode 3946: reward = -122.83, steps = 30 02:46:12 [INFO] train episode 3947: reward = -127.34, steps = 18 02:46:14 [INFO] train episode 3948: reward = -101.45, steps = 21 02:46:17 [INFO] train episode 3949: reward = -213.00, steps = 26 02:46:19 [INFO] train episode 3950: reward = -129.95, steps = 24 02:46:20 [INFO] train episode 3951: reward = -101.74, steps = 21 02:46:23 [INFO] train episode 3952: reward = -193.17, steps = 29 02:46:25 [INFO] train episode 3953: reward = -155.14, steps = 19 02:46:26 [INFO] train episode 3954: reward = -103.96, steps = 21 02:46:28 [INFO] train episode 3955: reward = -126.35, steps = 20 02:46:31 [INFO] train episode 3956: reward = -132.21, steps = 25 02:46:33 [INFO] train episode 3957: reward = -119.95, steps = 29 02:46:35 [INFO] train episode 3958: reward = -79.37, steps = 23 02:46:37 [INFO] train episode 3959: reward = -135.54, steps = 24 02:46:39 [INFO] train episode 3960: reward = -121.85, steps = 21 02:46:41 [INFO] train episode 3961: reward = -110.42, steps = 22 02:46:43 [INFO] train episode 3962: reward = -151.56, steps = 21 02:46:45 [INFO] train episode 3963: reward = -123.93, steps = 26 02:46:48 [INFO] train episode 3964: reward = -148.83, steps = 25 02:46:50 [INFO] train episode 3965: reward = -137.72, steps = 22 02:46:52 [INFO] train episode 3966: reward = -204.83, steps = 27 02:46:55 [INFO] train episode 3967: reward = -191.58, steps = 38 02:46:57 [INFO] train episode 3968: reward = -88.27, steps = 20 02:46:59 [INFO] train episode 3969: reward = -98.27, steps = 25 02:47:01 [INFO] train episode 3970: reward = -173.52, steps = 19 02:47:04 [INFO] train episode 3971: reward = -99.66, steps = 37 02:47:06 [INFO] train episode 3972: reward = -107.03, steps = 17 02:47:08 [INFO] train episode 3973: reward = -168.94, steps = 24 02:47:10 [INFO] train episode 3974: reward = -104.94, steps = 23 02:47:12 [INFO] train episode 3975: reward = -140.03, steps = 18 02:47:14 [INFO] train episode 3976: reward = -114.55, steps = 29 02:47:16 [INFO] train episode 3977: reward = -85.57, steps = 21 02:47:18 [INFO] train episode 3978: reward = -123.11, steps = 20 02:47:20 [INFO] train episode 3979: reward = -127.40, steps = 24 02:47:23 [INFO] train episode 3980: reward = -120.84, steps = 30 02:47:24 [INFO] train episode 3981: reward = -147.71, steps = 18 02:47:27 [INFO] train episode 3982: reward = -118.96, steps = 24 02:47:29 [INFO] train episode 3983: reward = -197.52, steps = 31 02:47:32 [INFO] train episode 3984: reward = -157.09, steps = 30 02:47:34 [INFO] train episode 3985: reward = -100.20, steps = 21 02:47:36 [INFO] train episode 3986: reward = -94.14, steps = 21 02:47:38 [INFO] train episode 3987: reward = -114.16, steps = 22 02:47:40 [INFO] train episode 3988: reward = -134.61, steps = 25 02:47:43 [INFO] train episode 3989: reward = -108.39, steps = 29 02:47:44 [INFO] train episode 3990: reward = -106.01, steps = 21 02:47:47 [INFO] train episode 3991: reward = -125.68, steps = 27 02:47:48 [INFO] train episode 3992: reward = -87.98, steps = 20 02:47:51 [INFO] train episode 3993: reward = -150.97, steps = 25 02:47:53 [INFO] train episode 3994: reward = -162.85, steps = 23 02:47:55 [INFO] train episode 3995: reward = -127.00, steps = 20 02:47:57 [INFO] train episode 3996: reward = -113.86, steps = 27 02:47:59 [INFO] train episode 3997: reward = -97.25, steps = 20 02:48:01 [INFO] train episode 3998: reward = -75.77, steps = 19 02:48:02 [INFO] train episode 3999: reward = -136.90, steps = 18 02:48:04 [INFO] train episode 4000: reward = -121.19, steps = 23 02:48:06 [INFO] train episode 4001: reward = -97.35, steps = 19 02:48:08 [INFO] train episode 4002: reward = -132.15, steps = 26 02:48:11 [INFO] train episode 4003: reward = -104.84, steps = 26 02:48:13 [INFO] train episode 4004: reward = -145.46, steps = 30 02:48:16 [INFO] train episode 4005: reward = -132.50, steps = 30 02:48:17 [INFO] train episode 4006: reward = -73.77, steps = 12 02:48:19 [INFO] train episode 4007: reward = -194.48, steps = 20 02:48:23 [INFO] train episode 4008: reward = -174.43, steps = 32 02:48:24 [INFO] train episode 4009: reward = -123.48, steps = 19 02:48:26 [INFO] train episode 4010: reward = -131.97, steps = 20 02:48:29 [INFO] train episode 4011: reward = -155.80, steps = 30 02:48:31 [INFO] train episode 4012: reward = -155.77, steps = 25 02:48:33 [INFO] train episode 4013: reward = -81.21, steps = 24 02:48:35 [INFO] train episode 4014: reward = -132.12, steps = 21 02:48:38 [INFO] train episode 4015: reward = -93.89, steps = 26 02:48:39 [INFO] train episode 4016: reward = -120.24, steps = 22 02:48:41 [INFO] train episode 4017: reward = -117.33, steps = 19 02:48:43 [INFO] train episode 4018: reward = -131.65, steps = 25 02:48:45 [INFO] train episode 4019: reward = -216.20, steps = 23 02:48:47 [INFO] train episode 4020: reward = -114.38, steps = 22 02:48:50 [INFO] train episode 4021: reward = -228.66, steps = 30 02:48:52 [INFO] train episode 4022: reward = -80.62, steps = 20 02:48:54 [INFO] train episode 4023: reward = -107.30, steps = 29 02:48:56 [INFO] train episode 4024: reward = -107.59, steps = 24 02:48:59 [INFO] train episode 4025: reward = -120.72, steps = 25 02:49:01 [INFO] train episode 4026: reward = -140.37, steps = 25 02:49:03 [INFO] train episode 4027: reward = -112.46, steps = 19 02:49:06 [INFO] train episode 4028: reward = -157.73, steps = 34 02:49:08 [INFO] train episode 4029: reward = -115.14, steps = 25 02:49:10 [INFO] train episode 4030: reward = -114.23, steps = 22 02:49:12 [INFO] train episode 4031: reward = -173.30, steps = 20 02:49:14 [INFO] train episode 4032: reward = -180.43, steps = 26 02:49:17 [INFO] train episode 4033: reward = -162.65, steps = 35 02:49:19 [INFO] train episode 4034: reward = -112.88, steps = 22 02:49:21 [INFO] train episode 4035: reward = -131.81, steps = 25 02:49:23 [INFO] train episode 4036: reward = -125.06, steps = 24 02:49:25 [INFO] train episode 4037: reward = -115.29, steps = 20 02:49:27 [INFO] train episode 4038: reward = -153.66, steps = 19 02:49:29 [INFO] train episode 4039: reward = -130.78, steps = 24 02:49:31 [INFO] train episode 4040: reward = -148.07, steps = 21 02:49:33 [INFO] train episode 4041: reward = -148.38, steps = 22 02:49:35 [INFO] train episode 4042: reward = -98.70, steps = 23 02:49:37 [INFO] train episode 4043: reward = -129.18, steps = 25 02:49:39 [INFO] train episode 4044: reward = -101.25, steps = 20 02:49:42 [INFO] train episode 4045: reward = -121.82, steps = 28 02:49:44 [INFO] train episode 4046: reward = -149.23, steps = 22 02:49:45 [INFO] train episode 4047: reward = -90.65, steps = 18 02:49:47 [INFO] train episode 4048: reward = -110.82, steps = 19 02:49:49 [INFO] train episode 4049: reward = -91.19, steps = 26 02:49:52 [INFO] train episode 4050: reward = -180.68, steps = 32 02:49:54 [INFO] train episode 4051: reward = -74.59, steps = 21 02:49:56 [INFO] train episode 4052: reward = -94.84, steps = 29 02:49:59 [INFO] train episode 4053: reward = -68.61, steps = 24 02:50:02 [INFO] train episode 4054: reward = -132.68, steps = 30 02:50:03 [INFO] train episode 4055: reward = -121.39, steps = 21 02:50:06 [INFO] train episode 4056: reward = -131.46, steps = 33 02:50:10 [INFO] train episode 4057: reward = -216.22, steps = 39 02:50:12 [INFO] train episode 4058: reward = -143.69, steps = 27 02:50:14 [INFO] train episode 4059: reward = -101.76, steps = 22 02:50:16 [INFO] train episode 4060: reward = -104.42, steps = 20 02:50:18 [INFO] train episode 4061: reward = -141.36, steps = 26 02:50:20 [INFO] train episode 4062: reward = -151.60, steps = 20 02:50:22 [INFO] train episode 4063: reward = -106.46, steps = 27 02:50:25 [INFO] train episode 4064: reward = -136.08, steps = 29 02:50:27 [INFO] train episode 4065: reward = -116.45, steps = 22 02:50:29 [INFO] train episode 4066: reward = -113.86, steps = 25 02:50:31 [INFO] train episode 4067: reward = -115.64, steps = 19 02:50:34 [INFO] train episode 4068: reward = -159.81, steps = 34 02:50:36 [INFO] train episode 4069: reward = -126.13, steps = 25 02:50:38 [INFO] train episode 4070: reward = -111.29, steps = 23 02:50:40 [INFO] train episode 4071: reward = -168.29, steps = 26 02:50:42 [INFO] train episode 4072: reward = -101.90, steps = 23 02:50:45 [INFO] train episode 4073: reward = -121.73, steps = 25 02:50:47 [INFO] train episode 4074: reward = -113.26, steps = 19 02:50:50 [INFO] train episode 4075: reward = -154.00, steps = 34 02:50:52 [INFO] train episode 4076: reward = -176.82, steps = 32 02:50:54 [INFO] train episode 4077: reward = -94.20, steps = 17 02:50:56 [INFO] train episode 4078: reward = -106.82, steps = 24 02:50:58 [INFO] train episode 4079: reward = -136.09, steps = 19 02:51:00 [INFO] train episode 4080: reward = -111.88, steps = 25 02:51:03 [INFO] train episode 4081: reward = -111.80, steps = 28 02:51:06 [INFO] train episode 4082: reward = -174.89, steps = 37 02:51:09 [INFO] train episode 4083: reward = -145.14, steps = 33 02:51:11 [INFO] train episode 4084: reward = -170.74, steps = 29 02:51:13 [INFO] train episode 4085: reward = -188.81, steps = 22 02:51:16 [INFO] train episode 4086: reward = -143.11, steps = 28 02:51:19 [INFO] train episode 4087: reward = -103.07, steps = 29 02:51:22 [INFO] train episode 4088: reward = -118.26, steps = 29 02:51:24 [INFO] train episode 4089: reward = -109.23, steps = 22 02:51:26 [INFO] train episode 4090: reward = -124.15, steps = 25 02:51:28 [INFO] train episode 4091: reward = -144.52, steps = 29 02:51:31 [INFO] train episode 4092: reward = -74.71, steps = 25 02:51:33 [INFO] train episode 4093: reward = -104.03, steps = 31 02:51:36 [INFO] train episode 4094: reward = -186.83, steps = 24 02:51:39 [INFO] train episode 4095: reward = -128.48, steps = 44 02:51:42 [INFO] train episode 4096: reward = -110.83, steps = 28 02:51:45 [INFO] train episode 4097: reward = -165.70, steps = 28 02:51:47 [INFO] train episode 4098: reward = -110.98, steps = 31 02:51:49 [INFO] train episode 4099: reward = -107.89, steps = 21 02:51:53 [INFO] train episode 4100: reward = -120.83, steps = 29 02:51:55 [INFO] train episode 4101: reward = -125.92, steps = 23 02:51:58 [INFO] train episode 4102: reward = -170.51, steps = 40 02:52:00 [INFO] train episode 4103: reward = -106.77, steps = 22 02:52:02 [INFO] train episode 4104: reward = -127.23, steps = 21 02:52:05 [INFO] train episode 4105: reward = -77.64, steps = 21 02:52:07 [INFO] train episode 4106: reward = -105.63, steps = 22 02:52:10 [INFO] train episode 4107: reward = -110.55, steps = 33 02:52:13 [INFO] train episode 4108: reward = -134.05, steps = 28 02:52:15 [INFO] train episode 4109: reward = -141.92, steps = 30 02:52:18 [INFO] train episode 4110: reward = -102.80, steps = 27 02:52:20 [INFO] train episode 4111: reward = -129.15, steps = 28 02:52:23 [INFO] train episode 4112: reward = -170.38, steps = 29 02:52:25 [INFO] train episode 4113: reward = -116.64, steps = 23 02:52:28 [INFO] train episode 4114: reward = -130.16, steps = 21 02:52:30 [INFO] train episode 4115: reward = -126.29, steps = 25 02:52:32 [INFO] train episode 4116: reward = -230.56, steps = 24 02:52:34 [INFO] train episode 4117: reward = -111.27, steps = 22 02:52:36 [INFO] train episode 4118: reward = -115.80, steps = 21 02:52:38 [INFO] train episode 4119: reward = -83.45, steps = 27 02:52:40 [INFO] train episode 4120: reward = -131.40, steps = 23 02:52:43 [INFO] train episode 4121: reward = -122.69, steps = 25 02:52:46 [INFO] train episode 4122: reward = -111.96, steps = 36 02:52:49 [INFO] train episode 4123: reward = -116.85, steps = 28 02:52:52 [INFO] train episode 4124: reward = -173.04, steps = 38 02:52:54 [INFO] train episode 4125: reward = -92.79, steps = 20 02:52:56 [INFO] train episode 4126: reward = -201.57, steps = 27 02:52:58 [INFO] train episode 4127: reward = -145.09, steps = 21 02:53:00 [INFO] train episode 4128: reward = -139.15, steps = 20 02:53:02 [INFO] train episode 4129: reward = -97.65, steps = 23 02:53:05 [INFO] train episode 4130: reward = -157.09, steps = 30 02:53:06 [INFO] train episode 4131: reward = -127.09, steps = 19 02:53:10 [INFO] train episode 4132: reward = -154.00, steps = 38 02:53:12 [INFO] train episode 4133: reward = -151.15, steps = 25 02:53:15 [INFO] train episode 4134: reward = -127.86, steps = 30 02:53:18 [INFO] train episode 4135: reward = -132.06, steps = 34 02:53:21 [INFO] train episode 4136: reward = -141.27, steps = 35 02:53:24 [INFO] train episode 4137: reward = -139.48, steps = 25 02:53:26 [INFO] train episode 4138: reward = -130.00, steps = 25 02:53:28 [INFO] train episode 4139: reward = -98.93, steps = 24 02:53:31 [INFO] train episode 4140: reward = -112.99, steps = 28 02:53:34 [INFO] train episode 4141: reward = -174.24, steps = 28 02:53:36 [INFO] train episode 4142: reward = -168.41, steps = 26 02:53:38 [INFO] train episode 4143: reward = -105.37, steps = 24 02:53:41 [INFO] train episode 4144: reward = -101.84, steps = 24 02:53:43 [INFO] train episode 4145: reward = -126.67, steps = 24 02:53:45 [INFO] train episode 4146: reward = -164.89, steps = 26 02:53:47 [INFO] train episode 4147: reward = -130.11, steps = 21 02:53:50 [INFO] train episode 4148: reward = -109.69, steps = 22 02:53:52 [INFO] train episode 4149: reward = -115.81, steps = 22 02:53:54 [INFO] train episode 4150: reward = -124.81, steps = 20 02:53:56 [INFO] train episode 4151: reward = -111.60, steps = 27 02:53:58 [INFO] train episode 4152: reward = -97.10, steps = 21 02:54:00 [INFO] train episode 4153: reward = -94.73, steps = 25 02:54:03 [INFO] train episode 4154: reward = -85.15, steps = 29 02:54:05 [INFO] train episode 4155: reward = -143.88, steps = 28 02:54:07 [INFO] train episode 4156: reward = -105.32, steps = 19 02:54:09 [INFO] train episode 4157: reward = -119.72, steps = 28 02:54:11 [INFO] train episode 4158: reward = -156.78, steps = 19 02:54:13 [INFO] train episode 4159: reward = -69.33, steps = 22 02:54:16 [INFO] train episode 4160: reward = -117.67, steps = 25 02:54:18 [INFO] train episode 4161: reward = -97.39, steps = 20 02:54:20 [INFO] train episode 4162: reward = -139.71, steps = 19 02:54:21 [INFO] train episode 4163: reward = -144.30, steps = 21 02:54:23 [INFO] train episode 4164: reward = -89.58, steps = 20 02:54:26 [INFO] train episode 4165: reward = -129.15, steps = 26 02:54:27 [INFO] train episode 4166: reward = -131.42, steps = 20 02:54:30 [INFO] train episode 4167: reward = -98.64, steps = 27 02:54:33 [INFO] train episode 4168: reward = -143.44, steps = 40 02:54:35 [INFO] train episode 4169: reward = -92.97, steps = 21 02:54:38 [INFO] train episode 4170: reward = -145.82, steps = 29 02:54:41 [INFO] train episode 4171: reward = -178.67, steps = 30 02:54:43 [INFO] train episode 4172: reward = -90.89, steps = 27 02:54:45 [INFO] train episode 4173: reward = -113.68, steps = 21 02:54:48 [INFO] train episode 4174: reward = -152.22, steps = 36 02:54:50 [INFO] train episode 4175: reward = -150.58, steps = 23 02:54:52 [INFO] train episode 4176: reward = -98.56, steps = 24 02:54:54 [INFO] train episode 4177: reward = -176.96, steps = 27 02:54:57 [INFO] train episode 4178: reward = -125.81, steps = 23 02:54:58 [INFO] train episode 4179: reward = -98.25, steps = 20 02:55:00 [INFO] train episode 4180: reward = -158.93, steps = 21 02:55:02 [INFO] train episode 4181: reward = -151.23, steps = 21 02:55:05 [INFO] train episode 4182: reward = -170.82, steps = 27 02:55:06 [INFO] train episode 4183: reward = -72.95, steps = 19 02:55:08 [INFO] train episode 4184: reward = -147.11, steps = 26 02:55:11 [INFO] train episode 4185: reward = -142.18, steps = 26 02:55:13 [INFO] train episode 4186: reward = -93.19, steps = 19 02:55:15 [INFO] train episode 4187: reward = -119.17, steps = 30 02:55:17 [INFO] train episode 4188: reward = -69.83, steps = 22 02:55:20 [INFO] train episode 4189: reward = -159.04, steps = 28 02:55:21 [INFO] train episode 4190: reward = -148.00, steps = 19 02:55:24 [INFO] train episode 4191: reward = -127.72, steps = 25 02:55:25 [INFO] train episode 4192: reward = -102.21, steps = 19 02:55:28 [INFO] train episode 4193: reward = -141.76, steps = 27 02:55:30 [INFO] train episode 4194: reward = -162.18, steps = 23 02:55:33 [INFO] train episode 4195: reward = -174.66, steps = 30 02:55:35 [INFO] train episode 4196: reward = -111.74, steps = 23 02:55:37 [INFO] train episode 4197: reward = -171.53, steps = 27 02:55:39 [INFO] train episode 4198: reward = -96.81, steps = 19 02:55:41 [INFO] train episode 4199: reward = -148.74, steps = 25 02:55:44 [INFO] train episode 4200: reward = -110.91, steps = 27 02:55:45 [INFO] train episode 4201: reward = -129.84, steps = 21 02:55:48 [INFO] train episode 4202: reward = -222.17, steps = 29 02:55:50 [INFO] train episode 4203: reward = -140.86, steps = 26 02:55:53 [INFO] train episode 4204: reward = -161.55, steps = 32 02:55:55 [INFO] train episode 4205: reward = -93.09, steps = 20 02:55:57 [INFO] train episode 4206: reward = -114.56, steps = 25 02:55:59 [INFO] train episode 4207: reward = -114.40, steps = 22 02:56:01 [INFO] train episode 4208: reward = -177.82, steps = 25 02:56:03 [INFO] train episode 4209: reward = -153.04, steps = 23 02:56:06 [INFO] train episode 4210: reward = -121.50, steps = 25 02:56:08 [INFO] train episode 4211: reward = -107.33, steps = 28 02:56:10 [INFO] train episode 4212: reward = -192.87, steps = 27 02:56:13 [INFO] train episode 4213: reward = -147.46, steps = 36 02:56:16 [INFO] train episode 4214: reward = -142.83, steps = 23 02:56:18 [INFO] train episode 4215: reward = -177.40, steps = 23 02:56:20 [INFO] train episode 4216: reward = -69.59, steps = 21 02:56:22 [INFO] train episode 4217: reward = -133.72, steps = 23 02:56:24 [INFO] train episode 4218: reward = -236.14, steps = 26 02:56:26 [INFO] train episode 4219: reward = -124.65, steps = 26 02:56:28 [INFO] train episode 4220: reward = -107.32, steps = 27 02:56:30 [INFO] train episode 4221: reward = -152.20, steps = 19 02:56:33 [INFO] train episode 4222: reward = -163.81, steps = 32 02:56:35 [INFO] train episode 4223: reward = -139.93, steps = 24 02:56:37 [INFO] train episode 4224: reward = -137.11, steps = 23 02:56:40 [INFO] train episode 4225: reward = -224.50, steps = 27 02:56:42 [INFO] train episode 4226: reward = -98.02, steps = 26 02:56:44 [INFO] train episode 4227: reward = -90.32, steps = 20 02:56:46 [INFO] train episode 4228: reward = -122.06, steps = 23 02:56:48 [INFO] train episode 4229: reward = -126.27, steps = 25 02:56:51 [INFO] train episode 4230: reward = -145.67, steps = 25 02:56:53 [INFO] train episode 4231: reward = -97.02, steps = 25 02:56:55 [INFO] train episode 4232: reward = -121.26, steps = 25 02:56:57 [INFO] train episode 4233: reward = -141.94, steps = 21 02:56:59 [INFO] train episode 4234: reward = -129.74, steps = 26 02:57:01 [INFO] train episode 4235: reward = -112.79, steps = 25 02:57:04 [INFO] train episode 4236: reward = -120.03, steps = 29 02:57:07 [INFO] train episode 4237: reward = -152.66, steps = 26 02:57:10 [INFO] train episode 4238: reward = -171.66, steps = 31 02:57:12 [INFO] train episode 4239: reward = -147.19, steps = 20 02:57:15 [INFO] train episode 4240: reward = -166.20, steps = 33 02:57:18 [INFO] train episode 4241: reward = -140.34, steps = 32 02:57:20 [INFO] train episode 4242: reward = -95.80, steps = 25 02:57:23 [INFO] train episode 4243: reward = -159.68, steps = 32 02:57:25 [INFO] train episode 4244: reward = -105.11, steps = 21 02:57:27 [INFO] train episode 4245: reward = -123.07, steps = 29 02:57:29 [INFO] train episode 4246: reward = -106.56, steps = 18 02:57:31 [INFO] train episode 4247: reward = -137.17, steps = 26 02:57:34 [INFO] train episode 4248: reward = -155.92, steps = 31 02:57:36 [INFO] train episode 4249: reward = -106.00, steps = 26 02:57:38 [INFO] train episode 4250: reward = -120.48, steps = 19 02:57:41 [INFO] train episode 4251: reward = -146.64, steps = 36 02:57:43 [INFO] train episode 4252: reward = -165.19, steps = 22 02:57:46 [INFO] train episode 4253: reward = -113.59, steps = 29 02:57:49 [INFO] train episode 4254: reward = -120.89, steps = 35 02:57:51 [INFO] train episode 4255: reward = -131.19, steps = 31 02:57:54 [INFO] train episode 4256: reward = -128.97, steps = 26 02:57:56 [INFO] train episode 4257: reward = -79.35, steps = 23 02:57:58 [INFO] train episode 4258: reward = -181.01, steps = 23 02:58:01 [INFO] train episode 4259: reward = -187.15, steps = 33 02:58:03 [INFO] train episode 4260: reward = -99.14, steps = 27 02:58:06 [INFO] train episode 4261: reward = -133.19, steps = 26 02:58:08 [INFO] train episode 4262: reward = -124.11, steps = 23 02:58:10 [INFO] train episode 4263: reward = -105.87, steps = 24 02:58:13 [INFO] train episode 4264: reward = -145.24, steps = 30 02:58:15 [INFO] train episode 4265: reward = -88.90, steps = 23 02:58:16 [INFO] train episode 4266: reward = -171.56, steps = 20 02:58:19 [INFO] train episode 4267: reward = -117.61, steps = 24 02:58:21 [INFO] train episode 4268: reward = -140.99, steps = 30 02:58:23 [INFO] train episode 4269: reward = -127.76, steps = 25 02:58:26 [INFO] train episode 4270: reward = -145.84, steps = 24 02:58:28 [INFO] train episode 4271: reward = -162.92, steps = 20 02:58:30 [INFO] train episode 4272: reward = -124.07, steps = 33 02:58:32 [INFO] train episode 4273: reward = -134.42, steps = 23 02:58:35 [INFO] train episode 4274: reward = -107.45, steps = 26 02:58:37 [INFO] train episode 4275: reward = -109.88, steps = 27 02:58:39 [INFO] train episode 4276: reward = -120.58, steps = 22 02:58:41 [INFO] train episode 4277: reward = -134.34, steps = 21 02:58:43 [INFO] train episode 4278: reward = -159.49, steps = 25 02:58:46 [INFO] train episode 4279: reward = -180.19, steps = 26 02:58:49 [INFO] train episode 4280: reward = -176.48, steps = 39 02:58:52 [INFO] train episode 4281: reward = -141.75, steps = 31 02:58:54 [INFO] train episode 4282: reward = -183.11, steps = 34 02:58:57 [INFO] train episode 4283: reward = -136.71, steps = 26 02:58:59 [INFO] train episode 4284: reward = -111.64, steps = 23 02:59:02 [INFO] train episode 4285: reward = -156.09, steps = 27 02:59:03 [INFO] train episode 4286: reward = -110.17, steps = 20 02:59:05 [INFO] train episode 4287: reward = -147.24, steps = 23 02:59:07 [INFO] train episode 4288: reward = -122.14, steps = 24 02:59:09 [INFO] train episode 4289: reward = -171.19, steps = 21 02:59:12 [INFO] train episode 4290: reward = -134.31, steps = 28 02:59:15 [INFO] train episode 4291: reward = -145.34, steps = 31 02:59:17 [INFO] train episode 4292: reward = -137.46, steps = 29 02:59:20 [INFO] train episode 4293: reward = -155.73, steps = 29 02:59:22 [INFO] train episode 4294: reward = -149.38, steps = 30 02:59:24 [INFO] train episode 4295: reward = -100.50, steps = 20 02:59:27 [INFO] train episode 4296: reward = -108.26, steps = 31 02:59:29 [INFO] train episode 4297: reward = -118.79, steps = 26 02:59:32 [INFO] train episode 4298: reward = -119.14, steps = 21 02:59:34 [INFO] train episode 4299: reward = -166.50, steps = 23 02:59:36 [INFO] train episode 4300: reward = -111.01, steps = 19 02:59:38 [INFO] train episode 4301: reward = -148.09, steps = 26 02:59:40 [INFO] train episode 4302: reward = -197.28, steps = 23 02:59:42 [INFO] train episode 4303: reward = -143.49, steps = 20 02:59:44 [INFO] train episode 4304: reward = -139.48, steps = 26 02:59:46 [INFO] train episode 4305: reward = -126.00, steps = 24 02:59:49 [INFO] train episode 4306: reward = -90.25, steps = 29 02:59:51 [INFO] train episode 4307: reward = -213.11, steps = 30 02:59:54 [INFO] train episode 4308: reward = -119.87, steps = 24 02:59:55 [INFO] train episode 4309: reward = -127.68, steps = 21 02:59:57 [INFO] train episode 4310: reward = -119.71, steps = 21 02:59:59 [INFO] train episode 4311: reward = -91.38, steps = 23 03:00:02 [INFO] train episode 4312: reward = -189.45, steps = 28 03:00:06 [INFO] train episode 4313: reward = -134.80, steps = 31 03:00:08 [INFO] train episode 4314: reward = -143.18, steps = 28 03:00:10 [INFO] train episode 4315: reward = -103.97, steps = 26 03:00:12 [INFO] train episode 4316: reward = -116.05, steps = 19 03:00:15 [INFO] train episode 4317: reward = -112.32, steps = 29 03:00:17 [INFO] train episode 4318: reward = -144.24, steps = 23 03:00:19 [INFO] train episode 4319: reward = -128.06, steps = 23 03:00:21 [INFO] train episode 4320: reward = -129.23, steps = 23 03:00:23 [INFO] train episode 4321: reward = -115.73, steps = 23 03:00:25 [INFO] train episode 4322: reward = -109.35, steps = 22 03:00:27 [INFO] train episode 4323: reward = -111.35, steps = 22 03:00:29 [INFO] train episode 4324: reward = -114.20, steps = 25 03:00:32 [INFO] train episode 4325: reward = -126.90, steps = 30 03:00:34 [INFO] train episode 4326: reward = -131.25, steps = 30 03:00:37 [INFO] train episode 4327: reward = -165.83, steps = 24 03:00:40 [INFO] train episode 4328: reward = -165.05, steps = 33 03:00:41 [INFO] train episode 4329: reward = -69.33, steps = 20 03:00:43 [INFO] train episode 4330: reward = -113.99, steps = 20 03:00:45 [INFO] train episode 4331: reward = -168.03, steps = 24 03:00:47 [INFO] train episode 4332: reward = -107.28, steps = 22 03:00:49 [INFO] train episode 4333: reward = -97.49, steps = 19 03:00:52 [INFO] train episode 4334: reward = -151.87, steps = 31 03:00:54 [INFO] train episode 4335: reward = -125.79, steps = 28 03:00:58 [INFO] train episode 4336: reward = -165.52, steps = 37 03:01:00 [INFO] train episode 4337: reward = -76.95, steps = 27 03:01:02 [INFO] train episode 4338: reward = -157.95, steps = 20 03:01:04 [INFO] train episode 4339: reward = -114.27, steps = 21 03:01:06 [INFO] train episode 4340: reward = -143.54, steps = 22 03:01:08 [INFO] train episode 4341: reward = -198.78, steps = 21 03:01:10 [INFO] train episode 4342: reward = -133.75, steps = 25 03:01:12 [INFO] train episode 4343: reward = -114.15, steps = 23 03:01:15 [INFO] train episode 4344: reward = -109.92, steps = 29 03:01:16 [INFO] train episode 4345: reward = -148.69, steps = 19 03:01:18 [INFO] train episode 4346: reward = -148.46, steps = 25 03:01:21 [INFO] train episode 4347: reward = -103.32, steps = 26 03:01:24 [INFO] train episode 4348: reward = -190.06, steps = 35 03:01:26 [INFO] train episode 4349: reward = -149.04, steps = 24 03:01:28 [INFO] train episode 4350: reward = -124.21, steps = 21 03:01:30 [INFO] train episode 4351: reward = -121.93, steps = 25 03:01:32 [INFO] train episode 4352: reward = -97.05, steps = 23 03:01:35 [INFO] train episode 4353: reward = -148.32, steps = 33 03:01:37 [INFO] train episode 4354: reward = -111.98, steps = 25 03:01:40 [INFO] train episode 4355: reward = -166.50, steps = 31 03:01:42 [INFO] train episode 4356: reward = -136.33, steps = 21 03:01:44 [INFO] train episode 4357: reward = -145.97, steps = 20 03:01:46 [INFO] train episode 4358: reward = -86.59, steps = 19 03:01:48 [INFO] train episode 4359: reward = -112.61, steps = 27 03:01:51 [INFO] train episode 4360: reward = -165.17, steps = 29 03:01:52 [INFO] train episode 4361: reward = -110.50, steps = 22 03:01:55 [INFO] train episode 4362: reward = -152.41, steps = 23 03:01:57 [INFO] train episode 4363: reward = -191.96, steps = 24 03:01:59 [INFO] train episode 4364: reward = -73.12, steps = 24 03:02:01 [INFO] train episode 4365: reward = -117.99, steps = 23 03:02:03 [INFO] train episode 4366: reward = -146.25, steps = 22 03:02:05 [INFO] train episode 4367: reward = -163.84, steps = 19 03:02:07 [INFO] train episode 4368: reward = -196.23, steps = 24 03:02:09 [INFO] train episode 4369: reward = -176.34, steps = 22 03:02:11 [INFO] train episode 4370: reward = -108.78, steps = 20 03:02:13 [INFO] train episode 4371: reward = -163.18, steps = 21 03:02:15 [INFO] train episode 4372: reward = -133.24, steps = 19 03:02:17 [INFO] train episode 4373: reward = -114.01, steps = 26 03:02:19 [INFO] train episode 4374: reward = -158.86, steps = 28 03:02:23 [INFO] train episode 4375: reward = -142.56, steps = 36 03:02:25 [INFO] train episode 4376: reward = -124.45, steps = 33 03:02:28 [INFO] train episode 4377: reward = -151.01, steps = 28 03:02:30 [INFO] train episode 4378: reward = -195.96, steps = 26 03:02:32 [INFO] train episode 4379: reward = -116.32, steps = 20 03:02:35 [INFO] train episode 4380: reward = -111.55, steps = 31 03:02:37 [INFO] train episode 4381: reward = -109.39, steps = 23 03:02:39 [INFO] train episode 4382: reward = -93.61, steps = 23 03:02:41 [INFO] train episode 4383: reward = -99.15, steps = 20 03:02:43 [INFO] train episode 4384: reward = -177.96, steps = 31 03:02:46 [INFO] train episode 4385: reward = -85.45, steps = 28 03:02:49 [INFO] train episode 4386: reward = -95.42, steps = 28 03:02:51 [INFO] train episode 4387: reward = -144.94, steps = 31 03:02:54 [INFO] train episode 4388: reward = -139.76, steps = 34 03:02:56 [INFO] train episode 4389: reward = -129.33, steps = 25 03:02:59 [INFO] train episode 4390: reward = -122.07, steps = 21 03:03:01 [INFO] train episode 4391: reward = -160.66, steps = 28 03:03:04 [INFO] train episode 4392: reward = -140.53, steps = 24 03:03:06 [INFO] train episode 4393: reward = -94.14, steps = 26 03:03:09 [INFO] train episode 4394: reward = -150.55, steps = 27 03:03:11 [INFO] train episode 4395: reward = -162.08, steps = 29 03:03:13 [INFO] train episode 4396: reward = -134.74, steps = 23 03:03:16 [INFO] train episode 4397: reward = -150.26, steps = 27 03:03:18 [INFO] train episode 4398: reward = -148.92, steps = 26 03:03:20 [INFO] train episode 4399: reward = -107.57, steps = 20 03:03:22 [INFO] train episode 4400: reward = -149.48, steps = 26 03:03:26 [INFO] train episode 4401: reward = -236.90, steps = 45 03:03:28 [INFO] train episode 4402: reward = -113.19, steps = 21 03:03:30 [INFO] train episode 4403: reward = -111.72, steps = 27 03:03:32 [INFO] train episode 4404: reward = -119.26, steps = 21 03:03:34 [INFO] train episode 4405: reward = -149.06, steps = 22 03:03:37 [INFO] train episode 4406: reward = -148.19, steps = 23 03:03:38 [INFO] train episode 4407: reward = -108.13, steps = 21 03:03:41 [INFO] train episode 4408: reward = -125.45, steps = 35 03:03:43 [INFO] train episode 4409: reward = -187.36, steps = 20 03:03:46 [INFO] train episode 4410: reward = -195.67, steps = 38 03:03:48 [INFO] train episode 4411: reward = -109.81, steps = 22 03:03:51 [INFO] train episode 4412: reward = -142.71, steps = 22 03:03:53 [INFO] train episode 4413: reward = -144.27, steps = 22 03:03:56 [INFO] train episode 4414: reward = -202.07, steps = 41 03:03:59 [INFO] train episode 4415: reward = -155.48, steps = 28 03:04:03 [INFO] train episode 4416: reward = -199.55, steps = 52 03:04:05 [INFO] train episode 4417: reward = -106.57, steps = 22 03:04:07 [INFO] train episode 4418: reward = -132.06, steps = 19 03:04:09 [INFO] train episode 4419: reward = -132.87, steps = 26 03:04:12 [INFO] train episode 4420: reward = -131.15, steps = 28 03:04:14 [INFO] train episode 4421: reward = -178.44, steps = 25 03:04:17 [INFO] train episode 4422: reward = -190.94, steps = 36 03:04:19 [INFO] train episode 4423: reward = -91.73, steps = 22 03:04:21 [INFO] train episode 4424: reward = -136.88, steps = 19 03:04:23 [INFO] train episode 4425: reward = -125.28, steps = 23 03:04:25 [INFO] train episode 4426: reward = -115.25, steps = 28 03:04:28 [INFO] train episode 4427: reward = -93.02, steps = 25 03:04:30 [INFO] train episode 4428: reward = -120.49, steps = 25 03:04:32 [INFO] train episode 4429: reward = -125.62, steps = 20 03:04:34 [INFO] train episode 4430: reward = -144.95, steps = 26 03:04:36 [INFO] train episode 4431: reward = -123.97, steps = 20 03:04:37 [INFO] train episode 4432: reward = -88.58, steps = 21 03:04:40 [INFO] train episode 4433: reward = -120.31, steps = 29 03:04:42 [INFO] train episode 4434: reward = -143.95, steps = 26 03:04:45 [INFO] train episode 4435: reward = -175.83, steps = 32 03:04:47 [INFO] train episode 4436: reward = -227.21, steps = 21 03:04:49 [INFO] train episode 4437: reward = -165.69, steps = 24 03:04:52 [INFO] train episode 4438: reward = -172.66, steps = 37 03:04:54 [INFO] train episode 4439: reward = -110.95, steps = 21 03:04:58 [INFO] train episode 4440: reward = -179.65, steps = 36 03:05:01 [INFO] train episode 4441: reward = -116.81, steps = 33 03:05:03 [INFO] train episode 4442: reward = -151.75, steps = 23 03:05:05 [INFO] train episode 4443: reward = -111.83, steps = 20 03:05:06 [INFO] train episode 4444: reward = -127.38, steps = 21 03:05:08 [INFO] train episode 4445: reward = -120.30, steps = 23 03:05:11 [INFO] train episode 4446: reward = -153.74, steps = 27 03:05:14 [INFO] train episode 4447: reward = -146.42, steps = 28 03:05:15 [INFO] train episode 4448: reward = -99.75, steps = 20 03:05:17 [INFO] train episode 4449: reward = -158.46, steps = 22 03:05:19 [INFO] train episode 4450: reward = -123.76, steps = 24 03:05:21 [INFO] train episode 4451: reward = -110.69, steps = 23 03:05:24 [INFO] train episode 4452: reward = -140.73, steps = 29 03:05:26 [INFO] train episode 4453: reward = -117.11, steps = 22 03:05:28 [INFO] train episode 4454: reward = -111.27, steps = 21 03:05:30 [INFO] train episode 4455: reward = -175.75, steps = 25 03:05:33 [INFO] train episode 4456: reward = -151.68, steps = 27 03:05:35 [INFO] train episode 4457: reward = -192.19, steps = 29 03:05:37 [INFO] train episode 4458: reward = -106.85, steps = 25 03:05:40 [INFO] train episode 4459: reward = -87.84, steps = 26 03:05:41 [INFO] train episode 4460: reward = -142.86, steps = 21 03:05:43 [INFO] train episode 4461: reward = -117.69, steps = 20 03:05:45 [INFO] train episode 4462: reward = -133.84, steps = 19 03:05:48 [INFO] train episode 4463: reward = -208.69, steps = 38 03:05:51 [INFO] train episode 4464: reward = -147.18, steps = 26 03:05:54 [INFO] train episode 4465: reward = -123.57, steps = 27 03:05:57 [INFO] train episode 4466: reward = -143.42, steps = 32 03:05:59 [INFO] train episode 4467: reward = -130.98, steps = 29 03:06:02 [INFO] train episode 4468: reward = -134.34, steps = 27 03:06:04 [INFO] train episode 4469: reward = -93.29, steps = 21 03:06:05 [INFO] train episode 4470: reward = -107.67, steps = 19 03:06:07 [INFO] train episode 4471: reward = -83.08, steps = 23 03:06:10 [INFO] train episode 4472: reward = -78.95, steps = 24 03:06:11 [INFO] train episode 4473: reward = -125.72, steps = 22 03:06:14 [INFO] train episode 4474: reward = -83.78, steps = 27 03:06:17 [INFO] train episode 4475: reward = -191.67, steps = 30 03:06:19 [INFO] train episode 4476: reward = -161.48, steps = 27 03:06:21 [INFO] train episode 4477: reward = -105.74, steps = 20 03:06:23 [INFO] train episode 4478: reward = -147.13, steps = 26 03:06:25 [INFO] train episode 4479: reward = -122.01, steps = 20 03:06:27 [INFO] train episode 4480: reward = -134.33, steps = 19 03:06:28 [INFO] train episode 4481: reward = -92.88, steps = 20 03:06:31 [INFO] train episode 4482: reward = -134.73, steps = 29 03:06:33 [INFO] train episode 4483: reward = -96.41, steps = 19 03:06:35 [INFO] train episode 4484: reward = -138.14, steps = 24 03:06:37 [INFO] train episode 4485: reward = -161.27, steps = 20 03:06:39 [INFO] train episode 4486: reward = -154.27, steps = 31 03:06:42 [INFO] train episode 4487: reward = -114.31, steps = 31 03:06:45 [INFO] train episode 4488: reward = -137.13, steps = 29 03:06:46 [INFO] train episode 4489: reward = -117.60, steps = 18 03:06:49 [INFO] train episode 4490: reward = -115.62, steps = 22 03:06:51 [INFO] train episode 4491: reward = -117.27, steps = 25 03:06:53 [INFO] train episode 4492: reward = -107.41, steps = 28 03:06:56 [INFO] train episode 4493: reward = -185.08, steps = 35 03:06:58 [INFO] train episode 4494: reward = -80.51, steps = 22 03:07:00 [INFO] train episode 4495: reward = -168.26, steps = 27 03:07:02 [INFO] train episode 4496: reward = -83.53, steps = 23 03:07:05 [INFO] train episode 4497: reward = -90.03, steps = 27 03:07:08 [INFO] train episode 4498: reward = -146.94, steps = 30 03:07:10 [INFO] train episode 4499: reward = -127.46, steps = 26 03:07:13 [INFO] train episode 4500: reward = -150.42, steps = 29 03:07:14 [INFO] train episode 4501: reward = -102.18, steps = 21 03:07:16 [INFO] train episode 4502: reward = -101.38, steps = 20 03:07:18 [INFO] train episode 4503: reward = -114.75, steps = 20 03:07:20 [INFO] train episode 4504: reward = -146.99, steps = 25 03:07:23 [INFO] train episode 4505: reward = -140.71, steps = 25 03:07:25 [INFO] train episode 4506: reward = -170.78, steps = 21 03:07:26 [INFO] train episode 4507: reward = -172.45, steps = 20 03:07:28 [INFO] train episode 4508: reward = -121.61, steps = 21 03:07:30 [INFO] train episode 4509: reward = -111.95, steps = 23 03:07:33 [INFO] train episode 4510: reward = -198.71, steps = 33 03:07:35 [INFO] train episode 4511: reward = -116.07, steps = 19 03:07:38 [INFO] train episode 4512: reward = -86.83, steps = 26 03:07:40 [INFO] train episode 4513: reward = -145.91, steps = 25 03:07:41 [INFO] train episode 4514: reward = -83.21, steps = 20 03:07:43 [INFO] train episode 4515: reward = -143.89, steps = 19 03:07:46 [INFO] train episode 4516: reward = -113.71, steps = 37 03:07:49 [INFO] train episode 4517: reward = -145.09, steps = 31 03:07:52 [INFO] train episode 4518: reward = -160.41, steps = 34 03:07:54 [INFO] train episode 4519: reward = -140.97, steps = 25 03:07:57 [INFO] train episode 4520: reward = -182.57, steps = 24 03:07:59 [INFO] train episode 4521: reward = -128.48, steps = 34 03:08:02 [INFO] train episode 4522: reward = -192.61, steps = 26 03:08:04 [INFO] train episode 4523: reward = -147.87, steps = 30 03:08:06 [INFO] train episode 4524: reward = -112.15, steps = 21 03:08:08 [INFO] train episode 4525: reward = -142.36, steps = 24 03:08:11 [INFO] train episode 4526: reward = -150.84, steps = 23 03:08:13 [INFO] train episode 4527: reward = -124.86, steps = 26 03:08:15 [INFO] train episode 4528: reward = -172.04, steps = 21 03:08:17 [INFO] train episode 4529: reward = -189.23, steps = 23 03:08:19 [INFO] train episode 4530: reward = -136.75, steps = 27 03:08:21 [INFO] train episode 4531: reward = -165.48, steps = 22 03:08:23 [INFO] train episode 4532: reward = -138.32, steps = 23 03:08:26 [INFO] train episode 4533: reward = -131.99, steps = 23 03:08:28 [INFO] train episode 4534: reward = -151.46, steps = 23 03:08:29 [INFO] train episode 4535: reward = -109.80, steps = 18 03:08:31 [INFO] train episode 4536: reward = -147.17, steps = 26 03:08:35 [INFO] train episode 4537: reward = -120.48, steps = 38 03:08:38 [INFO] train episode 4538: reward = -129.46, steps = 34 03:08:40 [INFO] train episode 4539: reward = -121.78, steps = 24 03:08:42 [INFO] train episode 4540: reward = -103.67, steps = 19 03:08:43 [INFO] train episode 4541: reward = -101.51, steps = 17 03:08:45 [INFO] train episode 4542: reward = -200.24, steps = 25 03:08:48 [INFO] train episode 4543: reward = -105.88, steps = 24 03:08:51 [INFO] train episode 4544: reward = -191.20, steps = 29 03:08:53 [INFO] train episode 4545: reward = -146.16, steps = 31 03:08:55 [INFO] train episode 4546: reward = -131.33, steps = 20 03:08:57 [INFO] train episode 4547: reward = -97.22, steps = 22 03:08:59 [INFO] train episode 4548: reward = -115.36, steps = 23 03:09:02 [INFO] train episode 4549: reward = -151.77, steps = 30 03:09:05 [INFO] train episode 4550: reward = -135.06, steps = 29 03:09:07 [INFO] train episode 4551: reward = -141.24, steps = 30 03:09:10 [INFO] train episode 4552: reward = -119.70, steps = 30 03:09:13 [INFO] train episode 4553: reward = -165.20, steps = 30 03:09:17 [INFO] train episode 4554: reward = -223.10, steps = 44 03:09:19 [INFO] train episode 4555: reward = -145.24, steps = 26 03:09:21 [INFO] train episode 4556: reward = -132.74, steps = 29 03:09:23 [INFO] train episode 4557: reward = -104.34, steps = 20 03:09:25 [INFO] train episode 4558: reward = -109.10, steps = 26 03:09:28 [INFO] train episode 4559: reward = -173.30, steps = 25 03:09:30 [INFO] train episode 4560: reward = -89.92, steps = 25 03:09:33 [INFO] train episode 4561: reward = -133.92, steps = 30 03:09:35 [INFO] train episode 4562: reward = -92.23, steps = 19 03:09:37 [INFO] train episode 4563: reward = -211.83, steps = 28 03:09:39 [INFO] train episode 4564: reward = -159.36, steps = 22 03:09:41 [INFO] train episode 4565: reward = -84.10, steps = 26 03:09:44 [INFO] train episode 4566: reward = -116.15, steps = 29 03:09:47 [INFO] train episode 4567: reward = -155.08, steps = 28 03:09:49 [INFO] train episode 4568: reward = -122.46, steps = 26 03:09:50 [INFO] train episode 4569: reward = -108.38, steps = 18 03:09:53 [INFO] train episode 4570: reward = -144.53, steps = 34 03:09:56 [INFO] train episode 4571: reward = -178.42, steps = 28 03:09:59 [INFO] train episode 4572: reward = -150.64, steps = 34 03:10:01 [INFO] train episode 4573: reward = -124.67, steps = 28 03:10:03 [INFO] train episode 4574: reward = -141.99, steps = 21 03:10:06 [INFO] train episode 4575: reward = -160.22, steps = 25 03:10:08 [INFO] train episode 4576: reward = -175.73, steps = 27 03:10:10 [INFO] train episode 4577: reward = -103.29, steps = 20 03:10:12 [INFO] train episode 4578: reward = -155.18, steps = 27 03:10:15 [INFO] train episode 4579: reward = -152.00, steps = 33 03:10:17 [INFO] train episode 4580: reward = -102.77, steps = 21 03:10:19 [INFO] train episode 4581: reward = -125.65, steps = 22 03:10:22 [INFO] train episode 4582: reward = -141.20, steps = 34 03:10:24 [INFO] train episode 4583: reward = -93.32, steps = 29 03:10:27 [INFO] train episode 4584: reward = -131.23, steps = 25 03:10:29 [INFO] train episode 4585: reward = -167.96, steps = 25 03:10:31 [INFO] train episode 4586: reward = -112.96, steps = 30 03:10:35 [INFO] train episode 4587: reward = -232.25, steps = 39 03:10:37 [INFO] train episode 4588: reward = -187.38, steps = 23 03:10:40 [INFO] train episode 4589: reward = -86.70, steps = 30 03:10:42 [INFO] train episode 4590: reward = -177.49, steps = 23 03:10:44 [INFO] train episode 4591: reward = -167.23, steps = 31 03:10:46 [INFO] train episode 4592: reward = -101.74, steps = 21 03:10:48 [INFO] train episode 4593: reward = -129.46, steps = 25 03:10:50 [INFO] train episode 4594: reward = -113.20, steps = 24 03:10:54 [INFO] train episode 4595: reward = -137.73, steps = 36 03:10:57 [INFO] train episode 4596: reward = -117.99, steps = 33 03:10:59 [INFO] train episode 4597: reward = -114.26, steps = 23 03:11:02 [INFO] train episode 4598: reward = -149.81, steps = 32 03:11:04 [INFO] train episode 4599: reward = -118.36, steps = 22 03:11:05 [INFO] train episode 4600: reward = -176.20, steps = 21 03:11:07 [INFO] train episode 4601: reward = -104.01, steps = 19 03:11:10 [INFO] train episode 4602: reward = -139.77, steps = 30 03:11:13 [INFO] train episode 4603: reward = -153.32, steps = 33 03:11:15 [INFO] train episode 4604: reward = -121.90, steps = 19 03:11:17 [INFO] train episode 4605: reward = -143.40, steps = 34 03:11:20 [INFO] train episode 4606: reward = -143.67, steps = 25 03:11:22 [INFO] train episode 4607: reward = -84.00, steps = 21 03:11:24 [INFO] train episode 4608: reward = -104.88, steps = 21 03:11:25 [INFO] train episode 4609: reward = -117.65, steps = 19 03:11:28 [INFO] train episode 4610: reward = -149.18, steps = 30 03:11:30 [INFO] train episode 4611: reward = -126.64, steps = 27 03:11:32 [INFO] train episode 4612: reward = -103.49, steps = 23 03:11:34 [INFO] train episode 4613: reward = -95.22, steps = 20 03:11:36 [INFO] train episode 4614: reward = -122.37, steps = 22 03:11:38 [INFO] train episode 4615: reward = -162.22, steps = 23 03:11:42 [INFO] train episode 4616: reward = -200.83, steps = 37 03:11:44 [INFO] train episode 4617: reward = -140.40, steps = 22 03:11:47 [INFO] train episode 4618: reward = -185.02, steps = 26 03:11:50 [INFO] train episode 4619: reward = -155.66, steps = 35 03:11:51 [INFO] train episode 4620: reward = -83.28, steps = 19 03:11:54 [INFO] train episode 4621: reward = -182.52, steps = 34 03:11:56 [INFO] train episode 4622: reward = -84.82, steps = 20 03:11:59 [INFO] train episode 4623: reward = -99.03, steps = 24 03:12:01 [INFO] train episode 4624: reward = -79.36, steps = 24 03:12:03 [INFO] train episode 4625: reward = -113.77, steps = 25 03:12:05 [INFO] train episode 4626: reward = -107.50, steps = 22 03:12:07 [INFO] train episode 4627: reward = -100.88, steps = 24 03:12:09 [INFO] train episode 4628: reward = -124.05, steps = 24 03:12:11 [INFO] train episode 4629: reward = -102.33, steps = 24 03:12:13 [INFO] train episode 4630: reward = -229.70, steps = 22 03:12:16 [INFO] train episode 4631: reward = -137.31, steps = 28 03:12:18 [INFO] train episode 4632: reward = -130.35, steps = 24 03:12:21 [INFO] train episode 4633: reward = -157.13, steps = 30 03:12:24 [INFO] train episode 4634: reward = -163.72, steps = 39 03:12:26 [INFO] train episode 4635: reward = -84.80, steps = 21 03:12:28 [INFO] train episode 4636: reward = -141.11, steps = 25 03:12:31 [INFO] train episode 4637: reward = -169.78, steps = 31 03:12:35 [INFO] train episode 4638: reward = -131.41, steps = 43 03:12:37 [INFO] train episode 4639: reward = -112.32, steps = 30 03:12:39 [INFO] train episode 4640: reward = -94.95, steps = 26 03:12:42 [INFO] train episode 4641: reward = -133.76, steps = 27 03:12:45 [INFO] train episode 4642: reward = -111.23, steps = 27 03:12:47 [INFO] train episode 4643: reward = -181.93, steps = 29 03:12:50 [INFO] train episode 4644: reward = -203.23, steps = 32 03:12:53 [INFO] train episode 4645: reward = -138.13, steps = 36 03:12:55 [INFO] train episode 4646: reward = -217.57, steps = 29 03:12:57 [INFO] train episode 4647: reward = -97.08, steps = 20 03:13:00 [INFO] train episode 4648: reward = -107.92, steps = 30 03:13:02 [INFO] train episode 4649: reward = -131.97, steps = 20 03:13:04 [INFO] train episode 4650: reward = -133.86, steps = 26 03:13:06 [INFO] train episode 4651: reward = -122.01, steps = 23 03:13:08 [INFO] train episode 4652: reward = -137.59, steps = 23 03:13:11 [INFO] train episode 4653: reward = -150.38, steps = 31 03:13:13 [INFO] train episode 4654: reward = -117.76, steps = 29 03:13:15 [INFO] train episode 4655: reward = -131.35, steps = 25 03:13:18 [INFO] train episode 4656: reward = -170.02, steps = 23 03:13:20 [INFO] train episode 4657: reward = -119.12, steps = 29 03:13:23 [INFO] train episode 4658: reward = -118.53, steps = 32 03:13:25 [INFO] train episode 4659: reward = -130.26, steps = 24 03:13:28 [INFO] train episode 4660: reward = -248.95, steps = 26 03:13:30 [INFO] train episode 4661: reward = -168.94, steps = 29 03:13:32 [INFO] train episode 4662: reward = -85.11, steps = 19 03:13:34 [INFO] train episode 4663: reward = -133.51, steps = 24 03:13:37 [INFO] train episode 4664: reward = -117.77, steps = 33 03:13:39 [INFO] train episode 4665: reward = -132.31, steps = 22 03:13:41 [INFO] train episode 4666: reward = -174.14, steps = 28 03:13:43 [INFO] train episode 4667: reward = -187.09, steps = 22 03:13:45 [INFO] train episode 4668: reward = -147.57, steps = 25 03:13:48 [INFO] train episode 4669: reward = -181.87, steps = 25 03:13:50 [INFO] train episode 4670: reward = -103.73, steps = 20 03:13:52 [INFO] train episode 4671: reward = -170.31, steps = 26 03:13:54 [INFO] train episode 4672: reward = -119.58, steps = 23 03:13:56 [INFO] train episode 4673: reward = -168.92, steps = 26 03:13:58 [INFO] train episode 4674: reward = -129.66, steps = 26 03:14:01 [INFO] train episode 4675: reward = -141.15, steps = 33 03:14:04 [INFO] train episode 4676: reward = -99.98, steps = 29 03:14:07 [INFO] train episode 4677: reward = -125.04, steps = 31 03:14:08 [INFO] train episode 4678: reward = -134.00, steps = 18 03:14:11 [INFO] train episode 4679: reward = -113.80, steps = 28 03:14:13 [INFO] train episode 4680: reward = -154.76, steps = 24 03:14:15 [INFO] train episode 4681: reward = -125.56, steps = 28 03:14:17 [INFO] train episode 4682: reward = -152.65, steps = 24 03:14:20 [INFO] train episode 4683: reward = -153.54, steps = 27 03:14:22 [INFO] train episode 4684: reward = -145.23, steps = 22 03:14:25 [INFO] train episode 4685: reward = -129.38, steps = 28 03:14:27 [INFO] train episode 4686: reward = -136.39, steps = 30 03:14:29 [INFO] train episode 4687: reward = -135.71, steps = 25 03:14:32 [INFO] train episode 4688: reward = -118.76, steps = 32 03:14:36 [INFO] train episode 4689: reward = -128.49, steps = 26 03:14:38 [INFO] train episode 4690: reward = -102.43, steps = 20 03:14:39 [INFO] train episode 4691: reward = -101.85, steps = 20 03:14:41 [INFO] train episode 4692: reward = -188.26, steps = 22 03:14:44 [INFO] train episode 4693: reward = -204.50, steps = 34 03:14:46 [INFO] train episode 4694: reward = -102.83, steps = 20 03:14:48 [INFO] train episode 4695: reward = -103.48, steps = 26 03:14:52 [INFO] train episode 4696: reward = -157.78, steps = 39 03:14:54 [INFO] train episode 4697: reward = -145.13, steps = 20 03:14:56 [INFO] train episode 4698: reward = -160.94, steps = 22 03:14:58 [INFO] train episode 4699: reward = -90.78, steps = 21 03:15:00 [INFO] train episode 4700: reward = -166.47, steps = 26 03:15:03 [INFO] train episode 4701: reward = -132.22, steps = 40 03:15:05 [INFO] train episode 4702: reward = -77.49, steps = 21 03:15:08 [INFO] train episode 4703: reward = -257.93, steps = 30 03:15:11 [INFO] train episode 4704: reward = -124.01, steps = 32 03:15:13 [INFO] train episode 4705: reward = -78.16, steps = 24 03:15:16 [INFO] train episode 4706: reward = -231.28, steps = 40 03:15:19 [INFO] train episode 4707: reward = -173.06, steps = 33 03:15:21 [INFO] train episode 4708: reward = -110.44, steps = 23 03:15:24 [INFO] train episode 4709: reward = -142.81, steps = 29 03:15:26 [INFO] train episode 4710: reward = -176.15, steps = 25 03:15:29 [INFO] train episode 4711: reward = -137.99, steps = 28 03:15:32 [INFO] train episode 4712: reward = -132.81, steps = 36 03:15:34 [INFO] train episode 4713: reward = -148.34, steps = 25 03:15:36 [INFO] train episode 4714: reward = -119.76, steps = 24 03:15:39 [INFO] train episode 4715: reward = -207.15, steps = 35 03:15:42 [INFO] train episode 4716: reward = -126.33, steps = 25 03:15:44 [INFO] train episode 4717: reward = -98.16, steps = 21 03:15:46 [INFO] train episode 4718: reward = -134.06, steps = 23 03:15:49 [INFO] train episode 4719: reward = -173.38, steps = 36 03:15:51 [INFO] train episode 4720: reward = -113.88, steps = 29 03:15:53 [INFO] train episode 4721: reward = -107.78, steps = 19 03:15:55 [INFO] train episode 4722: reward = -132.07, steps = 24 03:15:58 [INFO] train episode 4723: reward = -153.17, steps = 31 03:16:00 [INFO] train episode 4724: reward = -108.92, steps = 27 03:16:03 [INFO] train episode 4725: reward = -179.13, steps = 35 03:16:06 [INFO] train episode 4726: reward = -129.65, steps = 27 03:16:08 [INFO] train episode 4727: reward = -209.52, steps = 21 03:16:10 [INFO] train episode 4728: reward = -99.13, steps = 26 03:16:13 [INFO] train episode 4729: reward = -140.54, steps = 34 03:16:17 [INFO] train episode 4730: reward = -206.60, steps = 43 03:16:20 [INFO] train episode 4731: reward = -186.51, steps = 37 03:16:22 [INFO] train episode 4732: reward = -115.14, steps = 20 03:16:24 [INFO] train episode 4733: reward = -143.54, steps = 24 03:16:26 [INFO] train episode 4734: reward = -155.53, steps = 28 03:16:28 [INFO] train episode 4735: reward = -130.35, steps = 22 03:16:31 [INFO] train episode 4736: reward = -120.23, steps = 36 03:16:33 [INFO] train episode 4737: reward = -116.44, steps = 22 03:16:35 [INFO] train episode 4738: reward = -194.75, steps = 21 03:16:38 [INFO] train episode 4739: reward = -87.15, steps = 27 03:16:40 [INFO] train episode 4740: reward = -131.79, steps = 29 03:16:42 [INFO] train episode 4741: reward = -141.82, steps = 18 03:16:44 [INFO] train episode 4742: reward = -151.83, steps = 26 03:16:46 [INFO] train episode 4743: reward = -129.31, steps = 24 03:16:48 [INFO] train episode 4744: reward = -112.93, steps = 21 03:16:50 [INFO] train episode 4745: reward = -126.63, steps = 23 03:16:53 [INFO] train episode 4746: reward = -140.91, steps = 29 03:16:55 [INFO] train episode 4747: reward = -149.15, steps = 32 03:16:58 [INFO] train episode 4748: reward = -133.32, steps = 25 03:17:00 [INFO] train episode 4749: reward = -78.09, steps = 24 03:17:02 [INFO] train episode 4750: reward = -135.91, steps = 25 03:17:05 [INFO] train episode 4751: reward = -112.94, steps = 29 03:17:08 [INFO] train episode 4752: reward = -181.44, steps = 38 03:17:10 [INFO] train episode 4753: reward = -118.02, steps = 28 03:17:12 [INFO] train episode 4754: reward = -114.11, steps = 20 03:17:14 [INFO] train episode 4755: reward = -92.77, steps = 21 03:17:17 [INFO] train episode 4756: reward = -167.43, steps = 39 03:17:20 [INFO] train episode 4757: reward = -89.85, steps = 23 03:17:23 [INFO] train episode 4758: reward = -158.18, steps = 36 03:17:25 [INFO] train episode 4759: reward = -135.66, steps = 27 03:17:28 [INFO] train episode 4760: reward = -146.50, steps = 21 03:17:30 [INFO] train episode 4761: reward = -127.97, steps = 24 03:17:32 [INFO] train episode 4762: reward = -137.98, steps = 20 03:17:34 [INFO] train episode 4763: reward = -135.06, steps = 23 03:17:38 [INFO] train episode 4764: reward = -150.87, steps = 41 03:17:41 [INFO] train episode 4765: reward = -160.55, steps = 43 03:17:43 [INFO] train episode 4766: reward = -105.27, steps = 21 03:17:46 [INFO] train episode 4767: reward = -106.85, steps = 37 03:17:49 [INFO] train episode 4768: reward = -130.83, steps = 33 03:17:52 [INFO] train episode 4769: reward = -159.55, steps = 30 03:17:55 [INFO] train episode 4770: reward = -182.59, steps = 29 03:17:57 [INFO] train episode 4771: reward = -126.40, steps = 25 03:17:59 [INFO] train episode 4772: reward = -168.35, steps = 20 03:18:01 [INFO] train episode 4773: reward = -163.16, steps = 30 03:18:05 [INFO] train episode 4774: reward = -268.38, steps = 48 03:18:07 [INFO] train episode 4775: reward = -124.73, steps = 21 03:18:10 [INFO] train episode 4776: reward = -163.15, steps = 32 03:18:13 [INFO] train episode 4777: reward = -139.43, steps = 34 03:18:16 [INFO] train episode 4778: reward = -186.54, steps = 33 03:18:17 [INFO] train episode 4779: reward = -125.25, steps = 18 03:18:20 [INFO] train episode 4780: reward = -105.63, steps = 26 03:18:23 [INFO] train episode 4781: reward = -138.51, steps = 36 03:18:25 [INFO] train episode 4782: reward = -106.86, steps = 25 03:18:27 [INFO] train episode 4783: reward = -104.31, steps = 19 03:18:30 [INFO] train episode 4784: reward = -127.62, steps = 31 03:18:32 [INFO] train episode 4785: reward = -126.40, steps = 30 03:18:35 [INFO] train episode 4786: reward = -149.25, steps = 30 03:18:39 [INFO] train episode 4787: reward = -149.02, steps = 47 03:18:41 [INFO] train episode 4788: reward = -125.31, steps = 21 03:18:43 [INFO] train episode 4789: reward = -168.43, steps = 25 03:18:45 [INFO] train episode 4790: reward = -188.71, steps = 24 03:18:48 [INFO] train episode 4791: reward = -192.72, steps = 36 03:18:50 [INFO] train episode 4792: reward = -112.55, steps = 20 03:18:52 [INFO] train episode 4793: reward = -122.86, steps = 20 03:18:54 [INFO] train episode 4794: reward = -145.16, steps = 23 03:18:57 [INFO] train episode 4795: reward = -186.56, steps = 35 03:19:00 [INFO] train episode 4796: reward = -145.54, steps = 29 03:19:03 [INFO] train episode 4797: reward = -144.46, steps = 37 03:19:05 [INFO] train episode 4798: reward = -118.77, steps = 20 03:19:07 [INFO] train episode 4799: reward = -207.58, steps = 30 03:19:09 [INFO] train episode 4800: reward = -149.92, steps = 25 03:19:12 [INFO] train episode 4801: reward = -88.66, steps = 27 03:19:14 [INFO] train episode 4802: reward = -119.47, steps = 17 03:19:16 [INFO] train episode 4803: reward = -163.40, steps = 26 03:19:18 [INFO] train episode 4804: reward = -153.17, steps = 30 03:19:21 [INFO] train episode 4805: reward = -162.30, steps = 29 03:19:23 [INFO] train episode 4806: reward = -106.42, steps = 25 03:19:26 [INFO] train episode 4807: reward = -159.25, steps = 32 03:19:28 [INFO] train episode 4808: reward = -97.14, steps = 23 03:19:30 [INFO] train episode 4809: reward = -87.18, steps = 23 03:19:32 [INFO] train episode 4810: reward = -93.47, steps = 19 03:19:34 [INFO] train episode 4811: reward = -111.26, steps = 24 03:19:36 [INFO] train episode 4812: reward = -131.77, steps = 28 03:19:39 [INFO] train episode 4813: reward = -166.25, steps = 32 03:19:43 [INFO] train episode 4814: reward = -176.87, steps = 41 03:19:47 [INFO] train episode 4815: reward = -225.20, steps = 41 03:19:49 [INFO] train episode 4816: reward = -128.60, steps = 31 03:19:52 [INFO] train episode 4817: reward = -138.56, steps = 31 03:19:54 [INFO] train episode 4818: reward = -160.79, steps = 23 03:19:56 [INFO] train episode 4819: reward = -148.44, steps = 22 03:19:58 [INFO] train episode 4820: reward = -132.42, steps = 32 03:20:01 [INFO] train episode 4821: reward = -112.93, steps = 28 03:20:03 [INFO] train episode 4822: reward = -188.49, steps = 25 03:20:05 [INFO] train episode 4823: reward = -144.01, steps = 23 03:20:07 [INFO] train episode 4824: reward = -118.00, steps = 23 03:20:10 [INFO] train episode 4825: reward = -172.11, steps = 35 03:20:14 [INFO] train episode 4826: reward = -87.51, steps = 40 03:20:16 [INFO] train episode 4827: reward = -89.49, steps = 20 03:20:18 [INFO] train episode 4828: reward = -159.32, steps = 29 03:20:21 [INFO] train episode 4829: reward = -128.40, steps = 26 03:20:23 [INFO] train episode 4830: reward = -69.91, steps = 20 03:20:26 [INFO] train episode 4831: reward = -122.89, steps = 30 03:20:28 [INFO] train episode 4832: reward = -108.24, steps = 28 03:20:30 [INFO] train episode 4833: reward = -84.61, steps = 21 03:20:32 [INFO] train episode 4834: reward = -98.46, steps = 22 03:20:35 [INFO] train episode 4835: reward = -128.30, steps = 27 03:20:38 [INFO] train episode 4836: reward = -146.81, steps = 23 03:20:40 [INFO] train episode 4837: reward = -114.94, steps = 29 03:20:43 [INFO] train episode 4838: reward = -147.63, steps = 32 03:20:46 [INFO] train episode 4839: reward = -100.98, steps = 23 03:20:49 [INFO] train episode 4840: reward = -197.29, steps = 34 03:20:51 [INFO] train episode 4841: reward = -145.66, steps = 22 03:20:54 [INFO] train episode 4842: reward = -145.95, steps = 33 03:20:57 [INFO] train episode 4843: reward = -150.35, steps = 28 03:20:59 [INFO] train episode 4844: reward = -86.31, steps = 26 03:21:02 [INFO] train episode 4845: reward = -96.72, steps = 28 03:21:05 [INFO] train episode 4846: reward = -244.53, steps = 40 03:21:10 [INFO] train episode 4847: reward = -209.68, steps = 48 03:21:12 [INFO] train episode 4848: reward = -108.08, steps = 21 03:21:14 [INFO] train episode 4849: reward = -158.81, steps = 28 03:21:18 [INFO] train episode 4850: reward = -144.34, steps = 48 03:21:20 [INFO] train episode 4851: reward = -111.59, steps = 19 03:21:22 [INFO] train episode 4852: reward = -119.96, steps = 21 03:21:25 [INFO] train episode 4853: reward = -195.05, steps = 32 03:21:27 [INFO] train episode 4854: reward = -91.39, steps = 23 03:21:30 [INFO] train episode 4855: reward = -163.75, steps = 32 03:21:32 [INFO] train episode 4856: reward = -146.83, steps = 26 03:21:34 [INFO] train episode 4857: reward = -122.77, steps = 22 03:21:36 [INFO] train episode 4858: reward = -167.71, steps = 27 03:21:38 [INFO] train episode 4859: reward = -158.64, steps = 19 03:21:41 [INFO] train episode 4860: reward = -147.23, steps = 25 03:21:43 [INFO] train episode 4861: reward = -128.75, steps = 26 03:21:45 [INFO] train episode 4862: reward = -102.19, steps = 26 03:21:48 [INFO] train episode 4863: reward = -145.40, steps = 28 03:21:50 [INFO] train episode 4864: reward = -141.67, steps = 32 03:21:53 [INFO] train episode 4865: reward = -137.43, steps = 31 03:21:55 [INFO] train episode 4866: reward = -129.72, steps = 29 03:21:58 [INFO] train episode 4867: reward = -141.89, steps = 29 03:22:01 [INFO] train episode 4868: reward = -187.57, steps = 29 03:22:03 [INFO] train episode 4869: reward = -148.77, steps = 28 03:22:07 [INFO] train episode 4870: reward = -212.35, steps = 39 03:22:09 [INFO] train episode 4871: reward = -132.39, steps = 28 03:22:12 [INFO] train episode 4872: reward = -163.04, steps = 28 03:22:14 [INFO] train episode 4873: reward = -99.41, steps = 20 03:22:15 [INFO] train episode 4874: reward = -96.99, steps = 20 03:22:17 [INFO] train episode 4875: reward = -89.85, steps = 21 03:22:20 [INFO] train episode 4876: reward = -127.80, steps = 28 03:22:22 [INFO] train episode 4877: reward = -121.82, steps = 24 03:22:24 [INFO] train episode 4878: reward = -136.77, steps = 26 03:22:26 [INFO] train episode 4879: reward = -124.42, steps = 24 03:22:29 [INFO] train episode 4880: reward = -160.45, steps = 24 03:22:31 [INFO] train episode 4881: reward = -93.50, steps = 26 03:22:33 [INFO] train episode 4882: reward = -112.41, steps = 20 03:22:35 [INFO] train episode 4883: reward = -120.88, steps = 28 03:22:38 [INFO] train episode 4884: reward = -179.62, steps = 30 03:22:40 [INFO] train episode 4885: reward = -129.80, steps = 24 03:22:42 [INFO] train episode 4886: reward = -105.12, steps = 23 03:22:44 [INFO] train episode 4887: reward = -83.29, steps = 23 03:22:48 [INFO] train episode 4888: reward = -114.97, steps = 40 03:22:50 [INFO] train episode 4889: reward = -146.95, steps = 24 03:22:52 [INFO] train episode 4890: reward = -142.15, steps = 25 03:22:55 [INFO] train episode 4891: reward = -108.12, steps = 34 03:22:57 [INFO] train episode 4892: reward = -144.72, steps = 24 03:22:59 [INFO] train episode 4893: reward = -130.48, steps = 20 03:23:02 [INFO] train episode 4894: reward = -164.58, steps = 32 03:23:04 [INFO] train episode 4895: reward = -103.78, steps = 27 03:23:06 [INFO] train episode 4896: reward = -141.94, steps = 22 03:23:09 [INFO] train episode 4897: reward = -133.90, steps = 29 03:23:12 [INFO] train episode 4898: reward = -160.33, steps = 38 03:23:15 [INFO] train episode 4899: reward = -184.35, steps = 37 03:23:19 [INFO] train episode 4900: reward = -180.41, steps = 33 03:23:21 [INFO] train episode 4901: reward = -106.30, steps = 20 03:23:23 [INFO] train episode 4902: reward = -131.71, steps = 29 03:23:25 [INFO] train episode 4903: reward = -131.48, steps = 26 03:23:27 [INFO] train episode 4904: reward = -157.34, steps = 23 03:23:29 [INFO] train episode 4905: reward = -103.73, steps = 19 03:23:31 [INFO] train episode 4906: reward = -112.40, steps = 23 03:23:35 [INFO] train episode 4907: reward = -166.70, steps = 43 03:23:38 [INFO] train episode 4908: reward = -161.32, steps = 30 03:23:40 [INFO] train episode 4909: reward = -143.73, steps = 23 03:23:41 [INFO] train episode 4910: reward = -134.42, steps = 19 03:23:44 [INFO] train episode 4911: reward = -97.98, steps = 35 03:23:46 [INFO] train episode 4912: reward = -174.61, steps = 23 03:23:49 [INFO] train episode 4913: reward = -134.10, steps = 23 03:23:51 [INFO] train episode 4914: reward = -158.95, steps = 31 03:23:54 [INFO] train episode 4915: reward = -145.53, steps = 31 03:23:57 [INFO] train episode 4916: reward = -109.43, steps = 31 03:23:59 [INFO] train episode 4917: reward = -164.46, steps = 20 03:24:01 [INFO] train episode 4918: reward = -147.48, steps = 29 03:24:04 [INFO] train episode 4919: reward = -230.43, steps = 36 03:24:07 [INFO] train episode 4920: reward = -129.29, steps = 21 03:24:08 [INFO] train episode 4921: reward = -133.89, steps = 21 03:24:11 [INFO] train episode 4922: reward = -133.78, steps = 29 03:24:13 [INFO] train episode 4923: reward = -123.03, steps = 28 03:24:16 [INFO] train episode 4924: reward = -147.14, steps = 27 03:24:18 [INFO] train episode 4925: reward = -63.39, steps = 23 03:24:20 [INFO] train episode 4926: reward = -97.61, steps = 27 03:24:22 [INFO] train episode 4927: reward = -109.66, steps = 22 03:24:25 [INFO] train episode 4928: reward = -151.29, steps = 36 03:24:28 [INFO] train episode 4929: reward = -149.99, steps = 30 03:24:30 [INFO] train episode 4930: reward = -108.54, steps = 24 03:24:32 [INFO] train episode 4931: reward = -97.46, steps = 23 03:24:35 [INFO] train episode 4932: reward = -202.89, steps = 39 03:24:38 [INFO] train episode 4933: reward = -96.25, steps = 21 03:24:40 [INFO] train episode 4934: reward = -118.86, steps = 27 03:24:42 [INFO] train episode 4935: reward = -76.91, steps = 20 03:24:44 [INFO] train episode 4936: reward = -123.33, steps = 27 03:24:46 [INFO] train episode 4937: reward = -143.61, steps = 23 03:24:49 [INFO] train episode 4938: reward = -127.13, steps = 26 03:24:52 [INFO] train episode 4939: reward = -129.94, steps = 34 03:24:54 [INFO] train episode 4940: reward = -105.32, steps = 25 03:24:57 [INFO] train episode 4941: reward = -79.64, steps = 28 03:24:59 [INFO] train episode 4942: reward = -118.86, steps = 26 03:25:01 [INFO] train episode 4943: reward = -79.74, steps = 22 03:25:03 [INFO] train episode 4944: reward = -94.07, steps = 28 03:25:05 [INFO] train episode 4945: reward = -129.50, steps = 24 03:25:07 [INFO] train episode 4946: reward = -114.42, steps = 23 03:25:11 [INFO] train episode 4947: reward = -243.39, steps = 36 03:25:14 [INFO] train episode 4948: reward = -182.38, steps = 33 03:25:16 [INFO] train episode 4949: reward = -246.95, steps = 32 03:25:19 [INFO] train episode 4950: reward = -132.65, steps = 30 03:25:21 [INFO] train episode 4951: reward = -138.83, steps = 22 03:25:23 [INFO] train episode 4952: reward = -105.80, steps = 23 03:25:26 [INFO] train episode 4953: reward = -134.60, steps = 27 03:25:28 [INFO] train episode 4954: reward = -87.29, steps = 27 03:25:30 [INFO] train episode 4955: reward = -128.57, steps = 22 03:25:32 [INFO] train episode 4956: reward = -150.25, steps = 26 03:25:34 [INFO] train episode 4957: reward = -78.47, steps = 19 03:25:36 [INFO] train episode 4958: reward = -145.25, steps = 25 03:25:39 [INFO] train episode 4959: reward = -160.92, steps = 28 03:25:40 [INFO] train episode 4960: reward = -115.13, steps = 20 03:25:43 [INFO] train episode 4961: reward = -119.20, steps = 27 03:25:45 [INFO] train episode 4962: reward = -153.01, steps = 23 03:25:47 [INFO] train episode 4963: reward = -105.11, steps = 23 03:25:49 [INFO] train episode 4964: reward = -133.78, steps = 22 03:25:51 [INFO] train episode 4965: reward = -131.17, steps = 29 03:25:55 [INFO] train episode 4966: reward = -150.07, steps = 40 03:25:57 [INFO] train episode 4967: reward = -116.62, steps = 25 03:25:59 [INFO] train episode 4968: reward = -166.78, steps = 26 03:26:03 [INFO] train episode 4969: reward = -253.12, steps = 41 03:26:05 [INFO] train episode 4970: reward = -149.10, steps = 25 03:26:07 [INFO] train episode 4971: reward = -186.51, steps = 24 03:26:09 [INFO] train episode 4972: reward = -154.91, steps = 20 03:26:12 [INFO] train episode 4973: reward = -119.24, steps = 28 03:26:14 [INFO] train episode 4974: reward = -178.18, steps = 17 03:26:17 [INFO] train episode 4975: reward = -129.61, steps = 28 03:26:20 [INFO] train episode 4976: reward = -171.35, steps = 36 03:26:23 [INFO] train episode 4977: reward = -170.87, steps = 38 03:26:25 [INFO] train episode 4978: reward = -126.36, steps = 26 03:26:27 [INFO] train episode 4979: reward = -127.80, steps = 23 03:26:29 [INFO] train episode 4980: reward = -92.25, steps = 25 03:26:31 [INFO] train episode 4981: reward = -84.56, steps = 19 03:26:34 [INFO] train episode 4982: reward = -149.16, steps = 25 03:26:36 [INFO] train episode 4983: reward = -137.03, steps = 26 03:26:39 [INFO] train episode 4984: reward = -243.33, steps = 43 03:26:41 [INFO] train episode 4985: reward = -98.82, steps = 20 03:26:44 [INFO] train episode 4986: reward = -192.88, steps = 30 03:26:46 [INFO] train episode 4987: reward = -129.77, steps = 25 03:26:49 [INFO] train episode 4988: reward = -197.07, steps = 27 03:26:51 [INFO] train episode 4989: reward = -141.62, steps = 24 03:26:54 [INFO] train episode 4990: reward = -108.03, steps = 35 03:26:56 [INFO] train episode 4991: reward = -121.92, steps = 25 03:26:58 [INFO] train episode 4992: reward = -125.01, steps = 30 03:27:01 [INFO] train episode 4993: reward = -152.05, steps = 32 03:27:04 [INFO] train episode 4994: reward = -154.59, steps = 26 03:27:07 [INFO] train episode 4995: reward = -133.61, steps = 31 03:27:08 [INFO] train episode 4996: reward = -121.99, steps = 20 03:27:10 [INFO] train episode 4997: reward = -116.28, steps = 19 03:27:13 [INFO] train episode 4998: reward = -128.87, steps = 30 03:27:14 [INFO] train episode 4999: reward = -103.80, steps = 19 03:27:17 [INFO] train episode 5000: reward = -144.39, steps = 33 03:27:21 [INFO] train episode 5001: reward = -208.70, steps = 43 03:27:24 [INFO] train episode 5002: reward = -125.68, steps = 37 03:27:27 [INFO] train episode 5003: reward = -169.24, steps = 29 03:27:28 [INFO] train episode 5004: reward = -173.71, steps = 18 03:27:31 [INFO] train episode 5005: reward = -144.37, steps = 27 03:27:33 [INFO] train episode 5006: reward = -117.84, steps = 25 03:27:35 [INFO] train episode 5007: reward = -120.32, steps = 23 03:27:38 [INFO] train episode 5008: reward = -188.59, steps = 26 03:27:40 [INFO] train episode 5009: reward = -124.05, steps = 23 03:27:42 [INFO] train episode 5010: reward = -150.05, steps = 21 03:27:44 [INFO] train episode 5011: reward = -150.83, steps = 32 03:27:46 [INFO] train episode 5012: reward = -114.69, steps = 25 03:27:50 [INFO] train episode 5013: reward = -170.60, steps = 36 03:27:52 [INFO] train episode 5014: reward = -111.33, steps = 20 03:27:54 [INFO] train episode 5015: reward = -142.45, steps = 32 03:27:57 [INFO] train episode 5016: reward = -231.58, steps = 29 03:27:59 [INFO] train episode 5017: reward = -123.64, steps = 27 03:28:01 [INFO] train episode 5018: reward = -133.31, steps = 24 03:28:03 [INFO] train episode 5019: reward = -107.16, steps = 19 03:28:05 [INFO] train episode 5020: reward = -89.27, steps = 24 03:28:08 [INFO] train episode 5021: reward = -118.13, steps = 27 03:28:11 [INFO] train episode 5022: reward = -164.23, steps = 31 03:28:13 [INFO] train episode 5023: reward = -140.10, steps = 33 03:28:16 [INFO] train episode 5024: reward = -181.24, steps = 33 03:28:19 [INFO] train episode 5025: reward = -212.52, steps = 34 03:28:22 [INFO] train episode 5026: reward = -172.10, steps = 28 03:28:24 [INFO] train episode 5027: reward = -168.60, steps = 27 03:28:27 [INFO] train episode 5028: reward = -149.62, steps = 27 03:28:29 [INFO] train episode 5029: reward = -112.66, steps = 22 03:28:30 [INFO] train episode 5030: reward = -180.66, steps = 21 03:28:33 [INFO] train episode 5031: reward = -96.99, steps = 26 03:28:35 [INFO] train episode 5032: reward = -123.29, steps = 28 03:28:37 [INFO] train episode 5033: reward = -105.23, steps = 19 03:28:39 [INFO] train episode 5034: reward = -101.06, steps = 24 03:28:42 [INFO] train episode 5035: reward = -129.34, steps = 26 03:28:45 [INFO] train episode 5036: reward = -119.99, steps = 38 03:28:48 [INFO] train episode 5037: reward = -232.42, steps = 35 03:28:51 [INFO] train episode 5038: reward = -197.68, steps = 34 03:28:53 [INFO] train episode 5039: reward = -103.33, steps = 24 03:28:55 [INFO] train episode 5040: reward = -133.91, steps = 26 03:28:57 [INFO] train episode 5041: reward = -110.49, steps = 22 03:29:00 [INFO] train episode 5042: reward = -138.10, steps = 28 03:29:05 [INFO] train episode 5043: reward = -226.15, steps = 49 03:29:09 [INFO] train episode 5044: reward = -175.35, steps = 37 03:29:11 [INFO] train episode 5045: reward = -128.08, steps = 31 03:29:15 [INFO] train episode 5046: reward = -154.78, steps = 36 03:29:17 [INFO] train episode 5047: reward = -140.79, steps = 24 03:29:19 [INFO] train episode 5048: reward = -138.14, steps = 30 03:29:21 [INFO] train episode 5049: reward = -98.43, steps = 22 03:29:24 [INFO] train episode 5050: reward = -137.65, steps = 28 03:29:26 [INFO] train episode 5051: reward = -157.11, steps = 28 03:29:29 [INFO] train episode 5052: reward = -166.07, steps = 27 03:29:31 [INFO] train episode 5053: reward = -133.78, steps = 29 03:29:34 [INFO] train episode 5054: reward = -127.43, steps = 30 03:29:37 [INFO] train episode 5055: reward = -93.94, steps = 30 03:29:39 [INFO] train episode 5056: reward = -101.38, steps = 25 03:29:41 [INFO] train episode 5057: reward = -106.51, steps = 22 03:29:43 [INFO] train episode 5058: reward = -144.00, steps = 26 03:29:46 [INFO] train episode 5059: reward = -77.50, steps = 23 03:29:48 [INFO] train episode 5060: reward = -168.72, steps = 26 03:29:50 [INFO] train episode 5061: reward = -132.96, steps = 21 03:29:52 [INFO] train episode 5062: reward = -142.74, steps = 31 03:29:55 [INFO] train episode 5063: reward = -113.10, steps = 27 03:29:58 [INFO] train episode 5064: reward = -139.74, steps = 38 03:30:00 [INFO] train episode 5065: reward = -77.49, steps = 25 03:30:03 [INFO] train episode 5066: reward = -76.84, steps = 25 03:30:05 [INFO] train episode 5067: reward = -128.82, steps = 26 03:30:08 [INFO] train episode 5068: reward = -234.04, steps = 29 03:30:10 [INFO] train episode 5069: reward = -126.59, steps = 25 03:30:12 [INFO] train episode 5070: reward = -132.66, steps = 28 03:30:14 [INFO] train episode 5071: reward = -167.60, steps = 27 03:30:18 [INFO] train episode 5072: reward = -272.85, steps = 39 03:30:20 [INFO] train episode 5073: reward = -85.53, steps = 21 03:30:22 [INFO] train episode 5074: reward = -118.05, steps = 22 03:30:24 [INFO] train episode 5075: reward = -96.63, steps = 20 03:30:26 [INFO] train episode 5076: reward = -120.89, steps = 26 03:30:28 [INFO] train episode 5077: reward = -130.85, steps = 24 03:30:31 [INFO] train episode 5078: reward = -140.77, steps = 31 03:30:33 [INFO] train episode 5079: reward = -139.61, steps = 20 03:30:35 [INFO] train episode 5080: reward = -113.21, steps = 21 03:30:38 [INFO] train episode 5081: reward = -186.65, steps = 33 03:30:40 [INFO] train episode 5082: reward = -118.80, steps = 19 03:30:43 [INFO] train episode 5083: reward = -126.86, steps = 35 03:30:44 [INFO] train episode 5084: reward = -92.30, steps = 19 03:30:46 [INFO] train episode 5085: reward = -66.78, steps = 21 03:30:48 [INFO] train episode 5086: reward = -91.43, steps = 25 03:30:51 [INFO] train episode 5087: reward = -159.82, steps = 27 03:30:53 [INFO] train episode 5088: reward = -84.85, steps = 20 03:30:55 [INFO] train episode 5089: reward = -115.64, steps = 24 03:30:57 [INFO] train episode 5090: reward = -133.74, steps = 25 03:31:00 [INFO] train episode 5091: reward = -227.66, steps = 32 03:31:02 [INFO] train episode 5092: reward = -129.37, steps = 25 03:31:06 [INFO] train episode 5093: reward = -138.51, steps = 47 03:31:09 [INFO] train episode 5094: reward = -195.00, steps = 30 03:31:11 [INFO] train episode 5095: reward = -132.92, steps = 24 03:31:15 [INFO] train episode 5096: reward = -205.13, steps = 40 03:31:17 [INFO] train episode 5097: reward = -123.93, steps = 23 03:31:19 [INFO] train episode 5098: reward = -100.02, steps = 28 03:31:22 [INFO] train episode 5099: reward = -134.51, steps = 27 03:31:24 [INFO] train episode 5100: reward = -191.91, steps = 25 03:31:26 [INFO] train episode 5101: reward = -104.90, steps = 20 03:31:28 [INFO] train episode 5102: reward = -210.20, steps = 25 03:31:30 [INFO] train episode 5103: reward = -123.17, steps = 27 03:31:32 [INFO] train episode 5104: reward = -160.85, steps = 21 03:31:35 [INFO] train episode 5105: reward = -131.91, steps = 27 03:31:38 [INFO] train episode 5106: reward = -117.79, steps = 31 03:31:40 [INFO] train episode 5107: reward = -110.59, steps = 25 03:31:42 [INFO] train episode 5108: reward = -94.37, steps = 25 03:31:44 [INFO] train episode 5109: reward = -188.31, steps = 27 03:31:46 [INFO] train episode 5110: reward = -117.19, steps = 19 03:31:49 [INFO] train episode 5111: reward = -164.40, steps = 33 03:31:51 [INFO] train episode 5112: reward = -154.62, steps = 24 03:31:54 [INFO] train episode 5113: reward = -147.60, steps = 26 03:31:56 [INFO] train episode 5114: reward = -143.07, steps = 30 03:31:59 [INFO] train episode 5115: reward = -165.92, steps = 19 03:32:01 [INFO] train episode 5116: reward = -79.44, steps = 25 03:32:03 [INFO] train episode 5117: reward = -118.85, steps = 22 03:32:04 [INFO] train episode 5118: reward = -98.03, steps = 20 03:32:06 [INFO] train episode 5119: reward = -95.65, steps = 19 03:32:09 [INFO] train episode 5120: reward = -170.11, steps = 27 03:32:11 [INFO] train episode 5121: reward = -71.78, steps = 23 03:32:13 [INFO] train episode 5122: reward = -113.38, steps = 21 03:32:16 [INFO] train episode 5123: reward = -140.16, steps = 32 03:32:17 [INFO] train episode 5124: reward = -134.45, steps = 22 03:32:20 [INFO] train episode 5125: reward = -81.60, steps = 25 03:32:21 [INFO] train episode 5126: reward = -115.55, steps = 22 03:32:24 [INFO] train episode 5127: reward = -159.57, steps = 28 03:32:26 [INFO] train episode 5128: reward = -95.02, steps = 23 03:32:28 [INFO] train episode 5129: reward = -89.71, steps = 20 03:32:30 [INFO] train episode 5130: reward = -145.40, steps = 25 03:32:32 [INFO] train episode 5131: reward = -115.50, steps = 21 03:32:34 [INFO] train episode 5132: reward = -60.77, steps = 24 03:32:36 [INFO] train episode 5133: reward = -74.29, steps = 23 03:32:40 [INFO] train episode 5134: reward = -112.04, steps = 43 03:32:43 [INFO] train episode 5135: reward = -139.57, steps = 30 03:32:45 [INFO] train episode 5136: reward = -93.95, steps = 28 03:32:47 [INFO] train episode 5137: reward = -127.37, steps = 18 03:32:49 [INFO] train episode 5138: reward = -130.33, steps = 26 03:32:53 [INFO] train episode 5139: reward = -110.79, steps = 41 03:32:56 [INFO] train episode 5140: reward = -106.77, steps = 36 03:32:58 [INFO] train episode 5141: reward = -107.50, steps = 24 03:33:00 [INFO] train episode 5142: reward = -79.52, steps = 23 03:33:03 [INFO] train episode 5143: reward = -112.06, steps = 29 03:33:05 [INFO] train episode 5144: reward = -110.27, steps = 24 03:33:09 [INFO] train episode 5145: reward = -262.00, steps = 53 03:33:11 [INFO] train episode 5146: reward = -142.55, steps = 18 03:33:14 [INFO] train episode 5147: reward = -103.01, steps = 29 03:33:16 [INFO] train episode 5148: reward = -125.13, steps = 23 03:33:18 [INFO] train episode 5149: reward = -96.44, steps = 21 03:33:19 [INFO] train episode 5150: reward = -134.30, steps = 20 03:33:22 [INFO] train episode 5151: reward = -155.72, steps = 26 03:33:23 [INFO] train episode 5152: reward = -96.94, steps = 19 03:33:26 [INFO] train episode 5153: reward = -114.70, steps = 25 03:33:28 [INFO] train episode 5154: reward = -145.36, steps = 32 03:33:31 [INFO] train episode 5155: reward = -112.37, steps = 26 03:33:33 [INFO] train episode 5156: reward = -119.91, steps = 19 03:33:35 [INFO] train episode 5157: reward = -96.31, steps = 22 03:33:36 [INFO] train episode 5158: reward = -163.86, steps = 19 03:33:38 [INFO] train episode 5159: reward = -103.27, steps = 20 03:33:40 [INFO] train episode 5160: reward = -94.51, steps = 22 03:33:43 [INFO] train episode 5161: reward = -154.37, steps = 34 03:33:45 [INFO] train episode 5162: reward = -186.42, steps = 28 03:33:48 [INFO] train episode 5163: reward = -137.47, steps = 23 03:33:53 [INFO] train episode 5164: reward = -251.75, steps = 57 03:33:55 [INFO] train episode 5165: reward = -154.70, steps = 25 03:33:56 [INFO] train episode 5166: reward = -151.96, steps = 20 03:33:59 [INFO] train episode 5167: reward = -103.60, steps = 26 03:34:01 [INFO] train episode 5168: reward = -139.62, steps = 23 03:34:03 [INFO] train episode 5169: reward = -130.71, steps = 25 03:34:05 [INFO] train episode 5170: reward = -87.71, steps = 19 03:34:08 [INFO] train episode 5171: reward = -136.57, steps = 31 03:34:10 [INFO] train episode 5172: reward = -123.65, steps = 22 03:34:12 [INFO] train episode 5173: reward = -139.09, steps = 26 03:34:14 [INFO] train episode 5174: reward = -131.59, steps = 23 03:34:17 [INFO] train episode 5175: reward = -181.14, steps = 29 03:34:19 [INFO] train episode 5176: reward = -136.53, steps = 24 03:34:21 [INFO] train episode 5177: reward = -103.24, steps = 27 03:34:23 [INFO] train episode 5178: reward = -110.99, steps = 20 03:34:26 [INFO] train episode 5179: reward = -84.24, steps = 29 03:34:28 [INFO] train episode 5180: reward = -190.86, steps = 31 03:34:30 [INFO] train episode 5181: reward = -70.58, steps = 20 03:34:32 [INFO] train episode 5182: reward = -121.77, steps = 21 03:34:35 [INFO] train episode 5183: reward = -121.80, steps = 26 03:34:37 [INFO] train episode 5184: reward = -96.36, steps = 21 03:34:39 [INFO] train episode 5185: reward = -149.91, steps = 25 03:34:41 [INFO] train episode 5186: reward = -145.69, steps = 23 03:34:43 [INFO] train episode 5187: reward = -162.23, steps = 24 03:34:45 [INFO] train episode 5188: reward = -115.65, steps = 22 03:34:47 [INFO] train episode 5189: reward = -117.73, steps = 23 03:34:50 [INFO] train episode 5190: reward = -185.80, steps = 32 03:34:53 [INFO] train episode 5191: reward = -107.55, steps = 26 03:34:55 [INFO] train episode 5192: reward = -96.94, steps = 23 03:34:58 [INFO] train episode 5193: reward = -87.09, steps = 27 03:35:00 [INFO] train episode 5194: reward = -114.84, steps = 24 03:35:02 [INFO] train episode 5195: reward = -120.15, steps = 26 03:35:04 [INFO] train episode 5196: reward = -101.16, steps = 20 03:35:05 [INFO] train episode 5197: reward = -95.70, steps = 20 03:35:08 [INFO] train episode 5198: reward = -127.02, steps = 23 03:35:10 [INFO] train episode 5199: reward = -154.69, steps = 29 03:35:14 [INFO] train episode 5200: reward = -123.45, steps = 39 03:35:16 [INFO] train episode 5201: reward = -100.25, steps = 23 03:35:18 [INFO] train episode 5202: reward = -156.73, steps = 28 03:35:21 [INFO] train episode 5203: reward = -131.36, steps = 29 03:35:23 [INFO] train episode 5204: reward = -160.68, steps = 26 03:35:26 [INFO] train episode 5205: reward = -121.42, steps = 27 03:35:28 [INFO] train episode 5206: reward = -103.28, steps = 22 03:35:29 [INFO] train episode 5207: reward = -125.95, steps = 21 03:35:32 [INFO] train episode 5208: reward = -138.59, steps = 27 03:35:34 [INFO] train episode 5209: reward = -136.29, steps = 30 03:35:36 [INFO] train episode 5210: reward = -143.90, steps = 24 03:35:38 [INFO] train episode 5211: reward = -99.59, steps = 24 03:35:42 [INFO] train episode 5212: reward = -215.61, steps = 32 03:35:44 [INFO] train episode 5213: reward = -239.49, steps = 34 03:35:47 [INFO] train episode 5214: reward = -164.71, steps = 30 03:35:49 [INFO] train episode 5215: reward = -89.80, steps = 20 03:35:51 [INFO] train episode 5216: reward = -123.02, steps = 24 03:35:53 [INFO] train episode 5217: reward = -101.54, steps = 23 03:35:56 [INFO] train episode 5218: reward = -135.31, steps = 32 03:35:58 [INFO] train episode 5219: reward = -113.71, steps = 21 03:36:00 [INFO] train episode 5220: reward = -105.30, steps = 28 03:36:04 [INFO] train episode 5221: reward = -169.33, steps = 43 03:36:06 [INFO] train episode 5222: reward = -87.37, steps = 28 03:36:09 [INFO] train episode 5223: reward = -161.09, steps = 33 03:36:13 [INFO] train episode 5224: reward = -124.79, steps = 38 03:36:16 [INFO] train episode 5225: reward = -144.18, steps = 32 03:36:18 [INFO] train episode 5226: reward = -156.63, steps = 27 03:36:20 [INFO] train episode 5227: reward = -160.57, steps = 28 03:36:22 [INFO] train episode 5228: reward = -63.32, steps = 20 03:36:26 [INFO] train episode 5229: reward = -146.96, steps = 41 03:36:28 [INFO] train episode 5230: reward = -112.03, steps = 20 03:36:31 [INFO] train episode 5231: reward = -167.20, steps = 31 03:36:33 [INFO] train episode 5232: reward = -96.16, steps = 27 03:36:35 [INFO] train episode 5233: reward = -137.97, steps = 26 03:36:38 [INFO] train episode 5234: reward = -149.18, steps = 26 03:36:40 [INFO] train episode 5235: reward = -107.40, steps = 29 03:36:42 [INFO] train episode 5236: reward = -222.84, steps = 19 03:36:45 [INFO] train episode 5237: reward = -91.46, steps = 28 03:36:46 [INFO] train episode 5238: reward = -85.51, steps = 19 03:36:48 [INFO] train episode 5239: reward = -94.09, steps = 20 03:36:51 [INFO] train episode 5240: reward = -118.29, steps = 32 03:36:53 [INFO] train episode 5241: reward = -97.15, steps = 25 03:36:55 [INFO] train episode 5242: reward = -152.15, steps = 22 03:36:57 [INFO] train episode 5243: reward = -86.24, steps = 21 03:36:58 [INFO] train episode 5244: reward = -79.47, steps = 19 03:37:01 [INFO] train episode 5245: reward = -91.57, steps = 21 03:37:03 [INFO] train episode 5246: reward = -121.04, steps = 24 03:37:05 [INFO] train episode 5247: reward = -91.46, steps = 28 03:37:07 [INFO] train episode 5248: reward = -100.84, steps = 25 03:37:10 [INFO] train episode 5249: reward = -99.45, steps = 27 03:37:11 [INFO] train episode 5250: reward = -113.20, steps = 20 03:37:14 [INFO] train episode 5251: reward = -90.55, steps = 33 03:37:16 [INFO] train episode 5252: reward = -133.25, steps = 20 03:37:19 [INFO] train episode 5253: reward = -182.45, steps = 29 03:37:21 [INFO] train episode 5254: reward = -125.16, steps = 24 03:37:25 [INFO] train episode 5255: reward = -125.42, steps = 34 03:37:27 [INFO] train episode 5256: reward = -106.71, steps = 27 03:37:29 [INFO] train episode 5257: reward = -116.96, steps = 21 03:37:31 [INFO] train episode 5258: reward = -92.09, steps = 19 03:37:34 [INFO] train episode 5259: reward = -137.50, steps = 34 03:37:37 [INFO] train episode 5260: reward = -149.43, steps = 27 03:37:39 [INFO] train episode 5261: reward = -83.56, steps = 19 03:37:41 [INFO] train episode 5262: reward = -127.26, steps = 30 03:37:45 [INFO] train episode 5263: reward = -295.01, steps = 44 03:37:49 [INFO] train episode 5264: reward = -193.79, steps = 29 03:37:51 [INFO] train episode 5265: reward = -130.99, steps = 25 03:37:53 [INFO] train episode 5266: reward = -134.25, steps = 19 03:37:55 [INFO] train episode 5267: reward = -125.71, steps = 22 03:37:57 [INFO] train episode 5268: reward = -131.58, steps = 25 03:37:59 [INFO] train episode 5269: reward = -77.32, steps = 19 03:38:02 [INFO] train episode 5270: reward = -152.34, steps = 31 03:38:04 [INFO] train episode 5271: reward = -166.21, steps = 27 03:38:06 [INFO] train episode 5272: reward = -117.85, steps = 20 03:38:08 [INFO] train episode 5273: reward = -88.36, steps = 21 03:38:10 [INFO] train episode 5274: reward = -128.68, steps = 19 03:38:12 [INFO] train episode 5275: reward = -119.55, steps = 27 03:38:14 [INFO] train episode 5276: reward = -117.65, steps = 19 03:38:17 [INFO] train episode 5277: reward = -183.38, steps = 30 03:38:19 [INFO] train episode 5278: reward = -98.27, steps = 23 03:38:22 [INFO] train episode 5279: reward = -236.05, steps = 35 03:38:26 [INFO] train episode 5280: reward = -181.22, steps = 33 03:38:28 [INFO] train episode 5281: reward = -134.14, steps = 29 03:38:31 [INFO] train episode 5282: reward = -168.24, steps = 23 03:38:33 [INFO] train episode 5283: reward = -126.72, steps = 22 03:38:35 [INFO] train episode 5284: reward = -166.43, steps = 30 03:38:37 [INFO] train episode 5285: reward = -109.74, steps = 21 03:38:40 [INFO] train episode 5286: reward = -139.73, steps = 30 03:38:45 [INFO] train episode 5287: reward = -193.45, steps = 43 03:38:46 [INFO] train episode 5288: reward = -136.17, steps = 19 03:38:49 [INFO] train episode 5289: reward = -115.05, steps = 30 03:38:52 [INFO] train episode 5290: reward = -143.08, steps = 25 03:38:54 [INFO] train episode 5291: reward = -137.44, steps = 22 03:38:56 [INFO] train episode 5292: reward = -116.92, steps = 27 03:38:59 [INFO] train episode 5293: reward = -174.33, steps = 32 03:39:02 [INFO] train episode 5294: reward = -179.67, steps = 29 03:39:05 [INFO] train episode 5295: reward = -170.07, steps = 28 03:39:08 [INFO] train episode 5296: reward = -153.35, steps = 31 03:39:10 [INFO] train episode 5297: reward = -155.82, steps = 25 03:39:12 [INFO] train episode 5298: reward = -66.79, steps = 20 03:39:14 [INFO] train episode 5299: reward = -241.49, steps = 25 03:39:17 [INFO] train episode 5300: reward = -164.07, steps = 31 03:39:21 [INFO] train episode 5301: reward = -233.10, steps = 45 03:39:24 [INFO] train episode 5302: reward = -69.72, steps = 24 03:39:27 [INFO] train episode 5303: reward = -130.88, steps = 30 03:39:30 [INFO] train episode 5304: reward = -115.86, steps = 33 03:39:33 [INFO] train episode 5305: reward = -80.57, steps = 32 03:39:37 [INFO] train episode 5306: reward = -181.46, steps = 43 03:39:39 [INFO] train episode 5307: reward = -120.68, steps = 25 03:39:41 [INFO] train episode 5308: reward = -90.88, steps = 21 03:39:43 [INFO] train episode 5309: reward = -243.82, steps = 24 03:39:44 [INFO] train episode 5310: reward = -164.70, steps = 20 03:39:47 [INFO] train episode 5311: reward = -75.35, steps = 23 03:39:49 [INFO] train episode 5312: reward = -156.50, steps = 29 03:39:52 [INFO] train episode 5313: reward = -148.88, steps = 30 03:39:55 [INFO] train episode 5314: reward = -169.81, steps = 31 03:39:57 [INFO] train episode 5315: reward = -133.84, steps = 24 03:39:59 [INFO] train episode 5316: reward = -175.23, steps = 26 03:40:01 [INFO] train episode 5317: reward = -73.94, steps = 19 03:40:03 [INFO] train episode 5318: reward = -129.80, steps = 23 03:40:06 [INFO] train episode 5319: reward = -123.07, steps = 33 03:40:08 [INFO] train episode 5320: reward = -122.73, steps = 19 03:40:09 [INFO] train episode 5321: reward = -114.92, steps = 21 03:40:11 [INFO] train episode 5322: reward = -105.21, steps = 21 03:40:14 [INFO] train episode 5323: reward = -153.12, steps = 28 03:40:15 [INFO] train episode 5324: reward = -145.41, steps = 20 03:40:18 [INFO] train episode 5325: reward = -123.53, steps = 27 03:40:21 [INFO] train episode 5326: reward = -150.55, steps = 35 03:40:24 [INFO] train episode 5327: reward = -89.63, steps = 32 03:40:26 [INFO] train episode 5328: reward = -210.32, steps = 30 03:40:29 [INFO] train episode 5329: reward = -182.32, steps = 32 03:40:31 [INFO] train episode 5330: reward = -103.86, steps = 23 03:40:33 [INFO] train episode 5331: reward = -83.01, steps = 21 03:40:37 [INFO] train episode 5332: reward = -160.59, steps = 43 03:40:40 [INFO] train episode 5333: reward = -144.82, steps = 28 03:40:43 [INFO] train episode 5334: reward = -118.09, steps = 34 03:40:45 [INFO] train episode 5335: reward = -155.74, steps = 24 03:40:49 [INFO] train episode 5336: reward = -148.41, steps = 39 03:40:51 [INFO] train episode 5337: reward = -132.44, steps = 30 03:40:54 [INFO] train episode 5338: reward = -130.27, steps = 25 03:40:57 [INFO] train episode 5339: reward = -184.73, steps = 30 03:40:59 [INFO] train episode 5340: reward = -90.55, steps = 25 03:41:01 [INFO] train episode 5341: reward = -155.91, steps = 23 03:41:03 [INFO] train episode 5342: reward = -80.00, steps = 23 03:41:06 [INFO] train episode 5343: reward = -162.34, steps = 36 03:41:09 [INFO] train episode 5344: reward = -212.26, steps = 33 03:41:11 [INFO] train episode 5345: reward = -162.29, steps = 27 03:41:13 [INFO] train episode 5346: reward = -77.02, steps = 19 03:41:15 [INFO] train episode 5347: reward = -158.42, steps = 24 03:41:17 [INFO] train episode 5348: reward = -93.82, steps = 27 03:41:20 [INFO] train episode 5349: reward = -127.00, steps = 25 03:41:22 [INFO] train episode 5350: reward = -133.37, steps = 26 03:41:24 [INFO] train episode 5351: reward = -137.57, steps = 29 03:41:27 [INFO] train episode 5352: reward = -116.08, steps = 23 03:41:30 [INFO] train episode 5353: reward = -144.23, steps = 32 03:41:31 [INFO] train episode 5354: reward = -98.26, steps = 21 03:41:33 [INFO] train episode 5355: reward = -122.64, steps = 22 03:41:35 [INFO] train episode 5356: reward = -132.72, steps = 17 03:41:37 [INFO] train episode 5357: reward = -98.63, steps = 20 03:41:39 [INFO] train episode 5358: reward = -134.56, steps = 24 03:41:40 [INFO] train episode 5359: reward = -102.98, steps = 21 03:41:43 [INFO] train episode 5360: reward = -114.53, steps = 29 03:41:46 [INFO] train episode 5361: reward = -129.08, steps = 27 03:41:51 [INFO] train episode 5362: reward = -264.77, steps = 59 03:41:53 [INFO] train episode 5363: reward = -97.84, steps = 26 03:41:55 [INFO] train episode 5364: reward = -155.29, steps = 22 03:41:57 [INFO] train episode 5365: reward = -161.39, steps = 21 03:41:59 [INFO] train episode 5366: reward = -122.02, steps = 22 03:42:01 [INFO] train episode 5367: reward = -143.99, steps = 28 03:42:04 [INFO] train episode 5368: reward = -97.32, steps = 28 03:42:06 [INFO] train episode 5369: reward = -164.00, steps = 26 03:42:08 [INFO] train episode 5370: reward = -132.04, steps = 25 03:42:10 [INFO] train episode 5371: reward = -99.70, steps = 21 03:42:13 [INFO] train episode 5372: reward = -195.41, steps = 28 03:42:15 [INFO] train episode 5373: reward = -121.13, steps = 28 03:42:17 [INFO] train episode 5374: reward = -122.20, steps = 23 03:42:19 [INFO] train episode 5375: reward = -123.93, steps = 22 03:42:21 [INFO] train episode 5376: reward = -142.70, steps = 16 03:42:24 [INFO] train episode 5377: reward = -131.75, steps = 35 03:42:26 [INFO] train episode 5378: reward = -108.15, steps = 29 03:42:30 [INFO] train episode 5379: reward = -197.39, steps = 39 03:42:32 [INFO] train episode 5380: reward = -75.27, steps = 21 03:42:33 [INFO] train episode 5381: reward = -79.33, steps = 19 03:42:36 [INFO] train episode 5382: reward = -171.28, steps = 29 03:42:42 [INFO] train episode 5383: reward = -229.60, steps = 64 03:42:43 [INFO] train episode 5384: reward = -95.42, steps = 23 03:42:46 [INFO] train episode 5385: reward = -120.74, steps = 25 03:42:50 [INFO] train episode 5386: reward = -212.05, steps = 42 03:42:55 [INFO] train episode 5387: reward = -276.55, steps = 60 03:42:57 [INFO] train episode 5388: reward = -155.66, steps = 26 03:42:59 [INFO] train episode 5389: reward = -90.99, steps = 21 03:43:01 [INFO] train episode 5390: reward = -95.15, steps = 21 03:43:03 [INFO] train episode 5391: reward = -104.71, steps = 19 03:43:05 [INFO] train episode 5392: reward = -230.97, steps = 30 03:43:07 [INFO] train episode 5393: reward = -85.28, steps = 24 03:43:10 [INFO] train episode 5394: reward = -121.84, steps = 30 03:43:14 [INFO] train episode 5395: reward = -214.86, steps = 42 03:43:15 [INFO] train episode 5396: reward = -133.33, steps = 20 03:43:19 [INFO] train episode 5397: reward = -219.77, steps = 44 03:43:21 [INFO] train episode 5398: reward = -118.33, steps = 23 03:43:23 [INFO] train episode 5399: reward = -93.45, steps = 24 03:43:26 [INFO] train episode 5400: reward = -124.79, steps = 26 03:43:28 [INFO] train episode 5401: reward = -123.38, steps = 21 03:43:29 [INFO] train episode 5402: reward = -129.63, steps = 21 03:43:32 [INFO] train episode 5403: reward = -170.83, steps = 25 03:43:34 [INFO] train episode 5404: reward = -109.24, steps = 24 03:43:36 [INFO] train episode 5405: reward = -148.25, steps = 24 03:43:38 [INFO] train episode 5406: reward = -162.05, steps = 25 03:43:41 [INFO] train episode 5407: reward = -171.81, steps = 22 03:43:43 [INFO] train episode 5408: reward = -154.43, steps = 18 03:43:44 [INFO] train episode 5409: reward = -112.97, steps = 19 03:43:47 [INFO] train episode 5410: reward = -170.22, steps = 34 03:43:50 [INFO] train episode 5411: reward = -118.33, steps = 31 03:43:53 [INFO] train episode 5412: reward = -125.00, steps = 32 03:43:55 [INFO] train episode 5413: reward = -157.10, steps = 23 03:43:57 [INFO] train episode 5414: reward = -93.91, steps = 26 03:43:59 [INFO] train episode 5415: reward = -118.47, steps = 22 03:44:02 [INFO] train episode 5416: reward = -96.54, steps = 27 03:44:04 [INFO] train episode 5417: reward = -103.31, steps = 24 03:44:06 [INFO] train episode 5418: reward = -96.99, steps = 26 03:44:09 [INFO] train episode 5419: reward = -153.15, steps = 30 03:44:11 [INFO] train episode 5420: reward = -127.75, steps = 29 03:44:14 [INFO] train episode 5421: reward = -150.31, steps = 34 03:44:16 [INFO] train episode 5422: reward = -79.55, steps = 24 03:44:19 [INFO] train episode 5423: reward = -165.73, steps = 35 03:44:21 [INFO] train episode 5424: reward = -177.37, steps = 21 03:44:23 [INFO] train episode 5425: reward = -97.27, steps = 19 03:44:26 [INFO] train episode 5426: reward = -150.25, steps = 27 03:44:30 [INFO] train episode 5427: reward = -236.83, steps = 48 03:44:32 [INFO] train episode 5428: reward = -78.17, steps = 31 03:44:34 [INFO] train episode 5429: reward = -131.28, steps = 25 03:44:37 [INFO] train episode 5430: reward = -151.40, steps = 23 03:44:40 [INFO] train episode 5431: reward = -160.71, steps = 35 03:44:42 [INFO] train episode 5432: reward = -142.34, steps = 22 03:44:46 [INFO] train episode 5433: reward = -215.80, steps = 40 03:44:49 [INFO] train episode 5434: reward = -176.58, steps = 37 03:44:50 [INFO] train episode 5435: reward = -50.78, steps = 19 03:44:53 [INFO] train episode 5436: reward = -120.05, steps = 28 03:44:55 [INFO] train episode 5437: reward = -132.93, steps = 25 03:44:57 [INFO] train episode 5438: reward = -117.66, steps = 21 03:45:00 [INFO] train episode 5439: reward = -162.45, steps = 28 03:45:02 [INFO] train episode 5440: reward = -76.29, steps = 23 03:45:03 [INFO] train episode 5441: reward = -84.98, steps = 20 03:45:06 [INFO] train episode 5442: reward = -181.86, steps = 27 03:45:08 [INFO] train episode 5443: reward = -198.29, steps = 29 03:45:11 [INFO] train episode 5444: reward = -161.64, steps = 26 03:45:13 [INFO] train episode 5445: reward = -134.58, steps = 30 03:45:16 [INFO] train episode 5446: reward = -123.07, steps = 26 03:45:18 [INFO] train episode 5447: reward = -131.19, steps = 27 03:45:20 [INFO] train episode 5448: reward = -151.05, steps = 20 03:45:23 [INFO] train episode 5449: reward = -136.01, steps = 37 03:45:25 [INFO] train episode 5450: reward = -72.22, steps = 20 03:45:27 [INFO] train episode 5451: reward = -124.70, steps = 26 03:45:29 [INFO] train episode 5452: reward = -89.42, steps = 20 03:45:32 [INFO] train episode 5453: reward = -191.09, steps = 37 03:45:34 [INFO] train episode 5454: reward = -104.51, steps = 23 03:45:37 [INFO] train episode 5455: reward = -169.99, steps = 28 03:45:39 [INFO] train episode 5456: reward = -124.90, steps = 24 03:45:42 [INFO] train episode 5457: reward = -143.04, steps = 35 03:45:45 [INFO] train episode 5458: reward = -175.90, steps = 29 03:45:47 [INFO] train episode 5459: reward = -102.58, steps = 26 03:45:49 [INFO] train episode 5460: reward = -80.83, steps = 19 03:45:50 [INFO] train episode 5461: reward = -130.88, steps = 20 03:45:52 [INFO] train episode 5462: reward = -115.35, steps = 20 03:45:55 [INFO] train episode 5463: reward = -151.92, steps = 30 03:45:57 [INFO] train episode 5464: reward = -133.25, steps = 24 03:45:59 [INFO] train episode 5465: reward = -101.71, steps = 30 03:46:02 [INFO] train episode 5466: reward = -122.02, steps = 22 03:46:04 [INFO] train episode 5467: reward = -101.49, steps = 23 03:46:06 [INFO] train episode 5468: reward = -138.97, steps = 30 03:46:08 [INFO] train episode 5469: reward = -93.57, steps = 20 03:46:11 [INFO] train episode 5470: reward = -105.58, steps = 33 03:46:13 [INFO] train episode 5471: reward = -111.04, steps = 23 03:46:15 [INFO] train episode 5472: reward = -114.16, steps = 24 03:46:17 [INFO] train episode 5473: reward = -91.80, steps = 20 03:46:19 [INFO] train episode 5474: reward = -122.55, steps = 19 03:46:21 [INFO] train episode 5475: reward = -150.96, steps = 27 03:46:23 [INFO] train episode 5476: reward = -124.78, steps = 26 03:46:25 [INFO] train episode 5477: reward = -121.80, steps = 24 03:46:29 [INFO] train episode 5478: reward = -153.16, steps = 41 03:46:31 [INFO] train episode 5479: reward = -128.94, steps = 23 03:46:34 [INFO] train episode 5480: reward = -131.83, steps = 22 03:46:36 [INFO] train episode 5481: reward = -150.74, steps = 20 03:46:38 [INFO] train episode 5482: reward = -131.11, steps = 23 03:46:41 [INFO] train episode 5483: reward = -195.44, steps = 27 03:46:42 [INFO] train episode 5484: reward = -172.57, steps = 18 03:46:44 [INFO] train episode 5485: reward = -189.73, steps = 24 03:46:47 [INFO] train episode 5486: reward = -128.73, steps = 26 03:46:49 [INFO] train episode 5487: reward = -109.81, steps = 29 03:46:52 [INFO] train episode 5488: reward = -126.87, steps = 29 03:46:54 [INFO] train episode 5489: reward = -122.09, steps = 20 03:46:56 [INFO] train episode 5490: reward = -132.25, steps = 22 03:46:59 [INFO] train episode 5491: reward = -214.86, steps = 36 03:47:02 [INFO] train episode 5492: reward = -135.56, steps = 36 03:47:04 [INFO] train episode 5493: reward = -129.97, steps = 26 03:47:06 [INFO] train episode 5494: reward = -86.58, steps = 19 03:47:08 [INFO] train episode 5495: reward = -161.45, steps = 24 03:47:10 [INFO] train episode 5496: reward = -98.96, steps = 22 03:47:12 [INFO] train episode 5497: reward = -105.00, steps = 21 03:47:14 [INFO] train episode 5498: reward = -127.61, steps = 23 03:47:17 [INFO] train episode 5499: reward = -107.83, steps = 34 03:47:19 [INFO] train episode 5500: reward = -139.06, steps = 25 03:47:21 [INFO] train episode 5501: reward = -89.42, steps = 21 03:47:24 [INFO] train episode 5502: reward = -127.46, steps = 29 03:47:26 [INFO] train episode 5503: reward = -128.45, steps = 25 03:47:28 [INFO] train episode 5504: reward = -104.70, steps = 22 03:47:30 [INFO] train episode 5505: reward = -176.33, steps = 25 03:47:34 [INFO] train episode 5506: reward = -163.57, steps = 43 03:47:36 [INFO] train episode 5507: reward = -131.23, steps = 21 03:47:38 [INFO] train episode 5508: reward = -161.01, steps = 25 03:47:41 [INFO] train episode 5509: reward = -160.71, steps = 27 03:47:43 [INFO] train episode 5510: reward = -130.53, steps = 27 03:47:46 [INFO] train episode 5511: reward = -143.66, steps = 31 03:47:48 [INFO] train episode 5512: reward = -142.85, steps = 26 03:47:50 [INFO] train episode 5513: reward = -124.27, steps = 29 03:47:54 [INFO] train episode 5514: reward = -154.15, steps = 41 03:47:58 [INFO] train episode 5515: reward = -173.05, steps = 41 03:48:00 [INFO] train episode 5516: reward = -127.69, steps = 29 03:48:02 [INFO] train episode 5517: reward = -91.31, steps = 24 03:48:04 [INFO] train episode 5518: reward = -102.71, steps = 20 03:48:06 [INFO] train episode 5519: reward = -96.33, steps = 19 03:48:09 [INFO] train episode 5520: reward = -153.43, steps = 35 03:48:12 [INFO] train episode 5521: reward = -136.67, steps = 34 03:48:15 [INFO] train episode 5522: reward = -248.38, steps = 34 03:48:18 [INFO] train episode 5523: reward = -143.88, steps = 31 03:48:20 [INFO] train episode 5524: reward = -153.44, steps = 30 03:48:22 [INFO] train episode 5525: reward = -93.85, steps = 23 03:48:25 [INFO] train episode 5526: reward = -126.25, steps = 28 03:48:27 [INFO] train episode 5527: reward = -82.14, steps = 19 03:48:29 [INFO] train episode 5528: reward = -108.71, steps = 28 03:48:31 [INFO] train episode 5529: reward = -78.52, steps = 22 03:48:34 [INFO] train episode 5530: reward = -192.83, steps = 33 03:48:36 [INFO] train episode 5531: reward = -121.30, steps = 21 03:48:39 [INFO] train episode 5532: reward = -176.09, steps = 33 03:48:40 [INFO] train episode 5533: reward = -98.80, steps = 19 03:48:44 [INFO] train episode 5534: reward = -142.80, steps = 36 03:48:47 [INFO] train episode 5535: reward = -159.37, steps = 33 03:48:50 [INFO] train episode 5536: reward = -216.89, steps = 33 03:48:51 [INFO] train episode 5537: reward = -112.72, steps = 22 03:48:55 [INFO] train episode 5538: reward = -146.48, steps = 40 03:48:58 [INFO] train episode 5539: reward = -186.80, steps = 27 03:49:00 [INFO] train episode 5540: reward = -108.97, steps = 25 03:49:01 [INFO] train episode 5541: reward = -148.40, steps = 19 03:49:04 [INFO] train episode 5542: reward = -105.99, steps = 32 03:49:07 [INFO] train episode 5543: reward = -157.21, steps = 28 03:49:08 [INFO] train episode 5544: reward = -73.04, steps = 21 03:49:10 [INFO] train episode 5545: reward = -127.55, steps = 21 03:49:14 [INFO] train episode 5546: reward = -132.46, steps = 34 03:49:15 [INFO] train episode 5547: reward = -172.39, steps = 19 03:49:17 [INFO] train episode 5548: reward = -140.04, steps = 22 03:49:20 [INFO] train episode 5549: reward = -113.11, steps = 30 03:49:22 [INFO] train episode 5550: reward = -151.47, steps = 28 03:49:25 [INFO] train episode 5551: reward = -166.47, steps = 36 03:49:28 [INFO] train episode 5552: reward = -129.78, steps = 20 03:49:30 [INFO] train episode 5553: reward = -96.07, steps = 25 03:49:32 [INFO] train episode 5554: reward = -106.00, steps = 19 03:49:34 [INFO] train episode 5555: reward = -130.51, steps = 25 03:49:36 [INFO] train episode 5556: reward = -87.00, steps = 21 03:49:39 [INFO] train episode 5557: reward = -192.43, steps = 32 03:49:41 [INFO] train episode 5558: reward = -159.26, steps = 24 03:49:44 [INFO] train episode 5559: reward = -144.94, steps = 32 03:49:46 [INFO] train episode 5560: reward = -134.43, steps = 21 03:49:48 [INFO] train episode 5561: reward = -115.43, steps = 27 03:49:51 [INFO] train episode 5562: reward = -215.98, steps = 33 03:49:55 [INFO] train episode 5563: reward = -119.30, steps = 43 03:49:57 [INFO] train episode 5564: reward = -84.64, steps = 22 03:49:59 [INFO] train episode 5565: reward = -112.82, steps = 29 03:50:03 [INFO] train episode 5566: reward = -207.84, steps = 42 03:50:05 [INFO] train episode 5567: reward = -82.24, steps = 20 03:50:08 [INFO] train episode 5568: reward = -189.96, steps = 34 03:50:11 [INFO] train episode 5569: reward = -187.48, steps = 35 03:50:13 [INFO] train episode 5570: reward = -130.32, steps = 26 03:50:15 [INFO] train episode 5571: reward = -160.86, steps = 23 03:50:17 [INFO] train episode 5572: reward = -87.50, steps = 20 03:50:20 [INFO] train episode 5573: reward = -128.25, steps = 29 03:50:22 [INFO] train episode 5574: reward = -196.68, steps = 32 03:50:25 [INFO] train episode 5575: reward = -165.56, steps = 28 03:50:27 [INFO] train episode 5576: reward = -107.80, steps = 22 03:50:30 [INFO] train episode 5577: reward = -129.94, steps = 33 03:50:31 [INFO] train episode 5578: reward = -201.84, steps = 22 03:50:34 [INFO] train episode 5579: reward = -91.95, steps = 21 03:50:36 [INFO] train episode 5580: reward = -165.27, steps = 27 03:50:38 [INFO] train episode 5581: reward = -184.58, steps = 27 03:50:40 [INFO] train episode 5582: reward = -129.21, steps = 19 03:50:42 [INFO] train episode 5583: reward = -91.57, steps = 19 03:50:43 [INFO] train episode 5584: reward = -154.93, steps = 19 03:50:46 [INFO] train episode 5585: reward = -155.69, steps = 27 03:50:48 [INFO] train episode 5586: reward = -179.43, steps = 24 03:50:50 [INFO] train episode 5587: reward = -218.34, steps = 22 03:50:53 [INFO] train episode 5588: reward = -128.91, steps = 30 03:50:55 [INFO] train episode 5589: reward = -111.47, steps = 22 03:50:58 [INFO] train episode 5590: reward = -105.91, steps = 37 03:51:00 [INFO] train episode 5591: reward = -150.32, steps = 27 03:51:03 [INFO] train episode 5592: reward = -98.40, steps = 28 03:51:05 [INFO] train episode 5593: reward = -124.77, steps = 22 03:51:07 [INFO] train episode 5594: reward = -120.20, steps = 23 03:51:09 [INFO] train episode 5595: reward = -166.28, steps = 23 03:51:11 [INFO] train episode 5596: reward = -123.88, steps = 26 03:51:13 [INFO] train episode 5597: reward = -130.85, steps = 20 03:51:15 [INFO] train episode 5598: reward = -102.53, steps = 20 03:51:17 [INFO] train episode 5599: reward = -117.25, steps = 26 03:51:22 [INFO] train episode 5600: reward = -161.08, steps = 47 03:51:24 [INFO] train episode 5601: reward = -104.00, steps = 26 03:51:27 [INFO] train episode 5602: reward = -112.28, steps = 33 03:51:29 [INFO] train episode 5603: reward = -99.48, steps = 23 03:51:31 [INFO] train episode 5604: reward = -83.76, steps = 21 03:51:32 [INFO] train episode 5605: reward = -159.02, steps = 18 03:51:34 [INFO] train episode 5606: reward = -115.44, steps = 22 03:51:36 [INFO] train episode 5607: reward = -67.01, steps = 24 03:51:38 [INFO] train episode 5608: reward = -104.03, steps = 20 03:51:41 [INFO] train episode 5609: reward = -126.71, steps = 25 03:51:43 [INFO] train episode 5610: reward = -115.65, steps = 22 03:51:45 [INFO] train episode 5611: reward = -50.70, steps = 21 03:51:46 [INFO] train episode 5612: reward = -102.07, steps = 21 03:51:49 [INFO] train episode 5613: reward = -138.12, steps = 25 03:51:50 [INFO] train episode 5614: reward = -65.90, steps = 19 03:51:52 [INFO] train episode 5615: reward = -174.18, steps = 26 03:51:55 [INFO] train episode 5616: reward = -178.91, steps = 26 03:51:58 [INFO] train episode 5617: reward = -147.49, steps = 32 03:52:00 [INFO] train episode 5618: reward = -109.09, steps = 22 03:52:02 [INFO] train episode 5619: reward = -76.61, steps = 19 03:52:03 [INFO] train episode 5620: reward = -190.80, steps = 20 03:52:05 [INFO] train episode 5621: reward = -148.30, steps = 23 03:52:07 [INFO] train episode 5622: reward = -114.09, steps = 23 03:52:10 [INFO] train episode 5623: reward = -155.45, steps = 25 03:52:12 [INFO] train episode 5624: reward = -167.31, steps = 20 03:52:13 [INFO] train episode 5625: reward = -88.49, steps = 20 03:52:15 [INFO] train episode 5626: reward = -93.34, steps = 20 03:52:18 [INFO] train episode 5627: reward = -167.07, steps = 29 03:52:21 [INFO] train episode 5628: reward = -101.16, steps = 27 03:52:23 [INFO] train episode 5629: reward = -86.45, steps = 22 03:52:25 [INFO] train episode 5630: reward = -165.60, steps = 23 03:52:26 [INFO] train episode 5631: reward = -89.65, steps = 19 03:52:29 [INFO] train episode 5632: reward = -102.06, steps = 21 03:52:31 [INFO] train episode 5633: reward = -185.03, steps = 20 03:52:33 [INFO] train episode 5634: reward = -120.19, steps = 30 03:52:35 [INFO] train episode 5635: reward = -169.06, steps = 24 03:52:37 [INFO] train episode 5636: reward = -131.70, steps = 23 03:52:39 [INFO] train episode 5637: reward = -114.58, steps = 22 03:52:42 [INFO] train episode 5638: reward = -138.84, steps = 28 03:52:44 [INFO] train episode 5639: reward = -128.47, steps = 26 03:52:46 [INFO] train episode 5640: reward = -129.12, steps = 22 03:52:48 [INFO] train episode 5641: reward = -158.36, steps = 22 03:52:51 [INFO] train episode 5642: reward = -182.34, steps = 38 03:52:53 [INFO] train episode 5643: reward = -136.07, steps = 25 03:52:55 [INFO] train episode 5644: reward = -77.49, steps = 22 03:52:58 [INFO] train episode 5645: reward = -164.03, steps = 25 03:53:00 [INFO] train episode 5646: reward = -93.96, steps = 23 03:53:02 [INFO] train episode 5647: reward = -125.10, steps = 22 03:53:04 [INFO] train episode 5648: reward = -145.62, steps = 25 03:53:07 [INFO] train episode 5649: reward = -269.67, steps = 34 03:53:09 [INFO] train episode 5650: reward = -151.55, steps = 28 03:53:12 [INFO] train episode 5651: reward = -102.31, steps = 30 03:53:15 [INFO] train episode 5652: reward = -187.81, steps = 29 03:53:18 [INFO] train episode 5653: reward = -189.67, steps = 32 03:53:20 [INFO] train episode 5654: reward = -130.89, steps = 25 03:53:22 [INFO] train episode 5655: reward = -165.51, steps = 28 03:53:25 [INFO] train episode 5656: reward = -112.99, steps = 27 03:53:26 [INFO] train episode 5657: reward = -166.88, steps = 21 03:53:29 [INFO] train episode 5658: reward = -132.68, steps = 28 03:53:30 [INFO] train episode 5659: reward = -193.39, steps = 19 03:53:34 [INFO] train episode 5660: reward = -163.43, steps = 32 03:53:35 [INFO] train episode 5661: reward = -91.71, steps = 20 03:53:37 [INFO] train episode 5662: reward = -87.03, steps = 23 03:53:39 [INFO] train episode 5663: reward = -139.15, steps = 25 03:53:41 [INFO] train episode 5664: reward = -119.48, steps = 19 03:53:43 [INFO] train episode 5665: reward = -81.33, steps = 19 03:53:45 [INFO] train episode 5666: reward = -101.16, steps = 26 03:53:48 [INFO] train episode 5667: reward = -127.62, steps = 30 03:53:50 [INFO] train episode 5668: reward = -83.92, steps = 20 03:53:52 [INFO] train episode 5669: reward = -122.69, steps = 20 03:53:54 [INFO] train episode 5670: reward = -189.97, steps = 31 03:53:56 [INFO] train episode 5671: reward = -142.61, steps = 21 03:53:59 [INFO] train episode 5672: reward = -174.60, steps = 39 03:54:02 [INFO] train episode 5673: reward = -164.79, steps = 35 03:54:04 [INFO] train episode 5674: reward = -89.02, steps = 19 03:54:07 [INFO] train episode 5675: reward = -101.34, steps = 30 03:54:09 [INFO] train episode 5676: reward = -81.92, steps = 23 03:54:11 [INFO] train episode 5677: reward = -76.77, steps = 19 03:54:13 [INFO] train episode 5678: reward = -102.48, steps = 32 03:54:16 [INFO] train episode 5679: reward = -163.29, steps = 30 03:54:18 [INFO] train episode 5680: reward = -97.98, steps = 26 03:54:20 [INFO] train episode 5681: reward = -96.62, steps = 21 03:54:22 [INFO] train episode 5682: reward = -118.89, steps = 23 03:54:24 [INFO] train episode 5683: reward = -141.77, steps = 23 03:54:26 [INFO] train episode 5684: reward = -95.57, steps = 20 03:54:28 [INFO] train episode 5685: reward = -92.17, steps = 22 03:54:30 [INFO] train episode 5686: reward = -97.04, steps = 19 03:54:32 [INFO] train episode 5687: reward = -162.48, steps = 27 03:54:34 [INFO] train episode 5688: reward = -109.74, steps = 23 03:54:37 [INFO] train episode 5689: reward = -246.26, steps = 28 03:54:39 [INFO] train episode 5690: reward = -171.97, steps = 28 03:54:41 [INFO] train episode 5691: reward = -113.01, steps = 21 03:54:44 [INFO] train episode 5692: reward = -93.63, steps = 26 03:54:46 [INFO] train episode 5693: reward = -166.44, steps = 32 03:54:49 [INFO] train episode 5694: reward = -150.49, steps = 26 03:54:50 [INFO] train episode 5695: reward = -107.64, steps = 21 03:54:53 [INFO] train episode 5696: reward = -119.64, steps = 23 03:54:55 [INFO] train episode 5697: reward = -143.00, steps = 20 03:54:57 [INFO] train episode 5698: reward = -143.06, steps = 29 03:54:59 [INFO] train episode 5699: reward = -96.83, steps = 23 03:55:01 [INFO] train episode 5700: reward = -71.11, steps = 20 03:55:03 [INFO] train episode 5701: reward = -143.59, steps = 24 03:55:07 [INFO] train episode 5702: reward = -208.47, steps = 48 03:55:09 [INFO] train episode 5703: reward = -114.44, steps = 23 03:55:11 [INFO] train episode 5704: reward = -119.62, steps = 21 03:55:14 [INFO] train episode 5705: reward = -122.76, steps = 25 03:55:17 [INFO] train episode 5706: reward = -158.97, steps = 33 03:55:20 [INFO] train episode 5707: reward = -151.36, steps = 33 03:55:22 [INFO] train episode 5708: reward = -72.59, steps = 22 03:55:25 [INFO] train episode 5709: reward = -144.38, steps = 32 03:55:29 [INFO] train episode 5710: reward = -201.09, steps = 46 03:55:30 [INFO] train episode 5711: reward = -103.91, steps = 21 03:55:32 [INFO] train episode 5712: reward = -106.49, steps = 23 03:55:35 [INFO] train episode 5713: reward = -266.43, steps = 30 03:55:37 [INFO] train episode 5714: reward = -103.61, steps = 28 03:55:41 [INFO] train episode 5715: reward = -156.64, steps = 37 03:55:43 [INFO] train episode 5716: reward = -210.23, steps = 29 03:55:46 [INFO] train episode 5717: reward = -151.02, steps = 33 03:55:48 [INFO] train episode 5718: reward = -82.16, steps = 21 03:55:50 [INFO] train episode 5719: reward = -179.04, steps = 28 03:55:53 [INFO] train episode 5720: reward = -122.18, steps = 25 03:55:55 [INFO] train episode 5721: reward = -136.69, steps = 24 03:55:57 [INFO] train episode 5722: reward = -130.57, steps = 20 03:55:59 [INFO] train episode 5723: reward = -114.39, steps = 27 03:56:01 [INFO] train episode 5724: reward = -146.45, steps = 19 03:56:03 [INFO] train episode 5725: reward = -160.71, steps = 30 03:56:06 [INFO] train episode 5726: reward = -127.33, steps = 26 03:56:07 [INFO] train episode 5727: reward = -133.04, steps = 20 03:56:10 [INFO] train episode 5728: reward = -77.50, steps = 28 03:56:13 [INFO] train episode 5729: reward = -114.32, steps = 32 03:56:15 [INFO] train episode 5730: reward = -119.34, steps = 19 03:56:17 [INFO] train episode 5731: reward = -161.29, steps = 29 03:56:19 [INFO] train episode 5732: reward = -77.41, steps = 20 03:56:21 [INFO] train episode 5733: reward = -99.38, steps = 21 03:56:23 [INFO] train episode 5734: reward = -295.62, steps = 28 03:56:25 [INFO] train episode 5735: reward = -172.64, steps = 21 03:56:27 [INFO] train episode 5736: reward = -130.49, steps = 20 03:56:29 [INFO] train episode 5737: reward = -84.75, steps = 25 03:56:33 [INFO] train episode 5738: reward = -174.77, steps = 47 03:56:36 [INFO] train episode 5739: reward = -196.90, steps = 33 03:56:38 [INFO] train episode 5740: reward = -116.02, steps = 20 03:56:40 [INFO] train episode 5741: reward = -187.12, steps = 25 03:56:42 [INFO] train episode 5742: reward = -112.40, steps = 24 03:56:45 [INFO] train episode 5743: reward = -99.59, steps = 27 03:56:47 [INFO] train episode 5744: reward = -143.91, steps = 27 03:56:50 [INFO] train episode 5745: reward = -139.73, steps = 30 03:56:52 [INFO] train episode 5746: reward = -132.88, steps = 26 03:56:54 [INFO] train episode 5747: reward = -111.72, steps = 20 03:56:56 [INFO] train episode 5748: reward = -136.81, steps = 25 03:56:58 [INFO] train episode 5749: reward = -104.98, steps = 27 03:57:01 [INFO] train episode 5750: reward = -102.75, steps = 19 03:57:04 [INFO] train episode 5751: reward = -185.20, steps = 36 03:57:05 [INFO] train episode 5752: reward = -108.56, steps = 20 03:57:08 [INFO] train episode 5753: reward = -129.97, steps = 26 03:57:10 [INFO] train episode 5754: reward = -89.22, steps = 30 03:57:12 [INFO] train episode 5755: reward = -129.16, steps = 23 03:57:14 [INFO] train episode 5756: reward = -80.33, steps = 20 03:57:17 [INFO] train episode 5757: reward = -100.04, steps = 27 03:57:19 [INFO] train episode 5758: reward = -130.99, steps = 22 03:57:21 [INFO] train episode 5759: reward = -132.62, steps = 22 03:57:23 [INFO] train episode 5760: reward = -101.79, steps = 22 03:57:24 [INFO] train episode 5761: reward = -96.47, steps = 21 03:57:26 [INFO] train episode 5762: reward = -54.92, steps = 20 03:57:28 [INFO] train episode 5763: reward = -151.57, steps = 22 03:57:30 [INFO] train episode 5764: reward = -153.45, steps = 27 03:57:33 [INFO] train episode 5765: reward = -129.23, steps = 25 03:57:35 [INFO] train episode 5766: reward = -79.87, steps = 23 03:57:37 [INFO] train episode 5767: reward = -162.58, steps = 25 03:57:40 [INFO] train episode 5768: reward = -150.12, steps = 34 03:57:42 [INFO] train episode 5769: reward = -128.70, steps = 28 03:57:45 [INFO] train episode 5770: reward = -98.88, steps = 30 03:57:47 [INFO] train episode 5771: reward = -88.12, steps = 23 03:57:49 [INFO] train episode 5772: reward = -118.96, steps = 23 03:57:51 [INFO] train episode 5773: reward = -161.83, steps = 24 03:57:54 [INFO] train episode 5774: reward = -127.08, steps = 27 03:57:56 [INFO] train episode 5775: reward = -124.01, steps = 22 03:57:57 [INFO] train episode 5776: reward = -90.37, steps = 21 03:57:59 [INFO] train episode 5777: reward = -81.07, steps = 19 03:58:03 [INFO] train episode 5778: reward = -144.14, steps = 42 03:58:08 [INFO] train episode 5779: reward = -142.64, steps = 48 03:58:11 [INFO] train episode 5780: reward = -170.47, steps = 37 03:58:13 [INFO] train episode 5781: reward = -145.64, steps = 24 03:58:16 [INFO] train episode 5782: reward = -113.29, steps = 28 03:58:17 [INFO] train episode 5783: reward = -185.70, steps = 19 03:58:20 [INFO] train episode 5784: reward = -227.02, steps = 29 03:58:26 [INFO] train episode 5785: reward = -310.70, steps = 62 03:58:28 [INFO] train episode 5786: reward = -117.50, steps = 24 03:58:30 [INFO] train episode 5787: reward = -103.51, steps = 31 03:58:32 [INFO] train episode 5788: reward = -107.59, steps = 24 03:58:35 [INFO] train episode 5789: reward = -138.83, steps = 31 03:58:37 [INFO] train episode 5790: reward = -141.05, steps = 22 03:58:40 [INFO] train episode 5791: reward = -197.55, steps = 36 03:58:43 [INFO] train episode 5792: reward = -149.04, steps = 27 03:58:46 [INFO] train episode 5793: reward = -136.82, steps = 35 03:58:48 [INFO] train episode 5794: reward = -126.04, steps = 25 03:58:50 [INFO] train episode 5795: reward = -142.54, steps = 29 03:58:53 [INFO] train episode 5796: reward = -193.13, steps = 27 03:58:55 [INFO] train episode 5797: reward = -301.29, steps = 28 03:58:57 [INFO] train episode 5798: reward = -180.62, steps = 18 03:58:59 [INFO] train episode 5799: reward = -87.24, steps = 21 03:59:01 [INFO] train episode 5800: reward = -102.87, steps = 19 03:59:02 [INFO] train episode 5801: reward = -173.00, steps = 21 03:59:04 [INFO] train episode 5802: reward = -138.35, steps = 23 03:59:07 [INFO] train episode 5803: reward = -133.73, steps = 24 03:59:08 [INFO] train episode 5804: reward = -94.31, steps = 20 03:59:11 [INFO] train episode 5805: reward = -235.37, steps = 31 03:59:13 [INFO] train episode 5806: reward = -139.95, steps = 23 03:59:16 [INFO] train episode 5807: reward = -151.55, steps = 27 03:59:19 [INFO] train episode 5808: reward = -137.35, steps = 26 03:59:21 [INFO] train episode 5809: reward = -123.92, steps = 24 03:59:23 [INFO] train episode 5810: reward = -109.45, steps = 23 03:59:26 [INFO] train episode 5811: reward = -211.12, steps = 32 03:59:29 [INFO] train episode 5812: reward = -148.92, steps = 29 03:59:31 [INFO] train episode 5813: reward = -97.49, steps = 20 03:59:33 [INFO] train episode 5814: reward = -160.87, steps = 28 03:59:36 [INFO] train episode 5815: reward = -152.68, steps = 32 03:59:38 [INFO] train episode 5816: reward = -141.15, steps = 25 03:59:40 [INFO] train episode 5817: reward = -100.65, steps = 20 03:59:42 [INFO] train episode 5818: reward = -111.10, steps = 30 03:59:45 [INFO] train episode 5819: reward = -117.71, steps = 30 03:59:47 [INFO] train episode 5820: reward = -156.65, steps = 19 03:59:49 [INFO] train episode 5821: reward = -153.75, steps = 25 03:59:53 [INFO] train episode 5822: reward = -242.28, steps = 39 03:59:55 [INFO] train episode 5823: reward = -122.43, steps = 28 03:59:58 [INFO] train episode 5824: reward = -174.96, steps = 34 04:00:02 [INFO] train episode 5825: reward = -169.18, steps = 36 04:00:04 [INFO] train episode 5826: reward = -126.95, steps = 26 04:00:06 [INFO] train episode 5827: reward = -172.50, steps = 21 04:00:07 [INFO] train episode 5828: reward = -113.76, steps = 19 04:00:10 [INFO] train episode 5829: reward = -145.39, steps = 25 04:00:11 [INFO] train episode 5830: reward = -136.68, steps = 20 04:00:14 [INFO] train episode 5831: reward = -152.63, steps = 26 04:00:16 [INFO] train episode 5832: reward = -158.95, steps = 27 04:00:18 [INFO] train episode 5833: reward = -183.75, steps = 19 04:00:21 [INFO] train episode 5834: reward = -166.09, steps = 30 04:00:23 [INFO] train episode 5835: reward = -112.75, steps = 32 04:00:25 [INFO] train episode 5836: reward = -122.39, steps = 21 04:00:27 [INFO] train episode 5837: reward = -142.74, steps = 23 04:00:29 [INFO] train episode 5838: reward = -112.49, steps = 20 04:00:31 [INFO] train episode 5839: reward = -129.96, steps = 23 04:00:35 [INFO] train episode 5840: reward = -201.29, steps = 40 04:00:37 [INFO] train episode 5841: reward = -139.71, steps = 27 04:00:40 [INFO] train episode 5842: reward = -217.62, steps = 27 04:00:42 [INFO] train episode 5843: reward = -93.96, steps = 24 04:00:44 [INFO] train episode 5844: reward = -140.63, steps = 29 04:00:47 [INFO] train episode 5845: reward = -142.97, steps = 28 04:00:49 [INFO] train episode 5846: reward = -156.40, steps = 28 04:00:51 [INFO] train episode 5847: reward = -173.17, steps = 19 04:00:53 [INFO] train episode 5848: reward = -123.35, steps = 26 04:00:56 [INFO] train episode 5849: reward = -114.14, steps = 28 04:00:58 [INFO] train episode 5850: reward = -140.04, steps = 30 04:01:02 [INFO] train episode 5851: reward = -165.68, steps = 38 04:01:05 [INFO] train episode 5852: reward = -99.32, steps = 22 04:01:06 [INFO] train episode 5853: reward = -157.50, steps = 21 04:01:09 [INFO] train episode 5854: reward = -131.67, steps = 26 04:01:10 [INFO] train episode 5855: reward = -115.48, steps = 19 04:01:12 [INFO] train episode 5856: reward = -134.15, steps = 24 04:01:16 [INFO] train episode 5857: reward = -143.20, steps = 37 04:01:18 [INFO] train episode 5858: reward = -93.21, steps = 31 04:01:21 [INFO] train episode 5859: reward = -81.28, steps = 21 04:01:22 [INFO] train episode 5860: reward = -156.66, steps = 21 04:01:24 [INFO] train episode 5861: reward = -124.01, steps = 19 04:01:26 [INFO] train episode 5862: reward = -168.06, steps = 19 04:01:28 [INFO] train episode 5863: reward = -114.96, steps = 27 04:01:30 [INFO] train episode 5864: reward = -90.30, steps = 22 04:01:32 [INFO] train episode 5865: reward = -124.16, steps = 23 04:01:34 [INFO] train episode 5866: reward = -121.65, steps = 22 04:01:37 [INFO] train episode 5867: reward = -129.09, steps = 26 04:01:39 [INFO] train episode 5868: reward = -89.43, steps = 29 04:01:41 [INFO] train episode 5869: reward = -97.36, steps = 21 04:01:43 [INFO] train episode 5870: reward = -71.51, steps = 20 04:01:45 [INFO] train episode 5871: reward = -138.76, steps = 25 04:01:47 [INFO] train episode 5872: reward = -155.22, steps = 27 04:01:50 [INFO] train episode 5873: reward = -134.12, steps = 26 04:01:51 [INFO] train episode 5874: reward = -93.19, steps = 22 04:01:54 [INFO] train episode 5875: reward = -206.18, steps = 28 04:01:56 [INFO] train episode 5876: reward = -129.43, steps = 24 04:01:59 [INFO] train episode 5877: reward = -174.08, steps = 27 04:02:01 [INFO] train episode 5878: reward = -125.74, steps = 21 04:02:04 [INFO] train episode 5879: reward = -234.76, steps = 41 04:02:07 [INFO] train episode 5880: reward = -128.00, steps = 25 04:02:10 [INFO] train episode 5881: reward = -179.83, steps = 39 04:02:13 [INFO] train episode 5882: reward = -207.81, steps = 33 04:02:15 [INFO] train episode 5883: reward = -187.61, steps = 24 04:02:17 [INFO] train episode 5884: reward = -97.43, steps = 25 04:02:19 [INFO] train episode 5885: reward = -109.47, steps = 19 04:02:22 [INFO] train episode 5886: reward = -143.17, steps = 35 04:02:24 [INFO] train episode 5887: reward = -159.47, steps = 20 04:02:27 [INFO] train episode 5888: reward = -117.73, steps = 34 04:02:30 [INFO] train episode 5889: reward = -144.62, steps = 29 04:02:33 [INFO] train episode 5890: reward = -222.96, steps = 38 04:02:37 [INFO] train episode 5891: reward = -265.11, steps = 48 04:02:40 [INFO] train episode 5892: reward = -147.65, steps = 32 04:02:43 [INFO] train episode 5893: reward = -153.56, steps = 26 04:02:44 [INFO] train episode 5894: reward = -116.65, steps = 20 04:02:46 [INFO] train episode 5895: reward = -88.36, steps = 20 04:02:48 [INFO] train episode 5896: reward = -139.26, steps = 27 04:02:51 [INFO] train episode 5897: reward = -119.57, steps = 24 04:02:53 [INFO] train episode 5898: reward = -96.94, steps = 26 04:02:55 [INFO] train episode 5899: reward = -233.70, steps = 20 04:02:57 [INFO] train episode 5900: reward = -76.65, steps = 22 04:02:59 [INFO] train episode 5901: reward = -69.56, steps = 19 04:03:02 [INFO] train episode 5902: reward = -164.10, steps = 34 04:03:03 [INFO] train episode 5903: reward = -90.63, steps = 19 04:03:05 [INFO] train episode 5904: reward = -100.84, steps = 21 04:03:07 [INFO] train episode 5905: reward = -159.47, steps = 24 04:03:09 [INFO] train episode 5906: reward = -135.69, steps = 24 04:03:11 [INFO] train episode 5907: reward = -161.32, steps = 18 04:03:13 [INFO] train episode 5908: reward = -174.10, steps = 26 04:03:16 [INFO] train episode 5909: reward = -190.17, steps = 31 04:03:18 [INFO] train episode 5910: reward = -126.12, steps = 24 04:03:20 [INFO] train episode 5911: reward = -160.99, steps = 22 04:03:22 [INFO] train episode 5912: reward = -86.52, steps = 21 04:03:26 [INFO] train episode 5913: reward = -386.35, steps = 47 04:03:28 [INFO] train episode 5914: reward = -113.51, steps = 25 04:03:31 [INFO] train episode 5915: reward = -141.32, steps = 23 04:03:32 [INFO] train episode 5916: reward = -121.26, steps = 22 04:03:34 [INFO] train episode 5917: reward = -90.94, steps = 19 04:03:36 [INFO] train episode 5918: reward = -78.91, steps = 21 04:03:38 [INFO] train episode 5919: reward = -135.10, steps = 25 04:03:40 [INFO] train episode 5920: reward = -191.67, steps = 26 04:03:42 [INFO] train episode 5921: reward = -104.18, steps = 22 04:03:46 [INFO] train episode 5922: reward = -189.19, steps = 38 04:03:48 [INFO] train episode 5923: reward = -174.27, steps = 28 04:03:51 [INFO] train episode 5924: reward = -184.74, steps = 28 04:03:53 [INFO] train episode 5925: reward = -163.45, steps = 26 04:03:56 [INFO] train episode 5926: reward = -114.11, steps = 29 04:03:58 [INFO] train episode 5927: reward = -153.68, steps = 25 04:04:01 [INFO] train episode 5928: reward = -147.50, steps = 29 04:04:03 [INFO] train episode 5929: reward = -223.84, steps = 23 04:04:06 [INFO] train episode 5930: reward = -168.03, steps = 29 04:04:08 [INFO] train episode 5931: reward = -148.62, steps = 22 04:04:11 [INFO] train episode 5932: reward = -177.25, steps = 39 04:04:13 [INFO] train episode 5933: reward = -109.68, steps = 25 04:04:15 [INFO] train episode 5934: reward = -124.21, steps = 23 04:04:20 [INFO] train episode 5935: reward = -310.00, steps = 47 04:04:23 [INFO] train episode 5936: reward = -155.20, steps = 32 04:04:24 [INFO] train episode 5937: reward = -114.27, steps = 22 04:04:27 [INFO] train episode 5938: reward = -138.84, steps = 28 04:04:29 [INFO] train episode 5939: reward = -106.89, steps = 27 04:04:31 [INFO] train episode 5940: reward = -102.31, steps = 22 04:04:33 [INFO] train episode 5941: reward = -130.75, steps = 22 04:04:35 [INFO] train episode 5942: reward = -78.09, steps = 19 04:04:37 [INFO] train episode 5943: reward = -85.70, steps = 19 04:04:39 [INFO] train episode 5944: reward = -128.31, steps = 24 04:04:41 [INFO] train episode 5945: reward = -256.73, steps = 25 04:04:43 [INFO] train episode 5946: reward = -83.95, steps = 20 04:04:45 [INFO] train episode 5947: reward = -183.62, steps = 29 04:04:48 [INFO] train episode 5948: reward = -178.38, steps = 30 04:04:50 [INFO] train episode 5949: reward = -100.56, steps = 21 04:04:53 [INFO] train episode 5950: reward = -70.60, steps = 29 04:04:55 [INFO] train episode 5951: reward = -205.74, steps = 30 04:04:58 [INFO] train episode 5952: reward = -185.82, steps = 24 04:05:00 [INFO] train episode 5953: reward = -134.71, steps = 33 04:05:02 [INFO] train episode 5954: reward = -164.79, steps = 23 04:05:04 [INFO] train episode 5955: reward = -99.92, steps = 24 04:05:08 [INFO] train episode 5956: reward = -186.41, steps = 31 04:05:11 [INFO] train episode 5957: reward = -183.66, steps = 35 04:05:12 [INFO] train episode 5958: reward = -132.50, steps = 20 04:05:17 [INFO] train episode 5959: reward = -233.25, steps = 49 04:05:20 [INFO] train episode 5960: reward = -188.18, steps = 44 04:05:23 [INFO] train episode 5961: reward = -165.74, steps = 30 04:05:25 [INFO] train episode 5962: reward = -127.39, steps = 21 04:05:27 [INFO] train episode 5963: reward = -114.99, steps = 26 04:05:32 [INFO] train episode 5964: reward = -237.19, steps = 49 04:05:33 [INFO] train episode 5965: reward = -139.31, steps = 17 04:05:35 [INFO] train episode 5966: reward = -159.84, steps = 26 04:05:38 [INFO] train episode 5967: reward = -145.11, steps = 22 04:05:39 [INFO] train episode 5968: reward = -96.09, steps = 21 04:05:43 [INFO] train episode 5969: reward = -254.75, steps = 43 04:05:46 [INFO] train episode 5970: reward = -179.86, steps = 31 04:05:47 [INFO] train episode 5971: reward = -157.88, steps = 17 04:05:50 [INFO] train episode 5972: reward = -165.31, steps = 27 04:05:51 [INFO] train episode 5973: reward = -128.00, steps = 20 04:05:54 [INFO] train episode 5974: reward = -89.15, steps = 23 04:05:56 [INFO] train episode 5975: reward = -154.09, steps = 32 04:05:59 [INFO] train episode 5976: reward = -116.06, steps = 25 04:06:01 [INFO] train episode 5977: reward = -151.81, steps = 25 04:06:04 [INFO] train episode 5978: reward = -237.43, steps = 37 04:06:06 [INFO] train episode 5979: reward = -80.98, steps = 21 04:06:10 [INFO] train episode 5980: reward = -251.57, steps = 51 04:06:12 [INFO] train episode 5981: reward = -90.68, steps = 22 04:06:16 [INFO] train episode 5982: reward = -159.75, steps = 43 04:06:19 [INFO] train episode 5983: reward = -149.31, steps = 34 04:06:22 [INFO] train episode 5984: reward = -226.12, steps = 35 04:06:25 [INFO] train episode 5985: reward = -238.20, steps = 31 04:06:27 [INFO] train episode 5986: reward = -69.16, steps = 19 04:06:29 [INFO] train episode 5987: reward = -177.88, steps = 27 04:06:31 [INFO] train episode 5988: reward = -112.17, steps = 18 04:06:32 [INFO] train episode 5989: reward = -154.37, steps = 20 04:06:35 [INFO] train episode 5990: reward = -108.76, steps = 31 04:06:38 [INFO] train episode 5991: reward = -223.55, steps = 32 04:06:41 [INFO] train episode 5992: reward = -171.47, steps = 27 04:06:43 [INFO] train episode 5993: reward = -141.81, steps = 25 04:06:44 [INFO] train episode 5994: reward = -72.42, steps = 19 04:06:48 [INFO] train episode 5995: reward = -200.04, steps = 36 04:06:52 [INFO] train episode 5996: reward = -228.86, steps = 41 04:06:54 [INFO] train episode 5997: reward = -116.14, steps = 23 04:06:56 [INFO] train episode 5998: reward = -157.90, steps = 23 04:06:58 [INFO] train episode 5999: reward = -179.47, steps = 23 04:07:00 [INFO] train episode 6000: reward = -183.46, steps = 22 04:07:02 [INFO] train episode 6001: reward = -142.71, steps = 18 04:07:04 [INFO] train episode 6002: reward = -155.42, steps = 23 04:07:06 [INFO] train episode 6003: reward = -173.96, steps = 22 04:07:07 [INFO] train episode 6004: reward = -165.84, steps = 19 04:07:11 [INFO] train episode 6005: reward = -172.64, steps = 44 04:07:14 [INFO] train episode 6006: reward = -219.35, steps = 26 04:07:17 [INFO] train episode 6007: reward = -147.03, steps = 35 04:07:19 [INFO] train episode 6008: reward = -205.59, steps = 29 04:07:21 [INFO] train episode 6009: reward = -93.58, steps = 20 04:07:23 [INFO] train episode 6010: reward = -98.01, steps = 25 04:07:26 [INFO] train episode 6011: reward = -114.71, steps = 35 04:07:28 [INFO] train episode 6012: reward = -197.06, steps = 19 04:07:31 [INFO] train episode 6013: reward = -239.61, steps = 28 04:07:33 [INFO] train episode 6014: reward = -120.84, steps = 31 04:07:37 [INFO] train episode 6015: reward = -155.91, steps = 43 04:07:39 [INFO] train episode 6016: reward = -156.37, steps = 25 04:07:41 [INFO] train episode 6017: reward = -139.79, steps = 26 04:07:45 [INFO] train episode 6018: reward = -73.68, steps = 36 04:07:47 [INFO] train episode 6019: reward = -247.16, steps = 26 04:07:49 [INFO] train episode 6020: reward = -177.03, steps = 28 04:07:52 [INFO] train episode 6021: reward = -116.69, steps = 30 04:07:54 [INFO] train episode 6022: reward = -118.58, steps = 24 04:07:56 [INFO] train episode 6023: reward = -147.60, steps = 27 04:07:58 [INFO] train episode 6024: reward = -196.86, steps = 22 04:08:01 [INFO] train episode 6025: reward = -216.82, steps = 25 04:08:02 [INFO] train episode 6026: reward = -96.73, steps = 18 04:08:05 [INFO] train episode 6027: reward = -178.16, steps = 26 04:08:07 [INFO] train episode 6028: reward = -86.18, steps = 25 04:08:09 [INFO] train episode 6029: reward = -155.29, steps = 19 04:08:11 [INFO] train episode 6030: reward = -190.25, steps = 32 04:08:13 [INFO] train episode 6031: reward = -170.86, steps = 25 04:08:16 [INFO] train episode 6032: reward = -192.84, steps = 30 04:08:19 [INFO] train episode 6033: reward = -142.22, steps = 29 04:08:22 [INFO] train episode 6034: reward = -143.87, steps = 32 04:08:24 [INFO] train episode 6035: reward = -134.79, steps = 26 04:08:25 [INFO] train episode 6036: reward = -110.10, steps = 18 04:08:28 [INFO] train episode 6037: reward = -171.45, steps = 35 04:08:31 [INFO] train episode 6038: reward = -184.34, steps = 27 04:08:35 [INFO] train episode 6039: reward = -224.69, steps = 40 04:08:36 [INFO] train episode 6040: reward = -169.94, steps = 20 04:08:39 [INFO] train episode 6041: reward = -209.98, steps = 26 04:08:42 [INFO] train episode 6042: reward = -169.04, steps = 33 04:08:43 [INFO] train episode 6043: reward = -151.53, steps = 21 04:08:45 [INFO] train episode 6044: reward = -85.81, steps = 20 04:08:47 [INFO] train episode 6045: reward = -138.90, steps = 23 04:08:50 [INFO] train episode 6046: reward = -92.48, steps = 26 04:08:52 [INFO] train episode 6047: reward = -151.31, steps = 20 04:08:53 [INFO] train episode 6048: reward = -182.95, steps = 20 04:08:57 [INFO] train episode 6049: reward = -286.90, steps = 49 04:09:00 [INFO] train episode 6050: reward = -163.84, steps = 29 04:09:02 [INFO] train episode 6051: reward = -127.40, steps = 29 04:09:05 [INFO] train episode 6052: reward = -102.13, steps = 22 04:09:07 [INFO] train episode 6053: reward = -108.66, steps = 23 04:09:09 [INFO] train episode 6054: reward = -168.81, steps = 30 04:09:12 [INFO] train episode 6055: reward = -229.65, steps = 32 04:09:15 [INFO] train episode 6056: reward = -226.20, steps = 32 04:09:17 [INFO] train episode 6057: reward = -110.97, steps = 30 04:09:19 [INFO] train episode 6058: reward = -197.98, steps = 19 04:09:22 [INFO] train episode 6059: reward = -163.86, steps = 33 04:09:25 [INFO] train episode 6060: reward = -136.17, steps = 31 04:09:28 [INFO] train episode 6061: reward = -220.78, steps = 37 04:09:31 [INFO] train episode 6062: reward = -140.45, steps = 26 04:09:36 [INFO] train episode 6063: reward = -306.09, steps = 61 04:09:39 [INFO] train episode 6064: reward = -175.35, steps = 28 04:09:40 [INFO] train episode 6065: reward = -68.16, steps = 21 04:09:42 [INFO] train episode 6066: reward = -95.66, steps = 23 04:09:45 [INFO] train episode 6067: reward = -156.44, steps = 19 04:09:47 [INFO] train episode 6068: reward = -168.90, steps = 22 04:09:48 [INFO] train episode 6069: reward = -172.42, steps = 19 04:09:51 [INFO] train episode 6070: reward = -122.11, steps = 23 04:09:53 [INFO] train episode 6071: reward = -166.89, steps = 23 04:09:55 [INFO] train episode 6072: reward = -114.61, steps = 23 04:09:57 [INFO] train episode 6073: reward = -164.08, steps = 29 04:10:00 [INFO] train episode 6074: reward = -187.51, steps = 31 04:10:04 [INFO] train episode 6075: reward = -154.14, steps = 45 04:10:06 [INFO] train episode 6076: reward = -158.97, steps = 25 04:10:08 [INFO] train episode 6077: reward = -175.55, steps = 27 04:10:11 [INFO] train episode 6078: reward = -156.51, steps = 27 04:10:13 [INFO] train episode 6079: reward = -127.06, steps = 27 04:10:16 [INFO] train episode 6080: reward = -200.88, steps = 35 04:10:18 [INFO] train episode 6081: reward = -89.09, steps = 20 04:10:20 [INFO] train episode 6082: reward = -111.54, steps = 23 04:10:23 [INFO] train episode 6083: reward = -189.44, steps = 32 04:10:26 [INFO] train episode 6084: reward = -177.85, steps = 33 04:10:30 [INFO] train episode 6085: reward = -205.10, steps = 45 04:10:32 [INFO] train episode 6086: reward = -149.48, steps = 26 04:10:36 [INFO] train episode 6087: reward = -304.07, steps = 48 04:10:39 [INFO] train episode 6088: reward = -82.79, steps = 26 04:10:40 [INFO] train episode 6089: reward = -101.20, steps = 18 04:10:42 [INFO] train episode 6090: reward = -76.08, steps = 20 04:10:45 [INFO] train episode 6091: reward = -115.22, steps = 26 04:10:47 [INFO] train episode 6092: reward = -131.95, steps = 27 04:10:49 [INFO] train episode 6093: reward = -124.51, steps = 19 04:10:50 [INFO] train episode 6094: reward = -157.75, steps = 19 04:10:53 [INFO] train episode 6095: reward = -162.13, steps = 28 04:10:54 [INFO] train episode 6096: reward = -93.98, steps = 19 04:10:56 [INFO] train episode 6097: reward = -144.28, steps = 18 04:10:59 [INFO] train episode 6098: reward = -258.23, steps = 31 04:11:01 [INFO] train episode 6099: reward = -132.88, steps = 20 04:11:03 [INFO] train episode 6100: reward = -141.19, steps = 23 04:11:05 [INFO] train episode 6101: reward = -157.39, steps = 21 04:11:07 [INFO] train episode 6102: reward = -135.77, steps = 28 04:11:09 [INFO] train episode 6103: reward = -204.88, steps = 20 04:11:12 [INFO] train episode 6104: reward = -197.28, steps = 36 04:11:14 [INFO] train episode 6105: reward = -109.57, steps = 22 04:11:17 [INFO] train episode 6106: reward = -262.87, steps = 34 04:11:19 [INFO] train episode 6107: reward = -95.00, steps = 19 04:11:22 [INFO] train episode 6108: reward = -189.93, steps = 38 04:11:24 [INFO] train episode 6109: reward = -108.47, steps = 19 04:11:26 [INFO] train episode 6110: reward = -125.29, steps = 27 04:11:28 [INFO] train episode 6111: reward = -173.85, steps = 22 04:11:32 [INFO] train episode 6112: reward = -235.20, steps = 44 04:11:34 [INFO] train episode 6113: reward = -130.54, steps = 22 04:11:36 [INFO] train episode 6114: reward = -122.39, steps = 22 04:11:39 [INFO] train episode 6115: reward = -263.31, steps = 36 04:11:41 [INFO] train episode 6116: reward = -175.78, steps = 26 04:11:43 [INFO] train episode 6117: reward = -181.25, steps = 23 04:11:47 [INFO] train episode 6118: reward = -239.19, steps = 40 04:11:49 [INFO] train episode 6119: reward = -152.72, steps = 21 04:11:51 [INFO] train episode 6120: reward = -96.24, steps = 24 04:11:53 [INFO] train episode 6121: reward = -144.68, steps = 27 04:11:56 [INFO] train episode 6122: reward = -84.39, steps = 29 04:11:59 [INFO] train episode 6123: reward = -173.87, steps = 42 04:12:01 [INFO] train episode 6124: reward = -119.06, steps = 20 04:12:03 [INFO] train episode 6125: reward = -111.81, steps = 20 04:12:05 [INFO] train episode 6126: reward = -94.01, steps = 19 04:12:07 [INFO] train episode 6127: reward = -104.44, steps = 23 04:12:09 [INFO] train episode 6128: reward = -109.96, steps = 28 04:12:12 [INFO] train episode 6129: reward = -167.41, steps = 28 04:12:14 [INFO] train episode 6130: reward = -295.22, steps = 23 04:12:16 [INFO] train episode 6131: reward = -177.21, steps = 19 04:12:18 [INFO] train episode 6132: reward = -139.44, steps = 21 04:12:20 [INFO] train episode 6133: reward = -96.05, steps = 20 04:12:21 [INFO] train episode 6134: reward = -65.46, steps = 19 04:12:23 [INFO] train episode 6135: reward = -145.87, steps = 23 04:12:25 [INFO] train episode 6136: reward = -146.36, steps = 24 04:12:27 [INFO] train episode 6137: reward = -94.99, steps = 22 04:12:30 [INFO] train episode 6138: reward = -150.36, steps = 26 04:12:31 [INFO] train episode 6139: reward = -134.43, steps = 19 04:12:35 [INFO] train episode 6140: reward = -183.27, steps = 35 04:12:37 [INFO] train episode 6141: reward = -116.72, steps = 20 04:12:39 [INFO] train episode 6142: reward = -175.65, steps = 19 04:12:41 [INFO] train episode 6143: reward = -147.98, steps = 24 04:12:43 [INFO] train episode 6144: reward = -358.35, steps = 24 04:12:46 [INFO] train episode 6145: reward = -167.60, steps = 27 04:12:49 [INFO] train episode 6146: reward = -162.19, steps = 33 04:12:51 [INFO] train episode 6147: reward = -105.55, steps = 26 04:12:53 [INFO] train episode 6148: reward = -161.06, steps = 19 04:12:54 [INFO] train episode 6149: reward = -115.62, steps = 19 04:12:56 [INFO] train episode 6150: reward = -102.44, steps = 20 04:12:58 [INFO] train episode 6151: reward = -111.42, steps = 23 04:13:00 [INFO] train episode 6152: reward = -114.48, steps = 21 04:13:02 [INFO] train episode 6153: reward = -192.50, steps = 24 04:13:04 [INFO] train episode 6154: reward = -128.37, steps = 24 04:13:07 [INFO] train episode 6155: reward = -118.70, steps = 30 04:13:10 [INFO] train episode 6156: reward = -170.83, steps = 28 04:13:12 [INFO] train episode 6157: reward = -132.32, steps = 27 04:13:15 [INFO] train episode 6158: reward = -226.30, steps = 35 04:13:16 [INFO] train episode 6159: reward = -188.63, steps = 18 04:13:20 [INFO] train episode 6160: reward = -205.42, steps = 42 04:13:22 [INFO] train episode 6161: reward = -176.80, steps = 21 04:13:24 [INFO] train episode 6162: reward = -179.51, steps = 19 04:13:27 [INFO] train episode 6163: reward = -115.60, steps = 30 04:13:29 [INFO] train episode 6164: reward = -138.59, steps = 26 04:13:32 [INFO] train episode 6165: reward = -127.35, steps = 41 04:13:34 [INFO] train episode 6166: reward = -113.19, steps = 19 04:13:36 [INFO] train episode 6167: reward = -123.87, steps = 24 04:13:38 [INFO] train episode 6168: reward = -100.21, steps = 23 04:13:40 [INFO] train episode 6169: reward = -145.98, steps = 21 04:13:42 [INFO] train episode 6170: reward = -246.08, steps = 24 04:13:44 [INFO] train episode 6171: reward = -137.35, steps = 24 04:13:47 [INFO] train episode 6172: reward = -173.04, steps = 24 04:13:49 [INFO] train episode 6173: reward = -72.32, steps = 23 04:13:51 [INFO] train episode 6174: reward = -141.43, steps = 28 04:13:53 [INFO] train episode 6175: reward = -186.95, steps = 19 04:13:55 [INFO] train episode 6176: reward = -180.01, steps = 26 04:13:57 [INFO] train episode 6177: reward = -205.28, steps = 19 04:14:00 [INFO] train episode 6178: reward = -210.35, steps = 30 04:14:03 [INFO] train episode 6179: reward = -233.65, steps = 37 04:14:05 [INFO] train episode 6180: reward = -66.15, steps = 23 04:14:07 [INFO] train episode 6181: reward = -142.40, steps = 25 04:14:09 [INFO] train episode 6182: reward = -159.28, steps = 30 04:14:12 [INFO] train episode 6183: reward = -160.39, steps = 19 04:14:14 [INFO] train episode 6184: reward = -158.95, steps = 25 04:14:18 [INFO] train episode 6185: reward = -306.17, steps = 49 04:14:20 [INFO] train episode 6186: reward = -213.31, steps = 22 04:14:21 [INFO] train episode 6187: reward = -156.80, steps = 19 04:14:24 [INFO] train episode 6188: reward = -170.10, steps = 31 04:14:26 [INFO] train episode 6189: reward = -120.48, steps = 23 04:14:29 [INFO] train episode 6190: reward = -112.33, steps = 32 04:14:32 [INFO] train episode 6191: reward = -140.12, steps = 26 04:14:33 [INFO] train episode 6192: reward = -112.83, steps = 21 04:14:37 [INFO] train episode 6193: reward = -171.55, steps = 38 04:14:39 [INFO] train episode 6194: reward = -254.25, steps = 31 04:14:41 [INFO] train episode 6195: reward = -174.52, steps = 24 04:14:43 [INFO] train episode 6196: reward = -115.64, steps = 19 04:14:46 [INFO] train episode 6197: reward = -152.19, steps = 24 04:14:48 [INFO] train episode 6198: reward = -200.00, steps = 25 04:14:50 [INFO] train episode 6199: reward = -110.69, steps = 20 04:14:52 [INFO] train episode 6200: reward = -126.48, steps = 19 04:14:54 [INFO] train episode 6201: reward = -180.59, steps = 23 04:14:56 [INFO] train episode 6202: reward = -120.87, steps = 28 04:14:58 [INFO] train episode 6203: reward = -103.83, steps = 21 04:15:01 [INFO] train episode 6204: reward = -165.18, steps = 28 04:15:04 [INFO] train episode 6205: reward = -185.63, steps = 33 04:15:06 [INFO] train episode 6206: reward = -166.50, steps = 24 04:15:07 [INFO] train episode 6207: reward = -104.03, steps = 19 04:15:09 [INFO] train episode 6208: reward = -96.51, steps = 19 04:15:12 [INFO] train episode 6209: reward = -204.29, steps = 29 04:15:14 [INFO] train episode 6210: reward = -204.43, steps = 24 04:15:17 [INFO] train episode 6211: reward = -142.67, steps = 34 04:15:20 [INFO] train episode 6212: reward = -114.58, steps = 30 04:15:24 [INFO] train episode 6213: reward = -249.48, steps = 53 04:15:27 [INFO] train episode 6214: reward = -194.97, steps = 29 04:15:30 [INFO] train episode 6215: reward = -145.90, steps = 26 04:15:31 [INFO] train episode 6216: reward = -169.50, steps = 20 04:15:34 [INFO] train episode 6217: reward = -92.22, steps = 20 04:15:37 [INFO] train episode 6218: reward = -209.95, steps = 38 04:15:39 [INFO] train episode 6219: reward = -172.29, steps = 23 04:15:41 [INFO] train episode 6220: reward = -80.82, steps = 28 04:15:44 [INFO] train episode 6221: reward = -167.88, steps = 26 04:15:46 [INFO] train episode 6222: reward = -120.57, steps = 25 04:15:49 [INFO] train episode 6223: reward = -160.47, steps = 33 04:15:52 [INFO] train episode 6224: reward = -247.74, steps = 33 04:15:54 [INFO] train episode 6225: reward = -139.62, steps = 22 04:15:55 [INFO] train episode 6226: reward = -237.38, steps = 20 04:15:58 [INFO] train episode 6227: reward = -251.45, steps = 30 04:16:01 [INFO] train episode 6228: reward = -180.18, steps = 38 04:16:03 [INFO] train episode 6229: reward = -127.69, steps = 24 04:16:07 [INFO] train episode 6230: reward = -176.85, steps = 32 04:16:08 [INFO] train episode 6231: reward = -91.43, steps = 20 04:16:11 [INFO] train episode 6232: reward = -119.92, steps = 27 04:16:12 [INFO] train episode 6233: reward = -147.79, steps = 19 04:16:15 [INFO] train episode 6234: reward = -206.86, steps = 26 04:16:16 [INFO] train episode 6235: reward = -85.06, steps = 21 04:16:19 [INFO] train episode 6236: reward = -131.15, steps = 31 04:16:22 [INFO] train episode 6237: reward = -133.95, steps = 25 04:16:24 [INFO] train episode 6238: reward = -139.68, steps = 24 04:16:26 [INFO] train episode 6239: reward = -136.94, steps = 22 04:16:27 [INFO] train episode 6240: reward = -155.38, steps = 20 04:16:30 [INFO] train episode 6241: reward = -186.88, steps = 26 04:16:34 [INFO] train episode 6242: reward = -249.72, steps = 50 04:16:36 [INFO] train episode 6243: reward = -238.11, steps = 27 04:16:38 [INFO] train episode 6244: reward = -229.45, steps = 20 04:16:41 [INFO] train episode 6245: reward = -133.21, steps = 25 04:16:43 [INFO] train episode 6246: reward = -187.87, steps = 24 04:16:45 [INFO] train episode 6247: reward = -121.36, steps = 21 04:16:47 [INFO] train episode 6248: reward = -192.68, steps = 23 04:16:49 [INFO] train episode 6249: reward = -157.76, steps = 28 04:16:51 [INFO] train episode 6250: reward = -99.18, steps = 19 04:16:53 [INFO] train episode 6251: reward = -148.01, steps = 24 04:16:56 [INFO] train episode 6252: reward = -206.36, steps = 28 04:16:58 [INFO] train episode 6253: reward = -213.40, steps = 28 04:17:00 [INFO] train episode 6254: reward = -126.57, steps = 19 04:17:02 [INFO] train episode 6255: reward = -131.45, steps = 18 04:17:05 [INFO] train episode 6256: reward = -142.35, steps = 36 04:17:07 [INFO] train episode 6257: reward = -116.32, steps = 27 04:17:09 [INFO] train episode 6258: reward = -91.41, steps = 24 04:17:12 [INFO] train episode 6259: reward = -145.55, steps = 30 04:17:14 [INFO] train episode 6260: reward = -133.26, steps = 26 04:17:16 [INFO] train episode 6261: reward = -117.53, steps = 19 04:17:18 [INFO] train episode 6262: reward = -311.59, steps = 25 04:17:20 [INFO] train episode 6263: reward = -116.45, steps = 23 04:17:22 [INFO] train episode 6264: reward = -70.02, steps = 20 04:17:24 [INFO] train episode 6265: reward = -103.12, steps = 25 04:17:26 [INFO] train episode 6266: reward = -117.72, steps = 20 04:17:28 [INFO] train episode 6267: reward = -118.86, steps = 19 04:17:31 [INFO] train episode 6268: reward = -138.34, steps = 33 04:17:34 [INFO] train episode 6269: reward = -253.14, steps = 37 04:17:36 [INFO] train episode 6270: reward = -131.99, steps = 28 04:17:39 [INFO] train episode 6271: reward = -209.74, steps = 29 04:17:41 [INFO] train episode 6272: reward = -141.03, steps = 27 04:17:48 [INFO] train episode 6273: reward = -379.52, steps = 71 04:17:50 [INFO] train episode 6274: reward = -154.25, steps = 28 04:17:53 [INFO] train episode 6275: reward = -126.18, steps = 32 04:17:55 [INFO] train episode 6276: reward = -141.81, steps = 26 04:17:57 [INFO] train episode 6277: reward = -172.57, steps = 23 04:17:59 [INFO] train episode 6278: reward = -171.18, steps = 23 04:18:01 [INFO] train episode 6279: reward = -130.74, steps = 21 04:18:04 [INFO] train episode 6280: reward = -100.42, steps = 28 04:18:06 [INFO] train episode 6281: reward = -120.45, steps = 25 04:18:08 [INFO] train episode 6282: reward = -109.78, steps = 23 04:18:11 [INFO] train episode 6283: reward = -149.28, steps = 31 04:18:12 [INFO] train episode 6284: reward = -125.16, steps = 20 04:18:14 [INFO] train episode 6285: reward = -109.04, steps = 18 04:18:16 [INFO] train episode 6286: reward = -108.51, steps = 21 04:18:18 [INFO] train episode 6287: reward = -95.38, steps = 21 04:18:21 [INFO] train episode 6288: reward = -309.24, steps = 29 04:18:23 [INFO] train episode 6289: reward = -126.09, steps = 24 04:18:25 [INFO] train episode 6290: reward = -106.63, steps = 16 04:18:27 [INFO] train episode 6291: reward = -108.61, steps = 26 04:18:29 [INFO] train episode 6292: reward = -84.16, steps = 21 04:18:31 [INFO] train episode 6293: reward = -185.25, steps = 18 04:18:33 [INFO] train episode 6294: reward = -180.78, steps = 20 04:18:35 [INFO] train episode 6295: reward = -124.22, steps = 25 04:18:38 [INFO] train episode 6296: reward = -226.39, steps = 35 04:18:40 [INFO] train episode 6297: reward = -136.17, steps = 19 04:18:41 [INFO] train episode 6298: reward = -93.70, steps = 20 04:18:44 [INFO] train episode 6299: reward = -118.57, steps = 27 04:18:46 [INFO] train episode 6300: reward = -149.95, steps = 28 04:18:48 [INFO] train episode 6301: reward = -156.33, steps = 20 04:18:50 [INFO] train episode 6302: reward = -112.36, steps = 21 04:18:52 [INFO] train episode 6303: reward = -79.53, steps = 19 04:18:54 [INFO] train episode 6304: reward = -107.93, steps = 27 04:18:56 [INFO] train episode 6305: reward = -183.39, steps = 23 04:18:58 [INFO] train episode 6306: reward = -131.94, steps = 21 04:19:01 [INFO] train episode 6307: reward = -293.95, steps = 30 04:19:03 [INFO] train episode 6308: reward = -175.70, steps = 26 04:19:06 [INFO] train episode 6309: reward = -105.91, steps = 24 04:19:08 [INFO] train episode 6310: reward = -117.48, steps = 27 04:19:10 [INFO] train episode 6311: reward = -166.00, steps = 29 04:19:12 [INFO] train episode 6312: reward = -125.01, steps = 22 04:19:14 [INFO] train episode 6313: reward = -158.33, steps = 24 04:19:17 [INFO] train episode 6314: reward = -170.99, steps = 29 04:19:19 [INFO] train episode 6315: reward = -82.44, steps = 20 04:19:21 [INFO] train episode 6316: reward = -165.96, steps = 25 04:19:24 [INFO] train episode 6317: reward = -132.66, steps = 33 04:19:26 [INFO] train episode 6318: reward = -126.65, steps = 26 04:19:28 [INFO] train episode 6319: reward = -86.51, steps = 19 04:19:30 [INFO] train episode 6320: reward = -181.96, steps = 24 04:19:32 [INFO] train episode 6321: reward = -251.73, steps = 20 04:19:34 [INFO] train episode 6322: reward = -149.88, steps = 28 04:19:37 [INFO] train episode 6323: reward = -140.45, steps = 24 04:19:39 [INFO] train episode 6324: reward = -198.27, steps = 29 04:19:42 [INFO] train episode 6325: reward = -325.42, steps = 28 04:19:44 [INFO] train episode 6326: reward = -155.40, steps = 22 04:19:46 [INFO] train episode 6327: reward = -202.31, steps = 24 04:19:48 [INFO] train episode 6328: reward = -130.15, steps = 24 04:19:50 [INFO] train episode 6329: reward = -241.56, steps = 26 04:19:52 [INFO] train episode 6330: reward = -144.95, steps = 18 04:19:54 [INFO] train episode 6331: reward = -113.96, steps = 25 04:19:56 [INFO] train episode 6332: reward = -148.15, steps = 24 04:19:59 [INFO] train episode 6333: reward = -173.81, steps = 27 04:20:01 [INFO] train episode 6334: reward = -149.60, steps = 33 04:20:04 [INFO] train episode 6335: reward = -160.63, steps = 29 04:20:06 [INFO] train episode 6336: reward = -158.62, steps = 19 04:20:08 [INFO] train episode 6337: reward = -114.34, steps = 22 04:20:11 [INFO] train episode 6338: reward = -119.81, steps = 30 04:20:13 [INFO] train episode 6339: reward = -169.27, steps = 28 04:20:15 [INFO] train episode 6340: reward = -127.71, steps = 24 04:20:17 [INFO] train episode 6341: reward = -175.91, steps = 20 04:20:19 [INFO] train episode 6342: reward = -129.03, steps = 22 04:20:21 [INFO] train episode 6343: reward = -121.12, steps = 28 04:20:23 [INFO] train episode 6344: reward = -162.27, steps = 21 04:20:26 [INFO] train episode 6345: reward = -124.83, steps = 27 04:20:28 [INFO] train episode 6346: reward = -71.88, steps = 25 04:20:30 [INFO] train episode 6347: reward = -127.04, steps = 25 04:20:33 [INFO] train episode 6348: reward = -81.58, steps = 23 04:20:35 [INFO] train episode 6349: reward = -98.57, steps = 19 04:20:38 [INFO] train episode 6350: reward = -180.71, steps = 32 04:20:42 [INFO] train episode 6351: reward = -207.26, steps = 34 04:20:44 [INFO] train episode 6352: reward = -143.31, steps = 23 04:20:46 [INFO] train episode 6353: reward = -86.64, steps = 21 04:20:48 [INFO] train episode 6354: reward = -158.32, steps = 29 04:20:51 [INFO] train episode 6355: reward = -153.57, steps = 22 04:20:52 [INFO] train episode 6356: reward = -145.27, steps = 19 04:20:54 [INFO] train episode 6357: reward = -118.50, steps = 20 04:20:57 [INFO] train episode 6358: reward = -143.02, steps = 29 04:20:59 [INFO] train episode 6359: reward = -107.65, steps = 19 04:21:01 [INFO] train episode 6360: reward = -116.37, steps = 27 04:21:03 [INFO] train episode 6361: reward = -122.85, steps = 21 04:21:05 [INFO] train episode 6362: reward = -101.46, steps = 24 04:21:07 [INFO] train episode 6363: reward = -161.11, steps = 19 04:21:09 [INFO] train episode 6364: reward = -144.06, steps = 26 04:21:11 [INFO] train episode 6365: reward = -77.53, steps = 21 04:21:13 [INFO] train episode 6366: reward = -174.02, steps = 18 04:21:15 [INFO] train episode 6367: reward = -105.07, steps = 24 04:21:17 [INFO] train episode 6368: reward = -167.23, steps = 24 04:21:20 [INFO] train episode 6369: reward = -145.56, steps = 25 04:21:23 [INFO] train episode 6370: reward = -124.05, steps = 26 04:21:25 [INFO] train episode 6371: reward = -88.24, steps = 26 04:21:27 [INFO] train episode 6372: reward = -171.39, steps = 26 04:21:31 [INFO] train episode 6373: reward = -181.94, steps = 38 04:21:34 [INFO] train episode 6374: reward = -256.18, steps = 33 04:21:35 [INFO] train episode 6375: reward = -92.36, steps = 20 04:21:38 [INFO] train episode 6376: reward = -161.37, steps = 32 04:21:40 [INFO] train episode 6377: reward = -66.50, steps = 20 04:21:42 [INFO] train episode 6378: reward = -158.96, steps = 24 04:21:44 [INFO] train episode 6379: reward = -112.73, steps = 19 04:21:47 [INFO] train episode 6380: reward = -149.59, steps = 40 04:21:50 [INFO] train episode 6381: reward = -124.30, steps = 28 04:21:52 [INFO] train episode 6382: reward = -155.16, steps = 20 04:21:54 [INFO] train episode 6383: reward = -192.30, steps = 27 04:21:56 [INFO] train episode 6384: reward = -256.24, steps = 25 04:21:59 [INFO] train episode 6385: reward = -94.89, steps = 34 04:22:03 [INFO] train episode 6386: reward = -112.88, steps = 42 04:22:05 [INFO] train episode 6387: reward = -153.09, steps = 24 04:22:07 [INFO] train episode 6388: reward = -178.45, steps = 24 04:22:10 [INFO] train episode 6389: reward = -225.75, steps = 36 04:22:12 [INFO] train episode 6390: reward = -157.97, steps = 22 04:22:14 [INFO] train episode 6391: reward = -137.50, steps = 22 04:22:16 [INFO] train episode 6392: reward = -147.27, steps = 18 04:22:18 [INFO] train episode 6393: reward = -215.06, steps = 28 04:22:21 [INFO] train episode 6394: reward = -109.15, steps = 22 04:22:23 [INFO] train episode 6395: reward = -140.15, steps = 23 04:22:24 [INFO] train episode 6396: reward = -130.58, steps = 19 04:22:27 [INFO] train episode 6397: reward = -180.69, steps = 27 04:22:30 [INFO] train episode 6398: reward = -229.35, steps = 33 04:22:32 [INFO] train episode 6399: reward = -184.10, steps = 25 04:22:34 [INFO] train episode 6400: reward = -97.71, steps = 20 04:22:36 [INFO] train episode 6401: reward = -110.31, steps = 21 04:22:38 [INFO] train episode 6402: reward = -145.07, steps = 24 04:22:40 [INFO] train episode 6403: reward = -206.74, steps = 29 04:22:43 [INFO] train episode 6404: reward = -157.65, steps = 27 04:22:45 [INFO] train episode 6405: reward = -278.18, steps = 24 04:22:47 [INFO] train episode 6406: reward = -165.58, steps = 28 04:22:49 [INFO] train episode 6407: reward = -123.85, steps = 21 04:22:52 [INFO] train episode 6408: reward = -105.86, steps = 24 04:22:53 [INFO] train episode 6409: reward = -108.54, steps = 20 04:22:56 [INFO] train episode 6410: reward = -114.39, steps = 28 04:22:59 [INFO] train episode 6411: reward = -118.04, steps = 37 04:23:01 [INFO] train episode 6412: reward = -143.58, steps = 21 04:23:03 [INFO] train episode 6413: reward = -135.63, steps = 19 04:23:04 [INFO] train episode 6414: reward = -137.70, steps = 20 04:23:07 [INFO] train episode 6415: reward = -149.97, steps = 25 04:23:10 [INFO] train episode 6416: reward = -147.54, steps = 30 04:23:12 [INFO] train episode 6417: reward = -167.73, steps = 25 04:23:15 [INFO] train episode 6418: reward = -181.63, steps = 37 04:23:16 [INFO] train episode 6419: reward = -179.01, steps = 18 04:23:19 [INFO] train episode 6420: reward = -191.11, steps = 32 04:23:21 [INFO] train episode 6421: reward = -157.39, steps = 19 04:23:23 [INFO] train episode 6422: reward = -102.24, steps = 25 04:23:25 [INFO] train episode 6423: reward = -107.44, steps = 20 04:23:28 [INFO] train episode 6424: reward = -128.88, steps = 26 04:23:29 [INFO] train episode 6425: reward = -92.66, steps = 23 04:23:31 [INFO] train episode 6426: reward = -163.58, steps = 21 04:23:35 [INFO] train episode 6427: reward = -182.98, steps = 42 04:23:39 [INFO] train episode 6428: reward = -200.91, steps = 42 04:23:41 [INFO] train episode 6429: reward = -167.94, steps = 30 04:23:44 [INFO] train episode 6430: reward = -171.45, steps = 26 04:23:46 [INFO] train episode 6431: reward = -98.94, steps = 24 04:23:48 [INFO] train episode 6432: reward = -95.03, steps = 22 04:23:51 [INFO] train episode 6433: reward = -143.07, steps = 42 04:23:54 [INFO] train episode 6434: reward = -153.27, steps = 25 04:23:56 [INFO] train episode 6435: reward = -394.37, steps = 22 04:23:58 [INFO] train episode 6436: reward = -133.51, steps = 23 04:24:00 [INFO] train episode 6437: reward = -149.53, steps = 19 04:24:01 [INFO] train episode 6438: reward = -170.15, steps = 21 04:24:03 [INFO] train episode 6439: reward = -101.61, steps = 21 04:24:06 [INFO] train episode 6440: reward = -244.70, steps = 28 04:24:08 [INFO] train episode 6441: reward = -201.96, steps = 21 04:24:11 [INFO] train episode 6442: reward = -177.51, steps = 37 04:24:15 [INFO] train episode 6443: reward = -221.83, steps = 36 04:24:17 [INFO] train episode 6444: reward = -152.73, steps = 24 04:24:20 [INFO] train episode 6445: reward = -195.51, steps = 28 04:24:22 [INFO] train episode 6446: reward = -189.08, steps = 30 04:24:24 [INFO] train episode 6447: reward = -126.23, steps = 20 04:24:28 [INFO] train episode 6448: reward = -183.60, steps = 46 04:24:31 [INFO] train episode 6449: reward = -106.45, steps = 30 04:24:33 [INFO] train episode 6450: reward = -177.53, steps = 26 04:24:35 [INFO] train episode 6451: reward = -77.83, steps = 19 04:24:37 [INFO] train episode 6452: reward = -114.30, steps = 21 04:24:39 [INFO] train episode 6453: reward = -152.30, steps = 24 04:24:41 [INFO] train episode 6454: reward = -70.24, steps = 21 04:24:43 [INFO] train episode 6455: reward = -213.21, steps = 23 04:24:45 [INFO] train episode 6456: reward = -156.31, steps = 22 04:24:47 [INFO] train episode 6457: reward = -126.14, steps = 25 04:24:49 [INFO] train episode 6458: reward = -140.18, steps = 20 04:24:51 [INFO] train episode 6459: reward = -167.45, steps = 26 04:24:53 [INFO] train episode 6460: reward = -128.02, steps = 19 04:24:56 [INFO] train episode 6461: reward = -89.23, steps = 34 04:24:59 [INFO] train episode 6462: reward = -136.93, steps = 34 04:25:01 [INFO] train episode 6463: reward = -136.00, steps = 20 04:25:04 [INFO] train episode 6464: reward = -135.67, steps = 29 04:25:06 [INFO] train episode 6465: reward = -207.87, steps = 24 04:25:08 [INFO] train episode 6466: reward = -125.99, steps = 25 04:25:10 [INFO] train episode 6467: reward = -103.58, steps = 21 04:25:12 [INFO] train episode 6468: reward = -162.36, steps = 21 04:25:14 [INFO] train episode 6469: reward = -150.41, steps = 27 04:25:16 [INFO] train episode 6470: reward = -151.09, steps = 25 04:25:19 [INFO] train episode 6471: reward = -146.73, steps = 24 04:25:21 [INFO] train episode 6472: reward = -154.35, steps = 28 04:25:24 [INFO] train episode 6473: reward = -120.27, steps = 28 04:25:25 [INFO] train episode 6474: reward = -150.50, steps = 19 04:25:27 [INFO] train episode 6475: reward = -97.98, steps = 21 04:25:30 [INFO] train episode 6476: reward = -159.06, steps = 28 04:25:32 [INFO] train episode 6477: reward = -198.69, steps = 25 04:25:34 [INFO] train episode 6478: reward = -139.61, steps = 25 04:25:36 [INFO] train episode 6479: reward = -98.09, steps = 23 04:25:39 [INFO] train episode 6480: reward = -194.05, steps = 29 04:25:41 [INFO] train episode 6481: reward = -140.73, steps = 27 04:25:43 [INFO] train episode 6482: reward = -77.79, steps = 21 04:25:45 [INFO] train episode 6483: reward = -156.66, steps = 29 04:25:47 [INFO] train episode 6484: reward = -141.77, steps = 20 04:25:50 [INFO] train episode 6485: reward = -127.39, steps = 27 04:25:52 [INFO] train episode 6486: reward = -198.18, steps = 24 04:25:54 [INFO] train episode 6487: reward = -184.14, steps = 23 04:25:56 [INFO] train episode 6488: reward = -93.28, steps = 21 04:25:59 [INFO] train episode 6489: reward = -158.83, steps = 31 04:26:01 [INFO] train episode 6490: reward = -118.18, steps = 23 04:26:03 [INFO] train episode 6491: reward = -155.57, steps = 24 04:26:05 [INFO] train episode 6492: reward = -179.70, steps = 26 04:26:08 [INFO] train episode 6493: reward = -126.09, steps = 31 04:26:10 [INFO] train episode 6494: reward = -164.23, steps = 19 04:26:12 [INFO] train episode 6495: reward = -125.04, steps = 22 04:26:14 [INFO] train episode 6496: reward = -194.06, steps = 23 04:26:16 [INFO] train episode 6497: reward = -258.11, steps = 34 04:26:19 [INFO] train episode 6498: reward = -174.27, steps = 29 04:26:22 [INFO] train episode 6499: reward = -163.67, steps = 33 04:26:25 [INFO] train episode 6500: reward = -110.96, steps = 33 04:26:27 [INFO] train episode 6501: reward = -203.39, steps = 22 04:26:29 [INFO] train episode 6502: reward = -166.33, steps = 22 04:26:31 [INFO] train episode 6503: reward = -130.36, steps = 22 04:26:34 [INFO] train episode 6504: reward = -112.16, steps = 36 04:26:36 [INFO] train episode 6505: reward = -118.91, steps = 21 04:26:38 [INFO] train episode 6506: reward = -217.42, steps = 22 04:26:40 [INFO] train episode 6507: reward = -326.71, steps = 19 04:26:42 [INFO] train episode 6508: reward = -230.78, steps = 27 04:26:44 [INFO] train episode 6509: reward = -124.96, steps = 22 04:26:46 [INFO] train episode 6510: reward = -134.74, steps = 24 04:26:49 [INFO] train episode 6511: reward = -143.36, steps = 30 04:26:50 [INFO] train episode 6512: reward = -161.09, steps = 18 04:26:53 [INFO] train episode 6513: reward = -115.04, steps = 30 04:26:55 [INFO] train episode 6514: reward = -103.55, steps = 25 04:26:58 [INFO] train episode 6515: reward = -189.11, steps = 27 04:27:01 [INFO] train episode 6516: reward = -144.48, steps = 33 04:27:03 [INFO] train episode 6517: reward = -182.72, steps = 34 04:27:06 [INFO] train episode 6518: reward = -211.79, steps = 27 04:27:09 [INFO] train episode 6519: reward = -122.32, steps = 24 04:27:11 [INFO] train episode 6520: reward = -110.64, steps = 25 04:27:14 [INFO] train episode 6521: reward = -176.06, steps = 29 04:27:16 [INFO] train episode 6522: reward = -182.68, steps = 25 04:27:18 [INFO] train episode 6523: reward = -194.68, steps = 27 04:27:20 [INFO] train episode 6524: reward = -118.84, steps = 22 04:27:23 [INFO] train episode 6525: reward = -201.93, steps = 32 04:27:27 [INFO] train episode 6526: reward = -175.39, steps = 41 04:27:29 [INFO] train episode 6527: reward = -174.07, steps = 26 04:27:31 [INFO] train episode 6528: reward = -125.85, steps = 18 04:27:32 [INFO] train episode 6529: reward = -113.09, steps = 20 04:27:35 [INFO] train episode 6530: reward = -153.40, steps = 29 04:27:37 [INFO] train episode 6531: reward = -156.08, steps = 29 04:27:40 [INFO] train episode 6532: reward = -186.57, steps = 30 04:27:43 [INFO] train episode 6533: reward = -131.99, steps = 28 04:27:45 [INFO] train episode 6534: reward = -136.15, steps = 24 04:27:49 [INFO] train episode 6535: reward = -147.95, steps = 46 04:27:51 [INFO] train episode 6536: reward = -122.94, steps = 24 04:27:53 [INFO] train episode 6537: reward = -115.56, steps = 25 04:27:55 [INFO] train episode 6538: reward = -128.18, steps = 21 04:27:57 [INFO] train episode 6539: reward = -140.40, steps = 22 04:28:00 [INFO] train episode 6540: reward = -135.04, steps = 34 04:28:03 [INFO] train episode 6541: reward = -144.57, steps = 28 04:28:04 [INFO] train episode 6542: reward = -134.35, steps = 19 04:28:06 [INFO] train episode 6543: reward = -235.14, steps = 22 04:28:08 [INFO] train episode 6544: reward = -96.60, steps = 18 04:28:10 [INFO] train episode 6545: reward = -131.75, steps = 24 04:28:13 [INFO] train episode 6546: reward = -188.35, steps = 35 04:28:16 [INFO] train episode 6547: reward = -248.59, steps = 32 04:28:18 [INFO] train episode 6548: reward = -122.88, steps = 29 04:28:20 [INFO] train episode 6549: reward = -89.33, steps = 20 04:28:22 [INFO] train episode 6550: reward = -131.12, steps = 27 04:28:25 [INFO] train episode 6551: reward = -158.58, steps = 27 04:28:27 [INFO] train episode 6552: reward = -110.39, steps = 24 04:28:29 [INFO] train episode 6553: reward = -183.16, steps = 30 04:28:32 [INFO] train episode 6554: reward = -166.77, steps = 21 04:28:34 [INFO] train episode 6555: reward = -78.47, steps = 27 04:28:36 [INFO] train episode 6556: reward = -183.31, steps = 24 04:28:38 [INFO] train episode 6557: reward = -181.70, steps = 20 04:28:40 [INFO] train episode 6558: reward = -118.47, steps = 23 04:28:42 [INFO] train episode 6559: reward = -142.57, steps = 30 04:28:44 [INFO] train episode 6560: reward = -102.82, steps = 21 04:28:47 [INFO] train episode 6561: reward = -208.87, steps = 27 04:28:49 [INFO] train episode 6562: reward = -139.64, steps = 20 04:28:51 [INFO] train episode 6563: reward = -157.96, steps = 29 04:28:53 [INFO] train episode 6564: reward = -165.36, steps = 22 04:28:56 [INFO] train episode 6565: reward = -181.89, steps = 30 04:28:58 [INFO] train episode 6566: reward = -186.98, steps = 21 04:29:00 [INFO] train episode 6567: reward = -152.04, steps = 27 04:29:03 [INFO] train episode 6568: reward = -130.22, steps = 30 04:29:06 [INFO] train episode 6569: reward = -150.61, steps = 25 04:29:08 [INFO] train episode 6570: reward = -105.10, steps = 21 04:29:10 [INFO] train episode 6571: reward = -200.86, steps = 28 04:29:14 [INFO] train episode 6572: reward = -181.37, steps = 40 04:29:16 [INFO] train episode 6573: reward = -154.47, steps = 28 04:29:18 [INFO] train episode 6574: reward = -193.07, steps = 29 04:29:23 [INFO] train episode 6575: reward = -320.39, steps = 55 04:29:26 [INFO] train episode 6576: reward = -129.27, steps = 24 04:29:28 [INFO] train episode 6577: reward = -149.44, steps = 31 04:29:31 [INFO] train episode 6578: reward = -112.87, steps = 26 04:29:32 [INFO] train episode 6579: reward = -81.83, steps = 21 04:29:34 [INFO] train episode 6580: reward = -184.69, steps = 18 04:29:37 [INFO] train episode 6581: reward = -173.90, steps = 30 04:29:39 [INFO] train episode 6582: reward = -106.79, steps = 19 04:29:41 [INFO] train episode 6583: reward = -140.48, steps = 27 04:29:44 [INFO] train episode 6584: reward = -237.44, steps = 37 04:29:46 [INFO] train episode 6585: reward = -123.82, steps = 27 04:29:49 [INFO] train episode 6586: reward = -153.43, steps = 25 04:29:51 [INFO] train episode 6587: reward = -153.35, steps = 25 04:29:55 [INFO] train episode 6588: reward = -227.39, steps = 39 04:29:58 [INFO] train episode 6589: reward = -167.45, steps = 36 04:30:01 [INFO] train episode 6590: reward = -170.27, steps = 31 04:30:03 [INFO] train episode 6591: reward = -200.02, steps = 22 04:30:07 [INFO] train episode 6592: reward = -121.67, steps = 38 04:30:10 [INFO] train episode 6593: reward = -288.61, steps = 31 04:30:12 [INFO] train episode 6594: reward = -98.81, steps = 31 04:30:14 [INFO] train episode 6595: reward = -134.24, steps = 19 04:30:16 [INFO] train episode 6596: reward = -156.09, steps = 19 04:30:18 [INFO] train episode 6597: reward = -188.01, steps = 29 04:30:20 [INFO] train episode 6598: reward = -301.12, steps = 27 04:30:22 [INFO] train episode 6599: reward = -167.79, steps = 23 04:30:24 [INFO] train episode 6600: reward = -216.98, steps = 18 04:30:26 [INFO] train episode 6601: reward = -108.06, steps = 20 04:30:28 [INFO] train episode 6602: reward = -143.70, steps = 24 04:30:31 [INFO] train episode 6603: reward = -191.01, steps = 32 04:30:33 [INFO] train episode 6604: reward = -115.34, steps = 23 04:30:36 [INFO] train episode 6605: reward = -170.24, steps = 31 04:30:38 [INFO] train episode 6606: reward = -130.83, steps = 27 04:30:40 [INFO] train episode 6607: reward = -131.47, steps = 25 04:30:43 [INFO] train episode 6608: reward = -218.43, steps = 32 04:30:45 [INFO] train episode 6609: reward = -92.12, steps = 23 04:30:47 [INFO] train episode 6610: reward = -220.28, steps = 24 04:30:49 [INFO] train episode 6611: reward = -204.75, steps = 19 04:30:51 [INFO] train episode 6612: reward = -145.33, steps = 20 04:30:53 [INFO] train episode 6613: reward = -177.67, steps = 22 04:30:55 [INFO] train episode 6614: reward = -135.71, steps = 30 04:30:58 [INFO] train episode 6615: reward = -105.28, steps = 21 04:31:00 [INFO] train episode 6616: reward = -275.78, steps = 26 04:31:02 [INFO] train episode 6617: reward = -185.16, steps = 26 04:31:04 [INFO] train episode 6618: reward = -111.22, steps = 20 04:31:06 [INFO] train episode 6619: reward = -360.83, steps = 26 04:31:10 [INFO] train episode 6620: reward = -209.33, steps = 41 04:31:12 [INFO] train episode 6621: reward = -130.95, steps = 21 04:31:14 [INFO] train episode 6622: reward = -93.81, steps = 19 04:31:16 [INFO] train episode 6623: reward = -119.46, steps = 24 04:31:18 [INFO] train episode 6624: reward = -187.50, steps = 24 04:31:19 [INFO] train episode 6625: reward = -178.77, steps = 20 04:31:22 [INFO] train episode 6626: reward = -118.70, steps = 28 04:31:25 [INFO] train episode 6627: reward = -248.49, steps = 41 04:31:28 [INFO] train episode 6628: reward = -184.05, steps = 34 04:31:31 [INFO] train episode 6629: reward = -113.94, steps = 30 04:31:34 [INFO] train episode 6630: reward = -135.81, steps = 25 04:31:36 [INFO] train episode 6631: reward = -137.57, steps = 30 04:31:38 [INFO] train episode 6632: reward = -91.63, steps = 20 04:31:40 [INFO] train episode 6633: reward = -214.42, steps = 23 04:31:43 [INFO] train episode 6634: reward = -185.96, steps = 33 04:31:45 [INFO] train episode 6635: reward = -103.24, steps = 25 04:31:47 [INFO] train episode 6636: reward = -98.64, steps = 19 04:31:50 [INFO] train episode 6637: reward = -122.60, steps = 30 04:31:51 [INFO] train episode 6638: reward = -136.58, steps = 20 04:31:53 [INFO] train episode 6639: reward = -153.13, steps = 23 04:31:56 [INFO] train episode 6640: reward = -185.67, steps = 28 04:31:58 [INFO] train episode 6641: reward = -231.98, steps = 31 04:32:01 [INFO] train episode 6642: reward = -115.04, steps = 19 04:32:05 [INFO] train episode 6643: reward = -294.20, steps = 48 04:32:07 [INFO] train episode 6644: reward = -127.68, steps = 23 04:32:09 [INFO] train episode 6645: reward = -114.40, steps = 23 04:32:12 [INFO] train episode 6646: reward = -272.53, steps = 34 04:32:13 [INFO] train episode 6647: reward = -112.31, steps = 21 04:32:16 [INFO] train episode 6648: reward = -167.37, steps = 33 04:32:18 [INFO] train episode 6649: reward = -104.32, steps = 19 04:32:20 [INFO] train episode 6650: reward = -119.52, steps = 24 04:32:23 [INFO] train episode 6651: reward = -122.49, steps = 24 04:32:24 [INFO] train episode 6652: reward = -207.42, steps = 21 04:32:27 [INFO] train episode 6653: reward = -210.22, steps = 25 04:32:29 [INFO] train episode 6654: reward = -179.50, steps = 24 04:32:36 [INFO] train episode 6655: reward = -346.31, steps = 79 04:32:38 [INFO] train episode 6656: reward = -131.49, steps = 19 04:32:40 [INFO] train episode 6657: reward = -111.19, steps = 27 04:32:42 [INFO] train episode 6658: reward = -87.55, steps = 25 04:32:45 [INFO] train episode 6659: reward = -196.07, steps = 36 04:32:48 [INFO] train episode 6660: reward = -121.07, steps = 28 04:32:50 [INFO] train episode 6661: reward = -109.39, steps = 26 04:32:52 [INFO] train episode 6662: reward = -134.72, steps = 26 04:32:57 [INFO] train episode 6663: reward = -147.32, steps = 40 04:32:59 [INFO] train episode 6664: reward = -207.45, steps = 31 04:33:01 [INFO] train episode 6665: reward = -74.87, steps = 20 04:33:04 [INFO] train episode 6666: reward = -163.33, steps = 29 04:33:07 [INFO] train episode 6667: reward = -128.39, steps = 34 04:33:10 [INFO] train episode 6668: reward = -89.47, steps = 33 04:33:14 [INFO] train episode 6669: reward = -179.74, steps = 44 04:33:16 [INFO] train episode 6670: reward = -160.90, steps = 23 04:33:18 [INFO] train episode 6671: reward = -204.83, steps = 26 04:33:21 [INFO] train episode 6672: reward = -273.40, steps = 31 04:33:25 [INFO] train episode 6673: reward = -221.09, steps = 42 04:33:27 [INFO] train episode 6674: reward = -175.99, steps = 34 04:33:29 [INFO] train episode 6675: reward = -115.63, steps = 22 04:33:32 [INFO] train episode 6676: reward = -119.61, steps = 32 04:33:34 [INFO] train episode 6677: reward = -136.96, steps = 19 04:33:36 [INFO] train episode 6678: reward = -115.40, steps = 29 04:33:39 [INFO] train episode 6679: reward = -126.15, steps = 21 04:33:41 [INFO] train episode 6680: reward = -97.93, steps = 23 04:33:43 [INFO] train episode 6681: reward = -182.37, steps = 32 04:33:45 [INFO] train episode 6682: reward = -120.58, steps = 20 04:33:47 [INFO] train episode 6683: reward = -116.78, steps = 20 04:33:49 [INFO] train episode 6684: reward = -120.84, steps = 28 04:33:51 [INFO] train episode 6685: reward = -182.31, steps = 20 04:33:53 [INFO] train episode 6686: reward = -163.08, steps = 27 04:33:57 [INFO] train episode 6687: reward = -124.58, steps = 37 04:34:00 [INFO] train episode 6688: reward = -110.25, steps = 30 04:34:02 [INFO] train episode 6689: reward = -168.31, steps = 29 04:34:04 [INFO] train episode 6690: reward = -119.65, steps = 23 04:34:06 [INFO] train episode 6691: reward = -120.42, steps = 20 04:34:08 [INFO] train episode 6692: reward = -185.20, steps = 24 04:34:10 [INFO] train episode 6693: reward = -128.74, steps = 22 04:34:14 [INFO] train episode 6694: reward = -157.35, steps = 41 04:34:16 [INFO] train episode 6695: reward = -210.19, steps = 21 04:34:17 [INFO] train episode 6696: reward = -195.61, steps = 20 04:34:20 [INFO] train episode 6697: reward = -173.93, steps = 33 04:34:22 [INFO] train episode 6698: reward = -185.93, steps = 23 04:34:25 [INFO] train episode 6699: reward = -89.54, steps = 31 04:34:28 [INFO] train episode 6700: reward = -154.60, steps = 31 04:34:30 [INFO] train episode 6701: reward = -173.83, steps = 27 04:34:33 [INFO] train episode 6702: reward = -189.93, steps = 29 04:34:35 [INFO] train episode 6703: reward = -127.62, steps = 26 04:34:38 [INFO] train episode 6704: reward = -138.41, steps = 30 04:34:41 [INFO] train episode 6705: reward = -200.27, steps = 33 04:34:44 [INFO] train episode 6706: reward = -118.97, steps = 33 04:34:47 [INFO] train episode 6707: reward = -94.43, steps = 30 04:34:49 [INFO] train episode 6708: reward = -244.17, steps = 22 04:34:51 [INFO] train episode 6709: reward = -103.24, steps = 25 04:34:54 [INFO] train episode 6710: reward = -148.33, steps = 37 04:34:56 [INFO] train episode 6711: reward = -209.16, steps = 20 04:34:58 [INFO] train episode 6712: reward = -181.32, steps = 21 04:35:00 [INFO] train episode 6713: reward = -118.43, steps = 23 04:35:02 [INFO] train episode 6714: reward = -123.31, steps = 20 04:35:04 [INFO] train episode 6715: reward = -140.66, steps = 26 04:35:07 [INFO] train episode 6716: reward = -143.34, steps = 33 04:35:09 [INFO] train episode 6717: reward = -158.14, steps = 25 04:35:11 [INFO] train episode 6718: reward = -87.74, steps = 21 04:35:14 [INFO] train episode 6719: reward = -140.05, steps = 34 04:35:17 [INFO] train episode 6720: reward = -139.55, steps = 26 04:35:18 [INFO] train episode 6721: reward = -125.86, steps = 20 04:35:21 [INFO] train episode 6722: reward = -150.40, steps = 31 04:35:24 [INFO] train episode 6723: reward = -154.38, steps = 30 04:35:26 [INFO] train episode 6724: reward = -121.11, steps = 22 04:35:28 [INFO] train episode 6725: reward = -104.16, steps = 23 04:35:29 [INFO] train episode 6726: reward = -133.53, steps = 19 04:35:32 [INFO] train episode 6727: reward = -116.76, steps = 23 04:35:34 [INFO] train episode 6728: reward = -152.19, steps = 26 04:35:36 [INFO] train episode 6729: reward = -168.17, steps = 19 04:35:38 [INFO] train episode 6730: reward = -123.04, steps = 22 04:35:39 [INFO] train episode 6731: reward = -130.96, steps = 19 04:35:44 [INFO] train episode 6732: reward = -270.24, steps = 49 04:35:47 [INFO] train episode 6733: reward = -172.56, steps = 35 04:35:49 [INFO] train episode 6734: reward = -110.43, steps = 22 04:35:51 [INFO] train episode 6735: reward = -152.84, steps = 19 04:35:53 [INFO] train episode 6736: reward = -173.21, steps = 23 04:35:55 [INFO] train episode 6737: reward = -140.00, steps = 24 04:35:58 [INFO] train episode 6738: reward = -165.49, steps = 28 04:36:00 [INFO] train episode 6739: reward = -118.66, steps = 29 04:36:02 [INFO] train episode 6740: reward = -90.95, steps = 22 04:36:05 [INFO] train episode 6741: reward = -151.33, steps = 26 04:36:08 [INFO] train episode 6742: reward = -122.47, steps = 30 04:36:10 [INFO] train episode 6743: reward = -115.14, steps = 24 04:36:12 [INFO] train episode 6744: reward = -153.63, steps = 31 04:36:14 [INFO] train episode 6745: reward = -108.22, steps = 22 04:36:17 [INFO] train episode 6746: reward = -193.99, steps = 31 04:36:19 [INFO] train episode 6747: reward = -186.06, steps = 18 04:36:22 [INFO] train episode 6748: reward = -152.17, steps = 33 04:36:23 [INFO] train episode 6749: reward = -61.82, steps = 20 04:36:26 [INFO] train episode 6750: reward = -94.47, steps = 26 04:36:28 [INFO] train episode 6751: reward = -77.99, steps = 25 04:36:30 [INFO] train episode 6752: reward = -193.27, steps = 24 04:36:32 [INFO] train episode 6753: reward = -172.19, steps = 19 04:36:34 [INFO] train episode 6754: reward = -199.71, steps = 27 04:36:37 [INFO] train episode 6755: reward = -122.91, steps = 22 04:36:39 [INFO] train episode 6756: reward = -207.88, steps = 23 04:36:41 [INFO] train episode 6757: reward = -138.20, steps = 22 04:36:44 [INFO] train episode 6758: reward = -169.43, steps = 38 04:36:47 [INFO] train episode 6759: reward = -151.38, steps = 32 04:36:50 [INFO] train episode 6760: reward = -136.18, steps = 34 04:36:52 [INFO] train episode 6761: reward = -154.23, steps = 28 04:36:57 [INFO] train episode 6762: reward = -223.17, steps = 56 04:37:01 [INFO] train episode 6763: reward = -255.73, steps = 39 04:37:03 [INFO] train episode 6764: reward = -140.27, steps = 34 04:37:06 [INFO] train episode 6765: reward = -218.96, steps = 25 04:37:08 [INFO] train episode 6766: reward = -155.90, steps = 22 04:37:10 [INFO] train episode 6767: reward = -124.12, steps = 19 04:37:13 [INFO] train episode 6768: reward = -177.33, steps = 38 04:37:15 [INFO] train episode 6769: reward = -152.81, steps = 20 04:37:17 [INFO] train episode 6770: reward = -197.42, steps = 23 04:37:19 [INFO] train episode 6771: reward = -89.49, steps = 24 04:37:21 [INFO] train episode 6772: reward = -245.88, steps = 25 04:37:23 [INFO] train episode 6773: reward = -162.89, steps = 25 04:37:26 [INFO] train episode 6774: reward = -128.08, steps = 25 04:37:28 [INFO] train episode 6775: reward = -118.71, steps = 26 04:37:30 [INFO] train episode 6776: reward = -194.88, steps = 28 04:37:33 [INFO] train episode 6777: reward = -81.10, steps = 32 04:37:35 [INFO] train episode 6778: reward = -96.58, steps = 21 04:37:37 [INFO] train episode 6779: reward = -119.13, steps = 26 04:37:40 [INFO] train episode 6780: reward = -170.95, steps = 30 04:37:42 [INFO] train episode 6781: reward = -88.41, steps = 21 04:37:44 [INFO] train episode 6782: reward = -135.57, steps = 18 04:37:46 [INFO] train episode 6783: reward = -195.43, steps = 27 04:37:48 [INFO] train episode 6784: reward = -161.39, steps = 24 04:37:51 [INFO] train episode 6785: reward = -120.23, steps = 34 04:37:53 [INFO] train episode 6786: reward = -233.88, steps = 29 04:37:56 [INFO] train episode 6787: reward = -183.30, steps = 33 04:37:59 [INFO] train episode 6788: reward = -90.26, steps = 24 04:38:02 [INFO] train episode 6789: reward = -129.96, steps = 36 04:38:04 [INFO] train episode 6790: reward = -114.05, steps = 27 04:38:06 [INFO] train episode 6791: reward = -119.76, steps = 22 04:38:08 [INFO] train episode 6792: reward = -130.76, steps = 24 04:38:10 [INFO] train episode 6793: reward = -200.05, steps = 28 04:38:14 [INFO] train episode 6794: reward = -141.03, steps = 34 04:38:16 [INFO] train episode 6795: reward = -96.86, steps = 23 04:38:18 [INFO] train episode 6796: reward = -120.37, steps = 27 04:38:20 [INFO] train episode 6797: reward = -89.71, steps = 23 04:38:22 [INFO] train episode 6798: reward = -125.48, steps = 19 04:38:24 [INFO] train episode 6799: reward = -173.01, steps = 20 04:38:27 [INFO] train episode 6800: reward = -148.47, steps = 37 04:38:29 [INFO] train episode 6801: reward = -104.94, steps = 25 04:38:32 [INFO] train episode 6802: reward = -135.80, steps = 28 04:38:34 [INFO] train episode 6803: reward = -183.94, steps = 26 04:38:36 [INFO] train episode 6804: reward = -126.28, steps = 19 04:38:38 [INFO] train episode 6805: reward = -130.79, steps = 21 04:38:40 [INFO] train episode 6806: reward = -103.16, steps = 24 04:38:43 [INFO] train episode 6807: reward = -236.55, steps = 34 04:38:46 [INFO] train episode 6808: reward = -176.49, steps = 23 04:38:48 [INFO] train episode 6809: reward = -181.81, steps = 30 04:38:51 [INFO] train episode 6810: reward = -163.72, steps = 34 04:38:53 [INFO] train episode 6811: reward = -116.49, steps = 25 04:38:56 [INFO] train episode 6812: reward = -129.44, steps = 31 04:38:58 [INFO] train episode 6813: reward = -108.27, steps = 23 04:39:00 [INFO] train episode 6814: reward = -130.47, steps = 25 04:39:03 [INFO] train episode 6815: reward = -116.17, steps = 24 04:39:04 [INFO] train episode 6816: reward = -119.60, steps = 20 04:39:07 [INFO] train episode 6817: reward = -172.70, steps = 25 04:39:09 [INFO] train episode 6818: reward = -154.98, steps = 33 04:39:11 [INFO] train episode 6819: reward = -132.98, steps = 21 04:39:13 [INFO] train episode 6820: reward = -222.08, steps = 23 04:39:16 [INFO] train episode 6821: reward = -120.88, steps = 30 04:39:19 [INFO] train episode 6822: reward = -118.39, steps = 30 04:39:22 [INFO] train episode 6823: reward = -191.18, steps = 37 04:39:24 [INFO] train episode 6824: reward = -130.88, steps = 26 04:39:26 [INFO] train episode 6825: reward = -144.30, steps = 23 04:39:29 [INFO] train episode 6826: reward = -143.82, steps = 38 04:39:31 [INFO] train episode 6827: reward = -112.95, steps = 19 04:39:34 [INFO] train episode 6828: reward = -138.77, steps = 27 04:39:36 [INFO] train episode 6829: reward = -89.69, steps = 20 04:39:38 [INFO] train episode 6830: reward = -100.60, steps = 30 04:39:41 [INFO] train episode 6831: reward = -188.39, steps = 32 04:39:45 [INFO] train episode 6832: reward = -252.25, steps = 51 04:39:47 [INFO] train episode 6833: reward = -211.97, steps = 18 04:39:51 [INFO] train episode 6834: reward = -249.26, steps = 42 04:39:54 [INFO] train episode 6835: reward = -204.67, steps = 36 04:39:56 [INFO] train episode 6836: reward = -145.05, steps = 24 04:39:58 [INFO] train episode 6837: reward = -206.04, steps = 29 04:40:00 [INFO] train episode 6838: reward = -96.15, steps = 22 04:40:02 [INFO] train episode 6839: reward = -165.27, steps = 21 04:40:04 [INFO] train episode 6840: reward = -128.64, steps = 24 04:40:08 [INFO] train episode 6841: reward = -161.56, steps = 34 04:40:10 [INFO] train episode 6842: reward = -101.00, steps = 23 04:40:12 [INFO] train episode 6843: reward = -104.32, steps = 28 04:40:15 [INFO] train episode 6844: reward = -148.77, steps = 39 04:40:17 [INFO] train episode 6845: reward = -191.10, steps = 23 04:40:19 [INFO] train episode 6846: reward = -253.60, steps = 22 04:40:21 [INFO] train episode 6847: reward = -97.15, steps = 24 04:40:24 [INFO] train episode 6848: reward = -137.02, steps = 27 04:40:26 [INFO] train episode 6849: reward = -117.08, steps = 23 04:40:28 [INFO] train episode 6850: reward = -156.02, steps = 24 04:40:30 [INFO] train episode 6851: reward = -118.85, steps = 27 04:40:33 [INFO] train episode 6852: reward = -101.01, steps = 29 04:40:35 [INFO] train episode 6853: reward = -140.40, steps = 23 04:40:37 [INFO] train episode 6854: reward = -152.40, steps = 21 04:40:39 [INFO] train episode 6855: reward = -204.84, steps = 22 04:40:41 [INFO] train episode 6856: reward = -148.23, steps = 24 04:40:45 [INFO] train episode 6857: reward = -273.78, steps = 50 04:40:47 [INFO] train episode 6858: reward = -131.55, steps = 19 04:40:49 [INFO] train episode 6859: reward = -86.84, steps = 25 04:40:52 [INFO] train episode 6860: reward = -111.72, steps = 33 04:40:55 [INFO] train episode 6861: reward = -136.78, steps = 26 04:40:57 [INFO] train episode 6862: reward = -170.02, steps = 22 04:40:59 [INFO] train episode 6863: reward = -131.87, steps = 23 04:41:03 [INFO] train episode 6864: reward = -188.35, steps = 48 04:41:05 [INFO] train episode 6865: reward = -145.02, steps = 20 04:41:07 [INFO] train episode 6866: reward = -115.66, steps = 28 04:41:09 [INFO] train episode 6867: reward = -173.70, steps = 26 04:41:12 [INFO] train episode 6868: reward = -98.51, steps = 29 04:41:16 [INFO] train episode 6869: reward = -185.07, steps = 52 04:41:18 [INFO] train episode 6870: reward = -143.82, steps = 18 04:41:20 [INFO] train episode 6871: reward = -212.76, steps = 25 04:41:22 [INFO] train episode 6872: reward = -101.61, steps = 24 04:41:25 [INFO] train episode 6873: reward = -122.71, steps = 32 04:41:27 [INFO] train episode 6874: reward = -139.93, steps = 23 04:41:29 [INFO] train episode 6875: reward = -166.80, steps = 21 04:41:31 [INFO] train episode 6876: reward = -215.60, steps = 19 04:41:34 [INFO] train episode 6877: reward = -91.93, steps = 32 04:41:35 [INFO] train episode 6878: reward = -144.27, steps = 18 04:41:38 [INFO] train episode 6879: reward = -317.74, steps = 24 04:41:40 [INFO] train episode 6880: reward = -151.29, steps = 25 04:41:43 [INFO] train episode 6881: reward = -105.40, steps = 23 04:41:44 [INFO] train episode 6882: reward = -172.73, steps = 21 04:41:47 [INFO] train episode 6883: reward = -237.51, steps = 26 04:41:49 [INFO] train episode 6884: reward = -151.49, steps = 30 04:41:53 [INFO] train episode 6885: reward = -184.01, steps = 38 04:41:54 [INFO] train episode 6886: reward = -130.68, steps = 22 04:41:56 [INFO] train episode 6887: reward = -156.68, steps = 22 04:41:59 [INFO] train episode 6888: reward = -135.43, steps = 32 04:42:02 [INFO] train episode 6889: reward = -142.92, steps = 28 04:42:05 [INFO] train episode 6890: reward = -215.13, steps = 39 04:42:07 [INFO] train episode 6891: reward = -87.84, steps = 20 04:42:09 [INFO] train episode 6892: reward = -119.21, steps = 22 04:42:11 [INFO] train episode 6893: reward = -107.99, steps = 21 04:42:13 [INFO] train episode 6894: reward = -126.28, steps = 26 04:42:16 [INFO] train episode 6895: reward = -136.34, steps = 31 04:42:18 [INFO] train episode 6896: reward = -149.98, steps = 25 04:42:22 [INFO] train episode 6897: reward = -169.81, steps = 39 04:42:24 [INFO] train episode 6898: reward = -79.22, steps = 24 04:42:26 [INFO] train episode 6899: reward = -121.49, steps = 22 04:42:27 [INFO] train episode 6900: reward = -155.83, steps = 21 04:42:30 [INFO] train episode 6901: reward = -107.55, steps = 26 04:42:32 [INFO] train episode 6902: reward = -177.90, steps = 22 04:42:34 [INFO] train episode 6903: reward = -140.70, steps = 24 04:42:36 [INFO] train episode 6904: reward = -117.96, steps = 26 04:42:39 [INFO] train episode 6905: reward = -153.85, steps = 31 04:42:41 [INFO] train episode 6906: reward = -113.31, steps = 27 04:42:43 [INFO] train episode 6907: reward = -100.75, steps = 24 04:42:45 [INFO] train episode 6908: reward = -128.15, steps = 24 04:42:48 [INFO] train episode 6909: reward = -161.93, steps = 23 04:42:50 [INFO] train episode 6910: reward = -148.17, steps = 24 04:42:52 [INFO] train episode 6911: reward = -153.76, steps = 28 04:42:54 [INFO] train episode 6912: reward = -117.25, steps = 20 04:42:57 [INFO] train episode 6913: reward = -101.85, steps = 33 04:42:59 [INFO] train episode 6914: reward = -118.23, steps = 28 04:43:01 [INFO] train episode 6915: reward = -166.26, steps = 27 04:43:04 [INFO] train episode 6916: reward = -282.22, steps = 25 04:43:06 [INFO] train episode 6917: reward = -124.90, steps = 24 04:43:10 [INFO] train episode 6918: reward = -210.80, steps = 46 04:43:12 [INFO] train episode 6919: reward = -185.79, steps = 24 04:43:15 [INFO] train episode 6920: reward = -188.72, steps = 33 04:43:17 [INFO] train episode 6921: reward = -129.92, steps = 28 04:43:21 [INFO] train episode 6922: reward = -207.37, steps = 42 04:43:23 [INFO] train episode 6923: reward = -64.46, steps = 20 04:43:25 [INFO] train episode 6924: reward = -101.18, steps = 23 04:43:27 [INFO] train episode 6925: reward = -108.45, steps = 25 04:43:29 [INFO] train episode 6926: reward = -102.69, steps = 22 04:43:31 [INFO] train episode 6927: reward = -126.90, steps = 30 04:43:34 [INFO] train episode 6928: reward = -113.98, steps = 28 04:43:36 [INFO] train episode 6929: reward = -105.98, steps = 19 04:43:38 [INFO] train episode 6930: reward = -118.91, steps = 21 04:43:40 [INFO] train episode 6931: reward = -84.21, steps = 24 04:43:42 [INFO] train episode 6932: reward = -142.75, steps = 21 04:43:44 [INFO] train episode 6933: reward = -112.25, steps = 25 04:43:47 [INFO] train episode 6934: reward = -84.08, steps = 36 04:43:49 [INFO] train episode 6935: reward = -134.04, steps = 20 04:43:51 [INFO] train episode 6936: reward = -125.60, steps = 26 04:43:53 [INFO] train episode 6937: reward = -264.17, steps = 24 04:43:56 [INFO] train episode 6938: reward = -154.21, steps = 33 04:43:58 [INFO] train episode 6939: reward = -101.90, steps = 21 04:44:01 [INFO] train episode 6940: reward = -182.98, steps = 40 04:44:04 [INFO] train episode 6941: reward = -152.83, steps = 36 04:44:07 [INFO] train episode 6942: reward = -105.11, steps = 28 04:44:10 [INFO] train episode 6943: reward = -163.32, steps = 38 04:44:14 [INFO] train episode 6944: reward = -148.03, steps = 36 04:44:15 [INFO] train episode 6945: reward = -108.26, steps = 21 04:44:17 [INFO] train episode 6946: reward = -142.21, steps = 19 04:44:19 [INFO] train episode 6947: reward = -130.79, steps = 23 04:44:22 [INFO] train episode 6948: reward = -95.50, steps = 26 04:44:24 [INFO] train episode 6949: reward = -128.91, steps = 28 04:44:27 [INFO] train episode 6950: reward = -107.30, steps = 29 04:44:30 [INFO] train episode 6951: reward = -157.02, steps = 26 04:44:32 [INFO] train episode 6952: reward = -145.08, steps = 28 04:44:35 [INFO] train episode 6953: reward = -285.93, steps = 32 04:44:37 [INFO] train episode 6954: reward = -179.58, steps = 28 04:44:39 [INFO] train episode 6955: reward = -99.60, steps = 20 04:44:41 [INFO] train episode 6956: reward = -74.70, steps = 20 04:44:43 [INFO] train episode 6957: reward = -121.60, steps = 25 04:44:45 [INFO] train episode 6958: reward = -92.49, steps = 23 04:44:47 [INFO] train episode 6959: reward = -110.52, steps = 24 04:44:50 [INFO] train episode 6960: reward = -145.69, steps = 28 04:44:52 [INFO] train episode 6961: reward = -86.59, steps = 26 04:44:55 [INFO] train episode 6962: reward = -163.75, steps = 28 04:44:57 [INFO] train episode 6963: reward = -150.32, steps = 19 04:44:59 [INFO] train episode 6964: reward = -126.48, steps = 21 04:45:01 [INFO] train episode 6965: reward = -82.77, steps = 24 04:45:04 [INFO] train episode 6966: reward = -150.76, steps = 40 04:45:06 [INFO] train episode 6967: reward = -88.25, steps = 21 04:45:08 [INFO] train episode 6968: reward = -123.09, steps = 25 04:45:10 [INFO] train episode 6969: reward = -141.16, steps = 18 04:45:13 [INFO] train episode 6970: reward = -205.51, steps = 34 04:45:16 [INFO] train episode 6971: reward = -166.80, steps = 32 04:45:18 [INFO] train episode 6972: reward = -154.53, steps = 22 04:45:20 [INFO] train episode 6973: reward = -101.23, steps = 23 04:45:22 [INFO] train episode 6974: reward = -83.53, steps = 20 04:45:23 [INFO] train episode 6975: reward = -109.67, steps = 20 04:45:26 [INFO] train episode 6976: reward = -135.35, steps = 26 04:45:29 [INFO] train episode 6977: reward = -170.80, steps = 32 04:45:31 [INFO] train episode 6978: reward = -140.62, steps = 22 04:45:33 [INFO] train episode 6979: reward = -103.47, steps = 32 04:45:35 [INFO] train episode 6980: reward = -92.98, steps = 21 04:45:37 [INFO] train episode 6981: reward = -114.17, steps = 22 04:45:40 [INFO] train episode 6982: reward = -103.63, steps = 30 04:45:42 [INFO] train episode 6983: reward = -134.67, steps = 23 04:45:44 [INFO] train episode 6984: reward = -143.72, steps = 26 04:45:46 [INFO] train episode 6985: reward = -153.69, steps = 23 04:45:49 [INFO] train episode 6986: reward = -174.70, steps = 25 04:45:51 [INFO] train episode 6987: reward = -128.05, steps = 26 04:45:53 [INFO] train episode 6988: reward = -160.53, steps = 20 04:45:55 [INFO] train episode 6989: reward = -148.36, steps = 24 04:45:57 [INFO] train episode 6990: reward = -77.07, steps = 22 04:45:59 [INFO] train episode 6991: reward = -130.31, steps = 20 04:46:01 [INFO] train episode 6992: reward = -109.87, steps = 23 04:46:03 [INFO] train episode 6993: reward = -176.27, steps = 26 04:46:06 [INFO] train episode 6994: reward = -123.93, steps = 35 04:46:09 [INFO] train episode 6995: reward = -132.91, steps = 30 04:46:11 [INFO] train episode 6996: reward = -162.56, steps = 27 04:46:13 [INFO] train episode 6997: reward = -136.36, steps = 24 04:46:15 [INFO] train episode 6998: reward = -176.40, steps = 23 04:46:18 [INFO] train episode 6999: reward = -138.41, steps = 27 04:46:20 [INFO] train episode 7000: reward = -138.02, steps = 25 04:46:22 [INFO] train episode 7001: reward = -150.43, steps = 19 04:46:24 [INFO] train episode 7002: reward = -175.04, steps = 23 04:46:26 [INFO] train episode 7003: reward = -101.33, steps = 25 04:46:28 [INFO] train episode 7004: reward = -145.29, steps = 21 04:46:29 [INFO] train episode 7005: reward = -105.53, steps = 19 04:46:33 [INFO] train episode 7006: reward = -144.79, steps = 33 04:46:35 [INFO] train episode 7007: reward = -123.19, steps = 24 04:46:37 [INFO] train episode 7008: reward = -190.46, steps = 30 04:46:39 [INFO] train episode 7009: reward = -119.84, steps = 22 04:46:41 [INFO] train episode 7010: reward = -108.42, steps = 19 04:46:43 [INFO] train episode 7011: reward = -148.54, steps = 25 04:46:45 [INFO] train episode 7012: reward = -75.68, steps = 19 04:46:47 [INFO] train episode 7013: reward = -115.21, steps = 25 04:46:50 [INFO] train episode 7014: reward = -161.73, steps = 29 04:46:52 [INFO] train episode 7015: reward = -105.37, steps = 28 04:46:55 [INFO] train episode 7016: reward = -136.59, steps = 27 04:46:57 [INFO] train episode 7017: reward = -93.28, steps = 32 04:47:00 [INFO] train episode 7018: reward = -154.68, steps = 27 04:47:01 [INFO] train episode 7019: reward = -180.34, steps = 21 04:47:04 [INFO] train episode 7020: reward = -176.54, steps = 24 04:47:07 [INFO] train episode 7021: reward = -101.90, steps = 27 04:47:10 [INFO] train episode 7022: reward = -175.09, steps = 33 04:47:12 [INFO] train episode 7023: reward = -115.50, steps = 25 04:47:14 [INFO] train episode 7024: reward = -173.36, steps = 20 04:47:17 [INFO] train episode 7025: reward = -180.70, steps = 31 04:47:20 [INFO] train episode 7026: reward = -97.94, steps = 29 04:47:22 [INFO] train episode 7027: reward = -100.50, steps = 21 04:47:24 [INFO] train episode 7028: reward = -155.17, steps = 23 04:47:26 [INFO] train episode 7029: reward = -82.65, steps = 20 04:47:28 [INFO] train episode 7030: reward = -96.22, steps = 20 04:47:30 [INFO] train episode 7031: reward = -108.36, steps = 23 04:47:32 [INFO] train episode 7032: reward = -159.69, steps = 20 04:47:34 [INFO] train episode 7033: reward = -119.13, steps = 21 04:47:36 [INFO] train episode 7034: reward = -178.53, steps = 25 04:47:38 [INFO] train episode 7035: reward = -152.67, steps = 25 04:47:40 [INFO] train episode 7036: reward = -140.77, steps = 20 04:47:43 [INFO] train episode 7037: reward = -180.67, steps = 33 04:47:45 [INFO] train episode 7038: reward = -155.29, steps = 27 04:47:47 [INFO] train episode 7039: reward = -131.30, steps = 19 04:47:49 [INFO] train episode 7040: reward = -152.33, steps = 24 04:47:51 [INFO] train episode 7041: reward = -179.06, steps = 21 04:47:53 [INFO] train episode 7042: reward = -154.13, steps = 22 04:47:55 [INFO] train episode 7043: reward = -113.42, steps = 26 04:47:57 [INFO] train episode 7044: reward = -131.07, steps = 21 04:47:59 [INFO] train episode 7045: reward = -131.71, steps = 26 04:48:02 [INFO] train episode 7046: reward = -207.46, steps = 27 04:48:04 [INFO] train episode 7047: reward = -116.90, steps = 26 04:48:07 [INFO] train episode 7048: reward = -123.43, steps = 32 04:48:10 [INFO] train episode 7049: reward = -110.14, steps = 33 04:48:12 [INFO] train episode 7050: reward = -109.80, steps = 20 04:48:14 [INFO] train episode 7051: reward = -135.34, steps = 25 04:48:16 [INFO] train episode 7052: reward = -121.30, steps = 18 04:48:17 [INFO] train episode 7053: reward = -83.99, steps = 19 04:48:19 [INFO] train episode 7054: reward = -94.05, steps = 25 04:48:22 [INFO] train episode 7055: reward = -111.41, steps = 27 04:48:24 [INFO] train episode 7056: reward = -139.44, steps = 22 04:48:27 [INFO] train episode 7057: reward = -162.14, steps = 39 04:48:29 [INFO] train episode 7058: reward = -100.44, steps = 21 04:48:31 [INFO] train episode 7059: reward = -115.83, steps = 22 04:48:33 [INFO] train episode 7060: reward = -124.88, steps = 18 04:48:35 [INFO] train episode 7061: reward = -90.44, steps = 21 04:48:37 [INFO] train episode 7062: reward = -174.11, steps = 26 04:48:39 [INFO] train episode 7063: reward = -165.79, steps = 23 04:48:41 [INFO] train episode 7064: reward = -104.41, steps = 19 04:48:43 [INFO] train episode 7065: reward = -138.16, steps = 24 04:48:45 [INFO] train episode 7066: reward = -82.11, steps = 24 04:48:47 [INFO] train episode 7067: reward = -94.49, steps = 21 04:48:50 [INFO] train episode 7068: reward = -131.94, steps = 31 04:48:51 [INFO] train episode 7069: reward = -166.24, steps = 22 04:48:54 [INFO] train episode 7070: reward = -165.30, steps = 26 04:48:56 [INFO] train episode 7071: reward = -109.09, steps = 26 04:48:58 [INFO] train episode 7072: reward = -140.01, steps = 21 04:49:01 [INFO] train episode 7073: reward = -193.18, steps = 28 04:49:02 [INFO] train episode 7074: reward = -117.84, steps = 21 04:49:04 [INFO] train episode 7075: reward = -105.91, steps = 22 04:49:07 [INFO] train episode 7076: reward = -105.08, steps = 28 04:49:08 [INFO] train episode 7077: reward = -110.51, steps = 20 04:49:10 [INFO] train episode 7078: reward = -170.52, steps = 19 04:49:12 [INFO] train episode 7079: reward = -89.48, steps = 21 04:49:14 [INFO] train episode 7080: reward = -184.25, steps = 23 04:49:17 [INFO] train episode 7081: reward = -116.51, steps = 25 04:49:19 [INFO] train episode 7082: reward = -162.24, steps = 27 04:49:21 [INFO] train episode 7083: reward = -96.80, steps = 19 04:49:23 [INFO] train episode 7084: reward = -134.93, steps = 26 04:49:25 [INFO] train episode 7085: reward = -114.01, steps = 23 04:49:28 [INFO] train episode 7086: reward = -154.10, steps = 36 04:49:30 [INFO] train episode 7087: reward = -157.88, steps = 24 04:49:34 [INFO] train episode 7088: reward = -203.43, steps = 41 04:49:37 [INFO] train episode 7089: reward = -141.01, steps = 35 04:49:40 [INFO] train episode 7090: reward = -120.64, steps = 40 04:49:42 [INFO] train episode 7091: reward = -294.44, steps = 20 04:49:44 [INFO] train episode 7092: reward = -92.51, steps = 22 04:49:46 [INFO] train episode 7093: reward = -121.86, steps = 23 04:49:49 [INFO] train episode 7094: reward = -134.92, steps = 29 04:49:51 [INFO] train episode 7095: reward = -135.50, steps = 23 04:49:54 [INFO] train episode 7096: reward = -111.61, steps = 41 04:49:57 [INFO] train episode 7097: reward = -157.70, steps = 25 04:49:59 [INFO] train episode 7098: reward = -166.60, steps = 21 04:50:02 [INFO] train episode 7099: reward = -180.30, steps = 36 04:50:04 [INFO] train episode 7100: reward = -117.94, steps = 22 04:50:08 [INFO] train episode 7101: reward = -172.66, steps = 39 04:50:11 [INFO] train episode 7102: reward = -101.86, steps = 29 04:50:13 [INFO] train episode 7103: reward = -120.24, steps = 30 04:50:16 [INFO] train episode 7104: reward = -118.75, steps = 30 04:50:19 [INFO] train episode 7105: reward = -121.11, steps = 22 04:50:22 [INFO] train episode 7106: reward = -162.88, steps = 26 04:50:25 [INFO] train episode 7107: reward = -148.25, steps = 34 04:50:27 [INFO] train episode 7108: reward = -151.64, steps = 22 04:50:31 [INFO] train episode 7109: reward = -146.66, steps = 48 04:50:38 [INFO] train episode 7110: reward = -239.01, steps = 66 04:50:41 [INFO] train episode 7111: reward = -113.74, steps = 31 04:50:43 [INFO] train episode 7112: reward = -160.48, steps = 23 04:50:45 [INFO] train episode 7113: reward = -122.94, steps = 21 04:50:47 [INFO] train episode 7114: reward = -190.74, steps = 27 04:50:51 [INFO] train episode 7115: reward = -124.80, steps = 43 04:50:54 [INFO] train episode 7116: reward = -127.67, steps = 27 04:50:56 [INFO] train episode 7117: reward = -136.53, steps = 21 04:50:58 [INFO] train episode 7118: reward = -73.11, steps = 28 04:51:01 [INFO] train episode 7119: reward = -166.00, steps = 25 04:51:03 [INFO] train episode 7120: reward = -112.74, steps = 19 04:51:05 [INFO] train episode 7121: reward = -116.68, steps = 26 04:51:07 [INFO] train episode 7122: reward = -107.48, steps = 26 04:51:11 [INFO] train episode 7123: reward = -103.82, steps = 29 04:51:13 [INFO] train episode 7124: reward = -137.05, steps = 24 04:51:16 [INFO] train episode 7125: reward = -175.01, steps = 31 04:51:18 [INFO] train episode 7126: reward = -74.46, steps = 22 04:51:20 [INFO] train episode 7127: reward = -76.86, steps = 21 04:51:22 [INFO] train episode 7128: reward = -81.39, steps = 20 04:51:25 [INFO] train episode 7129: reward = -107.26, steps = 27 04:51:27 [INFO] train episode 7130: reward = -155.00, steps = 22 04:51:29 [INFO] train episode 7131: reward = -124.33, steps = 22 04:51:32 [INFO] train episode 7132: reward = -147.76, steps = 30 04:51:35 [INFO] train episode 7133: reward = -117.56, steps = 29 04:51:37 [INFO] train episode 7134: reward = -126.75, steps = 26 04:51:41 [INFO] train episode 7135: reward = -140.16, steps = 39 04:51:43 [INFO] train episode 7136: reward = -170.34, steps = 25 04:51:46 [INFO] train episode 7137: reward = -144.09, steps = 25 04:51:48 [INFO] train episode 7138: reward = -115.51, steps = 26 04:51:50 [INFO] train episode 7139: reward = -113.18, steps = 25 04:51:52 [INFO] train episode 7140: reward = -86.37, steps = 22 04:51:56 [INFO] train episode 7141: reward = -113.55, steps = 36 04:51:58 [INFO] train episode 7142: reward = -93.86, steps = 22 04:52:01 [INFO] train episode 7143: reward = -142.57, steps = 37 04:52:04 [INFO] train episode 7144: reward = -134.89, steps = 37 04:52:06 [INFO] train episode 7145: reward = -115.85, steps = 22 04:52:08 [INFO] train episode 7146: reward = -145.15, steps = 22 04:52:10 [INFO] train episode 7147: reward = -85.12, steps = 20 04:52:13 [INFO] train episode 7148: reward = -141.94, steps = 27 04:52:15 [INFO] train episode 7149: reward = -122.89, steps = 25 04:52:17 [INFO] train episode 7150: reward = -121.15, steps = 23 04:52:20 [INFO] train episode 7151: reward = -135.75, steps = 33 04:52:22 [INFO] train episode 7152: reward = -122.38, steps = 27 04:52:24 [INFO] train episode 7153: reward = -119.33, steps = 24 04:52:27 [INFO] train episode 7154: reward = -159.04, steps = 25 04:52:29 [INFO] train episode 7155: reward = -150.70, steps = 23 04:52:32 [INFO] train episode 7156: reward = -214.92, steps = 41 04:52:35 [INFO] train episode 7157: reward = -179.61, steps = 30 04:52:37 [INFO] train episode 7158: reward = -224.53, steps = 25 04:52:41 [INFO] train episode 7159: reward = -165.17, steps = 45 04:52:44 [INFO] train episode 7160: reward = -130.50, steps = 29 04:52:46 [INFO] train episode 7161: reward = -162.83, steps = 31 04:52:48 [INFO] train episode 7162: reward = -118.94, steps = 20 04:52:50 [INFO] train episode 7163: reward = -101.14, steps = 27 04:52:54 [INFO] train episode 7164: reward = -146.35, steps = 36 04:52:57 [INFO] train episode 7165: reward = -160.57, steps = 40 04:52:59 [INFO] train episode 7166: reward = -70.43, steps = 19 04:53:01 [INFO] train episode 7167: reward = -113.10, steps = 21 04:53:03 [INFO] train episode 7168: reward = -145.57, steps = 27 04:53:05 [INFO] train episode 7169: reward = -100.27, steps = 19 04:53:06 [INFO] train episode 7170: reward = -115.53, steps = 19 04:53:10 [INFO] train episode 7171: reward = -156.27, steps = 34 04:53:12 [INFO] train episode 7172: reward = -96.55, steps = 23 04:53:13 [INFO] train episode 7173: reward = -112.96, steps = 21 04:53:15 [INFO] train episode 7174: reward = -87.45, steps = 21 04:53:18 [INFO] train episode 7175: reward = -211.14, steps = 25 04:53:20 [INFO] train episode 7176: reward = -71.83, steps = 26 04:53:23 [INFO] train episode 7177: reward = -130.44, steps = 30 04:53:26 [INFO] train episode 7178: reward = -138.42, steps = 28 04:53:28 [INFO] train episode 7179: reward = -68.13, steps = 23 04:53:30 [INFO] train episode 7180: reward = -143.61, steps = 20 04:53:32 [INFO] train episode 7181: reward = -139.69, steps = 27 04:53:35 [INFO] train episode 7182: reward = -136.02, steps = 33 04:53:37 [INFO] train episode 7183: reward = -160.79, steps = 21 04:53:39 [INFO] train episode 7184: reward = -142.08, steps = 28 04:53:41 [INFO] train episode 7185: reward = -131.89, steps = 23 04:53:44 [INFO] train episode 7186: reward = -152.08, steps = 34 04:53:47 [INFO] train episode 7187: reward = -142.84, steps = 28 04:53:49 [INFO] train episode 7188: reward = -86.01, steps = 31 04:53:53 [INFO] train episode 7189: reward = -136.75, steps = 38 04:53:56 [INFO] train episode 7190: reward = -166.12, steps = 32 04:53:58 [INFO] train episode 7191: reward = -109.41, steps = 21 04:54:00 [INFO] train episode 7192: reward = -139.35, steps = 23 04:54:03 [INFO] train episode 7193: reward = -108.19, steps = 34 04:54:04 [INFO] train episode 7194: reward = -141.97, steps = 21 04:54:08 [INFO] train episode 7195: reward = -301.73, steps = 39 04:54:10 [INFO] train episode 7196: reward = -122.13, steps = 29 04:54:13 [INFO] train episode 7197: reward = -165.82, steps = 28 04:54:15 [INFO] train episode 7198: reward = -133.82, steps = 21 04:54:17 [INFO] train episode 7199: reward = -94.62, steps = 27 04:54:20 [INFO] train episode 7200: reward = -105.07, steps = 36 04:54:22 [INFO] train episode 7201: reward = -132.66, steps = 20 04:54:24 [INFO] train episode 7202: reward = -157.75, steps = 29 04:54:26 [INFO] train episode 7203: reward = -175.86, steps = 22 04:54:29 [INFO] train episode 7204: reward = -202.27, steps = 27 04:54:32 [INFO] train episode 7205: reward = -124.28, steps = 34 04:54:34 [INFO] train episode 7206: reward = -91.98, steps = 20 04:54:36 [INFO] train episode 7207: reward = -103.45, steps = 21 04:54:39 [INFO] train episode 7208: reward = -163.55, steps = 36 04:54:40 [INFO] train episode 7209: reward = -109.20, steps = 19 04:54:43 [INFO] train episode 7210: reward = -143.99, steps = 29 04:54:45 [INFO] train episode 7211: reward = -184.65, steps = 22 04:54:47 [INFO] train episode 7212: reward = -75.23, steps = 21 04:54:50 [INFO] train episode 7213: reward = -129.72, steps = 33 04:54:52 [INFO] train episode 7214: reward = -129.06, steps = 24 04:54:54 [INFO] train episode 7215: reward = -131.89, steps = 21 04:54:55 [INFO] train episode 7216: reward = -81.14, steps = 21 04:54:58 [INFO] train episode 7217: reward = -103.10, steps = 27 04:55:00 [INFO] train episode 7218: reward = -116.15, steps = 25 04:55:03 [INFO] train episode 7219: reward = -115.57, steps = 28 04:55:05 [INFO] train episode 7220: reward = -74.96, steps = 20 04:55:06 [INFO] train episode 7221: reward = -135.30, steps = 22 04:55:09 [INFO] train episode 7222: reward = -130.42, steps = 30 04:55:12 [INFO] train episode 7223: reward = -125.59, steps = 32 04:55:13 [INFO] train episode 7224: reward = -85.23, steps = 19 04:55:16 [INFO] train episode 7225: reward = -74.37, steps = 21 04:55:17 [INFO] train episode 7226: reward = -84.04, steps = 19 04:55:19 [INFO] train episode 7227: reward = -156.67, steps = 24 04:55:22 [INFO] train episode 7228: reward = -129.67, steps = 26 04:55:23 [INFO] train episode 7229: reward = -140.60, steps = 19 04:55:25 [INFO] train episode 7230: reward = -114.27, steps = 22 04:55:28 [INFO] train episode 7231: reward = -175.46, steps = 26 04:55:30 [INFO] train episode 7232: reward = -117.04, steps = 25 04:55:32 [INFO] train episode 7233: reward = -126.50, steps = 24 04:55:35 [INFO] train episode 7234: reward = -112.34, steps = 31 04:55:37 [INFO] train episode 7235: reward = -180.90, steps = 20 04:55:39 [INFO] train episode 7236: reward = -110.53, steps = 24 04:55:41 [INFO] train episode 7237: reward = -110.25, steps = 24 04:55:43 [INFO] train episode 7238: reward = -148.08, steps = 22 04:55:45 [INFO] train episode 7239: reward = -138.13, steps = 24 04:55:48 [INFO] train episode 7240: reward = -121.86, steps = 28 04:55:50 [INFO] train episode 7241: reward = -86.98, steps = 24 04:55:52 [INFO] train episode 7242: reward = -103.64, steps = 25 04:55:54 [INFO] train episode 7243: reward = -142.70, steps = 20 04:55:55 [INFO] train episode 7244: reward = -135.11, steps = 21 04:55:58 [INFO] train episode 7245: reward = -185.12, steps = 26 04:55:59 [INFO] train episode 7246: reward = -112.28, steps = 22 04:56:02 [INFO] train episode 7247: reward = -95.20, steps = 25 04:56:05 [INFO] train episode 7248: reward = -179.08, steps = 34 04:56:07 [INFO] train episode 7249: reward = -82.24, steps = 19 04:56:10 [INFO] train episode 7250: reward = -135.91, steps = 28 04:56:13 [INFO] train episode 7251: reward = -160.24, steps = 38 04:56:15 [INFO] train episode 7252: reward = -91.42, steps = 27 04:56:18 [INFO] train episode 7253: reward = -112.32, steps = 31 04:56:21 [INFO] train episode 7254: reward = -133.39, steps = 29 04:56:23 [INFO] train episode 7255: reward = -109.72, steps = 24 04:56:25 [INFO] train episode 7256: reward = -151.01, steps = 22 04:56:28 [INFO] train episode 7257: reward = -121.53, steps = 32 04:56:29 [INFO] train episode 7258: reward = -138.91, steps = 21 04:56:32 [INFO] train episode 7259: reward = -128.63, steps = 27 04:56:34 [INFO] train episode 7260: reward = -118.97, steps = 24 04:56:36 [INFO] train episode 7261: reward = -161.23, steps = 22 04:56:39 [INFO] train episode 7262: reward = -120.71, steps = 27 04:56:40 [INFO] train episode 7263: reward = -107.82, steps = 19 04:56:42 [INFO] train episode 7264: reward = -153.31, steps = 24 04:56:44 [INFO] train episode 7265: reward = -83.54, steps = 24 04:56:46 [INFO] train episode 7266: reward = -84.66, steps = 24 04:56:48 [INFO] train episode 7267: reward = -92.51, steps = 22 04:56:51 [INFO] train episode 7268: reward = -136.56, steps = 27 04:56:53 [INFO] train episode 7269: reward = -174.49, steps = 26 04:56:56 [INFO] train episode 7270: reward = -193.28, steps = 28 04:56:58 [INFO] train episode 7271: reward = -83.58, steps = 26 04:57:01 [INFO] train episode 7272: reward = -120.57, steps = 33 04:57:04 [INFO] train episode 7273: reward = -133.78, steps = 35 04:57:07 [INFO] train episode 7274: reward = -92.29, steps = 32 04:57:10 [INFO] train episode 7275: reward = -88.86, steps = 31 04:57:13 [INFO] train episode 7276: reward = -176.22, steps = 34 04:57:15 [INFO] train episode 7277: reward = -109.01, steps = 22 04:57:16 [INFO] train episode 7278: reward = -125.97, steps = 20 04:57:19 [INFO] train episode 7279: reward = -163.35, steps = 29 04:57:21 [INFO] train episode 7280: reward = -139.87, steps = 24 04:57:23 [INFO] train episode 7281: reward = -129.83, steps = 27 04:57:26 [INFO] train episode 7282: reward = -111.63, steps = 21 04:57:29 [INFO] train episode 7283: reward = -151.69, steps = 35 04:57:31 [INFO] train episode 7284: reward = -104.89, steps = 25 04:57:33 [INFO] train episode 7285: reward = -120.91, steps = 25 04:57:35 [INFO] train episode 7286: reward = -108.64, steps = 30 04:57:37 [INFO] train episode 7287: reward = -151.22, steps = 21 04:57:41 [INFO] train episode 7288: reward = -153.92, steps = 39 04:57:43 [INFO] train episode 7289: reward = -199.88, steps = 25 04:57:45 [INFO] train episode 7290: reward = -124.69, steps = 21 04:57:47 [INFO] train episode 7291: reward = -154.97, steps = 21 04:57:49 [INFO] train episode 7292: reward = -129.93, steps = 20 04:57:52 [INFO] train episode 7293: reward = -140.92, steps = 35 04:57:54 [INFO] train episode 7294: reward = -140.09, steps = 27 04:57:57 [INFO] train episode 7295: reward = -116.88, steps = 31 04:57:59 [INFO] train episode 7296: reward = -128.52, steps = 21 04:58:02 [INFO] train episode 7297: reward = -121.49, steps = 35 04:58:04 [INFO] train episode 7298: reward = -119.20, steps = 20 04:58:06 [INFO] train episode 7299: reward = -133.52, steps = 30 04:58:08 [INFO] train episode 7300: reward = -140.49, steps = 25 04:58:11 [INFO] train episode 7301: reward = -163.46, steps = 32 04:58:13 [INFO] train episode 7302: reward = -136.18, steps = 25 04:58:17 [INFO] train episode 7303: reward = -172.75, steps = 36 04:58:18 [INFO] train episode 7304: reward = -144.66, steps = 21 04:58:21 [INFO] train episode 7305: reward = -125.94, steps = 31 04:58:23 [INFO] train episode 7306: reward = -235.42, steps = 23 04:58:25 [INFO] train episode 7307: reward = -126.78, steps = 26 04:58:28 [INFO] train episode 7308: reward = -117.87, steps = 32 04:58:32 [INFO] train episode 7309: reward = -141.01, steps = 40 04:58:34 [INFO] train episode 7310: reward = -132.59, steps = 22 04:58:36 [INFO] train episode 7311: reward = -137.46, steps = 31 04:58:39 [INFO] train episode 7312: reward = -121.67, steps = 26 04:58:41 [INFO] train episode 7313: reward = -127.87, steps = 24 04:58:43 [INFO] train episode 7314: reward = -120.09, steps = 27 04:58:46 [INFO] train episode 7315: reward = -200.24, steps = 26 04:58:48 [INFO] train episode 7316: reward = -88.47, steps = 21 04:58:50 [INFO] train episode 7317: reward = -122.36, steps = 25 04:58:52 [INFO] train episode 7318: reward = -168.90, steps = 29 04:58:55 [INFO] train episode 7319: reward = -116.67, steps = 33 04:58:58 [INFO] train episode 7320: reward = -157.65, steps = 33 04:59:00 [INFO] train episode 7321: reward = -83.82, steps = 21 04:59:03 [INFO] train episode 7322: reward = -182.93, steps = 27 04:59:06 [INFO] train episode 7323: reward = -168.04, steps = 37 04:59:08 [INFO] train episode 7324: reward = -121.09, steps = 23 04:59:11 [INFO] train episode 7325: reward = -130.43, steps = 29 04:59:14 [INFO] train episode 7326: reward = -150.07, steps = 37 04:59:16 [INFO] train episode 7327: reward = -155.39, steps = 23 04:59:18 [INFO] train episode 7328: reward = -169.18, steps = 21 04:59:21 [INFO] train episode 7329: reward = -105.21, steps = 26 04:59:23 [INFO] train episode 7330: reward = -109.08, steps = 32 04:59:26 [INFO] train episode 7331: reward = -162.72, steps = 28 04:59:28 [INFO] train episode 7332: reward = -215.76, steps = 22 04:59:30 [INFO] train episode 7333: reward = -111.55, steps = 26 04:59:32 [INFO] train episode 7334: reward = -114.69, steps = 25 04:59:36 [INFO] train episode 7335: reward = -165.11, steps = 44 04:59:40 [INFO] train episode 7336: reward = -134.81, steps = 39 04:59:42 [INFO] train episode 7337: reward = -76.93, steps = 26 04:59:44 [INFO] train episode 7338: reward = -145.87, steps = 20 04:59:46 [INFO] train episode 7339: reward = -113.06, steps = 30 04:59:48 [INFO] train episode 7340: reward = -130.22, steps = 20 04:59:51 [INFO] train episode 7341: reward = -105.09, steps = 32 04:59:54 [INFO] train episode 7342: reward = -242.79, steps = 30 04:59:56 [INFO] train episode 7343: reward = -104.51, steps = 31 04:59:58 [INFO] train episode 7344: reward = -108.55, steps = 27 05:00:01 [INFO] train episode 7345: reward = -113.03, steps = 27 05:00:03 [INFO] train episode 7346: reward = -162.26, steps = 23 05:00:06 [INFO] train episode 7347: reward = -113.84, steps = 23 05:00:07 [INFO] train episode 7348: reward = -149.53, steps = 21 05:00:09 [INFO] train episode 7349: reward = -128.69, steps = 21 05:00:12 [INFO] train episode 7350: reward = -165.37, steps = 26 05:00:14 [INFO] train episode 7351: reward = -132.36, steps = 25 05:00:16 [INFO] train episode 7352: reward = -102.49, steps = 24 05:00:18 [INFO] train episode 7353: reward = -132.55, steps = 24 05:00:20 [INFO] train episode 7354: reward = -194.51, steps = 28 05:00:23 [INFO] train episode 7355: reward = -105.14, steps = 28 05:00:27 [INFO] train episode 7356: reward = -144.81, steps = 47 05:00:29 [INFO] train episode 7357: reward = -117.14, steps = 23 05:00:31 [INFO] train episode 7358: reward = -120.24, steps = 26 05:00:34 [INFO] train episode 7359: reward = -265.66, steps = 28 05:00:37 [INFO] train episode 7360: reward = -111.99, steps = 34 05:00:39 [INFO] train episode 7361: reward = -176.65, steps = 27 05:00:42 [INFO] train episode 7362: reward = -125.11, steps = 26 05:00:44 [INFO] train episode 7363: reward = -101.53, steps = 23 05:00:46 [INFO] train episode 7364: reward = -87.68, steps = 27 05:00:48 [INFO] train episode 7365: reward = -90.37, steps = 22 05:00:52 [INFO] train episode 7366: reward = -107.64, steps = 45 05:00:54 [INFO] train episode 7367: reward = -113.50, steps = 25 05:00:57 [INFO] train episode 7368: reward = -145.92, steps = 29 05:00:59 [INFO] train episode 7369: reward = -187.26, steps = 30 05:01:03 [INFO] train episode 7370: reward = -198.82, steps = 43 05:01:05 [INFO] train episode 7371: reward = -153.33, steps = 24 05:01:07 [INFO] train episode 7372: reward = -138.56, steps = 27 05:01:10 [INFO] train episode 7373: reward = -80.69, steps = 22 05:01:11 [INFO] train episode 7374: reward = -142.34, steps = 21 05:01:14 [INFO] train episode 7375: reward = -99.74, steps = 26 05:01:16 [INFO] train episode 7376: reward = -133.99, steps = 29 05:01:18 [INFO] train episode 7377: reward = -159.48, steps = 19 05:01:20 [INFO] train episode 7378: reward = -120.76, steps = 22 05:01:23 [INFO] train episode 7379: reward = -147.89, steps = 36 05:01:26 [INFO] train episode 7380: reward = -161.28, steps = 40 05:01:29 [INFO] train episode 7381: reward = -150.12, steps = 28 05:01:31 [INFO] train episode 7382: reward = -137.59, steps = 25 05:01:33 [INFO] train episode 7383: reward = -64.61, steps = 26 05:01:35 [INFO] train episode 7384: reward = -125.95, steps = 22 05:01:37 [INFO] train episode 7385: reward = -148.62, steps = 21 05:01:39 [INFO] train episode 7386: reward = -120.27, steps = 25 05:01:42 [INFO] train episode 7387: reward = -161.40, steps = 28 05:01:44 [INFO] train episode 7388: reward = -128.87, steps = 25 05:01:46 [INFO] train episode 7389: reward = -130.77, steps = 20 05:01:48 [INFO] train episode 7390: reward = -89.97, steps = 21 05:01:50 [INFO] train episode 7391: reward = -152.88, steps = 24 05:01:52 [INFO] train episode 7392: reward = -139.80, steps = 22 05:01:53 [INFO] train episode 7393: reward = -239.40, steps = 20 05:01:57 [INFO] train episode 7394: reward = -201.78, steps = 29 05:01:59 [INFO] train episode 7395: reward = -131.92, steps = 27 05:02:02 [INFO] train episode 7396: reward = -111.86, steps = 26 05:02:05 [INFO] train episode 7397: reward = -157.73, steps = 34 05:02:08 [INFO] train episode 7398: reward = -160.93, steps = 36 05:02:10 [INFO] train episode 7399: reward = -147.98, steps = 30 05:02:14 [INFO] train episode 7400: reward = -88.95, steps = 41 05:02:16 [INFO] train episode 7401: reward = -161.74, steps = 22 05:02:19 [INFO] train episode 7402: reward = -136.84, steps = 27 05:02:22 [INFO] train episode 7403: reward = -147.38, steps = 38 05:02:24 [INFO] train episode 7404: reward = -170.72, steps = 24 05:02:26 [INFO] train episode 7405: reward = -121.96, steps = 23 05:02:28 [INFO] train episode 7406: reward = -172.97, steps = 25 05:02:30 [INFO] train episode 7407: reward = -100.46, steps = 22 05:02:33 [INFO] train episode 7408: reward = -164.38, steps = 30 05:02:35 [INFO] train episode 7409: reward = -166.74, steps = 25 05:02:37 [INFO] train episode 7410: reward = -134.10, steps = 27 05:02:40 [INFO] train episode 7411: reward = -98.39, steps = 30 05:02:42 [INFO] train episode 7412: reward = -144.12, steps = 29 05:02:44 [INFO] train episode 7413: reward = -148.89, steps = 21 05:02:48 [INFO] train episode 7414: reward = -106.01, steps = 35 05:02:50 [INFO] train episode 7415: reward = -130.69, steps = 26 05:02:52 [INFO] train episode 7416: reward = -152.17, steps = 26 05:02:55 [INFO] train episode 7417: reward = -174.21, steps = 32 05:02:58 [INFO] train episode 7418: reward = -124.23, steps = 36 05:03:02 [INFO] train episode 7419: reward = -126.40, steps = 44 05:03:05 [INFO] train episode 7420: reward = -130.82, steps = 28 05:03:07 [INFO] train episode 7421: reward = -229.27, steps = 24 05:03:09 [INFO] train episode 7422: reward = -147.52, steps = 28 05:03:11 [INFO] train episode 7423: reward = -145.34, steps = 20 05:03:13 [INFO] train episode 7424: reward = -144.54, steps = 24 05:03:16 [INFO] train episode 7425: reward = -165.85, steps = 30 05:03:19 [INFO] train episode 7426: reward = -158.35, steps = 33 05:03:21 [INFO] train episode 7427: reward = -179.21, steps = 26 05:03:24 [INFO] train episode 7428: reward = -117.22, steps = 37 05:03:26 [INFO] train episode 7429: reward = -110.55, steps = 26 05:03:28 [INFO] train episode 7430: reward = -140.48, steps = 20 05:03:31 [INFO] train episode 7431: reward = -116.64, steps = 28 05:03:33 [INFO] train episode 7432: reward = -130.94, steps = 22 05:03:35 [INFO] train episode 7433: reward = -120.26, steps = 22 05:03:36 [INFO] train episode 7434: reward = -126.09, steps = 17 05:03:38 [INFO] train episode 7435: reward = -108.86, steps = 25 05:03:41 [INFO] train episode 7436: reward = -124.02, steps = 27 05:03:43 [INFO] train episode 7437: reward = -135.04, steps = 23 05:03:45 [INFO] train episode 7438: reward = -106.26, steps = 20 05:03:47 [INFO] train episode 7439: reward = -182.48, steps = 25 05:03:49 [INFO] train episode 7440: reward = -112.43, steps = 23 05:03:51 [INFO] train episode 7441: reward = -104.64, steps = 26 05:03:54 [INFO] train episode 7442: reward = -147.55, steps = 28 05:03:57 [INFO] train episode 7443: reward = -156.64, steps = 36 05:03:59 [INFO] train episode 7444: reward = -136.03, steps = 24 05:04:01 [INFO] train episode 7445: reward = -139.32, steps = 26 05:04:04 [INFO] train episode 7446: reward = -180.53, steps = 38 05:04:07 [INFO] train episode 7447: reward = -165.44, steps = 30 05:04:09 [INFO] train episode 7448: reward = -144.46, steps = 21 05:04:12 [INFO] train episode 7449: reward = -187.34, steps = 31 05:04:14 [INFO] train episode 7450: reward = -128.92, steps = 27 05:04:17 [INFO] train episode 7451: reward = -136.55, steps = 29 05:04:19 [INFO] train episode 7452: reward = -150.63, steps = 27 05:04:21 [INFO] train episode 7453: reward = -125.47, steps = 20 05:04:24 [INFO] train episode 7454: reward = -125.30, steps = 31 05:04:27 [INFO] train episode 7455: reward = -165.39, steps = 32 05:04:30 [INFO] train episode 7456: reward = -139.78, steps = 36 05:04:33 [INFO] train episode 7457: reward = -164.74, steps = 36 05:04:35 [INFO] train episode 7458: reward = -132.63, steps = 26 05:04:38 [INFO] train episode 7459: reward = -202.88, steps = 26 05:04:41 [INFO] train episode 7460: reward = -183.79, steps = 35 05:04:43 [INFO] train episode 7461: reward = -104.54, steps = 29 05:04:45 [INFO] train episode 7462: reward = -195.05, steps = 22 05:04:47 [INFO] train episode 7463: reward = -121.26, steps = 23 05:04:51 [INFO] train episode 7464: reward = -136.29, steps = 31 05:04:52 [INFO] train episode 7465: reward = -129.20, steps = 20 05:04:55 [INFO] train episode 7466: reward = -228.82, steps = 30 05:04:58 [INFO] train episode 7467: reward = -245.66, steps = 30 05:05:00 [INFO] train episode 7468: reward = -160.29, steps = 24 05:05:02 [INFO] train episode 7469: reward = -107.39, steps = 21 05:05:04 [INFO] train episode 7470: reward = -185.17, steps = 25 05:05:06 [INFO] train episode 7471: reward = -122.61, steps = 28 05:05:09 [INFO] train episode 7472: reward = -222.78, steps = 25 05:05:11 [INFO] train episode 7473: reward = -75.36, steps = 19 05:05:13 [INFO] train episode 7474: reward = -131.03, steps = 24 05:05:16 [INFO] train episode 7475: reward = -166.53, steps = 30 05:05:19 [INFO] train episode 7476: reward = -182.22, steps = 30 05:05:23 [INFO] train episode 7477: reward = -97.82, steps = 45 05:05:26 [INFO] train episode 7478: reward = -101.17, steps = 32 05:05:28 [INFO] train episode 7479: reward = -108.46, steps = 20 05:05:30 [INFO] train episode 7480: reward = -149.43, steps = 23 05:05:33 [INFO] train episode 7481: reward = -114.26, steps = 27 05:05:35 [INFO] train episode 7482: reward = -128.96, steps = 24 05:05:38 [INFO] train episode 7483: reward = -145.82, steps = 30 05:05:41 [INFO] train episode 7484: reward = -106.19, steps = 43 05:05:45 [INFO] train episode 7485: reward = -232.10, steps = 37 05:05:47 [INFO] train episode 7486: reward = -111.47, steps = 21 05:05:50 [INFO] train episode 7487: reward = -179.60, steps = 31 05:05:52 [INFO] train episode 7488: reward = -149.57, steps = 30 05:05:54 [INFO] train episode 7489: reward = -130.35, steps = 22 05:05:56 [INFO] train episode 7490: reward = -167.78, steps = 27 05:05:59 [INFO] train episode 7491: reward = -127.77, steps = 28 05:06:01 [INFO] train episode 7492: reward = -157.10, steps = 24 05:06:03 [INFO] train episode 7493: reward = -139.40, steps = 23 05:06:05 [INFO] train episode 7494: reward = -118.25, steps = 19 05:06:08 [INFO] train episode 7495: reward = -126.84, steps = 28 05:06:10 [INFO] train episode 7496: reward = -119.63, steps = 21 05:06:12 [INFO] train episode 7497: reward = -130.44, steps = 22 05:06:15 [INFO] train episode 7498: reward = -150.53, steps = 39 05:06:18 [INFO] train episode 7499: reward = -149.48, steps = 28 05:06:20 [INFO] train episode 7500: reward = -91.10, steps = 19 05:06:22 [INFO] train episode 7501: reward = -115.63, steps = 29 05:06:25 [INFO] train episode 7502: reward = -103.14, steps = 31 05:06:27 [INFO] train episode 7503: reward = -97.67, steps = 22 05:06:29 [INFO] train episode 7504: reward = -131.65, steps = 22 05:06:31 [INFO] train episode 7505: reward = -159.08, steps = 30 05:06:34 [INFO] train episode 7506: reward = -107.54, steps = 30 05:06:36 [INFO] train episode 7507: reward = -128.75, steps = 20 05:06:38 [INFO] train episode 7508: reward = -191.84, steps = 25 05:06:40 [INFO] train episode 7509: reward = -149.98, steps = 20 05:06:42 [INFO] train episode 7510: reward = -143.08, steps = 22 05:06:45 [INFO] train episode 7511: reward = -134.85, steps = 35 05:06:47 [INFO] train episode 7512: reward = -87.20, steps = 32 05:06:50 [INFO] train episode 7513: reward = -136.28, steps = 29 05:06:53 [INFO] train episode 7514: reward = -138.94, steps = 32 05:06:56 [INFO] train episode 7515: reward = -176.97, steps = 31 05:06:59 [INFO] train episode 7516: reward = -170.42, steps = 35 05:07:03 [INFO] train episode 7517: reward = -237.78, steps = 45 05:07:06 [INFO] train episode 7518: reward = -144.37, steps = 37 05:07:09 [INFO] train episode 7519: reward = -113.66, steps = 35 05:07:14 [INFO] train episode 7520: reward = -184.34, steps = 57 05:07:16 [INFO] train episode 7521: reward = -116.45, steps = 24 05:07:18 [INFO] train episode 7522: reward = -103.63, steps = 22 05:07:21 [INFO] train episode 7523: reward = -189.51, steps = 31 05:07:23 [INFO] train episode 7524: reward = -142.35, steps = 24 05:07:26 [INFO] train episode 7525: reward = -113.67, steps = 34 05:07:28 [INFO] train episode 7526: reward = -137.75, steps = 24 05:07:30 [INFO] train episode 7527: reward = -136.16, steps = 22 05:07:33 [INFO] train episode 7528: reward = -163.10, steps = 30 05:07:35 [INFO] train episode 7529: reward = -113.62, steps = 30 05:07:39 [INFO] train episode 7530: reward = -132.58, steps = 34 05:07:41 [INFO] train episode 7531: reward = -115.24, steps = 32 05:07:44 [INFO] train episode 7532: reward = -149.43, steps = 27 05:07:47 [INFO] train episode 7533: reward = -144.44, steps = 25 05:07:49 [INFO] train episode 7534: reward = -123.82, steps = 32 05:07:52 [INFO] train episode 7535: reward = -161.15, steps = 28 05:07:54 [INFO] train episode 7536: reward = -105.31, steps = 25 05:07:57 [INFO] train episode 7537: reward = -116.63, steps = 34 05:08:01 [INFO] train episode 7538: reward = -160.95, steps = 38 05:08:03 [INFO] train episode 7539: reward = -79.12, steps = 25 05:08:06 [INFO] train episode 7540: reward = -111.00, steps = 33 05:08:07 [INFO] train episode 7541: reward = -131.70, steps = 20 05:08:10 [INFO] train episode 7542: reward = -120.01, steps = 27 05:08:12 [INFO] train episode 7543: reward = -126.89, steps = 28 05:08:16 [INFO] train episode 7544: reward = -133.46, steps = 39 05:08:20 [INFO] train episode 7545: reward = -257.26, steps = 48 05:08:22 [INFO] train episode 7546: reward = -134.64, steps = 26 05:08:25 [INFO] train episode 7547: reward = -162.94, steps = 31 05:08:28 [INFO] train episode 7548: reward = -189.50, steps = 36 05:08:31 [INFO] train episode 7549: reward = -152.88, steps = 34 05:08:33 [INFO] train episode 7550: reward = -98.15, steps = 18 05:08:35 [INFO] train episode 7551: reward = -163.67, steps = 23 05:08:37 [INFO] train episode 7552: reward = -119.75, steps = 27 05:08:40 [INFO] train episode 7553: reward = -85.14, steps = 31 05:08:42 [INFO] train episode 7554: reward = -153.35, steps = 25 05:08:45 [INFO] train episode 7555: reward = -143.99, steps = 27 05:08:48 [INFO] train episode 7556: reward = -113.35, steps = 36 05:08:50 [INFO] train episode 7557: reward = -122.38, steps = 22 05:08:52 [INFO] train episode 7558: reward = -132.30, steps = 30 05:08:54 [INFO] train episode 7559: reward = -117.33, steps = 23 05:08:56 [INFO] train episode 7560: reward = -115.18, steps = 24 05:08:58 [INFO] train episode 7561: reward = -80.07, steps = 20 05:09:01 [INFO] train episode 7562: reward = -206.07, steps = 33 05:09:04 [INFO] train episode 7563: reward = -113.74, steps = 35 05:09:06 [INFO] train episode 7564: reward = -131.78, steps = 23 05:09:09 [INFO] train episode 7565: reward = -72.27, steps = 37 05:09:11 [INFO] train episode 7566: reward = -128.47, steps = 19 05:09:13 [INFO] train episode 7567: reward = -145.06, steps = 23 05:09:16 [INFO] train episode 7568: reward = -143.46, steps = 25 05:09:18 [INFO] train episode 7569: reward = -161.14, steps = 34 05:09:21 [INFO] train episode 7570: reward = -156.85, steps = 30 05:09:23 [INFO] train episode 7571: reward = -130.89, steps = 25 05:09:25 [INFO] train episode 7572: reward = -107.66, steps = 21 05:09:28 [INFO] train episode 7573: reward = -149.44, steps = 31 05:09:31 [INFO] train episode 7574: reward = -109.68, steps = 33 05:09:33 [INFO] train episode 7575: reward = -115.87, steps = 25 05:09:36 [INFO] train episode 7576: reward = -103.76, steps = 34 05:09:38 [INFO] train episode 7577: reward = -144.58, steps = 22 05:09:41 [INFO] train episode 7578: reward = -118.33, steps = 30 05:09:42 [INFO] train episode 7579: reward = -142.46, steps = 21 05:09:44 [INFO] train episode 7580: reward = -113.75, steps = 20 05:09:47 [INFO] train episode 7581: reward = -148.93, steps = 25 05:09:50 [INFO] train episode 7582: reward = -89.36, steps = 34 05:09:52 [INFO] train episode 7583: reward = -116.39, steps = 29 05:09:54 [INFO] train episode 7584: reward = -162.24, steps = 27 05:09:57 [INFO] train episode 7585: reward = -95.11, steps = 24 05:09:59 [INFO] train episode 7586: reward = -83.47, steps = 25 05:10:01 [INFO] train episode 7587: reward = -85.76, steps = 23 05:10:03 [INFO] train episode 7588: reward = -107.15, steps = 24 05:10:06 [INFO] train episode 7589: reward = -82.09, steps = 31 05:10:08 [INFO] train episode 7590: reward = -131.78, steps = 24 05:10:10 [INFO] train episode 7591: reward = -138.92, steps = 27 05:10:12 [INFO] train episode 7592: reward = -116.59, steps = 23 05:10:15 [INFO] train episode 7593: reward = -124.24, steps = 26 05:10:17 [INFO] train episode 7594: reward = -132.29, steps = 24 05:10:20 [INFO] train episode 7595: reward = -131.70, steps = 36 05:10:22 [INFO] train episode 7596: reward = -115.22, steps = 26 05:10:25 [INFO] train episode 7597: reward = -165.47, steps = 32 05:10:27 [INFO] train episode 7598: reward = -125.49, steps = 26 05:10:30 [INFO] train episode 7599: reward = -129.38, steps = 26 05:10:32 [INFO] train episode 7600: reward = -114.51, steps = 28 05:10:35 [INFO] train episode 7601: reward = -130.14, steps = 30 05:10:38 [INFO] train episode 7602: reward = -116.16, steps = 31 05:10:41 [INFO] train episode 7603: reward = -104.37, steps = 31 05:10:43 [INFO] train episode 7604: reward = -145.87, steps = 19 05:10:44 [INFO] train episode 7605: reward = -137.02, steps = 20 05:10:48 [INFO] train episode 7606: reward = -131.97, steps = 42 05:10:50 [INFO] train episode 7607: reward = -137.38, steps = 24 05:10:52 [INFO] train episode 7608: reward = -98.55, steps = 20 05:10:54 [INFO] train episode 7609: reward = -127.95, steps = 22 05:10:57 [INFO] train episode 7610: reward = -161.11, steps = 34 05:11:00 [INFO] train episode 7611: reward = -206.40, steps = 29 05:11:02 [INFO] train episode 7612: reward = -121.11, steps = 26 05:11:04 [INFO] train episode 7613: reward = -66.40, steps = 21 05:11:06 [INFO] train episode 7614: reward = -87.94, steps = 23 05:11:09 [INFO] train episode 7615: reward = -126.92, steps = 36 05:11:12 [INFO] train episode 7616: reward = -151.53, steps = 33 05:11:14 [INFO] train episode 7617: reward = -122.87, steps = 27 05:11:18 [INFO] train episode 7618: reward = -198.78, steps = 43 05:11:20 [INFO] train episode 7619: reward = -118.85, steps = 27 05:11:24 [INFO] train episode 7620: reward = -121.58, steps = 38 05:11:26 [INFO] train episode 7621: reward = -164.25, steps = 27 05:11:29 [INFO] train episode 7622: reward = -123.36, steps = 31 05:11:31 [INFO] train episode 7623: reward = -95.38, steps = 25 05:11:33 [INFO] train episode 7624: reward = -118.72, steps = 24 05:11:37 [INFO] train episode 7625: reward = -166.05, steps = 43 05:11:40 [INFO] train episode 7626: reward = -190.75, steps = 30 05:11:42 [INFO] train episode 7627: reward = -91.64, steps = 31 05:11:46 [INFO] train episode 7628: reward = -93.72, steps = 40 05:11:48 [INFO] train episode 7629: reward = -159.86, steps = 31 05:11:52 [INFO] train episode 7630: reward = -173.81, steps = 37 05:11:53 [INFO] train episode 7631: reward = -69.11, steps = 18 05:11:57 [INFO] train episode 7632: reward = -132.09, steps = 39 05:11:59 [INFO] train episode 7633: reward = -152.39, steps = 27 05:12:02 [INFO] train episode 7634: reward = -94.24, steps = 36 05:12:04 [INFO] train episode 7635: reward = -138.83, steps = 20 05:12:06 [INFO] train episode 7636: reward = -107.18, steps = 21 05:12:08 [INFO] train episode 7637: reward = -100.14, steps = 28 05:12:11 [INFO] train episode 7638: reward = -141.20, steps = 23 05:12:13 [INFO] train episode 7639: reward = -133.56, steps = 26 05:12:16 [INFO] train episode 7640: reward = -114.51, steps = 32 05:12:18 [INFO] train episode 7641: reward = -86.96, steps = 23 05:12:20 [INFO] train episode 7642: reward = -84.19, steps = 20 05:12:23 [INFO] train episode 7643: reward = -120.29, steps = 33 05:12:25 [INFO] train episode 7644: reward = -143.32, steps = 25 05:12:28 [INFO] train episode 7645: reward = -109.38, steps = 29 05:12:29 [INFO] train episode 7646: reward = -71.60, steps = 22 05:12:32 [INFO] train episode 7647: reward = -146.22, steps = 30 05:12:34 [INFO] train episode 7648: reward = -133.56, steps = 28 05:12:38 [INFO] train episode 7649: reward = -182.42, steps = 38 05:12:40 [INFO] train episode 7650: reward = -118.80, steps = 30 05:12:43 [INFO] train episode 7651: reward = -151.80, steps = 30 05:12:45 [INFO] train episode 7652: reward = -155.82, steps = 24 05:12:49 [INFO] train episode 7653: reward = -154.11, steps = 40 05:12:51 [INFO] train episode 7654: reward = -122.57, steps = 25 05:12:53 [INFO] train episode 7655: reward = -147.69, steps = 20 05:12:55 [INFO] train episode 7656: reward = -91.13, steps = 27 05:12:57 [INFO] train episode 7657: reward = -144.09, steps = 27 05:13:00 [INFO] train episode 7658: reward = -130.98, steps = 24 05:13:02 [INFO] train episode 7659: reward = -136.73, steps = 29 05:13:05 [INFO] train episode 7660: reward = -142.72, steps = 35 05:13:07 [INFO] train episode 7661: reward = -124.84, steps = 20 05:13:09 [INFO] train episode 7662: reward = -100.46, steps = 24 05:13:12 [INFO] train episode 7663: reward = -199.33, steps = 28 05:13:14 [INFO] train episode 7664: reward = -172.57, steps = 26 05:13:17 [INFO] train episode 7665: reward = -168.75, steps = 30 05:13:19 [INFO] train episode 7666: reward = -167.72, steps = 31 05:13:21 [INFO] train episode 7667: reward = -118.24, steps = 20 05:13:23 [INFO] train episode 7668: reward = -163.52, steps = 23 05:13:25 [INFO] train episode 7669: reward = -127.04, steps = 21 05:13:28 [INFO] train episode 7670: reward = -141.89, steps = 32 05:13:31 [INFO] train episode 7671: reward = -182.08, steps = 27 05:13:34 [INFO] train episode 7672: reward = -157.10, steps = 28 05:13:36 [INFO] train episode 7673: reward = -147.14, steps = 28 05:13:39 [INFO] train episode 7674: reward = -122.24, steps = 36 05:13:41 [INFO] train episode 7675: reward = -93.56, steps = 22 05:13:43 [INFO] train episode 7676: reward = -100.73, steps = 26 05:13:48 [INFO] train episode 7677: reward = -140.10, steps = 45 05:13:51 [INFO] train episode 7678: reward = -132.14, steps = 39 05:13:53 [INFO] train episode 7679: reward = -139.17, steps = 25 05:13:56 [INFO] train episode 7680: reward = -122.72, steps = 32 05:13:58 [INFO] train episode 7681: reward = -150.97, steps = 26 05:14:00 [INFO] train episode 7682: reward = -92.28, steps = 20 05:14:02 [INFO] train episode 7683: reward = -110.11, steps = 29 05:14:05 [INFO] train episode 7684: reward = -168.38, steps = 32 05:14:08 [INFO] train episode 7685: reward = -91.34, steps = 34 05:14:11 [INFO] train episode 7686: reward = -121.78, steps = 24 05:14:15 [INFO] train episode 7687: reward = -169.18, steps = 51 05:14:17 [INFO] train episode 7688: reward = -112.03, steps = 25 05:14:19 [INFO] train episode 7689: reward = -60.99, steps = 24 05:14:21 [INFO] train episode 7690: reward = -108.83, steps = 20 05:14:24 [INFO] train episode 7691: reward = -146.75, steps = 30 05:14:26 [INFO] train episode 7692: reward = -91.73, steps = 22 05:14:28 [INFO] train episode 7693: reward = -112.91, steps = 24 05:14:30 [INFO] train episode 7694: reward = -141.39, steps = 29 05:14:33 [INFO] train episode 7695: reward = -151.45, steps = 32 05:14:37 [INFO] train episode 7696: reward = -108.53, steps = 41 05:14:41 [INFO] train episode 7697: reward = -84.03, steps = 46 05:14:44 [INFO] train episode 7698: reward = -170.28, steps = 37 05:14:46 [INFO] train episode 7699: reward = -120.45, steps = 28 05:14:49 [INFO] train episode 7700: reward = -145.72, steps = 25 05:14:51 [INFO] train episode 7701: reward = -122.49, steps = 27 05:14:54 [INFO] train episode 7702: reward = -202.31, steps = 30 05:14:56 [INFO] train episode 7703: reward = -124.00, steps = 29 05:14:59 [INFO] train episode 7704: reward = -154.11, steps = 34 05:15:02 [INFO] train episode 7705: reward = -205.62, steps = 29 05:15:04 [INFO] train episode 7706: reward = -79.39, steps = 25 05:15:07 [INFO] train episode 7707: reward = -123.22, steps = 27 05:15:09 [INFO] train episode 7708: reward = -133.15, steps = 23 05:15:11 [INFO] train episode 7709: reward = -83.09, steps = 22 05:15:14 [INFO] train episode 7710: reward = -120.56, steps = 33 05:15:16 [INFO] train episode 7711: reward = -96.18, steps = 24 05:15:18 [INFO] train episode 7712: reward = -118.92, steps = 18 05:15:20 [INFO] train episode 7713: reward = -170.45, steps = 31 05:15:23 [INFO] train episode 7714: reward = -121.54, steps = 26 05:15:27 [INFO] train episode 7715: reward = -137.35, steps = 42 05:15:28 [INFO] train episode 7716: reward = -123.56, steps = 21 05:15:30 [INFO] train episode 7717: reward = -144.23, steps = 23 05:15:34 [INFO] train episode 7718: reward = -117.60, steps = 46 05:15:37 [INFO] train episode 7719: reward = -120.92, steps = 29 05:15:39 [INFO] train episode 7720: reward = -104.92, steps = 24 05:15:41 [INFO] train episode 7721: reward = -136.00, steps = 22 05:15:43 [INFO] train episode 7722: reward = -123.47, steps = 25 05:15:46 [INFO] train episode 7723: reward = -128.58, steps = 27 05:15:48 [INFO] train episode 7724: reward = -141.24, steps = 32 05:15:51 [INFO] train episode 7725: reward = -74.90, steps = 33 05:15:54 [INFO] train episode 7726: reward = -84.64, steps = 27 05:15:57 [INFO] train episode 7727: reward = -199.74, steps = 35 05:16:00 [INFO] train episode 7728: reward = -104.72, steps = 32 05:16:02 [INFO] train episode 7729: reward = -104.30, steps = 28 05:16:04 [INFO] train episode 7730: reward = -115.58, steps = 26 05:16:06 [INFO] train episode 7731: reward = -113.00, steps = 22 05:16:09 [INFO] train episode 7732: reward = -121.58, steps = 24 05:16:12 [INFO] train episode 7733: reward = -77.51, steps = 33 05:16:14 [INFO] train episode 7734: reward = -100.40, steps = 25 05:16:16 [INFO] train episode 7735: reward = -187.99, steps = 22 05:16:18 [INFO] train episode 7736: reward = -206.92, steps = 29 05:16:20 [INFO] train episode 7737: reward = -118.55, steps = 25 05:16:23 [INFO] train episode 7738: reward = -128.24, steps = 25 05:16:26 [INFO] train episode 7739: reward = -122.36, steps = 32 05:16:29 [INFO] train episode 7740: reward = -69.97, steps = 23 05:16:31 [INFO] train episode 7741: reward = -138.18, steps = 33 05:16:34 [INFO] train episode 7742: reward = -93.50, steps = 35 05:16:37 [INFO] train episode 7743: reward = -150.27, steps = 25 05:16:39 [INFO] train episode 7744: reward = -167.62, steps = 26 05:16:41 [INFO] train episode 7745: reward = -111.86, steps = 28 05:16:44 [INFO] train episode 7746: reward = -106.70, steps = 29 05:16:46 [INFO] train episode 7747: reward = -84.85, steps = 20 05:16:48 [INFO] train episode 7748: reward = -150.92, steps = 28 05:16:51 [INFO] train episode 7749: reward = -92.99, steps = 26 05:16:53 [INFO] train episode 7750: reward = -93.30, steps = 33 05:16:55 [INFO] train episode 7751: reward = -109.77, steps = 20 05:16:57 [INFO] train episode 7752: reward = -100.58, steps = 27 05:16:59 [INFO] train episode 7753: reward = -119.56, steps = 20 05:17:02 [INFO] train episode 7754: reward = -76.20, steps = 32 05:17:05 [INFO] train episode 7755: reward = -54.99, steps = 31 05:17:07 [INFO] train episode 7756: reward = -90.90, steps = 27 05:17:10 [INFO] train episode 7757: reward = -135.93, steps = 25 05:17:12 [INFO] train episode 7758: reward = -156.72, steps = 29 05:17:14 [INFO] train episode 7759: reward = -137.21, steps = 26 05:17:17 [INFO] train episode 7760: reward = -167.66, steps = 29 05:17:21 [INFO] train episode 7761: reward = -194.38, steps = 47 05:17:23 [INFO] train episode 7762: reward = -107.36, steps = 24 05:17:26 [INFO] train episode 7763: reward = -113.72, steps = 25 05:17:27 [INFO] train episode 7764: reward = -88.31, steps = 20 05:17:30 [INFO] train episode 7765: reward = -177.93, steps = 30 05:17:32 [INFO] train episode 7766: reward = -103.33, steps = 23 05:17:34 [INFO] train episode 7767: reward = -84.42, steps = 21 05:17:36 [INFO] train episode 7768: reward = -146.97, steps = 26 05:17:39 [INFO] train episode 7769: reward = -148.42, steps = 36 05:17:42 [INFO] train episode 7770: reward = -114.69, steps = 31 05:17:45 [INFO] train episode 7771: reward = -141.81, steps = 29 05:17:48 [INFO] train episode 7772: reward = -137.24, steps = 35 05:17:50 [INFO] train episode 7773: reward = -108.66, steps = 22 05:17:52 [INFO] train episode 7774: reward = -157.46, steps = 25 05:17:54 [INFO] train episode 7775: reward = -134.46, steps = 25 05:17:56 [INFO] train episode 7776: reward = -109.58, steps = 25 05:17:58 [INFO] train episode 7777: reward = -135.40, steps = 22 05:18:01 [INFO] train episode 7778: reward = -132.83, steps = 26 05:18:03 [INFO] train episode 7779: reward = -160.85, steps = 29 05:18:07 [INFO] train episode 7780: reward = -193.70, steps = 37 05:18:08 [INFO] train episode 7781: reward = -88.98, steps = 21 05:18:11 [INFO] train episode 7782: reward = -97.75, steps = 24 05:18:13 [INFO] train episode 7783: reward = -118.54, steps = 26 05:18:15 [INFO] train episode 7784: reward = -83.65, steps = 25 05:18:17 [INFO] train episode 7785: reward = -93.57, steps = 25 05:18:20 [INFO] train episode 7786: reward = -125.93, steps = 27 05:18:22 [INFO] train episode 7787: reward = -103.70, steps = 22 05:18:24 [INFO] train episode 7788: reward = -110.11, steps = 22 05:18:26 [INFO] train episode 7789: reward = -103.87, steps = 28 05:18:30 [INFO] train episode 7790: reward = -181.40, steps = 41 05:18:32 [INFO] train episode 7791: reward = -108.51, steps = 24 05:18:34 [INFO] train episode 7792: reward = -88.10, steps = 30 05:18:37 [INFO] train episode 7793: reward = -108.57, steps = 22 05:18:39 [INFO] train episode 7794: reward = -110.89, steps = 24 05:18:41 [INFO] train episode 7795: reward = -180.39, steps = 27 05:18:43 [INFO] train episode 7796: reward = -108.64, steps = 22 05:18:45 [INFO] train episode 7797: reward = -91.41, steps = 22 05:18:47 [INFO] train episode 7798: reward = -106.97, steps = 28 05:18:49 [INFO] train episode 7799: reward = -178.97, steps = 25 05:18:53 [INFO] train episode 7800: reward = -143.34, steps = 40 05:18:56 [INFO] train episode 7801: reward = -83.76, steps = 34 05:18:59 [INFO] train episode 7802: reward = -104.10, steps = 37 05:19:01 [INFO] train episode 7803: reward = -154.87, steps = 21 05:19:04 [INFO] train episode 7804: reward = -112.16, steps = 35 05:19:06 [INFO] train episode 7805: reward = -171.85, steps = 22 05:19:08 [INFO] train episode 7806: reward = -103.49, steps = 21 05:19:12 [INFO] train episode 7807: reward = -183.83, steps = 45 05:19:14 [INFO] train episode 7808: reward = -134.85, steps = 21 05:19:17 [INFO] train episode 7809: reward = -116.15, steps = 24 05:19:19 [INFO] train episode 7810: reward = -119.80, steps = 26 05:19:21 [INFO] train episode 7811: reward = -122.24, steps = 27 05:19:25 [INFO] train episode 7812: reward = -170.74, steps = 41 05:19:27 [INFO] train episode 7813: reward = -110.97, steps = 21 05:19:29 [INFO] train episode 7814: reward = -81.98, steps = 23 05:19:32 [INFO] train episode 7815: reward = -128.17, steps = 30 05:19:35 [INFO] train episode 7816: reward = -176.56, steps = 35 05:19:36 [INFO] train episode 7817: reward = -118.65, steps = 19 05:19:39 [INFO] train episode 7818: reward = -166.71, steps = 32 05:19:41 [INFO] train episode 7819: reward = -111.74, steps = 26 05:19:43 [INFO] train episode 7820: reward = -118.90, steps = 21 05:19:46 [INFO] train episode 7821: reward = -136.69, steps = 26 05:19:47 [INFO] train episode 7822: reward = -134.45, steps = 20 05:19:50 [INFO] train episode 7823: reward = -143.75, steps = 35 05:19:53 [INFO] train episode 7824: reward = -146.06, steps = 26 05:19:56 [INFO] train episode 7825: reward = -210.53, steps = 36 05:19:58 [INFO] train episode 7826: reward = -122.26, steps = 23 05:20:00 [INFO] train episode 7827: reward = -104.55, steps = 20 05:20:02 [INFO] train episode 7828: reward = -133.92, steps = 24 05:20:04 [INFO] train episode 7829: reward = -106.37, steps = 25 05:20:07 [INFO] train episode 7830: reward = -127.38, steps = 30 05:20:09 [INFO] train episode 7831: reward = -122.90, steps = 23 05:20:10 [INFO] train episode 7832: reward = -122.94, steps = 21 05:20:14 [INFO] train episode 7833: reward = -157.30, steps = 42 05:20:17 [INFO] train episode 7834: reward = -116.71, steps = 36 05:20:20 [INFO] train episode 7835: reward = -127.68, steps = 31 05:20:22 [INFO] train episode 7836: reward = -71.32, steps = 24 05:20:25 [INFO] train episode 7837: reward = -116.65, steps = 28 05:20:28 [INFO] train episode 7838: reward = -119.31, steps = 34 05:20:30 [INFO] train episode 7839: reward = -111.55, steps = 31 05:20:33 [INFO] train episode 7840: reward = -67.57, steps = 22 05:20:36 [INFO] train episode 7841: reward = -186.53, steps = 33 05:20:38 [INFO] train episode 7842: reward = -73.15, steps = 21 05:20:41 [INFO] train episode 7843: reward = -72.41, steps = 23 05:20:43 [INFO] train episode 7844: reward = -103.09, steps = 24 05:20:46 [INFO] train episode 7845: reward = -152.57, steps = 29 05:20:48 [INFO] train episode 7846: reward = -92.19, steps = 21 05:20:50 [INFO] train episode 7847: reward = -128.32, steps = 19 05:20:52 [INFO] train episode 7848: reward = -107.68, steps = 21 05:20:55 [INFO] train episode 7849: reward = -151.72, steps = 28 05:20:59 [INFO] train episode 7850: reward = -186.79, steps = 53 05:21:03 [INFO] train episode 7851: reward = -151.49, steps = 35 05:21:06 [INFO] train episode 7852: reward = -154.49, steps = 41 05:21:10 [INFO] train episode 7853: reward = -170.56, steps = 42 05:21:14 [INFO] train episode 7854: reward = -199.63, steps = 46 05:21:16 [INFO] train episode 7855: reward = -67.92, steps = 24 05:21:19 [INFO] train episode 7856: reward = -129.57, steps = 37 05:21:22 [INFO] train episode 7857: reward = -65.48, steps = 33 05:21:24 [INFO] train episode 7858: reward = -113.28, steps = 21 05:21:27 [INFO] train episode 7859: reward = -223.54, steps = 42 05:21:30 [INFO] train episode 7860: reward = -124.90, steps = 27 05:21:32 [INFO] train episode 7861: reward = -89.96, steps = 26 05:21:35 [INFO] train episode 7862: reward = -184.31, steps = 25 05:21:37 [INFO] train episode 7863: reward = -127.33, steps = 23 05:21:39 [INFO] train episode 7864: reward = -97.98, steps = 27 05:21:41 [INFO] train episode 7865: reward = -146.45, steps = 28 05:21:43 [INFO] train episode 7866: reward = -100.19, steps = 25 05:21:46 [INFO] train episode 7867: reward = -168.83, steps = 31 05:21:48 [INFO] train episode 7868: reward = -149.40, steps = 23 05:21:52 [INFO] train episode 7869: reward = -177.62, steps = 35 05:21:54 [INFO] train episode 7870: reward = -88.96, steps = 24 05:21:56 [INFO] train episode 7871: reward = -95.59, steps = 27 05:21:58 [INFO] train episode 7872: reward = -116.91, steps = 24 05:22:00 [INFO] train episode 7873: reward = -110.38, steps = 28 05:22:03 [INFO] train episode 7874: reward = -103.48, steps = 25 05:22:05 [INFO] train episode 7875: reward = -102.05, steps = 21 05:22:06 [INFO] train episode 7876: reward = -97.22, steps = 18 05:22:09 [INFO] train episode 7877: reward = -70.21, steps = 24 05:22:12 [INFO] train episode 7878: reward = -123.25, steps = 26 05:22:13 [INFO] train episode 7879: reward = -97.85, steps = 22 05:22:16 [INFO] train episode 7880: reward = -92.24, steps = 30 05:22:18 [INFO] train episode 7881: reward = -81.00, steps = 26 05:22:21 [INFO] train episode 7882: reward = -119.17, steps = 31 05:22:24 [INFO] train episode 7883: reward = -134.11, steps = 31 05:22:28 [INFO] train episode 7884: reward = -105.05, steps = 46 05:22:31 [INFO] train episode 7885: reward = -117.45, steps = 42 05:22:33 [INFO] train episode 7886: reward = -87.83, steps = 21 05:22:36 [INFO] train episode 7887: reward = -118.81, steps = 33 05:22:39 [INFO] train episode 7888: reward = -106.15, steps = 21 05:22:41 [INFO] train episode 7889: reward = -101.28, steps = 24 05:22:43 [INFO] train episode 7890: reward = -126.31, steps = 25 05:22:46 [INFO] train episode 7891: reward = -137.91, steps = 34 05:22:48 [INFO] train episode 7892: reward = -89.50, steps = 27 05:22:50 [INFO] train episode 7893: reward = -122.75, steps = 25 05:22:52 [INFO] train episode 7894: reward = -136.27, steps = 24 05:22:55 [INFO] train episode 7895: reward = -97.46, steps = 33 05:22:58 [INFO] train episode 7896: reward = -148.15, steps = 29 05:23:00 [INFO] train episode 7897: reward = -111.19, steps = 26 05:23:02 [INFO] train episode 7898: reward = -130.73, steps = 21 05:23:04 [INFO] train episode 7899: reward = -138.29, steps = 23 05:23:06 [INFO] train episode 7900: reward = -114.00, steps = 25 05:23:09 [INFO] train episode 7901: reward = -135.56, steps = 27 05:23:12 [INFO] train episode 7902: reward = -107.75, steps = 30 05:23:14 [INFO] train episode 7903: reward = -91.12, steps = 28 05:23:17 [INFO] train episode 7904: reward = -172.07, steps = 36 05:23:21 [INFO] train episode 7905: reward = -142.47, steps = 43 05:23:23 [INFO] train episode 7906: reward = -99.20, steps = 25 05:23:26 [INFO] train episode 7907: reward = -100.80, steps = 31 05:23:28 [INFO] train episode 7908: reward = -94.13, steps = 20 05:23:30 [INFO] train episode 7909: reward = -96.76, steps = 30 05:23:32 [INFO] train episode 7910: reward = -98.60, steps = 23 05:23:35 [INFO] train episode 7911: reward = -147.84, steps = 31 05:23:37 [INFO] train episode 7912: reward = -166.87, steps = 25 05:23:39 [INFO] train episode 7913: reward = -114.12, steps = 22 05:23:42 [INFO] train episode 7914: reward = -98.81, steps = 31 05:23:44 [INFO] train episode 7915: reward = -54.69, steps = 23 05:23:46 [INFO] train episode 7916: reward = -104.05, steps = 28 05:23:48 [INFO] train episode 7917: reward = -119.06, steps = 20 05:23:50 [INFO] train episode 7918: reward = -100.12, steps = 24 05:23:53 [INFO] train episode 7919: reward = -124.93, steps = 38 05:23:56 [INFO] train episode 7920: reward = -83.41, steps = 25 05:23:59 [INFO] train episode 7921: reward = -123.13, steps = 33 05:24:02 [INFO] train episode 7922: reward = -175.47, steps = 33 05:24:06 [INFO] train episode 7923: reward = -120.20, steps = 45 05:24:09 [INFO] train episode 7924: reward = -136.25, steps = 35 05:24:12 [INFO] train episode 7925: reward = -118.57, steps = 41 05:24:15 [INFO] train episode 7926: reward = -93.35, steps = 27 05:24:17 [INFO] train episode 7927: reward = -95.29, steps = 24 05:24:19 [INFO] train episode 7928: reward = -159.91, steps = 26 05:24:21 [INFO] train episode 7929: reward = -91.69, steps = 24 05:24:24 [INFO] train episode 7930: reward = -139.57, steps = 28 05:24:25 [INFO] train episode 7931: reward = -85.54, steps = 20 05:24:27 [INFO] train episode 7932: reward = -90.79, steps = 24 05:24:31 [INFO] train episode 7933: reward = -164.08, steps = 31 05:24:34 [INFO] train episode 7934: reward = -123.33, steps = 35 05:24:36 [INFO] train episode 7935: reward = -105.59, steps = 28 05:24:39 [INFO] train episode 7936: reward = -79.52, steps = 37 05:24:43 [INFO] train episode 7937: reward = -87.98, steps = 47 05:24:47 [INFO] train episode 7938: reward = -119.56, steps = 38 05:24:49 [INFO] train episode 7939: reward = -86.99, steps = 26 05:24:51 [INFO] train episode 7940: reward = -81.86, steps = 23 05:24:54 [INFO] train episode 7941: reward = -104.49, steps = 30 05:24:56 [INFO] train episode 7942: reward = -67.62, steps = 31 05:24:59 [INFO] train episode 7943: reward = -152.95, steps = 29 05:25:04 [INFO] train episode 7944: reward = -156.21, steps = 43 05:25:06 [INFO] train episode 7945: reward = -88.08, steps = 23 05:25:08 [INFO] train episode 7946: reward = -67.43, steps = 25 05:25:11 [INFO] train episode 7947: reward = -121.00, steps = 35 05:25:13 [INFO] train episode 7948: reward = -101.50, steps = 28 05:25:16 [INFO] train episode 7949: reward = -66.12, steps = 27 05:25:20 [INFO] train episode 7950: reward = -123.40, steps = 49 05:25:22 [INFO] train episode 7951: reward = -96.28, steps = 24 05:25:25 [INFO] train episode 7952: reward = -93.14, steps = 28 05:25:28 [INFO] train episode 7953: reward = -137.13, steps = 31 05:25:30 [INFO] train episode 7954: reward = -61.59, steps = 24 05:25:31 [INFO] train episode 7955: reward = -108.73, steps = 18 05:25:33 [INFO] train episode 7956: reward = -99.00, steps = 20 05:25:36 [INFO] train episode 7957: reward = -121.73, steps = 26 05:25:38 [INFO] train episode 7958: reward = -72.76, steps = 24 05:25:40 [INFO] train episode 7959: reward = -150.36, steps = 27 05:25:42 [INFO] train episode 7960: reward = -104.32, steps = 26 05:25:44 [INFO] train episode 7961: reward = -148.07, steps = 21 05:25:47 [INFO] train episode 7962: reward = -110.43, steps = 27 05:25:49 [INFO] train episode 7963: reward = -78.39, steps = 28 05:25:52 [INFO] train episode 7964: reward = -82.01, steps = 25 05:25:56 [INFO] train episode 7965: reward = -191.66, steps = 53 05:25:58 [INFO] train episode 7966: reward = -113.10, steps = 27 05:26:01 [INFO] train episode 7967: reward = -108.63, steps = 25 05:26:03 [INFO] train episode 7968: reward = -114.47, steps = 25 05:26:05 [INFO] train episode 7969: reward = -73.02, steps = 20 05:26:07 [INFO] train episode 7970: reward = -112.20, steps = 24 05:26:09 [INFO] train episode 7971: reward = -98.73, steps = 20 05:26:11 [INFO] train episode 7972: reward = -95.86, steps = 23 05:26:14 [INFO] train episode 7973: reward = -152.55, steps = 36 05:26:16 [INFO] train episode 7974: reward = -81.36, steps = 21 05:26:18 [INFO] train episode 7975: reward = -98.80, steps = 32 05:26:20 [INFO] train episode 7976: reward = -110.21, steps = 21 05:26:24 [INFO] train episode 7977: reward = -77.08, steps = 37 05:26:27 [INFO] train episode 7978: reward = -98.10, steps = 33 05:26:30 [INFO] train episode 7979: reward = -95.30, steps = 34 05:26:32 [INFO] train episode 7980: reward = -114.50, steps = 23 05:26:35 [INFO] train episode 7981: reward = -129.72, steps = 40 05:26:37 [INFO] train episode 7982: reward = -112.44, steps = 21 05:26:39 [INFO] train episode 7983: reward = -71.39, steps = 22 05:26:43 [INFO] train episode 7984: reward = -168.64, steps = 40 05:26:44 [INFO] train episode 7985: reward = -80.62, steps = 21 05:26:46 [INFO] train episode 7986: reward = -107.53, steps = 20 05:26:48 [INFO] train episode 7987: reward = -111.74, steps = 23 05:26:51 [INFO] train episode 7988: reward = -160.08, steps = 37 05:26:54 [INFO] train episode 7989: reward = -64.56, steps = 26 05:26:56 [INFO] train episode 7990: reward = -81.08, steps = 26 05:26:59 [INFO] train episode 7991: reward = -92.58, steps = 37 05:27:02 [INFO] train episode 7992: reward = -170.88, steps = 27 05:27:04 [INFO] train episode 7993: reward = -130.08, steps = 27 05:27:07 [INFO] train episode 7994: reward = -141.58, steps = 33 05:27:10 [INFO] train episode 7995: reward = -103.18, steps = 31 05:27:12 [INFO] train episode 7996: reward = -112.03, steps = 19 05:27:14 [INFO] train episode 7997: reward = -66.61, steps = 25 05:27:17 [INFO] train episode 7998: reward = -148.17, steps = 34 05:27:19 [INFO] train episode 7999: reward = -113.28, steps = 25 05:27:22 [INFO] train episode 8000: reward = -97.80, steps = 29 05:27:23 [INFO] train episode 8001: reward = -78.78, steps = 17 05:27:26 [INFO] train episode 8002: reward = -105.94, steps = 30 05:27:28 [INFO] train episode 8003: reward = -76.16, steps = 25 05:27:31 [INFO] train episode 8004: reward = -160.31, steps = 27 05:27:33 [INFO] train episode 8005: reward = -126.96, steps = 23 05:27:35 [INFO] train episode 8006: reward = -56.00, steps = 27 05:27:39 [INFO] train episode 8007: reward = -140.20, steps = 39 05:27:41 [INFO] train episode 8008: reward = -76.02, steps = 27 05:27:43 [INFO] train episode 8009: reward = -90.47, steps = 20 05:27:45 [INFO] train episode 8010: reward = -86.38, steps = 19 05:27:48 [INFO] train episode 8011: reward = -82.89, steps = 35 05:27:49 [INFO] train episode 8012: reward = -74.33, steps = 20 05:27:52 [INFO] train episode 8013: reward = -116.80, steps = 32 05:27:55 [INFO] train episode 8014: reward = -95.07, steps = 34 05:27:58 [INFO] train episode 8015: reward = -113.51, steps = 30 05:28:02 [INFO] train episode 8016: reward = -87.23, steps = 31 05:28:04 [INFO] train episode 8017: reward = -108.90, steps = 31 05:28:06 [INFO] train episode 8018: reward = -83.90, steps = 24 05:28:08 [INFO] train episode 8019: reward = -92.78, steps = 20 05:28:11 [INFO] train episode 8020: reward = -106.61, steps = 41 05:28:14 [INFO] train episode 8021: reward = -89.20, steps = 24 05:28:18 [INFO] train episode 8022: reward = -85.05, steps = 50 05:28:20 [INFO] train episode 8023: reward = -111.85, steps = 25 05:28:22 [INFO] train episode 8024: reward = -70.31, steps = 22 05:28:24 [INFO] train episode 8025: reward = -112.00, steps = 21 05:28:26 [INFO] train episode 8026: reward = -108.95, steps = 22 05:28:28 [INFO] train episode 8027: reward = -106.85, steps = 22 05:28:30 [INFO] train episode 8028: reward = -65.02, steps = 19 05:28:32 [INFO] train episode 8029: reward = -164.07, steps = 20 05:28:34 [INFO] train episode 8030: reward = -117.82, steps = 22 05:28:37 [INFO] train episode 8031: reward = -147.00, steps = 38 05:28:39 [INFO] train episode 8032: reward = -92.48, steps = 21 05:28:41 [INFO] train episode 8033: reward = -98.20, steps = 25 05:28:44 [INFO] train episode 8034: reward = -70.16, steps = 30 05:28:45 [INFO] train episode 8035: reward = -120.61, steps = 20 05:28:49 [INFO] train episode 8036: reward = -135.79, steps = 36 05:28:51 [INFO] train episode 8037: reward = -107.03, steps = 30 05:28:54 [INFO] train episode 8038: reward = -117.65, steps = 35 05:28:58 [INFO] train episode 8039: reward = -119.82, steps = 38 05:29:00 [INFO] train episode 8040: reward = -100.15, steps = 29 05:29:02 [INFO] train episode 8041: reward = -116.87, steps = 19 05:29:04 [INFO] train episode 8042: reward = -115.47, steps = 22 05:29:06 [INFO] train episode 8043: reward = -94.53, steps = 21 05:29:09 [INFO] train episode 8044: reward = -147.47, steps = 26 05:29:12 [INFO] train episode 8045: reward = -108.55, steps = 34 05:29:14 [INFO] train episode 8046: reward = -83.39, steps = 28 05:29:18 [INFO] train episode 8047: reward = -173.60, steps = 47 05:29:21 [INFO] train episode 8048: reward = -110.44, steps = 33 05:29:24 [INFO] train episode 8049: reward = -45.00, steps = 30 05:29:26 [INFO] train episode 8050: reward = -67.81, steps = 23 05:29:28 [INFO] train episode 8051: reward = -123.08, steps = 30 05:29:31 [INFO] train episode 8052: reward = -49.43, steps = 24 05:29:33 [INFO] train episode 8053: reward = -82.69, steps = 31 05:29:35 [INFO] train episode 8054: reward = -88.47, steps = 21 05:29:38 [INFO] train episode 8055: reward = -131.61, steps = 26 05:29:40 [INFO] train episode 8056: reward = -156.75, steps = 24 05:29:42 [INFO] train episode 8057: reward = -96.02, steps = 31 05:29:44 [INFO] train episode 8058: reward = -86.76, steps = 21 05:29:47 [INFO] train episode 8059: reward = -122.95, steps = 32 05:29:49 [INFO] train episode 8060: reward = -159.99, steps = 28 05:29:52 [INFO] train episode 8061: reward = -121.96, steps = 30 05:29:55 [INFO] train episode 8062: reward = -125.08, steps = 26 05:29:58 [INFO] train episode 8063: reward = -95.93, steps = 41 05:30:00 [INFO] train episode 8064: reward = -93.38, steps = 24 05:30:03 [INFO] train episode 8065: reward = -118.72, steps = 28 05:30:05 [INFO] train episode 8066: reward = -111.20, steps = 25 05:30:07 [INFO] train episode 8067: reward = -102.48, steps = 24 05:30:09 [INFO] train episode 8068: reward = -74.60, steps = 20 05:30:12 [INFO] train episode 8069: reward = -126.08, steps = 33 05:30:14 [INFO] train episode 8070: reward = -127.10, steps = 26 05:30:16 [INFO] train episode 8071: reward = -80.48, steps = 25 05:30:19 [INFO] train episode 8072: reward = -114.74, steps = 25 05:30:21 [INFO] train episode 8073: reward = -104.04, steps = 24 05:30:23 [INFO] train episode 8074: reward = -90.95, steps = 29 05:30:25 [INFO] train episode 8075: reward = -69.42, steps = 20 05:30:27 [INFO] train episode 8076: reward = -87.78, steps = 22 05:30:29 [INFO] train episode 8077: reward = -87.98, steps = 24 05:30:32 [INFO] train episode 8078: reward = -96.28, steps = 29 05:30:34 [INFO] train episode 8079: reward = -145.33, steps = 25 05:30:37 [INFO] train episode 8080: reward = -115.33, steps = 31 05:30:39 [INFO] train episode 8081: reward = -102.24, steps = 27 05:30:42 [INFO] train episode 8082: reward = -131.20, steps = 36 05:30:45 [INFO] train episode 8083: reward = -95.17, steps = 32 05:30:49 [INFO] train episode 8084: reward = -99.75, steps = 44 05:30:52 [INFO] train episode 8085: reward = -75.47, steps = 21 05:30:54 [INFO] train episode 8086: reward = -139.92, steps = 25 05:30:58 [INFO] train episode 8087: reward = -79.72, steps = 43 05:31:00 [INFO] train episode 8088: reward = -77.81, steps = 27 05:31:03 [INFO] train episode 8089: reward = -109.76, steps = 33 05:31:06 [INFO] train episode 8090: reward = -80.99, steps = 32 05:31:09 [INFO] train episode 8091: reward = -108.57, steps = 35 05:31:11 [INFO] train episode 8092: reward = -145.78, steps = 26 05:31:14 [INFO] train episode 8093: reward = -106.33, steps = 27 05:31:16 [INFO] train episode 8094: reward = -69.65, steps = 25 05:31:18 [INFO] train episode 8095: reward = -104.81, steps = 24 05:31:20 [INFO] train episode 8096: reward = -77.18, steps = 21 05:31:22 [INFO] train episode 8097: reward = -83.32, steps = 29 05:31:25 [INFO] train episode 8098: reward = -114.73, steps = 32 05:31:28 [INFO] train episode 8099: reward = -68.02, steps = 32 05:31:30 [INFO] train episode 8100: reward = -115.11, steps = 20 05:31:34 [INFO] train episode 8101: reward = -102.50, steps = 43 05:31:36 [INFO] train episode 8102: reward = -89.70, steps = 24 05:31:38 [INFO] train episode 8103: reward = -129.48, steps = 30 05:31:41 [INFO] train episode 8104: reward = -110.43, steps = 34 05:31:45 [INFO] train episode 8105: reward = -54.55, steps = 37 05:31:47 [INFO] train episode 8106: reward = -79.34, steps = 31 05:31:50 [INFO] train episode 8107: reward = -125.72, steps = 30 05:31:52 [INFO] train episode 8108: reward = -96.91, steps = 23 05:31:54 [INFO] train episode 8109: reward = -92.78, steps = 26 05:31:56 [INFO] train episode 8110: reward = -90.18, steps = 22 05:31:58 [INFO] train episode 8111: reward = -95.54, steps = 24 05:32:01 [INFO] train episode 8112: reward = -87.94, steps = 26 05:32:03 [INFO] train episode 8113: reward = -72.16, steps = 22 05:32:05 [INFO] train episode 8114: reward = -86.49, steps = 28 05:32:07 [INFO] train episode 8115: reward = -108.09, steps = 21 05:32:09 [INFO] train episode 8116: reward = -93.97, steps = 19 05:32:11 [INFO] train episode 8117: reward = -102.39, steps = 24 05:32:13 [INFO] train episode 8118: reward = -106.18, steps = 26 05:32:15 [INFO] train episode 8119: reward = -83.18, steps = 24 05:32:17 [INFO] train episode 8120: reward = -107.59, steps = 23 05:32:20 [INFO] train episode 8121: reward = -142.60, steps = 24 05:32:22 [INFO] train episode 8122: reward = -72.03, steps = 28 05:32:25 [INFO] train episode 8123: reward = -193.66, steps = 36 05:32:27 [INFO] train episode 8124: reward = -184.06, steps = 22 05:32:29 [INFO] train episode 8125: reward = -62.16, steps = 19 05:32:30 [INFO] train episode 8126: reward = -83.60, steps = 21 05:32:33 [INFO] train episode 8127: reward = -69.74, steps = 20 05:32:34 [INFO] train episode 8128: reward = -73.83, steps = 22 05:32:36 [INFO] train episode 8129: reward = -96.18, steps = 21 05:32:38 [INFO] train episode 8130: reward = -97.90, steps = 23 05:32:41 [INFO] train episode 8131: reward = -159.51, steps = 30 05:32:43 [INFO] train episode 8132: reward = -59.97, steps = 20 05:32:45 [INFO] train episode 8133: reward = -64.18, steps = 21 05:32:47 [INFO] train episode 8134: reward = -82.94, steps = 26 05:32:49 [INFO] train episode 8135: reward = -89.34, steps = 22 05:32:52 [INFO] train episode 8136: reward = -67.67, steps = 31 05:32:54 [INFO] train episode 8137: reward = -84.89, steps = 20 05:32:57 [INFO] train episode 8138: reward = -144.37, steps = 39 05:32:59 [INFO] train episode 8139: reward = -121.02, steps = 24 05:33:01 [INFO] train episode 8140: reward = -97.16, steps = 23 05:33:03 [INFO] train episode 8141: reward = -84.47, steps = 21 05:33:05 [INFO] train episode 8142: reward = -80.60, steps = 22 05:33:08 [INFO] train episode 8143: reward = -196.04, steps = 34 05:33:10 [INFO] train episode 8144: reward = -78.57, steps = 21 05:33:12 [INFO] train episode 8145: reward = -83.38, steps = 27 05:33:14 [INFO] train episode 8146: reward = -98.13, steps = 25 05:33:17 [INFO] train episode 8147: reward = -114.55, steps = 23 05:33:18 [INFO] train episode 8148: reward = -71.58, steps = 20 05:33:21 [INFO] train episode 8149: reward = -89.76, steps = 27 05:33:24 [INFO] train episode 8150: reward = -160.92, steps = 33 05:33:26 [INFO] train episode 8151: reward = -141.47, steps = 24 05:33:28 [INFO] train episode 8152: reward = -104.65, steps = 20 05:33:30 [INFO] train episode 8153: reward = -154.02, steps = 24 05:33:32 [INFO] train episode 8154: reward = -154.75, steps = 23 05:33:35 [INFO] train episode 8155: reward = -94.44, steps = 31 05:33:38 [INFO] train episode 8156: reward = -129.64, steps = 36 05:33:40 [INFO] train episode 8157: reward = -97.61, steps = 20 05:33:42 [INFO] train episode 8158: reward = -98.09, steps = 25 05:33:46 [INFO] train episode 8159: reward = -115.96, steps = 33 05:33:48 [INFO] train episode 8160: reward = -87.95, steps = 23 05:33:50 [INFO] train episode 8161: reward = -79.34, steps = 26 05:33:52 [INFO] train episode 8162: reward = -72.80, steps = 20 05:33:55 [INFO] train episode 8163: reward = -118.15, steps = 31 05:33:57 [INFO] train episode 8164: reward = -112.30, steps = 23 05:33:59 [INFO] train episode 8165: reward = -87.84, steps = 28 05:34:01 [INFO] train episode 8166: reward = -103.49, steps = 20 05:34:03 [INFO] train episode 8167: reward = -63.24, steps = 21 05:34:04 [INFO] train episode 8168: reward = -79.54, steps = 22 05:34:07 [INFO] train episode 8169: reward = -88.64, steps = 30 05:34:10 [INFO] train episode 8170: reward = -103.22, steps = 25 05:34:12 [INFO] train episode 8171: reward = -88.24, steps = 27 05:34:15 [INFO] train episode 8172: reward = -143.22, steps = 31 05:34:16 [INFO] train episode 8173: reward = -75.33, steps = 19 05:34:18 [INFO] train episode 8174: reward = -82.87, steps = 25 05:34:21 [INFO] train episode 8175: reward = -90.28, steps = 30 05:34:23 [INFO] train episode 8176: reward = -142.54, steps = 25 05:34:25 [INFO] train episode 8177: reward = -75.82, steps = 20 05:34:28 [INFO] train episode 8178: reward = -58.46, steps = 28 05:34:30 [INFO] train episode 8179: reward = -113.75, steps = 26 05:34:32 [INFO] train episode 8180: reward = -108.81, steps = 24 05:34:34 [INFO] train episode 8181: reward = -105.28, steps = 20 05:34:36 [INFO] train episode 8182: reward = -86.26, steps = 22 05:34:38 [INFO] train episode 8183: reward = -90.45, steps = 22 05:34:41 [INFO] train episode 8184: reward = -105.16, steps = 32 05:34:43 [INFO] train episode 8185: reward = -69.73, steps = 23 05:34:45 [INFO] train episode 8186: reward = -92.06, steps = 22 05:34:47 [INFO] train episode 8187: reward = -96.34, steps = 21 05:34:50 [INFO] train episode 8188: reward = -146.23, steps = 36 05:34:52 [INFO] train episode 8189: reward = -147.59, steps = 27 05:34:54 [INFO] train episode 8190: reward = -123.58, steps = 20 05:34:56 [INFO] train episode 8191: reward = -134.90, steps = 27 05:34:58 [INFO] train episode 8192: reward = -50.56, steps = 20 05:35:00 [INFO] train episode 8193: reward = -69.74, steps = 23 05:35:03 [INFO] train episode 8194: reward = -94.24, steps = 34 05:35:05 [INFO] train episode 8195: reward = -75.25, steps = 22 05:35:07 [INFO] train episode 8196: reward = -81.15, steps = 20 05:35:09 [INFO] train episode 8197: reward = -90.51, steps = 21 05:35:11 [INFO] train episode 8198: reward = -65.80, steps = 28 05:35:14 [INFO] train episode 8199: reward = -99.61, steps = 25 05:35:15 [INFO] train episode 8200: reward = -78.05, steps = 19 05:35:18 [INFO] train episode 8201: reward = -86.42, steps = 35 05:35:22 [INFO] train episode 8202: reward = -135.92, steps = 41 05:35:24 [INFO] train episode 8203: reward = -90.96, steps = 24 05:35:26 [INFO] train episode 8204: reward = -61.81, steps = 23 05:35:28 [INFO] train episode 8205: reward = -73.80, steps = 26 05:35:31 [INFO] train episode 8206: reward = -94.15, steps = 34 05:35:34 [INFO] train episode 8207: reward = -100.77, steps = 26 05:35:36 [INFO] train episode 8208: reward = -87.21, steps = 24 05:35:39 [INFO] train episode 8209: reward = -126.13, steps = 40 05:35:42 [INFO] train episode 8210: reward = -92.10, steps = 29 05:35:43 [INFO] train episode 8211: reward = -92.89, steps = 19 05:35:46 [INFO] train episode 8212: reward = -100.66, steps = 28 05:35:49 [INFO] train episode 8213: reward = -82.61, steps = 30 05:35:51 [INFO] train episode 8214: reward = -65.06, steps = 19 05:35:53 [INFO] train episode 8215: reward = -97.69, steps = 24 05:35:56 [INFO] train episode 8216: reward = -146.13, steps = 39 05:35:58 [INFO] train episode 8217: reward = -68.15, steps = 24 05:36:00 [INFO] train episode 8218: reward = -85.84, steps = 23 05:36:02 [INFO] train episode 8219: reward = -138.75, steps = 21 05:36:04 [INFO] train episode 8220: reward = -134.32, steps = 22 05:36:06 [INFO] train episode 8221: reward = -81.23, steps = 21 05:36:09 [INFO] train episode 8222: reward = -115.69, steps = 31 05:36:12 [INFO] train episode 8223: reward = -118.68, steps = 41 05:36:15 [INFO] train episode 8224: reward = -123.08, steps = 34 05:36:18 [INFO] train episode 8225: reward = -88.42, steps = 28 05:36:20 [INFO] train episode 8226: reward = -76.18, steps = 19 05:36:22 [INFO] train episode 8227: reward = -71.93, steps = 21 05:36:24 [INFO] train episode 8228: reward = -96.28, steps = 24 05:36:27 [INFO] train episode 8229: reward = -124.12, steps = 40 05:36:29 [INFO] train episode 8230: reward = -127.39, steps = 24 05:36:31 [INFO] train episode 8231: reward = -60.55, steps = 20 05:36:34 [INFO] train episode 8232: reward = -148.29, steps = 30 05:36:36 [INFO] train episode 8233: reward = -95.46, steps = 28 05:36:39 [INFO] train episode 8234: reward = -79.89, steps = 22 05:36:42 [INFO] train episode 8235: reward = -69.72, steps = 34 05:36:45 [INFO] train episode 8236: reward = -134.74, steps = 30 05:36:46 [INFO] train episode 8237: reward = -83.28, steps = 20 05:36:49 [INFO] train episode 8238: reward = -110.84, steps = 34 05:36:52 [INFO] train episode 8239: reward = -85.92, steps = 24 05:36:54 [INFO] train episode 8240: reward = -74.44, steps = 25 05:36:56 [INFO] train episode 8241: reward = -106.16, steps = 26 05:36:59 [INFO] train episode 8242: reward = -105.73, steps = 30 05:37:01 [INFO] train episode 8243: reward = -75.67, steps = 23 05:37:04 [INFO] train episode 8244: reward = -78.45, steps = 33 05:37:06 [INFO] train episode 8245: reward = -75.08, steps = 26 05:37:08 [INFO] train episode 8246: reward = -84.54, steps = 26 05:37:10 [INFO] train episode 8247: reward = -80.92, steps = 21 05:37:12 [INFO] train episode 8248: reward = -71.96, steps = 23 05:37:14 [INFO] train episode 8249: reward = -68.12, steps = 21 05:37:16 [INFO] train episode 8250: reward = -79.48, steps = 22 05:37:19 [INFO] train episode 8251: reward = -149.27, steps = 37 05:37:21 [INFO] train episode 8252: reward = -64.59, steps = 19 05:37:23 [INFO] train episode 8253: reward = -66.61, steps = 21 05:37:26 [INFO] train episode 8254: reward = -93.16, steps = 28 05:37:27 [INFO] train episode 8255: reward = -83.83, steps = 19 05:37:29 [INFO] train episode 8256: reward = -122.36, steps = 22 05:37:32 [INFO] train episode 8257: reward = -140.67, steps = 27 05:37:33 [INFO] train episode 8258: reward = -90.16, steps = 21 05:37:35 [INFO] train episode 8259: reward = -81.36, steps = 22 05:37:38 [INFO] train episode 8260: reward = -85.60, steps = 25 05:37:40 [INFO] train episode 8261: reward = -103.15, steps = 26 05:37:43 [INFO] train episode 8262: reward = -121.24, steps = 31 05:37:45 [INFO] train episode 8263: reward = -113.32, steps = 28 05:37:47 [INFO] train episode 8264: reward = -138.19, steps = 24 05:37:49 [INFO] train episode 8265: reward = -123.95, steps = 23 05:37:53 [INFO] train episode 8266: reward = -100.55, steps = 39 05:37:56 [INFO] train episode 8267: reward = -88.30, steps = 33 05:37:58 [INFO] train episode 8268: reward = -155.07, steps = 31 05:38:00 [INFO] train episode 8269: reward = -105.48, steps = 23 05:38:02 [INFO] train episode 8270: reward = -81.30, steps = 26 05:38:04 [INFO] train episode 8271: reward = -91.68, steps = 20 05:38:06 [INFO] train episode 8272: reward = -64.86, steps = 18 05:38:09 [INFO] train episode 8273: reward = -135.75, steps = 36 05:38:11 [INFO] train episode 8274: reward = -67.11, steps = 20 05:38:12 [INFO] train episode 8275: reward = -91.19, steps = 19 05:38:14 [INFO] train episode 8276: reward = -102.22, steps = 24 05:38:18 [INFO] train episode 8277: reward = -108.53, steps = 38 05:38:20 [INFO] train episode 8278: reward = -104.00, steps = 27 05:38:22 [INFO] train episode 8279: reward = -104.68, steps = 20 05:38:23 [INFO] train episode 8280: reward = -100.62, steps = 19 05:38:26 [INFO] train episode 8281: reward = -117.88, steps = 29 05:38:28 [INFO] train episode 8282: reward = -82.74, steps = 21 05:38:30 [INFO] train episode 8283: reward = -87.34, steps = 21 05:38:32 [INFO] train episode 8284: reward = -76.88, steps = 30 05:38:34 [INFO] train episode 8285: reward = -95.33, steps = 23 05:38:37 [INFO] train episode 8286: reward = -76.88, steps = 37 05:38:39 [INFO] train episode 8287: reward = -80.73, steps = 26 05:38:42 [INFO] train episode 8288: reward = -62.33, steps = 24 05:38:44 [INFO] train episode 8289: reward = -75.43, steps = 31 05:38:47 [INFO] train episode 8290: reward = -79.21, steps = 29 05:38:49 [INFO] train episode 8291: reward = -94.91, steps = 23 05:38:51 [INFO] train episode 8292: reward = -96.10, steps = 20 05:38:52 [INFO] train episode 8293: reward = -115.69, steps = 20 05:38:54 [INFO] train episode 8294: reward = -85.57, steps = 23 05:38:57 [INFO] train episode 8295: reward = -88.60, steps = 32 05:39:00 [INFO] train episode 8296: reward = -95.55, steps = 29 05:39:02 [INFO] train episode 8297: reward = -87.94, steps = 22 05:39:05 [INFO] train episode 8298: reward = -179.64, steps = 43 05:39:07 [INFO] train episode 8299: reward = -68.03, steps = 22 05:39:09 [INFO] train episode 8300: reward = -69.44, steps = 19 05:39:11 [INFO] train episode 8301: reward = -158.01, steps = 29 05:39:14 [INFO] train episode 8302: reward = -93.17, steps = 28 05:39:16 [INFO] train episode 8303: reward = -110.73, steps = 26 05:39:20 [INFO] train episode 8304: reward = -122.52, steps = 46 05:39:22 [INFO] train episode 8305: reward = -83.93, steps = 25 05:39:24 [INFO] train episode 8306: reward = -84.39, steps = 28 05:39:26 [INFO] train episode 8307: reward = -74.07, steps = 21 05:39:29 [INFO] train episode 8308: reward = -77.47, steps = 25 05:39:32 [INFO] train episode 8309: reward = -76.79, steps = 30 05:39:33 [INFO] train episode 8310: reward = -92.91, steps = 18 05:39:35 [INFO] train episode 8311: reward = -97.18, steps = 22 05:39:37 [INFO] train episode 8312: reward = -108.38, steps = 21 05:39:39 [INFO] train episode 8313: reward = -127.65, steps = 27 05:39:41 [INFO] train episode 8314: reward = -93.68, steps = 21 05:39:43 [INFO] train episode 8315: reward = -101.68, steps = 24 05:39:46 [INFO] train episode 8316: reward = -103.26, steps = 33 05:39:49 [INFO] train episode 8317: reward = -118.32, steps = 27 05:39:51 [INFO] train episode 8318: reward = -56.36, steps = 24 05:39:53 [INFO] train episode 8319: reward = -77.50, steps = 23 05:39:55 [INFO] train episode 8320: reward = -59.88, steps = 28 05:39:57 [INFO] train episode 8321: reward = -94.77, steps = 21 05:39:59 [INFO] train episode 8322: reward = -104.03, steps = 25 05:40:01 [INFO] train episode 8323: reward = -86.59, steps = 19 05:40:04 [INFO] train episode 8324: reward = -127.85, steps = 35 05:40:06 [INFO] train episode 8325: reward = -76.61, steps = 22 05:40:08 [INFO] train episode 8326: reward = -137.81, steps = 26 05:40:09 [INFO] train episode 8327: reward = -71.07, steps = 20 05:40:11 [INFO] train episode 8328: reward = -97.68, steps = 21 05:40:13 [INFO] train episode 8329: reward = -66.15, steps = 20 05:40:15 [INFO] train episode 8330: reward = -91.13, steps = 27 05:40:18 [INFO] train episode 8331: reward = -95.03, steps = 24 05:40:20 [INFO] train episode 8332: reward = -87.40, steps = 27 05:40:23 [INFO] train episode 8333: reward = -106.44, steps = 38 05:40:25 [INFO] train episode 8334: reward = -115.48, steps = 25 05:40:27 [INFO] train episode 8335: reward = -89.32, steps = 21 05:40:29 [INFO] train episode 8336: reward = -120.57, steps = 28 05:40:32 [INFO] train episode 8337: reward = -159.44, steps = 25 05:40:34 [INFO] train episode 8338: reward = -106.55, steps = 21 05:40:36 [INFO] train episode 8339: reward = -85.34, steps = 26 05:40:39 [INFO] train episode 8340: reward = -99.01, steps = 37 05:40:41 [INFO] train episode 8341: reward = -131.72, steps = 25 05:40:43 [INFO] train episode 8342: reward = -112.66, steps = 26 05:40:45 [INFO] train episode 8343: reward = -74.90, steps = 21 05:40:47 [INFO] train episode 8344: reward = -89.96, steps = 23 05:40:50 [INFO] train episode 8345: reward = -104.12, steps = 26 05:40:52 [INFO] train episode 8346: reward = -114.96, steps = 33 05:40:55 [INFO] train episode 8347: reward = -94.95, steps = 28 05:40:57 [INFO] train episode 8348: reward = -96.24, steps = 31 05:40:59 [INFO] train episode 8349: reward = -79.17, steps = 22 05:41:02 [INFO] train episode 8350: reward = -141.50, steps = 32 05:41:04 [INFO] train episode 8351: reward = -57.37, steps = 23 05:41:06 [INFO] train episode 8352: reward = -85.76, steps = 21 05:41:08 [INFO] train episode 8353: reward = -62.84, steps = 20 05:41:10 [INFO] train episode 8354: reward = -93.17, steps = 19 05:41:11 [INFO] train episode 8355: reward = -81.76, steps = 21 05:41:13 [INFO] train episode 8356: reward = -76.62, steps = 19 05:41:15 [INFO] train episode 8357: reward = -117.74, steps = 28 05:41:17 [INFO] train episode 8358: reward = -115.12, steps = 21 05:41:19 [INFO] train episode 8359: reward = -123.19, steps = 19 05:41:21 [INFO] train episode 8360: reward = -86.74, steps = 20 05:41:22 [INFO] train episode 8361: reward = -94.19, steps = 19 05:41:24 [INFO] train episode 8362: reward = -81.02, steps = 19 05:41:26 [INFO] train episode 8363: reward = -82.87, steps = 20 05:41:28 [INFO] train episode 8364: reward = -67.06, steps = 23 05:41:29 [INFO] train episode 8365: reward = -150.43, steps = 19 05:41:32 [INFO] train episode 8366: reward = -94.48, steps = 37 05:41:35 [INFO] train episode 8367: reward = -76.96, steps = 24 05:41:37 [INFO] train episode 8368: reward = -80.15, steps = 25 05:41:39 [INFO] train episode 8369: reward = -91.49, steps = 20 05:41:41 [INFO] train episode 8370: reward = -87.89, steps = 25 05:41:43 [INFO] train episode 8371: reward = -94.34, steps = 20 05:41:44 [INFO] train episode 8372: reward = -69.01, steps = 20 05:41:46 [INFO] train episode 8373: reward = -114.07, steps = 20 05:41:48 [INFO] train episode 8374: reward = -123.47, steps = 25 05:41:50 [INFO] train episode 8375: reward = -123.33, steps = 23 05:41:53 [INFO] train episode 8376: reward = -82.02, steps = 27 05:41:55 [INFO] train episode 8377: reward = -67.18, steps = 28 05:41:57 [INFO] train episode 8378: reward = -76.07, steps = 20 05:41:59 [INFO] train episode 8379: reward = -112.40, steps = 34 05:42:01 [INFO] train episode 8380: reward = -86.23, steps = 24 05:42:05 [INFO] train episode 8381: reward = -72.83, steps = 34 05:42:07 [INFO] train episode 8382: reward = -60.26, steps = 32 05:42:09 [INFO] train episode 8383: reward = -80.14, steps = 20 05:42:11 [INFO] train episode 8384: reward = -70.82, steps = 23 05:42:13 [INFO] train episode 8385: reward = -90.31, steps = 26 05:42:17 [INFO] train episode 8386: reward = -121.59, steps = 34 05:42:19 [INFO] train episode 8387: reward = -78.59, steps = 21 05:42:22 [INFO] train episode 8388: reward = -68.52, steps = 37 05:42:25 [INFO] train episode 8389: reward = -105.56, steps = 27 05:42:27 [INFO] train episode 8390: reward = -59.57, steps = 27 05:42:29 [INFO] train episode 8391: reward = -102.97, steps = 28 05:42:31 [INFO] train episode 8392: reward = -93.21, steps = 21 05:42:33 [INFO] train episode 8393: reward = -70.43, steps = 27 05:42:36 [INFO] train episode 8394: reward = -143.93, steps = 30 05:42:38 [INFO] train episode 8395: reward = -77.67, steps = 20 05:42:40 [INFO] train episode 8396: reward = -115.83, steps = 24 05:42:42 [INFO] train episode 8397: reward = -87.03, steps = 22 05:42:43 [INFO] train episode 8398: reward = -69.51, steps = 19 05:42:46 [INFO] train episode 8399: reward = -94.06, steps = 28 05:42:49 [INFO] train episode 8400: reward = -90.33, steps = 33 05:42:51 [INFO] train episode 8401: reward = -76.37, steps = 25 05:42:53 [INFO] train episode 8402: reward = -62.22, steps = 20 05:42:54 [INFO] train episode 8403: reward = -93.07, steps = 20 05:42:56 [INFO] train episode 8404: reward = -106.51, steps = 20 05:42:58 [INFO] train episode 8405: reward = -101.00, steps = 26 05:43:00 [INFO] train episode 8406: reward = -77.72, steps = 19 05:43:02 [INFO] train episode 8407: reward = -80.21, steps = 21 05:43:05 [INFO] train episode 8408: reward = -111.24, steps = 32 05:43:06 [INFO] train episode 8409: reward = -86.90, steps = 19 05:43:08 [INFO] train episode 8410: reward = -92.56, steps = 21 05:43:11 [INFO] train episode 8411: reward = -88.84, steps = 27 05:43:13 [INFO] train episode 8412: reward = -89.80, steps = 27 05:43:15 [INFO] train episode 8413: reward = -87.96, steps = 28 05:43:18 [INFO] train episode 8414: reward = -106.27, steps = 36 05:43:20 [INFO] train episode 8415: reward = -84.31, steps = 24 05:43:23 [INFO] train episode 8416: reward = -109.98, steps = 31 05:43:26 [INFO] train episode 8417: reward = -98.16, steps = 32 05:43:29 [INFO] train episode 8418: reward = -83.68, steps = 36 05:43:31 [INFO] train episode 8419: reward = -139.49, steps = 21 05:43:32 [INFO] train episode 8420: reward = -122.32, steps = 20 05:43:34 [INFO] train episode 8421: reward = -83.53, steps = 24 05:43:36 [INFO] train episode 8422: reward = -75.59, steps = 19 05:43:39 [INFO] train episode 8423: reward = -90.75, steps = 31 05:43:41 [INFO] train episode 8424: reward = -78.16, steps = 20 05:43:42 [INFO] train episode 8425: reward = -91.80, steps = 20 05:43:46 [INFO] train episode 8426: reward = -121.74, steps = 40 05:43:48 [INFO] train episode 8427: reward = -87.74, steps = 26 05:43:50 [INFO] train episode 8428: reward = -89.05, steps = 21 05:43:52 [INFO] train episode 8429: reward = -69.27, steps = 23 05:43:54 [INFO] train episode 8430: reward = -99.79, steps = 31 05:43:56 [INFO] train episode 8431: reward = -85.43, steps = 19 05:43:58 [INFO] train episode 8432: reward = -89.97, steps = 21 05:44:00 [INFO] train episode 8433: reward = -91.04, steps = 26 05:44:03 [INFO] train episode 8434: reward = -114.59, steps = 33 05:44:06 [INFO] train episode 8435: reward = -115.34, steps = 33 05:44:08 [INFO] train episode 8436: reward = -88.17, steps = 20 05:44:09 [INFO] train episode 8437: reward = -102.34, steps = 19 05:44:12 [INFO] train episode 8438: reward = -106.98, steps = 24 05:44:14 [INFO] train episode 8439: reward = -96.66, steps = 23 05:44:16 [INFO] train episode 8440: reward = -139.62, steps = 29 05:44:18 [INFO] train episode 8441: reward = -86.17, steps = 21 05:44:20 [INFO] train episode 8442: reward = -98.29, steps = 26 05:44:22 [INFO] train episode 8443: reward = -70.55, steps = 20 05:44:24 [INFO] train episode 8444: reward = -84.06, steps = 27 05:44:26 [INFO] train episode 8445: reward = -81.05, steps = 19 05:44:28 [INFO] train episode 8446: reward = -93.08, steps = 20 05:44:31 [INFO] train episode 8447: reward = -93.36, steps = 32 05:44:33 [INFO] train episode 8448: reward = -77.27, steps = 33 05:44:35 [INFO] train episode 8449: reward = -117.95, steps = 22 05:44:37 [INFO] train episode 8450: reward = -98.53, steps = 19 05:44:39 [INFO] train episode 8451: reward = -68.37, steps = 20 05:44:41 [INFO] train episode 8452: reward = -86.03, steps = 20 05:44:43 [INFO] train episode 8453: reward = -121.02, steps = 20 05:44:45 [INFO] train episode 8454: reward = -85.58, steps = 20 05:44:46 [INFO] train episode 8455: reward = -68.01, steps = 22 05:44:48 [INFO] train episode 8456: reward = -103.18, steps = 23 05:44:51 [INFO] train episode 8457: reward = -115.18, steps = 26 05:44:52 [INFO] train episode 8458: reward = -67.65, steps = 21 05:44:55 [INFO] train episode 8459: reward = -62.96, steps = 25 05:44:58 [INFO] train episode 8460: reward = -108.07, steps = 40 05:45:00 [INFO] train episode 8461: reward = -67.16, steps = 21 05:45:02 [INFO] train episode 8462: reward = -118.99, steps = 21 05:45:04 [INFO] train episode 8463: reward = -60.13, steps = 21 05:45:06 [INFO] train episode 8464: reward = -91.26, steps = 20 05:45:08 [INFO] train episode 8465: reward = -63.33, steps = 27 05:45:11 [INFO] train episode 8466: reward = -118.93, steps = 30 05:45:14 [INFO] train episode 8467: reward = -87.28, steps = 30 05:45:16 [INFO] train episode 8468: reward = -74.88, steps = 23 05:45:19 [INFO] train episode 8469: reward = -93.89, steps = 32 05:45:21 [INFO] train episode 8470: reward = -60.97, steps = 19 05:45:24 [INFO] train episode 8471: reward = -135.46, steps = 37 05:45:26 [INFO] train episode 8472: reward = -73.44, steps = 23 05:45:27 [INFO] train episode 8473: reward = -87.35, steps = 21 05:45:29 [INFO] train episode 8474: reward = -84.42, steps = 22 05:45:31 [INFO] train episode 8475: reward = -87.22, steps = 19 05:45:34 [INFO] train episode 8476: reward = -91.24, steps = 27 05:45:37 [INFO] train episode 8477: reward = -79.90, steps = 40 05:45:39 [INFO] train episode 8478: reward = -95.21, steps = 28 05:45:41 [INFO] train episode 8479: reward = -79.13, steps = 19 05:45:43 [INFO] train episode 8480: reward = -143.87, steps = 21 05:45:45 [INFO] train episode 8481: reward = -99.95, steps = 22 05:45:47 [INFO] train episode 8482: reward = -84.17, steps = 25 05:45:49 [INFO] train episode 8483: reward = -80.37, steps = 27 05:45:52 [INFO] train episode 8484: reward = -109.21, steps = 30 05:45:54 [INFO] train episode 8485: reward = -122.40, steps = 25 05:45:56 [INFO] train episode 8486: reward = -86.84, steps = 20 05:45:57 [INFO] train episode 8487: reward = -71.32, steps = 20 05:46:00 [INFO] train episode 8488: reward = -93.71, steps = 32 05:46:04 [INFO] train episode 8489: reward = -74.24, steps = 44 05:46:06 [INFO] train episode 8490: reward = -106.57, steps = 19 05:46:08 [INFO] train episode 8491: reward = -100.04, steps = 21 05:46:10 [INFO] train episode 8492: reward = -101.46, steps = 26 05:46:11 [INFO] train episode 8493: reward = -84.01, steps = 19 05:46:13 [INFO] train episode 8494: reward = -66.38, steps = 20 05:46:15 [INFO] train episode 8495: reward = -77.92, steps = 20 05:46:16 [INFO] train episode 8496: reward = -92.14, steps = 20 05:46:19 [INFO] train episode 8497: reward = -74.89, steps = 28 05:46:21 [INFO] train episode 8498: reward = -80.85, steps = 20 05:46:23 [INFO] train episode 8499: reward = -85.34, steps = 22 05:46:24 [INFO] train episode 8500: reward = -119.42, steps = 19 05:46:26 [INFO] train episode 8501: reward = -77.81, steps = 19 05:46:28 [INFO] train episode 8502: reward = -81.13, steps = 21 05:46:30 [INFO] train episode 8503: reward = -80.47, steps = 26 05:46:32 [INFO] train episode 8504: reward = -96.03, steps = 24 05:46:34 [INFO] train episode 8505: reward = -76.36, steps = 19 05:46:36 [INFO] train episode 8506: reward = -83.13, steps = 24 05:46:38 [INFO] train episode 8507: reward = -85.64, steps = 19 05:46:40 [INFO] train episode 8508: reward = -71.69, steps = 22 05:46:42 [INFO] train episode 8509: reward = -84.38, steps = 27 05:46:44 [INFO] train episode 8510: reward = -71.82, steps = 20 05:46:46 [INFO] train episode 8511: reward = -82.45, steps = 28 05:46:49 [INFO] train episode 8512: reward = -102.85, steps = 29 05:46:51 [INFO] train episode 8513: reward = -92.08, steps = 20 05:46:54 [INFO] train episode 8514: reward = -116.63, steps = 46 05:46:56 [INFO] train episode 8515: reward = -120.15, steps = 24 05:46:58 [INFO] train episode 8516: reward = -137.27, steps = 20 05:47:00 [INFO] train episode 8517: reward = -96.91, steps = 26 05:47:03 [INFO] train episode 8518: reward = -80.55, steps = 25 05:47:05 [INFO] train episode 8519: reward = -73.32, steps = 24 05:47:07 [INFO] train episode 8520: reward = -75.99, steps = 21 05:47:10 [INFO] train episode 8521: reward = -97.24, steps = 34 05:47:12 [INFO] train episode 8522: reward = -69.36, steps = 29 05:47:15 [INFO] train episode 8523: reward = -105.54, steps = 41 05:47:18 [INFO] train episode 8524: reward = -90.62, steps = 25 05:47:19 [INFO] train episode 8525: reward = -87.52, steps = 22 05:47:22 [INFO] train episode 8526: reward = -68.34, steps = 21 05:47:24 [INFO] train episode 8527: reward = -70.73, steps = 25 05:47:26 [INFO] train episode 8528: reward = -81.08, steps = 32 05:47:28 [INFO] train episode 8529: reward = -88.25, steps = 24 05:47:30 [INFO] train episode 8530: reward = -75.58, steps = 20 05:47:32 [INFO] train episode 8531: reward = -126.55, steps = 22 05:47:34 [INFO] train episode 8532: reward = -135.07, steps = 19 05:47:37 [INFO] train episode 8533: reward = -116.74, steps = 30 05:47:39 [INFO] train episode 8534: reward = -89.75, steps = 29 05:47:42 [INFO] train episode 8535: reward = -104.73, steps = 36 05:47:45 [INFO] train episode 8536: reward = -110.67, steps = 30 05:47:47 [INFO] train episode 8537: reward = -97.79, steps = 27 05:47:48 [INFO] train episode 8538: reward = -82.05, steps = 19 05:47:52 [INFO] train episode 8539: reward = -106.99, steps = 37 05:47:54 [INFO] train episode 8540: reward = -112.03, steps = 20 05:47:56 [INFO] train episode 8541: reward = -59.49, steps = 20 05:47:58 [INFO] train episode 8542: reward = -88.31, steps = 24 05:48:00 [INFO] train episode 8543: reward = -100.58, steps = 26 05:48:02 [INFO] train episode 8544: reward = -108.15, steps = 20 05:48:04 [INFO] train episode 8545: reward = -79.04, steps = 20 05:48:06 [INFO] train episode 8546: reward = -85.31, steps = 20 05:48:08 [INFO] train episode 8547: reward = -102.84, steps = 26 05:48:10 [INFO] train episode 8548: reward = -96.32, steps = 20 05:48:12 [INFO] train episode 8549: reward = -76.95, steps = 20 05:48:13 [INFO] train episode 8550: reward = -94.91, steps = 19 05:48:15 [INFO] train episode 8551: reward = -123.47, steps = 26 05:48:17 [INFO] train episode 8552: reward = -70.03, steps = 20 05:48:19 [INFO] train episode 8553: reward = -115.14, steps = 20 05:48:21 [INFO] train episode 8554: reward = -73.16, steps = 20 05:48:23 [INFO] train episode 8555: reward = -120.38, steps = 26 05:48:25 [INFO] train episode 8556: reward = -80.87, steps = 22 05:48:27 [INFO] train episode 8557: reward = -82.98, steps = 23 05:48:28 [INFO] train episode 8558: reward = -94.92, steps = 19 05:48:31 [INFO] train episode 8559: reward = -124.15, steps = 24 05:48:33 [INFO] train episode 8560: reward = -84.12, steps = 24 05:48:34 [INFO] train episode 8561: reward = -105.75, steps = 21 05:48:36 [INFO] train episode 8562: reward = -122.26, steps = 20 05:48:38 [INFO] train episode 8563: reward = -72.05, steps = 24 05:48:42 [INFO] train episode 8564: reward = -95.05, steps = 37 05:48:43 [INFO] train episode 8565: reward = -99.94, steps = 19 05:48:45 [INFO] train episode 8566: reward = -104.85, steps = 21 05:48:47 [INFO] train episode 8567: reward = -120.17, steps = 20 05:48:49 [INFO] train episode 8568: reward = -70.65, steps = 21 05:48:51 [INFO] train episode 8569: reward = -102.08, steps = 25 05:48:53 [INFO] train episode 8570: reward = -112.32, steps = 21 05:48:54 [INFO] train episode 8571: reward = -108.92, steps = 21 05:48:57 [INFO] train episode 8572: reward = -61.00, steps = 23 05:48:59 [INFO] train episode 8573: reward = -74.18, steps = 24 05:49:01 [INFO] train episode 8574: reward = -102.38, steps = 21 05:49:03 [INFO] train episode 8575: reward = -115.30, steps = 26 05:49:06 [INFO] train episode 8576: reward = -107.21, steps = 38 05:49:08 [INFO] train episode 8577: reward = -78.33, steps = 30 05:49:11 [INFO] train episode 8578: reward = -85.06, steps = 21 05:49:13 [INFO] train episode 8579: reward = -96.38, steps = 24 05:49:15 [INFO] train episode 8580: reward = -103.93, steps = 26 05:49:17 [INFO] train episode 8581: reward = -136.97, steps = 23 05:49:19 [INFO] train episode 8582: reward = -130.81, steps = 22 05:49:20 [INFO] train episode 8583: reward = -84.33, steps = 22 05:49:23 [INFO] train episode 8584: reward = -95.33, steps = 27 05:49:24 [INFO] train episode 8585: reward = -82.24, steps = 19 05:49:27 [INFO] train episode 8586: reward = -103.42, steps = 24 05:49:29 [INFO] train episode 8587: reward = -84.93, steps = 30 05:49:32 [INFO] train episode 8588: reward = -81.41, steps = 28 05:49:34 [INFO] train episode 8589: reward = -90.16, steps = 22 05:49:36 [INFO] train episode 8590: reward = -89.35, steps = 31 05:49:38 [INFO] train episode 8591: reward = -77.86, steps = 20 05:49:42 [INFO] train episode 8592: reward = -154.27, steps = 42 05:49:44 [INFO] train episode 8593: reward = -101.60, steps = 22 05:49:46 [INFO] train episode 8594: reward = -88.99, steps = 29 05:49:48 [INFO] train episode 8595: reward = -88.35, steps = 24 05:49:50 [INFO] train episode 8596: reward = -80.62, steps = 20 05:49:52 [INFO] train episode 8597: reward = -162.33, steps = 21 05:49:54 [INFO] train episode 8598: reward = -87.07, steps = 27 05:49:56 [INFO] train episode 8599: reward = -78.30, steps = 19 05:49:58 [INFO] train episode 8600: reward = -90.39, steps = 23 05:50:00 [INFO] train episode 8601: reward = -109.31, steps = 28 05:50:03 [INFO] train episode 8602: reward = -138.09, steps = 37 05:50:06 [INFO] train episode 8603: reward = -82.83, steps = 27 05:50:07 [INFO] train episode 8604: reward = -123.02, steps = 20 05:50:10 [INFO] train episode 8605: reward = -96.61, steps = 27 05:50:12 [INFO] train episode 8606: reward = -84.91, steps = 26 05:50:14 [INFO] train episode 8607: reward = -139.65, steps = 20 05:50:16 [INFO] train episode 8608: reward = -100.96, steps = 25 05:50:18 [INFO] train episode 8609: reward = -99.37, steps = 20 05:50:20 [INFO] train episode 8610: reward = -95.40, steps = 24 05:50:22 [INFO] train episode 8611: reward = -105.63, steps = 20 05:50:23 [INFO] train episode 8612: reward = -94.47, steps = 19 05:50:25 [INFO] train episode 8613: reward = -119.78, steps = 25 05:50:29 [INFO] train episode 8614: reward = -93.88, steps = 35 05:50:30 [INFO] train episode 8615: reward = -95.32, steps = 19 05:50:33 [INFO] train episode 8616: reward = -89.78, steps = 35 05:50:35 [INFO] train episode 8617: reward = -98.91, steps = 23 05:50:37 [INFO] train episode 8618: reward = -117.93, steps = 21 05:50:39 [INFO] train episode 8619: reward = -84.08, steps = 21 05:50:41 [INFO] train episode 8620: reward = -70.78, steps = 23 05:50:43 [INFO] train episode 8621: reward = -116.42, steps = 21 05:50:46 [INFO] train episode 8622: reward = -94.28, steps = 21 05:50:48 [INFO] train episode 8623: reward = -94.75, steps = 32 05:50:50 [INFO] train episode 8624: reward = -98.92, steps = 23 05:50:52 [INFO] train episode 8625: reward = -88.69, steps = 23 05:50:54 [INFO] train episode 8626: reward = -87.26, steps = 19 05:50:56 [INFO] train episode 8627: reward = -61.13, steps = 29 05:50:58 [INFO] train episode 8628: reward = -83.11, steps = 23 05:51:02 [INFO] train episode 8629: reward = -94.57, steps = 36 05:51:03 [INFO] train episode 8630: reward = -130.95, steps = 22 05:51:05 [INFO] train episode 8631: reward = -81.59, steps = 19 05:51:07 [INFO] train episode 8632: reward = -123.17, steps = 27 05:51:10 [INFO] train episode 8633: reward = -79.98, steps = 25 05:51:11 [INFO] train episode 8634: reward = -78.50, steps = 22 05:51:13 [INFO] train episode 8635: reward = -107.24, steps = 22 05:51:16 [INFO] train episode 8636: reward = -82.69, steps = 22 05:51:17 [INFO] train episode 8637: reward = -88.58, steps = 23 05:51:20 [INFO] train episode 8638: reward = -120.27, steps = 36 05:51:23 [INFO] train episode 8639: reward = -138.85, steps = 28 05:51:24 [INFO] train episode 8640: reward = -107.48, steps = 19 05:51:27 [INFO] train episode 8641: reward = -110.64, steps = 24 05:51:29 [INFO] train episode 8642: reward = -74.31, steps = 29 05:51:31 [INFO] train episode 8643: reward = -84.64, steps = 25 05:51:33 [INFO] train episode 8644: reward = -127.80, steps = 21 05:51:35 [INFO] train episode 8645: reward = -96.57, steps = 25 05:51:37 [INFO] train episode 8646: reward = -65.27, steps = 20 05:51:39 [INFO] train episode 8647: reward = -92.41, steps = 19 05:51:40 [INFO] train episode 8648: reward = -87.54, steps = 20 05:51:43 [INFO] train episode 8649: reward = -100.16, steps = 34 05:51:45 [INFO] train episode 8650: reward = -147.65, steps = 19 05:51:48 [INFO] train episode 8651: reward = -103.03, steps = 28 05:51:50 [INFO] train episode 8652: reward = -99.47, steps = 24 05:51:51 [INFO] train episode 8653: reward = -91.85, steps = 20 05:51:54 [INFO] train episode 8654: reward = -115.04, steps = 25 05:51:55 [INFO] train episode 8655: reward = -123.99, steps = 20 05:51:57 [INFO] train episode 8656: reward = -70.50, steps = 22 05:52:00 [INFO] train episode 8657: reward = -76.75, steps = 29 05:52:01 [INFO] train episode 8658: reward = -103.25, steps = 19 05:52:04 [INFO] train episode 8659: reward = -112.67, steps = 33 05:52:06 [INFO] train episode 8660: reward = -78.13, steps = 24 05:52:08 [INFO] train episode 8661: reward = -114.95, steps = 20 05:52:10 [INFO] train episode 8662: reward = -126.73, steps = 21 05:52:12 [INFO] train episode 8663: reward = -83.22, steps = 19 05:52:13 [INFO] train episode 8664: reward = -83.46, steps = 19 05:52:15 [INFO] train episode 8665: reward = -101.30, steps = 21 05:52:17 [INFO] train episode 8666: reward = -86.93, steps = 23 05:52:19 [INFO] train episode 8667: reward = -78.99, steps = 22 05:52:21 [INFO] train episode 8668: reward = -106.76, steps = 25 05:52:23 [INFO] train episode 8669: reward = -107.02, steps = 21 05:52:25 [INFO] train episode 8670: reward = -104.55, steps = 23 05:52:27 [INFO] train episode 8671: reward = -106.64, steps = 23 05:52:29 [INFO] train episode 8672: reward = -92.93, steps = 28 05:52:31 [INFO] train episode 8673: reward = -99.27, steps = 20 05:52:33 [INFO] train episode 8674: reward = -120.69, steps = 21 05:52:36 [INFO] train episode 8675: reward = -77.63, steps = 28 05:52:37 [INFO] train episode 8676: reward = -72.32, steps = 19 05:52:39 [INFO] train episode 8677: reward = -105.85, steps = 19 05:52:41 [INFO] train episode 8678: reward = -74.91, steps = 21 05:52:43 [INFO] train episode 8679: reward = -102.09, steps = 27 05:52:45 [INFO] train episode 8680: reward = -80.86, steps = 20 05:52:47 [INFO] train episode 8681: reward = -90.79, steps = 30 05:52:50 [INFO] train episode 8682: reward = -95.97, steps = 30 05:52:52 [INFO] train episode 8683: reward = -73.22, steps = 28 05:52:56 [INFO] train episode 8684: reward = -160.15, steps = 36 05:52:57 [INFO] train episode 8685: reward = -92.93, steps = 22 05:53:00 [INFO] train episode 8686: reward = -93.24, steps = 32 05:53:02 [INFO] train episode 8687: reward = -118.23, steps = 28 05:53:04 [INFO] train episode 8688: reward = -78.24, steps = 22 05:53:07 [INFO] train episode 8689: reward = -75.77, steps = 29 05:53:09 [INFO] train episode 8690: reward = -92.38, steps = 21 05:53:11 [INFO] train episode 8691: reward = -90.62, steps = 19 05:53:12 [INFO] train episode 8692: reward = -75.13, steps = 21 05:53:15 [INFO] train episode 8693: reward = -84.32, steps = 31 05:53:17 [INFO] train episode 8694: reward = -80.26, steps = 19 05:53:18 [INFO] train episode 8695: reward = -74.09, steps = 21 05:53:22 [INFO] train episode 8696: reward = -110.15, steps = 38 05:53:24 [INFO] train episode 8697: reward = -59.96, steps = 21 05:53:26 [INFO] train episode 8698: reward = -76.88, steps = 25 05:53:28 [INFO] train episode 8699: reward = -116.35, steps = 23 05:53:30 [INFO] train episode 8700: reward = -76.87, steps = 20 05:53:31 [INFO] train episode 8701: reward = -93.01, steps = 22 05:53:35 [INFO] train episode 8702: reward = -120.07, steps = 33 05:53:37 [INFO] train episode 8703: reward = -82.06, steps = 19 05:53:39 [INFO] train episode 8704: reward = -106.92, steps = 19 05:53:41 [INFO] train episode 8705: reward = -144.17, steps = 28 05:53:43 [INFO] train episode 8706: reward = -78.19, steps = 20 05:53:44 [INFO] train episode 8707: reward = -174.90, steps = 20 05:53:46 [INFO] train episode 8708: reward = -98.03, steps = 22 05:53:48 [INFO] train episode 8709: reward = -76.41, steps = 19 05:53:50 [INFO] train episode 8710: reward = -118.23, steps = 28 05:53:52 [INFO] train episode 8711: reward = -77.04, steps = 21 05:53:54 [INFO] train episode 8712: reward = -81.60, steps = 22 05:53:57 [INFO] train episode 8713: reward = -119.39, steps = 29 05:53:59 [INFO] train episode 8714: reward = -65.07, steps = 24 05:54:01 [INFO] train episode 8715: reward = -73.12, steps = 21 05:54:02 [INFO] train episode 8716: reward = -80.53, steps = 21 05:54:05 [INFO] train episode 8717: reward = -81.48, steps = 28 05:54:06 [INFO] train episode 8718: reward = -80.47, steps = 19 05:54:09 [INFO] train episode 8719: reward = -95.11, steps = 26 05:54:11 [INFO] train episode 8720: reward = -127.04, steps = 30 05:54:13 [INFO] train episode 8721: reward = -58.35, steps = 20 05:54:15 [INFO] train episode 8722: reward = -101.05, steps = 18 05:54:17 [INFO] train episode 8723: reward = -86.96, steps = 24 05:54:19 [INFO] train episode 8724: reward = -91.82, steps = 23 05:54:21 [INFO] train episode 8725: reward = -123.91, steps = 31 05:54:24 [INFO] train episode 8726: reward = -103.74, steps = 27 05:54:27 [INFO] train episode 8727: reward = -158.32, steps = 31 05:54:29 [INFO] train episode 8728: reward = -103.84, steps = 30 05:54:31 [INFO] train episode 8729: reward = -97.18, steps = 21 05:54:33 [INFO] train episode 8730: reward = -70.73, steps = 20 05:54:34 [INFO] train episode 8731: reward = -75.66, steps = 19 05:54:37 [INFO] train episode 8732: reward = -87.27, steps = 24 05:54:39 [INFO] train episode 8733: reward = -152.41, steps = 31 05:54:42 [INFO] train episode 8734: reward = -108.28, steps = 28 05:54:45 [INFO] train episode 8735: reward = -98.83, steps = 34 05:54:48 [INFO] train episode 8736: reward = -121.43, steps = 25 05:54:50 [INFO] train episode 8737: reward = -84.32, steps = 19 05:54:52 [INFO] train episode 8738: reward = -101.98, steps = 22 05:54:54 [INFO] train episode 8739: reward = -122.12, steps = 18 05:54:56 [INFO] train episode 8740: reward = -87.72, steps = 23 05:54:58 [INFO] train episode 8741: reward = -102.84, steps = 19 05:55:00 [INFO] train episode 8742: reward = -88.04, steps = 23 05:55:04 [INFO] train episode 8743: reward = -179.71, steps = 36 05:55:07 [INFO] train episode 8744: reward = -148.48, steps = 33 05:55:09 [INFO] train episode 8745: reward = -123.29, steps = 23 05:55:11 [INFO] train episode 8746: reward = -92.05, steps = 24 05:55:13 [INFO] train episode 8747: reward = -95.13, steps = 21 05:55:16 [INFO] train episode 8748: reward = -105.56, steps = 23 05:55:17 [INFO] train episode 8749: reward = -76.51, steps = 21 05:55:19 [INFO] train episode 8750: reward = -87.95, steps = 20 05:55:21 [INFO] train episode 8751: reward = -112.89, steps = 24 05:55:23 [INFO] train episode 8752: reward = -105.93, steps = 19 05:55:25 [INFO] train episode 8753: reward = -93.13, steps = 21 05:55:27 [INFO] train episode 8754: reward = -104.77, steps = 32 05:55:29 [INFO] train episode 8755: reward = -68.47, steps = 21 05:55:32 [INFO] train episode 8756: reward = -63.45, steps = 27 05:55:33 [INFO] train episode 8757: reward = -84.04, steps = 20 05:55:35 [INFO] train episode 8758: reward = -75.26, steps = 24 05:55:37 [INFO] train episode 8759: reward = -73.90, steps = 20 05:55:39 [INFO] train episode 8760: reward = -84.81, steps = 20 05:55:41 [INFO] train episode 8761: reward = -76.29, steps = 20 05:55:42 [INFO] train episode 8762: reward = -104.49, steps = 20 05:55:44 [INFO] train episode 8763: reward = -102.46, steps = 25 05:55:46 [INFO] train episode 8764: reward = -82.94, steps = 21 05:55:48 [INFO] train episode 8765: reward = -87.68, steps = 21 05:55:51 [INFO] train episode 8766: reward = -105.59, steps = 36 05:55:53 [INFO] train episode 8767: reward = -69.26, steps = 21 05:55:55 [INFO] train episode 8768: reward = -110.51, steps = 25 05:55:57 [INFO] train episode 8769: reward = -92.32, steps = 19 05:55:59 [INFO] train episode 8770: reward = -86.96, steps = 20 05:56:00 [INFO] train episode 8771: reward = -84.03, steps = 20 05:56:02 [INFO] train episode 8772: reward = -78.32, steps = 19 05:56:04 [INFO] train episode 8773: reward = -75.88, steps = 20 05:56:06 [INFO] train episode 8774: reward = -93.72, steps = 23 05:56:08 [INFO] train episode 8775: reward = -128.41, steps = 21 05:56:09 [INFO] train episode 8776: reward = -97.36, steps = 20 05:56:12 [INFO] train episode 8777: reward = -128.25, steps = 24 05:56:13 [INFO] train episode 8778: reward = -85.45, steps = 20 05:56:15 [INFO] train episode 8779: reward = -120.22, steps = 23 05:56:17 [INFO] train episode 8780: reward = -76.57, steps = 19 05:56:20 [INFO] train episode 8781: reward = -76.06, steps = 32 05:56:22 [INFO] train episode 8782: reward = -130.87, steps = 29 05:56:25 [INFO] train episode 8783: reward = -115.57, steps = 32 05:56:28 [INFO] train episode 8784: reward = -94.03, steps = 22 05:56:30 [INFO] train episode 8785: reward = -88.29, steps = 25 05:56:32 [INFO] train episode 8786: reward = -94.11, steps = 29 05:56:35 [INFO] train episode 8787: reward = -86.29, steps = 30 05:56:37 [INFO] train episode 8788: reward = -119.39, steps = 24 05:56:39 [INFO] train episode 8789: reward = -100.31, steps = 25 05:56:41 [INFO] train episode 8790: reward = -82.03, steps = 19 05:56:43 [INFO] train episode 8791: reward = -102.43, steps = 24 05:56:46 [INFO] train episode 8792: reward = -92.25, steps = 31 05:56:50 [INFO] train episode 8793: reward = -91.66, steps = 50 05:56:52 [INFO] train episode 8794: reward = -115.76, steps = 22 05:56:54 [INFO] train episode 8795: reward = -81.63, steps = 19 05:56:56 [INFO] train episode 8796: reward = -102.39, steps = 27 05:56:58 [INFO] train episode 8797: reward = -72.03, steps = 24 05:57:00 [INFO] train episode 8798: reward = -92.43, steps = 20 05:57:02 [INFO] train episode 8799: reward = -84.78, steps = 25 05:57:03 [INFO] train episode 8800: reward = -96.47, steps = 20 05:57:06 [INFO] train episode 8801: reward = -98.54, steps = 24 05:57:08 [INFO] train episode 8802: reward = -71.73, steps = 21 05:57:10 [INFO] train episode 8803: reward = -95.95, steps = 26 05:57:13 [INFO] train episode 8804: reward = -112.73, steps = 34 05:57:15 [INFO] train episode 8805: reward = -79.99, steps = 20 05:57:16 [INFO] train episode 8806: reward = -78.85, steps = 20 05:57:19 [INFO] train episode 8807: reward = -125.38, steps = 26 05:57:21 [INFO] train episode 8808: reward = -100.28, steps = 23 05:57:23 [INFO] train episode 8809: reward = -92.27, steps = 29 05:57:25 [INFO] train episode 8810: reward = -74.19, steps = 19 05:57:27 [INFO] train episode 8811: reward = -83.60, steps = 25 05:57:29 [INFO] train episode 8812: reward = -111.07, steps = 20 05:57:30 [INFO] train episode 8813: reward = -89.33, steps = 20 05:57:34 [INFO] train episode 8814: reward = -191.96, steps = 39 05:57:35 [INFO] train episode 8815: reward = -120.45, steps = 20 05:57:38 [INFO] train episode 8816: reward = -78.24, steps = 19 05:57:39 [INFO] train episode 8817: reward = -99.42, steps = 21 05:57:42 [INFO] train episode 8818: reward = -97.10, steps = 30 05:57:44 [INFO] train episode 8819: reward = -118.54, steps = 22 05:57:46 [INFO] train episode 8820: reward = -121.43, steps = 29 05:57:48 [INFO] train episode 8821: reward = -91.01, steps = 20 05:57:50 [INFO] train episode 8822: reward = -96.24, steps = 26 05:57:52 [INFO] train episode 8823: reward = -98.36, steps = 19 05:57:54 [INFO] train episode 8824: reward = -68.77, steps = 19 05:57:56 [INFO] train episode 8825: reward = -90.25, steps = 23 05:57:57 [INFO] train episode 8826: reward = -75.52, steps = 19 05:57:59 [INFO] train episode 8827: reward = -97.82, steps = 26 05:58:01 [INFO] train episode 8828: reward = -115.39, steps = 20 05:58:03 [INFO] train episode 8829: reward = -115.77, steps = 22 05:58:05 [INFO] train episode 8830: reward = -100.49, steps = 27 05:58:07 [INFO] train episode 8831: reward = -79.06, steps = 20 05:58:09 [INFO] train episode 8832: reward = -94.11, steps = 21 05:58:11 [INFO] train episode 8833: reward = -84.30, steps = 22 05:58:13 [INFO] train episode 8834: reward = -86.54, steps = 27 05:58:15 [INFO] train episode 8835: reward = -122.02, steps = 20 05:58:17 [INFO] train episode 8836: reward = -93.33, steps = 20 05:58:18 [INFO] train episode 8837: reward = -78.81, steps = 20 05:58:21 [INFO] train episode 8838: reward = -132.30, steps = 29 05:58:23 [INFO] train episode 8839: reward = -132.81, steps = 21 05:58:25 [INFO] train episode 8840: reward = -85.76, steps = 24 05:58:27 [INFO] train episode 8841: reward = -84.92, steps = 21 05:58:29 [INFO] train episode 8842: reward = -114.57, steps = 21 05:58:30 [INFO] train episode 8843: reward = -84.88, steps = 19 05:58:32 [INFO] train episode 8844: reward = -92.96, steps = 20 05:58:34 [INFO] train episode 8845: reward = -104.82, steps = 22 05:58:36 [INFO] train episode 8846: reward = -82.44, steps = 20 05:58:38 [INFO] train episode 8847: reward = -76.96, steps = 23 05:58:40 [INFO] train episode 8848: reward = -67.06, steps = 20 05:58:42 [INFO] train episode 8849: reward = -65.80, steps = 20 05:58:44 [INFO] train episode 8850: reward = -87.74, steps = 20 05:58:46 [INFO] train episode 8851: reward = -100.65, steps = 27 05:58:48 [INFO] train episode 8852: reward = -85.39, steps = 20 05:58:50 [INFO] train episode 8853: reward = -101.73, steps = 21 05:58:53 [INFO] train episode 8854: reward = -138.66, steps = 29 05:58:56 [INFO] train episode 8855: reward = -57.62, steps = 25 05:58:59 [INFO] train episode 8856: reward = -87.51, steps = 29 05:59:02 [INFO] train episode 8857: reward = -111.41, steps = 27 05:59:04 [INFO] train episode 8858: reward = -81.52, steps = 19 05:59:05 [INFO] train episode 8859: reward = -70.90, steps = 19 05:59:08 [INFO] train episode 8860: reward = -106.41, steps = 24 05:59:10 [INFO] train episode 8861: reward = -97.49, steps = 27 05:59:13 [INFO] train episode 8862: reward = -100.57, steps = 31 05:59:16 [INFO] train episode 8863: reward = -81.49, steps = 27 05:59:18 [INFO] train episode 8864: reward = -84.51, steps = 21 05:59:20 [INFO] train episode 8865: reward = -68.83, steps = 19 05:59:23 [INFO] train episode 8866: reward = -136.31, steps = 29 05:59:25 [INFO] train episode 8867: reward = -122.28, steps = 20 05:59:27 [INFO] train episode 8868: reward = -83.71, steps = 22 05:59:29 [INFO] train episode 8869: reward = -94.61, steps = 19 05:59:31 [INFO] train episode 8870: reward = -83.47, steps = 24 05:59:33 [INFO] train episode 8871: reward = -77.11, steps = 20 05:59:35 [INFO] train episode 8872: reward = -129.72, steps = 20 05:59:38 [INFO] train episode 8873: reward = -96.40, steps = 24 05:59:40 [INFO] train episode 8874: reward = -100.91, steps = 23 05:59:42 [INFO] train episode 8875: reward = -96.50, steps = 22 05:59:45 [INFO] train episode 8876: reward = -121.91, steps = 28 05:59:46 [INFO] train episode 8877: reward = -74.50, steps = 20 05:59:48 [INFO] train episode 8878: reward = -88.28, steps = 19 05:59:51 [INFO] train episode 8879: reward = -62.24, steps = 25 05:59:53 [INFO] train episode 8880: reward = -116.07, steps = 22 05:59:55 [INFO] train episode 8881: reward = -91.47, steps = 24 05:59:58 [INFO] train episode 8882: reward = -90.72, steps = 23 05:59:59 [INFO] train episode 8883: reward = -73.52, steps = 19 06:00:01 [INFO] train episode 8884: reward = -72.31, steps = 20 06:00:03 [INFO] train episode 8885: reward = -117.46, steps = 20 06:00:05 [INFO] train episode 8886: reward = -81.82, steps = 20 06:00:07 [INFO] train episode 8887: reward = -92.44, steps = 20 06:00:10 [INFO] train episode 8888: reward = -109.22, steps = 28 06:00:12 [INFO] train episode 8889: reward = -59.53, steps = 21 06:00:14 [INFO] train episode 8890: reward = -98.29, steps = 19 06:00:16 [INFO] train episode 8891: reward = -83.99, steps = 19 06:00:18 [INFO] train episode 8892: reward = -104.93, steps = 19 06:00:20 [INFO] train episode 8893: reward = -96.36, steps = 20 06:00:23 [INFO] train episode 8894: reward = -98.85, steps = 35 06:00:26 [INFO] train episode 8895: reward = -123.55, steps = 27 06:00:28 [INFO] train episode 8896: reward = -77.86, steps = 18 06:00:30 [INFO] train episode 8897: reward = -90.42, steps = 29 06:00:33 [INFO] train episode 8898: reward = -103.64, steps = 32 06:00:35 [INFO] train episode 8899: reward = -91.68, steps = 21 06:00:38 [INFO] train episode 8900: reward = -77.88, steps = 30 06:00:40 [INFO] train episode 8901: reward = -76.57, steps = 20 06:00:42 [INFO] train episode 8902: reward = -141.72, steps = 21 06:00:44 [INFO] train episode 8903: reward = -74.59, steps = 19 06:00:46 [INFO] train episode 8904: reward = -100.37, steps = 19 06:00:48 [INFO] train episode 8905: reward = -87.87, steps = 23 06:00:50 [INFO] train episode 8906: reward = -78.34, steps = 19 06:00:52 [INFO] train episode 8907: reward = -106.88, steps = 22 06:00:54 [INFO] train episode 8908: reward = -150.93, steps = 24 06:00:56 [INFO] train episode 8909: reward = -132.87, steps = 24 06:00:59 [INFO] train episode 8910: reward = -67.15, steps = 23 06:01:02 [INFO] train episode 8911: reward = -117.17, steps = 28 06:01:04 [INFO] train episode 8912: reward = -117.95, steps = 26 06:01:06 [INFO] train episode 8913: reward = -101.94, steps = 19 06:01:08 [INFO] train episode 8914: reward = -107.97, steps = 20 06:01:10 [INFO] train episode 8915: reward = -90.16, steps = 23 06:01:12 [INFO] train episode 8916: reward = -102.80, steps = 19 06:01:14 [INFO] train episode 8917: reward = -102.65, steps = 25 06:01:17 [INFO] train episode 8918: reward = -85.98, steps = 29 06:01:19 [INFO] train episode 8919: reward = -85.82, steps = 19 06:01:21 [INFO] train episode 8920: reward = -96.60, steps = 19 06:01:22 [INFO] train episode 8921: reward = -97.27, steps = 19 06:01:25 [INFO] train episode 8922: reward = -149.35, steps = 25 06:01:27 [INFO] train episode 8923: reward = -109.48, steps = 20 06:01:29 [INFO] train episode 8924: reward = -90.52, steps = 20 06:01:31 [INFO] train episode 8925: reward = -74.35, steps = 21 06:01:33 [INFO] train episode 8926: reward = -71.50, steps = 21 06:01:34 [INFO] train episode 8927: reward = -92.94, steps = 19 06:01:37 [INFO] train episode 8928: reward = -108.05, steps = 21 06:01:38 [INFO] train episode 8929: reward = -94.42, steps = 19 06:01:40 [INFO] train episode 8930: reward = -95.72, steps = 19 06:01:43 [INFO] train episode 8931: reward = -76.49, steps = 26 06:01:45 [INFO] train episode 8932: reward = -99.48, steps = 27 06:01:48 [INFO] train episode 8933: reward = -100.75, steps = 28 06:01:50 [INFO] train episode 8934: reward = -83.10, steps = 20 06:01:52 [INFO] train episode 8935: reward = -103.21, steps = 25 06:01:54 [INFO] train episode 8936: reward = -87.77, steps = 20 06:01:56 [INFO] train episode 8937: reward = -94.40, steps = 20 06:01:57 [INFO] train episode 8938: reward = -96.47, steps = 19 06:01:59 [INFO] train episode 8939: reward = -134.08, steps = 21 06:02:02 [INFO] train episode 8940: reward = -110.28, steps = 25 06:02:05 [INFO] train episode 8941: reward = -114.05, steps = 37 06:02:07 [INFO] train episode 8942: reward = -78.49, steps = 23 06:02:09 [INFO] train episode 8943: reward = -138.43, steps = 20 06:02:11 [INFO] train episode 8944: reward = -82.23, steps = 19 06:02:14 [INFO] train episode 8945: reward = -80.59, steps = 30 06:02:16 [INFO] train episode 8946: reward = -107.08, steps = 25 06:02:18 [INFO] train episode 8947: reward = -73.44, steps = 19 06:02:20 [INFO] train episode 8948: reward = -67.27, steps = 19 06:02:22 [INFO] train episode 8949: reward = -88.85, steps = 19 06:02:24 [INFO] train episode 8950: reward = -111.91, steps = 32 06:02:29 [INFO] train episode 8951: reward = -95.17, steps = 41 06:02:31 [INFO] train episode 8952: reward = -91.71, steps = 21 06:02:33 [INFO] train episode 8953: reward = -98.90, steps = 21 06:02:35 [INFO] train episode 8954: reward = -102.66, steps = 18 06:02:37 [INFO] train episode 8955: reward = -81.44, steps = 20 06:02:40 [INFO] train episode 8956: reward = -123.78, steps = 36 06:02:42 [INFO] train episode 8957: reward = -100.89, steps = 21 06:02:44 [INFO] train episode 8958: reward = -99.70, steps = 22 06:02:46 [INFO] train episode 8959: reward = -128.76, steps = 21 06:02:48 [INFO] train episode 8960: reward = -121.92, steps = 19 06:02:50 [INFO] train episode 8961: reward = -93.27, steps = 26 06:02:53 [INFO] train episode 8962: reward = -90.51, steps = 22 06:02:54 [INFO] train episode 8963: reward = -102.44, steps = 20 06:02:56 [INFO] train episode 8964: reward = -108.94, steps = 21 06:02:58 [INFO] train episode 8965: reward = -99.66, steps = 19 06:03:00 [INFO] train episode 8966: reward = -73.80, steps = 20 06:03:02 [INFO] train episode 8967: reward = -74.01, steps = 19 06:03:04 [INFO] train episode 8968: reward = -102.21, steps = 20 06:03:06 [INFO] train episode 8969: reward = -87.42, steps = 21 06:03:08 [INFO] train episode 8970: reward = -131.77, steps = 19 06:03:11 [INFO] train episode 8971: reward = -82.78, steps = 27 06:03:13 [INFO] train episode 8972: reward = -77.10, steps = 19 06:03:14 [INFO] train episode 8973: reward = -89.56, steps = 19 06:03:17 [INFO] train episode 8974: reward = -156.07, steps = 23 06:03:19 [INFO] train episode 8975: reward = -75.42, steps = 21 06:03:21 [INFO] train episode 8976: reward = -111.87, steps = 19 06:03:23 [INFO] train episode 8977: reward = -105.64, steps = 20 06:03:25 [INFO] train episode 8978: reward = -66.66, steps = 20 06:03:27 [INFO] train episode 8979: reward = -74.65, steps = 22 06:03:29 [INFO] train episode 8980: reward = -85.42, steps = 24 06:03:31 [INFO] train episode 8981: reward = -74.13, steps = 25 06:03:33 [INFO] train episode 8982: reward = -118.15, steps = 19 06:03:36 [INFO] train episode 8983: reward = -112.38, steps = 22 06:03:37 [INFO] train episode 8984: reward = -79.26, steps = 22 06:03:40 [INFO] train episode 8985: reward = -130.47, steps = 30 06:03:42 [INFO] train episode 8986: reward = -94.24, steps = 24 06:03:44 [INFO] train episode 8987: reward = -84.03, steps = 21 06:03:46 [INFO] train episode 8988: reward = -75.59, steps = 21 06:03:47 [INFO] train episode 8989: reward = -65.41, steps = 19 06:03:49 [INFO] train episode 8990: reward = -102.67, steps = 20 06:03:51 [INFO] train episode 8991: reward = -69.42, steps = 22 06:03:53 [INFO] train episode 8992: reward = -101.86, steps = 24 06:03:56 [INFO] train episode 8993: reward = -96.32, steps = 34 06:03:58 [INFO] train episode 8994: reward = -84.83, steps = 21 06:03:59 [INFO] train episode 8995: reward = -105.81, steps = 19 06:04:02 [INFO] train episode 8996: reward = -108.62, steps = 25 06:04:04 [INFO] train episode 8997: reward = -70.52, steps = 25 06:04:06 [INFO] train episode 8998: reward = -91.81, steps = 22 06:04:09 [INFO] train episode 8999: reward = -90.65, steps = 30 06:04:11 [INFO] train episode 9000: reward = -95.96, steps = 27 06:04:12 [INFO] train episode 9001: reward = -117.22, steps = 19 06:04:14 [INFO] train episode 9002: reward = -82.31, steps = 19 06:04:16 [INFO] train episode 9003: reward = -97.12, steps = 19 06:04:17 [INFO] train episode 9004: reward = -119.06, steps = 20 06:04:19 [INFO] train episode 9005: reward = -85.83, steps = 20 06:04:21 [INFO] train episode 9006: reward = -102.19, steps = 19 06:04:23 [INFO] train episode 9007: reward = -125.73, steps = 26 06:04:25 [INFO] train episode 9008: reward = -77.25, steps = 24 06:04:28 [INFO] train episode 9009: reward = -155.43, steps = 27 06:04:29 [INFO] train episode 9010: reward = -90.38, steps = 21 06:04:31 [INFO] train episode 9011: reward = -74.15, steps = 20 06:04:33 [INFO] train episode 9012: reward = -111.88, steps = 20 06:04:35 [INFO] train episode 9013: reward = -95.49, steps = 22 06:04:37 [INFO] train episode 9014: reward = -77.32, steps = 22 06:04:39 [INFO] train episode 9015: reward = -100.94, steps = 20 06:04:40 [INFO] train episode 9016: reward = -79.75, steps = 19 06:04:42 [INFO] train episode 9017: reward = -84.49, steps = 20 06:04:44 [INFO] train episode 9018: reward = -143.17, steps = 25 06:04:47 [INFO] train episode 9019: reward = -89.85, steps = 33 06:04:49 [INFO] train episode 9020: reward = -143.01, steps = 22 06:04:51 [INFO] train episode 9021: reward = -181.84, steps = 28 06:04:53 [INFO] train episode 9022: reward = -104.72, steps = 19 06:04:56 [INFO] train episode 9023: reward = -121.49, steps = 29 06:04:57 [INFO] train episode 9024: reward = -83.87, steps = 19 06:04:59 [INFO] train episode 9025: reward = -62.93, steps = 19 06:05:01 [INFO] train episode 9026: reward = -81.90, steps = 19 06:05:03 [INFO] train episode 9027: reward = -90.33, steps = 23 06:05:04 [INFO] train episode 9028: reward = -77.38, steps = 20 06:05:06 [INFO] train episode 9029: reward = -110.91, steps = 21 06:05:09 [INFO] train episode 9030: reward = -102.66, steps = 29 06:05:10 [INFO] train episode 9031: reward = -120.25, steps = 18 06:05:12 [INFO] train episode 9032: reward = -89.83, steps = 21 06:05:14 [INFO] train episode 9033: reward = -158.21, steps = 25 06:05:17 [INFO] train episode 9034: reward = -71.14, steps = 27 06:05:18 [INFO] train episode 9035: reward = -99.42, steps = 20 06:05:20 [INFO] train episode 9036: reward = -98.80, steps = 20 06:05:22 [INFO] train episode 9037: reward = -120.23, steps = 23 06:05:24 [INFO] train episode 9038: reward = -73.51, steps = 19 06:05:28 [INFO] train episode 9039: reward = -90.40, steps = 34 06:05:29 [INFO] train episode 9040: reward = -85.18, steps = 20 06:05:31 [INFO] train episode 9041: reward = -109.73, steps = 20 06:05:33 [INFO] train episode 9042: reward = -94.22, steps = 19 06:05:34 [INFO] train episode 9043: reward = -80.49, steps = 19 06:05:36 [INFO] train episode 9044: reward = -75.06, steps = 20 06:05:38 [INFO] train episode 9045: reward = -92.21, steps = 19 06:05:40 [INFO] train episode 9046: reward = -81.57, steps = 26 06:05:42 [INFO] train episode 9047: reward = -101.42, steps = 19 06:05:44 [INFO] train episode 9048: reward = -84.26, steps = 20 06:05:45 [INFO] train episode 9049: reward = -97.04, steps = 19 06:05:47 [INFO] train episode 9050: reward = -86.97, steps = 23 06:05:50 [INFO] train episode 9051: reward = -82.48, steps = 29 06:05:51 [INFO] train episode 9052: reward = -90.54, steps = 19 06:05:53 [INFO] train episode 9053: reward = -102.73, steps = 22 06:05:55 [INFO] train episode 9054: reward = -105.18, steps = 20 06:05:57 [INFO] train episode 9055: reward = -88.57, steps = 20 06:05:59 [INFO] train episode 9056: reward = -100.90, steps = 25 06:06:02 [INFO] train episode 9057: reward = -77.59, steps = 34 06:06:03 [INFO] train episode 9058: reward = -102.20, steps = 19 06:06:06 [INFO] train episode 9059: reward = -106.64, steps = 26 06:06:08 [INFO] train episode 9060: reward = -100.88, steps = 23 06:06:09 [INFO] train episode 9061: reward = -78.42, steps = 19 06:06:11 [INFO] train episode 9062: reward = -86.29, steps = 20 06:06:13 [INFO] train episode 9063: reward = -121.52, steps = 23 06:06:15 [INFO] train episode 9064: reward = -93.87, steps = 19 06:06:17 [INFO] train episode 9065: reward = -85.49, steps = 20 06:06:18 [INFO] train episode 9066: reward = -106.65, steps = 19 06:06:21 [INFO] train episode 9067: reward = -168.01, steps = 30 06:06:22 [INFO] train episode 9068: reward = -139.31, steps = 19 06:06:25 [INFO] train episode 9069: reward = -137.87, steps = 31 06:06:27 [INFO] train episode 9070: reward = -108.83, steps = 19 06:06:29 [INFO] train episode 9071: reward = -93.35, steps = 26 06:06:31 [INFO] train episode 9072: reward = -101.80, steps = 22 06:06:34 [INFO] train episode 9073: reward = -94.77, steps = 29 06:06:35 [INFO] train episode 9074: reward = -69.29, steps = 19 06:06:37 [INFO] train episode 9075: reward = -115.08, steps = 21 06:06:39 [INFO] train episode 9076: reward = -95.10, steps = 25 06:06:41 [INFO] train episode 9077: reward = -103.68, steps = 19 06:06:44 [INFO] train episode 9078: reward = -100.88, steps = 32 06:06:46 [INFO] train episode 9079: reward = -108.18, steps = 20 06:06:48 [INFO] train episode 9080: reward = -113.79, steps = 29 06:06:50 [INFO] train episode 9081: reward = -76.06, steps = 19 06:06:52 [INFO] train episode 9082: reward = -103.52, steps = 20 06:06:54 [INFO] train episode 9083: reward = -111.15, steps = 23 06:06:56 [INFO] train episode 9084: reward = -105.68, steps = 28 06:06:58 [INFO] train episode 9085: reward = -117.79, steps = 28 06:07:00 [INFO] train episode 9086: reward = -99.20, steps = 19 06:07:02 [INFO] train episode 9087: reward = -83.38, steps = 23 06:07:05 [INFO] train episode 9088: reward = -133.23, steps = 37 06:07:07 [INFO] train episode 9089: reward = -104.48, steps = 20 06:07:09 [INFO] train episode 9090: reward = -121.04, steps = 23 06:07:11 [INFO] train episode 9091: reward = -108.70, steps = 20 06:07:13 [INFO] train episode 9092: reward = -103.55, steps = 28 06:07:15 [INFO] train episode 9093: reward = -127.89, steps = 20 06:07:17 [INFO] train episode 9094: reward = -111.37, steps = 24 06:07:19 [INFO] train episode 9095: reward = -82.42, steps = 19 06:07:21 [INFO] train episode 9096: reward = -78.91, steps = 20 06:07:23 [INFO] train episode 9097: reward = -111.97, steps = 26 06:07:25 [INFO] train episode 9098: reward = -92.44, steps = 29 06:07:27 [INFO] train episode 9099: reward = -120.42, steps = 21 06:07:29 [INFO] train episode 9100: reward = -81.93, steps = 19 06:07:31 [INFO] train episode 9101: reward = -100.63, steps = 19 06:07:33 [INFO] train episode 9102: reward = -77.53, steps = 20 06:07:34 [INFO] train episode 9103: reward = -80.51, steps = 19 06:07:36 [INFO] train episode 9104: reward = -103.63, steps = 20 06:07:38 [INFO] train episode 9105: reward = -90.75, steps = 21 06:07:39 [INFO] train episode 9106: reward = -93.03, steps = 19 06:07:41 [INFO] train episode 9107: reward = -97.32, steps = 19 06:07:43 [INFO] train episode 9108: reward = -90.02, steps = 21 06:07:45 [INFO] train episode 9109: reward = -76.20, steps = 25 06:07:46 [INFO] train episode 9110: reward = -120.15, steps = 19 06:07:49 [INFO] train episode 9111: reward = -75.14, steps = 20 06:07:50 [INFO] train episode 9112: reward = -80.53, steps = 20 06:07:52 [INFO] train episode 9113: reward = -73.35, steps = 20 06:07:55 [INFO] train episode 9114: reward = -109.43, steps = 32 06:07:56 [INFO] train episode 9115: reward = -98.16, steps = 22 06:07:58 [INFO] train episode 9116: reward = -101.98, steps = 21 06:08:01 [INFO] train episode 9117: reward = -130.02, steps = 26 06:08:02 [INFO] train episode 9118: reward = -96.45, steps = 19 06:08:04 [INFO] train episode 9119: reward = -69.54, steps = 19 06:08:06 [INFO] train episode 9120: reward = -106.39, steps = 20 06:08:08 [INFO] train episode 9121: reward = -84.66, steps = 24 06:08:10 [INFO] train episode 9122: reward = -127.20, steps = 28 06:08:13 [INFO] train episode 9123: reward = -101.50, steps = 22 06:08:15 [INFO] train episode 9124: reward = -84.06, steps = 20 06:08:16 [INFO] train episode 9125: reward = -87.81, steps = 19 06:08:18 [INFO] train episode 9126: reward = -96.48, steps = 26 06:08:20 [INFO] train episode 9127: reward = -116.04, steps = 19 06:08:22 [INFO] train episode 9128: reward = -96.68, steps = 24 06:08:24 [INFO] train episode 9129: reward = -135.61, steps = 19 06:08:26 [INFO] train episode 9130: reward = -98.29, steps = 19 06:08:27 [INFO] train episode 9131: reward = -94.54, steps = 20 06:08:29 [INFO] train episode 9132: reward = -107.09, steps = 18 06:08:31 [INFO] train episode 9133: reward = -79.50, steps = 21 06:08:32 [INFO] train episode 9134: reward = -101.32, steps = 19 06:08:34 [INFO] train episode 9135: reward = -81.64, steps = 23 06:08:36 [INFO] train episode 9136: reward = -98.00, steps = 18 06:08:38 [INFO] train episode 9137: reward = -93.09, steps = 19 06:08:40 [INFO] train episode 9138: reward = -121.71, steps = 20 06:08:42 [INFO] train episode 9139: reward = -81.47, steps = 23 06:08:43 [INFO] train episode 9140: reward = -119.65, steps = 20 06:08:45 [INFO] train episode 9141: reward = -118.60, steps = 21 06:08:47 [INFO] train episode 9142: reward = -101.34, steps = 22 06:08:49 [INFO] train episode 9143: reward = -95.72, steps = 19 06:08:50 [INFO] train episode 9144: reward = -98.07, steps = 19 06:08:53 [INFO] train episode 9145: reward = -76.12, steps = 21 06:08:54 [INFO] train episode 9146: reward = -90.94, steps = 19 06:08:56 [INFO] train episode 9147: reward = -89.86, steps = 20 06:08:58 [INFO] train episode 9148: reward = -94.83, steps = 23 06:09:00 [INFO] train episode 9149: reward = -54.16, steps = 20 06:09:01 [INFO] train episode 9150: reward = -89.06, steps = 19 06:09:03 [INFO] train episode 9151: reward = -86.28, steps = 19 06:09:06 [INFO] train episode 9152: reward = -124.80, steps = 31 06:09:08 [INFO] train episode 9153: reward = -55.64, steps = 22 06:09:10 [INFO] train episode 9154: reward = -104.21, steps = 20 06:09:12 [INFO] train episode 9155: reward = -144.66, steps = 26 06:09:13 [INFO] train episode 9156: reward = -91.19, steps = 19 06:09:16 [INFO] train episode 9157: reward = -88.42, steps = 27 06:09:17 [INFO] train episode 9158: reward = -79.55, steps = 20 06:09:19 [INFO] train episode 9159: reward = -86.18, steps = 21 06:09:21 [INFO] train episode 9160: reward = -82.05, steps = 25 06:09:23 [INFO] train episode 9161: reward = -116.91, steps = 19 06:09:25 [INFO] train episode 9162: reward = -81.91, steps = 21 06:09:27 [INFO] train episode 9163: reward = -96.62, steps = 22 06:09:29 [INFO] train episode 9164: reward = -97.29, steps = 19 06:09:30 [INFO] train episode 9165: reward = -80.95, steps = 20 06:09:32 [INFO] train episode 9166: reward = -96.50, steps = 20 06:09:34 [INFO] train episode 9167: reward = -77.64, steps = 22 06:09:36 [INFO] train episode 9168: reward = -100.73, steps = 19 06:09:38 [INFO] train episode 9169: reward = -107.63, steps = 22 06:09:40 [INFO] train episode 9170: reward = -71.33, steps = 19 06:09:41 [INFO] train episode 9171: reward = -94.28, steps = 20 06:09:43 [INFO] train episode 9172: reward = -100.03, steps = 23 06:09:45 [INFO] train episode 9173: reward = -95.36, steps = 21 06:09:47 [INFO] train episode 9174: reward = -100.05, steps = 19 06:09:48 [INFO] train episode 9175: reward = -93.55, steps = 19 06:09:50 [INFO] train episode 9176: reward = -96.39, steps = 18 06:09:52 [INFO] train episode 9177: reward = -97.73, steps = 24 06:09:53 [INFO] train episode 9178: reward = -84.12, steps = 19 06:09:55 [INFO] train episode 9179: reward = -81.95, steps = 19 06:09:57 [INFO] train episode 9180: reward = -104.96, steps = 20 06:09:59 [INFO] train episode 9181: reward = -130.25, steps = 20 06:10:01 [INFO] train episode 9182: reward = -96.20, steps = 20 06:10:04 [INFO] train episode 9183: reward = -123.75, steps = 36 06:10:05 [INFO] train episode 9184: reward = -79.16, steps = 19 06:10:07 [INFO] train episode 9185: reward = -98.07, steps = 22 06:10:10 [INFO] train episode 9186: reward = -110.80, steps = 28 06:10:12 [INFO] train episode 9187: reward = -80.73, steps = 19 06:10:13 [INFO] train episode 9188: reward = -90.44, steps = 19 06:10:15 [INFO] train episode 9189: reward = -129.48, steps = 25 06:10:18 [INFO] train episode 9190: reward = -98.61, steps = 30 06:10:19 [INFO] train episode 9191: reward = -127.26, steps = 20 06:10:22 [INFO] train episode 9192: reward = -92.67, steps = 24 06:10:23 [INFO] train episode 9193: reward = -81.66, steps = 20 06:10:25 [INFO] train episode 9194: reward = -142.02, steps = 21 06:10:27 [INFO] train episode 9195: reward = -84.85, steps = 24 06:10:29 [INFO] train episode 9196: reward = -90.88, steps = 20 06:10:31 [INFO] train episode 9197: reward = -117.05, steps = 20 06:10:32 [INFO] train episode 9198: reward = -72.59, steps = 19 06:10:34 [INFO] train episode 9199: reward = -98.90, steps = 20 06:10:36 [INFO] train episode 9200: reward = -102.13, steps = 20 06:10:38 [INFO] train episode 9201: reward = -102.41, steps = 18 06:10:39 [INFO] train episode 9202: reward = -118.38, steps = 19 06:10:41 [INFO] train episode 9203: reward = -113.25, steps = 18 06:10:43 [INFO] train episode 9204: reward = -85.74, steps = 20 06:10:45 [INFO] train episode 9205: reward = -78.24, steps = 19 06:10:46 [INFO] train episode 9206: reward = -129.67, steps = 19 06:10:48 [INFO] train episode 9207: reward = -114.34, steps = 19 06:10:50 [INFO] train episode 9208: reward = -91.98, steps = 20 06:10:52 [INFO] train episode 9209: reward = -114.10, steps = 28 06:10:54 [INFO] train episode 9210: reward = -94.64, steps = 21 06:10:56 [INFO] train episode 9211: reward = -116.13, steps = 31 06:10:58 [INFO] train episode 9212: reward = -74.75, steps = 19 06:11:00 [INFO] train episode 9213: reward = -116.04, steps = 19 06:11:03 [INFO] train episode 9214: reward = -109.65, steps = 23 06:11:04 [INFO] train episode 9215: reward = -100.94, steps = 20 06:11:06 [INFO] train episode 9216: reward = -67.76, steps = 21 06:11:08 [INFO] train episode 9217: reward = -69.14, steps = 21 06:11:10 [INFO] train episode 9218: reward = -104.19, steps = 27 06:11:12 [INFO] train episode 9219: reward = -84.32, steps = 18 06:11:14 [INFO] train episode 9220: reward = -86.52, steps = 24 06:11:16 [INFO] train episode 9221: reward = -85.97, steps = 25 06:11:18 [INFO] train episode 9222: reward = -113.13, steps = 18 06:11:20 [INFO] train episode 9223: reward = -82.83, steps = 19 06:11:21 [INFO] train episode 9224: reward = -79.34, steps = 21 06:11:23 [INFO] train episode 9225: reward = -104.17, steps = 21 06:11:25 [INFO] train episode 9226: reward = -99.42, steps = 19 06:11:27 [INFO] train episode 9227: reward = -89.06, steps = 22 06:11:29 [INFO] train episode 9228: reward = -125.54, steps = 21 06:11:31 [INFO] train episode 9229: reward = -99.30, steps = 20 06:11:32 [INFO] train episode 9230: reward = -89.11, steps = 20 06:11:34 [INFO] train episode 9231: reward = -81.45, steps = 21 06:11:36 [INFO] train episode 9232: reward = -97.37, steps = 19 06:11:37 [INFO] train episode 9233: reward = -96.09, steps = 19 06:11:39 [INFO] train episode 9234: reward = -142.49, steps = 19 06:11:41 [INFO] train episode 9235: reward = -111.60, steps = 20 06:11:42 [INFO] train episode 9236: reward = -112.00, steps = 19 06:11:45 [INFO] train episode 9237: reward = -143.51, steps = 24 06:11:47 [INFO] train episode 9238: reward = -92.49, steps = 22 06:11:49 [INFO] train episode 9239: reward = -119.64, steps = 22 06:11:50 [INFO] train episode 9240: reward = -98.37, steps = 20 06:11:52 [INFO] train episode 9241: reward = -94.67, steps = 21 06:11:54 [INFO] train episode 9242: reward = -132.66, steps = 23 06:11:56 [INFO] train episode 9243: reward = -101.41, steps = 19 06:11:57 [INFO] train episode 9244: reward = -145.89, steps = 21 06:12:00 [INFO] train episode 9245: reward = -101.92, steps = 26 06:12:02 [INFO] train episode 9246: reward = -73.64, steps = 22 06:12:03 [INFO] train episode 9247: reward = -96.74, steps = 19 06:12:05 [INFO] train episode 9248: reward = -117.78, steps = 21 06:12:07 [INFO] train episode 9249: reward = -81.76, steps = 21 06:12:09 [INFO] train episode 9250: reward = -84.95, steps = 20 06:12:10 [INFO] train episode 9251: reward = -84.93, steps = 19 06:12:12 [INFO] train episode 9252: reward = -73.88, steps = 25 06:12:14 [INFO] train episode 9253: reward = -96.32, steps = 19 06:12:17 [INFO] train episode 9254: reward = -108.94, steps = 23 06:12:18 [INFO] train episode 9255: reward = -97.20, steps = 22 06:12:20 [INFO] train episode 9256: reward = -63.98, steps = 20 06:12:22 [INFO] train episode 9257: reward = -90.07, steps = 19 06:12:24 [INFO] train episode 9258: reward = -121.43, steps = 20 06:12:25 [INFO] train episode 9259: reward = -110.61, steps = 22 06:12:27 [INFO] train episode 9260: reward = -78.19, steps = 20 06:12:29 [INFO] train episode 9261: reward = -100.90, steps = 24 06:12:31 [INFO] train episode 9262: reward = -83.28, steps = 20 06:12:33 [INFO] train episode 9263: reward = -106.17, steps = 21 06:12:35 [INFO] train episode 9264: reward = -96.36, steps = 20 06:12:37 [INFO] train episode 9265: reward = -121.98, steps = 26 06:12:39 [INFO] train episode 9266: reward = -127.41, steps = 27 06:12:41 [INFO] train episode 9267: reward = -103.23, steps = 20 06:12:43 [INFO] train episode 9268: reward = -96.65, steps = 19 06:12:45 [INFO] train episode 9269: reward = -123.84, steps = 28 06:12:47 [INFO] train episode 9270: reward = -100.02, steps = 19 06:12:49 [INFO] train episode 9271: reward = -105.83, steps = 20 06:12:50 [INFO] train episode 9272: reward = -88.77, steps = 20 06:12:52 [INFO] train episode 9273: reward = -110.19, steps = 19 06:12:54 [INFO] train episode 9274: reward = -76.06, steps = 19 06:12:55 [INFO] train episode 9275: reward = -82.95, steps = 18 06:12:57 [INFO] train episode 9276: reward = -104.79, steps = 22 06:12:59 [INFO] train episode 9277: reward = -84.65, steps = 20 06:13:01 [INFO] train episode 9278: reward = -78.52, steps = 19 06:13:03 [INFO] train episode 9279: reward = -85.56, steps = 25 06:13:05 [INFO] train episode 9280: reward = -111.06, steps = 20 06:13:07 [INFO] train episode 9281: reward = -122.71, steps = 25 06:13:09 [INFO] train episode 9282: reward = -91.28, steps = 19 06:13:10 [INFO] train episode 9283: reward = -107.22, steps = 20 06:13:12 [INFO] train episode 9284: reward = -66.99, steps = 19 06:13:14 [INFO] train episode 9285: reward = -101.48, steps = 26 06:13:16 [INFO] train episode 9286: reward = -82.77, steps = 19 06:13:18 [INFO] train episode 9287: reward = -86.37, steps = 19 06:13:20 [INFO] train episode 9288: reward = -91.75, steps = 19 06:13:22 [INFO] train episode 9289: reward = -134.48, steps = 30 06:13:24 [INFO] train episode 9290: reward = -103.94, steps = 23 06:13:26 [INFO] train episode 9291: reward = -119.01, steps = 24 06:13:28 [INFO] train episode 9292: reward = -96.07, steps = 21 06:13:30 [INFO] train episode 9293: reward = -111.36, steps = 19 06:13:32 [INFO] train episode 9294: reward = -117.24, steps = 25 06:13:34 [INFO] train episode 9295: reward = -76.01, steps = 20 06:13:36 [INFO] train episode 9296: reward = -73.81, steps = 19 06:13:38 [INFO] train episode 9297: reward = -110.13, steps = 26 06:13:39 [INFO] train episode 9298: reward = -91.54, steps = 19 06:13:41 [INFO] train episode 9299: reward = -67.47, steps = 20 06:13:43 [INFO] train episode 9300: reward = -105.99, steps = 22 06:13:45 [INFO] train episode 9301: reward = -100.31, steps = 18 06:13:46 [INFO] train episode 9302: reward = -107.40, steps = 22 06:13:49 [INFO] train episode 9303: reward = -105.11, steps = 25 06:13:50 [INFO] train episode 9304: reward = -102.38, steps = 19 06:13:53 [INFO] train episode 9305: reward = -67.64, steps = 25 06:13:55 [INFO] train episode 9306: reward = -104.71, steps = 21 06:13:57 [INFO] train episode 9307: reward = -82.29, steps = 19 06:13:59 [INFO] train episode 9308: reward = -85.10, steps = 20 06:14:01 [INFO] train episode 9309: reward = -100.64, steps = 22 06:14:02 [INFO] train episode 9310: reward = -119.14, steps = 21 06:14:04 [INFO] train episode 9311: reward = -97.56, steps = 20 06:14:06 [INFO] train episode 9312: reward = -88.88, steps = 19 06:14:08 [INFO] train episode 9313: reward = -82.91, steps = 20 06:14:10 [INFO] train episode 9314: reward = -98.80, steps = 22 06:14:11 [INFO] train episode 9315: reward = -72.20, steps = 21 06:14:13 [INFO] train episode 9316: reward = -90.53, steps = 19 06:14:15 [INFO] train episode 9317: reward = -107.44, steps = 20 06:14:16 [INFO] train episode 9318: reward = -106.87, steps = 18 06:14:18 [INFO] train episode 9319: reward = -83.41, steps = 19 06:14:20 [INFO] train episode 9320: reward = -85.83, steps = 19 06:14:22 [INFO] train episode 9321: reward = -94.35, steps = 22 06:14:24 [INFO] train episode 9322: reward = -87.39, steps = 19 06:14:25 [INFO] train episode 9323: reward = -101.35, steps = 19 06:14:27 [INFO] train episode 9324: reward = -86.21, steps = 22 06:14:29 [INFO] train episode 9325: reward = -98.99, steps = 19 06:14:31 [INFO] train episode 9326: reward = -148.40, steps = 26 06:14:32 [INFO] train episode 9327: reward = -80.01, steps = 19 06:14:34 [INFO] train episode 9328: reward = -114.22, steps = 20 06:14:36 [INFO] train episode 9329: reward = -76.16, steps = 19 06:14:38 [INFO] train episode 9330: reward = -129.91, steps = 22 06:14:40 [INFO] train episode 9331: reward = -95.36, steps = 19 06:14:41 [INFO] train episode 9332: reward = -87.56, steps = 19 06:14:44 [INFO] train episode 9333: reward = -138.13, steps = 28 06:14:46 [INFO] train episode 9334: reward = -111.38, steps = 23 06:14:48 [INFO] train episode 9335: reward = -122.71, steps = 26 06:14:50 [INFO] train episode 9336: reward = -121.12, steps = 19 06:14:51 [INFO] train episode 9337: reward = -78.23, steps = 20 06:14:53 [INFO] train episode 9338: reward = -97.51, steps = 20 06:14:55 [INFO] train episode 9339: reward = -94.43, steps = 20 06:14:57 [INFO] train episode 9340: reward = -116.24, steps = 19 06:14:59 [INFO] train episode 9341: reward = -71.31, steps = 25 06:15:01 [INFO] train episode 9342: reward = -82.46, steps = 20 06:15:03 [INFO] train episode 9343: reward = -125.35, steps = 24 06:15:04 [INFO] train episode 9344: reward = -104.29, steps = 20 06:15:07 [INFO] train episode 9345: reward = -115.72, steps = 28 06:15:08 [INFO] train episode 9346: reward = -87.84, steps = 19 06:15:11 [INFO] train episode 9347: reward = -97.76, steps = 26 06:15:13 [INFO] train episode 9348: reward = -111.90, steps = 20 06:15:14 [INFO] train episode 9349: reward = -79.55, steps = 20 06:15:17 [INFO] train episode 9350: reward = -94.31, steps = 26 06:15:19 [INFO] train episode 9351: reward = -70.67, steps = 20 06:15:21 [INFO] train episode 9352: reward = -107.44, steps = 29 06:15:23 [INFO] train episode 9353: reward = -90.31, steps = 20 06:15:25 [INFO] train episode 9354: reward = -85.38, steps = 22 06:15:27 [INFO] train episode 9355: reward = -100.62, steps = 20 06:15:28 [INFO] train episode 9356: reward = -103.51, steps = 17 06:15:30 [INFO] train episode 9357: reward = -93.05, steps = 19 06:15:32 [INFO] train episode 9358: reward = -92.35, steps = 23 06:15:34 [INFO] train episode 9359: reward = -97.81, steps = 18 06:15:36 [INFO] train episode 9360: reward = -115.47, steps = 31 06:15:38 [INFO] train episode 9361: reward = -127.76, steps = 19 06:15:40 [INFO] train episode 9362: reward = -142.96, steps = 20 06:15:41 [INFO] train episode 9363: reward = -132.66, steps = 19 06:15:43 [INFO] train episode 9364: reward = -98.19, steps = 18 06:15:45 [INFO] train episode 9365: reward = -100.35, steps = 19 06:15:47 [INFO] train episode 9366: reward = -102.60, steps = 30 06:15:50 [INFO] train episode 9367: reward = -88.42, steps = 29 06:15:51 [INFO] train episode 9368: reward = -104.85, steps = 19 06:15:53 [INFO] train episode 9369: reward = -87.71, steps = 21 06:15:55 [INFO] train episode 9370: reward = -134.91, steps = 20 06:15:57 [INFO] train episode 9371: reward = -99.75, steps = 26 06:16:00 [INFO] train episode 9372: reward = -74.31, steps = 25 06:16:02 [INFO] train episode 9373: reward = -72.26, steps = 30 06:16:04 [INFO] train episode 9374: reward = -99.90, steps = 20 06:16:06 [INFO] train episode 9375: reward = -84.85, steps = 23 06:16:08 [INFO] train episode 9376: reward = -107.58, steps = 19 06:16:09 [INFO] train episode 9377: reward = -88.55, steps = 20 06:16:12 [INFO] train episode 9378: reward = -130.37, steps = 32 06:16:14 [INFO] train episode 9379: reward = -90.91, steps = 20 06:16:16 [INFO] train episode 9380: reward = -92.83, steps = 20 06:16:18 [INFO] train episode 9381: reward = -143.73, steps = 26 06:16:20 [INFO] train episode 9382: reward = -108.91, steps = 28 06:16:22 [INFO] train episode 9383: reward = -73.85, steps = 19 06:16:24 [INFO] train episode 9384: reward = -119.81, steps = 20 06:16:26 [INFO] train episode 9385: reward = -113.96, steps = 23 06:16:27 [INFO] train episode 9386: reward = -130.07, steps = 19 06:16:29 [INFO] train episode 9387: reward = -84.44, steps = 25 06:16:31 [INFO] train episode 9388: reward = -108.55, steps = 19 06:16:33 [INFO] train episode 9389: reward = -78.89, steps = 22 06:16:35 [INFO] train episode 9390: reward = -89.76, steps = 20 06:16:36 [INFO] train episode 9391: reward = -96.90, steps = 19 06:16:38 [INFO] train episode 9392: reward = -83.18, steps = 19 06:16:40 [INFO] train episode 9393: reward = -141.98, steps = 20 06:16:42 [INFO] train episode 9394: reward = -86.00, steps = 19 06:16:44 [INFO] train episode 9395: reward = -120.69, steps = 19 06:16:46 [INFO] train episode 9396: reward = -119.65, steps = 20 06:16:48 [INFO] train episode 9397: reward = -81.23, steps = 22 06:16:50 [INFO] train episode 9398: reward = -90.03, steps = 19 06:16:51 [INFO] train episode 9399: reward = -80.41, steps = 20 06:16:53 [INFO] train episode 9400: reward = -99.45, steps = 19 06:16:55 [INFO] train episode 9401: reward = -143.90, steps = 20 06:16:57 [INFO] train episode 9402: reward = -84.17, steps = 23 06:16:58 [INFO] train episode 9403: reward = -82.69, steps = 19 06:17:00 [INFO] train episode 9404: reward = -86.71, steps = 19 06:17:02 [INFO] train episode 9405: reward = -102.70, steps = 20 06:17:04 [INFO] train episode 9406: reward = -86.19, steps = 19 06:17:05 [INFO] train episode 9407: reward = -131.66, steps = 20 06:17:07 [INFO] train episode 9408: reward = -74.79, steps = 21 06:17:09 [INFO] train episode 9409: reward = -100.88, steps = 21 06:17:11 [INFO] train episode 9410: reward = -113.17, steps = 20 06:17:12 [INFO] train episode 9411: reward = -77.88, steps = 19 06:17:14 [INFO] train episode 9412: reward = -74.46, steps = 20 06:17:16 [INFO] train episode 9413: reward = -101.69, steps = 19 06:17:17 [INFO] train episode 9414: reward = -133.71, steps = 18 06:17:19 [INFO] train episode 9415: reward = -86.77, steps = 20 06:17:21 [INFO] train episode 9416: reward = -107.76, steps = 19 06:17:23 [INFO] train episode 9417: reward = -85.87, steps = 19 06:17:25 [INFO] train episode 9418: reward = -106.80, steps = 27 06:17:27 [INFO] train episode 9419: reward = -99.83, steps = 22 06:17:29 [INFO] train episode 9420: reward = -118.67, steps = 26 06:17:31 [INFO] train episode 9421: reward = -94.89, steps = 27 06:17:33 [INFO] train episode 9422: reward = -111.62, steps = 19 06:17:35 [INFO] train episode 9423: reward = -101.42, steps = 19 06:17:37 [INFO] train episode 9424: reward = -87.08, steps = 19 06:17:39 [INFO] train episode 9425: reward = -67.84, steps = 21 06:17:40 [INFO] train episode 9426: reward = -70.09, steps = 20 06:17:42 [INFO] train episode 9427: reward = -108.59, steps = 19 06:17:44 [INFO] train episode 9428: reward = -81.82, steps = 21 06:17:46 [INFO] train episode 9429: reward = -70.59, steps = 20 06:17:48 [INFO] train episode 9430: reward = -82.25, steps = 26 06:17:49 [INFO] train episode 9431: reward = -115.06, steps = 19 06:17:51 [INFO] train episode 9432: reward = -106.58, steps = 19 06:17:53 [INFO] train episode 9433: reward = -100.73, steps = 20 06:17:55 [INFO] train episode 9434: reward = -131.06, steps = 23 06:17:57 [INFO] train episode 9435: reward = -87.15, steps = 19 06:17:58 [INFO] train episode 9436: reward = -85.06, steps = 20 06:18:01 [INFO] train episode 9437: reward = -134.41, steps = 24 06:18:03 [INFO] train episode 9438: reward = -124.06, steps = 27 06:18:05 [INFO] train episode 9439: reward = -103.92, steps = 20 06:18:07 [INFO] train episode 9440: reward = -96.28, steps = 19 06:18:08 [INFO] train episode 9441: reward = -84.87, steps = 20 06:18:10 [INFO] train episode 9442: reward = -84.92, steps = 20 06:18:12 [INFO] train episode 9443: reward = -76.91, steps = 18 06:18:13 [INFO] train episode 9444: reward = -92.05, steps = 23 06:18:15 [INFO] train episode 9445: reward = -85.90, steps = 22 06:18:17 [INFO] train episode 9446: reward = -97.89, steps = 23 06:18:21 [INFO] train episode 9447: reward = -121.32, steps = 41 06:18:23 [INFO] train episode 9448: reward = -86.85, steps = 20 06:18:25 [INFO] train episode 9449: reward = -77.60, steps = 22 06:18:27 [INFO] train episode 9450: reward = -108.46, steps = 31 06:18:29 [INFO] train episode 9451: reward = -79.32, steps = 20 06:18:31 [INFO] train episode 9452: reward = -128.63, steps = 19 06:18:32 [INFO] train episode 9453: reward = -91.27, steps = 18 06:18:34 [INFO] train episode 9454: reward = -105.30, steps = 20 06:18:36 [INFO] train episode 9455: reward = -90.48, steps = 19 06:18:37 [INFO] train episode 9456: reward = -93.21, steps = 19 06:18:40 [INFO] train episode 9457: reward = -107.29, steps = 22 06:18:41 [INFO] train episode 9458: reward = -109.02, steps = 20 06:18:43 [INFO] train episode 9459: reward = -96.36, steps = 19 06:18:45 [INFO] train episode 9460: reward = -132.35, steps = 29 06:18:47 [INFO] train episode 9461: reward = -110.26, steps = 24 06:18:49 [INFO] train episode 9462: reward = -95.56, steps = 19 06:18:51 [INFO] train episode 9463: reward = -95.41, steps = 19 06:18:52 [INFO] train episode 9464: reward = -68.94, steps = 20 06:18:55 [INFO] train episode 9465: reward = -122.80, steps = 25 06:18:57 [INFO] train episode 9466: reward = -107.50, steps = 21 06:18:58 [INFO] train episode 9467: reward = -95.93, steps = 20 06:19:00 [INFO] train episode 9468: reward = -73.76, steps = 19 06:19:02 [INFO] train episode 9469: reward = -93.68, steps = 18 06:19:04 [INFO] train episode 9470: reward = -88.71, steps = 30 06:19:06 [INFO] train episode 9471: reward = -128.37, steps = 19 06:19:07 [INFO] train episode 9472: reward = -92.00, steps = 19 06:19:10 [INFO] train episode 9473: reward = -84.58, steps = 20 06:19:11 [INFO] train episode 9474: reward = -118.87, steps = 20 06:19:13 [INFO] train episode 9475: reward = -80.04, steps = 20 06:19:15 [INFO] train episode 9476: reward = -82.45, steps = 19 06:19:17 [INFO] train episode 9477: reward = -96.17, steps = 28 06:19:19 [INFO] train episode 9478: reward = -91.86, steps = 20 06:19:20 [INFO] train episode 9479: reward = -102.86, steps = 19 06:19:22 [INFO] train episode 9480: reward = -109.65, steps = 18 06:19:24 [INFO] train episode 9481: reward = -98.66, steps = 19 06:19:26 [INFO] train episode 9482: reward = -117.70, steps = 30 06:19:28 [INFO] train episode 9483: reward = -94.53, steps = 19 06:19:30 [INFO] train episode 9484: reward = -84.65, steps = 21 06:19:32 [INFO] train episode 9485: reward = -104.69, steps = 20 06:19:34 [INFO] train episode 9486: reward = -103.71, steps = 18 06:19:36 [INFO] train episode 9487: reward = -115.68, steps = 19 06:19:37 [INFO] train episode 9488: reward = -90.48, steps = 20 06:19:39 [INFO] train episode 9489: reward = -115.17, steps = 19 06:19:41 [INFO] train episode 9490: reward = -106.10, steps = 20 06:19:43 [INFO] train episode 9491: reward = -96.10, steps = 25 06:19:45 [INFO] train episode 9492: reward = -101.67, steps = 18 06:19:46 [INFO] train episode 9493: reward = -93.19, steps = 19 06:19:48 [INFO] train episode 9494: reward = -87.13, steps = 19 06:19:51 [INFO] train episode 9495: reward = -120.89, steps = 31 06:19:52 [INFO] train episode 9496: reward = -82.41, steps = 19 06:19:54 [INFO] train episode 9497: reward = -92.32, steps = 20 06:19:56 [INFO] train episode 9498: reward = -91.05, steps = 20 06:19:58 [INFO] train episode 9499: reward = -102.07, steps = 21 06:19:59 [INFO] train episode 9500: reward = -109.59, steps = 18 06:20:01 [INFO] train episode 9501: reward = -96.38, steps = 19 06:20:03 [INFO] train episode 9502: reward = -92.36, steps = 22 06:20:05 [INFO] train episode 9503: reward = -89.26, steps = 21 06:20:07 [INFO] train episode 9504: reward = -128.32, steps = 22 06:20:08 [INFO] train episode 9505: reward = -80.47, steps = 19 06:20:10 [INFO] train episode 9506: reward = -123.90, steps = 23 06:20:12 [INFO] train episode 9507: reward = -107.14, steps = 20 06:20:14 [INFO] train episode 9508: reward = -108.67, steps = 20 06:20:16 [INFO] train episode 9509: reward = -98.56, steps = 20 06:20:17 [INFO] train episode 9510: reward = -84.99, steps = 19 06:20:19 [INFO] train episode 9511: reward = -90.05, steps = 20 06:20:21 [INFO] train episode 9512: reward = -88.58, steps = 23 06:20:23 [INFO] train episode 9513: reward = -83.60, steps = 23 06:20:25 [INFO] train episode 9514: reward = -103.32, steps = 22 06:20:28 [INFO] train episode 9515: reward = -103.37, steps = 30 06:20:30 [INFO] train episode 9516: reward = -128.73, steps = 23 06:20:32 [INFO] train episode 9517: reward = -78.52, steps = 19 06:20:34 [INFO] train episode 9518: reward = -93.06, steps = 21 06:20:36 [INFO] train episode 9519: reward = -76.03, steps = 21 06:20:38 [INFO] train episode 9520: reward = -119.21, steps = 21 06:20:40 [INFO] train episode 9521: reward = -105.67, steps = 23 06:20:42 [INFO] train episode 9522: reward = -83.63, steps = 20 06:20:44 [INFO] train episode 9523: reward = -90.65, steps = 19 06:20:46 [INFO] train episode 9524: reward = -74.94, steps = 19 06:20:48 [INFO] train episode 9525: reward = -88.15, steps = 19 06:20:50 [INFO] train episode 9526: reward = -96.13, steps = 19 06:20:52 [INFO] train episode 9527: reward = -79.90, steps = 20 06:20:53 [INFO] train episode 9528: reward = -108.01, steps = 19 06:20:56 [INFO] train episode 9529: reward = -89.58, steps = 24 06:20:58 [INFO] train episode 9530: reward = -76.84, steps = 19 06:20:59 [INFO] train episode 9531: reward = -90.87, steps = 18 06:21:01 [INFO] train episode 9532: reward = -104.42, steps = 19 06:21:02 [INFO] train episode 9533: reward = -94.41, steps = 19 06:21:05 [INFO] train episode 9534: reward = -90.79, steps = 22 06:21:06 [INFO] train episode 9535: reward = -82.81, steps = 20 06:21:09 [INFO] train episode 9536: reward = -109.78, steps = 27 06:21:10 [INFO] train episode 9537: reward = -88.80, steps = 19 06:21:12 [INFO] train episode 9538: reward = -87.16, steps = 19 06:21:14 [INFO] train episode 9539: reward = -78.25, steps = 20 06:21:16 [INFO] train episode 9540: reward = -98.40, steps = 21 06:21:17 [INFO] train episode 9541: reward = -109.47, steps = 20 06:21:19 [INFO] train episode 9542: reward = -84.80, steps = 19 06:21:21 [INFO] train episode 9543: reward = -87.16, steps = 21 06:21:23 [INFO] train episode 9544: reward = -93.34, steps = 19 06:21:24 [INFO] train episode 9545: reward = -93.64, steps = 19 06:21:26 [INFO] train episode 9546: reward = -98.00, steps = 19 06:21:28 [INFO] train episode 9547: reward = -94.54, steps = 22 06:21:30 [INFO] train episode 9548: reward = -96.98, steps = 20 06:21:31 [INFO] train episode 9549: reward = -89.82, steps = 20 06:21:33 [INFO] train episode 9550: reward = -101.19, steps = 20 06:21:35 [INFO] train episode 9551: reward = -94.60, steps = 19 06:21:37 [INFO] train episode 9552: reward = -75.95, steps = 19 06:21:39 [INFO] train episode 9553: reward = -80.63, steps = 22 06:21:41 [INFO] train episode 9554: reward = -71.03, steps = 26 06:21:43 [INFO] train episode 9555: reward = -73.01, steps = 22 06:21:44 [INFO] train episode 9556: reward = -102.09, steps = 20 06:21:46 [INFO] train episode 9557: reward = -87.72, steps = 19 06:21:48 [INFO] train episode 9558: reward = -117.86, steps = 25 06:21:50 [INFO] train episode 9559: reward = -137.84, steps = 19 06:21:52 [INFO] train episode 9560: reward = -98.39, steps = 23 06:21:54 [INFO] train episode 9561: reward = -99.72, steps = 19 06:21:55 [INFO] train episode 9562: reward = -103.21, steps = 19 06:21:57 [INFO] train episode 9563: reward = -98.03, steps = 21 06:21:59 [INFO] train episode 9564: reward = -110.82, steps = 26 06:22:01 [INFO] train episode 9565: reward = -110.52, steps = 19 06:22:03 [INFO] train episode 9566: reward = -109.54, steps = 25 06:22:05 [INFO] train episode 9567: reward = -95.04, steps = 19 06:22:08 [INFO] train episode 9568: reward = -119.91, steps = 27 06:22:09 [INFO] train episode 9569: reward = -80.36, steps = 20 06:22:11 [INFO] train episode 9570: reward = -107.62, steps = 19 06:22:13 [INFO] train episode 9571: reward = -87.55, steps = 19 06:22:14 [INFO] train episode 9572: reward = -94.18, steps = 19 06:22:16 [INFO] train episode 9573: reward = -79.64, steps = 19 06:22:18 [INFO] train episode 9574: reward = -114.19, steps = 21 06:22:19 [INFO] train episode 9575: reward = -109.02, steps = 19 06:22:21 [INFO] train episode 9576: reward = -94.80, steps = 26 06:22:24 [INFO] train episode 9577: reward = -102.08, steps = 19 06:22:26 [INFO] train episode 9578: reward = -72.32, steps = 21 06:22:28 [INFO] train episode 9579: reward = -122.23, steps = 19 06:22:30 [INFO] train episode 9580: reward = -108.74, steps = 22 06:22:31 [INFO] train episode 9581: reward = -101.06, steps = 20 06:22:33 [INFO] train episode 9582: reward = -96.00, steps = 20 06:22:35 [INFO] train episode 9583: reward = -92.08, steps = 20 06:22:37 [INFO] train episode 9584: reward = -84.55, steps = 20 06:22:38 [INFO] train episode 9585: reward = -125.38, steps = 19 06:22:40 [INFO] train episode 9586: reward = -105.32, steps = 20 06:22:42 [INFO] train episode 9587: reward = -97.48, steps = 19 06:22:44 [INFO] train episode 9588: reward = -97.27, steps = 22 06:22:45 [INFO] train episode 9589: reward = -96.88, steps = 19 06:22:47 [INFO] train episode 9590: reward = -99.90, steps = 19 06:22:49 [INFO] train episode 9591: reward = -111.31, steps = 21 06:22:51 [INFO] train episode 9592: reward = -81.90, steps = 19 06:22:52 [INFO] train episode 9593: reward = -94.92, steps = 19 06:22:54 [INFO] train episode 9594: reward = -106.50, steps = 19 06:22:56 [INFO] train episode 9595: reward = -89.54, steps = 18 06:22:57 [INFO] train episode 9596: reward = -99.68, steps = 20 06:22:59 [INFO] train episode 9597: reward = -81.68, steps = 20 06:23:01 [INFO] train episode 9598: reward = -85.24, steps = 19 06:23:02 [INFO] train episode 9599: reward = -87.65, steps = 19 06:23:05 [INFO] train episode 9600: reward = -85.94, steps = 27 06:23:07 [INFO] train episode 9601: reward = -82.47, steps = 24 06:23:09 [INFO] train episode 9602: reward = -109.56, steps = 20 06:23:11 [INFO] train episode 9603: reward = -73.58, steps = 19 06:23:12 [INFO] train episode 9604: reward = -84.69, steps = 20 06:23:14 [INFO] train episode 9605: reward = -104.17, steps = 19 06:23:16 [INFO] train episode 9606: reward = -75.98, steps = 20 06:23:18 [INFO] train episode 9607: reward = -85.85, steps = 19 06:23:19 [INFO] train episode 9608: reward = -84.20, steps = 23 06:23:21 [INFO] train episode 9609: reward = -66.05, steps = 20 06:23:23 [INFO] train episode 9610: reward = -98.88, steps = 19 06:23:24 [INFO] train episode 9611: reward = -95.80, steps = 19 06:23:26 [INFO] train episode 9612: reward = -111.28, steps = 20 06:23:28 [INFO] train episode 9613: reward = -98.00, steps = 20 06:23:31 [INFO] train episode 9614: reward = -92.88, steps = 27 06:23:32 [INFO] train episode 9615: reward = -88.52, steps = 20 06:23:34 [INFO] train episode 9616: reward = -120.28, steps = 19 06:23:35 [INFO] train episode 9617: reward = -90.78, steps = 19 06:23:37 [INFO] train episode 9618: reward = -86.83, steps = 20 06:23:40 [INFO] train episode 9619: reward = -108.19, steps = 32 06:23:42 [INFO] train episode 9620: reward = -79.41, steps = 19 06:23:44 [INFO] train episode 9621: reward = -91.08, steps = 21 06:23:45 [INFO] train episode 9622: reward = -87.24, steps = 19 06:23:47 [INFO] train episode 9623: reward = -130.70, steps = 19 06:23:49 [INFO] train episode 9624: reward = -105.80, steps = 19 06:23:51 [INFO] train episode 9625: reward = -106.42, steps = 25 06:23:52 [INFO] train episode 9626: reward = -97.06, steps = 20 06:23:54 [INFO] train episode 9627: reward = -95.42, steps = 19 06:23:56 [INFO] train episode 9628: reward = -82.36, steps = 25 06:23:58 [INFO] train episode 9629: reward = -127.27, steps = 19 06:24:00 [INFO] train episode 9630: reward = -90.75, steps = 19 06:24:02 [INFO] train episode 9631: reward = -90.18, steps = 19 06:24:03 [INFO] train episode 9632: reward = -89.60, steps = 20 06:24:05 [INFO] train episode 9633: reward = -102.15, steps = 19 06:24:07 [INFO] train episode 9634: reward = -96.52, steps = 20 06:24:09 [INFO] train episode 9635: reward = -90.00, steps = 30 06:24:11 [INFO] train episode 9636: reward = -96.09, steps = 19 06:24:13 [INFO] train episode 9637: reward = -100.38, steps = 21 06:24:15 [INFO] train episode 9638: reward = -94.26, steps = 22 06:24:17 [INFO] train episode 9639: reward = -71.36, steps = 19 06:24:19 [INFO] train episode 9640: reward = -112.88, steps = 24 06:24:20 [INFO] train episode 9641: reward = -109.27, steps = 19 06:24:22 [INFO] train episode 9642: reward = -102.34, steps = 19 06:24:24 [INFO] train episode 9643: reward = -132.34, steps = 20 06:24:26 [INFO] train episode 9644: reward = -116.12, steps = 21 06:24:28 [INFO] train episode 9645: reward = -74.22, steps = 21 06:24:29 [INFO] train episode 9646: reward = -103.10, steps = 18 06:24:31 [INFO] train episode 9647: reward = -80.75, steps = 19 06:24:33 [INFO] train episode 9648: reward = -88.81, steps = 19 06:24:35 [INFO] train episode 9649: reward = -152.88, steps = 27 06:24:37 [INFO] train episode 9650: reward = -84.97, steps = 19 06:24:38 [INFO] train episode 9651: reward = -96.38, steps = 19 06:24:40 [INFO] train episode 9652: reward = -103.26, steps = 20 06:24:42 [INFO] train episode 9653: reward = -91.28, steps = 19 06:24:43 [INFO] train episode 9654: reward = -101.52, steps = 18 06:24:46 [INFO] train episode 9655: reward = -80.63, steps = 21 06:24:48 [INFO] train episode 9656: reward = -90.93, steps = 23 06:24:49 [INFO] train episode 9657: reward = -101.80, steps = 19 06:24:51 [INFO] train episode 9658: reward = -147.28, steps = 19 06:24:53 [INFO] train episode 9659: reward = -89.65, steps = 19 06:24:54 [INFO] train episode 9660: reward = -84.13, steps = 20 06:24:57 [INFO] train episode 9661: reward = -93.91, steps = 27 06:24:58 [INFO] train episode 9662: reward = -86.69, steps = 19 06:25:00 [INFO] train episode 9663: reward = -63.98, steps = 19 06:25:02 [INFO] train episode 9664: reward = -89.77, steps = 19 06:25:04 [INFO] train episode 9665: reward = -95.27, steps = 25 06:25:06 [INFO] train episode 9666: reward = -85.72, steps = 21 06:25:07 [INFO] train episode 9667: reward = -67.84, steps = 20 06:25:09 [INFO] train episode 9668: reward = -76.64, steps = 19 06:25:11 [INFO] train episode 9669: reward = -113.66, steps = 18 06:25:12 [INFO] train episode 9670: reward = -97.68, steps = 21 06:25:15 [INFO] train episode 9671: reward = -102.57, steps = 20 06:25:17 [INFO] train episode 9672: reward = -99.80, steps = 19 06:25:19 [INFO] train episode 9673: reward = -104.89, steps = 19 06:25:20 [INFO] train episode 9674: reward = -85.44, steps = 21 06:25:22 [INFO] train episode 9675: reward = -91.69, steps = 20 06:25:24 [INFO] train episode 9676: reward = -87.94, steps = 27 06:25:26 [INFO] train episode 9677: reward = -90.77, steps = 19 06:25:28 [INFO] train episode 9678: reward = -123.87, steps = 20 06:25:29 [INFO] train episode 9679: reward = -91.91, steps = 19 06:25:31 [INFO] train episode 9680: reward = -82.26, steps = 19 06:25:33 [INFO] train episode 9681: reward = -92.85, steps = 21 06:25:35 [INFO] train episode 9682: reward = -76.57, steps = 20 06:25:37 [INFO] train episode 9683: reward = -94.29, steps = 19 06:25:38 [INFO] train episode 9684: reward = -88.24, steps = 19 06:25:40 [INFO] train episode 9685: reward = -83.71, steps = 19 06:25:41 [INFO] train episode 9686: reward = -83.86, steps = 19 06:25:43 [INFO] train episode 9687: reward = -98.96, steps = 22 06:25:45 [INFO] train episode 9688: reward = -87.88, steps = 22 06:25:47 [INFO] train episode 9689: reward = -98.24, steps = 19 06:25:49 [INFO] train episode 9690: reward = -72.11, steps = 20 06:25:51 [INFO] train episode 9691: reward = -70.91, steps = 19 06:25:53 [INFO] train episode 9692: reward = -121.33, steps = 31 06:25:55 [INFO] train episode 9693: reward = -107.42, steps = 19 06:25:56 [INFO] train episode 9694: reward = -143.15, steps = 18 06:25:59 [INFO] train episode 9695: reward = -126.64, steps = 32 06:26:01 [INFO] train episode 9696: reward = -102.32, steps = 18 06:26:03 [INFO] train episode 9697: reward = -93.25, steps = 23 06:26:05 [INFO] train episode 9698: reward = -103.39, steps = 20 06:26:06 [INFO] train episode 9699: reward = -77.24, steps = 19 06:26:08 [INFO] train episode 9700: reward = -88.26, steps = 20 06:26:10 [INFO] train episode 9701: reward = -83.41, steps = 22 06:26:12 [INFO] train episode 9702: reward = -79.35, steps = 19 06:26:13 [INFO] train episode 9703: reward = -95.71, steps = 21 06:26:15 [INFO] train episode 9704: reward = -92.55, steps = 22 06:26:17 [INFO] train episode 9705: reward = -91.52, steps = 19 06:26:19 [INFO] train episode 9706: reward = -108.24, steps = 19 06:26:21 [INFO] train episode 9707: reward = -106.09, steps = 19 06:26:23 [INFO] train episode 9708: reward = -101.04, steps = 25 06:26:24 [INFO] train episode 9709: reward = -98.04, steps = 20 06:26:26 [INFO] train episode 9710: reward = -90.07, steps = 19 06:26:28 [INFO] train episode 9711: reward = -100.74, steps = 19 06:26:29 [INFO] train episode 9712: reward = -90.04, steps = 19 06:26:31 [INFO] train episode 9713: reward = -92.34, steps = 19 06:26:33 [INFO] train episode 9714: reward = -94.69, steps = 20 06:26:34 [INFO] train episode 9715: reward = -86.93, steps = 18 06:26:36 [INFO] train episode 9716: reward = -105.32, steps = 19 06:26:38 [INFO] train episode 9717: reward = -85.67, steps = 19 06:26:40 [INFO] train episode 9718: reward = -99.21, steps = 25 06:26:42 [INFO] train episode 9719: reward = -109.06, steps = 20 06:26:44 [INFO] train episode 9720: reward = -94.80, steps = 18 06:26:46 [INFO] train episode 9721: reward = -98.15, steps = 35 06:26:48 [INFO] train episode 9722: reward = -108.95, steps = 19 06:26:50 [INFO] train episode 9723: reward = -94.61, steps = 19 06:26:52 [INFO] train episode 9724: reward = -82.05, steps = 20 06:26:54 [INFO] train episode 9725: reward = -96.89, steps = 24 06:26:56 [INFO] train episode 9726: reward = -75.00, steps = 20 06:26:57 [INFO] train episode 9727: reward = -94.16, steps = 20 06:26:59 [INFO] train episode 9728: reward = -94.57, steps = 19 06:27:01 [INFO] train episode 9729: reward = -85.60, steps = 19 06:27:03 [INFO] train episode 9730: reward = -144.14, steps = 26 06:27:05 [INFO] train episode 9731: reward = -100.19, steps = 18 06:27:06 [INFO] train episode 9732: reward = -83.09, steps = 20 06:27:08 [INFO] train episode 9733: reward = -93.49, steps = 19 06:27:10 [INFO] train episode 9734: reward = -86.40, steps = 19 06:27:12 [INFO] train episode 9735: reward = -106.59, steps = 19 06:27:13 [INFO] train episode 9736: reward = -76.34, steps = 19 06:27:15 [INFO] train episode 9737: reward = -119.26, steps = 20 06:27:17 [INFO] train episode 9738: reward = -95.07, steps = 18 06:27:18 [INFO] train episode 9739: reward = -109.30, steps = 19 06:27:20 [INFO] train episode 9740: reward = -115.94, steps = 19 06:27:22 [INFO] train episode 9741: reward = -90.74, steps = 19 06:27:23 [INFO] train episode 9742: reward = -93.30, steps = 20 06:27:25 [INFO] train episode 9743: reward = -86.02, steps = 19 06:27:27 [INFO] train episode 9744: reward = -101.28, steps = 18 06:27:29 [INFO] train episode 9745: reward = -110.35, steps = 28 06:27:31 [INFO] train episode 9746: reward = -113.73, steps = 19 06:27:33 [INFO] train episode 9747: reward = -92.66, steps = 22 06:27:35 [INFO] train episode 9748: reward = -99.78, steps = 24 06:27:37 [INFO] train episode 9749: reward = -109.46, steps = 24 06:27:39 [INFO] train episode 9750: reward = -102.85, steps = 21 06:27:41 [INFO] train episode 9751: reward = -206.83, steps = 27 06:27:43 [INFO] train episode 9752: reward = -75.35, steps = 19 06:27:45 [INFO] train episode 9753: reward = -93.02, steps = 20 06:27:46 [INFO] train episode 9754: reward = -91.92, steps = 20 06:27:48 [INFO] train episode 9755: reward = -80.86, steps = 20 06:27:51 [INFO] train episode 9756: reward = -81.98, steps = 29 06:27:53 [INFO] train episode 9757: reward = -74.28, steps = 25 06:27:54 [INFO] train episode 9758: reward = -102.59, steps = 19 06:27:56 [INFO] train episode 9759: reward = -90.22, steps = 19 06:27:58 [INFO] train episode 9760: reward = -125.32, steps = 19 06:28:00 [INFO] train episode 9761: reward = -123.86, steps = 25 06:28:02 [INFO] train episode 9762: reward = -101.71, steps = 19 06:28:04 [INFO] train episode 9763: reward = -82.96, steps = 19 06:28:06 [INFO] train episode 9764: reward = -99.45, steps = 19 06:28:08 [INFO] train episode 9765: reward = -111.61, steps = 26 06:28:10 [INFO] train episode 9766: reward = -110.46, steps = 20 06:28:12 [INFO] train episode 9767: reward = -139.11, steps = 22 06:28:14 [INFO] train episode 9768: reward = -87.37, steps = 20 06:28:15 [INFO] train episode 9769: reward = -92.34, steps = 20 06:28:17 [INFO] train episode 9770: reward = -89.17, steps = 20 06:28:19 [INFO] train episode 9771: reward = -68.84, steps = 19 06:28:20 [INFO] train episode 9772: reward = -98.18, steps = 19 06:28:22 [INFO] train episode 9773: reward = -88.01, steps = 20 06:28:24 [INFO] train episode 9774: reward = -109.10, steps = 19 06:28:26 [INFO] train episode 9775: reward = -113.46, steps = 20 06:28:27 [INFO] train episode 9776: reward = -95.86, steps = 18 06:28:29 [INFO] train episode 9777: reward = -105.16, steps = 20 06:28:31 [INFO] train episode 9778: reward = -93.55, steps = 19 06:28:33 [INFO] train episode 9779: reward = -73.82, steps = 20 06:28:34 [INFO] train episode 9780: reward = -101.64, steps = 20 06:28:36 [INFO] train episode 9781: reward = -81.36, steps = 21 06:28:38 [INFO] train episode 9782: reward = -105.86, steps = 19 06:28:39 [INFO] train episode 9783: reward = -98.41, steps = 20 06:28:41 [INFO] train episode 9784: reward = -96.95, steps = 21 06:28:43 [INFO] train episode 9785: reward = -85.64, steps = 19 06:28:45 [INFO] train episode 9786: reward = -98.94, steps = 24 06:28:47 [INFO] train episode 9787: reward = -125.99, steps = 22 06:28:49 [INFO] train episode 9788: reward = -86.95, steps = 19 06:28:51 [INFO] train episode 9789: reward = -87.54, steps = 20 06:28:52 [INFO] train episode 9790: reward = -95.16, steps = 19 06:28:54 [INFO] train episode 9791: reward = -104.82, steps = 19 06:28:55 [INFO] train episode 9792: reward = -75.75, steps = 19 06:28:57 [INFO] train episode 9793: reward = -97.43, steps = 22 06:28:59 [INFO] train episode 9794: reward = -98.84, steps = 19 06:29:01 [INFO] train episode 9795: reward = -111.47, steps = 18 06:29:03 [INFO] train episode 9796: reward = -103.67, steps = 19 06:29:05 [INFO] train episode 9797: reward = -93.16, steps = 19 06:29:07 [INFO] train episode 9798: reward = -103.28, steps = 19 06:29:08 [INFO] train episode 9799: reward = -89.12, steps = 21 06:29:10 [INFO] train episode 9800: reward = -76.38, steps = 18 06:29:12 [INFO] train episode 9801: reward = -100.66, steps = 26 06:29:14 [INFO] train episode 9802: reward = -94.99, steps = 20 06:29:16 [INFO] train episode 9803: reward = -73.76, steps = 20 06:29:17 [INFO] train episode 9804: reward = -85.62, steps = 19 06:29:19 [INFO] train episode 9805: reward = -74.47, steps = 20 06:29:21 [INFO] train episode 9806: reward = -98.46, steps = 22 06:29:23 [INFO] train episode 9807: reward = -93.90, steps = 20 06:29:24 [INFO] train episode 9808: reward = -106.67, steps = 19 06:29:26 [INFO] train episode 9809: reward = -96.52, steps = 20 06:29:28 [INFO] train episode 9810: reward = -123.88, steps = 22 06:29:30 [INFO] train episode 9811: reward = -80.48, steps = 19 06:29:32 [INFO] train episode 9812: reward = -96.17, steps = 20 06:29:33 [INFO] train episode 9813: reward = -141.20, steps = 19 06:29:35 [INFO] train episode 9814: reward = -106.55, steps = 18 06:29:37 [INFO] train episode 9815: reward = -114.05, steps = 21 06:29:38 [INFO] train episode 9816: reward = -100.64, steps = 20 06:29:40 [INFO] train episode 9817: reward = -75.24, steps = 18 06:29:42 [INFO] train episode 9818: reward = -105.76, steps = 19 06:29:43 [INFO] train episode 9819: reward = -80.98, steps = 21 06:29:45 [INFO] train episode 9820: reward = -81.38, steps = 19 06:29:47 [INFO] train episode 9821: reward = -102.67, steps = 20 06:29:49 [INFO] train episode 9822: reward = -83.52, steps = 19 06:29:50 [INFO] train episode 9823: reward = -93.83, steps = 19 06:29:52 [INFO] train episode 9824: reward = -81.61, steps = 19 06:29:53 [INFO] train episode 9825: reward = -105.26, steps = 18 06:29:55 [INFO] train episode 9826: reward = -83.99, steps = 22 06:29:57 [INFO] train episode 9827: reward = -91.71, steps = 19 06:29:59 [INFO] train episode 9828: reward = -127.13, steps = 19 06:30:00 [INFO] train episode 9829: reward = -90.47, steps = 20 06:30:02 [INFO] train episode 9830: reward = -99.33, steps = 20 06:30:04 [INFO] train episode 9831: reward = -91.00, steps = 19 06:30:06 [INFO] train episode 9832: reward = -86.14, steps = 20 06:30:07 [INFO] train episode 9833: reward = -93.89, steps = 19 06:30:09 [INFO] train episode 9834: reward = -118.58, steps = 20 06:30:11 [INFO] train episode 9835: reward = -89.17, steps = 19 06:30:12 [INFO] train episode 9836: reward = -101.55, steps = 19 06:30:15 [INFO] train episode 9837: reward = -130.01, steps = 27 06:30:16 [INFO] train episode 9838: reward = -66.71, steps = 20 06:30:19 [INFO] train episode 9839: reward = -87.04, steps = 25 06:30:21 [INFO] train episode 9840: reward = -106.72, steps = 20 06:30:23 [INFO] train episode 9841: reward = -116.95, steps = 20 06:30:24 [INFO] train episode 9842: reward = -85.47, steps = 20 06:30:26 [INFO] train episode 9843: reward = -124.53, steps = 25 06:30:28 [INFO] train episode 9844: reward = -72.80, steps = 22 06:30:31 [INFO] train episode 9845: reward = -111.69, steps = 28 06:30:32 [INFO] train episode 9846: reward = -111.88, steps = 20 06:30:34 [INFO] train episode 9847: reward = -91.51, steps = 19 06:30:37 [INFO] train episode 9848: reward = -119.66, steps = 27 06:30:38 [INFO] train episode 9849: reward = -73.45, steps = 19 06:30:41 [INFO] train episode 9850: reward = -100.72, steps = 27 06:30:43 [INFO] train episode 9851: reward = -79.91, steps = 20 06:30:44 [INFO] train episode 9852: reward = -94.44, steps = 20 06:30:47 [INFO] train episode 9853: reward = -107.14, steps = 28 06:30:48 [INFO] train episode 9854: reward = -159.01, steps = 19 06:30:51 [INFO] train episode 9855: reward = -83.42, steps = 22 06:30:52 [INFO] train episode 9856: reward = -88.25, steps = 19 06:30:55 [INFO] train episode 9857: reward = -91.42, steps = 21 06:30:56 [INFO] train episode 9858: reward = -93.22, steps = 19 06:30:58 [INFO] train episode 9859: reward = -85.34, steps = 19 06:31:00 [INFO] train episode 9860: reward = -75.66, steps = 20 06:31:02 [INFO] train episode 9861: reward = -95.37, steps = 21 06:31:03 [INFO] train episode 9862: reward = -98.95, steps = 19 06:31:06 [INFO] train episode 9863: reward = -92.31, steps = 33 06:31:08 [INFO] train episode 9864: reward = -71.99, steps = 20 06:31:10 [INFO] train episode 9865: reward = -101.43, steps = 20 06:31:11 [INFO] train episode 9866: reward = -98.57, steps = 19 06:31:13 [INFO] train episode 9867: reward = -86.55, steps = 22 06:31:15 [INFO] train episode 9868: reward = -91.29, steps = 19 06:31:17 [INFO] train episode 9869: reward = -91.98, steps = 20 06:31:18 [INFO] train episode 9870: reward = -70.82, steps = 19 06:31:20 [INFO] train episode 9871: reward = -76.54, steps = 22 06:31:22 [INFO] train episode 9872: reward = -76.02, steps = 19 06:31:24 [INFO] train episode 9873: reward = -94.18, steps = 20 06:31:26 [INFO] train episode 9874: reward = -135.40, steps = 20 06:31:27 [INFO] train episode 9875: reward = -96.12, steps = 19 06:31:29 [INFO] train episode 9876: reward = -95.79, steps = 20 06:31:31 [INFO] train episode 9877: reward = -70.64, steps = 25 06:31:33 [INFO] train episode 9878: reward = -97.97, steps = 19 06:31:34 [INFO] train episode 9879: reward = -98.07, steps = 19 06:31:37 [INFO] train episode 9880: reward = -113.13, steps = 27 06:31:39 [INFO] train episode 9881: reward = -81.93, steps = 25 06:31:41 [INFO] train episode 9882: reward = -79.45, steps = 19 06:31:43 [INFO] train episode 9883: reward = -91.44, steps = 21 06:31:44 [INFO] train episode 9884: reward = -91.83, steps = 19 06:31:46 [INFO] train episode 9885: reward = -80.48, steps = 19 06:31:47 [INFO] train episode 9886: reward = -88.53, steps = 20 06:31:49 [INFO] train episode 9887: reward = -76.71, steps = 20 06:31:51 [INFO] train episode 9888: reward = -95.33, steps = 19 06:31:52 [INFO] train episode 9889: reward = -100.11, steps = 19 06:31:55 [INFO] train episode 9890: reward = -81.13, steps = 20 06:31:56 [INFO] train episode 9891: reward = -73.66, steps = 19 06:31:58 [INFO] train episode 9892: reward = -105.87, steps = 19 06:32:00 [INFO] train episode 9893: reward = -85.54, steps = 20 06:32:02 [INFO] train episode 9894: reward = -92.91, steps = 31 06:32:04 [INFO] train episode 9895: reward = -80.97, steps = 19 06:32:05 [INFO] train episode 9896: reward = -84.15, steps = 19 06:32:08 [INFO] train episode 9897: reward = -84.65, steps = 24 06:32:10 [INFO] train episode 9898: reward = -107.01, steps = 24 06:32:12 [INFO] train episode 9899: reward = -111.90, steps = 18 06:32:13 [INFO] train episode 9900: reward = -94.28, steps = 19 06:32:15 [INFO] train episode 9901: reward = -161.35, steps = 21 06:32:17 [INFO] train episode 9902: reward = -109.26, steps = 21 06:32:19 [INFO] train episode 9903: reward = -142.94, steps = 22 06:32:20 [INFO] train episode 9904: reward = -64.63, steps = 21 06:32:22 [INFO] train episode 9905: reward = -102.10, steps = 19 06:32:24 [INFO] train episode 9906: reward = -112.57, steps = 19 06:32:26 [INFO] train episode 9907: reward = -108.66, steps = 24 06:32:28 [INFO] train episode 9908: reward = -71.10, steps = 20 06:32:29 [INFO] train episode 9909: reward = -100.04, steps = 18 06:32:31 [INFO] train episode 9910: reward = -88.16, steps = 19 06:32:33 [INFO] train episode 9911: reward = -104.27, steps = 20 06:32:35 [INFO] train episode 9912: reward = -104.35, steps = 19 06:32:36 [INFO] train episode 9913: reward = -81.53, steps = 20 06:32:38 [INFO] train episode 9914: reward = -78.01, steps = 20 06:32:40 [INFO] train episode 9915: reward = -90.47, steps = 19 06:32:42 [INFO] train episode 9916: reward = -78.90, steps = 19 06:32:44 [INFO] train episode 9917: reward = -89.98, steps = 23 06:32:46 [INFO] train episode 9918: reward = -90.30, steps = 23 06:32:47 [INFO] train episode 9919: reward = -105.10, steps = 20 06:32:49 [INFO] train episode 9920: reward = -76.51, steps = 19 06:32:51 [INFO] train episode 9921: reward = -89.28, steps = 20 06:32:52 [INFO] train episode 9922: reward = -105.08, steps = 19 06:32:54 [INFO] train episode 9923: reward = -74.45, steps = 20 06:32:56 [INFO] train episode 9924: reward = -95.67, steps = 20 06:32:58 [INFO] train episode 9925: reward = -95.08, steps = 20 06:33:00 [INFO] train episode 9926: reward = -85.51, steps = 20 06:33:01 [INFO] train episode 9927: reward = -91.40, steps = 20 06:33:03 [INFO] train episode 9928: reward = -103.24, steps = 20 06:33:05 [INFO] train episode 9929: reward = -90.58, steps = 20 06:33:07 [INFO] train episode 9930: reward = -80.68, steps = 24 06:33:09 [INFO] train episode 9931: reward = -83.47, steps = 20 06:33:10 [INFO] train episode 9932: reward = -84.86, steps = 20 06:33:13 [INFO] train episode 9933: reward = -127.97, steps = 27 06:33:15 [INFO] train episode 9934: reward = -80.88, steps = 21 06:33:16 [INFO] train episode 9935: reward = -75.12, steps = 19 06:33:19 [INFO] train episode 9936: reward = -93.75, steps = 26 06:33:20 [INFO] train episode 9937: reward = -96.01, steps = 19 06:33:22 [INFO] train episode 9938: reward = -78.92, steps = 18 06:33:23 [INFO] train episode 9939: reward = -100.08, steps = 19 06:33:25 [INFO] train episode 9940: reward = -77.37, steps = 20 06:33:27 [INFO] train episode 9941: reward = -112.77, steps = 25 06:33:29 [INFO] train episode 9942: reward = -108.08, steps = 23 06:33:31 [INFO] train episode 9943: reward = -87.81, steps = 21 06:33:33 [INFO] train episode 9944: reward = -91.81, steps = 19 06:33:35 [INFO] train episode 9945: reward = -79.82, steps = 19 06:33:36 [INFO] train episode 9946: reward = -74.23, steps = 19 06:33:38 [INFO] train episode 9947: reward = -96.15, steps = 19 06:33:39 [INFO] train episode 9948: reward = -91.01, steps = 19 06:33:41 [INFO] train episode 9949: reward = -81.72, steps = 20 06:33:44 [INFO] train episode 9950: reward = -108.58, steps = 19 06:33:46 [INFO] train episode 9951: reward = -83.36, steps = 19 06:33:47 [INFO] train episode 9952: reward = -112.86, steps = 21 06:33:50 [INFO] train episode 9953: reward = -135.85, steps = 31 06:33:52 [INFO] train episode 9954: reward = -97.20, steps = 20 06:33:53 [INFO] train episode 9955: reward = -81.27, steps = 19 06:33:55 [INFO] train episode 9956: reward = -91.40, steps = 18 06:33:57 [INFO] train episode 9957: reward = -82.85, steps = 20 06:33:58 [INFO] train episode 9958: reward = -102.06, steps = 19 06:34:00 [INFO] train episode 9959: reward = -89.84, steps = 19 06:34:02 [INFO] train episode 9960: reward = -123.02, steps = 21 06:34:04 [INFO] train episode 9961: reward = -148.75, steps = 19 06:34:05 [INFO] train episode 9962: reward = -95.02, steps = 19 06:34:07 [INFO] train episode 9963: reward = -86.70, steps = 19 06:34:09 [INFO] train episode 9964: reward = -74.83, steps = 20 06:34:10 [INFO] train episode 9965: reward = -102.93, steps = 20 06:34:12 [INFO] train episode 9966: reward = -62.09, steps = 19 06:34:14 [INFO] train episode 9967: reward = -137.98, steps = 22 06:34:17 [INFO] train episode 9968: reward = -102.91, steps = 30 06:34:19 [INFO] train episode 9969: reward = -77.42, steps = 22 06:34:20 [INFO] train episode 9970: reward = -102.72, steps = 19 06:34:22 [INFO] train episode 9971: reward = -87.38, steps = 24 06:34:24 [INFO] train episode 9972: reward = -94.68, steps = 19 06:34:26 [INFO] train episode 9973: reward = -95.45, steps = 20 06:34:27 [INFO] train episode 9974: reward = -95.63, steps = 20 06:34:29 [INFO] train episode 9975: reward = -90.66, steps = 22 06:34:32 [INFO] train episode 9976: reward = -81.21, steps = 20 06:34:33 [INFO] train episode 9977: reward = -64.30, steps = 19 06:34:35 [INFO] train episode 9978: reward = -96.16, steps = 20 06:34:37 [INFO] train episode 9979: reward = -166.55, steps = 26 06:34:39 [INFO] train episode 9980: reward = -80.01, steps = 21 06:34:42 [INFO] train episode 9981: reward = -86.04, steps = 33 06:34:44 [INFO] train episode 9982: reward = -81.17, steps = 19 06:34:45 [INFO] train episode 9983: reward = -71.67, steps = 21 06:34:48 [INFO] train episode 9984: reward = -99.00, steps = 24 06:34:49 [INFO] train episode 9985: reward = -72.77, steps = 19 06:34:52 [INFO] train episode 9986: reward = -109.90, steps = 27 06:34:54 [INFO] train episode 9987: reward = -69.71, steps = 23 06:34:55 [INFO] train episode 9988: reward = -92.29, steps = 20 06:34:57 [INFO] train episode 9989: reward = -87.60, steps = 19 06:34:59 [INFO] train episode 9990: reward = -74.66, steps = 19 06:35:00 [INFO] train episode 9991: reward = -69.49, steps = 20 06:35:02 [INFO] train episode 9992: reward = -88.40, steps = 19 06:35:04 [INFO] train episode 9993: reward = -99.04, steps = 19 06:35:06 [INFO] train episode 9994: reward = -75.22, steps = 20 06:35:08 [INFO] train episode 9995: reward = -70.52, steps = 21 06:35:09 [INFO] train episode 9996: reward = -84.65, steps = 22 06:35:11 [INFO] train episode 9997: reward = -81.77, steps = 19 06:35:13 [INFO] train episode 9998: reward = -91.84, steps = 19 06:35:15 [INFO] train episode 9999: reward = -85.97, steps = 24 06:35:17 [INFO] train episode 10000: reward = -93.88, steps = 25 06:35:19 [INFO] train episode 10001: reward = -115.06, steps = 20 06:35:22 [INFO] train episode 10002: reward = -94.96, steps = 29 06:35:23 [INFO] train episode 10003: reward = -83.54, steps = 22 06:35:25 [INFO] train episode 10004: reward = -82.68, steps = 19 06:35:27 [INFO] train episode 10005: reward = -96.66, steps = 19 06:35:28 [INFO] train episode 10006: reward = -126.62, steps = 19 06:35:30 [INFO] train episode 10007: reward = -99.18, steps = 21 06:35:33 [INFO] train episode 10008: reward = -91.56, steps = 30 06:35:35 [INFO] train episode 10009: reward = -88.81, steps = 19 06:35:37 [INFO] train episode 10010: reward = -85.01, steps = 22 06:35:38 [INFO] train episode 10011: reward = -86.51, steps = 20 06:35:40 [INFO] train episode 10012: reward = -94.67, steps = 18 06:35:42 [INFO] train episode 10013: reward = -84.95, steps = 21 06:35:43 [INFO] train episode 10014: reward = -76.02, steps = 19 06:35:45 [INFO] train episode 10015: reward = -84.45, steps = 22 06:35:47 [INFO] train episode 10016: reward = -80.33, steps = 20 06:35:48 [INFO] train episode 10017: reward = -74.79, steps = 19 06:35:50 [INFO] train episode 10018: reward = -90.45, steps = 19 06:35:52 [INFO] train episode 10019: reward = -87.14, steps = 19 06:35:54 [INFO] train episode 10020: reward = -82.51, steps = 19 06:35:55 [INFO] train episode 10021: reward = -95.92, steps = 20 06:35:57 [INFO] train episode 10022: reward = -83.63, steps = 20 06:35:59 [INFO] train episode 10023: reward = -92.65, steps = 19 06:36:00 [INFO] train episode 10024: reward = -70.13, steps = 19 06:36:02 [INFO] train episode 10025: reward = -86.90, steps = 20 06:36:04 [INFO] train episode 10026: reward = -87.69, steps = 19 06:36:06 [INFO] train episode 10027: reward = -82.73, steps = 18 06:36:07 [INFO] train episode 10028: reward = -110.41, steps = 20 06:36:09 [INFO] train episode 10029: reward = -75.87, steps = 21 06:36:11 [INFO] train episode 10030: reward = -92.55, steps = 21 06:36:13 [INFO] train episode 10031: reward = -104.05, steps = 20 06:36:15 [INFO] train episode 10032: reward = -132.08, steps = 21 06:36:17 [INFO] train episode 10033: reward = -117.63, steps = 33 06:36:20 [INFO] train episode 10034: reward = -113.75, steps = 26 06:36:22 [INFO] train episode 10035: reward = -107.15, steps = 19 06:36:23 [INFO] train episode 10036: reward = -92.26, steps = 20 06:36:26 [INFO] train episode 10037: reward = -101.99, steps = 26 06:36:28 [INFO] train episode 10038: reward = -75.81, steps = 25 06:36:29 [INFO] train episode 10039: reward = -65.00, steps = 20 06:36:31 [INFO] train episode 10040: reward = -79.10, steps = 19 06:36:33 [INFO] train episode 10041: reward = -65.80, steps = 19 06:36:35 [INFO] train episode 10042: reward = -88.30, steps = 19 06:36:37 [INFO] train episode 10043: reward = -85.15, steps = 19 06:36:39 [INFO] train episode 10044: reward = -84.55, steps = 22 06:36:41 [INFO] train episode 10045: reward = -104.51, steps = 20 06:36:43 [INFO] train episode 10046: reward = -87.05, steps = 29 06:36:45 [INFO] train episode 10047: reward = -80.41, steps = 20 06:36:47 [INFO] train episode 10048: reward = -80.40, steps = 23 06:36:48 [INFO] train episode 10049: reward = -114.03, steps = 19 06:36:50 [INFO] train episode 10050: reward = -93.19, steps = 20 06:36:52 [INFO] train episode 10051: reward = -87.05, steps = 19 06:36:54 [INFO] train episode 10052: reward = -102.60, steps = 21 06:36:56 [INFO] train episode 10053: reward = -80.41, steps = 21 06:36:58 [INFO] train episode 10054: reward = -103.43, steps = 20 06:37:00 [INFO] train episode 10055: reward = -96.76, steps = 26 06:37:02 [INFO] train episode 10056: reward = -84.16, steps = 19 06:37:03 [INFO] train episode 10057: reward = -88.75, steps = 19 06:37:05 [INFO] train episode 10058: reward = -123.03, steps = 19 06:37:06 [INFO] train episode 10059: reward = -83.05, steps = 19 06:37:08 [INFO] train episode 10060: reward = -78.07, steps = 20 06:37:10 [INFO] train episode 10061: reward = -92.82, steps = 20 06:37:12 [INFO] train episode 10062: reward = -119.46, steps = 18 06:37:13 [INFO] train episode 10063: reward = -103.00, steps = 19 06:37:15 [INFO] train episode 10064: reward = -86.47, steps = 19 06:37:17 [INFO] train episode 10065: reward = -89.33, steps = 20 06:37:18 [INFO] train episode 10066: reward = -73.34, steps = 20 06:37:21 [INFO] train episode 10067: reward = -104.37, steps = 32 06:37:23 [INFO] train episode 10068: reward = -78.99, steps = 19 06:37:25 [INFO] train episode 10069: reward = -116.02, steps = 19 06:37:27 [INFO] train episode 10070: reward = -62.45, steps = 21 06:37:29 [INFO] train episode 10071: reward = -84.68, steps = 20 06:37:31 [INFO] train episode 10072: reward = -122.36, steps = 26 06:37:33 [INFO] train episode 10073: reward = -119.01, steps = 24 06:37:34 [INFO] train episode 10074: reward = -107.56, steps = 19 06:37:36 [INFO] train episode 10075: reward = -87.68, steps = 20 06:37:38 [INFO] train episode 10076: reward = -86.42, steps = 18 06:37:39 [INFO] train episode 10077: reward = -71.07, steps = 18 06:37:42 [INFO] train episode 10078: reward = -112.65, steps = 22 06:37:43 [INFO] train episode 10079: reward = -88.56, steps = 19 06:37:45 [INFO] train episode 10080: reward = -105.00, steps = 19 06:37:47 [INFO] train episode 10081: reward = -96.40, steps = 19 06:37:48 [INFO] train episode 10082: reward = -92.36, steps = 19 06:37:50 [INFO] train episode 10083: reward = -175.83, steps = 20 06:37:52 [INFO] train episode 10084: reward = -77.47, steps = 19 06:37:54 [INFO] train episode 10085: reward = -93.82, steps = 28 06:37:56 [INFO] train episode 10086: reward = -92.39, steps = 18 06:37:58 [INFO] train episode 10087: reward = -92.53, steps = 19 06:37:59 [INFO] train episode 10088: reward = -74.83, steps = 19 06:38:01 [INFO] train episode 10089: reward = -113.29, steps = 20 06:38:03 [INFO] train episode 10090: reward = -86.27, steps = 20 06:38:04 [INFO] train episode 10091: reward = -70.67, steps = 19 06:38:06 [INFO] train episode 10092: reward = -80.04, steps = 19 06:38:08 [INFO] train episode 10093: reward = -67.26, steps = 20 06:38:09 [INFO] train episode 10094: reward = -79.48, steps = 19 06:38:11 [INFO] train episode 10095: reward = -105.78, steps = 19 06:38:13 [INFO] train episode 10096: reward = -95.55, steps = 20 06:38:15 [INFO] train episode 10097: reward = -86.78, steps = 19 06:38:16 [INFO] train episode 10098: reward = -118.56, steps = 19 06:38:18 [INFO] train episode 10099: reward = -74.03, steps = 19 06:38:20 [INFO] train episode 10100: reward = -92.39, steps = 19 06:38:21 [INFO] train episode 10101: reward = -97.26, steps = 21 06:38:23 [INFO] train episode 10102: reward = -79.85, steps = 19 06:38:25 [INFO] train episode 10103: reward = -66.92, steps = 21 06:38:27 [INFO] train episode 10104: reward = -76.18, steps = 20 06:38:29 [INFO] train episode 10105: reward = -92.71, steps = 25 06:38:31 [INFO] train episode 10106: reward = -79.65, steps = 19 06:38:33 [INFO] train episode 10107: reward = -73.01, steps = 31 06:38:35 [INFO] train episode 10108: reward = -113.10, steps = 20 06:38:37 [INFO] train episode 10109: reward = -79.32, steps = 19 06:38:38 [INFO] train episode 10110: reward = -84.68, steps = 18 06:38:40 [INFO] train episode 10111: reward = -60.58, steps = 20 06:38:42 [INFO] train episode 10112: reward = -86.38, steps = 19 06:38:45 [INFO] train episode 10113: reward = -106.10, steps = 31 06:38:46 [INFO] train episode 10114: reward = -100.04, steps = 19 06:38:48 [INFO] train episode 10115: reward = -85.17, steps = 20 06:38:50 [INFO] train episode 10116: reward = -91.56, steps = 24 06:38:52 [INFO] train episode 10117: reward = -111.88, steps = 20 06:38:54 [INFO] train episode 10118: reward = -126.63, steps = 29 06:38:56 [INFO] train episode 10119: reward = -118.99, steps = 20 06:38:58 [INFO] train episode 10120: reward = -71.05, steps = 19 06:38:59 [INFO] train episode 10121: reward = -82.33, steps = 19 06:39:01 [INFO] train episode 10122: reward = -85.30, steps = 19 06:39:04 [INFO] train episode 10123: reward = -80.88, steps = 27 06:39:05 [INFO] train episode 10124: reward = -80.98, steps = 20 06:39:07 [INFO] train episode 10125: reward = -61.72, steps = 22 06:39:09 [INFO] train episode 10126: reward = -87.38, steps = 19 06:39:11 [INFO] train episode 10127: reward = -86.42, steps = 20 06:39:12 [INFO] train episode 10128: reward = -102.11, steps = 19 06:39:14 [INFO] train episode 10129: reward = -99.76, steps = 19 06:39:16 [INFO] train episode 10130: reward = -89.31, steps = 19 06:39:17 [INFO] train episode 10131: reward = -87.54, steps = 19 06:39:19 [INFO] train episode 10132: reward = -93.36, steps = 18 06:39:21 [INFO] train episode 10133: reward = -97.40, steps = 19 06:39:23 [INFO] train episode 10134: reward = -91.17, steps = 19 06:39:25 [INFO] train episode 10135: reward = -82.22, steps = 26 06:39:27 [INFO] train episode 10136: reward = -65.42, steps = 19 06:39:29 [INFO] train episode 10137: reward = -83.44, steps = 19 06:39:30 [INFO] train episode 10138: reward = -101.19, steps = 22 06:39:33 [INFO] train episode 10139: reward = -70.97, steps = 20 06:39:34 [INFO] train episode 10140: reward = -80.58, steps = 21 06:39:36 [INFO] train episode 10141: reward = -80.68, steps = 20 06:39:38 [INFO] train episode 10142: reward = -82.71, steps = 19 06:39:39 [INFO] train episode 10143: reward = -86.60, steps = 19 06:39:41 [INFO] train episode 10144: reward = -88.23, steps = 23 06:39:43 [INFO] train episode 10145: reward = -85.14, steps = 25 06:39:45 [INFO] train episode 10146: reward = -86.25, steps = 20 06:39:47 [INFO] train episode 10147: reward = -90.28, steps = 19 06:39:49 [INFO] train episode 10148: reward = -100.87, steps = 22 06:39:51 [INFO] train episode 10149: reward = -70.94, steps = 19 06:39:53 [INFO] train episode 10150: reward = -85.52, steps = 28 06:39:55 [INFO] train episode 10151: reward = -77.23, steps = 19 06:39:57 [INFO] train episode 10152: reward = -90.08, steps = 25 06:39:58 [INFO] train episode 10153: reward = -88.23, steps = 19 06:40:01 [INFO] train episode 10154: reward = -118.07, steps = 32 06:40:03 [INFO] train episode 10155: reward = -86.30, steps = 19 06:40:05 [INFO] train episode 10156: reward = -71.99, steps = 20 06:40:06 [INFO] train episode 10157: reward = -68.23, steps = 19 06:40:08 [INFO] train episode 10158: reward = -80.12, steps = 19 06:40:10 [INFO] train episode 10159: reward = -73.19, steps = 20 06:40:12 [INFO] train episode 10160: reward = -83.23, steps = 22 06:40:14 [INFO] train episode 10161: reward = -107.66, steps = 24 06:40:16 [INFO] train episode 10162: reward = -84.45, steps = 24 06:40:17 [INFO] train episode 10163: reward = -75.90, steps = 20 06:40:19 [INFO] train episode 10164: reward = -66.08, steps = 19 06:40:21 [INFO] train episode 10165: reward = -77.45, steps = 19 06:40:23 [INFO] train episode 10166: reward = -83.54, steps = 19 06:40:24 [INFO] train episode 10167: reward = -89.74, steps = 20 06:40:26 [INFO] train episode 10168: reward = -60.91, steps = 20 06:40:28 [INFO] train episode 10169: reward = -69.55, steps = 19 06:40:29 [INFO] train episode 10170: reward = -91.59, steps = 18 06:40:31 [INFO] train episode 10171: reward = -82.39, steps = 19 06:40:33 [INFO] train episode 10172: reward = -103.59, steps = 19 06:40:34 [INFO] train episode 10173: reward = -76.50, steps = 19 06:40:37 [INFO] train episode 10174: reward = -79.02, steps = 25 06:40:38 [INFO] train episode 10175: reward = -86.40, steps = 20 06:40:40 [INFO] train episode 10176: reward = -73.62, steps = 19 06:40:42 [INFO] train episode 10177: reward = -93.12, steps = 19 06:40:44 [INFO] train episode 10178: reward = -120.09, steps = 23 06:40:46 [INFO] train episode 10179: reward = -95.85, steps = 27 06:40:48 [INFO] train episode 10180: reward = -70.57, steps = 20 06:40:49 [INFO] train episode 10181: reward = -76.59, steps = 20 06:40:52 [INFO] train episode 10182: reward = -88.51, steps = 24 06:40:54 [INFO] train episode 10183: reward = -99.99, steps = 20 06:40:55 [INFO] train episode 10184: reward = -85.37, steps = 22 06:40:57 [INFO] train episode 10185: reward = -89.68, steps = 20 06:40:59 [INFO] train episode 10186: reward = -80.72, steps = 22 06:41:01 [INFO] train episode 10187: reward = -102.87, steps = 19 06:41:04 [INFO] train episode 10188: reward = -92.25, steps = 37 06:41:06 [INFO] train episode 10189: reward = -94.96, steps = 20 06:41:08 [INFO] train episode 10190: reward = -135.92, steps = 19 06:41:09 [INFO] train episode 10191: reward = -113.50, steps = 19 06:41:11 [INFO] train episode 10192: reward = -74.90, steps = 20 06:41:13 [INFO] train episode 10193: reward = -77.95, steps = 22 06:41:15 [INFO] train episode 10194: reward = -72.37, steps = 20 06:41:16 [INFO] train episode 10195: reward = -72.44, steps = 20 06:41:18 [INFO] train episode 10196: reward = -99.92, steps = 19 06:41:20 [INFO] train episode 10197: reward = -74.66, steps = 19 06:41:21 [INFO] train episode 10198: reward = -69.29, steps = 19 06:41:23 [INFO] train episode 10199: reward = -86.49, steps = 19 06:41:25 [INFO] train episode 10200: reward = -64.41, steps = 23 06:41:27 [INFO] train episode 10201: reward = -83.64, steps = 19 06:41:29 [INFO] train episode 10202: reward = -92.12, steps = 20 06:41:30 [INFO] train episode 10203: reward = -61.90, steps = 20 06:41:32 [INFO] train episode 10204: reward = -150.88, steps = 19 06:41:34 [INFO] train episode 10205: reward = -84.78, steps = 22 06:41:36 [INFO] train episode 10206: reward = -95.74, steps = 26 06:41:38 [INFO] train episode 10207: reward = -65.22, steps = 19 06:41:40 [INFO] train episode 10208: reward = -74.99, steps = 20 06:41:41 [INFO] train episode 10209: reward = -75.35, steps = 19 06:41:43 [INFO] train episode 10210: reward = -69.25, steps = 19 06:41:45 [INFO] train episode 10211: reward = -70.74, steps = 19 06:41:46 [INFO] train episode 10212: reward = -71.49, steps = 20 06:41:48 [INFO] train episode 10213: reward = -81.65, steps = 19 06:41:50 [INFO] train episode 10214: reward = -123.93, steps = 20 06:41:52 [INFO] train episode 10215: reward = -115.43, steps = 20 06:41:54 [INFO] train episode 10216: reward = -75.19, steps = 21 06:41:57 [INFO] train episode 10217: reward = -98.93, steps = 35 06:41:59 [INFO] train episode 10218: reward = -91.25, steps = 23 06:42:00 [INFO] train episode 10219: reward = -98.81, steps = 19 06:42:03 [INFO] train episode 10220: reward = -97.03, steps = 27 06:42:04 [INFO] train episode 10221: reward = -55.35, steps = 20 06:42:06 [INFO] train episode 10222: reward = -90.78, steps = 19 06:42:08 [INFO] train episode 10223: reward = -94.54, steps = 20 06:42:10 [INFO] train episode 10224: reward = -79.75, steps = 19 06:42:12 [INFO] train episode 10225: reward = -82.21, steps = 20 06:42:14 [INFO] train episode 10226: reward = -79.67, steps = 20 06:42:16 [INFO] train episode 10227: reward = -79.84, steps = 19 06:42:17 [INFO] train episode 10228: reward = -70.96, steps = 20 06:42:19 [INFO] train episode 10229: reward = -74.61, steps = 20 06:42:21 [INFO] train episode 10230: reward = -73.82, steps = 20 06:42:22 [INFO] train episode 10231: reward = -147.72, steps = 21 06:42:24 [INFO] train episode 10232: reward = -61.14, steps = 20 06:42:26 [INFO] train episode 10233: reward = -81.37, steps = 19 06:42:28 [INFO] train episode 10234: reward = -82.30, steps = 24 06:42:30 [INFO] train episode 10235: reward = -84.19, steps = 20 06:42:32 [INFO] train episode 10236: reward = -77.34, steps = 19 06:42:33 [INFO] train episode 10237: reward = -94.73, steps = 19 06:42:35 [INFO] train episode 10238: reward = -99.50, steps = 20 06:42:37 [INFO] train episode 10239: reward = -134.98, steps = 21 06:42:39 [INFO] train episode 10240: reward = -86.79, steps = 27 06:42:41 [INFO] train episode 10241: reward = -85.61, steps = 19 06:42:43 [INFO] train episode 10242: reward = -77.45, steps = 21 06:42:45 [INFO] train episode 10243: reward = -83.22, steps = 20 06:42:46 [INFO] train episode 10244: reward = -81.92, steps = 20 06:42:48 [INFO] train episode 10245: reward = -77.98, steps = 19 06:42:50 [INFO] train episode 10246: reward = -95.32, steps = 20 06:42:51 [INFO] train episode 10247: reward = -84.83, steps = 20 06:42:54 [INFO] train episode 10248: reward = -96.89, steps = 26 06:42:55 [INFO] train episode 10249: reward = -90.46, steps = 19 06:42:57 [INFO] train episode 10250: reward = -121.34, steps = 21 06:42:59 [INFO] train episode 10251: reward = -83.33, steps = 20 06:43:01 [INFO] train episode 10252: reward = -93.40, steps = 19 06:43:02 [INFO] train episode 10253: reward = -67.37, steps = 19 06:43:04 [INFO] train episode 10254: reward = -75.83, steps = 19 06:43:06 [INFO] train episode 10255: reward = -79.24, steps = 20 06:43:07 [INFO] train episode 10256: reward = -74.71, steps = 19 06:43:09 [INFO] train episode 10257: reward = -84.82, steps = 24 06:43:11 [INFO] train episode 10258: reward = -68.93, steps = 19 06:43:13 [INFO] train episode 10259: reward = -70.83, steps = 22 06:43:15 [INFO] train episode 10260: reward = -74.20, steps = 19 06:43:17 [INFO] train episode 10261: reward = -87.23, steps = 20 06:43:18 [INFO] train episode 10262: reward = -84.51, steps = 21 06:43:20 [INFO] train episode 10263: reward = -82.55, steps = 20 06:43:22 [INFO] train episode 10264: reward = -75.19, steps = 19 06:43:24 [INFO] train episode 10265: reward = -60.04, steps = 20 06:43:25 [INFO] train episode 10266: reward = -77.73, steps = 19 06:43:27 [INFO] train episode 10267: reward = -82.29, steps = 19 06:43:29 [INFO] train episode 10268: reward = -91.75, steps = 18 06:43:30 [INFO] train episode 10269: reward = -76.46, steps = 18 06:43:32 [INFO] train episode 10270: reward = -72.95, steps = 20 06:43:34 [INFO] train episode 10271: reward = -89.80, steps = 19 06:43:35 [INFO] train episode 10272: reward = -106.97, steps = 20 06:43:37 [INFO] train episode 10273: reward = -74.68, steps = 22 06:43:39 [INFO] train episode 10274: reward = -98.13, steps = 19 06:43:40 [INFO] train episode 10275: reward = -98.53, steps = 19 06:43:42 [INFO] train episode 10276: reward = -71.51, steps = 20 06:43:44 [INFO] train episode 10277: reward = -89.14, steps = 21 06:43:46 [INFO] train episode 10278: reward = -83.94, steps = 19 06:43:48 [INFO] train episode 10279: reward = -105.23, steps = 19 06:43:49 [INFO] train episode 10280: reward = -75.83, steps = 18 06:43:51 [INFO] train episode 10281: reward = -76.37, steps = 19 06:43:53 [INFO] train episode 10282: reward = -108.89, steps = 22 06:43:54 [INFO] train episode 10283: reward = -82.87, steps = 19 06:43:56 [INFO] train episode 10284: reward = -83.28, steps = 20 06:43:58 [INFO] train episode 10285: reward = -67.15, steps = 24 06:44:00 [INFO] train episode 10286: reward = -61.44, steps = 19 06:44:02 [INFO] train episode 10287: reward = -97.76, steps = 19 06:44:04 [INFO] train episode 10288: reward = -66.60, steps = 24 06:44:05 [INFO] train episode 10289: reward = -78.86, steps = 20 06:44:08 [INFO] train episode 10290: reward = -86.85, steps = 30 06:44:10 [INFO] train episode 10291: reward = -79.55, steps = 19 06:44:11 [INFO] train episode 10292: reward = -95.67, steps = 20 06:44:13 [INFO] train episode 10293: reward = -72.38, steps = 19 06:44:15 [INFO] train episode 10294: reward = -85.11, steps = 19 06:44:17 [INFO] train episode 10295: reward = -76.23, steps = 21 06:44:18 [INFO] train episode 10296: reward = -76.89, steps = 20 06:44:20 [INFO] train episode 10297: reward = -98.15, steps = 22 06:44:22 [INFO] train episode 10298: reward = -98.86, steps = 19 06:44:24 [INFO] train episode 10299: reward = -73.51, steps = 21 06:44:25 [INFO] train episode 10300: reward = -79.57, steps = 19 06:44:27 [INFO] train episode 10301: reward = -81.80, steps = 18 06:44:29 [INFO] train episode 10302: reward = -81.47, steps = 19 06:44:30 [INFO] train episode 10303: reward = -88.91, steps = 20 06:44:32 [INFO] train episode 10304: reward = -68.90, steps = 19 06:44:34 [INFO] train episode 10305: reward = -110.30, steps = 19 06:44:36 [INFO] train episode 10306: reward = -74.36, steps = 21 06:44:37 [INFO] train episode 10307: reward = -87.92, steps = 19 06:44:39 [INFO] train episode 10308: reward = -91.42, steps = 19 06:44:41 [INFO] train episode 10309: reward = -76.05, steps = 19 06:44:43 [INFO] train episode 10310: reward = -72.86, steps = 21 06:44:44 [INFO] train episode 10311: reward = -92.34, steps = 19 06:44:46 [INFO] train episode 10312: reward = -105.31, steps = 22 06:44:48 [INFO] train episode 10313: reward = -72.83, steps = 18 06:44:50 [INFO] train episode 10314: reward = -116.87, steps = 29 06:44:52 [INFO] train episode 10315: reward = -110.62, steps = 20 06:44:54 [INFO] train episode 10316: reward = -73.92, steps = 19 06:44:55 [INFO] train episode 10317: reward = -69.10, steps = 19 06:44:58 [INFO] train episode 10318: reward = -88.89, steps = 27 06:44:59 [INFO] train episode 10319: reward = -87.45, steps = 19 06:45:02 [INFO] train episode 10320: reward = -82.60, steps = 19 06:45:04 [INFO] train episode 10321: reward = -71.20, steps = 23 06:45:06 [INFO] train episode 10322: reward = -70.35, steps = 21 06:45:08 [INFO] train episode 10323: reward = -79.41, steps = 19 06:45:09 [INFO] train episode 10324: reward = -71.24, steps = 21 06:45:11 [INFO] train episode 10325: reward = -100.11, steps = 19 06:45:13 [INFO] train episode 10326: reward = -118.37, steps = 27 06:45:15 [INFO] train episode 10327: reward = -78.13, steps = 19 06:45:17 [INFO] train episode 10328: reward = -112.94, steps = 24 06:45:19 [INFO] train episode 10329: reward = -82.70, steps = 19 06:45:21 [INFO] train episode 10330: reward = -116.53, steps = 20 06:45:22 [INFO] train episode 10331: reward = -93.61, steps = 19 06:45:24 [INFO] train episode 10332: reward = -95.68, steps = 19 06:45:26 [INFO] train episode 10333: reward = -91.48, steps = 19 06:45:28 [INFO] train episode 10334: reward = -75.45, steps = 19 06:45:29 [INFO] train episode 10335: reward = -85.90, steps = 20 06:45:31 [INFO] train episode 10336: reward = -107.95, steps = 19 06:45:33 [INFO] train episode 10337: reward = -89.42, steps = 26 06:45:35 [INFO] train episode 10338: reward = -97.21, steps = 20 06:45:37 [INFO] train episode 10339: reward = -87.21, steps = 19 06:45:39 [INFO] train episode 10340: reward = -90.28, steps = 20 06:45:40 [INFO] train episode 10341: reward = -102.69, steps = 19 06:45:42 [INFO] train episode 10342: reward = -87.19, steps = 19 06:45:44 [INFO] train episode 10343: reward = -105.72, steps = 24 06:45:46 [INFO] train episode 10344: reward = -86.63, steps = 27 06:45:48 [INFO] train episode 10345: reward = -86.01, steps = 19 06:45:49 [INFO] train episode 10346: reward = -83.75, steps = 19 06:45:52 [INFO] train episode 10347: reward = -73.05, steps = 28 06:45:54 [INFO] train episode 10348: reward = -84.39, steps = 20 06:45:55 [INFO] train episode 10349: reward = -61.61, steps = 19 06:45:57 [INFO] train episode 10350: reward = -96.75, steps = 21 06:45:59 [INFO] train episode 10351: reward = -74.09, steps = 18 06:46:01 [INFO] train episode 10352: reward = -81.68, steps = 27 06:46:03 [INFO] train episode 10353: reward = -70.84, steps = 19 06:46:04 [INFO] train episode 10354: reward = -78.65, steps = 19 06:46:07 [INFO] train episode 10355: reward = -81.55, steps = 25 06:46:09 [INFO] train episode 10356: reward = -73.08, steps = 20 06:46:10 [INFO] train episode 10357: reward = -67.79, steps = 20 06:46:12 [INFO] train episode 10358: reward = -78.58, steps = 23 06:46:14 [INFO] train episode 10359: reward = -80.39, steps = 21 06:46:16 [INFO] train episode 10360: reward = -109.21, steps = 27 06:46:18 [INFO] train episode 10361: reward = -104.05, steps = 19 06:46:20 [INFO] train episode 10362: reward = -102.77, steps = 20 06:46:23 [INFO] train episode 10363: reward = -110.78, steps = 34 06:46:25 [INFO] train episode 10364: reward = -77.88, steps = 27 06:46:27 [INFO] train episode 10365: reward = -70.94, steps = 22 06:46:29 [INFO] train episode 10366: reward = -101.28, steps = 19 06:46:31 [INFO] train episode 10367: reward = -70.39, steps = 20 06:46:32 [INFO] train episode 10368: reward = -72.00, steps = 19 06:46:34 [INFO] train episode 10369: reward = -91.97, steps = 19 06:46:36 [INFO] train episode 10370: reward = -66.24, steps = 22 06:46:38 [INFO] train episode 10371: reward = -77.03, steps = 19 06:46:40 [INFO] train episode 10372: reward = -76.81, steps = 19 06:46:41 [INFO] train episode 10373: reward = -119.71, steps = 22 06:46:44 [INFO] train episode 10374: reward = -92.73, steps = 28 06:46:46 [INFO] train episode 10375: reward = -108.11, steps = 20 06:46:47 [INFO] train episode 10376: reward = -79.76, steps = 20 06:46:49 [INFO] train episode 10377: reward = -99.21, steps = 21 06:46:51 [INFO] train episode 10378: reward = -64.98, steps = 19 06:46:53 [INFO] train episode 10379: reward = -87.49, steps = 22 06:46:55 [INFO] train episode 10380: reward = -132.01, steps = 19 06:46:56 [INFO] train episode 10381: reward = -72.76, steps = 19 06:46:58 [INFO] train episode 10382: reward = -88.92, steps = 20 06:47:00 [INFO] train episode 10383: reward = -82.05, steps = 19 06:47:01 [INFO] train episode 10384: reward = -82.53, steps = 19 06:47:03 [INFO] train episode 10385: reward = -86.86, steps = 20 06:47:05 [INFO] train episode 10386: reward = -66.03, steps = 20 06:47:07 [INFO] train episode 10387: reward = -97.56, steps = 27 06:47:09 [INFO] train episode 10388: reward = -74.82, steps = 20 06:47:11 [INFO] train episode 10389: reward = -102.85, steps = 18 06:47:12 [INFO] train episode 10390: reward = -73.80, steps = 19 06:47:14 [INFO] train episode 10391: reward = -87.38, steps = 19 06:47:15 [INFO] train episode 10392: reward = -76.48, steps = 19 06:47:17 [INFO] train episode 10393: reward = -67.63, steps = 19 06:47:19 [INFO] train episode 10394: reward = -96.15, steps = 19 06:47:20 [INFO] train episode 10395: reward = -96.02, steps = 19 06:47:23 [INFO] train episode 10396: reward = -84.06, steps = 33 06:47:25 [INFO] train episode 10397: reward = -80.16, steps = 19 06:47:27 [INFO] train episode 10398: reward = -78.02, steps = 19 06:47:28 [INFO] train episode 10399: reward = -83.20, steps = 19 06:47:31 [INFO] train episode 10400: reward = -103.21, steps = 27 06:47:32 [INFO] train episode 10401: reward = -89.61, steps = 18 06:47:34 [INFO] train episode 10402: reward = -74.90, steps = 20 06:47:36 [INFO] train episode 10403: reward = -80.42, steps = 19 06:47:37 [INFO] train episode 10404: reward = -70.19, steps = 20 06:47:39 [INFO] train episode 10405: reward = -94.78, steps = 24 06:47:41 [INFO] train episode 10406: reward = -77.03, steps = 19 06:47:44 [INFO] train episode 10407: reward = -77.52, steps = 30 06:47:46 [INFO] train episode 10408: reward = -80.15, steps = 19 06:47:47 [INFO] train episode 10409: reward = -89.66, steps = 20 06:47:49 [INFO] train episode 10410: reward = -93.91, steps = 21 06:47:53 [INFO] train episode 10411: reward = -100.30, steps = 34 06:47:54 [INFO] train episode 10412: reward = -82.54, steps = 19 06:47:57 [INFO] train episode 10413: reward = -85.87, steps = 28 06:47:59 [INFO] train episode 10414: reward = -51.95, steps = 24 06:48:01 [INFO] train episode 10415: reward = -69.40, steps = 19 06:48:03 [INFO] train episode 10416: reward = -96.38, steps = 18 06:48:05 [INFO] train episode 10417: reward = -77.43, steps = 27 06:48:06 [INFO] train episode 10418: reward = -89.58, steps = 18 06:48:08 [INFO] train episode 10419: reward = -92.88, steps = 24 06:48:11 [INFO] train episode 10420: reward = -85.26, steps = 28 06:48:13 [INFO] train episode 10421: reward = -89.55, steps = 19 06:48:15 [INFO] train episode 10422: reward = -88.15, steps = 23 06:48:17 [INFO] train episode 10423: reward = -73.57, steps = 21 06:48:18 [INFO] train episode 10424: reward = -87.73, steps = 20 06:48:20 [INFO] train episode 10425: reward = -77.26, steps = 20 06:48:22 [INFO] train episode 10426: reward = -68.95, steps = 20 06:48:23 [INFO] train episode 10427: reward = -67.63, steps = 19 06:48:25 [INFO] train episode 10428: reward = -103.30, steps = 24 06:48:27 [INFO] train episode 10429: reward = -84.60, steps = 20 06:48:29 [INFO] train episode 10430: reward = -102.34, steps = 16 06:48:31 [INFO] train episode 10431: reward = -89.64, steps = 22 06:48:32 [INFO] train episode 10432: reward = -78.13, steps = 19 06:48:34 [INFO] train episode 10433: reward = -59.67, steps = 21 06:48:36 [INFO] train episode 10434: reward = -106.30, steps = 20 06:48:38 [INFO] train episode 10435: reward = -80.07, steps = 23 06:48:40 [INFO] train episode 10436: reward = -141.69, steps = 26 06:48:42 [INFO] train episode 10437: reward = -69.30, steps = 19 06:48:44 [INFO] train episode 10438: reward = -109.05, steps = 20 06:48:46 [INFO] train episode 10439: reward = -99.30, steps = 25 06:48:48 [INFO] train episode 10440: reward = -86.53, steps = 22 06:48:50 [INFO] train episode 10441: reward = -94.11, steps = 19 06:48:51 [INFO] train episode 10442: reward = -79.20, steps = 21 06:48:53 [INFO] train episode 10443: reward = -88.16, steps = 19 06:48:55 [INFO] train episode 10444: reward = -63.18, steps = 29 06:48:57 [INFO] train episode 10445: reward = -92.44, steps = 19 06:48:59 [INFO] train episode 10446: reward = -99.31, steps = 23 06:49:01 [INFO] train episode 10447: reward = -98.56, steps = 19 06:49:03 [INFO] train episode 10448: reward = -118.07, steps = 18 06:49:04 [INFO] train episode 10449: reward = -68.17, steps = 20 06:49:06 [INFO] train episode 10450: reward = -72.15, steps = 19 06:49:08 [INFO] train episode 10451: reward = -81.03, steps = 19 06:49:09 [INFO] train episode 10452: reward = -73.52, steps = 19 06:49:12 [INFO] train episode 10453: reward = -147.82, steps = 25 06:49:14 [INFO] train episode 10454: reward = -99.97, steps = 19 06:49:17 [INFO] train episode 10455: reward = -73.41, steps = 33 06:49:19 [INFO] train episode 10456: reward = -76.92, steps = 19 06:49:20 [INFO] train episode 10457: reward = -79.54, steps = 19 06:49:22 [INFO] train episode 10458: reward = -108.46, steps = 24 06:49:24 [INFO] train episode 10459: reward = -84.37, steps = 20 06:49:26 [INFO] train episode 10460: reward = -75.35, steps = 26 06:49:28 [INFO] train episode 10461: reward = -74.57, steps = 20 06:49:30 [INFO] train episode 10462: reward = -119.27, steps = 22 06:49:32 [INFO] train episode 10463: reward = -101.60, steps = 19 06:49:33 [INFO] train episode 10464: reward = -84.53, steps = 20 06:49:35 [INFO] train episode 10465: reward = -74.57, steps = 23 06:49:37 [INFO] train episode 10466: reward = -81.54, steps = 19 06:49:39 [INFO] train episode 10467: reward = -106.90, steps = 24 06:49:41 [INFO] train episode 10468: reward = -95.45, steps = 20 06:49:42 [INFO] train episode 10469: reward = -114.28, steps = 18 06:49:45 [INFO] train episode 10470: reward = -111.55, steps = 28 06:49:47 [INFO] train episode 10471: reward = -73.50, steps = 24 06:49:49 [INFO] train episode 10472: reward = -76.69, steps = 20 06:49:51 [INFO] train episode 10473: reward = -87.86, steps = 25 06:49:53 [INFO] train episode 10474: reward = -71.47, steps = 20 06:49:55 [INFO] train episode 10475: reward = -92.02, steps = 30 06:49:57 [INFO] train episode 10476: reward = -86.36, steps = 20 06:49:59 [INFO] train episode 10477: reward = -68.07, steps = 25 06:50:01 [INFO] train episode 10478: reward = -85.64, steps = 20 06:50:03 [INFO] train episode 10479: reward = -75.61, steps = 20 06:50:05 [INFO] train episode 10480: reward = -86.88, steps = 18 06:50:07 [INFO] train episode 10481: reward = -103.35, steps = 27 06:50:09 [INFO] train episode 10482: reward = -102.74, steps = 21 06:50:11 [INFO] train episode 10483: reward = -76.70, steps = 25 06:50:13 [INFO] train episode 10484: reward = -91.16, steps = 28 06:50:15 [INFO] train episode 10485: reward = -68.67, steps = 23 06:50:17 [INFO] train episode 10486: reward = -77.88, steps = 20 06:50:19 [INFO] train episode 10487: reward = -84.30, steps = 19 06:50:21 [INFO] train episode 10488: reward = -123.63, steps = 19 06:50:22 [INFO] train episode 10489: reward = -74.08, steps = 21 06:50:24 [INFO] train episode 10490: reward = -76.95, steps = 18 06:50:26 [INFO] train episode 10491: reward = -76.35, steps = 20 06:50:27 [INFO] train episode 10492: reward = -74.57, steps = 20 06:50:29 [INFO] train episode 10493: reward = -66.38, steps = 19 06:50:31 [INFO] train episode 10494: reward = -101.47, steps = 23 06:50:33 [INFO] train episode 10495: reward = -76.13, steps = 19 06:50:35 [INFO] train episode 10496: reward = -142.91, steps = 22 06:50:37 [INFO] train episode 10497: reward = -66.83, steps = 20 06:50:39 [INFO] train episode 10498: reward = -70.18, steps = 25 06:50:40 [INFO] train episode 10499: reward = -63.25, steps = 20 06:50:43 [INFO] train episode 10500: reward = -123.66, steps = 24 06:50:45 [INFO] train episode 10501: reward = -77.29, steps = 19 06:50:47 [INFO] train episode 10502: reward = -64.93, steps = 20 06:50:48 [INFO] train episode 10503: reward = -87.12, steps = 19 06:50:51 [INFO] train episode 10504: reward = -119.04, steps = 24 06:50:52 [INFO] train episode 10505: reward = -76.97, steps = 19 06:50:54 [INFO] train episode 10506: reward = -79.24, steps = 20 06:50:56 [INFO] train episode 10507: reward = -92.32, steps = 20 06:50:57 [INFO] train episode 10508: reward = -97.13, steps = 20 06:50:59 [INFO] train episode 10509: reward = -99.12, steps = 19 06:51:01 [INFO] train episode 10510: reward = -74.94, steps = 20 06:51:03 [INFO] train episode 10511: reward = -87.74, steps = 19 06:51:04 [INFO] train episode 10512: reward = -117.72, steps = 20 06:51:07 [INFO] train episode 10513: reward = -112.73, steps = 22 06:51:08 [INFO] train episode 10514: reward = -68.39, steps = 22 06:51:10 [INFO] train episode 10515: reward = -125.46, steps = 23 06:51:12 [INFO] train episode 10516: reward = -93.34, steps = 20 06:51:14 [INFO] train episode 10517: reward = -77.63, steps = 19 06:51:16 [INFO] train episode 10518: reward = -94.25, steps = 27 06:51:18 [INFO] train episode 10519: reward = -87.00, steps = 21 06:51:20 [INFO] train episode 10520: reward = -83.51, steps = 26 06:51:22 [INFO] train episode 10521: reward = -64.99, steps = 20 06:51:24 [INFO] train episode 10522: reward = -113.71, steps = 21 06:51:26 [INFO] train episode 10523: reward = -88.56, steps = 20 06:51:27 [INFO] train episode 10524: reward = -84.01, steps = 19 06:51:29 [INFO] train episode 10525: reward = -64.12, steps = 20 06:51:31 [INFO] train episode 10526: reward = -94.69, steps = 24 06:51:33 [INFO] train episode 10527: reward = -81.29, steps = 20 06:51:35 [INFO] train episode 10528: reward = -103.11, steps = 28 06:51:37 [INFO] train episode 10529: reward = -85.92, steps = 25 06:51:39 [INFO] train episode 10530: reward = -95.46, steps = 23 06:51:41 [INFO] train episode 10531: reward = -70.12, steps = 18 06:51:43 [INFO] train episode 10532: reward = -90.08, steps = 23 06:51:45 [INFO] train episode 10533: reward = -115.81, steps = 24 06:51:47 [INFO] train episode 10534: reward = -82.75, steps = 22 06:51:49 [INFO] train episode 10535: reward = -96.52, steps = 23 06:51:51 [INFO] train episode 10536: reward = -87.87, steps = 27 06:51:54 [INFO] train episode 10537: reward = -86.73, steps = 28 06:51:57 [INFO] train episode 10538: reward = -113.36, steps = 38 06:51:59 [INFO] train episode 10539: reward = -82.90, steps = 24 06:52:01 [INFO] train episode 10540: reward = -97.19, steps = 24 06:52:03 [INFO] train episode 10541: reward = -101.09, steps = 22 06:52:05 [INFO] train episode 10542: reward = -93.96, steps = 27 06:52:08 [INFO] train episode 10543: reward = -75.13, steps = 30 06:52:11 [INFO] train episode 10544: reward = -110.65, steps = 33 06:52:13 [INFO] train episode 10545: reward = -78.63, steps = 20 06:52:15 [INFO] train episode 10546: reward = -80.86, steps = 24 06:52:16 [INFO] train episode 10547: reward = -68.52, steps = 20 06:52:18 [INFO] train episode 10548: reward = -96.47, steps = 25 06:52:20 [INFO] train episode 10549: reward = -84.12, steps = 21 06:52:22 [INFO] train episode 10550: reward = -102.44, steps = 23 06:52:24 [INFO] train episode 10551: reward = -91.08, steps = 20 06:52:26 [INFO] train episode 10552: reward = -137.23, steps = 17 06:52:28 [INFO] train episode 10553: reward = -93.97, steps = 25 06:52:30 [INFO] train episode 10554: reward = -66.20, steps = 20 06:52:33 [INFO] train episode 10555: reward = -101.05, steps = 38 06:52:35 [INFO] train episode 10556: reward = -82.98, steps = 24 06:52:37 [INFO] train episode 10557: reward = -97.75, steps = 21 06:52:39 [INFO] train episode 10558: reward = -96.17, steps = 29 06:52:41 [INFO] train episode 10559: reward = -71.34, steps = 19 06:52:43 [INFO] train episode 10560: reward = -90.41, steps = 19 06:52:44 [INFO] train episode 10561: reward = -72.78, steps = 19 06:52:46 [INFO] train episode 10562: reward = -114.70, steps = 21 06:52:48 [INFO] train episode 10563: reward = -71.89, steps = 21 06:52:50 [INFO] train episode 10564: reward = -70.58, steps = 19 06:52:51 [INFO] train episode 10565: reward = -78.11, steps = 20 06:52:53 [INFO] train episode 10566: reward = -89.57, steps = 20 06:52:55 [INFO] train episode 10567: reward = -129.20, steps = 19 06:52:57 [INFO] train episode 10568: reward = -66.12, steps = 18 06:52:59 [INFO] train episode 10569: reward = -87.18, steps = 29 06:53:01 [INFO] train episode 10570: reward = -122.24, steps = 20 06:53:02 [INFO] train episode 10571: reward = -64.13, steps = 19 06:53:05 [INFO] train episode 10572: reward = -72.01, steps = 29 06:53:07 [INFO] train episode 10573: reward = -68.08, steps = 19 06:53:08 [INFO] train episode 10574: reward = -73.20, steps = 19 06:53:10 [INFO] train episode 10575: reward = -105.88, steps = 19 06:53:12 [INFO] train episode 10576: reward = -102.54, steps = 20 06:53:14 [INFO] train episode 10577: reward = -66.67, steps = 20 06:53:16 [INFO] train episode 10578: reward = -139.56, steps = 22 06:53:17 [INFO] train episode 10579: reward = -74.90, steps = 19 06:53:19 [INFO] train episode 10580: reward = -77.87, steps = 19 06:53:21 [INFO] train episode 10581: reward = -92.60, steps = 23 06:53:22 [INFO] train episode 10582: reward = -79.51, steps = 18 06:53:24 [INFO] train episode 10583: reward = -85.62, steps = 20 06:53:26 [INFO] train episode 10584: reward = -83.11, steps = 20 06:53:28 [INFO] train episode 10585: reward = -96.07, steps = 26 06:53:30 [INFO] train episode 10586: reward = -78.64, steps = 19 06:53:33 [INFO] train episode 10587: reward = -98.61, steps = 22 06:53:34 [INFO] train episode 10588: reward = -100.43, steps = 20 06:53:36 [INFO] train episode 10589: reward = -86.36, steps = 24 06:53:38 [INFO] train episode 10590: reward = -101.13, steps = 20 06:53:40 [INFO] train episode 10591: reward = -110.00, steps = 20 06:53:42 [INFO] train episode 10592: reward = -88.04, steps = 25 06:53:44 [INFO] train episode 10593: reward = -60.73, steps = 21 06:53:46 [INFO] train episode 10594: reward = -69.69, steps = 21 06:53:48 [INFO] train episode 10595: reward = -91.44, steps = 23 06:53:50 [INFO] train episode 10596: reward = -74.90, steps = 20 06:53:51 [INFO] train episode 10597: reward = -99.40, steps = 20 06:53:54 [INFO] train episode 10598: reward = -88.21, steps = 27 06:53:56 [INFO] train episode 10599: reward = -82.52, steps = 25 06:53:58 [INFO] train episode 10600: reward = -81.11, steps = 26 06:54:00 [INFO] train episode 10601: reward = -72.26, steps = 20 06:54:02 [INFO] train episode 10602: reward = -79.94, steps = 20 06:54:04 [INFO] train episode 10603: reward = -99.56, steps = 21 06:54:05 [INFO] train episode 10604: reward = -79.65, steps = 21 06:54:08 [INFO] train episode 10605: reward = -79.32, steps = 27 06:54:09 [INFO] train episode 10606: reward = -97.06, steps = 18 06:54:11 [INFO] train episode 10607: reward = -87.08, steps = 25 06:54:13 [INFO] train episode 10608: reward = -90.20, steps = 19 06:54:16 [INFO] train episode 10609: reward = -73.85, steps = 27 06:54:19 [INFO] train episode 10610: reward = -66.48, steps = 34 06:54:20 [INFO] train episode 10611: reward = -82.30, steps = 19 06:54:22 [INFO] train episode 10612: reward = -91.74, steps = 20 06:54:23 [INFO] train episode 10613: reward = -111.23, steps = 13 06:54:25 [INFO] train episode 10614: reward = -82.52, steps = 20 06:54:27 [INFO] train episode 10615: reward = -76.83, steps = 22 06:54:29 [INFO] train episode 10616: reward = -79.47, steps = 22 06:54:31 [INFO] train episode 10617: reward = -65.79, steps = 22 06:54:33 [INFO] train episode 10618: reward = -75.84, steps = 20 06:54:34 [INFO] train episode 10619: reward = -83.10, steps = 21 06:54:36 [INFO] train episode 10620: reward = -143.32, steps = 20 06:54:38 [INFO] train episode 10621: reward = -74.42, steps = 20 06:54:40 [INFO] train episode 10622: reward = -68.35, steps = 19 06:54:42 [INFO] train episode 10623: reward = -110.89, steps = 27 06:54:44 [INFO] train episode 10624: reward = -76.03, steps = 20 06:54:46 [INFO] train episode 10625: reward = -86.94, steps = 24 06:54:48 [INFO] train episode 10626: reward = -85.71, steps = 20 06:54:50 [INFO] train episode 10627: reward = -63.94, steps = 26 06:54:52 [INFO] train episode 10628: reward = -111.92, steps = 20 06:54:54 [INFO] train episode 10629: reward = -78.31, steps = 26 06:54:55 [INFO] train episode 10630: reward = -78.33, steps = 19 06:54:57 [INFO] train episode 10631: reward = -102.48, steps = 19 06:54:59 [INFO] train episode 10632: reward = -108.99, steps = 20 06:55:01 [INFO] train episode 10633: reward = -75.11, steps = 23 06:55:03 [INFO] train episode 10634: reward = -94.10, steps = 26 06:55:05 [INFO] train episode 10635: reward = -81.04, steps = 21 06:55:07 [INFO] train episode 10636: reward = -59.72, steps = 25 06:55:09 [INFO] train episode 10637: reward = -115.04, steps = 25 06:55:12 [INFO] train episode 10638: reward = -111.90, steps = 27 06:55:13 [INFO] train episode 10639: reward = -84.67, steps = 19 06:55:15 [INFO] train episode 10640: reward = -122.64, steps = 25 06:55:18 [INFO] train episode 10641: reward = -114.87, steps = 31 06:55:20 [INFO] train episode 10642: reward = -66.04, steps = 19 06:55:22 [INFO] train episode 10643: reward = -183.63, steps = 26 06:55:24 [INFO] train episode 10644: reward = -93.85, steps = 27 06:55:26 [INFO] train episode 10645: reward = -83.94, steps = 19 06:55:28 [INFO] train episode 10646: reward = -88.34, steps = 27 06:55:31 [INFO] train episode 10647: reward = -111.73, steps = 30 06:55:33 [INFO] train episode 10648: reward = -100.08, steps = 22 06:55:35 [INFO] train episode 10649: reward = -72.20, steps = 19 06:55:36 [INFO] train episode 10650: reward = -78.04, steps = 21 06:55:38 [INFO] train episode 10651: reward = -109.70, steps = 22 06:55:40 [INFO] train episode 10652: reward = -94.51, steps = 22 06:55:42 [INFO] train episode 10653: reward = -100.15, steps = 21 06:55:44 [INFO] train episode 10654: reward = -75.43, steps = 19 06:55:45 [INFO] train episode 10655: reward = -79.08, steps = 20 06:55:48 [INFO] train episode 10656: reward = -89.86, steps = 24 06:55:51 [INFO] train episode 10657: reward = -96.93, steps = 34 06:55:52 [INFO] train episode 10658: reward = -143.60, steps = 20 06:55:55 [INFO] train episode 10659: reward = -90.24, steps = 33 06:55:57 [INFO] train episode 10660: reward = -129.03, steps = 23 06:55:59 [INFO] train episode 10661: reward = -94.07, steps = 19 06:56:01 [INFO] train episode 10662: reward = -64.73, steps = 22 06:56:02 [INFO] train episode 10663: reward = -84.55, steps = 21 06:56:05 [INFO] train episode 10664: reward = -56.08, steps = 24 06:56:06 [INFO] train episode 10665: reward = -67.31, steps = 20 06:56:08 [INFO] train episode 10666: reward = -103.24, steps = 18 06:56:10 [INFO] train episode 10667: reward = -97.14, steps = 24 06:56:13 [INFO] train episode 10668: reward = -79.34, steps = 30 06:56:14 [INFO] train episode 10669: reward = -74.94, steps = 19 06:56:16 [INFO] train episode 10670: reward = -83.94, steps = 21 06:56:18 [INFO] train episode 10671: reward = -103.50, steps = 26 06:56:21 [INFO] train episode 10672: reward = -82.48, steps = 22 06:56:23 [INFO] train episode 10673: reward = -107.86, steps = 24 06:56:25 [INFO] train episode 10674: reward = -75.31, steps = 20 06:56:27 [INFO] train episode 10675: reward = -71.61, steps = 25 06:56:29 [INFO] train episode 10676: reward = -126.28, steps = 28 06:56:31 [INFO] train episode 10677: reward = -68.15, steps = 19 06:56:33 [INFO] train episode 10678: reward = -129.88, steps = 22 06:56:36 [INFO] train episode 10679: reward = -115.83, steps = 27 06:56:37 [INFO] train episode 10680: reward = -79.17, steps = 20 06:56:39 [INFO] train episode 10681: reward = -100.90, steps = 24 06:56:41 [INFO] train episode 10682: reward = -71.19, steps = 19 06:56:43 [INFO] train episode 10683: reward = -85.96, steps = 26 06:56:45 [INFO] train episode 10684: reward = -111.50, steps = 24 06:56:47 [INFO] train episode 10685: reward = -80.00, steps = 24 06:56:49 [INFO] train episode 10686: reward = -97.45, steps = 20 06:56:51 [INFO] train episode 10687: reward = -96.77, steps = 22 06:56:54 [INFO] train episode 10688: reward = -115.20, steps = 26 06:56:55 [INFO] train episode 10689: reward = -78.77, steps = 18 06:56:57 [INFO] train episode 10690: reward = -94.32, steps = 21 06:56:59 [INFO] train episode 10691: reward = -79.85, steps = 25 06:57:01 [INFO] train episode 10692: reward = -132.79, steps = 25 06:57:03 [INFO] train episode 10693: reward = -58.34, steps = 21 06:57:05 [INFO] train episode 10694: reward = -87.23, steps = 20 06:57:07 [INFO] train episode 10695: reward = -63.16, steps = 22 06:57:09 [INFO] train episode 10696: reward = -73.53, steps = 28 06:57:11 [INFO] train episode 10697: reward = -94.54, steps = 21 06:57:13 [INFO] train episode 10698: reward = -86.07, steps = 20 06:57:15 [INFO] train episode 10699: reward = -116.30, steps = 30 06:57:17 [INFO] train episode 10700: reward = -63.54, steps = 21 06:57:19 [INFO] train episode 10701: reward = -80.98, steps = 20 06:57:22 [INFO] train episode 10702: reward = -72.21, steps = 29 06:57:24 [INFO] train episode 10703: reward = -98.36, steps = 30 06:57:26 [INFO] train episode 10704: reward = -61.73, steps = 20 06:57:28 [INFO] train episode 10705: reward = -77.00, steps = 19 06:57:30 [INFO] train episode 10706: reward = -101.59, steps = 20 06:57:31 [INFO] train episode 10707: reward = -79.32, steps = 19 06:57:33 [INFO] train episode 10708: reward = -80.98, steps = 23 06:57:35 [INFO] train episode 10709: reward = -103.77, steps = 25 06:57:38 [INFO] train episode 10710: reward = -81.65, steps = 30 06:57:40 [INFO] train episode 10711: reward = -86.74, steps = 20 06:57:42 [INFO] train episode 10712: reward = -86.53, steps = 21 06:57:43 [INFO] train episode 10713: reward = -71.65, steps = 21 06:57:45 [INFO] train episode 10714: reward = -58.44, steps = 20 06:57:48 [INFO] train episode 10715: reward = -78.87, steps = 31 06:57:50 [INFO] train episode 10716: reward = -101.07, steps = 28 06:57:52 [INFO] train episode 10717: reward = -82.89, steps = 28 06:57:55 [INFO] train episode 10718: reward = -104.21, steps = 28 06:57:57 [INFO] train episode 10719: reward = -67.66, steps = 19 06:58:00 [INFO] train episode 10720: reward = -111.77, steps = 39 06:58:02 [INFO] train episode 10721: reward = -76.73, steps = 20 06:58:04 [INFO] train episode 10722: reward = -72.93, steps = 24 06:58:06 [INFO] train episode 10723: reward = -63.29, steps = 21 06:58:07 [INFO] train episode 10724: reward = -97.54, steps = 21 06:58:09 [INFO] train episode 10725: reward = -71.46, steps = 21 06:58:11 [INFO] train episode 10726: reward = -63.55, steps = 20 06:58:13 [INFO] train episode 10727: reward = -112.84, steps = 27 06:58:15 [INFO] train episode 10728: reward = -88.49, steps = 18 06:58:17 [INFO] train episode 10729: reward = -76.85, steps = 23 06:58:19 [INFO] train episode 10730: reward = -110.89, steps = 30 06:58:22 [INFO] train episode 10731: reward = -96.64, steps = 30 06:58:24 [INFO] train episode 10732: reward = -59.35, steps = 20 06:58:26 [INFO] train episode 10733: reward = -76.70, steps = 16 06:58:27 [INFO] train episode 10734: reward = -76.22, steps = 23 06:58:29 [INFO] train episode 10735: reward = -97.68, steps = 19 06:58:31 [INFO] train episode 10736: reward = -85.06, steps = 25 06:58:33 [INFO] train episode 10737: reward = -98.57, steps = 27 06:58:35 [INFO] train episode 10738: reward = -73.39, steps = 19 06:58:37 [INFO] train episode 10739: reward = -131.13, steps = 17 06:58:38 [INFO] train episode 10740: reward = -85.09, steps = 21 06:58:42 [INFO] train episode 10741: reward = -79.92, steps = 35 06:58:44 [INFO] train episode 10742: reward = -83.95, steps = 21 06:58:45 [INFO] train episode 10743: reward = -69.17, steps = 23 06:58:47 [INFO] train episode 10744: reward = -124.85, steps = 21 06:58:49 [INFO] train episode 10745: reward = -97.27, steps = 24 06:58:51 [INFO] train episode 10746: reward = -66.39, steps = 20 06:58:55 [INFO] train episode 10747: reward = -98.37, steps = 45 06:58:58 [INFO] train episode 10748: reward = -72.12, steps = 32 06:59:00 [INFO] train episode 10749: reward = -95.64, steps = 20 06:59:01 [INFO] train episode 10750: reward = -117.78, steps = 20 06:59:03 [INFO] train episode 10751: reward = -116.44, steps = 20 06:59:05 [INFO] train episode 10752: reward = -83.03, steps = 22 06:59:07 [INFO] train episode 10753: reward = -75.02, steps = 20 06:59:09 [INFO] train episode 10754: reward = -85.66, steps = 24 06:59:11 [INFO] train episode 10755: reward = -65.62, steps = 20 06:59:13 [INFO] train episode 10756: reward = -94.25, steps = 21 06:59:16 [INFO] train episode 10757: reward = -71.68, steps = 34 06:59:19 [INFO] train episode 10758: reward = -97.36, steps = 31 06:59:22 [INFO] train episode 10759: reward = -108.39, steps = 34 06:59:24 [INFO] train episode 10760: reward = -78.17, steps = 28 06:59:26 [INFO] train episode 10761: reward = -89.31, steps = 24 06:59:28 [INFO] train episode 10762: reward = -77.20, steps = 21 06:59:30 [INFO] train episode 10763: reward = -84.18, steps = 20 06:59:31 [INFO] train episode 10764: reward = -72.50, steps = 20 06:59:34 [INFO] train episode 10765: reward = -103.13, steps = 30 06:59:36 [INFO] train episode 10766: reward = -85.92, steps = 24 06:59:38 [INFO] train episode 10767: reward = -87.91, steps = 19 06:59:39 [INFO] train episode 10768: reward = -87.87, steps = 18 06:59:41 [INFO] train episode 10769: reward = -85.09, steps = 23 06:59:44 [INFO] train episode 10770: reward = -93.98, steps = 29 06:59:46 [INFO] train episode 10771: reward = -95.38, steps = 20 06:59:47 [INFO] train episode 10772: reward = -115.96, steps = 20 06:59:49 [INFO] train episode 10773: reward = -62.96, steps = 24 06:59:51 [INFO] train episode 10774: reward = -61.13, steps = 22 06:59:53 [INFO] train episode 10775: reward = -133.61, steps = 23 06:59:55 [INFO] train episode 10776: reward = -74.29, steps = 21 06:59:57 [INFO] train episode 10777: reward = -98.83, steps = 25 07:00:00 [INFO] train episode 10778: reward = -76.83, steps = 24 07:00:01 [INFO] train episode 10779: reward = -92.80, steps = 19 07:00:03 [INFO] train episode 10780: reward = -92.92, steps = 26 07:00:05 [INFO] train episode 10781: reward = -65.08, steps = 19 07:00:07 [INFO] train episode 10782: reward = -110.00, steps = 22 07:00:09 [INFO] train episode 10783: reward = -138.14, steps = 27 07:00:11 [INFO] train episode 10784: reward = -87.28, steps = 24 07:00:13 [INFO] train episode 10785: reward = -86.17, steps = 26 07:00:16 [INFO] train episode 10786: reward = -107.02, steps = 24 07:00:18 [INFO] train episode 10787: reward = -130.55, steps = 24 07:00:19 [INFO] train episode 10788: reward = -108.51, steps = 19 07:00:22 [INFO] train episode 10789: reward = -71.98, steps = 33 07:00:24 [INFO] train episode 10790: reward = -78.21, steps = 20 07:00:26 [INFO] train episode 10791: reward = -57.16, steps = 28 07:00:28 [INFO] train episode 10792: reward = -77.80, steps = 23 07:00:31 [INFO] train episode 10793: reward = -71.24, steps = 20 07:00:33 [INFO] train episode 10794: reward = -71.54, steps = 29 07:00:35 [INFO] train episode 10795: reward = -92.69, steps = 19 07:00:36 [INFO] train episode 10796: reward = -71.37, steps = 20 07:00:38 [INFO] train episode 10797: reward = -79.31, steps = 20 07:00:40 [INFO] train episode 10798: reward = -83.06, steps = 20 07:00:42 [INFO] train episode 10799: reward = -140.02, steps = 23 07:00:44 [INFO] train episode 10800: reward = -92.40, steps = 21 07:00:45 [INFO] train episode 10801: reward = -94.23, steps = 20 07:00:48 [INFO] train episode 10802: reward = -94.75, steps = 26 07:00:50 [INFO] train episode 10803: reward = -94.77, steps = 21 07:00:52 [INFO] train episode 10804: reward = -81.46, steps = 20 07:00:54 [INFO] train episode 10805: reward = -113.66, steps = 25 07:00:56 [INFO] train episode 10806: reward = -68.78, steps = 23 07:00:57 [INFO] train episode 10807: reward = -62.43, steps = 19 07:01:00 [INFO] train episode 10808: reward = -113.51, steps = 31 07:01:03 [INFO] train episode 10809: reward = -81.57, steps = 31 07:01:05 [INFO] train episode 10810: reward = -102.22, steps = 21 07:01:06 [INFO] train episode 10811: reward = -107.08, steps = 21 07:01:08 [INFO] train episode 10812: reward = -74.64, steps = 19 07:01:10 [INFO] train episode 10813: reward = -95.52, steps = 22 07:01:12 [INFO] train episode 10814: reward = -67.88, steps = 25 07:01:14 [INFO] train episode 10815: reward = -87.93, steps = 22 07:01:16 [INFO] train episode 10816: reward = -64.51, steps = 20 07:01:19 [INFO] train episode 10817: reward = -94.25, steps = 36 07:01:22 [INFO] train episode 10818: reward = -62.06, steps = 32 07:01:24 [INFO] train episode 10819: reward = -104.61, steps = 20 07:01:25 [INFO] train episode 10820: reward = -87.81, steps = 20 07:01:28 [INFO] train episode 10821: reward = -72.51, steps = 30 07:01:30 [INFO] train episode 10822: reward = -92.00, steps = 22 07:01:32 [INFO] train episode 10823: reward = -77.09, steps = 22 07:01:34 [INFO] train episode 10824: reward = -77.15, steps = 20 07:01:36 [INFO] train episode 10825: reward = -95.06, steps = 24 07:01:38 [INFO] train episode 10826: reward = -99.58, steps = 25 07:01:40 [INFO] train episode 10827: reward = -97.09, steps = 24 07:01:42 [INFO] train episode 10828: reward = -100.46, steps = 26 07:01:44 [INFO] train episode 10829: reward = -72.13, steps = 20 07:01:46 [INFO] train episode 10830: reward = -92.51, steps = 21 07:01:48 [INFO] train episode 10831: reward = -62.34, steps = 24 07:01:50 [INFO] train episode 10832: reward = -128.21, steps = 20 07:01:52 [INFO] train episode 10833: reward = -96.05, steps = 23 07:01:54 [INFO] train episode 10834: reward = -95.35, steps = 24 07:01:56 [INFO] train episode 10835: reward = -103.65, steps = 27 07:01:59 [INFO] train episode 10836: reward = -94.75, steps = 23 07:02:01 [INFO] train episode 10837: reward = -145.56, steps = 25 07:02:02 [INFO] train episode 10838: reward = -101.49, steps = 19 07:02:04 [INFO] train episode 10839: reward = -110.59, steps = 22 07:02:07 [INFO] train episode 10840: reward = -85.29, steps = 28 07:02:10 [INFO] train episode 10841: reward = -91.72, steps = 34 07:02:13 [INFO] train episode 10842: reward = -106.89, steps = 29 07:02:14 [INFO] train episode 10843: reward = -78.64, steps = 21 07:02:16 [INFO] train episode 10844: reward = -100.34, steps = 23 07:02:19 [INFO] train episode 10845: reward = -76.13, steps = 30 07:02:21 [INFO] train episode 10846: reward = -109.34, steps = 19 07:02:23 [INFO] train episode 10847: reward = -78.36, steps = 24 07:02:26 [INFO] train episode 10848: reward = -99.38, steps = 39 07:02:29 [INFO] train episode 10849: reward = -58.60, steps = 34 07:02:31 [INFO] train episode 10850: reward = -72.27, steps = 20 07:02:33 [INFO] train episode 10851: reward = -89.49, steps = 25 07:02:35 [INFO] train episode 10852: reward = -109.45, steps = 23 07:02:38 [INFO] train episode 10853: reward = -116.40, steps = 24 07:02:40 [INFO] train episode 10854: reward = -99.42, steps = 25 07:02:42 [INFO] train episode 10855: reward = -84.78, steps = 21 07:02:44 [INFO] train episode 10856: reward = -68.36, steps = 28 07:02:46 [INFO] train episode 10857: reward = -78.91, steps = 27 07:02:49 [INFO] train episode 10858: reward = -76.75, steps = 28 07:02:51 [INFO] train episode 10859: reward = -90.10, steps = 27 07:02:53 [INFO] train episode 10860: reward = -93.60, steps = 20 07:02:55 [INFO] train episode 10861: reward = -109.31, steps = 22 07:02:56 [INFO] train episode 10862: reward = -89.70, steps = 18 07:02:59 [INFO] train episode 10863: reward = -91.02, steps = 32 07:03:01 [INFO] train episode 10864: reward = -89.30, steps = 25 07:03:03 [INFO] train episode 10865: reward = -56.30, steps = 22 07:03:05 [INFO] train episode 10866: reward = -119.92, steps = 26 07:03:08 [INFO] train episode 10867: reward = -69.54, steps = 25 07:03:10 [INFO] train episode 10868: reward = -65.34, steps = 30 07:03:13 [INFO] train episode 10869: reward = -105.82, steps = 29 07:03:15 [INFO] train episode 10870: reward = -95.67, steps = 25 07:03:17 [INFO] train episode 10871: reward = -92.85, steps = 23 07:03:19 [INFO] train episode 10872: reward = -73.26, steps = 19 07:03:21 [INFO] train episode 10873: reward = -94.87, steps = 28 07:03:24 [INFO] train episode 10874: reward = -73.86, steps = 33 07:03:26 [INFO] train episode 10875: reward = -68.76, steps = 24 07:03:28 [INFO] train episode 10876: reward = -62.27, steps = 22 07:03:30 [INFO] train episode 10877: reward = -67.95, steps = 22 07:03:32 [INFO] train episode 10878: reward = -87.72, steps = 21 07:03:35 [INFO] train episode 10879: reward = -114.66, steps = 34 07:03:36 [INFO] train episode 10880: reward = -78.68, steps = 22 07:03:38 [INFO] train episode 10881: reward = -92.70, steps = 23 07:03:41 [INFO] train episode 10882: reward = -75.37, steps = 23 07:03:43 [INFO] train episode 10883: reward = -119.28, steps = 22 07:03:44 [INFO] train episode 10884: reward = -69.96, steps = 21 07:03:47 [INFO] train episode 10885: reward = -88.90, steps = 28 07:03:49 [INFO] train episode 10886: reward = -64.52, steps = 22 07:03:52 [INFO] train episode 10887: reward = -98.99, steps = 36 07:03:54 [INFO] train episode 10888: reward = -106.37, steps = 29 07:03:57 [INFO] train episode 10889: reward = -108.19, steps = 29 07:03:59 [INFO] train episode 10890: reward = -58.05, steps = 19 07:04:00 [INFO] train episode 10891: reward = -59.71, steps = 20 07:04:02 [INFO] train episode 10892: reward = -66.04, steps = 22 07:04:04 [INFO] train episode 10893: reward = -62.72, steps = 19 07:04:06 [INFO] train episode 10894: reward = -83.98, steps = 21 07:04:08 [INFO] train episode 10895: reward = -97.54, steps = 33 07:04:12 [INFO] train episode 10896: reward = -118.60, steps = 37 07:04:14 [INFO] train episode 10897: reward = -82.01, steps = 26 07:04:17 [INFO] train episode 10898: reward = -106.06, steps = 28 07:04:19 [INFO] train episode 10899: reward = -98.52, steps = 25 07:04:21 [INFO] train episode 10900: reward = -101.20, steps = 33 07:04:24 [INFO] train episode 10901: reward = -87.08, steps = 27 07:04:26 [INFO] train episode 10902: reward = -80.31, steps = 24 07:04:28 [INFO] train episode 10903: reward = -87.50, steps = 22 07:04:30 [INFO] train episode 10904: reward = -88.26, steps = 28 07:04:32 [INFO] train episode 10905: reward = -78.40, steps = 21 07:04:34 [INFO] train episode 10906: reward = -102.35, steps = 25 07:04:39 [INFO] train episode 10907: reward = -126.37, steps = 54 07:04:41 [INFO] train episode 10908: reward = -146.48, steps = 19 07:04:43 [INFO] train episode 10909: reward = -80.03, steps = 21 07:04:45 [INFO] train episode 10910: reward = -89.62, steps = 21 07:04:47 [INFO] train episode 10911: reward = -68.71, steps = 28 07:04:50 [INFO] train episode 10912: reward = -86.11, steps = 22 07:04:51 [INFO] train episode 10913: reward = -76.88, steps = 20 07:04:54 [INFO] train episode 10914: reward = -89.63, steps = 38 07:04:57 [INFO] train episode 10915: reward = -108.86, steps = 28 07:04:59 [INFO] train episode 10916: reward = -85.56, steps = 19 07:05:01 [INFO] train episode 10917: reward = -53.25, steps = 29 07:05:03 [INFO] train episode 10918: reward = -61.53, steps = 22 07:05:06 [INFO] train episode 10919: reward = -84.72, steps = 33 07:05:08 [INFO] train episode 10920: reward = -106.99, steps = 24 07:05:10 [INFO] train episode 10921: reward = -83.61, steps = 26 07:05:12 [INFO] train episode 10922: reward = -109.76, steps = 21 07:05:15 [INFO] train episode 10923: reward = -93.04, steps = 29 07:05:17 [INFO] train episode 10924: reward = -82.27, steps = 22 07:05:19 [INFO] train episode 10925: reward = -79.22, steps = 28 07:05:21 [INFO] train episode 10926: reward = -94.22, steps = 19 07:05:22 [INFO] train episode 10927: reward = -91.65, steps = 21 07:05:24 [INFO] train episode 10928: reward = -101.48, steps = 22 07:05:27 [INFO] train episode 10929: reward = -85.94, steps = 31 07:05:31 [INFO] train episode 10930: reward = -106.21, steps = 43 07:05:33 [INFO] train episode 10931: reward = -113.57, steps = 27 07:05:35 [INFO] train episode 10932: reward = -86.89, steps = 23 07:05:37 [INFO] train episode 10933: reward = -93.74, steps = 23 07:05:40 [INFO] train episode 10934: reward = -85.15, steps = 34 07:05:42 [INFO] train episode 10935: reward = -125.45, steps = 28 07:05:44 [INFO] train episode 10936: reward = -57.51, steps = 21 07:05:46 [INFO] train episode 10937: reward = -75.12, steps = 22 07:05:49 [INFO] train episode 10938: reward = -84.89, steps = 26 07:05:51 [INFO] train episode 10939: reward = -80.45, steps = 26 07:05:53 [INFO] train episode 10940: reward = -76.51, steps = 20 07:05:54 [INFO] train episode 10941: reward = -109.77, steps = 21 07:05:56 [INFO] train episode 10942: reward = -64.89, steps = 25 07:05:59 [INFO] train episode 10943: reward = -134.00, steps = 29 07:06:01 [INFO] train episode 10944: reward = -71.16, steps = 26 07:06:03 [INFO] train episode 10945: reward = -91.48, steps = 20 07:06:07 [INFO] train episode 10946: reward = -122.64, steps = 49 07:06:10 [INFO] train episode 10947: reward = -103.82, steps = 32 07:06:12 [INFO] train episode 10948: reward = -99.55, steps = 26 07:06:14 [INFO] train episode 10949: reward = -80.61, steps = 23 07:06:17 [INFO] train episode 10950: reward = -114.86, steps = 28 07:06:20 [INFO] train episode 10951: reward = -68.89, steps = 33 07:06:22 [INFO] train episode 10952: reward = -78.85, steps = 23 07:06:23 [INFO] train episode 10953: reward = -77.38, steps = 21 07:06:26 [INFO] train episode 10954: reward = -77.09, steps = 30 07:06:28 [INFO] train episode 10955: reward = -79.05, steps = 23 07:06:30 [INFO] train episode 10956: reward = -73.79, steps = 19 07:06:32 [INFO] train episode 10957: reward = -123.06, steps = 24 07:06:35 [INFO] train episode 10958: reward = -89.17, steps = 36 07:06:37 [INFO] train episode 10959: reward = -81.94, steps = 25 07:06:42 [INFO] train episode 10960: reward = -93.92, steps = 61 07:06:44 [INFO] train episode 10961: reward = -138.40, steps = 20 07:06:46 [INFO] train episode 10962: reward = -95.88, steps = 28 07:06:50 [INFO] train episode 10963: reward = -86.33, steps = 35 07:06:52 [INFO] train episode 10964: reward = -86.33, steps = 27 07:06:54 [INFO] train episode 10965: reward = -108.81, steps = 21 07:06:56 [INFO] train episode 10966: reward = -90.22, steps = 26 07:06:59 [INFO] train episode 10967: reward = -64.98, steps = 31 07:07:01 [INFO] train episode 10968: reward = -84.75, steps = 29 07:07:04 [INFO] train episode 10969: reward = -78.36, steps = 27 07:07:06 [INFO] train episode 10970: reward = -65.03, steps = 22 07:07:08 [INFO] train episode 10971: reward = -85.86, steps = 25 07:07:09 [INFO] train episode 10972: reward = -90.71, steps = 20 07:07:12 [INFO] train episode 10973: reward = -92.95, steps = 25 07:07:15 [INFO] train episode 10974: reward = -146.58, steps = 38 07:07:17 [INFO] train episode 10975: reward = -95.48, steps = 22 07:07:19 [INFO] train episode 10976: reward = -96.62, steps = 28 07:07:22 [INFO] train episode 10977: reward = -85.79, steps = 26 07:07:23 [INFO] train episode 10978: reward = -79.18, steps = 22 07:07:26 [INFO] train episode 10979: reward = -78.78, steps = 26 07:07:28 [INFO] train episode 10980: reward = -67.22, steps = 31 07:07:31 [INFO] train episode 10981: reward = -73.55, steps = 26 07:07:33 [INFO] train episode 10982: reward = -97.92, steps = 22 07:07:35 [INFO] train episode 10983: reward = -130.78, steps = 27 07:07:39 [INFO] train episode 10984: reward = -95.34, steps = 41 07:07:42 [INFO] train episode 10985: reward = -69.36, steps = 30 07:07:45 [INFO] train episode 10986: reward = -106.88, steps = 38 07:07:47 [INFO] train episode 10987: reward = -115.36, steps = 27 07:07:50 [INFO] train episode 10988: reward = -86.47, steps = 25 07:07:52 [INFO] train episode 10989: reward = -75.97, steps = 19 07:07:54 [INFO] train episode 10990: reward = -94.32, steps = 31 07:07:56 [INFO] train episode 10991: reward = -104.02, steps = 21 07:07:58 [INFO] train episode 10992: reward = -86.33, steps = 21 07:08:00 [INFO] train episode 10993: reward = -113.64, steps = 30 07:08:03 [INFO] train episode 10994: reward = -85.35, steps = 28 07:08:04 [INFO] train episode 10995: reward = -76.36, steps = 21 07:08:07 [INFO] train episode 10996: reward = -85.70, steps = 24 07:08:09 [INFO] train episode 10997: reward = -108.20, steps = 21 07:08:11 [INFO] train episode 10998: reward = -97.73, steps = 22 07:08:12 [INFO] train episode 10999: reward = -88.51, steps = 21 07:08:14 [INFO] train episode 11000: reward = -113.65, steps = 19 07:08:16 [INFO] train episode 11001: reward = -85.18, steps = 22 07:08:18 [INFO] train episode 11002: reward = -77.03, steps = 23 07:08:20 [INFO] train episode 11003: reward = -85.83, steps = 29 07:08:23 [INFO] train episode 11004: reward = -73.26, steps = 26 07:08:26 [INFO] train episode 11005: reward = -98.65, steps = 34 07:08:28 [INFO] train episode 11006: reward = -65.87, steps = 27 07:08:30 [INFO] train episode 11007: reward = -67.14, steps = 23 07:08:32 [INFO] train episode 11008: reward = -92.88, steps = 25 07:08:34 [INFO] train episode 11009: reward = -81.65, steps = 27 07:08:37 [INFO] train episode 11010: reward = -74.06, steps = 30 07:08:40 [INFO] train episode 11011: reward = -70.66, steps = 29 07:08:42 [INFO] train episode 11012: reward = -69.70, steps = 21 07:08:45 [INFO] train episode 11013: reward = -86.53, steps = 38 07:08:47 [INFO] train episode 11014: reward = -84.02, steps = 29 07:08:50 [INFO] train episode 11015: reward = -73.97, steps = 27 07:08:52 [INFO] train episode 11016: reward = -81.64, steps = 29 07:08:54 [INFO] train episode 11017: reward = -99.46, steps = 21 07:08:56 [INFO] train episode 11018: reward = -80.05, steps = 22 07:08:58 [INFO] train episode 11019: reward = -69.19, steps = 27 07:09:00 [INFO] train episode 11020: reward = -68.82, steps = 21 07:09:03 [INFO] train episode 11021: reward = -88.31, steps = 28 07:09:06 [INFO] train episode 11022: reward = -88.79, steps = 34 07:09:08 [INFO] train episode 11023: reward = -92.58, steps = 23 07:09:10 [INFO] train episode 11024: reward = -75.74, steps = 30 07:09:13 [INFO] train episode 11025: reward = -67.27, steps = 25 07:09:15 [INFO] train episode 11026: reward = -111.47, steps = 25 07:09:16 [INFO] train episode 11027: reward = -74.97, steps = 19 07:09:18 [INFO] train episode 11028: reward = -81.98, steps = 25 07:09:20 [INFO] train episode 11029: reward = -65.51, steps = 20 07:09:22 [INFO] train episode 11030: reward = -81.79, steps = 21 07:09:24 [INFO] train episode 11031: reward = -78.73, steps = 20 07:09:25 [INFO] train episode 11032: reward = -103.86, steps = 16 07:09:27 [INFO] train episode 11033: reward = -77.20, steps = 21 07:09:29 [INFO] train episode 11034: reward = -96.47, steps = 21 07:09:31 [INFO] train episode 11035: reward = -103.93, steps = 19 07:09:33 [INFO] train episode 11036: reward = -97.22, steps = 23 07:09:35 [INFO] train episode 11037: reward = -81.06, steps = 27 07:09:37 [INFO] train episode 11038: reward = -100.44, steps = 26 07:09:40 [INFO] train episode 11039: reward = -95.00, steps = 35 07:09:42 [INFO] train episode 11040: reward = -120.51, steps = 21 07:09:49 [INFO] train episode 11041: reward = -153.67, steps = 86 07:09:51 [INFO] train episode 11042: reward = -87.30, steps = 24 07:09:53 [INFO] train episode 11043: reward = -125.21, steps = 24 07:09:55 [INFO] train episode 11044: reward = -100.85, steps = 19 07:09:57 [INFO] train episode 11045: reward = -104.05, steps = 20 07:09:59 [INFO] train episode 11046: reward = -135.12, steps = 27 07:10:02 [INFO] train episode 11047: reward = -100.18, steps = 32 07:10:04 [INFO] train episode 11048: reward = -99.39, steps = 21 07:10:06 [INFO] train episode 11049: reward = -143.16, steps = 25 07:10:09 [INFO] train episode 11050: reward = -80.22, steps = 30 07:10:10 [INFO] train episode 11051: reward = -92.60, steps = 20 07:10:13 [INFO] train episode 11052: reward = -82.72, steps = 28 07:10:16 [INFO] train episode 11053: reward = -79.59, steps = 33 07:10:18 [INFO] train episode 11054: reward = -69.06, steps = 27 07:10:20 [INFO] train episode 11055: reward = -114.96, steps = 23 07:10:22 [INFO] train episode 11056: reward = -69.89, steps = 24 07:10:24 [INFO] train episode 11057: reward = -88.90, steps = 24 07:10:27 [INFO] train episode 11058: reward = -78.62, steps = 27 07:10:30 [INFO] train episode 11059: reward = -84.65, steps = 27 07:10:32 [INFO] train episode 11060: reward = -69.66, steps = 21 07:10:34 [INFO] train episode 11061: reward = -91.63, steps = 27 07:10:36 [INFO] train episode 11062: reward = -81.66, steps = 23 07:10:39 [INFO] train episode 11063: reward = -72.29, steps = 36 07:10:42 [INFO] train episode 11064: reward = -90.64, steps = 37 07:10:46 [INFO] train episode 11065: reward = -102.06, steps = 38 07:10:48 [INFO] train episode 11066: reward = -71.54, steps = 26 07:10:50 [INFO] train episode 11067: reward = -114.04, steps = 23 07:10:52 [INFO] train episode 11068: reward = -83.41, steps = 27 07:10:54 [INFO] train episode 11069: reward = -78.81, steps = 21 07:10:56 [INFO] train episode 11070: reward = -105.71, steps = 28 07:10:58 [INFO] train episode 11071: reward = -80.63, steps = 20 07:11:00 [INFO] train episode 11072: reward = -95.01, steps = 24 07:11:02 [INFO] train episode 11073: reward = -67.65, steps = 22 07:11:04 [INFO] train episode 11074: reward = -66.50, steps = 23 07:11:06 [INFO] train episode 11075: reward = -137.67, steps = 21 07:11:09 [INFO] train episode 11076: reward = -80.99, steps = 29 07:11:11 [INFO] train episode 11077: reward = -79.46, steps = 27 07:11:13 [INFO] train episode 11078: reward = -78.10, steps = 26 07:11:15 [INFO] train episode 11079: reward = -78.08, steps = 24 07:11:18 [INFO] train episode 11080: reward = -99.89, steps = 24 07:11:20 [INFO] train episode 11081: reward = -98.96, steps = 26 07:11:22 [INFO] train episode 11082: reward = -118.29, steps = 26 07:11:24 [INFO] train episode 11083: reward = -85.36, steps = 25 07:11:27 [INFO] train episode 11084: reward = -95.73, steps = 33 07:11:29 [INFO] train episode 11085: reward = -105.15, steps = 27 07:11:32 [INFO] train episode 11086: reward = -96.73, steps = 27 07:11:34 [INFO] train episode 11087: reward = -83.54, steps = 29 07:11:37 [INFO] train episode 11088: reward = -69.95, steps = 30 07:11:39 [INFO] train episode 11089: reward = -71.54, steps = 30 07:11:42 [INFO] train episode 11090: reward = -78.34, steps = 24 07:11:44 [INFO] train episode 11091: reward = -86.59, steps = 34 07:11:47 [INFO] train episode 11092: reward = -87.63, steps = 26 07:11:49 [INFO] train episode 11093: reward = -106.76, steps = 19 07:11:52 [INFO] train episode 11094: reward = -75.49, steps = 38 07:11:54 [INFO] train episode 11095: reward = -74.59, steps = 31 07:11:56 [INFO] train episode 11096: reward = -61.96, steps = 24 07:11:59 [INFO] train episode 11097: reward = -89.50, steps = 26 07:12:03 [INFO] train episode 11098: reward = -90.17, steps = 49 07:12:06 [INFO] train episode 11099: reward = -71.70, steps = 31 07:12:08 [INFO] train episode 11100: reward = -91.06, steps = 24 07:12:10 [INFO] train episode 11101: reward = -123.99, steps = 24 07:12:11 [INFO] train episode 11102: reward = -97.68, steps = 21 07:12:14 [INFO] train episode 11103: reward = -71.23, steps = 24 07:12:15 [INFO] train episode 11104: reward = -98.24, steps = 20 07:12:18 [INFO] train episode 11105: reward = -76.09, steps = 30 07:12:20 [INFO] train episode 11106: reward = -120.66, steps = 24 07:12:23 [INFO] train episode 11107: reward = -160.90, steps = 28 07:12:25 [INFO] train episode 11108: reward = -74.19, steps = 29 07:12:27 [INFO] train episode 11109: reward = -75.56, steps = 19 07:12:29 [INFO] train episode 11110: reward = -76.15, steps = 20 07:12:30 [INFO] train episode 11111: reward = -83.48, steps = 22 07:12:32 [INFO] train episode 11112: reward = -69.85, steps = 21 07:12:34 [INFO] train episode 11113: reward = -69.43, steps = 26 07:12:37 [INFO] train episode 11114: reward = -72.60, steps = 25 07:12:39 [INFO] train episode 11115: reward = -125.94, steps = 19 07:12:41 [INFO] train episode 11116: reward = -89.11, steps = 22 07:12:43 [INFO] train episode 11117: reward = -96.34, steps = 24 07:12:45 [INFO] train episode 11118: reward = -78.80, steps = 23 07:12:47 [INFO] train episode 11119: reward = -80.11, steps = 26 07:12:49 [INFO] train episode 11120: reward = -70.80, steps = 23 07:12:51 [INFO] train episode 11121: reward = -88.88, steps = 23 07:12:53 [INFO] train episode 11122: reward = -77.64, steps = 22 07:12:57 [INFO] train episode 11123: reward = -74.60, steps = 40 07:12:58 [INFO] train episode 11124: reward = -68.48, steps = 21 07:13:00 [INFO] train episode 11125: reward = -63.27, steps = 25 07:13:03 [INFO] train episode 11126: reward = -96.34, steps = 35 07:13:06 [INFO] train episode 11127: reward = -79.13, steps = 35 07:13:09 [INFO] train episode 11128: reward = -97.89, steps = 26 07:13:11 [INFO] train episode 11129: reward = -101.80, steps = 24 07:13:13 [INFO] train episode 11130: reward = -78.16, steps = 20 07:13:15 [INFO] train episode 11131: reward = -83.81, steps = 28 07:13:17 [INFO] train episode 11132: reward = -89.57, steps = 28 07:13:20 [INFO] train episode 11133: reward = -82.36, steps = 24 07:13:22 [INFO] train episode 11134: reward = -68.88, steps = 21 07:13:24 [INFO] train episode 11135: reward = -105.28, steps = 22 07:13:26 [INFO] train episode 11136: reward = -95.37, steps = 23 07:13:29 [INFO] train episode 11137: reward = -92.03, steps = 32 07:13:32 [INFO] train episode 11138: reward = -119.32, steps = 41 07:13:34 [INFO] train episode 11139: reward = -94.76, steps = 21 07:13:36 [INFO] train episode 11140: reward = -85.56, steps = 23 07:13:38 [INFO] train episode 11141: reward = -159.13, steps = 25 07:13:40 [INFO] train episode 11142: reward = -76.78, steps = 22 07:13:43 [INFO] train episode 11143: reward = -75.48, steps = 28 07:13:45 [INFO] train episode 11144: reward = -53.41, steps = 25 07:13:47 [INFO] train episode 11145: reward = -112.54, steps = 27 07:13:49 [INFO] train episode 11146: reward = -84.52, steps = 27 07:13:51 [INFO] train episode 11147: reward = -110.94, steps = 22 07:13:53 [INFO] train episode 11148: reward = -97.87, steps = 22 07:13:57 [INFO] train episode 11149: reward = -80.31, steps = 44 07:14:00 [INFO] train episode 11150: reward = -113.57, steps = 36 07:14:02 [INFO] train episode 11151: reward = -74.28, steps = 23 07:14:04 [INFO] train episode 11152: reward = -103.31, steps = 23 07:14:06 [INFO] train episode 11153: reward = -134.56, steps = 26 07:14:09 [INFO] train episode 11154: reward = -64.33, steps = 28 07:14:11 [INFO] train episode 11155: reward = -78.96, steps = 26 07:14:14 [INFO] train episode 11156: reward = -77.62, steps = 36 07:14:16 [INFO] train episode 11157: reward = -96.05, steps = 22 07:14:18 [INFO] train episode 11158: reward = -68.41, steps = 21 07:14:21 [INFO] train episode 11159: reward = -78.14, steps = 31 07:14:23 [INFO] train episode 11160: reward = -96.52, steps = 25 07:14:27 [INFO] train episode 11161: reward = -104.63, steps = 47 07:14:29 [INFO] train episode 11162: reward = -130.48, steps = 23 07:14:31 [INFO] train episode 11163: reward = -96.46, steps = 21 07:14:33 [INFO] train episode 11164: reward = -89.76, steps = 22 07:14:36 [INFO] train episode 11165: reward = -91.77, steps = 39 07:14:38 [INFO] train episode 11166: reward = -61.63, steps = 23 07:14:40 [INFO] train episode 11167: reward = -84.41, steps = 20 07:14:42 [INFO] train episode 11168: reward = -104.07, steps = 27 07:14:44 [INFO] train episode 11169: reward = -95.98, steps = 24 07:14:46 [INFO] train episode 11170: reward = -94.88, steps = 24 07:14:49 [INFO] train episode 11171: reward = -82.73, steps = 31 07:14:51 [INFO] train episode 11172: reward = -135.83, steps = 23 07:14:54 [INFO] train episode 11173: reward = -97.48, steps = 38 07:14:56 [INFO] train episode 11174: reward = -83.21, steps = 25 07:14:59 [INFO] train episode 11175: reward = -79.21, steps = 24 07:15:00 [INFO] train episode 11176: reward = -70.52, steps = 21 07:15:02 [INFO] train episode 11177: reward = -113.86, steps = 22 07:15:05 [INFO] train episode 11178: reward = -86.18, steps = 27 07:15:06 [INFO] train episode 11179: reward = -84.36, steps = 19 07:15:08 [INFO] train episode 11180: reward = -77.76, steps = 21 07:15:10 [INFO] train episode 11181: reward = -78.68, steps = 27 07:15:14 [INFO] train episode 11182: reward = -73.75, steps = 36 07:15:16 [INFO] train episode 11183: reward = -70.18, steps = 29 07:15:18 [INFO] train episode 11184: reward = -70.10, steps = 24 07:15:20 [INFO] train episode 11185: reward = -81.98, steps = 23 07:15:23 [INFO] train episode 11186: reward = -115.51, steps = 36 07:15:26 [INFO] train episode 11187: reward = -80.50, steps = 36 07:15:29 [INFO] train episode 11188: reward = -71.55, steps = 26 07:15:31 [INFO] train episode 11189: reward = -91.57, steps = 20 07:15:33 [INFO] train episode 11190: reward = -107.01, steps = 25 07:15:35 [INFO] train episode 11191: reward = -120.43, steps = 27 07:15:38 [INFO] train episode 11192: reward = -149.24, steps = 29 07:15:40 [INFO] train episode 11193: reward = -87.85, steps = 23 07:15:41 [INFO] train episode 11194: reward = -76.94, steps = 20 07:15:44 [INFO] train episode 11195: reward = -90.23, steps = 26 07:15:46 [INFO] train episode 11196: reward = -79.39, steps = 23 07:15:48 [INFO] train episode 11197: reward = -105.91, steps = 20 07:15:50 [INFO] train episode 11198: reward = -79.23, steps = 29 07:15:52 [INFO] train episode 11199: reward = -79.55, steps = 21 07:15:54 [INFO] train episode 11200: reward = -96.60, steps = 29 07:15:56 [INFO] train episode 11201: reward = -67.76, steps = 20 07:15:58 [INFO] train episode 11202: reward = -75.66, steps = 18 07:16:00 [INFO] train episode 11203: reward = -83.75, steps = 22 07:16:02 [INFO] train episode 11204: reward = -80.99, steps = 26 07:16:04 [INFO] train episode 11205: reward = -83.89, steps = 21 07:16:06 [INFO] train episode 11206: reward = -99.82, steps = 22 07:16:09 [INFO] train episode 11207: reward = -81.41, steps = 27 07:16:11 [INFO] train episode 11208: reward = -74.48, steps = 31 07:16:14 [INFO] train episode 11209: reward = -78.36, steps = 24 07:16:15 [INFO] train episode 11210: reward = -114.25, steps = 20 07:16:18 [INFO] train episode 11211: reward = -99.45, steps = 26 07:16:20 [INFO] train episode 11212: reward = -87.82, steps = 29 07:16:23 [INFO] train episode 11213: reward = -84.05, steps = 33 07:16:25 [INFO] train episode 11214: reward = -85.95, steps = 22 07:16:27 [INFO] train episode 11215: reward = -78.36, steps = 29 07:16:29 [INFO] train episode 11216: reward = -138.19, steps = 22 07:16:32 [INFO] train episode 11217: reward = -84.94, steps = 29 07:16:34 [INFO] train episode 11218: reward = -71.64, steps = 21 07:16:36 [INFO] train episode 11219: reward = -102.12, steps = 24 07:16:38 [INFO] train episode 11220: reward = -97.21, steps = 19 07:16:40 [INFO] train episode 11221: reward = -64.46, steps = 32 07:16:42 [INFO] train episode 11222: reward = -83.14, steps = 21 07:16:44 [INFO] train episode 11223: reward = -67.25, steps = 25 07:16:46 [INFO] train episode 11224: reward = -84.91, steps = 20 07:16:50 [INFO] train episode 11225: reward = -78.60, steps = 42 07:16:52 [INFO] train episode 11226: reward = -61.05, steps = 20 07:16:54 [INFO] train episode 11227: reward = -99.39, steps = 26 07:16:55 [INFO] train episode 11228: reward = -126.23, steps = 21 07:16:58 [INFO] train episode 11229: reward = -71.31, steps = 28 07:17:02 [INFO] train episode 11230: reward = -74.35, steps = 48 07:17:05 [INFO] train episode 11231: reward = -88.62, steps = 28 07:17:07 [INFO] train episode 11232: reward = -88.56, steps = 28 07:17:09 [INFO] train episode 11233: reward = -80.87, steps = 20 07:17:11 [INFO] train episode 11234: reward = -73.08, steps = 30 07:17:14 [INFO] train episode 11235: reward = -117.94, steps = 33 07:17:17 [INFO] train episode 11236: reward = -115.63, steps = 30 07:17:19 [INFO] train episode 11237: reward = -53.73, steps = 29 07:17:22 [INFO] train episode 11238: reward = -124.32, steps = 34 07:17:24 [INFO] train episode 11239: reward = -89.92, steps = 25 07:17:26 [INFO] train episode 11240: reward = -128.80, steps = 24 07:17:31 [INFO] train episode 11241: reward = -148.00, steps = 55 07:17:33 [INFO] train episode 11242: reward = -90.56, steps = 23 07:17:35 [INFO] train episode 11243: reward = -85.18, steps = 23 07:17:37 [INFO] train episode 11244: reward = -80.39, steps = 22 07:17:39 [INFO] train episode 11245: reward = -90.95, steps = 27 07:17:42 [INFO] train episode 11246: reward = -96.80, steps = 32 07:17:45 [INFO] train episode 11247: reward = -114.28, steps = 33 07:17:48 [INFO] train episode 11248: reward = -88.53, steps = 43 07:17:51 [INFO] train episode 11249: reward = -77.55, steps = 27 07:17:53 [INFO] train episode 11250: reward = -98.63, steps = 19 07:17:55 [INFO] train episode 11251: reward = -126.65, steps = 30 07:17:58 [INFO] train episode 11252: reward = -72.91, steps = 38 07:18:00 [INFO] train episode 11253: reward = -71.74, steps = 20 07:18:02 [INFO] train episode 11254: reward = -121.10, steps = 26 07:18:05 [INFO] train episode 11255: reward = -82.29, steps = 28 07:18:08 [INFO] train episode 11256: reward = -89.12, steps = 29 07:18:10 [INFO] train episode 11257: reward = -75.38, steps = 22 07:18:11 [INFO] train episode 11258: reward = -75.86, steps = 23 07:18:14 [INFO] train episode 11259: reward = -66.98, steps = 32 07:18:16 [INFO] train episode 11260: reward = -110.36, steps = 25 07:18:19 [INFO] train episode 11261: reward = -75.61, steps = 30 07:18:20 [INFO] train episode 11262: reward = -97.76, steps = 17 07:18:23 [INFO] train episode 11263: reward = -69.15, steps = 29 07:18:25 [INFO] train episode 11264: reward = -87.41, steps = 26 07:18:29 [INFO] train episode 11265: reward = -78.73, steps = 46 07:18:31 [INFO] train episode 11266: reward = -80.62, steps = 20 07:18:33 [INFO] train episode 11267: reward = -70.88, steps = 28 07:18:37 [INFO] train episode 11268: reward = -104.53, steps = 38 07:18:39 [INFO] train episode 11269: reward = -80.69, steps = 26 07:18:41 [INFO] train episode 11270: reward = -123.14, steps = 23 07:18:43 [INFO] train episode 11271: reward = -116.41, steps = 27 07:18:45 [INFO] train episode 11272: reward = -99.23, steps = 23 07:18:48 [INFO] train episode 11273: reward = -87.98, steps = 26 07:18:50 [INFO] train episode 11274: reward = -108.03, steps = 27 07:18:52 [INFO] train episode 11275: reward = -175.47, steps = 27 07:18:55 [INFO] train episode 11276: reward = -80.66, steps = 23 07:18:58 [INFO] train episode 11277: reward = -79.57, steps = 33 07:19:00 [INFO] train episode 11278: reward = -78.43, steps = 23 07:19:03 [INFO] train episode 11279: reward = -98.28, steps = 27 07:19:05 [INFO] train episode 11280: reward = -82.52, steps = 29 07:19:07 [INFO] train episode 11281: reward = -109.72, steps = 22 07:19:09 [INFO] train episode 11282: reward = -58.78, steps = 20 07:19:12 [INFO] train episode 11283: reward = -101.76, steps = 35 07:19:14 [INFO] train episode 11284: reward = -74.28, steps = 27 07:19:16 [INFO] train episode 11285: reward = -85.55, steps = 24 07:19:18 [INFO] train episode 11286: reward = -81.37, steps = 23 07:19:20 [INFO] train episode 11287: reward = -88.97, steps = 21 07:19:22 [INFO] train episode 11288: reward = -88.69, steps = 30 07:19:25 [INFO] train episode 11289: reward = -88.11, steps = 27 07:19:28 [INFO] train episode 11290: reward = -112.34, steps = 33 07:19:30 [INFO] train episode 11291: reward = -83.09, steps = 23 07:19:33 [INFO] train episode 11292: reward = -89.83, steps = 34 07:19:36 [INFO] train episode 11293: reward = -115.55, steps = 33 07:19:38 [INFO] train episode 11294: reward = -149.00, steps = 24 07:19:39 [INFO] train episode 11295: reward = -80.34, steps = 19 07:19:42 [INFO] train episode 11296: reward = -91.92, steps = 30 07:19:44 [INFO] train episode 11297: reward = -78.77, steps = 21 07:19:46 [INFO] train episode 11298: reward = -112.24, steps = 21 07:19:48 [INFO] train episode 11299: reward = -103.26, steps = 29 07:19:51 [INFO] train episode 11300: reward = -80.27, steps = 30 07:19:53 [INFO] train episode 11301: reward = -66.32, steps = 30 07:19:56 [INFO] train episode 11302: reward = -89.17, steps = 25 07:19:57 [INFO] train episode 11303: reward = -106.60, steps = 22 07:20:00 [INFO] train episode 11304: reward = -118.02, steps = 20 07:20:01 [INFO] train episode 11305: reward = -78.92, steps = 21 07:20:03 [INFO] train episode 11306: reward = -139.03, steps = 24 07:20:05 [INFO] train episode 11307: reward = -73.85, steps = 22 07:20:08 [INFO] train episode 11308: reward = -73.85, steps = 28 07:20:10 [INFO] train episode 11309: reward = -86.53, steps = 26 07:20:12 [INFO] train episode 11310: reward = -97.31, steps = 24 07:20:14 [INFO] train episode 11311: reward = -81.46, steps = 23 07:20:17 [INFO] train episode 11312: reward = -50.92, steps = 35 07:20:19 [INFO] train episode 11313: reward = -58.72, steps = 24 07:20:21 [INFO] train episode 11314: reward = -105.41, steps = 21 07:20:24 [INFO] train episode 11315: reward = -103.12, steps = 31 07:20:26 [INFO] train episode 11316: reward = -121.29, steps = 32 07:20:28 [INFO] train episode 11317: reward = -79.32, steps = 20 07:20:30 [INFO] train episode 11318: reward = -115.62, steps = 19 07:20:33 [INFO] train episode 11319: reward = -93.08, steps = 30 07:20:36 [INFO] train episode 11320: reward = -90.26, steps = 29 07:20:38 [INFO] train episode 11321: reward = -120.69, steps = 18 07:20:41 [INFO] train episode 11322: reward = -108.24, steps = 33 07:20:43 [INFO] train episode 11323: reward = -106.04, steps = 27 07:20:45 [INFO] train episode 11324: reward = -73.97, steps = 20 07:20:48 [INFO] train episode 11325: reward = -133.33, steps = 31 07:20:50 [INFO] train episode 11326: reward = -98.72, steps = 17 07:20:54 [INFO] train episode 11327: reward = -71.71, steps = 45 07:20:57 [INFO] train episode 11328: reward = -169.44, steps = 32 07:20:59 [INFO] train episode 11329: reward = -85.77, steps = 25 07:21:01 [INFO] train episode 11330: reward = -89.76, steps = 25 07:21:05 [INFO] train episode 11331: reward = -89.58, steps = 32 07:21:06 [INFO] train episode 11332: reward = -75.99, steps = 17 07:21:08 [INFO] train episode 11333: reward = -78.57, steps = 22 07:21:11 [INFO] train episode 11334: reward = -101.85, steps = 31 07:21:13 [INFO] train episode 11335: reward = -77.06, steps = 28 07:21:15 [INFO] train episode 11336: reward = -106.13, steps = 19 07:21:17 [INFO] train episode 11337: reward = -80.44, steps = 27 07:21:21 [INFO] train episode 11338: reward = -73.94, steps = 42 07:21:23 [INFO] train episode 11339: reward = -80.34, steps = 31 07:21:25 [INFO] train episode 11340: reward = -78.74, steps = 20 07:21:27 [INFO] train episode 11341: reward = -89.69, steps = 25 07:21:29 [INFO] train episode 11342: reward = -56.96, steps = 20 07:21:31 [INFO] train episode 11343: reward = -73.73, steps = 26 07:21:34 [INFO] train episode 11344: reward = -67.63, steps = 36 07:21:36 [INFO] train episode 11345: reward = -67.55, steps = 21 07:21:38 [INFO] train episode 11346: reward = -65.65, steps = 21 07:21:40 [INFO] train episode 11347: reward = -109.37, steps = 22 07:21:42 [INFO] train episode 11348: reward = -87.16, steps = 27 07:21:45 [INFO] train episode 11349: reward = -95.61, steps = 29 07:21:47 [INFO] train episode 11350: reward = -73.76, steps = 31 07:21:52 [INFO] train episode 11351: reward = -125.54, steps = 39 07:21:54 [INFO] train episode 11352: reward = -96.48, steps = 30 07:21:56 [INFO] train episode 11353: reward = -93.56, steps = 21 07:21:58 [INFO] train episode 11354: reward = -106.31, steps = 22 07:22:00 [INFO] train episode 11355: reward = -85.31, steps = 20 07:22:01 [INFO] train episode 11356: reward = -103.05, steps = 21 07:22:03 [INFO] train episode 11357: reward = -77.62, steps = 24 07:22:06 [INFO] train episode 11358: reward = -72.87, steps = 27 07:22:08 [INFO] train episode 11359: reward = -61.86, steps = 28 07:22:12 [INFO] train episode 11360: reward = -99.09, steps = 48 07:22:14 [INFO] train episode 11361: reward = -87.72, steps = 26 07:22:16 [INFO] train episode 11362: reward = -110.55, steps = 23 07:22:18 [INFO] train episode 11363: reward = -89.82, steps = 19 07:22:20 [INFO] train episode 11364: reward = -73.35, steps = 28 07:22:23 [INFO] train episode 11365: reward = -114.98, steps = 26 07:22:25 [INFO] train episode 11366: reward = -115.15, steps = 18 07:22:27 [INFO] train episode 11367: reward = -84.43, steps = 31 07:22:29 [INFO] train episode 11368: reward = -74.91, steps = 25 07:22:32 [INFO] train episode 11369: reward = -101.42, steps = 28 07:22:34 [INFO] train episode 11370: reward = -74.43, steps = 22 07:22:36 [INFO] train episode 11371: reward = -103.55, steps = 25 07:22:38 [INFO] train episode 11372: reward = -85.76, steps = 20 07:22:40 [INFO] train episode 11373: reward = -140.60, steps = 29 07:22:43 [INFO] train episode 11374: reward = -60.82, steps = 29 07:22:46 [INFO] train episode 11375: reward = -92.48, steps = 32 07:22:50 [INFO] train episode 11376: reward = -114.63, steps = 55 07:22:52 [INFO] train episode 11377: reward = -72.87, steps = 26 07:22:55 [INFO] train episode 11378: reward = -77.59, steps = 22 07:22:56 [INFO] train episode 11379: reward = -81.15, steps = 20 07:22:58 [INFO] train episode 11380: reward = -76.57, steps = 23 07:23:02 [INFO] train episode 11381: reward = -156.22, steps = 42 07:23:04 [INFO] train episode 11382: reward = -93.88, steps = 30 07:23:06 [INFO] train episode 11383: reward = -76.09, steps = 20 07:23:08 [INFO] train episode 11384: reward = -70.12, steps = 26 07:23:11 [INFO] train episode 11385: reward = -95.19, steps = 28 07:23:13 [INFO] train episode 11386: reward = -105.39, steps = 18 07:23:15 [INFO] train episode 11387: reward = -75.63, steps = 24 07:23:18 [INFO] train episode 11388: reward = -88.37, steps = 39 07:23:20 [INFO] train episode 11389: reward = -65.03, steps = 29 07:23:22 [INFO] train episode 11390: reward = -77.16, steps = 20 07:23:24 [INFO] train episode 11391: reward = -84.45, steps = 23 07:23:28 [INFO] train episode 11392: reward = -97.92, steps = 41 07:23:30 [INFO] train episode 11393: reward = -101.59, steps = 22 07:23:31 [INFO] train episode 11394: reward = -76.15, steps = 19 07:23:33 [INFO] train episode 11395: reward = -92.45, steps = 19 07:23:35 [INFO] train episode 11396: reward = -85.52, steps = 24 07:23:37 [INFO] train episode 11397: reward = -59.12, steps = 21 07:23:40 [INFO] train episode 11398: reward = -89.18, steps = 35 07:23:43 [INFO] train episode 11399: reward = -102.01, steps = 40 07:23:46 [INFO] train episode 11400: reward = -73.52, steps = 24 07:23:48 [INFO] train episode 11401: reward = -136.28, steps = 25 07:23:50 [INFO] train episode 11402: reward = -80.81, steps = 25 07:23:52 [INFO] train episode 11403: reward = -104.96, steps = 30 07:23:55 [INFO] train episode 11404: reward = -68.01, steps = 27 07:23:57 [INFO] train episode 11405: reward = -89.39, steps = 23 07:23:59 [INFO] train episode 11406: reward = -141.73, steps = 27 07:24:01 [INFO] train episode 11407: reward = -77.78, steps = 23 07:24:03 [INFO] train episode 11408: reward = -84.26, steps = 25 07:24:05 [INFO] train episode 11409: reward = -98.27, steps = 24 07:24:07 [INFO] train episode 11410: reward = -77.18, steps = 23 07:24:10 [INFO] train episode 11411: reward = -123.47, steps = 30 07:24:12 [INFO] train episode 11412: reward = -71.51, steps = 20 07:24:14 [INFO] train episode 11413: reward = -96.03, steps = 25 07:24:16 [INFO] train episode 11414: reward = -83.71, steps = 25 07:24:19 [INFO] train episode 11415: reward = -85.26, steps = 26 07:24:20 [INFO] train episode 11416: reward = -66.35, steps = 19 07:24:22 [INFO] train episode 11417: reward = -87.20, steps = 24 07:24:25 [INFO] train episode 11418: reward = -78.66, steps = 27 07:24:27 [INFO] train episode 11419: reward = -70.30, steps = 29 07:24:29 [INFO] train episode 11420: reward = -116.22, steps = 23 07:24:32 [INFO] train episode 11421: reward = -109.16, steps = 30 07:24:34 [INFO] train episode 11422: reward = -82.63, steps = 29 07:24:36 [INFO] train episode 11423: reward = -77.93, steps = 16 07:24:38 [INFO] train episode 11424: reward = -110.43, steps = 30 07:24:41 [INFO] train episode 11425: reward = -72.88, steps = 21 07:24:43 [INFO] train episode 11426: reward = -107.09, steps = 19 07:24:45 [INFO] train episode 11427: reward = -80.64, steps = 21 07:24:47 [INFO] train episode 11428: reward = -91.71, steps = 27 07:24:49 [INFO] train episode 11429: reward = -93.69, steps = 24 07:24:51 [INFO] train episode 11430: reward = -77.36, steps = 24 07:24:53 [INFO] train episode 11431: reward = -147.52, steps = 27 07:24:58 [INFO] train episode 11432: reward = -91.96, steps = 56 07:25:00 [INFO] train episode 11433: reward = -54.14, steps = 20 07:25:03 [INFO] train episode 11434: reward = -120.43, steps = 33 07:25:05 [INFO] train episode 11435: reward = -62.90, steps = 21 07:25:08 [INFO] train episode 11436: reward = -130.82, steps = 32 07:25:10 [INFO] train episode 11437: reward = -77.35, steps = 23 07:25:11 [INFO] train episode 11438: reward = -77.90, steps = 23 07:25:15 [INFO] train episode 11439: reward = -82.36, steps = 37 07:25:17 [INFO] train episode 11440: reward = -86.44, steps = 27 07:25:20 [INFO] train episode 11441: reward = -87.07, steps = 30 07:25:22 [INFO] train episode 11442: reward = -92.31, steps = 26 07:25:24 [INFO] train episode 11443: reward = -103.05, steps = 18 07:25:25 [INFO] train episode 11444: reward = -115.63, steps = 21 07:25:27 [INFO] train episode 11445: reward = -78.78, steps = 22 07:25:30 [INFO] train episode 11446: reward = -85.86, steps = 30 07:25:32 [INFO] train episode 11447: reward = -76.23, steps = 21 07:25:35 [INFO] train episode 11448: reward = -119.67, steps = 38 07:25:38 [INFO] train episode 11449: reward = -68.74, steps = 31 07:25:40 [INFO] train episode 11450: reward = -58.59, steps = 26 07:25:42 [INFO] train episode 11451: reward = -88.11, steps = 24 07:25:45 [INFO] train episode 11452: reward = -89.48, steps = 32 07:25:48 [INFO] train episode 11453: reward = -80.82, steps = 24 07:25:51 [INFO] train episode 11454: reward = -103.14, steps = 29 07:25:53 [INFO] train episode 11455: reward = -67.24, steps = 27 07:25:55 [INFO] train episode 11456: reward = -95.53, steps = 23 07:25:57 [INFO] train episode 11457: reward = -98.35, steps = 21 07:26:00 [INFO] train episode 11458: reward = -114.04, steps = 28 07:26:03 [INFO] train episode 11459: reward = -87.76, steps = 36 07:26:06 [INFO] train episode 11460: reward = -90.24, steps = 22 07:26:08 [INFO] train episode 11461: reward = -95.04, steps = 27 07:26:11 [INFO] train episode 11462: reward = -82.87, steps = 20 07:26:13 [INFO] train episode 11463: reward = -87.62, steps = 27 07:26:15 [INFO] train episode 11464: reward = -74.56, steps = 19 07:26:17 [INFO] train episode 11465: reward = -95.38, steps = 18 07:26:19 [INFO] train episode 11466: reward = -94.42, steps = 24 07:26:21 [INFO] train episode 11467: reward = -120.25, steps = 21 07:26:23 [INFO] train episode 11468: reward = -58.91, steps = 20 07:26:28 [INFO] train episode 11469: reward = -81.09, steps = 50 07:26:31 [INFO] train episode 11470: reward = -74.88, steps = 32 07:26:33 [INFO] train episode 11471: reward = -80.04, steps = 23 07:26:36 [INFO] train episode 11472: reward = -99.79, steps = 31 07:26:38 [INFO] train episode 11473: reward = -114.09, steps = 22 07:26:40 [INFO] train episode 11474: reward = -71.59, steps = 27 07:26:42 [INFO] train episode 11475: reward = -128.43, steps = 23 07:26:44 [INFO] train episode 11476: reward = -91.29, steps = 21 07:26:47 [INFO] train episode 11477: reward = -73.03, steps = 27 07:26:49 [INFO] train episode 11478: reward = -89.57, steps = 20 07:26:51 [INFO] train episode 11479: reward = -104.27, steps = 22 07:26:54 [INFO] train episode 11480: reward = -131.50, steps = 40 07:26:57 [INFO] train episode 11481: reward = -128.60, steps = 22 07:26:59 [INFO] train episode 11482: reward = -83.02, steps = 25 07:27:02 [INFO] train episode 11483: reward = -51.29, steps = 36 07:27:04 [INFO] train episode 11484: reward = -83.38, steps = 22 07:27:06 [INFO] train episode 11485: reward = -87.39, steps = 23 07:27:08 [INFO] train episode 11486: reward = -84.41, steps = 28 07:27:10 [INFO] train episode 11487: reward = -93.24, steps = 23 07:27:12 [INFO] train episode 11488: reward = -84.26, steps = 19 07:27:14 [INFO] train episode 11489: reward = -77.82, steps = 21 07:27:16 [INFO] train episode 11490: reward = -95.61, steps = 21 07:27:18 [INFO] train episode 11491: reward = -108.59, steps = 19 07:27:20 [INFO] train episode 11492: reward = -91.61, steps = 22 07:27:22 [INFO] train episode 11493: reward = -76.43, steps = 23 07:27:23 [INFO] train episode 11494: reward = -70.98, steps = 21 07:27:28 [INFO] train episode 11495: reward = -117.35, steps = 53 07:27:31 [INFO] train episode 11496: reward = -77.03, steps = 37 07:27:33 [INFO] train episode 11497: reward = -80.77, steps = 21 07:27:35 [INFO] train episode 11498: reward = -67.51, steps = 19 07:27:38 [INFO] train episode 11499: reward = -111.34, steps = 27 07:27:40 [INFO] train episode 11500: reward = -77.09, steps = 21 07:27:42 [INFO] train episode 11501: reward = -113.06, steps = 21 07:27:45 [INFO] train episode 11502: reward = -74.12, steps = 31 07:27:47 [INFO] train episode 11503: reward = -76.20, steps = 30 07:27:51 [INFO] train episode 11504: reward = -101.67, steps = 43 07:27:53 [INFO] train episode 11505: reward = -83.29, steps = 23 07:27:54 [INFO] train episode 11506: reward = -79.08, steps = 21 07:27:57 [INFO] train episode 11507: reward = -78.86, steps = 38 07:28:00 [INFO] train episode 11508: reward = -74.05, steps = 28 07:28:02 [INFO] train episode 11509: reward = -69.15, steps = 19 07:28:04 [INFO] train episode 11510: reward = -76.56, steps = 28 07:28:06 [INFO] train episode 11511: reward = -63.37, steps = 21 07:28:08 [INFO] train episode 11512: reward = -69.27, steps = 25 07:28:11 [INFO] train episode 11513: reward = -113.32, steps = 34 07:28:13 [INFO] train episode 11514: reward = -139.71, steps = 26 07:28:15 [INFO] train episode 11515: reward = -78.30, steps = 20 07:28:17 [INFO] train episode 11516: reward = -64.25, steps = 22 07:28:19 [INFO] train episode 11517: reward = -122.22, steps = 22 07:28:22 [INFO] train episode 11518: reward = -82.58, steps = 32 07:28:24 [INFO] train episode 11519: reward = -71.88, steps = 24 07:28:27 [INFO] train episode 11520: reward = -101.82, steps = 36 07:28:29 [INFO] train episode 11521: reward = -85.52, steps = 26 07:28:32 [INFO] train episode 11522: reward = -98.01, steps = 30 07:28:35 [INFO] train episode 11523: reward = -95.92, steps = 39 07:28:37 [INFO] train episode 11524: reward = -82.13, steps = 25 07:28:39 [INFO] train episode 11525: reward = -134.96, steps = 24 07:28:42 [INFO] train episode 11526: reward = -135.56, steps = 31 07:28:44 [INFO] train episode 11527: reward = -71.21, steps = 24 07:28:47 [INFO] train episode 11528: reward = -121.15, steps = 29 07:28:49 [INFO] train episode 11529: reward = -65.80, steps = 20 07:28:53 [INFO] train episode 11530: reward = -126.20, steps = 52 07:28:55 [INFO] train episode 11531: reward = -115.95, steps = 20 07:28:57 [INFO] train episode 11532: reward = -72.92, steps = 22 07:28:58 [INFO] train episode 11533: reward = -96.03, steps = 21 07:29:00 [INFO] train episode 11534: reward = -66.57, steps = 26 07:29:04 [INFO] train episode 11535: reward = -96.60, steps = 34 07:29:06 [INFO] train episode 11536: reward = -90.62, steps = 20 07:29:09 [INFO] train episode 11537: reward = -74.01, steps = 30 07:29:11 [INFO] train episode 11538: reward = -87.05, steps = 21 07:29:13 [INFO] train episode 11539: reward = -154.03, steps = 23 07:29:15 [INFO] train episode 11540: reward = -93.16, steps = 24 07:29:19 [INFO] train episode 11541: reward = -105.88, steps = 44 07:29:21 [INFO] train episode 11542: reward = -82.05, steps = 21 07:29:23 [INFO] train episode 11543: reward = -107.69, steps = 28 07:29:25 [INFO] train episode 11544: reward = -97.05, steps = 20 07:29:28 [INFO] train episode 11545: reward = -88.31, steps = 37 07:29:31 [INFO] train episode 11546: reward = -87.37, steps = 36 07:29:34 [INFO] train episode 11547: reward = -96.08, steps = 30 07:29:36 [INFO] train episode 11548: reward = -164.80, steps = 21 07:29:38 [INFO] train episode 11549: reward = -73.38, steps = 22 07:29:40 [INFO] train episode 11550: reward = -67.37, steps = 21 07:29:42 [INFO] train episode 11551: reward = -87.86, steps = 29 07:29:45 [INFO] train episode 11552: reward = -86.65, steps = 34 07:29:47 [INFO] train episode 11553: reward = -97.34, steps = 21 07:29:49 [INFO] train episode 11554: reward = -75.90, steps = 28 07:29:52 [INFO] train episode 11555: reward = -108.68, steps = 26 07:29:53 [INFO] train episode 11556: reward = -75.46, steps = 20 07:29:55 [INFO] train episode 11557: reward = -81.38, steps = 25 07:29:57 [INFO] train episode 11558: reward = -99.04, steps = 21 07:29:59 [INFO] train episode 11559: reward = -68.67, steps = 20 07:30:02 [INFO] train episode 11560: reward = -93.10, steps = 29 07:30:04 [INFO] train episode 11561: reward = -71.26, steps = 28 07:30:06 [INFO] train episode 11562: reward = -101.43, steps = 20 07:30:08 [INFO] train episode 11563: reward = -75.05, steps = 23 07:30:10 [INFO] train episode 11564: reward = -88.97, steps = 20 07:30:12 [INFO] train episode 11565: reward = -71.45, steps = 29 07:30:15 [INFO] train episode 11566: reward = -106.71, steps = 30 07:30:17 [INFO] train episode 11567: reward = -77.16, steps = 24 07:30:19 [INFO] train episode 11568: reward = -84.91, steps = 26 07:30:21 [INFO] train episode 11569: reward = -68.97, steps = 26 07:30:23 [INFO] train episode 11570: reward = -71.52, steps = 25 07:30:26 [INFO] train episode 11571: reward = -99.08, steps = 26 07:30:29 [INFO] train episode 11572: reward = -72.81, steps = 25 07:30:30 [INFO] train episode 11573: reward = -100.60, steps = 15 07:30:32 [INFO] train episode 11574: reward = -79.71, steps = 21 07:30:34 [INFO] train episode 11575: reward = -79.18, steps = 23 07:30:38 [INFO] train episode 11576: reward = -116.81, steps = 46 07:30:40 [INFO] train episode 11577: reward = -120.10, steps = 27 07:30:42 [INFO] train episode 11578: reward = -97.18, steps = 23 07:30:44 [INFO] train episode 11579: reward = -83.27, steps = 24 07:30:48 [INFO] train episode 11580: reward = -76.69, steps = 39 07:30:50 [INFO] train episode 11581: reward = -106.74, steps = 31 07:30:53 [INFO] train episode 11582: reward = -83.89, steps = 30 07:30:55 [INFO] train episode 11583: reward = -79.86, steps = 24 07:30:57 [INFO] train episode 11584: reward = -87.43, steps = 22 07:31:02 [INFO] train episode 11585: reward = -149.55, steps = 60 07:31:04 [INFO] train episode 11586: reward = -101.55, steps = 21 07:31:08 [INFO] train episode 11587: reward = -89.13, steps = 51 07:31:13 [INFO] train episode 11588: reward = -97.74, steps = 50 07:31:15 [INFO] train episode 11589: reward = -90.06, steps = 30 07:31:17 [INFO] train episode 11590: reward = -79.37, steps = 27 07:31:19 [INFO] train episode 11591: reward = -91.10, steps = 20 07:31:23 [INFO] train episode 11592: reward = -68.47, steps = 44 07:31:25 [INFO] train episode 11593: reward = -79.85, steps = 22 07:31:27 [INFO] train episode 11594: reward = -73.02, steps = 27 07:31:29 [INFO] train episode 11595: reward = -77.29, steps = 23 07:31:32 [INFO] train episode 11596: reward = -80.17, steps = 32 07:31:34 [INFO] train episode 11597: reward = -78.80, steps = 25 07:31:37 [INFO] train episode 11598: reward = -73.66, steps = 24 07:31:38 [INFO] train episode 11599: reward = -72.78, steps = 21 07:31:41 [INFO] train episode 11600: reward = -81.43, steps = 24 07:31:43 [INFO] train episode 11601: reward = -113.97, steps = 23 07:31:45 [INFO] train episode 11602: reward = -108.31, steps = 28 07:31:47 [INFO] train episode 11603: reward = -66.19, steps = 24 07:31:50 [INFO] train episode 11604: reward = -84.79, steps = 31 07:31:52 [INFO] train episode 11605: reward = -77.70, steps = 26 07:31:54 [INFO] train episode 11606: reward = -71.16, steps = 20 07:31:56 [INFO] train episode 11607: reward = -76.04, steps = 22 07:31:58 [INFO] train episode 11608: reward = -92.84, steps = 21 07:32:00 [INFO] train episode 11609: reward = -105.04, steps = 29 07:32:02 [INFO] train episode 11610: reward = -67.34, steps = 21 07:32:04 [INFO] train episode 11611: reward = -94.99, steps = 23 07:32:06 [INFO] train episode 11612: reward = -94.83, steps = 23 07:32:09 [INFO] train episode 11613: reward = -88.11, steps = 32 07:32:11 [INFO] train episode 11614: reward = -83.13, steps = 29 07:32:16 [INFO] train episode 11615: reward = -79.02, steps = 42 07:32:18 [INFO] train episode 11616: reward = -76.25, steps = 21 07:32:23 [INFO] train episode 11617: reward = -129.59, steps = 58 07:32:25 [INFO] train episode 11618: reward = -62.81, steps = 20 07:32:27 [INFO] train episode 11619: reward = -88.81, steps = 27 07:32:31 [INFO] train episode 11620: reward = -98.69, steps = 35 07:32:32 [INFO] train episode 11621: reward = -102.93, steps = 22 07:32:35 [INFO] train episode 11622: reward = -82.36, steps = 23 07:32:36 [INFO] train episode 11623: reward = -121.55, steps = 19 07:32:38 [INFO] train episode 11624: reward = -97.93, steps = 21 07:32:41 [INFO] train episode 11625: reward = -81.82, steps = 25 07:32:43 [INFO] train episode 11626: reward = -81.72, steps = 24 07:32:47 [INFO] train episode 11627: reward = -75.94, steps = 37 07:32:49 [INFO] train episode 11628: reward = -86.23, steps = 27 07:32:51 [INFO] train episode 11629: reward = -75.59, steps = 23 07:32:54 [INFO] train episode 11630: reward = -68.98, steps = 26 07:32:56 [INFO] train episode 11631: reward = -93.40, steps = 24 07:33:00 [INFO] train episode 11632: reward = -91.68, steps = 32 07:33:02 [INFO] train episode 11633: reward = -119.91, steps = 23 07:33:03 [INFO] train episode 11634: reward = -100.66, steps = 17 07:33:06 [INFO] train episode 11635: reward = -59.44, steps = 24 07:33:08 [INFO] train episode 11636: reward = -77.45, steps = 20 07:33:10 [INFO] train episode 11637: reward = -86.27, steps = 26 07:33:13 [INFO] train episode 11638: reward = -66.20, steps = 33 07:33:16 [INFO] train episode 11639: reward = -114.10, steps = 31 07:33:18 [INFO] train episode 11640: reward = -76.96, steps = 20 07:33:20 [INFO] train episode 11641: reward = -96.80, steps = 26 07:33:22 [INFO] train episode 11642: reward = -86.97, steps = 23 07:33:27 [INFO] train episode 11643: reward = -84.03, steps = 45 07:33:29 [INFO] train episode 11644: reward = -71.74, steps = 22 07:33:33 [INFO] train episode 11645: reward = -114.31, steps = 55 07:33:36 [INFO] train episode 11646: reward = -89.59, steps = 27 07:33:39 [INFO] train episode 11647: reward = -84.08, steps = 33 07:33:41 [INFO] train episode 11648: reward = -77.34, steps = 29 07:33:43 [INFO] train episode 11649: reward = -84.82, steps = 21 07:33:45 [INFO] train episode 11650: reward = -108.70, steps = 22 07:33:47 [INFO] train episode 11651: reward = -87.00, steps = 30 07:33:49 [INFO] train episode 11652: reward = -76.56, steps = 24 07:33:52 [INFO] train episode 11653: reward = -60.76, steps = 35 07:33:55 [INFO] train episode 11654: reward = -97.61, steps = 26 07:33:57 [INFO] train episode 11655: reward = -87.95, steps = 26 07:34:00 [INFO] train episode 11656: reward = -85.95, steps = 28 07:34:03 [INFO] train episode 11657: reward = -110.98, steps = 42 07:34:05 [INFO] train episode 11658: reward = -80.28, steps = 20 07:34:09 [INFO] train episode 11659: reward = -78.18, steps = 49 07:34:11 [INFO] train episode 11660: reward = -91.96, steps = 24 07:34:14 [INFO] train episode 11661: reward = -91.81, steps = 29 07:34:18 [INFO] train episode 11662: reward = -121.06, steps = 50 07:34:20 [INFO] train episode 11663: reward = -110.07, steps = 21 07:34:22 [INFO] train episode 11664: reward = -71.13, steps = 23 07:34:24 [INFO] train episode 11665: reward = -122.22, steps = 27 07:34:27 [INFO] train episode 11666: reward = -59.26, steps = 30 07:34:29 [INFO] train episode 11667: reward = -89.02, steps = 28 07:34:33 [INFO] train episode 11668: reward = -120.68, steps = 50 07:34:36 [INFO] train episode 11669: reward = -130.75, steps = 26 07:34:41 [INFO] train episode 11670: reward = -138.21, steps = 57 07:34:43 [INFO] train episode 11671: reward = -69.90, steps = 26 07:34:45 [INFO] train episode 11672: reward = -122.27, steps = 23 07:34:48 [INFO] train episode 11673: reward = -84.62, steps = 29 07:34:49 [INFO] train episode 11674: reward = -69.83, steps = 22 07:34:51 [INFO] train episode 11675: reward = -95.41, steps = 21 07:34:53 [INFO] train episode 11676: reward = -71.31, steps = 23 07:34:55 [INFO] train episode 11677: reward = -87.61, steps = 21 07:34:58 [INFO] train episode 11678: reward = -63.85, steps = 32 07:35:01 [INFO] train episode 11679: reward = -59.88, steps = 35 07:35:05 [INFO] train episode 11680: reward = -119.09, steps = 44 07:35:07 [INFO] train episode 11681: reward = -105.97, steps = 24 07:35:09 [INFO] train episode 11682: reward = -85.85, steps = 29 07:35:12 [INFO] train episode 11683: reward = -79.82, steps = 26 07:35:14 [INFO] train episode 11684: reward = -128.66, steps = 22 07:35:16 [INFO] train episode 11685: reward = -70.58, steps = 32 07:35:18 [INFO] train episode 11686: reward = -91.22, steps = 20 07:35:21 [INFO] train episode 11687: reward = -84.29, steps = 38 07:35:24 [INFO] train episode 11688: reward = -101.35, steps = 32 07:35:26 [INFO] train episode 11689: reward = -121.04, steps = 22 07:35:28 [INFO] train episode 11690: reward = -95.47, steps = 22 07:35:30 [INFO] train episode 11691: reward = -94.24, steps = 25 07:35:34 [INFO] train episode 11692: reward = -102.93, steps = 51 07:35:38 [INFO] train episode 11693: reward = -82.04, steps = 44 07:35:40 [INFO] train episode 11694: reward = -60.63, steps = 24 07:35:43 [INFO] train episode 11695: reward = -69.13, steps = 32 07:35:45 [INFO] train episode 11696: reward = -88.25, steps = 24 07:35:47 [INFO] train episode 11697: reward = -141.84, steps = 25 07:35:50 [INFO] train episode 11698: reward = -81.21, steps = 26 07:35:52 [INFO] train episode 11699: reward = -91.98, steps = 27 07:35:54 [INFO] train episode 11700: reward = -98.84, steps = 25 07:35:56 [INFO] train episode 11701: reward = -97.50, steps = 26 07:35:58 [INFO] train episode 11702: reward = -116.91, steps = 21 07:36:00 [INFO] train episode 11703: reward = -97.90, steps = 22 07:36:02 [INFO] train episode 11704: reward = -117.32, steps = 23 07:36:05 [INFO] train episode 11705: reward = -85.01, steps = 35 07:36:08 [INFO] train episode 11706: reward = -90.87, steps = 29 07:36:10 [INFO] train episode 11707: reward = -69.93, steps = 28 07:36:16 [INFO] train episode 11708: reward = -125.32, steps = 56 07:36:17 [INFO] train episode 11709: reward = -83.33, steps = 18 07:36:20 [INFO] train episode 11710: reward = -107.79, steps = 29 07:36:24 [INFO] train episode 11711: reward = -76.99, steps = 50 07:36:27 [INFO] train episode 11712: reward = -168.55, steps = 31 07:36:28 [INFO] train episode 11713: reward = -78.82, steps = 22 07:36:32 [INFO] train episode 11714: reward = -131.19, steps = 33 07:36:33 [INFO] train episode 11715: reward = -83.28, steps = 21 07:36:36 [INFO] train episode 11716: reward = -67.93, steps = 34 07:36:40 [INFO] train episode 11717: reward = -146.19, steps = 45 07:36:44 [INFO] train episode 11718: reward = -91.97, steps = 41 07:36:48 [INFO] train episode 11719: reward = -120.71, steps = 51 07:36:51 [INFO] train episode 11720: reward = -133.84, steps = 31 07:36:52 [INFO] train episode 11721: reward = -89.81, steps = 19 07:36:54 [INFO] train episode 11722: reward = -79.30, steps = 22 07:36:56 [INFO] train episode 11723: reward = -114.01, steps = 21 07:37:00 [INFO] train episode 11724: reward = -98.68, steps = 43 07:37:03 [INFO] train episode 11725: reward = -76.56, steps = 27 07:37:06 [INFO] train episode 11726: reward = -111.03, steps = 36 07:37:09 [INFO] train episode 11727: reward = -116.09, steps = 39 07:37:13 [INFO] train episode 11728: reward = -57.45, steps = 44 07:37:16 [INFO] train episode 11729: reward = -80.93, steps = 35 07:37:18 [INFO] train episode 11730: reward = -75.32, steps = 26 07:37:20 [INFO] train episode 11731: reward = -86.02, steps = 27 07:37:23 [INFO] train episode 11732: reward = -87.17, steps = 30 07:37:26 [INFO] train episode 11733: reward = -79.21, steps = 33 07:37:28 [INFO] train episode 11734: reward = -92.72, steps = 24 07:37:31 [INFO] train episode 11735: reward = -70.09, steps = 29 07:37:33 [INFO] train episode 11736: reward = -75.40, steps = 28 07:37:36 [INFO] train episode 11737: reward = -86.80, steps = 31 07:37:39 [INFO] train episode 11738: reward = -95.73, steps = 29 07:37:42 [INFO] train episode 11739: reward = -117.08, steps = 40 07:37:44 [INFO] train episode 11740: reward = -67.33, steps = 22 07:37:46 [INFO] train episode 11741: reward = -91.35, steps = 30 07:37:49 [INFO] train episode 11742: reward = -79.82, steps = 28 07:37:51 [INFO] train episode 11743: reward = -89.60, steps = 29 07:37:54 [INFO] train episode 11744: reward = -71.79, steps = 29 07:37:56 [INFO] train episode 11745: reward = -95.92, steps = 22 07:37:58 [INFO] train episode 11746: reward = -94.90, steps = 26 07:38:00 [INFO] train episode 11747: reward = -125.35, steps = 25 07:38:04 [INFO] train episode 11748: reward = -76.85, steps = 41 07:38:07 [INFO] train episode 11749: reward = -110.96, steps = 36 07:38:09 [INFO] train episode 11750: reward = -83.13, steps = 23 07:38:11 [INFO] train episode 11751: reward = -72.09, steps = 26 07:38:14 [INFO] train episode 11752: reward = -103.60, steps = 39 07:38:16 [INFO] train episode 11753: reward = -95.85, steps = 23 07:38:19 [INFO] train episode 11754: reward = -77.01, steps = 31 07:38:22 [INFO] train episode 11755: reward = -76.34, steps = 28 07:38:25 [INFO] train episode 11756: reward = -109.72, steps = 37 07:38:28 [INFO] train episode 11757: reward = -65.06, steps = 35 07:38:30 [INFO] train episode 11758: reward = -82.10, steps = 25 07:38:34 [INFO] train episode 11759: reward = -109.71, steps = 54 07:38:37 [INFO] train episode 11760: reward = -97.96, steps = 28 07:38:41 [INFO] train episode 11761: reward = -104.91, steps = 40 07:38:43 [INFO] train episode 11762: reward = -67.74, steps = 25 07:38:45 [INFO] train episode 11763: reward = -98.01, steps = 21 07:38:49 [INFO] train episode 11764: reward = -137.13, steps = 50 07:38:51 [INFO] train episode 11765: reward = -62.55, steps = 22 07:38:53 [INFO] train episode 11766: reward = -133.85, steps = 29 07:38:56 [INFO] train episode 11767: reward = -121.60, steps = 27 07:38:58 [INFO] train episode 11768: reward = -90.22, steps = 30 07:39:02 [INFO] train episode 11769: reward = -63.07, steps = 40 07:39:04 [INFO] train episode 11770: reward = -60.53, steps = 24 07:39:07 [INFO] train episode 11771: reward = -70.19, steps = 25 07:39:12 [INFO] train episode 11772: reward = -169.06, steps = 66 07:39:17 [INFO] train episode 11773: reward = -117.86, steps = 50 07:39:19 [INFO] train episode 11774: reward = -115.55, steps = 29 07:39:22 [INFO] train episode 11775: reward = -80.30, steps = 39 07:39:26 [INFO] train episode 11776: reward = -80.69, steps = 39 07:39:29 [INFO] train episode 11777: reward = -97.28, steps = 41 07:39:32 [INFO] train episode 11778: reward = -113.70, steps = 36 07:39:35 [INFO] train episode 11779: reward = -112.28, steps = 28 07:39:37 [INFO] train episode 11780: reward = -102.26, steps = 24 07:39:41 [INFO] train episode 11781: reward = -146.65, steps = 44 07:39:43 [INFO] train episode 11782: reward = -77.56, steps = 30 07:39:46 [INFO] train episode 11783: reward = -99.14, steps = 28 07:39:48 [INFO] train episode 11784: reward = -77.61, steps = 23 07:39:50 [INFO] train episode 11785: reward = -83.62, steps = 23 07:39:54 [INFO] train episode 11786: reward = -75.35, steps = 47 07:39:56 [INFO] train episode 11787: reward = -82.25, steps = 22 07:39:59 [INFO] train episode 11788: reward = -102.28, steps = 34 07:40:01 [INFO] train episode 11789: reward = -126.12, steps = 21 07:40:05 [INFO] train episode 11790: reward = -48.16, steps = 53 07:40:07 [INFO] train episode 11791: reward = -102.05, steps = 27 07:40:10 [INFO] train episode 11792: reward = -107.74, steps = 37 07:40:13 [INFO] train episode 11793: reward = -95.50, steps = 31 07:40:16 [INFO] train episode 11794: reward = -65.55, steps = 29 07:40:22 [INFO] train episode 11795: reward = -103.87, steps = 80 07:40:25 [INFO] train episode 11796: reward = -73.21, steps = 27 07:40:29 [INFO] train episode 11797: reward = -103.29, steps = 47 07:40:31 [INFO] train episode 11798: reward = -95.88, steps = 22 07:40:33 [INFO] train episode 11799: reward = -84.54, steps = 19 07:40:35 [INFO] train episode 11800: reward = -86.59, steps = 31 07:40:38 [INFO] train episode 11801: reward = -115.31, steps = 29 07:40:40 [INFO] train episode 11802: reward = -141.67, steps = 27 07:40:43 [INFO] train episode 11803: reward = -89.44, steps = 27 07:40:46 [INFO] train episode 11804: reward = -101.28, steps = 33 07:40:49 [INFO] train episode 11805: reward = -95.57, steps = 36 07:40:52 [INFO] train episode 11806: reward = -79.28, steps = 35 07:40:57 [INFO] train episode 11807: reward = -142.02, steps = 61 07:40:59 [INFO] train episode 11808: reward = -71.52, steps = 22 07:41:01 [INFO] train episode 11809: reward = -106.94, steps = 23 07:41:03 [INFO] train episode 11810: reward = -88.39, steps = 21 07:41:08 [INFO] train episode 11811: reward = -112.18, steps = 60 07:41:10 [INFO] train episode 11812: reward = -118.89, steps = 24 07:41:15 [INFO] train episode 11813: reward = -211.59, steps = 61 07:41:17 [INFO] train episode 11814: reward = -87.85, steps = 25 07:41:20 [INFO] train episode 11815: reward = -144.82, steps = 34 07:41:24 [INFO] train episode 11816: reward = -74.28, steps = 45 07:41:26 [INFO] train episode 11817: reward = -86.16, steps = 21 07:41:28 [INFO] train episode 11818: reward = -139.87, steps = 30 07:41:31 [INFO] train episode 11819: reward = -76.17, steps = 28 07:41:33 [INFO] train episode 11820: reward = -85.04, steps = 27 07:41:38 [INFO] train episode 11821: reward = -102.72, steps = 51 07:41:41 [INFO] train episode 11822: reward = -85.12, steps = 41 07:41:47 [INFO] train episode 11823: reward = -170.55, steps = 71 07:41:50 [INFO] train episode 11824: reward = -78.59, steps = 29 07:41:53 [INFO] train episode 11825: reward = -85.07, steps = 38 07:41:56 [INFO] train episode 11826: reward = -120.84, steps = 26 07:41:59 [INFO] train episode 11827: reward = -101.23, steps = 32 07:42:04 [INFO] train episode 11828: reward = -118.39, steps = 61 07:42:06 [INFO] train episode 11829: reward = -82.50, steps = 26 07:42:09 [INFO] train episode 11830: reward = -129.58, steps = 34 07:42:12 [INFO] train episode 11831: reward = -67.58, steps = 36 07:42:14 [INFO] train episode 11832: reward = -105.51, steps = 26 07:42:17 [INFO] train episode 11833: reward = -71.29, steps = 29 07:42:20 [INFO] train episode 11834: reward = -122.95, steps = 25 07:42:23 [INFO] train episode 11835: reward = -114.02, steps = 38 07:42:25 [INFO] train episode 11836: reward = -116.02, steps = 25 07:42:29 [INFO] train episode 11837: reward = -95.90, steps = 46 07:42:31 [INFO] train episode 11838: reward = -117.44, steps = 24 07:42:33 [INFO] train episode 11839: reward = -110.26, steps = 27 07:42:36 [INFO] train episode 11840: reward = -69.79, steps = 26 07:42:39 [INFO] train episode 11841: reward = -75.97, steps = 37 07:42:42 [INFO] train episode 11842: reward = -107.35, steps = 38 07:42:44 [INFO] train episode 11843: reward = -103.34, steps = 27 07:42:47 [INFO] train episode 11844: reward = -87.59, steps = 27 07:42:49 [INFO] train episode 11845: reward = -103.02, steps = 22 07:42:54 [INFO] train episode 11846: reward = -122.35, steps = 63 07:42:57 [INFO] train episode 11847: reward = -90.81, steps = 35 07:42:59 [INFO] train episode 11848: reward = -90.01, steps = 22 07:43:03 [INFO] train episode 11849: reward = -81.57, steps = 44 07:43:05 [INFO] train episode 11850: reward = -121.79, steps = 24 07:43:09 [INFO] train episode 11851: reward = -72.62, steps = 45 07:43:11 [INFO] train episode 11852: reward = -106.83, steps = 30 07:43:14 [INFO] train episode 11853: reward = -70.19, steps = 29 07:43:15 [INFO] train episode 11854: reward = -94.45, steps = 18 07:43:18 [INFO] train episode 11855: reward = -112.46, steps = 26 07:43:20 [INFO] train episode 11856: reward = -116.04, steps = 30 07:43:25 [INFO] train episode 11857: reward = -87.67, steps = 48 07:43:27 [INFO] train episode 11858: reward = -145.62, steps = 27 07:43:31 [INFO] train episode 11859: reward = -117.48, steps = 46 07:43:35 [INFO] train episode 11860: reward = -124.61, steps = 44 07:43:38 [INFO] train episode 11861: reward = -77.65, steps = 30 07:43:40 [INFO] train episode 11862: reward = -108.85, steps = 25 07:43:42 [INFO] train episode 11863: reward = -96.37, steps = 27 07:43:44 [INFO] train episode 11864: reward = -93.24, steps = 24 07:43:47 [INFO] train episode 11865: reward = -71.79, steps = 34 07:43:49 [INFO] train episode 11866: reward = -80.69, steps = 25 07:43:53 [INFO] train episode 11867: reward = -114.54, steps = 49 07:43:56 [INFO] train episode 11868: reward = -81.60, steps = 29 07:43:58 [INFO] train episode 11869: reward = -122.56, steps = 29 07:44:02 [INFO] train episode 11870: reward = -67.74, steps = 40 07:44:04 [INFO] train episode 11871: reward = -125.71, steps = 28 07:44:06 [INFO] train episode 11872: reward = -73.02, steps = 22 07:44:08 [INFO] train episode 11873: reward = -112.83, steps = 20 07:44:10 [INFO] train episode 11874: reward = -69.25, steps = 20 07:44:12 [INFO] train episode 11875: reward = -111.76, steps = 25 07:44:14 [INFO] train episode 11876: reward = -79.29, steps = 27 07:44:17 [INFO] train episode 11877: reward = -125.42, steps = 29 07:44:20 [INFO] train episode 11878: reward = -123.28, steps = 46 07:44:22 [INFO] train episode 11879: reward = -103.97, steps = 20 07:44:26 [INFO] train episode 11880: reward = -101.21, steps = 46 07:44:28 [INFO] train episode 11881: reward = -102.85, steps = 22 07:44:31 [INFO] train episode 11882: reward = -99.09, steps = 32 07:44:34 [INFO] train episode 11883: reward = -68.08, steps = 37 07:44:39 [INFO] train episode 11884: reward = -109.16, steps = 53 07:44:41 [INFO] train episode 11885: reward = -107.08, steps = 26 07:44:43 [INFO] train episode 11886: reward = -88.43, steps = 26 07:44:46 [INFO] train episode 11887: reward = -118.28, steps = 26 07:44:49 [INFO] train episode 11888: reward = -88.04, steps = 28 07:44:53 [INFO] train episode 11889: reward = -106.50, steps = 56 07:44:56 [INFO] train episode 11890: reward = -128.64, steps = 29 07:44:59 [INFO] train episode 11891: reward = -88.62, steps = 39 07:45:01 [INFO] train episode 11892: reward = -118.77, steps = 23 07:45:03 [INFO] train episode 11893: reward = -90.39, steps = 20 07:45:07 [INFO] train episode 11894: reward = -105.76, steps = 43 07:45:09 [INFO] train episode 11895: reward = -85.80, steps = 22 07:45:14 [INFO] train episode 11896: reward = -99.83, steps = 64 07:45:19 [INFO] train episode 11897: reward = -66.18, steps = 61 07:45:21 [INFO] train episode 11898: reward = -109.97, steps = 24 07:45:24 [INFO] train episode 11899: reward = -67.61, steps = 27 07:45:27 [INFO] train episode 11900: reward = -80.16, steps = 40 07:45:30 [INFO] train episode 11901: reward = -108.53, steps = 25 07:45:32 [INFO] train episode 11902: reward = -101.50, steps = 22 07:45:34 [INFO] train episode 11903: reward = -86.55, steps = 26 07:45:36 [INFO] train episode 11904: reward = -110.37, steps = 23 07:45:38 [INFO] train episode 11905: reward = -110.19, steps = 24 07:45:40 [INFO] train episode 11906: reward = -88.57, steps = 26 07:45:47 [INFO] train episode 11907: reward = -146.28, steps = 74 07:45:49 [INFO] train episode 11908: reward = -79.52, steps = 34 07:45:53 [INFO] train episode 11909: reward = -123.13, steps = 42 07:45:55 [INFO] train episode 11910: reward = -83.49, steps = 25 07:45:58 [INFO] train episode 11911: reward = -87.73, steps = 27 07:46:00 [INFO] train episode 11912: reward = -100.26, steps = 25 07:46:03 [INFO] train episode 11913: reward = -123.02, steps = 28 07:46:05 [INFO] train episode 11914: reward = -110.45, steps = 23 07:46:08 [INFO] train episode 11915: reward = -123.03, steps = 44 07:46:12 [INFO] train episode 11916: reward = -81.88, steps = 43 07:46:14 [INFO] train episode 11917: reward = -77.99, steps = 25 07:46:17 [INFO] train episode 11918: reward = -95.80, steps = 29 07:46:19 [INFO] train episode 11919: reward = -103.54, steps = 28 07:46:22 [INFO] train episode 11920: reward = -107.44, steps = 29 07:46:26 [INFO] train episode 11921: reward = -77.33, steps = 46 07:46:28 [INFO] train episode 11922: reward = -90.31, steps = 28 07:46:32 [INFO] train episode 11923: reward = -76.99, steps = 38 07:46:34 [INFO] train episode 11924: reward = -155.16, steps = 24 07:46:38 [INFO] train episode 11925: reward = -104.17, steps = 46 07:46:41 [INFO] train episode 11926: reward = -108.53, steps = 35 07:46:45 [INFO] train episode 11927: reward = -133.60, steps = 49 07:46:47 [INFO] train episode 11928: reward = -109.77, steps = 25 07:46:50 [INFO] train episode 11929: reward = -108.64, steps = 26 07:46:53 [INFO] train episode 11930: reward = -75.25, steps = 43 07:46:56 [INFO] train episode 11931: reward = -103.91, steps = 32 07:46:58 [INFO] train episode 11932: reward = -102.19, steps = 24 07:47:01 [INFO] train episode 11933: reward = -112.20, steps = 33 07:47:03 [INFO] train episode 11934: reward = -99.16, steps = 25 07:47:05 [INFO] train episode 11935: reward = -104.55, steps = 22 07:47:07 [INFO] train episode 11936: reward = -93.88, steps = 24 07:47:09 [INFO] train episode 11937: reward = -83.72, steps = 22 07:47:14 [INFO] train episode 11938: reward = -84.70, steps = 54 07:47:18 [INFO] train episode 11939: reward = -137.27, steps = 50 07:47:20 [INFO] train episode 11940: reward = -85.00, steps = 23 07:47:22 [INFO] train episode 11941: reward = -68.58, steps = 20 07:47:24 [INFO] train episode 11942: reward = -97.73, steps = 21 07:47:25 [INFO] train episode 11943: reward = -131.14, steps = 18 07:47:27 [INFO] train episode 11944: reward = -108.85, steps = 21 07:47:30 [INFO] train episode 11945: reward = -110.48, steps = 41 07:47:33 [INFO] train episode 11946: reward = -72.80, steps = 35 07:47:36 [INFO] train episode 11947: reward = -71.00, steps = 21 07:47:41 [INFO] train episode 11948: reward = -120.21, steps = 59 07:47:43 [INFO] train episode 11949: reward = -109.57, steps = 20 07:47:45 [INFO] train episode 11950: reward = -133.11, steps = 29 07:47:48 [INFO] train episode 11951: reward = -90.52, steps = 28 07:47:50 [INFO] train episode 11952: reward = -101.27, steps = 21 07:47:55 [INFO] train episode 11953: reward = -103.30, steps = 60 07:47:57 [INFO] train episode 11954: reward = -89.01, steps = 25 07:48:04 [INFO] train episode 11955: reward = -157.01, steps = 83 07:48:08 [INFO] train episode 11956: reward = -98.52, steps = 45 07:48:12 [INFO] train episode 11957: reward = -108.74, steps = 43 07:48:14 [INFO] train episode 11958: reward = -108.88, steps = 30 07:48:17 [INFO] train episode 11959: reward = -90.33, steps = 32 07:48:19 [INFO] train episode 11960: reward = -95.90, steps = 27 07:48:21 [INFO] train episode 11961: reward = -105.84, steps = 20 07:48:23 [INFO] train episode 11962: reward = -111.81, steps = 24 07:48:26 [INFO] train episode 11963: reward = -107.29, steps = 34 07:48:29 [INFO] train episode 11964: reward = -64.92, steps = 29 07:48:32 [INFO] train episode 11965: reward = -90.03, steps = 38 07:48:34 [INFO] train episode 11966: reward = -108.42, steps = 24 07:48:36 [INFO] train episode 11967: reward = -88.91, steps = 26 07:48:40 [INFO] train episode 11968: reward = -93.68, steps = 44 07:48:43 [INFO] train episode 11969: reward = -121.26, steps = 28 07:48:47 [INFO] train episode 11970: reward = -104.89, steps = 48 07:48:50 [INFO] train episode 11971: reward = -102.97, steps = 39 07:48:53 [INFO] train episode 11972: reward = -80.16, steps = 35 07:48:56 [INFO] train episode 11973: reward = -95.08, steps = 34 07:48:59 [INFO] train episode 11974: reward = -92.72, steps = 37 07:49:04 [INFO] train episode 11975: reward = -190.40, steps = 55 07:49:07 [INFO] train episode 11976: reward = -112.64, steps = 33 07:49:12 [INFO] train episode 11977: reward = -136.31, steps = 63 07:49:15 [INFO] train episode 11978: reward = -71.65, steps = 28 07:49:17 [INFO] train episode 11979: reward = -87.96, steps = 27 07:49:21 [INFO] train episode 11980: reward = -116.15, steps = 46 07:49:24 [INFO] train episode 11981: reward = -146.89, steps = 33 07:49:27 [INFO] train episode 11982: reward = -116.77, steps = 42 07:49:32 [INFO] train episode 11983: reward = -145.36, steps = 59 07:49:36 [INFO] train episode 11984: reward = -129.89, steps = 48 07:49:42 [INFO] train episode 11985: reward = -164.27, steps = 63 07:49:45 [INFO] train episode 11986: reward = -73.55, steps = 38 07:49:50 [INFO] train episode 11987: reward = -151.20, steps = 64 07:49:53 [INFO] train episode 11988: reward = -86.85, steps = 32 07:49:56 [INFO] train episode 11989: reward = -94.44, steps = 33 07:49:59 [INFO] train episode 11990: reward = -136.17, steps = 39 07:50:03 [INFO] train episode 11991: reward = -132.00, steps = 37 07:50:06 [INFO] train episode 11992: reward = -126.57, steps = 45 07:50:09 [INFO] train episode 11993: reward = -109.49, steps = 36 07:50:13 [INFO] train episode 11994: reward = -109.90, steps = 34 07:50:15 [INFO] train episode 11995: reward = -122.70, steps = 24 07:50:19 [INFO] train episode 11996: reward = -79.45, steps = 51 07:50:21 [INFO] train episode 11997: reward = -140.13, steps = 22 07:50:25 [INFO] train episode 11998: reward = -118.99, steps = 40 07:50:27 [INFO] train episode 11999: reward = -86.35, steps = 23 07:50:29 [INFO] train episode 12000: reward = -90.59, steps = 25 07:50:32 [INFO] train episode 12001: reward = -163.22, steps = 29 07:50:35 [INFO] train episode 12002: reward = -108.18, steps = 38 07:50:38 [INFO] train episode 12003: reward = -118.78, steps = 32 07:50:40 [INFO] train episode 12004: reward = -144.50, steps = 32 07:50:45 [INFO] train episode 12005: reward = -139.76, steps = 52 07:50:47 [INFO] train episode 12006: reward = -105.11, steps = 27 07:50:50 [INFO] train episode 12007: reward = -112.53, steps = 29 07:50:52 [INFO] train episode 12008: reward = -110.17, steps = 25 07:50:55 [INFO] train episode 12009: reward = -67.94, steps = 35 07:50:59 [INFO] train episode 12010: reward = -117.01, steps = 50 07:51:05 [INFO] train episode 12011: reward = -115.83, steps = 62 07:51:08 [INFO] train episode 12012: reward = -138.00, steps = 43 07:51:11 [INFO] train episode 12013: reward = -73.45, steps = 40 07:51:15 [INFO] train episode 12014: reward = -106.01, steps = 37 07:51:18 [INFO] train episode 12015: reward = -74.12, steps = 37 07:51:23 [INFO] train episode 12016: reward = -121.82, steps = 59 07:51:27 [INFO] train episode 12017: reward = -96.40, steps = 46 07:51:30 [INFO] train episode 12018: reward = -97.58, steps = 40 07:51:33 [INFO] train episode 12019: reward = -73.66, steps = 23 07:51:37 [INFO] train episode 12020: reward = -122.69, steps = 52 07:51:40 [INFO] train episode 12021: reward = -92.78, steps = 32 07:51:43 [INFO] train episode 12022: reward = -99.52, steps = 38 07:51:46 [INFO] train episode 12023: reward = -138.19, steps = 39 07:51:49 [INFO] train episode 12024: reward = -96.93, steps = 30 07:51:52 [INFO] train episode 12025: reward = -88.96, steps = 33 07:51:55 [INFO] train episode 12026: reward = -118.70, steps = 40 07:51:58 [INFO] train episode 12027: reward = -86.16, steps = 30 07:52:00 [INFO] train episode 12028: reward = -91.31, steps = 27 07:52:02 [INFO] train episode 12029: reward = -110.50, steps = 24 07:52:06 [INFO] train episode 12030: reward = -159.81, steps = 44 07:52:09 [INFO] train episode 12031: reward = -174.50, steps = 36 07:52:11 [INFO] train episode 12032: reward = -116.64, steps = 23 07:52:13 [INFO] train episode 12033: reward = -116.96, steps = 21 07:52:18 [INFO] train episode 12034: reward = -147.48, steps = 61 07:52:22 [INFO] train episode 12035: reward = -149.24, steps = 39 07:52:24 [INFO] train episode 12036: reward = -74.10, steps = 30 07:52:28 [INFO] train episode 12037: reward = -106.92, steps = 47 07:52:32 [INFO] train episode 12038: reward = -134.88, steps = 46 07:52:33 [INFO] train episode 12039: reward = -97.32, steps = 18 07:52:36 [INFO] train episode 12040: reward = -91.06, steps = 26 07:52:39 [INFO] train episode 12041: reward = -79.14, steps = 35 07:52:41 [INFO] train episode 12042: reward = -80.16, steps = 21 07:52:45 [INFO] train episode 12043: reward = -189.62, steps = 47 07:52:48 [INFO] train episode 12044: reward = -153.19, steps = 32 07:52:49 [INFO] train episode 12045: reward = -97.38, steps = 23 07:52:53 [INFO] train episode 12046: reward = -153.57, steps = 44 07:52:55 [INFO] train episode 12047: reward = -144.98, steps = 21 07:52:57 [INFO] train episode 12048: reward = -189.33, steps = 23 07:53:02 [INFO] train episode 12049: reward = -132.98, steps = 62 07:53:07 [INFO] train episode 12050: reward = -173.49, steps = 54 07:53:09 [INFO] train episode 12051: reward = -95.83, steps = 25 07:53:12 [INFO] train episode 12052: reward = -96.65, steps = 28 07:53:15 [INFO] train episode 12053: reward = -117.17, steps = 25 07:53:17 [INFO] train episode 12054: reward = -95.30, steps = 29 07:53:19 [INFO] train episode 12055: reward = -90.24, steps = 25 07:53:23 [INFO] train episode 12056: reward = -123.52, steps = 39 07:53:25 [INFO] train episode 12057: reward = -114.45, steps = 29 07:53:30 [INFO] train episode 12058: reward = -110.73, steps = 51 07:53:34 [INFO] train episode 12059: reward = -108.53, steps = 46 07:53:36 [INFO] train episode 12060: reward = -99.11, steps = 31 07:53:38 [INFO] train episode 12061: reward = -119.39, steps = 22 07:53:43 [INFO] train episode 12062: reward = -100.93, steps = 52 07:53:46 [INFO] train episode 12063: reward = -120.03, steps = 39 07:53:49 [INFO] train episode 12064: reward = -118.98, steps = 36 07:53:52 [INFO] train episode 12065: reward = -101.80, steps = 34 07:53:55 [INFO] train episode 12066: reward = -138.64, steps = 30 07:53:57 [INFO] train episode 12067: reward = -130.80, steps = 25 07:53:59 [INFO] train episode 12068: reward = -125.33, steps = 24 07:54:02 [INFO] train episode 12069: reward = -104.75, steps = 34 07:54:04 [INFO] train episode 12070: reward = -92.07, steps = 21 07:54:06 [INFO] train episode 12071: reward = -103.53, steps = 21 07:54:08 [INFO] train episode 12072: reward = -83.24, steps = 26 07:54:11 [INFO] train episode 12073: reward = -112.84, steps = 28 07:54:13 [INFO] train episode 12074: reward = -114.94, steps = 24 07:54:15 [INFO] train episode 12075: reward = -101.11, steps = 25 07:54:17 [INFO] train episode 12076: reward = -111.88, steps = 26 07:54:19 [INFO] train episode 12077: reward = -93.83, steps = 25 07:54:21 [INFO] train episode 12078: reward = -95.01, steps = 25 07:54:23 [INFO] train episode 12079: reward = -83.96, steps = 23 07:54:26 [INFO] train episode 12080: reward = -103.70, steps = 28 07:54:29 [INFO] train episode 12081: reward = -98.96, steps = 35 07:54:32 [INFO] train episode 12082: reward = -161.40, steps = 39 07:54:35 [INFO] train episode 12083: reward = -112.19, steps = 29 07:54:37 [INFO] train episode 12084: reward = -117.92, steps = 25 07:54:40 [INFO] train episode 12085: reward = -93.32, steps = 35 07:54:43 [INFO] train episode 12086: reward = -128.50, steps = 28 07:54:45 [INFO] train episode 12087: reward = -100.62, steps = 27 07:54:47 [INFO] train episode 12088: reward = -79.81, steps = 27 07:54:50 [INFO] train episode 12089: reward = -85.78, steps = 32 07:54:53 [INFO] train episode 12090: reward = -98.93, steps = 37 07:54:55 [INFO] train episode 12091: reward = -111.93, steps = 23 07:54:59 [INFO] train episode 12092: reward = -114.88, steps = 39 07:55:01 [INFO] train episode 12093: reward = -174.60, steps = 24 07:55:03 [INFO] train episode 12094: reward = -100.65, steps = 33 07:55:06 [INFO] train episode 12095: reward = -84.54, steps = 26 07:55:08 [INFO] train episode 12096: reward = -105.56, steps = 30 07:55:10 [INFO] train episode 12097: reward = -97.90, steps = 22 07:55:13 [INFO] train episode 12098: reward = -164.74, steps = 28 07:55:22 [INFO] train episode 12099: reward = -226.59, steps = 107 07:55:24 [INFO] train episode 12100: reward = -128.29, steps = 26 07:55:26 [INFO] train episode 12101: reward = -86.36, steps = 20 07:55:30 [INFO] train episode 12102: reward = -119.98, steps = 47 07:55:32 [INFO] train episode 12103: reward = -123.46, steps = 20 07:55:34 [INFO] train episode 12104: reward = -137.70, steps = 28 07:55:37 [INFO] train episode 12105: reward = -96.79, steps = 40 07:55:42 [INFO] train episode 12106: reward = -111.51, steps = 53 07:55:47 [INFO] train episode 12107: reward = -95.68, steps = 53 07:55:51 [INFO] train episode 12108: reward = -128.78, steps = 47 07:55:53 [INFO] train episode 12109: reward = -101.85, steps = 26 07:55:56 [INFO] train episode 12110: reward = -73.18, steps = 38 07:55:58 [INFO] train episode 12111: reward = -97.22, steps = 28 07:56:00 [INFO] train episode 12112: reward = -100.39, steps = 18 07:56:02 [INFO] train episode 12113: reward = -144.69, steps = 23 07:56:05 [INFO] train episode 12114: reward = -111.53, steps = 26 07:56:09 [INFO] train episode 12115: reward = -136.81, steps = 47 07:56:13 [INFO] train episode 12116: reward = -145.02, steps = 51 07:56:16 [INFO] train episode 12117: reward = -91.69, steps = 31 07:56:19 [INFO] train episode 12118: reward = -158.19, steps = 27 07:56:21 [INFO] train episode 12119: reward = -114.48, steps = 24 07:56:23 [INFO] train episode 12120: reward = -88.49, steps = 27 07:56:25 [INFO] train episode 12121: reward = -121.04, steps = 27 07:56:28 [INFO] train episode 12122: reward = -133.55, steps = 29 07:56:35 [INFO] train episode 12123: reward = -170.99, steps = 80 07:56:38 [INFO] train episode 12124: reward = -88.11, steps = 43 07:56:41 [INFO] train episode 12125: reward = -112.86, steps = 28 07:56:43 [INFO] train episode 12126: reward = -118.48, steps = 31 07:56:47 [INFO] train episode 12127: reward = -139.47, steps = 41 07:56:49 [INFO] train episode 12128: reward = -93.04, steps = 27 07:56:52 [INFO] train episode 12129: reward = -101.84, steps = 28 07:56:54 [INFO] train episode 12130: reward = -93.16, steps = 26 07:56:59 [INFO] train episode 12131: reward = -124.49, steps = 51 07:57:01 [INFO] train episode 12132: reward = -87.56, steps = 24 07:57:04 [INFO] train episode 12133: reward = -91.89, steps = 30 07:57:05 [INFO] train episode 12134: reward = -84.76, steps = 22 07:57:08 [INFO] train episode 12135: reward = -99.37, steps = 25 07:57:13 [INFO] train episode 12136: reward = -153.98, steps = 64 07:57:15 [INFO] train episode 12137: reward = -101.66, steps = 26 07:57:17 [INFO] train episode 12138: reward = -76.83, steps = 26 07:57:20 [INFO] train episode 12139: reward = -115.32, steps = 29 07:57:23 [INFO] train episode 12140: reward = -139.72, steps = 32 07:57:26 [INFO] train episode 12141: reward = -118.64, steps = 39 07:57:28 [INFO] train episode 12142: reward = -90.55, steps = 22 07:57:31 [INFO] train episode 12143: reward = -107.28, steps = 32 07:57:33 [INFO] train episode 12144: reward = -134.31, steps = 24 07:57:36 [INFO] train episode 12145: reward = -119.66, steps = 34 07:57:38 [INFO] train episode 12146: reward = -116.71, steps = 25 07:57:40 [INFO] train episode 12147: reward = -100.37, steps = 22 07:57:42 [INFO] train episode 12148: reward = -113.17, steps = 23 07:57:44 [INFO] train episode 12149: reward = -120.06, steps = 22 07:57:46 [INFO] train episode 12150: reward = -93.44, steps = 21 07:57:51 [INFO] train episode 12151: reward = -130.66, steps = 54 07:57:53 [INFO] train episode 12152: reward = -115.04, steps = 21 07:57:55 [INFO] train episode 12153: reward = -90.92, steps = 28 07:57:57 [INFO] train episode 12154: reward = -143.62, steps = 23 07:57:59 [INFO] train episode 12155: reward = -169.25, steps = 28 07:58:01 [INFO] train episode 12156: reward = -117.18, steps = 21 07:58:04 [INFO] train episode 12157: reward = -133.16, steps = 33 07:58:06 [INFO] train episode 12158: reward = -116.61, steps = 21 07:58:08 [INFO] train episode 12159: reward = -104.82, steps = 25 07:58:10 [INFO] train episode 12160: reward = -93.99, steps = 23 07:58:14 [INFO] train episode 12161: reward = -102.44, steps = 52 07:58:16 [INFO] train episode 12162: reward = -95.00, steps = 23 07:58:19 [INFO] train episode 12163: reward = -102.70, steps = 31 07:58:21 [INFO] train episode 12164: reward = -141.07, steps = 25 07:58:24 [INFO] train episode 12165: reward = -136.62, steps = 34 07:58:27 [INFO] train episode 12166: reward = -110.18, steps = 26 07:58:30 [INFO] train episode 12167: reward = -132.54, steps = 37 07:58:34 [INFO] train episode 12168: reward = -100.56, steps = 47 07:58:36 [INFO] train episode 12169: reward = -115.32, steps = 32 07:58:39 [INFO] train episode 12170: reward = -96.76, steps = 27 07:58:45 [INFO] train episode 12171: reward = -118.62, steps = 74 07:58:49 [INFO] train episode 12172: reward = -129.92, steps = 42 07:58:51 [INFO] train episode 12173: reward = -84.71, steps = 21 07:58:53 [INFO] train episode 12174: reward = -88.39, steps = 24 07:58:56 [INFO] train episode 12175: reward = -134.37, steps = 24 07:58:59 [INFO] train episode 12176: reward = -148.39, steps = 31 07:59:01 [INFO] train episode 12177: reward = -111.74, steps = 26 07:59:05 [INFO] train episode 12178: reward = -157.42, steps = 49 07:59:07 [INFO] train episode 12179: reward = -95.89, steps = 21 07:59:16 [INFO] train episode 12180: reward = -194.68, steps = 102 07:59:18 [INFO] train episode 12181: reward = -117.39, steps = 26 07:59:21 [INFO] train episode 12182: reward = -92.31, steps = 30 07:59:24 [INFO] train episode 12183: reward = -121.02, steps = 30 07:59:28 [INFO] train episode 12184: reward = -118.88, steps = 44 07:59:30 [INFO] train episode 12185: reward = -82.08, steps = 33 07:59:33 [INFO] train episode 12186: reward = -121.31, steps = 25 07:59:36 [INFO] train episode 12187: reward = -142.11, steps = 43 07:59:38 [INFO] train episode 12188: reward = -102.63, steps = 22 07:59:40 [INFO] train episode 12189: reward = -134.48, steps = 28 07:59:44 [INFO] train episode 12190: reward = -84.50, steps = 38 07:59:47 [INFO] train episode 12191: reward = -140.03, steps = 37 07:59:50 [INFO] train episode 12192: reward = -75.90, steps = 28 07:59:51 [INFO] train episode 12193: reward = -115.28, steps = 22 07:59:54 [INFO] train episode 12194: reward = -106.34, steps = 35 07:59:57 [INFO] train episode 12195: reward = -136.39, steps = 25 08:00:00 [INFO] train episode 12196: reward = -71.61, steps = 41 08:00:03 [INFO] train episode 12197: reward = -83.71, steps = 34 08:00:05 [INFO] train episode 12198: reward = -113.27, steps = 23 08:00:07 [INFO] train episode 12199: reward = -127.77, steps = 22 08:00:09 [INFO] train episode 12200: reward = -93.78, steps = 21 08:00:11 [INFO] train episode 12201: reward = -95.69, steps = 26 08:00:14 [INFO] train episode 12202: reward = -127.10, steps = 31 08:00:16 [INFO] train episode 12203: reward = -109.64, steps = 23 08:00:18 [INFO] train episode 12204: reward = -73.98, steps = 30 08:00:21 [INFO] train episode 12205: reward = -97.83, steps = 29 08:00:23 [INFO] train episode 12206: reward = -108.38, steps = 27 08:00:25 [INFO] train episode 12207: reward = -117.46, steps = 21 08:00:27 [INFO] train episode 12208: reward = -108.16, steps = 21 08:00:29 [INFO] train episode 12209: reward = -87.20, steps = 24 08:00:31 [INFO] train episode 12210: reward = -98.53, steps = 21 08:00:34 [INFO] train episode 12211: reward = -155.75, steps = 32 08:00:37 [INFO] train episode 12212: reward = -113.35, steps = 44 08:00:40 [INFO] train episode 12213: reward = -101.50, steps = 29 08:00:44 [INFO] train episode 12214: reward = -134.64, steps = 47 08:00:47 [INFO] train episode 12215: reward = -96.24, steps = 31 08:00:50 [INFO] train episode 12216: reward = -107.18, steps = 31 08:00:51 [INFO] train episode 12217: reward = -112.49, steps = 23 08:00:54 [INFO] train episode 12218: reward = -118.72, steps = 24 08:00:56 [INFO] train episode 12219: reward = -110.96, steps = 32 08:00:58 [INFO] train episode 12220: reward = -112.08, steps = 18 08:01:01 [INFO] train episode 12221: reward = -104.97, steps = 32 08:01:05 [INFO] train episode 12222: reward = -137.76, steps = 51 08:01:08 [INFO] train episode 12223: reward = -168.98, steps = 39 08:01:11 [INFO] train episode 12224: reward = -89.92, steps = 26 08:01:13 [INFO] train episode 12225: reward = -141.76, steps = 24 08:01:16 [INFO] train episode 12226: reward = -98.69, steps = 37 08:01:19 [INFO] train episode 12227: reward = -118.46, steps = 27 08:01:21 [INFO] train episode 12228: reward = -130.32, steps = 26 08:01:23 [INFO] train episode 12229: reward = -93.24, steps = 26 08:01:25 [INFO] train episode 12230: reward = -118.96, steps = 21 08:01:28 [INFO] train episode 12231: reward = -133.96, steps = 34 08:01:30 [INFO] train episode 12232: reward = -89.26, steps = 29 08:01:38 [INFO] train episode 12233: reward = -217.82, steps = 87 08:01:42 [INFO] train episode 12234: reward = -111.27, steps = 48 08:01:47 [INFO] train episode 12235: reward = -167.32, steps = 52 08:01:50 [INFO] train episode 12236: reward = -88.98, steps = 21 08:01:52 [INFO] train episode 12237: reward = -208.79, steps = 29 08:01:55 [INFO] train episode 12238: reward = -165.74, steps = 32 08:01:57 [INFO] train episode 12239: reward = -110.23, steps = 30 08:02:00 [INFO] train episode 12240: reward = -113.47, steps = 26 08:02:02 [INFO] train episode 12241: reward = -90.93, steps = 26 08:02:04 [INFO] train episode 12242: reward = -101.10, steps = 23 08:02:07 [INFO] train episode 12243: reward = -87.46, steps = 30 08:02:10 [INFO] train episode 12244: reward = -158.24, steps = 35 08:02:14 [INFO] train episode 12245: reward = -162.08, steps = 49 08:02:16 [INFO] train episode 12246: reward = -118.64, steps = 27 08:02:20 [INFO] train episode 12247: reward = -133.41, steps = 43 08:02:23 [INFO] train episode 12248: reward = -94.59, steps = 26 08:02:25 [INFO] train episode 12249: reward = -125.55, steps = 31 08:02:28 [INFO] train episode 12250: reward = -94.87, steps = 29 08:02:30 [INFO] train episode 12251: reward = -133.33, steps = 25 08:02:32 [INFO] train episode 12252: reward = -126.77, steps = 23 08:02:34 [INFO] train episode 12253: reward = -112.47, steps = 27 08:02:37 [INFO] train episode 12254: reward = -104.60, steps = 30 08:02:39 [INFO] train episode 12255: reward = -98.46, steps = 21 08:02:41 [INFO] train episode 12256: reward = -135.85, steps = 27 08:02:43 [INFO] train episode 12257: reward = -112.62, steps = 22 08:02:45 [INFO] train episode 12258: reward = -145.01, steps = 28 08:02:48 [INFO] train episode 12259: reward = -109.78, steps = 25 08:02:49 [INFO] train episode 12260: reward = -126.30, steps = 21 08:02:52 [INFO] train episode 12261: reward = -127.64, steps = 30 08:02:55 [INFO] train episode 12262: reward = -154.25, steps = 28 08:02:57 [INFO] train episode 12263: reward = -113.32, steps = 25 08:02:59 [INFO] train episode 12264: reward = -125.79, steps = 26 08:03:01 [INFO] train episode 12265: reward = -105.97, steps = 28 08:03:04 [INFO] train episode 12266: reward = -133.46, steps = 26 08:03:07 [INFO] train episode 12267: reward = -83.85, steps = 40 08:03:10 [INFO] train episode 12268: reward = -123.28, steps = 36 08:03:12 [INFO] train episode 12269: reward = -119.83, steps = 22 08:03:17 [INFO] train episode 12270: reward = -132.99, steps = 56 08:03:20 [INFO] train episode 12271: reward = -135.69, steps = 34 08:03:25 [INFO] train episode 12272: reward = -136.84, steps = 57 08:03:29 [INFO] train episode 12273: reward = -117.44, steps = 42 08:03:31 [INFO] train episode 12274: reward = -115.85, steps = 30 08:03:34 [INFO] train episode 12275: reward = -110.81, steps = 29 08:03:35 [INFO] train episode 12276: reward = -100.96, steps = 22 08:03:42 [INFO] train episode 12277: reward = -281.81, steps = 75 08:03:47 [INFO] train episode 12278: reward = -119.37, steps = 58 08:03:49 [INFO] train episode 12279: reward = -89.50, steps = 26 08:03:51 [INFO] train episode 12280: reward = -123.00, steps = 23 08:03:57 [INFO] train episode 12281: reward = -166.09, steps = 73 08:04:02 [INFO] train episode 12282: reward = -126.97, steps = 49 08:04:04 [INFO] train episode 12283: reward = -111.99, steps = 34 08:04:07 [INFO] train episode 12284: reward = -88.19, steps = 33 08:04:12 [INFO] train episode 12285: reward = -104.42, steps = 51 08:04:16 [INFO] train episode 12286: reward = -105.54, steps = 46 08:04:18 [INFO] train episode 12287: reward = -92.89, steps = 30 08:04:21 [INFO] train episode 12288: reward = -109.84, steps = 29 08:04:23 [INFO] train episode 12289: reward = -108.97, steps = 26 08:04:27 [INFO] train episode 12290: reward = -130.54, steps = 46 08:04:29 [INFO] train episode 12291: reward = -114.92, steps = 20 08:04:32 [INFO] train episode 12292: reward = -150.92, steps = 36 08:04:34 [INFO] train episode 12293: reward = -110.95, steps = 25 08:04:37 [INFO] train episode 12294: reward = -114.76, steps = 28 08:04:41 [INFO] train episode 12295: reward = -110.08, steps = 44 08:04:44 [INFO] train episode 12296: reward = -105.69, steps = 37 08:04:49 [INFO] train episode 12297: reward = -140.47, steps = 53 08:04:51 [INFO] train episode 12298: reward = -118.74, steps = 30 08:04:54 [INFO] train episode 12299: reward = -107.12, steps = 31 08:04:56 [INFO] train episode 12300: reward = -124.54, steps = 25 08:04:58 [INFO] train episode 12301: reward = -151.58, steps = 21 08:05:00 [INFO] train episode 12302: reward = -120.93, steps = 23 08:05:03 [INFO] train episode 12303: reward = -131.80, steps = 28 08:05:05 [INFO] train episode 12304: reward = -135.30, steps = 24 08:05:07 [INFO] train episode 12305: reward = -159.88, steps = 26 08:05:09 [INFO] train episode 12306: reward = -98.62, steps = 22 08:05:12 [INFO] train episode 12307: reward = -100.43, steps = 35 08:05:17 [INFO] train episode 12308: reward = -137.73, steps = 58 08:05:21 [INFO] train episode 12309: reward = -123.05, steps = 45 08:05:23 [INFO] train episode 12310: reward = -117.74, steps = 22 08:05:25 [INFO] train episode 12311: reward = -101.75, steps = 28 08:05:29 [INFO] train episode 12312: reward = -119.77, steps = 47 08:05:31 [INFO] train episode 12313: reward = -127.84, steps = 22 08:05:33 [INFO] train episode 12314: reward = -123.31, steps = 21 08:05:36 [INFO] train episode 12315: reward = -156.39, steps = 37 08:05:38 [INFO] train episode 12316: reward = -150.90, steps = 21 08:05:41 [INFO] train episode 12317: reward = -104.42, steps = 34 08:05:43 [INFO] train episode 12318: reward = -133.62, steps = 26 08:05:48 [INFO] train episode 12319: reward = -132.09, steps = 62 08:05:52 [INFO] train episode 12320: reward = -110.61, steps = 45 08:05:54 [INFO] train episode 12321: reward = -138.12, steps = 24 08:05:56 [INFO] train episode 12322: reward = -88.15, steps = 23 08:06:00 [INFO] train episode 12323: reward = -108.72, steps = 40 08:06:01 [INFO] train episode 12324: reward = -119.23, steps = 21 08:06:04 [INFO] train episode 12325: reward = -96.01, steps = 23 08:06:07 [INFO] train episode 12326: reward = -105.15, steps = 36 08:06:09 [INFO] train episode 12327: reward = -138.36, steps = 20 08:06:11 [INFO] train episode 12328: reward = -123.97, steps = 31 08:06:13 [INFO] train episode 12329: reward = -117.55, steps = 20 08:06:17 [INFO] train episode 12330: reward = -118.09, steps = 47 08:06:20 [INFO] train episode 12331: reward = -155.84, steps = 29 08:06:22 [INFO] train episode 12332: reward = -115.39, steps = 24 08:06:25 [INFO] train episode 12333: reward = -89.72, steps = 34 08:06:28 [INFO] train episode 12334: reward = -138.35, steps = 35 08:06:29 [INFO] train episode 12335: reward = -132.66, steps = 21 08:06:34 [INFO] train episode 12336: reward = -111.10, steps = 48 08:06:37 [INFO] train episode 12337: reward = -112.69, steps = 32 08:06:39 [INFO] train episode 12338: reward = -168.66, steps = 29 08:06:41 [INFO] train episode 12339: reward = -153.69, steps = 24 08:06:44 [INFO] train episode 12340: reward = -101.15, steps = 29 08:06:46 [INFO] train episode 12341: reward = -128.28, steps = 25 08:06:48 [INFO] train episode 12342: reward = -113.54, steps = 26 08:06:51 [INFO] train episode 12343: reward = -94.74, steps = 27 08:06:55 [INFO] train episode 12344: reward = -140.18, steps = 49 08:06:58 [INFO] train episode 12345: reward = -81.47, steps = 37 08:07:00 [INFO] train episode 12346: reward = -175.62, steps = 26 08:07:02 [INFO] train episode 12347: reward = -135.43, steps = 25 08:07:05 [INFO] train episode 12348: reward = -111.10, steps = 26 08:07:08 [INFO] train episode 12349: reward = -90.63, steps = 30 08:07:12 [INFO] train episode 12350: reward = -146.21, steps = 51 08:07:16 [INFO] train episode 12351: reward = -79.80, steps = 46 08:07:21 [INFO] train episode 12352: reward = -136.69, steps = 58 08:07:23 [INFO] train episode 12353: reward = -128.27, steps = 23 08:07:27 [INFO] train episode 12354: reward = -138.95, steps = 34 08:07:29 [INFO] train episode 12355: reward = -121.52, steps = 23 08:07:31 [INFO] train episode 12356: reward = -144.49, steps = 26 08:07:33 [INFO] train episode 12357: reward = -114.93, steps = 22 08:07:36 [INFO] train episode 12358: reward = -159.73, steps = 34 08:07:38 [INFO] train episode 12359: reward = -126.01, steps = 28 08:07:40 [INFO] train episode 12360: reward = -93.31, steps = 20 08:07:44 [INFO] train episode 12361: reward = -166.92, steps = 51 08:07:46 [INFO] train episode 12362: reward = -110.90, steps = 22 08:07:48 [INFO] train episode 12363: reward = -108.67, steps = 23 08:07:50 [INFO] train episode 12364: reward = -122.90, steps = 26 08:07:54 [INFO] train episode 12365: reward = -101.41, steps = 39 08:07:56 [INFO] train episode 12366: reward = -116.35, steps = 23 08:07:58 [INFO] train episode 12367: reward = -119.58, steps = 28 08:08:02 [INFO] train episode 12368: reward = -137.17, steps = 44 08:08:05 [INFO] train episode 12369: reward = -97.62, steps = 30 08:08:07 [INFO] train episode 12370: reward = -146.89, steps = 25 08:08:09 [INFO] train episode 12371: reward = -125.89, steps = 25 08:08:12 [INFO] train episode 12372: reward = -126.93, steps = 27 08:08:13 [INFO] train episode 12373: reward = -93.47, steps = 21 08:08:17 [INFO] train episode 12374: reward = -116.62, steps = 39 08:08:18 [INFO] train episode 12375: reward = -107.75, steps = 20 08:08:21 [INFO] train episode 12376: reward = -129.62, steps = 24 08:08:23 [INFO] train episode 12377: reward = -110.70, steps = 30 08:08:26 [INFO] train episode 12378: reward = -88.27, steps = 31 08:08:28 [INFO] train episode 12379: reward = -107.38, steps = 21 08:08:30 [INFO] train episode 12380: reward = -120.41, steps = 28 08:08:33 [INFO] train episode 12381: reward = -113.63, steps = 31 08:08:38 [INFO] train episode 12382: reward = -193.86, steps = 61 08:08:41 [INFO] train episode 12383: reward = -135.03, steps = 29 08:08:44 [INFO] train episode 12384: reward = -154.31, steps = 44 08:08:47 [INFO] train episode 12385: reward = -121.08, steps = 28 08:08:49 [INFO] train episode 12386: reward = -122.47, steps = 25 08:08:52 [INFO] train episode 12387: reward = -89.32, steps = 34 08:08:54 [INFO] train episode 12388: reward = -114.18, steps = 21 08:08:57 [INFO] train episode 12389: reward = -121.28, steps = 38 08:08:59 [INFO] train episode 12390: reward = -130.92, steps = 22 08:09:03 [INFO] train episode 12391: reward = -116.81, steps = 42 08:09:06 [INFO] train episode 12392: reward = -130.38, steps = 38 08:09:08 [INFO] train episode 12393: reward = -111.83, steps = 26 08:09:11 [INFO] train episode 12394: reward = -106.51, steps = 35 08:09:14 [INFO] train episode 12395: reward = -116.80, steps = 26 08:09:17 [INFO] train episode 12396: reward = -151.46, steps = 45 08:09:20 [INFO] train episode 12397: reward = -114.57, steps = 27 08:09:26 [INFO] train episode 12398: reward = -142.38, steps = 71 08:09:28 [INFO] train episode 12399: reward = -148.19, steps = 30 08:09:31 [INFO] train episode 12400: reward = -102.65, steps = 35 08:09:34 [INFO] train episode 12401: reward = -98.78, steps = 27 08:09:39 [INFO] train episode 12402: reward = -151.15, steps = 64 08:09:43 [INFO] train episode 12403: reward = -133.52, steps = 45 08:09:46 [INFO] train episode 12404: reward = -137.16, steps = 28 08:09:47 [INFO] train episode 12405: reward = -134.54, steps = 22 08:09:49 [INFO] train episode 12406: reward = -126.10, steps = 22 08:09:51 [INFO] train episode 12407: reward = -114.99, steps = 25 08:09:53 [INFO] train episode 12408: reward = -103.81, steps = 23 08:09:56 [INFO] train episode 12409: reward = -109.09, steps = 27 08:09:59 [INFO] train episode 12410: reward = -101.30, steps = 34 08:10:01 [INFO] train episode 12411: reward = -144.00, steps = 22 08:10:04 [INFO] train episode 12412: reward = -131.12, steps = 38 08:10:07 [INFO] train episode 12413: reward = -135.68, steps = 30 08:10:08 [INFO] train episode 12414: reward = -118.54, steps = 21 08:10:11 [INFO] train episode 12415: reward = -126.01, steps = 28 08:10:13 [INFO] train episode 12416: reward = -109.35, steps = 29 08:10:19 [INFO] train episode 12417: reward = -182.05, steps = 51 08:10:22 [INFO] train episode 12418: reward = -122.45, steps = 39 08:10:24 [INFO] train episode 12419: reward = -121.23, steps = 31 08:10:26 [INFO] train episode 12420: reward = -101.29, steps = 17 08:10:30 [INFO] train episode 12421: reward = -155.77, steps = 51 08:10:34 [INFO] train episode 12422: reward = -140.84, steps = 41 08:10:36 [INFO] train episode 12423: reward = -156.35, steps = 22 08:10:39 [INFO] train episode 12424: reward = -133.52, steps = 39 08:10:43 [INFO] train episode 12425: reward = -122.01, steps = 47 08:10:46 [INFO] train episode 12426: reward = -113.19, steps = 35 08:10:50 [INFO] train episode 12427: reward = -135.62, steps = 44 08:10:55 [INFO] train episode 12428: reward = -142.41, steps = 65 08:10:58 [INFO] train episode 12429: reward = -129.92, steps = 32 08:11:00 [INFO] train episode 12430: reward = -147.25, steps = 23 08:11:03 [INFO] train episode 12431: reward = -121.75, steps = 31 08:11:05 [INFO] train episode 12432: reward = -139.99, steps = 26 08:11:09 [INFO] train episode 12433: reward = -92.78, steps = 45 08:11:11 [INFO] train episode 12434: reward = -140.70, steps = 27 08:11:13 [INFO] train episode 12435: reward = -128.46, steps = 22 08:11:15 [INFO] train episode 12436: reward = -152.08, steps = 20 08:11:17 [INFO] train episode 12437: reward = -131.06, steps = 23 08:11:20 [INFO] train episode 12438: reward = -112.76, steps = 27 08:11:21 [INFO] train episode 12439: reward = -129.57, steps = 22 08:11:25 [INFO] train episode 12440: reward = -109.29, steps = 39 08:11:32 [INFO] train episode 12441: reward = -180.64, steps = 82 08:11:34 [INFO] train episode 12442: reward = -208.27, steps = 31 08:11:38 [INFO] train episode 12443: reward = -134.72, steps = 37 08:11:40 [INFO] train episode 12444: reward = -132.11, steps = 27 08:11:42 [INFO] train episode 12445: reward = -140.26, steps = 20 08:11:44 [INFO] train episode 12446: reward = -111.94, steps = 25 08:11:47 [INFO] train episode 12447: reward = -105.52, steps = 38 08:11:51 [INFO] train episode 12448: reward = -140.90, steps = 46 08:11:53 [INFO] train episode 12449: reward = -161.88, steps = 25 08:11:55 [INFO] train episode 12450: reward = -136.30, steps = 24 08:11:58 [INFO] train episode 12451: reward = -98.58, steps = 24 08:12:00 [INFO] train episode 12452: reward = -136.97, steps = 27 08:12:04 [INFO] train episode 12453: reward = -144.93, steps = 51 08:12:06 [INFO] train episode 12454: reward = -119.66, steps = 22 08:12:08 [INFO] train episode 12455: reward = -105.33, steps = 20 08:12:12 [INFO] train episode 12456: reward = -135.23, steps = 44 08:12:14 [INFO] train episode 12457: reward = -82.36, steps = 27 08:12:19 [INFO] train episode 12458: reward = -209.84, steps = 62 08:12:22 [INFO] train episode 12459: reward = -133.42, steps = 35 08:12:26 [INFO] train episode 12460: reward = -121.75, steps = 44 08:12:28 [INFO] train episode 12461: reward = -103.69, steps = 25 08:12:31 [INFO] train episode 12462: reward = -141.35, steps = 27 08:12:34 [INFO] train episode 12463: reward = -103.27, steps = 42 08:12:36 [INFO] train episode 12464: reward = -116.48, steps = 22 08:12:39 [INFO] train episode 12465: reward = -154.87, steps = 31 08:12:41 [INFO] train episode 12466: reward = -141.05, steps = 21 08:12:44 [INFO] train episode 12467: reward = -121.86, steps = 43 08:12:47 [INFO] train episode 12468: reward = -99.35, steps = 25 08:12:48 [INFO] train episode 12469: reward = -108.08, steps = 21 08:12:50 [INFO] train episode 12470: reward = -88.03, steps = 21 08:12:53 [INFO] train episode 12471: reward = -71.96, steps = 31 08:12:55 [INFO] train episode 12472: reward = -96.98, steps = 25 08:12:57 [INFO] train episode 12473: reward = -116.23, steps = 19 08:13:00 [INFO] train episode 12474: reward = -116.68, steps = 27 08:13:02 [INFO] train episode 12475: reward = -90.77, steps = 33 08:13:05 [INFO] train episode 12476: reward = -149.37, steps = 28 08:13:07 [INFO] train episode 12477: reward = -128.58, steps = 22 08:13:09 [INFO] train episode 12478: reward = -112.87, steps = 24 08:13:13 [INFO] train episode 12479: reward = -190.07, steps = 43 08:13:15 [INFO] train episode 12480: reward = -124.03, steps = 21 08:13:18 [INFO] train episode 12481: reward = -152.05, steps = 33 08:13:20 [INFO] train episode 12482: reward = -104.47, steps = 23 08:13:23 [INFO] train episode 12483: reward = -207.06, steps = 33 08:13:26 [INFO] train episode 12484: reward = -152.11, steps = 35 08:13:28 [INFO] train episode 12485: reward = -124.75, steps = 25 08:13:31 [INFO] train episode 12486: reward = -147.94, steps = 27 08:13:33 [INFO] train episode 12487: reward = -115.85, steps = 28 08:13:35 [INFO] train episode 12488: reward = -110.28, steps = 26 08:13:38 [INFO] train episode 12489: reward = -125.83, steps = 33 08:13:41 [INFO] train episode 12490: reward = -138.38, steps = 42 08:13:46 [INFO] train episode 12491: reward = -136.23, steps = 55 08:13:48 [INFO] train episode 12492: reward = -87.05, steps = 26 08:13:52 [INFO] train episode 12493: reward = -102.72, steps = 38 08:13:56 [INFO] train episode 12494: reward = -127.33, steps = 50 08:13:58 [INFO] train episode 12495: reward = -135.96, steps = 31 08:14:02 [INFO] train episode 12496: reward = -139.89, steps = 33 08:14:04 [INFO] train episode 12497: reward = -127.90, steps = 27 08:14:06 [INFO] train episode 12498: reward = -112.88, steps = 23 08:14:09 [INFO] train episode 12499: reward = -124.86, steps = 41 08:14:13 [INFO] train episode 12500: reward = -118.81, steps = 42 08:14:15 [INFO] train episode 12501: reward = -143.44, steps = 24 08:14:17 [INFO] train episode 12502: reward = -160.44, steps = 23 08:14:20 [INFO] train episode 12503: reward = -109.98, steps = 33 08:14:23 [INFO] train episode 12504: reward = -130.94, steps = 31 08:14:25 [INFO] train episode 12505: reward = -117.99, steps = 32 08:14:27 [INFO] train episode 12506: reward = -128.14, steps = 24 08:14:30 [INFO] train episode 12507: reward = -149.43, steps = 34 08:14:32 [INFO] train episode 12508: reward = -112.16, steps = 20 08:14:35 [INFO] train episode 12509: reward = -110.29, steps = 32 08:14:38 [INFO] train episode 12510: reward = -127.15, steps = 37 08:14:41 [INFO] train episode 12511: reward = -155.30, steps = 34 08:14:44 [INFO] train episode 12512: reward = -131.29, steps = 32 08:14:47 [INFO] train episode 12513: reward = -115.90, steps = 27 08:14:49 [INFO] train episode 12514: reward = -135.34, steps = 24 08:14:51 [INFO] train episode 12515: reward = -100.26, steps = 29 08:14:54 [INFO] train episode 12516: reward = -180.24, steps = 30 08:14:57 [INFO] train episode 12517: reward = -109.13, steps = 38 08:14:59 [INFO] train episode 12518: reward = -173.45, steps = 28 08:15:04 [INFO] train episode 12519: reward = -153.58, steps = 55 08:15:07 [INFO] train episode 12520: reward = -103.96, steps = 33 08:15:10 [INFO] train episode 12521: reward = -110.83, steps = 33 08:15:12 [INFO] train episode 12522: reward = -130.66, steps = 26 08:15:14 [INFO] train episode 12523: reward = -147.01, steps = 23 08:15:16 [INFO] train episode 12524: reward = -130.15, steps = 26 08:15:21 [INFO] train episode 12525: reward = -176.22, steps = 49 08:15:23 [INFO] train episode 12526: reward = -149.92, steps = 31 08:15:25 [INFO] train episode 12527: reward = -147.05, steps = 24 08:15:31 [INFO] train episode 12528: reward = -206.31, steps = 67 08:15:33 [INFO] train episode 12529: reward = -144.95, steps = 29 08:15:38 [INFO] train episode 12530: reward = -127.94, steps = 50 08:15:42 [INFO] train episode 12531: reward = -151.13, steps = 51 08:15:45 [INFO] train episode 12532: reward = -145.85, steps = 38 08:15:48 [INFO] train episode 12533: reward = -141.85, steps = 37 08:15:51 [INFO] train episode 12534: reward = -125.86, steps = 29 08:15:53 [INFO] train episode 12535: reward = -100.87, steps = 23 08:15:57 [INFO] train episode 12536: reward = -126.02, steps = 41 08:15:59 [INFO] train episode 12537: reward = -117.19, steps = 21 08:16:02 [INFO] train episode 12538: reward = -125.94, steps = 40 08:16:04 [INFO] train episode 12539: reward = -116.26, steps = 22 08:16:06 [INFO] train episode 12540: reward = -117.60, steps = 22 08:16:09 [INFO] train episode 12541: reward = -131.97, steps = 24 08:16:11 [INFO] train episode 12542: reward = -132.37, steps = 26 08:16:13 [INFO] train episode 12543: reward = -145.09, steps = 22 08:16:14 [INFO] train episode 12544: reward = -145.84, steps = 21 08:16:20 [INFO] train episode 12545: reward = -209.11, steps = 62 08:16:23 [INFO] train episode 12546: reward = -147.64, steps = 38 08:16:26 [INFO] train episode 12547: reward = -131.27, steps = 32 08:16:29 [INFO] train episode 12548: reward = -118.86, steps = 41 08:16:33 [INFO] train episode 12549: reward = -108.29, steps = 39 08:16:37 [INFO] train episode 12550: reward = -123.36, steps = 48 08:16:42 [INFO] train episode 12551: reward = -106.87, steps = 56 08:16:44 [INFO] train episode 12552: reward = -141.96, steps = 26 08:16:48 [INFO] train episode 12553: reward = -159.52, steps = 48 08:16:51 [INFO] train episode 12554: reward = -119.42, steps = 30 08:16:54 [INFO] train episode 12555: reward = -164.28, steps = 32 08:16:56 [INFO] train episode 12556: reward = -103.89, steps = 22 08:16:58 [INFO] train episode 12557: reward = -125.43, steps = 26 08:17:02 [INFO] train episode 12558: reward = -224.22, steps = 47 08:17:04 [INFO] train episode 12559: reward = -150.52, steps = 28 08:17:08 [INFO] train episode 12560: reward = -107.34, steps = 40 08:17:11 [INFO] train episode 12561: reward = -108.54, steps = 29 08:17:13 [INFO] train episode 12562: reward = -162.33, steps = 31 08:17:17 [INFO] train episode 12563: reward = -135.04, steps = 46 08:17:20 [INFO] train episode 12564: reward = -137.22, steps = 33 08:17:25 [INFO] train episode 12565: reward = -215.14, steps = 57 08:17:28 [INFO] train episode 12566: reward = -120.86, steps = 40 08:17:30 [INFO] train episode 12567: reward = -112.67, steps = 22 08:17:36 [INFO] train episode 12568: reward = -202.60, steps = 66 08:17:39 [INFO] train episode 12569: reward = -106.86, steps = 40 08:17:42 [INFO] train episode 12570: reward = -123.99, steps = 29 08:17:44 [INFO] train episode 12571: reward = -125.44, steps = 25 08:17:47 [INFO] train episode 12572: reward = -122.09, steps = 40 08:17:52 [INFO] train episode 12573: reward = -128.48, steps = 56 08:17:54 [INFO] train episode 12574: reward = -112.54, steps = 21 08:17:56 [INFO] train episode 12575: reward = -137.80, steps = 21 08:17:59 [INFO] train episode 12576: reward = -128.88, steps = 35 08:18:03 [INFO] train episode 12577: reward = -131.17, steps = 44 08:18:07 [INFO] train episode 12578: reward = -160.47, steps = 47 08:18:10 [INFO] train episode 12579: reward = -145.23, steps = 42 08:18:13 [INFO] train episode 12580: reward = -113.18, steps = 33 08:18:16 [INFO] train episode 12581: reward = -143.37, steps = 24 08:18:19 [INFO] train episode 12582: reward = -131.60, steps = 46 08:18:22 [INFO] train episode 12583: reward = -144.47, steps = 26 08:18:24 [INFO] train episode 12584: reward = -103.60, steps = 29 08:18:27 [INFO] train episode 12585: reward = -95.73, steps = 36 08:18:30 [INFO] train episode 12586: reward = -111.81, steps = 28 08:18:34 [INFO] train episode 12587: reward = -211.84, steps = 46 08:18:35 [INFO] train episode 12588: reward = -92.54, steps = 20 08:18:37 [INFO] train episode 12589: reward = -126.79, steps = 24 08:18:43 [INFO] train episode 12590: reward = -144.74, steps = 58 08:18:48 [INFO] train episode 12591: reward = -180.13, steps = 60 08:18:52 [INFO] train episode 12592: reward = -110.86, steps = 38 08:18:54 [INFO] train episode 12593: reward = -139.82, steps = 33 08:18:58 [INFO] train episode 12594: reward = -111.71, steps = 39 08:19:01 [INFO] train episode 12595: reward = -150.07, steps = 42 08:19:04 [INFO] train episode 12596: reward = -125.18, steps = 27 08:19:06 [INFO] train episode 12597: reward = -208.36, steps = 21 08:19:08 [INFO] train episode 12598: reward = -111.80, steps = 32 08:19:11 [INFO] train episode 12599: reward = -124.14, steps = 27 08:19:13 [INFO] train episode 12600: reward = -152.23, steps = 24 08:19:16 [INFO] train episode 12601: reward = -147.07, steps = 41 08:19:20 [INFO] train episode 12602: reward = -154.14, steps = 41 08:19:22 [INFO] train episode 12603: reward = -154.56, steps = 24 08:19:24 [INFO] train episode 12604: reward = -112.33, steps = 22 08:19:26 [INFO] train episode 12605: reward = -154.46, steps = 22 08:19:30 [INFO] train episode 12606: reward = -113.12, steps = 48 08:19:32 [INFO] train episode 12607: reward = -93.11, steps = 23 08:19:35 [INFO] train episode 12608: reward = -130.74, steps = 38 08:19:37 [INFO] train episode 12609: reward = -155.21, steps = 22 08:19:39 [INFO] train episode 12610: reward = -124.40, steps = 21 08:19:43 [INFO] train episode 12611: reward = -173.62, steps = 43 08:19:45 [INFO] train episode 12612: reward = -94.57, steps = 30 08:19:49 [INFO] train episode 12613: reward = -189.98, steps = 46 08:19:51 [INFO] train episode 12614: reward = -113.36, steps = 24 08:19:55 [INFO] train episode 12615: reward = -132.30, steps = 49 08:19:58 [INFO] train episode 12616: reward = -169.60, steps = 30 08:20:02 [INFO] train episode 12617: reward = -112.20, steps = 44 08:20:04 [INFO] train episode 12618: reward = -129.99, steps = 26 08:20:06 [INFO] train episode 12619: reward = -120.59, steps = 23 08:20:08 [INFO] train episode 12620: reward = -105.72, steps = 22 08:20:11 [INFO] train episode 12621: reward = -147.29, steps = 34 08:20:14 [INFO] train episode 12622: reward = -121.10, steps = 42 08:20:18 [INFO] train episode 12623: reward = -104.24, steps = 42 08:20:20 [INFO] train episode 12624: reward = -118.00, steps = 21 08:20:23 [INFO] train episode 12625: reward = -111.40, steps = 37 08:20:26 [INFO] train episode 12626: reward = -116.54, steps = 28 08:20:28 [INFO] train episode 12627: reward = -134.29, steps = 28 08:20:30 [INFO] train episode 12628: reward = -112.25, steps = 24 08:20:33 [INFO] train episode 12629: reward = -111.97, steps = 35 08:20:35 [INFO] train episode 12630: reward = -102.41, steps = 22 08:20:38 [INFO] train episode 12631: reward = -147.96, steps = 30 08:20:40 [INFO] train episode 12632: reward = -101.23, steps = 26 08:20:43 [INFO] train episode 12633: reward = -121.28, steps = 31 08:20:45 [INFO] train episode 12634: reward = -119.44, steps = 22 08:20:47 [INFO] train episode 12635: reward = -173.86, steps = 29 08:20:49 [INFO] train episode 12636: reward = -148.00, steps = 20 08:20:52 [INFO] train episode 12637: reward = -124.26, steps = 35 08:20:55 [INFO] train episode 12638: reward = -172.14, steps = 36 08:21:00 [INFO] train episode 12639: reward = -124.68, steps = 45 08:21:02 [INFO] train episode 12640: reward = -172.48, steps = 23 08:21:06 [INFO] train episode 12641: reward = -121.36, steps = 43 08:21:09 [INFO] train episode 12642: reward = -141.82, steps = 22 08:21:12 [INFO] train episode 12643: reward = -130.30, steps = 40 08:21:15 [INFO] train episode 12644: reward = -108.99, steps = 30 08:21:17 [INFO] train episode 12645: reward = -125.22, steps = 26 08:21:20 [INFO] train episode 12646: reward = -110.36, steps = 28 08:21:25 [INFO] train episode 12647: reward = -173.00, steps = 47 08:21:27 [INFO] train episode 12648: reward = -127.68, steps = 21 08:21:29 [INFO] train episode 12649: reward = -130.16, steps = 24 08:21:31 [INFO] train episode 12650: reward = -133.38, steps = 21 08:21:33 [INFO] train episode 12651: reward = -135.10, steps = 26 08:21:35 [INFO] train episode 12652: reward = -106.47, steps = 23 08:21:38 [INFO] train episode 12653: reward = -103.20, steps = 33 08:21:42 [INFO] train episode 12654: reward = -147.61, steps = 34 08:21:44 [INFO] train episode 12655: reward = -133.48, steps = 25 08:21:46 [INFO] train episode 12656: reward = -127.25, steps = 23 08:21:48 [INFO] train episode 12657: reward = -138.29, steps = 21 08:21:50 [INFO] train episode 12658: reward = -122.16, steps = 22 08:21:52 [INFO] train episode 12659: reward = -155.13, steps = 22 08:21:54 [INFO] train episode 12660: reward = -154.80, steps = 22 08:21:57 [INFO] train episode 12661: reward = -110.61, steps = 33 08:22:00 [INFO] train episode 12662: reward = -111.52, steps = 37 08:22:02 [INFO] train episode 12663: reward = -130.29, steps = 25 08:22:04 [INFO] train episode 12664: reward = -148.42, steps = 26 08:22:06 [INFO] train episode 12665: reward = -106.97, steps = 23 08:22:08 [INFO] train episode 12666: reward = -143.13, steps = 23 08:22:12 [INFO] train episode 12667: reward = -90.80, steps = 41 08:22:15 [INFO] train episode 12668: reward = -111.94, steps = 40 08:22:18 [INFO] train episode 12669: reward = -120.49, steps = 28 08:22:21 [INFO] train episode 12670: reward = -104.76, steps = 41 08:22:24 [INFO] train episode 12671: reward = -119.37, steps = 32 08:22:26 [INFO] train episode 12672: reward = -142.11, steps = 22 08:22:28 [INFO] train episode 12673: reward = -140.59, steps = 28 08:22:30 [INFO] train episode 12674: reward = -185.01, steps = 17 08:22:32 [INFO] train episode 12675: reward = -128.61, steps = 22 08:22:34 [INFO] train episode 12676: reward = -185.28, steps = 30 08:22:37 [INFO] train episode 12677: reward = -92.23, steps = 35 08:22:40 [INFO] train episode 12678: reward = -129.90, steps = 36 08:22:44 [INFO] train episode 12679: reward = -173.58, steps = 38 08:22:46 [INFO] train episode 12680: reward = -125.64, steps = 22 08:22:48 [INFO] train episode 12681: reward = -115.82, steps = 27 08:22:50 [INFO] train episode 12682: reward = -143.59, steps = 23 08:22:53 [INFO] train episode 12683: reward = -134.25, steps = 30 08:22:56 [INFO] train episode 12684: reward = -152.32, steps = 39 08:22:59 [INFO] train episode 12685: reward = -144.67, steps = 38 08:23:03 [INFO] train episode 12686: reward = -168.37, steps = 39 08:23:06 [INFO] train episode 12687: reward = -141.84, steps = 34 08:23:08 [INFO] train episode 12688: reward = -115.89, steps = 24 08:23:10 [INFO] train episode 12689: reward = -141.17, steps = 25 08:23:12 [INFO] train episode 12690: reward = -146.64, steps = 28 08:23:15 [INFO] train episode 12691: reward = -92.39, steps = 29 08:23:18 [INFO] train episode 12692: reward = -117.44, steps = 36 08:23:21 [INFO] train episode 12693: reward = -97.26, steps = 41 08:23:23 [INFO] train episode 12694: reward = -133.73, steps = 20 08:23:26 [INFO] train episode 12695: reward = -130.92, steps = 33 08:23:29 [INFO] train episode 12696: reward = -150.83, steps = 32 08:23:31 [INFO] train episode 12697: reward = -159.11, steps = 29 08:23:34 [INFO] train episode 12698: reward = -106.53, steps = 24 08:23:35 [INFO] train episode 12699: reward = -125.15, steps = 21 08:23:37 [INFO] train episode 12700: reward = -131.20, steps = 22 08:23:40 [INFO] train episode 12701: reward = -155.07, steps = 29 08:23:42 [INFO] train episode 12702: reward = -132.70, steps = 33 08:23:45 [INFO] train episode 12703: reward = -180.72, steps = 31 08:23:47 [INFO] train episode 12704: reward = -111.42, steps = 23 08:23:50 [INFO] train episode 12705: reward = -110.29, steps = 29 08:23:53 [INFO] train episode 12706: reward = -134.24, steps = 41 08:23:57 [INFO] train episode 12707: reward = -120.98, steps = 45 08:23:59 [INFO] train episode 12708: reward = -117.47, steps = 24 08:24:01 [INFO] train episode 12709: reward = -229.35, steps = 23 08:24:06 [INFO] train episode 12710: reward = -126.53, steps = 50 08:24:10 [INFO] train episode 12711: reward = -157.19, steps = 46 08:24:12 [INFO] train episode 12712: reward = -117.80, steps = 23 08:24:14 [INFO] train episode 12713: reward = -99.27, steps = 24 08:24:17 [INFO] train episode 12714: reward = -110.35, steps = 36 08:24:20 [INFO] train episode 12715: reward = -98.24, steps = 34 08:24:22 [INFO] train episode 12716: reward = -133.87, steps = 25 08:24:24 [INFO] train episode 12717: reward = -180.13, steps = 23 08:24:26 [INFO] train episode 12718: reward = -128.02, steps = 28 08:24:32 [INFO] train episode 12719: reward = -132.33, steps = 53 08:24:33 [INFO] train episode 12720: reward = -165.46, steps = 22 08:24:36 [INFO] train episode 12721: reward = -130.89, steps = 25 08:24:38 [INFO] train episode 12722: reward = -117.63, steps = 22 08:24:40 [INFO] train episode 12723: reward = -158.27, steps = 25 08:24:42 [INFO] train episode 12724: reward = -108.52, steps = 26 08:24:45 [INFO] train episode 12725: reward = -120.39, steps = 28 08:24:47 [INFO] train episode 12726: reward = -135.25, steps = 26 08:24:49 [INFO] train episode 12727: reward = -86.15, steps = 21 08:24:50 [INFO] train episode 12728: reward = -113.69, steps = 18 08:24:53 [INFO] train episode 12729: reward = -139.15, steps = 32 08:24:57 [INFO] train episode 12730: reward = -109.59, steps = 44 08:25:00 [INFO] train episode 12731: reward = -112.74, steps = 37 08:25:04 [INFO] train episode 12732: reward = -113.52, steps = 43 08:25:05 [INFO] train episode 12733: reward = -128.51, steps = 20 08:25:08 [INFO] train episode 12734: reward = -105.36, steps = 25 08:25:11 [INFO] train episode 12735: reward = -143.29, steps = 31 08:25:13 [INFO] train episode 12736: reward = -116.95, steps = 25 08:25:15 [INFO] train episode 12737: reward = -125.95, steps = 28 08:25:18 [INFO] train episode 12738: reward = -153.68, steps = 31 08:25:20 [INFO] train episode 12739: reward = -128.91, steps = 24 08:25:22 [INFO] train episode 12740: reward = -193.38, steps = 26 08:25:24 [INFO] train episode 12741: reward = -120.07, steps = 20 08:25:26 [INFO] train episode 12742: reward = -156.83, steps = 23 08:25:28 [INFO] train episode 12743: reward = -106.82, steps = 20 08:25:30 [INFO] train episode 12744: reward = -114.05, steps = 28 08:25:34 [INFO] train episode 12745: reward = -169.97, steps = 43 08:25:36 [INFO] train episode 12746: reward = -123.05, steps = 25 08:25:40 [INFO] train episode 12747: reward = -96.04, steps = 43 08:25:43 [INFO] train episode 12748: reward = -135.90, steps = 33 08:25:44 [INFO] train episode 12749: reward = -115.74, steps = 21 08:25:46 [INFO] train episode 12750: reward = -134.47, steps = 21 08:25:48 [INFO] train episode 12751: reward = -126.35, steps = 22 08:25:50 [INFO] train episode 12752: reward = -136.32, steps = 22 08:25:52 [INFO] train episode 12753: reward = -83.57, steps = 23 08:25:55 [INFO] train episode 12754: reward = -157.47, steps = 25 08:25:58 [INFO] train episode 12755: reward = -130.91, steps = 36 08:26:00 [INFO] train episode 12756: reward = -169.13, steps = 25 08:26:02 [INFO] train episode 12757: reward = -158.23, steps = 24 08:26:05 [INFO] train episode 12758: reward = -151.61, steps = 37 08:26:09 [INFO] train episode 12759: reward = -145.47, steps = 40 08:26:11 [INFO] train episode 12760: reward = -149.44, steps = 33 08:26:13 [INFO] train episode 12761: reward = -158.08, steps = 23 08:26:16 [INFO] train episode 12762: reward = -107.36, steps = 30 08:26:19 [INFO] train episode 12763: reward = -102.94, steps = 34 08:26:21 [INFO] train episode 12764: reward = -113.74, steps = 33 08:26:26 [INFO] train episode 12765: reward = -158.07, steps = 47 08:26:28 [INFO] train episode 12766: reward = -120.53, steps = 23 08:26:30 [INFO] train episode 12767: reward = -124.54, steps = 27 08:26:34 [INFO] train episode 12768: reward = -160.21, steps = 43 08:26:36 [INFO] train episode 12769: reward = -130.69, steps = 30 08:26:38 [INFO] train episode 12770: reward = -148.33, steps = 23 08:26:41 [INFO] train episode 12771: reward = -114.05, steps = 26 08:26:43 [INFO] train episode 12772: reward = -157.10, steps = 23 08:26:45 [INFO] train episode 12773: reward = -107.34, steps = 28 08:26:47 [INFO] train episode 12774: reward = -156.36, steps = 21 08:26:51 [INFO] train episode 12775: reward = -126.29, steps = 49 08:26:55 [INFO] train episode 12776: reward = -149.69, steps = 42 08:26:57 [INFO] train episode 12777: reward = -89.04, steps = 26 08:27:00 [INFO] train episode 12778: reward = -123.79, steps = 32 08:27:02 [INFO] train episode 12779: reward = -144.65, steps = 20 08:27:04 [INFO] train episode 12780: reward = -111.57, steps = 27 08:27:06 [INFO] train episode 12781: reward = -143.19, steps = 23 08:27:08 [INFO] train episode 12782: reward = -157.10, steps = 23 08:27:10 [INFO] train episode 12783: reward = -122.36, steps = 24 08:27:12 [INFO] train episode 12784: reward = -116.82, steps = 21 08:27:14 [INFO] train episode 12785: reward = -147.73, steps = 24 08:27:16 [INFO] train episode 12786: reward = -98.33, steps = 26 08:27:19 [INFO] train episode 12787: reward = -134.08, steps = 23 08:27:22 [INFO] train episode 12788: reward = -108.94, steps = 26 08:27:23 [INFO] train episode 12789: reward = -147.01, steps = 22 08:27:25 [INFO] train episode 12790: reward = -106.34, steps = 23 08:27:30 [INFO] train episode 12791: reward = -124.29, steps = 48 08:27:32 [INFO] train episode 12792: reward = -118.51, steps = 26 08:27:34 [INFO] train episode 12793: reward = -120.43, steps = 28 08:27:37 [INFO] train episode 12794: reward = -127.88, steps = 27 08:27:39 [INFO] train episode 12795: reward = -141.76, steps = 29 08:27:41 [INFO] train episode 12796: reward = -160.72, steps = 24 08:27:43 [INFO] train episode 12797: reward = -174.36, steps = 21 08:27:45 [INFO] train episode 12798: reward = -110.92, steps = 24 08:27:47 [INFO] train episode 12799: reward = -111.62, steps = 21 08:27:49 [INFO] train episode 12800: reward = -92.42, steps = 26 08:27:52 [INFO] train episode 12801: reward = -123.52, steps = 32 08:27:54 [INFO] train episode 12802: reward = -122.69, steps = 21 08:27:56 [INFO] train episode 12803: reward = -144.28, steps = 22 08:27:59 [INFO] train episode 12804: reward = -92.47, steps = 35 08:28:03 [INFO] train episode 12805: reward = -178.06, steps = 45 08:28:05 [INFO] train episode 12806: reward = -99.48, steps = 22 08:28:07 [INFO] train episode 12807: reward = -136.31, steps = 31 08:28:09 [INFO] train episode 12808: reward = -136.04, steps = 21 08:28:11 [INFO] train episode 12809: reward = -126.74, steps = 27 08:28:15 [INFO] train episode 12810: reward = -122.18, steps = 38 08:28:17 [INFO] train episode 12811: reward = -108.76, steps = 25 08:28:19 [INFO] train episode 12812: reward = -135.41, steps = 27 08:28:22 [INFO] train episode 12813: reward = -146.45, steps = 31 08:28:24 [INFO] train episode 12814: reward = -118.66, steps = 24 08:28:26 [INFO] train episode 12815: reward = -134.63, steps = 24 08:28:30 [INFO] train episode 12816: reward = -163.51, steps = 43 08:28:32 [INFO] train episode 12817: reward = -112.45, steps = 22 08:28:34 [INFO] train episode 12818: reward = -138.35, steps = 30 08:28:37 [INFO] train episode 12819: reward = -119.31, steps = 25 08:28:39 [INFO] train episode 12820: reward = -122.22, steps = 22 08:28:43 [INFO] train episode 12821: reward = -152.32, steps = 56 08:28:46 [INFO] train episode 12822: reward = -112.11, steps = 29 08:28:48 [INFO] train episode 12823: reward = -136.13, steps = 21 08:28:51 [INFO] train episode 12824: reward = -117.56, steps = 34 08:28:53 [INFO] train episode 12825: reward = -145.87, steps = 22 08:28:54 [INFO] train episode 12826: reward = -112.90, steps = 19 08:28:59 [INFO] train episode 12827: reward = -161.79, steps = 54 08:29:02 [INFO] train episode 12828: reward = -133.81, steps = 40 08:29:08 [INFO] train episode 12829: reward = -101.45, steps = 51 08:29:11 [INFO] train episode 12830: reward = -117.02, steps = 39 08:29:14 [INFO] train episode 12831: reward = -135.29, steps = 31 08:29:17 [INFO] train episode 12832: reward = -115.50, steps = 33 08:29:19 [INFO] train episode 12833: reward = -115.47, steps = 26 08:29:22 [INFO] train episode 12834: reward = -122.07, steps = 24 08:29:24 [INFO] train episode 12835: reward = -174.70, steps = 34 08:29:27 [INFO] train episode 12836: reward = -116.85, steps = 30 08:29:29 [INFO] train episode 12837: reward = -130.02, steps = 26 08:29:32 [INFO] train episode 12838: reward = -117.91, steps = 38 08:29:35 [INFO] train episode 12839: reward = -108.10, steps = 28 08:29:37 [INFO] train episode 12840: reward = -92.50, steps = 22 08:29:40 [INFO] train episode 12841: reward = -109.03, steps = 33 08:29:42 [INFO] train episode 12842: reward = -117.40, steps = 30 08:29:44 [INFO] train episode 12843: reward = -116.15, steps = 21 08:29:46 [INFO] train episode 12844: reward = -96.43, steps = 22 08:29:49 [INFO] train episode 12845: reward = -120.68, steps = 42 08:29:53 [INFO] train episode 12846: reward = -216.75, steps = 38 08:29:55 [INFO] train episode 12847: reward = -150.86, steps = 21 08:29:57 [INFO] train episode 12848: reward = -155.39, steps = 24 08:29:59 [INFO] train episode 12849: reward = -102.19, steps = 25 08:30:02 [INFO] train episode 12850: reward = -103.90, steps = 31 08:30:03 [INFO] train episode 12851: reward = -116.23, steps = 21 08:30:06 [INFO] train episode 12852: reward = -182.85, steps = 24 08:30:08 [INFO] train episode 12853: reward = -112.58, steps = 27 08:30:12 [INFO] train episode 12854: reward = -92.72, steps = 37 08:30:15 [INFO] train episode 12855: reward = -123.80, steps = 32 08:30:18 [INFO] train episode 12856: reward = -110.37, steps = 40 08:30:21 [INFO] train episode 12857: reward = -233.01, steps = 32 08:30:23 [INFO] train episode 12858: reward = -129.89, steps = 21 08:30:26 [INFO] train episode 12859: reward = -99.03, steps = 38 08:30:28 [INFO] train episode 12860: reward = -125.94, steps = 25 08:30:30 [INFO] train episode 12861: reward = -121.85, steps = 25 08:30:34 [INFO] train episode 12862: reward = -152.74, steps = 38 08:30:36 [INFO] train episode 12863: reward = -109.65, steps = 31 08:30:38 [INFO] train episode 12864: reward = -135.13, steps = 24 08:30:41 [INFO] train episode 12865: reward = -124.50, steps = 31 08:30:44 [INFO] train episode 12866: reward = -147.31, steps = 26 08:30:45 [INFO] train episode 12867: reward = -130.44, steps = 23 08:30:49 [INFO] train episode 12868: reward = -125.91, steps = 42 08:30:53 [INFO] train episode 12869: reward = -226.63, steps = 54 08:30:56 [INFO] train episode 12870: reward = -115.77, steps = 25 08:30:59 [INFO] train episode 12871: reward = -143.29, steps = 36 08:31:02 [INFO] train episode 12872: reward = -184.76, steps = 32 08:31:06 [INFO] train episode 12873: reward = -109.29, steps = 46 08:31:08 [INFO] train episode 12874: reward = -104.53, steps = 30 08:31:12 [INFO] train episode 12875: reward = -91.52, steps = 39 08:31:15 [INFO] train episode 12876: reward = -132.84, steps = 36 08:31:17 [INFO] train episode 12877: reward = -139.82, steps = 22 08:31:21 [INFO] train episode 12878: reward = -137.36, steps = 52 08:31:23 [INFO] train episode 12879: reward = -104.74, steps = 24 08:31:25 [INFO] train episode 12880: reward = -111.15, steps = 25 08:31:28 [INFO] train episode 12881: reward = -135.55, steps = 26 08:31:31 [INFO] train episode 12882: reward = -147.83, steps = 31 08:31:33 [INFO] train episode 12883: reward = -119.65, steps = 32 08:31:37 [INFO] train episode 12884: reward = -106.40, steps = 42 08:31:39 [INFO] train episode 12885: reward = -122.13, steps = 23 08:31:41 [INFO] train episode 12886: reward = -136.19, steps = 22 08:31:43 [INFO] train episode 12887: reward = -122.37, steps = 21 08:31:45 [INFO] train episode 12888: reward = -161.61, steps = 22 08:31:47 [INFO] train episode 12889: reward = -129.49, steps = 25 08:31:49 [INFO] train episode 12890: reward = -104.27, steps = 25 08:31:51 [INFO] train episode 12891: reward = -106.58, steps = 23 08:31:54 [INFO] train episode 12892: reward = -148.47, steps = 24 08:31:57 [INFO] train episode 12893: reward = -130.50, steps = 38 08:31:59 [INFO] train episode 12894: reward = -184.98, steps = 23 08:32:01 [INFO] train episode 12895: reward = -103.87, steps = 21 08:32:03 [INFO] train episode 12896: reward = -119.18, steps = 24 08:32:05 [INFO] train episode 12897: reward = -107.51, steps = 29 08:32:08 [INFO] train episode 12898: reward = -106.13, steps = 29 08:32:10 [INFO] train episode 12899: reward = -95.50, steps = 29 08:32:13 [INFO] train episode 12900: reward = -106.04, steps = 34 08:32:16 [INFO] train episode 12901: reward = -121.60, steps = 27 08:32:19 [INFO] train episode 12902: reward = -133.90, steps = 37 08:32:22 [INFO] train episode 12903: reward = -109.99, steps = 35 08:32:24 [INFO] train episode 12904: reward = -126.94, steps = 29 08:32:26 [INFO] train episode 12905: reward = -178.13, steps = 24 08:32:29 [INFO] train episode 12906: reward = -114.21, steps = 27 08:32:31 [INFO] train episode 12907: reward = -111.59, steps = 30 08:32:34 [INFO] train episode 12908: reward = -128.09, steps = 27 08:32:37 [INFO] train episode 12909: reward = -112.68, steps = 35 08:32:39 [INFO] train episode 12910: reward = -245.70, steps = 23 08:32:41 [INFO] train episode 12911: reward = -141.29, steps = 32 08:32:44 [INFO] train episode 12912: reward = -84.97, steps = 31 08:32:47 [INFO] train episode 12913: reward = -116.51, steps = 26 08:32:50 [INFO] train episode 12914: reward = -117.94, steps = 44 08:32:53 [INFO] train episode 12915: reward = -114.93, steps = 27 08:32:55 [INFO] train episode 12916: reward = -99.33, steps = 24 08:32:57 [INFO] train episode 12917: reward = -109.94, steps = 33 08:33:00 [INFO] train episode 12918: reward = -94.61, steps = 27 08:33:03 [INFO] train episode 12919: reward = -102.64, steps = 29 08:33:05 [INFO] train episode 12920: reward = -107.41, steps = 25 08:33:08 [INFO] train episode 12921: reward = -102.63, steps = 25 08:33:10 [INFO] train episode 12922: reward = -140.83, steps = 24 08:33:13 [INFO] train episode 12923: reward = -152.67, steps = 45 08:33:16 [INFO] train episode 12924: reward = -123.23, steps = 31 08:33:19 [INFO] train episode 12925: reward = -140.03, steps = 35 08:33:21 [INFO] train episode 12926: reward = -103.63, steps = 26 08:33:23 [INFO] train episode 12927: reward = -120.39, steps = 22 08:33:27 [INFO] train episode 12928: reward = -134.44, steps = 44 08:33:29 [INFO] train episode 12929: reward = -130.41, steps = 21 08:33:33 [INFO] train episode 12930: reward = -141.26, steps = 45 08:33:35 [INFO] train episode 12931: reward = -118.38, steps = 23 08:33:37 [INFO] train episode 12932: reward = -181.06, steps = 30 08:33:40 [INFO] train episode 12933: reward = -143.72, steps = 27 08:33:41 [INFO] train episode 12934: reward = -122.68, steps = 22 08:33:44 [INFO] train episode 12935: reward = -131.32, steps = 32 08:33:47 [INFO] train episode 12936: reward = -180.89, steps = 36 08:33:49 [INFO] train episode 12937: reward = -100.81, steps = 21 08:33:51 [INFO] train episode 12938: reward = -131.48, steps = 22 08:33:54 [INFO] train episode 12939: reward = -122.61, steps = 34 08:33:56 [INFO] train episode 12940: reward = -102.25, steps = 26 08:33:58 [INFO] train episode 12941: reward = -153.12, steps = 24 08:34:01 [INFO] train episode 12942: reward = -155.56, steps = 26 08:34:04 [INFO] train episode 12943: reward = -128.85, steps = 35 08:34:06 [INFO] train episode 12944: reward = -135.03, steps = 26 08:34:08 [INFO] train episode 12945: reward = -112.45, steps = 25 08:34:11 [INFO] train episode 12946: reward = -136.09, steps = 31 08:34:13 [INFO] train episode 12947: reward = -145.71, steps = 25 08:34:15 [INFO] train episode 12948: reward = -123.78, steps = 23 08:34:17 [INFO] train episode 12949: reward = -106.47, steps = 26 08:34:19 [INFO] train episode 12950: reward = -99.36, steps = 21 08:34:23 [INFO] train episode 12951: reward = -124.72, steps = 43 08:34:26 [INFO] train episode 12952: reward = -92.14, steps = 35 08:34:28 [INFO] train episode 12953: reward = -109.09, steps = 19 08:34:30 [INFO] train episode 12954: reward = -143.86, steps = 25 08:34:31 [INFO] train episode 12955: reward = -99.92, steps = 21 08:34:34 [INFO] train episode 12956: reward = -205.42, steps = 24 08:34:37 [INFO] train episode 12957: reward = -121.95, steps = 35 08:34:39 [INFO] train episode 12958: reward = -125.23, steps = 23 08:34:41 [INFO] train episode 12959: reward = -116.20, steps = 25 08:34:43 [INFO] train episode 12960: reward = -108.56, steps = 22 08:34:45 [INFO] train episode 12961: reward = -134.23, steps = 21 08:34:47 [INFO] train episode 12962: reward = -128.76, steps = 24 08:34:49 [INFO] train episode 12963: reward = -145.73, steps = 25 08:34:51 [INFO] train episode 12964: reward = -140.21, steps = 23 08:34:53 [INFO] train episode 12965: reward = -164.40, steps = 23 08:34:55 [INFO] train episode 12966: reward = -163.09, steps = 26 08:34:58 [INFO] train episode 12967: reward = -107.60, steps = 24 08:35:00 [INFO] train episode 12968: reward = -150.29, steps = 25 08:35:03 [INFO] train episode 12969: reward = -127.84, steps = 38 08:35:05 [INFO] train episode 12970: reward = -93.06, steps = 30 08:35:08 [INFO] train episode 12971: reward = -199.94, steps = 23 08:35:10 [INFO] train episode 12972: reward = -105.47, steps = 27 08:35:12 [INFO] train episode 12973: reward = -173.02, steps = 23 08:35:14 [INFO] train episode 12974: reward = -117.13, steps = 29 08:35:17 [INFO] train episode 12975: reward = -101.06, steps = 25 08:35:19 [INFO] train episode 12976: reward = -119.31, steps = 24 08:35:21 [INFO] train episode 12977: reward = -137.15, steps = 21 08:35:23 [INFO] train episode 12978: reward = -118.57, steps = 29 08:35:26 [INFO] train episode 12979: reward = -161.11, steps = 27 08:35:29 [INFO] train episode 12980: reward = -141.91, steps = 40 08:35:31 [INFO] train episode 12981: reward = -112.76, steps = 28 08:35:33 [INFO] train episode 12982: reward = -130.40, steps = 24 08:35:36 [INFO] train episode 12983: reward = -129.16, steps = 28 08:35:38 [INFO] train episode 12984: reward = -95.60, steps = 22 08:35:41 [INFO] train episode 12985: reward = -115.99, steps = 30 08:35:43 [INFO] train episode 12986: reward = -141.87, steps = 23 08:35:45 [INFO] train episode 12987: reward = -108.73, steps = 32 08:35:49 [INFO] train episode 12988: reward = -152.14, steps = 42 08:35:52 [INFO] train episode 12989: reward = -153.69, steps = 25 08:35:54 [INFO] train episode 12990: reward = -135.08, steps = 25 08:35:56 [INFO] train episode 12991: reward = -165.48, steps = 23 08:35:58 [INFO] train episode 12992: reward = -144.88, steps = 24 08:36:02 [INFO] train episode 12993: reward = -155.47, steps = 43 08:36:04 [INFO] train episode 12994: reward = -121.07, steps = 25 08:36:08 [INFO] train episode 12995: reward = -128.46, steps = 55 08:36:11 [INFO] train episode 12996: reward = -117.07, steps = 30 08:36:15 [INFO] train episode 12997: reward = -125.90, steps = 40 08:36:17 [INFO] train episode 12998: reward = -173.12, steps = 23 08:36:20 [INFO] train episode 12999: reward = -101.10, steps = 33 08:36:21 [INFO] train episode 13000: reward = -114.05, steps = 21 08:36:23 [INFO] train episode 13001: reward = -102.09, steps = 23 08:36:25 [INFO] train episode 13002: reward = -147.32, steps = 25 08:36:28 [INFO] train episode 13003: reward = -113.66, steps = 27 08:36:31 [INFO] train episode 13004: reward = -144.41, steps = 34 08:36:35 [INFO] train episode 13005: reward = -185.54, steps = 49 08:36:37 [INFO] train episode 13006: reward = -157.32, steps = 26 08:36:39 [INFO] train episode 13007: reward = -115.37, steps = 24 08:36:42 [INFO] train episode 13008: reward = -119.30, steps = 27 08:36:45 [INFO] train episode 13009: reward = -122.54, steps = 37 08:36:47 [INFO] train episode 13010: reward = -145.27, steps = 27 08:36:49 [INFO] train episode 13011: reward = -172.93, steps = 24 08:36:52 [INFO] train episode 13012: reward = -100.47, steps = 33 08:36:56 [INFO] train episode 13013: reward = -150.94, steps = 40 08:36:59 [INFO] train episode 13014: reward = -141.79, steps = 37 08:37:01 [INFO] train episode 13015: reward = -131.49, steps = 25 08:37:04 [INFO] train episode 13016: reward = -138.18, steps = 29 08:37:06 [INFO] train episode 13017: reward = -170.00, steps = 32 08:37:08 [INFO] train episode 13018: reward = -169.78, steps = 22 08:37:10 [INFO] train episode 13019: reward = -108.69, steps = 24 08:37:13 [INFO] train episode 13020: reward = -98.95, steps = 27 08:37:14 [INFO] train episode 13021: reward = -126.42, steps = 22 08:37:17 [INFO] train episode 13022: reward = -135.66, steps = 26 08:37:20 [INFO] train episode 13023: reward = -99.54, steps = 34 08:37:22 [INFO] train episode 13024: reward = -130.03, steps = 27 08:37:25 [INFO] train episode 13025: reward = -132.31, steps = 27 08:37:27 [INFO] train episode 13026: reward = -123.34, steps = 24 08:37:29 [INFO] train episode 13027: reward = -110.70, steps = 24 08:37:31 [INFO] train episode 13028: reward = -117.08, steps = 22 08:37:34 [INFO] train episode 13029: reward = -86.21, steps = 35 08:37:36 [INFO] train episode 13030: reward = -135.17, steps = 22 08:37:38 [INFO] train episode 13031: reward = -94.00, steps = 27 08:37:40 [INFO] train episode 13032: reward = -141.34, steps = 24 08:37:42 [INFO] train episode 13033: reward = -132.13, steps = 25 08:37:45 [INFO] train episode 13034: reward = -151.18, steps = 28 08:37:47 [INFO] train episode 13035: reward = -110.94, steps = 21 08:37:49 [INFO] train episode 13036: reward = -153.01, steps = 24 08:37:51 [INFO] train episode 13037: reward = -159.97, steps = 24 08:37:55 [INFO] train episode 13038: reward = -145.23, steps = 41 08:37:56 [INFO] train episode 13039: reward = -192.28, steps = 21 08:37:59 [INFO] train episode 13040: reward = -90.27, steps = 26 08:38:01 [INFO] train episode 13041: reward = -148.75, steps = 29 08:38:03 [INFO] train episode 13042: reward = -186.27, steps = 22 08:38:06 [INFO] train episode 13043: reward = -144.88, steps = 36 08:38:09 [INFO] train episode 13044: reward = -94.20, steps = 31 08:38:11 [INFO] train episode 13045: reward = -144.87, steps = 23 08:38:14 [INFO] train episode 13046: reward = -115.07, steps = 34 08:38:16 [INFO] train episode 13047: reward = -133.15, steps = 23 08:38:18 [INFO] train episode 13048: reward = -151.02, steps = 23 08:38:20 [INFO] train episode 13049: reward = -212.72, steps = 24 08:38:22 [INFO] train episode 13050: reward = -118.51, steps = 23 08:38:26 [INFO] train episode 13051: reward = -205.54, steps = 46 08:38:30 [INFO] train episode 13052: reward = -152.44, steps = 43 08:38:33 [INFO] train episode 13053: reward = -136.83, steps = 45 08:38:37 [INFO] train episode 13054: reward = -100.76, steps = 34 08:38:39 [INFO] train episode 13055: reward = -162.81, steps = 33 08:38:42 [INFO] train episode 13056: reward = -126.60, steps = 25 08:38:44 [INFO] train episode 13057: reward = -192.72, steps = 24 08:38:47 [INFO] train episode 13058: reward = -169.69, steps = 28 08:38:49 [INFO] train episode 13059: reward = -162.44, steps = 28 08:38:51 [INFO] train episode 13060: reward = -138.12, steps = 21 08:38:55 [INFO] train episode 13061: reward = -159.05, steps = 45 08:38:58 [INFO] train episode 13062: reward = -138.01, steps = 28 08:38:59 [INFO] train episode 13063: reward = -141.95, steps = 23 08:39:01 [INFO] train episode 13064: reward = -123.03, steps = 21 08:39:03 [INFO] train episode 13065: reward = -142.15, steps = 26 08:39:05 [INFO] train episode 13066: reward = -135.16, steps = 22 08:39:08 [INFO] train episode 13067: reward = -118.53, steps = 31 08:39:12 [INFO] train episode 13068: reward = -129.87, steps = 39 08:39:14 [INFO] train episode 13069: reward = -129.04, steps = 24 08:39:16 [INFO] train episode 13070: reward = -133.81, steps = 24 08:39:18 [INFO] train episode 13071: reward = -132.16, steps = 24 08:39:20 [INFO] train episode 13072: reward = -91.64, steps = 26 08:39:23 [INFO] train episode 13073: reward = -159.41, steps = 27 08:39:25 [INFO] train episode 13074: reward = -135.41, steps = 24 08:39:27 [INFO] train episode 13075: reward = -139.27, steps = 23 08:39:28 [INFO] train episode 13076: reward = -128.76, steps = 20 08:39:31 [INFO] train episode 13077: reward = -133.63, steps = 29 08:39:34 [INFO] train episode 13078: reward = -118.74, steps = 39 08:39:37 [INFO] train episode 13079: reward = -128.83, steps = 33 08:39:41 [INFO] train episode 13080: reward = -118.53, steps = 38 08:39:43 [INFO] train episode 13081: reward = -102.85, steps = 29 08:39:45 [INFO] train episode 13082: reward = -183.07, steps = 23 08:39:48 [INFO] train episode 13083: reward = -100.22, steps = 37 08:39:51 [INFO] train episode 13084: reward = -131.41, steps = 30 08:39:54 [INFO] train episode 13085: reward = -91.63, steps = 31 08:39:55 [INFO] train episode 13086: reward = -99.93, steps = 21 08:39:59 [INFO] train episode 13087: reward = -151.81, steps = 40 08:40:02 [INFO] train episode 13088: reward = -211.09, steps = 33 08:40:04 [INFO] train episode 13089: reward = -141.36, steps = 24 08:40:06 [INFO] train episode 13090: reward = -201.49, steps = 25 08:40:08 [INFO] train episode 13091: reward = -124.09, steps = 29 08:40:11 [INFO] train episode 13092: reward = -133.01, steps = 23 08:40:12 [INFO] train episode 13093: reward = -143.83, steps = 20 08:40:15 [INFO] train episode 13094: reward = -90.55, steps = 26 08:40:17 [INFO] train episode 13095: reward = -138.15, steps = 24 08:40:19 [INFO] train episode 13096: reward = -154.95, steps = 24 08:40:21 [INFO] train episode 13097: reward = -121.58, steps = 25 08:40:22 [INFO] train episode 13098: reward = -100.49, steps = 21 08:40:26 [INFO] train episode 13099: reward = -162.87, steps = 32 08:40:27 [INFO] train episode 13100: reward = -123.67, steps = 22 08:40:30 [INFO] train episode 13101: reward = -137.60, steps = 27 08:40:32 [INFO] train episode 13102: reward = -108.13, steps = 27 08:40:34 [INFO] train episode 13103: reward = -140.10, steps = 27 08:40:38 [INFO] train episode 13104: reward = -102.07, steps = 43 08:40:40 [INFO] train episode 13105: reward = -112.37, steps = 22 08:40:42 [INFO] train episode 13106: reward = -105.04, steps = 23 08:40:44 [INFO] train episode 13107: reward = -138.41, steps = 23 08:40:47 [INFO] train episode 13108: reward = -131.29, steps = 33 08:40:49 [INFO] train episode 13109: reward = -94.40, steps = 24 08:40:51 [INFO] train episode 13110: reward = -126.40, steps = 25 08:40:53 [INFO] train episode 13111: reward = -100.03, steps = 26 08:40:56 [INFO] train episode 13112: reward = -128.79, steps = 30 08:40:58 [INFO] train episode 13113: reward = -170.97, steps = 25 08:41:01 [INFO] train episode 13114: reward = -115.50, steps = 26 08:41:02 [INFO] train episode 13115: reward = -136.77, steps = 22 08:41:06 [INFO] train episode 13116: reward = -125.30, steps = 37 08:41:07 [INFO] train episode 13117: reward = -164.21, steps = 21 08:41:09 [INFO] train episode 13118: reward = -114.36, steps = 23 08:41:13 [INFO] train episode 13119: reward = -135.14, steps = 35 08:41:15 [INFO] train episode 13120: reward = -135.00, steps = 26 08:41:17 [INFO] train episode 13121: reward = -104.52, steps = 23 08:41:21 [INFO] train episode 13122: reward = -131.04, steps = 43 08:41:23 [INFO] train episode 13123: reward = -164.60, steps = 23 08:41:25 [INFO] train episode 13124: reward = -122.11, steps = 24 08:41:27 [INFO] train episode 13125: reward = -220.38, steps = 25 08:41:30 [INFO] train episode 13126: reward = -107.07, steps = 38 08:41:33 [INFO] train episode 13127: reward = -115.99, steps = 28 08:41:36 [INFO] train episode 13128: reward = -122.64, steps = 26 08:41:38 [INFO] train episode 13129: reward = -118.98, steps = 26 08:41:40 [INFO] train episode 13130: reward = -119.99, steps = 24 08:41:42 [INFO] train episode 13131: reward = -141.46, steps = 29 08:41:45 [INFO] train episode 13132: reward = -100.71, steps = 23 08:41:47 [INFO] train episode 13133: reward = -126.66, steps = 23 08:41:49 [INFO] train episode 13134: reward = -110.88, steps = 23 08:41:51 [INFO] train episode 13135: reward = -120.09, steps = 25 08:41:53 [INFO] train episode 13136: reward = -115.66, steps = 24 08:41:55 [INFO] train episode 13137: reward = -103.71, steps = 21 08:41:57 [INFO] train episode 13138: reward = -124.60, steps = 24 08:41:59 [INFO] train episode 13139: reward = -149.05, steps = 26 08:42:03 [INFO] train episode 13140: reward = -129.20, steps = 47 08:42:05 [INFO] train episode 13141: reward = -109.32, steps = 20 08:42:09 [INFO] train episode 13142: reward = -144.92, steps = 49 08:42:11 [INFO] train episode 13143: reward = -112.14, steps = 27 08:42:14 [INFO] train episode 13144: reward = -130.46, steps = 27 08:42:19 [INFO] train episode 13145: reward = -143.82, steps = 58 08:42:21 [INFO] train episode 13146: reward = -151.13, steps = 29 08:42:23 [INFO] train episode 13147: reward = -183.42, steps = 23 08:42:26 [INFO] train episode 13148: reward = -133.12, steps = 28 08:42:28 [INFO] train episode 13149: reward = -151.32, steps = 24 08:42:30 [INFO] train episode 13150: reward = -113.59, steps = 24 08:42:34 [INFO] train episode 13151: reward = -226.59, steps = 45 08:42:36 [INFO] train episode 13152: reward = -141.25, steps = 26 08:42:38 [INFO] train episode 13153: reward = -131.80, steps = 24 08:42:40 [INFO] train episode 13154: reward = -138.41, steps = 20 08:42:42 [INFO] train episode 13155: reward = -127.54, steps = 24 08:42:44 [INFO] train episode 13156: reward = -105.01, steps = 23 08:42:46 [INFO] train episode 13157: reward = -142.33, steps = 22 08:42:48 [INFO] train episode 13158: reward = -138.32, steps = 24 08:42:50 [INFO] train episode 13159: reward = -159.24, steps = 24 08:42:54 [INFO] train episode 13160: reward = -140.31, steps = 41 08:42:56 [INFO] train episode 13161: reward = -147.00, steps = 23 08:42:58 [INFO] train episode 13162: reward = -199.69, steps = 29 08:43:00 [INFO] train episode 13163: reward = -124.74, steps = 25 08:43:03 [INFO] train episode 13164: reward = -116.32, steps = 22 08:43:05 [INFO] train episode 13165: reward = -148.00, steps = 29 08:43:08 [INFO] train episode 13166: reward = -94.44, steps = 35 08:43:10 [INFO] train episode 13167: reward = -112.41, steps = 22 08:43:13 [INFO] train episode 13168: reward = -142.36, steps = 28 08:43:14 [INFO] train episode 13169: reward = -121.31, steps = 21 08:43:19 [INFO] train episode 13170: reward = -96.80, steps = 47 08:43:21 [INFO] train episode 13171: reward = -171.25, steps = 24 08:43:22 [INFO] train episode 13172: reward = -103.30, steps = 20 08:43:24 [INFO] train episode 13173: reward = -126.49, steps = 24 08:43:27 [INFO] train episode 13174: reward = -130.46, steps = 25 08:43:32 [INFO] train episode 13175: reward = -126.12, steps = 62 08:43:34 [INFO] train episode 13176: reward = -156.87, steps = 26 08:43:36 [INFO] train episode 13177: reward = -146.89, steps = 23 08:43:39 [INFO] train episode 13178: reward = -125.61, steps = 38 08:43:41 [INFO] train episode 13179: reward = -119.33, steps = 24 08:43:44 [INFO] train episode 13180: reward = -141.79, steps = 29 08:43:47 [INFO] train episode 13181: reward = -126.19, steps = 39 08:43:50 [INFO] train episode 13182: reward = -148.67, steps = 29 08:43:53 [INFO] train episode 13183: reward = -139.46, steps = 33 08:43:55 [INFO] train episode 13184: reward = -175.39, steps = 22 08:43:57 [INFO] train episode 13185: reward = -127.36, steps = 25 08:43:59 [INFO] train episode 13186: reward = -151.42, steps = 23 08:44:02 [INFO] train episode 13187: reward = -116.56, steps = 38 08:44:04 [INFO] train episode 13188: reward = -173.00, steps = 24 08:44:06 [INFO] train episode 13189: reward = -98.21, steps = 21 08:44:08 [INFO] train episode 13190: reward = -129.31, steps = 23 08:44:11 [INFO] train episode 13191: reward = -164.88, steps = 33 08:44:14 [INFO] train episode 13192: reward = -146.92, steps = 36 08:44:17 [INFO] train episode 13193: reward = -143.58, steps = 33 08:44:19 [INFO] train episode 13194: reward = -143.45, steps = 28 08:44:23 [INFO] train episode 13195: reward = -106.15, steps = 27 08:44:26 [INFO] train episode 13196: reward = -163.51, steps = 38 08:44:28 [INFO] train episode 13197: reward = -127.22, steps = 28 08:44:31 [INFO] train episode 13198: reward = -143.66, steps = 34 08:44:33 [INFO] train episode 13199: reward = -170.89, steps = 25 08:44:36 [INFO] train episode 13200: reward = -138.78, steps = 30 08:44:39 [INFO] train episode 13201: reward = -141.22, steps = 27 08:44:42 [INFO] train episode 13202: reward = -155.87, steps = 41 08:44:44 [INFO] train episode 13203: reward = -145.90, steps = 27 08:44:46 [INFO] train episode 13204: reward = -145.55, steps = 19 08:44:48 [INFO] train episode 13205: reward = -135.30, steps = 24 08:44:50 [INFO] train episode 13206: reward = -106.63, steps = 27 08:44:53 [INFO] train episode 13207: reward = -164.96, steps = 35 08:44:57 [INFO] train episode 13208: reward = -134.91, steps = 44 08:45:00 [INFO] train episode 13209: reward = -113.15, steps = 33 08:45:02 [INFO] train episode 13210: reward = -154.04, steps = 27 08:45:04 [INFO] train episode 13211: reward = -104.32, steps = 26 08:45:07 [INFO] train episode 13212: reward = -109.41, steps = 31 08:45:10 [INFO] train episode 13213: reward = -122.43, steps = 27 08:45:13 [INFO] train episode 13214: reward = -114.94, steps = 40 08:45:15 [INFO] train episode 13215: reward = -122.77, steps = 20 08:45:17 [INFO] train episode 13216: reward = -135.45, steps = 21 08:45:20 [INFO] train episode 13217: reward = -133.24, steps = 39 08:45:22 [INFO] train episode 13218: reward = -103.93, steps = 31 08:45:25 [INFO] train episode 13219: reward = -141.81, steps = 26 08:45:29 [INFO] train episode 13220: reward = -131.69, steps = 47 08:45:31 [INFO] train episode 13221: reward = -129.15, steps = 24 08:45:33 [INFO] train episode 13222: reward = -125.04, steps = 27 08:45:36 [INFO] train episode 13223: reward = -128.81, steps = 29 08:45:38 [INFO] train episode 13224: reward = -111.41, steps = 28 08:45:41 [INFO] train episode 13225: reward = -129.42, steps = 33 08:45:43 [INFO] train episode 13226: reward = -130.30, steps = 25 08:45:45 [INFO] train episode 13227: reward = -148.16, steps = 21 08:45:47 [INFO] train episode 13228: reward = -138.49, steps = 25 08:45:50 [INFO] train episode 13229: reward = -136.53, steps = 27 08:45:51 [INFO] train episode 13230: reward = -114.42, steps = 21 08:45:53 [INFO] train episode 13231: reward = -137.91, steps = 24 08:45:56 [INFO] train episode 13232: reward = -132.74, steps = 24 08:45:58 [INFO] train episode 13233: reward = -132.32, steps = 27 08:46:01 [INFO] train episode 13234: reward = -97.74, steps = 39 08:46:03 [INFO] train episode 13235: reward = -133.30, steps = 22 08:46:05 [INFO] train episode 13236: reward = -116.21, steps = 25 08:46:07 [INFO] train episode 13237: reward = -109.40, steps = 17 08:46:10 [INFO] train episode 13238: reward = -180.93, steps = 35 08:46:12 [INFO] train episode 13239: reward = -120.54, steps = 22 08:46:15 [INFO] train episode 13240: reward = -134.40, steps = 30 08:46:16 [INFO] train episode 13241: reward = -130.09, steps = 20 08:46:18 [INFO] train episode 13242: reward = -110.57, steps = 21 08:46:20 [INFO] train episode 13243: reward = -112.23, steps = 26 08:46:23 [INFO] train episode 13244: reward = -124.18, steps = 27 08:46:25 [INFO] train episode 13245: reward = -115.26, steps = 29 08:46:28 [INFO] train episode 13246: reward = -111.41, steps = 25 08:46:30 [INFO] train episode 13247: reward = -102.96, steps = 27 08:46:34 [INFO] train episode 13248: reward = -153.92, steps = 44 08:46:37 [INFO] train episode 13249: reward = -179.12, steps = 44 08:46:40 [INFO] train episode 13250: reward = -112.38, steps = 28 08:46:43 [INFO] train episode 13251: reward = -205.28, steps = 29 08:46:46 [INFO] train episode 13252: reward = -127.53, steps = 35 08:46:48 [INFO] train episode 13253: reward = -115.34, steps = 23 08:46:50 [INFO] train episode 13254: reward = -146.07, steps = 24 08:46:53 [INFO] train episode 13255: reward = -141.22, steps = 40 08:46:55 [INFO] train episode 13256: reward = -140.67, steps = 22 08:46:59 [INFO] train episode 13257: reward = -138.50, steps = 38 08:47:01 [INFO] train episode 13258: reward = -140.64, steps = 22 08:47:03 [INFO] train episode 13259: reward = -145.66, steps = 22 08:47:04 [INFO] train episode 13260: reward = -130.11, steps = 21 08:47:07 [INFO] train episode 13261: reward = -122.99, steps = 30 08:47:10 [INFO] train episode 13262: reward = -131.66, steps = 37 08:47:13 [INFO] train episode 13263: reward = -125.34, steps = 30 08:47:17 [INFO] train episode 13264: reward = -148.53, steps = 38 08:47:19 [INFO] train episode 13265: reward = -140.39, steps = 28 08:47:22 [INFO] train episode 13266: reward = -137.73, steps = 26 08:47:26 [INFO] train episode 13267: reward = -160.35, steps = 51 08:47:28 [INFO] train episode 13268: reward = -122.44, steps = 29 08:47:31 [INFO] train episode 13269: reward = -129.94, steps = 23 08:47:35 [INFO] train episode 13270: reward = -174.03, steps = 50 08:47:37 [INFO] train episode 13271: reward = -121.91, steps = 24 08:47:39 [INFO] train episode 13272: reward = -135.55, steps = 27 08:47:42 [INFO] train episode 13273: reward = -122.31, steps = 35 08:47:45 [INFO] train episode 13274: reward = -105.44, steps = 32 08:47:48 [INFO] train episode 13275: reward = -108.84, steps = 33 08:47:50 [INFO] train episode 13276: reward = -115.56, steps = 27 08:47:52 [INFO] train episode 13277: reward = -127.47, steps = 22 08:47:54 [INFO] train episode 13278: reward = -124.37, steps = 25 08:47:56 [INFO] train episode 13279: reward = -106.93, steps = 21 08:48:00 [INFO] train episode 13280: reward = -123.70, steps = 52 08:48:03 [INFO] train episode 13281: reward = -124.38, steps = 27 08:48:06 [INFO] train episode 13282: reward = -189.75, steps = 37 08:48:08 [INFO] train episode 13283: reward = -95.82, steps = 28 08:48:10 [INFO] train episode 13284: reward = -191.98, steps = 23 08:48:13 [INFO] train episode 13285: reward = -155.75, steps = 28 08:48:15 [INFO] train episode 13286: reward = -78.92, steps = 20 08:48:18 [INFO] train episode 13287: reward = -122.85, steps = 36 08:48:20 [INFO] train episode 13288: reward = -129.27, steps = 26 08:48:22 [INFO] train episode 13289: reward = -123.08, steps = 24 08:48:24 [INFO] train episode 13290: reward = -95.84, steps = 23 08:48:26 [INFO] train episode 13291: reward = -97.93, steps = 21 08:48:28 [INFO] train episode 13292: reward = -103.29, steps = 24 08:48:31 [INFO] train episode 13293: reward = -173.32, steps = 31 08:48:33 [INFO] train episode 13294: reward = -106.78, steps = 26 08:48:35 [INFO] train episode 13295: reward = -116.95, steps = 21 08:48:37 [INFO] train episode 13296: reward = -105.40, steps = 25 08:48:40 [INFO] train episode 13297: reward = -107.16, steps = 34 08:48:43 [INFO] train episode 13298: reward = -120.79, steps = 33 08:48:46 [INFO] train episode 13299: reward = -187.79, steps = 37 08:48:48 [INFO] train episode 13300: reward = -97.94, steps = 24 08:48:51 [INFO] train episode 13301: reward = -108.52, steps = 26 08:48:52 [INFO] train episode 13302: reward = -124.04, steps = 19 08:48:55 [INFO] train episode 13303: reward = -112.81, steps = 29 08:48:57 [INFO] train episode 13304: reward = -108.55, steps = 23 08:49:00 [INFO] train episode 13305: reward = -129.36, steps = 33 08:49:02 [INFO] train episode 13306: reward = -93.90, steps = 25 08:49:03 [INFO] train episode 13307: reward = -109.91, steps = 21 08:49:06 [INFO] train episode 13308: reward = -94.61, steps = 19 08:49:08 [INFO] train episode 13309: reward = -101.33, steps = 30 08:49:10 [INFO] train episode 13310: reward = -127.27, steps = 23 08:49:12 [INFO] train episode 13311: reward = -106.58, steps = 21 08:49:14 [INFO] train episode 13312: reward = -127.49, steps = 23 08:49:16 [INFO] train episode 13313: reward = -97.15, steps = 29 08:49:19 [INFO] train episode 13314: reward = -132.67, steps = 32 08:49:21 [INFO] train episode 13315: reward = -122.25, steps = 26 08:49:23 [INFO] train episode 13316: reward = -158.83, steps = 23 08:49:26 [INFO] train episode 13317: reward = -138.87, steps = 30 08:49:28 [INFO] train episode 13318: reward = -107.68, steps = 31 08:49:30 [INFO] train episode 13319: reward = -102.91, steps = 24 08:49:34 [INFO] train episode 13320: reward = -139.08, steps = 38 08:49:37 [INFO] train episode 13321: reward = -108.24, steps = 31 08:49:38 [INFO] train episode 13322: reward = -120.07, steps = 19 08:49:40 [INFO] train episode 13323: reward = -112.44, steps = 22 08:49:43 [INFO] train episode 13324: reward = -137.61, steps = 32 08:49:46 [INFO] train episode 13325: reward = -99.84, steps = 42 08:49:48 [INFO] train episode 13326: reward = -112.92, steps = 21 08:49:50 [INFO] train episode 13327: reward = -113.29, steps = 26 08:49:53 [INFO] train episode 13328: reward = -150.76, steps = 32 08:49:56 [INFO] train episode 13329: reward = -98.31, steps = 31 08:50:01 [INFO] train episode 13330: reward = -136.01, steps = 55 08:50:03 [INFO] train episode 13331: reward = -108.48, steps = 20 08:50:06 [INFO] train episode 13332: reward = -116.81, steps = 31 08:50:10 [INFO] train episode 13333: reward = -122.99, steps = 52 08:50:14 [INFO] train episode 13334: reward = -123.10, steps = 40 08:50:16 [INFO] train episode 13335: reward = -124.63, steps = 24 08:50:18 [INFO] train episode 13336: reward = -75.13, steps = 32 08:50:21 [INFO] train episode 13337: reward = -89.50, steps = 30 08:50:23 [INFO] train episode 13338: reward = -123.48, steps = 25 08:50:25 [INFO] train episode 13339: reward = -109.85, steps = 21 08:50:27 [INFO] train episode 13340: reward = -105.62, steps = 23 08:50:29 [INFO] train episode 13341: reward = -134.96, steps = 22 08:50:31 [INFO] train episode 13342: reward = -104.73, steps = 26 08:50:36 [INFO] train episode 13343: reward = -184.92, steps = 57 08:50:39 [INFO] train episode 13344: reward = -112.50, steps = 26 08:50:41 [INFO] train episode 13345: reward = -84.60, steps = 26 08:50:44 [INFO] train episode 13346: reward = -98.54, steps = 36 08:50:47 [INFO] train episode 13347: reward = -135.67, steps = 36 08:50:49 [INFO] train episode 13348: reward = -105.83, steps = 21 08:50:52 [INFO] train episode 13349: reward = -103.45, steps = 39 08:50:54 [INFO] train episode 13350: reward = -121.70, steps = 23 08:50:57 [INFO] train episode 13351: reward = -100.74, steps = 23 08:51:00 [INFO] train episode 13352: reward = -113.47, steps = 44 08:51:03 [INFO] train episode 13353: reward = -87.08, steps = 35 08:51:06 [INFO] train episode 13354: reward = -166.01, steps = 31 08:51:09 [INFO] train episode 13355: reward = -140.45, steps = 34 08:51:12 [INFO] train episode 13356: reward = -192.01, steps = 35 08:51:14 [INFO] train episode 13357: reward = -114.49, steps = 21 08:51:16 [INFO] train episode 13358: reward = -103.77, steps = 26 08:51:19 [INFO] train episode 13359: reward = -93.58, steps = 28 08:51:22 [INFO] train episode 13360: reward = -166.93, steps = 42 08:51:25 [INFO] train episode 13361: reward = -114.32, steps = 30 08:51:30 [INFO] train episode 13362: reward = -124.43, steps = 57 08:51:34 [INFO] train episode 13363: reward = -190.76, steps = 48 08:51:36 [INFO] train episode 13364: reward = -123.23, steps = 24 08:51:39 [INFO] train episode 13365: reward = -141.93, steps = 32 08:51:41 [INFO] train episode 13366: reward = -132.62, steps = 34 08:51:45 [INFO] train episode 13367: reward = -114.08, steps = 33 08:51:47 [INFO] train episode 13368: reward = -106.90, steps = 26 08:51:49 [INFO] train episode 13369: reward = -103.66, steps = 31 08:51:52 [INFO] train episode 13370: reward = -114.58, steps = 29 08:51:54 [INFO] train episode 13371: reward = -133.77, steps = 24 08:51:56 [INFO] train episode 13372: reward = -97.60, steps = 21 08:52:00 [INFO] train episode 13373: reward = -87.99, steps = 46 08:52:03 [INFO] train episode 13374: reward = -122.27, steps = 26 08:52:05 [INFO] train episode 13375: reward = -82.71, steps = 32 08:52:08 [INFO] train episode 13376: reward = -105.51, steps = 29 08:52:10 [INFO] train episode 13377: reward = -124.51, steps = 32 08:52:13 [INFO] train episode 13378: reward = -123.52, steps = 36 08:52:16 [INFO] train episode 13379: reward = -175.80, steps = 29 08:52:18 [INFO] train episode 13380: reward = -133.65, steps = 24 08:52:20 [INFO] train episode 13381: reward = -91.85, steps = 26 08:52:22 [INFO] train episode 13382: reward = -129.85, steps = 21 08:52:26 [INFO] train episode 13383: reward = -93.30, steps = 40 08:52:28 [INFO] train episode 13384: reward = -90.08, steps = 23 08:52:32 [INFO] train episode 13385: reward = -104.15, steps = 45 08:52:36 [INFO] train episode 13386: reward = -132.40, steps = 49 08:52:38 [INFO] train episode 13387: reward = -108.91, steps = 26 08:52:42 [INFO] train episode 13388: reward = -145.66, steps = 51 08:52:45 [INFO] train episode 13389: reward = -105.21, steps = 26 08:52:48 [INFO] train episode 13390: reward = -124.11, steps = 33 08:52:53 [INFO] train episode 13391: reward = -116.96, steps = 56 08:52:56 [INFO] train episode 13392: reward = -106.31, steps = 36 08:52:59 [INFO] train episode 13393: reward = -108.58, steps = 24 08:53:01 [INFO] train episode 13394: reward = -155.44, steps = 22 08:53:04 [INFO] train episode 13395: reward = -148.34, steps = 29 08:53:06 [INFO] train episode 13396: reward = -128.42, steps = 28 08:53:09 [INFO] train episode 13397: reward = -104.92, steps = 29 08:53:12 [INFO] train episode 13398: reward = -129.39, steps = 38 08:53:14 [INFO] train episode 13399: reward = -113.19, steps = 23 08:53:16 [INFO] train episode 13400: reward = -102.28, steps = 25 08:53:19 [INFO] train episode 13401: reward = -85.44, steps = 33 08:53:23 [INFO] train episode 13402: reward = -109.41, steps = 37 08:53:25 [INFO] train episode 13403: reward = -122.52, steps = 31 08:53:27 [INFO] train episode 13404: reward = -111.64, steps = 19 08:53:30 [INFO] train episode 13405: reward = -101.34, steps = 45 08:53:32 [INFO] train episode 13406: reward = -113.61, steps = 22 08:53:37 [INFO] train episode 13407: reward = -103.34, steps = 51 08:53:40 [INFO] train episode 13408: reward = -85.99, steps = 37 08:53:42 [INFO] train episode 13409: reward = -121.25, steps = 20 08:53:45 [INFO] train episode 13410: reward = -172.02, steps = 40 08:53:49 [INFO] train episode 13411: reward = -130.40, steps = 39 08:53:52 [INFO] train episode 13412: reward = -127.65, steps = 38 08:53:54 [INFO] train episode 13413: reward = -121.88, steps = 19 08:53:56 [INFO] train episode 13414: reward = -92.72, steps = 27 08:53:58 [INFO] train episode 13415: reward = -134.79, steps = 25 08:54:00 [INFO] train episode 13416: reward = -110.19, steps = 23 08:54:03 [INFO] train episode 13417: reward = -92.69, steps = 39 08:54:06 [INFO] train episode 13418: reward = -109.13, steps = 25 08:54:08 [INFO] train episode 13419: reward = -115.46, steps = 28 08:54:10 [INFO] train episode 13420: reward = -109.85, steps = 21 08:54:12 [INFO] train episode 13421: reward = -121.54, steps = 23 08:54:14 [INFO] train episode 13422: reward = -126.88, steps = 23 08:54:20 [INFO] train episode 13423: reward = -139.05, steps = 68 08:54:22 [INFO] train episode 13424: reward = -110.48, steps = 23 08:54:24 [INFO] train episode 13425: reward = -95.10, steps = 28 08:54:27 [INFO] train episode 13426: reward = -94.27, steps = 27 08:54:30 [INFO] train episode 13427: reward = -116.33, steps = 36 08:54:32 [INFO] train episode 13428: reward = -133.38, steps = 25 08:54:37 [INFO] train episode 13429: reward = -109.96, steps = 56 08:54:39 [INFO] train episode 13430: reward = -129.17, steps = 28 08:54:41 [INFO] train episode 13431: reward = -122.09, steps = 17 08:54:44 [INFO] train episode 13432: reward = -119.68, steps = 39 08:54:46 [INFO] train episode 13433: reward = -123.20, steps = 24 08:54:48 [INFO] train episode 13434: reward = -206.20, steps = 25 08:54:51 [INFO] train episode 13435: reward = -105.89, steps = 36 08:54:53 [INFO] train episode 13436: reward = -153.62, steps = 23 08:54:57 [INFO] train episode 13437: reward = -121.57, steps = 35 08:54:58 [INFO] train episode 13438: reward = -120.55, steps = 18 08:55:02 [INFO] train episode 13439: reward = -122.52, steps = 49 08:55:05 [INFO] train episode 13440: reward = -103.84, steps = 27 08:55:07 [INFO] train episode 13441: reward = -180.76, steps = 29 08:55:09 [INFO] train episode 13442: reward = -112.82, steps = 25 08:55:12 [INFO] train episode 13443: reward = -96.39, steps = 35 08:55:14 [INFO] train episode 13444: reward = -121.96, steps = 21 08:55:17 [INFO] train episode 13445: reward = -166.40, steps = 32 08:55:19 [INFO] train episode 13446: reward = -95.81, steps = 27 08:55:23 [INFO] train episode 13447: reward = -126.37, steps = 38 08:55:26 [INFO] train episode 13448: reward = -112.39, steps = 41 08:55:29 [INFO] train episode 13449: reward = -116.55, steps = 26 08:55:31 [INFO] train episode 13450: reward = -134.99, steps = 24 08:55:33 [INFO] train episode 13451: reward = -144.98, steps = 27 08:55:36 [INFO] train episode 13452: reward = -90.79, steps = 32 08:55:38 [INFO] train episode 13453: reward = -83.43, steps = 24 08:55:42 [INFO] train episode 13454: reward = -103.15, steps = 45 08:55:45 [INFO] train episode 13455: reward = -136.71, steps = 26 08:55:47 [INFO] train episode 13456: reward = -78.57, steps = 29 08:55:50 [INFO] train episode 13457: reward = -137.77, steps = 37 08:55:53 [INFO] train episode 13458: reward = -102.72, steps = 31 08:55:55 [INFO] train episode 13459: reward = -109.03, steps = 26 08:56:00 [INFO] train episode 13460: reward = -138.02, steps = 50 08:56:02 [INFO] train episode 13461: reward = -75.68, steps = 27 08:56:04 [INFO] train episode 13462: reward = -76.23, steps = 32 08:56:07 [INFO] train episode 13463: reward = -106.27, steps = 29 08:56:09 [INFO] train episode 13464: reward = -144.35, steps = 22 08:56:13 [INFO] train episode 13465: reward = -114.81, steps = 42 08:56:15 [INFO] train episode 13466: reward = -100.43, steps = 26 08:56:17 [INFO] train episode 13467: reward = -108.67, steps = 24 08:56:19 [INFO] train episode 13468: reward = -108.67, steps = 24 08:56:21 [INFO] train episode 13469: reward = -85.01, steps = 27 08:56:23 [INFO] train episode 13470: reward = -87.20, steps = 25 08:56:26 [INFO] train episode 13471: reward = -113.30, steps = 29 08:56:29 [INFO] train episode 13472: reward = -114.35, steps = 26 08:56:32 [INFO] train episode 13473: reward = -168.16, steps = 36 08:56:34 [INFO] train episode 13474: reward = -94.15, steps = 24 08:56:37 [INFO] train episode 13475: reward = -129.67, steps = 41 08:56:40 [INFO] train episode 13476: reward = -135.23, steps = 39 08:56:43 [INFO] train episode 13477: reward = -131.19, steps = 33 08:56:47 [INFO] train episode 13478: reward = -114.45, steps = 35 08:56:49 [INFO] train episode 13479: reward = -96.38, steps = 27 08:56:51 [INFO] train episode 13480: reward = -90.05, steps = 24 08:56:54 [INFO] train episode 13481: reward = -133.03, steps = 38 08:56:56 [INFO] train episode 13482: reward = -150.81, steps = 26 08:56:58 [INFO] train episode 13483: reward = -105.20, steps = 21 08:57:00 [INFO] train episode 13484: reward = -98.61, steps = 20 08:57:02 [INFO] train episode 13485: reward = -145.41, steps = 22 08:57:05 [INFO] train episode 13486: reward = -84.32, steps = 32 08:57:08 [INFO] train episode 13487: reward = -123.10, steps = 41 08:57:10 [INFO] train episode 13488: reward = -97.88, steps = 21 08:57:13 [INFO] train episode 13489: reward = -104.75, steps = 37 08:57:16 [INFO] train episode 13490: reward = -126.72, steps = 25 08:57:19 [INFO] train episode 13491: reward = -148.64, steps = 39 08:57:21 [INFO] train episode 13492: reward = -93.59, steps = 20 08:57:25 [INFO] train episode 13493: reward = -85.56, steps = 45 08:57:28 [INFO] train episode 13494: reward = -67.61, steps = 41 08:57:31 [INFO] train episode 13495: reward = -122.89, steps = 34 08:57:33 [INFO] train episode 13496: reward = -124.95, steps = 24 08:57:35 [INFO] train episode 13497: reward = -112.94, steps = 25 08:57:38 [INFO] train episode 13498: reward = -143.66, steps = 30 08:57:42 [INFO] train episode 13499: reward = -151.50, steps = 51 08:57:45 [INFO] train episode 13500: reward = -118.41, steps = 27 08:57:47 [INFO] train episode 13501: reward = -118.70, steps = 23 08:57:50 [INFO] train episode 13502: reward = -131.65, steps = 36 08:57:53 [INFO] train episode 13503: reward = -114.34, steps = 31 08:57:57 [INFO] train episode 13504: reward = -86.96, steps = 47 08:57:59 [INFO] train episode 13505: reward = -126.98, steps = 23 08:58:04 [INFO] train episode 13506: reward = -106.25, steps = 63 08:58:06 [INFO] train episode 13507: reward = -148.13, steps = 26 08:58:09 [INFO] train episode 13508: reward = -120.33, steps = 30 08:58:11 [INFO] train episode 13509: reward = -100.71, steps = 28 08:58:14 [INFO] train episode 13510: reward = -105.43, steps = 27 08:58:17 [INFO] train episode 13511: reward = -111.35, steps = 39 08:58:20 [INFO] train episode 13512: reward = -140.26, steps = 35 08:58:22 [INFO] train episode 13513: reward = -135.25, steps = 23 08:58:24 [INFO] train episode 13514: reward = -109.42, steps = 27 08:58:27 [INFO] train episode 13515: reward = -95.88, steps = 26 08:58:29 [INFO] train episode 13516: reward = -75.62, steps = 24 08:58:30 [INFO] train episode 13517: reward = -108.98, steps = 19 08:58:35 [INFO] train episode 13518: reward = -133.09, steps = 45 08:58:37 [INFO] train episode 13519: reward = -97.02, steps = 23 08:58:40 [INFO] train episode 13520: reward = -124.81, steps = 28 08:58:43 [INFO] train episode 13521: reward = -118.99, steps = 45 08:58:46 [INFO] train episode 13522: reward = -132.99, steps = 36 08:58:48 [INFO] train episode 13523: reward = -140.28, steps = 19 08:58:51 [INFO] train episode 13524: reward = -134.29, steps = 26 08:58:53 [INFO] train episode 13525: reward = -67.69, steps = 24 08:58:55 [INFO] train episode 13526: reward = -108.78, steps = 35 08:58:58 [INFO] train episode 13527: reward = -142.34, steps = 26 08:59:00 [INFO] train episode 13528: reward = -157.60, steps = 33 08:59:03 [INFO] train episode 13529: reward = -113.58, steps = 25 08:59:08 [INFO] train episode 13530: reward = -117.07, steps = 65 08:59:11 [INFO] train episode 13531: reward = -99.88, steps = 25 08:59:12 [INFO] train episode 13532: reward = -135.04, steps = 22 08:59:16 [INFO] train episode 13533: reward = -133.28, steps = 45 08:59:18 [INFO] train episode 13534: reward = -114.08, steps = 23 08:59:21 [INFO] train episode 13535: reward = -121.44, steps = 30 08:59:24 [INFO] train episode 13536: reward = -116.21, steps = 31 08:59:26 [INFO] train episode 13537: reward = -117.46, steps = 33 08:59:28 [INFO] train episode 13538: reward = -86.96, steps = 24 08:59:30 [INFO] train episode 13539: reward = -144.03, steps = 23 08:59:33 [INFO] train episode 13540: reward = -93.41, steps = 31 08:59:37 [INFO] train episode 13541: reward = -85.77, steps = 48 08:59:40 [INFO] train episode 13542: reward = -104.84, steps = 30 08:59:42 [INFO] train episode 13543: reward = -152.89, steps = 27 08:59:45 [INFO] train episode 13544: reward = -122.04, steps = 35 08:59:47 [INFO] train episode 13545: reward = -103.90, steps = 21 08:59:49 [INFO] train episode 13546: reward = -73.44, steps = 21 08:59:51 [INFO] train episode 13547: reward = -118.90, steps = 26 08:59:53 [INFO] train episode 13548: reward = -122.03, steps = 24 08:59:56 [INFO] train episode 13549: reward = -93.34, steps = 38 08:59:59 [INFO] train episode 13550: reward = -155.66, steps = 31 09:00:02 [INFO] train episode 13551: reward = -128.21, steps = 31 09:00:04 [INFO] train episode 13552: reward = -124.39, steps = 30 09:00:06 [INFO] train episode 13553: reward = -77.35, steps = 22 09:00:10 [INFO] train episode 13554: reward = -109.04, steps = 40 09:00:12 [INFO] train episode 13555: reward = -151.17, steps = 31 09:00:15 [INFO] train episode 13556: reward = -94.89, steps = 33 09:00:18 [INFO] train episode 13557: reward = -112.77, steps = 36 09:00:20 [INFO] train episode 13558: reward = -109.70, steps = 22 09:00:22 [INFO] train episode 13559: reward = -240.49, steps = 23 09:00:24 [INFO] train episode 13560: reward = -103.65, steps = 24 09:00:27 [INFO] train episode 13561: reward = -117.31, steps = 26 09:00:32 [INFO] train episode 13562: reward = -204.39, steps = 61 09:00:34 [INFO] train episode 13563: reward = -109.64, steps = 26 09:00:36 [INFO] train episode 13564: reward = -119.71, steps = 21 09:00:38 [INFO] train episode 13565: reward = -117.50, steps = 28 09:00:41 [INFO] train episode 13566: reward = -100.72, steps = 27 09:00:43 [INFO] train episode 13567: reward = -81.56, steps = 32 09:00:46 [INFO] train episode 13568: reward = -111.79, steps = 25 09:00:48 [INFO] train episode 13569: reward = -110.46, steps = 28 09:00:51 [INFO] train episode 13570: reward = -90.79, steps = 38 09:00:54 [INFO] train episode 13571: reward = -111.43, steps = 29 09:00:57 [INFO] train episode 13572: reward = -109.11, steps = 31 09:00:59 [INFO] train episode 13573: reward = -101.17, steps = 27 09:01:01 [INFO] train episode 13574: reward = -107.91, steps = 27 09:01:04 [INFO] train episode 13575: reward = -112.95, steps = 32 09:01:07 [INFO] train episode 13576: reward = -119.99, steps = 38 09:01:09 [INFO] train episode 13577: reward = -103.54, steps = 26 09:01:12 [INFO] train episode 13578: reward = -117.66, steps = 23 09:01:13 [INFO] train episode 13579: reward = -122.44, steps = 19 09:01:16 [INFO] train episode 13580: reward = -92.96, steps = 37 09:01:19 [INFO] train episode 13581: reward = -97.69, steps = 31 09:01:21 [INFO] train episode 13582: reward = -145.24, steps = 27 09:01:24 [INFO] train episode 13583: reward = -72.53, steps = 27 09:01:26 [INFO] train episode 13584: reward = -124.47, steps = 21 09:01:29 [INFO] train episode 13585: reward = -127.44, steps = 35 09:01:31 [INFO] train episode 13586: reward = -103.59, steps = 25 09:01:34 [INFO] train episode 13587: reward = -84.58, steps = 36 09:01:38 [INFO] train episode 13588: reward = -131.51, steps = 38 09:01:40 [INFO] train episode 13589: reward = -118.88, steps = 22 09:01:42 [INFO] train episode 13590: reward = -106.60, steps = 24 09:01:44 [INFO] train episode 13591: reward = -81.09, steps = 27 09:01:46 [INFO] train episode 13592: reward = -150.47, steps = 25 09:01:48 [INFO] train episode 13593: reward = -106.52, steps = 20 09:01:51 [INFO] train episode 13594: reward = -125.11, steps = 35 09:01:53 [INFO] train episode 13595: reward = -109.05, steps = 24 09:01:57 [INFO] train episode 13596: reward = -103.18, steps = 41 09:01:59 [INFO] train episode 13597: reward = -130.03, steps = 25 09:02:02 [INFO] train episode 13598: reward = -122.65, steps = 31 09:02:04 [INFO] train episode 13599: reward = -98.86, steps = 25 09:02:07 [INFO] train episode 13600: reward = -117.05, steps = 27 09:02:09 [INFO] train episode 13601: reward = -159.46, steps = 27 09:02:12 [INFO] train episode 13602: reward = -141.46, steps = 34 09:02:14 [INFO] train episode 13603: reward = -101.69, steps = 30 09:02:17 [INFO] train episode 13604: reward = -119.97, steps = 24 09:02:21 [INFO] train episode 13605: reward = -126.37, steps = 48 09:02:23 [INFO] train episode 13606: reward = -94.83, steps = 25 09:02:25 [INFO] train episode 13607: reward = -115.27, steps = 21 09:02:28 [INFO] train episode 13608: reward = -103.05, steps = 32 09:02:30 [INFO] train episode 13609: reward = -128.18, steps = 25 09:02:33 [INFO] train episode 13610: reward = -112.61, steps = 26 09:02:34 [INFO] train episode 13611: reward = -113.36, steps = 19 09:02:37 [INFO] train episode 13612: reward = -97.62, steps = 31 09:02:39 [INFO] train episode 13613: reward = -125.37, steps = 20 09:02:41 [INFO] train episode 13614: reward = -124.44, steps = 25 09:02:43 [INFO] train episode 13615: reward = -146.28, steps = 24 09:02:45 [INFO] train episode 13616: reward = -86.28, steps = 28 09:02:48 [INFO] train episode 13617: reward = -103.31, steps = 26 09:02:50 [INFO] train episode 13618: reward = -135.69, steps = 27 09:02:53 [INFO] train episode 13619: reward = -90.88, steps = 31 09:02:55 [INFO] train episode 13620: reward = -100.45, steps = 28 09:02:57 [INFO] train episode 13621: reward = -93.29, steps = 22 09:02:59 [INFO] train episode 13622: reward = -110.93, steps = 20 09:03:01 [INFO] train episode 13623: reward = -136.30, steps = 25 09:03:06 [INFO] train episode 13624: reward = -181.55, steps = 57 09:03:09 [INFO] train episode 13625: reward = -87.53, steps = 31 09:03:11 [INFO] train episode 13626: reward = -85.63, steps = 27 09:03:13 [INFO] train episode 13627: reward = -84.46, steps = 28 09:03:15 [INFO] train episode 13628: reward = -125.40, steps = 26 09:03:17 [INFO] train episode 13629: reward = -90.86, steps = 21 09:03:20 [INFO] train episode 13630: reward = -101.21, steps = 25 09:03:21 [INFO] train episode 13631: reward = -119.31, steps = 21 09:03:25 [INFO] train episode 13632: reward = -128.81, steps = 48 09:03:28 [INFO] train episode 13633: reward = -105.68, steps = 25 09:03:30 [INFO] train episode 13634: reward = -124.09, steps = 25 09:03:31 [INFO] train episode 13635: reward = -96.45, steps = 20 09:03:33 [INFO] train episode 13636: reward = -94.61, steps = 24 09:03:36 [INFO] train episode 13637: reward = -92.76, steps = 28 09:03:38 [INFO] train episode 13638: reward = -96.62, steps = 22 09:03:40 [INFO] train episode 13639: reward = -128.56, steps = 19 09:03:43 [INFO] train episode 13640: reward = -97.24, steps = 41 09:03:46 [INFO] train episode 13641: reward = -107.74, steps = 35 09:03:49 [INFO] train episode 13642: reward = -82.82, steps = 36 09:03:53 [INFO] train episode 13643: reward = -90.45, steps = 38 09:03:55 [INFO] train episode 13644: reward = -58.46, steps = 21 09:03:57 [INFO] train episode 13645: reward = -122.67, steps = 28 09:03:59 [INFO] train episode 13646: reward = -107.82, steps = 28 09:04:03 [INFO] train episode 13647: reward = -160.12, steps = 44 09:04:06 [INFO] train episode 13648: reward = -102.47, steps = 28 09:04:08 [INFO] train episode 13649: reward = -98.87, steps = 24 09:04:13 [INFO] train episode 13650: reward = -124.11, steps = 58 09:04:16 [INFO] train episode 13651: reward = -124.87, steps = 26 09:04:18 [INFO] train episode 13652: reward = -91.17, steps = 28 09:04:20 [INFO] train episode 13653: reward = -107.14, steps = 25 09:04:23 [INFO] train episode 13654: reward = -106.94, steps = 24 09:04:25 [INFO] train episode 13655: reward = -111.03, steps = 25 09:04:27 [INFO] train episode 13656: reward = -81.86, steps = 25 09:04:29 [INFO] train episode 13657: reward = -75.08, steps = 27 09:04:31 [INFO] train episode 13658: reward = -83.34, steps = 23 09:04:33 [INFO] train episode 13659: reward = -119.67, steps = 20 09:04:35 [INFO] train episode 13660: reward = -117.27, steps = 26 09:04:39 [INFO] train episode 13661: reward = -116.11, steps = 42 09:04:41 [INFO] train episode 13662: reward = -115.15, steps = 26 09:04:43 [INFO] train episode 13663: reward = -155.57, steps = 26 09:04:45 [INFO] train episode 13664: reward = -110.44, steps = 18 09:04:48 [INFO] train episode 13665: reward = -92.59, steps = 36 09:04:51 [INFO] train episode 13666: reward = -100.08, steps = 29 09:04:53 [INFO] train episode 13667: reward = -102.52, steps = 25 09:04:55 [INFO] train episode 13668: reward = -118.80, steps = 26 09:04:57 [INFO] train episode 13669: reward = -83.89, steps = 25 09:05:00 [INFO] train episode 13670: reward = -100.85, steps = 33 09:05:02 [INFO] train episode 13671: reward = -116.76, steps = 24 09:05:05 [INFO] train episode 13672: reward = -84.04, steps = 36 09:05:07 [INFO] train episode 13673: reward = -110.03, steps = 23 09:05:09 [INFO] train episode 13674: reward = -101.17, steps = 21 09:05:11 [INFO] train episode 13675: reward = -122.61, steps = 23 09:05:14 [INFO] train episode 13676: reward = -76.47, steps = 27 09:05:16 [INFO] train episode 13677: reward = -107.63, steps = 29 09:05:18 [INFO] train episode 13678: reward = -108.52, steps = 21 09:05:21 [INFO] train episode 13679: reward = -94.90, steps = 40 09:05:24 [INFO] train episode 13680: reward = -87.17, steps = 26 09:05:26 [INFO] train episode 13681: reward = -98.48, steps = 22 09:05:28 [INFO] train episode 13682: reward = -138.43, steps = 22 09:05:31 [INFO] train episode 13683: reward = -99.49, steps = 40 09:05:33 [INFO] train episode 13684: reward = -128.04, steps = 27 09:05:35 [INFO] train episode 13685: reward = -110.52, steps = 23 09:05:39 [INFO] train episode 13686: reward = -142.74, steps = 40 09:05:41 [INFO] train episode 13687: reward = -103.57, steps = 27 09:05:44 [INFO] train episode 13688: reward = -75.91, steps = 30 09:05:46 [INFO] train episode 13689: reward = -125.07, steps = 25 09:05:48 [INFO] train episode 13690: reward = -143.26, steps = 25 09:05:51 [INFO] train episode 13691: reward = -121.90, steps = 31 09:05:54 [INFO] train episode 13692: reward = -100.28, steps = 36 09:05:55 [INFO] train episode 13693: reward = -135.32, steps = 21 09:05:58 [INFO] train episode 13694: reward = -98.77, steps = 25 09:06:00 [INFO] train episode 13695: reward = -117.04, steps = 28 09:06:04 [INFO] train episode 13696: reward = -95.15, steps = 39 09:06:06 [INFO] train episode 13697: reward = -114.66, steps = 24 09:06:08 [INFO] train episode 13698: reward = -102.75, steps = 23 09:06:10 [INFO] train episode 13699: reward = -102.50, steps = 34 09:06:13 [INFO] train episode 13700: reward = -118.84, steps = 29 09:06:15 [INFO] train episode 13701: reward = -102.18, steps = 21 09:06:17 [INFO] train episode 13702: reward = -91.13, steps = 24 09:06:20 [INFO] train episode 13703: reward = -130.38, steps = 39 09:06:23 [INFO] train episode 13704: reward = -118.18, steps = 24 09:06:26 [INFO] train episode 13705: reward = -115.67, steps = 42 09:06:28 [INFO] train episode 13706: reward = -116.91, steps = 22 09:06:30 [INFO] train episode 13707: reward = -129.25, steps = 19 09:06:32 [INFO] train episode 13708: reward = -118.25, steps = 23 09:06:35 [INFO] train episode 13709: reward = -149.35, steps = 35 09:06:38 [INFO] train episode 13710: reward = -107.31, steps = 40 09:06:40 [INFO] train episode 13711: reward = -102.43, steps = 19 09:06:42 [INFO] train episode 13712: reward = -114.42, steps = 25 09:06:45 [INFO] train episode 13713: reward = -103.63, steps = 28 09:06:47 [INFO] train episode 13714: reward = -97.82, steps = 25 09:06:49 [INFO] train episode 13715: reward = -92.36, steps = 26 09:06:51 [INFO] train episode 13716: reward = -138.62, steps = 21 09:06:55 [INFO] train episode 13717: reward = -134.61, steps = 51 09:06:59 [INFO] train episode 13718: reward = -124.34, steps = 41 09:07:01 [INFO] train episode 13719: reward = -102.33, steps = 20 09:07:03 [INFO] train episode 13720: reward = -79.43, steps = 28 09:07:06 [INFO] train episode 13721: reward = -107.39, steps = 23 09:07:08 [INFO] train episode 13722: reward = -107.49, steps = 21 09:07:10 [INFO] train episode 13723: reward = -85.86, steps = 29 09:07:13 [INFO] train episode 13724: reward = -129.97, steps = 37 09:07:17 [INFO] train episode 13725: reward = -105.26, steps = 41 09:07:19 [INFO] train episode 13726: reward = -104.53, steps = 29 09:07:22 [INFO] train episode 13727: reward = -80.80, steps = 25 09:07:24 [INFO] train episode 13728: reward = -113.25, steps = 26 09:07:26 [INFO] train episode 13729: reward = -103.38, steps = 23 09:07:28 [INFO] train episode 13730: reward = -97.93, steps = 24 09:07:30 [INFO] train episode 13731: reward = -129.10, steps = 24 09:07:33 [INFO] train episode 13732: reward = -125.09, steps = 29 09:07:35 [INFO] train episode 13733: reward = -89.02, steps = 25 09:07:37 [INFO] train episode 13734: reward = -77.63, steps = 22 09:07:40 [INFO] train episode 13735: reward = -83.37, steps = 32 09:07:42 [INFO] train episode 13736: reward = -104.17, steps = 34 09:07:46 [INFO] train episode 13737: reward = -132.16, steps = 39 09:07:48 [INFO] train episode 13738: reward = -123.81, steps = 24 09:07:50 [INFO] train episode 13739: reward = -89.90, steps = 20 09:07:52 [INFO] train episode 13740: reward = -130.79, steps = 31 09:07:54 [INFO] train episode 13741: reward = -122.11, steps = 23 09:07:56 [INFO] train episode 13742: reward = -132.32, steps = 23 09:07:58 [INFO] train episode 13743: reward = -94.91, steps = 23 09:08:00 [INFO] train episode 13744: reward = -75.20, steps = 24 09:08:02 [INFO] train episode 13745: reward = -146.29, steps = 19 09:08:05 [INFO] train episode 13746: reward = -109.34, steps = 24 09:08:08 [INFO] train episode 13747: reward = -94.45, steps = 45 09:08:10 [INFO] train episode 13748: reward = -124.66, steps = 25 09:08:13 [INFO] train episode 13749: reward = -166.06, steps = 28 09:08:15 [INFO] train episode 13750: reward = -119.69, steps = 27 09:08:17 [INFO] train episode 13751: reward = -98.48, steps = 26 09:08:20 [INFO] train episode 13752: reward = -73.30, steps = 22 09:08:22 [INFO] train episode 13753: reward = -139.53, steps = 23 09:08:24 [INFO] train episode 13754: reward = -109.97, steps = 26 09:08:26 [INFO] train episode 13755: reward = -118.38, steps = 27 09:08:28 [INFO] train episode 13756: reward = -82.57, steps = 21 09:08:30 [INFO] train episode 13757: reward = -109.17, steps = 22 09:08:34 [INFO] train episode 13758: reward = -84.29, steps = 46 09:08:36 [INFO] train episode 13759: reward = -108.31, steps = 24 09:08:39 [INFO] train episode 13760: reward = -110.37, steps = 28 09:08:41 [INFO] train episode 13761: reward = -85.69, steps = 34 09:08:43 [INFO] train episode 13762: reward = -107.32, steps = 23 09:08:46 [INFO] train episode 13763: reward = -90.71, steps = 28 09:08:48 [INFO] train episode 13764: reward = -85.54, steps = 31 09:08:50 [INFO] train episode 13765: reward = -94.52, steps = 26 09:08:54 [INFO] train episode 13766: reward = -125.50, steps = 34 09:08:56 [INFO] train episode 13767: reward = -89.20, steps = 22 09:08:58 [INFO] train episode 13768: reward = -107.38, steps = 27 09:09:00 [INFO] train episode 13769: reward = -131.47, steps = 20 09:09:01 [INFO] train episode 13770: reward = -117.16, steps = 21 09:09:03 [INFO] train episode 13771: reward = -104.52, steps = 24 09:09:07 [INFO] train episode 13772: reward = -74.64, steps = 39 09:09:09 [INFO] train episode 13773: reward = -158.63, steps = 26 09:09:11 [INFO] train episode 13774: reward = -129.12, steps = 26 09:09:13 [INFO] train episode 13775: reward = -102.98, steps = 19 09:09:16 [INFO] train episode 13776: reward = -178.93, steps = 35 09:09:18 [INFO] train episode 13777: reward = -110.12, steps = 21 09:09:23 [INFO] train episode 13778: reward = -129.76, steps = 52 09:09:25 [INFO] train episode 13779: reward = -84.39, steps = 28 09:09:27 [INFO] train episode 13780: reward = -124.90, steps = 21 09:09:30 [INFO] train episode 13781: reward = -100.45, steps = 34 09:09:32 [INFO] train episode 13782: reward = -82.30, steps = 26 09:09:34 [INFO] train episode 13783: reward = -128.78, steps = 21 09:09:35 [INFO] train episode 13784: reward = -168.69, steps = 19 09:09:39 [INFO] train episode 13785: reward = -89.31, steps = 39 09:09:41 [INFO] train episode 13786: reward = -97.47, steps = 23 09:09:45 [INFO] train episode 13787: reward = -109.63, steps = 44 09:09:47 [INFO] train episode 13788: reward = -99.26, steps = 25 09:09:49 [INFO] train episode 13789: reward = -120.70, steps = 24 09:09:51 [INFO] train episode 13790: reward = -107.17, steps = 23 09:09:53 [INFO] train episode 13791: reward = -102.31, steps = 24 09:09:56 [INFO] train episode 13792: reward = -119.93, steps = 27 09:09:59 [INFO] train episode 13793: reward = -106.17, steps = 36 09:10:01 [INFO] train episode 13794: reward = -113.41, steps = 22 09:10:03 [INFO] train episode 13795: reward = -96.38, steps = 19 09:10:05 [INFO] train episode 13796: reward = -90.80, steps = 27 09:10:09 [INFO] train episode 13797: reward = -122.60, steps = 41 09:10:11 [INFO] train episode 13798: reward = -101.39, steps = 19 09:10:13 [INFO] train episode 13799: reward = -87.49, steps = 29 09:10:15 [INFO] train episode 13800: reward = -98.95, steps = 20 09:10:17 [INFO] train episode 13801: reward = -129.25, steps = 27 09:10:20 [INFO] train episode 13802: reward = -148.54, steps = 29 09:10:22 [INFO] train episode 13803: reward = -92.45, steps = 24 09:10:24 [INFO] train episode 13804: reward = -113.59, steps = 25 09:10:27 [INFO] train episode 13805: reward = -180.28, steps = 29 09:10:30 [INFO] train episode 13806: reward = -86.25, steps = 45 09:10:33 [INFO] train episode 13807: reward = -95.40, steps = 32 09:10:35 [INFO] train episode 13808: reward = -116.71, steps = 26 09:10:38 [INFO] train episode 13809: reward = -87.64, steps = 32 09:10:41 [INFO] train episode 13810: reward = -98.27, steps = 38 09:10:44 [INFO] train episode 13811: reward = -105.32, steps = 27 09:10:46 [INFO] train episode 13812: reward = -89.86, steps = 23 09:10:49 [INFO] train episode 13813: reward = -116.85, steps = 39 09:10:51 [INFO] train episode 13814: reward = -138.24, steps = 25 09:10:53 [INFO] train episode 13815: reward = -108.34, steps = 21 09:10:55 [INFO] train episode 13816: reward = -91.49, steps = 26 09:10:57 [INFO] train episode 13817: reward = -89.84, steps = 26 09:11:00 [INFO] train episode 13818: reward = -123.31, steps = 30 09:11:02 [INFO] train episode 13819: reward = -76.12, steps = 25 09:11:04 [INFO] train episode 13820: reward = -73.69, steps = 23 09:11:06 [INFO] train episode 13821: reward = -147.58, steps = 22 09:11:08 [INFO] train episode 13822: reward = -118.84, steps = 24 09:11:11 [INFO] train episode 13823: reward = -118.05, steps = 31 09:11:13 [INFO] train episode 13824: reward = -100.67, steps = 23 09:11:15 [INFO] train episode 13825: reward = -119.16, steps = 23 09:11:18 [INFO] train episode 13826: reward = -104.92, steps = 29 09:11:20 [INFO] train episode 13827: reward = -87.51, steps = 23 09:11:22 [INFO] train episode 13828: reward = -114.60, steps = 22 09:11:24 [INFO] train episode 13829: reward = -163.54, steps = 33 09:11:26 [INFO] train episode 13830: reward = -100.29, steps = 22 09:11:29 [INFO] train episode 13831: reward = -128.48, steps = 30 09:11:32 [INFO] train episode 13832: reward = -165.72, steps = 29 09:11:34 [INFO] train episode 13833: reward = -131.26, steps = 25 09:11:37 [INFO] train episode 13834: reward = -97.40, steps = 35 09:11:38 [INFO] train episode 13835: reward = -112.38, steps = 21 09:11:40 [INFO] train episode 13836: reward = -122.86, steps = 24 09:11:43 [INFO] train episode 13837: reward = -123.34, steps = 35 09:11:46 [INFO] train episode 13838: reward = -91.01, steps = 21 09:11:48 [INFO] train episode 13839: reward = -84.46, steps = 25 09:11:50 [INFO] train episode 13840: reward = -131.76, steps = 33 09:11:53 [INFO] train episode 13841: reward = -132.28, steps = 37 09:11:58 [INFO] train episode 13842: reward = -135.44, steps = 56 09:12:03 [INFO] train episode 13843: reward = -103.71, steps = 48 09:12:05 [INFO] train episode 13844: reward = -75.91, steps = 33 09:12:07 [INFO] train episode 13845: reward = -121.22, steps = 23 09:12:10 [INFO] train episode 13846: reward = -166.97, steps = 39 09:12:13 [INFO] train episode 13847: reward = -124.67, steps = 26 09:12:15 [INFO] train episode 13848: reward = -86.18, steps = 26 09:12:18 [INFO] train episode 13849: reward = -135.92, steps = 31 09:12:21 [INFO] train episode 13850: reward = -109.81, steps = 30 09:12:23 [INFO] train episode 13851: reward = -114.33, steps = 25 09:12:26 [INFO] train episode 13852: reward = -106.25, steps = 33 09:12:29 [INFO] train episode 13853: reward = -89.67, steps = 36 09:12:30 [INFO] train episode 13854: reward = -75.46, steps = 21 09:12:32 [INFO] train episode 13855: reward = -104.91, steps = 20 09:12:35 [INFO] train episode 13856: reward = -99.25, steps = 29 09:12:37 [INFO] train episode 13857: reward = -97.89, steps = 25 09:12:40 [INFO] train episode 13858: reward = -119.23, steps = 28 09:12:42 [INFO] train episode 13859: reward = -113.09, steps = 35 09:12:45 [INFO] train episode 13860: reward = -82.87, steps = 25 09:12:47 [INFO] train episode 13861: reward = -134.07, steps = 20 09:12:51 [INFO] train episode 13862: reward = -83.96, steps = 44 09:12:53 [INFO] train episode 13863: reward = -69.30, steps = 19 09:12:56 [INFO] train episode 13864: reward = -121.56, steps = 44 09:12:59 [INFO] train episode 13865: reward = -95.80, steps = 30 09:13:02 [INFO] train episode 13866: reward = -119.20, steps = 35 09:13:05 [INFO] train episode 13867: reward = -112.53, steps = 36 09:13:07 [INFO] train episode 13868: reward = -98.64, steps = 25 09:13:09 [INFO] train episode 13869: reward = -100.27, steps = 23 09:13:11 [INFO] train episode 13870: reward = -100.33, steps = 24 09:13:13 [INFO] train episode 13871: reward = -83.98, steps = 25 09:13:16 [INFO] train episode 13872: reward = -144.87, steps = 36 09:13:19 [INFO] train episode 13873: reward = -92.71, steps = 26 09:13:21 [INFO] train episode 13874: reward = -124.12, steps = 27 09:13:23 [INFO] train episode 13875: reward = -107.49, steps = 20 09:13:25 [INFO] train episode 13876: reward = -125.25, steps = 26 09:13:28 [INFO] train episode 13877: reward = -146.61, steps = 34 09:13:30 [INFO] train episode 13878: reward = -97.36, steps = 29 09:13:32 [INFO] train episode 13879: reward = -84.14, steps = 21 09:13:35 [INFO] train episode 13880: reward = -87.81, steps = 27 09:13:38 [INFO] train episode 13881: reward = -180.79, steps = 30 09:13:40 [INFO] train episode 13882: reward = -82.66, steps = 24 09:13:42 [INFO] train episode 13883: reward = -85.09, steps = 23 09:13:44 [INFO] train episode 13884: reward = -80.64, steps = 25 09:13:47 [INFO] train episode 13885: reward = -147.25, steps = 43 09:13:50 [INFO] train episode 13886: reward = -97.51, steps = 33 09:13:53 [INFO] train episode 13887: reward = -80.60, steps = 32 09:13:55 [INFO] train episode 13888: reward = -108.81, steps = 25 09:13:58 [INFO] train episode 13889: reward = -105.85, steps = 31 09:14:00 [INFO] train episode 13890: reward = -106.60, steps = 29 09:14:02 [INFO] train episode 13891: reward = -138.32, steps = 24 09:14:06 [INFO] train episode 13892: reward = -139.47, steps = 37 09:14:08 [INFO] train episode 13893: reward = -82.28, steps = 22 09:14:12 [INFO] train episode 13894: reward = -141.42, steps = 47 09:14:14 [INFO] train episode 13895: reward = -121.21, steps = 28 09:14:16 [INFO] train episode 13896: reward = -97.32, steps = 27 09:14:18 [INFO] train episode 13897: reward = -86.86, steps = 20 09:14:21 [INFO] train episode 13898: reward = -120.14, steps = 38 09:14:24 [INFO] train episode 13899: reward = -134.27, steps = 26 09:14:26 [INFO] train episode 13900: reward = -120.05, steps = 24 09:14:28 [INFO] train episode 13901: reward = -76.38, steps = 24 09:14:30 [INFO] train episode 13902: reward = -99.84, steps = 28 09:14:32 [INFO] train episode 13903: reward = -91.73, steps = 24 09:14:34 [INFO] train episode 13904: reward = -110.49, steps = 20 09:14:36 [INFO] train episode 13905: reward = -92.53, steps = 25 09:14:39 [INFO] train episode 13906: reward = -145.04, steps = 33 09:14:42 [INFO] train episode 13907: reward = -121.22, steps = 30 09:14:44 [INFO] train episode 13908: reward = -107.06, steps = 20 09:14:46 [INFO] train episode 13909: reward = -94.90, steps = 22 09:14:48 [INFO] train episode 13910: reward = -80.20, steps = 26 09:14:51 [INFO] train episode 13911: reward = -98.29, steps = 35 09:14:55 [INFO] train episode 13912: reward = -102.99, steps = 48 09:14:58 [INFO] train episode 13913: reward = -95.73, steps = 33 09:15:00 [INFO] train episode 13914: reward = -83.21, steps = 30 09:15:03 [INFO] train episode 13915: reward = -85.67, steps = 26 09:15:05 [INFO] train episode 13916: reward = -107.62, steps = 31 09:15:08 [INFO] train episode 13917: reward = -101.14, steps = 30 09:15:10 [INFO] train episode 13918: reward = -82.76, steps = 20 09:15:12 [INFO] train episode 13919: reward = -135.02, steps = 19 09:15:14 [INFO] train episode 13920: reward = -85.80, steps = 28 09:15:16 [INFO] train episode 13921: reward = -124.36, steps = 29 09:15:19 [INFO] train episode 13922: reward = -152.25, steps = 28 09:15:20 [INFO] train episode 13923: reward = -74.51, steps = 19 09:15:22 [INFO] train episode 13924: reward = -122.96, steps = 18 09:15:24 [INFO] train episode 13925: reward = -119.74, steps = 24 09:15:27 [INFO] train episode 13926: reward = -111.34, steps = 30 09:15:30 [INFO] train episode 13927: reward = -111.17, steps = 34 09:15:32 [INFO] train episode 13928: reward = -112.96, steps = 27 09:15:35 [INFO] train episode 13929: reward = -84.05, steps = 20 09:15:40 [INFO] train episode 13930: reward = -184.74, steps = 65 09:15:42 [INFO] train episode 13931: reward = -102.46, steps = 21 09:15:45 [INFO] train episode 13932: reward = -96.11, steps = 37 09:15:47 [INFO] train episode 13933: reward = -110.72, steps = 27 09:15:49 [INFO] train episode 13934: reward = -120.15, steps = 23 09:15:52 [INFO] train episode 13935: reward = -138.38, steps = 25 09:15:55 [INFO] train episode 13936: reward = -102.84, steps = 40 09:15:58 [INFO] train episode 13937: reward = -129.61, steps = 35 09:16:01 [INFO] train episode 13938: reward = -101.85, steps = 29 09:16:03 [INFO] train episode 13939: reward = -110.84, steps = 25 09:16:05 [INFO] train episode 13940: reward = -115.72, steps = 24 09:16:07 [INFO] train episode 13941: reward = -113.36, steps = 22 09:16:09 [INFO] train episode 13942: reward = -134.08, steps = 33 09:16:11 [INFO] train episode 13943: reward = -101.17, steps = 19 09:16:13 [INFO] train episode 13944: reward = -84.59, steps = 21 09:16:16 [INFO] train episode 13945: reward = -128.74, steps = 30 09:16:17 [INFO] train episode 13946: reward = -72.41, steps = 21 09:16:19 [INFO] train episode 13947: reward = -89.06, steps = 20 09:16:21 [INFO] train episode 13948: reward = -130.45, steps = 26 09:16:23 [INFO] train episode 13949: reward = -63.12, steps = 19 09:16:25 [INFO] train episode 13950: reward = -90.90, steps = 27 09:16:27 [INFO] train episode 13951: reward = -103.05, steps = 24 09:16:30 [INFO] train episode 13952: reward = -113.23, steps = 22 09:16:32 [INFO] train episode 13953: reward = -100.20, steps = 29 09:16:34 [INFO] train episode 13954: reward = -68.56, steps = 21 09:16:36 [INFO] train episode 13955: reward = -85.77, steps = 25 09:16:38 [INFO] train episode 13956: reward = -98.21, steps = 28 09:16:41 [INFO] train episode 13957: reward = -115.82, steps = 27 09:16:43 [INFO] train episode 13958: reward = -106.92, steps = 32 09:16:46 [INFO] train episode 13959: reward = -116.97, steps = 23 09:16:48 [INFO] train episode 13960: reward = -74.57, steps = 31 09:16:51 [INFO] train episode 13961: reward = -78.69, steps = 28 09:16:53 [INFO] train episode 13962: reward = -135.75, steps = 30 09:16:55 [INFO] train episode 13963: reward = -84.24, steps = 20 09:16:57 [INFO] train episode 13964: reward = -136.91, steps = 21 09:16:59 [INFO] train episode 13965: reward = -94.22, steps = 27 09:17:02 [INFO] train episode 13966: reward = -126.80, steps = 27 09:17:04 [INFO] train episode 13967: reward = -102.76, steps = 24 09:17:07 [INFO] train episode 13968: reward = -97.04, steps = 34 09:17:09 [INFO] train episode 13969: reward = -111.82, steps = 21 09:17:12 [INFO] train episode 13970: reward = -128.24, steps = 42 09:17:16 [INFO] train episode 13971: reward = -109.01, steps = 40 09:17:18 [INFO] train episode 13972: reward = -157.91, steps = 24 09:17:20 [INFO] train episode 13973: reward = -95.18, steps = 20 09:17:22 [INFO] train episode 13974: reward = -138.75, steps = 23 09:17:24 [INFO] train episode 13975: reward = -84.06, steps = 25 09:17:26 [INFO] train episode 13976: reward = -130.31, steps = 25 09:17:28 [INFO] train episode 13977: reward = -101.49, steps = 24 09:17:30 [INFO] train episode 13978: reward = -103.52, steps = 25 09:17:32 [INFO] train episode 13979: reward = -115.75, steps = 19 09:17:35 [INFO] train episode 13980: reward = -78.68, steps = 28 09:17:37 [INFO] train episode 13981: reward = -69.94, steps = 22 09:17:39 [INFO] train episode 13982: reward = -102.51, steps = 33 09:17:43 [INFO] train episode 13983: reward = -129.83, steps = 46 09:17:45 [INFO] train episode 13984: reward = -91.27, steps = 22 09:17:50 [INFO] train episode 13985: reward = -136.16, steps = 49 09:17:52 [INFO] train episode 13986: reward = -123.89, steps = 28 09:17:54 [INFO] train episode 13987: reward = -116.24, steps = 21 09:17:56 [INFO] train episode 13988: reward = -98.81, steps = 23 09:17:58 [INFO] train episode 13989: reward = -128.55, steps = 31 09:18:01 [INFO] train episode 13990: reward = -137.88, steps = 28 09:18:03 [INFO] train episode 13991: reward = -112.93, steps = 22 09:18:05 [INFO] train episode 13992: reward = -80.41, steps = 28 09:18:08 [INFO] train episode 13993: reward = -72.82, steps = 31 09:18:11 [INFO] train episode 13994: reward = -126.74, steps = 39 09:18:13 [INFO] train episode 13995: reward = -102.82, steps = 25 09:18:15 [INFO] train episode 13996: reward = -73.50, steps = 20 09:18:17 [INFO] train episode 13997: reward = -88.23, steps = 27 09:18:20 [INFO] train episode 13998: reward = -107.18, steps = 23 09:18:22 [INFO] train episode 13999: reward = -99.12, steps = 29 09:18:25 [INFO] train episode 14000: reward = -112.53, steps = 23 09:18:27 [INFO] train episode 14001: reward = -94.89, steps = 27 09:18:29 [INFO] train episode 14002: reward = -91.11, steps = 22 09:18:31 [INFO] train episode 14003: reward = -100.31, steps = 20 09:18:33 [INFO] train episode 14004: reward = -101.48, steps = 25 09:18:35 [INFO] train episode 14005: reward = -106.59, steps = 24 09:18:37 [INFO] train episode 14006: reward = -84.23, steps = 22 09:18:39 [INFO] train episode 14007: reward = -96.09, steps = 24 09:18:41 [INFO] train episode 14008: reward = -105.68, steps = 20 09:18:43 [INFO] train episode 14009: reward = -93.37, steps = 25 09:18:45 [INFO] train episode 14010: reward = -77.69, steps = 26 09:18:48 [INFO] train episode 14011: reward = -121.87, steps = 27 09:18:50 [INFO] train episode 14012: reward = -104.93, steps = 24 09:18:52 [INFO] train episode 14013: reward = -109.96, steps = 27 09:18:55 [INFO] train episode 14014: reward = -92.37, steps = 26 09:18:57 [INFO] train episode 14015: reward = -111.70, steps = 21 09:18:59 [INFO] train episode 14016: reward = -102.56, steps = 24 09:19:01 [INFO] train episode 14017: reward = -83.38, steps = 28 09:19:03 [INFO] train episode 14018: reward = -120.96, steps = 28 09:19:05 [INFO] train episode 14019: reward = -79.92, steps = 23 09:19:08 [INFO] train episode 14020: reward = -90.88, steps = 26 09:19:10 [INFO] train episode 14021: reward = -127.38, steps = 23 09:19:12 [INFO] train episode 14022: reward = -88.65, steps = 20 09:19:14 [INFO] train episode 14023: reward = -119.46, steps = 24 09:19:15 [INFO] train episode 14024: reward = -87.91, steps = 18 09:19:18 [INFO] train episode 14025: reward = -75.86, steps = 36 09:19:21 [INFO] train episode 14026: reward = -113.73, steps = 28 09:19:22 [INFO] train episode 14027: reward = -94.28, steps = 21 09:19:25 [INFO] train episode 14028: reward = -73.38, steps = 23 09:19:27 [INFO] train episode 14029: reward = -148.63, steps = 26 09:19:29 [INFO] train episode 14030: reward = -113.26, steps = 20 09:19:30 [INFO] train episode 14031: reward = -105.96, steps = 19 09:19:33 [INFO] train episode 14032: reward = -165.16, steps = 29 09:19:35 [INFO] train episode 14033: reward = -145.90, steps = 30 09:19:37 [INFO] train episode 14034: reward = -101.82, steps = 20 09:19:39 [INFO] train episode 14035: reward = -109.31, steps = 23 09:19:41 [INFO] train episode 14036: reward = -106.24, steps = 25 09:19:43 [INFO] train episode 14037: reward = -84.12, steps = 21 09:19:45 [INFO] train episode 14038: reward = -121.12, steps = 24 09:19:47 [INFO] train episode 14039: reward = -86.08, steps = 22 09:19:49 [INFO] train episode 14040: reward = -104.58, steps = 25 09:19:51 [INFO] train episode 14041: reward = -62.72, steps = 20 09:19:53 [INFO] train episode 14042: reward = -100.71, steps = 19 09:19:55 [INFO] train episode 14043: reward = -92.83, steps = 30 09:19:59 [INFO] train episode 14044: reward = -130.80, steps = 40 09:20:01 [INFO] train episode 14045: reward = -98.51, steps = 25 09:20:03 [INFO] train episode 14046: reward = -96.36, steps = 27 09:20:05 [INFO] train episode 14047: reward = -105.04, steps = 25 09:20:08 [INFO] train episode 14048: reward = -94.83, steps = 28 09:20:10 [INFO] train episode 14049: reward = -75.30, steps = 21 09:20:14 [INFO] train episode 14050: reward = -119.54, steps = 46 09:20:15 [INFO] train episode 14051: reward = -80.02, steps = 19 09:20:17 [INFO] train episode 14052: reward = -114.36, steps = 23 09:20:19 [INFO] train episode 14053: reward = -82.26, steps = 20 09:20:22 [INFO] train episode 14054: reward = -126.25, steps = 41 09:20:24 [INFO] train episode 14055: reward = -90.32, steps = 23 09:20:28 [INFO] train episode 14056: reward = -91.86, steps = 33 09:20:29 [INFO] train episode 14057: reward = -124.47, steps = 19 09:20:31 [INFO] train episode 14058: reward = -79.59, steps = 19 09:20:34 [INFO] train episode 14059: reward = -125.84, steps = 32 09:20:36 [INFO] train episode 14060: reward = -149.03, steps = 32 09:20:39 [INFO] train episode 14061: reward = -78.18, steps = 28 09:20:40 [INFO] train episode 14062: reward = -101.11, steps = 19 09:20:42 [INFO] train episode 14063: reward = -116.69, steps = 21 09:20:44 [INFO] train episode 14064: reward = -69.89, steps = 20 09:20:46 [INFO] train episode 14065: reward = -88.34, steps = 19 09:20:49 [INFO] train episode 14066: reward = -148.96, steps = 32 09:20:51 [INFO] train episode 14067: reward = -117.65, steps = 19 09:20:53 [INFO] train episode 14068: reward = -106.10, steps = 22 09:20:55 [INFO] train episode 14069: reward = -94.07, steps = 22 09:20:58 [INFO] train episode 14070: reward = -92.47, steps = 29 09:21:00 [INFO] train episode 14071: reward = -91.88, steps = 20 09:21:03 [INFO] train episode 14072: reward = -102.40, steps = 31 09:21:05 [INFO] train episode 14073: reward = -104.51, steps = 19 09:21:08 [INFO] train episode 14074: reward = -65.55, steps = 29 09:21:10 [INFO] train episode 14075: reward = -83.66, steps = 19 09:21:12 [INFO] train episode 14076: reward = -165.37, steps = 22 09:21:15 [INFO] train episode 14077: reward = -149.88, steps = 37 09:21:19 [INFO] train episode 14078: reward = -79.98, steps = 29 09:21:21 [INFO] train episode 14079: reward = -91.14, steps = 22 09:21:23 [INFO] train episode 14080: reward = -99.02, steps = 27 09:21:26 [INFO] train episode 14081: reward = -102.20, steps = 35 09:21:27 [INFO] train episode 14082: reward = -77.76, steps = 20 09:21:29 [INFO] train episode 14083: reward = -87.11, steps = 20 09:21:31 [INFO] train episode 14084: reward = -95.73, steps = 25 09:21:34 [INFO] train episode 14085: reward = -80.78, steps = 25 09:21:36 [INFO] train episode 14086: reward = -88.91, steps = 25 09:21:38 [INFO] train episode 14087: reward = -115.41, steps = 25 09:21:40 [INFO] train episode 14088: reward = -119.28, steps = 24 09:21:42 [INFO] train episode 14089: reward = -74.97, steps = 20 09:21:44 [INFO] train episode 14090: reward = -67.23, steps = 20 09:21:46 [INFO] train episode 14091: reward = -114.44, steps = 27 09:21:48 [INFO] train episode 14092: reward = -69.31, steps = 22 09:21:50 [INFO] train episode 14093: reward = -95.41, steps = 28 09:21:53 [INFO] train episode 14094: reward = -153.97, steps = 33 09:21:55 [INFO] train episode 14095: reward = -81.77, steps = 24 09:21:58 [INFO] train episode 14096: reward = -109.38, steps = 27 09:22:01 [INFO] train episode 14097: reward = -107.20, steps = 40 09:22:03 [INFO] train episode 14098: reward = -100.42, steps = 20 09:22:05 [INFO] train episode 14099: reward = -74.21, steps = 19 09:22:07 [INFO] train episode 14100: reward = -96.13, steps = 30 09:22:10 [INFO] train episode 14101: reward = -115.22, steps = 34 09:22:13 [INFO] train episode 14102: reward = -96.52, steps = 36 09:22:15 [INFO] train episode 14103: reward = -106.00, steps = 24 09:22:17 [INFO] train episode 14104: reward = -91.55, steps = 21 09:22:20 [INFO] train episode 14105: reward = -87.19, steps = 25 09:22:22 [INFO] train episode 14106: reward = -146.51, steps = 33 09:22:25 [INFO] train episode 14107: reward = -82.18, steps = 27 09:22:27 [INFO] train episode 14108: reward = -128.73, steps = 33 09:22:30 [INFO] train episode 14109: reward = -129.07, steps = 29 09:22:32 [INFO] train episode 14110: reward = -66.99, steps = 27 09:22:34 [INFO] train episode 14111: reward = -101.24, steps = 28 09:22:38 [INFO] train episode 14112: reward = -98.50, steps = 32 09:22:40 [INFO] train episode 14113: reward = -122.47, steps = 24 09:22:42 [INFO] train episode 14114: reward = -100.62, steps = 23 09:22:44 [INFO] train episode 14115: reward = -119.03, steps = 27 09:22:45 [INFO] train episode 14116: reward = -83.36, steps = 19 09:22:48 [INFO] train episode 14117: reward = -111.75, steps = 25 09:22:50 [INFO] train episode 14118: reward = -115.22, steps = 29 09:22:52 [INFO] train episode 14119: reward = -94.37, steps = 24 09:22:54 [INFO] train episode 14120: reward = -104.73, steps = 23 09:22:56 [INFO] train episode 14121: reward = -90.57, steps = 24 09:22:58 [INFO] train episode 14122: reward = -80.71, steps = 22 09:23:00 [INFO] train episode 14123: reward = -77.48, steps = 21 09:23:03 [INFO] train episode 14124: reward = -108.14, steps = 29 09:23:04 [INFO] train episode 14125: reward = -122.30, steps = 21 09:23:06 [INFO] train episode 14126: reward = -96.80, steps = 20 09:23:09 [INFO] train episode 14127: reward = -97.80, steps = 28 09:23:12 [INFO] train episode 14128: reward = -148.56, steps = 37 09:23:14 [INFO] train episode 14129: reward = -105.67, steps = 28 09:23:19 [INFO] train episode 14130: reward = -154.42, steps = 59 09:23:21 [INFO] train episode 14131: reward = -87.46, steps = 25 09:23:23 [INFO] train episode 14132: reward = -68.94, steps = 20 09:23:25 [INFO] train episode 14133: reward = -81.67, steps = 20 09:23:27 [INFO] train episode 14134: reward = -131.46, steps = 23 09:23:30 [INFO] train episode 14135: reward = -102.26, steps = 37 09:23:32 [INFO] train episode 14136: reward = -115.46, steps = 24 09:23:35 [INFO] train episode 14137: reward = -98.80, steps = 29 09:23:37 [INFO] train episode 14138: reward = -109.34, steps = 23 09:23:39 [INFO] train episode 14139: reward = -68.48, steps = 21 09:23:41 [INFO] train episode 14140: reward = -78.37, steps = 26 09:23:44 [INFO] train episode 14141: reward = -76.49, steps = 29 09:23:46 [INFO] train episode 14142: reward = -101.10, steps = 27 09:23:48 [INFO] train episode 14143: reward = -88.03, steps = 25 09:23:51 [INFO] train episode 14144: reward = -93.44, steps = 30 09:23:52 [INFO] train episode 14145: reward = -92.63, steps = 21 09:23:54 [INFO] train episode 14146: reward = -70.30, steps = 19 09:23:57 [INFO] train episode 14147: reward = -88.77, steps = 32 09:23:59 [INFO] train episode 14148: reward = -136.63, steps = 21 09:24:01 [INFO] train episode 14149: reward = -80.40, steps = 20 09:24:03 [INFO] train episode 14150: reward = -95.47, steps = 27 09:24:08 [INFO] train episode 14151: reward = -117.93, steps = 48 09:24:11 [INFO] train episode 14152: reward = -134.54, steps = 35 09:24:13 [INFO] train episode 14153: reward = -79.45, steps = 21 09:24:15 [INFO] train episode 14154: reward = -135.30, steps = 22 09:24:17 [INFO] train episode 14155: reward = -104.08, steps = 24 09:24:19 [INFO] train episode 14156: reward = -94.09, steps = 29 09:24:21 [INFO] train episode 14157: reward = -104.87, steps = 27 09:24:23 [INFO] train episode 14158: reward = -86.14, steps = 21 09:24:26 [INFO] train episode 14159: reward = -76.30, steps = 29 09:24:28 [INFO] train episode 14160: reward = -145.26, steps = 28 09:24:30 [INFO] train episode 14161: reward = -79.52, steps = 25 09:24:32 [INFO] train episode 14162: reward = -130.05, steps = 19 09:24:34 [INFO] train episode 14163: reward = -79.88, steps = 20 09:24:36 [INFO] train episode 14164: reward = -80.23, steps = 30 09:24:39 [INFO] train episode 14165: reward = -88.80, steps = 29 09:24:43 [INFO] train episode 14166: reward = -126.17, steps = 41 09:24:44 [INFO] train episode 14167: reward = -140.40, steps = 19 09:24:46 [INFO] train episode 14168: reward = -91.03, steps = 23 09:24:49 [INFO] train episode 14169: reward = -83.06, steps = 26 09:24:51 [INFO] train episode 14170: reward = -99.95, steps = 26 09:24:53 [INFO] train episode 14171: reward = -111.36, steps = 27 09:24:55 [INFO] train episode 14172: reward = -155.19, steps = 25 09:24:58 [INFO] train episode 14173: reward = -94.84, steps = 23 09:24:59 [INFO] train episode 14174: reward = -110.50, steps = 20 09:25:01 [INFO] train episode 14175: reward = -100.64, steps = 23 09:25:03 [INFO] train episode 14176: reward = -97.84, steps = 27 09:25:06 [INFO] train episode 14177: reward = -81.57, steps = 26 09:25:08 [INFO] train episode 14178: reward = -154.17, steps = 24 09:25:10 [INFO] train episode 14179: reward = -137.39, steps = 25 09:25:14 [INFO] train episode 14180: reward = -180.23, steps = 40 09:25:15 [INFO] train episode 14181: reward = -150.19, steps = 21 09:25:18 [INFO] train episode 14182: reward = -71.69, steps = 29 09:25:20 [INFO] train episode 14183: reward = -91.33, steps = 28 09:25:23 [INFO] train episode 14184: reward = -114.75, steps = 27 09:25:24 [INFO] train episode 14185: reward = -77.84, steps = 21 09:25:27 [INFO] train episode 14186: reward = -58.66, steps = 30 09:25:29 [INFO] train episode 14187: reward = -107.32, steps = 21 09:25:31 [INFO] train episode 14188: reward = -84.35, steps = 20 09:25:33 [INFO] train episode 14189: reward = -59.96, steps = 30 09:25:35 [INFO] train episode 14190: reward = -94.16, steps = 23 09:25:37 [INFO] train episode 14191: reward = -91.84, steps = 25 09:25:40 [INFO] train episode 14192: reward = -112.19, steps = 29 09:25:42 [INFO] train episode 14193: reward = -140.62, steps = 25 09:25:45 [INFO] train episode 14194: reward = -116.99, steps = 35 09:25:47 [INFO] train episode 14195: reward = -72.23, steps = 20 09:25:49 [INFO] train episode 14196: reward = -123.17, steps = 25 09:25:51 [INFO] train episode 14197: reward = -113.34, steps = 23 09:25:53 [INFO] train episode 14198: reward = -84.39, steps = 23 09:25:56 [INFO] train episode 14199: reward = -126.71, steps = 29 09:25:58 [INFO] train episode 14200: reward = -79.72, steps = 32 09:26:01 [INFO] train episode 14201: reward = -95.57, steps = 25 09:26:03 [INFO] train episode 14202: reward = -95.41, steps = 20 09:26:04 [INFO] train episode 14203: reward = -94.30, steps = 21 09:26:08 [INFO] train episode 14204: reward = -155.22, steps = 48 09:26:11 [INFO] train episode 14205: reward = -134.91, steps = 30 09:26:13 [INFO] train episode 14206: reward = -80.97, steps = 27 09:26:16 [INFO] train episode 14207: reward = -92.29, steps = 26 09:26:17 [INFO] train episode 14208: reward = -116.92, steps = 19 09:26:20 [INFO] train episode 14209: reward = -134.49, steps = 32 09:26:23 [INFO] train episode 14210: reward = -85.08, steps = 27 09:26:24 [INFO] train episode 14211: reward = -123.59, steps = 20 09:26:26 [INFO] train episode 14212: reward = -111.75, steps = 20 09:26:29 [INFO] train episode 14213: reward = -106.62, steps = 33 09:26:33 [INFO] train episode 14214: reward = -116.22, steps = 41 09:26:34 [INFO] train episode 14215: reward = -104.18, steps = 21 09:26:38 [INFO] train episode 14216: reward = -84.20, steps = 45 09:26:41 [INFO] train episode 14217: reward = -78.70, steps = 28 09:26:43 [INFO] train episode 14218: reward = -96.41, steps = 29 09:26:45 [INFO] train episode 14219: reward = -130.70, steps = 18 09:26:47 [INFO] train episode 14220: reward = -95.60, steps = 24 09:26:49 [INFO] train episode 14221: reward = -84.95, steps = 22 09:26:51 [INFO] train episode 14222: reward = -91.82, steps = 23 09:26:53 [INFO] train episode 14223: reward = -76.78, steps = 25 09:26:55 [INFO] train episode 14224: reward = -65.50, steps = 21 09:26:59 [INFO] train episode 14225: reward = -139.01, steps = 44 09:27:01 [INFO] train episode 14226: reward = -85.62, steps = 20 09:27:03 [INFO] train episode 14227: reward = -80.47, steps = 18 09:27:06 [INFO] train episode 14228: reward = -117.80, steps = 29 09:27:08 [INFO] train episode 14229: reward = -103.57, steps = 24 09:27:11 [INFO] train episode 14230: reward = -152.78, steps = 36 09:27:13 [INFO] train episode 14231: reward = -77.86, steps = 23 09:27:16 [INFO] train episode 14232: reward = -83.46, steps = 41 09:27:18 [INFO] train episode 14233: reward = -86.07, steps = 21 09:27:22 [INFO] train episode 14234: reward = -131.01, steps = 36 09:27:23 [INFO] train episode 14235: reward = -71.11, steps = 22 09:27:25 [INFO] train episode 14236: reward = -96.78, steps = 22 09:27:27 [INFO] train episode 14237: reward = -99.21, steps = 26 09:27:29 [INFO] train episode 14238: reward = -113.17, steps = 20 09:27:31 [INFO] train episode 14239: reward = -92.41, steps = 21 09:27:33 [INFO] train episode 14240: reward = -124.33, steps = 25 09:27:35 [INFO] train episode 14241: reward = -156.85, steps = 23 09:27:38 [INFO] train episode 14242: reward = -96.41, steps = 24 09:27:40 [INFO] train episode 14243: reward = -99.86, steps = 23 09:27:42 [INFO] train episode 14244: reward = -92.69, steps = 29 09:27:44 [INFO] train episode 14245: reward = -92.39, steps = 19 09:27:46 [INFO] train episode 14246: reward = -178.32, steps = 25 09:27:48 [INFO] train episode 14247: reward = -64.94, steps = 20 09:27:50 [INFO] train episode 14248: reward = -103.70, steps = 29 09:27:53 [INFO] train episode 14249: reward = -90.93, steps = 27 09:27:55 [INFO] train episode 14250: reward = -82.97, steps = 22 09:27:56 [INFO] train episode 14251: reward = -179.11, steps = 20 09:27:59 [INFO] train episode 14252: reward = -106.43, steps = 27 09:28:01 [INFO] train episode 14253: reward = -77.86, steps = 23 09:28:03 [INFO] train episode 14254: reward = -108.01, steps = 24 09:28:06 [INFO] train episode 14255: reward = -125.52, steps = 41 09:28:08 [INFO] train episode 14256: reward = -78.93, steps = 23 09:28:10 [INFO] train episode 14257: reward = -76.71, steps = 19 09:28:12 [INFO] train episode 14258: reward = -71.61, steps = 22 09:28:14 [INFO] train episode 14259: reward = -87.34, steps = 20 09:28:16 [INFO] train episode 14260: reward = -105.43, steps = 27 09:28:18 [INFO] train episode 14261: reward = -119.06, steps = 25 09:28:21 [INFO] train episode 14262: reward = -94.46, steps = 34 09:28:23 [INFO] train episode 14263: reward = -76.08, steps = 22 09:28:26 [INFO] train episode 14264: reward = -132.99, steps = 37 09:28:28 [INFO] train episode 14265: reward = -159.47, steps = 21 09:28:30 [INFO] train episode 14266: reward = -76.27, steps = 18 09:28:31 [INFO] train episode 14267: reward = -92.33, steps = 20 09:28:33 [INFO] train episode 14268: reward = -101.14, steps = 20 09:28:35 [INFO] train episode 14269: reward = -87.38, steps = 27 09:28:37 [INFO] train episode 14270: reward = -120.20, steps = 20 09:28:40 [INFO] train episode 14271: reward = -130.74, steps = 29 09:28:42 [INFO] train episode 14272: reward = -94.21, steps = 28 09:28:48 [INFO] train episode 14273: reward = -118.16, steps = 74 09:28:52 [INFO] train episode 14274: reward = -106.37, steps = 38 09:28:54 [INFO] train episode 14275: reward = -94.24, steps = 18 09:28:55 [INFO] train episode 14276: reward = -110.97, steps = 20 09:28:59 [INFO] train episode 14277: reward = -113.09, steps = 40 09:29:01 [INFO] train episode 14278: reward = -100.95, steps = 31 09:29:04 [INFO] train episode 14279: reward = -90.80, steps = 26 09:29:06 [INFO] train episode 14280: reward = -145.86, steps = 21 09:29:08 [INFO] train episode 14281: reward = -102.61, steps = 26 09:29:10 [INFO] train episode 14282: reward = -140.67, steps = 19 09:29:12 [INFO] train episode 14283: reward = -78.63, steps = 20 09:29:15 [INFO] train episode 14284: reward = -142.33, steps = 39 09:29:17 [INFO] train episode 14285: reward = -99.10, steps = 21 09:29:19 [INFO] train episode 14286: reward = -88.30, steps = 21 09:29:20 [INFO] train episode 14287: reward = -57.20, steps = 20 09:29:22 [INFO] train episode 14288: reward = -114.55, steps = 22 09:29:24 [INFO] train episode 14289: reward = -112.42, steps = 19 09:29:26 [INFO] train episode 14290: reward = -97.33, steps = 23 09:29:28 [INFO] train episode 14291: reward = -109.48, steps = 25 09:29:31 [INFO] train episode 14292: reward = -97.02, steps = 29 09:29:33 [INFO] train episode 14293: reward = -94.36, steps = 26 09:29:35 [INFO] train episode 14294: reward = -71.34, steps = 27 09:29:37 [INFO] train episode 14295: reward = -68.01, steps = 20 09:29:39 [INFO] train episode 14296: reward = -65.18, steps = 25 09:29:44 [INFO] train episode 14297: reward = -192.66, steps = 52 09:29:46 [INFO] train episode 14298: reward = -114.07, steps = 21 09:29:49 [INFO] train episode 14299: reward = -82.91, steps = 32 09:29:51 [INFO] train episode 14300: reward = -131.71, steps = 26 09:29:53 [INFO] train episode 14301: reward = -87.82, steps = 20 09:29:55 [INFO] train episode 14302: reward = -62.13, steps = 20 09:29:58 [INFO] train episode 14303: reward = -88.11, steps = 32 09:30:00 [INFO] train episode 14304: reward = -133.82, steps = 24 09:30:02 [INFO] train episode 14305: reward = -135.16, steps = 24 09:30:04 [INFO] train episode 14306: reward = -85.26, steps = 19 09:30:12 [INFO] train episode 14307: reward = -214.69, steps = 100 09:30:15 [INFO] train episode 14308: reward = -95.36, steps = 30 09:30:18 [INFO] train episode 14309: reward = -88.05, steps = 35 09:30:19 [INFO] train episode 14310: reward = -89.74, steps = 20 09:30:21 [INFO] train episode 14311: reward = -90.91, steps = 21 09:30:23 [INFO] train episode 14312: reward = -86.59, steps = 23 09:30:26 [INFO] train episode 14313: reward = -149.59, steps = 27 09:30:27 [INFO] train episode 14314: reward = -99.99, steps = 19 09:30:30 [INFO] train episode 14315: reward = -138.79, steps = 27 09:30:32 [INFO] train episode 14316: reward = -78.04, steps = 28 09:30:34 [INFO] train episode 14317: reward = -87.11, steps = 23 09:30:38 [INFO] train episode 14318: reward = -68.60, steps = 43 09:30:40 [INFO] train episode 14319: reward = -151.88, steps = 26 09:30:42 [INFO] train episode 14320: reward = -77.98, steps = 20 09:30:45 [INFO] train episode 14321: reward = -64.14, steps = 30 09:30:47 [INFO] train episode 14322: reward = -103.33, steps = 32 09:30:49 [INFO] train episode 14323: reward = -75.24, steps = 22 09:30:51 [INFO] train episode 14324: reward = -95.35, steps = 20 09:30:53 [INFO] train episode 14325: reward = -113.43, steps = 21 09:30:55 [INFO] train episode 14326: reward = -129.52, steps = 21 09:30:57 [INFO] train episode 14327: reward = -71.38, steps = 24 09:30:59 [INFO] train episode 14328: reward = -132.67, steps = 25 09:31:01 [INFO] train episode 14329: reward = -78.47, steps = 19 09:31:03 [INFO] train episode 14330: reward = -85.96, steps = 22 09:31:05 [INFO] train episode 14331: reward = -83.68, steps = 22 09:31:07 [INFO] train episode 14332: reward = -108.14, steps = 21 09:31:09 [INFO] train episode 14333: reward = -104.22, steps = 21 09:31:10 [INFO] train episode 14334: reward = -111.27, steps = 23 09:31:12 [INFO] train episode 14335: reward = -118.05, steps = 23 09:31:14 [INFO] train episode 14336: reward = -86.77, steps = 20 09:31:16 [INFO] train episode 14337: reward = -87.92, steps = 19 09:31:18 [INFO] train episode 14338: reward = -126.60, steps = 25 09:31:20 [INFO] train episode 14339: reward = -120.63, steps = 23 09:31:22 [INFO] train episode 14340: reward = -73.18, steps = 19 09:31:24 [INFO] train episode 14341: reward = -74.52, steps = 29 09:31:26 [INFO] train episode 14342: reward = -142.16, steps = 23 09:31:28 [INFO] train episode 14343: reward = -123.50, steps = 20 09:31:31 [INFO] train episode 14344: reward = -111.13, steps = 31 09:31:33 [INFO] train episode 14345: reward = -103.15, steps = 25 09:31:36 [INFO] train episode 14346: reward = -109.85, steps = 38 09:31:39 [INFO] train episode 14347: reward = -106.47, steps = 32 09:31:41 [INFO] train episode 14348: reward = -129.97, steps = 24 09:31:43 [INFO] train episode 14349: reward = -75.56, steps = 21 09:31:44 [INFO] train episode 14350: reward = -84.46, steps = 19 09:31:46 [INFO] train episode 14351: reward = -121.75, steps = 20 09:31:48 [INFO] train episode 14352: reward = -106.85, steps = 21 09:31:51 [INFO] train episode 14353: reward = -69.61, steps = 25 09:31:53 [INFO] train episode 14354: reward = -94.99, steps = 24 09:31:54 [INFO] train episode 14355: reward = -86.55, steps = 19 09:31:56 [INFO] train episode 14356: reward = -128.00, steps = 26 09:31:59 [INFO] train episode 14357: reward = -102.52, steps = 29 09:32:01 [INFO] train episode 14358: reward = -123.75, steps = 30 09:32:04 [INFO] train episode 14359: reward = -115.43, steps = 25 09:32:06 [INFO] train episode 14360: reward = -92.93, steps = 24 09:32:08 [INFO] train episode 14361: reward = -87.97, steps = 18 09:32:10 [INFO] train episode 14362: reward = -93.07, steps = 21 09:32:12 [INFO] train episode 14363: reward = -92.60, steps = 22 09:32:13 [INFO] train episode 14364: reward = -78.64, steps = 19 09:32:16 [INFO] train episode 14365: reward = -111.40, steps = 35 09:32:18 [INFO] train episode 14366: reward = -85.23, steps = 25 09:32:23 [INFO] train episode 14367: reward = -138.44, steps = 50 09:32:25 [INFO] train episode 14368: reward = -72.27, steps = 21 09:32:26 [INFO] train episode 14369: reward = -146.24, steps = 20 09:32:28 [INFO] train episode 14370: reward = -106.01, steps = 23 09:32:30 [INFO] train episode 14371: reward = -76.71, steps = 20 09:32:32 [INFO] train episode 14372: reward = -128.11, steps = 24 09:32:34 [INFO] train episode 14373: reward = -109.73, steps = 20 09:32:37 [INFO] train episode 14374: reward = -132.64, steps = 35 09:32:41 [INFO] train episode 14375: reward = -116.08, steps = 32 09:32:43 [INFO] train episode 14376: reward = -89.44, steps = 29 09:32:46 [INFO] train episode 14377: reward = -120.20, steps = 31 09:32:48 [INFO] train episode 14378: reward = -103.55, steps = 31 09:32:51 [INFO] train episode 14379: reward = -105.82, steps = 27 09:32:53 [INFO] train episode 14380: reward = -103.43, steps = 24 09:32:56 [INFO] train episode 14381: reward = -121.89, steps = 31 09:32:58 [INFO] train episode 14382: reward = -88.66, steps = 21 09:33:00 [INFO] train episode 14383: reward = -85.13, steps = 29 09:33:02 [INFO] train episode 14384: reward = -115.64, steps = 25 09:33:05 [INFO] train episode 14385: reward = -110.08, steps = 38 09:33:07 [INFO] train episode 14386: reward = -98.23, steps = 19 09:33:09 [INFO] train episode 14387: reward = -152.18, steps = 23 09:33:11 [INFO] train episode 14388: reward = -140.81, steps = 25 09:33:13 [INFO] train episode 14389: reward = -109.06, steps = 22 09:33:15 [INFO] train episode 14390: reward = -73.70, steps = 20 09:33:17 [INFO] train episode 14391: reward = -96.52, steps = 20 09:33:19 [INFO] train episode 14392: reward = -58.58, steps = 22 09:33:20 [INFO] train episode 14393: reward = -59.09, steps = 21 09:33:23 [INFO] train episode 14394: reward = -91.07, steps = 25 09:33:26 [INFO] train episode 14395: reward = -150.00, steps = 35 09:33:28 [INFO] train episode 14396: reward = -116.13, steps = 24 09:33:30 [INFO] train episode 14397: reward = -90.19, steps = 23 09:33:32 [INFO] train episode 14398: reward = -102.91, steps = 28 09:33:34 [INFO] train episode 14399: reward = -73.43, steps = 19 09:33:36 [INFO] train episode 14400: reward = -75.63, steps = 30 09:33:39 [INFO] train episode 14401: reward = -74.10, steps = 21 09:33:40 [INFO] train episode 14402: reward = -76.76, steps = 19 09:33:42 [INFO] train episode 14403: reward = -88.28, steps = 25 09:33:45 [INFO] train episode 14404: reward = -125.25, steps = 34 09:33:47 [INFO] train episode 14405: reward = -99.19, steps = 25 09:33:49 [INFO] train episode 14406: reward = -71.58, steps = 22 09:33:52 [INFO] train episode 14407: reward = -81.22, steps = 27 09:33:53 [INFO] train episode 14408: reward = -97.69, steps = 19 09:33:55 [INFO] train episode 14409: reward = -106.16, steps = 19 09:33:57 [INFO] train episode 14410: reward = -100.96, steps = 22 09:34:00 [INFO] train episode 14411: reward = -133.80, steps = 35 09:34:02 [INFO] train episode 14412: reward = -108.22, steps = 21 09:34:04 [INFO] train episode 14413: reward = -107.84, steps = 21 09:34:06 [INFO] train episode 14414: reward = -101.33, steps = 29 09:34:08 [INFO] train episode 14415: reward = -86.45, steps = 23 09:34:11 [INFO] train episode 14416: reward = -113.87, steps = 31 09:34:13 [INFO] train episode 14417: reward = -122.09, steps = 27 09:34:16 [INFO] train episode 14418: reward = -147.32, steps = 36 09:34:19 [INFO] train episode 14419: reward = -120.93, steps = 32 09:34:21 [INFO] train episode 14420: reward = -68.11, steps = 19 09:34:23 [INFO] train episode 14421: reward = -119.72, steps = 24 09:34:25 [INFO] train episode 14422: reward = -79.68, steps = 22 09:34:28 [INFO] train episode 14423: reward = -120.69, steps = 30 09:34:29 [INFO] train episode 14424: reward = -96.84, steps = 19 09:34:32 [INFO] train episode 14425: reward = -132.27, steps = 28 09:34:35 [INFO] train episode 14426: reward = -111.69, steps = 35 09:34:36 [INFO] train episode 14427: reward = -89.95, steps = 20 09:34:39 [INFO] train episode 14428: reward = -98.13, steps = 25 09:34:41 [INFO] train episode 14429: reward = -110.62, steps = 25 09:34:43 [INFO] train episode 14430: reward = -77.15, steps = 20 09:34:44 [INFO] train episode 14431: reward = -93.01, steps = 20 09:34:47 [INFO] train episode 14432: reward = -86.21, steps = 29 09:34:49 [INFO] train episode 14433: reward = -100.86, steps = 24 09:34:51 [INFO] train episode 14434: reward = -105.48, steps = 27 09:34:54 [INFO] train episode 14435: reward = -98.48, steps = 29 09:34:57 [INFO] train episode 14436: reward = -102.96, steps = 36 09:34:59 [INFO] train episode 14437: reward = -71.03, steps = 20 09:35:01 [INFO] train episode 14438: reward = -82.86, steps = 19 09:35:04 [INFO] train episode 14439: reward = -109.79, steps = 35 09:35:06 [INFO] train episode 14440: reward = -86.84, steps = 24 09:35:08 [INFO] train episode 14441: reward = -96.29, steps = 35 09:35:10 [INFO] train episode 14442: reward = -96.74, steps = 20 09:35:13 [INFO] train episode 14443: reward = -144.92, steps = 34 09:35:15 [INFO] train episode 14444: reward = -65.29, steps = 22 09:35:17 [INFO] train episode 14445: reward = -93.06, steps = 25 09:35:19 [INFO] train episode 14446: reward = -118.74, steps = 19 09:35:21 [INFO] train episode 14447: reward = -119.44, steps = 20 09:35:23 [INFO] train episode 14448: reward = -79.46, steps = 23 09:35:25 [INFO] train episode 14449: reward = -100.93, steps = 29 09:35:27 [INFO] train episode 14450: reward = -79.16, steps = 18 09:35:30 [INFO] train episode 14451: reward = -120.63, steps = 22 09:35:32 [INFO] train episode 14452: reward = -107.24, steps = 21 09:35:34 [INFO] train episode 14453: reward = -88.09, steps = 27 09:35:37 [INFO] train episode 14454: reward = -91.09, steps = 36 09:35:39 [INFO] train episode 14455: reward = -86.48, steps = 20 09:35:41 [INFO] train episode 14456: reward = -81.15, steps = 27 09:35:43 [INFO] train episode 14457: reward = -104.74, steps = 24 09:35:46 [INFO] train episode 14458: reward = -78.93, steps = 28 09:35:47 [INFO] train episode 14459: reward = -116.84, steps = 19 09:35:49 [INFO] train episode 14460: reward = -99.47, steps = 22 09:35:51 [INFO] train episode 14461: reward = -98.30, steps = 23 09:35:56 [INFO] train episode 14462: reward = -143.86, steps = 59 09:35:58 [INFO] train episode 14463: reward = -88.61, steps = 20 09:36:01 [INFO] train episode 14464: reward = -119.11, steps = 36 09:36:04 [INFO] train episode 14465: reward = -117.57, steps = 29 09:36:07 [INFO] train episode 14466: reward = -132.98, steps = 37 09:36:10 [INFO] train episode 14467: reward = -91.04, steps = 32 09:36:12 [INFO] train episode 14468: reward = -93.09, steps = 25 09:36:14 [INFO] train episode 14469: reward = -109.57, steps = 23 09:36:15 [INFO] train episode 14470: reward = -107.65, steps = 20 09:36:18 [INFO] train episode 14471: reward = -67.80, steps = 26 09:36:20 [INFO] train episode 14472: reward = -101.37, steps = 21 09:36:21 [INFO] train episode 14473: reward = -90.19, steps = 19 09:36:24 [INFO] train episode 14474: reward = -90.68, steps = 27 09:36:26 [INFO] train episode 14475: reward = -112.39, steps = 30 09:36:28 [INFO] train episode 14476: reward = -115.18, steps = 27 09:36:30 [INFO] train episode 14477: reward = -95.51, steps = 19 09:36:32 [INFO] train episode 14478: reward = -135.85, steps = 26 09:36:35 [INFO] train episode 14479: reward = -147.26, steps = 31 09:36:37 [INFO] train episode 14480: reward = -108.08, steps = 21 09:36:39 [INFO] train episode 14481: reward = -98.48, steps = 28 09:36:41 [INFO] train episode 14482: reward = -90.59, steps = 22 09:36:44 [INFO] train episode 14483: reward = -98.29, steps = 26 09:36:46 [INFO] train episode 14484: reward = -130.00, steps = 29 09:36:48 [INFO] train episode 14485: reward = -87.57, steps = 21 09:36:50 [INFO] train episode 14486: reward = -99.12, steps = 20 09:36:53 [INFO] train episode 14487: reward = -96.72, steps = 36 09:36:57 [INFO] train episode 14488: reward = -122.08, steps = 47 09:36:59 [INFO] train episode 14489: reward = -104.86, steps = 22 09:37:01 [INFO] train episode 14490: reward = -121.64, steps = 28 09:37:03 [INFO] train episode 14491: reward = -81.60, steps = 19 09:37:05 [INFO] train episode 14492: reward = -100.13, steps = 27 09:37:07 [INFO] train episode 14493: reward = -123.04, steps = 21 09:37:09 [INFO] train episode 14494: reward = -74.69, steps = 19 09:37:11 [INFO] train episode 14495: reward = -101.11, steps = 30 09:37:13 [INFO] train episode 14496: reward = -149.73, steps = 20 09:37:16 [INFO] train episode 14497: reward = -88.88, steps = 30 09:37:17 [INFO] train episode 14498: reward = -92.68, steps = 19 09:37:20 [INFO] train episode 14499: reward = -90.54, steps = 29 09:37:22 [INFO] train episode 14500: reward = -105.85, steps = 19 09:37:24 [INFO] train episode 14501: reward = -136.03, steps = 19 09:37:26 [INFO] train episode 14502: reward = -109.71, steps = 31 09:37:28 [INFO] train episode 14503: reward = -87.66, steps = 20 09:37:30 [INFO] train episode 14504: reward = -146.55, steps = 26 09:37:32 [INFO] train episode 14505: reward = -85.73, steps = 24 09:37:34 [INFO] train episode 14506: reward = -58.45, steps = 20 09:37:36 [INFO] train episode 14507: reward = -119.01, steps = 25 09:37:40 [INFO] train episode 14508: reward = -138.67, steps = 43 09:37:42 [INFO] train episode 14509: reward = -157.51, steps = 27 09:37:44 [INFO] train episode 14510: reward = -95.86, steps = 20 09:37:46 [INFO] train episode 14511: reward = -63.60, steps = 22 09:37:48 [INFO] train episode 14512: reward = -99.49, steps = 26 09:37:52 [INFO] train episode 14513: reward = -72.37, steps = 37 09:37:53 [INFO] train episode 14514: reward = -85.41, steps = 21 09:37:55 [INFO] train episode 14515: reward = -87.94, steps = 21 09:37:58 [INFO] train episode 14516: reward = -119.87, steps = 34 09:38:00 [INFO] train episode 14517: reward = -135.65, steps = 20 09:38:02 [INFO] train episode 14518: reward = -92.00, steps = 24 09:38:04 [INFO] train episode 14519: reward = -53.67, steps = 23 09:38:05 [INFO] train episode 14520: reward = -115.09, steps = 19 09:38:08 [INFO] train episode 14521: reward = -90.72, steps = 25 09:38:11 [INFO] train episode 14522: reward = -115.57, steps = 32 09:38:12 [INFO] train episode 14523: reward = -96.55, steps = 19 09:38:14 [INFO] train episode 14524: reward = -102.47, steps = 22 09:38:16 [INFO] train episode 14525: reward = -115.91, steps = 24 09:38:20 [INFO] train episode 14526: reward = -140.61, steps = 34 09:38:22 [INFO] train episode 14527: reward = -75.73, steps = 23 09:38:25 [INFO] train episode 14528: reward = -124.09, steps = 36 09:38:28 [INFO] train episode 14529: reward = -149.94, steps = 39 09:38:32 [INFO] train episode 14530: reward = -136.97, steps = 48 09:38:35 [INFO] train episode 14531: reward = -81.46, steps = 36 09:38:37 [INFO] train episode 14532: reward = -128.86, steps = 21 09:38:39 [INFO] train episode 14533: reward = -124.46, steps = 20 09:38:42 [INFO] train episode 14534: reward = -96.30, steps = 29 09:38:44 [INFO] train episode 14535: reward = -147.12, steps = 21 09:38:47 [INFO] train episode 14536: reward = -111.72, steps = 39 09:38:49 [INFO] train episode 14537: reward = -82.81, steps = 22 09:38:51 [INFO] train episode 14538: reward = -130.18, steps = 26 09:38:53 [INFO] train episode 14539: reward = -181.06, steps = 26 09:38:55 [INFO] train episode 14540: reward = -90.02, steps = 21 09:39:02 [INFO] train episode 14541: reward = -212.34, steps = 74 09:39:03 [INFO] train episode 14542: reward = -89.71, steps = 20 09:39:05 [INFO] train episode 14543: reward = -97.20, steps = 22 09:39:08 [INFO] train episode 14544: reward = -130.71, steps = 28 09:39:10 [INFO] train episode 14545: reward = -102.54, steps = 28 09:39:12 [INFO] train episode 14546: reward = -110.19, steps = 26 09:39:14 [INFO] train episode 14547: reward = -109.38, steps = 23 09:39:17 [INFO] train episode 14548: reward = -124.44, steps = 29 09:39:19 [INFO] train episode 14549: reward = -115.88, steps = 22 09:39:21 [INFO] train episode 14550: reward = -102.30, steps = 25 09:39:23 [INFO] train episode 14551: reward = -99.22, steps = 19 09:39:26 [INFO] train episode 14552: reward = -86.89, steps = 41 09:39:29 [INFO] train episode 14553: reward = -93.47, steps = 28 09:39:31 [INFO] train episode 14554: reward = -83.81, steps = 28 09:39:33 [INFO] train episode 14555: reward = -67.84, steps = 21 09:39:35 [INFO] train episode 14556: reward = -116.07, steps = 32 09:39:37 [INFO] train episode 14557: reward = -96.59, steps = 22 09:39:40 [INFO] train episode 14558: reward = -111.01, steps = 28 09:39:42 [INFO] train episode 14559: reward = -100.14, steps = 23 09:39:44 [INFO] train episode 14560: reward = -120.66, steps = 19 09:39:45 [INFO] train episode 14561: reward = -80.10, steps = 20 09:39:48 [INFO] train episode 14562: reward = -121.52, steps = 31 09:39:50 [INFO] train episode 14563: reward = -149.59, steps = 20 09:39:52 [INFO] train episode 14564: reward = -66.96, steps = 23 09:39:54 [INFO] train episode 14565: reward = -105.08, steps = 23 09:39:55 [INFO] train episode 14566: reward = -82.15, steps = 21 09:39:58 [INFO] train episode 14567: reward = -105.84, steps = 28 09:40:00 [INFO] train episode 14568: reward = -58.97, steps = 19 09:40:02 [INFO] train episode 14569: reward = -99.92, steps = 27 09:40:06 [INFO] train episode 14570: reward = -225.29, steps = 45 09:40:08 [INFO] train episode 14571: reward = -102.68, steps = 27 09:40:11 [INFO] train episode 14572: reward = -108.53, steps = 27 09:40:13 [INFO] train episode 14573: reward = -104.81, steps = 21 09:40:14 [INFO] train episode 14574: reward = -109.26, steps = 20 09:40:18 [INFO] train episode 14575: reward = -154.73, steps = 41 09:40:20 [INFO] train episode 14576: reward = -78.51, steps = 24 09:40:22 [INFO] train episode 14577: reward = -81.60, steps = 30 09:40:24 [INFO] train episode 14578: reward = -139.60, steps = 24 09:40:26 [INFO] train episode 14579: reward = -61.90, steps = 21 09:40:28 [INFO] train episode 14580: reward = -91.51, steps = 20 09:40:30 [INFO] train episode 14581: reward = -93.94, steps = 20 09:40:32 [INFO] train episode 14582: reward = -55.61, steps = 21 09:40:34 [INFO] train episode 14583: reward = -151.03, steps = 30 09:40:37 [INFO] train episode 14584: reward = -131.41, steps = 26 09:40:39 [INFO] train episode 14585: reward = -124.83, steps = 26 09:40:41 [INFO] train episode 14586: reward = -97.30, steps = 22 09:40:43 [INFO] train episode 14587: reward = -111.15, steps = 21 09:40:46 [INFO] train episode 14588: reward = -133.08, steps = 31 09:40:48 [INFO] train episode 14589: reward = -112.09, steps = 22 09:40:49 [INFO] train episode 14590: reward = -101.06, steps = 20 09:40:51 [INFO] train episode 14591: reward = -121.19, steps = 18 09:40:53 [INFO] train episode 14592: reward = -88.54, steps = 27 09:40:55 [INFO] train episode 14593: reward = -99.46, steps = 22 09:40:57 [INFO] train episode 14594: reward = -124.34, steps = 25 09:40:59 [INFO] train episode 14595: reward = -105.17, steps = 23 09:41:02 [INFO] train episode 14596: reward = -97.76, steps = 27 09:41:04 [INFO] train episode 14597: reward = -139.46, steps = 20 09:41:05 [INFO] train episode 14598: reward = -82.34, steps = 21 09:41:07 [INFO] train episode 14599: reward = -77.31, steps = 18 09:41:09 [INFO] train episode 14600: reward = -105.90, steps = 22 09:41:11 [INFO] train episode 14601: reward = -79.87, steps = 21 09:41:13 [INFO] train episode 14602: reward = -110.37, steps = 21 09:41:18 [INFO] train episode 14603: reward = -147.88, steps = 50 09:41:19 [INFO] train episode 14604: reward = -108.11, steps = 20 09:41:21 [INFO] train episode 14605: reward = -94.97, steps = 20 09:41:23 [INFO] train episode 14606: reward = -117.74, steps = 20 09:41:25 [INFO] train episode 14607: reward = -101.50, steps = 22 09:41:28 [INFO] train episode 14608: reward = -119.11, steps = 37 09:41:30 [INFO] train episode 14609: reward = -97.96, steps = 20 09:41:32 [INFO] train episode 14610: reward = -140.70, steps = 28 09:41:35 [INFO] train episode 14611: reward = -112.53, steps = 29 09:41:36 [INFO] train episode 14612: reward = -81.98, steps = 19 09:41:39 [INFO] train episode 14613: reward = -96.06, steps = 26 09:41:41 [INFO] train episode 14614: reward = -101.54, steps = 29 09:41:43 [INFO] train episode 14615: reward = -89.79, steps = 28 09:41:46 [INFO] train episode 14616: reward = -75.68, steps = 27 09:41:48 [INFO] train episode 14617: reward = -92.88, steps = 23 09:41:50 [INFO] train episode 14618: reward = -71.55, steps = 20 09:41:53 [INFO] train episode 14619: reward = -107.29, steps = 39 09:41:55 [INFO] train episode 14620: reward = -110.07, steps = 25 09:41:57 [INFO] train episode 14621: reward = -104.93, steps = 20 09:41:59 [INFO] train episode 14622: reward = -95.90, steps = 21 09:42:01 [INFO] train episode 14623: reward = -118.37, steps = 28 09:42:03 [INFO] train episode 14624: reward = -111.58, steps = 20 09:42:05 [INFO] train episode 14625: reward = -86.65, steps = 27 09:42:07 [INFO] train episode 14626: reward = -102.62, steps = 22 09:42:09 [INFO] train episode 14627: reward = -108.36, steps = 22 09:42:11 [INFO] train episode 14628: reward = -123.04, steps = 22 09:42:14 [INFO] train episode 14629: reward = -155.52, steps = 30 09:42:15 [INFO] train episode 14630: reward = -97.56, steps = 20 09:42:17 [INFO] train episode 14631: reward = -90.72, steps = 21 09:42:20 [INFO] train episode 14632: reward = -135.23, steps = 28 09:42:23 [INFO] train episode 14633: reward = -97.61, steps = 34 09:42:26 [INFO] train episode 14634: reward = -117.31, steps = 33 09:42:27 [INFO] train episode 14635: reward = -88.44, steps = 21 09:42:29 [INFO] train episode 14636: reward = -81.66, steps = 22 09:42:31 [INFO] train episode 14637: reward = -98.14, steps = 21 09:42:33 [INFO] train episode 14638: reward = -125.54, steps = 22 09:42:36 [INFO] train episode 14639: reward = -103.43, steps = 33 09:42:38 [INFO] train episode 14640: reward = -108.53, steps = 23 09:42:41 [INFO] train episode 14641: reward = -110.93, steps = 26 09:42:42 [INFO] train episode 14642: reward = -110.51, steps = 20 09:42:44 [INFO] train episode 14643: reward = -100.19, steps = 24 09:42:48 [INFO] train episode 14644: reward = -88.50, steps = 44 09:42:51 [INFO] train episode 14645: reward = -120.09, steps = 31 09:42:53 [INFO] train episode 14646: reward = -106.95, steps = 28 09:42:55 [INFO] train episode 14647: reward = -91.54, steps = 20 09:42:57 [INFO] train episode 14648: reward = -90.09, steps = 19 09:42:58 [INFO] train episode 14649: reward = -73.57, steps = 21 09:43:00 [INFO] train episode 14650: reward = -67.65, steps = 20 09:43:03 [INFO] train episode 14651: reward = -112.81, steps = 33 09:43:06 [INFO] train episode 14652: reward = -91.20, steps = 32 09:43:08 [INFO] train episode 14653: reward = -81.87, steps = 22 09:43:10 [INFO] train episode 14654: reward = -103.16, steps = 21 09:43:11 [INFO] train episode 14655: reward = -122.03, steps = 22 09:43:13 [INFO] train episode 14656: reward = -74.14, steps = 20 09:43:15 [INFO] train episode 14657: reward = -95.64, steps = 21 09:43:17 [INFO] train episode 14658: reward = -81.73, steps = 23 09:43:19 [INFO] train episode 14659: reward = -109.73, steps = 29 09:43:21 [INFO] train episode 14660: reward = -84.13, steps = 19 09:43:23 [INFO] train episode 14661: reward = -95.67, steps = 21 09:43:27 [INFO] train episode 14662: reward = -142.00, steps = 43 09:43:29 [INFO] train episode 14663: reward = -85.45, steps = 20 09:43:32 [INFO] train episode 14664: reward = -134.29, steps = 44 09:43:34 [INFO] train episode 14665: reward = -88.84, steps = 22 09:43:37 [INFO] train episode 14666: reward = -134.08, steps = 31 09:43:41 [INFO] train episode 14667: reward = -179.63, steps = 48 09:43:43 [INFO] train episode 14668: reward = -98.81, steps = 24 09:43:45 [INFO] train episode 14669: reward = -104.19, steps = 19 09:43:47 [INFO] train episode 14670: reward = -87.61, steps = 24 09:43:50 [INFO] train episode 14671: reward = -140.90, steps = 41 09:43:52 [INFO] train episode 14672: reward = -114.27, steps = 19 09:43:54 [INFO] train episode 14673: reward = -98.75, steps = 19 09:43:55 [INFO] train episode 14674: reward = -67.85, steps = 20 09:43:57 [INFO] train episode 14675: reward = -84.38, steps = 20 09:44:00 [INFO] train episode 14676: reward = -114.27, steps = 25 09:44:02 [INFO] train episode 14677: reward = -111.70, steps = 17 09:44:04 [INFO] train episode 14678: reward = -119.61, steps = 26 09:44:06 [INFO] train episode 14679: reward = -84.95, steps = 22 09:44:08 [INFO] train episode 14680: reward = -67.46, steps = 24 09:44:10 [INFO] train episode 14681: reward = -85.96, steps = 20 09:44:12 [INFO] train episode 14682: reward = -127.37, steps = 22 09:44:14 [INFO] train episode 14683: reward = -134.22, steps = 27 09:44:17 [INFO] train episode 14684: reward = -78.78, steps = 38 09:44:19 [INFO] train episode 14685: reward = -103.60, steps = 23 09:44:21 [INFO] train episode 14686: reward = -91.01, steps = 21 09:44:24 [INFO] train episode 14687: reward = -136.15, steps = 36 09:44:27 [INFO] train episode 14688: reward = -124.57, steps = 34 09:44:29 [INFO] train episode 14689: reward = -95.39, steps = 25 09:44:32 [INFO] train episode 14690: reward = -110.79, steps = 29 09:44:34 [INFO] train episode 14691: reward = -116.82, steps = 33 09:44:41 [INFO] train episode 14692: reward = -169.86, steps = 68 09:44:43 [INFO] train episode 14693: reward = -102.52, steps = 25 09:44:45 [INFO] train episode 14694: reward = -101.08, steps = 27 09:44:47 [INFO] train episode 14695: reward = -102.79, steps = 25 09:44:49 [INFO] train episode 14696: reward = -81.01, steps = 27 09:44:52 [INFO] train episode 14697: reward = -92.47, steps = 29 09:44:54 [INFO] train episode 14698: reward = -123.58, steps = 25 09:44:57 [INFO] train episode 14699: reward = -118.47, steps = 30 09:44:59 [INFO] train episode 14700: reward = -104.33, steps = 23 09:45:02 [INFO] train episode 14701: reward = -118.00, steps = 39 09:45:04 [INFO] train episode 14702: reward = -96.08, steps = 22 09:45:06 [INFO] train episode 14703: reward = -102.70, steps = 21 09:45:10 [INFO] train episode 14704: reward = -108.30, steps = 45 09:45:11 [INFO] train episode 14705: reward = -78.79, steps = 18 09:45:14 [INFO] train episode 14706: reward = -122.37, steps = 22 09:45:16 [INFO] train episode 14707: reward = -79.70, steps = 25 09:45:18 [INFO] train episode 14708: reward = -100.61, steps = 29 09:45:21 [INFO] train episode 14709: reward = -67.01, steps = 28 09:45:23 [INFO] train episode 14710: reward = -85.37, steps = 25 09:45:24 [INFO] train episode 14711: reward = -107.70, steps = 19 09:45:26 [INFO] train episode 14712: reward = -119.90, steps = 24 09:45:29 [INFO] train episode 14713: reward = -115.24, steps = 23 09:45:30 [INFO] train episode 14714: reward = -72.10, steps = 19 09:45:35 [INFO] train episode 14715: reward = -132.38, steps = 56 09:45:38 [INFO] train episode 14716: reward = -112.90, steps = 33 09:45:40 [INFO] train episode 14717: reward = -89.67, steps = 32 09:45:42 [INFO] train episode 14718: reward = -75.97, steps = 20 09:45:45 [INFO] train episode 14719: reward = -96.30, steps = 26 09:45:46 [INFO] train episode 14720: reward = -169.68, steps = 17 09:45:49 [INFO] train episode 14721: reward = -109.05, steps = 37 09:45:51 [INFO] train episode 14722: reward = -105.99, steps = 19 09:45:54 [INFO] train episode 14723: reward = -98.47, steps = 37 09:45:56 [INFO] train episode 14724: reward = -64.47, steps = 20 09:45:58 [INFO] train episode 14725: reward = -105.26, steps = 21 09:46:00 [INFO] train episode 14726: reward = -105.18, steps = 22 09:46:02 [INFO] train episode 14727: reward = -93.96, steps = 22 09:46:05 [INFO] train episode 14728: reward = -110.91, steps = 34 09:46:07 [INFO] train episode 14729: reward = -85.72, steps = 28 09:46:10 [INFO] train episode 14730: reward = -145.23, steps = 39 09:46:12 [INFO] train episode 14731: reward = -66.77, steps = 22 09:46:15 [INFO] train episode 14732: reward = -89.02, steps = 26 09:46:17 [INFO] train episode 14733: reward = -83.97, steps = 25 09:46:19 [INFO] train episode 14734: reward = -118.45, steps = 21 09:46:21 [INFO] train episode 14735: reward = -117.70, steps = 30 09:46:23 [INFO] train episode 14736: reward = -95.83, steps = 20 09:46:25 [INFO] train episode 14737: reward = -96.98, steps = 19 09:46:27 [INFO] train episode 14738: reward = -51.70, steps = 29 09:46:29 [INFO] train episode 14739: reward = -82.07, steps = 25 09:46:32 [INFO] train episode 14740: reward = -69.09, steps = 25 09:46:34 [INFO] train episode 14741: reward = -156.50, steps = 28 09:46:36 [INFO] train episode 14742: reward = -64.76, steps = 24 09:46:38 [INFO] train episode 14743: reward = -118.00, steps = 27 09:46:40 [INFO] train episode 14744: reward = -121.37, steps = 20 09:46:42 [INFO] train episode 14745: reward = -98.12, steps = 21 09:46:44 [INFO] train episode 14746: reward = -121.31, steps = 24 09:46:47 [INFO] train episode 14747: reward = -102.43, steps = 39 09:46:51 [INFO] train episode 14748: reward = -125.49, steps = 27 09:46:53 [INFO] train episode 14749: reward = -134.93, steps = 26 09:46:54 [INFO] train episode 14750: reward = -55.64, steps = 20 09:46:57 [INFO] train episode 14751: reward = -120.38, steps = 30 09:46:59 [INFO] train episode 14752: reward = -133.74, steps = 24 09:47:01 [INFO] train episode 14753: reward = -47.73, steps = 20 09:47:03 [INFO] train episode 14754: reward = -77.83, steps = 20 09:47:05 [INFO] train episode 14755: reward = -76.94, steps = 23 09:47:07 [INFO] train episode 14756: reward = -96.95, steps = 26 09:47:09 [INFO] train episode 14757: reward = -97.78, steps = 20 09:47:11 [INFO] train episode 14758: reward = -125.95, steps = 18 09:47:13 [INFO] train episode 14759: reward = -83.35, steps = 28 09:47:15 [INFO] train episode 14760: reward = -90.14, steps = 21 09:47:17 [INFO] train episode 14761: reward = -111.03, steps = 22 09:47:19 [INFO] train episode 14762: reward = -62.38, steps = 20 09:47:20 [INFO] train episode 14763: reward = -97.05, steps = 20 09:47:23 [INFO] train episode 14764: reward = -104.28, steps = 29 09:47:25 [INFO] train episode 14765: reward = -130.72, steps = 19 09:47:27 [INFO] train episode 14766: reward = -143.01, steps = 24 09:47:28 [INFO] train episode 14767: reward = -78.13, steps = 21 09:47:30 [INFO] train episode 14768: reward = -116.34, steps = 25 09:47:32 [INFO] train episode 14769: reward = -106.84, steps = 18 09:47:36 [INFO] train episode 14770: reward = -156.76, steps = 46 09:47:39 [INFO] train episode 14771: reward = -113.23, steps = 30 09:47:41 [INFO] train episode 14772: reward = -139.05, steps = 26 09:47:43 [INFO] train episode 14773: reward = -93.24, steps = 23 09:47:47 [INFO] train episode 14774: reward = -66.91, steps = 43 09:47:49 [INFO] train episode 14775: reward = -116.02, steps = 29 09:47:51 [INFO] train episode 14776: reward = -111.17, steps = 22 09:47:53 [INFO] train episode 14777: reward = -75.32, steps = 23 09:47:55 [INFO] train episode 14778: reward = -89.91, steps = 18 09:47:57 [INFO] train episode 14779: reward = -113.73, steps = 25 09:47:58 [INFO] train episode 14780: reward = -91.52, steps = 19 09:48:00 [INFO] train episode 14781: reward = -89.01, steps = 23 09:48:02 [INFO] train episode 14782: reward = -150.75, steps = 23 09:48:04 [INFO] train episode 14783: reward = -76.36, steps = 19 09:48:06 [INFO] train episode 14784: reward = -91.65, steps = 23 09:48:08 [INFO] train episode 14785: reward = -131.82, steps = 25 09:48:11 [INFO] train episode 14786: reward = -94.54, steps = 29 09:48:13 [INFO] train episode 14787: reward = -65.78, steps = 19 09:48:17 [INFO] train episode 14788: reward = -81.33, steps = 58 09:48:19 [INFO] train episode 14789: reward = -62.74, steps = 21 09:48:23 [INFO] train episode 14790: reward = -81.78, steps = 37 09:48:24 [INFO] train episode 14791: reward = -104.70, steps = 20 09:48:27 [INFO] train episode 14792: reward = -140.27, steps = 29 09:48:29 [INFO] train episode 14793: reward = -74.66, steps = 24 09:48:31 [INFO] train episode 14794: reward = -118.59, steps = 26 09:48:33 [INFO] train episode 14795: reward = -128.94, steps = 24 09:48:35 [INFO] train episode 14796: reward = -91.49, steps = 23 09:48:37 [INFO] train episode 14797: reward = -138.40, steps = 22 09:48:39 [INFO] train episode 14798: reward = -73.44, steps = 20 09:48:42 [INFO] train episode 14799: reward = -143.51, steps = 38 09:48:44 [INFO] train episode 14800: reward = -82.90, steps = 19 09:48:46 [INFO] train episode 14801: reward = -109.74, steps = 26 09:48:48 [INFO] train episode 14802: reward = -93.86, steps = 25 09:48:50 [INFO] train episode 14803: reward = -73.48, steps = 20 09:48:52 [INFO] train episode 14804: reward = -64.04, steps = 20 09:48:54 [INFO] train episode 14805: reward = -133.87, steps = 24 09:48:57 [INFO] train episode 14806: reward = -113.88, steps = 31 09:48:59 [INFO] train episode 14807: reward = -162.82, steps = 29 09:49:02 [INFO] train episode 14808: reward = -101.63, steps = 30 09:49:04 [INFO] train episode 14809: reward = -148.66, steps = 19 09:49:06 [INFO] train episode 14810: reward = -119.02, steps = 30 09:49:08 [INFO] train episode 14811: reward = -109.38, steps = 19 09:49:10 [INFO] train episode 14812: reward = -80.59, steps = 23 09:49:12 [INFO] train episode 14813: reward = -87.34, steps = 23 09:49:15 [INFO] train episode 14814: reward = -105.01, steps = 31 09:49:16 [INFO] train episode 14815: reward = -115.16, steps = 21 09:49:19 [INFO] train episode 14816: reward = -116.19, steps = 24 09:49:20 [INFO] train episode 14817: reward = -100.51, steps = 20 09:49:23 [INFO] train episode 14818: reward = -56.41, steps = 32 09:49:25 [INFO] train episode 14819: reward = -116.05, steps = 25 09:49:28 [INFO] train episode 14820: reward = -157.01, steps = 33 09:49:30 [INFO] train episode 14821: reward = -105.64, steps = 24 09:49:32 [INFO] train episode 14822: reward = -76.81, steps = 20 09:49:34 [INFO] train episode 14823: reward = -115.49, steps = 20 09:49:35 [INFO] train episode 14824: reward = -95.81, steps = 21 09:49:38 [INFO] train episode 14825: reward = -115.65, steps = 29 09:49:41 [INFO] train episode 14826: reward = -90.98, steps = 28 09:49:43 [INFO] train episode 14827: reward = -86.55, steps = 21 09:49:45 [INFO] train episode 14828: reward = -84.76, steps = 20 09:49:47 [INFO] train episode 14829: reward = -63.34, steps = 22 09:49:49 [INFO] train episode 14830: reward = -116.50, steps = 24 09:49:51 [INFO] train episode 14831: reward = -66.29, steps = 21 09:49:52 [INFO] train episode 14832: reward = -146.81, steps = 20 09:49:54 [INFO] train episode 14833: reward = -91.26, steps = 22 09:49:57 [INFO] train episode 14834: reward = -97.38, steps = 33 09:49:59 [INFO] train episode 14835: reward = -91.21, steps = 23 09:50:02 [INFO] train episode 14836: reward = -131.81, steps = 29 09:50:04 [INFO] train episode 14837: reward = -78.95, steps = 21 09:50:05 [INFO] train episode 14838: reward = -97.34, steps = 20 09:50:07 [INFO] train episode 14839: reward = -75.99, steps = 21 09:50:09 [INFO] train episode 14840: reward = -101.87, steps = 27 09:50:12 [INFO] train episode 14841: reward = -141.29, steps = 28 09:50:14 [INFO] train episode 14842: reward = -105.45, steps = 20 09:50:16 [INFO] train episode 14843: reward = -106.03, steps = 28 09:50:18 [INFO] train episode 14844: reward = -50.87, steps = 20 09:50:20 [INFO] train episode 14845: reward = -104.36, steps = 19 09:50:22 [INFO] train episode 14846: reward = -108.91, steps = 30 09:50:24 [INFO] train episode 14847: reward = -70.44, steps = 20 09:50:25 [INFO] train episode 14848: reward = -93.73, steps = 20 09:50:28 [INFO] train episode 14849: reward = -91.35, steps = 25 09:50:30 [INFO] train episode 14850: reward = -116.08, steps = 20 09:50:31 [INFO] train episode 14851: reward = -67.60, steps = 20 09:50:33 [INFO] train episode 14852: reward = -109.61, steps = 22 09:50:35 [INFO] train episode 14853: reward = -87.98, steps = 19 09:50:37 [INFO] train episode 14854: reward = -122.30, steps = 27 09:50:39 [INFO] train episode 14855: reward = -107.27, steps = 26 09:50:41 [INFO] train episode 14856: reward = -125.31, steps = 19 09:50:43 [INFO] train episode 14857: reward = -99.25, steps = 22 09:50:46 [INFO] train episode 14858: reward = -117.68, steps = 34 09:50:49 [INFO] train episode 14859: reward = -125.12, steps = 34 09:50:51 [INFO] train episode 14860: reward = -100.48, steps = 23 09:50:53 [INFO] train episode 14861: reward = -115.21, steps = 27 09:50:55 [INFO] train episode 14862: reward = -92.81, steps = 22 09:50:58 [INFO] train episode 14863: reward = -108.93, steps = 31 09:51:00 [INFO] train episode 14864: reward = -134.57, steps = 25 09:51:04 [INFO] train episode 14865: reward = -77.59, steps = 40 09:51:05 [INFO] train episode 14866: reward = -110.80, steps = 21 09:51:07 [INFO] train episode 14867: reward = -67.20, steps = 19 09:51:09 [INFO] train episode 14868: reward = -153.26, steps = 20 09:51:11 [INFO] train episode 14869: reward = -106.51, steps = 20 09:51:12 [INFO] train episode 14870: reward = -77.12, steps = 20 09:51:14 [INFO] train episode 14871: reward = -98.51, steps = 19 09:51:17 [INFO] train episode 14872: reward = -100.93, steps = 27 09:51:20 [INFO] train episode 14873: reward = -146.26, steps = 35 09:51:22 [INFO] train episode 14874: reward = -106.75, steps = 27 09:51:23 [INFO] train episode 14875: reward = -88.03, steps = 19 09:51:26 [INFO] train episode 14876: reward = -128.66, steps = 33 09:51:29 [INFO] train episode 14877: reward = -103.29, steps = 28 09:51:30 [INFO] train episode 14878: reward = -84.58, steps = 20 09:51:33 [INFO] train episode 14879: reward = -83.87, steps = 22 09:51:34 [INFO] train episode 14880: reward = -64.51, steps = 20 09:51:36 [INFO] train episode 14881: reward = -119.21, steps = 24 09:51:38 [INFO] train episode 14882: reward = -85.70, steps = 20 09:51:40 [INFO] train episode 14883: reward = -77.81, steps = 19 09:51:41 [INFO] train episode 14884: reward = -89.32, steps = 20 09:51:43 [INFO] train episode 14885: reward = -99.11, steps = 19 09:51:45 [INFO] train episode 14886: reward = -70.61, steps = 19 09:51:47 [INFO] train episode 14887: reward = -90.92, steps = 28 09:51:50 [INFO] train episode 14888: reward = -132.03, steps = 30 09:51:53 [INFO] train episode 14889: reward = -123.20, steps = 33 09:51:55 [INFO] train episode 14890: reward = -120.82, steps = 25 09:51:57 [INFO] train episode 14891: reward = -106.26, steps = 24 09:51:59 [INFO] train episode 14892: reward = -110.54, steps = 29 09:52:02 [INFO] train episode 14893: reward = -111.95, steps = 27 09:52:04 [INFO] train episode 14894: reward = -106.30, steps = 29 09:52:07 [INFO] train episode 14895: reward = -83.12, steps = 26 09:52:08 [INFO] train episode 14896: reward = -77.88, steps = 19 09:52:10 [INFO] train episode 14897: reward = -99.38, steps = 21 09:52:13 [INFO] train episode 14898: reward = -101.12, steps = 29 09:52:15 [INFO] train episode 14899: reward = -71.24, steps = 23 09:52:17 [INFO] train episode 14900: reward = -81.67, steps = 22 09:52:19 [INFO] train episode 14901: reward = -84.44, steps = 21 09:52:21 [INFO] train episode 14902: reward = -68.29, steps = 22 09:52:22 [INFO] train episode 14903: reward = -77.21, steps = 20 09:52:24 [INFO] train episode 14904: reward = -76.85, steps = 20 09:52:26 [INFO] train episode 14905: reward = -154.73, steps = 19 09:52:28 [INFO] train episode 14906: reward = -78.79, steps = 22 09:52:30 [INFO] train episode 14907: reward = -79.21, steps = 21 09:52:32 [INFO] train episode 14908: reward = -75.30, steps = 21 09:52:35 [INFO] train episode 14909: reward = -85.89, steps = 34 09:52:37 [INFO] train episode 14910: reward = -115.89, steps = 22 09:52:39 [INFO] train episode 14911: reward = -98.43, steps = 24 09:52:42 [INFO] train episode 14912: reward = -90.38, steps = 32 09:52:45 [INFO] train episode 14913: reward = -108.05, steps = 31 09:52:46 [INFO] train episode 14914: reward = -93.81, steps = 18 09:52:48 [INFO] train episode 14915: reward = -121.96, steps = 21 09:52:50 [INFO] train episode 14916: reward = -87.43, steps = 22 09:52:52 [INFO] train episode 14917: reward = -64.62, steps = 21 09:52:54 [INFO] train episode 14918: reward = -87.62, steps = 19 09:52:56 [INFO] train episode 14919: reward = -69.84, steps = 22 09:52:57 [INFO] train episode 14920: reward = -79.88, steps = 19 09:52:59 [INFO] train episode 14921: reward = -99.58, steps = 21 09:53:01 [INFO] train episode 14922: reward = -79.05, steps = 26 09:53:03 [INFO] train episode 14923: reward = -75.87, steps = 24 09:53:05 [INFO] train episode 14924: reward = -105.95, steps = 23 09:53:08 [INFO] train episode 14925: reward = -117.46, steps = 22 09:53:10 [INFO] train episode 14926: reward = -73.80, steps = 24 09:53:12 [INFO] train episode 14927: reward = -175.87, steps = 32 09:53:16 [INFO] train episode 14928: reward = -148.49, steps = 43 09:53:18 [INFO] train episode 14929: reward = -106.98, steps = 31 09:53:20 [INFO] train episode 14930: reward = -102.30, steps = 23 09:53:24 [INFO] train episode 14931: reward = -164.29, steps = 34 09:53:25 [INFO] train episode 14932: reward = -114.37, steps = 21 09:53:28 [INFO] train episode 14933: reward = -122.57, steps = 33 09:53:30 [INFO] train episode 14934: reward = -85.29, steps = 26 09:53:32 [INFO] train episode 14935: reward = -103.77, steps = 19 09:53:34 [INFO] train episode 14936: reward = -82.96, steps = 20 09:53:36 [INFO] train episode 14937: reward = -96.43, steps = 23 09:53:38 [INFO] train episode 14938: reward = -111.03, steps = 24 09:53:40 [INFO] train episode 14939: reward = -84.70, steps = 21 09:53:43 [INFO] train episode 14940: reward = -119.81, steps = 33 09:53:45 [INFO] train episode 14941: reward = -92.73, steps = 26 09:53:47 [INFO] train episode 14942: reward = -119.88, steps = 21 09:53:51 [INFO] train episode 14943: reward = -138.64, steps = 45 09:53:53 [INFO] train episode 14944: reward = -75.55, steps = 24 09:53:55 [INFO] train episode 14945: reward = -109.18, steps = 25 09:53:58 [INFO] train episode 14946: reward = -117.97, steps = 39 09:54:00 [INFO] train episode 14947: reward = -105.75, steps = 21 09:54:02 [INFO] train episode 14948: reward = -107.94, steps = 18 09:54:04 [INFO] train episode 14949: reward = -146.57, steps = 28 09:54:06 [INFO] train episode 14950: reward = -80.97, steps = 25 09:54:08 [INFO] train episode 14951: reward = -95.80, steps = 25 09:54:11 [INFO] train episode 14952: reward = -151.63, steps = 32 09:54:14 [INFO] train episode 14953: reward = -73.25, steps = 30 09:54:16 [INFO] train episode 14954: reward = -108.18, steps = 20 09:54:18 [INFO] train episode 14955: reward = -126.21, steps = 24 09:54:20 [INFO] train episode 14956: reward = -99.67, steps = 25 09:54:22 [INFO] train episode 14957: reward = -108.41, steps = 24 09:54:24 [INFO] train episode 14958: reward = -79.28, steps = 22 09:54:26 [INFO] train episode 14959: reward = -104.29, steps = 20 09:54:28 [INFO] train episode 14960: reward = -102.45, steps = 22 09:54:29 [INFO] train episode 14961: reward = -79.93, steps = 22 09:54:31 [INFO] train episode 14962: reward = -102.52, steps = 21 09:54:33 [INFO] train episode 14963: reward = -131.67, steps = 19 09:54:35 [INFO] train episode 14964: reward = -95.29, steps = 20 09:54:36 [INFO] train episode 14965: reward = -120.01, steps = 20 09:54:38 [INFO] train episode 14966: reward = -112.00, steps = 19 09:54:42 [INFO] train episode 14967: reward = -126.74, steps = 41 09:54:43 [INFO] train episode 14968: reward = -100.52, steps = 19 09:54:46 [INFO] train episode 14969: reward = -84.50, steps = 36 09:54:50 [INFO] train episode 14970: reward = -178.69, steps = 39 09:54:52 [INFO] train episode 14971: reward = -129.27, steps = 22 09:54:54 [INFO] train episode 14972: reward = -94.03, steps = 23 09:54:56 [INFO] train episode 14973: reward = -111.81, steps = 20 09:54:57 [INFO] train episode 14974: reward = -75.83, steps = 20 09:54:59 [INFO] train episode 14975: reward = -109.62, steps = 21 09:55:02 [INFO] train episode 14976: reward = -73.79, steps = 28 09:55:05 [INFO] train episode 14977: reward = -117.64, steps = 39 09:55:07 [INFO] train episode 14978: reward = -95.51, steps = 24 09:55:09 [INFO] train episode 14979: reward = -73.44, steps = 20 09:55:10 [INFO] train episode 14980: reward = -44.70, steps = 21 09:55:13 [INFO] train episode 14981: reward = -76.90, steps = 25 09:55:15 [INFO] train episode 14982: reward = -110.36, steps = 20 09:55:17 [INFO] train episode 14983: reward = -114.99, steps = 29 09:55:20 [INFO] train episode 14984: reward = -75.95, steps = 22 09:55:21 [INFO] train episode 14985: reward = -79.50, steps = 20 09:55:24 [INFO] train episode 14986: reward = -88.31, steps = 32 09:55:26 [INFO] train episode 14987: reward = -91.47, steps = 19 09:55:28 [INFO] train episode 14988: reward = -97.12, steps = 22 09:55:31 [INFO] train episode 14989: reward = -62.96, steps = 30 09:55:32 [INFO] train episode 14990: reward = -71.90, steps = 22 09:55:34 [INFO] train episode 14991: reward = -115.60, steps = 22 09:55:37 [INFO] train episode 14992: reward = -154.98, steps = 28 09:55:39 [INFO] train episode 14993: reward = -92.15, steps = 29 09:55:41 [INFO] train episode 14994: reward = -60.92, steps = 20 09:55:43 [INFO] train episode 14995: reward = -75.63, steps = 20 09:55:45 [INFO] train episode 14996: reward = -83.94, steps = 19 09:55:46 [INFO] train episode 14997: reward = -140.49, steps = 21 09:55:48 [INFO] train episode 14998: reward = -80.80, steps = 22 09:55:52 [INFO] train episode 14999: reward = -113.34, steps = 42 09:55:54 [INFO] train episode 15000: reward = -57.88, steps = 24 09:55:56 [INFO] train episode 15001: reward = -88.14, steps = 28 09:55:58 [INFO] train episode 15002: reward = -83.28, steps = 20 09:56:00 [INFO] train episode 15003: reward = -114.71, steps = 20 09:56:02 [INFO] train episode 15004: reward = -107.88, steps = 20 09:56:05 [INFO] train episode 15005: reward = -89.02, steps = 34 09:56:07 [INFO] train episode 15006: reward = -113.02, steps = 29 09:56:10 [INFO] train episode 15007: reward = -129.44, steps = 32 09:56:12 [INFO] train episode 15008: reward = -83.99, steps = 24 09:56:13 [INFO] train episode 15009: reward = -78.88, steps = 19 09:56:16 [INFO] train episode 15010: reward = -95.80, steps = 21 09:56:17 [INFO] train episode 15011: reward = -114.35, steps = 21 09:56:19 [INFO] train episode 15012: reward = -85.36, steps = 24 09:56:22 [INFO] train episode 15013: reward = -110.93, steps = 29 09:56:24 [INFO] train episode 15014: reward = -91.72, steps = 21 09:56:28 [INFO] train episode 15015: reward = -161.43, steps = 49 09:56:30 [INFO] train episode 15016: reward = -96.13, steps = 26 09:56:34 [INFO] train episode 15017: reward = -102.04, steps = 39 09:56:36 [INFO] train episode 15018: reward = -76.19, steps = 23 09:56:37 [INFO] train episode 15019: reward = -94.59, steps = 21 09:56:39 [INFO] train episode 15020: reward = -93.23, steps = 20 09:56:41 [INFO] train episode 15021: reward = -102.35, steps = 20 09:56:43 [INFO] train episode 15022: reward = -103.88, steps = 27 09:56:45 [INFO] train episode 15023: reward = -72.38, steps = 22 09:56:47 [INFO] train episode 15024: reward = -75.14, steps = 20 09:56:50 [INFO] train episode 15025: reward = -87.40, steps = 31 09:56:51 [INFO] train episode 15026: reward = -94.70, steps = 19 09:56:54 [INFO] train episode 15027: reward = -95.56, steps = 30 09:56:56 [INFO] train episode 15028: reward = -84.24, steps = 26 09:56:58 [INFO] train episode 15029: reward = -127.88, steps = 19 09:57:00 [INFO] train episode 15030: reward = -89.89, steps = 25 09:57:02 [INFO] train episode 15031: reward = -71.46, steps = 23 09:57:04 [INFO] train episode 15032: reward = -104.88, steps = 24 09:57:06 [INFO] train episode 15033: reward = -115.39, steps = 25 09:57:08 [INFO] train episode 15034: reward = -121.62, steps = 20 09:57:12 [INFO] train episode 15035: reward = -111.35, steps = 41 09:57:14 [INFO] train episode 15036: reward = -93.72, steps = 26 09:57:16 [INFO] train episode 15037: reward = -87.23, steps = 25 09:57:18 [INFO] train episode 15038: reward = -95.13, steps = 25 09:57:20 [INFO] train episode 15039: reward = -70.08, steps = 20 09:57:22 [INFO] train episode 15040: reward = -51.10, steps = 24 09:57:24 [INFO] train episode 15041: reward = -83.50, steps = 19 09:57:26 [INFO] train episode 15042: reward = -80.29, steps = 23 09:57:28 [INFO] train episode 15043: reward = -79.99, steps = 21 09:57:30 [INFO] train episode 15044: reward = -113.09, steps = 19 09:57:33 [INFO] train episode 15045: reward = -98.87, steps = 38 09:57:35 [INFO] train episode 15046: reward = -112.40, steps = 27 09:57:38 [INFO] train episode 15047: reward = -87.85, steps = 29 09:57:40 [INFO] train episode 15048: reward = -96.41, steps = 25 09:57:44 [INFO] train episode 15049: reward = -92.44, steps = 48 09:57:47 [INFO] train episode 15050: reward = -107.35, steps = 40 09:57:50 [INFO] train episode 15051: reward = -85.01, steps = 32 09:57:52 [INFO] train episode 15052: reward = -69.24, steps = 19 09:57:54 [INFO] train episode 15053: reward = -109.24, steps = 20 09:57:56 [INFO] train episode 15054: reward = -75.58, steps = 28 09:57:59 [INFO] train episode 15055: reward = -138.90, steps = 28 09:58:01 [INFO] train episode 15056: reward = -113.14, steps = 23 09:58:02 [INFO] train episode 15057: reward = -99.92, steps = 20 09:58:05 [INFO] train episode 15058: reward = -122.93, steps = 23 09:58:06 [INFO] train episode 15059: reward = -89.76, steps = 21 09:58:10 [INFO] train episode 15060: reward = -106.40, steps = 31 09:58:12 [INFO] train episode 15061: reward = -103.83, steps = 23 09:58:15 [INFO] train episode 15062: reward = -96.11, steps = 45 09:58:19 [INFO] train episode 15063: reward = -105.65, steps = 37 09:58:21 [INFO] train episode 15064: reward = -136.42, steps = 26 09:58:24 [INFO] train episode 15065: reward = -106.14, steps = 30 09:58:26 [INFO] train episode 15066: reward = -88.92, steps = 24 09:58:28 [INFO] train episode 15067: reward = -117.33, steps = 32 09:58:31 [INFO] train episode 15068: reward = -110.95, steps = 28 09:58:33 [INFO] train episode 15069: reward = -96.77, steps = 20 09:58:35 [INFO] train episode 15070: reward = -103.01, steps = 25 09:58:39 [INFO] train episode 15071: reward = -197.80, steps = 52 09:58:42 [INFO] train episode 15072: reward = -105.92, steps = 26 09:58:43 [INFO] train episode 15073: reward = -75.07, steps = 19 09:58:45 [INFO] train episode 15074: reward = -79.49, steps = 20 09:58:47 [INFO] train episode 15075: reward = -75.88, steps = 19 09:58:48 [INFO] train episode 15076: reward = -84.06, steps = 21 09:58:50 [INFO] train episode 15077: reward = -129.61, steps = 22 09:58:53 [INFO] train episode 15078: reward = -77.87, steps = 29 09:58:55 [INFO] train episode 15079: reward = -76.29, steps = 24 09:58:58 [INFO] train episode 15080: reward = -86.92, steps = 28 09:58:59 [INFO] train episode 15081: reward = -75.03, steps = 19 09:59:01 [INFO] train episode 15082: reward = -77.14, steps = 20 09:59:03 [INFO] train episode 15083: reward = -71.99, steps = 28 09:59:05 [INFO] train episode 15084: reward = -106.99, steps = 20 09:59:07 [INFO] train episode 15085: reward = -99.54, steps = 20 09:59:10 [INFO] train episode 15086: reward = -142.25, steps = 28 09:59:11 [INFO] train episode 15087: reward = -84.30, steps = 21 09:59:13 [INFO] train episode 15088: reward = -115.02, steps = 21 09:59:15 [INFO] train episode 15089: reward = -108.14, steps = 20 09:59:17 [INFO] train episode 15090: reward = -84.77, steps = 21 09:59:19 [INFO] train episode 15091: reward = -129.66, steps = 23 09:59:21 [INFO] train episode 15092: reward = -204.84, steps = 23 09:59:24 [INFO] train episode 15093: reward = -102.40, steps = 37 09:59:26 [INFO] train episode 15094: reward = -148.07, steps = 20 09:59:27 [INFO] train episode 15095: reward = -76.75, steps = 19 09:59:30 [INFO] train episode 15096: reward = -92.05, steps = 36 09:59:33 [INFO] train episode 15097: reward = -130.47, steps = 25 09:59:34 [INFO] train episode 15098: reward = -162.72, steps = 23 09:59:36 [INFO] train episode 15099: reward = -85.87, steps = 22 09:59:38 [INFO] train episode 15100: reward = -73.44, steps = 23 09:59:41 [INFO] train episode 15101: reward = -132.34, steps = 24 09:59:42 [INFO] train episode 15102: reward = -60.54, steps = 20 09:59:45 [INFO] train episode 15103: reward = -113.67, steps = 30 09:59:47 [INFO] train episode 15104: reward = -88.43, steps = 24 09:59:49 [INFO] train episode 15105: reward = -80.22, steps = 23 09:59:51 [INFO] train episode 15106: reward = -104.98, steps = 20 09:59:53 [INFO] train episode 15107: reward = -155.02, steps = 25 09:59:55 [INFO] train episode 15108: reward = -113.71, steps = 30 09:59:58 [INFO] train episode 15109: reward = -126.56, steps = 25 10:00:00 [INFO] train episode 15110: reward = -125.20, steps = 28 10:00:02 [INFO] train episode 15111: reward = -95.64, steps = 23 10:00:04 [INFO] train episode 15112: reward = -62.09, steps = 20 10:00:06 [INFO] train episode 15113: reward = -101.26, steps = 23 10:00:08 [INFO] train episode 15114: reward = -103.91, steps = 23 10:00:10 [INFO] train episode 15115: reward = -73.39, steps = 20 10:00:13 [INFO] train episode 15116: reward = -108.00, steps = 38 10:00:15 [INFO] train episode 15117: reward = -93.42, steps = 21 10:00:17 [INFO] train episode 15118: reward = -98.68, steps = 22 10:00:19 [INFO] train episode 15119: reward = -111.25, steps = 22 10:00:20 [INFO] train episode 15120: reward = -91.55, steps = 20 10:00:23 [INFO] train episode 15121: reward = -87.31, steps = 26 10:00:24 [INFO] train episode 15122: reward = -79.81, steps = 20 10:00:27 [INFO] train episode 15123: reward = -125.95, steps = 28 10:00:29 [INFO] train episode 15124: reward = -78.92, steps = 24 10:00:31 [INFO] train episode 15125: reward = -102.83, steps = 29 10:00:34 [INFO] train episode 15126: reward = -95.42, steps = 27 10:00:36 [INFO] train episode 15127: reward = -75.34, steps = 25 10:00:38 [INFO] train episode 15128: reward = -93.88, steps = 21 10:00:40 [INFO] train episode 15129: reward = -87.88, steps = 21 10:00:41 [INFO] train episode 15130: reward = -93.87, steps = 23 10:00:44 [INFO] train episode 15131: reward = -87.42, steps = 21 10:00:45 [INFO] train episode 15132: reward = -67.95, steps = 19 10:00:47 [INFO] train episode 15133: reward = -78.23, steps = 25 10:00:50 [INFO] train episode 15134: reward = -115.10, steps = 28 10:00:51 [INFO] train episode 15135: reward = -64.53, steps = 20 10:00:55 [INFO] train episode 15136: reward = -102.81, steps = 38 10:00:56 [INFO] train episode 15137: reward = -61.52, steps = 20 10:01:00 [INFO] train episode 15138: reward = -80.22, steps = 30 10:01:02 [INFO] train episode 15139: reward = -120.22, steps = 20 10:01:04 [INFO] train episode 15140: reward = -101.95, steps = 23 10:01:06 [INFO] train episode 15141: reward = -84.66, steps = 34 10:01:08 [INFO] train episode 15142: reward = -65.70, steps = 21 10:01:11 [INFO] train episode 15143: reward = -113.79, steps = 30 10:01:14 [INFO] train episode 15144: reward = -81.02, steps = 34 10:01:17 [INFO] train episode 15145: reward = -103.63, steps = 41 10:01:20 [INFO] train episode 15146: reward = -143.10, steps = 28 10:01:24 [INFO] train episode 15147: reward = -106.02, steps = 45 10:01:25 [INFO] train episode 15148: reward = -68.46, steps = 21 10:01:27 [INFO] train episode 15149: reward = -57.28, steps = 19 10:01:29 [INFO] train episode 15150: reward = -100.02, steps = 28 10:01:32 [INFO] train episode 15151: reward = -97.71, steps = 29 10:01:34 [INFO] train episode 15152: reward = -71.58, steps = 19 10:01:36 [INFO] train episode 15153: reward = -101.34, steps = 25 10:01:38 [INFO] train episode 15154: reward = -100.68, steps = 21 10:01:39 [INFO] train episode 15155: reward = -94.31, steps = 20 10:01:41 [INFO] train episode 15156: reward = -84.69, steps = 21 10:01:43 [INFO] train episode 15157: reward = -80.43, steps = 20 10:01:46 [INFO] train episode 15158: reward = -104.25, steps = 28 10:01:47 [INFO] train episode 15159: reward = -89.04, steps = 20 10:01:49 [INFO] train episode 15160: reward = -119.80, steps = 25 10:01:52 [INFO] train episode 15161: reward = -121.63, steps = 27 10:01:53 [INFO] train episode 15162: reward = -78.95, steps = 20 10:01:56 [INFO] train episode 15163: reward = -140.89, steps = 24 10:01:57 [INFO] train episode 15164: reward = -99.92, steps = 21 10:02:00 [INFO] train episode 15165: reward = -65.97, steps = 28 10:02:03 [INFO] train episode 15166: reward = -134.26, steps = 29 10:02:04 [INFO] train episode 15167: reward = -80.74, steps = 21 10:02:06 [INFO] train episode 15168: reward = -154.19, steps = 23 10:02:08 [INFO] train episode 15169: reward = -90.24, steps = 20 10:02:10 [INFO] train episode 15170: reward = -94.77, steps = 26 10:02:12 [INFO] train episode 15171: reward = -83.45, steps = 20 10:02:14 [INFO] train episode 15172: reward = -81.06, steps = 21 10:02:16 [INFO] train episode 15173: reward = -87.14, steps = 18 10:02:19 [INFO] train episode 15174: reward = -80.82, steps = 30 10:02:21 [INFO] train episode 15175: reward = -134.66, steps = 25 10:02:23 [INFO] train episode 15176: reward = -87.83, steps = 23 10:02:26 [INFO] train episode 15177: reward = -126.43, steps = 38 10:02:30 [INFO] train episode 15178: reward = -147.84, steps = 43 10:02:31 [INFO] train episode 15179: reward = -98.45, steps = 20 10:02:33 [INFO] train episode 15180: reward = -84.79, steps = 21 10:02:35 [INFO] train episode 15181: reward = -114.74, steps = 19 10:02:37 [INFO] train episode 15182: reward = -93.75, steps = 24 10:02:40 [INFO] train episode 15183: reward = -92.54, steps = 29 10:02:42 [INFO] train episode 15184: reward = -79.25, steps = 23 10:02:44 [INFO] train episode 15185: reward = -58.11, steps = 20 10:02:46 [INFO] train episode 15186: reward = -63.61, steps = 23 10:02:47 [INFO] train episode 15187: reward = -84.52, steps = 21 10:02:50 [INFO] train episode 15188: reward = -58.44, steps = 26 10:02:53 [INFO] train episode 15189: reward = -105.26, steps = 36 10:02:55 [INFO] train episode 15190: reward = -93.29, steps = 26 10:02:58 [INFO] train episode 15191: reward = -69.80, steps = 29 10:03:00 [INFO] train episode 15192: reward = -71.49, steps = 21 10:03:01 [INFO] train episode 15193: reward = -91.70, steps = 20 10:03:03 [INFO] train episode 15194: reward = -94.51, steps = 19 10:03:05 [INFO] train episode 15195: reward = -128.24, steps = 21 10:03:07 [INFO] train episode 15196: reward = -81.30, steps = 19 10:03:09 [INFO] train episode 15197: reward = -84.04, steps = 22 10:03:10 [INFO] train episode 15198: reward = -89.67, steps = 19 10:03:12 [INFO] train episode 15199: reward = -95.25, steps = 20 10:03:14 [INFO] train episode 15200: reward = -81.60, steps = 20 10:03:16 [INFO] train episode 15201: reward = -65.07, steps = 21 10:03:18 [INFO] train episode 15202: reward = -146.03, steps = 32 10:03:20 [INFO] train episode 15203: reward = -74.50, steps = 22 10:03:23 [INFO] train episode 15204: reward = -95.14, steps = 34 10:03:25 [INFO] train episode 15205: reward = -79.76, steps = 21 10:03:27 [INFO] train episode 15206: reward = -61.49, steps = 21 10:03:29 [INFO] train episode 15207: reward = -90.05, steps = 26 10:03:31 [INFO] train episode 15208: reward = -91.35, steps = 22 10:03:33 [INFO] train episode 15209: reward = -91.83, steps = 20 10:03:34 [INFO] train episode 15210: reward = -104.32, steps = 19 10:03:36 [INFO] train episode 15211: reward = -85.44, steps = 20 10:03:38 [INFO] train episode 15212: reward = -85.48, steps = 20 10:03:42 [INFO] train episode 15213: reward = -168.83, steps = 39 10:03:45 [INFO] train episode 15214: reward = -85.70, steps = 42 10:03:47 [INFO] train episode 15215: reward = -103.70, steps = 21 10:03:49 [INFO] train episode 15216: reward = -91.65, steps = 20 10:03:51 [INFO] train episode 15217: reward = -91.86, steps = 19 10:03:53 [INFO] train episode 15218: reward = -97.73, steps = 20 10:03:55 [INFO] train episode 15219: reward = -71.89, steps = 19 10:03:57 [INFO] train episode 15220: reward = -109.16, steps = 23 10:03:59 [INFO] train episode 15221: reward = -96.05, steps = 24 10:04:03 [INFO] train episode 15222: reward = -152.95, steps = 48 10:04:05 [INFO] train episode 15223: reward = -85.72, steps = 26 10:04:07 [INFO] train episode 15224: reward = -107.62, steps = 27 10:04:10 [INFO] train episode 15225: reward = -97.01, steps = 25 10:04:12 [INFO] train episode 15226: reward = -98.65, steps = 24 10:04:14 [INFO] train episode 15227: reward = -80.91, steps = 25 10:04:16 [INFO] train episode 15228: reward = -112.41, steps = 25 10:04:18 [INFO] train episode 15229: reward = -100.48, steps = 19 10:04:19 [INFO] train episode 15230: reward = -66.90, steps = 20 10:04:21 [INFO] train episode 15231: reward = -90.34, steps = 19 10:04:23 [INFO] train episode 15232: reward = -107.35, steps = 28 10:04:26 [INFO] train episode 15233: reward = -73.06, steps = 29 10:04:28 [INFO] train episode 15234: reward = -61.64, steps = 22 10:04:30 [INFO] train episode 15235: reward = -117.37, steps = 21 10:04:32 [INFO] train episode 15236: reward = -92.35, steps = 27 10:04:34 [INFO] train episode 15237: reward = -56.81, steps = 21 10:04:36 [INFO] train episode 15238: reward = -71.38, steps = 19 10:04:38 [INFO] train episode 15239: reward = -92.96, steps = 23 10:04:39 [INFO] train episode 15240: reward = -75.63, steps = 19 10:04:41 [INFO] train episode 15241: reward = -118.35, steps = 19 10:04:44 [INFO] train episode 15242: reward = -106.97, steps = 37 10:04:46 [INFO] train episode 15243: reward = -60.44, steps = 21 10:04:48 [INFO] train episode 15244: reward = -109.35, steps = 19 10:04:50 [INFO] train episode 15245: reward = -98.59, steps = 29 10:04:52 [INFO] train episode 15246: reward = -97.28, steps = 23 10:04:54 [INFO] train episode 15247: reward = -130.79, steps = 21 10:04:56 [INFO] train episode 15248: reward = -64.41, steps = 21 10:04:58 [INFO] train episode 15249: reward = -82.93, steps = 19 10:05:00 [INFO] train episode 15250: reward = -59.50, steps = 21 10:05:01 [INFO] train episode 15251: reward = -76.74, steps = 20 10:05:04 [INFO] train episode 15252: reward = -114.80, steps = 27 10:05:06 [INFO] train episode 15253: reward = -139.26, steps = 27 10:05:08 [INFO] train episode 15254: reward = -79.12, steps = 20 10:05:10 [INFO] train episode 15255: reward = -71.88, steps = 30 10:05:12 [INFO] train episode 15256: reward = -105.55, steps = 26 10:05:15 [INFO] train episode 15257: reward = -95.35, steps = 20 10:05:17 [INFO] train episode 15258: reward = -72.45, steps = 23 10:05:18 [INFO] train episode 15259: reward = -83.30, steps = 21 10:05:20 [INFO] train episode 15260: reward = -145.69, steps = 24 10:05:22 [INFO] train episode 15261: reward = -92.15, steps = 22 10:05:24 [INFO] train episode 15262: reward = -92.58, steps = 24 10:05:26 [INFO] train episode 15263: reward = -106.96, steps = 22 10:05:28 [INFO] train episode 15264: reward = -71.87, steps = 20 10:05:30 [INFO] train episode 15265: reward = -71.98, steps = 21 10:05:32 [INFO] train episode 15266: reward = -70.08, steps = 21 10:05:33 [INFO] train episode 15267: reward = -114.33, steps = 18 10:05:36 [INFO] train episode 15268: reward = -75.06, steps = 24 10:05:37 [INFO] train episode 15269: reward = -65.36, steps = 21 10:05:39 [INFO] train episode 15270: reward = -72.24, steps = 21 10:05:42 [INFO] train episode 15271: reward = -71.92, steps = 29 10:05:43 [INFO] train episode 15272: reward = -64.27, steps = 21 10:05:46 [INFO] train episode 15273: reward = -125.78, steps = 27 10:05:48 [INFO] train episode 15274: reward = -82.94, steps = 19 10:05:50 [INFO] train episode 15275: reward = -129.30, steps = 29 10:05:52 [INFO] train episode 15276: reward = -71.93, steps = 20 10:05:54 [INFO] train episode 15277: reward = -96.84, steps = 24 10:05:56 [INFO] train episode 15278: reward = -104.01, steps = 19 10:05:57 [INFO] train episode 15279: reward = -72.20, steps = 22 10:05:59 [INFO] train episode 15280: reward = -73.43, steps = 23 10:06:02 [INFO] train episode 15281: reward = -62.57, steps = 25 10:06:04 [INFO] train episode 15282: reward = -91.47, steps = 26 10:06:07 [INFO] train episode 15283: reward = -61.83, steps = 31 10:06:09 [INFO] train episode 15284: reward = -81.31, steps = 22 10:06:10 [INFO] train episode 15285: reward = -125.94, steps = 22 10:06:12 [INFO] train episode 15286: reward = -116.35, steps = 19 10:06:15 [INFO] train episode 15287: reward = -89.07, steps = 31 10:06:17 [INFO] train episode 15288: reward = -92.09, steps = 20 10:06:18 [INFO] train episode 15289: reward = -54.81, steps = 20 10:06:20 [INFO] train episode 15290: reward = -87.75, steps = 22 10:06:22 [INFO] train episode 15291: reward = -103.40, steps = 20 10:06:24 [INFO] train episode 15292: reward = -93.61, steps = 20 10:06:25 [INFO] train episode 15293: reward = -71.68, steps = 20 10:06:28 [INFO] train episode 15294: reward = -134.38, steps = 37 10:06:31 [INFO] train episode 15295: reward = -84.83, steps = 28 10:06:33 [INFO] train episode 15296: reward = -102.07, steps = 23 10:06:35 [INFO] train episode 15297: reward = -89.64, steps = 22 10:06:39 [INFO] train episode 15298: reward = -94.66, steps = 38 10:06:41 [INFO] train episode 15299: reward = -75.61, steps = 18 10:06:42 [INFO] train episode 15300: reward = -85.07, steps = 19 10:06:44 [INFO] train episode 15301: reward = -80.15, steps = 21 10:06:46 [INFO] train episode 15302: reward = -75.13, steps = 21 10:06:48 [INFO] train episode 15303: reward = -104.22, steps = 25 10:06:51 [INFO] train episode 15304: reward = -85.29, steps = 26 10:06:54 [INFO] train episode 15305: reward = -132.18, steps = 36 10:06:55 [INFO] train episode 15306: reward = -81.45, steps = 21 10:06:57 [INFO] train episode 15307: reward = -105.98, steps = 22 10:06:59 [INFO] train episode 15308: reward = -101.61, steps = 19 10:07:01 [INFO] train episode 15309: reward = -73.88, steps = 27 10:07:04 [INFO] train episode 15310: reward = -79.78, steps = 32 10:07:07 [INFO] train episode 15311: reward = -140.66, steps = 25 10:07:09 [INFO] train episode 15312: reward = -89.07, steps = 32 10:07:11 [INFO] train episode 15313: reward = -60.41, steps = 20 10:07:14 [INFO] train episode 15314: reward = -92.95, steps = 38 10:07:16 [INFO] train episode 15315: reward = -114.39, steps = 23 10:07:18 [INFO] train episode 15316: reward = -70.99, steps = 23 10:07:20 [INFO] train episode 15317: reward = -81.83, steps = 20 10:07:23 [INFO] train episode 15318: reward = -125.71, steps = 26 10:07:24 [INFO] train episode 15319: reward = -84.34, steps = 20 10:07:26 [INFO] train episode 15320: reward = -76.24, steps = 24 10:07:28 [INFO] train episode 15321: reward = -101.04, steps = 24 10:07:30 [INFO] train episode 15322: reward = -91.56, steps = 20 10:07:32 [INFO] train episode 15323: reward = -79.05, steps = 20 10:07:34 [INFO] train episode 15324: reward = -100.08, steps = 22 10:07:35 [INFO] train episode 15325: reward = -87.42, steps = 21 10:07:38 [INFO] train episode 15326: reward = -92.15, steps = 22 10:07:40 [INFO] train episode 15327: reward = -131.56, steps = 28 10:07:43 [INFO] train episode 15328: reward = -75.74, steps = 30 10:07:45 [INFO] train episode 15329: reward = -96.87, steps = 26 10:07:48 [INFO] train episode 15330: reward = -89.69, steps = 32 10:07:50 [INFO] train episode 15331: reward = -108.64, steps = 31 10:07:54 [INFO] train episode 15332: reward = -82.10, steps = 41 10:07:56 [INFO] train episode 15333: reward = -119.57, steps = 20 10:07:57 [INFO] train episode 15334: reward = -92.02, steps = 19 10:07:59 [INFO] train episode 15335: reward = -81.10, steps = 20 10:08:01 [INFO] train episode 15336: reward = -85.42, steps = 21 10:08:03 [INFO] train episode 15337: reward = -98.70, steps = 23 10:08:05 [INFO] train episode 15338: reward = -135.70, steps = 32 10:08:08 [INFO] train episode 15339: reward = -111.91, steps = 25 10:08:10 [INFO] train episode 15340: reward = -60.58, steps = 20 10:08:12 [INFO] train episode 15341: reward = -76.98, steps = 23 10:08:13 [INFO] train episode 15342: reward = -65.43, steps = 21 10:08:15 [INFO] train episode 15343: reward = -51.94, steps = 22 10:08:18 [INFO] train episode 15344: reward = -105.00, steps = 31 10:08:20 [INFO] train episode 15345: reward = -68.68, steps = 22 10:08:22 [INFO] train episode 15346: reward = -118.33, steps = 26 10:08:24 [INFO] train episode 15347: reward = -75.33, steps = 21 10:08:27 [INFO] train episode 15348: reward = -74.33, steps = 29 10:08:28 [INFO] train episode 15349: reward = -133.20, steps = 21 10:08:31 [INFO] train episode 15350: reward = -109.72, steps = 26 10:08:32 [INFO] train episode 15351: reward = -75.86, steps = 20 10:08:35 [INFO] train episode 15352: reward = -108.04, steps = 35 10:08:37 [INFO] train episode 15353: reward = -86.35, steps = 19 10:08:39 [INFO] train episode 15354: reward = -116.88, steps = 20 10:08:41 [INFO] train episode 15355: reward = -88.52, steps = 25 10:08:43 [INFO] train episode 15356: reward = -71.03, steps = 19 10:08:45 [INFO] train episode 15357: reward = -96.07, steps = 22 10:08:47 [INFO] train episode 15358: reward = -109.11, steps = 26 10:08:50 [INFO] train episode 15359: reward = -81.03, steps = 32 10:08:53 [INFO] train episode 15360: reward = -84.71, steps = 28 10:08:54 [INFO] train episode 15361: reward = -125.09, steps = 18 10:08:58 [INFO] train episode 15362: reward = -114.75, steps = 27 10:09:00 [INFO] train episode 15363: reward = -116.35, steps = 23 10:09:03 [INFO] train episode 15364: reward = -99.98, steps = 30 10:09:04 [INFO] train episode 15365: reward = -100.43, steps = 22 10:09:06 [INFO] train episode 15366: reward = -95.19, steps = 22 10:09:08 [INFO] train episode 15367: reward = -82.01, steps = 20 10:09:11 [INFO] train episode 15368: reward = -140.50, steps = 29 10:09:13 [INFO] train episode 15369: reward = -132.58, steps = 29 10:09:15 [INFO] train episode 15370: reward = -109.37, steps = 25 10:09:18 [INFO] train episode 15371: reward = -56.13, steps = 25 10:09:19 [INFO] train episode 15372: reward = -59.06, steps = 20 10:09:21 [INFO] train episode 15373: reward = -78.17, steps = 20 10:09:23 [INFO] train episode 15374: reward = -76.67, steps = 19 10:09:25 [INFO] train episode 15375: reward = -94.67, steps = 28 10:09:27 [INFO] train episode 15376: reward = -86.80, steps = 28 10:09:30 [INFO] train episode 15377: reward = -63.12, steps = 21 10:09:32 [INFO] train episode 15378: reward = -87.81, steps = 22 10:09:34 [INFO] train episode 15379: reward = -76.88, steps = 19 10:09:36 [INFO] train episode 15380: reward = -71.29, steps = 19 10:09:38 [INFO] train episode 15381: reward = -104.32, steps = 23 10:09:39 [INFO] train episode 15382: reward = -75.39, steps = 22 10:09:41 [INFO] train episode 15383: reward = -65.15, steps = 19 10:09:43 [INFO] train episode 15384: reward = -65.63, steps = 24 10:09:46 [INFO] train episode 15385: reward = -80.43, steps = 30 10:09:48 [INFO] train episode 15386: reward = -59.44, steps = 20 10:09:49 [INFO] train episode 15387: reward = -128.61, steps = 18 10:09:52 [INFO] train episode 15388: reward = -50.73, steps = 25 10:09:53 [INFO] train episode 15389: reward = -99.69, steps = 23 10:09:56 [INFO] train episode 15390: reward = -101.33, steps = 33 10:10:00 [INFO] train episode 15391: reward = -115.16, steps = 41 10:10:03 [INFO] train episode 15392: reward = -72.79, steps = 28 10:10:05 [INFO] train episode 15393: reward = -66.92, steps = 29 10:10:07 [INFO] train episode 15394: reward = -77.39, steps = 19 10:10:08 [INFO] train episode 15395: reward = -82.61, steps = 21 10:10:10 [INFO] train episode 15396: reward = -88.63, steps = 19 10:10:12 [INFO] train episode 15397: reward = -103.83, steps = 25 10:10:14 [INFO] train episode 15398: reward = -120.97, steps = 18 10:10:20 [INFO] train episode 15399: reward = -191.15, steps = 74 10:10:23 [INFO] train episode 15400: reward = -73.91, steps = 29 10:10:25 [INFO] train episode 15401: reward = -76.29, steps = 27 10:10:27 [INFO] train episode 15402: reward = -105.49, steps = 26 10:10:29 [INFO] train episode 15403: reward = -75.35, steps = 19 10:10:31 [INFO] train episode 15404: reward = -88.97, steps = 21 10:10:33 [INFO] train episode 15405: reward = -70.42, steps = 20 10:10:35 [INFO] train episode 15406: reward = -67.88, steps = 24 10:10:37 [INFO] train episode 15407: reward = -131.76, steps = 24 10:10:39 [INFO] train episode 15408: reward = -88.88, steps = 22 10:10:41 [INFO] train episode 15409: reward = -64.18, steps = 21 10:10:42 [INFO] train episode 15410: reward = -70.86, steps = 20 10:10:45 [INFO] train episode 15411: reward = -88.58, steps = 27 10:10:47 [INFO] train episode 15412: reward = -58.60, steps = 26 10:10:50 [INFO] train episode 15413: reward = -87.39, steps = 27 10:10:52 [INFO] train episode 15414: reward = -90.92, steps = 28 10:10:54 [INFO] train episode 15415: reward = -77.13, steps = 22 10:10:56 [INFO] train episode 15416: reward = -79.48, steps = 23 10:11:00 [INFO] train episode 15417: reward = -79.97, steps = 48 10:11:02 [INFO] train episode 15418: reward = -122.37, steps = 31 10:11:05 [INFO] train episode 15419: reward = -103.06, steps = 31 10:11:09 [INFO] train episode 15420: reward = -90.38, steps = 39 10:11:10 [INFO] train episode 15421: reward = -83.37, steps = 20 10:11:12 [INFO] train episode 15422: reward = -140.32, steps = 22 10:11:14 [INFO] train episode 15423: reward = -82.79, steps = 25 10:11:16 [INFO] train episode 15424: reward = -98.20, steps = 20 10:11:19 [INFO] train episode 15425: reward = -63.24, steps = 30 10:11:21 [INFO] train episode 15426: reward = -108.82, steps = 20 10:11:23 [INFO] train episode 15427: reward = -71.60, steps = 24 10:11:25 [INFO] train episode 15428: reward = -87.24, steps = 30 10:11:28 [INFO] train episode 15429: reward = -99.34, steps = 24 10:11:29 [INFO] train episode 15430: reward = -79.50, steps = 19 10:11:32 [INFO] train episode 15431: reward = -60.47, steps = 35 10:11:34 [INFO] train episode 15432: reward = -77.57, steps = 24 10:11:37 [INFO] train episode 15433: reward = -113.39, steps = 32 10:11:39 [INFO] train episode 15434: reward = -92.81, steps = 23 10:11:41 [INFO] train episode 15435: reward = -97.21, steps = 23 10:11:43 [INFO] train episode 15436: reward = -92.99, steps = 21 10:11:45 [INFO] train episode 15437: reward = -82.26, steps = 20 10:11:47 [INFO] train episode 15438: reward = -118.15, steps = 26 10:11:49 [INFO] train episode 15439: reward = -97.86, steps = 19 10:11:52 [INFO] train episode 15440: reward = -113.19, steps = 31 10:11:54 [INFO] train episode 15441: reward = -87.04, steps = 21 10:11:56 [INFO] train episode 15442: reward = -76.81, steps = 30 10:11:58 [INFO] train episode 15443: reward = -97.33, steps = 20 10:12:00 [INFO] train episode 15444: reward = -100.09, steps = 21 10:12:02 [INFO] train episode 15445: reward = -72.02, steps = 22 10:12:04 [INFO] train episode 15446: reward = -84.01, steps = 27 10:12:05 [INFO] train episode 15447: reward = -94.28, steps = 19 10:12:07 [INFO] train episode 15448: reward = -81.86, steps = 19 10:12:09 [INFO] train episode 15449: reward = -63.53, steps = 20 10:12:12 [INFO] train episode 15450: reward = -119.68, steps = 31 10:12:14 [INFO] train episode 15451: reward = -96.92, steps = 31 10:12:18 [INFO] train episode 15452: reward = -166.66, steps = 43 10:12:22 [INFO] train episode 15453: reward = -75.73, steps = 36 10:12:24 [INFO] train episode 15454: reward = -94.67, steps = 20 10:12:27 [INFO] train episode 15455: reward = -72.35, steps = 41 10:12:29 [INFO] train episode 15456: reward = -73.29, steps = 20 10:12:31 [INFO] train episode 15457: reward = -84.13, steps = 20 10:12:33 [INFO] train episode 15458: reward = -105.00, steps = 28 10:12:36 [INFO] train episode 15459: reward = -110.76, steps = 28 10:12:38 [INFO] train episode 15460: reward = -111.38, steps = 30 10:12:42 [INFO] train episode 15461: reward = -105.90, steps = 36 10:12:45 [INFO] train episode 15462: reward = -122.20, steps = 37 10:12:47 [INFO] train episode 15463: reward = -66.11, steps = 23 10:12:50 [INFO] train episode 15464: reward = -80.32, steps = 35 10:12:53 [INFO] train episode 15465: reward = -114.90, steps = 40 10:12:55 [INFO] train episode 15466: reward = -97.38, steps = 21 10:12:58 [INFO] train episode 15467: reward = -77.28, steps = 26 10:12:59 [INFO] train episode 15468: reward = -64.15, steps = 21 10:13:01 [INFO] train episode 15469: reward = -60.37, steps = 19 10:13:04 [INFO] train episode 15470: reward = -98.69, steps = 36 10:13:06 [INFO] train episode 15471: reward = -58.68, steps = 20 10:13:08 [INFO] train episode 15472: reward = -91.60, steps = 23 10:13:10 [INFO] train episode 15473: reward = -107.50, steps = 23 10:13:12 [INFO] train episode 15474: reward = -95.10, steps = 21 10:13:14 [INFO] train episode 15475: reward = -87.24, steps = 19 10:13:15 [INFO] train episode 15476: reward = -63.88, steps = 20 10:13:20 [INFO] train episode 15477: reward = -170.29, steps = 59 10:13:24 [INFO] train episode 15478: reward = -105.88, steps = 47 10:13:26 [INFO] train episode 15479: reward = -101.17, steps = 22 10:13:28 [INFO] train episode 15480: reward = -58.24, steps = 20 10:13:30 [INFO] train episode 15481: reward = -89.70, steps = 22 10:13:32 [INFO] train episode 15482: reward = -71.69, steps = 21 10:13:33 [INFO] train episode 15483: reward = -56.89, steps = 19 10:13:36 [INFO] train episode 15484: reward = -92.21, steps = 26 10:13:37 [INFO] train episode 15485: reward = -96.60, steps = 21 10:13:40 [INFO] train episode 15486: reward = -111.57, steps = 31 10:13:44 [INFO] train episode 15487: reward = -111.34, steps = 44 10:13:47 [INFO] train episode 15488: reward = -101.42, steps = 34 10:13:49 [INFO] train episode 15489: reward = -111.64, steps = 19 10:13:51 [INFO] train episode 15490: reward = -80.88, steps = 22 10:13:53 [INFO] train episode 15491: reward = -86.27, steps = 29 10:13:55 [INFO] train episode 15492: reward = -77.18, steps = 18 10:13:57 [INFO] train episode 15493: reward = -80.27, steps = 26 10:13:59 [INFO] train episode 15494: reward = -96.22, steps = 23 10:14:01 [INFO] train episode 15495: reward = -74.24, steps = 24 10:14:03 [INFO] train episode 15496: reward = -84.59, steps = 25 10:14:05 [INFO] train episode 15497: reward = -79.58, steps = 20 10:14:07 [INFO] train episode 15498: reward = -77.55, steps = 19 10:14:10 [INFO] train episode 15499: reward = -82.36, steps = 34 10:14:12 [INFO] train episode 15500: reward = -134.44, steps = 29 10:14:14 [INFO] train episode 15501: reward = -58.50, steps = 21 10:14:16 [INFO] train episode 15502: reward = -67.46, steps = 20 10:14:18 [INFO] train episode 15503: reward = -78.88, steps = 21 10:14:19 [INFO] train episode 15504: reward = -62.81, steps = 19 10:14:22 [INFO] train episode 15505: reward = -89.53, steps = 26 10:14:23 [INFO] train episode 15506: reward = -88.30, steps = 20 10:14:25 [INFO] train episode 15507: reward = -67.60, steps = 21 10:14:27 [INFO] train episode 15508: reward = -80.05, steps = 20 10:14:29 [INFO] train episode 15509: reward = -92.38, steps = 20 10:14:31 [INFO] train episode 15510: reward = -85.59, steps = 25 10:14:33 [INFO] train episode 15511: reward = -64.02, steps = 21 10:14:35 [INFO] train episode 15512: reward = -95.07, steps = 20 10:14:37 [INFO] train episode 15513: reward = -129.47, steps = 24 10:14:39 [INFO] train episode 15514: reward = -99.86, steps = 24 10:14:41 [INFO] train episode 15515: reward = -99.52, steps = 20 10:14:43 [INFO] train episode 15516: reward = -95.00, steps = 24 10:14:45 [INFO] train episode 15517: reward = -68.03, steps = 22 10:14:48 [INFO] train episode 15518: reward = -82.73, steps = 36 10:14:50 [INFO] train episode 15519: reward = -123.55, steps = 20 10:14:52 [INFO] train episode 15520: reward = -96.06, steps = 20 10:14:53 [INFO] train episode 15521: reward = -72.99, steps = 21 10:14:56 [INFO] train episode 15522: reward = -91.47, steps = 28 10:14:58 [INFO] train episode 15523: reward = -95.33, steps = 24 10:14:59 [INFO] train episode 15524: reward = -66.44, steps = 20 10:15:02 [INFO] train episode 15525: reward = -93.33, steps = 24 10:15:04 [INFO] train episode 15526: reward = -81.01, steps = 20 10:15:06 [INFO] train episode 15527: reward = -87.01, steps = 24 10:15:07 [INFO] train episode 15528: reward = -78.27, steps = 20 10:15:09 [INFO] train episode 15529: reward = -94.07, steps = 19 10:15:13 [INFO] train episode 15530: reward = -95.50, steps = 36 10:15:15 [INFO] train episode 15531: reward = -139.09, steps = 18 10:15:17 [INFO] train episode 15532: reward = -87.18, steps = 24 10:15:19 [INFO] train episode 15533: reward = -65.28, steps = 25 10:15:21 [INFO] train episode 15534: reward = -76.64, steps = 20 10:15:23 [INFO] train episode 15535: reward = -106.72, steps = 28 10:15:26 [INFO] train episode 15536: reward = -96.43, steps = 33 10:15:28 [INFO] train episode 15537: reward = -89.01, steps = 19 10:15:29 [INFO] train episode 15538: reward = -101.04, steps = 20 10:15:31 [INFO] train episode 15539: reward = -112.35, steps = 19 10:15:33 [INFO] train episode 15540: reward = -92.07, steps = 25 10:15:35 [INFO] train episode 15541: reward = -99.78, steps = 21 10:15:37 [INFO] train episode 15542: reward = -65.13, steps = 22 10:15:40 [INFO] train episode 15543: reward = -77.17, steps = 30 10:15:42 [INFO] train episode 15544: reward = -86.03, steps = 21 10:15:44 [INFO] train episode 15545: reward = -107.64, steps = 24 10:15:45 [INFO] train episode 15546: reward = -103.17, steps = 19 10:15:48 [INFO] train episode 15547: reward = -101.29, steps = 32 10:15:50 [INFO] train episode 15548: reward = -82.04, steps = 21 10:15:52 [INFO] train episode 15549: reward = -113.52, steps = 19 10:15:53 [INFO] train episode 15550: reward = -103.08, steps = 18 10:15:55 [INFO] train episode 15551: reward = -62.84, steps = 19 10:15:57 [INFO] train episode 15552: reward = -57.04, steps = 19 10:15:58 [INFO] train episode 15553: reward = -61.87, steps = 20 10:16:00 [INFO] train episode 15554: reward = -78.40, steps = 23 10:16:02 [INFO] train episode 15555: reward = -58.30, steps = 21 10:16:05 [INFO] train episode 15556: reward = -110.51, steps = 28 10:16:07 [INFO] train episode 15557: reward = -60.36, steps = 26 10:16:09 [INFO] train episode 15558: reward = -110.11, steps = 29 10:16:11 [INFO] train episode 15559: reward = -73.65, steps = 21 10:16:13 [INFO] train episode 15560: reward = -118.96, steps = 24 10:16:15 [INFO] train episode 15561: reward = -72.45, steps = 21 10:16:18 [INFO] train episode 15562: reward = -101.27, steps = 38 10:16:22 [INFO] train episode 15563: reward = -71.29, steps = 45 10:16:25 [INFO] train episode 15564: reward = -82.84, steps = 24 10:16:26 [INFO] train episode 15565: reward = -83.61, steps = 22 10:16:29 [INFO] train episode 15566: reward = -128.76, steps = 35 10:16:32 [INFO] train episode 15567: reward = -101.97, steps = 35 10:16:34 [INFO] train episode 15568: reward = -62.72, steps = 20 10:16:37 [INFO] train episode 15569: reward = -104.02, steps = 26 10:16:39 [INFO] train episode 15570: reward = -117.35, steps = 28 10:16:41 [INFO] train episode 15571: reward = -83.09, steps = 19 10:16:43 [INFO] train episode 15572: reward = -115.40, steps = 25 10:16:45 [INFO] train episode 15573: reward = -98.49, steps = 22 10:16:47 [INFO] train episode 15574: reward = -69.06, steps = 21 10:16:49 [INFO] train episode 15575: reward = -100.80, steps = 29 10:16:51 [INFO] train episode 15576: reward = -67.41, steps = 19 10:16:54 [INFO] train episode 15577: reward = -73.30, steps = 31 10:16:56 [INFO] train episode 15578: reward = -103.18, steps = 33 10:16:59 [INFO] train episode 15579: reward = -100.21, steps = 25 10:17:01 [INFO] train episode 15580: reward = -78.70, steps = 23 10:17:03 [INFO] train episode 15581: reward = -89.31, steps = 27 10:17:05 [INFO] train episode 15582: reward = -77.29, steps = 28 10:17:08 [INFO] train episode 15583: reward = -51.67, steps = 23 10:17:12 [INFO] train episode 15584: reward = -170.75, steps = 51 10:17:14 [INFO] train episode 15585: reward = -107.63, steps = 21 10:17:16 [INFO] train episode 15586: reward = -73.19, steps = 20 10:17:18 [INFO] train episode 15587: reward = -69.44, steps = 22 10:17:20 [INFO] train episode 15588: reward = -97.03, steps = 21 10:17:21 [INFO] train episode 15589: reward = -79.43, steps = 21 10:17:24 [INFO] train episode 15590: reward = -76.89, steps = 23 10:17:26 [INFO] train episode 15591: reward = -73.12, steps = 26 10:17:29 [INFO] train episode 15592: reward = -58.73, steps = 36 10:17:31 [INFO] train episode 15593: reward = -103.93, steps = 25 10:17:34 [INFO] train episode 15594: reward = -105.75, steps = 27 10:17:35 [INFO] train episode 15595: reward = -82.61, steps = 21 10:17:38 [INFO] train episode 15596: reward = -90.70, steps = 29 10:17:40 [INFO] train episode 15597: reward = -75.71, steps = 22 10:17:42 [INFO] train episode 15598: reward = -81.41, steps = 26 10:17:45 [INFO] train episode 15599: reward = -70.70, steps = 34 10:17:47 [INFO] train episode 15600: reward = -71.74, steps = 25 10:17:49 [INFO] train episode 15601: reward = -109.79, steps = 21 10:17:51 [INFO] train episode 15602: reward = -96.85, steps = 20 10:17:53 [INFO] train episode 15603: reward = -84.65, steps = 20 10:17:54 [INFO] train episode 15604: reward = -60.58, steps = 20 10:17:57 [INFO] train episode 15605: reward = -70.56, steps = 30 10:18:00 [INFO] train episode 15606: reward = -76.69, steps = 31 10:18:03 [INFO] train episode 15607: reward = -94.50, steps = 27 10:18:05 [INFO] train episode 15608: reward = -92.29, steps = 20 10:18:07 [INFO] train episode 15609: reward = -110.51, steps = 19 10:18:08 [INFO] train episode 15610: reward = -91.52, steps = 22 10:18:10 [INFO] train episode 15611: reward = -98.51, steps = 19 10:18:12 [INFO] train episode 15612: reward = -103.51, steps = 19 10:18:14 [INFO] train episode 15613: reward = -102.77, steps = 23 10:18:16 [INFO] train episode 15614: reward = -77.46, steps = 24 10:18:18 [INFO] train episode 15615: reward = -63.91, steps = 19 10:18:19 [INFO] train episode 15616: reward = -69.44, steps = 20 10:18:22 [INFO] train episode 15617: reward = -78.96, steps = 24 10:18:24 [INFO] train episode 15618: reward = -51.77, steps = 25 10:18:25 [INFO] train episode 15619: reward = -77.81, steps = 20 10:18:28 [INFO] train episode 15620: reward = -110.21, steps = 20 10:18:29 [INFO] train episode 15621: reward = -59.69, steps = 21 10:18:31 [INFO] train episode 15622: reward = -75.55, steps = 20 10:18:34 [INFO] train episode 15623: reward = -87.48, steps = 41 10:18:36 [INFO] train episode 15624: reward = -83.55, steps = 20 10:18:39 [INFO] train episode 15625: reward = -69.82, steps = 32 10:18:41 [INFO] train episode 15626: reward = -67.44, steps = 20 10:18:42 [INFO] train episode 15627: reward = -87.61, steps = 21 10:18:46 [INFO] train episode 15628: reward = -100.66, steps = 35 10:18:48 [INFO] train episode 15629: reward = -72.53, steps = 29 10:18:50 [INFO] train episode 15630: reward = -48.68, steps = 20 10:18:52 [INFO] train episode 15631: reward = -107.56, steps = 22 10:18:54 [INFO] train episode 15632: reward = -101.30, steps = 27 10:18:56 [INFO] train episode 15633: reward = -98.00, steps = 22 10:18:58 [INFO] train episode 15634: reward = -72.14, steps = 19 10:19:01 [INFO] train episode 15635: reward = -113.65, steps = 32 10:19:03 [INFO] train episode 15636: reward = -74.95, steps = 25 10:19:05 [INFO] train episode 15637: reward = -78.30, steps = 20 10:19:07 [INFO] train episode 15638: reward = -89.24, steps = 21 10:19:09 [INFO] train episode 15639: reward = -81.20, steps = 27 10:19:11 [INFO] train episode 15640: reward = -71.89, steps = 31 10:19:14 [INFO] train episode 15641: reward = -123.97, steps = 24 10:19:16 [INFO] train episode 15642: reward = -120.88, steps = 23 10:19:18 [INFO] train episode 15643: reward = -74.23, steps = 19 10:19:19 [INFO] train episode 15644: reward = -69.17, steps = 19 10:19:21 [INFO] train episode 15645: reward = -76.51, steps = 22 10:19:24 [INFO] train episode 15646: reward = -116.69, steps = 33 10:19:26 [INFO] train episode 15647: reward = -66.47, steps = 20 10:19:27 [INFO] train episode 15648: reward = -56.88, steps = 19 10:19:29 [INFO] train episode 15649: reward = -101.80, steps = 23 10:19:31 [INFO] train episode 15650: reward = -110.19, steps = 20 10:19:33 [INFO] train episode 15651: reward = -86.09, steps = 20 10:19:36 [INFO] train episode 15652: reward = -107.34, steps = 41 10:19:39 [INFO] train episode 15653: reward = -49.76, steps = 25 10:19:41 [INFO] train episode 15654: reward = -88.96, steps = 28 10:19:43 [INFO] train episode 15655: reward = -47.73, steps = 23 10:19:46 [INFO] train episode 15656: reward = -67.06, steps = 28 10:19:48 [INFO] train episode 15657: reward = -52.71, steps = 24 10:19:50 [INFO] train episode 15658: reward = -117.59, steps = 22 10:19:52 [INFO] train episode 15659: reward = -85.25, steps = 22 10:19:53 [INFO] train episode 15660: reward = -180.18, steps = 19 10:19:55 [INFO] train episode 15661: reward = -82.27, steps = 21 10:19:57 [INFO] train episode 15662: reward = -88.19, steps = 24 10:20:00 [INFO] train episode 15663: reward = -85.97, steps = 32 10:20:02 [INFO] train episode 15664: reward = -67.36, steps = 20 10:20:05 [INFO] train episode 15665: reward = -98.55, steps = 29 10:20:06 [INFO] train episode 15666: reward = -107.35, steps = 21 10:20:08 [INFO] train episode 15667: reward = -83.15, steps = 23 10:20:10 [INFO] train episode 15668: reward = -69.89, steps = 20 10:20:12 [INFO] train episode 15669: reward = -100.62, steps = 20 10:20:14 [INFO] train episode 15670: reward = -81.43, steps = 21 10:20:18 [INFO] train episode 15671: reward = -101.79, steps = 43 10:20:20 [INFO] train episode 15672: reward = -101.48, steps = 25 10:20:21 [INFO] train episode 15673: reward = -89.32, steps = 20 10:20:23 [INFO] train episode 15674: reward = -75.60, steps = 19 10:20:25 [INFO] train episode 15675: reward = -83.12, steps = 22 10:20:27 [INFO] train episode 15676: reward = -138.26, steps = 19 10:20:29 [INFO] train episode 15677: reward = -135.44, steps = 26 10:20:30 [INFO] train episode 15678: reward = -83.19, steps = 19 10:20:32 [INFO] train episode 15679: reward = -72.82, steps = 20 10:20:38 [INFO] train episode 15680: reward = -150.40, steps = 65 10:20:40 [INFO] train episode 15681: reward = -67.77, steps = 27 10:20:43 [INFO] train episode 15682: reward = -83.13, steps = 30 10:20:45 [INFO] train episode 15683: reward = -81.34, steps = 25 10:20:47 [INFO] train episode 15684: reward = -105.61, steps = 27 10:20:50 [INFO] train episode 15685: reward = -91.09, steps = 23 10:20:52 [INFO] train episode 15686: reward = -73.15, steps = 18 10:20:55 [INFO] train episode 15687: reward = -51.41, steps = 21 10:20:57 [INFO] train episode 15688: reward = -107.40, steps = 25 10:20:59 [INFO] train episode 15689: reward = -84.41, steps = 21 10:21:01 [INFO] train episode 15690: reward = -111.18, steps = 23 10:21:04 [INFO] train episode 15691: reward = -86.61, steps = 23 10:21:06 [INFO] train episode 15692: reward = -127.10, steps = 29 10:21:10 [INFO] train episode 15693: reward = -144.24, steps = 35 10:21:12 [INFO] train episode 15694: reward = -72.06, steps = 25 10:21:14 [INFO] train episode 15695: reward = -55.41, steps = 20 10:21:16 [INFO] train episode 15696: reward = -64.53, steps = 19 10:21:17 [INFO] train episode 15697: reward = -68.21, steps = 20 10:21:19 [INFO] train episode 15698: reward = -75.45, steps = 24 10:21:21 [INFO] train episode 15699: reward = -71.14, steps = 23 10:21:23 [INFO] train episode 15700: reward = -82.36, steps = 20 10:21:25 [INFO] train episode 15701: reward = -80.57, steps = 22 10:21:27 [INFO] train episode 15702: reward = -94.42, steps = 24 10:21:30 [INFO] train episode 15703: reward = -102.90, steps = 33 10:21:32 [INFO] train episode 15704: reward = -62.50, steps = 20 10:21:34 [INFO] train episode 15705: reward = -115.27, steps = 25 10:21:37 [INFO] train episode 15706: reward = -94.53, steps = 31 10:21:40 [INFO] train episode 15707: reward = -98.72, steps = 31 10:21:42 [INFO] train episode 15708: reward = -70.22, steps = 22 10:21:44 [INFO] train episode 15709: reward = -67.17, steps = 25 10:21:45 [INFO] train episode 15710: reward = -92.28, steps = 19 10:21:50 [INFO] train episode 15711: reward = -118.17, steps = 56 10:21:53 [INFO] train episode 15712: reward = -91.71, steps = 39 10:21:55 [INFO] train episode 15713: reward = -75.48, steps = 20 10:21:57 [INFO] train episode 15714: reward = -93.16, steps = 20 10:21:59 [INFO] train episode 15715: reward = -66.16, steps = 22 10:22:02 [INFO] train episode 15716: reward = -86.92, steps = 32 10:22:03 [INFO] train episode 15717: reward = -86.37, steps = 20 10:22:05 [INFO] train episode 15718: reward = -96.42, steps = 19 10:22:07 [INFO] train episode 15719: reward = -87.52, steps = 22 10:22:09 [INFO] train episode 15720: reward = -98.45, steps = 24 10:22:10 [INFO] train episode 15721: reward = -95.51, steps = 18 10:22:13 [INFO] train episode 15722: reward = -52.15, steps = 22 10:22:14 [INFO] train episode 15723: reward = -103.23, steps = 20 10:22:17 [INFO] train episode 15724: reward = -71.15, steps = 35 10:22:19 [INFO] train episode 15725: reward = -88.64, steps = 21 10:22:21 [INFO] train episode 15726: reward = -97.62, steps = 21 10:22:23 [INFO] train episode 15727: reward = -60.67, steps = 25 10:22:27 [INFO] train episode 15728: reward = -83.93, steps = 44 10:22:29 [INFO] train episode 15729: reward = -59.07, steps = 24 10:22:31 [INFO] train episode 15730: reward = -89.92, steps = 19 10:22:33 [INFO] train episode 15731: reward = -86.69, steps = 21 10:22:34 [INFO] train episode 15732: reward = -78.96, steps = 20 10:22:37 [INFO] train episode 15733: reward = -138.36, steps = 28 10:22:39 [INFO] train episode 15734: reward = -86.15, steps = 25 10:22:41 [INFO] train episode 15735: reward = -89.78, steps = 29 10:22:44 [INFO] train episode 15736: reward = -90.12, steps = 21 10:22:45 [INFO] train episode 15737: reward = -90.77, steps = 20 10:22:48 [INFO] train episode 15738: reward = -122.05, steps = 30 10:22:50 [INFO] train episode 15739: reward = -108.19, steps = 21 10:22:51 [INFO] train episode 15740: reward = -80.20, steps = 20 10:22:54 [INFO] train episode 15741: reward = -83.74, steps = 24 10:22:57 [INFO] train episode 15742: reward = -114.67, steps = 37 10:22:59 [INFO] train episode 15743: reward = -102.50, steps = 27 10:23:01 [INFO] train episode 15744: reward = -84.08, steps = 22 10:23:03 [INFO] train episode 15745: reward = -75.52, steps = 24 10:23:05 [INFO] train episode 15746: reward = -69.57, steps = 20 10:23:08 [INFO] train episode 15747: reward = -128.37, steps = 34 10:23:10 [INFO] train episode 15748: reward = -88.69, steps = 29 10:23:13 [INFO] train episode 15749: reward = -68.70, steps = 26 10:23:15 [INFO] train episode 15750: reward = -95.12, steps = 23 10:23:18 [INFO] train episode 15751: reward = -98.02, steps = 34 10:23:20 [INFO] train episode 15752: reward = -83.68, steps = 30 10:23:22 [INFO] train episode 15753: reward = -112.21, steps = 19 10:23:24 [INFO] train episode 15754: reward = -109.69, steps = 19 10:23:26 [INFO] train episode 15755: reward = -74.51, steps = 22 10:23:27 [INFO] train episode 15756: reward = -55.54, steps = 21 10:23:30 [INFO] train episode 15757: reward = -95.40, steps = 29 10:23:32 [INFO] train episode 15758: reward = -90.44, steps = 20 10:23:34 [INFO] train episode 15759: reward = -106.14, steps = 24 10:23:36 [INFO] train episode 15760: reward = -94.86, steps = 23 10:23:38 [INFO] train episode 15761: reward = -78.50, steps = 20 10:23:40 [INFO] train episode 15762: reward = -108.30, steps = 25 10:23:42 [INFO] train episode 15763: reward = -66.28, steps = 23 10:23:44 [INFO] train episode 15764: reward = -94.35, steps = 21 10:23:47 [INFO] train episode 15765: reward = -87.03, steps = 20 10:23:48 [INFO] train episode 15766: reward = -61.62, steps = 19 10:23:50 [INFO] train episode 15767: reward = -98.13, steps = 20 10:23:52 [INFO] train episode 15768: reward = -98.49, steps = 24 10:23:54 [INFO] train episode 15769: reward = -106.92, steps = 20 10:23:56 [INFO] train episode 15770: reward = -57.64, steps = 28 10:23:58 [INFO] train episode 15771: reward = -81.50, steps = 21 10:24:02 [INFO] train episode 15772: reward = -124.73, steps = 40 10:24:04 [INFO] train episode 15773: reward = -85.66, steps = 21 10:24:06 [INFO] train episode 15774: reward = -101.71, steps = 34 10:24:09 [INFO] train episode 15775: reward = -68.51, steps = 25 10:24:11 [INFO] train episode 15776: reward = -146.55, steps = 22 10:24:12 [INFO] train episode 15777: reward = -87.25, steps = 19 10:24:14 [INFO] train episode 15778: reward = -100.39, steps = 20 10:24:16 [INFO] train episode 15779: reward = -92.04, steps = 21 10:24:18 [INFO] train episode 15780: reward = -58.02, steps = 19 10:24:20 [INFO] train episode 15781: reward = -99.75, steps = 22 10:24:22 [INFO] train episode 15782: reward = -82.45, steps = 26 10:24:24 [INFO] train episode 15783: reward = -110.92, steps = 27 10:24:26 [INFO] train episode 15784: reward = -54.37, steps = 20 10:24:28 [INFO] train episode 15785: reward = -69.97, steps = 22 10:24:30 [INFO] train episode 15786: reward = -80.50, steps = 20 10:24:31 [INFO] train episode 15787: reward = -89.36, steps = 20 10:24:34 [INFO] train episode 15788: reward = -72.43, steps = 29 10:24:36 [INFO] train episode 15789: reward = -77.12, steps = 25 10:24:38 [INFO] train episode 15790: reward = -134.32, steps = 21 10:24:40 [INFO] train episode 15791: reward = -62.39, steps = 21 10:24:42 [INFO] train episode 15792: reward = -67.56, steps = 20 10:24:44 [INFO] train episode 15793: reward = -120.66, steps = 28 10:24:46 [INFO] train episode 15794: reward = -62.15, steps = 19 10:24:48 [INFO] train episode 15795: reward = -68.50, steps = 26 10:24:51 [INFO] train episode 15796: reward = -141.97, steps = 28 10:24:53 [INFO] train episode 15797: reward = -102.32, steps = 25 10:24:55 [INFO] train episode 15798: reward = -76.38, steps = 20 10:24:56 [INFO] train episode 15799: reward = -82.41, steps = 18 10:24:59 [INFO] train episode 15800: reward = -115.47, steps = 32 10:25:01 [INFO] train episode 15801: reward = -94.16, steps = 24 10:25:03 [INFO] train episode 15802: reward = -90.40, steps = 21 10:25:06 [INFO] train episode 15803: reward = -74.49, steps = 30 10:25:08 [INFO] train episode 15804: reward = -81.44, steps = 31 10:25:10 [INFO] train episode 15805: reward = -68.02, steps = 23 10:25:12 [INFO] train episode 15806: reward = -84.16, steps = 20 10:25:14 [INFO] train episode 15807: reward = -94.42, steps = 27 10:25:19 [INFO] train episode 15808: reward = -154.79, steps = 55 10:25:21 [INFO] train episode 15809: reward = -100.37, steps = 19 10:25:23 [INFO] train episode 15810: reward = -98.53, steps = 20 10:25:26 [INFO] train episode 15811: reward = -86.88, steps = 38 10:25:28 [INFO] train episode 15812: reward = -55.25, steps = 21 10:25:30 [INFO] train episode 15813: reward = -70.74, steps = 24 10:25:32 [INFO] train episode 15814: reward = -97.04, steps = 20 10:25:33 [INFO] train episode 15815: reward = -72.45, steps = 20 10:25:36 [INFO] train episode 15816: reward = -68.38, steps = 29 10:25:38 [INFO] train episode 15817: reward = -52.28, steps = 26 10:25:41 [INFO] train episode 15818: reward = -86.33, steps = 26 10:25:42 [INFO] train episode 15819: reward = -69.80, steps = 20 10:25:45 [INFO] train episode 15820: reward = -84.62, steps = 31 10:25:47 [INFO] train episode 15821: reward = -111.44, steps = 25 10:25:49 [INFO] train episode 15822: reward = -107.03, steps = 28 10:25:53 [INFO] train episode 15823: reward = -116.04, steps = 32 10:25:55 [INFO] train episode 15824: reward = -55.55, steps = 26 10:25:59 [INFO] train episode 15825: reward = -88.32, steps = 47 10:26:01 [INFO] train episode 15826: reward = -86.18, steps = 26 10:26:05 [INFO] train episode 15827: reward = -123.34, steps = 44 10:26:06 [INFO] train episode 15828: reward = -99.94, steps = 19 10:26:08 [INFO] train episode 15829: reward = -89.98, steps = 19 10:26:11 [INFO] train episode 15830: reward = -90.26, steps = 26 10:26:13 [INFO] train episode 15831: reward = -109.64, steps = 28 10:26:15 [INFO] train episode 15832: reward = -71.85, steps = 21 10:26:17 [INFO] train episode 15833: reward = -71.72, steps = 21 10:26:19 [INFO] train episode 15834: reward = -80.46, steps = 30 10:26:21 [INFO] train episode 15835: reward = -82.58, steps = 27 10:26:25 [INFO] train episode 15836: reward = -77.21, steps = 34 10:26:28 [INFO] train episode 15837: reward = -136.20, steps = 45 10:26:31 [INFO] train episode 15838: reward = -85.70, steps = 27 10:26:33 [INFO] train episode 15839: reward = -104.32, steps = 27 10:26:37 [INFO] train episode 15840: reward = -157.59, steps = 37 10:26:39 [INFO] train episode 15841: reward = -108.24, steps = 26 10:26:42 [INFO] train episode 15842: reward = -77.79, steps = 29 10:26:46 [INFO] train episode 15843: reward = -99.25, steps = 43 10:26:48 [INFO] train episode 15844: reward = -65.18, steps = 21 10:26:50 [INFO] train episode 15845: reward = -67.97, steps = 24 10:26:51 [INFO] train episode 15846: reward = -80.50, steps = 20 10:26:53 [INFO] train episode 15847: reward = -85.16, steps = 19 10:26:55 [INFO] train episode 15848: reward = -91.09, steps = 28 10:26:58 [INFO] train episode 15849: reward = -51.82, steps = 27 10:27:00 [INFO] train episode 15850: reward = -89.07, steps = 25 10:27:05 [INFO] train episode 15851: reward = -107.99, steps = 54 10:27:07 [INFO] train episode 15852: reward = -68.36, steps = 20 10:27:09 [INFO] train episode 15853: reward = -79.23, steps = 32 10:27:12 [INFO] train episode 15854: reward = -109.99, steps = 32 10:27:14 [INFO] train episode 15855: reward = -79.25, steps = 20 10:27:16 [INFO] train episode 15856: reward = -59.49, steps = 22 10:27:18 [INFO] train episode 15857: reward = -109.32, steps = 19 10:27:19 [INFO] train episode 15858: reward = -69.10, steps = 19 10:27:21 [INFO] train episode 15859: reward = -82.49, steps = 23 10:27:23 [INFO] train episode 15860: reward = -78.44, steps = 18 10:27:25 [INFO] train episode 15861: reward = -112.88, steps = 20 10:27:27 [INFO] train episode 15862: reward = -99.20, steps = 23 10:27:29 [INFO] train episode 15863: reward = -83.65, steps = 28 10:27:32 [INFO] train episode 15864: reward = -150.74, steps = 30 10:27:34 [INFO] train episode 15865: reward = -101.00, steps = 22 10:27:36 [INFO] train episode 15866: reward = -81.04, steps = 22 10:27:38 [INFO] train episode 15867: reward = -109.31, steps = 25 10:27:41 [INFO] train episode 15868: reward = -99.92, steps = 32 10:27:43 [INFO] train episode 15869: reward = -97.27, steps = 24 10:27:45 [INFO] train episode 15870: reward = -69.72, steps = 23 10:27:47 [INFO] train episode 15871: reward = -95.72, steps = 21 10:27:49 [INFO] train episode 15872: reward = -101.82, steps = 19 10:27:51 [INFO] train episode 15873: reward = -68.44, steps = 32 10:27:53 [INFO] train episode 15874: reward = -80.09, steps = 24 10:27:57 [INFO] train episode 15875: reward = -162.62, steps = 41 10:27:58 [INFO] train episode 15876: reward = -84.70, steps = 20 10:28:02 [INFO] train episode 15877: reward = -85.60, steps = 33 10:28:03 [INFO] train episode 15878: reward = -82.47, steps = 20 10:28:05 [INFO] train episode 15879: reward = -99.88, steps = 19 10:28:07 [INFO] train episode 15880: reward = -78.09, steps = 20 10:28:09 [INFO] train episode 15881: reward = -65.01, steps = 22 10:28:12 [INFO] train episode 15882: reward = -109.29, steps = 35 10:28:13 [INFO] train episode 15883: reward = -75.45, steps = 19 10:28:15 [INFO] train episode 15884: reward = -86.47, steps = 21 10:28:19 [INFO] train episode 15885: reward = -132.71, steps = 42 10:28:20 [INFO] train episode 15886: reward = -102.50, steps = 18 10:28:23 [INFO] train episode 15887: reward = -98.99, steps = 29 10:28:25 [INFO] train episode 15888: reward = -66.30, steps = 20 10:28:26 [INFO] train episode 15889: reward = -72.31, steps = 20 10:28:31 [INFO] train episode 15890: reward = -120.65, steps = 50 10:28:33 [INFO] train episode 15891: reward = -70.51, steps = 22 10:28:34 [INFO] train episode 15892: reward = -100.88, steps = 18 10:28:37 [INFO] train episode 15893: reward = -100.56, steps = 25 10:28:39 [INFO] train episode 15894: reward = -83.19, steps = 24 10:28:40 [INFO] train episode 15895: reward = -65.88, steps = 20 10:28:42 [INFO] train episode 15896: reward = -101.08, steps = 18 10:28:44 [INFO] train episode 15897: reward = -85.13, steps = 20 10:28:46 [INFO] train episode 15898: reward = -80.67, steps = 28 10:28:48 [INFO] train episode 15899: reward = -101.08, steps = 20 10:28:50 [INFO] train episode 15900: reward = -77.44, steps = 22 10:28:52 [INFO] train episode 15901: reward = -61.30, steps = 20 10:28:54 [INFO] train episode 15902: reward = -66.99, steps = 21 10:28:56 [INFO] train episode 15903: reward = -93.90, steps = 34 10:28:59 [INFO] train episode 15904: reward = -79.11, steps = 26 10:29:01 [INFO] train episode 15905: reward = -99.16, steps = 25 10:29:04 [INFO] train episode 15906: reward = -73.54, steps = 22 10:29:05 [INFO] train episode 15907: reward = -108.61, steps = 19 10:29:07 [INFO] train episode 15908: reward = -81.23, steps = 19 10:29:09 [INFO] train episode 15909: reward = -90.07, steps = 20 10:29:11 [INFO] train episode 15910: reward = -79.30, steps = 21 10:29:14 [INFO] train episode 15911: reward = -102.40, steps = 33 10:29:17 [INFO] train episode 15912: reward = -118.27, steps = 42 10:29:20 [INFO] train episode 15913: reward = -107.72, steps = 28 10:29:22 [INFO] train episode 15914: reward = -103.45, steps = 24 10:29:24 [INFO] train episode 15915: reward = -124.03, steps = 26 10:29:26 [INFO] train episode 15916: reward = -110.52, steps = 21 10:29:28 [INFO] train episode 15917: reward = -79.27, steps = 19 10:29:30 [INFO] train episode 15918: reward = -66.45, steps = 24 10:29:33 [INFO] train episode 15919: reward = -74.47, steps = 33 10:29:35 [INFO] train episode 15920: reward = -52.09, steps = 24 10:29:37 [INFO] train episode 15921: reward = -83.91, steps = 21 10:29:39 [INFO] train episode 15922: reward = -82.05, steps = 21 10:29:41 [INFO] train episode 15923: reward = -121.02, steps = 28 10:29:44 [INFO] train episode 15924: reward = -94.55, steps = 28 10:29:46 [INFO] train episode 15925: reward = -69.97, steps = 24 10:29:48 [INFO] train episode 15926: reward = -106.35, steps = 24 10:29:50 [INFO] train episode 15927: reward = -89.30, steps = 26 10:29:52 [INFO] train episode 15928: reward = -67.88, steps = 21 10:29:54 [INFO] train episode 15929: reward = -93.98, steps = 19 10:29:56 [INFO] train episode 15930: reward = -95.62, steps = 25 10:29:58 [INFO] train episode 15931: reward = -95.07, steps = 28 10:30:01 [INFO] train episode 15932: reward = -107.22, steps = 27 10:30:06 [INFO] train episode 15933: reward = -131.04, steps = 67 10:30:09 [INFO] train episode 15934: reward = -55.88, steps = 22 10:30:10 [INFO] train episode 15935: reward = -76.30, steps = 22 10:30:12 [INFO] train episode 15936: reward = -54.17, steps = 20 10:30:14 [INFO] train episode 15937: reward = -96.00, steps = 25 10:30:18 [INFO] train episode 15938: reward = -90.70, steps = 39 10:30:20 [INFO] train episode 15939: reward = -102.56, steps = 25 10:30:21 [INFO] train episode 15940: reward = -44.43, steps = 19 10:30:24 [INFO] train episode 15941: reward = -100.70, steps = 24 10:30:27 [INFO] train episode 15942: reward = -88.91, steps = 33 10:30:28 [INFO] train episode 15943: reward = -99.38, steps = 21 10:30:31 [INFO] train episode 15944: reward = -130.94, steps = 31 10:30:33 [INFO] train episode 15945: reward = -126.96, steps = 19 10:30:34 [INFO] train episode 15946: reward = -83.91, steps = 20 10:30:36 [INFO] train episode 15947: reward = -75.60, steps = 24 10:30:39 [INFO] train episode 15948: reward = -56.26, steps = 20 10:30:41 [INFO] train episode 15949: reward = -61.05, steps = 23 10:30:44 [INFO] train episode 15950: reward = -59.14, steps = 36 10:30:46 [INFO] train episode 15951: reward = -100.18, steps = 25 10:30:48 [INFO] train episode 15952: reward = -75.81, steps = 26 10:30:51 [INFO] train episode 15953: reward = -69.56, steps = 31 10:30:52 [INFO] train episode 15954: reward = -88.39, steps = 21 10:30:55 [INFO] train episode 15955: reward = -53.06, steps = 30 10:30:58 [INFO] train episode 15956: reward = -86.81, steps = 31 10:31:00 [INFO] train episode 15957: reward = -72.52, steps = 28 10:31:02 [INFO] train episode 15958: reward = -130.26, steps = 24 10:31:06 [INFO] train episode 15959: reward = -112.34, steps = 38 10:31:08 [INFO] train episode 15960: reward = -80.00, steps = 20 10:31:10 [INFO] train episode 15961: reward = -71.53, steps = 20 10:31:12 [INFO] train episode 15962: reward = -88.27, steps = 30 10:31:14 [INFO] train episode 15963: reward = -92.06, steps = 22 10:31:17 [INFO] train episode 15964: reward = -57.19, steps = 32 10:31:19 [INFO] train episode 15965: reward = -154.76, steps = 27 10:31:22 [INFO] train episode 15966: reward = -98.55, steps = 39 10:31:26 [INFO] train episode 15967: reward = -87.54, steps = 32 10:31:27 [INFO] train episode 15968: reward = -62.20, steps = 21 10:31:30 [INFO] train episode 15969: reward = -129.22, steps = 32 10:31:32 [INFO] train episode 15970: reward = -90.04, steps = 18 10:31:33 [INFO] train episode 15971: reward = -89.49, steps = 22 10:31:37 [INFO] train episode 15972: reward = -97.09, steps = 37 10:31:40 [INFO] train episode 15973: reward = -64.88, steps = 35 10:31:42 [INFO] train episode 15974: reward = -59.27, steps = 21 10:31:44 [INFO] train episode 15975: reward = -64.30, steps = 30 10:31:46 [INFO] train episode 15976: reward = -82.11, steps = 23 10:31:50 [INFO] train episode 15977: reward = -104.63, steps = 42 10:31:52 [INFO] train episode 15978: reward = -126.13, steps = 31 10:31:54 [INFO] train episode 15979: reward = -72.69, steps = 19 10:31:56 [INFO] train episode 15980: reward = -53.98, steps = 21 10:31:58 [INFO] train episode 15981: reward = -75.14, steps = 26 10:32:00 [INFO] train episode 15982: reward = -80.85, steps = 22 10:32:03 [INFO] train episode 15983: reward = -93.91, steps = 30 10:32:05 [INFO] train episode 15984: reward = -69.44, steps = 20 10:32:07 [INFO] train episode 15985: reward = -111.32, steps = 24 10:32:09 [INFO] train episode 15986: reward = -114.14, steps = 26 10:32:11 [INFO] train episode 15987: reward = -58.29, steps = 26 10:32:14 [INFO] train episode 15988: reward = -76.55, steps = 26 10:32:18 [INFO] train episode 15989: reward = -96.05, steps = 43 10:32:21 [INFO] train episode 15990: reward = -86.84, steps = 29 10:32:23 [INFO] train episode 15991: reward = -95.85, steps = 20 10:32:25 [INFO] train episode 15992: reward = -69.07, steps = 26 10:32:27 [INFO] train episode 15993: reward = -85.22, steps = 20 10:32:31 [INFO] train episode 15994: reward = -126.12, steps = 44 10:32:33 [INFO] train episode 15995: reward = -140.75, steps = 26 10:32:35 [INFO] train episode 15996: reward = -114.37, steps = 27 10:32:39 [INFO] train episode 15997: reward = -150.57, steps = 41 10:32:44 [INFO] train episode 15998: reward = -187.60, steps = 60 10:32:46 [INFO] train episode 15999: reward = -90.42, steps = 20 10:32:48 [INFO] train episode 16000: reward = -86.24, steps = 21 10:32:49 [INFO] train episode 16001: reward = -76.71, steps = 20 10:32:51 [INFO] train episode 16002: reward = -80.33, steps = 20 10:32:53 [INFO] train episode 16003: reward = -98.69, steps = 20 10:32:56 [INFO] train episode 16004: reward = -110.23, steps = 38 10:32:58 [INFO] train episode 16005: reward = -119.68, steps = 29 10:33:00 [INFO] train episode 16006: reward = -65.52, steps = 22 10:33:05 [INFO] train episode 16007: reward = -98.63, steps = 45 10:33:06 [INFO] train episode 16008: reward = -62.22, steps = 21 10:33:08 [INFO] train episode 16009: reward = -84.25, steps = 20 10:33:10 [INFO] train episode 16010: reward = -107.69, steps = 21 10:33:12 [INFO] train episode 16011: reward = -95.63, steps = 26 10:33:15 [INFO] train episode 16012: reward = -110.56, steps = 32 10:33:18 [INFO] train episode 16013: reward = -100.36, steps = 29 10:33:19 [INFO] train episode 16014: reward = -90.98, steps = 19 10:33:21 [INFO] train episode 16015: reward = -71.85, steps = 22 10:33:24 [INFO] train episode 16016: reward = -73.45, steps = 33 10:33:26 [INFO] train episode 16017: reward = -60.44, steps = 24 10:33:28 [INFO] train episode 16018: reward = -96.01, steps = 26 10:33:30 [INFO] train episode 16019: reward = -78.26, steps = 21 10:33:33 [INFO] train episode 16020: reward = -70.32, steps = 24 10:33:35 [INFO] train episode 16021: reward = -97.12, steps = 26 10:33:36 [INFO] train episode 16022: reward = -45.17, steps = 20 10:33:39 [INFO] train episode 16023: reward = -74.95, steps = 26 10:33:40 [INFO] train episode 16024: reward = -69.58, steps = 20 10:33:42 [INFO] train episode 16025: reward = -50.26, steps = 22 10:33:44 [INFO] train episode 16026: reward = -94.85, steps = 24 10:33:47 [INFO] train episode 16027: reward = -79.37, steps = 26 10:33:49 [INFO] train episode 16028: reward = -77.25, steps = 20 10:33:50 [INFO] train episode 16029: reward = -71.11, steps = 20 10:33:52 [INFO] train episode 16030: reward = -72.28, steps = 20 10:33:54 [INFO] train episode 16031: reward = -59.41, steps = 26 10:33:56 [INFO] train episode 16032: reward = -86.82, steps = 26 10:33:58 [INFO] train episode 16033: reward = -53.39, steps = 21 10:34:00 [INFO] train episode 16034: reward = -72.42, steps = 20 10:34:03 [INFO] train episode 16035: reward = -89.22, steps = 29 10:34:05 [INFO] train episode 16036: reward = -95.72, steps = 24 10:34:07 [INFO] train episode 16037: reward = -77.28, steps = 21 10:34:09 [INFO] train episode 16038: reward = -48.51, steps = 22 10:34:10 [INFO] train episode 16039: reward = -107.31, steps = 20 10:34:12 [INFO] train episode 16040: reward = -68.67, steps = 20 10:34:14 [INFO] train episode 16041: reward = -100.13, steps = 21 10:34:16 [INFO] train episode 16042: reward = -70.43, steps = 20 10:34:18 [INFO] train episode 16043: reward = -65.53, steps = 32 10:34:21 [INFO] train episode 16044: reward = -81.92, steps = 22 10:34:22 [INFO] train episode 16045: reward = -112.58, steps = 21 10:34:24 [INFO] train episode 16046: reward = -90.63, steps = 20 10:34:26 [INFO] train episode 16047: reward = -105.38, steps = 23 10:34:28 [INFO] train episode 16048: reward = -78.44, steps = 22 10:34:30 [INFO] train episode 16049: reward = -78.08, steps = 22 10:34:33 [INFO] train episode 16050: reward = -114.77, steps = 37 10:34:36 [INFO] train episode 16051: reward = -126.37, steps = 25 10:34:38 [INFO] train episode 16052: reward = -97.33, steps = 30 10:34:40 [INFO] train episode 16053: reward = -58.78, steps = 21 10:34:42 [INFO] train episode 16054: reward = -83.83, steps = 19 10:34:43 [INFO] train episode 16055: reward = -62.04, steps = 22 10:34:45 [INFO] train episode 16056: reward = -90.47, steps = 19 10:34:47 [INFO] train episode 16057: reward = -93.59, steps = 26 10:34:49 [INFO] train episode 16058: reward = -75.17, steps = 24 10:34:52 [INFO] train episode 16059: reward = -49.14, steps = 24 10:34:54 [INFO] train episode 16060: reward = -75.59, steps = 25 10:34:56 [INFO] train episode 16061: reward = -69.16, steps = 19 10:34:57 [INFO] train episode 16062: reward = -72.29, steps = 21 10:34:59 [INFO] train episode 16063: reward = -80.76, steps = 22 10:35:01 [INFO] train episode 16064: reward = -91.05, steps = 20 10:35:03 [INFO] train episode 16065: reward = -88.22, steps = 20 10:35:05 [INFO] train episode 16066: reward = -82.63, steps = 30 10:35:09 [INFO] train episode 16067: reward = -56.24, steps = 24 10:35:12 [INFO] train episode 16068: reward = -99.88, steps = 37 10:35:14 [INFO] train episode 16069: reward = -72.81, steps = 30 10:35:19 [INFO] train episode 16070: reward = -171.51, steps = 56 10:35:24 [INFO] train episode 16071: reward = -163.69, steps = 52 10:35:25 [INFO] train episode 16072: reward = -75.57, steps = 19 10:35:27 [INFO] train episode 16073: reward = -100.06, steps = 20 10:35:29 [INFO] train episode 16074: reward = -58.55, steps = 22 10:35:31 [INFO] train episode 16075: reward = -79.04, steps = 19 10:35:33 [INFO] train episode 16076: reward = -63.60, steps = 29 10:35:35 [INFO] train episode 16077: reward = -95.19, steps = 22 10:35:36 [INFO] train episode 16078: reward = -85.91, steps = 19 10:35:39 [INFO] train episode 16079: reward = -90.32, steps = 25 10:35:41 [INFO] train episode 16080: reward = -61.77, steps = 22 10:35:43 [INFO] train episode 16081: reward = -71.51, steps = 27 10:35:45 [INFO] train episode 16082: reward = -64.03, steps = 25 10:35:48 [INFO] train episode 16083: reward = -81.33, steps = 28 10:35:49 [INFO] train episode 16084: reward = -63.91, steps = 19 10:35:51 [INFO] train episode 16085: reward = -95.07, steps = 20 10:35:55 [INFO] train episode 16086: reward = -121.99, steps = 39 10:35:57 [INFO] train episode 16087: reward = -57.80, steps = 22 10:35:59 [INFO] train episode 16088: reward = -64.20, steps = 25 10:36:01 [INFO] train episode 16089: reward = -76.28, steps = 29 10:36:05 [INFO] train episode 16090: reward = -117.27, steps = 42 10:36:07 [INFO] train episode 16091: reward = -66.82, steps = 20 10:36:08 [INFO] train episode 16092: reward = -109.11, steps = 20 10:36:12 [INFO] train episode 16093: reward = -139.28, steps = 36 10:36:14 [INFO] train episode 16094: reward = -87.99, steps = 20 10:36:15 [INFO] train episode 16095: reward = -63.78, steps = 21 10:36:17 [INFO] train episode 16096: reward = -75.67, steps = 20 10:36:20 [INFO] train episode 16097: reward = -116.32, steps = 34 10:36:22 [INFO] train episode 16098: reward = -98.74, steps = 21 10:36:24 [INFO] train episode 16099: reward = -95.40, steps = 21 10:36:25 [INFO] train episode 16100: reward = -50.36, steps = 20 10:36:27 [INFO] train episode 16101: reward = -97.22, steps = 21 10:36:31 [INFO] train episode 16102: reward = -104.45, steps = 38 10:36:32 [INFO] train episode 16103: reward = -79.73, steps = 20 10:36:34 [INFO] train episode 16104: reward = -104.43, steps = 25 10:36:36 [INFO] train episode 16105: reward = -68.10, steps = 20 10:36:39 [INFO] train episode 16106: reward = -80.62, steps = 35 10:36:41 [INFO] train episode 16107: reward = -50.12, steps = 21 10:36:43 [INFO] train episode 16108: reward = -83.36, steps = 20 10:36:47 [INFO] train episode 16109: reward = -134.32, steps = 48 10:36:50 [INFO] train episode 16110: reward = -66.41, steps = 34 10:36:54 [INFO] train episode 16111: reward = -128.27, steps = 46 10:36:56 [INFO] train episode 16112: reward = -57.12, steps = 21 10:36:57 [INFO] train episode 16113: reward = -81.40, steps = 19 10:37:00 [INFO] train episode 16114: reward = -80.83, steps = 23 10:37:03 [INFO] train episode 16115: reward = -100.47, steps = 40 10:37:05 [INFO] train episode 16116: reward = -62.58, steps = 20 10:37:06 [INFO] train episode 16117: reward = -96.30, steps = 19 10:37:08 [INFO] train episode 16118: reward = -109.66, steps = 20 10:37:10 [INFO] train episode 16119: reward = -86.03, steps = 21 10:37:12 [INFO] train episode 16120: reward = -93.83, steps = 23 10:37:16 [INFO] train episode 16121: reward = -102.82, steps = 41 10:37:17 [INFO] train episode 16122: reward = -69.86, steps = 21 10:37:19 [INFO] train episode 16123: reward = -73.69, steps = 21 10:37:21 [INFO] train episode 16124: reward = -75.44, steps = 19 10:37:23 [INFO] train episode 16125: reward = -91.27, steps = 27 10:37:25 [INFO] train episode 16126: reward = -69.40, steps = 20 10:37:28 [INFO] train episode 16127: reward = -71.67, steps = 28 10:37:30 [INFO] train episode 16128: reward = -100.05, steps = 27 10:37:32 [INFO] train episode 16129: reward = -89.43, steps = 23 10:37:34 [INFO] train episode 16130: reward = -58.46, steps = 22 10:37:36 [INFO] train episode 16131: reward = -64.41, steps = 25 10:37:40 [INFO] train episode 16132: reward = -115.33, steps = 49 10:37:42 [INFO] train episode 16133: reward = -81.62, steps = 19 10:37:45 [INFO] train episode 16134: reward = -102.69, steps = 30 10:37:48 [INFO] train episode 16135: reward = -91.19, steps = 36 10:37:50 [INFO] train episode 16136: reward = -97.52, steps = 23 10:37:52 [INFO] train episode 16137: reward = -79.01, steps = 26 10:37:54 [INFO] train episode 16138: reward = -90.20, steps = 18 10:37:56 [INFO] train episode 16139: reward = -88.43, steps = 27 10:37:59 [INFO] train episode 16140: reward = -81.18, steps = 24 10:38:01 [INFO] train episode 16141: reward = -59.64, steps = 21 10:38:04 [INFO] train episode 16142: reward = -103.28, steps = 32 10:38:05 [INFO] train episode 16143: reward = -87.51, steps = 19 10:38:07 [INFO] train episode 16144: reward = -73.81, steps = 20 10:38:09 [INFO] train episode 16145: reward = -86.76, steps = 20 10:38:11 [INFO] train episode 16146: reward = -49.28, steps = 20 10:38:12 [INFO] train episode 16147: reward = -50.19, steps = 22 10:38:14 [INFO] train episode 16148: reward = -71.15, steps = 23 10:38:16 [INFO] train episode 16149: reward = -95.47, steps = 20 10:38:19 [INFO] train episode 16150: reward = -78.25, steps = 24 10:38:20 [INFO] train episode 16151: reward = -95.26, steps = 20 10:38:23 [INFO] train episode 16152: reward = -146.12, steps = 29 10:38:25 [INFO] train episode 16153: reward = -77.75, steps = 20 10:38:26 [INFO] train episode 16154: reward = -111.56, steps = 19 10:38:28 [INFO] train episode 16155: reward = -104.59, steps = 21 10:38:30 [INFO] train episode 16156: reward = -104.78, steps = 28 10:38:33 [INFO] train episode 16157: reward = -142.64, steps = 35 10:38:35 [INFO] train episode 16158: reward = -72.08, steps = 20 10:38:39 [INFO] train episode 16159: reward = -98.75, steps = 37 10:38:40 [INFO] train episode 16160: reward = -73.65, steps = 20 10:38:43 [INFO] train episode 16161: reward = -144.26, steps = 29 10:38:45 [INFO] train episode 16162: reward = -51.26, steps = 21 10:38:47 [INFO] train episode 16163: reward = -146.26, steps = 31 10:38:50 [INFO] train episode 16164: reward = -80.30, steps = 22 10:38:52 [INFO] train episode 16165: reward = -86.95, steps = 25 10:38:54 [INFO] train episode 16166: reward = -68.90, steps = 21 10:38:56 [INFO] train episode 16167: reward = -95.58, steps = 24 10:38:58 [INFO] train episode 16168: reward = -95.55, steps = 24 10:39:00 [INFO] train episode 16169: reward = -87.93, steps = 33 10:39:04 [INFO] train episode 16170: reward = -117.24, steps = 40 10:39:06 [INFO] train episode 16171: reward = -122.99, steps = 24 10:39:08 [INFO] train episode 16172: reward = -81.61, steps = 21 10:39:11 [INFO] train episode 16173: reward = -79.96, steps = 38 10:39:13 [INFO] train episode 16174: reward = -83.97, steps = 24 10:39:15 [INFO] train episode 16175: reward = -103.97, steps = 23 10:39:17 [INFO] train episode 16176: reward = -70.58, steps = 21 10:39:19 [INFO] train episode 16177: reward = -151.62, steps = 29 10:39:22 [INFO] train episode 16178: reward = -86.30, steps = 21 10:39:24 [INFO] train episode 16179: reward = -74.90, steps = 27 10:39:26 [INFO] train episode 16180: reward = -83.49, steps = 22 10:39:28 [INFO] train episode 16181: reward = -73.41, steps = 27 10:39:30 [INFO] train episode 16182: reward = -85.85, steps = 23 10:39:32 [INFO] train episode 16183: reward = -65.72, steps = 23 10:39:34 [INFO] train episode 16184: reward = -86.86, steps = 20 10:39:35 [INFO] train episode 16185: reward = -102.39, steps = 19 10:39:38 [INFO] train episode 16186: reward = -48.89, steps = 22 10:39:40 [INFO] train episode 16187: reward = -102.36, steps = 25 10:39:42 [INFO] train episode 16188: reward = -111.25, steps = 21 10:39:43 [INFO] train episode 16189: reward = -65.47, steps = 21 10:39:45 [INFO] train episode 16190: reward = -104.17, steps = 23 10:39:47 [INFO] train episode 16191: reward = -73.28, steps = 19 10:39:49 [INFO] train episode 16192: reward = -131.25, steps = 19 10:39:51 [INFO] train episode 16193: reward = -104.05, steps = 26 10:39:53 [INFO] train episode 16194: reward = -76.08, steps = 20 10:39:55 [INFO] train episode 16195: reward = -75.60, steps = 21 10:39:57 [INFO] train episode 16196: reward = -91.06, steps = 26 10:39:59 [INFO] train episode 16197: reward = -79.64, steps = 23 10:40:00 [INFO] train episode 16198: reward = -61.06, steps = 19 10:40:03 [INFO] train episode 16199: reward = -86.19, steps = 26 10:40:04 [INFO] train episode 16200: reward = -87.03, steps = 20 10:40:06 [INFO] train episode 16201: reward = -91.37, steps = 21 10:40:09 [INFO] train episode 16202: reward = -81.80, steps = 26 10:40:11 [INFO] train episode 16203: reward = -88.28, steps = 30 10:40:13 [INFO] train episode 16204: reward = -84.45, steps = 21 10:40:15 [INFO] train episode 16205: reward = -115.47, steps = 19 10:40:16 [INFO] train episode 16206: reward = -81.39, steps = 19 10:40:19 [INFO] train episode 16207: reward = -91.94, steps = 36 10:40:21 [INFO] train episode 16208: reward = -104.53, steps = 20 10:40:23 [INFO] train episode 16209: reward = -69.49, steps = 21 10:40:25 [INFO] train episode 16210: reward = -96.55, steps = 20 10:40:28 [INFO] train episode 16211: reward = -71.58, steps = 31 10:40:30 [INFO] train episode 16212: reward = -85.33, steps = 25 10:40:32 [INFO] train episode 16213: reward = -84.07, steps = 20 10:40:33 [INFO] train episode 16214: reward = -100.25, steps = 19 10:40:35 [INFO] train episode 16215: reward = -82.32, steps = 19 10:40:37 [INFO] train episode 16216: reward = -78.19, steps = 24 10:40:40 [INFO] train episode 16217: reward = -60.34, steps = 26 10:40:41 [INFO] train episode 16218: reward = -92.86, steps = 22 10:40:44 [INFO] train episode 16219: reward = -79.14, steps = 32 10:40:46 [INFO] train episode 16220: reward = -81.05, steps = 20 10:40:49 [INFO] train episode 16221: reward = -63.17, steps = 32 10:40:52 [INFO] train episode 16222: reward = -85.26, steps = 26 10:40:53 [INFO] train episode 16223: reward = -80.13, steps = 19 10:40:55 [INFO] train episode 16224: reward = -83.91, steps = 21 10:40:57 [INFO] train episode 16225: reward = -75.83, steps = 20 10:40:59 [INFO] train episode 16226: reward = -47.85, steps = 21 10:41:01 [INFO] train episode 16227: reward = -101.53, steps = 23 10:41:03 [INFO] train episode 16228: reward = -52.95, steps = 21 10:41:05 [INFO] train episode 16229: reward = -135.92, steps = 29 10:41:07 [INFO] train episode 16230: reward = -103.65, steps = 25 10:41:11 [INFO] train episode 16231: reward = -102.45, steps = 38 10:41:13 [INFO] train episode 16232: reward = -74.59, steps = 30 10:41:15 [INFO] train episode 16233: reward = -74.66, steps = 20 10:41:17 [INFO] train episode 16234: reward = -74.01, steps = 21 10:41:20 [INFO] train episode 16235: reward = -77.33, steps = 30 10:41:21 [INFO] train episode 16236: reward = -92.99, steps = 21 10:41:23 [INFO] train episode 16237: reward = -63.27, steps = 19 10:41:25 [INFO] train episode 16238: reward = -64.69, steps = 23 10:41:27 [INFO] train episode 16239: reward = -103.42, steps = 19 10:41:29 [INFO] train episode 16240: reward = -87.59, steps = 19 10:41:31 [INFO] train episode 16241: reward = -93.08, steps = 25 10:41:33 [INFO] train episode 16242: reward = -95.54, steps = 21 10:41:34 [INFO] train episode 16243: reward = -51.47, steps = 20 10:41:37 [INFO] train episode 16244: reward = -78.17, steps = 24 10:41:38 [INFO] train episode 16245: reward = -99.22, steps = 19 10:41:40 [INFO] train episode 16246: reward = -109.51, steps = 23 10:41:43 [INFO] train episode 16247: reward = -167.93, steps = 30 10:41:45 [INFO] train episode 16248: reward = -74.81, steps = 20 10:41:47 [INFO] train episode 16249: reward = -78.01, steps = 22 10:41:50 [INFO] train episode 16250: reward = -95.26, steps = 33 10:41:51 [INFO] train episode 16251: reward = -86.60, steps = 20 10:41:54 [INFO] train episode 16252: reward = -85.66, steps = 27 10:41:55 [INFO] train episode 16253: reward = -99.54, steps = 21 10:41:57 [INFO] train episode 16254: reward = -97.01, steps = 21 10:42:00 [INFO] train episode 16255: reward = -89.83, steps = 33 10:42:02 [INFO] train episode 16256: reward = -76.30, steps = 24 10:42:04 [INFO] train episode 16257: reward = -79.55, steps = 19 10:42:06 [INFO] train episode 16258: reward = -71.67, steps = 21 10:42:09 [INFO] train episode 16259: reward = -117.52, steps = 34 10:42:11 [INFO] train episode 16260: reward = -102.99, steps = 23 10:42:13 [INFO] train episode 16261: reward = -94.29, steps = 27 10:42:16 [INFO] train episode 16262: reward = -72.08, steps = 26 10:42:18 [INFO] train episode 16263: reward = -111.71, steps = 28 10:42:20 [INFO] train episode 16264: reward = -117.26, steps = 20 10:42:22 [INFO] train episode 16265: reward = -83.86, steps = 21 10:42:23 [INFO] train episode 16266: reward = -61.61, steps = 21 10:42:25 [INFO] train episode 16267: reward = -74.40, steps = 20 10:42:27 [INFO] train episode 16268: reward = -75.82, steps = 24 10:42:29 [INFO] train episode 16269: reward = -84.05, steps = 21 10:42:32 [INFO] train episode 16270: reward = -128.03, steps = 37 10:42:34 [INFO] train episode 16271: reward = -56.01, steps = 20 10:42:36 [INFO] train episode 16272: reward = -95.96, steps = 20 10:42:38 [INFO] train episode 16273: reward = -93.96, steps = 22 10:42:41 [INFO] train episode 16274: reward = -68.98, steps = 34 10:42:44 [INFO] train episode 16275: reward = -109.35, steps = 41 10:42:48 [INFO] train episode 16276: reward = -70.88, steps = 37 10:42:49 [INFO] train episode 16277: reward = -79.09, steps = 21 10:42:51 [INFO] train episode 16278: reward = -81.29, steps = 19 10:42:53 [INFO] train episode 16279: reward = -99.84, steps = 25 10:42:55 [INFO] train episode 16280: reward = -101.94, steps = 27 10:42:57 [INFO] train episode 16281: reward = -82.39, steps = 24 10:43:00 [INFO] train episode 16282: reward = -106.63, steps = 29 10:43:06 [INFO] train episode 16283: reward = -190.14, steps = 62 10:43:08 [INFO] train episode 16284: reward = -64.21, steps = 24 10:43:10 [INFO] train episode 16285: reward = -80.80, steps = 26 10:43:12 [INFO] train episode 16286: reward = -75.28, steps = 22 10:43:13 [INFO] train episode 16287: reward = -99.72, steps = 19 10:43:16 [INFO] train episode 16288: reward = -99.63, steps = 33 10:43:19 [INFO] train episode 16289: reward = -72.49, steps = 22 10:43:20 [INFO] train episode 16290: reward = -56.93, steps = 23 10:43:23 [INFO] train episode 16291: reward = -91.31, steps = 24 10:43:24 [INFO] train episode 16292: reward = -65.52, steps = 21 10:43:26 [INFO] train episode 16293: reward = -80.66, steps = 22 10:43:29 [INFO] train episode 16294: reward = -84.84, steps = 26 10:43:30 [INFO] train episode 16295: reward = -75.74, steps = 21 10:43:34 [INFO] train episode 16296: reward = -95.67, steps = 38 10:43:36 [INFO] train episode 16297: reward = -133.59, steps = 27 10:43:38 [INFO] train episode 16298: reward = -51.82, steps = 19 10:43:40 [INFO] train episode 16299: reward = -55.62, steps = 21 10:43:43 [INFO] train episode 16300: reward = -72.13, steps = 37 10:43:46 [INFO] train episode 16301: reward = -76.03, steps = 26 10:43:47 [INFO] train episode 16302: reward = -97.96, steps = 20 10:43:49 [INFO] train episode 16303: reward = -52.79, steps = 20 10:43:51 [INFO] train episode 16304: reward = -73.76, steps = 19 10:43:53 [INFO] train episode 16305: reward = -90.10, steps = 28 10:43:56 [INFO] train episode 16306: reward = -95.60, steps = 26 10:43:57 [INFO] train episode 16307: reward = -85.29, steps = 19 10:44:01 [INFO] train episode 16308: reward = -129.10, steps = 42 10:44:03 [INFO] train episode 16309: reward = -121.25, steps = 25 10:44:05 [INFO] train episode 16310: reward = -135.78, steps = 21 10:44:09 [INFO] train episode 16311: reward = -90.31, steps = 48 10:44:11 [INFO] train episode 16312: reward = -84.32, steps = 20 10:44:13 [INFO] train episode 16313: reward = -83.75, steps = 25 10:44:15 [INFO] train episode 16314: reward = -93.64, steps = 28 10:44:18 [INFO] train episode 16315: reward = -68.01, steps = 27 10:44:20 [INFO] train episode 16316: reward = -91.34, steps = 22 10:44:24 [INFO] train episode 16317: reward = -115.76, steps = 44 10:44:25 [INFO] train episode 16318: reward = -61.29, steps = 20 10:44:28 [INFO] train episode 16319: reward = -102.45, steps = 31 10:44:30 [INFO] train episode 16320: reward = -72.23, steps = 26 10:44:32 [INFO] train episode 16321: reward = -68.22, steps = 19 10:44:34 [INFO] train episode 16322: reward = -64.15, steps = 28 10:44:36 [INFO] train episode 16323: reward = -107.58, steps = 21 10:44:39 [INFO] train episode 16324: reward = -100.04, steps = 35 10:44:42 [INFO] train episode 16325: reward = -77.09, steps = 31 10:44:44 [INFO] train episode 16326: reward = -72.16, steps = 20 10:44:46 [INFO] train episode 16327: reward = -64.06, steps = 22 10:44:48 [INFO] train episode 16328: reward = -59.24, steps = 21 10:44:49 [INFO] train episode 16329: reward = -84.50, steps = 22 10:44:52 [INFO] train episode 16330: reward = -64.23, steps = 25 10:44:55 [INFO] train episode 16331: reward = -102.25, steps = 31 10:44:56 [INFO] train episode 16332: reward = -78.32, steps = 22 10:44:59 [INFO] train episode 16333: reward = -113.09, steps = 26 10:45:00 [INFO] train episode 16334: reward = -86.32, steps = 21 10:45:03 [INFO] train episode 16335: reward = -63.83, steps = 25 10:45:05 [INFO] train episode 16336: reward = -106.88, steps = 24 10:45:08 [INFO] train episode 16337: reward = -145.32, steps = 35 10:45:10 [INFO] train episode 16338: reward = -69.50, steps = 23 10:45:12 [INFO] train episode 16339: reward = -92.52, steps = 24 10:45:14 [INFO] train episode 16340: reward = -73.20, steps = 21 10:45:16 [INFO] train episode 16341: reward = -88.28, steps = 22 10:45:20 [INFO] train episode 16342: reward = -131.23, steps = 54 10:45:24 [INFO] train episode 16343: reward = -101.66, steps = 46 10:45:26 [INFO] train episode 16344: reward = -96.73, steps = 22 10:45:28 [INFO] train episode 16345: reward = -85.72, steps = 21 10:45:31 [INFO] train episode 16346: reward = -93.40, steps = 33 10:45:33 [INFO] train episode 16347: reward = -115.83, steps = 26 10:45:36 [INFO] train episode 16348: reward = -71.54, steps = 28 10:45:39 [INFO] train episode 16349: reward = -84.49, steps = 35 10:45:42 [INFO] train episode 16350: reward = -111.89, steps = 33 10:45:44 [INFO] train episode 16351: reward = -73.49, steps = 27 10:45:46 [INFO] train episode 16352: reward = -63.49, steps = 21 10:45:48 [INFO] train episode 16353: reward = -115.98, steps = 25 10:45:50 [INFO] train episode 16354: reward = -49.60, steps = 26 10:45:53 [INFO] train episode 16355: reward = -75.10, steps = 35 10:45:56 [INFO] train episode 16356: reward = -123.89, steps = 26 10:45:57 [INFO] train episode 16357: reward = -61.89, steps = 21 10:46:00 [INFO] train episode 16358: reward = -94.40, steps = 26 10:46:03 [INFO] train episode 16359: reward = -133.65, steps = 34 10:46:04 [INFO] train episode 16360: reward = -102.58, steps = 21 10:46:06 [INFO] train episode 16361: reward = -119.91, steps = 20 10:46:08 [INFO] train episode 16362: reward = -121.77, steps = 24 10:46:10 [INFO] train episode 16363: reward = -59.98, steps = 22 10:46:12 [INFO] train episode 16364: reward = -66.38, steps = 20 10:46:14 [INFO] train episode 16365: reward = -132.47, steps = 22 10:46:16 [INFO] train episode 16366: reward = -93.85, steps = 25 10:46:19 [INFO] train episode 16367: reward = -166.64, steps = 39 10:46:21 [INFO] train episode 16368: reward = -70.22, steps = 23 10:46:23 [INFO] train episode 16369: reward = -91.01, steps = 24 10:46:25 [INFO] train episode 16370: reward = -69.45, steps = 22 10:46:28 [INFO] train episode 16371: reward = -83.58, steps = 22 10:46:30 [INFO] train episode 16372: reward = -105.84, steps = 26 10:46:33 [INFO] train episode 16373: reward = -71.57, steps = 26 10:46:35 [INFO] train episode 16374: reward = -77.04, steps = 21 10:46:36 [INFO] train episode 16375: reward = -99.63, steps = 21 10:46:38 [INFO] train episode 16376: reward = -83.72, steps = 23 10:46:40 [INFO] train episode 16377: reward = -97.08, steps = 22 10:46:42 [INFO] train episode 16378: reward = -67.08, steps = 20 10:46:44 [INFO] train episode 16379: reward = -89.49, steps = 19 10:46:46 [INFO] train episode 16380: reward = -93.95, steps = 24 10:46:49 [INFO] train episode 16381: reward = -96.91, steps = 29 10:46:50 [INFO] train episode 16382: reward = -76.57, steps = 20 10:46:52 [INFO] train episode 16383: reward = -65.96, steps = 20 10:46:54 [INFO] train episode 16384: reward = -88.03, steps = 21 10:46:56 [INFO] train episode 16385: reward = -60.44, steps = 23 10:47:01 [INFO] train episode 16386: reward = -115.47, steps = 59 10:47:03 [INFO] train episode 16387: reward = -89.46, steps = 27 10:47:06 [INFO] train episode 16388: reward = -143.35, steps = 29 10:47:10 [INFO] train episode 16389: reward = -75.36, steps = 44 10:47:11 [INFO] train episode 16390: reward = -94.72, steps = 19 10:47:14 [INFO] train episode 16391: reward = -114.22, steps = 29 10:47:16 [INFO] train episode 16392: reward = -115.47, steps = 27 10:47:18 [INFO] train episode 16393: reward = -61.77, steps = 20 10:47:21 [INFO] train episode 16394: reward = -110.07, steps = 31 10:47:23 [INFO] train episode 16395: reward = -61.42, steps = 23 10:47:25 [INFO] train episode 16396: reward = -80.45, steps = 21 10:47:27 [INFO] train episode 16397: reward = -116.77, steps = 27 10:47:30 [INFO] train episode 16398: reward = -83.50, steps = 27 10:47:32 [INFO] train episode 16399: reward = -81.36, steps = 24 10:47:35 [INFO] train episode 16400: reward = -71.66, steps = 32 10:47:37 [INFO] train episode 16401: reward = -75.84, steps = 27 10:47:39 [INFO] train episode 16402: reward = -132.24, steps = 29 10:47:41 [INFO] train episode 16403: reward = -60.18, steps = 20 10:47:43 [INFO] train episode 16404: reward = -52.93, steps = 22 10:47:45 [INFO] train episode 16405: reward = -111.09, steps = 27 10:47:48 [INFO] train episode 16406: reward = -85.72, steps = 29 10:47:50 [INFO] train episode 16407: reward = -75.75, steps = 25 10:47:52 [INFO] train episode 16408: reward = -53.77, steps = 24 10:47:54 [INFO] train episode 16409: reward = -58.68, steps = 22 10:47:56 [INFO] train episode 16410: reward = -69.99, steps = 21 10:47:59 [INFO] train episode 16411: reward = -57.49, steps = 29 10:48:00 [INFO] train episode 16412: reward = -68.27, steps = 21 10:48:03 [INFO] train episode 16413: reward = -68.80, steps = 32 10:48:06 [INFO] train episode 16414: reward = -121.34, steps = 34 10:48:08 [INFO] train episode 16415: reward = -64.28, steps = 22 10:48:10 [INFO] train episode 16416: reward = -86.68, steps = 21 10:48:12 [INFO] train episode 16417: reward = -100.04, steps = 22 10:48:15 [INFO] train episode 16418: reward = -96.02, steps = 35 10:48:17 [INFO] train episode 16419: reward = -106.47, steps = 30 10:48:19 [INFO] train episode 16420: reward = -133.58, steps = 20 10:48:22 [INFO] train episode 16421: reward = -94.62, steps = 28 10:48:24 [INFO] train episode 16422: reward = -66.95, steps = 22 10:48:26 [INFO] train episode 16423: reward = -90.88, steps = 22 10:48:28 [INFO] train episode 16424: reward = -84.94, steps = 26 10:48:30 [INFO] train episode 16425: reward = -109.59, steps = 26 10:48:32 [INFO] train episode 16426: reward = -128.42, steps = 27 10:48:34 [INFO] train episode 16427: reward = -98.06, steps = 20 10:48:36 [INFO] train episode 16428: reward = -95.47, steps = 21 10:48:39 [INFO] train episode 16429: reward = -156.26, steps = 26 10:48:41 [INFO] train episode 16430: reward = -97.15, steps = 21 10:48:42 [INFO] train episode 16431: reward = -61.08, steps = 20 10:48:45 [INFO] train episode 16432: reward = -53.36, steps = 26 10:48:46 [INFO] train episode 16433: reward = -79.22, steps = 20 10:48:48 [INFO] train episode 16434: reward = -77.34, steps = 22 10:48:51 [INFO] train episode 16435: reward = -87.30, steps = 31 10:48:53 [INFO] train episode 16436: reward = -54.31, steps = 20 10:48:56 [INFO] train episode 16437: reward = -95.45, steps = 35 10:48:59 [INFO] train episode 16438: reward = -73.12, steps = 35 10:49:01 [INFO] train episode 16439: reward = -54.23, steps = 21 10:49:03 [INFO] train episode 16440: reward = -63.95, steps = 29 10:49:05 [INFO] train episode 16441: reward = -61.90, steps = 23 10:49:08 [INFO] train episode 16442: reward = -103.79, steps = 24 10:49:10 [INFO] train episode 16443: reward = -89.91, steps = 30 10:49:12 [INFO] train episode 16444: reward = -67.73, steps = 20 10:49:14 [INFO] train episode 16445: reward = -96.27, steps = 27 10:49:16 [INFO] train episode 16446: reward = -67.76, steps = 24 10:49:18 [INFO] train episode 16447: reward = -101.29, steps = 22 10:49:21 [INFO] train episode 16448: reward = -95.38, steps = 23 10:49:23 [INFO] train episode 16449: reward = -93.54, steps = 27 10:49:26 [INFO] train episode 16450: reward = -67.97, steps = 26 10:49:28 [INFO] train episode 16451: reward = -87.42, steps = 30 10:49:32 [INFO] train episode 16452: reward = -129.65, steps = 43 10:49:34 [INFO] train episode 16453: reward = -97.86, steps = 21 10:49:36 [INFO] train episode 16454: reward = -143.33, steps = 26 10:49:40 [INFO] train episode 16455: reward = -99.53, steps = 51 10:49:45 [INFO] train episode 16456: reward = -104.75, steps = 49 10:49:46 [INFO] train episode 16457: reward = -61.58, steps = 20 10:49:49 [INFO] train episode 16458: reward = -77.27, steps = 30 10:49:51 [INFO] train episode 16459: reward = -82.15, steps = 22 10:49:53 [INFO] train episode 16460: reward = -79.75, steps = 22 10:49:55 [INFO] train episode 16461: reward = -74.39, steps = 23 10:49:57 [INFO] train episode 16462: reward = -67.88, steps = 22 10:49:59 [INFO] train episode 16463: reward = -109.45, steps = 25 10:50:01 [INFO] train episode 16464: reward = -67.42, steps = 20 10:50:03 [INFO] train episode 16465: reward = -112.79, steps = 25 10:50:06 [INFO] train episode 16466: reward = -102.72, steps = 36 10:50:08 [INFO] train episode 16467: reward = -75.34, steps = 21 10:50:10 [INFO] train episode 16468: reward = -69.71, steps = 24 10:50:12 [INFO] train episode 16469: reward = -52.19, steps = 20 10:50:17 [INFO] train episode 16470: reward = -145.53, steps = 56 10:50:18 [INFO] train episode 16471: reward = -54.08, steps = 21 10:50:23 [INFO] train episode 16472: reward = -128.87, steps = 49 10:50:25 [INFO] train episode 16473: reward = -76.33, steps = 24 10:50:29 [INFO] train episode 16474: reward = -103.96, steps = 44 10:50:31 [INFO] train episode 16475: reward = -66.13, steps = 24 10:50:33 [INFO] train episode 16476: reward = -91.67, steps = 26 10:50:35 [INFO] train episode 16477: reward = -66.84, steps = 21 10:50:39 [INFO] train episode 16478: reward = -112.81, steps = 49 10:50:41 [INFO] train episode 16479: reward = -87.86, steps = 23 10:50:43 [INFO] train episode 16480: reward = -80.96, steps = 20 10:50:45 [INFO] train episode 16481: reward = -69.28, steps = 26 10:50:47 [INFO] train episode 16482: reward = -89.41, steps = 21 10:50:49 [INFO] train episode 16483: reward = -103.32, steps = 22 10:50:51 [INFO] train episode 16484: reward = -88.32, steps = 26 10:50:53 [INFO] train episode 16485: reward = -113.62, steps = 19 10:50:55 [INFO] train episode 16486: reward = -91.89, steps = 20 10:50:57 [INFO] train episode 16487: reward = -108.79, steps = 23 10:51:01 [INFO] train episode 16488: reward = -152.23, steps = 41 10:51:04 [INFO] train episode 16489: reward = -129.83, steps = 36 10:51:05 [INFO] train episode 16490: reward = -68.14, steps = 21 10:51:08 [INFO] train episode 16491: reward = -159.93, steps = 33 10:51:10 [INFO] train episode 16492: reward = -47.57, steps = 25 10:51:12 [INFO] train episode 16493: reward = -58.09, steps = 20 10:51:14 [INFO] train episode 16494: reward = -113.25, steps = 24 10:51:17 [INFO] train episode 16495: reward = -70.96, steps = 21 10:51:20 [INFO] train episode 16496: reward = -83.60, steps = 30 10:51:23 [INFO] train episode 16497: reward = -90.21, steps = 35 10:51:24 [INFO] train episode 16498: reward = -99.03, steps = 20 10:51:27 [INFO] train episode 16499: reward = -86.12, steps = 27 10:51:29 [INFO] train episode 16500: reward = -82.80, steps = 24 10:51:30 [INFO] train episode 16501: reward = -99.81, steps = 19 10:51:33 [INFO] train episode 16502: reward = -72.43, steps = 27 10:51:35 [INFO] train episode 16503: reward = -55.87, steps = 24 10:51:37 [INFO] train episode 16504: reward = -57.59, steps = 21 10:51:41 [INFO] train episode 16505: reward = -97.34, steps = 43 10:51:42 [INFO] train episode 16506: reward = -75.25, steps = 21 10:51:44 [INFO] train episode 16507: reward = -83.33, steps = 20 10:51:46 [INFO] train episode 16508: reward = -79.40, steps = 23 10:51:49 [INFO] train episode 16509: reward = -108.64, steps = 25 10:51:51 [INFO] train episode 16510: reward = -104.05, steps = 23 10:51:53 [INFO] train episode 16511: reward = -156.39, steps = 29 10:51:55 [INFO] train episode 16512: reward = -69.16, steps = 21 10:51:57 [INFO] train episode 16513: reward = -102.94, steps = 24 10:52:05 [INFO] train episode 16514: reward = -208.42, steps = 86 10:52:07 [INFO] train episode 16515: reward = -71.17, steps = 31 10:52:09 [INFO] train episode 16516: reward = -73.12, steps = 19 10:52:11 [INFO] train episode 16517: reward = -79.98, steps = 21 10:52:15 [INFO] train episode 16518: reward = -93.21, steps = 41 10:52:18 [INFO] train episode 16519: reward = -96.94, steps = 35 10:52:20 [INFO] train episode 16520: reward = -90.75, steps = 23 10:52:22 [INFO] train episode 16521: reward = -75.26, steps = 23 10:52:24 [INFO] train episode 16522: reward = -75.22, steps = 25 10:52:28 [INFO] train episode 16523: reward = -106.93, steps = 45 10:52:31 [INFO] train episode 16524: reward = -153.81, steps = 31 10:52:32 [INFO] train episode 16525: reward = -82.72, steps = 20 10:52:36 [INFO] train episode 16526: reward = -145.64, steps = 43 10:52:40 [INFO] train episode 16527: reward = -153.81, steps = 41 10:52:42 [INFO] train episode 16528: reward = -79.37, steps = 24 10:52:44 [INFO] train episode 16529: reward = -92.06, steps = 24 10:52:46 [INFO] train episode 16530: reward = -69.78, steps = 29 10:52:48 [INFO] train episode 16531: reward = -122.85, steps = 24 10:52:53 [INFO] train episode 16532: reward = -127.63, steps = 53 10:52:55 [INFO] train episode 16533: reward = -71.25, steps = 20 10:53:02 [INFO] train episode 16534: reward = -190.69, steps = 85 10:53:04 [INFO] train episode 16535: reward = -78.78, steps = 21 10:53:06 [INFO] train episode 16536: reward = -75.35, steps = 22 10:53:08 [INFO] train episode 16537: reward = -73.08, steps = 21 10:53:10 [INFO] train episode 16538: reward = -65.48, steps = 21 10:53:12 [INFO] train episode 16539: reward = -91.93, steps = 19 10:53:13 [INFO] train episode 16540: reward = -86.02, steps = 20 10:53:16 [INFO] train episode 16541: reward = -75.22, steps = 26 10:53:21 [INFO] train episode 16542: reward = -151.35, steps = 62 10:53:23 [INFO] train episode 16543: reward = -130.50, steps = 26 10:53:25 [INFO] train episode 16544: reward = -65.75, steps = 22 10:53:27 [INFO] train episode 16545: reward = -77.02, steps = 22 10:53:31 [INFO] train episode 16546: reward = -89.75, steps = 47 10:53:33 [INFO] train episode 16547: reward = -59.01, steps = 21 10:53:35 [INFO] train episode 16548: reward = -74.89, steps = 26 10:53:37 [INFO] train episode 16549: reward = -103.23, steps = 24 10:53:39 [INFO] train episode 16550: reward = -56.47, steps = 23 10:53:41 [INFO] train episode 16551: reward = -40.21, steps = 20 10:53:43 [INFO] train episode 16552: reward = -98.73, steps = 25 10:53:48 [INFO] train episode 16553: reward = -115.59, steps = 55 10:53:50 [INFO] train episode 16554: reward = -81.09, steps = 29 10:53:52 [INFO] train episode 16555: reward = -57.68, steps = 20 10:53:56 [INFO] train episode 16556: reward = -135.55, steps = 46 10:53:58 [INFO] train episode 16557: reward = -67.45, steps = 19 10:54:00 [INFO] train episode 16558: reward = -82.03, steps = 26 10:54:03 [INFO] train episode 16559: reward = -85.92, steps = 28 10:54:05 [INFO] train episode 16560: reward = -71.69, steps = 30 10:54:07 [INFO] train episode 16561: reward = -57.46, steps = 20 10:54:09 [INFO] train episode 16562: reward = -81.73, steps = 21 10:54:11 [INFO] train episode 16563: reward = -78.75, steps = 22 10:54:15 [INFO] train episode 16564: reward = -174.50, steps = 45 10:54:17 [INFO] train episode 16565: reward = -68.09, steps = 21 10:54:19 [INFO] train episode 16566: reward = -85.04, steps = 25 10:54:22 [INFO] train episode 16567: reward = -122.95, steps = 36 10:54:25 [INFO] train episode 16568: reward = -98.00, steps = 37 10:54:27 [INFO] train episode 16569: reward = -71.06, steps = 21 10:54:29 [INFO] train episode 16570: reward = -66.53, steps = 26 10:54:33 [INFO] train episode 16571: reward = -138.30, steps = 39 10:54:35 [INFO] train episode 16572: reward = -85.21, steps = 25 10:54:38 [INFO] train episode 16573: reward = -68.55, steps = 32 10:54:40 [INFO] train episode 16574: reward = -113.82, steps = 24 10:54:41 [INFO] train episode 16575: reward = -62.69, steps = 21 10:54:45 [INFO] train episode 16576: reward = -113.92, steps = 41 10:54:47 [INFO] train episode 16577: reward = -60.98, steps = 23 10:54:50 [INFO] train episode 16578: reward = -70.60, steps = 28 10:54:52 [INFO] train episode 16579: reward = -92.54, steps = 24 10:54:54 [INFO] train episode 16580: reward = -69.65, steps = 33 10:54:56 [INFO] train episode 16581: reward = -68.02, steps = 22 10:54:59 [INFO] train episode 16582: reward = -71.20, steps = 27 10:55:03 [INFO] train episode 16583: reward = -121.68, steps = 36 10:55:05 [INFO] train episode 16584: reward = -102.31, steps = 22 10:55:06 [INFO] train episode 16585: reward = -75.91, steps = 18 10:55:09 [INFO] train episode 16586: reward = -62.96, steps = 28 10:55:11 [INFO] train episode 16587: reward = -95.42, steps = 25 10:55:13 [INFO] train episode 16588: reward = -115.92, steps = 26 10:55:15 [INFO] train episode 16589: reward = -65.42, steps = 20 10:55:17 [INFO] train episode 16590: reward = -91.54, steps = 24 10:55:19 [INFO] train episode 16591: reward = -102.37, steps = 19 10:55:21 [INFO] train episode 16592: reward = -91.31, steps = 30 10:55:25 [INFO] train episode 16593: reward = -148.55, steps = 46 10:55:27 [INFO] train episode 16594: reward = -70.94, steps = 26 10:55:34 [INFO] train episode 16595: reward = -189.36, steps = 75 10:55:37 [INFO] train episode 16596: reward = -123.96, steps = 39 10:55:39 [INFO] train episode 16597: reward = -92.26, steps = 20 10:55:41 [INFO] train episode 16598: reward = -75.48, steps = 28 10:55:43 [INFO] train episode 16599: reward = -112.32, steps = 18 10:55:45 [INFO] train episode 16600: reward = -81.25, steps = 21 10:55:48 [INFO] train episode 16601: reward = -94.04, steps = 31 10:55:50 [INFO] train episode 16602: reward = -70.34, steps = 19 10:55:51 [INFO] train episode 16603: reward = -65.23, steps = 21 10:55:54 [INFO] train episode 16604: reward = -96.38, steps = 30 10:55:56 [INFO] train episode 16605: reward = -97.78, steps = 26 10:55:58 [INFO] train episode 16606: reward = -95.94, steps = 22 10:56:00 [INFO] train episode 16607: reward = -78.55, steps = 20 10:56:01 [INFO] train episode 16608: reward = -65.54, steps = 21 10:56:04 [INFO] train episode 16609: reward = -65.78, steps = 20 10:56:07 [INFO] train episode 16610: reward = -107.37, steps = 38 10:56:09 [INFO] train episode 16611: reward = -103.68, steps = 29 10:56:12 [INFO] train episode 16612: reward = -104.38, steps = 28 10:56:15 [INFO] train episode 16613: reward = -154.54, steps = 38 10:56:17 [INFO] train episode 16614: reward = -71.54, steps = 19 10:56:19 [INFO] train episode 16615: reward = -100.66, steps = 23 10:56:21 [INFO] train episode 16616: reward = -73.62, steps = 25 10:56:23 [INFO] train episode 16617: reward = -61.89, steps = 20 10:56:25 [INFO] train episode 16618: reward = -84.96, steps = 26 10:56:27 [INFO] train episode 16619: reward = -102.44, steps = 26 10:56:29 [INFO] train episode 16620: reward = -59.16, steps = 24 10:56:32 [INFO] train episode 16621: reward = -143.55, steps = 33 10:56:35 [INFO] train episode 16622: reward = -94.41, steps = 28 10:56:39 [INFO] train episode 16623: reward = -109.62, steps = 42 10:56:40 [INFO] train episode 16624: reward = -66.73, steps = 21 10:56:42 [INFO] train episode 16625: reward = -130.59, steps = 20 10:56:44 [INFO] train episode 16626: reward = -63.58, steps = 23 10:56:46 [INFO] train episode 16627: reward = -71.69, steps = 21 10:56:48 [INFO] train episode 16628: reward = -65.35, steps = 23 10:56:52 [INFO] train episode 16629: reward = -97.49, steps = 38 10:56:53 [INFO] train episode 16630: reward = -105.20, steps = 21 10:56:55 [INFO] train episode 16631: reward = -62.29, steps = 20 10:56:57 [INFO] train episode 16632: reward = -82.06, steps = 26 10:57:00 [INFO] train episode 16633: reward = -154.61, steps = 31 10:57:02 [INFO] train episode 16634: reward = -71.44, steps = 23 10:57:05 [INFO] train episode 16635: reward = -86.29, steps = 35 10:57:09 [INFO] train episode 16636: reward = -87.66, steps = 43 10:57:11 [INFO] train episode 16637: reward = -104.08, steps = 25 10:57:13 [INFO] train episode 16638: reward = -79.01, steps = 20 10:57:16 [INFO] train episode 16639: reward = -104.25, steps = 35 10:57:18 [INFO] train episode 16640: reward = -50.01, steps = 30 10:57:20 [INFO] train episode 16641: reward = -123.20, steps = 18 10:57:23 [INFO] train episode 16642: reward = -102.27, steps = 25 10:57:27 [INFO] train episode 16643: reward = -195.72, steps = 50 10:57:29 [INFO] train episode 16644: reward = -96.43, steps = 32 10:57:32 [INFO] train episode 16645: reward = -75.03, steps = 25 10:57:34 [INFO] train episode 16646: reward = -65.76, steps = 25 10:57:35 [INFO] train episode 16647: reward = -65.80, steps = 19 10:57:39 [INFO] train episode 16648: reward = -136.12, steps = 40 10:57:41 [INFO] train episode 16649: reward = -39.21, steps = 25 10:57:44 [INFO] train episode 16650: reward = -101.43, steps = 34 10:57:50 [INFO] train episode 16651: reward = -133.64, steps = 66 10:57:55 [INFO] train episode 16652: reward = -100.69, steps = 50 10:57:59 [INFO] train episode 16653: reward = -75.81, steps = 54 10:58:01 [INFO] train episode 16654: reward = -62.35, steps = 21 10:58:03 [INFO] train episode 16655: reward = -84.75, steps = 25 10:58:05 [INFO] train episode 16656: reward = -92.43, steps = 21 10:58:07 [INFO] train episode 16657: reward = -155.50, steps = 24 10:58:09 [INFO] train episode 16658: reward = -77.71, steps = 22 10:58:12 [INFO] train episode 16659: reward = -47.36, steps = 30 10:58:14 [INFO] train episode 16660: reward = -105.67, steps = 23 10:58:16 [INFO] train episode 16661: reward = -93.35, steps = 23 10:58:18 [INFO] train episode 16662: reward = -83.64, steps = 25 10:58:20 [INFO] train episode 16663: reward = -104.33, steps = 24 10:58:22 [INFO] train episode 16664: reward = -97.45, steps = 22 10:58:24 [INFO] train episode 16665: reward = -84.63, steps = 23 10:58:28 [INFO] train episode 16666: reward = -116.72, steps = 40 10:58:30 [INFO] train episode 16667: reward = -103.30, steps = 24 10:58:32 [INFO] train episode 16668: reward = -63.05, steps = 20 10:58:34 [INFO] train episode 16669: reward = -80.40, steps = 24 10:58:36 [INFO] train episode 16670: reward = -88.43, steps = 27 10:58:38 [INFO] train episode 16671: reward = -65.99, steps = 26 10:58:42 [INFO] train episode 16672: reward = -118.92, steps = 42 10:58:44 [INFO] train episode 16673: reward = -99.85, steps = 22 10:58:46 [INFO] train episode 16674: reward = -87.18, steps = 19 10:58:48 [INFO] train episode 16675: reward = -77.53, steps = 21 10:58:52 [INFO] train episode 16676: reward = -127.63, steps = 56 10:58:55 [INFO] train episode 16677: reward = -94.14, steps = 33 10:58:57 [INFO] train episode 16678: reward = -76.76, steps = 20 10:58:59 [INFO] train episode 16679: reward = -79.54, steps = 22 10:59:01 [INFO] train episode 16680: reward = -96.71, steps = 22 10:59:03 [INFO] train episode 16681: reward = -110.11, steps = 27 10:59:06 [INFO] train episode 16682: reward = -136.61, steps = 32 10:59:08 [INFO] train episode 16683: reward = -53.27, steps = 28 10:59:11 [INFO] train episode 16684: reward = -79.32, steps = 26 10:59:16 [INFO] train episode 16685: reward = -129.06, steps = 60 10:59:18 [INFO] train episode 16686: reward = -114.24, steps = 26 10:59:21 [INFO] train episode 16687: reward = -122.25, steps = 26 10:59:22 [INFO] train episode 16688: reward = -96.17, steps = 19 10:59:24 [INFO] train episode 16689: reward = -69.07, steps = 23 10:59:27 [INFO] train episode 16690: reward = -114.08, steps = 29 10:59:29 [INFO] train episode 16691: reward = -101.90, steps = 23 10:59:31 [INFO] train episode 16692: reward = -98.07, steps = 22 10:59:36 [INFO] train episode 16693: reward = -163.57, steps = 68 10:59:39 [INFO] train episode 16694: reward = -77.99, steps = 30 10:59:41 [INFO] train episode 16695: reward = -55.65, steps = 19 10:59:43 [INFO] train episode 16696: reward = -99.15, steps = 25 10:59:45 [INFO] train episode 16697: reward = -87.40, steps = 18 10:59:47 [INFO] train episode 16698: reward = -73.29, steps = 21 10:59:48 [INFO] train episode 16699: reward = -77.57, steps = 19 10:59:50 [INFO] train episode 16700: reward = -64.55, steps = 21 10:59:52 [INFO] train episode 16701: reward = -82.90, steps = 20 10:59:54 [INFO] train episode 16702: reward = -111.52, steps = 30 10:59:57 [INFO] train episode 16703: reward = -61.14, steps = 27 11:00:03 [INFO] train episode 16704: reward = -207.51, steps = 67 11:00:05 [INFO] train episode 16705: reward = -89.19, steps = 33 11:00:07 [INFO] train episode 16706: reward = -108.27, steps = 24 11:00:09 [INFO] train episode 16707: reward = -91.76, steps = 20 11:00:11 [INFO] train episode 16708: reward = -75.97, steps = 20 11:00:14 [INFO] train episode 16709: reward = -123.55, steps = 40 11:00:18 [INFO] train episode 16710: reward = -97.05, steps = 45 11:00:20 [INFO] train episode 16711: reward = -93.61, steps = 19 11:00:22 [INFO] train episode 16712: reward = -55.12, steps = 21 11:00:24 [INFO] train episode 16713: reward = -75.61, steps = 30 11:00:27 [INFO] train episode 16714: reward = -100.39, steps = 30 11:00:29 [INFO] train episode 16715: reward = -81.07, steps = 22 11:00:31 [INFO] train episode 16716: reward = -67.62, steps = 22 11:00:33 [INFO] train episode 16717: reward = -77.59, steps = 19 11:00:35 [INFO] train episode 16718: reward = -106.75, steps = 33 11:00:38 [INFO] train episode 16719: reward = -100.57, steps = 24 11:00:40 [INFO] train episode 16720: reward = -94.00, steps = 29 11:00:42 [INFO] train episode 16721: reward = -97.26, steps = 23 11:00:44 [INFO] train episode 16722: reward = -70.97, steps = 19 11:00:50 [INFO] train episode 16723: reward = -136.02, steps = 60 11:00:51 [INFO] train episode 16724: reward = -59.73, steps = 20 11:00:54 [INFO] train episode 16725: reward = -91.20, steps = 26 11:00:56 [INFO] train episode 16726: reward = -89.43, steps = 22 11:00:59 [INFO] train episode 16727: reward = -64.21, steps = 40 11:01:01 [INFO] train episode 16728: reward = -89.69, steps = 26 11:01:05 [INFO] train episode 16729: reward = -88.69, steps = 36 11:01:07 [INFO] train episode 16730: reward = -54.81, steps = 28 11:01:10 [INFO] train episode 16731: reward = -128.59, steps = 35 11:01:16 [INFO] train episode 16732: reward = -268.05, steps = 73 11:01:20 [INFO] train episode 16733: reward = -126.50, steps = 44 11:01:22 [INFO] train episode 16734: reward = -85.59, steps = 27 11:01:24 [INFO] train episode 16735: reward = -58.32, steps = 21 11:01:27 [INFO] train episode 16736: reward = -68.13, steps = 31 11:01:29 [INFO] train episode 16737: reward = -75.05, steps = 31 11:01:31 [INFO] train episode 16738: reward = -89.35, steps = 21 11:01:33 [INFO] train episode 16739: reward = -78.56, steps = 20 11:01:37 [INFO] train episode 16740: reward = -173.35, steps = 47 11:01:39 [INFO] train episode 16741: reward = -69.02, steps = 21 11:01:42 [INFO] train episode 16742: reward = -81.06, steps = 30 11:01:44 [INFO] train episode 16743: reward = -94.69, steps = 24 11:01:46 [INFO] train episode 16744: reward = -101.00, steps = 26 11:01:49 [INFO] train episode 16745: reward = -62.60, steps = 33 11:01:51 [INFO] train episode 16746: reward = -88.20, steps = 23 11:01:53 [INFO] train episode 16747: reward = -105.30, steps = 27 11:01:55 [INFO] train episode 16748: reward = -69.71, steps = 22 11:01:58 [INFO] train episode 16749: reward = -85.28, steps = 30 11:02:00 [INFO] train episode 16750: reward = -95.61, steps = 25 11:02:02 [INFO] train episode 16751: reward = -95.46, steps = 22 11:02:04 [INFO] train episode 16752: reward = -80.52, steps = 23 11:02:06 [INFO] train episode 16753: reward = -72.73, steps = 20 11:02:07 [INFO] train episode 16754: reward = -84.03, steps = 20 11:02:10 [INFO] train episode 16755: reward = -66.02, steps = 23 11:02:11 [INFO] train episode 16756: reward = -96.48, steps = 22 11:02:15 [INFO] train episode 16757: reward = -127.54, steps = 40 11:02:17 [INFO] train episode 16758: reward = -65.78, steps = 25 11:02:20 [INFO] train episode 16759: reward = -122.02, steps = 40 11:02:22 [INFO] train episode 16760: reward = -69.14, steps = 22 11:02:26 [INFO] train episode 16761: reward = -67.73, steps = 34 11:02:28 [INFO] train episode 16762: reward = -67.36, steps = 22 11:02:30 [INFO] train episode 16763: reward = -87.10, steps = 24 11:02:33 [INFO] train episode 16764: reward = -92.28, steps = 38 11:02:36 [INFO] train episode 16765: reward = -111.09, steps = 35 11:02:40 [INFO] train episode 16766: reward = -92.93, steps = 37 11:02:42 [INFO] train episode 16767: reward = -66.65, steps = 29 11:02:44 [INFO] train episode 16768: reward = -76.46, steps = 21 11:02:47 [INFO] train episode 16769: reward = -65.69, steps = 31 11:02:49 [INFO] train episode 16770: reward = -57.34, steps = 25 11:02:52 [INFO] train episode 16771: reward = -72.51, steps = 37 11:02:55 [INFO] train episode 16772: reward = -90.32, steps = 28 11:02:58 [INFO] train episode 16773: reward = -122.95, steps = 34 11:03:00 [INFO] train episode 16774: reward = -76.74, steps = 19 11:03:02 [INFO] train episode 16775: reward = -84.71, steps = 25 11:03:04 [INFO] train episode 16776: reward = -85.63, steps = 23 11:03:06 [INFO] train episode 16777: reward = -99.92, steps = 29 11:03:08 [INFO] train episode 16778: reward = -81.42, steps = 19 11:03:11 [INFO] train episode 16779: reward = -101.66, steps = 37 11:03:13 [INFO] train episode 16780: reward = -84.30, steps = 22 11:03:15 [INFO] train episode 16781: reward = -51.96, steps = 20 11:03:17 [INFO] train episode 16782: reward = -54.23, steps = 24 11:03:20 [INFO] train episode 16783: reward = -78.50, steps = 28 11:03:22 [INFO] train episode 16784: reward = -90.32, steps = 27 11:03:24 [INFO] train episode 16785: reward = -84.46, steps = 22 11:03:26 [INFO] train episode 16786: reward = -105.88, steps = 26 11:03:29 [INFO] train episode 16787: reward = -101.66, steps = 33 11:03:31 [INFO] train episode 16788: reward = -59.16, steps = 21 11:03:33 [INFO] train episode 16789: reward = -93.30, steps = 20 11:03:36 [INFO] train episode 16790: reward = -71.71, steps = 25 11:03:38 [INFO] train episode 16791: reward = -106.23, steps = 27 11:03:41 [INFO] train episode 16792: reward = -114.89, steps = 31 11:03:43 [INFO] train episode 16793: reward = -113.59, steps = 30 11:03:46 [INFO] train episode 16794: reward = -102.05, steps = 33 11:03:48 [INFO] train episode 16795: reward = -61.87, steps = 19 11:03:50 [INFO] train episode 16796: reward = -81.19, steps = 27 11:03:53 [INFO] train episode 16797: reward = -81.06, steps = 28 11:03:57 [INFO] train episode 16798: reward = -62.54, steps = 47 11:04:00 [INFO] train episode 16799: reward = -81.43, steps = 30 11:04:01 [INFO] train episode 16800: reward = -67.29, steps = 20 11:04:04 [INFO] train episode 16801: reward = -68.85, steps = 30 11:04:06 [INFO] train episode 16802: reward = -70.05, steps = 23 11:04:08 [INFO] train episode 16803: reward = -125.58, steps = 27 11:04:13 [INFO] train episode 16804: reward = -121.48, steps = 54 11:04:16 [INFO] train episode 16805: reward = -68.53, steps = 30 11:04:18 [INFO] train episode 16806: reward = -77.10, steps = 29 11:04:20 [INFO] train episode 16807: reward = -91.74, steps = 19 11:04:22 [INFO] train episode 16808: reward = -50.69, steps = 20 11:04:24 [INFO] train episode 16809: reward = -94.23, steps = 31 11:04:26 [INFO] train episode 16810: reward = -96.24, steps = 27 11:04:32 [INFO] train episode 16811: reward = -100.95, steps = 57 11:04:33 [INFO] train episode 16812: reward = -69.57, steps = 22 11:04:36 [INFO] train episode 16813: reward = -68.90, steps = 27 11:04:40 [INFO] train episode 16814: reward = -90.05, steps = 47 11:04:42 [INFO] train episode 16815: reward = -64.79, steps = 22 11:04:43 [INFO] train episode 16816: reward = -52.48, steps = 19 11:04:47 [INFO] train episode 16817: reward = -155.40, steps = 44 11:04:51 [INFO] train episode 16818: reward = -94.24, steps = 44 11:04:53 [INFO] train episode 16819: reward = -98.13, steps = 24 11:04:55 [INFO] train episode 16820: reward = -85.78, steps = 27 11:04:58 [INFO] train episode 16821: reward = -109.95, steps = 36 11:05:01 [INFO] train episode 16822: reward = -95.74, steps = 25 11:05:03 [INFO] train episode 16823: reward = -105.03, steps = 30 11:05:05 [INFO] train episode 16824: reward = -54.92, steps = 20 11:05:07 [INFO] train episode 16825: reward = -75.14, steps = 27 11:05:10 [INFO] train episode 16826: reward = -101.41, steps = 26 11:05:12 [INFO] train episode 16827: reward = -65.40, steps = 31 11:05:14 [INFO] train episode 16828: reward = -83.71, steps = 25 11:05:17 [INFO] train episode 16829: reward = -127.64, steps = 35 11:05:20 [INFO] train episode 16830: reward = -90.50, steps = 21 11:05:22 [INFO] train episode 16831: reward = -63.16, steps = 23 11:05:23 [INFO] train episode 16832: reward = -79.58, steps = 19 11:05:26 [INFO] train episode 16833: reward = -119.16, steps = 33 11:05:28 [INFO] train episode 16834: reward = -81.65, steps = 19 11:05:30 [INFO] train episode 16835: reward = -102.51, steps = 25 11:05:32 [INFO] train episode 16836: reward = -93.22, steps = 21 11:05:36 [INFO] train episode 16837: reward = -125.10, steps = 48 11:05:38 [INFO] train episode 16838: reward = -91.59, steps = 27 11:05:41 [INFO] train episode 16839: reward = -79.67, steps = 35 11:05:44 [INFO] train episode 16840: reward = -65.52, steps = 29 11:05:46 [INFO] train episode 16841: reward = -44.52, steps = 25 11:05:48 [INFO] train episode 16842: reward = -70.98, steps = 21 11:05:51 [INFO] train episode 16843: reward = -76.05, steps = 37 11:05:54 [INFO] train episode 16844: reward = -76.63, steps = 27 11:05:55 [INFO] train episode 16845: reward = -58.70, steps = 21 11:06:00 [INFO] train episode 16846: reward = -92.45, steps = 53 11:06:03 [INFO] train episode 16847: reward = -100.95, steps = 35 11:06:05 [INFO] train episode 16848: reward = -103.60, steps = 26 11:06:12 [INFO] train episode 16849: reward = -153.33, steps = 77 11:06:14 [INFO] train episode 16850: reward = -115.48, steps = 31 11:06:16 [INFO] train episode 16851: reward = -77.42, steps = 24 11:06:20 [INFO] train episode 16852: reward = -99.58, steps = 47 11:06:25 [INFO] train episode 16853: reward = -60.31, steps = 44 11:06:27 [INFO] train episode 16854: reward = -104.11, steps = 20 11:06:29 [INFO] train episode 16855: reward = -92.03, steps = 20 11:06:31 [INFO] train episode 16856: reward = -96.92, steps = 31 11:06:34 [INFO] train episode 16857: reward = -104.59, steps = 28 11:06:39 [INFO] train episode 16858: reward = -86.51, steps = 22 11:06:44 [INFO] train episode 16859: reward = -118.18, steps = 24 11:06:52 [INFO] train episode 16860: reward = -82.07, steps = 56 11:06:57 [INFO] train episode 16861: reward = -104.63, steps = 33 11:07:01 [INFO] train episode 16862: reward = -65.97, steps = 23 11:07:04 [INFO] train episode 16863: reward = -75.63, steps = 23 11:07:09 [INFO] train episode 16864: reward = -78.30, steps = 32 11:07:15 [INFO] train episode 16865: reward = -91.11, steps = 37 11:07:18 [INFO] train episode 16866: reward = -110.79, steps = 20 11:07:21 [INFO] train episode 16867: reward = -91.86, steps = 21 11:07:28 [INFO] train episode 16868: reward = -110.66, steps = 41 11:07:36 [INFO] train episode 16869: reward = -147.51, steps = 52 11:07:41 [INFO] train episode 16870: reward = -86.07, steps = 48 11:07:44 [INFO] train episode 16871: reward = -85.69, steps = 27 11:07:47 [INFO] train episode 16872: reward = -64.48, steps = 22 11:07:50 [INFO] train episode 16873: reward = -67.31, steps = 29 11:07:53 [INFO] train episode 16874: reward = -102.58, steps = 40 11:07:55 [INFO] train episode 16875: reward = -94.24, steps = 22 11:07:56 [INFO] train episode 16876: reward = -81.01, steps = 19 11:08:00 [INFO] train episode 16877: reward = -78.62, steps = 33 11:08:02 [INFO] train episode 16878: reward = -98.03, steps = 22 11:08:05 [INFO] train episode 16879: reward = -97.12, steps = 24 11:08:07 [INFO] train episode 16880: reward = -60.43, steps = 20 11:08:13 [INFO] train episode 16881: reward = -148.89, steps = 54 11:08:16 [INFO] train episode 16882: reward = -97.61, steps = 30 11:08:18 [INFO] train episode 16883: reward = -78.17, steps = 23 11:08:20 [INFO] train episode 16884: reward = -91.83, steps = 21 11:08:22 [INFO] train episode 16885: reward = -66.14, steps = 24 11:08:26 [INFO] train episode 16886: reward = -90.89, steps = 36 11:08:28 [INFO] train episode 16887: reward = -101.89, steps = 21 11:08:30 [INFO] train episode 16888: reward = -96.85, steps = 23 11:08:32 [INFO] train episode 16889: reward = -122.71, steps = 23 11:08:35 [INFO] train episode 16890: reward = -91.27, steps = 25 11:08:38 [INFO] train episode 16891: reward = -80.70, steps = 25 11:08:40 [INFO] train episode 16892: reward = -98.22, steps = 23 11:08:42 [INFO] train episode 16893: reward = -81.23, steps = 23 11:08:45 [INFO] train episode 16894: reward = -60.43, steps = 34 11:08:48 [INFO] train episode 16895: reward = -73.62, steps = 35 11:08:51 [INFO] train episode 16896: reward = -80.62, steps = 29 11:08:54 [INFO] train episode 16897: reward = -66.34, steps = 37 11:08:59 [INFO] train episode 16898: reward = -98.90, steps = 37 11:09:03 [INFO] train episode 16899: reward = -86.10, steps = 38 11:09:06 [INFO] train episode 16900: reward = -66.95, steps = 21 11:09:09 [INFO] train episode 16901: reward = -56.96, steps = 22 11:09:13 [INFO] train episode 16902: reward = -94.67, steps = 33 11:09:16 [INFO] train episode 16903: reward = -95.00, steps = 21 11:09:19 [INFO] train episode 16904: reward = -62.89, steps = 31 11:09:22 [INFO] train episode 16905: reward = -78.80, steps = 20 11:09:26 [INFO] train episode 16906: reward = -119.16, steps = 43 11:09:29 [INFO] train episode 16907: reward = -66.71, steps = 23 11:09:32 [INFO] train episode 16908: reward = -65.69, steps = 22 11:09:36 [INFO] train episode 16909: reward = -137.62, steps = 31 11:09:39 [INFO] train episode 16910: reward = -80.47, steps = 28 11:09:43 [INFO] train episode 16911: reward = -76.36, steps = 29 11:09:46 [INFO] train episode 16912: reward = -129.83, steps = 34 11:09:49 [INFO] train episode 16913: reward = -75.10, steps = 22 11:09:51 [INFO] train episode 16914: reward = -57.06, steps = 22 11:09:56 [INFO] train episode 16915: reward = -97.60, steps = 44 11:10:00 [INFO] train episode 16916: reward = -67.90, steps = 31 11:10:04 [INFO] train episode 16917: reward = -93.60, steps = 33 11:10:07 [INFO] train episode 16918: reward = -122.16, steps = 30 11:10:10 [INFO] train episode 16919: reward = -113.46, steps = 25 11:10:13 [INFO] train episode 16920: reward = -73.84, steps = 22 11:10:16 [INFO] train episode 16921: reward = -71.83, steps = 19 11:10:19 [INFO] train episode 16922: reward = -78.49, steps = 25 11:10:22 [INFO] train episode 16923: reward = -63.03, steps = 23 11:10:27 [INFO] train episode 16924: reward = -60.41, steps = 44 11:10:29 [INFO] train episode 16925: reward = -60.57, steps = 23 11:10:31 [INFO] train episode 16926: reward = -75.06, steps = 22 11:10:39 [INFO] train episode 16927: reward = -209.89, steps = 63 11:10:43 [INFO] train episode 16928: reward = -85.65, steps = 26 11:10:45 [INFO] train episode 16929: reward = -82.05, steps = 22 11:10:51 [INFO] train episode 16930: reward = -122.95, steps = 42 11:10:54 [INFO] train episode 16931: reward = -90.03, steps = 30 11:10:59 [INFO] train episode 16932: reward = -86.90, steps = 39 11:11:02 [INFO] train episode 16933: reward = -79.36, steps = 25 11:11:10 [INFO] train episode 16934: reward = -125.84, steps = 66 11:11:15 [INFO] train episode 16935: reward = -88.57, steps = 46 11:11:16 [INFO] train episode 16936: reward = -94.48, steps = 18 11:11:22 [INFO] train episode 16937: reward = -145.12, steps = 57 11:11:28 [INFO] train episode 16938: reward = -145.62, steps = 63 11:11:33 [INFO] train episode 16939: reward = -211.27, steps = 55 11:11:35 [INFO] train episode 16940: reward = -84.33, steps = 26 11:11:40 [INFO] train episode 16941: reward = -109.67, steps = 46 11:11:42 [INFO] train episode 16942: reward = -94.52, steps = 26 11:11:44 [INFO] train episode 16943: reward = -96.26, steps = 23 11:11:46 [INFO] train episode 16944: reward = -91.50, steps = 29 11:11:50 [INFO] train episode 16945: reward = -91.35, steps = 44 11:11:53 [INFO] train episode 16946: reward = -81.03, steps = 28 11:11:55 [INFO] train episode 16947: reward = -61.28, steps = 28 11:11:57 [INFO] train episode 16948: reward = -96.33, steps = 20 11:12:00 [INFO] train episode 16949: reward = -79.49, steps = 26 11:12:02 [INFO] train episode 16950: reward = -73.47, steps = 23 11:12:07 [INFO] train episode 16951: reward = -78.74, steps = 58 11:12:08 [INFO] train episode 16952: reward = -59.97, steps = 20 11:12:12 [INFO] train episode 16953: reward = -121.26, steps = 40 11:12:14 [INFO] train episode 16954: reward = -83.16, steps = 24 11:12:17 [INFO] train episode 16955: reward = -80.44, steps = 33 11:12:20 [INFO] train episode 16956: reward = -108.19, steps = 29 11:12:22 [INFO] train episode 16957: reward = -60.68, steps = 20 11:12:27 [INFO] train episode 16958: reward = -94.46, steps = 53 11:12:30 [INFO] train episode 16959: reward = -137.70, steps = 45 11:12:33 [INFO] train episode 16960: reward = -93.46, steps = 28 11:12:36 [INFO] train episode 16961: reward = -87.24, steps = 31 11:12:37 [INFO] train episode 16962: reward = -88.88, steps = 18 11:12:42 [INFO] train episode 16963: reward = -58.08, steps = 51 11:12:46 [INFO] train episode 16964: reward = -105.67, steps = 39 11:12:47 [INFO] train episode 16965: reward = -68.69, steps = 19 11:12:52 [INFO] train episode 16966: reward = -110.29, steps = 51 11:12:54 [INFO] train episode 16967: reward = -88.94, steps = 21 11:12:57 [INFO] train episode 16968: reward = -158.51, steps = 45 11:13:01 [INFO] train episode 16969: reward = -99.00, steps = 36 11:13:03 [INFO] train episode 16970: reward = -81.37, steps = 28 11:13:06 [INFO] train episode 16971: reward = -83.24, steps = 31 11:13:09 [INFO] train episode 16972: reward = -110.19, steps = 35 11:13:11 [INFO] train episode 16973: reward = -105.20, steps = 23 11:13:13 [INFO] train episode 16974: reward = -90.90, steps = 21 11:13:17 [INFO] train episode 16975: reward = -92.89, steps = 47 11:13:19 [INFO] train episode 16976: reward = -84.37, steps = 21 11:13:21 [INFO] train episode 16977: reward = -90.43, steps = 21 11:13:23 [INFO] train episode 16978: reward = -84.98, steps = 22 11:13:27 [INFO] train episode 16979: reward = -68.82, steps = 37 11:13:29 [INFO] train episode 16980: reward = -77.65, steps = 20 11:13:31 [INFO] train episode 16981: reward = -67.78, steps = 20 11:13:34 [INFO] train episode 16982: reward = -120.43, steps = 37 11:13:36 [INFO] train episode 16983: reward = -69.07, steps = 22 11:13:40 [INFO] train episode 16984: reward = -102.17, steps = 44 11:13:42 [INFO] train episode 16985: reward = -85.27, steps = 22 11:13:44 [INFO] train episode 16986: reward = -77.58, steps = 21 11:13:46 [INFO] train episode 16987: reward = -79.96, steps = 22 11:13:48 [INFO] train episode 16988: reward = -77.36, steps = 22 11:13:50 [INFO] train episode 16989: reward = -87.65, steps = 19 11:13:53 [INFO] train episode 16990: reward = -107.90, steps = 34 11:13:54 [INFO] train episode 16991: reward = -64.18, steps = 20 11:13:57 [INFO] train episode 16992: reward = -80.34, steps = 32 11:13:59 [INFO] train episode 16993: reward = -67.51, steps = 20 11:14:03 [INFO] train episode 16994: reward = -173.01, steps = 45 11:14:09 [INFO] train episode 16995: reward = -141.65, steps = 68 11:14:14 [INFO] train episode 16996: reward = -137.66, steps = 58 11:14:18 [INFO] train episode 16997: reward = -122.99, steps = 42 11:14:21 [INFO] train episode 16998: reward = -111.32, steps = 39 11:14:24 [INFO] train episode 16999: reward = -93.30, steps = 32 11:14:27 [INFO] train episode 17000: reward = -77.01, steps = 28 11:14:29 [INFO] train episode 17001: reward = -94.58, steps = 24 11:14:30 [INFO] train episode 17002: reward = -65.23, steps = 19 11:14:33 [INFO] train episode 17003: reward = -58.92, steps = 27 11:14:35 [INFO] train episode 17004: reward = -50.15, steps = 22 11:14:37 [INFO] train episode 17005: reward = -109.05, steps = 18 11:14:39 [INFO] train episode 17006: reward = -65.45, steps = 23 11:14:41 [INFO] train episode 17007: reward = -76.91, steps = 20 11:14:42 [INFO] train episode 17008: reward = -67.17, steps = 20 11:14:44 [INFO] train episode 17009: reward = -116.18, steps = 23 11:14:49 [INFO] train episode 17010: reward = -94.97, steps = 52 11:14:51 [INFO] train episode 17011: reward = -70.73, steps = 24 11:14:56 [INFO] train episode 17012: reward = -164.92, steps = 59 11:15:00 [INFO] train episode 17013: reward = -108.10, steps = 39 11:15:02 [INFO] train episode 17014: reward = -90.70, steps = 21 11:15:07 [INFO] train episode 17015: reward = -87.49, steps = 66 11:15:11 [INFO] train episode 17016: reward = -74.84, steps = 38 11:15:13 [INFO] train episode 17017: reward = -105.63, steps = 27 11:15:15 [INFO] train episode 17018: reward = -94.89, steps = 22 11:15:18 [INFO] train episode 17019: reward = -106.65, steps = 26 11:15:21 [INFO] train episode 17020: reward = -105.35, steps = 43 11:15:23 [INFO] train episode 17021: reward = -87.42, steps = 24 11:15:26 [INFO] train episode 17022: reward = -63.56, steps = 23 11:15:28 [INFO] train episode 17023: reward = -76.43, steps = 19 11:15:32 [INFO] train episode 17024: reward = -125.02, steps = 45 11:15:35 [INFO] train episode 17025: reward = -116.30, steps = 43 11:15:41 [INFO] train episode 17026: reward = -125.70, steps = 59 11:15:44 [INFO] train episode 17027: reward = -75.55, steps = 30 11:15:49 [INFO] train episode 17028: reward = -122.70, steps = 58 11:15:52 [INFO] train episode 17029: reward = -89.57, steps = 43 11:15:55 [INFO] train episode 17030: reward = -89.87, steps = 29 11:15:59 [INFO] train episode 17031: reward = -90.73, steps = 39 11:16:03 [INFO] train episode 17032: reward = -108.49, steps = 50 11:16:05 [INFO] train episode 17033: reward = -102.38, steps = 25 11:16:07 [INFO] train episode 17034: reward = -115.08, steps = 21 11:16:09 [INFO] train episode 17035: reward = -85.05, steps = 29 11:16:13 [INFO] train episode 17036: reward = -59.49, steps = 37 11:16:16 [INFO] train episode 17037: reward = -69.87, steps = 34 11:16:20 [INFO] train episode 17038: reward = -127.89, steps = 45 11:16:25 [INFO] train episode 17039: reward = -139.75, steps = 55 11:16:33 [INFO] train episode 17040: reward = -205.98, steps = 81 11:16:36 [INFO] train episode 17041: reward = -137.05, steps = 46 11:16:40 [INFO] train episode 17042: reward = -125.33, steps = 46 11:16:44 [INFO] train episode 17043: reward = -90.30, steps = 43 11:16:47 [INFO] train episode 17044: reward = -74.78, steps = 24 11:16:51 [INFO] train episode 17045: reward = -153.80, steps = 49 11:16:53 [INFO] train episode 17046: reward = -70.81, steps = 27 11:16:56 [INFO] train episode 17047: reward = -89.36, steps = 34 11:16:58 [INFO] train episode 17048: reward = -91.24, steps = 18 11:17:01 [INFO] train episode 17049: reward = -75.17, steps = 34 11:17:05 [INFO] train episode 17050: reward = -140.37, steps = 41 11:17:09 [INFO] train episode 17051: reward = -126.44, steps = 48 11:17:11 [INFO] train episode 17052: reward = -103.20, steps = 26 11:17:13 [INFO] train episode 17053: reward = -73.20, steps = 20 11:17:16 [INFO] train episode 17054: reward = -110.36, steps = 35 11:17:20 [INFO] train episode 17055: reward = -94.44, steps = 45 11:17:23 [INFO] train episode 17056: reward = -38.95, steps = 27 11:17:26 [INFO] train episode 17057: reward = -79.79, steps = 39 11:17:30 [INFO] train episode 17058: reward = -123.03, steps = 43 11:17:33 [INFO] train episode 17059: reward = -120.90, steps = 36 11:17:36 [INFO] train episode 17060: reward = -70.21, steps = 23 11:17:40 [INFO] train episode 17061: reward = -108.07, steps = 45 11:17:43 [INFO] train episode 17062: reward = -93.42, steps = 41 11:17:46 [INFO] train episode 17063: reward = -77.20, steps = 35 11:17:48 [INFO] train episode 17064: reward = -89.21, steps = 22 11:17:55 [INFO] train episode 17065: reward = -158.10, steps = 76 11:17:57 [INFO] train episode 17066: reward = -79.70, steps = 24 11:17:59 [INFO] train episode 17067: reward = -96.33, steps = 21 11:18:03 [INFO] train episode 17068: reward = -113.17, steps = 45 11:18:05 [INFO] train episode 17069: reward = -73.90, steps = 21 11:18:07 [INFO] train episode 17070: reward = -90.27, steps = 19 11:18:09 [INFO] train episode 17071: reward = -87.93, steps = 28 11:18:12 [INFO] train episode 17072: reward = -99.45, steps = 30 11:18:14 [INFO] train episode 17073: reward = -80.54, steps = 21 11:18:17 [INFO] train episode 17074: reward = -116.11, steps = 37 11:18:19 [INFO] train episode 17075: reward = -87.99, steps = 28 11:18:21 [INFO] train episode 17076: reward = -64.73, steps = 22 11:18:24 [INFO] train episode 17077: reward = -62.24, steps = 25 11:18:29 [INFO] train episode 17078: reward = -102.04, steps = 61 11:18:31 [INFO] train episode 17079: reward = -81.08, steps = 28 11:18:34 [INFO] train episode 17080: reward = -98.32, steps = 35 11:18:38 [INFO] train episode 17081: reward = -103.45, steps = 37 11:18:40 [INFO] train episode 17082: reward = -77.53, steps = 21 11:18:42 [INFO] train episode 17083: reward = -93.03, steps = 28 11:18:46 [INFO] train episode 17084: reward = -127.30, steps = 46 11:18:48 [INFO] train episode 17085: reward = -57.29, steps = 22 11:18:51 [INFO] train episode 17086: reward = -78.59, steps = 26 11:18:53 [INFO] train episode 17087: reward = -81.93, steps = 32 11:18:56 [INFO] train episode 17088: reward = -80.23, steps = 22 11:18:58 [INFO] train episode 17089: reward = -96.84, steps = 27 11:19:00 [INFO] train episode 17090: reward = -76.26, steps = 24 11:19:04 [INFO] train episode 17091: reward = -89.04, steps = 38 11:19:06 [INFO] train episode 17092: reward = -69.84, steps = 32 11:19:09 [INFO] train episode 17093: reward = -62.06, steps = 29 11:19:12 [INFO] train episode 17094: reward = -112.56, steps = 33 11:19:17 [INFO] train episode 17095: reward = -152.97, steps = 52 11:19:19 [INFO] train episode 17096: reward = -69.53, steps = 23 11:19:21 [INFO] train episode 17097: reward = -98.99, steps = 21 11:19:24 [INFO] train episode 17098: reward = -91.57, steps = 26 11:19:29 [INFO] train episode 17099: reward = -120.40, steps = 60 11:19:31 [INFO] train episode 17100: reward = -64.34, steps = 19 11:19:33 [INFO] train episode 17101: reward = -92.86, steps = 25 11:19:35 [INFO] train episode 17102: reward = -52.88, steps = 25 11:19:38 [INFO] train episode 17103: reward = -96.78, steps = 27 11:19:40 [INFO] train episode 17104: reward = -93.58, steps = 31 11:19:42 [INFO] train episode 17105: reward = -79.53, steps = 23 11:19:45 [INFO] train episode 17106: reward = -85.43, steps = 29 11:19:48 [INFO] train episode 17107: reward = -92.93, steps = 32 11:19:52 [INFO] train episode 17108: reward = -99.74, steps = 41 11:19:55 [INFO] train episode 17109: reward = -75.58, steps = 39 11:19:58 [INFO] train episode 17110: reward = -74.52, steps = 33 11:20:00 [INFO] train episode 17111: reward = -73.80, steps = 21 11:20:03 [INFO] train episode 17112: reward = -124.28, steps = 35 11:20:05 [INFO] train episode 17113: reward = -72.14, steps = 22 11:20:09 [INFO] train episode 17114: reward = -72.46, steps = 39 11:20:11 [INFO] train episode 17115: reward = -126.94, steps = 30 11:20:14 [INFO] train episode 17116: reward = -73.72, steps = 36 11:20:16 [INFO] train episode 17117: reward = -90.93, steps = 20 11:20:19 [INFO] train episode 17118: reward = -91.07, steps = 24 11:20:20 [INFO] train episode 17119: reward = -57.75, steps = 20 11:20:22 [INFO] train episode 17120: reward = -66.65, steps = 23 11:20:25 [INFO] train episode 17121: reward = -98.26, steps = 27 11:20:29 [INFO] train episode 17122: reward = -158.96, steps = 44 11:20:30 [INFO] train episode 17123: reward = -72.93, steps = 22 11:20:34 [INFO] train episode 17124: reward = -89.01, steps = 41 11:20:37 [INFO] train episode 17125: reward = -80.05, steps = 32 11:20:40 [INFO] train episode 17126: reward = -90.37, steps = 32 11:20:44 [INFO] train episode 17127: reward = -86.80, steps = 52 11:20:46 [INFO] train episode 17128: reward = -57.85, steps = 22 11:20:49 [INFO] train episode 17129: reward = -98.12, steps = 30 11:20:53 [INFO] train episode 17130: reward = -83.42, steps = 28 11:20:58 [INFO] train episode 17131: reward = -91.96, steps = 56 11:21:00 [INFO] train episode 17132: reward = -91.93, steps = 24 11:21:04 [INFO] train episode 17133: reward = -87.44, steps = 35 11:21:09 [INFO] train episode 17134: reward = -96.90, steps = 46 11:21:12 [INFO] train episode 17135: reward = -77.89, steps = 40 11:21:15 [INFO] train episode 17136: reward = -85.35, steps = 27 11:21:19 [INFO] train episode 17137: reward = -96.65, steps = 46 11:21:24 [INFO] train episode 17138: reward = -51.54, steps = 61 11:21:27 [INFO] train episode 17139: reward = -109.93, steps = 24 11:21:32 [INFO] train episode 17140: reward = -167.06, steps = 62 11:21:34 [INFO] train episode 17141: reward = -83.84, steps = 22 11:21:37 [INFO] train episode 17142: reward = -82.14, steps = 36 11:21:41 [INFO] train episode 17143: reward = -90.80, steps = 42 11:21:43 [INFO] train episode 17144: reward = -87.82, steps = 25 11:21:47 [INFO] train episode 17145: reward = -58.53, steps = 42 11:21:49 [INFO] train episode 17146: reward = -76.10, steps = 30 11:21:52 [INFO] train episode 17147: reward = -108.96, steps = 28 11:21:55 [INFO] train episode 17148: reward = -79.83, steps = 35 11:21:57 [INFO] train episode 17149: reward = -62.31, steps = 22 11:22:02 [INFO] train episode 17150: reward = -151.84, steps = 57 11:22:05 [INFO] train episode 17151: reward = -108.92, steps = 39 11:22:08 [INFO] train episode 17152: reward = -87.25, steps = 30 11:22:10 [INFO] train episode 17153: reward = -67.84, steps = 22 11:22:13 [INFO] train episode 17154: reward = -116.38, steps = 29 11:22:15 [INFO] train episode 17155: reward = -60.79, steps = 21 11:22:18 [INFO] train episode 17156: reward = -90.48, steps = 31 11:22:21 [INFO] train episode 17157: reward = -59.90, steps = 26 11:22:23 [INFO] train episode 17158: reward = -62.61, steps = 32 11:22:26 [INFO] train episode 17159: reward = -81.17, steps = 26 11:22:28 [INFO] train episode 17160: reward = -66.11, steps = 26 11:22:30 [INFO] train episode 17161: reward = -81.46, steps = 24 11:22:38 [INFO] train episode 17162: reward = -157.92, steps = 91 11:22:42 [INFO] train episode 17163: reward = -156.49, steps = 39 11:22:46 [INFO] train episode 17164: reward = -112.06, steps = 51 11:22:50 [INFO] train episode 17165: reward = -59.69, steps = 43 11:22:54 [INFO] train episode 17166: reward = -141.66, steps = 47 11:22:56 [INFO] train episode 17167: reward = -67.53, steps = 25 11:23:00 [INFO] train episode 17168: reward = -102.30, steps = 38 11:23:02 [INFO] train episode 17169: reward = -86.14, steps = 32 11:23:05 [INFO] train episode 17170: reward = -93.35, steps = 26 11:23:11 [INFO] train episode 17171: reward = -140.27, steps = 75 11:23:15 [INFO] train episode 17172: reward = -77.96, steps = 46 11:23:18 [INFO] train episode 17173: reward = -59.74, steps = 29 11:23:21 [INFO] train episode 17174: reward = -81.19, steps = 35 11:23:23 [INFO] train episode 17175: reward = -96.50, steps = 21 11:23:27 [INFO] train episode 17176: reward = -83.34, steps = 40 11:23:29 [INFO] train episode 17177: reward = -109.11, steps = 28 11:23:34 [INFO] train episode 17178: reward = -132.67, steps = 61 11:23:36 [INFO] train episode 17179: reward = -52.10, steps = 21 11:23:39 [INFO] train episode 17180: reward = -78.23, steps = 28 11:23:43 [INFO] train episode 17181: reward = -75.59, steps = 49 11:23:45 [INFO] train episode 17182: reward = -88.00, steps = 20 11:23:47 [INFO] train episode 17183: reward = -81.32, steps = 24 11:23:52 [INFO] train episode 17184: reward = -183.50, steps = 54 11:23:57 [INFO] train episode 17185: reward = -146.64, steps = 61 11:24:01 [INFO] train episode 17186: reward = -70.76, steps = 45 11:24:06 [INFO] train episode 17187: reward = -95.45, steps = 59 11:24:09 [INFO] train episode 17188: reward = -132.82, steps = 32 11:24:12 [INFO] train episode 17189: reward = -118.68, steps = 28 11:24:14 [INFO] train episode 17190: reward = -86.25, steps = 25 11:24:18 [INFO] train episode 17191: reward = -102.65, steps = 45 11:24:21 [INFO] train episode 17192: reward = -102.39, steps = 33 11:24:23 [INFO] train episode 17193: reward = -59.21, steps = 27 11:24:29 [INFO] train episode 17194: reward = -199.71, steps = 61 11:24:33 [INFO] train episode 17195: reward = -91.23, steps = 46 11:24:35 [INFO] train episode 17196: reward = -69.23, steps = 24 11:24:38 [INFO] train episode 17197: reward = -107.61, steps = 42 11:24:40 [INFO] train episode 17198: reward = -76.48, steps = 19 11:24:43 [INFO] train episode 17199: reward = -82.28, steps = 25 11:24:45 [INFO] train episode 17200: reward = -73.64, steps = 24 11:24:47 [INFO] train episode 17201: reward = -75.70, steps = 27 11:24:53 [INFO] train episode 17202: reward = -97.78, steps = 64 11:24:58 [INFO] train episode 17203: reward = -135.50, steps = 62 11:25:02 [INFO] train episode 17204: reward = -67.40, steps = 46 11:25:07 [INFO] train episode 17205: reward = -134.47, steps = 57 11:25:09 [INFO] train episode 17206: reward = -57.49, steps = 24 11:25:13 [INFO] train episode 17207: reward = -87.09, steps = 33 11:25:16 [INFO] train episode 17208: reward = -51.05, steps = 25 11:25:22 [INFO] train episode 17209: reward = -86.12, steps = 72 11:25:26 [INFO] train episode 17210: reward = -78.29, steps = 51 11:25:31 [INFO] train episode 17211: reward = -85.99, steps = 53 11:25:35 [INFO] train episode 17212: reward = -75.36, steps = 43 11:25:37 [INFO] train episode 17213: reward = -75.29, steps = 19 11:25:38 [INFO] train episode 17214: reward = -84.26, steps = 20 11:25:43 [INFO] train episode 17215: reward = -164.94, steps = 57 11:25:46 [INFO] train episode 17216: reward = -83.47, steps = 23 11:25:48 [INFO] train episode 17217: reward = -76.74, steps = 19 11:25:51 [INFO] train episode 17218: reward = -74.94, steps = 37 11:25:54 [INFO] train episode 17219: reward = -98.05, steps = 33 11:25:56 [INFO] train episode 17220: reward = -74.58, steps = 21 11:25:59 [INFO] train episode 17221: reward = -64.28, steps = 33 11:26:01 [INFO] train episode 17222: reward = -61.05, steps = 29 11:26:05 [INFO] train episode 17223: reward = -140.14, steps = 46 11:26:08 [INFO] train episode 17224: reward = -102.75, steps = 34 11:26:12 [INFO] train episode 17225: reward = -71.48, steps = 40 11:26:14 [INFO] train episode 17226: reward = -68.41, steps = 26 11:26:17 [INFO] train episode 17227: reward = -91.85, steps = 36 11:26:20 [INFO] train episode 17228: reward = -54.97, steps = 30 11:26:23 [INFO] train episode 17229: reward = -79.82, steps = 28 11:26:26 [INFO] train episode 17230: reward = -128.41, steps = 32 11:26:28 [INFO] train episode 17231: reward = -99.89, steps = 23 11:26:30 [INFO] train episode 17232: reward = -83.98, steps = 23 11:26:33 [INFO] train episode 17233: reward = -93.97, steps = 44 11:26:36 [INFO] train episode 17234: reward = -77.76, steps = 26 11:26:40 [INFO] train episode 17235: reward = -112.75, steps = 44 11:26:43 [INFO] train episode 17236: reward = -87.44, steps = 36 11:26:47 [INFO] train episode 17237: reward = -112.54, steps = 42 11:26:49 [INFO] train episode 17238: reward = -75.89, steps = 21 11:26:50 [INFO] train episode 17239: reward = -73.07, steps = 21 11:26:54 [INFO] train episode 17240: reward = -90.81, steps = 39 11:26:56 [INFO] train episode 17241: reward = -78.93, steps = 24 11:26:58 [INFO] train episode 17242: reward = -85.79, steps = 20 11:27:00 [INFO] train episode 17243: reward = -87.29, steps = 18 11:27:02 [INFO] train episode 17244: reward = -72.59, steps = 27 11:27:04 [INFO] train episode 17245: reward = -77.33, steps = 25 11:27:07 [INFO] train episode 17246: reward = -109.66, steps = 30 11:27:11 [INFO] train episode 17247: reward = -128.23, steps = 36 11:27:13 [INFO] train episode 17248: reward = -101.32, steps = 29 11:27:16 [INFO] train episode 17249: reward = -99.19, steps = 35 11:27:18 [INFO] train episode 17250: reward = -85.11, steps = 24 11:27:21 [INFO] train episode 17251: reward = -112.24, steps = 29 11:27:24 [INFO] train episode 17252: reward = -109.18, steps = 37 11:27:28 [INFO] train episode 17253: reward = -105.11, steps = 39 11:27:32 [INFO] train episode 17254: reward = -109.74, steps = 45 11:27:35 [INFO] train episode 17255: reward = -99.71, steps = 42 11:27:39 [INFO] train episode 17256: reward = -128.98, steps = 43 11:27:43 [INFO] train episode 17257: reward = -111.83, steps = 45 11:27:45 [INFO] train episode 17258: reward = -82.66, steps = 25 11:27:50 [INFO] train episode 17259: reward = -137.81, steps = 52 11:27:52 [INFO] train episode 17260: reward = -85.26, steps = 21 11:27:54 [INFO] train episode 17261: reward = -60.36, steps = 25 11:27:56 [INFO] train episode 17262: reward = -63.38, steps = 23 11:28:01 [INFO] train episode 17263: reward = -93.30, steps = 53 11:28:04 [INFO] train episode 17264: reward = -64.95, steps = 33 11:28:06 [INFO] train episode 17265: reward = -88.59, steps = 21 11:28:10 [INFO] train episode 17266: reward = -92.26, steps = 36 11:28:12 [INFO] train episode 17267: reward = -80.44, steps = 22 11:28:15 [INFO] train episode 17268: reward = -131.03, steps = 31 11:28:18 [INFO] train episode 17269: reward = -111.51, steps = 31 11:28:21 [INFO] train episode 17270: reward = -98.15, steps = 38 11:28:25 [INFO] train episode 17271: reward = -63.42, steps = 39 11:28:28 [INFO] train episode 17272: reward = -72.88, steps = 42 11:28:31 [INFO] train episode 17273: reward = -62.32, steps = 21 11:28:34 [INFO] train episode 17274: reward = -101.15, steps = 35 11:28:36 [INFO] train episode 17275: reward = -91.88, steps = 29 11:28:40 [INFO] train episode 17276: reward = -136.46, steps = 47 11:28:46 [INFO] train episode 17277: reward = -122.37, steps = 66 11:28:48 [INFO] train episode 17278: reward = -67.21, steps = 20 11:28:52 [INFO] train episode 17279: reward = -128.46, steps = 41 11:28:54 [INFO] train episode 17280: reward = -126.38, steps = 19 11:28:57 [INFO] train episode 17281: reward = -77.93, steps = 39 11:28:59 [INFO] train episode 17282: reward = -80.75, steps = 22 11:29:02 [INFO] train episode 17283: reward = -64.86, steps = 29 11:29:06 [INFO] train episode 17284: reward = -52.17, steps = 37 11:29:12 [INFO] train episode 17285: reward = -163.59, steps = 69 11:29:14 [INFO] train episode 17286: reward = -68.80, steps = 26 11:29:18 [INFO] train episode 17287: reward = -143.22, steps = 47 11:29:21 [INFO] train episode 17288: reward = -84.84, steps = 32 11:29:24 [INFO] train episode 17289: reward = -60.53, steps = 33 11:29:27 [INFO] train episode 17290: reward = -103.51, steps = 35 11:29:30 [INFO] train episode 17291: reward = -89.79, steps = 29 11:29:33 [INFO] train episode 17292: reward = -65.06, steps = 35 11:29:40 [INFO] train episode 17293: reward = -140.91, steps = 79 11:29:43 [INFO] train episode 17294: reward = -76.43, steps = 29 11:29:47 [INFO] train episode 17295: reward = -83.01, steps = 50 11:29:49 [INFO] train episode 17296: reward = -79.95, steps = 28 11:29:56 [INFO] train episode 17297: reward = -149.66, steps = 66 11:30:00 [INFO] train episode 17298: reward = -89.15, steps = 50 11:30:02 [INFO] train episode 17299: reward = -89.03, steps = 28 11:30:10 [INFO] train episode 17300: reward = -127.36, steps = 85 11:30:13 [INFO] train episode 17301: reward = -68.40, steps = 38 11:30:17 [INFO] train episode 17302: reward = -91.95, steps = 37 11:30:18 [INFO] train episode 17303: reward = -68.38, steps = 20 11:30:21 [INFO] train episode 17304: reward = -67.32, steps = 25 11:30:23 [INFO] train episode 17305: reward = -86.34, steps = 22 11:30:28 [INFO] train episode 17306: reward = -153.83, steps = 60 11:30:32 [INFO] train episode 17307: reward = -81.07, steps = 41 11:30:35 [INFO] train episode 17308: reward = -77.71, steps = 44 11:30:38 [INFO] train episode 17309: reward = -64.82, steps = 23 11:30:40 [INFO] train episode 17310: reward = -90.42, steps = 27 11:30:44 [INFO] train episode 17311: reward = -100.34, steps = 41 11:30:46 [INFO] train episode 17312: reward = -57.50, steps = 25 11:30:49 [INFO] train episode 17313: reward = -105.61, steps = 34 11:30:51 [INFO] train episode 17314: reward = -77.59, steps = 28 11:30:55 [INFO] train episode 17315: reward = -136.77, steps = 45 11:30:59 [INFO] train episode 17316: reward = -106.98, steps = 35 11:31:01 [INFO] train episode 17317: reward = -95.62, steps = 28 11:31:03 [INFO] train episode 17318: reward = -112.06, steps = 25 11:31:06 [INFO] train episode 17319: reward = -72.26, steps = 24 11:31:11 [INFO] train episode 17320: reward = -90.14, steps = 60 11:31:15 [INFO] train episode 17321: reward = -153.92, steps = 33 11:31:16 [INFO] train episode 17322: reward = -105.19, steps = 20 11:31:20 [INFO] train episode 17323: reward = -60.43, steps = 38 11:31:22 [INFO] train episode 17324: reward = -49.16, steps = 31 11:31:27 [INFO] train episode 17325: reward = -123.35, steps = 57 11:31:31 [INFO] train episode 17326: reward = -64.74, steps = 33 11:31:33 [INFO] train episode 17327: reward = -71.89, steps = 26 11:31:35 [INFO] train episode 17328: reward = -75.05, steps = 26 11:31:38 [INFO] train episode 17329: reward = -93.93, steps = 27 11:31:41 [INFO] train episode 17330: reward = -108.22, steps = 34 11:31:47 [INFO] train episode 17331: reward = -116.28, steps = 67 11:31:51 [INFO] train episode 17332: reward = -111.88, steps = 53 11:31:55 [INFO] train episode 17333: reward = -101.90, steps = 39 11:32:01 [INFO] train episode 17334: reward = -136.82, steps = 70 11:32:04 [INFO] train episode 17335: reward = -94.61, steps = 30 11:32:08 [INFO] train episode 17336: reward = -79.71, steps = 46 11:32:09 [INFO] train episode 17337: reward = -68.34, steps = 20 11:32:11 [INFO] train episode 17338: reward = -68.19, steps = 23 11:32:15 [INFO] train episode 17339: reward = -81.75, steps = 38 11:32:16 [INFO] train episode 17340: reward = -108.28, steps = 19 11:32:21 [INFO] train episode 17341: reward = -121.09, steps = 50 11:32:24 [INFO] train episode 17342: reward = -70.77, steps = 32 11:32:26 [INFO] train episode 17343: reward = -65.79, steps = 23 11:32:31 [INFO] train episode 17344: reward = -138.89, steps = 61 11:32:34 [INFO] train episode 17345: reward = -112.70, steps = 27 11:32:37 [INFO] train episode 17346: reward = -89.27, steps = 26 11:32:40 [INFO] train episode 17347: reward = -104.86, steps = 37 11:32:43 [INFO] train episode 17348: reward = -119.32, steps = 31 11:32:46 [INFO] train episode 17349: reward = -103.80, steps = 41 11:32:48 [INFO] train episode 17350: reward = -68.98, steps = 20 11:32:51 [INFO] train episode 17351: reward = -83.67, steps = 31 11:32:55 [INFO] train episode 17352: reward = -58.91, steps = 41 11:32:58 [INFO] train episode 17353: reward = -123.94, steps = 37 11:33:04 [INFO] train episode 17354: reward = -144.11, steps = 60 11:33:06 [INFO] train episode 17355: reward = -78.65, steps = 22 11:33:10 [INFO] train episode 17356: reward = -121.99, steps = 47 11:33:12 [INFO] train episode 17357: reward = -71.62, steps = 21 11:33:14 [INFO] train episode 17358: reward = -53.77, steps = 25 11:33:17 [INFO] train episode 17359: reward = -85.44, steps = 24 11:33:18 [INFO] train episode 17360: reward = -55.12, steps = 21 11:33:21 [INFO] train episode 17361: reward = -77.21, steps = 30 11:33:26 [INFO] train episode 17362: reward = -72.67, steps = 51 11:33:28 [INFO] train episode 17363: reward = -75.07, steps = 27 11:33:31 [INFO] train episode 17364: reward = -69.00, steps = 30 11:33:36 [INFO] train episode 17365: reward = -81.03, steps = 52 11:33:38 [INFO] train episode 17366: reward = -56.48, steps = 30 11:33:41 [INFO] train episode 17367: reward = -88.15, steps = 28 11:33:45 [INFO] train episode 17368: reward = -110.80, steps = 41 11:33:47 [INFO] train episode 17369: reward = -85.51, steps = 24 11:33:49 [INFO] train episode 17370: reward = -71.65, steps = 24 11:33:52 [INFO] train episode 17371: reward = -79.54, steps = 38 11:33:56 [INFO] train episode 17372: reward = -84.97, steps = 41 11:33:58 [INFO] train episode 17373: reward = -95.91, steps = 25 11:34:01 [INFO] train episode 17374: reward = -81.23, steps = 31 11:34:05 [INFO] train episode 17375: reward = -125.15, steps = 42 11:34:09 [INFO] train episode 17376: reward = -143.92, steps = 38 11:34:12 [INFO] train episode 17377: reward = -94.88, steps = 41 11:34:17 [INFO] train episode 17378: reward = -87.76, steps = 54 11:34:19 [INFO] train episode 17379: reward = -83.97, steps = 21 11:34:22 [INFO] train episode 17380: reward = -67.97, steps = 36 11:34:26 [INFO] train episode 17381: reward = -74.33, steps = 38 11:34:33 [INFO] train episode 17382: reward = -121.99, steps = 86 11:34:36 [INFO] train episode 17383: reward = -98.46, steps = 24 11:34:38 [INFO] train episode 17384: reward = -110.71, steps = 23 11:34:40 [INFO] train episode 17385: reward = -72.54, steps = 29 11:34:42 [INFO] train episode 17386: reward = -98.05, steps = 24 11:34:44 [INFO] train episode 17387: reward = -87.31, steps = 26 11:34:48 [INFO] train episode 17388: reward = -113.91, steps = 33 11:34:51 [INFO] train episode 17389: reward = -65.65, steps = 34 11:34:53 [INFO] train episode 17390: reward = -73.96, steps = 24 11:34:55 [INFO] train episode 17391: reward = -57.31, steps = 22 11:35:00 [INFO] train episode 17392: reward = -103.02, steps = 55 11:35:02 [INFO] train episode 17393: reward = -82.14, steps = 31 11:35:05 [INFO] train episode 17394: reward = -71.66, steps = 23 11:35:08 [INFO] train episode 17395: reward = -104.64, steps = 34 11:35:10 [INFO] train episode 17396: reward = -84.49, steps = 25 11:35:14 [INFO] train episode 17397: reward = -97.15, steps = 47 11:35:18 [INFO] train episode 17398: reward = -91.77, steps = 44 11:35:21 [INFO] train episode 17399: reward = -69.20, steps = 26 11:35:24 [INFO] train episode 17400: reward = -124.25, steps = 38 11:35:27 [INFO] train episode 17401: reward = -106.38, steps = 29 11:35:30 [INFO] train episode 17402: reward = -83.43, steps = 40 11:35:34 [INFO] train episode 17403: reward = -72.24, steps = 38 11:35:39 [INFO] train episode 17404: reward = -104.37, steps = 57 11:35:44 [INFO] train episode 17405: reward = -93.87, steps = 52 11:35:46 [INFO] train episode 17406: reward = -76.95, steps = 26 11:35:49 [INFO] train episode 17407: reward = -90.04, steps = 32 11:35:52 [INFO] train episode 17408: reward = -103.75, steps = 35 11:35:54 [INFO] train episode 17409: reward = -82.13, steps = 20 11:35:57 [INFO] train episode 17410: reward = -45.52, steps = 27 11:36:01 [INFO] train episode 17411: reward = -91.83, steps = 52 11:36:04 [INFO] train episode 17412: reward = -68.38, steps = 31 11:36:09 [INFO] train episode 17413: reward = -114.00, steps = 56 11:36:13 [INFO] train episode 17414: reward = -156.46, steps = 44 11:36:16 [INFO] train episode 17415: reward = -96.34, steps = 34 11:36:18 [INFO] train episode 17416: reward = -99.06, steps = 22 11:36:21 [INFO] train episode 17417: reward = -53.18, steps = 34 11:36:27 [INFO] train episode 17418: reward = -155.09, steps = 64 11:36:31 [INFO] train episode 17419: reward = -85.12, steps = 49 11:36:33 [INFO] train episode 17420: reward = -74.35, steps = 22 11:36:38 [INFO] train episode 17421: reward = -127.52, steps = 58 11:36:41 [INFO] train episode 17422: reward = -110.06, steps = 33 11:36:43 [INFO] train episode 17423: reward = -83.05, steps = 19 11:36:46 [INFO] train episode 17424: reward = -85.43, steps = 35 11:36:49 [INFO] train episode 17425: reward = -83.43, steps = 39 11:36:53 [INFO] train episode 17426: reward = -79.41, steps = 48 11:36:56 [INFO] train episode 17427: reward = -108.41, steps = 31 11:36:59 [INFO] train episode 17428: reward = -69.30, steps = 34 11:37:03 [INFO] train episode 17429: reward = -86.73, steps = 36 11:37:07 [INFO] train episode 17430: reward = -110.20, steps = 41 11:37:09 [INFO] train episode 17431: reward = -81.98, steps = 29 11:37:12 [INFO] train episode 17432: reward = -68.96, steps = 26 11:37:16 [INFO] train episode 17433: reward = -70.94, steps = 44 11:37:19 [INFO] train episode 17434: reward = -69.95, steps = 36 11:37:23 [INFO] train episode 17435: reward = -67.69, steps = 50 11:37:26 [INFO] train episode 17436: reward = -61.31, steps = 27 11:37:29 [INFO] train episode 17437: reward = -75.40, steps = 37 11:37:32 [INFO] train episode 17438: reward = -90.01, steps = 31 11:37:37 [INFO] train episode 17439: reward = -74.30, steps = 50 11:37:42 [INFO] train episode 17440: reward = -89.94, steps = 62 11:37:45 [INFO] train episode 17441: reward = -75.92, steps = 30 11:37:49 [INFO] train episode 17442: reward = -74.42, steps = 47 11:37:52 [INFO] train episode 17443: reward = -66.65, steps = 31 11:37:54 [INFO] train episode 17444: reward = -80.59, steps = 28 11:37:56 [INFO] train episode 17445: reward = -82.20, steps = 23 11:37:59 [INFO] train episode 17446: reward = -73.15, steps = 37 11:38:02 [INFO] train episode 17447: reward = -55.87, steps = 33 11:38:05 [INFO] train episode 17448: reward = -60.74, steps = 27 11:38:08 [INFO] train episode 17449: reward = -78.60, steps = 30 11:38:11 [INFO] train episode 17450: reward = -82.79, steps = 40 11:38:16 [INFO] train episode 17451: reward = -156.16, steps = 59 11:38:18 [INFO] train episode 17452: reward = -61.88, steps = 20 11:38:20 [INFO] train episode 17453: reward = -67.79, steps = 21 11:38:24 [INFO] train episode 17454: reward = -100.26, steps = 35 11:38:29 [INFO] train episode 17455: reward = -80.43, steps = 60 11:38:32 [INFO] train episode 17456: reward = -70.17, steps = 31 11:38:34 [INFO] train episode 17457: reward = -64.88, steps = 27 11:38:36 [INFO] train episode 17458: reward = -66.31, steps = 25 11:38:40 [INFO] train episode 17459: reward = -122.42, steps = 43 11:38:45 [INFO] train episode 17460: reward = -96.00, steps = 52 11:38:49 [INFO] train episode 17461: reward = -88.84, steps = 43 11:38:53 [INFO] train episode 17462: reward = -141.39, steps = 46 11:38:55 [INFO] train episode 17463: reward = -77.30, steps = 25 11:39:00 [INFO] train episode 17464: reward = -91.67, steps = 53 11:39:02 [INFO] train episode 17465: reward = -61.55, steps = 24 11:39:04 [INFO] train episode 17466: reward = -52.74, steps = 22 11:39:06 [INFO] train episode 17467: reward = -90.39, steps = 26 11:39:09 [INFO] train episode 17468: reward = -122.70, steps = 30 11:39:13 [INFO] train episode 17469: reward = -109.84, steps = 43 11:39:18 [INFO] train episode 17470: reward = -146.35, steps = 62 11:39:21 [INFO] train episode 17471: reward = -75.77, steps = 27 11:39:24 [INFO] train episode 17472: reward = -59.50, steps = 41 11:39:29 [INFO] train episode 17473: reward = -90.74, steps = 50 11:39:33 [INFO] train episode 17474: reward = -91.48, steps = 44 11:39:35 [INFO] train episode 17475: reward = -61.50, steps = 23 11:39:37 [INFO] train episode 17476: reward = -78.88, steps = 25 11:39:39 [INFO] train episode 17477: reward = -75.77, steps = 27 11:39:46 [INFO] train episode 17478: reward = -160.04, steps = 79 11:39:48 [INFO] train episode 17479: reward = -63.50, steps = 22 11:39:51 [INFO] train episode 17480: reward = -56.16, steps = 36 11:39:53 [INFO] train episode 17481: reward = -77.92, steps = 19 11:39:57 [INFO] train episode 17482: reward = -136.93, steps = 46 11:40:05 [INFO] train episode 17483: reward = -113.51, steps = 81 11:40:07 [INFO] train episode 17484: reward = -59.71, steps = 20 11:40:13 [INFO] train episode 17485: reward = -100.44, steps = 66 11:40:15 [INFO] train episode 17486: reward = -65.02, steps = 21 11:40:17 [INFO] train episode 17487: reward = -82.95, steps = 27 11:40:21 [INFO] train episode 17488: reward = -105.80, steps = 39 11:40:22 [INFO] train episode 17489: reward = -103.42, steps = 19 11:40:25 [INFO] train episode 17490: reward = -72.27, steps = 31 11:40:30 [INFO] train episode 17491: reward = -125.36, steps = 53 11:40:36 [INFO] train episode 17492: reward = -129.09, steps = 74 11:40:42 [INFO] train episode 17493: reward = -110.79, steps = 65 11:40:45 [INFO] train episode 17494: reward = -87.75, steps = 30 11:40:47 [INFO] train episode 17495: reward = -79.73, steps = 31 11:40:51 [INFO] train episode 17496: reward = -66.97, steps = 36 11:40:53 [INFO] train episode 17497: reward = -70.30, steps = 21 11:40:57 [INFO] train episode 17498: reward = -121.64, steps = 54 11:40:59 [INFO] train episode 17499: reward = -74.60, steps = 26 11:41:02 [INFO] train episode 17500: reward = -83.48, steps = 24 11:41:08 [INFO] train episode 17501: reward = -84.30, steps = 75 11:41:16 [INFO] train episode 17502: reward = -140.99, steps = 89 11:41:20 [INFO] train episode 17503: reward = -105.15, steps = 44 11:41:22 [INFO] train episode 17504: reward = -63.48, steps = 21 11:41:24 [INFO] train episode 17505: reward = -74.99, steps = 21 11:41:26 [INFO] train episode 17506: reward = -63.95, steps = 23 11:41:28 [INFO] train episode 17507: reward = -69.84, steps = 22 11:41:32 [INFO] train episode 17508: reward = -59.57, steps = 43 11:41:35 [INFO] train episode 17509: reward = -100.78, steps = 35 11:41:37 [INFO] train episode 17510: reward = -80.48, steps = 24 11:41:41 [INFO] train episode 17511: reward = -82.87, steps = 40 11:41:43 [INFO] train episode 17512: reward = -57.95, steps = 23 11:41:46 [INFO] train episode 17513: reward = -86.46, steps = 40 11:41:50 [INFO] train episode 17514: reward = -75.38, steps = 42 11:41:54 [INFO] train episode 17515: reward = -106.37, steps = 48 11:41:57 [INFO] train episode 17516: reward = -72.19, steps = 31 11:41:59 [INFO] train episode 17517: reward = -71.12, steps = 27 11:42:01 [INFO] train episode 17518: reward = -64.47, steps = 22 11:42:03 [INFO] train episode 17519: reward = -72.92, steps = 24 11:42:10 [INFO] train episode 17520: reward = -186.65, steps = 72 11:42:16 [INFO] train episode 17521: reward = -139.20, steps = 68 11:42:19 [INFO] train episode 17522: reward = -96.85, steps = 36 11:42:23 [INFO] train episode 17523: reward = -75.73, steps = 47 11:42:26 [INFO] train episode 17524: reward = -71.55, steps = 30 11:42:30 [INFO] train episode 17525: reward = -108.01, steps = 40 11:42:32 [INFO] train episode 17526: reward = -89.61, steps = 22 11:42:35 [INFO] train episode 17527: reward = -69.37, steps = 43 11:42:41 [INFO] train episode 17528: reward = -97.19, steps = 63 11:42:44 [INFO] train episode 17529: reward = -102.37, steps = 31 11:42:46 [INFO] train episode 17530: reward = -80.47, steps = 21 11:42:48 [INFO] train episode 17531: reward = -107.20, steps = 29 11:42:53 [INFO] train episode 17532: reward = -125.41, steps = 56 11:42:56 [INFO] train episode 17533: reward = -109.09, steps = 35 11:43:03 [INFO] train episode 17534: reward = -121.05, steps = 59 11:43:05 [INFO] train episode 17535: reward = -105.41, steps = 22 11:43:09 [INFO] train episode 17536: reward = -97.02, steps = 48 11:43:11 [INFO] train episode 17537: reward = -50.79, steps = 32 11:43:13 [INFO] train episode 17538: reward = -82.31, steps = 21 11:43:15 [INFO] train episode 17539: reward = -66.82, steps = 25 11:43:20 [INFO] train episode 17540: reward = -100.90, steps = 49 11:43:22 [INFO] train episode 17541: reward = -83.55, steps = 25 11:43:24 [INFO] train episode 17542: reward = -61.02, steps = 23 11:43:29 [INFO] train episode 17543: reward = -77.04, steps = 60 11:43:34 [INFO] train episode 17544: reward = -108.32, steps = 54 11:43:38 [INFO] train episode 17545: reward = -55.49, steps = 39 11:43:42 [INFO] train episode 17546: reward = -48.47, steps = 42 11:43:48 [INFO] train episode 17547: reward = -91.67, steps = 69 11:43:50 [INFO] train episode 17548: reward = -90.04, steps = 28 11:43:53 [INFO] train episode 17549: reward = -73.95, steps = 29 11:43:55 [INFO] train episode 17550: reward = -74.26, steps = 29 11:43:59 [INFO] train episode 17551: reward = -58.12, steps = 40 11:44:01 [INFO] train episode 17552: reward = -77.05, steps = 28 11:44:05 [INFO] train episode 17553: reward = -116.75, steps = 36 11:44:08 [INFO] train episode 17554: reward = -95.97, steps = 35 11:44:10 [INFO] train episode 17555: reward = -71.83, steps = 21 11:44:15 [INFO] train episode 17556: reward = -120.17, steps = 61 11:44:19 [INFO] train episode 17557: reward = -53.30, steps = 40 11:44:22 [INFO] train episode 17558: reward = -68.47, steps = 36 11:44:24 [INFO] train episode 17559: reward = -86.63, steps = 21 11:44:28 [INFO] train episode 17560: reward = -64.71, steps = 44 11:44:29 [INFO] train episode 17561: reward = -58.39, steps = 21 11:44:31 [INFO] train episode 17562: reward = -84.98, steps = 22 11:44:35 [INFO] train episode 17563: reward = -74.82, steps = 38 11:44:40 [INFO] train episode 17564: reward = -77.83, steps = 60 11:44:44 [INFO] train episode 17565: reward = -76.45, steps = 40 11:44:46 [INFO] train episode 17566: reward = -74.73, steps = 28 11:44:49 [INFO] train episode 17567: reward = -82.01, steps = 27 11:44:52 [INFO] train episode 17568: reward = -82.34, steps = 38 11:44:55 [INFO] train episode 17569: reward = -86.69, steps = 32 11:44:58 [INFO] train episode 17570: reward = -106.19, steps = 35 11:45:01 [INFO] train episode 17571: reward = -94.97, steps = 37 11:45:05 [INFO] train episode 17572: reward = -86.62, steps = 43 11:45:11 [INFO] train episode 17573: reward = -75.71, steps = 58 11:45:13 [INFO] train episode 17574: reward = -97.84, steps = 32 11:45:15 [INFO] train episode 17575: reward = -88.46, steps = 23 11:45:19 [INFO] train episode 17576: reward = -72.62, steps = 40 11:45:23 [INFO] train episode 17577: reward = -99.75, steps = 47 11:45:26 [INFO] train episode 17578: reward = -112.17, steps = 32 11:45:30 [INFO] train episode 17579: reward = -118.96, steps = 42 11:45:34 [INFO] train episode 17580: reward = -51.51, steps = 48 11:45:36 [INFO] train episode 17581: reward = -67.22, steps = 22 11:45:38 [INFO] train episode 17582: reward = -58.61, steps = 23 11:45:41 [INFO] train episode 17583: reward = -82.97, steps = 27 11:45:45 [INFO] train episode 17584: reward = -67.17, steps = 45 11:45:48 [INFO] train episode 17585: reward = -83.00, steps = 31 11:45:50 [INFO] train episode 17586: reward = -76.90, steps = 29 11:45:54 [INFO] train episode 17587: reward = -107.55, steps = 38 11:45:58 [INFO] train episode 17588: reward = -87.80, steps = 42 11:46:01 [INFO] train episode 17589: reward = -52.70, steps = 22 11:46:04 [INFO] train episode 17590: reward = -73.83, steps = 38 11:46:07 [INFO] train episode 17591: reward = -67.83, steps = 36 11:46:11 [INFO] train episode 17592: reward = -109.79, steps = 40 11:46:15 [INFO] train episode 17593: reward = -112.90, steps = 49 11:46:19 [INFO] train episode 17594: reward = -109.98, steps = 38 11:46:20 [INFO] train episode 17595: reward = -61.85, steps = 19 11:46:27 [INFO] train episode 17596: reward = -158.35, steps = 77 11:46:31 [INFO] train episode 17597: reward = -86.74, steps = 47 11:46:34 [INFO] train episode 17598: reward = -64.66, steps = 34 11:46:37 [INFO] train episode 17599: reward = -103.06, steps = 36 11:46:39 [INFO] train episode 17600: reward = -59.71, steps = 21 11:46:44 [INFO] train episode 17601: reward = -81.89, steps = 60 11:46:49 [INFO] train episode 17602: reward = -66.77, steps = 50 11:46:53 [INFO] train episode 17603: reward = -74.73, steps = 41 11:46:55 [INFO] train episode 17604: reward = -74.99, steps = 30 11:46:59 [INFO] train episode 17605: reward = -58.53, steps = 44 11:47:01 [INFO] train episode 17606: reward = -68.06, steps = 23 11:47:04 [INFO] train episode 17607: reward = -86.09, steps = 31 11:47:07 [INFO] train episode 17608: reward = -79.50, steps = 29 11:47:09 [INFO] train episode 17609: reward = -73.22, steps = 23 11:47:13 [INFO] train episode 17610: reward = -73.89, steps = 46 11:47:16 [INFO] train episode 17611: reward = -61.91, steps = 35 11:47:18 [INFO] train episode 17612: reward = -91.21, steps = 26 11:47:21 [INFO] train episode 17613: reward = -67.84, steps = 28 11:47:28 [INFO] train episode 17614: reward = -181.07, steps = 74 11:47:32 [INFO] train episode 17615: reward = -63.05, steps = 50 11:47:37 [INFO] train episode 17616: reward = -52.52, steps = 49 11:47:44 [INFO] train episode 17617: reward = -140.41, steps = 78 11:47:46 [INFO] train episode 17618: reward = -52.56, steps = 26 11:47:49 [INFO] train episode 17619: reward = -71.78, steps = 32 11:47:53 [INFO] train episode 17620: reward = -53.31, steps = 42 11:47:56 [INFO] train episode 17621: reward = -55.71, steps = 39 11:48:02 [INFO] train episode 17622: reward = -96.41, steps = 68 11:48:04 [INFO] train episode 17623: reward = -60.85, steps = 23 11:48:08 [INFO] train episode 17624: reward = -115.02, steps = 47 11:48:11 [INFO] train episode 17625: reward = -94.12, steps = 34 11:48:18 [INFO] train episode 17626: reward = -75.98, steps = 81 11:48:21 [INFO] train episode 17627: reward = -98.81, steps = 27 11:48:23 [INFO] train episode 17628: reward = -59.62, steps = 22 11:48:29 [INFO] train episode 17629: reward = -83.11, steps = 69 11:48:31 [INFO] train episode 17630: reward = -71.18, steps = 19 11:48:40 [INFO] train episode 17631: reward = -185.85, steps = 104 11:48:41 [INFO] train episode 17632: reward = -88.39, steps = 20 11:48:44 [INFO] train episode 17633: reward = -47.65, steps = 29 11:48:49 [INFO] train episode 17634: reward = -88.24, steps = 54 11:48:54 [INFO] train episode 17635: reward = -73.80, steps = 48 11:48:59 [INFO] train episode 17636: reward = -105.14, steps = 52 11:49:01 [INFO] train episode 17637: reward = -52.81, steps = 30 11:49:04 [INFO] train episode 17638: reward = -78.49, steps = 22 11:49:07 [INFO] train episode 17639: reward = -71.90, steps = 37 11:49:10 [INFO] train episode 17640: reward = -59.15, steps = 37 11:49:13 [INFO] train episode 17641: reward = -57.59, steps = 34 11:49:16 [INFO] train episode 17642: reward = -57.92, steps = 35 11:49:21 [INFO] train episode 17643: reward = -93.99, steps = 53 11:49:23 [INFO] train episode 17644: reward = -47.74, steps = 21 11:49:25 [INFO] train episode 17645: reward = -68.92, steps = 23 11:49:31 [INFO] train episode 17646: reward = -92.68, steps = 68 11:49:36 [INFO] train episode 17647: reward = -89.88, steps = 56 11:49:41 [INFO] train episode 17648: reward = -76.59, steps = 64 11:49:44 [INFO] train episode 17649: reward = -59.82, steps = 27 11:49:50 [INFO] train episode 17650: reward = -119.95, steps = 72 11:49:53 [INFO] train episode 17651: reward = -86.80, steps = 23 11:49:55 [INFO] train episode 17652: reward = -63.40, steps = 25 11:50:01 [INFO] train episode 17653: reward = -107.79, steps = 64 11:50:04 [INFO] train episode 17654: reward = -80.32, steps = 33 11:50:07 [INFO] train episode 17655: reward = -49.71, steps = 34 11:50:10 [INFO] train episode 17656: reward = -97.81, steps = 28 11:50:17 [INFO] train episode 17657: reward = -152.66, steps = 85 11:50:19 [INFO] train episode 17658: reward = -76.78, steps = 25 11:50:23 [INFO] train episode 17659: reward = -84.74, steps = 47 11:50:27 [INFO] train episode 17660: reward = -78.01, steps = 37 11:50:30 [INFO] train episode 17661: reward = -85.89, steps = 33 11:50:34 [INFO] train episode 17662: reward = -125.40, steps = 54 11:50:40 [INFO] train episode 17663: reward = -124.75, steps = 64 11:50:42 [INFO] train episode 17664: reward = -97.71, steps = 26 11:50:46 [INFO] train episode 17665: reward = -41.19, steps = 38 11:50:48 [INFO] train episode 17666: reward = -66.77, steps = 32 11:50:50 [INFO] train episode 17667: reward = -52.69, steps = 20 11:50:54 [INFO] train episode 17668: reward = -87.08, steps = 45 11:50:59 [INFO] train episode 17669: reward = -100.61, steps = 45 11:51:01 [INFO] train episode 17670: reward = -90.41, steps = 32 11:51:03 [INFO] train episode 17671: reward = -101.99, steps = 18 11:51:05 [INFO] train episode 17672: reward = -81.42, steps = 23 11:51:07 [INFO] train episode 17673: reward = -65.35, steps = 21 11:51:09 [INFO] train episode 17674: reward = -66.94, steps = 21 11:51:14 [INFO] train episode 17675: reward = -101.69, steps = 54 11:51:17 [INFO] train episode 17676: reward = -68.01, steps = 30 11:51:20 [INFO] train episode 17677: reward = -83.07, steps = 43 11:51:27 [INFO] train episode 17678: reward = -140.94, steps = 72 11:51:28 [INFO] train episode 17679: reward = -81.74, steps = 20 11:51:31 [INFO] train episode 17680: reward = -70.43, steps = 24 11:51:35 [INFO] train episode 17681: reward = -80.95, steps = 42 11:51:38 [INFO] train episode 17682: reward = -86.43, steps = 41 11:51:44 [INFO] train episode 17683: reward = -131.61, steps = 67 11:51:47 [INFO] train episode 17684: reward = -51.42, steps = 31 11:51:51 [INFO] train episode 17685: reward = -76.32, steps = 36 11:51:54 [INFO] train episode 17686: reward = -68.28, steps = 38 11:51:59 [INFO] train episode 17687: reward = -67.87, steps = 52 11:52:03 [INFO] train episode 17688: reward = -86.31, steps = 48 11:52:07 [INFO] train episode 17689: reward = -70.95, steps = 42 11:52:09 [INFO] train episode 17690: reward = -52.46, steps = 21 11:52:13 [INFO] train episode 17691: reward = -82.20, steps = 45 11:52:18 [INFO] train episode 17692: reward = -151.54, steps = 60 11:52:20 [INFO] train episode 17693: reward = -57.10, steps = 27 11:52:23 [INFO] train episode 17694: reward = -58.87, steps = 33 11:52:25 [INFO] train episode 17695: reward = -71.68, steps = 22 11:52:29 [INFO] train episode 17696: reward = -73.08, steps = 37 11:52:32 [INFO] train episode 17697: reward = -98.62, steps = 40 11:52:37 [INFO] train episode 17698: reward = -113.31, steps = 55 11:52:41 [INFO] train episode 17699: reward = -54.88, steps = 44 11:52:45 [INFO] train episode 17700: reward = -42.93, steps = 48 11:52:47 [INFO] train episode 17701: reward = -47.22, steps = 21 11:52:50 [INFO] train episode 17702: reward = -83.87, steps = 26 11:52:54 [INFO] train episode 17703: reward = -53.09, steps = 51 11:52:58 [INFO] train episode 17704: reward = -131.02, steps = 35 11:53:03 [INFO] train episode 17705: reward = -91.60, steps = 54 11:53:05 [INFO] train episode 17706: reward = -62.60, steps = 24 11:53:06 [INFO] train episode 17707: reward = -74.06, steps = 19 11:53:11 [INFO] train episode 17708: reward = -86.90, steps = 46 11:53:15 [INFO] train episode 17709: reward = -64.98, steps = 46 11:53:19 [INFO] train episode 17710: reward = -79.94, steps = 48 11:53:22 [INFO] train episode 17711: reward = -72.34, steps = 36 11:53:24 [INFO] train episode 17712: reward = -81.42, steps = 28 11:53:27 [INFO] train episode 17713: reward = -71.16, steps = 21 11:53:31 [INFO] train episode 17714: reward = -92.87, steps = 49 11:53:36 [INFO] train episode 17715: reward = -48.08, steps = 56 11:53:39 [INFO] train episode 17716: reward = -82.54, steps = 43 11:53:42 [INFO] train episode 17717: reward = -71.98, steps = 31 11:53:47 [INFO] train episode 17718: reward = -49.31, steps = 51 11:53:50 [INFO] train episode 17719: reward = -92.06, steps = 37 11:53:53 [INFO] train episode 17720: reward = -72.32, steps = 37 11:53:57 [INFO] train episode 17721: reward = -78.93, steps = 37 11:53:59 [INFO] train episode 17722: reward = -55.43, steps = 20 11:54:01 [INFO] train episode 17723: reward = -75.27, steps = 29 11:54:05 [INFO] train episode 17724: reward = -95.09, steps = 44 11:54:12 [INFO] train episode 17725: reward = -132.94, steps = 74 11:54:14 [INFO] train episode 17726: reward = -67.15, steps = 30 11:54:20 [INFO] train episode 17727: reward = -105.41, steps = 64 11:54:22 [INFO] train episode 17728: reward = -59.42, steps = 22 11:54:24 [INFO] train episode 17729: reward = -73.63, steps = 27 11:54:31 [INFO] train episode 17730: reward = -101.90, steps = 73 11:54:35 [INFO] train episode 17731: reward = -95.38, steps = 42 11:54:38 [INFO] train episode 17732: reward = -83.44, steps = 38 11:54:44 [INFO] train episode 17733: reward = -126.24, steps = 75 11:54:51 [INFO] train episode 17734: reward = -120.81, steps = 57 11:54:53 [INFO] train episode 17735: reward = -81.82, steps = 22 11:54:57 [INFO] train episode 17736: reward = -100.53, steps = 47 11:54:59 [INFO] train episode 17737: reward = -52.44, steps = 29 11:55:02 [INFO] train episode 17738: reward = -80.21, steps = 24 11:55:08 [INFO] train episode 17739: reward = -132.54, steps = 75 11:55:12 [INFO] train episode 17740: reward = -66.61, steps = 40 11:55:17 [INFO] train episode 17741: reward = -93.39, steps = 62 11:55:19 [INFO] train episode 17742: reward = -59.98, steps = 20 11:55:22 [INFO] train episode 17743: reward = -62.79, steps = 25 11:55:26 [INFO] train episode 17744: reward = -71.09, steps = 50 11:55:28 [INFO] train episode 17745: reward = -59.10, steps = 25 11:55:33 [INFO] train episode 17746: reward = -71.52, steps = 50 11:55:35 [INFO] train episode 17747: reward = -62.78, steps = 24 11:55:37 [INFO] train episode 17748: reward = -54.31, steps = 22 11:55:40 [INFO] train episode 17749: reward = -93.26, steps = 27 11:55:44 [INFO] train episode 17750: reward = -90.48, steps = 49 11:55:48 [INFO] train episode 17751: reward = -64.24, steps = 42 11:55:49 [INFO] train episode 17752: reward = -68.67, steps = 18 11:55:54 [INFO] train episode 17753: reward = -62.92, steps = 48 11:55:56 [INFO] train episode 17754: reward = -63.13, steps = 24 11:55:58 [INFO] train episode 17755: reward = -52.83, steps = 19 11:56:00 [INFO] train episode 17756: reward = -74.49, steps = 28 11:56:02 [INFO] train episode 17757: reward = -66.94, steps = 25 11:56:08 [INFO] train episode 17758: reward = -49.92, steps = 61 11:56:11 [INFO] train episode 17759: reward = -76.60, steps = 36 11:56:15 [INFO] train episode 17760: reward = -80.69, steps = 37 11:56:16 [INFO] train episode 17761: reward = -54.13, steps = 19 11:56:20 [INFO] train episode 17762: reward = -84.46, steps = 46 11:56:23 [INFO] train episode 17763: reward = -68.96, steps = 30 11:56:27 [INFO] train episode 17764: reward = -74.44, steps = 42 11:56:29 [INFO] train episode 17765: reward = -99.37, steps = 26 11:56:32 [INFO] train episode 17766: reward = -79.46, steps = 25 11:56:34 [INFO] train episode 17767: reward = -73.88, steps = 26 11:56:38 [INFO] train episode 17768: reward = -66.56, steps = 41 11:56:41 [INFO] train episode 17769: reward = -80.55, steps = 42 11:56:45 [INFO] train episode 17770: reward = -80.24, steps = 39 11:56:48 [INFO] train episode 17771: reward = -57.34, steps = 36 11:56:53 [INFO] train episode 17772: reward = -62.42, steps = 51 11:56:57 [INFO] train episode 17773: reward = -55.02, steps = 49 11:57:00 [INFO] train episode 17774: reward = -82.63, steps = 29 11:57:06 [INFO] train episode 17775: reward = -122.07, steps = 73 11:57:10 [INFO] train episode 17776: reward = -70.43, steps = 45 11:57:13 [INFO] train episode 17777: reward = -77.83, steps = 34 11:57:17 [INFO] train episode 17778: reward = -92.74, steps = 36 11:57:23 [INFO] train episode 17779: reward = -103.44, steps = 71 11:57:25 [INFO] train episode 17780: reward = -63.20, steps = 21 11:57:29 [INFO] train episode 17781: reward = -62.75, steps = 51 11:57:33 [INFO] train episode 17782: reward = -110.80, steps = 45 11:57:36 [INFO] train episode 17783: reward = -69.96, steps = 29 11:57:39 [INFO] train episode 17784: reward = -57.58, steps = 39 11:57:42 [INFO] train episode 17785: reward = -84.51, steps = 31 11:57:48 [INFO] train episode 17786: reward = -92.30, steps = 55 11:57:56 [INFO] train episode 17787: reward = -138.63, steps = 94 11:57:59 [INFO] train episode 17788: reward = -59.85, steps = 31 11:58:03 [INFO] train episode 17789: reward = -119.57, steps = 42 11:58:05 [INFO] train episode 17790: reward = -51.80, steps = 23 11:58:09 [INFO] train episode 17791: reward = -56.43, steps = 38 11:58:11 [INFO] train episode 17792: reward = -55.54, steps = 25 11:58:15 [INFO] train episode 17793: reward = -97.51, steps = 46 11:58:19 [INFO] train episode 17794: reward = -57.95, steps = 41 11:58:22 [INFO] train episode 17795: reward = -55.64, steps = 28 11:58:26 [INFO] train episode 17796: reward = -47.03, steps = 46 11:58:28 [INFO] train episode 17797: reward = -54.76, steps = 30 11:58:33 [INFO] train episode 17798: reward = -61.57, steps = 53 11:58:38 [INFO] train episode 17799: reward = -143.24, steps = 56 11:58:44 [INFO] train episode 17800: reward = -91.02, steps = 63 11:58:46 [INFO] train episode 17801: reward = -51.59, steps = 21 11:58:49 [INFO] train episode 17802: reward = -77.94, steps = 37 11:58:51 [INFO] train episode 17803: reward = -78.99, steps = 27 11:58:55 [INFO] train episode 17804: reward = -70.07, steps = 40 11:59:00 [INFO] train episode 17805: reward = -84.30, steps = 54 11:59:05 [INFO] train episode 17806: reward = -61.85, steps = 60 11:59:08 [INFO] train episode 17807: reward = -81.43, steps = 35 11:59:13 [INFO] train episode 17808: reward = -99.55, steps = 47 11:59:17 [INFO] train episode 17809: reward = -61.20, steps = 44 11:59:22 [INFO] train episode 17810: reward = -91.03, steps = 43 11:59:26 [INFO] train episode 17811: reward = -49.36, steps = 45 11:59:31 [INFO] train episode 17812: reward = -74.70, steps = 60 11:59:36 [INFO] train episode 17813: reward = -80.87, steps = 55 11:59:42 [INFO] train episode 17814: reward = -60.07, steps = 66 11:59:46 [INFO] train episode 17815: reward = -95.54, steps = 50 11:59:50 [INFO] train episode 17816: reward = -92.99, steps = 41 11:59:55 [INFO] train episode 17817: reward = -101.94, steps = 63 11:59:59 [INFO] train episode 17818: reward = -69.01, steps = 35 12:00:04 [INFO] train episode 17819: reward = -145.65, steps = 54 12:00:06 [INFO] train episode 17820: reward = -48.00, steps = 25 12:00:10 [INFO] train episode 17821: reward = -121.03, steps = 51 12:00:13 [INFO] train episode 17822: reward = -70.51, steps = 26 12:00:17 [INFO] train episode 17823: reward = -91.58, steps = 53 12:00:20 [INFO] train episode 17824: reward = -62.54, steps = 26 12:00:22 [INFO] train episode 17825: reward = -65.73, steps = 27 12:00:26 [INFO] train episode 17826: reward = -81.32, steps = 38 12:00:31 [INFO] train episode 17827: reward = -69.21, steps = 66 12:00:35 [INFO] train episode 17828: reward = -64.34, steps = 42 12:00:37 [INFO] train episode 17829: reward = -74.33, steps = 20 12:00:41 [INFO] train episode 17830: reward = -66.89, steps = 40 12:00:44 [INFO] train episode 17831: reward = -59.65, steps = 37 12:00:52 [INFO] train episode 17832: reward = -80.11, steps = 78 12:00:55 [INFO] train episode 17833: reward = -51.32, steps = 42 12:01:03 [INFO] train episode 17834: reward = -184.96, steps = 91 12:01:05 [INFO] train episode 17835: reward = -64.10, steps = 20 12:01:07 [INFO] train episode 17836: reward = -44.57, steps = 23 12:01:11 [INFO] train episode 17837: reward = -65.37, steps = 43 12:01:14 [INFO] train episode 17838: reward = -66.87, steps = 35 12:01:17 [INFO] train episode 17839: reward = -46.97, steps = 34 12:01:20 [INFO] train episode 17840: reward = -101.73, steps = 30 12:01:24 [INFO] train episode 17841: reward = -101.17, steps = 43 12:01:26 [INFO] train episode 17842: reward = -76.11, steps = 28 12:01:28 [INFO] train episode 17843: reward = -78.50, steps = 21 12:01:31 [INFO] train episode 17844: reward = -73.12, steps = 29 12:01:32 [INFO] train episode 17845: reward = -57.06, steps = 20 12:01:35 [INFO] train episode 17846: reward = -65.21, steps = 31 12:01:38 [INFO] train episode 17847: reward = -78.63, steps = 34 12:01:44 [INFO] train episode 17848: reward = -109.07, steps = 60 12:01:50 [INFO] train episode 17849: reward = -144.99, steps = 72 12:01:52 [INFO] train episode 17850: reward = -68.71, steps = 22 12:01:57 [INFO] train episode 17851: reward = -69.96, steps = 48 12:02:01 [INFO] train episode 17852: reward = -53.31, steps = 49 12:02:04 [INFO] train episode 17853: reward = -73.28, steps = 36 12:02:09 [INFO] train episode 17854: reward = -98.78, steps = 51 12:02:12 [INFO] train episode 17855: reward = -62.64, steps = 37 12:02:14 [INFO] train episode 17856: reward = -72.57, steps = 20 12:02:20 [INFO] train episode 17857: reward = -71.23, steps = 64 12:02:23 [INFO] train episode 17858: reward = -54.31, steps = 37 12:02:25 [INFO] train episode 17859: reward = -63.50, steps = 27 12:02:28 [INFO] train episode 17860: reward = -80.87, steps = 33 12:02:35 [INFO] train episode 17861: reward = -168.47, steps = 76 12:02:39 [INFO] train episode 17862: reward = -73.20, steps = 35 12:02:41 [INFO] train episode 17863: reward = -86.62, steps = 27 12:02:43 [INFO] train episode 17864: reward = -70.14, steps = 21 12:02:47 [INFO] train episode 17865: reward = -68.95, steps = 41 12:02:49 [INFO] train episode 17866: reward = -84.04, steps = 27 12:02:53 [INFO] train episode 17867: reward = -103.27, steps = 45 12:02:55 [INFO] train episode 17868: reward = -114.03, steps = 18 12:02:59 [INFO] train episode 17869: reward = -67.83, steps = 50 12:03:01 [INFO] train episode 17870: reward = -69.28, steps = 20 12:03:03 [INFO] train episode 17871: reward = -60.99, steps = 21 12:03:08 [INFO] train episode 17872: reward = -93.50, steps = 53 12:03:14 [INFO] train episode 17873: reward = -140.10, steps = 71 12:03:16 [INFO] train episode 17874: reward = -71.18, steps = 23 12:03:21 [INFO] train episode 17875: reward = -68.79, steps = 55 12:03:24 [INFO] train episode 17876: reward = -65.74, steps = 34 12:03:26 [INFO] train episode 17877: reward = -70.23, steps = 23 12:03:29 [INFO] train episode 17878: reward = -45.47, steps = 36 12:03:37 [INFO] train episode 17879: reward = -118.25, steps = 88 12:03:39 [INFO] train episode 17880: reward = -66.25, steps = 25 12:03:43 [INFO] train episode 17881: reward = -74.43, steps = 42 12:03:46 [INFO] train episode 17882: reward = -64.25, steps = 37 12:03:49 [INFO] train episode 17883: reward = -78.77, steps = 19 12:03:52 [INFO] train episode 17884: reward = -62.03, steps = 34 12:03:54 [INFO] train episode 17885: reward = -68.31, steps = 20 12:03:59 [INFO] train episode 17886: reward = -95.51, steps = 55 12:04:04 [INFO] train episode 17887: reward = -137.99, steps = 67 12:04:07 [INFO] train episode 17888: reward = -134.59, steps = 31 12:04:13 [INFO] train episode 17889: reward = -93.03, steps = 62 12:04:18 [INFO] train episode 17890: reward = -51.26, steps = 59 12:04:21 [INFO] train episode 17891: reward = -48.67, steps = 39 12:04:25 [INFO] train episode 17892: reward = -102.92, steps = 44 12:04:28 [INFO] train episode 17893: reward = -65.96, steps = 31 12:04:33 [INFO] train episode 17894: reward = -73.13, steps = 57 12:04:36 [INFO] train episode 17895: reward = -53.21, steps = 33 12:04:38 [INFO] train episode 17896: reward = -92.24, steps = 25 12:04:41 [INFO] train episode 17897: reward = -80.63, steps = 33 12:04:47 [INFO] train episode 17898: reward = -136.12, steps = 65 12:04:49 [INFO] train episode 17899: reward = -64.07, steps = 19 12:04:56 [INFO] train episode 17900: reward = -108.43, steps = 78 12:05:01 [INFO] train episode 17901: reward = -78.51, steps = 58 12:05:05 [INFO] train episode 17902: reward = -64.64, steps = 51 12:05:08 [INFO] train episode 17903: reward = -60.96, steps = 29 12:05:11 [INFO] train episode 17904: reward = -108.95, steps = 38 12:05:13 [INFO] train episode 17905: reward = -77.90, steps = 22 12:05:17 [INFO] train episode 17906: reward = -83.81, steps = 44 12:05:20 [INFO] train episode 17907: reward = -102.68, steps = 36 12:05:24 [INFO] train episode 17908: reward = -96.10, steps = 38 12:05:27 [INFO] train episode 17909: reward = -79.55, steps = 40 12:05:34 [INFO] train episode 17910: reward = -117.95, steps = 77 12:05:36 [INFO] train episode 17911: reward = -48.75, steps = 21 12:05:39 [INFO] train episode 17912: reward = -55.79, steps = 40 12:05:41 [INFO] train episode 17913: reward = -65.60, steps = 21 12:05:44 [INFO] train episode 17914: reward = -104.51, steps = 28 12:05:48 [INFO] train episode 17915: reward = -51.02, steps = 40 12:05:52 [INFO] train episode 17916: reward = -71.59, steps = 50 12:05:57 [INFO] train episode 17917: reward = -84.59, steps = 57 12:06:01 [INFO] train episode 17918: reward = -74.80, steps = 39 12:06:06 [INFO] train episode 17919: reward = -53.12, steps = 53 12:06:08 [INFO] train episode 17920: reward = -65.95, steps = 26 12:06:12 [INFO] train episode 17921: reward = -48.27, steps = 44 12:06:17 [INFO] train episode 17922: reward = -97.37, steps = 64 12:06:22 [INFO] train episode 17923: reward = -89.52, steps = 51 12:06:29 [INFO] train episode 17924: reward = -151.18, steps = 83 12:06:32 [INFO] train episode 17925: reward = -78.13, steps = 28 12:06:34 [INFO] train episode 17926: reward = -46.06, steps = 23 12:06:36 [INFO] train episode 17927: reward = -65.59, steps = 25 12:06:42 [INFO] train episode 17928: reward = -76.15, steps = 61 12:06:46 [INFO] train episode 17929: reward = -68.54, steps = 45 12:06:51 [INFO] train episode 17930: reward = -80.63, steps = 56 12:06:54 [INFO] train episode 17931: reward = -74.92, steps = 28 12:06:57 [INFO] train episode 17932: reward = -56.39, steps = 31 12:06:59 [INFO] train episode 17933: reward = -54.27, steps = 28 12:07:02 [INFO] train episode 17934: reward = -96.26, steps = 31 12:07:04 [INFO] train episode 17935: reward = -50.17, steps = 22 12:07:06 [INFO] train episode 17936: reward = -63.76, steps = 25 12:07:09 [INFO] train episode 17937: reward = -69.59, steps = 28 12:07:14 [INFO] train episode 17938: reward = -73.16, steps = 54 12:07:16 [INFO] train episode 17939: reward = -65.52, steps = 26 12:07:18 [INFO] train episode 17940: reward = -73.29, steps = 21 12:07:23 [INFO] train episode 17941: reward = -114.38, steps = 53 12:07:26 [INFO] train episode 17942: reward = -69.75, steps = 37 12:07:29 [INFO] train episode 17943: reward = -72.18, steps = 35 12:07:33 [INFO] train episode 17944: reward = -75.57, steps = 39 12:07:36 [INFO] train episode 17945: reward = -67.27, steps = 39 12:07:39 [INFO] train episode 17946: reward = -85.67, steps = 39 12:07:44 [INFO] train episode 17947: reward = -65.14, steps = 43 12:07:49 [INFO] train episode 17948: reward = -110.79, steps = 62 12:07:53 [INFO] train episode 17949: reward = -83.01, steps = 54 12:07:55 [INFO] train episode 17950: reward = -91.06, steps = 19 12:08:01 [INFO] train episode 17951: reward = -80.85, steps = 68 12:08:03 [INFO] train episode 17952: reward = -61.10, steps = 20 12:08:06 [INFO] train episode 17953: reward = -96.90, steps = 32 12:08:08 [INFO] train episode 17954: reward = -59.90, steps = 23 12:08:11 [INFO] train episode 17955: reward = -100.22, steps = 32 12:08:15 [INFO] train episode 17956: reward = -109.59, steps = 46 12:08:18 [INFO] train episode 17957: reward = -64.80, steps = 37 12:08:22 [INFO] train episode 17958: reward = -66.43, steps = 44 12:08:24 [INFO] train episode 17959: reward = -62.60, steps = 21 12:08:27 [INFO] train episode 17960: reward = -59.57, steps = 33 12:08:29 [INFO] train episode 17961: reward = -66.00, steps = 29 12:08:37 [INFO] train episode 17962: reward = -66.78, steps = 82 12:08:41 [INFO] train episode 17963: reward = -83.79, steps = 47 12:08:45 [INFO] train episode 17964: reward = -85.58, steps = 43 12:08:47 [INFO] train episode 17965: reward = -80.28, steps = 26 12:08:54 [INFO] train episode 17966: reward = -97.12, steps = 72 12:08:56 [INFO] train episode 17967: reward = -46.85, steps = 22 12:09:01 [INFO] train episode 17968: reward = -92.31, steps = 62 12:09:03 [INFO] train episode 17969: reward = -70.20, steps = 27 12:09:07 [INFO] train episode 17970: reward = -68.00, steps = 36 12:09:09 [INFO] train episode 17971: reward = -48.25, steps = 21 12:09:11 [INFO] train episode 17972: reward = -72.59, steps = 31 12:09:17 [INFO] train episode 17973: reward = -100.98, steps = 71 12:09:20 [INFO] train episode 17974: reward = -74.15, steps = 34 12:09:23 [INFO] train episode 17975: reward = -69.50, steps = 20 12:09:29 [INFO] train episode 17976: reward = -141.89, steps = 72 12:09:31 [INFO] train episode 17977: reward = -100.00, steps = 25 12:09:34 [INFO] train episode 17978: reward = -104.12, steps = 33 12:09:40 [INFO] train episode 17979: reward = -116.09, steps = 69 12:09:44 [INFO] train episode 17980: reward = -65.41, steps = 34 12:09:47 [INFO] train episode 17981: reward = -87.72, steps = 41 12:09:51 [INFO] train episode 17982: reward = -82.54, steps = 44 12:09:54 [INFO] train episode 17983: reward = -53.30, steps = 30 12:09:57 [INFO] train episode 17984: reward = -52.33, steps = 30 12:10:00 [INFO] train episode 17985: reward = -48.44, steps = 35 12:10:04 [INFO] train episode 17986: reward = -72.75, steps = 53 12:10:09 [INFO] train episode 17987: reward = -61.03, steps = 51 12:10:13 [INFO] train episode 17988: reward = -102.77, steps = 50 12:10:19 [INFO] train episode 17989: reward = -111.16, steps = 69 12:10:21 [INFO] train episode 17990: reward = -81.99, steps = 23 12:10:24 [INFO] train episode 17991: reward = -59.68, steps = 31 12:10:26 [INFO] train episode 17992: reward = -79.23, steps = 19 12:10:28 [INFO] train episode 17993: reward = -89.73, steps = 26 12:10:33 [INFO] train episode 17994: reward = -103.61, steps = 54 12:10:37 [INFO] train episode 17995: reward = -115.30, steps = 47 12:10:43 [INFO] train episode 17996: reward = -49.92, steps = 64 12:10:47 [INFO] train episode 17997: reward = -72.79, steps = 49 12:10:50 [INFO] train episode 17998: reward = -78.80, steps = 35 12:10:53 [INFO] train episode 17999: reward = -96.71, steps = 31 12:10:55 [INFO] train episode 18000: reward = -67.27, steps = 24 12:10:59 [INFO] train episode 18001: reward = -86.06, steps = 44 12:11:04 [INFO] train episode 18002: reward = -38.82, steps = 50 12:11:06 [INFO] train episode 18003: reward = -82.76, steps = 27 12:11:13 [INFO] train episode 18004: reward = -77.99, steps = 82 12:11:20 [INFO] train episode 18005: reward = -112.53, steps = 71 12:11:22 [INFO] train episode 18006: reward = -83.75, steps = 22 12:11:26 [INFO] train episode 18007: reward = -90.70, steps = 45 12:11:28 [INFO] train episode 18008: reward = -70.68, steps = 28 12:11:30 [INFO] train episode 18009: reward = -74.68, steps = 27 12:11:33 [INFO] train episode 18010: reward = -81.99, steps = 31 12:11:36 [INFO] train episode 18011: reward = -70.88, steps = 23 12:11:39 [INFO] train episode 18012: reward = -72.83, steps = 42 12:11:42 [INFO] train episode 18013: reward = -70.67, steps = 27 12:11:44 [INFO] train episode 18014: reward = -72.70, steps = 25 12:11:46 [INFO] train episode 18015: reward = -66.46, steps = 21 12:11:50 [INFO] train episode 18016: reward = -60.76, steps = 47 12:11:55 [INFO] train episode 18017: reward = -115.21, steps = 53 12:11:58 [INFO] train episode 18018: reward = -133.11, steps = 39 12:12:02 [INFO] train episode 18019: reward = -95.98, steps = 47 12:12:06 [INFO] train episode 18020: reward = -70.80, steps = 43 12:12:11 [INFO] train episode 18021: reward = -42.24, steps = 63 12:12:14 [INFO] train episode 18022: reward = -73.33, steps = 30 12:12:16 [INFO] train episode 18023: reward = -64.11, steps = 22 12:12:22 [INFO] train episode 18024: reward = -134.83, steps = 61 12:12:25 [INFO] train episode 18025: reward = -76.31, steps = 31 12:12:27 [INFO] train episode 18026: reward = -99.76, steps = 23 12:12:31 [INFO] train episode 18027: reward = -101.44, steps = 53 12:12:36 [INFO] train episode 18028: reward = -125.76, steps = 54 12:12:41 [INFO] train episode 18029: reward = -105.85, steps = 41 12:12:43 [INFO] train episode 18030: reward = -46.32, steps = 22 12:12:47 [INFO] train episode 18031: reward = -83.07, steps = 40 12:12:50 [INFO] train episode 18032: reward = -87.78, steps = 42 12:12:54 [INFO] train episode 18033: reward = -79.16, steps = 38 12:12:57 [INFO] train episode 18034: reward = -54.22, steps = 36 12:13:00 [INFO] train episode 18035: reward = -55.74, steps = 30 12:13:02 [INFO] train episode 18036: reward = -49.72, steps = 26 12:13:04 [INFO] train episode 18037: reward = -49.72, steps = 21 12:13:08 [INFO] train episode 18038: reward = -57.06, steps = 43 12:13:11 [INFO] train episode 18039: reward = -93.59, steps = 30 12:13:15 [INFO] train episode 18040: reward = -80.16, steps = 45 12:13:17 [INFO] train episode 18041: reward = -55.66, steps = 22 12:13:23 [INFO] train episode 18042: reward = -92.46, steps = 70 12:13:25 [INFO] train episode 18043: reward = -68.01, steps = 23 12:13:28 [INFO] train episode 18044: reward = -68.94, steps = 32 12:13:31 [INFO] train episode 18045: reward = -76.44, steps = 28 12:13:32 [INFO] train episode 18046: reward = -84.42, steps = 21 12:13:35 [INFO] train episode 18047: reward = -81.21, steps = 33 12:13:38 [INFO] train episode 18048: reward = -89.33, steps = 25 12:13:40 [INFO] train episode 18049: reward = -66.16, steps = 27 12:13:44 [INFO] train episode 18050: reward = -101.04, steps = 35 12:13:48 [INFO] train episode 18051: reward = -95.90, steps = 47 12:13:50 [INFO] train episode 18052: reward = -83.12, steps = 21 12:13:52 [INFO] train episode 18053: reward = -67.23, steps = 27 12:13:59 [INFO] train episode 18054: reward = -96.82, steps = 78 12:14:01 [INFO] train episode 18055: reward = -54.62, steps = 21 12:14:03 [INFO] train episode 18056: reward = -62.88, steps = 23 12:14:05 [INFO] train episode 18057: reward = -81.66, steps = 21 12:14:08 [INFO] train episode 18058: reward = -122.59, steps = 39 12:14:10 [INFO] train episode 18059: reward = -44.10, steps = 19 12:14:12 [INFO] train episode 18060: reward = -64.15, steps = 21 12:14:14 [INFO] train episode 18061: reward = -84.19, steps = 22 12:14:18 [INFO] train episode 18062: reward = -103.61, steps = 45 12:14:22 [INFO] train episode 18063: reward = -89.10, steps = 50 12:14:25 [INFO] train episode 18064: reward = -57.30, steps = 33 12:14:28 [INFO] train episode 18065: reward = -69.36, steps = 31 12:14:30 [INFO] train episode 18066: reward = -85.39, steps = 27 12:14:32 [INFO] train episode 18067: reward = -56.25, steps = 23 12:14:37 [INFO] train episode 18068: reward = -86.31, steps = 47 12:14:39 [INFO] train episode 18069: reward = -66.52, steps = 24 12:14:44 [INFO] train episode 18070: reward = -121.24, steps = 62 12:14:49 [INFO] train episode 18071: reward = -89.02, steps = 52 12:14:53 [INFO] train episode 18072: reward = -66.20, steps = 43 12:14:57 [INFO] train episode 18073: reward = -75.20, steps = 53 12:15:00 [INFO] train episode 18074: reward = -47.45, steps = 25 12:15:02 [INFO] train episode 18075: reward = -67.63, steps = 27 12:15:04 [INFO] train episode 18076: reward = -66.74, steps = 24 12:15:10 [INFO] train episode 18077: reward = -95.49, steps = 58 12:15:13 [INFO] train episode 18078: reward = -86.82, steps = 36 12:15:15 [INFO] train episode 18079: reward = -82.19, steps = 21 12:15:23 [INFO] train episode 18080: reward = -129.44, steps = 91 12:15:28 [INFO] train episode 18081: reward = -74.09, steps = 52 12:15:32 [INFO] train episode 18082: reward = -59.64, steps = 44 12:15:34 [INFO] train episode 18083: reward = -86.09, steps = 31 12:15:38 [INFO] train episode 18084: reward = -153.58, steps = 36 12:15:41 [INFO] train episode 18085: reward = -114.93, steps = 25 12:15:44 [INFO] train episode 18086: reward = -69.63, steps = 40 12:15:48 [INFO] train episode 18087: reward = -62.07, steps = 43 12:15:51 [INFO] train episode 18088: reward = -63.96, steps = 28 12:15:56 [INFO] train episode 18089: reward = -96.21, steps = 57 12:15:58 [INFO] train episode 18090: reward = -49.39, steps = 28 12:16:04 [INFO] train episode 18091: reward = -79.49, steps = 63 12:16:07 [INFO] train episode 18092: reward = -89.83, steps = 37 12:16:09 [INFO] train episode 18093: reward = -93.62, steps = 19 12:16:15 [INFO] train episode 18094: reward = -102.04, steps = 64 12:16:20 [INFO] train episode 18095: reward = -104.21, steps = 56 12:16:24 [INFO] train episode 18096: reward = -47.30, steps = 47 12:16:27 [INFO] train episode 18097: reward = -89.92, steps = 36 12:16:31 [INFO] train episode 18098: reward = -51.96, steps = 40 12:16:36 [INFO] train episode 18099: reward = -110.52, steps = 66 12:16:39 [INFO] train episode 18100: reward = -77.36, steps = 33 12:16:43 [INFO] train episode 18101: reward = -74.08, steps = 45 12:16:49 [INFO] train episode 18102: reward = -71.19, steps = 66 12:16:52 [INFO] train episode 18103: reward = -54.86, steps = 29 12:16:56 [INFO] train episode 18104: reward = -73.19, steps = 52 12:17:00 [INFO] train episode 18105: reward = -111.79, steps = 39 12:17:03 [INFO] train episode 18106: reward = -60.26, steps = 31 12:17:05 [INFO] train episode 18107: reward = -82.91, steps = 20 12:17:08 [INFO] train episode 18108: reward = -90.05, steps = 35 12:17:11 [INFO] train episode 18109: reward = -83.37, steps = 44 12:17:13 [INFO] train episode 18110: reward = -69.60, steps = 19 12:17:16 [INFO] train episode 18111: reward = -63.60, steps = 31 12:17:19 [INFO] train episode 18112: reward = -39.53, steps = 35 12:17:23 [INFO] train episode 18113: reward = -69.21, steps = 46 12:17:26 [INFO] train episode 18114: reward = -65.46, steps = 34 12:17:29 [INFO] train episode 18115: reward = -56.05, steps = 31 12:17:32 [INFO] train episode 18116: reward = -91.48, steps = 38 12:17:36 [INFO] train episode 18117: reward = -88.74, steps = 34 12:17:40 [INFO] train episode 18118: reward = -51.59, steps = 46 12:17:46 [INFO] train episode 18119: reward = -167.74, steps = 73 12:17:52 [INFO] train episode 18120: reward = -87.23, steps = 55 12:17:55 [INFO] train episode 18121: reward = -69.65, steps = 43 12:17:59 [INFO] train episode 18122: reward = -140.21, steps = 45 12:18:02 [INFO] train episode 18123: reward = -79.86, steps = 35 12:18:07 [INFO] train episode 18124: reward = -68.92, steps = 53 12:18:12 [INFO] train episode 18125: reward = -96.48, steps = 61 12:18:17 [INFO] train episode 18126: reward = -118.60, steps = 56 12:18:21 [INFO] train episode 18127: reward = -67.55, steps = 43 12:18:23 [INFO] train episode 18128: reward = -70.01, steps = 23 12:18:26 [INFO] train episode 18129: reward = -59.69, steps = 31 12:18:28 [INFO] train episode 18130: reward = -48.72, steps = 26 12:18:30 [INFO] train episode 18131: reward = -71.90, steps = 23 12:18:37 [INFO] train episode 18132: reward = -112.07, steps = 69 12:18:40 [INFO] train episode 18133: reward = -74.86, steps = 32 12:18:44 [INFO] train episode 18134: reward = -78.45, steps = 37 12:18:47 [INFO] train episode 18135: reward = -52.76, steps = 40 12:18:54 [INFO] train episode 18136: reward = -94.39, steps = 77 12:18:58 [INFO] train episode 18137: reward = -64.97, steps = 43 12:19:00 [INFO] train episode 18138: reward = -66.43, steps = 23 12:19:05 [INFO] train episode 18139: reward = -60.41, steps = 56 12:19:09 [INFO] train episode 18140: reward = -73.85, steps = 49 12:19:11 [INFO] train episode 18141: reward = -57.82, steps = 23 12:19:15 [INFO] train episode 18142: reward = -80.87, steps = 43 12:19:17 [INFO] train episode 18143: reward = -90.42, steps = 20 12:19:19 [INFO] train episode 18144: reward = -69.80, steps = 22 12:19:24 [INFO] train episode 18145: reward = -98.29, steps = 58 12:19:28 [INFO] train episode 18146: reward = -70.59, steps = 45 12:19:32 [INFO] train episode 18147: reward = -90.14, steps = 43 12:19:38 [INFO] train episode 18148: reward = -143.90, steps = 71 12:19:40 [INFO] train episode 18149: reward = -61.31, steps = 24 12:19:43 [INFO] train episode 18150: reward = -69.24, steps = 30 12:19:45 [INFO] train episode 18151: reward = -61.51, steps = 20 12:19:48 [INFO] train episode 18152: reward = -74.87, steps = 37 12:19:51 [INFO] train episode 18153: reward = -62.72, steps = 29 12:19:54 [INFO] train episode 18154: reward = -93.60, steps = 32 12:19:56 [INFO] train episode 18155: reward = -53.10, steps = 28 12:19:59 [INFO] train episode 18156: reward = -120.14, steps = 28 12:20:03 [INFO] train episode 18157: reward = -77.95, steps = 50 12:20:08 [INFO] train episode 18158: reward = -87.69, steps = 49 12:20:13 [INFO] train episode 18159: reward = -125.77, steps = 61 12:20:16 [INFO] train episode 18160: reward = -61.42, steps = 32 12:20:20 [INFO] train episode 18161: reward = -75.98, steps = 44 12:20:22 [INFO] train episode 18162: reward = -61.41, steps = 19 12:20:24 [INFO] train episode 18163: reward = -50.67, steps = 25 12:20:26 [INFO] train episode 18164: reward = -67.27, steps = 20 12:20:32 [INFO] train episode 18165: reward = -129.53, steps = 74 12:20:36 [INFO] train episode 18166: reward = -70.26, steps = 32 12:20:43 [INFO] train episode 18167: reward = -98.53, steps = 81 12:20:45 [INFO] train episode 18168: reward = -57.00, steps = 32 12:20:47 [INFO] train episode 18169: reward = -60.99, steps = 23 12:20:51 [INFO] train episode 18170: reward = -72.64, steps = 34 12:20:55 [INFO] train episode 18171: reward = -79.59, steps = 32 12:20:57 [INFO] train episode 18172: reward = -89.33, steps = 27 12:21:02 [INFO] train episode 18173: reward = -74.07, steps = 47 12:21:06 [INFO] train episode 18174: reward = -65.90, steps = 39 12:21:11 [INFO] train episode 18175: reward = -59.80, steps = 48 12:21:14 [INFO] train episode 18176: reward = -45.07, steps = 36 12:21:17 [INFO] train episode 18177: reward = -60.60, steps = 33 12:21:20 [INFO] train episode 18178: reward = -72.66, steps = 38 12:21:23 [INFO] train episode 18179: reward = -49.35, steps = 27 12:21:25 [INFO] train episode 18180: reward = -102.20, steps = 26 12:21:31 [INFO] train episode 18181: reward = -113.16, steps = 65 12:21:33 [INFO] train episode 18182: reward = -79.29, steps = 26 12:21:37 [INFO] train episode 18183: reward = -46.14, steps = 34 12:21:43 [INFO] train episode 18184: reward = -142.07, steps = 67 12:21:45 [INFO] train episode 18185: reward = -67.27, steps = 25 12:21:49 [INFO] train episode 18186: reward = -73.66, steps = 47 12:21:51 [INFO] train episode 18187: reward = -51.66, steps = 21 12:21:54 [INFO] train episode 18188: reward = -82.34, steps = 31 12:21:58 [INFO] train episode 18189: reward = -85.00, steps = 53 12:22:01 [INFO] train episode 18190: reward = -65.62, steps = 29 12:22:05 [INFO] train episode 18191: reward = -58.18, steps = 46 12:22:09 [INFO] train episode 18192: reward = -38.11, steps = 40 12:22:13 [INFO] train episode 18193: reward = -74.45, steps = 47 12:22:17 [INFO] train episode 18194: reward = -163.20, steps = 49 12:22:21 [INFO] train episode 18195: reward = -68.48, steps = 41 12:22:24 [INFO] train episode 18196: reward = -66.52, steps = 29 12:22:25 [INFO] train episode 18197: reward = -62.70, steps = 20 12:22:28 [INFO] train episode 18198: reward = -33.41, steps = 28 12:22:30 [INFO] train episode 18199: reward = -79.02, steps = 19 12:22:32 [INFO] train episode 18200: reward = -71.68, steps = 23 12:22:34 [INFO] train episode 18201: reward = -72.23, steps = 20 12:22:37 [INFO] train episode 18202: reward = -69.91, steps = 31 12:22:41 [INFO] train episode 18203: reward = -49.52, steps = 52 12:22:43 [INFO] train episode 18204: reward = -69.76, steps = 24 12:22:46 [INFO] train episode 18205: reward = -86.19, steps = 37 12:22:50 [INFO] train episode 18206: reward = -60.22, steps = 34 12:22:54 [INFO] train episode 18207: reward = -69.84, steps = 45 12:22:57 [INFO] train episode 18208: reward = -85.19, steps = 40 12:22:59 [INFO] train episode 18209: reward = -70.06, steps = 20 12:23:01 [INFO] train episode 18210: reward = -72.60, steps = 24 12:23:04 [INFO] train episode 18211: reward = -56.74, steps = 29 12:23:07 [INFO] train episode 18212: reward = -85.99, steps = 34 12:23:13 [INFO] train episode 18213: reward = -71.73, steps = 71 12:23:18 [INFO] train episode 18214: reward = -100.59, steps = 54 12:23:24 [INFO] train episode 18215: reward = -86.71, steps = 61 12:23:27 [INFO] train episode 18216: reward = -44.69, steps = 42 12:23:32 [INFO] train episode 18217: reward = -83.77, steps = 55 12:23:34 [INFO] train episode 18218: reward = -80.18, steps = 26 12:23:37 [INFO] train episode 18219: reward = -61.66, steps = 33 12:23:40 [INFO] train episode 18220: reward = -38.69, steps = 30 12:23:45 [INFO] train episode 18221: reward = -63.69, steps = 54 12:23:50 [INFO] train episode 18222: reward = -80.82, steps = 62 12:23:54 [INFO] train episode 18223: reward = -71.80, steps = 43 12:23:59 [INFO] train episode 18224: reward = -80.09, steps = 55 12:24:02 [INFO] train episode 18225: reward = -98.29, steps = 37 12:24:06 [INFO] train episode 18226: reward = -73.40, steps = 43 12:24:13 [INFO] train episode 18227: reward = -131.48, steps = 76 12:24:16 [INFO] train episode 18228: reward = -47.20, steps = 32 12:24:20 [INFO] train episode 18229: reward = -103.78, steps = 47 12:24:24 [INFO] train episode 18230: reward = -109.73, steps = 49 12:24:27 [INFO] train episode 18231: reward = -68.39, steps = 33 12:24:30 [INFO] train episode 18232: reward = -54.95, steps = 24 12:24:37 [INFO] train episode 18233: reward = -124.54, steps = 76 12:24:39 [INFO] train episode 18234: reward = -50.65, steps = 23 12:24:42 [INFO] train episode 18235: reward = -57.42, steps = 31 12:24:46 [INFO] train episode 18236: reward = -71.35, steps = 49 12:24:49 [INFO] train episode 18237: reward = -59.37, steps = 31 12:24:52 [INFO] train episode 18238: reward = -45.81, steps = 31 12:24:55 [INFO] train episode 18239: reward = -82.65, steps = 35 12:25:00 [INFO] train episode 18240: reward = -83.51, steps = 59 12:25:03 [INFO] train episode 18241: reward = -85.03, steps = 29 12:25:05 [INFO] train episode 18242: reward = -49.34, steps = 23 12:25:10 [INFO] train episode 18243: reward = -94.91, steps = 55 12:25:12 [INFO] train episode 18244: reward = -67.85, steps = 27 12:25:15 [INFO] train episode 18245: reward = -61.53, steps = 40 12:25:21 [INFO] train episode 18246: reward = -65.79, steps = 61 12:25:28 [INFO] train episode 18247: reward = -153.56, steps = 82 12:25:30 [INFO] train episode 18248: reward = -50.80, steps = 23 12:25:34 [INFO] train episode 18249: reward = -73.21, steps = 40 12:25:37 [INFO] train episode 18250: reward = -77.40, steps = 33 12:25:40 [INFO] train episode 18251: reward = -41.76, steps = 36 12:25:44 [INFO] train episode 18252: reward = -123.01, steps = 41 12:25:46 [INFO] train episode 18253: reward = -42.15, steps = 28 12:25:48 [INFO] train episode 18254: reward = -69.62, steps = 20 12:25:54 [INFO] train episode 18255: reward = -93.54, steps = 70 12:25:58 [INFO] train episode 18256: reward = -49.07, steps = 40 12:26:05 [INFO] train episode 18257: reward = -117.21, steps = 82 12:26:11 [INFO] train episode 18258: reward = -134.87, steps = 67 12:26:13 [INFO] train episode 18259: reward = -63.70, steps = 26 12:26:18 [INFO] train episode 18260: reward = -87.94, steps = 60 12:26:21 [INFO] train episode 18261: reward = -91.83, steps = 36 12:26:25 [INFO] train episode 18262: reward = -101.98, steps = 35 12:26:27 [INFO] train episode 18263: reward = -95.58, steps = 27 12:26:31 [INFO] train episode 18264: reward = -64.19, steps = 41 12:26:34 [INFO] train episode 18265: reward = -99.82, steps = 44 12:26:37 [INFO] train episode 18266: reward = -111.07, steps = 33 12:26:44 [INFO] train episode 18267: reward = -83.50, steps = 74 12:26:47 [INFO] train episode 18268: reward = -72.89, steps = 29 12:26:53 [INFO] train episode 18269: reward = -133.15, steps = 78 12:26:56 [INFO] train episode 18270: reward = -46.00, steps = 25 12:27:00 [INFO] train episode 18271: reward = -46.31, steps = 51 12:27:02 [INFO] train episode 18272: reward = -60.20, steps = 22 12:27:11 [INFO] train episode 18273: reward = -133.10, steps = 107 12:27:15 [INFO] train episode 18274: reward = -114.84, steps = 37 12:27:19 [INFO] train episode 18275: reward = -52.76, steps = 47 12:27:23 [INFO] train episode 18276: reward = -114.00, steps = 46 12:27:26 [INFO] train episode 18277: reward = -80.60, steps = 28 12:27:30 [INFO] train episode 18278: reward = -56.29, steps = 48 12:27:34 [INFO] train episode 18279: reward = -74.85, steps = 38 12:27:37 [INFO] train episode 18280: reward = -55.19, steps = 26 12:27:40 [INFO] train episode 18281: reward = -52.67, steps = 43 12:27:42 [INFO] train episode 18282: reward = -76.81, steps = 21 12:27:50 [INFO] train episode 18283: reward = -138.38, steps = 92 12:27:54 [INFO] train episode 18284: reward = -75.69, steps = 42 12:27:56 [INFO] train episode 18285: reward = -55.37, steps = 25 12:27:58 [INFO] train episode 18286: reward = -48.63, steps = 28 12:28:01 [INFO] train episode 18287: reward = -69.99, steps = 26 12:28:04 [INFO] train episode 18288: reward = -90.61, steps = 31 12:28:06 [INFO] train episode 18289: reward = -60.02, steps = 21 12:28:09 [INFO] train episode 18290: reward = -97.51, steps = 33 12:28:14 [INFO] train episode 18291: reward = -106.38, steps = 59 12:28:16 [INFO] train episode 18292: reward = -76.18, steps = 32 12:28:20 [INFO] train episode 18293: reward = -63.57, steps = 38 12:28:23 [INFO] train episode 18294: reward = -93.46, steps = 27 12:28:31 [INFO] train episode 18295: reward = -140.24, steps = 94 12:28:36 [INFO] train episode 18296: reward = -94.09, steps = 59 12:28:40 [INFO] train episode 18297: reward = -44.54, steps = 38 12:28:44 [INFO] train episode 18298: reward = -83.82, steps = 49 12:28:47 [INFO] train episode 18299: reward = -64.03, steps = 40 12:28:54 [INFO] train episode 18300: reward = -89.17, steps = 67 12:28:59 [INFO] train episode 18301: reward = -104.97, steps = 59 12:29:01 [INFO] train episode 18302: reward = -94.09, steps = 22 12:29:05 [INFO] train episode 18303: reward = -52.46, steps = 38 12:29:07 [INFO] train episode 18304: reward = -78.16, steps = 24 12:29:10 [INFO] train episode 18305: reward = -62.72, steps = 29 12:29:14 [INFO] train episode 18306: reward = -61.60, steps = 41 12:29:16 [INFO] train episode 18307: reward = -75.42, steps = 21 12:29:18 [INFO] train episode 18308: reward = -94.03, steps = 27 12:29:22 [INFO] train episode 18309: reward = -98.34, steps = 52 12:29:27 [INFO] train episode 18310: reward = -82.43, steps = 48 12:29:29 [INFO] train episode 18311: reward = -54.50, steps = 30 12:29:34 [INFO] train episode 18312: reward = -67.36, steps = 47 12:29:36 [INFO] train episode 18313: reward = -60.44, steps = 31 12:29:38 [INFO] train episode 18314: reward = -57.20, steps = 20 12:29:41 [INFO] train episode 18315: reward = -72.90, steps = 33 12:29:44 [INFO] train episode 18316: reward = -59.57, steps = 26 12:29:46 [INFO] train episode 18317: reward = -64.74, steps = 27 12:29:49 [INFO] train episode 18318: reward = -76.78, steps = 28 12:29:53 [INFO] train episode 18319: reward = -60.17, steps = 51 12:29:56 [INFO] train episode 18320: reward = -47.96, steps = 30 12:30:00 [INFO] train episode 18321: reward = -97.93, steps = 45 12:30:04 [INFO] train episode 18322: reward = -66.84, steps = 44 12:30:09 [INFO] train episode 18323: reward = -61.50, steps = 63 12:30:12 [INFO] train episode 18324: reward = -79.44, steps = 30 12:30:14 [INFO] train episode 18325: reward = -79.80, steps = 19 12:30:16 [INFO] train episode 18326: reward = -69.16, steps = 21 12:30:18 [INFO] train episode 18327: reward = -48.40, steps = 23 12:30:19 [INFO] train episode 18328: reward = -48.52, steps = 19 12:30:24 [INFO] train episode 18329: reward = -69.69, steps = 48 12:30:26 [INFO] train episode 18330: reward = -82.38, steps = 25 12:30:31 [INFO] train episode 18331: reward = -60.73, steps = 42 12:30:32 [INFO] train episode 18332: reward = -67.21, steps = 19 12:30:39 [INFO] train episode 18333: reward = -103.54, steps = 72 12:30:41 [INFO] train episode 18334: reward = -48.28, steps = 27 12:30:43 [INFO] train episode 18335: reward = -61.10, steps = 25 12:30:47 [INFO] train episode 18336: reward = -77.17, steps = 41 12:30:51 [INFO] train episode 18337: reward = -52.35, steps = 45 12:30:54 [INFO] train episode 18338: reward = -87.33, steps = 40 12:31:00 [INFO] train episode 18339: reward = -106.34, steps = 62 12:31:02 [INFO] train episode 18340: reward = -55.00, steps = 29 12:31:05 [INFO] train episode 18341: reward = -45.57, steps = 29 12:31:10 [INFO] train episode 18342: reward = -97.55, steps = 60 12:31:14 [INFO] train episode 18343: reward = -59.33, steps = 44 12:31:16 [INFO] train episode 18344: reward = -59.57, steps = 23 12:31:20 [INFO] train episode 18345: reward = -48.49, steps = 40 12:31:25 [INFO] train episode 18346: reward = -102.61, steps = 59 12:31:29 [INFO] train episode 18347: reward = -80.22, steps = 47 12:31:31 [INFO] train episode 18348: reward = -87.40, steps = 21 12:31:33 [INFO] train episode 18349: reward = -39.34, steps = 22 12:31:38 [INFO] train episode 18350: reward = -57.25, steps = 50 12:31:40 [INFO] train episode 18351: reward = -55.13, steps = 26 12:31:43 [INFO] train episode 18352: reward = -73.79, steps = 29 12:31:46 [INFO] train episode 18353: reward = -98.63, steps = 43 12:31:53 [INFO] train episode 18354: reward = -138.31, steps = 74 12:31:58 [INFO] train episode 18355: reward = -96.31, steps = 55 12:32:00 [INFO] train episode 18356: reward = -48.13, steps = 29 12:32:03 [INFO] train episode 18357: reward = -64.41, steps = 33 12:32:07 [INFO] train episode 18358: reward = -68.49, steps = 47 12:32:11 [INFO] train episode 18359: reward = -59.87, steps = 40 12:32:13 [INFO] train episode 18360: reward = -57.02, steps = 26 12:32:15 [INFO] train episode 18361: reward = -56.38, steps = 21 12:32:21 [INFO] train episode 18362: reward = -157.92, steps = 62 12:32:25 [INFO] train episode 18363: reward = -138.17, steps = 48 12:32:29 [INFO] train episode 18364: reward = -56.65, steps = 35 12:32:33 [INFO] train episode 18365: reward = -63.11, steps = 46 12:32:35 [INFO] train episode 18366: reward = -61.72, steps = 20 12:32:37 [INFO] train episode 18367: reward = -91.14, steps = 23 12:32:39 [INFO] train episode 18368: reward = -52.43, steps = 24 12:32:41 [INFO] train episode 18369: reward = -70.03, steps = 22 12:32:45 [INFO] train episode 18370: reward = -59.11, steps = 51 12:32:48 [INFO] train episode 18371: reward = -74.84, steps = 24 12:32:50 [INFO] train episode 18372: reward = -60.89, steps = 25 12:32:53 [INFO] train episode 18373: reward = -55.00, steps = 38 12:32:56 [INFO] train episode 18374: reward = -62.40, steps = 34 12:32:58 [INFO] train episode 18375: reward = -56.61, steps = 21 12:33:03 [INFO] train episode 18376: reward = -72.27, steps = 43 12:33:04 [INFO] train episode 18377: reward = -49.86, steps = 20 12:33:07 [INFO] train episode 18378: reward = -67.69, steps = 31 12:33:09 [INFO] train episode 18379: reward = -63.87, steps = 20 12:33:14 [INFO] train episode 18380: reward = -141.41, steps = 57 12:33:16 [INFO] train episode 18381: reward = -58.23, steps = 23 12:33:20 [INFO] train episode 18382: reward = -73.99, steps = 41 12:33:26 [INFO] train episode 18383: reward = -60.32, steps = 63 12:33:29 [INFO] train episode 18384: reward = -45.09, steps = 36 12:33:33 [INFO] train episode 18385: reward = -93.23, steps = 38 12:33:37 [INFO] train episode 18386: reward = -56.81, steps = 48 12:33:41 [INFO] train episode 18387: reward = -76.58, steps = 48 12:33:44 [INFO] train episode 18388: reward = -42.35, steps = 26 12:33:48 [INFO] train episode 18389: reward = -84.63, steps = 49 12:33:51 [INFO] train episode 18390: reward = -52.42, steps = 28 12:33:54 [INFO] train episode 18391: reward = -69.05, steps = 31 12:33:59 [INFO] train episode 18392: reward = -106.00, steps = 62 12:34:01 [INFO] train episode 18393: reward = -48.31, steps = 23 12:34:06 [INFO] train episode 18394: reward = -79.57, steps = 57 12:34:11 [INFO] train episode 18395: reward = -74.95, steps = 52 12:34:15 [INFO] train episode 18396: reward = -90.98, steps = 46 12:34:19 [INFO] train episode 18397: reward = -113.68, steps = 47 12:34:21 [INFO] train episode 18398: reward = -42.86, steps = 22 12:34:25 [INFO] train episode 18399: reward = -36.42, steps = 41 12:34:28 [INFO] train episode 18400: reward = -62.77, steps = 41 12:34:32 [INFO] train episode 18401: reward = -38.35, steps = 45 12:34:34 [INFO] train episode 18402: reward = -55.53, steps = 21 12:34:36 [INFO] train episode 18403: reward = -50.41, steps = 22 12:34:41 [INFO] train episode 18404: reward = -124.49, steps = 49 12:34:43 [INFO] train episode 18405: reward = -59.80, steps = 20 12:34:47 [INFO] train episode 18406: reward = -75.34, steps = 51 12:34:49 [INFO] train episode 18407: reward = -52.48, steps = 21 12:34:51 [INFO] train episode 18408: reward = -68.91, steps = 23 12:34:54 [INFO] train episode 18409: reward = -76.47, steps = 35 12:34:58 [INFO] train episode 18410: reward = -49.34, steps = 42 12:35:01 [INFO] train episode 18411: reward = -73.48, steps = 30 12:35:04 [INFO] train episode 18412: reward = -43.08, steps = 35 12:35:07 [INFO] train episode 18413: reward = -70.54, steps = 31 12:35:09 [INFO] train episode 18414: reward = -49.29, steps = 25 12:35:14 [INFO] train episode 18415: reward = -98.94, steps = 54 12:35:19 [INFO] train episode 18416: reward = -120.29, steps = 54 12:35:21 [INFO] train episode 18417: reward = -75.39, steps = 26 12:35:24 [INFO] train episode 18418: reward = -109.11, steps = 37 12:35:27 [INFO] train episode 18419: reward = -56.15, steps = 34 12:35:32 [INFO] train episode 18420: reward = -106.42, steps = 53 12:35:37 [INFO] train episode 18421: reward = -92.80, steps = 54 12:35:40 [INFO] train episode 18422: reward = -87.02, steps = 31 12:35:44 [INFO] train episode 18423: reward = -116.91, steps = 50 12:35:49 [INFO] train episode 18424: reward = -63.48, steps = 48 12:35:52 [INFO] train episode 18425: reward = -48.43, steps = 37 12:35:54 [INFO] train episode 18426: reward = -90.82, steps = 30 12:35:58 [INFO] train episode 18427: reward = -63.93, steps = 39 12:36:00 [INFO] train episode 18428: reward = -54.38, steps = 25 12:36:03 [INFO] train episode 18429: reward = -61.50, steps = 27 12:36:08 [INFO] train episode 18430: reward = -115.95, steps = 55 12:36:12 [INFO] train episode 18431: reward = -59.78, steps = 56 12:36:16 [INFO] train episode 18432: reward = -85.50, steps = 44 12:36:18 [INFO] train episode 18433: reward = -68.20, steps = 21 12:36:21 [INFO] train episode 18434: reward = -101.71, steps = 27 12:36:26 [INFO] train episode 18435: reward = -47.72, steps = 48 12:36:28 [INFO] train episode 18436: reward = -55.89, steps = 20 12:36:30 [INFO] train episode 18437: reward = -80.40, steps = 32 12:36:35 [INFO] train episode 18438: reward = -54.74, steps = 47 12:36:38 [INFO] train episode 18439: reward = -49.71, steps = 36 12:36:40 [INFO] train episode 18440: reward = -88.54, steps = 29 12:36:47 [INFO] train episode 18441: reward = -127.31, steps = 73 12:36:52 [INFO] train episode 18442: reward = -93.01, steps = 52 12:36:54 [INFO] train episode 18443: reward = -83.01, steps = 22 12:36:57 [INFO] train episode 18444: reward = -71.64, steps = 38 12:36:59 [INFO] train episode 18445: reward = -55.17, steps = 21 12:37:02 [INFO] train episode 18446: reward = -125.46, steps = 34 12:37:06 [INFO] train episode 18447: reward = -66.30, steps = 51 12:37:10 [INFO] train episode 18448: reward = -63.81, steps = 34 12:37:13 [INFO] train episode 18449: reward = -43.73, steps = 33 12:37:15 [INFO] train episode 18450: reward = -64.43, steps = 20 12:37:18 [INFO] train episode 18451: reward = -87.98, steps = 38 12:37:21 [INFO] train episode 18452: reward = -93.79, steps = 32 12:37:24 [INFO] train episode 18453: reward = -72.27, steps = 33 12:37:27 [INFO] train episode 18454: reward = -51.93, steps = 37 12:37:29 [INFO] train episode 18455: reward = -83.24, steps = 21 12:37:33 [INFO] train episode 18456: reward = -126.97, steps = 45 12:37:38 [INFO] train episode 18457: reward = -122.51, steps = 54 12:37:42 [INFO] train episode 18458: reward = -101.22, steps = 44 12:37:44 [INFO] train episode 18459: reward = -51.88, steps = 21 12:37:48 [INFO] train episode 18460: reward = -102.88, steps = 45 12:37:51 [INFO] train episode 18461: reward = -33.71, steps = 37 12:37:53 [INFO] train episode 18462: reward = -45.48, steps = 24 12:37:57 [INFO] train episode 18463: reward = -85.52, steps = 38 12:38:00 [INFO] train episode 18464: reward = -116.32, steps = 40 12:38:03 [INFO] train episode 18465: reward = -56.06, steps = 32 12:38:07 [INFO] train episode 18466: reward = -101.16, steps = 52 12:38:10 [INFO] train episode 18467: reward = -42.30, steps = 30 12:38:16 [INFO] train episode 18468: reward = -62.38, steps = 59 12:38:19 [INFO] train episode 18469: reward = -76.16, steps = 45 12:38:22 [INFO] train episode 18470: reward = -60.68, steps = 26 12:38:23 [INFO] train episode 18471: reward = -75.41, steps = 19 12:38:26 [INFO] train episode 18472: reward = -39.76, steps = 30 12:38:29 [INFO] train episode 18473: reward = -80.41, steps = 28 12:38:32 [INFO] train episode 18474: reward = -46.49, steps = 35 12:38:34 [INFO] train episode 18475: reward = -79.85, steps = 24 12:38:36 [INFO] train episode 18476: reward = -71.72, steps = 22 12:38:38 [INFO] train episode 18477: reward = -58.71, steps = 22 12:38:45 [INFO] train episode 18478: reward = -116.63, steps = 80 12:38:49 [INFO] train episode 18479: reward = -62.85, steps = 39 12:38:54 [INFO] train episode 18480: reward = -58.87, steps = 62 12:38:59 [INFO] train episode 18481: reward = -92.54, steps = 58 12:39:03 [INFO] train episode 18482: reward = -70.84, steps = 41 12:39:05 [INFO] train episode 18483: reward = -72.61, steps = 19 12:39:06 [INFO] train episode 18484: reward = -47.49, steps = 21 12:39:10 [INFO] train episode 18485: reward = -50.62, steps = 41 12:39:12 [INFO] train episode 18486: reward = -69.68, steps = 22 12:39:14 [INFO] train episode 18487: reward = -59.16, steps = 27 12:39:16 [INFO] train episode 18488: reward = -68.17, steps = 23 12:39:19 [INFO] train episode 18489: reward = -51.11, steps = 24 12:39:22 [INFO] train episode 18490: reward = -70.63, steps = 28 12:39:26 [INFO] train episode 18491: reward = -59.68, steps = 46 12:39:28 [INFO] train episode 18492: reward = -56.63, steps = 24 12:39:31 [INFO] train episode 18493: reward = -57.82, steps = 34 12:39:35 [INFO] train episode 18494: reward = -57.38, steps = 39 12:39:39 [INFO] train episode 18495: reward = -67.67, steps = 43 12:39:41 [INFO] train episode 18496: reward = -98.77, steps = 26 12:39:45 [INFO] train episode 18497: reward = -51.10, steps = 41 12:39:47 [INFO] train episode 18498: reward = -66.61, steps = 22 12:39:49 [INFO] train episode 18499: reward = -84.19, steps = 22 12:39:53 [INFO] train episode 18500: reward = -71.74, steps = 39 12:39:56 [INFO] train episode 18501: reward = -98.73, steps = 42 12:39:59 [INFO] train episode 18502: reward = -67.74, steps = 33 12:40:03 [INFO] train episode 18503: reward = -49.03, steps = 38 12:40:05 [INFO] train episode 18504: reward = -77.10, steps = 30 12:40:09 [INFO] train episode 18505: reward = -50.53, steps = 31 12:40:20 [INFO] train episode 18506: reward = -170.63, steps = 129 12:40:24 [INFO] train episode 18507: reward = -53.97, steps = 48 12:40:28 [INFO] train episode 18508: reward = -66.62, steps = 45 12:40:32 [INFO] train episode 18509: reward = -87.65, steps = 49 12:40:36 [INFO] train episode 18510: reward = -92.28, steps = 42 12:40:39 [INFO] train episode 18511: reward = -50.47, steps = 35 12:40:42 [INFO] train episode 18512: reward = -55.89, steps = 27 12:40:44 [INFO] train episode 18513: reward = -73.86, steps = 24 12:40:46 [INFO] train episode 18514: reward = -52.18, steps = 26 12:40:48 [INFO] train episode 18515: reward = -48.17, steps = 22 12:40:50 [INFO] train episode 18516: reward = -65.05, steps = 19 12:40:53 [INFO] train episode 18517: reward = -66.30, steps = 38 12:40:55 [INFO] train episode 18518: reward = -41.95, steps = 24 12:40:59 [INFO] train episode 18519: reward = -101.59, steps = 34 12:41:02 [INFO] train episode 18520: reward = -89.37, steps = 38 12:41:05 [INFO] train episode 18521: reward = -88.50, steps = 35 12:41:09 [INFO] train episode 18522: reward = -62.15, steps = 42 12:41:11 [INFO] train episode 18523: reward = -46.40, steps = 27 12:41:16 [INFO] train episode 18524: reward = -55.61, steps = 49 12:41:20 [INFO] train episode 18525: reward = -64.82, steps = 47 12:41:24 [INFO] train episode 18526: reward = -38.36, steps = 52 12:41:29 [INFO] train episode 18527: reward = -79.21, steps = 51 12:41:33 [INFO] train episode 18528: reward = -120.65, steps = 42 12:41:35 [INFO] train episode 18529: reward = -66.74, steps = 21 12:41:40 [INFO] train episode 18530: reward = -85.25, steps = 63 12:41:42 [INFO] train episode 18531: reward = -43.63, steps = 25 12:41:47 [INFO] train episode 18532: reward = -58.40, steps = 56 12:41:50 [INFO] train episode 18533: reward = -70.59, steps = 32 12:41:52 [INFO] train episode 18534: reward = -86.73, steps = 21 12:41:56 [INFO] train episode 18535: reward = -113.22, steps = 47 12:41:58 [INFO] train episode 18536: reward = -69.35, steps = 21 12:42:03 [INFO] train episode 18537: reward = -56.84, steps = 50 12:42:06 [INFO] train episode 18538: reward = -156.15, steps = 39 12:42:08 [INFO] train episode 18539: reward = -63.73, steps = 20 12:42:14 [INFO] train episode 18540: reward = -112.45, steps = 71 12:42:20 [INFO] train episode 18541: reward = -92.32, steps = 52 12:42:23 [INFO] train episode 18542: reward = -61.16, steps = 41 12:42:27 [INFO] train episode 18543: reward = -56.02, steps = 35 12:42:34 [INFO] train episode 18544: reward = -92.02, steps = 81 12:42:37 [INFO] train episode 18545: reward = -82.51, steps = 36 12:42:39 [INFO] train episode 18546: reward = -57.14, steps = 23 12:42:41 [INFO] train episode 18547: reward = -51.71, steps = 23 12:42:44 [INFO] train episode 18548: reward = -56.92, steps = 32 12:42:47 [INFO] train episode 18549: reward = -70.70, steps = 28 12:42:50 [INFO] train episode 18550: reward = -59.99, steps = 38 12:42:52 [INFO] train episode 18551: reward = -35.97, steps = 21 12:42:56 [INFO] train episode 18552: reward = -100.78, steps = 44 12:43:00 [INFO] train episode 18553: reward = -61.35, steps = 50 12:43:03 [INFO] train episode 18554: reward = -81.29, steps = 27 12:43:07 [INFO] train episode 18555: reward = -65.99, steps = 44 12:43:09 [INFO] train episode 18556: reward = -43.02, steps = 25 12:43:11 [INFO] train episode 18557: reward = -71.77, steps = 25 12:43:13 [INFO] train episode 18558: reward = -64.18, steps = 24 12:43:19 [INFO] train episode 18559: reward = -77.75, steps = 68 12:43:22 [INFO] train episode 18560: reward = -54.37, steps = 33 12:43:24 [INFO] train episode 18561: reward = -78.81, steps = 26 12:43:32 [INFO] train episode 18562: reward = -70.38, steps = 85 12:43:38 [INFO] train episode 18563: reward = -69.52, steps = 73 12:43:41 [INFO] train episode 18564: reward = -55.97, steps = 29 12:43:45 [INFO] train episode 18565: reward = -33.98, steps = 41 12:43:46 [INFO] train episode 18566: reward = -48.06, steps = 20 12:43:51 [INFO] train episode 18567: reward = -75.39, steps = 49 12:43:52 [INFO] train episode 18568: reward = -58.42, steps = 20 12:43:55 [INFO] train episode 18569: reward = -45.55, steps = 29 12:43:59 [INFO] train episode 18570: reward = -64.45, steps = 42 12:44:03 [INFO] train episode 18571: reward = -60.89, steps = 40 12:44:05 [INFO] train episode 18572: reward = -84.35, steps = 25 12:44:06 [INFO] train episode 18573: reward = -68.67, steps = 20 12:44:11 [INFO] train episode 18574: reward = -49.71, steps = 54 12:44:15 [INFO] train episode 18575: reward = -78.87, steps = 38 12:44:21 [INFO] train episode 18576: reward = -137.39, steps = 74 12:44:30 [INFO] train episode 18577: reward = -129.30, steps = 106 12:44:33 [INFO] train episode 18578: reward = -55.18, steps = 31 12:44:35 [INFO] train episode 18579: reward = -41.65, steps = 22 12:44:40 [INFO] train episode 18580: reward = -59.60, steps = 47 12:44:42 [INFO] train episode 18581: reward = -48.12, steps = 33 12:44:47 [INFO] train episode 18582: reward = -107.17, steps = 54 12:44:50 [INFO] train episode 18583: reward = -63.05, steps = 31 12:44:55 [INFO] train episode 18584: reward = -37.38, steps = 50 12:44:58 [INFO] train episode 18585: reward = -91.35, steps = 39 12:45:00 [INFO] train episode 18586: reward = -46.59, steps = 23 12:45:02 [INFO] train episode 18587: reward = -82.17, steps = 23 12:45:08 [INFO] train episode 18588: reward = -69.71, steps = 63 12:45:11 [INFO] train episode 18589: reward = -50.87, steps = 41 12:45:13 [INFO] train episode 18590: reward = -72.07, steps = 20 12:45:19 [INFO] train episode 18591: reward = -133.24, steps = 58 12:45:23 [INFO] train episode 18592: reward = -55.52, steps = 36 12:45:26 [INFO] train episode 18593: reward = -81.57, steps = 34 12:45:30 [INFO] train episode 18594: reward = -85.22, steps = 55 12:45:32 [INFO] train episode 18595: reward = -52.52, steps = 23 12:45:35 [INFO] train episode 18596: reward = -54.75, steps = 30 12:45:40 [INFO] train episode 18597: reward = -73.60, steps = 55 12:45:44 [INFO] train episode 18598: reward = -51.14, steps = 40 12:45:46 [INFO] train episode 18599: reward = -69.94, steps = 24 12:45:53 [INFO] train episode 18600: reward = -121.35, steps = 81 12:45:56 [INFO] train episode 18601: reward = -75.01, steps = 28 12:45:58 [INFO] train episode 18602: reward = -89.47, steps = 28 12:46:00 [INFO] train episode 18603: reward = -82.28, steps = 20 12:46:04 [INFO] train episode 18604: reward = -68.00, steps = 39 12:46:06 [INFO] train episode 18605: reward = -63.76, steps = 22 12:46:09 [INFO] train episode 18606: reward = -44.36, steps = 37 12:46:12 [INFO] train episode 18607: reward = -57.28, steps = 32 12:46:19 [INFO] train episode 18608: reward = -145.31, steps = 76 12:46:21 [INFO] train episode 18609: reward = -66.84, steps = 27 12:46:26 [INFO] train episode 18610: reward = -88.53, steps = 57 12:46:30 [INFO] train episode 18611: reward = -77.07, steps = 43 12:46:33 [INFO] train episode 18612: reward = -43.67, steps = 35 12:46:37 [INFO] train episode 18613: reward = -60.26, steps = 45 12:46:40 [INFO] train episode 18614: reward = -66.44, steps = 37 12:46:43 [INFO] train episode 18615: reward = -52.93, steps = 23 12:46:45 [INFO] train episode 18616: reward = -67.04, steps = 21 12:46:47 [INFO] train episode 18617: reward = -46.32, steps = 29 12:46:51 [INFO] train episode 18618: reward = -80.02, steps = 34 12:46:52 [INFO] train episode 18619: reward = -110.93, steps = 21 12:46:56 [INFO] train episode 18620: reward = -42.96, steps = 39 12:46:59 [INFO] train episode 18621: reward = -57.28, steps = 34 12:47:05 [INFO] train episode 18622: reward = -37.74, steps = 61 12:47:09 [INFO] train episode 18623: reward = -73.03, steps = 46 12:47:13 [INFO] train episode 18624: reward = -39.73, steps = 50 12:47:17 [INFO] train episode 18625: reward = -64.56, steps = 42 12:47:19 [INFO] train episode 18626: reward = -95.03, steps = 22 12:47:25 [INFO] train episode 18627: reward = -129.10, steps = 59 12:47:26 [INFO] train episode 18628: reward = -62.61, steps = 21 12:47:31 [INFO] train episode 18629: reward = -19.33, steps = 50 12:47:34 [INFO] train episode 18630: reward = -48.90, steps = 30 12:47:36 [INFO] train episode 18631: reward = -75.12, steps = 22 12:47:40 [INFO] train episode 18632: reward = -137.20, steps = 43 12:47:42 [INFO] train episode 18633: reward = -56.12, steps = 27 12:47:47 [INFO] train episode 18634: reward = -68.13, steps = 56 12:47:50 [INFO] train episode 18635: reward = -36.55, steps = 28 12:47:54 [INFO] train episode 18636: reward = -59.23, steps = 43 12:47:55 [INFO] train episode 18637: reward = -69.12, steps = 19 12:47:57 [INFO] train episode 18638: reward = -61.84, steps = 21 12:48:00 [INFO] train episode 18639: reward = -101.43, steps = 36 12:48:06 [INFO] train episode 18640: reward = -106.90, steps = 56 12:48:08 [INFO] train episode 18641: reward = -33.57, steps = 27 12:48:11 [INFO] train episode 18642: reward = -52.09, steps = 31 12:48:15 [INFO] train episode 18643: reward = -58.10, steps = 50 12:48:21 [INFO] train episode 18644: reward = -101.84, steps = 63 12:48:25 [INFO] train episode 18645: reward = -89.01, steps = 33 12:48:27 [INFO] train episode 18646: reward = -54.71, steps = 30 12:48:31 [INFO] train episode 18647: reward = -73.97, steps = 46 12:48:34 [INFO] train episode 18648: reward = -48.49, steps = 32 12:48:40 [INFO] train episode 18649: reward = -46.68, steps = 55 12:48:42 [INFO] train episode 18650: reward = -83.70, steps = 25 12:48:46 [INFO] train episode 18651: reward = -56.79, steps = 43 12:48:48 [INFO] train episode 18652: reward = -60.59, steps = 25 12:48:52 [INFO] train episode 18653: reward = -69.45, steps = 53 12:48:56 [INFO] train episode 18654: reward = -48.15, steps = 36 12:48:58 [INFO] train episode 18655: reward = -47.26, steps = 19 12:49:01 [INFO] train episode 18656: reward = -71.06, steps = 39 12:49:04 [INFO] train episode 18657: reward = -59.45, steps = 34 12:49:07 [INFO] train episode 18658: reward = -99.81, steps = 40 12:49:10 [INFO] train episode 18659: reward = -70.07, steps = 32 12:49:14 [INFO] train episode 18660: reward = -92.24, steps = 40 12:49:17 [INFO] train episode 18661: reward = -74.73, steps = 37 12:49:20 [INFO] train episode 18662: reward = -74.11, steps = 26 12:49:22 [INFO] train episode 18663: reward = -78.11, steps = 31 12:49:30 [INFO] train episode 18664: reward = -80.46, steps = 79 12:49:32 [INFO] train episode 18665: reward = -60.99, steps = 24 12:49:34 [INFO] train episode 18666: reward = -55.09, steps = 22 12:49:36 [INFO] train episode 18667: reward = -69.72, steps = 20 12:49:39 [INFO] train episode 18668: reward = -53.71, steps = 34 12:49:42 [INFO] train episode 18669: reward = -62.96, steps = 43 12:49:48 [INFO] train episode 18670: reward = -83.12, steps = 61 12:49:50 [INFO] train episode 18671: reward = -78.07, steps = 22 12:49:52 [INFO] train episode 18672: reward = -73.29, steps = 23 12:49:58 [INFO] train episode 18673: reward = -142.88, steps = 75 12:50:00 [INFO] train episode 18674: reward = -76.69, steps = 20 12:50:03 [INFO] train episode 18675: reward = -53.25, steps = 23 12:50:05 [INFO] train episode 18676: reward = -49.95, steps = 29 12:50:07 [INFO] train episode 18677: reward = -48.79, steps = 21 12:50:11 [INFO] train episode 18678: reward = -78.68, steps = 49 12:50:16 [INFO] train episode 18679: reward = -94.31, steps = 59 12:50:21 [INFO] train episode 18680: reward = -101.72, steps = 49 12:50:24 [INFO] train episode 18681: reward = -93.71, steps = 40 12:50:29 [INFO] train episode 18682: reward = -68.14, steps = 45 12:50:33 [INFO] train episode 18683: reward = -104.03, steps = 47 12:50:38 [INFO] train episode 18684: reward = -61.63, steps = 59 12:50:41 [INFO] train episode 18685: reward = -95.54, steps = 34 12:50:46 [INFO] train episode 18686: reward = -72.34, steps = 50 12:50:49 [INFO] train episode 18687: reward = -73.27, steps = 41 12:50:51 [INFO] train episode 18688: reward = -65.77, steps = 23 12:50:53 [INFO] train episode 18689: reward = -93.60, steps = 18 12:50:57 [INFO] train episode 18690: reward = -49.59, steps = 39 12:50:59 [INFO] train episode 18691: reward = -71.73, steps = 33 12:51:04 [INFO] train episode 18692: reward = -45.84, steps = 53 12:51:06 [INFO] train episode 18693: reward = -76.81, steps = 23 12:51:11 [INFO] train episode 18694: reward = -63.92, steps = 46 12:51:13 [INFO] train episode 18695: reward = -88.10, steps = 27 12:51:17 [INFO] train episode 18696: reward = -41.89, steps = 42 12:51:21 [INFO] train episode 18697: reward = -109.08, steps = 40 12:51:25 [INFO] train episode 18698: reward = -87.22, steps = 38 12:51:27 [INFO] train episode 18699: reward = -61.10, steps = 27 12:51:33 [INFO] train episode 18700: reward = -116.43, steps = 71 12:51:36 [INFO] train episode 18701: reward = -48.70, steps = 28 12:51:38 [INFO] train episode 18702: reward = -50.69, steps = 26 12:51:41 [INFO] train episode 18703: reward = -80.24, steps = 33 12:51:43 [INFO] train episode 18704: reward = -68.68, steps = 20 12:51:45 [INFO] train episode 18705: reward = -60.32, steps = 20 12:51:47 [INFO] train episode 18706: reward = -64.46, steps = 28 12:51:52 [INFO] train episode 18707: reward = -69.20, steps = 54 12:51:56 [INFO] train episode 18708: reward = -112.39, steps = 49 12:51:59 [INFO] train episode 18709: reward = -95.33, steps = 33 12:52:01 [INFO] train episode 18710: reward = -55.13, steps = 21 12:52:05 [INFO] train episode 18711: reward = -99.85, steps = 45 12:52:07 [INFO] train episode 18712: reward = -51.00, steps = 20 12:52:10 [INFO] train episode 18713: reward = -72.38, steps = 34 12:52:14 [INFO] train episode 18714: reward = -44.62, steps = 48 12:52:16 [INFO] train episode 18715: reward = -76.44, steps = 21 12:52:19 [INFO] train episode 18716: reward = -66.03, steps = 28 12:52:21 [INFO] train episode 18717: reward = -31.28, steps = 28 12:52:24 [INFO] train episode 18718: reward = -81.63, steps = 35 12:52:31 [INFO] train episode 18719: reward = -50.04, steps = 72 12:52:35 [INFO] train episode 18720: reward = -90.48, steps = 52 12:52:38 [INFO] train episode 18721: reward = -66.87, steps = 26 12:52:43 [INFO] train episode 18722: reward = -56.33, steps = 60 12:52:47 [INFO] train episode 18723: reward = -71.17, steps = 45 12:52:50 [INFO] train episode 18724: reward = -59.35, steps = 36 12:52:54 [INFO] train episode 18725: reward = -90.35, steps = 50 12:52:58 [INFO] train episode 18726: reward = -47.87, steps = 44 12:53:03 [INFO] train episode 18727: reward = -51.47, steps = 46 12:53:04 [INFO] train episode 18728: reward = -68.89, steps = 21 12:53:09 [INFO] train episode 18729: reward = -84.31, steps = 47 12:53:10 [INFO] train episode 18730: reward = -59.35, steps = 22 12:53:12 [INFO] train episode 18731: reward = -65.22, steps = 21 12:53:15 [INFO] train episode 18732: reward = -84.82, steps = 36 12:53:21 [INFO] train episode 18733: reward = -68.61, steps = 58 12:53:25 [INFO] train episode 18734: reward = -75.62, steps = 52 12:53:29 [INFO] train episode 18735: reward = -145.75, steps = 44 12:53:32 [INFO] train episode 18736: reward = -79.34, steps = 31 12:53:37 [INFO] train episode 18737: reward = -101.63, steps = 54 12:53:39 [INFO] train episode 18738: reward = -113.57, steps = 25 12:53:43 [INFO] train episode 18739: reward = -60.82, steps = 54 12:53:45 [INFO] train episode 18740: reward = -68.01, steps = 21 12:53:48 [INFO] train episode 18741: reward = -96.11, steps = 34 12:53:51 [INFO] train episode 18742: reward = -53.52, steps = 25 12:53:53 [INFO] train episode 18743: reward = -51.55, steps = 27 12:53:57 [INFO] train episode 18744: reward = -76.51, steps = 40 12:53:59 [INFO] train episode 18745: reward = -67.37, steps = 24 12:54:03 [INFO] train episode 18746: reward = -84.72, steps = 52 12:54:07 [INFO] train episode 18747: reward = -64.41, steps = 33 12:54:15 [INFO] train episode 18748: reward = -170.06, steps = 89 12:54:17 [INFO] train episode 18749: reward = -51.66, steps = 23 12:54:20 [INFO] train episode 18750: reward = -41.33, steps = 38 12:54:24 [INFO] train episode 18751: reward = -75.81, steps = 37 12:54:27 [INFO] train episode 18752: reward = -64.45, steps = 32 12:54:30 [INFO] train episode 18753: reward = -96.32, steps = 45 12:54:32 [INFO] train episode 18754: reward = -58.36, steps = 23 12:54:36 [INFO] train episode 18755: reward = -98.75, steps = 46 12:54:40 [INFO] train episode 18756: reward = -46.74, steps = 37 12:54:44 [INFO] train episode 18757: reward = -49.32, steps = 45 12:54:48 [INFO] train episode 18758: reward = -88.11, steps = 46 12:54:52 [INFO] train episode 18759: reward = -108.28, steps = 50 12:54:54 [INFO] train episode 18760: reward = -68.16, steps = 22 12:54:59 [INFO] train episode 18761: reward = -80.35, steps = 50 12:55:03 [INFO] train episode 18762: reward = -57.41, steps = 47 12:55:07 [INFO] train episode 18763: reward = -53.60, steps = 45 12:55:09 [INFO] train episode 18764: reward = -71.64, steps = 26 12:55:11 [INFO] train episode 18765: reward = -57.46, steps = 21 12:55:14 [INFO] train episode 18766: reward = -50.80, steps = 29 12:55:18 [INFO] train episode 18767: reward = -91.11, steps = 49 12:55:21 [INFO] train episode 18768: reward = -65.27, steps = 34 12:55:27 [INFO] train episode 18769: reward = -52.27, steps = 73 12:55:32 [INFO] train episode 18770: reward = -54.16, steps = 53 12:55:36 [INFO] train episode 18771: reward = -80.63, steps = 49 12:55:39 [INFO] train episode 18772: reward = -111.23, steps = 29 12:55:44 [INFO] train episode 18773: reward = -135.39, steps = 60 12:55:50 [INFO] train episode 18774: reward = -112.02, steps = 68 12:55:54 [INFO] train episode 18775: reward = -62.11, steps = 38 12:55:59 [INFO] train episode 18776: reward = -103.31, steps = 64 12:56:01 [INFO] train episode 18777: reward = -74.91, steps = 20 12:56:06 [INFO] train episode 18778: reward = -86.05, steps = 60 12:56:09 [INFO] train episode 18779: reward = -71.18, steps = 31 12:56:11 [INFO] train episode 18780: reward = -48.22, steps = 24 12:56:14 [INFO] train episode 18781: reward = -44.98, steps = 37 12:56:18 [INFO] train episode 18782: reward = -62.64, steps = 41 12:56:20 [INFO] train episode 18783: reward = -66.93, steps = 20 12:56:23 [INFO] train episode 18784: reward = -62.12, steps = 36 12:56:29 [INFO] train episode 18785: reward = -104.05, steps = 65 12:56:31 [INFO] train episode 18786: reward = -79.83, steps = 28 12:56:35 [INFO] train episode 18787: reward = -114.51, steps = 38 12:56:37 [INFO] train episode 18788: reward = -55.53, steps = 26 12:56:39 [INFO] train episode 18789: reward = -83.57, steps = 23 12:56:42 [INFO] train episode 18790: reward = -101.71, steps = 33 12:56:44 [INFO] train episode 18791: reward = -54.05, steps = 27 12:56:46 [INFO] train episode 18792: reward = -74.31, steps = 21 12:56:49 [INFO] train episode 18793: reward = -60.82, steps = 31 12:56:52 [INFO] train episode 18794: reward = -59.81, steps = 35 12:56:55 [INFO] train episode 18795: reward = -42.28, steps = 24 12:56:57 [INFO] train episode 18796: reward = -70.53, steps = 31 12:57:01 [INFO] train episode 18797: reward = -101.81, steps = 40 12:57:03 [INFO] train episode 18798: reward = -81.04, steps = 22 12:57:10 [INFO] train episode 18799: reward = -109.71, steps = 74 12:57:12 [INFO] train episode 18800: reward = -68.85, steps = 25 12:57:17 [INFO] train episode 18801: reward = -53.85, steps = 52 12:57:22 [INFO] train episode 18802: reward = -77.08, steps = 60 12:57:28 [INFO] train episode 18803: reward = -97.05, steps = 61 12:57:30 [INFO] train episode 18804: reward = -65.31, steps = 22 12:57:32 [INFO] train episode 18805: reward = -55.61, steps = 23 12:57:36 [INFO] train episode 18806: reward = -52.01, steps = 46 12:57:39 [INFO] train episode 18807: reward = -61.59, steps = 37 12:57:43 [INFO] train episode 18808: reward = -51.54, steps = 39 12:57:47 [INFO] train episode 18809: reward = -65.87, steps = 48 12:57:50 [INFO] train episode 18810: reward = -67.14, steps = 36 12:57:52 [INFO] train episode 18811: reward = -90.29, steps = 27 12:57:57 [INFO] train episode 18812: reward = -125.94, steps = 47 12:57:59 [INFO] train episode 18813: reward = -52.35, steps = 27 12:58:03 [INFO] train episode 18814: reward = -73.68, steps = 49 12:58:06 [INFO] train episode 18815: reward = -85.12, steps = 38 12:58:09 [INFO] train episode 18816: reward = -65.17, steps = 27 12:58:14 [INFO] train episode 18817: reward = -68.76, steps = 53 12:58:16 [INFO] train episode 18818: reward = -47.36, steps = 29 12:58:19 [INFO] train episode 18819: reward = -60.86, steps = 30 12:58:21 [INFO] train episode 18820: reward = -50.67, steps = 19 12:58:23 [INFO] train episode 18821: reward = -104.52, steps = 32 12:58:26 [INFO] train episode 18822: reward = -44.79, steps = 26 12:58:29 [INFO] train episode 18823: reward = -106.94, steps = 36 12:58:33 [INFO] train episode 18824: reward = -58.27, steps = 49 12:58:37 [INFO] train episode 18825: reward = -100.42, steps = 44 12:58:40 [INFO] train episode 18826: reward = -50.53, steps = 29 12:58:45 [INFO] train episode 18827: reward = -68.19, steps = 55 12:58:49 [INFO] train episode 18828: reward = -55.30, steps = 42 12:58:50 [INFO] train episode 18829: reward = -48.31, steps = 22 12:58:54 [INFO] train episode 18830: reward = -48.35, steps = 44 12:58:58 [INFO] train episode 18831: reward = -137.76, steps = 39 12:59:00 [INFO] train episode 18832: reward = -72.66, steps = 30 12:59:09 [INFO] train episode 18833: reward = -155.66, steps = 92 12:59:11 [INFO] train episode 18834: reward = -49.39, steps = 27 12:59:14 [INFO] train episode 18835: reward = -75.95, steps = 36 12:59:18 [INFO] train episode 18836: reward = -63.99, steps = 42 12:59:21 [INFO] train episode 18837: reward = -60.85, steps = 33 12:59:25 [INFO] train episode 18838: reward = -102.11, steps = 46 12:59:30 [INFO] train episode 18839: reward = -105.04, steps = 67 12:59:32 [INFO] train episode 18840: reward = -50.20, steps = 20 12:59:36 [INFO] train episode 18841: reward = -64.46, steps = 44 12:59:40 [INFO] train episode 18842: reward = -39.22, steps = 40 12:59:44 [INFO] train episode 18843: reward = -82.14, steps = 48 12:59:47 [INFO] train episode 18844: reward = -74.44, steps = 30 12:59:50 [INFO] train episode 18845: reward = -71.74, steps = 30 12:59:52 [INFO] train episode 18846: reward = -90.53, steps = 29 12:59:57 [INFO] train episode 18847: reward = -89.08, steps = 53 13:00:00 [INFO] train episode 18848: reward = -85.88, steps = 36 13:00:02 [INFO] train episode 18849: reward = -68.75, steps = 30 13:00:07 [INFO] train episode 18850: reward = -59.57, steps = 38 13:00:09 [INFO] train episode 18851: reward = -49.93, steps = 24 13:00:11 [INFO] train episode 18852: reward = -80.05, steps = 25 13:00:15 [INFO] train episode 18853: reward = -66.47, steps = 44 13:00:17 [INFO] train episode 18854: reward = -117.99, steps = 25 13:00:21 [INFO] train episode 18855: reward = -115.57, steps = 39 13:00:27 [INFO] train episode 18856: reward = -181.58, steps = 68 13:00:32 [INFO] train episode 18857: reward = -91.77, steps = 55 13:00:37 [INFO] train episode 18858: reward = -50.99, steps = 54 13:00:40 [INFO] train episode 18859: reward = -78.18, steps = 32 13:00:45 [INFO] train episode 18860: reward = -66.89, steps = 54 13:00:49 [INFO] train episode 18861: reward = -79.54, steps = 45 13:00:51 [INFO] train episode 18862: reward = -100.27, steps = 25 13:00:53 [INFO] train episode 18863: reward = -56.81, steps = 26 13:01:00 [INFO] train episode 18864: reward = -67.89, steps = 74 13:01:02 [INFO] train episode 18865: reward = -61.63, steps = 26 13:01:04 [INFO] train episode 18866: reward = -65.97, steps = 18 13:01:08 [INFO] train episode 18867: reward = -70.23, steps = 43 13:01:12 [INFO] train episode 18868: reward = -44.48, steps = 51 13:01:18 [INFO] train episode 18869: reward = -47.25, steps = 60 13:01:20 [INFO] train episode 18870: reward = -66.55, steps = 24 13:01:22 [INFO] train episode 18871: reward = -44.14, steps = 24 13:01:24 [INFO] train episode 18872: reward = -68.33, steps = 21 13:01:26 [INFO] train episode 18873: reward = -55.72, steps = 29 13:01:32 [INFO] train episode 18874: reward = -86.56, steps = 64 13:01:34 [INFO] train episode 18875: reward = -114.95, steps = 29 13:01:37 [INFO] train episode 18876: reward = -49.22, steps = 23 13:01:39 [INFO] train episode 18877: reward = -87.64, steps = 30 13:01:43 [INFO] train episode 18878: reward = -51.89, steps = 42 13:01:49 [INFO] train episode 18879: reward = -119.37, steps = 62 13:01:52 [INFO] train episode 18880: reward = -57.45, steps = 46 13:01:57 [INFO] train episode 18881: reward = -74.75, steps = 51 13:02:04 [INFO] train episode 18882: reward = -164.64, steps = 83 13:02:06 [INFO] train episode 18883: reward = -82.68, steps = 20 13:02:10 [INFO] train episode 18884: reward = -112.64, steps = 48 13:02:15 [INFO] train episode 18885: reward = -47.83, steps = 53 13:02:18 [INFO] train episode 18886: reward = -59.18, steps = 31 13:02:20 [INFO] train episode 18887: reward = -59.04, steps = 21 13:02:22 [INFO] train episode 18888: reward = -36.40, steps = 28 13:02:29 [INFO] train episode 18889: reward = -120.48, steps = 83 13:02:32 [INFO] train episode 18890: reward = -60.89, steps = 29 13:02:35 [INFO] train episode 18891: reward = -101.02, steps = 27 13:02:37 [INFO] train episode 18892: reward = -76.48, steps = 29 13:02:41 [INFO] train episode 18893: reward = -77.25, steps = 36 13:02:45 [INFO] train episode 18894: reward = -87.37, steps = 53 13:02:47 [INFO] train episode 18895: reward = -76.97, steps = 22 13:02:50 [INFO] train episode 18896: reward = -71.51, steps = 26 13:02:52 [INFO] train episode 18897: reward = -65.66, steps = 24 13:02:58 [INFO] train episode 18898: reward = -106.04, steps = 58 13:03:00 [INFO] train episode 18899: reward = -65.69, steps = 20 13:03:03 [INFO] train episode 18900: reward = -82.76, steps = 28 13:03:05 [INFO] train episode 18901: reward = -46.77, steps = 20 13:03:06 [INFO] train episode 18902: reward = -51.66, steps = 21 13:03:09 [INFO] train episode 18903: reward = -65.15, steps = 19 13:03:11 [INFO] train episode 18904: reward = -69.26, steps = 24 13:03:14 [INFO] train episode 18905: reward = -36.19, steps = 44 13:03:16 [INFO] train episode 18906: reward = -63.23, steps = 19 13:03:19 [INFO] train episode 18907: reward = -41.58, steps = 31 13:03:24 [INFO] train episode 18908: reward = -43.80, steps = 59 13:03:27 [INFO] train episode 18909: reward = -58.87, steps = 32 13:03:30 [INFO] train episode 18910: reward = -71.73, steps = 38 13:03:37 [INFO] train episode 18911: reward = -159.88, steps = 72 13:03:41 [INFO] train episode 18912: reward = -133.93, steps = 49 13:03:45 [INFO] train episode 18913: reward = -63.09, steps = 43 13:03:47 [INFO] train episode 18914: reward = -79.46, steps = 23 13:03:49 [INFO] train episode 18915: reward = -61.53, steps = 25 13:03:53 [INFO] train episode 18916: reward = -77.13, steps = 40 13:03:55 [INFO] train episode 18917: reward = -77.87, steps = 30 13:04:01 [INFO] train episode 18918: reward = -116.24, steps = 59 13:04:05 [INFO] train episode 18919: reward = -50.02, steps = 43 13:04:07 [INFO] train episode 18920: reward = -31.50, steps = 31 13:04:12 [INFO] train episode 18921: reward = -83.25, steps = 52 13:04:17 [INFO] train episode 18922: reward = -83.71, steps = 57 13:04:22 [INFO] train episode 18923: reward = -128.31, steps = 61 13:04:25 [INFO] train episode 18924: reward = -52.06, steps = 29 13:04:27 [INFO] train episode 18925: reward = -59.60, steps = 23 13:04:31 [INFO] train episode 18926: reward = -73.86, steps = 41 13:04:35 [INFO] train episode 18927: reward = -78.26, steps = 43 13:04:39 [INFO] train episode 18928: reward = -86.69, steps = 40 13:04:42 [INFO] train episode 18929: reward = -75.74, steps = 43 13:04:48 [INFO] train episode 18930: reward = -153.09, steps = 57 13:04:52 [INFO] train episode 18931: reward = -82.54, steps = 54 13:04:56 [INFO] train episode 18932: reward = -65.98, steps = 38 13:04:59 [INFO] train episode 18933: reward = -69.79, steps = 40 13:05:04 [INFO] train episode 18934: reward = -70.57, steps = 54 13:05:09 [INFO] train episode 18935: reward = -71.24, steps = 51 13:05:10 [INFO] train episode 18936: reward = -66.44, steps = 20 13:05:14 [INFO] train episode 18937: reward = -75.30, steps = 35 13:05:16 [INFO] train episode 18938: reward = -45.23, steps = 23 13:05:17 [INFO] train episode 18939: reward = -44.68, steps = 20 13:05:20 [INFO] train episode 18940: reward = -61.27, steps = 23 13:05:22 [INFO] train episode 18941: reward = -66.75, steps = 26 13:05:26 [INFO] train episode 18942: reward = -128.87, steps = 43 13:05:30 [INFO] train episode 18943: reward = -89.24, steps = 50 13:05:32 [INFO] train episode 18944: reward = -53.03, steps = 23 13:05:36 [INFO] train episode 18945: reward = -120.03, steps = 38 13:05:39 [INFO] train episode 18946: reward = -92.10, steps = 31 13:05:41 [INFO] train episode 18947: reward = -58.65, steps = 20 13:05:44 [INFO] train episode 18948: reward = -49.22, steps = 42 13:05:49 [INFO] train episode 18949: reward = -51.24, steps = 51 13:05:53 [INFO] train episode 18950: reward = -97.23, steps = 47 13:05:57 [INFO] train episode 18951: reward = -68.03, steps = 37 13:06:01 [INFO] train episode 18952: reward = -69.61, steps = 40 13:06:03 [INFO] train episode 18953: reward = -58.91, steps = 21 13:06:07 [INFO] train episode 18954: reward = -70.99, steps = 45 13:06:11 [INFO] train episode 18955: reward = -69.29, steps = 48 13:06:14 [INFO] train episode 18956: reward = -79.97, steps = 34 13:06:18 [INFO] train episode 18957: reward = -50.35, steps = 39 13:06:23 [INFO] train episode 18958: reward = -84.07, steps = 64 13:06:28 [INFO] train episode 18959: reward = -77.84, steps = 54 13:06:33 [INFO] train episode 18960: reward = -87.90, steps = 58 13:06:36 [INFO] train episode 18961: reward = -67.44, steps = 30 13:06:38 [INFO] train episode 18962: reward = -78.06, steps = 31 13:06:41 [INFO] train episode 18963: reward = -69.36, steps = 25 13:06:45 [INFO] train episode 18964: reward = -43.58, steps = 40 13:06:47 [INFO] train episode 18965: reward = -74.70, steps = 29 13:06:50 [INFO] train episode 18966: reward = -23.87, steps = 31 13:06:53 [INFO] train episode 18967: reward = -61.47, steps = 36 13:06:56 [INFO] train episode 18968: reward = -65.97, steps = 31 13:07:00 [INFO] train episode 18969: reward = -38.17, steps = 48 13:07:03 [INFO] train episode 18970: reward = -61.22, steps = 25 13:07:06 [INFO] train episode 18971: reward = -70.19, steps = 34 13:07:12 [INFO] train episode 18972: reward = -85.46, steps = 76 13:07:14 [INFO] train episode 18973: reward = -71.57, steps = 24 13:07:18 [INFO] train episode 18974: reward = -36.34, steps = 39 13:07:21 [INFO] train episode 18975: reward = -63.41, steps = 37 13:07:26 [INFO] train episode 18976: reward = -67.58, steps = 52 13:07:32 [INFO] train episode 18977: reward = -101.07, steps = 70 13:07:34 [INFO] train episode 18978: reward = -56.70, steps = 25 13:07:36 [INFO] train episode 18979: reward = -67.05, steps = 21 13:07:40 [INFO] train episode 18980: reward = -58.85, steps = 44 13:07:43 [INFO] train episode 18981: reward = -96.61, steps = 27 13:07:45 [INFO] train episode 18982: reward = -39.62, steps = 31 13:07:49 [INFO] train episode 18983: reward = -72.43, steps = 43 13:07:53 [INFO] train episode 18984: reward = -130.46, steps = 39 13:07:55 [INFO] train episode 18985: reward = -58.37, steps = 31 13:07:57 [INFO] train episode 18986: reward = -76.72, steps = 22 13:08:00 [INFO] train episode 18987: reward = -41.15, steps = 36 13:08:04 [INFO] train episode 18988: reward = -82.08, steps = 41 13:08:06 [INFO] train episode 18989: reward = -56.97, steps = 22 13:08:10 [INFO] train episode 18990: reward = -68.98, steps = 38 13:08:14 [INFO] train episode 18991: reward = -75.27, steps = 54 13:08:20 [INFO] train episode 18992: reward = -110.82, steps = 63 13:08:26 [INFO] train episode 18993: reward = -116.02, steps = 68 13:08:28 [INFO] train episode 18994: reward = -65.33, steps = 28 13:08:32 [INFO] train episode 18995: reward = -54.90, steps = 42 13:08:34 [INFO] train episode 18996: reward = -52.60, steps = 20 13:08:35 [INFO] train episode 18997: reward = -51.25, steps = 21 13:08:39 [INFO] train episode 18998: reward = -62.99, steps = 39 13:08:44 [INFO] train episode 18999: reward = -68.87, steps = 52 13:08:46 [INFO] train episode 19000: reward = -73.78, steps = 25 13:08:50 [INFO] train episode 19001: reward = -95.20, steps = 43 13:08:52 [INFO] train episode 19002: reward = -57.78, steps = 27 13:08:55 [INFO] train episode 19003: reward = -97.20, steps = 23 13:08:58 [INFO] train episode 19004: reward = -49.39, steps = 26 13:09:00 [INFO] train episode 19005: reward = -63.39, steps = 29 13:09:02 [INFO] train episode 19006: reward = -79.40, steps = 25 13:09:06 [INFO] train episode 19007: reward = -65.84, steps = 48 13:09:08 [INFO] train episode 19008: reward = -83.41, steps = 22 13:09:11 [INFO] train episode 19009: reward = -71.87, steps = 27 13:09:13 [INFO] train episode 19010: reward = -55.25, steps = 26 13:09:16 [INFO] train episode 19011: reward = -71.06, steps = 27 13:09:17 [INFO] train episode 19012: reward = -93.88, steps = 18 13:09:21 [INFO] train episode 19013: reward = -79.24, steps = 43 13:09:23 [INFO] train episode 19014: reward = -90.04, steps = 20 13:09:25 [INFO] train episode 19015: reward = -73.02, steps = 20 13:09:27 [INFO] train episode 19016: reward = -53.43, steps = 24 13:09:31 [INFO] train episode 19017: reward = -49.69, steps = 47 13:09:36 [INFO] train episode 19018: reward = -73.91, steps = 61 13:09:38 [INFO] train episode 19019: reward = -83.16, steps = 21 13:09:43 [INFO] train episode 19020: reward = -100.67, steps = 53 13:09:47 [INFO] train episode 19021: reward = -45.18, steps = 41 13:09:51 [INFO] train episode 19022: reward = -48.23, steps = 49 13:09:53 [INFO] train episode 19023: reward = -72.80, steps = 30 13:09:59 [INFO] train episode 19024: reward = -165.86, steps = 65 13:10:02 [INFO] train episode 19025: reward = -37.84, steps = 33 13:10:04 [INFO] train episode 19026: reward = -53.02, steps = 21 13:10:06 [INFO] train episode 19027: reward = -77.90, steps = 22 13:10:09 [INFO] train episode 19028: reward = -77.19, steps = 30 13:10:13 [INFO] train episode 19029: reward = -60.14, steps = 50 13:10:17 [INFO] train episode 19030: reward = -45.31, steps = 48 13:10:20 [INFO] train episode 19031: reward = -49.30, steps = 27 13:10:25 [INFO] train episode 19032: reward = -135.97, steps = 65 13:10:29 [INFO] train episode 19033: reward = -62.54, steps = 38 13:10:32 [INFO] train episode 19034: reward = -37.86, steps = 36 13:10:36 [INFO] train episode 19035: reward = -77.07, steps = 49 13:10:41 [INFO] train episode 19036: reward = -110.11, steps = 49 13:10:44 [INFO] train episode 19037: reward = -110.55, steps = 45 13:10:49 [INFO] train episode 19038: reward = -76.40, steps = 50 13:10:52 [INFO] train episode 19039: reward = -34.18, steps = 30 13:10:57 [INFO] train episode 19040: reward = -142.03, steps = 67 13:11:03 [INFO] train episode 19041: reward = -86.39, steps = 65 13:11:06 [INFO] train episode 19042: reward = -74.57, steps = 32 13:11:09 [INFO] train episode 19043: reward = -59.91, steps = 33 13:11:11 [INFO] train episode 19044: reward = -55.08, steps = 27 13:11:13 [INFO] train episode 19045: reward = -59.57, steps = 23 13:11:21 [INFO] train episode 19046: reward = -134.82, steps = 81 13:11:23 [INFO] train episode 19047: reward = -53.64, steps = 27 13:11:27 [INFO] train episode 19048: reward = -64.00, steps = 41 13:11:28 [INFO] train episode 19049: reward = -59.87, steps = 20 13:11:34 [INFO] train episode 19050: reward = -54.48, steps = 61 13:11:38 [INFO] train episode 19051: reward = -69.79, steps = 51 13:11:41 [INFO] train episode 19052: reward = -73.53, steps = 25 13:11:43 [INFO] train episode 19053: reward = -78.04, steps = 33 13:11:46 [INFO] train episode 19054: reward = -100.07, steps = 28 13:11:48 [INFO] train episode 19055: reward = -41.99, steps = 22 13:11:52 [INFO] train episode 19056: reward = -66.45, steps = 32 13:11:56 [INFO] train episode 19057: reward = -107.63, steps = 46 13:11:59 [INFO] train episode 19058: reward = -58.10, steps = 36 13:12:05 [INFO] train episode 19059: reward = -93.76, steps = 70 13:12:12 [INFO] train episode 19060: reward = -141.36, steps = 69 13:12:14 [INFO] train episode 19061: reward = -67.48, steps = 24 13:12:20 [INFO] train episode 19062: reward = -115.29, steps = 71 13:12:23 [INFO] train episode 19063: reward = -48.09, steps = 35 13:12:27 [INFO] train episode 19064: reward = -76.34, steps = 34 13:12:29 [INFO] train episode 19065: reward = -47.64, steps = 24 13:12:32 [INFO] train episode 19066: reward = -41.77, steps = 33 13:12:35 [INFO] train episode 19067: reward = -98.30, steps = 45 13:12:38 [INFO] train episode 19068: reward = -95.13, steps = 24 13:12:42 [INFO] train episode 19069: reward = -96.03, steps = 51 13:12:44 [INFO] train episode 19070: reward = -55.34, steps = 20 13:12:48 [INFO] train episode 19071: reward = -61.70, steps = 49 13:12:57 [INFO] train episode 19072: reward = -167.67, steps = 100 13:13:02 [INFO] train episode 19073: reward = -170.79, steps = 58 13:13:05 [INFO] train episode 19074: reward = -63.67, steps = 29 13:13:10 [INFO] train episode 19075: reward = -119.07, steps = 56 13:13:12 [INFO] train episode 19076: reward = -66.14, steps = 32 13:13:15 [INFO] train episode 19077: reward = -84.19, steps = 22 13:13:17 [INFO] train episode 19078: reward = -72.88, steps = 21 13:13:19 [INFO] train episode 19079: reward = -59.83, steps = 27 13:13:22 [INFO] train episode 19080: reward = -121.75, steps = 36 13:13:24 [INFO] train episode 19081: reward = -56.93, steps = 23 13:13:27 [INFO] train episode 19082: reward = -45.06, steps = 35 13:13:29 [INFO] train episode 19083: reward = -86.53, steps = 20 13:13:36 [INFO] train episode 19084: reward = -100.36, steps = 75 13:13:40 [INFO] train episode 19085: reward = -77.62, steps = 47 13:13:43 [INFO] train episode 19086: reward = -54.92, steps = 43 13:13:46 [INFO] train episode 19087: reward = -43.41, steps = 25 13:13:49 [INFO] train episode 19088: reward = -94.11, steps = 31 13:13:52 [INFO] train episode 19089: reward = -106.71, steps = 37 13:13:58 [INFO] train episode 19090: reward = -163.80, steps = 75 13:14:04 [INFO] train episode 19091: reward = -155.20, steps = 57 13:14:08 [INFO] train episode 19092: reward = -79.97, steps = 48 13:14:11 [INFO] train episode 19093: reward = -71.38, steps = 32 13:14:13 [INFO] train episode 19094: reward = -55.77, steps = 25 13:14:18 [INFO] train episode 19095: reward = -83.44, steps = 55 13:14:23 [INFO] train episode 19096: reward = -111.52, steps = 60 13:14:27 [INFO] train episode 19097: reward = -34.79, steps = 39 13:14:30 [INFO] train episode 19098: reward = -59.00, steps = 40 13:14:33 [INFO] train episode 19099: reward = -69.02, steps = 25 13:14:35 [INFO] train episode 19100: reward = -67.20, steps = 23 13:14:38 [INFO] train episode 19101: reward = -85.09, steps = 34 13:14:42 [INFO] train episode 19102: reward = -30.97, steps = 43 13:14:46 [INFO] train episode 19103: reward = -75.88, steps = 41 13:14:49 [INFO] train episode 19104: reward = -41.09, steps = 27 13:14:52 [INFO] train episode 19105: reward = -61.07, steps = 37 13:14:57 [INFO] train episode 19106: reward = -104.14, steps = 56 13:15:00 [INFO] train episode 19107: reward = -60.79, steps = 34 13:15:03 [INFO] train episode 19108: reward = -105.80, steps = 39 13:15:05 [INFO] train episode 19109: reward = -84.37, steps = 22 13:15:09 [INFO] train episode 19110: reward = -50.62, steps = 36 13:15:11 [INFO] train episode 19111: reward = -88.37, steps = 23 13:15:14 [INFO] train episode 19112: reward = -102.46, steps = 28 13:15:17 [INFO] train episode 19113: reward = -87.23, steps = 35 13:15:19 [INFO] train episode 19114: reward = -85.41, steps = 23 13:15:25 [INFO] train episode 19115: reward = -72.68, steps = 68 13:15:29 [INFO] train episode 19116: reward = -87.63, steps = 40 13:15:33 [INFO] train episode 19117: reward = -86.76, steps = 47 13:15:37 [INFO] train episode 19118: reward = -105.49, steps = 50 13:15:42 [INFO] train episode 19119: reward = -61.80, steps = 49 13:15:45 [INFO] train episode 19120: reward = -98.66, steps = 29 13:15:49 [INFO] train episode 19121: reward = -91.65, steps = 46 13:15:51 [INFO] train episode 19122: reward = -61.12, steps = 31 13:15:54 [INFO] train episode 19123: reward = -56.70, steps = 25 13:15:57 [INFO] train episode 19124: reward = -61.58, steps = 37 13:15:58 [INFO] train episode 19125: reward = -44.48, steps = 19 13:16:04 [INFO] train episode 19126: reward = -90.43, steps = 55 13:16:08 [INFO] train episode 19127: reward = -51.74, steps = 52 13:16:13 [INFO] train episode 19128: reward = -106.46, steps = 57 13:16:15 [INFO] train episode 19129: reward = -84.89, steps = 21 13:16:18 [INFO] train episode 19130: reward = -59.81, steps = 27 13:16:21 [INFO] train episode 19131: reward = -109.74, steps = 42 13:16:26 [INFO] train episode 19132: reward = -110.82, steps = 52 13:16:28 [INFO] train episode 19133: reward = -41.06, steps = 23 13:16:32 [INFO] train episode 19134: reward = -70.54, steps = 39 13:16:34 [INFO] train episode 19135: reward = -78.12, steps = 24 13:16:38 [INFO] train episode 19136: reward = -43.99, steps = 41 13:16:40 [INFO] train episode 19137: reward = -46.31, steps = 30 13:16:44 [INFO] train episode 19138: reward = -70.44, steps = 38 13:16:46 [INFO] train episode 19139: reward = -73.13, steps = 31 13:16:50 [INFO] train episode 19140: reward = -89.63, steps = 37 13:16:52 [INFO] train episode 19141: reward = -94.69, steps = 23 13:16:54 [INFO] train episode 19142: reward = -91.91, steps = 27 13:17:00 [INFO] train episode 19143: reward = -167.13, steps = 67 13:17:03 [INFO] train episode 19144: reward = -40.81, steps = 37 13:17:07 [INFO] train episode 19145: reward = -49.04, steps = 39 13:17:09 [INFO] train episode 19146: reward = -93.62, steps = 19 13:17:14 [INFO] train episode 19147: reward = -178.08, steps = 63 13:17:17 [INFO] train episode 19148: reward = -65.79, steps = 30 13:17:20 [INFO] train episode 19149: reward = -77.05, steps = 32 13:17:22 [INFO] train episode 19150: reward = -40.42, steps = 27 13:17:27 [INFO] train episode 19151: reward = -59.10, steps = 50 13:17:29 [INFO] train episode 19152: reward = -55.20, steps = 28 13:17:32 [INFO] train episode 19153: reward = -81.52, steps = 30 13:17:35 [INFO] train episode 19154: reward = -95.30, steps = 43 13:17:41 [INFO] train episode 19155: reward = -127.58, steps = 64 13:17:48 [INFO] train episode 19156: reward = -129.18, steps = 73 13:17:50 [INFO] train episode 19157: reward = -44.22, steps = 21 13:17:53 [INFO] train episode 19158: reward = -64.28, steps = 30 13:17:55 [INFO] train episode 19159: reward = -65.82, steps = 25 13:18:00 [INFO] train episode 19160: reward = -65.62, steps = 52 13:18:05 [INFO] train episode 19161: reward = -94.79, steps = 50 13:18:07 [INFO] train episode 19162: reward = -95.60, steps = 32 13:18:10 [INFO] train episode 19163: reward = -68.60, steps = 30 13:18:13 [INFO] train episode 19164: reward = -38.75, steps = 36 13:18:16 [INFO] train episode 19165: reward = -70.35, steps = 29 13:18:18 [INFO] train episode 19166: reward = -93.93, steps = 18 13:18:20 [INFO] train episode 19167: reward = -50.98, steps = 23 13:18:23 [INFO] train episode 19168: reward = -89.50, steps = 41 13:18:26 [INFO] train episode 19169: reward = -75.75, steps = 37 13:18:31 [INFO] train episode 19170: reward = -109.13, steps = 52 13:18:34 [INFO] train episode 19171: reward = -69.20, steps = 39 13:18:37 [INFO] train episode 19172: reward = -82.25, steps = 26 13:18:41 [INFO] train episode 19173: reward = -80.60, steps = 48 13:18:45 [INFO] train episode 19174: reward = -113.40, steps = 43 13:18:47 [INFO] train episode 19175: reward = -48.88, steps = 25 13:18:49 [INFO] train episode 19176: reward = -41.46, steps = 20 13:18:51 [INFO] train episode 19177: reward = -43.94, steps = 25 13:18:54 [INFO] train episode 19178: reward = -97.50, steps = 29 13:18:58 [INFO] train episode 19179: reward = -59.95, steps = 50 13:19:02 [INFO] train episode 19180: reward = -108.71, steps = 35 13:19:04 [INFO] train episode 19181: reward = -60.14, steps = 22 13:19:06 [INFO] train episode 19182: reward = -70.61, steps = 24 13:19:11 [INFO] train episode 19183: reward = -150.50, steps = 58 13:19:13 [INFO] train episode 19184: reward = -107.61, steps = 31 13:19:15 [INFO] train episode 19185: reward = -71.26, steps = 21 13:19:18 [INFO] train episode 19186: reward = -78.28, steps = 31 13:19:21 [INFO] train episode 19187: reward = -28.60, steps = 32 13:19:26 [INFO] train episode 19188: reward = -83.39, steps = 52 13:19:27 [INFO] train episode 19189: reward = -94.77, steps = 20 13:19:30 [INFO] train episode 19190: reward = -64.42, steps = 25 13:19:33 [INFO] train episode 19191: reward = -104.97, steps = 37 13:19:38 [INFO] train episode 19192: reward = -120.59, steps = 51 13:19:40 [INFO] train episode 19193: reward = -65.94, steps = 24 13:19:43 [INFO] train episode 19194: reward = -44.53, steps = 39 13:19:49 [INFO] train episode 19195: reward = -75.71, steps = 60 13:19:51 [INFO] train episode 19196: reward = -79.21, steps = 22 13:19:53 [INFO] train episode 19197: reward = -71.09, steps = 31 13:19:57 [INFO] train episode 19198: reward = -74.30, steps = 37 13:20:00 [INFO] train episode 19199: reward = -72.23, steps = 40 13:20:04 [INFO] train episode 19200: reward = -78.33, steps = 47 13:20:08 [INFO] train episode 19201: reward = -69.15, steps = 46 13:20:10 [INFO] train episode 19202: reward = -73.70, steps = 21 13:20:13 [INFO] train episode 19203: reward = -64.24, steps = 30 13:20:16 [INFO] train episode 19204: reward = -57.27, steps = 35 13:20:20 [INFO] train episode 19205: reward = -85.15, steps = 50 13:20:25 [INFO] train episode 19206: reward = -92.42, steps = 46 13:20:28 [INFO] train episode 19207: reward = -50.43, steps = 38 13:20:32 [INFO] train episode 19208: reward = -36.00, steps = 43 13:20:35 [INFO] train episode 19209: reward = -51.77, steps = 39 13:20:40 [INFO] train episode 19210: reward = -77.43, steps = 53 13:20:45 [INFO] train episode 19211: reward = -147.86, steps = 47 13:20:49 [INFO] train episode 19212: reward = -98.72, steps = 47 13:20:53 [INFO] train episode 19213: reward = -99.72, steps = 35 13:20:56 [INFO] train episode 19214: reward = -76.07, steps = 24 13:20:59 [INFO] train episode 19215: reward = -50.54, steps = 35 13:21:02 [INFO] train episode 19216: reward = -60.27, steps = 32 13:21:06 [INFO] train episode 19217: reward = -57.43, steps = 36 13:21:11 [INFO] train episode 19218: reward = -84.51, steps = 54 13:21:14 [INFO] train episode 19219: reward = -42.47, steps = 35 13:21:16 [INFO] train episode 19220: reward = -89.12, steps = 21 13:21:19 [INFO] train episode 19221: reward = -62.87, steps = 29 13:21:21 [INFO] train episode 19222: reward = -43.73, steps = 32 13:21:26 [INFO] train episode 19223: reward = -107.84, steps = 50 13:21:28 [INFO] train episode 19224: reward = -78.29, steps = 26 13:21:32 [INFO] train episode 19225: reward = -76.61, steps = 43 13:21:35 [INFO] train episode 19226: reward = -65.57, steps = 29 13:21:38 [INFO] train episode 19227: reward = -63.36, steps = 39 13:21:41 [INFO] train episode 19228: reward = -103.88, steps = 29 13:21:43 [INFO] train episode 19229: reward = -100.22, steps = 31 13:21:46 [INFO] train episode 19230: reward = -64.08, steps = 26 13:21:48 [INFO] train episode 19231: reward = -70.76, steps = 21 13:21:52 [INFO] train episode 19232: reward = -132.28, steps = 53 13:21:56 [INFO] train episode 19233: reward = -80.30, steps = 42 13:21:59 [INFO] train episode 19234: reward = -53.48, steps = 29 13:22:01 [INFO] train episode 19235: reward = -90.07, steps = 30 13:22:04 [INFO] train episode 19236: reward = -62.55, steps = 26 13:22:08 [INFO] train episode 19237: reward = -92.29, steps = 49 13:22:10 [INFO] train episode 19238: reward = -44.73, steps = 26 13:22:13 [INFO] train episode 19239: reward = -100.07, steps = 31 13:22:16 [INFO] train episode 19240: reward = -61.02, steps = 39 13:22:19 [INFO] train episode 19241: reward = -75.10, steps = 25 13:22:22 [INFO] train episode 19242: reward = -80.95, steps = 41 13:22:24 [INFO] train episode 19243: reward = -89.27, steps = 23 13:22:26 [INFO] train episode 19244: reward = -86.54, steps = 20 13:22:28 [INFO] train episode 19245: reward = -64.15, steps = 24 13:22:31 [INFO] train episode 19246: reward = -100.14, steps = 35 13:22:35 [INFO] train episode 19247: reward = -95.23, steps = 41 13:22:37 [INFO] train episode 19248: reward = -48.73, steps = 21 13:22:41 [INFO] train episode 19249: reward = -91.04, steps = 46 13:22:43 [INFO] train episode 19250: reward = -63.59, steps = 23 13:22:45 [INFO] train episode 19251: reward = -40.69, steps = 23 13:22:49 [INFO] train episode 19252: reward = -87.62, steps = 42 13:22:52 [INFO] train episode 19253: reward = -94.59, steps = 32 13:22:54 [INFO] train episode 19254: reward = -53.27, steps = 25 13:22:57 [INFO] train episode 19255: reward = -79.75, steps = 27 13:23:02 [INFO] train episode 19256: reward = -50.20, steps = 59 13:23:05 [INFO] train episode 19257: reward = -117.63, steps = 38 13:23:07 [INFO] train episode 19258: reward = -42.92, steps = 20 13:23:10 [INFO] train episode 19259: reward = -42.23, steps = 28 13:23:14 [INFO] train episode 19260: reward = -65.27, steps = 46 13:23:17 [INFO] train episode 19261: reward = -119.74, steps = 42 13:23:24 [INFO] train episode 19262: reward = -87.12, steps = 72 13:23:28 [INFO] train episode 19263: reward = -67.48, steps = 49 13:23:32 [INFO] train episode 19264: reward = -79.67, steps = 45 13:23:34 [INFO] train episode 19265: reward = -57.36, steps = 20 13:23:37 [INFO] train episode 19266: reward = -57.44, steps = 42 13:23:39 [INFO] train episode 19267: reward = -68.83, steps = 20 13:23:44 [INFO] train episode 19268: reward = -100.66, steps = 37 13:23:46 [INFO] train episode 19269: reward = -92.64, steps = 34 13:23:51 [INFO] train episode 19270: reward = -87.84, steps = 48 13:23:53 [INFO] train episode 19271: reward = -53.37, steps = 23 13:23:55 [INFO] train episode 19272: reward = -77.97, steps = 21 13:23:58 [INFO] train episode 19273: reward = -65.87, steps = 30 13:24:01 [INFO] train episode 19274: reward = -66.41, steps = 34 13:24:05 [INFO] train episode 19275: reward = -34.09, steps = 54 13:24:08 [INFO] train episode 19276: reward = -52.27, steps = 32 13:24:11 [INFO] train episode 19277: reward = -106.82, steps = 31 13:24:15 [INFO] train episode 19278: reward = -64.46, steps = 41 13:24:18 [INFO] train episode 19279: reward = -89.00, steps = 32 13:24:21 [INFO] train episode 19280: reward = -62.88, steps = 45 13:24:24 [INFO] train episode 19281: reward = -65.33, steps = 31 13:24:26 [INFO] train episode 19282: reward = -61.08, steps = 22 13:24:28 [INFO] train episode 19283: reward = -68.04, steps = 24 13:24:33 [INFO] train episode 19284: reward = -73.72, steps = 46 13:24:35 [INFO] train episode 19285: reward = -82.50, steps = 31 13:24:40 [INFO] train episode 19286: reward = -103.05, steps = 56 13:24:42 [INFO] train episode 19287: reward = -68.99, steps = 21 13:24:45 [INFO] train episode 19288: reward = -86.00, steps = 32 13:24:47 [INFO] train episode 19289: reward = -76.35, steps = 24 13:24:49 [INFO] train episode 19290: reward = -71.13, steps = 24 13:24:53 [INFO] train episode 19291: reward = -77.17, steps = 36 13:24:58 [INFO] train episode 19292: reward = -112.85, steps = 65 13:25:03 [INFO] train episode 19293: reward = -49.08, steps = 44 13:25:08 [INFO] train episode 19294: reward = -112.66, steps = 64 13:25:13 [INFO] train episode 19295: reward = -118.19, steps = 55 13:25:17 [INFO] train episode 19296: reward = -109.10, steps = 46 13:25:19 [INFO] train episode 19297: reward = -81.63, steps = 19 13:25:23 [INFO] train episode 19298: reward = -108.46, steps = 41 13:25:25 [INFO] train episode 19299: reward = -56.69, steps = 22 13:25:27 [INFO] train episode 19300: reward = -67.67, steps = 21 13:25:30 [INFO] train episode 19301: reward = -75.37, steps = 33 13:25:39 [INFO] train episode 19302: reward = -111.75, steps = 98 13:25:44 [INFO] train episode 19303: reward = -93.69, steps = 52 13:25:46 [INFO] train episode 19304: reward = -66.03, steps = 24 13:25:49 [INFO] train episode 19305: reward = -82.24, steps = 39 13:25:51 [INFO] train episode 19306: reward = -53.50, steps = 22 13:25:56 [INFO] train episode 19307: reward = -54.76, steps = 46 13:25:58 [INFO] train episode 19308: reward = -40.93, steps = 26 13:26:00 [INFO] train episode 19309: reward = -35.02, steps = 26 13:26:04 [INFO] train episode 19310: reward = -47.33, steps = 35 13:26:06 [INFO] train episode 19311: reward = -86.76, steps = 25 13:26:08 [INFO] train episode 19312: reward = -89.63, steps = 19 13:26:10 [INFO] train episode 19313: reward = -75.57, steps = 21 13:26:12 [INFO] train episode 19314: reward = -90.96, steps = 28 13:26:15 [INFO] train episode 19315: reward = -87.25, steps = 30 13:26:18 [INFO] train episode 19316: reward = -64.42, steps = 34 13:26:22 [INFO] train episode 19317: reward = -51.57, steps = 51 13:26:27 [INFO] train episode 19318: reward = -149.73, steps = 51 13:26:30 [INFO] train episode 19319: reward = -79.16, steps = 27 13:26:31 [INFO] train episode 19320: reward = -55.39, steps = 21 13:26:34 [INFO] train episode 19321: reward = -92.78, steps = 29 13:26:39 [INFO] train episode 19322: reward = -107.80, steps = 50 13:26:43 [INFO] train episode 19323: reward = -62.96, steps = 30 13:26:45 [INFO] train episode 19324: reward = -107.57, steps = 24 13:26:47 [INFO] train episode 19325: reward = -81.59, steps = 25 13:26:52 [INFO] train episode 19326: reward = -86.96, steps = 58 13:26:57 [INFO] train episode 19327: reward = -113.49, steps = 57 13:27:00 [INFO] train episode 19328: reward = -87.34, steps = 23 13:27:02 [INFO] train episode 19329: reward = -53.30, steps = 23 13:27:04 [INFO] train episode 19330: reward = -76.13, steps = 21 13:27:07 [INFO] train episode 19331: reward = -49.20, steps = 36 13:27:12 [INFO] train episode 19332: reward = -112.07, steps = 64 13:27:15 [INFO] train episode 19333: reward = -96.41, steps = 28 13:27:17 [INFO] train episode 19334: reward = -77.25, steps = 24 13:27:20 [INFO] train episode 19335: reward = -72.65, steps = 37 13:27:23 [INFO] train episode 19336: reward = -65.75, steps = 22 13:27:25 [INFO] train episode 19337: reward = -54.81, steps = 30 13:27:28 [INFO] train episode 19338: reward = -48.07, steps = 30 13:27:33 [INFO] train episode 19339: reward = -84.36, steps = 55 13:27:36 [INFO] train episode 19340: reward = -72.78, steps = 30 13:27:40 [INFO] train episode 19341: reward = -109.36, steps = 43 13:27:43 [INFO] train episode 19342: reward = -74.79, steps = 37 13:27:45 [INFO] train episode 19343: reward = -39.80, steps = 23 13:27:48 [INFO] train episode 19344: reward = -75.00, steps = 33 13:27:51 [INFO] train episode 19345: reward = -60.33, steps = 29 13:27:52 [INFO] train episode 19346: reward = -66.20, steps = 20 13:28:01 [INFO] train episode 19347: reward = -214.86, steps = 100 13:28:03 [INFO] train episode 19348: reward = -41.60, steps = 20 13:28:07 [INFO] train episode 19349: reward = -88.97, steps = 40 13:28:11 [INFO] train episode 19350: reward = -62.62, steps = 44 13:28:13 [INFO] train episode 19351: reward = -53.39, steps = 21 13:28:17 [INFO] train episode 19352: reward = -109.38, steps = 57 13:28:21 [INFO] train episode 19353: reward = -86.71, steps = 38 13:28:25 [INFO] train episode 19354: reward = -97.94, steps = 47 13:28:27 [INFO] train episode 19355: reward = -47.97, steps = 21 13:28:32 [INFO] train episode 19356: reward = -140.31, steps = 57 13:28:35 [INFO] train episode 19357: reward = -79.16, steps = 29 13:28:40 [INFO] train episode 19358: reward = -77.99, steps = 57 13:28:44 [INFO] train episode 19359: reward = -119.55, steps = 50 13:28:46 [INFO] train episode 19360: reward = -125.47, steps = 24 13:28:48 [INFO] train episode 19361: reward = -86.79, steps = 19 13:28:50 [INFO] train episode 19362: reward = -97.37, steps = 25 13:28:55 [INFO] train episode 19363: reward = -65.83, steps = 54 13:28:58 [INFO] train episode 19364: reward = -38.73, steps = 32 13:29:04 [INFO] train episode 19365: reward = -79.58, steps = 58 13:29:08 [INFO] train episode 19366: reward = -104.27, steps = 49 13:29:11 [INFO] train episode 19367: reward = -90.39, steps = 26 13:29:13 [INFO] train episode 19368: reward = -49.96, steps = 25 13:29:16 [INFO] train episode 19369: reward = -72.91, steps = 31 13:29:19 [INFO] train episode 19370: reward = -95.51, steps = 44 13:29:23 [INFO] train episode 19371: reward = -68.76, steps = 42 13:29:25 [INFO] train episode 19372: reward = -75.78, steps = 24 13:29:28 [INFO] train episode 19373: reward = -55.24, steps = 24 13:29:30 [INFO] train episode 19374: reward = -64.07, steps = 22 13:29:32 [INFO] train episode 19375: reward = -56.09, steps = 22 13:29:34 [INFO] train episode 19376: reward = -66.15, steps = 30 13:29:39 [INFO] train episode 19377: reward = -93.41, steps = 42 13:29:42 [INFO] train episode 19378: reward = -33.30, steps = 35 13:29:47 [INFO] train episode 19379: reward = -38.13, steps = 60 13:29:49 [INFO] train episode 19380: reward = -59.97, steps = 20 13:29:51 [INFO] train episode 19381: reward = -74.56, steps = 22 13:29:53 [INFO] train episode 19382: reward = -76.00, steps = 27 13:29:56 [INFO] train episode 19383: reward = -69.74, steps = 25 13:30:03 [INFO] train episode 19384: reward = -121.26, steps = 78 13:30:07 [INFO] train episode 19385: reward = -73.56, steps = 44 13:30:10 [INFO] train episode 19386: reward = -55.45, steps = 34 13:30:12 [INFO] train episode 19387: reward = -76.51, steps = 30 13:30:14 [INFO] train episode 19388: reward = -34.51, steps = 20 13:30:17 [INFO] train episode 19389: reward = -37.52, steps = 30 13:30:21 [INFO] train episode 19390: reward = -62.45, steps = 46 13:30:23 [INFO] train episode 19391: reward = -49.34, steps = 29 13:30:25 [INFO] train episode 19392: reward = -88.69, steps = 21 13:30:28 [INFO] train episode 19393: reward = -43.38, steps = 29 13:30:32 [INFO] train episode 19394: reward = -48.86, steps = 45 13:30:34 [INFO] train episode 19395: reward = -102.32, steps = 23 13:30:36 [INFO] train episode 19396: reward = -43.74, steps = 25 13:30:43 [INFO] train episode 19397: reward = -133.85, steps = 76 13:30:50 [INFO] train episode 19398: reward = -100.53, steps = 71 13:30:55 [INFO] train episode 19399: reward = -128.65, steps = 63 13:31:00 [INFO] train episode 19400: reward = -100.74, steps = 56 13:31:04 [INFO] train episode 19401: reward = -123.53, steps = 47 13:31:07 [INFO] train episode 19402: reward = -60.05, steps = 25 13:31:10 [INFO] train episode 19403: reward = -71.90, steps = 39 13:31:15 [INFO] train episode 19404: reward = -154.58, steps = 54 13:31:20 [INFO] train episode 19405: reward = -120.98, steps = 61 13:31:24 [INFO] train episode 19406: reward = -69.92, steps = 38 13:31:26 [INFO] train episode 19407: reward = -61.50, steps = 32 13:31:29 [INFO] train episode 19408: reward = -91.88, steps = 30 13:31:31 [INFO] train episode 19409: reward = -89.08, steps = 18 13:31:34 [INFO] train episode 19410: reward = -49.21, steps = 32 13:31:36 [INFO] train episode 19411: reward = -60.31, steps = 30 13:31:40 [INFO] train episode 19412: reward = -91.78, steps = 34 13:31:42 [INFO] train episode 19413: reward = -86.93, steps = 20 13:31:44 [INFO] train episode 19414: reward = -69.16, steps = 22 13:31:46 [INFO] train episode 19415: reward = -32.78, steps = 33 13:31:49 [INFO] train episode 19416: reward = -91.28, steps = 34 13:31:51 [INFO] train episode 19417: reward = -80.93, steps = 20 13:31:53 [INFO] train episode 19418: reward = -69.64, steps = 18 13:31:55 [INFO] train episode 19419: reward = -117.68, steps = 22 13:31:59 [INFO] train episode 19420: reward = -64.94, steps = 44 13:32:04 [INFO] train episode 19421: reward = -132.19, steps = 63 13:32:06 [INFO] train episode 19422: reward = -67.54, steps = 19 13:32:09 [INFO] train episode 19423: reward = -52.90, steps = 30 13:32:11 [INFO] train episode 19424: reward = -85.14, steps = 22 13:32:14 [INFO] train episode 19425: reward = -92.32, steps = 29 13:32:19 [INFO] train episode 19426: reward = -120.00, steps = 54 13:32:21 [INFO] train episode 19427: reward = -149.54, steps = 30 13:32:25 [INFO] train episode 19428: reward = -77.13, steps = 41 13:32:30 [INFO] train episode 19429: reward = -71.65, steps = 52 13:32:35 [INFO] train episode 19430: reward = -85.10, steps = 47 13:32:37 [INFO] train episode 19431: reward = -54.78, steps = 24 13:32:40 [INFO] train episode 19432: reward = -52.69, steps = 29 13:32:45 [INFO] train episode 19433: reward = -74.76, steps = 54 13:32:47 [INFO] train episode 19434: reward = -73.84, steps = 23 13:32:49 [INFO] train episode 19435: reward = -51.80, steps = 21 13:32:51 [INFO] train episode 19436: reward = -67.18, steps = 22 13:32:54 [INFO] train episode 19437: reward = -93.87, steps = 32 13:32:58 [INFO] train episode 19438: reward = -78.28, steps = 50 13:33:04 [INFO] train episode 19439: reward = -93.45, steps = 61 13:33:07 [INFO] train episode 19440: reward = -58.31, steps = 29 13:33:09 [INFO] train episode 19441: reward = -63.96, steps = 25 13:33:12 [INFO] train episode 19442: reward = -82.92, steps = 29 13:33:14 [INFO] train episode 19443: reward = -98.53, steps = 30 13:33:18 [INFO] train episode 19444: reward = -87.64, steps = 42 13:33:21 [INFO] train episode 19445: reward = -62.01, steps = 29 13:33:26 [INFO] train episode 19446: reward = -128.85, steps = 49 13:33:29 [INFO] train episode 19447: reward = -77.89, steps = 44 13:33:31 [INFO] train episode 19448: reward = -57.98, steps = 22 13:33:35 [INFO] train episode 19449: reward = -67.31, steps = 37 13:33:37 [INFO] train episode 19450: reward = -44.05, steps = 24 13:33:40 [INFO] train episode 19451: reward = -50.22, steps = 33 13:33:43 [INFO] train episode 19452: reward = -110.64, steps = 31 13:33:45 [INFO] train episode 19453: reward = -66.04, steps = 21 13:33:47 [INFO] train episode 19454: reward = -56.83, steps = 23 13:33:49 [INFO] train episode 19455: reward = -88.84, steps = 21 13:33:51 [INFO] train episode 19456: reward = -29.86, steps = 21 13:33:54 [INFO] train episode 19457: reward = -45.37, steps = 32 13:33:57 [INFO] train episode 19458: reward = -68.48, steps = 33 13:33:59 [INFO] train episode 19459: reward = -53.23, steps = 24 13:34:01 [INFO] train episode 19460: reward = -55.92, steps = 21 13:34:03 [INFO] train episode 19461: reward = -77.48, steps = 22 13:34:06 [INFO] train episode 19462: reward = -57.51, steps = 29 13:34:10 [INFO] train episode 19463: reward = -53.88, steps = 44 13:34:13 [INFO] train episode 19464: reward = -53.75, steps = 24 13:34:18 [INFO] train episode 19465: reward = -146.99, steps = 66 13:34:22 [INFO] train episode 19466: reward = -72.46, steps = 40 13:34:24 [INFO] train episode 19467: reward = -65.62, steps = 28 13:34:27 [INFO] train episode 19468: reward = -76.24, steps = 28 13:34:31 [INFO] train episode 19469: reward = -124.87, steps = 37 13:34:33 [INFO] train episode 19470: reward = -64.63, steps = 23 13:34:37 [INFO] train episode 19471: reward = -86.62, steps = 50 13:34:39 [INFO] train episode 19472: reward = -89.72, steps = 21 13:34:41 [INFO] train episode 19473: reward = -96.06, steps = 22 13:34:44 [INFO] train episode 19474: reward = -55.75, steps = 32 13:34:48 [INFO] train episode 19475: reward = -70.85, steps = 49 13:34:52 [INFO] train episode 19476: reward = -81.86, steps = 43 13:34:58 [INFO] train episode 19477: reward = -147.73, steps = 74 13:35:01 [INFO] train episode 19478: reward = -62.69, steps = 24 13:35:03 [INFO] train episode 19479: reward = -55.15, steps = 28 13:35:06 [INFO] train episode 19480: reward = -80.18, steps = 34 13:35:08 [INFO] train episode 19481: reward = -46.82, steps = 23 13:35:11 [INFO] train episode 19482: reward = -85.28, steps = 26 13:35:14 [INFO] train episode 19483: reward = -132.73, steps = 43 13:35:18 [INFO] train episode 19484: reward = -98.29, steps = 41 13:35:22 [INFO] train episode 19485: reward = -108.06, steps = 36 13:35:26 [INFO] train episode 19486: reward = -127.93, steps = 52 13:35:28 [INFO] train episode 19487: reward = -57.63, steps = 22 13:35:34 [INFO] train episode 19488: reward = -61.22, steps = 59 13:35:37 [INFO] train episode 19489: reward = -66.82, steps = 33 13:35:39 [INFO] train episode 19490: reward = -76.39, steps = 24 13:35:42 [INFO] train episode 19491: reward = -66.44, steps = 24 13:35:46 [INFO] train episode 19492: reward = -104.17, steps = 49 13:35:49 [INFO] train episode 19493: reward = -66.91, steps = 27 13:35:52 [INFO] train episode 19494: reward = -91.34, steps = 39 13:35:55 [INFO] train episode 19495: reward = -35.64, steps = 32 13:35:59 [INFO] train episode 19496: reward = -65.18, steps = 43 13:36:03 [INFO] train episode 19497: reward = -163.72, steps = 52 13:36:06 [INFO] train episode 19498: reward = -64.93, steps = 25 13:36:09 [INFO] train episode 19499: reward = -80.69, steps = 36 13:36:11 [INFO] train episode 19500: reward = -51.82, steps = 22 13:36:14 [INFO] train episode 19501: reward = -73.50, steps = 33 13:36:18 [INFO] train episode 19502: reward = -73.89, steps = 45 13:36:20 [INFO] train episode 19503: reward = -66.04, steps = 28 13:36:23 [INFO] train episode 19504: reward = -41.26, steps = 22 13:36:25 [INFO] train episode 19505: reward = -44.85, steps = 31 13:36:28 [INFO] train episode 19506: reward = -72.17, steps = 31 13:36:30 [INFO] train episode 19507: reward = -45.67, steps = 25 13:36:33 [INFO] train episode 19508: reward = -98.40, steps = 24 13:36:35 [INFO] train episode 19509: reward = -84.92, steps = 24 13:36:39 [INFO] train episode 19510: reward = -73.53, steps = 44 13:36:43 [INFO] train episode 19511: reward = -52.96, steps = 40 13:36:46 [INFO] train episode 19512: reward = -85.68, steps = 32 13:36:50 [INFO] train episode 19513: reward = -40.35, steps = 54 13:36:52 [INFO] train episode 19514: reward = -57.58, steps = 21 13:36:57 [INFO] train episode 19515: reward = -48.72, steps = 48 13:37:01 [INFO] train episode 19516: reward = -112.88, steps = 45 13:37:05 [INFO] train episode 19517: reward = -96.13, steps = 46 13:37:11 [INFO] train episode 19518: reward = -119.92, steps = 73 13:37:17 [INFO] train episode 19519: reward = -105.45, steps = 60 13:37:20 [INFO] train episode 19520: reward = -107.32, steps = 36 13:37:22 [INFO] train episode 19521: reward = -79.39, steps = 19 13:37:25 [INFO] train episode 19522: reward = -49.83, steps = 36 13:37:27 [INFO] train episode 19523: reward = -54.27, steps = 24 13:37:30 [INFO] train episode 19524: reward = -72.71, steps = 23 13:37:36 [INFO] train episode 19525: reward = -153.62, steps = 73 13:37:39 [INFO] train episode 19526: reward = -75.49, steps = 31 13:37:41 [INFO] train episode 19527: reward = -104.86, steps = 25 13:37:44 [INFO] train episode 19528: reward = -90.82, steps = 32 13:37:47 [INFO] train episode 19529: reward = -80.17, steps = 35 13:37:51 [INFO] train episode 19530: reward = -98.48, steps = 37 13:37:53 [INFO] train episode 19531: reward = -83.66, steps = 29 13:37:59 [INFO] train episode 19532: reward = -160.18, steps = 66 13:38:01 [INFO] train episode 19533: reward = -78.01, steps = 22 13:38:03 [INFO] train episode 19534: reward = -65.48, steps = 20 13:38:06 [INFO] train episode 19535: reward = -62.55, steps = 28 13:38:09 [INFO] train episode 19536: reward = -96.33, steps = 31 13:38:11 [INFO] train episode 19537: reward = -59.46, steps = 23 13:38:13 [INFO] train episode 19538: reward = -80.35, steps = 32 13:38:18 [INFO] train episode 19539: reward = -81.05, steps = 50 13:38:20 [INFO] train episode 19540: reward = -79.05, steps = 15 13:38:23 [INFO] train episode 19541: reward = -89.30, steps = 45 13:38:26 [INFO] train episode 19542: reward = -86.12, steps = 29 13:38:28 [INFO] train episode 19543: reward = -80.63, steps = 23 13:38:30 [INFO] train episode 19544: reward = -49.45, steps = 21 13:38:33 [INFO] train episode 19545: reward = -83.94, steps = 21 13:38:35 [INFO] train episode 19546: reward = -62.51, steps = 23 13:38:42 [INFO] train episode 19547: reward = -94.44, steps = 73 13:38:45 [INFO] train episode 19548: reward = -96.95, steps = 41 13:38:47 [INFO] train episode 19549: reward = -60.84, steps = 21 13:38:53 [INFO] train episode 19550: reward = -88.66, steps = 59 13:38:55 [INFO] train episode 19551: reward = -72.10, steps = 22 13:38:58 [INFO] train episode 19552: reward = -71.53, steps = 35 13:39:01 [INFO] train episode 19553: reward = -41.13, steps = 31 13:39:03 [INFO] train episode 19554: reward = -51.59, steps = 24 13:39:08 [INFO] train episode 19555: reward = -121.73, steps = 57 13:39:12 [INFO] train episode 19556: reward = -60.13, steps = 44 13:39:14 [INFO] train episode 19557: reward = -43.51, steps = 25 13:39:18 [INFO] train episode 19558: reward = -123.99, steps = 35 13:39:19 [INFO] train episode 19559: reward = -75.52, steps = 21 13:39:21 [INFO] train episode 19560: reward = -56.63, steps = 20 13:39:24 [INFO] train episode 19561: reward = -115.72, steps = 32 13:39:27 [INFO] train episode 19562: reward = -64.75, steps = 21 13:39:29 [INFO] train episode 19563: reward = -152.77, steps = 32 13:39:33 [INFO] train episode 19564: reward = -89.16, steps = 36 13:39:34 [INFO] train episode 19565: reward = -76.05, steps = 19 13:39:39 [INFO] train episode 19566: reward = -53.04, steps = 53 13:39:42 [INFO] train episode 19567: reward = -63.77, steps = 33 13:39:45 [INFO] train episode 19568: reward = -61.74, steps = 26 13:39:48 [INFO] train episode 19569: reward = -88.63, steps = 42 13:39:50 [INFO] train episode 19570: reward = -70.81, steps = 22 13:39:56 [INFO] train episode 19571: reward = -96.06, steps = 64 13:40:00 [INFO] train episode 19572: reward = -56.43, steps = 38 13:40:07 [INFO] train episode 19573: reward = -148.06, steps = 90 13:40:10 [INFO] train episode 19574: reward = -85.60, steps = 26 13:40:12 [INFO] train episode 19575: reward = -69.65, steps = 28 13:40:14 [INFO] train episode 19576: reward = -86.05, steps = 20 13:40:19 [INFO] train episode 19577: reward = -63.27, steps = 49 13:40:21 [INFO] train episode 19578: reward = -83.23, steps = 22 13:40:22 [INFO] train episode 19579: reward = -68.07, steps = 20 13:40:24 [INFO] train episode 19580: reward = -85.01, steps = 19 13:40:28 [INFO] train episode 19581: reward = -69.27, steps = 46 13:40:35 [INFO] train episode 19582: reward = -103.10, steps = 74 13:40:37 [INFO] train episode 19583: reward = -73.37, steps = 23 13:40:42 [INFO] train episode 19584: reward = -119.13, steps = 58 13:40:45 [INFO] train episode 19585: reward = -57.35, steps = 33 13:40:49 [INFO] train episode 19586: reward = -70.66, steps = 38 13:40:51 [INFO] train episode 19587: reward = -107.14, steps = 23 13:40:54 [INFO] train episode 19588: reward = -111.21, steps = 29 13:40:56 [INFO] train episode 19589: reward = -70.33, steps = 30 13:40:59 [INFO] train episode 19590: reward = -67.71, steps = 27 13:41:01 [INFO] train episode 19591: reward = -57.88, steps = 26 13:41:09 [INFO] train episode 19592: reward = -107.21, steps = 96 13:41:14 [INFO] train episode 19593: reward = -85.15, steps = 52 13:41:19 [INFO] train episode 19594: reward = -100.21, steps = 54 13:41:23 [INFO] train episode 19595: reward = -80.81, steps = 41 13:41:25 [INFO] train episode 19596: reward = -49.29, steps = 28 13:41:27 [INFO] train episode 19597: reward = -48.96, steps = 23 13:41:35 [INFO] train episode 19598: reward = -149.37, steps = 77 13:41:38 [INFO] train episode 19599: reward = -56.98, steps = 29 13:41:42 [INFO] train episode 19600: reward = -94.96, steps = 43 13:41:44 [INFO] train episode 19601: reward = -58.92, steps = 32 13:41:47 [INFO] train episode 19602: reward = -78.57, steps = 33 13:41:49 [INFO] train episode 19603: reward = -96.24, steps = 21 13:41:51 [INFO] train episode 19604: reward = -46.83, steps = 23 13:41:53 [INFO] train episode 19605: reward = -66.21, steps = 19 13:41:55 [INFO] train episode 19606: reward = -76.08, steps = 21 13:41:58 [INFO] train episode 19607: reward = -51.05, steps = 29 13:42:01 [INFO] train episode 19608: reward = -89.99, steps = 35 13:42:03 [INFO] train episode 19609: reward = -71.33, steps = 21 13:42:05 [INFO] train episode 19610: reward = -98.90, steps = 25 13:42:09 [INFO] train episode 19611: reward = -83.42, steps = 41 13:42:13 [INFO] train episode 19612: reward = -64.10, steps = 39 13:42:15 [INFO] train episode 19613: reward = -78.62, steps = 23 13:42:17 [INFO] train episode 19614: reward = -51.60, steps = 23 13:42:19 [INFO] train episode 19615: reward = -61.74, steps = 26 13:42:22 [INFO] train episode 19616: reward = -69.28, steps = 27 13:42:24 [INFO] train episode 19617: reward = -102.53, steps = 23 13:42:26 [INFO] train episode 19618: reward = -68.46, steps = 21 13:42:29 [INFO] train episode 19619: reward = -55.26, steps = 26 13:42:31 [INFO] train episode 19620: reward = -78.30, steps = 29 13:42:33 [INFO] train episode 19621: reward = -77.21, steps = 20 13:42:35 [INFO] train episode 19622: reward = -79.66, steps = 25 13:42:38 [INFO] train episode 19623: reward = -118.56, steps = 37 13:42:42 [INFO] train episode 19624: reward = -104.76, steps = 38 13:42:44 [INFO] train episode 19625: reward = -76.54, steps = 19 13:42:48 [INFO] train episode 19626: reward = -150.46, steps = 43 13:42:50 [INFO] train episode 19627: reward = -67.96, steps = 32 13:42:52 [INFO] train episode 19628: reward = -43.90, steps = 22 13:42:58 [INFO] train episode 19629: reward = -145.36, steps = 60 13:43:03 [INFO] train episode 19630: reward = -148.68, steps = 56 13:43:05 [INFO] train episode 19631: reward = -60.12, steps = 27 13:43:08 [INFO] train episode 19632: reward = -75.69, steps = 27 13:43:10 [INFO] train episode 19633: reward = -40.15, steps = 27 13:43:12 [INFO] train episode 19634: reward = -65.81, steps = 21 13:43:19 [INFO] train episode 19635: reward = -150.98, steps = 74 13:43:21 [INFO] train episode 19636: reward = -73.15, steps = 20 13:43:23 [INFO] train episode 19637: reward = -71.33, steps = 22 13:43:25 [INFO] train episode 19638: reward = -85.62, steps = 20 13:43:28 [INFO] train episode 19639: reward = -60.68, steps = 40 13:43:30 [INFO] train episode 19640: reward = -67.81, steps = 27 13:43:34 [INFO] train episode 19641: reward = -74.23, steps = 34 13:43:36 [INFO] train episode 19642: reward = -56.80, steps = 27 13:43:39 [INFO] train episode 19643: reward = -53.23, steps = 32 13:43:43 [INFO] train episode 19644: reward = -59.13, steps = 43 13:43:47 [INFO] train episode 19645: reward = -85.19, steps = 50 13:43:52 [INFO] train episode 19646: reward = -104.07, steps = 54 13:43:57 [INFO] train episode 19647: reward = -114.26, steps = 52 13:44:00 [INFO] train episode 19648: reward = -68.21, steps = 32 13:44:03 [INFO] train episode 19649: reward = -85.21, steps = 32 13:44:05 [INFO] train episode 19650: reward = -83.99, steps = 26 13:44:07 [INFO] train episode 19651: reward = -67.60, steps = 23 13:44:10 [INFO] train episode 19652: reward = -79.76, steps = 26 13:44:13 [INFO] train episode 19653: reward = -104.87, steps = 36 13:44:15 [INFO] train episode 19654: reward = -61.55, steps = 20 13:44:18 [INFO] train episode 19655: reward = -55.04, steps = 32 13:44:19 [INFO] train episode 19656: reward = -87.72, steps = 19 13:44:24 [INFO] train episode 19657: reward = -117.73, steps = 49 13:44:27 [INFO] train episode 19658: reward = -116.62, steps = 31 13:44:29 [INFO] train episode 19659: reward = -78.53, steps = 21 13:44:32 [INFO] train episode 19660: reward = -101.07, steps = 35 13:44:35 [INFO] train episode 19661: reward = -95.91, steps = 24 13:44:38 [INFO] train episode 19662: reward = -114.03, steps = 35 13:44:41 [INFO] train episode 19663: reward = -53.37, steps = 33 13:44:44 [INFO] train episode 19664: reward = -74.83, steps = 32 13:44:46 [INFO] train episode 19665: reward = -94.03, steps = 22 13:44:50 [INFO] train episode 19666: reward = -125.08, steps = 49 13:44:54 [INFO] train episode 19667: reward = -108.16, steps = 37 13:44:55 [INFO] train episode 19668: reward = -56.03, steps = 20 13:44:59 [INFO] train episode 19669: reward = -61.27, steps = 34 13:45:01 [INFO] train episode 19670: reward = -68.91, steps = 26 13:45:03 [INFO] train episode 19671: reward = -41.13, steps = 24 13:45:06 [INFO] train episode 19672: reward = -84.85, steps = 25 13:45:09 [INFO] train episode 19673: reward = -121.51, steps = 33 13:45:11 [INFO] train episode 19674: reward = -86.99, steps = 33 13:45:14 [INFO] train episode 19675: reward = -53.13, steps = 26 13:45:16 [INFO] train episode 19676: reward = -47.23, steps = 19 13:45:20 [INFO] train episode 19677: reward = -105.56, steps = 48 13:45:22 [INFO] train episode 19678: reward = -110.20, steps = 20 13:45:24 [INFO] train episode 19679: reward = -48.53, steps = 25 13:45:27 [INFO] train episode 19680: reward = -93.20, steps = 34 13:45:32 [INFO] train episode 19681: reward = -147.11, steps = 45 13:45:33 [INFO] train episode 19682: reward = -104.31, steps = 18 13:45:36 [INFO] train episode 19683: reward = -82.15, steps = 28 13:45:38 [INFO] train episode 19684: reward = -61.81, steps = 26 13:45:40 [INFO] train episode 19685: reward = -52.45, steps = 28 13:45:42 [INFO] train episode 19686: reward = -52.18, steps = 19 13:45:44 [INFO] train episode 19687: reward = -87.71, steps = 24 13:45:47 [INFO] train episode 19688: reward = -59.82, steps = 22 13:45:51 [INFO] train episode 19689: reward = -90.17, steps = 51 13:45:54 [INFO] train episode 19690: reward = -69.53, steps = 26 13:45:55 [INFO] train episode 19691: reward = -51.03, steps = 20 13:45:58 [INFO] train episode 19692: reward = -85.21, steps = 31 13:46:00 [INFO] train episode 19693: reward = -87.98, steps = 25 13:46:04 [INFO] train episode 19694: reward = -42.45, steps = 31 13:46:07 [INFO] train episode 19695: reward = -85.66, steps = 36 13:46:09 [INFO] train episode 19696: reward = -73.88, steps = 24 13:46:13 [INFO] train episode 19697: reward = -114.27, steps = 41 13:46:15 [INFO] train episode 19698: reward = -58.99, steps = 31 13:46:18 [INFO] train episode 19699: reward = -75.67, steps = 27 13:46:20 [INFO] train episode 19700: reward = -71.47, steps = 26 13:46:22 [INFO] train episode 19701: reward = -53.10, steps = 23 13:46:25 [INFO] train episode 19702: reward = -102.34, steps = 27 13:46:29 [INFO] train episode 19703: reward = -50.86, steps = 52 13:46:31 [INFO] train episode 19704: reward = -62.01, steps = 24 13:46:34 [INFO] train episode 19705: reward = -117.05, steps = 30 13:46:38 [INFO] train episode 19706: reward = -78.41, steps = 38 13:46:40 [INFO] train episode 19707: reward = -64.68, steps = 22 13:46:43 [INFO] train episode 19708: reward = -46.10, steps = 38 13:46:45 [INFO] train episode 19709: reward = -64.80, steps = 24 13:46:47 [INFO] train episode 19710: reward = -82.77, steps = 24 13:46:50 [INFO] train episode 19711: reward = -86.56, steps = 36 13:46:53 [INFO] train episode 19712: reward = -43.76, steps = 22 13:46:55 [INFO] train episode 19713: reward = -88.01, steps = 19 13:46:56 [INFO] train episode 19714: reward = -77.90, steps = 20 13:47:00 [INFO] train episode 19715: reward = -54.82, steps = 45 13:47:05 [INFO] train episode 19716: reward = -141.03, steps = 54 13:47:10 [INFO] train episode 19717: reward = -87.39, steps = 48 13:47:13 [INFO] train episode 19718: reward = -56.16, steps = 37 13:47:15 [INFO] train episode 19719: reward = -69.83, steps = 27 13:47:18 [INFO] train episode 19720: reward = -86.37, steps = 28 13:47:20 [INFO] train episode 19721: reward = -75.81, steps = 24 13:47:22 [INFO] train episode 19722: reward = -56.23, steps = 27 13:47:25 [INFO] train episode 19723: reward = -72.28, steps = 22 13:47:29 [INFO] train episode 19724: reward = -108.05, steps = 46 13:47:32 [INFO] train episode 19725: reward = -104.18, steps = 22 13:47:33 [INFO] train episode 19726: reward = -80.66, steps = 20 13:47:35 [INFO] train episode 19727: reward = -76.84, steps = 24 13:47:38 [INFO] train episode 19728: reward = -61.17, steps = 25 13:47:41 [INFO] train episode 19729: reward = -73.10, steps = 34 13:47:43 [INFO] train episode 19730: reward = -73.57, steps = 24 13:47:47 [INFO] train episode 19731: reward = -93.75, steps = 44 13:47:49 [INFO] train episode 19732: reward = -72.44, steps = 27 13:47:52 [INFO] train episode 19733: reward = -77.14, steps = 26 13:47:54 [INFO] train episode 19734: reward = -59.66, steps = 27 13:47:58 [INFO] train episode 19735: reward = -103.88, steps = 45 13:48:00 [INFO] train episode 19736: reward = -62.70, steps = 19 13:48:03 [INFO] train episode 19737: reward = -98.79, steps = 30 13:48:05 [INFO] train episode 19738: reward = -101.97, steps = 19 13:48:08 [INFO] train episode 19739: reward = -67.24, steps = 29 13:48:10 [INFO] train episode 19740: reward = -104.11, steps = 23 13:48:13 [INFO] train episode 19741: reward = -84.67, steps = 43 13:48:17 [INFO] train episode 19742: reward = -71.49, steps = 32 13:48:20 [INFO] train episode 19743: reward = -76.10, steps = 37 13:48:22 [INFO] train episode 19744: reward = -66.69, steps = 22 13:48:24 [INFO] train episode 19745: reward = -57.00, steps = 19 13:48:27 [INFO] train episode 19746: reward = -60.54, steps = 39 13:48:29 [INFO] train episode 19747: reward = -69.26, steps = 22 13:48:31 [INFO] train episode 19748: reward = -68.73, steps = 20 13:48:35 [INFO] train episode 19749: reward = -68.41, steps = 38 13:48:37 [INFO] train episode 19750: reward = -81.95, steps = 27 13:48:40 [INFO] train episode 19751: reward = -81.02, steps = 25 13:48:41 [INFO] train episode 19752: reward = -69.91, steps = 20 13:48:44 [INFO] train episode 19753: reward = -63.54, steps = 26 13:48:47 [INFO] train episode 19754: reward = -77.03, steps = 34 13:48:51 [INFO] train episode 19755: reward = -105.20, steps = 41 13:48:54 [INFO] train episode 19756: reward = -94.41, steps = 39 13:48:56 [INFO] train episode 19757: reward = -65.32, steps = 22 13:48:58 [INFO] train episode 19758: reward = -52.69, steps = 23 13:49:00 [INFO] train episode 19759: reward = -81.84, steps = 25 13:49:03 [INFO] train episode 19760: reward = -70.50, steps = 23 13:49:08 [INFO] train episode 19761: reward = -108.56, steps = 55 13:49:09 [INFO] train episode 19762: reward = -84.55, steps = 19 13:49:13 [INFO] train episode 19763: reward = -86.49, steps = 40 13:49:15 [INFO] train episode 19764: reward = -40.38, steps = 22 13:49:17 [INFO] train episode 19765: reward = -54.29, steps = 27 13:49:19 [INFO] train episode 19766: reward = -65.33, steps = 20 13:49:21 [INFO] train episode 19767: reward = -88.42, steps = 23 13:49:23 [INFO] train episode 19768: reward = -51.99, steps = 21 13:49:25 [INFO] train episode 19769: reward = -48.81, steps = 20 13:49:27 [INFO] train episode 19770: reward = -55.53, steps = 20 13:49:28 [INFO] train episode 19771: reward = -65.50, steps = 22 13:49:31 [INFO] train episode 19772: reward = -94.15, steps = 24 13:49:33 [INFO] train episode 19773: reward = -56.27, steps = 25 13:49:38 [INFO] train episode 19774: reward = -65.75, steps = 59 13:49:40 [INFO] train episode 19775: reward = -61.11, steps = 22 13:49:46 [INFO] train episode 19776: reward = -107.13, steps = 64 13:49:48 [INFO] train episode 19777: reward = -88.21, steps = 31 13:49:51 [INFO] train episode 19778: reward = -54.30, steps = 23 13:49:54 [INFO] train episode 19779: reward = -64.51, steps = 35 13:49:57 [INFO] train episode 19780: reward = -65.81, steps = 38 13:50:00 [INFO] train episode 19781: reward = -89.57, steps = 23 13:50:02 [INFO] train episode 19782: reward = -78.33, steps = 29 13:50:06 [INFO] train episode 19783: reward = -93.14, steps = 45 13:50:10 [INFO] train episode 19784: reward = -94.08, steps = 40 13:50:12 [INFO] train episode 19785: reward = -63.05, steps = 25 13:50:16 [INFO] train episode 19786: reward = -73.14, steps = 39 13:50:18 [INFO] train episode 19787: reward = -105.96, steps = 24 13:50:20 [INFO] train episode 19788: reward = -76.62, steps = 29 13:50:25 [INFO] train episode 19789: reward = -119.33, steps = 50 13:50:29 [INFO] train episode 19790: reward = -93.68, steps = 30 13:50:31 [INFO] train episode 19791: reward = -53.35, steps = 26 13:50:33 [INFO] train episode 19792: reward = -78.34, steps = 24 13:50:38 [INFO] train episode 19793: reward = -114.08, steps = 57 13:50:42 [INFO] train episode 19794: reward = -58.43, steps = 38 13:50:44 [INFO] train episode 19795: reward = -53.94, steps = 19 13:50:47 [INFO] train episode 19796: reward = -95.29, steps = 36 13:50:49 [INFO] train episode 19797: reward = -57.00, steps = 25 13:50:52 [INFO] train episode 19798: reward = -81.07, steps = 30 13:50:56 [INFO] train episode 19799: reward = -109.13, steps = 48 13:51:01 [INFO] train episode 19800: reward = -142.90, steps = 49 13:51:03 [INFO] train episode 19801: reward = -63.93, steps = 27 13:51:05 [INFO] train episode 19802: reward = -109.73, steps = 22 13:51:07 [INFO] train episode 19803: reward = -116.21, steps = 23 13:51:11 [INFO] train episode 19804: reward = -116.15, steps = 45 13:51:14 [INFO] train episode 19805: reward = -53.94, steps = 29 13:51:19 [INFO] train episode 19806: reward = -68.11, steps = 56 13:51:21 [INFO] train episode 19807: reward = -69.90, steps = 21 13:51:24 [INFO] train episode 19808: reward = -111.33, steps = 34 13:51:28 [INFO] train episode 19809: reward = -76.29, steps = 44 13:51:30 [INFO] train episode 19810: reward = -85.75, steps = 26 13:51:32 [INFO] train episode 19811: reward = -95.20, steps = 28 13:51:35 [INFO] train episode 19812: reward = -81.91, steps = 23 13:51:38 [INFO] train episode 19813: reward = -56.22, steps = 29 13:51:39 [INFO] train episode 19814: reward = -45.11, steps = 21 13:51:43 [INFO] train episode 19815: reward = -66.93, steps = 34 13:51:44 [INFO] train episode 19816: reward = -131.91, steps = 21 13:51:46 [INFO] train episode 19817: reward = -72.76, steps = 17 13:51:52 [INFO] train episode 19818: reward = -87.22, steps = 63 13:51:54 [INFO] train episode 19819: reward = -53.96, steps = 20 13:51:56 [INFO] train episode 19820: reward = -66.07, steps = 30 13:51:58 [INFO] train episode 19821: reward = -72.83, steps = 23 13:52:01 [INFO] train episode 19822: reward = -50.87, steps = 30 13:52:03 [INFO] train episode 19823: reward = -67.09, steps = 23 13:52:06 [INFO] train episode 19824: reward = -69.02, steps = 27 13:52:08 [INFO] train episode 19825: reward = -57.62, steps = 26 13:52:11 [INFO] train episode 19826: reward = -74.55, steps = 27 13:52:13 [INFO] train episode 19827: reward = -45.73, steps = 26 13:52:15 [INFO] train episode 19828: reward = -51.60, steps = 20 13:52:18 [INFO] train episode 19829: reward = -100.16, steps = 35 13:52:20 [INFO] train episode 19830: reward = -55.62, steps = 25 13:52:23 [INFO] train episode 19831: reward = -82.68, steps = 29 13:52:27 [INFO] train episode 19832: reward = -68.78, steps = 43 13:52:31 [INFO] train episode 19833: reward = -111.82, steps = 41 13:52:34 [INFO] train episode 19834: reward = -108.91, steps = 37 13:52:36 [INFO] train episode 19835: reward = -64.17, steps = 22 13:52:38 [INFO] train episode 19836: reward = -67.89, steps = 20 13:52:41 [INFO] train episode 19837: reward = -102.35, steps = 27 13:52:43 [INFO] train episode 19838: reward = -60.79, steps = 24 13:52:46 [INFO] train episode 19839: reward = -118.74, steps = 40 13:52:48 [INFO] train episode 19840: reward = -65.18, steps = 22 13:52:51 [INFO] train episode 19841: reward = -58.02, steps = 27 13:52:53 [INFO] train episode 19842: reward = -49.19, steps = 22 13:52:55 [INFO] train episode 19843: reward = -112.32, steps = 29 13:52:58 [INFO] train episode 19844: reward = -117.38, steps = 30 13:53:02 [INFO] train episode 19845: reward = -109.51, steps = 38 13:53:05 [INFO] train episode 19846: reward = -101.15, steps = 37 13:53:07 [INFO] train episode 19847: reward = -62.51, steps = 23 13:53:11 [INFO] train episode 19848: reward = -60.10, steps = 43 13:53:13 [INFO] train episode 19849: reward = -89.74, steps = 25 13:53:17 [INFO] train episode 19850: reward = -47.50, steps = 46 13:53:22 [INFO] train episode 19851: reward = -115.65, steps = 50 13:53:26 [INFO] train episode 19852: reward = -84.58, steps = 41 13:53:28 [INFO] train episode 19853: reward = -68.78, steps = 21 13:53:32 [INFO] train episode 19854: reward = -107.56, steps = 50 13:53:36 [INFO] train episode 19855: reward = -123.19, steps = 46 13:53:39 [INFO] train episode 19856: reward = -52.15, steps = 33 13:53:41 [INFO] train episode 19857: reward = -44.62, steps = 20 13:53:44 [INFO] train episode 19858: reward = -92.84, steps = 35 13:53:48 [INFO] train episode 19859: reward = -69.78, steps = 39 13:53:50 [INFO] train episode 19860: reward = -57.32, steps = 23 13:53:53 [INFO] train episode 19861: reward = -77.96, steps = 36 13:53:57 [INFO] train episode 19862: reward = -96.37, steps = 42 13:53:59 [INFO] train episode 19863: reward = -101.47, steps = 22 13:54:01 [INFO] train episode 19864: reward = -77.08, steps = 27 13:54:05 [INFO] train episode 19865: reward = -96.20, steps = 38 13:54:07 [INFO] train episode 19866: reward = -55.78, steps = 25 13:54:09 [INFO] train episode 19867: reward = -86.20, steps = 19 13:54:11 [INFO] train episode 19868: reward = -101.04, steps = 23 13:54:15 [INFO] train episode 19869: reward = -85.19, steps = 39 13:54:17 [INFO] train episode 19870: reward = -75.61, steps = 25 13:54:19 [INFO] train episode 19871: reward = -48.87, steps = 25 13:54:22 [INFO] train episode 19872: reward = -103.83, steps = 36 13:54:25 [INFO] train episode 19873: reward = -64.44, steps = 33 13:54:28 [INFO] train episode 19874: reward = -89.72, steps = 26 13:54:29 [INFO] train episode 19875: reward = -63.88, steps = 20 13:54:32 [INFO] train episode 19876: reward = -74.95, steps = 23 13:54:34 [INFO] train episode 19877: reward = -98.63, steps = 26 13:54:36 [INFO] train episode 19878: reward = -76.23, steps = 22 13:54:39 [INFO] train episode 19879: reward = -87.10, steps = 30 13:54:41 [INFO] train episode 19880: reward = -69.75, steps = 23 13:54:44 [INFO] train episode 19881: reward = -116.05, steps = 35 13:54:47 [INFO] train episode 19882: reward = -56.62, steps = 29 13:54:48 [INFO] train episode 19883: reward = -76.30, steps = 21 13:54:50 [INFO] train episode 19884: reward = -83.27, steps = 19 13:54:52 [INFO] train episode 19885: reward = -102.78, steps = 20 13:54:54 [INFO] train episode 19886: reward = -90.63, steps = 22 13:54:56 [INFO] train episode 19887: reward = -45.14, steps = 19 13:54:59 [INFO] train episode 19888: reward = -75.13, steps = 31 13:55:04 [INFO] train episode 19889: reward = -89.10, steps = 55 13:55:06 [INFO] train episode 19890: reward = -57.49, steps = 32 13:55:10 [INFO] train episode 19891: reward = -78.10, steps = 32 13:55:12 [INFO] train episode 19892: reward = -58.16, steps = 27 13:55:15 [INFO] train episode 19893: reward = -109.40, steps = 35 13:55:17 [INFO] train episode 19894: reward = -98.87, steps = 20 13:55:19 [INFO] train episode 19895: reward = -57.94, steps = 20 13:55:21 [INFO] train episode 19896: reward = -82.91, steps = 23 13:55:24 [INFO] train episode 19897: reward = -58.97, steps = 33 13:55:26 [INFO] train episode 19898: reward = -106.36, steps = 22 13:55:29 [INFO] train episode 19899: reward = -59.40, steps = 32 13:55:31 [INFO] train episode 19900: reward = -79.87, steps = 23 13:55:34 [INFO] train episode 19901: reward = -77.97, steps = 34 13:55:39 [INFO] train episode 19902: reward = -84.46, steps = 54 13:55:41 [INFO] train episode 19903: reward = -69.67, steps = 26 13:55:44 [INFO] train episode 19904: reward = -84.57, steps = 31 13:55:48 [INFO] train episode 19905: reward = -87.56, steps = 40 13:55:50 [INFO] train episode 19906: reward = -73.66, steps = 28 13:55:52 [INFO] train episode 19907: reward = -76.08, steps = 23 13:55:55 [INFO] train episode 19908: reward = -62.02, steps = 24 13:55:58 [INFO] train episode 19909: reward = -60.92, steps = 38 13:56:00 [INFO] train episode 19910: reward = -75.15, steps = 19 13:56:02 [INFO] train episode 19911: reward = -75.86, steps = 19 13:56:04 [INFO] train episode 19912: reward = -82.75, steps = 25 13:56:09 [INFO] train episode 19913: reward = -132.59, steps = 58 13:56:13 [INFO] train episode 19914: reward = -66.90, steps = 48 13:56:16 [INFO] train episode 19915: reward = -77.87, steps = 19 13:56:22 [INFO] train episode 19916: reward = -121.47, steps = 70 13:56:27 [INFO] train episode 19917: reward = -105.00, steps = 50 13:56:29 [INFO] train episode 19918: reward = -63.52, steps = 29 13:56:33 [INFO] train episode 19919: reward = -105.66, steps = 40 13:56:36 [INFO] train episode 19920: reward = -81.20, steps = 29 13:56:38 [INFO] train episode 19921: reward = -104.09, steps = 19 13:56:40 [INFO] train episode 19922: reward = -46.56, steps = 28 13:56:42 [INFO] train episode 19923: reward = -78.79, steps = 26 13:56:45 [INFO] train episode 19924: reward = -79.14, steps = 27 13:56:48 [INFO] train episode 19925: reward = -81.32, steps = 36 13:56:51 [INFO] train episode 19926: reward = -53.86, steps = 26 13:56:53 [INFO] train episode 19927: reward = -81.64, steps = 32 13:56:59 [INFO] train episode 19928: reward = -76.18, steps = 59 13:57:01 [INFO] train episode 19929: reward = -72.00, steps = 20 13:57:03 [INFO] train episode 19930: reward = -79.87, steps = 27 13:57:06 [INFO] train episode 19931: reward = -57.40, steps = 34 13:57:10 [INFO] train episode 19932: reward = -81.59, steps = 45 13:57:12 [INFO] train episode 19933: reward = -90.97, steps = 26 13:57:14 [INFO] train episode 19934: reward = -90.85, steps = 22 13:57:19 [INFO] train episode 19935: reward = -96.83, steps = 49 13:57:23 [INFO] train episode 19936: reward = -125.18, steps = 41 13:57:26 [INFO] train episode 19937: reward = -100.62, steps = 33 13:57:28 [INFO] train episode 19938: reward = -49.23, steps = 28 13:57:33 [INFO] train episode 19939: reward = -140.79, steps = 63 13:57:37 [INFO] train episode 19940: reward = -143.60, steps = 47 13:57:40 [INFO] train episode 19941: reward = -57.84, steps = 28 13:57:42 [INFO] train episode 19942: reward = -48.58, steps = 20 13:57:46 [INFO] train episode 19943: reward = -124.20, steps = 49 13:57:48 [INFO] train episode 19944: reward = -83.35, steps = 19 13:57:58 [INFO] train episode 19945: reward = -140.48, steps = 111 13:58:01 [INFO] train episode 19946: reward = -44.67, steps = 34 13:58:03 [INFO] train episode 19947: reward = -62.89, steps = 22 13:58:05 [INFO] train episode 19948: reward = -98.75, steps = 32 13:58:08 [INFO] train episode 19949: reward = -79.96, steps = 30 13:58:11 [INFO] train episode 19950: reward = -60.72, steps = 28 13:58:14 [INFO] train episode 19951: reward = -87.57, steps = 32 13:58:16 [INFO] train episode 19952: reward = -63.12, steps = 22 13:58:17 [INFO] train episode 19953: reward = -103.79, steps = 20 13:58:20 [INFO] train episode 19954: reward = -96.01, steps = 31 13:58:23 [INFO] train episode 19955: reward = -83.21, steps = 33 13:58:27 [INFO] train episode 19956: reward = -49.24, steps = 37 13:58:28 [INFO] train episode 19957: reward = -53.57, steps = 20 13:58:31 [INFO] train episode 19958: reward = -58.37, steps = 25 13:58:33 [INFO] train episode 19959: reward = -53.61, steps = 20 13:58:35 [INFO] train episode 19960: reward = -63.24, steps = 23 13:58:37 [INFO] train episode 19961: reward = -92.95, steps = 24 13:58:43 [INFO] train episode 19962: reward = -152.91, steps = 71 13:58:46 [INFO] train episode 19963: reward = -99.03, steps = 29 13:58:52 [INFO] train episode 19964: reward = -111.30, steps = 71 13:58:54 [INFO] train episode 19965: reward = -39.79, steps = 23 13:58:57 [INFO] train episode 19966: reward = -72.20, steps = 38 13:59:00 [INFO] train episode 19967: reward = -74.17, steps = 24 13:59:02 [INFO] train episode 19968: reward = -72.41, steps = 30 13:59:04 [INFO] train episode 19969: reward = -64.41, steps = 21 13:59:06 [INFO] train episode 19970: reward = -64.68, steps = 22 13:59:09 [INFO] train episode 19971: reward = -70.82, steps = 29 13:59:11 [INFO] train episode 19972: reward = -53.24, steps = 26 13:59:14 [INFO] train episode 19973: reward = -63.65, steps = 38 13:59:16 [INFO] train episode 19974: reward = -75.21, steps = 20 13:59:19 [INFO] train episode 19975: reward = -105.38, steps = 32 13:59:22 [INFO] train episode 19976: reward = -107.44, steps = 24 13:59:24 [INFO] train episode 19977: reward = -40.91, steps = 23 13:59:27 [INFO] train episode 19978: reward = -88.08, steps = 29 13:59:29 [INFO] train episode 19979: reward = -73.62, steps = 25 13:59:35 [INFO] train episode 19980: reward = -151.52, steps = 71 13:59:39 [INFO] train episode 19981: reward = -66.22, steps = 46 13:59:42 [INFO] train episode 19982: reward = -53.81, steps = 34 13:59:45 [INFO] train episode 19983: reward = -85.06, steps = 36 13:59:47 [INFO] train episode 19984: reward = -43.23, steps = 23 13:59:52 [INFO] train episode 19985: reward = -77.69, steps = 46 13:59:54 [INFO] train episode 19986: reward = -57.26, steps = 25 13:59:56 [INFO] train episode 19987: reward = -55.52, steps = 21 14:00:00 [INFO] train episode 19988: reward = -98.08, steps = 54 14:00:03 [INFO] train episode 19989: reward = -49.14, steps = 26 14:00:07 [INFO] train episode 19990: reward = -113.42, steps = 49 14:00:09 [INFO] train episode 19991: reward = -43.65, steps = 27 14:00:12 [INFO] train episode 19992: reward = -74.03, steps = 32 14:00:16 [INFO] train episode 19993: reward = -124.39, steps = 40 14:00:18 [INFO] train episode 19994: reward = -78.42, steps = 22 14:00:21 [INFO] train episode 19995: reward = -91.49, steps = 36 14:00:23 [INFO] train episode 19996: reward = -68.15, steps = 21 14:00:25 [INFO] train episode 19997: reward = -60.46, steps = 19 14:00:26 [INFO] train episode 19998: reward = -83.78, steps = 21 14:00:30 [INFO] train episode 19999: reward = -55.11, steps = 41 14:00:33 [INFO] train episode 20000: reward = -77.70, steps = 36 14:00:36 [INFO] train episode 20001: reward = -88.26, steps = 36 14:00:39 [INFO] train episode 20002: reward = -80.35, steps = 32 14:00:43 [INFO] train episode 20003: reward = -62.73, steps = 40 14:00:45 [INFO] train episode 20004: reward = -73.29, steps = 20 14:00:47 [INFO] train episode 20005: reward = -46.02, steps = 25 14:00:51 [INFO] train episode 20006: reward = -59.17, steps = 46 14:00:56 [INFO] train episode 20007: reward = -110.44, steps = 60 14:00:59 [INFO] train episode 20008: reward = -74.28, steps = 28 14:01:01 [INFO] train episode 20009: reward = -75.48, steps = 23 14:01:05 [INFO] train episode 20010: reward = -89.46, steps = 45 14:01:07 [INFO] train episode 20011: reward = -71.84, steps = 24 14:01:11 [INFO] train episode 20012: reward = -86.64, steps = 42 14:01:13 [INFO] train episode 20013: reward = -39.56, steps = 27 14:01:15 [INFO] train episode 20014: reward = -61.30, steps = 21 14:01:17 [INFO] train episode 20015: reward = -91.55, steps = 25 14:01:19 [INFO] train episode 20016: reward = -61.58, steps = 23 14:01:23 [INFO] train episode 20017: reward = -85.12, steps = 42 14:01:25 [INFO] train episode 20018: reward = -88.93, steps = 21 14:01:27 [INFO] train episode 20019: reward = -80.46, steps = 23 14:01:29 [INFO] train episode 20020: reward = -64.01, steps = 22 14:01:31 [INFO] train episode 20021: reward = -63.39, steps = 19 14:01:32 [INFO] train episode 20022: reward = -85.39, steps = 17 14:01:34 [INFO] train episode 20023: reward = -66.57, steps = 22 14:01:36 [INFO] train episode 20024: reward = -69.60, steps = 23 14:01:39 [INFO] train episode 20025: reward = -49.59, steps = 25 14:01:40 [INFO] train episode 20026: reward = -42.96, steps = 20 14:01:45 [INFO] train episode 20027: reward = -107.64, steps = 50 14:01:48 [INFO] train episode 20028: reward = -43.68, steps = 34 14:01:52 [INFO] train episode 20029: reward = -68.24, steps = 50 14:01:54 [INFO] train episode 20030: reward = -78.46, steps = 20 14:01:56 [INFO] train episode 20031: reward = -34.55, steps = 23 14:02:01 [INFO] train episode 20032: reward = -140.99, steps = 44 14:02:03 [INFO] train episode 20033: reward = -108.20, steps = 26 14:02:05 [INFO] train episode 20034: reward = -81.65, steps = 25 14:02:08 [INFO] train episode 20035: reward = -77.34, steps = 29 14:02:10 [INFO] train episode 20036: reward = -64.05, steps = 25 14:02:12 [INFO] train episode 20037: reward = -71.05, steps = 29 14:02:14 [INFO] train episode 20038: reward = -81.38, steps = 24 14:02:19 [INFO] train episode 20039: reward = -41.85, steps = 36 14:02:21 [INFO] train episode 20040: reward = -58.21, steps = 28 14:02:23 [INFO] train episode 20041: reward = -83.46, steps = 20 14:02:26 [INFO] train episode 20042: reward = -55.41, steps = 41 14:02:30 [INFO] train episode 20043: reward = -63.56, steps = 46 14:02:33 [INFO] train episode 20044: reward = -70.88, steps = 26 14:02:35 [INFO] train episode 20045: reward = -90.04, steps = 24 14:02:40 [INFO] train episode 20046: reward = -84.21, steps = 54 14:02:43 [INFO] train episode 20047: reward = -102.62, steps = 35 14:02:45 [INFO] train episode 20048: reward = -91.77, steps = 22 14:02:48 [INFO] train episode 20049: reward = -67.18, steps = 26 14:02:51 [INFO] train episode 20050: reward = -70.95, steps = 35 14:02:53 [INFO] train episode 20051: reward = -129.11, steps = 28 14:02:55 [INFO] train episode 20052: reward = -117.65, steps = 20 14:02:57 [INFO] train episode 20053: reward = -72.61, steps = 22 14:02:59 [INFO] train episode 20054: reward = -62.43, steps = 22 14:03:01 [INFO] train episode 20055: reward = -83.20, steps = 21 14:03:03 [INFO] train episode 20056: reward = -75.08, steps = 22 14:03:05 [INFO] train episode 20057: reward = -75.99, steps = 24 14:03:08 [INFO] train episode 20058: reward = -113.51, steps = 38 14:03:11 [INFO] train episode 20059: reward = -65.43, steps = 25 14:03:14 [INFO] train episode 20060: reward = -62.41, steps = 33 14:03:18 [INFO] train episode 20061: reward = -96.38, steps = 50 14:03:21 [INFO] train episode 20062: reward = -81.92, steps = 32 14:03:23 [INFO] train episode 20063: reward = -51.67, steps = 23 14:03:25 [INFO] train episode 20064: reward = -84.78, steps = 23 14:03:27 [INFO] train episode 20065: reward = -66.22, steps = 24 14:03:29 [INFO] train episode 20066: reward = -50.13, steps = 20 14:03:32 [INFO] train episode 20067: reward = -113.53, steps = 31 14:03:35 [INFO] train episode 20068: reward = -73.07, steps = 35 14:03:38 [INFO] train episode 20069: reward = -67.79, steps = 36 14:03:40 [INFO] train episode 20070: reward = -87.59, steps = 20 14:03:46 [INFO] train episode 20071: reward = -129.93, steps = 64 14:03:50 [INFO] train episode 20072: reward = -97.78, steps = 49 14:03:52 [INFO] train episode 20073: reward = -93.17, steps = 20 14:03:54 [INFO] train episode 20074: reward = -70.72, steps = 24 14:03:58 [INFO] train episode 20075: reward = -102.12, steps = 42 14:04:00 [INFO] train episode 20076: reward = -78.64, steps = 27 14:04:04 [INFO] train episode 20077: reward = -49.93, steps = 46 14:04:08 [INFO] train episode 20078: reward = -134.63, steps = 44 14:04:11 [INFO] train episode 20079: reward = -60.47, steps = 28 14:04:13 [INFO] train episode 20080: reward = -54.90, steps = 21 14:04:14 [INFO] train episode 20081: reward = -120.39, steps = 17 14:04:17 [INFO] train episode 20082: reward = -65.28, steps = 36 14:04:20 [INFO] train episode 20083: reward = -82.86, steps = 26 14:04:22 [INFO] train episode 20084: reward = -74.79, steps = 31 14:04:24 [INFO] train episode 20085: reward = -101.40, steps = 20 14:04:27 [INFO] train episode 20086: reward = -91.04, steps = 26 14:04:29 [INFO] train episode 20087: reward = -82.08, steps = 21 14:04:31 [INFO] train episode 20088: reward = -58.94, steps = 31 14:04:35 [INFO] train episode 20089: reward = -53.34, steps = 40 14:04:38 [INFO] train episode 20090: reward = -88.39, steps = 35 14:04:40 [INFO] train episode 20091: reward = -54.66, steps = 21 14:04:44 [INFO] train episode 20092: reward = -81.78, steps = 50 14:04:47 [INFO] train episode 20093: reward = -55.47, steps = 26 14:04:48 [INFO] train episode 20094: reward = -41.53, steps = 22 14:04:50 [INFO] train episode 20095: reward = -73.21, steps = 21 14:04:52 [INFO] train episode 20096: reward = -53.93, steps = 21 14:04:55 [INFO] train episode 20097: reward = -57.02, steps = 30 14:04:56 [INFO] train episode 20098: reward = -100.83, steps = 19 14:04:59 [INFO] train episode 20099: reward = -55.29, steps = 20 14:05:01 [INFO] train episode 20100: reward = -114.32, steps = 25 14:05:03 [INFO] train episode 20101: reward = -57.48, steps = 24 14:05:05 [INFO] train episode 20102: reward = -70.23, steps = 21 14:05:08 [INFO] train episode 20103: reward = -56.96, steps = 33 14:05:10 [INFO] train episode 20104: reward = -69.90, steps = 22 14:05:12 [INFO] train episode 20105: reward = -91.74, steps = 22 14:05:15 [INFO] train episode 20106: reward = -65.10, steps = 24 14:05:18 [INFO] train episode 20107: reward = -56.69, steps = 30 14:05:20 [INFO] train episode 20108: reward = -86.20, steps = 28 14:05:22 [INFO] train episode 20109: reward = -52.92, steps = 22 14:05:25 [INFO] train episode 20110: reward = -66.11, steps = 33 14:05:29 [INFO] train episode 20111: reward = -47.42, steps = 39 14:05:31 [INFO] train episode 20112: reward = -69.05, steps = 24 14:05:33 [INFO] train episode 20113: reward = -69.00, steps = 28 14:05:36 [INFO] train episode 20114: reward = -72.02, steps = 28 14:05:38 [INFO] train episode 20115: reward = -56.96, steps = 25 14:05:40 [INFO] train episode 20116: reward = -99.70, steps = 26 14:05:43 [INFO] train episode 20117: reward = -59.40, steps = 28 14:05:45 [INFO] train episode 20118: reward = -72.03, steps = 28 14:05:48 [INFO] train episode 20119: reward = -69.89, steps = 26 14:05:49 [INFO] train episode 20120: reward = -103.87, steps = 18 14:05:51 [INFO] train episode 20121: reward = -67.13, steps = 24 14:05:56 [INFO] train episode 20122: reward = -78.64, steps = 52 14:05:58 [INFO] train episode 20123: reward = -57.86, steps = 23 14:06:00 [INFO] train episode 20124: reward = -55.48, steps = 28 14:06:03 [INFO] train episode 20125: reward = -78.43, steps = 26 14:06:05 [INFO] train episode 20126: reward = -105.31, steps = 27 14:06:08 [INFO] train episode 20127: reward = -59.74, steps = 28 14:06:11 [INFO] train episode 20128: reward = -85.62, steps = 41 14:06:13 [INFO] train episode 20129: reward = -52.45, steps = 23 14:06:15 [INFO] train episode 20130: reward = -66.80, steps = 22 14:06:18 [INFO] train episode 20131: reward = -87.19, steps = 29 14:06:20 [INFO] train episode 20132: reward = -61.58, steps = 22 14:06:23 [INFO] train episode 20133: reward = -60.30, steps = 36 14:06:28 [INFO] train episode 20134: reward = -73.42, steps = 55 14:06:30 [INFO] train episode 20135: reward = -62.25, steps = 20 14:06:32 [INFO] train episode 20136: reward = -107.89, steps = 21 14:06:33 [INFO] train episode 20137: reward = -62.67, steps = 22 14:06:35 [INFO] train episode 20138: reward = -58.80, steps = 20 14:06:38 [INFO] train episode 20139: reward = -63.63, steps = 27 14:06:41 [INFO] train episode 20140: reward = -81.53, steps = 28 14:06:44 [INFO] train episode 20141: reward = -91.20, steps = 41 14:06:47 [INFO] train episode 20142: reward = -70.00, steps = 39 14:06:49 [INFO] train episode 20143: reward = -77.11, steps = 20 14:06:52 [INFO] train episode 20144: reward = -46.75, steps = 28 14:06:54 [INFO] train episode 20145: reward = -82.43, steps = 21 14:06:56 [INFO] train episode 20146: reward = -83.28, steps = 20 14:06:58 [INFO] train episode 20147: reward = -95.93, steps = 22 14:07:00 [INFO] train episode 20148: reward = -52.10, steps = 33 14:07:02 [INFO] train episode 20149: reward = -55.94, steps = 21 14:07:05 [INFO] train episode 20150: reward = -69.12, steps = 28 14:07:07 [INFO] train episode 20151: reward = -64.80, steps = 21 14:07:08 [INFO] train episode 20152: reward = -91.34, steps = 18 14:07:10 [INFO] train episode 20153: reward = -58.56, steps = 20 14:07:12 [INFO] train episode 20154: reward = -73.08, steps = 23 14:07:16 [INFO] train episode 20155: reward = -96.77, steps = 38 14:07:17 [INFO] train episode 20156: reward = -62.69, steps = 19 14:07:20 [INFO] train episode 20157: reward = -83.20, steps = 31 14:07:23 [INFO] train episode 20158: reward = -84.46, steps = 30 14:07:25 [INFO] train episode 20159: reward = -41.02, steps = 24 14:07:27 [INFO] train episode 20160: reward = -61.24, steps = 22 14:07:30 [INFO] train episode 20161: reward = -92.60, steps = 29 14:07:33 [INFO] train episode 20162: reward = -60.15, steps = 36 14:07:35 [INFO] train episode 20163: reward = -74.63, steps = 27 14:07:37 [INFO] train episode 20164: reward = -95.40, steps = 24 14:07:40 [INFO] train episode 20165: reward = -54.10, steps = 25 14:07:42 [INFO] train episode 20166: reward = -65.63, steps = 24 14:07:45 [INFO] train episode 20167: reward = -58.18, steps = 29 14:07:48 [INFO] train episode 20168: reward = -112.00, steps = 44 14:07:51 [INFO] train episode 20169: reward = -91.56, steps = 27 14:07:53 [INFO] train episode 20170: reward = -61.58, steps = 22 14:07:55 [INFO] train episode 20171: reward = -118.35, steps = 30 14:07:59 [INFO] train episode 20172: reward = -102.46, steps = 36 14:08:01 [INFO] train episode 20173: reward = -74.75, steps = 22 14:08:04 [INFO] train episode 20174: reward = -66.21, steps = 33 14:08:05 [INFO] train episode 20175: reward = -72.41, steps = 22 14:08:09 [INFO] train episode 20176: reward = -72.47, steps = 36 14:08:13 [INFO] train episode 20177: reward = -114.29, steps = 39 14:08:17 [INFO] train episode 20178: reward = -55.27, steps = 44 14:08:21 [INFO] train episode 20179: reward = -101.06, steps = 43 14:08:23 [INFO] train episode 20180: reward = -45.60, steps = 23 14:08:25 [INFO] train episode 20181: reward = -80.81, steps = 33 14:08:29 [INFO] train episode 20182: reward = -71.07, steps = 44 14:08:34 [INFO] train episode 20183: reward = -78.41, steps = 48 14:08:36 [INFO] train episode 20184: reward = -80.02, steps = 21 14:08:38 [INFO] train episode 20185: reward = -60.68, steps = 19 14:08:40 [INFO] train episode 20186: reward = -71.62, steps = 29 14:08:42 [INFO] train episode 20187: reward = -76.45, steps = 19 14:08:44 [INFO] train episode 20188: reward = -73.54, steps = 19 14:08:46 [INFO] train episode 20189: reward = -56.01, steps = 26 14:08:48 [INFO] train episode 20190: reward = -73.77, steps = 23 14:08:50 [INFO] train episode 20191: reward = -49.22, steps = 25 14:08:54 [INFO] train episode 20192: reward = -74.79, steps = 40 14:08:57 [INFO] train episode 20193: reward = -89.09, steps = 36 14:09:00 [INFO] train episode 20194: reward = -95.94, steps = 40 14:09:02 [INFO] train episode 20195: reward = -69.75, steps = 20 14:09:05 [INFO] train episode 20196: reward = -60.58, steps = 28 14:09:08 [INFO] train episode 20197: reward = -78.88, steps = 40 14:09:13 [INFO] train episode 20198: reward = -105.65, steps = 49 14:09:17 [INFO] train episode 20199: reward = -59.73, steps = 46 14:09:21 [INFO] train episode 20200: reward = -116.75, steps = 53 14:09:24 [INFO] train episode 20201: reward = -60.83, steps = 27 14:09:29 [INFO] train episode 20202: reward = -104.50, steps = 57 14:09:32 [INFO] train episode 20203: reward = -100.88, steps = 37 14:09:33 [INFO] train episode 20204: reward = -56.00, steps = 20 14:09:36 [INFO] train episode 20205: reward = -55.91, steps = 21 14:09:38 [INFO] train episode 20206: reward = -60.23, steps = 28 14:09:43 [INFO] train episode 20207: reward = -86.11, steps = 54 14:09:45 [INFO] train episode 20208: reward = -40.61, steps = 20 14:09:47 [INFO] train episode 20209: reward = -72.97, steps = 27 14:09:50 [INFO] train episode 20210: reward = -95.27, steps = 31 14:09:52 [INFO] train episode 20211: reward = -71.64, steps = 28 14:09:56 [INFO] train episode 20212: reward = -88.96, steps = 44 14:10:00 [INFO] train episode 20213: reward = -74.97, steps = 39 14:10:02 [INFO] train episode 20214: reward = -70.23, steps = 23 14:10:04 [INFO] train episode 20215: reward = -82.97, steps = 23 14:10:05 [INFO] train episode 20216: reward = -66.16, steps = 20 14:10:08 [INFO] train episode 20217: reward = -55.04, steps = 23 14:10:10 [INFO] train episode 20218: reward = -44.05, steps = 21 14:10:12 [INFO] train episode 20219: reward = -64.50, steps = 25 14:10:14 [INFO] train episode 20220: reward = -98.28, steps = 28 14:10:17 [INFO] train episode 20221: reward = -63.44, steps = 28 14:10:19 [INFO] train episode 20222: reward = -61.44, steps = 29 14:10:21 [INFO] train episode 20223: reward = -88.56, steps = 20 14:10:26 [INFO] train episode 20224: reward = -110.20, steps = 52 14:10:30 [INFO] train episode 20225: reward = -99.73, steps = 46 14:10:32 [INFO] train episode 20226: reward = -52.36, steps = 22 14:10:34 [INFO] train episode 20227: reward = -73.62, steps = 25 14:10:36 [INFO] train episode 20228: reward = -51.11, steps = 22 14:10:39 [INFO] train episode 20229: reward = -65.52, steps = 27 14:10:41 [INFO] train episode 20230: reward = -95.79, steps = 22 14:10:43 [INFO] train episode 20231: reward = -89.77, steps = 20 14:10:45 [INFO] train episode 20232: reward = -64.54, steps = 24 14:10:47 [INFO] train episode 20233: reward = -74.84, steps = 27 14:10:49 [INFO] train episode 20234: reward = -52.46, steps = 21 14:10:52 [INFO] train episode 20235: reward = -159.04, steps = 35 14:10:54 [INFO] train episode 20236: reward = -54.46, steps = 23 14:10:56 [INFO] train episode 20237: reward = -45.40, steps = 22 14:10:58 [INFO] train episode 20238: reward = -90.59, steps = 22 14:11:02 [INFO] train episode 20239: reward = -110.39, steps = 42 14:11:05 [INFO] train episode 20240: reward = -41.02, steps = 28 14:11:08 [INFO] train episode 20241: reward = -54.35, steps = 34 14:11:11 [INFO] train episode 20242: reward = -50.23, steps = 33 14:11:13 [INFO] train episode 20243: reward = -60.80, steps = 21 14:11:15 [INFO] train episode 20244: reward = -88.38, steps = 20 14:11:17 [INFO] train episode 20245: reward = -65.40, steps = 26 14:11:19 [INFO] train episode 20246: reward = -48.50, steps = 21 14:11:22 [INFO] train episode 20247: reward = -53.83, steps = 30 14:11:24 [INFO] train episode 20248: reward = -75.85, steps = 26 14:11:27 [INFO] train episode 20249: reward = -62.77, steps = 33 14:11:31 [INFO] train episode 20250: reward = -73.41, steps = 39 14:11:32 [INFO] train episode 20251: reward = -71.46, steps = 19 14:11:34 [INFO] train episode 20252: reward = -45.05, steps = 21 14:11:37 [INFO] train episode 20253: reward = -81.51, steps = 30 14:11:39 [INFO] train episode 20254: reward = -87.42, steps = 29 14:11:42 [INFO] train episode 20255: reward = -64.66, steps = 34 14:11:47 [INFO] train episode 20256: reward = -97.24, steps = 53 14:11:49 [INFO] train episode 20257: reward = -69.85, steps = 20 14:11:51 [INFO] train episode 20258: reward = -54.91, steps = 22 14:11:54 [INFO] train episode 20259: reward = -78.90, steps = 36 14:11:57 [INFO] train episode 20260: reward = -92.29, steps = 31 14:11:59 [INFO] train episode 20261: reward = -70.17, steps = 25 14:12:02 [INFO] train episode 20262: reward = -73.73, steps = 27 14:12:04 [INFO] train episode 20263: reward = -111.33, steps = 27 14:12:08 [INFO] train episode 20264: reward = -64.04, steps = 50 14:12:11 [INFO] train episode 20265: reward = -105.89, steps = 28 14:12:12 [INFO] train episode 20266: reward = -86.25, steps = 19 14:12:17 [INFO] train episode 20267: reward = -102.66, steps = 49 14:12:20 [INFO] train episode 20268: reward = -111.04, steps = 39 14:12:27 [INFO] train episode 20269: reward = -137.92, steps = 71 14:12:29 [INFO] train episode 20270: reward = -67.64, steps = 32 14:12:34 [INFO] train episode 20271: reward = -119.45, steps = 46 14:12:35 [INFO] train episode 20272: reward = -67.78, steps = 19 14:12:39 [INFO] train episode 20273: reward = -90.41, steps = 41 14:12:41 [INFO] train episode 20274: reward = -87.62, steps = 29 14:12:43 [INFO] train episode 20275: reward = -78.92, steps = 20 14:12:45 [INFO] train episode 20276: reward = -83.00, steps = 19 14:12:47 [INFO] train episode 20277: reward = -80.43, steps = 19 14:12:48 [INFO] train episode 20278: reward = -115.11, steps = 21 14:12:51 [INFO] train episode 20279: reward = -73.78, steps = 25 14:12:53 [INFO] train episode 20280: reward = -107.80, steps = 25 14:12:55 [INFO] train episode 20281: reward = -71.51, steps = 22 14:12:59 [INFO] train episode 20282: reward = -114.58, steps = 44 14:13:02 [INFO] train episode 20283: reward = -91.02, steps = 32 14:13:04 [INFO] train episode 20284: reward = -91.51, steps = 20 14:13:06 [INFO] train episode 20285: reward = -60.57, steps = 28 14:13:11 [INFO] train episode 20286: reward = -102.74, steps = 53 14:13:15 [INFO] train episode 20287: reward = -118.09, steps = 45 14:13:21 [INFO] train episode 20288: reward = -90.37, steps = 71 14:13:23 [INFO] train episode 20289: reward = -68.07, steps = 20 14:13:26 [INFO] train episode 20290: reward = -120.02, steps = 27 14:13:28 [INFO] train episode 20291: reward = -103.49, steps = 21 14:13:31 [INFO] train episode 20292: reward = -90.33, steps = 38 14:13:34 [INFO] train episode 20293: reward = -71.70, steps = 31 14:13:36 [INFO] train episode 20294: reward = -69.55, steps = 23 14:13:40 [INFO] train episode 20295: reward = -125.32, steps = 41 14:13:43 [INFO] train episode 20296: reward = -151.43, steps = 43 14:13:45 [INFO] train episode 20297: reward = -63.50, steps = 21 14:13:48 [INFO] train episode 20298: reward = -67.51, steps = 35 14:13:50 [INFO] train episode 20299: reward = -55.57, steps = 21 14:13:53 [INFO] train episode 20300: reward = -71.67, steps = 27 14:13:55 [INFO] train episode 20301: reward = -60.70, steps = 30 14:13:58 [INFO] train episode 20302: reward = -48.98, steps = 25 14:14:01 [INFO] train episode 20303: reward = -66.70, steps = 26 14:14:03 [INFO] train episode 20304: reward = -80.08, steps = 21 14:14:05 [INFO] train episode 20305: reward = -73.42, steps = 22 14:14:07 [INFO] train episode 20306: reward = -85.18, steps = 22 14:14:09 [INFO] train episode 20307: reward = -105.69, steps = 19 14:14:10 [INFO] train episode 20308: reward = -97.98, steps = 20 14:14:13 [INFO] train episode 20309: reward = -71.12, steps = 28 14:14:16 [INFO] train episode 20310: reward = -70.23, steps = 29 14:14:20 [INFO] train episode 20311: reward = -104.49, steps = 43 14:14:24 [INFO] train episode 20312: reward = -77.93, steps = 47 14:14:26 [INFO] train episode 20313: reward = -68.64, steps = 23 14:14:28 [INFO] train episode 20314: reward = -82.11, steps = 21 14:14:31 [INFO] train episode 20315: reward = -84.80, steps = 29 14:14:32 [INFO] train episode 20316: reward = -84.74, steps = 22 14:14:34 [INFO] train episode 20317: reward = -88.64, steps = 20 14:14:37 [INFO] train episode 20318: reward = -94.48, steps = 31 14:14:40 [INFO] train episode 20319: reward = -76.31, steps = 31 14:14:43 [INFO] train episode 20320: reward = -81.99, steps = 34 14:14:45 [INFO] train episode 20321: reward = -96.51, steps = 24 14:14:47 [INFO] train episode 20322: reward = -70.61, steps = 20 14:14:49 [INFO] train episode 20323: reward = -87.17, steps = 27 14:14:52 [INFO] train episode 20324: reward = -66.10, steps = 28 14:14:54 [INFO] train episode 20325: reward = -54.36, steps = 20 14:14:58 [INFO] train episode 20326: reward = -81.78, steps = 44 14:15:02 [INFO] train episode 20327: reward = -124.94, steps = 50 14:15:05 [INFO] train episode 20328: reward = -55.95, steps = 25 14:15:06 [INFO] train episode 20329: reward = -74.97, steps = 22 14:15:09 [INFO] train episode 20330: reward = -69.70, steps = 33 14:15:11 [INFO] train episode 20331: reward = -123.35, steps = 20 14:15:13 [INFO] train episode 20332: reward = -56.34, steps = 19 14:15:15 [INFO] train episode 20333: reward = -67.66, steps = 22 14:15:17 [INFO] train episode 20334: reward = -119.83, steps = 24 14:15:20 [INFO] train episode 20335: reward = -95.48, steps = 30 14:15:24 [INFO] train episode 20336: reward = -48.35, steps = 46 14:15:26 [INFO] train episode 20337: reward = -78.52, steps = 22 14:15:28 [INFO] train episode 20338: reward = -53.27, steps = 24 14:15:30 [INFO] train episode 20339: reward = -59.21, steps = 23 14:15:34 [INFO] train episode 20340: reward = -99.11, steps = 40 14:15:37 [INFO] train episode 20341: reward = -93.03, steps = 32 14:15:40 [INFO] train episode 20342: reward = -160.49, steps = 31 14:15:42 [INFO] train episode 20343: reward = -80.87, steps = 26 14:15:44 [INFO] train episode 20344: reward = -57.96, steps = 20 14:15:47 [INFO] train episode 20345: reward = -66.55, steps = 38 14:15:49 [INFO] train episode 20346: reward = -56.86, steps = 20 14:15:52 [INFO] train episode 20347: reward = -75.49, steps = 34 14:15:55 [INFO] train episode 20348: reward = -57.84, steps = 26 14:15:57 [INFO] train episode 20349: reward = -77.25, steps = 26 14:15:59 [INFO] train episode 20350: reward = -51.80, steps = 22 14:16:02 [INFO] train episode 20351: reward = -55.69, steps = 40 14:16:06 [INFO] train episode 20352: reward = -139.31, steps = 36 14:16:11 [INFO] train episode 20353: reward = -111.90, steps = 54 14:16:14 [INFO] train episode 20354: reward = -88.99, steps = 32 14:16:16 [INFO] train episode 20355: reward = -91.46, steps = 32 14:16:19 [INFO] train episode 20356: reward = -66.68, steps = 32 14:16:21 [INFO] train episode 20357: reward = -68.57, steps = 22 14:16:24 [INFO] train episode 20358: reward = -81.74, steps = 25 14:16:27 [INFO] train episode 20359: reward = -57.27, steps = 30 14:16:29 [INFO] train episode 20360: reward = -90.73, steps = 23 14:16:33 [INFO] train episode 20361: reward = -150.41, steps = 47 14:16:37 [INFO] train episode 20362: reward = -102.73, steps = 45 14:16:39 [INFO] train episode 20363: reward = -70.49, steps = 32 14:16:42 [INFO] train episode 20364: reward = -83.21, steps = 23 14:16:44 [INFO] train episode 20365: reward = -53.93, steps = 24 14:16:48 [INFO] train episode 20366: reward = -120.68, steps = 41 14:16:50 [INFO] train episode 20367: reward = -113.27, steps = 31 14:16:53 [INFO] train episode 20368: reward = -59.73, steps = 24 14:16:54 [INFO] train episode 20369: reward = -54.18, steps = 21 14:16:59 [INFO] train episode 20370: reward = -136.54, steps = 41 14:17:02 [INFO] train episode 20371: reward = -48.25, steps = 31 14:17:05 [INFO] train episode 20372: reward = -129.04, steps = 38 14:17:09 [INFO] train episode 20373: reward = -123.25, steps = 47 14:17:13 [INFO] train episode 20374: reward = -86.50, steps = 39 14:17:15 [INFO] train episode 20375: reward = -63.78, steps = 23 14:17:19 [INFO] train episode 20376: reward = -92.99, steps = 37 14:17:21 [INFO] train episode 20377: reward = -87.82, steps = 28 14:17:23 [INFO] train episode 20378: reward = -77.56, steps = 21 14:17:27 [INFO] train episode 20379: reward = -97.03, steps = 44 14:17:29 [INFO] train episode 20380: reward = -68.78, steps = 20 14:17:33 [INFO] train episode 20381: reward = -98.12, steps = 49 14:17:36 [INFO] train episode 20382: reward = -46.72, steps = 30 14:17:38 [INFO] train episode 20383: reward = -71.92, steps = 31 14:17:40 [INFO] train episode 20384: reward = -50.49, steps = 22 14:17:43 [INFO] train episode 20385: reward = -41.80, steps = 29 14:17:46 [INFO] train episode 20386: reward = -72.04, steps = 36 14:17:49 [INFO] train episode 20387: reward = -102.97, steps = 25 14:17:51 [INFO] train episode 20388: reward = -57.87, steps = 23 14:17:53 [INFO] train episode 20389: reward = -82.02, steps = 25 14:17:55 [INFO] train episode 20390: reward = -45.29, steps = 28 14:17:58 [INFO] train episode 20391: reward = -50.08, steps = 27 14:18:01 [INFO] train episode 20392: reward = -91.42, steps = 39 14:18:04 [INFO] train episode 20393: reward = -84.57, steps = 24 14:18:07 [INFO] train episode 20394: reward = -63.87, steps = 32 14:18:10 [INFO] train episode 20395: reward = -70.23, steps = 36 14:18:12 [INFO] train episode 20396: reward = -74.52, steps = 22 14:18:14 [INFO] train episode 20397: reward = -76.49, steps = 26 14:18:18 [INFO] train episode 20398: reward = -87.34, steps = 47 14:18:21 [INFO] train episode 20399: reward = -67.80, steps = 22 14:18:22 [INFO] train episode 20400: reward = -63.33, steps = 19 14:18:25 [INFO] train episode 20401: reward = -98.63, steps = 34 14:18:27 [INFO] train episode 20402: reward = -78.78, steps = 26 14:18:30 [INFO] train episode 20403: reward = -100.01, steps = 29 14:18:32 [INFO] train episode 20404: reward = -55.55, steps = 20 14:18:34 [INFO] train episode 20405: reward = -44.89, steps = 23 14:18:41 [INFO] train episode 20406: reward = -150.39, steps = 78 14:18:43 [INFO] train episode 20407: reward = -69.40, steps = 22 14:18:46 [INFO] train episode 20408: reward = -76.46, steps = 38 14:18:48 [INFO] train episode 20409: reward = -72.51, steps = 22 14:18:50 [INFO] train episode 20410: reward = -48.35, steps = 19 14:18:52 [INFO] train episode 20411: reward = -44.03, steps = 25 14:18:54 [INFO] train episode 20412: reward = -63.84, steps = 21 14:18:56 [INFO] train episode 20413: reward = -57.38, steps = 21 14:19:00 [INFO] train episode 20414: reward = -93.02, steps = 42 14:19:02 [INFO] train episode 20415: reward = -63.75, steps = 22 14:19:04 [INFO] train episode 20416: reward = -61.65, steps = 25 14:19:06 [INFO] train episode 20417: reward = -51.15, steps = 20 14:19:08 [INFO] train episode 20418: reward = -83.66, steps = 29 14:19:12 [INFO] train episode 20419: reward = -48.03, steps = 31 14:19:13 [INFO] train episode 20420: reward = -83.14, steps = 21 14:19:15 [INFO] train episode 20421: reward = -96.42, steps = 20 14:19:17 [INFO] train episode 20422: reward = -88.01, steps = 25 14:19:21 [INFO] train episode 20423: reward = -62.08, steps = 35 14:19:23 [INFO] train episode 20424: reward = -83.93, steps = 29 14:19:25 [INFO] train episode 20425: reward = -46.94, steps = 21 14:19:30 [INFO] train episode 20426: reward = -110.77, steps = 54 14:19:34 [INFO] train episode 20427: reward = -78.12, steps = 40 14:19:36 [INFO] train episode 20428: reward = -71.07, steps = 21 14:19:40 [INFO] train episode 20429: reward = -95.16, steps = 49 14:19:42 [INFO] train episode 20430: reward = -61.21, steps = 24 14:19:44 [INFO] train episode 20431: reward = -54.57, steps = 22 14:19:46 [INFO] train episode 20432: reward = -60.63, steps = 20 14:19:49 [INFO] train episode 20433: reward = -99.97, steps = 33 14:19:51 [INFO] train episode 20434: reward = -81.23, steps = 25 14:19:53 [INFO] train episode 20435: reward = -54.09, steps = 26 14:19:57 [INFO] train episode 20436: reward = -55.09, steps = 23 14:19:59 [INFO] train episode 20437: reward = -83.97, steps = 23 14:20:01 [INFO] train episode 20438: reward = -125.44, steps = 27 14:20:03 [INFO] train episode 20439: reward = -50.36, steps = 20 14:20:05 [INFO] train episode 20440: reward = -92.80, steps = 26 14:20:08 [INFO] train episode 20441: reward = -71.19, steps = 27 14:20:10 [INFO] train episode 20442: reward = -63.11, steps = 24 14:20:11 [INFO] train episode 20443: reward = -92.72, steps = 20 14:20:13 [INFO] train episode 20444: reward = -54.00, steps = 21 14:20:16 [INFO] train episode 20445: reward = -54.64, steps = 21 14:20:18 [INFO] train episode 20446: reward = -74.97, steps = 22 14:20:20 [INFO] train episode 20447: reward = -56.58, steps = 33 14:20:24 [INFO] train episode 20448: reward = -52.56, steps = 49 14:20:27 [INFO] train episode 20449: reward = -53.48, steps = 30 14:20:29 [INFO] train episode 20450: reward = -73.73, steps = 23 14:20:31 [INFO] train episode 20451: reward = -58.62, steps = 21 14:20:34 [INFO] train episode 20452: reward = -92.68, steps = 35 14:20:37 [INFO] train episode 20453: reward = -89.37, steps = 23 14:20:39 [INFO] train episode 20454: reward = -51.44, steps = 22 14:20:42 [INFO] train episode 20455: reward = -81.14, steps = 41 14:20:44 [INFO] train episode 20456: reward = -97.90, steps = 22 14:20:46 [INFO] train episode 20457: reward = -45.50, steps = 23 14:20:50 [INFO] train episode 20458: reward = -81.55, steps = 32 14:20:52 [INFO] train episode 20459: reward = -89.00, steps = 19 14:20:55 [INFO] train episode 20460: reward = -62.98, steps = 36 14:20:58 [INFO] train episode 20461: reward = -47.80, steps = 25 14:21:00 [INFO] train episode 20462: reward = -78.16, steps = 22 14:21:03 [INFO] train episode 20463: reward = -89.07, steps = 29 14:21:07 [INFO] train episode 20464: reward = -76.34, steps = 40 14:21:09 [INFO] train episode 20465: reward = -69.36, steps = 24 14:21:12 [INFO] train episode 20466: reward = -89.61, steps = 25 14:21:14 [INFO] train episode 20467: reward = -77.04, steps = 20 14:21:15 [INFO] train episode 20468: reward = -95.95, steps = 18 14:21:17 [INFO] train episode 20469: reward = -46.42, steps = 21 14:21:19 [INFO] train episode 20470: reward = -107.14, steps = 20 14:21:21 [INFO] train episode 20471: reward = -70.09, steps = 23 14:21:24 [INFO] train episode 20472: reward = -67.72, steps = 26 14:21:26 [INFO] train episode 20473: reward = -69.12, steps = 29 14:21:29 [INFO] train episode 20474: reward = -51.52, steps = 26 14:21:31 [INFO] train episode 20475: reward = -57.44, steps = 23 14:21:35 [INFO] train episode 20476: reward = -96.32, steps = 46 14:21:37 [INFO] train episode 20477: reward = -62.98, steps = 22 14:21:40 [INFO] train episode 20478: reward = -57.08, steps = 27 14:21:42 [INFO] train episode 20479: reward = -112.17, steps = 27 14:21:46 [INFO] train episode 20480: reward = -75.58, steps = 41 14:21:49 [INFO] train episode 20481: reward = -81.15, steps = 34 14:21:51 [INFO] train episode 20482: reward = -107.42, steps = 23 14:21:55 [INFO] train episode 20483: reward = -78.93, steps = 47 14:21:57 [INFO] train episode 20484: reward = -58.89, steps = 21 14:21:59 [INFO] train episode 20485: reward = -62.30, steps = 24 14:22:03 [INFO] train episode 20486: reward = -97.23, steps = 42 14:22:07 [INFO] train episode 20487: reward = -97.34, steps = 49 14:22:13 [INFO] train episode 20488: reward = -188.53, steps = 62 14:22:14 [INFO] train episode 20489: reward = -56.23, steps = 20 14:22:16 [INFO] train episode 20490: reward = -59.57, steps = 20 14:22:18 [INFO] train episode 20491: reward = -74.58, steps = 22 14:22:21 [INFO] train episode 20492: reward = -78.54, steps = 38 14:22:23 [INFO] train episode 20493: reward = -66.86, steps = 24 14:22:26 [INFO] train episode 20494: reward = -83.72, steps = 31 14:22:29 [INFO] train episode 20495: reward = -80.53, steps = 26 14:22:31 [INFO] train episode 20496: reward = -58.29, steps = 26 14:22:35 [INFO] train episode 20497: reward = -57.83, steps = 42 14:22:40 [INFO] train episode 20498: reward = -79.65, steps = 53 14:22:42 [INFO] train episode 20499: reward = -44.85, steps = 25 14:22:44 [INFO] train episode 20500: reward = -75.65, steps = 28 14:22:47 [INFO] train episode 20501: reward = -112.74, steps = 28 14:22:49 [INFO] train episode 20502: reward = -77.68, steps = 25 14:22:51 [INFO] train episode 20503: reward = -94.30, steps = 22 14:22:53 [INFO] train episode 20504: reward = -50.69, steps = 22 14:22:56 [INFO] train episode 20505: reward = -59.08, steps = 24 14:22:59 [INFO] train episode 20506: reward = -92.78, steps = 35 14:23:02 [INFO] train episode 20507: reward = -65.83, steps = 27 14:23:05 [INFO] train episode 20508: reward = -88.83, steps = 33 14:23:07 [INFO] train episode 20509: reward = -71.72, steps = 29 14:23:10 [INFO] train episode 20510: reward = -48.76, steps = 38 14:23:13 [INFO] train episode 20511: reward = -94.31, steps = 32 14:23:16 [INFO] train episode 20512: reward = -85.43, steps = 28 14:23:17 [INFO] train episode 20513: reward = -81.03, steps = 18 14:23:21 [INFO] train episode 20514: reward = -72.53, steps = 46 14:23:23 [INFO] train episode 20515: reward = -104.99, steps = 22 14:23:27 [INFO] train episode 20516: reward = -109.54, steps = 41 14:23:29 [INFO] train episode 20517: reward = -56.69, steps = 23 14:23:30 [INFO] train episode 20518: reward = -102.96, steps = 18 14:23:33 [INFO] train episode 20519: reward = -58.67, steps = 23 14:23:35 [INFO] train episode 20520: reward = -78.21, steps = 21 14:23:36 [INFO] train episode 20521: reward = -62.89, steps = 19 14:23:39 [INFO] train episode 20522: reward = -66.61, steps = 34 14:23:42 [INFO] train episode 20523: reward = -69.99, steps = 27 14:23:44 [INFO] train episode 20524: reward = -43.81, steps = 27 14:23:46 [INFO] train episode 20525: reward = -122.49, steps = 19 14:23:48 [INFO] train episode 20526: reward = -73.02, steps = 20 14:23:50 [INFO] train episode 20527: reward = -75.50, steps = 22 14:23:52 [INFO] train episode 20528: reward = -74.55, steps = 24 14:23:55 [INFO] train episode 20529: reward = -80.18, steps = 34 14:24:01 [INFO] train episode 20530: reward = -145.00, steps = 69 14:24:03 [INFO] train episode 20531: reward = -86.85, steps = 23 14:24:05 [INFO] train episode 20532: reward = -55.08, steps = 21 14:24:08 [INFO] train episode 20533: reward = -75.01, steps = 33 14:24:11 [INFO] train episode 20534: reward = -49.28, steps = 28 14:24:13 [INFO] train episode 20535: reward = -56.21, steps = 24 14:24:15 [INFO] train episode 20536: reward = -75.55, steps = 21 14:24:17 [INFO] train episode 20537: reward = -96.26, steps = 22 14:24:19 [INFO] train episode 20538: reward = -74.03, steps = 25 14:24:22 [INFO] train episode 20539: reward = -97.30, steps = 31 14:24:25 [INFO] train episode 20540: reward = -139.16, steps = 41 14:24:29 [INFO] train episode 20541: reward = -67.78, steps = 40 14:24:31 [INFO] train episode 20542: reward = -61.04, steps = 20 14:24:32 [INFO] train episode 20543: reward = -80.35, steps = 20 14:24:34 [INFO] train episode 20544: reward = -97.12, steps = 23 14:24:37 [INFO] train episode 20545: reward = -67.14, steps = 26 14:24:40 [INFO] train episode 20546: reward = -63.19, steps = 27 14:24:43 [INFO] train episode 20547: reward = -102.27, steps = 41 14:24:45 [INFO] train episode 20548: reward = -40.53, steps = 21 14:24:47 [INFO] train episode 20549: reward = -81.81, steps = 19 14:24:49 [INFO] train episode 20550: reward = -64.76, steps = 26 14:24:51 [INFO] train episode 20551: reward = -59.56, steps = 21 14:24:54 [INFO] train episode 20552: reward = -93.49, steps = 27 14:24:56 [INFO] train episode 20553: reward = -74.84, steps = 27 14:25:00 [INFO] train episode 20554: reward = -104.83, steps = 46 14:25:03 [INFO] train episode 20555: reward = -107.77, steps = 24 14:25:05 [INFO] train episode 20556: reward = -62.84, steps = 21 14:25:08 [INFO] train episode 20557: reward = -90.60, steps = 32 14:25:10 [INFO] train episode 20558: reward = -58.22, steps = 22 14:25:11 [INFO] train episode 20559: reward = -94.35, steps = 19 14:25:15 [INFO] train episode 20560: reward = -54.92, steps = 33 14:25:19 [INFO] train episode 20561: reward = -100.68, steps = 45 14:25:21 [INFO] train episode 20562: reward = -74.89, steps = 30 14:25:24 [INFO] train episode 20563: reward = -79.69, steps = 27 14:25:27 [INFO] train episode 20564: reward = -135.11, steps = 41 14:25:30 [INFO] train episode 20565: reward = -81.96, steps = 21 14:25:32 [INFO] train episode 20566: reward = -42.06, steps = 27 14:25:34 [INFO] train episode 20567: reward = -66.79, steps = 19 14:25:37 [INFO] train episode 20568: reward = -70.13, steps = 35 14:25:39 [INFO] train episode 20569: reward = -54.84, steps = 27 14:25:43 [INFO] train episode 20570: reward = -58.27, steps = 46 14:25:46 [INFO] train episode 20571: reward = -63.98, steps = 23 14:25:47 [INFO] train episode 20572: reward = -82.33, steps = 19 14:25:49 [INFO] train episode 20573: reward = -54.74, steps = 20 14:25:52 [INFO] train episode 20574: reward = -67.85, steps = 21 14:25:54 [INFO] train episode 20575: reward = -62.09, steps = 20 14:25:56 [INFO] train episode 20576: reward = -83.64, steps = 21 14:25:58 [INFO] train episode 20577: reward = -87.60, steps = 25 14:26:00 [INFO] train episode 20578: reward = -90.44, steps = 26 14:26:04 [INFO] train episode 20579: reward = -54.50, steps = 36 14:26:05 [INFO] train episode 20580: reward = -70.80, steps = 19 14:26:08 [INFO] train episode 20581: reward = -59.97, steps = 24 14:26:10 [INFO] train episode 20582: reward = -76.50, steps = 26 14:26:13 [INFO] train episode 20583: reward = -64.06, steps = 33 14:26:15 [INFO] train episode 20584: reward = -58.95, steps = 21 14:26:17 [INFO] train episode 20585: reward = -46.92, steps = 24 14:26:18 [INFO] train episode 20586: reward = -83.63, steps = 19 14:26:22 [INFO] train episode 20587: reward = -85.92, steps = 35 14:26:24 [INFO] train episode 20588: reward = -61.74, steps = 20 14:26:27 [INFO] train episode 20589: reward = -135.83, steps = 42 14:26:30 [INFO] train episode 20590: reward = -94.09, steps = 34 14:26:32 [INFO] train episode 20591: reward = -72.76, steps = 22 14:26:37 [INFO] train episode 20592: reward = -138.58, steps = 43 14:26:39 [INFO] train episode 20593: reward = -44.28, steps = 21 14:26:40 [INFO] train episode 20594: reward = -80.08, steps = 19 14:26:42 [INFO] train episode 20595: reward = -55.02, steps = 21 14:26:46 [INFO] train episode 20596: reward = -103.71, steps = 42 14:26:48 [INFO] train episode 20597: reward = -99.20, steps = 22 14:26:50 [INFO] train episode 20598: reward = -56.38, steps = 22 14:26:56 [INFO] train episode 20599: reward = -129.11, steps = 72 14:26:59 [INFO] train episode 20600: reward = -78.63, steps = 26 14:27:01 [INFO] train episode 20601: reward = -51.24, steps = 21 14:27:04 [INFO] train episode 20602: reward = -97.30, steps = 33 14:27:08 [INFO] train episode 20603: reward = -120.33, steps = 52 14:27:11 [INFO] train episode 20604: reward = -63.09, steps = 27 14:27:14 [INFO] train episode 20605: reward = -54.26, steps = 35 14:27:17 [INFO] train episode 20606: reward = -104.68, steps = 34 14:27:19 [INFO] train episode 20607: reward = -59.12, steps = 29 14:27:21 [INFO] train episode 20608: reward = -71.83, steps = 21 14:27:26 [INFO] train episode 20609: reward = -72.49, steps = 47 14:27:28 [INFO] train episode 20610: reward = -52.63, steps = 29 14:27:31 [INFO] train episode 20611: reward = -53.01, steps = 26 14:27:34 [INFO] train episode 20612: reward = -84.60, steps = 46 14:27:36 [INFO] train episode 20613: reward = -84.94, steps = 20 14:27:38 [INFO] train episode 20614: reward = -40.87, steps = 22 14:27:40 [INFO] train episode 20615: reward = -73.60, steps = 20 14:27:44 [INFO] train episode 20616: reward = -44.63, steps = 33 14:27:48 [INFO] train episode 20617: reward = -75.92, steps = 45 14:27:50 [INFO] train episode 20618: reward = -73.86, steps = 28 14:27:55 [INFO] train episode 20619: reward = -155.44, steps = 56 14:27:58 [INFO] train episode 20620: reward = -87.94, steps = 29 14:28:00 [INFO] train episode 20621: reward = -63.94, steps = 20 14:28:02 [INFO] train episode 20622: reward = -69.78, steps = 25 14:28:08 [INFO] train episode 20623: reward = -136.84, steps = 66 14:28:11 [INFO] train episode 20624: reward = -97.63, steps = 35 14:28:13 [INFO] train episode 20625: reward = -54.48, steps = 20 14:28:14 [INFO] train episode 20626: reward = -42.01, steps = 21 14:28:18 [INFO] train episode 20627: reward = -64.72, steps = 34 14:28:21 [INFO] train episode 20628: reward = -81.68, steps = 33 14:28:23 [INFO] train episode 20629: reward = -97.12, steps = 21 14:28:26 [INFO] train episode 20630: reward = -96.97, steps = 32 14:28:28 [INFO] train episode 20631: reward = -62.45, steps = 20 14:28:30 [INFO] train episode 20632: reward = -83.98, steps = 25 14:28:33 [INFO] train episode 20633: reward = -79.13, steps = 36 14:28:37 [INFO] train episode 20634: reward = -96.29, steps = 45 14:28:40 [INFO] train episode 20635: reward = -68.12, steps = 25 14:28:43 [INFO] train episode 20636: reward = -24.21, steps = 36 14:28:45 [INFO] train episode 20637: reward = -37.86, steps = 23 14:28:50 [INFO] train episode 20638: reward = -89.30, steps = 39 14:28:52 [INFO] train episode 20639: reward = -83.00, steps = 27 14:28:54 [INFO] train episode 20640: reward = -65.97, steps = 20 14:28:57 [INFO] train episode 20641: reward = -110.96, steps = 39 14:28:59 [INFO] train episode 20642: reward = -95.40, steps = 22 14:29:01 [INFO] train episode 20643: reward = -71.37, steps = 20 14:29:03 [INFO] train episode 20644: reward = -119.38, steps = 22 14:29:06 [INFO] train episode 20645: reward = -55.30, steps = 27 14:29:11 [INFO] train episode 20646: reward = -75.75, steps = 51 14:29:14 [INFO] train episode 20647: reward = -78.91, steps = 36 14:29:16 [INFO] train episode 20648: reward = -60.69, steps = 27 14:29:19 [INFO] train episode 20649: reward = -63.54, steps = 25 14:29:21 [INFO] train episode 20650: reward = -79.58, steps = 24 14:29:24 [INFO] train episode 20651: reward = -87.99, steps = 31 14:29:27 [INFO] train episode 20652: reward = -122.36, steps = 40 14:29:29 [INFO] train episode 20653: reward = -55.03, steps = 20 14:29:31 [INFO] train episode 20654: reward = -51.56, steps = 24 14:29:33 [INFO] train episode 20655: reward = -58.54, steps = 21 14:29:36 [INFO] train episode 20656: reward = -79.90, steps = 29 14:29:37 [INFO] train episode 20657: reward = -62.26, steps = 19 14:29:40 [INFO] train episode 20658: reward = -46.21, steps = 28 14:29:43 [INFO] train episode 20659: reward = -50.24, steps = 29 14:29:46 [INFO] train episode 20660: reward = -67.33, steps = 34 14:29:49 [INFO] train episode 20661: reward = -53.25, steps = 37 14:29:51 [INFO] train episode 20662: reward = -52.23, steps = 23 14:29:53 [INFO] train episode 20663: reward = -75.73, steps = 22 14:29:57 [INFO] train episode 20664: reward = -82.60, steps = 37 14:29:59 [INFO] train episode 20665: reward = -81.48, steps = 22 14:30:02 [INFO] train episode 20666: reward = -71.40, steps = 33 14:30:05 [INFO] train episode 20667: reward = -79.31, steps = 37 14:30:09 [INFO] train episode 20668: reward = -104.70, steps = 41 14:30:13 [INFO] train episode 20669: reward = -70.84, steps = 45 14:30:15 [INFO] train episode 20670: reward = -55.78, steps = 27 14:30:18 [INFO] train episode 20671: reward = -106.09, steps = 32 14:30:20 [INFO] train episode 20672: reward = -78.28, steps = 23 14:30:22 [INFO] train episode 20673: reward = -53.69, steps = 21 14:30:25 [INFO] train episode 20674: reward = -141.59, steps = 37 14:30:30 [INFO] train episode 20675: reward = -93.73, steps = 52 14:30:32 [INFO] train episode 20676: reward = -26.93, steps = 29 14:30:35 [INFO] train episode 20677: reward = -90.06, steps = 28 14:30:37 [INFO] train episode 20678: reward = -51.47, steps = 20 14:30:38 [INFO] train episode 20679: reward = -81.94, steps = 20 14:30:41 [INFO] train episode 20680: reward = -77.95, steps = 28 14:30:43 [INFO] train episode 20681: reward = -64.83, steps = 22 14:30:47 [INFO] train episode 20682: reward = -51.48, steps = 41 14:30:51 [INFO] train episode 20683: reward = -112.41, steps = 49 14:30:53 [INFO] train episode 20684: reward = -69.90, steps = 27 14:30:56 [INFO] train episode 20685: reward = -67.43, steps = 29 14:30:57 [INFO] train episode 20686: reward = -90.66, steps = 18 14:31:00 [INFO] train episode 20687: reward = -51.47, steps = 25 14:31:02 [INFO] train episode 20688: reward = -79.53, steps = 25 14:31:05 [INFO] train episode 20689: reward = -76.18, steps = 34 14:31:07 [INFO] train episode 20690: reward = -81.05, steps = 20 14:31:11 [INFO] train episode 20691: reward = -95.51, steps = 50 14:31:16 [INFO] train episode 20692: reward = -94.63, steps = 48 14:31:18 [INFO] train episode 20693: reward = -54.45, steps = 22 14:31:22 [INFO] train episode 20694: reward = -64.85, steps = 42 14:31:25 [INFO] train episode 20695: reward = -64.61, steps = 39 14:31:28 [INFO] train episode 20696: reward = -64.13, steps = 32 14:31:31 [INFO] train episode 20697: reward = -70.34, steps = 32 14:31:33 [INFO] train episode 20698: reward = -64.50, steps = 29 14:31:37 [INFO] train episode 20699: reward = -93.99, steps = 41 14:31:39 [INFO] train episode 20700: reward = -70.10, steps = 19 14:31:43 [INFO] train episode 20701: reward = -95.08, steps = 43 14:31:45 [INFO] train episode 20702: reward = -45.77, steps = 22 14:31:47 [INFO] train episode 20703: reward = -71.24, steps = 21 14:31:50 [INFO] train episode 20704: reward = -63.73, steps = 32 14:31:52 [INFO] train episode 20705: reward = -60.62, steps = 21 14:31:54 [INFO] train episode 20706: reward = -69.98, steps = 18 14:31:57 [INFO] train episode 20707: reward = -88.36, steps = 31 14:32:00 [INFO] train episode 20708: reward = -66.19, steps = 35 14:32:03 [INFO] train episode 20709: reward = -121.97, steps = 39 14:32:06 [INFO] train episode 20710: reward = -51.29, steps = 32 14:32:10 [INFO] train episode 20711: reward = -108.18, steps = 44 14:32:12 [INFO] train episode 20712: reward = -53.70, steps = 21 14:32:14 [INFO] train episode 20713: reward = -68.67, steps = 24 14:32:16 [INFO] train episode 20714: reward = -77.54, steps = 21 14:32:18 [INFO] train episode 20715: reward = -76.95, steps = 27 14:32:21 [INFO] train episode 20716: reward = -45.90, steps = 31 14:32:23 [INFO] train episode 20717: reward = -72.04, steps = 23 14:32:26 [INFO] train episode 20718: reward = -84.15, steps = 21 14:32:28 [INFO] train episode 20719: reward = -103.73, steps = 25 14:32:30 [INFO] train episode 20720: reward = -85.82, steps = 23 14:32:33 [INFO] train episode 20721: reward = -60.37, steps = 31 14:32:36 [INFO] train episode 20722: reward = -100.56, steps = 41 14:32:38 [INFO] train episode 20723: reward = -59.48, steps = 22 14:32:42 [INFO] train episode 20724: reward = -74.98, steps = 34 14:32:44 [INFO] train episode 20725: reward = -56.04, steps = 28 14:32:46 [INFO] train episode 20726: reward = -63.67, steps = 21 14:32:50 [INFO] train episode 20727: reward = -119.49, steps = 42 14:32:52 [INFO] train episode 20728: reward = -92.14, steps = 28 14:32:54 [INFO] train episode 20729: reward = -76.63, steps = 21 14:32:57 [INFO] train episode 20730: reward = -102.63, steps = 34 14:33:00 [INFO] train episode 20731: reward = -81.53, steps = 27 14:33:02 [INFO] train episode 20732: reward = -60.40, steps = 29 14:33:05 [INFO] train episode 20733: reward = -70.05, steps = 36 14:33:07 [INFO] train episode 20734: reward = -64.77, steps = 19 14:33:12 [INFO] train episode 20735: reward = -108.89, steps = 52 14:33:14 [INFO] train episode 20736: reward = -60.57, steps = 23 14:33:16 [INFO] train episode 20737: reward = -126.51, steps = 21 14:33:21 [INFO] train episode 20738: reward = -113.41, steps = 55 14:33:23 [INFO] train episode 20739: reward = -70.59, steps = 20 14:33:25 [INFO] train episode 20740: reward = -63.26, steps = 26 14:33:27 [INFO] train episode 20741: reward = -75.64, steps = 21 14:33:32 [INFO] train episode 20742: reward = -72.92, steps = 49 14:33:35 [INFO] train episode 20743: reward = -63.70, steps = 39 14:33:40 [INFO] train episode 20744: reward = -99.16, steps = 51 14:33:43 [INFO] train episode 20745: reward = -77.76, steps = 36 14:33:45 [INFO] train episode 20746: reward = -59.65, steps = 21 14:33:47 [INFO] train episode 20747: reward = -50.02, steps = 21 14:33:51 [INFO] train episode 20748: reward = -132.66, steps = 42 14:33:52 [INFO] train episode 20749: reward = -49.91, steps = 21 14:33:56 [INFO] train episode 20750: reward = -94.21, steps = 37 14:33:58 [INFO] train episode 20751: reward = -92.88, steps = 30 14:34:00 [INFO] train episode 20752: reward = -68.61, steps = 20 14:34:04 [INFO] train episode 20753: reward = -79.15, steps = 34 14:34:06 [INFO] train episode 20754: reward = -53.68, steps = 31 14:34:09 [INFO] train episode 20755: reward = -115.91, steps = 32 14:34:11 [INFO] train episode 20756: reward = -88.80, steps = 23 14:34:13 [INFO] train episode 20757: reward = -69.59, steps = 21 14:34:15 [INFO] train episode 20758: reward = -85.65, steps = 28 14:34:18 [INFO] train episode 20759: reward = -38.55, steps = 35 14:34:21 [INFO] train episode 20760: reward = -72.98, steps = 22 14:34:22 [INFO] train episode 20761: reward = -68.94, steps = 21 14:34:26 [INFO] train episode 20762: reward = -78.54, steps = 36 14:34:27 [INFO] train episode 20763: reward = -61.39, steps = 21 14:34:31 [INFO] train episode 20764: reward = -126.42, steps = 41 14:34:33 [INFO] train episode 20765: reward = -72.29, steps = 23 14:34:35 [INFO] train episode 20766: reward = -67.82, steps = 21 14:34:37 [INFO] train episode 20767: reward = -71.42, steps = 20 14:34:39 [INFO] train episode 20768: reward = -71.56, steps = 24 14:34:43 [INFO] train episode 20769: reward = -84.43, steps = 28 14:34:45 [INFO] train episode 20770: reward = -69.09, steps = 30 14:34:48 [INFO] train episode 20771: reward = -85.35, steps = 24 14:34:50 [INFO] train episode 20772: reward = -43.20, steps = 22 14:34:51 [INFO] train episode 20773: reward = -63.23, steps = 20 14:34:54 [INFO] train episode 20774: reward = -47.50, steps = 22 14:34:56 [INFO] train episode 20775: reward = -114.21, steps = 27 14:34:59 [INFO] train episode 20776: reward = -79.09, steps = 30 14:35:02 [INFO] train episode 20777: reward = -81.55, steps = 31 14:35:04 [INFO] train episode 20778: reward = -68.77, steps = 25 14:35:06 [INFO] train episode 20779: reward = -53.20, steps = 24 14:35:08 [INFO] train episode 20780: reward = -57.00, steps = 21 14:35:10 [INFO] train episode 20781: reward = -64.69, steps = 19 14:35:12 [INFO] train episode 20782: reward = -44.16, steps = 21 14:35:14 [INFO] train episode 20783: reward = -66.33, steps = 24 14:35:18 [INFO] train episode 20784: reward = -108.47, steps = 49 14:35:21 [INFO] train episode 20785: reward = -73.43, steps = 28 14:35:23 [INFO] train episode 20786: reward = -75.52, steps = 22 14:35:27 [INFO] train episode 20787: reward = -144.70, steps = 45 14:35:29 [INFO] train episode 20788: reward = -59.72, steps = 24 14:35:31 [INFO] train episode 20789: reward = -84.28, steps = 20 14:35:33 [INFO] train episode 20790: reward = -48.97, steps = 19 14:35:35 [INFO] train episode 20791: reward = -51.41, steps = 22 14:35:37 [INFO] train episode 20792: reward = -47.26, steps = 21 14:35:39 [INFO] train episode 20793: reward = -74.24, steps = 25 14:35:41 [INFO] train episode 20794: reward = -66.56, steps = 20 14:35:43 [INFO] train episode 20795: reward = -77.97, steps = 26 14:35:45 [INFO] train episode 20796: reward = -56.86, steps = 23 14:35:48 [INFO] train episode 20797: reward = -78.34, steps = 33 14:35:50 [INFO] train episode 20798: reward = -86.61, steps = 20 14:35:52 [INFO] train episode 20799: reward = -59.85, steps = 21 14:35:54 [INFO] train episode 20800: reward = -72.72, steps = 21 14:35:57 [INFO] train episode 20801: reward = -80.44, steps = 34 14:35:59 [INFO] train episode 20802: reward = -77.29, steps = 24 14:36:02 [INFO] train episode 20803: reward = -68.36, steps = 26 14:36:05 [INFO] train episode 20804: reward = -88.12, steps = 35 14:36:07 [INFO] train episode 20805: reward = -69.15, steps = 21 14:36:09 [INFO] train episode 20806: reward = -67.87, steps = 31 14:36:11 [INFO] train episode 20807: reward = -50.41, steps = 22 14:36:13 [INFO] train episode 20808: reward = -74.15, steps = 23 14:36:15 [INFO] train episode 20809: reward = -37.36, steps = 21 14:36:17 [INFO] train episode 20810: reward = -95.75, steps = 23 14:36:20 [INFO] train episode 20811: reward = -60.69, steps = 32 14:36:22 [INFO] train episode 20812: reward = -50.35, steps = 23 14:36:25 [INFO] train episode 20813: reward = -64.73, steps = 25 14:36:26 [INFO] train episode 20814: reward = -54.94, steps = 20 14:36:28 [INFO] train episode 20815: reward = -70.18, steps = 20 14:36:30 [INFO] train episode 20816: reward = -78.77, steps = 22 14:36:32 [INFO] train episode 20817: reward = -72.33, steps = 21 14:36:35 [INFO] train episode 20818: reward = -79.06, steps = 33 14:36:38 [INFO] train episode 20819: reward = -75.97, steps = 34 14:36:40 [INFO] train episode 20820: reward = -57.40, steps = 20 14:36:42 [INFO] train episode 20821: reward = -66.97, steps = 23 14:36:44 [INFO] train episode 20822: reward = -75.09, steps = 24 14:36:47 [INFO] train episode 20823: reward = -78.52, steps = 25 14:36:49 [INFO] train episode 20824: reward = -66.64, steps = 23 14:36:51 [INFO] train episode 20825: reward = -78.17, steps = 24 14:36:55 [INFO] train episode 20826: reward = -70.63, steps = 42 14:36:57 [INFO] train episode 20827: reward = -74.20, steps = 31 14:37:00 [INFO] train episode 20828: reward = -97.45, steps = 26 14:37:02 [INFO] train episode 20829: reward = -89.50, steps = 22 14:37:04 [INFO] train episode 20830: reward = -51.35, steps = 21 14:37:05 [INFO] train episode 20831: reward = -83.73, steps = 18 14:37:08 [INFO] train episode 20832: reward = -69.72, steps = 34 14:37:10 [INFO] train episode 20833: reward = -64.42, steps = 24 14:37:12 [INFO] train episode 20834: reward = -91.87, steps = 22 14:37:16 [INFO] train episode 20835: reward = -117.06, steps = 39 14:37:19 [INFO] train episode 20836: reward = -82.87, steps = 35 14:37:21 [INFO] train episode 20837: reward = -53.29, steps = 21 14:37:23 [INFO] train episode 20838: reward = -91.58, steps = 22 14:37:26 [INFO] train episode 20839: reward = -73.27, steps = 32 14:37:28 [INFO] train episode 20840: reward = -70.05, steps = 22 14:37:30 [INFO] train episode 20841: reward = -69.10, steps = 27 14:37:36 [INFO] train episode 20842: reward = -110.71, steps = 61 14:37:41 [INFO] train episode 20843: reward = -147.11, steps = 51 14:37:46 [INFO] train episode 20844: reward = -153.31, steps = 53 14:37:48 [INFO] train episode 20845: reward = -68.01, steps = 25 14:37:50 [INFO] train episode 20846: reward = -63.25, steps = 26 14:37:54 [INFO] train episode 20847: reward = -95.96, steps = 46 14:37:58 [INFO] train episode 20848: reward = -114.70, steps = 40 14:38:01 [INFO] train episode 20849: reward = -62.81, steps = 31 14:38:04 [INFO] train episode 20850: reward = -33.59, steps = 39 14:38:06 [INFO] train episode 20851: reward = -50.45, steps = 20 14:38:09 [INFO] train episode 20852: reward = -53.30, steps = 32 14:38:12 [INFO] train episode 20853: reward = -91.99, steps = 35 14:38:14 [INFO] train episode 20854: reward = -60.03, steps = 19 14:38:16 [INFO] train episode 20855: reward = -100.06, steps = 30 14:38:20 [INFO] train episode 20856: reward = -55.47, steps = 37 14:38:21 [INFO] train episode 20857: reward = -67.85, steps = 23 14:38:23 [INFO] train episode 20858: reward = -57.50, steps = 21 14:38:27 [INFO] train episode 20859: reward = -152.25, steps = 39 14:38:30 [INFO] train episode 20860: reward = -42.36, steps = 33 14:38:32 [INFO] train episode 20861: reward = -61.59, steps = 21 14:38:34 [INFO] train episode 20862: reward = -46.99, steps = 22 14:38:39 [INFO] train episode 20863: reward = -156.87, steps = 57 14:38:41 [INFO] train episode 20864: reward = -65.85, steps = 22 14:38:43 [INFO] train episode 20865: reward = -62.64, steps = 26 14:38:46 [INFO] train episode 20866: reward = -69.91, steps = 24 14:38:47 [INFO] train episode 20867: reward = -74.01, steps = 20 14:38:50 [INFO] train episode 20868: reward = -78.95, steps = 34 14:38:52 [INFO] train episode 20869: reward = -52.30, steps = 21 14:38:57 [INFO] train episode 20870: reward = -84.72, steps = 49 14:38:58 [INFO] train episode 20871: reward = -62.98, steps = 21 14:39:01 [INFO] train episode 20872: reward = -66.36, steps = 21 14:39:03 [INFO] train episode 20873: reward = -62.86, steps = 25 14:39:05 [INFO] train episode 20874: reward = -60.26, steps = 28 14:39:07 [INFO] train episode 20875: reward = -69.84, steps = 23 14:39:10 [INFO] train episode 20876: reward = -56.55, steps = 39 14:39:12 [INFO] train episode 20877: reward = -65.70, steps = 19 14:39:18 [INFO] train episode 20878: reward = -217.37, steps = 69 14:39:21 [INFO] train episode 20879: reward = -78.08, steps = 31 14:39:26 [INFO] train episode 20880: reward = -124.16, steps = 59 14:39:28 [INFO] train episode 20881: reward = -110.60, steps = 23 14:39:30 [INFO] train episode 20882: reward = -59.34, steps = 20 14:39:32 [INFO] train episode 20883: reward = -55.85, steps = 20 14:39:35 [INFO] train episode 20884: reward = -97.19, steps = 36 14:39:37 [INFO] train episode 20885: reward = -84.55, steps = 25 14:39:41 [INFO] train episode 20886: reward = -60.64, steps = 39 14:39:43 [INFO] train episode 20887: reward = -98.04, steps = 27 14:39:45 [INFO] train episode 20888: reward = -68.40, steps = 25 14:39:47 [INFO] train episode 20889: reward = -89.72, steps = 22 14:39:50 [INFO] train episode 20890: reward = -73.23, steps = 23 14:39:53 [INFO] train episode 20891: reward = -88.71, steps = 42 14:39:55 [INFO] train episode 20892: reward = -80.43, steps = 23 14:39:59 [INFO] train episode 20893: reward = -98.38, steps = 38 14:40:01 [INFO] train episode 20894: reward = -73.85, steps = 26 14:40:06 [INFO] train episode 20895: reward = -110.70, steps = 56 14:40:09 [INFO] train episode 20896: reward = -83.17, steps = 28 14:40:11 [INFO] train episode 20897: reward = -89.39, steps = 20 14:40:14 [INFO] train episode 20898: reward = -86.78, steps = 37 14:40:16 [INFO] train episode 20899: reward = -77.92, steps = 24 14:40:19 [INFO] train episode 20900: reward = -92.64, steps = 25 14:40:21 [INFO] train episode 20901: reward = -58.52, steps = 25 14:40:24 [INFO] train episode 20902: reward = -98.57, steps = 32 14:40:26 [INFO] train episode 20903: reward = -57.41, steps = 21 14:40:28 [INFO] train episode 20904: reward = -79.30, steps = 24 14:40:30 [INFO] train episode 20905: reward = -44.59, steps = 19 14:40:38 [INFO] train episode 20906: reward = -149.79, steps = 85 14:40:41 [INFO] train episode 20907: reward = -89.39, steps = 29 14:40:43 [INFO] train episode 20908: reward = -62.08, steps = 26 14:40:46 [INFO] train episode 20909: reward = -63.99, steps = 30 14:40:48 [INFO] train episode 20910: reward = -55.58, steps = 24 14:40:50 [INFO] train episode 20911: reward = -61.44, steps = 23 14:40:52 [INFO] train episode 20912: reward = -62.42, steps = 26 14:40:55 [INFO] train episode 20913: reward = -84.93, steps = 22 14:40:58 [INFO] train episode 20914: reward = -107.84, steps = 43 14:41:00 [INFO] train episode 20915: reward = -65.96, steps = 20 14:41:03 [INFO] train episode 20916: reward = -71.62, steps = 29 14:41:05 [INFO] train episode 20917: reward = -54.05, steps = 23 14:41:07 [INFO] train episode 20918: reward = -73.59, steps = 25 14:41:10 [INFO] train episode 20919: reward = -70.10, steps = 33 14:41:12 [INFO] train episode 20920: reward = -63.69, steps = 19 14:41:14 [INFO] train episode 20921: reward = -103.44, steps = 20 14:41:18 [INFO] train episode 20922: reward = -70.49, steps = 41 14:41:22 [INFO] train episode 20923: reward = -91.87, steps = 51 14:41:24 [INFO] train episode 20924: reward = -59.96, steps = 20 14:41:30 [INFO] train episode 20925: reward = -119.09, steps = 67 14:41:32 [INFO] train episode 20926: reward = -65.39, steps = 20 14:41:34 [INFO] train episode 20927: reward = -86.75, steps = 22 14:41:35 [INFO] train episode 20928: reward = -40.13, steps = 20 14:41:37 [INFO] train episode 20929: reward = -44.64, steps = 20 14:41:39 [INFO] train episode 20930: reward = -62.76, steps = 21 14:41:43 [INFO] train episode 20931: reward = -104.54, steps = 44 14:41:47 [INFO] train episode 20932: reward = -79.74, steps = 41 14:41:49 [INFO] train episode 20933: reward = -71.16, steps = 23 14:41:51 [INFO] train episode 20934: reward = -62.58, steps = 29 14:41:53 [INFO] train episode 20935: reward = -52.83, steps = 20 14:41:56 [INFO] train episode 20936: reward = -97.44, steps = 35 14:42:00 [INFO] train episode 20937: reward = -62.52, steps = 37 14:42:03 [INFO] train episode 20938: reward = -86.67, steps = 44 14:42:05 [INFO] train episode 20939: reward = -63.37, steps = 22 14:42:08 [INFO] train episode 20940: reward = -81.12, steps = 30 14:42:11 [INFO] train episode 20941: reward = -117.88, steps = 39 14:42:13 [INFO] train episode 20942: reward = -76.30, steps = 19 14:42:15 [INFO] train episode 20943: reward = -92.25, steps = 24 14:42:18 [INFO] train episode 20944: reward = -58.74, steps = 25 14:42:20 [INFO] train episode 20945: reward = -63.21, steps = 27 14:42:22 [INFO] train episode 20946: reward = -60.77, steps = 22 14:42:25 [INFO] train episode 20947: reward = -116.35, steps = 33 14:42:27 [INFO] train episode 20948: reward = -63.06, steps = 20 14:42:29 [INFO] train episode 20949: reward = -79.21, steps = 22 14:42:31 [INFO] train episode 20950: reward = -63.73, steps = 24 14:42:33 [INFO] train episode 20951: reward = -82.63, steps = 19 14:42:36 [INFO] train episode 20952: reward = -76.26, steps = 33 14:42:40 [INFO] train episode 20953: reward = -81.11, steps = 44 14:42:42 [INFO] train episode 20954: reward = -64.40, steps = 25 14:42:44 [INFO] train episode 20955: reward = -45.29, steps = 26 14:42:46 [INFO] train episode 20956: reward = -58.88, steps = 21 14:42:48 [INFO] train episode 20957: reward = -72.12, steps = 19 14:42:50 [INFO] train episode 20958: reward = -62.85, steps = 21 14:42:52 [INFO] train episode 20959: reward = -77.65, steps = 26 14:42:55 [INFO] train episode 20960: reward = -69.36, steps = 30 14:42:59 [INFO] train episode 20961: reward = -92.46, steps = 46 14:43:01 [INFO] train episode 20962: reward = -81.43, steps = 31 14:43:04 [INFO] train episode 20963: reward = -45.77, steps = 22 14:43:07 [INFO] train episode 20964: reward = -68.56, steps = 38 14:43:11 [INFO] train episode 20965: reward = -119.12, steps = 41 14:43:14 [INFO] train episode 20966: reward = -70.79, steps = 34 14:43:15 [INFO] train episode 20967: reward = -45.06, steps = 21 14:43:21 [INFO] train episode 20968: reward = -121.60, steps = 58 14:43:23 [INFO] train episode 20969: reward = -64.47, steps = 25 14:43:26 [INFO] train episode 20970: reward = -102.52, steps = 38 14:43:31 [INFO] train episode 20971: reward = -62.36, steps = 50 14:43:33 [INFO] train episode 20972: reward = -62.55, steps = 20 14:43:35 [INFO] train episode 20973: reward = -116.47, steps = 19 14:43:37 [INFO] train episode 20974: reward = -28.89, steps = 20 14:43:40 [INFO] train episode 20975: reward = -86.30, steps = 25 14:43:42 [INFO] train episode 20976: reward = -55.53, steps = 21 14:43:44 [INFO] train episode 20977: reward = -102.15, steps = 26 14:43:46 [INFO] train episode 20978: reward = -76.05, steps = 20 14:43:49 [INFO] train episode 20979: reward = -99.96, steps = 35 14:43:51 [INFO] train episode 20980: reward = -129.56, steps = 30 14:43:57 [INFO] train episode 20981: reward = -100.80, steps = 59 14:44:01 [INFO] train episode 20982: reward = -45.78, steps = 46 14:44:03 [INFO] train episode 20983: reward = -88.96, steps = 25 14:44:05 [INFO] train episode 20984: reward = -63.01, steps = 22 14:44:08 [INFO] train episode 20985: reward = -48.83, steps = 33 14:44:10 [INFO] train episode 20986: reward = -85.61, steps = 19 14:44:12 [INFO] train episode 20987: reward = -76.28, steps = 24 14:44:15 [INFO] train episode 20988: reward = -84.64, steps = 28 14:44:18 [INFO] train episode 20989: reward = -87.26, steps = 35 14:44:20 [INFO] train episode 20990: reward = -44.08, steps = 30 14:44:23 [INFO] train episode 20991: reward = -66.64, steps = 29 14:44:25 [INFO] train episode 20992: reward = -82.05, steps = 19 14:44:27 [INFO] train episode 20993: reward = -95.44, steps = 25 14:44:31 [INFO] train episode 20994: reward = -58.70, steps = 46 14:44:35 [INFO] train episode 20995: reward = -68.31, steps = 38 14:44:37 [INFO] train episode 20996: reward = -56.49, steps = 24 14:44:39 [INFO] train episode 20997: reward = -53.68, steps = 30 14:44:42 [INFO] train episode 20998: reward = -51.40, steps = 29 14:44:44 [INFO] train episode 20999: reward = -76.36, steps = 21 14:44:47 [INFO] train episode 21000: reward = -55.71, steps = 33 14:44:50 [INFO] train episode 21001: reward = -93.46, steps = 29 14:44:52 [INFO] train episode 21002: reward = -76.18, steps = 28 14:44:56 [INFO] train episode 21003: reward = -100.79, steps = 37 14:44:58 [INFO] train episode 21004: reward = -94.86, steps = 30 14:45:02 [INFO] train episode 21005: reward = -75.15, steps = 33 14:45:04 [INFO] train episode 21006: reward = -82.17, steps = 23 14:45:06 [INFO] train episode 21007: reward = -56.43, steps = 23 14:45:08 [INFO] train episode 21008: reward = -53.01, steps = 20 14:45:10 [INFO] train episode 21009: reward = -61.85, steps = 29 14:45:12 [INFO] train episode 21010: reward = -138.40, steps = 25 14:45:15 [INFO] train episode 21011: reward = -56.00, steps = 30 14:45:19 [INFO] train episode 21012: reward = -64.08, steps = 35 14:45:20 [INFO] train episode 21013: reward = -59.46, steps = 21 14:45:23 [INFO] train episode 21014: reward = -72.53, steps = 33 14:45:27 [INFO] train episode 21015: reward = -127.62, steps = 39 14:45:29 [INFO] train episode 21016: reward = -116.52, steps = 22 14:45:32 [INFO] train episode 21017: reward = -83.53, steps = 38 14:45:34 [INFO] train episode 21018: reward = -43.63, steps = 20 14:45:36 [INFO] train episode 21019: reward = -81.06, steps = 23 14:45:38 [INFO] train episode 21020: reward = -82.18, steps = 22 14:45:41 [INFO] train episode 21021: reward = -58.65, steps = 29 14:45:42 [INFO] train episode 21022: reward = -91.24, steps = 19 14:45:44 [INFO] train episode 21023: reward = -75.80, steps = 20 14:45:47 [INFO] train episode 21024: reward = -108.24, steps = 34 14:45:51 [INFO] train episode 21025: reward = -162.92, steps = 45 14:45:54 [INFO] train episode 21026: reward = -95.31, steps = 35 14:45:57 [INFO] train episode 21027: reward = -86.74, steps = 24 14:45:59 [INFO] train episode 21028: reward = -47.11, steps = 22 14:46:01 [INFO] train episode 21029: reward = -65.22, steps = 33 14:46:04 [INFO] train episode 21030: reward = -95.08, steps = 26 14:46:06 [INFO] train episode 21031: reward = -111.25, steps = 21 14:46:09 [INFO] train episode 21032: reward = -100.44, steps = 36 14:46:11 [INFO] train episode 21033: reward = -74.69, steps = 20 14:46:13 [INFO] train episode 21034: reward = -118.26, steps = 24 14:46:15 [INFO] train episode 21035: reward = -49.95, steps = 20 14:46:17 [INFO] train episode 21036: reward = -63.60, steps = 30 14:46:20 [INFO] train episode 21037: reward = -73.77, steps = 26 14:46:23 [INFO] train episode 21038: reward = -62.25, steps = 30 14:46:25 [INFO] train episode 21039: reward = -67.37, steps = 22 14:46:28 [INFO] train episode 21040: reward = -67.87, steps = 38 14:46:30 [INFO] train episode 21041: reward = -83.68, steps = 19 14:46:32 [INFO] train episode 21042: reward = -69.30, steps = 21 14:46:34 [INFO] train episode 21043: reward = -71.19, steps = 21 14:46:37 [INFO] train episode 21044: reward = -68.19, steps = 25 14:46:39 [INFO] train episode 21045: reward = -88.24, steps = 22 14:46:41 [INFO] train episode 21046: reward = -49.62, steps = 19 14:46:43 [INFO] train episode 21047: reward = -93.83, steps = 28 14:46:45 [INFO] train episode 21048: reward = -41.84, steps = 25 14:46:48 [INFO] train episode 21049: reward = -50.07, steps = 27 14:46:51 [INFO] train episode 21050: reward = -73.98, steps = 41 14:46:53 [INFO] train episode 21051: reward = -59.22, steps = 20 14:46:56 [INFO] train episode 21052: reward = -59.24, steps = 33 14:47:00 [INFO] train episode 21053: reward = -65.16, steps = 47 14:47:02 [INFO] train episode 21054: reward = -64.60, steps = 20 14:47:05 [INFO] train episode 21055: reward = -63.92, steps = 29 14:47:07 [INFO] train episode 21056: reward = -64.41, steps = 25 14:47:09 [INFO] train episode 21057: reward = -62.82, steps = 29 14:47:12 [INFO] train episode 21058: reward = -116.78, steps = 20 14:47:14 [INFO] train episode 21059: reward = -59.83, steps = 27 14:47:18 [INFO] train episode 21060: reward = -63.57, steps = 46 14:47:21 [INFO] train episode 21061: reward = -83.16, steps = 33 14:47:23 [INFO] train episode 21062: reward = -76.99, steps = 25 14:47:25 [INFO] train episode 21063: reward = -53.75, steps = 26 14:47:28 [INFO] train episode 21064: reward = -53.70, steps = 24 14:47:32 [INFO] train episode 21065: reward = -77.03, steps = 48 14:47:34 [INFO] train episode 21066: reward = -62.04, steps = 21 14:47:36 [INFO] train episode 21067: reward = -75.25, steps = 19 14:47:38 [INFO] train episode 21068: reward = -66.48, steps = 26 14:47:40 [INFO] train episode 21069: reward = -115.14, steps = 21 14:47:42 [INFO] train episode 21070: reward = -56.23, steps = 22 14:47:45 [INFO] train episode 21071: reward = -72.06, steps = 21 14:47:47 [INFO] train episode 21072: reward = -65.51, steps = 28 14:47:49 [INFO] train episode 21073: reward = -62.98, steps = 21 14:47:51 [INFO] train episode 21074: reward = -71.01, steps = 25 14:47:53 [INFO] train episode 21075: reward = -75.20, steps = 19 14:47:57 [INFO] train episode 21076: reward = -89.58, steps = 46 14:48:01 [INFO] train episode 21077: reward = -76.85, steps = 43 14:48:05 [INFO] train episode 21078: reward = -108.28, steps = 43 14:48:06 [INFO] train episode 21079: reward = -55.24, steps = 22 14:48:09 [INFO] train episode 21080: reward = -77.93, steps = 33 14:48:12 [INFO] train episode 21081: reward = -72.88, steps = 27 14:48:13 [INFO] train episode 21082: reward = -83.08, steps = 19 14:48:16 [INFO] train episode 21083: reward = -58.50, steps = 26 14:48:18 [INFO] train episode 21084: reward = -80.74, steps = 26 14:48:21 [INFO] train episode 21085: reward = -78.13, steps = 25 14:48:26 [INFO] train episode 21086: reward = -144.79, steps = 54 14:48:29 [INFO] train episode 21087: reward = -83.68, steps = 34 14:48:32 [INFO] train episode 21088: reward = -97.76, steps = 39 14:48:34 [INFO] train episode 21089: reward = -91.44, steps = 18 14:48:38 [INFO] train episode 21090: reward = -66.51, steps = 41 14:48:39 [INFO] train episode 21091: reward = -72.12, steps = 20 14:48:41 [INFO] train episode 21092: reward = -50.92, steps = 24 14:48:44 [INFO] train episode 21093: reward = -108.60, steps = 29 14:48:48 [INFO] train episode 21094: reward = -76.27, steps = 45 14:48:50 [INFO] train episode 21095: reward = -69.39, steps = 20 14:48:52 [INFO] train episode 21096: reward = -58.83, steps = 22 14:48:54 [INFO] train episode 21097: reward = -50.87, steps = 26 14:48:57 [INFO] train episode 21098: reward = -95.71, steps = 37 14:49:01 [INFO] train episode 21099: reward = -130.86, steps = 39 14:49:03 [INFO] train episode 21100: reward = -79.92, steps = 22 14:49:05 [INFO] train episode 21101: reward = -52.48, steps = 19 14:49:07 [INFO] train episode 21102: reward = -86.11, steps = 24 14:49:08 [INFO] train episode 21103: reward = -61.81, steps = 19 14:49:11 [INFO] train episode 21104: reward = -54.74, steps = 24 14:49:12 [INFO] train episode 21105: reward = -95.95, steps = 19 14:49:14 [INFO] train episode 21106: reward = -61.42, steps = 24 14:49:17 [INFO] train episode 21107: reward = -68.41, steps = 31 14:49:19 [INFO] train episode 21108: reward = -72.87, steps = 20 14:49:22 [INFO] train episode 21109: reward = -63.58, steps = 32 14:49:26 [INFO] train episode 21110: reward = -53.34, steps = 41 14:49:28 [INFO] train episode 21111: reward = -56.16, steps = 20 14:49:31 [INFO] train episode 21112: reward = -74.28, steps = 33 14:49:33 [INFO] train episode 21113: reward = -29.77, steps = 23 14:49:35 [INFO] train episode 21114: reward = -46.19, steps = 20 14:49:39 [INFO] train episode 21115: reward = -65.99, steps = 41 14:49:40 [INFO] train episode 21116: reward = -103.17, steps = 19 14:49:43 [INFO] train episode 21117: reward = -82.99, steps = 27 14:49:45 [INFO] train episode 21118: reward = -64.34, steps = 33 14:49:48 [INFO] train episode 21119: reward = -100.84, steps = 34 14:49:50 [INFO] train episode 21120: reward = -42.29, steps = 22 14:49:52 [INFO] train episode 21121: reward = -47.55, steps = 19 14:49:58 [INFO] train episode 21122: reward = -113.28, steps = 63 14:50:01 [INFO] train episode 21123: reward = -102.58, steps = 38 14:50:03 [INFO] train episode 21124: reward = -72.97, steps = 19 14:50:04 [INFO] train episode 21125: reward = -55.76, steps = 19 14:50:08 [INFO] train episode 21126: reward = -65.64, steps = 36 14:50:11 [INFO] train episode 21127: reward = -88.16, steps = 36 14:50:13 [INFO] train episode 21128: reward = -56.75, steps = 22 14:50:16 [INFO] train episode 21129: reward = -73.43, steps = 32 14:50:18 [INFO] train episode 21130: reward = -64.84, steps = 20 14:50:19 [INFO] train episode 21131: reward = -65.83, steps = 18 14:50:21 [INFO] train episode 21132: reward = -66.65, steps = 22 14:50:24 [INFO] train episode 21133: reward = -59.29, steps = 29 14:50:26 [INFO] train episode 21134: reward = -65.79, steps = 21 14:50:28 [INFO] train episode 21135: reward = -116.78, steps = 25 14:50:31 [INFO] train episode 21136: reward = -49.60, steps = 36 14:50:34 [INFO] train episode 21137: reward = -80.66, steps = 33 14:50:36 [INFO] train episode 21138: reward = -60.41, steps = 22 14:50:38 [INFO] train episode 21139: reward = -63.77, steps = 22 14:50:41 [INFO] train episode 21140: reward = -44.47, steps = 26 14:50:45 [INFO] train episode 21141: reward = -93.34, steps = 47 14:50:47 [INFO] train episode 21142: reward = -75.12, steps = 20 14:50:49 [INFO] train episode 21143: reward = -92.54, steps = 23 14:50:52 [INFO] train episode 21144: reward = -87.26, steps = 30 14:50:54 [INFO] train episode 21145: reward = -68.32, steps = 25 14:50:56 [INFO] train episode 21146: reward = -103.76, steps = 26 14:50:58 [INFO] train episode 21147: reward = -54.85, steps = 25 14:51:01 [INFO] train episode 21148: reward = -65.90, steps = 25 14:51:03 [INFO] train episode 21149: reward = -83.00, steps = 25 14:51:05 [INFO] train episode 21150: reward = -51.63, steps = 27 14:51:07 [INFO] train episode 21151: reward = -48.93, steps = 19 14:51:10 [INFO] train episode 21152: reward = -91.30, steps = 32 14:51:16 [INFO] train episode 21153: reward = -118.46, steps = 60 14:51:17 [INFO] train episode 21154: reward = -55.42, steps = 20 14:51:20 [INFO] train episode 21155: reward = -77.43, steps = 26 14:51:22 [INFO] train episode 21156: reward = -76.83, steps = 26 14:51:24 [INFO] train episode 21157: reward = -90.67, steps = 22 14:51:26 [INFO] train episode 21158: reward = -91.05, steps = 20 14:51:28 [INFO] train episode 21159: reward = -88.64, steps = 26 14:51:30 [INFO] train episode 21160: reward = -87.49, steps = 22 14:51:32 [INFO] train episode 21161: reward = -94.18, steps = 24 14:51:35 [INFO] train episode 21162: reward = -65.22, steps = 26 14:51:37 [INFO] train episode 21163: reward = -67.83, steps = 24 14:51:40 [INFO] train episode 21164: reward = -91.32, steps = 34 14:51:43 [INFO] train episode 21165: reward = -67.97, steps = 32 14:51:45 [INFO] train episode 21166: reward = -108.14, steps = 31 14:51:48 [INFO] train episode 21167: reward = -41.16, steps = 30 14:51:50 [INFO] train episode 21168: reward = -68.26, steps = 21 14:51:53 [INFO] train episode 21169: reward = -87.51, steps = 32 14:51:57 [INFO] train episode 21170: reward = -72.84, steps = 40 14:51:59 [INFO] train episode 21171: reward = -95.67, steps = 26 14:52:02 [INFO] train episode 21172: reward = -90.56, steps = 30 14:52:04 [INFO] train episode 21173: reward = -66.23, steps = 23 14:52:08 [INFO] train episode 21174: reward = -63.09, steps = 38 14:52:10 [INFO] train episode 21175: reward = -70.51, steps = 23 14:52:12 [INFO] train episode 21176: reward = -77.83, steps = 31 14:52:15 [INFO] train episode 21177: reward = -54.30, steps = 33 14:52:17 [INFO] train episode 21178: reward = -53.04, steps = 24 14:52:19 [INFO] train episode 21179: reward = -52.98, steps = 21 14:52:24 [INFO] train episode 21180: reward = -100.56, steps = 36 14:52:27 [INFO] train episode 21181: reward = -89.90, steps = 39 14:52:30 [INFO] train episode 21182: reward = -83.43, steps = 34 14:52:34 [INFO] train episode 21183: reward = -62.99, steps = 49 14:52:38 [INFO] train episode 21184: reward = -119.33, steps = 39 14:52:40 [INFO] train episode 21185: reward = -41.06, steps = 21 14:52:42 [INFO] train episode 21186: reward = -53.55, steps = 22 14:52:44 [INFO] train episode 21187: reward = -64.95, steps = 20 14:52:46 [INFO] train episode 21188: reward = -54.93, steps = 22 14:52:47 [INFO] train episode 21189: reward = -57.87, steps = 20 14:52:49 [INFO] train episode 21190: reward = -69.81, steps = 23 14:52:52 [INFO] train episode 21191: reward = -87.87, steps = 32 14:52:55 [INFO] train episode 21192: reward = -86.14, steps = 21 14:52:58 [INFO] train episode 21193: reward = -83.89, steps = 36 14:53:00 [INFO] train episode 21194: reward = -99.41, steps = 23 14:53:01 [INFO] train episode 21195: reward = -63.84, steps = 20 14:53:03 [INFO] train episode 21196: reward = -77.26, steps = 21 14:53:07 [INFO] train episode 21197: reward = -142.12, steps = 45 14:53:10 [INFO] train episode 21198: reward = -81.10, steps = 32 14:53:12 [INFO] train episode 21199: reward = -64.35, steps = 20 14:53:16 [INFO] train episode 21200: reward = -60.95, steps = 46 14:53:18 [INFO] train episode 21201: reward = -95.90, steps = 20 14:53:21 [INFO] train episode 21202: reward = -101.01, steps = 39 14:53:24 [INFO] train episode 21203: reward = -64.24, steps = 31 14:53:27 [INFO] train episode 21204: reward = -87.46, steps = 30 14:53:29 [INFO] train episode 21205: reward = -81.23, steps = 20 14:53:30 [INFO] train episode 21206: reward = -123.14, steps = 21 14:53:33 [INFO] train episode 21207: reward = -101.81, steps = 33 14:53:35 [INFO] train episode 21208: reward = -60.00, steps = 22 14:53:37 [INFO] train episode 21209: reward = -81.57, steps = 24 14:53:40 [INFO] train episode 21210: reward = -75.23, steps = 25 14:53:41 [INFO] train episode 21211: reward = -57.62, steps = 20 14:53:44 [INFO] train episode 21212: reward = -61.72, steps = 21 14:53:47 [INFO] train episode 21213: reward = -101.78, steps = 37 14:53:50 [INFO] train episode 21214: reward = -67.72, steps = 30 14:53:51 [INFO] train episode 21215: reward = -52.47, steps = 21 14:53:54 [INFO] train episode 21216: reward = -85.27, steps = 36 14:53:57 [INFO] train episode 21217: reward = -63.01, steps = 24 14:53:59 [INFO] train episode 21218: reward = -79.24, steps = 22 14:54:01 [INFO] train episode 21219: reward = -70.71, steps = 24 14:54:04 [INFO] train episode 21220: reward = -74.38, steps = 31 14:54:06 [INFO] train episode 21221: reward = -87.53, steps = 24 14:54:09 [INFO] train episode 21222: reward = -101.99, steps = 40 14:54:11 [INFO] train episode 21223: reward = -62.99, steps = 25 14:54:13 [INFO] train episode 21224: reward = -89.99, steps = 24 14:54:16 [INFO] train episode 21225: reward = -73.89, steps = 24 14:54:20 [INFO] train episode 21226: reward = -106.15, steps = 48 14:54:24 [INFO] train episode 21227: reward = -93.21, steps = 42 14:54:27 [INFO] train episode 21228: reward = -95.20, steps = 35 14:54:28 [INFO] train episode 21229: reward = -82.79, steps = 21 14:54:31 [INFO] train episode 21230: reward = -56.94, steps = 26 14:54:34 [INFO] train episode 21231: reward = -82.68, steps = 29 14:54:36 [INFO] train episode 21232: reward = -71.35, steps = 21 14:54:39 [INFO] train episode 21233: reward = -61.59, steps = 35 14:54:41 [INFO] train episode 21234: reward = -88.34, steps = 23 14:54:44 [INFO] train episode 21235: reward = -83.68, steps = 37 14:54:46 [INFO] train episode 21236: reward = -67.58, steps = 28 14:54:49 [INFO] train episode 21237: reward = -75.13, steps = 27 14:54:51 [INFO] train episode 21238: reward = -61.11, steps = 21 14:54:54 [INFO] train episode 21239: reward = -55.88, steps = 31 14:54:56 [INFO] train episode 21240: reward = -64.06, steps = 21 14:55:00 [INFO] train episode 21241: reward = -97.01, steps = 48 14:55:03 [INFO] train episode 21242: reward = -67.67, steps = 35 14:55:05 [INFO] train episode 21243: reward = -77.01, steps = 22 14:55:08 [INFO] train episode 21244: reward = -83.80, steps = 24 14:55:09 [INFO] train episode 21245: reward = -60.20, steps = 22 14:55:12 [INFO] train episode 21246: reward = -87.76, steps = 26 14:55:14 [INFO] train episode 21247: reward = -66.76, steps = 30 14:55:16 [INFO] train episode 21248: reward = -68.87, steps = 24 14:55:20 [INFO] train episode 21249: reward = -65.90, steps = 30 14:55:23 [INFO] train episode 21250: reward = -93.54, steps = 32 14:55:25 [INFO] train episode 21251: reward = -110.31, steps = 23 14:55:29 [INFO] train episode 21252: reward = -71.72, steps = 46 14:55:31 [INFO] train episode 21253: reward = -80.50, steps = 29 14:55:36 [INFO] train episode 21254: reward = -96.52, steps = 53 14:55:40 [INFO] train episode 21255: reward = -88.22, steps = 45 14:55:44 [INFO] train episode 21256: reward = -222.46, steps = 45 14:55:46 [INFO] train episode 21257: reward = -84.77, steps = 20 14:55:48 [INFO] train episode 21258: reward = -79.55, steps = 20 14:55:49 [INFO] train episode 21259: reward = -51.31, steps = 20 14:55:54 [INFO] train episode 21260: reward = -54.59, steps = 48 14:55:57 [INFO] train episode 21261: reward = -65.83, steps = 31 14:55:58 [INFO] train episode 21262: reward = -63.73, steps = 22 14:56:03 [INFO] train episode 21263: reward = -110.72, steps = 56 14:56:06 [INFO] train episode 21264: reward = -70.24, steps = 25 14:56:10 [INFO] train episode 21265: reward = -162.35, steps = 52 14:56:13 [INFO] train episode 21266: reward = -64.16, steps = 25 14:56:14 [INFO] train episode 21267: reward = -68.08, steps = 22 14:56:17 [INFO] train episode 21268: reward = -112.00, steps = 31 14:56:19 [INFO] train episode 21269: reward = -56.31, steps = 20 14:56:22 [INFO] train episode 21270: reward = -67.99, steps = 32 14:56:25 [INFO] train episode 21271: reward = -97.76, steps = 38 14:56:28 [INFO] train episode 21272: reward = -90.71, steps = 26 14:56:30 [INFO] train episode 21273: reward = -57.22, steps = 30 14:56:36 [INFO] train episode 21274: reward = -116.94, steps = 64 14:56:38 [INFO] train episode 21275: reward = -69.50, steps = 24 14:56:40 [INFO] train episode 21276: reward = -59.05, steps = 25 14:56:42 [INFO] train episode 21277: reward = -93.96, steps = 22 14:56:45 [INFO] train episode 21278: reward = -58.97, steps = 31 14:56:47 [INFO] train episode 21279: reward = -57.33, steps = 21 14:56:50 [INFO] train episode 21280: reward = -97.24, steps = 34 14:56:55 [INFO] train episode 21281: reward = -131.71, steps = 55 14:57:01 [INFO] train episode 21282: reward = -109.82, steps = 72 14:57:05 [INFO] train episode 21283: reward = -154.29, steps = 51 14:57:07 [INFO] train episode 21284: reward = -68.10, steps = 21 14:57:10 [INFO] train episode 21285: reward = -94.26, steps = 32 14:57:12 [INFO] train episode 21286: reward = -49.22, steps = 27 14:57:15 [INFO] train episode 21287: reward = -70.04, steps = 28 14:57:17 [INFO] train episode 21288: reward = -63.38, steps = 24 14:57:20 [INFO] train episode 21289: reward = -74.72, steps = 25 14:57:21 [INFO] train episode 21290: reward = -69.03, steps = 21 14:57:24 [INFO] train episode 21291: reward = -53.63, steps = 26 14:57:26 [INFO] train episode 21292: reward = -93.84, steps = 21 14:57:28 [INFO] train episode 21293: reward = -57.23, steps = 30 14:57:31 [INFO] train episode 21294: reward = -59.78, steps = 29 14:57:33 [INFO] train episode 21295: reward = -82.99, steps = 19 14:57:35 [INFO] train episode 21296: reward = -60.27, steps = 21 14:57:39 [INFO] train episode 21297: reward = -108.14, steps = 52 14:57:42 [INFO] train episode 21298: reward = -40.12, steps = 29 14:57:45 [INFO] train episode 21299: reward = -72.49, steps = 31 14:57:47 [INFO] train episode 21300: reward = -66.94, steps = 21 14:57:50 [INFO] train episode 21301: reward = -75.50, steps = 32 14:57:53 [INFO] train episode 21302: reward = -80.64, steps = 30 14:57:55 [INFO] train episode 21303: reward = -111.47, steps = 28 14:57:57 [INFO] train episode 21304: reward = -60.70, steps = 20 14:57:59 [INFO] train episode 21305: reward = -78.42, steps = 29 14:58:01 [INFO] train episode 21306: reward = -121.06, steps = 20 14:58:03 [INFO] train episode 21307: reward = -70.40, steps = 20 14:58:05 [INFO] train episode 21308: reward = -85.64, steps = 20 14:58:07 [INFO] train episode 21309: reward = -59.40, steps = 22 14:58:09 [INFO] train episode 21310: reward = -74.86, steps = 28 14:58:14 [INFO] train episode 21311: reward = -55.38, steps = 46 14:58:18 [INFO] train episode 21312: reward = -60.06, steps = 38 14:58:20 [INFO] train episode 21313: reward = -54.58, steps = 27 14:58:23 [INFO] train episode 21314: reward = -42.77, steps = 29 14:58:25 [INFO] train episode 21315: reward = -86.07, steps = 19 14:58:27 [INFO] train episode 21316: reward = -79.58, steps = 27 14:58:29 [INFO] train episode 21317: reward = -151.84, steps = 24 14:58:34 [INFO] train episode 21318: reward = -104.73, steps = 53 14:58:36 [INFO] train episode 21319: reward = -90.73, steps = 21 14:58:38 [INFO] train episode 21320: reward = -52.11, steps = 21 14:58:40 [INFO] train episode 21321: reward = -54.89, steps = 26 14:58:43 [INFO] train episode 21322: reward = -114.26, steps = 29 14:58:45 [INFO] train episode 21323: reward = -98.45, steps = 27 14:58:48 [INFO] train episode 21324: reward = -62.38, steps = 34 14:58:51 [INFO] train episode 21325: reward = -105.16, steps = 32 14:58:55 [INFO] train episode 21326: reward = -88.47, steps = 41 14:58:57 [INFO] train episode 21327: reward = -69.86, steps = 31 14:59:00 [INFO] train episode 21328: reward = -124.49, steps = 36 14:59:02 [INFO] train episode 21329: reward = -86.95, steps = 21 14:59:04 [INFO] train episode 21330: reward = -68.43, steps = 20 14:59:07 [INFO] train episode 21331: reward = -70.71, steps = 33 14:59:11 [INFO] train episode 21332: reward = -80.17, steps = 41 14:59:14 [INFO] train episode 21333: reward = -115.33, steps = 41 14:59:16 [INFO] train episode 21334: reward = -49.74, steps = 23 14:59:19 [INFO] train episode 21335: reward = -66.58, steps = 31 14:59:21 [INFO] train episode 21336: reward = -99.95, steps = 24 14:59:24 [INFO] train episode 21337: reward = -96.87, steps = 37 14:59:27 [INFO] train episode 21338: reward = -48.74, steps = 24 14:59:31 [INFO] train episode 21339: reward = -145.97, steps = 45 14:59:33 [INFO] train episode 21340: reward = -110.65, steps = 33 14:59:36 [INFO] train episode 21341: reward = -66.95, steps = 23 14:59:37 [INFO] train episode 21342: reward = -84.55, steps = 22 14:59:40 [INFO] train episode 21343: reward = -95.35, steps = 30 14:59:43 [INFO] train episode 21344: reward = -59.71, steps = 25 14:59:45 [INFO] train episode 21345: reward = -70.70, steps = 25 14:59:47 [INFO] train episode 21346: reward = -63.04, steps = 25 14:59:49 [INFO] train episode 21347: reward = -74.88, steps = 24 14:59:52 [INFO] train episode 21348: reward = -48.66, steps = 31 14:59:54 [INFO] train episode 21349: reward = -107.22, steps = 28 14:59:57 [INFO] train episode 21350: reward = -64.48, steps = 28 14:59:59 [INFO] train episode 21351: reward = -50.70, steps = 21 15:00:02 [INFO] train episode 21352: reward = -65.43, steps = 35 15:00:04 [INFO] train episode 21353: reward = -61.81, steps = 23 15:00:06 [INFO] train episode 21354: reward = -89.09, steps = 30 15:00:08 [INFO] train episode 21355: reward = -94.88, steps = 22 15:00:11 [INFO] train episode 21356: reward = -81.42, steps = 31 15:00:16 [INFO] train episode 21357: reward = -131.35, steps = 48 15:00:17 [INFO] train episode 21358: reward = -83.47, steps = 21 15:00:19 [INFO] train episode 21359: reward = -62.15, steps = 19 15:00:25 [INFO] train episode 21360: reward = -136.69, steps = 66 15:00:27 [INFO] train episode 21361: reward = -41.18, steps = 31 15:00:29 [INFO] train episode 21362: reward = -66.61, steps = 19 15:00:32 [INFO] train episode 21363: reward = -63.75, steps = 24 15:00:34 [INFO] train episode 21364: reward = -67.37, steps = 27 15:00:36 [INFO] train episode 21365: reward = -57.92, steps = 20 15:00:38 [INFO] train episode 21366: reward = -69.26, steps = 29 15:00:40 [INFO] train episode 21367: reward = -44.73, steps = 20 15:00:42 [INFO] train episode 21368: reward = -79.60, steps = 24 15:00:44 [INFO] train episode 21369: reward = -62.72, steps = 20 15:00:46 [INFO] train episode 21370: reward = -39.92, steps = 23 15:00:48 [INFO] train episode 21371: reward = -63.32, steps = 20 15:00:51 [INFO] train episode 21372: reward = -46.71, steps = 27 15:00:53 [INFO] train episode 21373: reward = -91.29, steps = 27 15:00:56 [INFO] train episode 21374: reward = -53.61, steps = 37 15:00:58 [INFO] train episode 21375: reward = -78.72, steps = 22 15:01:00 [INFO] train episode 21376: reward = -69.32, steps = 19 15:01:03 [INFO] train episode 21377: reward = -65.34, steps = 35 15:01:08 [INFO] train episode 21378: reward = -89.11, steps = 44 15:01:10 [INFO] train episode 21379: reward = -71.41, steps = 30 15:01:14 [INFO] train episode 21380: reward = -83.08, steps = 45 15:01:17 [INFO] train episode 21381: reward = -70.98, steps = 28 15:01:21 [INFO] train episode 21382: reward = -198.39, steps = 41 15:01:24 [INFO] train episode 21383: reward = -100.09, steps = 45 15:01:27 [INFO] train episode 21384: reward = -70.31, steps = 35 15:01:30 [INFO] train episode 21385: reward = -90.63, steps = 28 15:01:33 [INFO] train episode 21386: reward = -27.20, steps = 32 15:01:35 [INFO] train episode 21387: reward = -78.99, steps = 22 15:01:37 [INFO] train episode 21388: reward = -77.42, steps = 23 15:01:40 [INFO] train episode 21389: reward = -75.09, steps = 39 15:01:44 [INFO] train episode 21390: reward = -110.65, steps = 44 15:01:47 [INFO] train episode 21391: reward = -97.14, steps = 30 15:01:49 [INFO] train episode 21392: reward = -72.73, steps = 26 15:01:52 [INFO] train episode 21393: reward = -47.60, steps = 26 15:01:54 [INFO] train episode 21394: reward = -87.27, steps = 24 15:01:57 [INFO] train episode 21395: reward = -67.38, steps = 33 15:01:59 [INFO] train episode 21396: reward = -73.46, steps = 27 15:02:02 [INFO] train episode 21397: reward = -101.50, steps = 34 15:02:05 [INFO] train episode 21398: reward = -71.09, steps = 28 15:02:08 [INFO] train episode 21399: reward = -87.24, steps = 34 15:02:10 [INFO] train episode 21400: reward = -60.86, steps = 25 15:02:12 [INFO] train episode 21401: reward = -72.88, steps = 24 15:02:15 [INFO] train episode 21402: reward = -86.85, steps = 32 15:02:18 [INFO] train episode 21403: reward = -70.95, steps = 31 15:02:20 [INFO] train episode 21404: reward = -86.26, steps = 21 15:02:24 [INFO] train episode 21405: reward = -71.08, steps = 43 15:02:27 [INFO] train episode 21406: reward = -81.91, steps = 41 15:02:29 [INFO] train episode 21407: reward = -87.49, steps = 22 15:02:31 [INFO] train episode 21408: reward = -67.30, steps = 24 15:02:34 [INFO] train episode 21409: reward = -57.91, steps = 33 15:02:36 [INFO] train episode 21410: reward = -74.80, steps = 20 15:02:39 [INFO] train episode 21411: reward = -57.86, steps = 32 15:02:42 [INFO] train episode 21412: reward = -79.64, steps = 31 15:02:44 [INFO] train episode 21413: reward = -80.01, steps = 20 15:02:46 [INFO] train episode 21414: reward = -65.13, steps = 20 15:02:49 [INFO] train episode 21415: reward = -84.07, steps = 30 15:02:51 [INFO] train episode 21416: reward = -46.84, steps = 30 15:02:53 [INFO] train episode 21417: reward = -67.50, steps = 23 15:02:56 [INFO] train episode 21418: reward = -83.59, steps = 28 15:02:58 [INFO] train episode 21419: reward = -67.23, steps = 25 15:03:02 [INFO] train episode 21420: reward = -72.27, steps = 42 15:03:05 [INFO] train episode 21421: reward = -53.89, steps = 31 15:03:09 [INFO] train episode 21422: reward = -102.18, steps = 46 15:03:12 [INFO] train episode 21423: reward = -90.70, steps = 29 15:03:15 [INFO] train episode 21424: reward = -63.10, steps = 37 15:03:18 [INFO] train episode 21425: reward = -78.50, steps = 31 15:03:20 [INFO] train episode 21426: reward = -98.58, steps = 21 15:03:22 [INFO] train episode 21427: reward = -78.75, steps = 25 15:03:26 [INFO] train episode 21428: reward = -73.25, steps = 40 15:03:28 [INFO] train episode 21429: reward = -96.19, steps = 20 15:03:31 [INFO] train episode 21430: reward = -57.54, steps = 31 15:03:33 [INFO] train episode 21431: reward = -56.13, steps = 31 15:03:38 [INFO] train episode 21432: reward = -100.39, steps = 55 15:03:41 [INFO] train episode 21433: reward = -89.61, steps = 28 15:03:43 [INFO] train episode 21434: reward = -70.13, steps = 28 15:03:46 [INFO] train episode 21435: reward = -61.63, steps = 31 15:03:48 [INFO] train episode 21436: reward = -60.51, steps = 23 15:03:50 [INFO] train episode 21437: reward = -60.44, steps = 23 15:03:53 [INFO] train episode 21438: reward = -84.97, steps = 29 15:03:55 [INFO] train episode 21439: reward = -53.35, steps = 25 15:03:58 [INFO] train episode 21440: reward = -118.27, steps = 33 15:04:00 [INFO] train episode 21441: reward = -32.13, steps = 20 15:04:04 [INFO] train episode 21442: reward = -88.52, steps = 36 15:04:08 [INFO] train episode 21443: reward = -90.61, steps = 45 15:04:10 [INFO] train episode 21444: reward = -74.74, steps = 27 15:04:12 [INFO] train episode 21445: reward = -62.66, steps = 22 15:04:14 [INFO] train episode 21446: reward = -59.95, steps = 25 15:04:19 [INFO] train episode 21447: reward = -61.39, steps = 50 15:04:21 [INFO] train episode 21448: reward = -54.87, steps = 20 15:04:24 [INFO] train episode 21449: reward = -83.74, steps = 33 15:04:27 [INFO] train episode 21450: reward = -84.70, steps = 36 15:04:29 [INFO] train episode 21451: reward = -51.60, steps = 20 15:04:31 [INFO] train episode 21452: reward = -64.98, steps = 30 15:04:34 [INFO] train episode 21453: reward = -62.55, steps = 32 15:04:36 [INFO] train episode 21454: reward = -81.85, steps = 22 15:04:41 [INFO] train episode 21455: reward = -99.36, steps = 58 15:04:43 [INFO] train episode 21456: reward = -76.99, steps = 26 15:04:46 [INFO] train episode 21457: reward = -75.46, steps = 25 15:04:47 [INFO] train episode 21458: reward = -98.92, steps = 20 15:04:49 [INFO] train episode 21459: reward = -100.71, steps = 21 15:04:52 [INFO] train episode 21460: reward = -43.19, steps = 22 15:04:55 [INFO] train episode 21461: reward = -88.30, steps = 43 15:04:57 [INFO] train episode 21462: reward = -64.30, steps = 26 15:04:59 [INFO] train episode 21463: reward = -90.75, steps = 20 15:05:04 [INFO] train episode 21464: reward = -70.11, steps = 56 15:05:07 [INFO] train episode 21465: reward = -85.19, steps = 37 15:05:10 [INFO] train episode 21466: reward = -76.78, steps = 33 15:05:12 [INFO] train episode 21467: reward = -59.36, steps = 22 15:05:15 [INFO] train episode 21468: reward = -61.82, steps = 34 15:05:17 [INFO] train episode 21469: reward = -74.75, steps = 20 15:05:20 [INFO] train episode 21470: reward = -85.53, steps = 30 15:05:22 [INFO] train episode 21471: reward = -79.74, steps = 20 15:05:25 [INFO] train episode 21472: reward = -76.39, steps = 30 15:05:27 [INFO] train episode 21473: reward = -49.94, steps = 25 15:05:30 [INFO] train episode 21474: reward = -51.58, steps = 30 15:05:31 [INFO] train episode 21475: reward = -70.20, steps = 20 15:05:34 [INFO] train episode 21476: reward = -60.46, steps = 28 15:05:36 [INFO] train episode 21477: reward = -91.06, steps = 21 15:05:38 [INFO] train episode 21478: reward = -33.46, steps = 23 15:05:41 [INFO] train episode 21479: reward = -102.94, steps = 32 15:05:43 [INFO] train episode 21480: reward = -82.01, steps = 23 15:05:46 [INFO] train episode 21481: reward = -110.68, steps = 37 15:05:52 [INFO] train episode 21482: reward = -129.58, steps = 63 15:05:53 [INFO] train episode 21483: reward = -98.36, steps = 19 15:05:57 [INFO] train episode 21484: reward = -60.30, steps = 41 15:06:01 [INFO] train episode 21485: reward = -168.67, steps = 43 15:06:03 [INFO] train episode 21486: reward = -57.04, steps = 19 15:06:04 [INFO] train episode 21487: reward = -76.70, steps = 20 15:06:07 [INFO] train episode 21488: reward = -108.76, steps = 30 15:06:09 [INFO] train episode 21489: reward = -51.96, steps = 24 15:06:11 [INFO] train episode 21490: reward = -126.47, steps = 24 15:06:14 [INFO] train episode 21491: reward = -90.61, steps = 31 15:06:17 [INFO] train episode 21492: reward = -69.45, steps = 27 15:06:19 [INFO] train episode 21493: reward = -68.56, steps = 26 15:06:21 [INFO] train episode 21494: reward = -82.94, steps = 27 15:06:25 [INFO] train episode 21495: reward = -78.80, steps = 51 15:06:28 [INFO] train episode 21496: reward = -80.58, steps = 34 15:06:32 [INFO] train episode 21497: reward = -44.36, steps = 38 15:06:34 [INFO] train episode 21498: reward = -52.01, steps = 27 15:06:37 [INFO] train episode 21499: reward = -65.56, steps = 29 15:06:40 [INFO] train episode 21500: reward = -59.48, steps = 27 15:06:42 [INFO] train episode 21501: reward = -63.66, steps = 22 15:06:44 [INFO] train episode 21502: reward = -46.85, steps = 25 15:06:46 [INFO] train episode 21503: reward = -98.37, steps = 21 15:06:48 [INFO] train episode 21504: reward = -49.10, steps = 23 15:06:50 [INFO] train episode 21505: reward = -54.16, steps = 23 15:06:52 [INFO] train episode 21506: reward = -85.38, steps = 27 15:06:55 [INFO] train episode 21507: reward = -85.14, steps = 30 15:06:58 [INFO] train episode 21508: reward = -107.60, steps = 27 15:07:01 [INFO] train episode 21509: reward = -78.11, steps = 27 15:07:05 [INFO] train episode 21510: reward = -72.56, steps = 45 15:07:07 [INFO] train episode 21511: reward = -48.62, steps = 23 15:07:08 [INFO] train episode 21512: reward = -100.72, steps = 19 15:07:10 [INFO] train episode 21513: reward = -38.31, steps = 20 15:07:13 [INFO] train episode 21514: reward = -45.73, steps = 31 15:07:15 [INFO] train episode 21515: reward = -58.43, steps = 23 15:07:20 [INFO] train episode 21516: reward = -100.08, steps = 54 15:07:23 [INFO] train episode 21517: reward = -93.00, steps = 36 15:07:26 [INFO] train episode 21518: reward = -74.88, steps = 29 15:07:29 [INFO] train episode 21519: reward = -70.49, steps = 40 15:07:32 [INFO] train episode 21520: reward = -105.48, steps = 32 15:07:36 [INFO] train episode 21521: reward = -60.69, steps = 43 15:07:43 [INFO] train episode 21522: reward = -134.15, steps = 77 15:07:46 [INFO] train episode 21523: reward = -77.19, steps = 37 15:07:48 [INFO] train episode 21524: reward = -59.99, steps = 27 15:07:50 [INFO] train episode 21525: reward = -68.61, steps = 25 15:07:53 [INFO] train episode 21526: reward = -45.29, steps = 27 15:07:57 [INFO] train episode 21527: reward = -89.38, steps = 45 15:08:02 [INFO] train episode 21528: reward = -75.19, steps = 54 15:08:06 [INFO] train episode 21529: reward = -83.95, steps = 48 15:08:08 [INFO] train episode 21530: reward = -56.79, steps = 23 15:08:11 [INFO] train episode 21531: reward = -75.46, steps = 39 15:08:14 [INFO] train episode 21532: reward = -74.64, steps = 26 15:08:16 [INFO] train episode 21533: reward = -112.05, steps = 26 15:08:20 [INFO] train episode 21534: reward = -123.57, steps = 51 15:08:23 [INFO] train episode 21535: reward = -60.17, steps = 29 15:08:26 [INFO] train episode 21536: reward = -69.53, steps = 30 15:08:29 [INFO] train episode 21537: reward = -76.55, steps = 41 15:08:31 [INFO] train episode 21538: reward = -57.94, steps = 20 15:08:33 [INFO] train episode 21539: reward = -68.00, steps = 20 15:08:35 [INFO] train episode 21540: reward = -97.08, steps = 25 15:08:37 [INFO] train episode 21541: reward = -116.21, steps = 22 15:08:39 [INFO] train episode 21542: reward = -58.35, steps = 25 15:08:42 [INFO] train episode 21543: reward = -50.72, steps = 22 15:08:43 [INFO] train episode 21544: reward = -45.92, steps = 22 15:08:46 [INFO] train episode 21545: reward = -60.49, steps = 24 15:08:48 [INFO] train episode 21546: reward = -62.54, steps = 27 15:08:51 [INFO] train episode 21547: reward = -71.54, steps = 27 15:08:53 [INFO] train episode 21548: reward = -55.57, steps = 31 15:08:56 [INFO] train episode 21549: reward = -55.45, steps = 30 15:09:00 [INFO] train episode 21550: reward = -63.23, steps = 47 15:09:03 [INFO] train episode 21551: reward = -78.84, steps = 35 15:09:05 [INFO] train episode 21552: reward = -59.02, steps = 21 15:09:08 [INFO] train episode 21553: reward = -89.39, steps = 32 15:09:10 [INFO] train episode 21554: reward = -61.01, steps = 19 15:09:14 [INFO] train episode 21555: reward = -90.17, steps = 38 15:09:16 [INFO] train episode 21556: reward = -75.46, steps = 22 15:09:18 [INFO] train episode 21557: reward = -67.48, steps = 23 15:09:21 [INFO] train episode 21558: reward = -119.18, steps = 36 15:09:23 [INFO] train episode 21559: reward = -62.75, steps = 29 15:09:25 [INFO] train episode 21560: reward = -67.52, steps = 20 15:09:27 [INFO] train episode 21561: reward = -52.69, steps = 25 15:09:31 [INFO] train episode 21562: reward = -77.79, steps = 35 15:09:34 [INFO] train episode 21563: reward = -73.18, steps = 35 15:09:37 [INFO] train episode 21564: reward = -64.20, steps = 35 15:09:39 [INFO] train episode 21565: reward = -80.71, steps = 25 15:09:41 [INFO] train episode 21566: reward = -56.26, steps = 23 15:09:43 [INFO] train episode 21567: reward = -70.25, steps = 20 15:09:47 [INFO] train episode 21568: reward = -88.91, steps = 46 15:09:50 [INFO] train episode 21569: reward = -45.99, steps = 25 15:09:52 [INFO] train episode 21570: reward = -37.85, steps = 22 15:09:54 [INFO] train episode 21571: reward = -57.96, steps = 20 15:09:57 [INFO] train episode 21572: reward = -84.59, steps = 27 15:09:59 [INFO] train episode 21573: reward = -80.47, steps = 28 15:10:01 [INFO] train episode 21574: reward = -62.73, steps = 26 15:10:04 [INFO] train episode 21575: reward = -105.75, steps = 24 15:10:08 [INFO] train episode 21576: reward = -104.64, steps = 46 15:10:10 [INFO] train episode 21577: reward = -86.74, steps = 23 15:10:13 [INFO] train episode 21578: reward = -91.01, steps = 33 15:10:14 [INFO] train episode 21579: reward = -56.56, steps = 20 15:10:17 [INFO] train episode 21580: reward = -46.28, steps = 31 15:10:20 [INFO] train episode 21581: reward = -62.08, steps = 26 15:10:23 [INFO] train episode 21582: reward = -99.73, steps = 39 15:10:25 [INFO] train episode 21583: reward = -81.07, steps = 24 15:10:29 [INFO] train episode 21584: reward = -61.19, steps = 43 15:10:31 [INFO] train episode 21585: reward = -51.49, steps = 26 15:10:33 [INFO] train episode 21586: reward = -48.41, steps = 23 15:10:36 [INFO] train episode 21587: reward = -88.46, steps = 34 15:10:38 [INFO] train episode 21588: reward = -49.27, steps = 22 15:10:41 [INFO] train episode 21589: reward = -106.38, steps = 31 15:10:44 [INFO] train episode 21590: reward = -78.03, steps = 38 15:10:46 [INFO] train episode 21591: reward = -68.41, steps = 24 15:10:49 [INFO] train episode 21592: reward = -51.38, steps = 35 15:10:52 [INFO] train episode 21593: reward = -71.94, steps = 21 15:10:54 [INFO] train episode 21594: reward = -64.92, steps = 25 15:10:57 [INFO] train episode 21595: reward = -41.44, steps = 33 15:10:59 [INFO] train episode 21596: reward = -76.43, steps = 24 15:11:03 [INFO] train episode 21597: reward = -94.14, steps = 45 15:11:05 [INFO] train episode 21598: reward = -65.75, steps = 23 15:11:10 [INFO] train episode 21599: reward = -136.30, steps = 53 15:11:13 [INFO] train episode 21600: reward = -80.85, steps = 38 15:11:15 [INFO] train episode 21601: reward = -85.49, steps = 24 15:11:18 [INFO] train episode 21602: reward = -76.72, steps = 39 15:11:20 [INFO] train episode 21603: reward = -98.26, steps = 21 15:11:25 [INFO] train episode 21604: reward = -94.02, steps = 55 15:11:27 [INFO] train episode 21605: reward = -80.33, steps = 23 15:11:30 [INFO] train episode 21606: reward = -78.54, steps = 36 15:11:34 [INFO] train episode 21607: reward = -46.70, steps = 40 15:11:37 [INFO] train episode 21608: reward = -73.39, steps = 41 15:11:39 [INFO] train episode 21609: reward = -91.13, steps = 20 15:11:41 [INFO] train episode 21610: reward = -68.53, steps = 22 15:11:43 [INFO] train episode 21611: reward = -67.07, steps = 20 15:11:45 [INFO] train episode 21612: reward = -61.59, steps = 23 15:11:48 [INFO] train episode 21613: reward = -76.58, steps = 31 15:11:51 [INFO] train episode 21614: reward = -50.72, steps = 41 15:11:54 [INFO] train episode 21615: reward = -80.48, steps = 29 15:11:57 [INFO] train episode 21616: reward = -89.04, steps = 37 15:11:59 [INFO] train episode 21617: reward = -83.37, steps = 24 15:12:02 [INFO] train episode 21618: reward = -57.93, steps = 27 15:12:05 [INFO] train episode 21619: reward = -47.93, steps = 37 15:12:09 [INFO] train episode 21620: reward = -75.92, steps = 46 15:12:11 [INFO] train episode 21621: reward = -70.50, steps = 23 15:12:13 [INFO] train episode 21622: reward = -83.95, steps = 20 15:12:16 [INFO] train episode 21623: reward = -85.77, steps = 36 15:12:18 [INFO] train episode 21624: reward = -91.15, steps = 22 15:12:21 [INFO] train episode 21625: reward = -78.08, steps = 31 15:12:23 [INFO] train episode 21626: reward = -51.33, steps = 21 15:12:27 [INFO] train episode 21627: reward = -117.35, steps = 49 15:12:31 [INFO] train episode 21628: reward = -61.35, steps = 42 15:12:33 [INFO] train episode 21629: reward = -108.94, steps = 25 15:12:36 [INFO] train episode 21630: reward = -84.01, steps = 28 15:12:38 [INFO] train episode 21631: reward = -64.44, steps = 23 15:12:41 [INFO] train episode 21632: reward = -71.93, steps = 33 15:12:44 [INFO] train episode 21633: reward = -129.32, steps = 31 15:12:48 [INFO] train episode 21634: reward = -108.95, steps = 39 15:12:51 [INFO] train episode 21635: reward = -102.52, steps = 37 15:12:56 [INFO] train episode 21636: reward = -79.86, steps = 55 15:12:59 [INFO] train episode 21637: reward = -61.53, steps = 34 15:13:03 [INFO] train episode 21638: reward = -97.29, steps = 44 15:13:05 [INFO] train episode 21639: reward = -81.09, steps = 19 15:13:07 [INFO] train episode 21640: reward = -48.27, steps = 21 15:13:09 [INFO] train episode 21641: reward = -73.04, steps = 29 15:13:14 [INFO] train episode 21642: reward = -108.83, steps = 57 15:13:19 [INFO] train episode 21643: reward = -81.78, steps = 52 15:13:21 [INFO] train episode 21644: reward = -75.99, steps = 25 15:13:25 [INFO] train episode 21645: reward = -49.68, steps = 35 15:13:27 [INFO] train episode 21646: reward = -101.07, steps = 25 15:13:31 [INFO] train episode 21647: reward = -64.59, steps = 48 15:13:33 [INFO] train episode 21648: reward = -64.66, steps = 21 15:13:38 [INFO] train episode 21649: reward = -77.93, steps = 57 15:13:41 [INFO] train episode 21650: reward = -81.11, steps = 39 15:13:44 [INFO] train episode 21651: reward = -92.84, steps = 28 15:13:46 [INFO] train episode 21652: reward = -67.60, steps = 29 15:13:51 [INFO] train episode 21653: reward = -90.82, steps = 52 15:13:55 [INFO] train episode 21654: reward = -92.24, steps = 48 15:13:57 [INFO] train episode 21655: reward = -110.56, steps = 18 15:14:00 [INFO] train episode 21656: reward = -64.04, steps = 42 15:14:03 [INFO] train episode 21657: reward = -99.62, steps = 32 15:14:08 [INFO] train episode 21658: reward = -73.10, steps = 47 15:14:11 [INFO] train episode 21659: reward = -100.33, steps = 41 15:14:14 [INFO] train episode 21660: reward = -98.84, steps = 29 15:14:17 [INFO] train episode 21661: reward = -62.08, steps = 36 15:14:20 [INFO] train episode 21662: reward = -82.00, steps = 38 15:14:24 [INFO] train episode 21663: reward = -105.14, steps = 44 15:14:26 [INFO] train episode 21664: reward = -83.15, steps = 19 15:14:28 [INFO] train episode 21665: reward = -48.85, steps = 21 15:14:30 [INFO] train episode 21666: reward = -69.48, steps = 29 15:14:32 [INFO] train episode 21667: reward = -49.68, steps = 21 15:14:34 [INFO] train episode 21668: reward = -68.53, steps = 24 15:14:38 [INFO] train episode 21669: reward = -60.77, steps = 39 15:14:40 [INFO] train episode 21670: reward = -44.20, steps = 24 15:14:43 [INFO] train episode 21671: reward = -40.45, steps = 28 15:14:45 [INFO] train episode 21672: reward = -116.32, steps = 32 15:14:48 [INFO] train episode 21673: reward = -72.96, steps = 32 15:14:52 [INFO] train episode 21674: reward = -59.96, steps = 42 15:14:55 [INFO] train episode 21675: reward = -61.11, steps = 28 15:14:57 [INFO] train episode 21676: reward = -45.76, steps = 22 15:15:00 [INFO] train episode 21677: reward = -58.00, steps = 36 15:15:02 [INFO] train episode 21678: reward = -104.33, steps = 28 15:15:05 [INFO] train episode 21679: reward = -51.09, steps = 30 15:15:07 [INFO] train episode 21680: reward = -58.12, steps = 22 15:15:09 [INFO] train episode 21681: reward = -110.55, steps = 21 15:15:11 [INFO] train episode 21682: reward = -78.63, steps = 28 15:15:15 [INFO] train episode 21683: reward = -78.98, steps = 39 15:15:17 [INFO] train episode 21684: reward = -55.55, steps = 28 15:15:20 [INFO] train episode 21685: reward = -78.31, steps = 28 15:15:22 [INFO] train episode 21686: reward = -97.33, steps = 24 15:15:24 [INFO] train episode 21687: reward = -58.64, steps = 25 15:15:29 [INFO] train episode 21688: reward = -102.82, steps = 48 15:15:33 [INFO] train episode 21689: reward = -61.42, steps = 48 15:15:37 [INFO] train episode 21690: reward = -75.80, steps = 40 15:15:39 [INFO] train episode 21691: reward = -61.28, steps = 22 15:15:42 [INFO] train episode 21692: reward = -105.22, steps = 33 15:15:47 [INFO] train episode 21693: reward = -79.85, steps = 52 15:15:49 [INFO] train episode 21694: reward = -83.12, steps = 26 15:15:52 [INFO] train episode 21695: reward = -47.15, steps = 24 15:15:53 [INFO] train episode 21696: reward = -79.66, steps = 22 15:15:56 [INFO] train episode 21697: reward = -51.61, steps = 33 15:15:58 [INFO] train episode 21698: reward = -65.14, steps = 22 15:16:01 [INFO] train episode 21699: reward = -46.06, steps = 29 15:16:03 [INFO] train episode 21700: reward = -53.99, steps = 23 15:16:06 [INFO] train episode 21701: reward = -70.31, steps = 34 15:16:10 [INFO] train episode 21702: reward = -71.27, steps = 49 15:16:12 [INFO] train episode 21703: reward = -83.47, steps = 20 15:16:17 [INFO] train episode 21704: reward = -49.99, steps = 54 15:16:20 [INFO] train episode 21705: reward = -86.77, steps = 34 15:16:22 [INFO] train episode 21706: reward = -53.30, steps = 23 15:16:24 [INFO] train episode 21707: reward = -85.08, steps = 25 15:16:28 [INFO] train episode 21708: reward = -106.32, steps = 46 15:16:31 [INFO] train episode 21709: reward = -87.35, steps = 27 15:16:33 [INFO] train episode 21710: reward = -70.76, steps = 18 15:16:35 [INFO] train episode 21711: reward = -72.13, steps = 20 15:16:37 [INFO] train episode 21712: reward = -77.12, steps = 24 15:16:39 [INFO] train episode 21713: reward = -77.66, steps = 21 15:16:41 [INFO] train episode 21714: reward = -108.76, steps = 24 15:16:43 [INFO] train episode 21715: reward = -57.22, steps = 23 15:16:45 [INFO] train episode 21716: reward = -76.58, steps = 18 15:16:47 [INFO] train episode 21717: reward = -77.32, steps = 33 15:16:52 [INFO] train episode 21718: reward = -63.12, steps = 44 15:16:54 [INFO] train episode 21719: reward = -58.50, steps = 25 15:16:57 [INFO] train episode 21720: reward = -62.77, steps = 32 15:16:58 [INFO] train episode 21721: reward = -106.68, steps = 19 15:17:01 [INFO] train episode 21722: reward = -90.38, steps = 36 15:17:06 [INFO] train episode 21723: reward = -70.27, steps = 46 15:17:07 [INFO] train episode 21724: reward = -82.05, steps = 19 15:17:11 [INFO] train episode 21725: reward = -59.86, steps = 40 15:17:14 [INFO] train episode 21726: reward = -100.15, steps = 36 15:17:16 [INFO] train episode 21727: reward = -70.90, steps = 27 15:17:20 [INFO] train episode 21728: reward = -87.17, steps = 43 15:17:22 [INFO] train episode 21729: reward = -49.58, steps = 19 15:17:25 [INFO] train episode 21730: reward = -80.57, steps = 27 15:17:27 [INFO] train episode 21731: reward = -91.71, steps = 31 15:17:29 [INFO] train episode 21732: reward = -80.74, steps = 19 15:17:31 [INFO] train episode 21733: reward = -60.00, steps = 21 15:17:34 [INFO] train episode 21734: reward = -87.00, steps = 32 15:17:36 [INFO] train episode 21735: reward = -57.36, steps = 24 15:17:38 [INFO] train episode 21736: reward = -114.63, steps = 27 15:17:40 [INFO] train episode 21737: reward = -74.75, steps = 23 15:17:43 [INFO] train episode 21738: reward = -100.36, steps = 35 15:17:48 [INFO] train episode 21739: reward = -125.17, steps = 47 15:17:50 [INFO] train episode 21740: reward = -97.32, steps = 25 15:17:52 [INFO] train episode 21741: reward = -76.27, steps = 30 15:17:55 [INFO] train episode 21742: reward = -73.96, steps = 28 15:17:58 [INFO] train episode 21743: reward = -65.45, steps = 31 15:18:01 [INFO] train episode 21744: reward = -94.21, steps = 32 15:18:05 [INFO] train episode 21745: reward = -55.10, steps = 57 15:18:07 [INFO] train episode 21746: reward = -117.02, steps = 20 15:18:09 [INFO] train episode 21747: reward = -112.29, steps = 21 15:18:13 [INFO] train episode 21748: reward = -112.49, steps = 44 15:18:17 [INFO] train episode 21749: reward = -69.56, steps = 40 15:18:20 [INFO] train episode 21750: reward = -65.95, steps = 43 15:18:23 [INFO] train episode 21751: reward = -89.13, steps = 35 15:18:25 [INFO] train episode 21752: reward = -69.95, steps = 23 15:18:28 [INFO] train episode 21753: reward = -67.63, steps = 24 15:18:31 [INFO] train episode 21754: reward = -57.30, steps = 28 15:18:33 [INFO] train episode 21755: reward = -89.03, steps = 20 15:18:34 [INFO] train episode 21756: reward = -62.47, steps = 21 15:18:37 [INFO] train episode 21757: reward = -62.07, steps = 25 15:18:39 [INFO] train episode 21758: reward = -112.84, steps = 22 15:18:42 [INFO] train episode 21759: reward = -45.40, steps = 29 15:18:44 [INFO] train episode 21760: reward = -81.79, steps = 20 15:18:46 [INFO] train episode 21761: reward = -51.90, steps = 25 15:18:49 [INFO] train episode 21762: reward = -81.98, steps = 24 15:18:53 [INFO] train episode 21763: reward = -59.97, steps = 57 15:18:57 [INFO] train episode 21764: reward = -101.63, steps = 45 15:19:01 [INFO] train episode 21765: reward = -103.72, steps = 34 15:19:04 [INFO] train episode 21766: reward = -57.16, steps = 37 15:19:08 [INFO] train episode 21767: reward = -80.59, steps = 44 15:19:10 [INFO] train episode 21768: reward = -127.59, steps = 27 15:19:12 [INFO] train episode 21769: reward = -61.80, steps = 22 15:19:16 [INFO] train episode 21770: reward = -110.14, steps = 42 15:19:18 [INFO] train episode 21771: reward = -63.72, steps = 26 15:19:22 [INFO] train episode 21772: reward = -91.16, steps = 44 15:19:25 [INFO] train episode 21773: reward = -68.75, steps = 30 15:19:27 [INFO] train episode 21774: reward = -51.24, steps = 25 15:19:30 [INFO] train episode 21775: reward = -66.99, steps = 36 15:19:33 [INFO] train episode 21776: reward = -71.99, steps = 32 15:19:36 [INFO] train episode 21777: reward = -71.02, steps = 29 15:19:39 [INFO] train episode 21778: reward = -93.75, steps = 45 15:19:41 [INFO] train episode 21779: reward = -90.89, steps = 19 15:19:43 [INFO] train episode 21780: reward = -79.10, steps = 23 15:19:46 [INFO] train episode 21781: reward = -69.29, steps = 36 15:19:49 [INFO] train episode 21782: reward = -70.67, steps = 26 15:19:52 [INFO] train episode 21783: reward = -86.36, steps = 38 15:19:57 [INFO] train episode 21784: reward = -76.60, steps = 50 15:19:58 [INFO] train episode 21785: reward = -88.17, steps = 19 15:20:01 [INFO] train episode 21786: reward = -60.00, steps = 28 15:20:04 [INFO] train episode 21787: reward = -60.63, steps = 36 15:20:06 [INFO] train episode 21788: reward = -44.17, steps = 21 15:20:08 [INFO] train episode 21789: reward = -57.55, steps = 22 15:20:11 [INFO] train episode 21790: reward = -54.25, steps = 28 15:20:16 [INFO] train episode 21791: reward = -85.97, steps = 58 15:20:18 [INFO] train episode 21792: reward = -39.09, steps = 23 15:20:22 [INFO] train episode 21793: reward = -91.28, steps = 47 15:20:26 [INFO] train episode 21794: reward = -71.52, steps = 48 15:20:29 [INFO] train episode 21795: reward = -118.58, steps = 35 15:20:31 [INFO] train episode 21796: reward = -82.91, steps = 26 15:20:36 [INFO] train episode 21797: reward = -110.22, steps = 54 15:20:40 [INFO] train episode 21798: reward = -102.29, steps = 43 15:20:42 [INFO] train episode 21799: reward = -84.51, steps = 23 15:20:45 [INFO] train episode 21800: reward = -54.61, steps = 26 15:20:46 [INFO] train episode 21801: reward = -80.90, steps = 21 15:20:50 [INFO] train episode 21802: reward = -74.79, steps = 39 15:20:52 [INFO] train episode 21803: reward = -69.52, steps = 23 15:20:57 [INFO] train episode 21804: reward = -64.63, steps = 40 15:20:59 [INFO] train episode 21805: reward = -42.89, steps = 26 15:21:05 [INFO] train episode 21806: reward = -96.14, steps = 56 15:21:08 [INFO] train episode 21807: reward = -65.99, steps = 37 15:21:13 [INFO] train episode 21808: reward = -55.27, steps = 48 15:21:15 [INFO] train episode 21809: reward = -100.39, steps = 22 15:21:18 [INFO] train episode 21810: reward = -93.09, steps = 26 15:21:21 [INFO] train episode 21811: reward = -118.03, steps = 39 15:21:23 [INFO] train episode 21812: reward = -67.34, steps = 22 15:21:28 [INFO] train episode 21813: reward = -153.97, steps = 56 15:21:31 [INFO] train episode 21814: reward = -68.70, steps = 30 15:21:35 [INFO] train episode 21815: reward = -96.85, steps = 44 15:21:39 [INFO] train episode 21816: reward = -55.01, steps = 47 15:21:44 [INFO] train episode 21817: reward = -79.98, steps = 52 15:21:49 [INFO] train episode 21818: reward = -144.12, steps = 54 15:21:51 [INFO] train episode 21819: reward = -90.19, steps = 26 15:21:54 [INFO] train episode 21820: reward = -90.81, steps = 29 15:21:59 [INFO] train episode 21821: reward = -81.56, steps = 57 15:22:00 [INFO] train episode 21822: reward = -100.83, steps = 20 15:22:04 [INFO] train episode 21823: reward = -70.01, steps = 38 15:22:06 [INFO] train episode 21824: reward = -55.17, steps = 23 15:22:10 [INFO] train episode 21825: reward = -72.27, steps = 42 15:22:11 [INFO] train episode 21826: reward = -95.62, steps = 20 15:22:15 [INFO] train episode 21827: reward = -80.87, steps = 45 15:22:21 [INFO] train episode 21828: reward = -89.85, steps = 61 15:22:24 [INFO] train episode 21829: reward = -80.37, steps = 33 15:22:27 [INFO] train episode 21830: reward = -83.13, steps = 35 15:22:29 [INFO] train episode 21831: reward = -111.10, steps = 30 15:22:34 [INFO] train episode 21832: reward = -56.72, steps = 50 15:22:36 [INFO] train episode 21833: reward = -57.56, steps = 22 15:22:39 [INFO] train episode 21834: reward = -57.56, steps = 27 15:22:42 [INFO] train episode 21835: reward = -44.96, steps = 33 15:22:45 [INFO] train episode 21836: reward = -79.62, steps = 35 15:22:46 [INFO] train episode 21837: reward = -87.02, steps = 19 15:22:48 [INFO] train episode 21838: reward = -54.44, steps = 24 15:22:51 [INFO] train episode 21839: reward = -48.94, steps = 29 15:22:55 [INFO] train episode 21840: reward = -51.83, steps = 37 15:22:57 [INFO] train episode 21841: reward = -95.27, steps = 31 15:23:00 [INFO] train episode 21842: reward = -72.03, steps = 26 15:23:03 [INFO] train episode 21843: reward = -63.90, steps = 37 15:23:06 [INFO] train episode 21844: reward = -69.44, steps = 37 15:23:09 [INFO] train episode 21845: reward = -54.41, steps = 30 15:23:11 [INFO] train episode 21846: reward = -49.70, steps = 24 15:23:13 [INFO] train episode 21847: reward = -87.21, steps = 20 15:23:16 [INFO] train episode 21848: reward = -55.01, steps = 35 15:23:18 [INFO] train episode 21849: reward = -85.11, steps = 20 15:23:20 [INFO] train episode 21850: reward = -127.40, steps = 22 15:23:23 [INFO] train episode 21851: reward = -57.50, steps = 37 15:23:26 [INFO] train episode 21852: reward = -79.23, steps = 29 15:23:28 [INFO] train episode 21853: reward = -86.45, steps = 26 15:23:31 [INFO] train episode 21854: reward = -112.06, steps = 25 15:23:32 [INFO] train episode 21855: reward = -103.15, steps = 19 15:23:34 [INFO] train episode 21856: reward = -61.17, steps = 21 15:23:38 [INFO] train episode 21857: reward = -75.52, steps = 41 15:23:42 [INFO] train episode 21858: reward = -130.84, steps = 48 15:23:44 [INFO] train episode 21859: reward = -61.79, steps = 21 15:23:47 [INFO] train episode 21860: reward = -139.80, steps = 35 15:23:51 [INFO] train episode 21861: reward = -48.69, steps = 42 15:23:54 [INFO] train episode 21862: reward = -67.55, steps = 41 15:23:58 [INFO] train episode 21863: reward = -98.52, steps = 43 15:24:00 [INFO] train episode 21864: reward = -81.94, steps = 20 15:24:02 [INFO] train episode 21865: reward = -48.21, steps = 23 15:24:04 [INFO] train episode 21866: reward = -92.06, steps = 25 15:24:09 [INFO] train episode 21867: reward = -40.41, steps = 51 15:24:11 [INFO] train episode 21868: reward = -57.10, steps = 25 15:24:14 [INFO] train episode 21869: reward = -58.91, steps = 25 15:24:15 [INFO] train episode 21870: reward = -65.57, steps = 19 15:24:18 [INFO] train episode 21871: reward = -65.13, steps = 35 15:24:21 [INFO] train episode 21872: reward = -99.55, steps = 35 15:24:23 [INFO] train episode 21873: reward = -56.32, steps = 21 15:24:27 [INFO] train episode 21874: reward = -62.23, steps = 41 15:24:31 [INFO] train episode 21875: reward = -58.98, steps = 34 15:24:33 [INFO] train episode 21876: reward = -72.45, steps = 23 15:24:37 [INFO] train episode 21877: reward = -62.67, steps = 49 15:24:43 [INFO] train episode 21878: reward = -124.34, steps = 64 15:24:46 [INFO] train episode 21879: reward = -68.53, steps = 32 15:24:49 [INFO] train episode 21880: reward = -70.74, steps = 32 15:24:51 [INFO] train episode 21881: reward = -95.29, steps = 30 15:24:53 [INFO] train episode 21882: reward = -66.36, steps = 20 15:24:56 [INFO] train episode 21883: reward = -61.08, steps = 31 15:24:58 [INFO] train episode 21884: reward = -106.32, steps = 24 15:25:00 [INFO] train episode 21885: reward = -61.27, steps = 25 15:25:03 [INFO] train episode 21886: reward = -45.50, steps = 22 15:25:05 [INFO] train episode 21887: reward = -86.87, steps = 22 15:25:08 [INFO] train episode 21888: reward = -102.29, steps = 39 15:25:10 [INFO] train episode 21889: reward = -56.55, steps = 28 15:25:14 [INFO] train episode 21890: reward = -76.91, steps = 38 15:25:18 [INFO] train episode 21891: reward = -121.52, steps = 50 15:25:21 [INFO] train episode 21892: reward = -70.42, steps = 24 15:25:26 [INFO] train episode 21893: reward = -90.33, steps = 58 15:25:27 [INFO] train episode 21894: reward = -39.14, steps = 22 15:25:30 [INFO] train episode 21895: reward = -78.67, steps = 35 15:25:35 [INFO] train episode 21896: reward = -88.90, steps = 52 15:25:38 [INFO] train episode 21897: reward = -64.66, steps = 27 15:25:41 [INFO] train episode 21898: reward = -91.76, steps = 35 15:25:43 [INFO] train episode 21899: reward = -84.93, steps = 20 15:25:45 [INFO] train episode 21900: reward = -76.36, steps = 27 15:25:47 [INFO] train episode 21901: reward = -72.83, steps = 21 15:25:49 [INFO] train episode 21902: reward = -32.66, steps = 26 15:25:52 [INFO] train episode 21903: reward = -77.11, steps = 34 15:25:55 [INFO] train episode 21904: reward = -114.83, steps = 27 15:25:57 [INFO] train episode 21905: reward = -69.79, steps = 28 15:25:59 [INFO] train episode 21906: reward = -61.97, steps = 22 15:26:02 [INFO] train episode 21907: reward = -117.50, steps = 37 15:26:04 [INFO] train episode 21908: reward = -54.40, steps = 23 15:26:07 [INFO] train episode 21909: reward = -65.44, steps = 26 15:26:10 [INFO] train episode 21910: reward = -90.34, steps = 32 15:26:13 [INFO] train episode 21911: reward = -76.50, steps = 33 15:26:16 [INFO] train episode 21912: reward = -71.99, steps = 40 15:26:19 [INFO] train episode 21913: reward = -65.87, steps = 32 15:26:21 [INFO] train episode 21914: reward = -70.33, steps = 28 15:26:24 [INFO] train episode 21915: reward = -81.25, steps = 33 15:26:28 [INFO] train episode 21916: reward = -117.36, steps = 35 15:26:29 [INFO] train episode 21917: reward = -64.46, steps = 21 15:26:34 [INFO] train episode 21918: reward = -112.68, steps = 58 15:26:37 [INFO] train episode 21919: reward = -71.88, steps = 29 15:26:41 [INFO] train episode 21920: reward = -83.92, steps = 43 15:26:44 [INFO] train episode 21921: reward = -69.07, steps = 37 15:26:46 [INFO] train episode 21922: reward = -92.39, steps = 24 15:26:49 [INFO] train episode 21923: reward = -47.26, steps = 26 15:26:51 [INFO] train episode 21924: reward = -59.47, steps = 23 15:26:52 [INFO] train episode 21925: reward = -66.96, steps = 20 15:26:54 [INFO] train episode 21926: reward = -97.48, steps = 21 15:26:58 [INFO] train episode 21927: reward = -113.33, steps = 32 15:27:00 [INFO] train episode 21928: reward = -60.58, steps = 30 15:27:02 [INFO] train episode 21929: reward = -95.05, steps = 20 15:27:07 [INFO] train episode 21930: reward = -61.70, steps = 54 15:27:10 [INFO] train episode 21931: reward = -77.86, steps = 44 15:27:13 [INFO] train episode 21932: reward = -77.55, steps = 28 15:27:16 [INFO] train episode 21933: reward = -52.65, steps = 35 15:27:18 [INFO] train episode 21934: reward = -61.82, steps = 25 15:27:22 [INFO] train episode 21935: reward = -104.63, steps = 36 15:27:26 [INFO] train episode 21936: reward = -71.20, steps = 38 15:27:27 [INFO] train episode 21937: reward = -88.81, steps = 18 15:27:31 [INFO] train episode 21938: reward = -70.28, steps = 32 15:27:34 [INFO] train episode 21939: reward = -59.88, steps = 39 15:27:36 [INFO] train episode 21940: reward = -81.24, steps = 20 15:27:39 [INFO] train episode 21941: reward = -73.37, steps = 36 15:27:40 [INFO] train episode 21942: reward = -80.04, steps = 18 15:27:44 [INFO] train episode 21943: reward = -73.64, steps = 38 15:27:47 [INFO] train episode 21944: reward = -67.25, steps = 28 15:27:49 [INFO] train episode 21945: reward = -64.86, steps = 29 15:27:52 [INFO] train episode 21946: reward = -77.54, steps = 28 15:27:54 [INFO] train episode 21947: reward = -50.31, steps = 32 15:27:57 [INFO] train episode 21948: reward = -80.32, steps = 29 15:28:00 [INFO] train episode 21949: reward = -74.47, steps = 32 15:28:04 [INFO] train episode 21950: reward = -68.16, steps = 44 15:28:07 [INFO] train episode 21951: reward = -60.64, steps = 39 15:28:10 [INFO] train episode 21952: reward = -88.52, steps = 36 15:28:17 [INFO] train episode 21953: reward = -173.52, steps = 73 15:28:21 [INFO] train episode 21954: reward = -64.45, steps = 41 15:28:23 [INFO] train episode 21955: reward = -60.02, steps = 25 15:28:25 [INFO] train episode 21956: reward = -66.00, steps = 24 15:28:28 [INFO] train episode 21957: reward = -62.86, steps = 39 15:28:31 [INFO] train episode 21958: reward = -63.01, steps = 31 15:28:33 [INFO] train episode 21959: reward = -43.09, steps = 21 15:28:35 [INFO] train episode 21960: reward = -73.25, steps = 21 15:28:39 [INFO] train episode 21961: reward = -47.87, steps = 44 15:28:42 [INFO] train episode 21962: reward = -76.96, steps = 40 15:28:44 [INFO] train episode 21963: reward = -88.22, steps = 19 15:28:47 [INFO] train episode 21964: reward = -77.89, steps = 29 15:28:49 [INFO] train episode 21965: reward = -71.47, steps = 23 15:28:52 [INFO] train episode 21966: reward = -56.53, steps = 34 15:28:56 [INFO] train episode 21967: reward = -71.22, steps = 43 15:28:57 [INFO] train episode 21968: reward = -75.68, steps = 21 15:29:00 [INFO] train episode 21969: reward = -90.54, steps = 31 15:29:04 [INFO] train episode 21970: reward = -76.51, steps = 33 15:29:06 [INFO] train episode 21971: reward = -53.26, steps = 21 15:29:08 [INFO] train episode 21972: reward = -49.29, steps = 24 15:29:13 [INFO] train episode 21973: reward = -83.83, steps = 54 15:29:15 [INFO] train episode 21974: reward = -86.59, steps = 19 15:29:17 [INFO] train episode 21975: reward = -81.06, steps = 23 15:29:19 [INFO] train episode 21976: reward = -77.23, steps = 27 15:29:22 [INFO] train episode 21977: reward = -43.39, steps = 31 15:29:25 [INFO] train episode 21978: reward = -58.11, steps = 38 15:29:28 [INFO] train episode 21979: reward = -67.30, steps = 33 15:29:30 [INFO] train episode 21980: reward = -76.87, steps = 24 15:29:32 [INFO] train episode 21981: reward = -50.40, steps = 19 15:29:34 [INFO] train episode 21982: reward = -69.45, steps = 21 15:29:36 [INFO] train episode 21983: reward = -78.25, steps = 28 15:29:38 [INFO] train episode 21984: reward = -70.37, steps = 24 15:29:41 [INFO] train episode 21985: reward = -75.07, steps = 23 15:29:44 [INFO] train episode 21986: reward = -74.10, steps = 43 15:29:47 [INFO] train episode 21987: reward = -93.85, steps = 27 15:29:50 [INFO] train episode 21988: reward = -78.97, steps = 34 15:29:54 [INFO] train episode 21989: reward = -72.33, steps = 46 15:29:55 [INFO] train episode 21990: reward = -77.73, steps = 18 15:29:59 [INFO] train episode 21991: reward = -61.83, steps = 43 15:30:01 [INFO] train episode 21992: reward = -42.58, steps = 23 15:30:06 [INFO] train episode 21993: reward = -122.37, steps = 53 15:30:08 [INFO] train episode 21994: reward = -71.07, steps = 20 15:30:10 [INFO] train episode 21995: reward = -85.98, steps = 24 15:30:12 [INFO] train episode 21996: reward = -79.83, steps = 24 15:30:14 [INFO] train episode 21997: reward = -77.02, steps = 20 15:30:16 [INFO] train episode 21998: reward = -63.31, steps = 20 15:30:18 [INFO] train episode 21999: reward = -59.40, steps = 23 15:30:21 [INFO] train episode 22000: reward = -61.42, steps = 30 15:30:25 [INFO] train episode 22001: reward = -68.05, steps = 40 15:30:27 [INFO] train episode 22002: reward = -77.30, steps = 31 15:30:33 [INFO] train episode 22003: reward = -102.32, steps = 56 15:30:37 [INFO] train episode 22004: reward = -61.50, steps = 44 15:30:39 [INFO] train episode 22005: reward = -56.42, steps = 24 15:30:42 [INFO] train episode 22006: reward = -47.08, steps = 38 15:30:45 [INFO] train episode 22007: reward = -83.83, steps = 34 15:30:48 [INFO] train episode 22008: reward = -24.90, steps = 34 15:30:52 [INFO] train episode 22009: reward = -71.73, steps = 42 15:30:54 [INFO] train episode 22010: reward = -105.59, steps = 26 15:30:57 [INFO] train episode 22011: reward = -73.86, steps = 31 15:30:59 [INFO] train episode 22012: reward = -62.89, steps = 24 15:31:02 [INFO] train episode 22013: reward = -72.37, steps = 27 15:31:07 [INFO] train episode 22014: reward = -108.97, steps = 60 15:31:11 [INFO] train episode 22015: reward = -61.55, steps = 45 15:31:14 [INFO] train episode 22016: reward = -52.19, steps = 39 15:31:16 [INFO] train episode 22017: reward = -63.21, steps = 21 15:31:19 [INFO] train episode 22018: reward = -91.44, steps = 30 15:31:21 [INFO] train episode 22019: reward = -89.56, steps = 19 15:31:24 [INFO] train episode 22020: reward = -83.02, steps = 32 15:31:26 [INFO] train episode 22021: reward = -61.93, steps = 23 15:31:28 [INFO] train episode 22022: reward = -63.93, steps = 31 15:31:30 [INFO] train episode 22023: reward = -67.38, steps = 22 15:31:32 [INFO] train episode 22024: reward = -61.92, steps = 24 15:31:35 [INFO] train episode 22025: reward = -75.85, steps = 23 15:31:37 [INFO] train episode 22026: reward = -117.06, steps = 31 15:31:40 [INFO] train episode 22027: reward = -56.62, steps = 25 15:31:42 [INFO] train episode 22028: reward = -71.61, steps = 29 15:31:45 [INFO] train episode 22029: reward = -73.15, steps = 31 15:31:47 [INFO] train episode 22030: reward = -69.42, steps = 24 15:31:50 [INFO] train episode 22031: reward = -79.52, steps = 30 15:31:54 [INFO] train episode 22032: reward = -121.70, steps = 45 15:31:56 [INFO] train episode 22033: reward = -69.07, steps = 20 15:31:58 [INFO] train episode 22034: reward = -53.99, steps = 22 15:32:02 [INFO] train episode 22035: reward = -98.36, steps = 55 15:32:04 [INFO] train episode 22036: reward = -87.80, steps = 22 15:32:12 [INFO] train episode 22037: reward = -145.17, steps = 80 15:32:14 [INFO] train episode 22038: reward = -81.92, steps = 26 15:32:18 [INFO] train episode 22039: reward = -131.29, steps = 46 15:32:22 [INFO] train episode 22040: reward = -67.97, steps = 42 15:32:24 [INFO] train episode 22041: reward = -55.12, steps = 19 15:32:28 [INFO] train episode 22042: reward = -98.26, steps = 50 15:32:31 [INFO] train episode 22043: reward = -94.51, steps = 37 15:32:33 [INFO] train episode 22044: reward = -55.02, steps = 27 15:32:37 [INFO] train episode 22045: reward = -68.35, steps = 39 15:32:39 [INFO] train episode 22046: reward = -53.04, steps = 21 15:32:41 [INFO] train episode 22047: reward = -52.70, steps = 22 15:32:44 [INFO] train episode 22048: reward = -66.03, steps = 33 15:32:46 [INFO] train episode 22049: reward = -81.63, steps = 22 15:32:48 [INFO] train episode 22050: reward = -95.32, steps = 22 15:32:52 [INFO] train episode 22051: reward = -70.29, steps = 45 15:32:55 [INFO] train episode 22052: reward = -104.65, steps = 29 15:32:57 [INFO] train episode 22053: reward = -52.20, steps = 25 15:32:59 [INFO] train episode 22054: reward = -72.06, steps = 23 15:33:02 [INFO] train episode 22055: reward = -74.42, steps = 38 15:33:04 [INFO] train episode 22056: reward = -65.62, steps = 20 15:33:08 [INFO] train episode 22057: reward = -80.38, steps = 41 15:33:11 [INFO] train episode 22058: reward = -41.58, steps = 35 15:33:13 [INFO] train episode 22059: reward = -107.37, steps = 21 15:33:15 [INFO] train episode 22060: reward = -48.76, steps = 21 15:33:19 [INFO] train episode 22061: reward = -87.22, steps = 33 15:33:22 [INFO] train episode 22062: reward = -63.87, steps = 39 15:33:24 [INFO] train episode 22063: reward = -80.55, steps = 28 15:33:26 [INFO] train episode 22064: reward = -60.82, steps = 23 15:33:30 [INFO] train episode 22065: reward = -77.54, steps = 34 15:33:32 [INFO] train episode 22066: reward = -99.03, steps = 29 15:33:36 [INFO] train episode 22067: reward = -63.30, steps = 39 15:33:38 [INFO] train episode 22068: reward = -46.91, steps = 24 15:33:41 [INFO] train episode 22069: reward = -91.65, steps = 38 15:33:43 [INFO] train episode 22070: reward = -64.18, steps = 23 15:33:47 [INFO] train episode 22071: reward = -106.57, steps = 39 15:33:50 [INFO] train episode 22072: reward = -96.12, steps = 35 15:33:53 [INFO] train episode 22073: reward = -73.53, steps = 32 15:33:57 [INFO] train episode 22074: reward = -72.28, steps = 47 15:33:59 [INFO] train episode 22075: reward = -71.35, steps = 27 15:34:03 [INFO] train episode 22076: reward = -64.88, steps = 33 15:34:05 [INFO] train episode 22077: reward = -86.47, steps = 22 15:34:07 [INFO] train episode 22078: reward = -51.05, steps = 27 15:34:10 [INFO] train episode 22079: reward = -142.23, steps = 37 15:34:12 [INFO] train episode 22080: reward = -42.19, steps = 21 15:34:14 [INFO] train episode 22081: reward = -72.98, steps = 27 15:34:18 [INFO] train episode 22082: reward = -45.32, steps = 30 15:34:23 [INFO] train episode 22083: reward = -116.06, steps = 59 15:34:25 [INFO] train episode 22084: reward = -67.48, steps = 25 15:34:28 [INFO] train episode 22085: reward = -73.46, steps = 35 15:34:32 [INFO] train episode 22086: reward = -100.77, steps = 52 15:34:37 [INFO] train episode 22087: reward = -80.50, steps = 51 15:34:39 [INFO] train episode 22088: reward = -57.47, steps = 21 15:34:42 [INFO] train episode 22089: reward = -59.87, steps = 31 15:34:46 [INFO] train episode 22090: reward = -72.69, steps = 55 15:34:50 [INFO] train episode 22091: reward = -72.30, steps = 34 15:34:53 [INFO] train episode 22092: reward = -54.31, steps = 38 15:34:56 [INFO] train episode 22093: reward = -85.11, steps = 33 15:35:00 [INFO] train episode 22094: reward = -74.39, steps = 49 15:35:02 [INFO] train episode 22095: reward = -95.95, steps = 26 15:35:07 [INFO] train episode 22096: reward = -79.29, steps = 46 15:35:09 [INFO] train episode 22097: reward = -55.09, steps = 23 15:35:11 [INFO] train episode 22098: reward = -41.38, steps = 23 15:35:13 [INFO] train episode 22099: reward = -71.59, steps = 25 15:35:15 [INFO] train episode 22100: reward = -93.72, steps = 21 15:35:16 [INFO] train episode 22101: reward = -65.78, steps = 20 15:35:20 [INFO] train episode 22102: reward = -88.95, steps = 38 15:35:25 [INFO] train episode 22103: reward = -134.70, steps = 50 15:35:28 [INFO] train episode 22104: reward = -69.20, steps = 44 15:35:31 [INFO] train episode 22105: reward = -61.86, steps = 31 15:35:34 [INFO] train episode 22106: reward = -73.45, steps = 36 15:35:36 [INFO] train episode 22107: reward = -68.21, steps = 26 15:35:38 [INFO] train episode 22108: reward = -83.80, steps = 19 15:35:41 [INFO] train episode 22109: reward = -99.01, steps = 34 15:35:44 [INFO] train episode 22110: reward = -55.52, steps = 35 15:35:47 [INFO] train episode 22111: reward = -54.98, steps = 27 15:35:48 [INFO] train episode 22112: reward = -131.77, steps = 21 15:35:50 [INFO] train episode 22113: reward = -64.95, steps = 21 15:35:55 [INFO] train episode 22114: reward = -125.13, steps = 50 15:35:57 [INFO] train episode 22115: reward = -92.55, steps = 28 15:36:00 [INFO] train episode 22116: reward = -76.53, steps = 27 15:36:02 [INFO] train episode 22117: reward = -64.09, steps = 22 15:36:04 [INFO] train episode 22118: reward = -111.71, steps = 23 15:36:08 [INFO] train episode 22119: reward = -47.92, steps = 45 15:36:11 [INFO] train episode 22120: reward = -62.65, steps = 28 15:36:15 [INFO] train episode 22121: reward = -81.04, steps = 43 15:36:18 [INFO] train episode 22122: reward = -64.49, steps = 31 15:36:20 [INFO] train episode 22123: reward = -66.34, steps = 32 15:36:25 [INFO] train episode 22124: reward = -86.10, steps = 48 15:36:27 [INFO] train episode 22125: reward = -59.65, steps = 26 15:36:30 [INFO] train episode 22126: reward = -42.97, steps = 36 15:36:33 [INFO] train episode 22127: reward = -113.33, steps = 36 15:36:37 [INFO] train episode 22128: reward = -56.41, steps = 40 15:36:40 [INFO] train episode 22129: reward = -94.17, steps = 40 15:36:43 [INFO] train episode 22130: reward = -77.01, steps = 24 15:36:48 [INFO] train episode 22131: reward = -94.77, steps = 52 15:36:50 [INFO] train episode 22132: reward = -44.60, steps = 28 15:36:52 [INFO] train episode 22133: reward = -82.50, steps = 22 15:36:54 [INFO] train episode 22134: reward = -81.63, steps = 19 15:36:56 [INFO] train episode 22135: reward = -76.81, steps = 24 15:37:01 [INFO] train episode 22136: reward = -106.14, steps = 57 15:37:05 [INFO] train episode 22137: reward = -104.70, steps = 49 15:37:08 [INFO] train episode 22138: reward = -92.39, steps = 38 15:37:12 [INFO] train episode 22139: reward = -55.08, steps = 41 15:37:15 [INFO] train episode 22140: reward = -96.14, steps = 31 15:37:17 [INFO] train episode 22141: reward = -53.21, steps = 21 15:37:19 [INFO] train episode 22142: reward = -54.65, steps = 23 15:37:22 [INFO] train episode 22143: reward = -63.37, steps = 34 15:37:24 [INFO] train episode 22144: reward = -49.86, steps = 24 15:37:26 [INFO] train episode 22145: reward = -54.16, steps = 24 15:37:28 [INFO] train episode 22146: reward = -80.00, steps = 19 15:37:30 [INFO] train episode 22147: reward = -78.57, steps = 23 15:37:34 [INFO] train episode 22148: reward = -65.55, steps = 38 15:37:37 [INFO] train episode 22149: reward = -55.19, steps = 38 15:37:40 [INFO] train episode 22150: reward = -65.78, steps = 38 15:37:44 [INFO] train episode 22151: reward = -79.81, steps = 38 15:37:46 [INFO] train episode 22152: reward = -73.46, steps = 27 15:37:49 [INFO] train episode 22153: reward = -81.43, steps = 30 15:37:52 [INFO] train episode 22154: reward = -88.06, steps = 30 15:37:54 [INFO] train episode 22155: reward = -97.14, steps = 23 15:37:57 [INFO] train episode 22156: reward = -87.86, steps = 42 15:37:59 [INFO] train episode 22157: reward = -72.23, steps = 23 15:38:02 [INFO] train episode 22158: reward = -54.23, steps = 31 15:38:04 [INFO] train episode 22159: reward = -52.98, steps = 23 15:38:09 [INFO] train episode 22160: reward = -46.41, steps = 48 15:38:11 [INFO] train episode 22161: reward = -99.52, steps = 27 15:38:14 [INFO] train episode 22162: reward = -89.16, steps = 40 15:38:16 [INFO] train episode 22163: reward = -72.11, steps = 20 15:38:18 [INFO] train episode 22164: reward = -52.11, steps = 20 15:38:22 [INFO] train episode 22165: reward = -75.54, steps = 46 15:38:24 [INFO] train episode 22166: reward = -78.88, steps = 24 15:38:29 [INFO] train episode 22167: reward = -82.24, steps = 49 15:38:32 [INFO] train episode 22168: reward = -37.02, steps = 37 15:38:36 [INFO] train episode 22169: reward = -61.81, steps = 43 15:38:39 [INFO] train episode 22170: reward = -104.13, steps = 35 15:38:42 [INFO] train episode 22171: reward = -72.12, steps = 40 15:38:45 [INFO] train episode 22172: reward = -99.84, steps = 35 15:38:49 [INFO] train episode 22173: reward = -96.10, steps = 44 15:38:56 [INFO] train episode 22174: reward = -140.42, steps = 74 15:38:58 [INFO] train episode 22175: reward = -49.15, steps = 22 15:39:00 [INFO] train episode 22176: reward = -103.58, steps = 26 15:39:02 [INFO] train episode 22177: reward = -63.51, steps = 20 15:39:04 [INFO] train episode 22178: reward = -56.52, steps = 22 15:39:06 [INFO] train episode 22179: reward = -66.37, steps = 21 15:39:10 [INFO] train episode 22180: reward = -81.30, steps = 36 15:39:14 [INFO] train episode 22181: reward = -80.23, steps = 41 15:39:16 [INFO] train episode 22182: reward = -90.76, steps = 25 15:39:18 [INFO] train episode 22183: reward = -97.59, steps = 28 15:39:21 [INFO] train episode 22184: reward = -62.22, steps = 32 15:39:23 [INFO] train episode 22185: reward = -69.82, steps = 24 15:39:25 [INFO] train episode 22186: reward = -71.27, steps = 20 15:39:28 [INFO] train episode 22187: reward = -53.87, steps = 25 15:39:30 [INFO] train episode 22188: reward = -57.75, steps = 21 15:39:33 [INFO] train episode 22189: reward = -100.04, steps = 42 15:39:36 [INFO] train episode 22190: reward = -64.37, steps = 27 15:39:39 [INFO] train episode 22191: reward = -88.83, steps = 34 15:39:40 [INFO] train episode 22192: reward = -83.80, steps = 23 15:39:45 [INFO] train episode 22193: reward = -62.59, steps = 42 15:39:46 [INFO] train episode 22194: reward = -111.96, steps = 20 15:39:49 [INFO] train episode 22195: reward = -57.34, steps = 30 15:39:52 [INFO] train episode 22196: reward = -69.34, steps = 33 15:39:54 [INFO] train episode 22197: reward = -68.10, steps = 28 15:39:57 [INFO] train episode 22198: reward = -70.19, steps = 34 15:40:00 [INFO] train episode 22199: reward = -88.62, steps = 25 15:40:02 [INFO] train episode 22200: reward = -92.05, steps = 30 15:40:06 [INFO] train episode 22201: reward = -91.65, steps = 39 15:40:09 [INFO] train episode 22202: reward = -84.39, steps = 37 15:40:13 [INFO] train episode 22203: reward = -79.73, steps = 49 15:40:16 [INFO] train episode 22204: reward = -67.51, steps = 25 15:40:20 [INFO] train episode 22205: reward = -53.78, steps = 51 15:40:23 [INFO] train episode 22206: reward = -80.18, steps = 26 15:40:25 [INFO] train episode 22207: reward = -68.26, steps = 27 15:40:27 [INFO] train episode 22208: reward = -76.57, steps = 19 15:40:30 [INFO] train episode 22209: reward = -78.26, steps = 34 15:40:33 [INFO] train episode 22210: reward = -50.30, steps = 28 15:40:35 [INFO] train episode 22211: reward = -82.00, steps = 26 15:40:37 [INFO] train episode 22212: reward = -59.27, steps = 28 15:40:42 [INFO] train episode 22213: reward = -46.66, steps = 51 15:40:44 [INFO] train episode 22214: reward = -61.19, steps = 20 15:40:47 [INFO] train episode 22215: reward = -68.89, steps = 35 15:40:50 [INFO] train episode 22216: reward = -118.35, steps = 27 15:40:54 [INFO] train episode 22217: reward = -54.46, steps = 42 15:40:57 [INFO] train episode 22218: reward = -133.60, steps = 34 15:41:00 [INFO] train episode 22219: reward = -38.32, steps = 24 15:41:02 [INFO] train episode 22220: reward = -70.01, steps = 26 15:41:06 [INFO] train episode 22221: reward = -57.05, steps = 46 15:41:10 [INFO] train episode 22222: reward = -58.85, steps = 41 15:41:13 [INFO] train episode 22223: reward = -75.81, steps = 37 15:41:16 [INFO] train episode 22224: reward = -46.97, steps = 40 15:41:20 [INFO] train episode 22225: reward = -78.20, steps = 36 15:41:24 [INFO] train episode 22226: reward = -49.51, steps = 45 15:41:26 [INFO] train episode 22227: reward = -56.55, steps = 23 15:41:29 [INFO] train episode 22228: reward = -68.28, steps = 37 15:41:33 [INFO] train episode 22229: reward = -52.63, steps = 38 15:41:35 [INFO] train episode 22230: reward = -66.88, steps = 29 15:41:39 [INFO] train episode 22231: reward = -134.60, steps = 40 15:41:41 [INFO] train episode 22232: reward = -54.17, steps = 20 15:41:43 [INFO] train episode 22233: reward = -79.81, steps = 23 15:41:45 [INFO] train episode 22234: reward = -79.22, steps = 26 15:41:47 [INFO] train episode 22235: reward = -52.26, steps = 21 15:41:51 [INFO] train episode 22236: reward = -46.76, steps = 44 15:41:53 [INFO] train episode 22237: reward = -58.55, steps = 29 15:41:57 [INFO] train episode 22238: reward = -53.25, steps = 34 15:41:59 [INFO] train episode 22239: reward = -85.40, steps = 29 15:42:01 [INFO] train episode 22240: reward = -51.14, steps = 22 15:42:05 [INFO] train episode 22241: reward = -70.24, steps = 39 15:42:08 [INFO] train episode 22242: reward = -60.53, steps = 36 15:42:11 [INFO] train episode 22243: reward = -76.43, steps = 30 15:42:14 [INFO] train episode 22244: reward = -68.15, steps = 26 15:42:16 [INFO] train episode 22245: reward = -82.27, steps = 31 15:42:19 [INFO] train episode 22246: reward = -70.23, steps = 27 15:42:21 [INFO] train episode 22247: reward = -52.83, steps = 30 15:42:24 [INFO] train episode 22248: reward = -70.01, steps = 23 15:42:26 [INFO] train episode 22249: reward = -81.00, steps = 22 15:42:27 [INFO] train episode 22250: reward = -68.06, steps = 20 15:42:30 [INFO] train episode 22251: reward = -64.17, steps = 22 15:42:32 [INFO] train episode 22252: reward = -87.87, steps = 30 15:42:34 [INFO] train episode 22253: reward = -61.43, steps = 23 15:42:36 [INFO] train episode 22254: reward = -57.61, steps = 24 15:42:38 [INFO] train episode 22255: reward = -47.27, steps = 22 15:42:40 [INFO] train episode 22256: reward = -85.29, steps = 22 15:42:46 [INFO] train episode 22257: reward = -111.42, steps = 59 15:42:49 [INFO] train episode 22258: reward = -84.38, steps = 37 15:42:52 [INFO] train episode 22259: reward = -91.57, steps = 41 15:42:56 [INFO] train episode 22260: reward = -77.28, steps = 39 15:43:00 [INFO] train episode 22261: reward = -102.16, steps = 50 15:43:03 [INFO] train episode 22262: reward = -59.89, steps = 33 15:43:06 [INFO] train episode 22263: reward = -44.19, steps = 25 15:43:07 [INFO] train episode 22264: reward = -43.45, steps = 21 15:43:11 [INFO] train episode 22265: reward = -83.51, steps = 39 15:43:16 [INFO] train episode 22266: reward = -88.35, steps = 57 15:43:18 [INFO] train episode 22267: reward = -34.08, steps = 22 15:43:21 [INFO] train episode 22268: reward = -35.11, steps = 36 15:43:26 [INFO] train episode 22269: reward = -100.42, steps = 54 15:43:28 [INFO] train episode 22270: reward = -73.62, steps = 21 15:43:30 [INFO] train episode 22271: reward = -53.17, steps = 27 15:43:34 [INFO] train episode 22272: reward = -60.27, steps = 39 15:43:37 [INFO] train episode 22273: reward = -81.92, steps = 44 15:43:41 [INFO] train episode 22274: reward = -91.95, steps = 36 15:43:45 [INFO] train episode 22275: reward = -125.39, steps = 50 15:43:48 [INFO] train episode 22276: reward = -50.14, steps = 32 15:43:50 [INFO] train episode 22277: reward = -73.23, steps = 19 15:43:52 [INFO] train episode 22278: reward = -74.99, steps = 27 15:43:55 [INFO] train episode 22279: reward = -63.45, steps = 31 15:43:58 [INFO] train episode 22280: reward = -71.11, steps = 31 15:43:59 [INFO] train episode 22281: reward = -48.85, steps = 20 15:44:02 [INFO] train episode 22282: reward = -49.76, steps = 33 15:44:05 [INFO] train episode 22283: reward = -60.74, steps = 29 15:44:07 [INFO] train episode 22284: reward = -59.35, steps = 21 15:44:09 [INFO] train episode 22285: reward = -63.03, steps = 26 15:44:13 [INFO] train episode 22286: reward = -108.54, steps = 43 15:44:15 [INFO] train episode 22287: reward = -65.44, steps = 28 15:44:18 [INFO] train episode 22288: reward = -57.26, steps = 24 15:44:20 [INFO] train episode 22289: reward = -79.41, steps = 23 15:44:23 [INFO] train episode 22290: reward = -135.30, steps = 40 15:44:25 [INFO] train episode 22291: reward = -134.05, steps = 22 15:44:27 [INFO] train episode 22292: reward = -106.26, steps = 20 15:44:29 [INFO] train episode 22293: reward = -59.65, steps = 24 15:44:32 [INFO] train episode 22294: reward = -106.57, steps = 27 15:44:35 [INFO] train episode 22295: reward = -68.51, steps = 34 15:44:37 [INFO] train episode 22296: reward = -64.70, steps = 27 15:44:39 [INFO] train episode 22297: reward = -43.49, steps = 22 15:44:43 [INFO] train episode 22298: reward = -100.78, steps = 38 15:44:45 [INFO] train episode 22299: reward = -78.57, steps = 22 15:44:47 [INFO] train episode 22300: reward = -53.05, steps = 25 15:44:49 [INFO] train episode 22301: reward = -61.93, steps = 21 15:44:51 [INFO] train episode 22302: reward = -69.47, steps = 27 15:44:54 [INFO] train episode 22303: reward = -82.33, steps = 29 15:44:56 [INFO] train episode 22304: reward = -95.80, steps = 21 15:44:58 [INFO] train episode 22305: reward = -60.20, steps = 22 15:45:01 [INFO] train episode 22306: reward = -59.98, steps = 29 15:45:04 [INFO] train episode 22307: reward = -60.10, steps = 27 15:45:09 [INFO] train episode 22308: reward = -147.18, steps = 56 15:45:12 [INFO] train episode 22309: reward = -70.97, steps = 37 15:45:15 [INFO] train episode 22310: reward = -109.92, steps = 28 15:45:19 [INFO] train episode 22311: reward = -87.40, steps = 44 15:45:23 [INFO] train episode 22312: reward = -104.38, steps = 46 15:45:25 [INFO] train episode 22313: reward = -75.49, steps = 32 15:45:27 [INFO] train episode 22314: reward = -146.30, steps = 19 15:45:29 [INFO] train episode 22315: reward = -82.76, steps = 20 15:45:31 [INFO] train episode 22316: reward = -71.73, steps = 21 15:45:33 [INFO] train episode 22317: reward = -45.15, steps = 27 15:45:36 [INFO] train episode 22318: reward = -51.20, steps = 33 15:45:40 [INFO] train episode 22319: reward = -48.88, steps = 41 15:45:42 [INFO] train episode 22320: reward = -36.76, steps = 26 15:45:45 [INFO] train episode 22321: reward = -88.80, steps = 33 15:45:47 [INFO] train episode 22322: reward = -56.05, steps = 23 15:45:50 [INFO] train episode 22323: reward = -79.76, steps = 32 15:45:53 [INFO] train episode 22324: reward = -43.49, steps = 30 15:45:55 [INFO] train episode 22325: reward = -40.63, steps = 23 15:45:58 [INFO] train episode 22326: reward = -52.35, steps = 37 15:46:03 [INFO] train episode 22327: reward = -114.23, steps = 54 15:46:06 [INFO] train episode 22328: reward = -75.28, steps = 39 15:46:08 [INFO] train episode 22329: reward = -82.25, steps = 22 15:46:12 [INFO] train episode 22330: reward = -111.28, steps = 44 15:46:15 [INFO] train episode 22331: reward = -71.95, steps = 32 15:46:19 [INFO] train episode 22332: reward = -47.78, steps = 36 15:46:20 [INFO] train episode 22333: reward = -80.93, steps = 20 15:46:22 [INFO] train episode 22334: reward = -79.11, steps = 23 15:46:26 [INFO] train episode 22335: reward = -89.02, steps = 45 15:46:29 [INFO] train episode 22336: reward = -85.08, steps = 30 15:46:32 [INFO] train episode 22337: reward = -119.52, steps = 32 15:46:34 [INFO] train episode 22338: reward = -77.20, steps = 27 15:46:42 [INFO] train episode 22339: reward = -101.56, steps = 83 15:46:46 [INFO] train episode 22340: reward = -46.42, steps = 56 15:46:49 [INFO] train episode 22341: reward = -62.22, steps = 29 15:46:53 [INFO] train episode 22342: reward = -124.96, steps = 45 15:46:55 [INFO] train episode 22343: reward = -88.12, steps = 20 15:46:57 [INFO] train episode 22344: reward = -42.97, steps = 27 15:46:59 [INFO] train episode 22345: reward = -75.76, steps = 20 15:47:02 [INFO] train episode 22346: reward = -56.02, steps = 37 15:47:05 [INFO] train episode 22347: reward = -52.37, steps = 31 15:47:08 [INFO] train episode 22348: reward = -84.77, steps = 28 15:47:12 [INFO] train episode 22349: reward = -95.39, steps = 46 15:47:15 [INFO] train episode 22350: reward = -62.00, steps = 40 15:47:18 [INFO] train episode 22351: reward = -88.98, steps = 34 15:47:22 [INFO] train episode 22352: reward = -94.00, steps = 37 15:47:24 [INFO] train episode 22353: reward = -96.17, steps = 22 15:47:28 [INFO] train episode 22354: reward = -119.32, steps = 48 15:47:30 [INFO] train episode 22355: reward = -58.29, steps = 24 15:47:32 [INFO] train episode 22356: reward = -53.50, steps = 21 15:47:35 [INFO] train episode 22357: reward = -72.72, steps = 39 15:47:39 [INFO] train episode 22358: reward = -93.36, steps = 42 15:47:41 [INFO] train episode 22359: reward = -77.93, steps = 24 15:47:43 [INFO] train episode 22360: reward = -66.06, steps = 24 15:47:46 [INFO] train episode 22361: reward = -81.12, steps = 29 15:47:49 [INFO] train episode 22362: reward = -57.94, steps = 39 15:47:51 [INFO] train episode 22363: reward = -62.01, steps = 22 15:47:54 [INFO] train episode 22364: reward = -99.39, steps = 35 15:47:58 [INFO] train episode 22365: reward = -103.57, steps = 37 15:48:02 [INFO] train episode 22366: reward = -53.59, steps = 42 15:48:05 [INFO] train episode 22367: reward = -101.09, steps = 35 15:48:10 [INFO] train episode 22368: reward = -145.84, steps = 63 15:48:14 [INFO] train episode 22369: reward = -60.84, steps = 35 15:48:17 [INFO] train episode 22370: reward = -78.35, steps = 33 15:48:21 [INFO] train episode 22371: reward = -59.06, steps = 50 15:48:23 [INFO] train episode 22372: reward = -62.23, steps = 23 15:48:25 [INFO] train episode 22373: reward = -89.32, steps = 22 15:48:28 [INFO] train episode 22374: reward = -66.63, steps = 28 15:48:31 [INFO] train episode 22375: reward = -68.26, steps = 35 15:48:34 [INFO] train episode 22376: reward = -73.88, steps = 36 15:48:37 [INFO] train episode 22377: reward = -80.88, steps = 26 15:48:42 [INFO] train episode 22378: reward = -132.50, steps = 64 15:48:46 [INFO] train episode 22379: reward = -63.08, steps = 37 15:48:48 [INFO] train episode 22380: reward = -92.86, steps = 24 15:48:50 [INFO] train episode 22381: reward = -47.28, steps = 24 15:48:53 [INFO] train episode 22382: reward = -81.13, steps = 32 15:48:56 [INFO] train episode 22383: reward = -74.12, steps = 30 15:49:00 [INFO] train episode 22384: reward = -131.08, steps = 49 15:49:02 [INFO] train episode 22385: reward = -40.91, steps = 20 15:49:05 [INFO] train episode 22386: reward = -111.54, steps = 37 15:49:08 [INFO] train episode 22387: reward = -47.16, steps = 30 15:49:11 [INFO] train episode 22388: reward = -79.25, steps = 43 15:49:14 [INFO] train episode 22389: reward = -75.64, steps = 35 15:49:16 [INFO] train episode 22390: reward = -57.68, steps = 22 15:49:19 [INFO] train episode 22391: reward = -72.52, steps = 30 15:49:21 [INFO] train episode 22392: reward = -59.05, steps = 22 15:49:23 [INFO] train episode 22393: reward = -60.06, steps = 24 15:49:26 [INFO] train episode 22394: reward = -89.94, steps = 33 15:49:29 [INFO] train episode 22395: reward = -58.50, steps = 27 15:49:32 [INFO] train episode 22396: reward = -50.81, steps = 39 15:49:37 [INFO] train episode 22397: reward = -130.04, steps = 50 15:49:40 [INFO] train episode 22398: reward = -73.31, steps = 31 15:49:44 [INFO] train episode 22399: reward = -72.75, steps = 51 15:49:47 [INFO] train episode 22400: reward = -63.65, steps = 30 15:49:48 [INFO] train episode 22401: reward = -73.63, steps = 21 15:49:51 [INFO] train episode 22402: reward = -63.08, steps = 24 15:49:54 [INFO] train episode 22403: reward = -83.84, steps = 35 15:49:56 [INFO] train episode 22404: reward = -47.08, steps = 24 15:49:58 [INFO] train episode 22405: reward = -62.34, steps = 23 15:50:01 [INFO] train episode 22406: reward = -74.24, steps = 32 15:50:03 [INFO] train episode 22407: reward = -43.66, steps = 21 15:50:05 [INFO] train episode 22408: reward = -52.56, steps = 23 15:50:08 [INFO] train episode 22409: reward = -99.82, steps = 37 15:50:11 [INFO] train episode 22410: reward = -123.61, steps = 26 15:50:13 [INFO] train episode 22411: reward = -79.57, steps = 30 15:50:17 [INFO] train episode 22412: reward = -61.69, steps = 45 15:50:20 [INFO] train episode 22413: reward = -80.22, steps = 35 15:50:22 [INFO] train episode 22414: reward = -91.96, steps = 25 15:50:25 [INFO] train episode 22415: reward = -40.46, steps = 23 15:50:27 [INFO] train episode 22416: reward = -87.43, steps = 31 15:50:31 [INFO] train episode 22417: reward = -84.30, steps = 47 15:50:34 [INFO] train episode 22418: reward = -66.15, steps = 34 15:50:37 [INFO] train episode 22419: reward = -71.53, steps = 33 15:50:40 [INFO] train episode 22420: reward = -92.01, steps = 27 15:50:43 [INFO] train episode 22421: reward = -76.68, steps = 29 15:50:46 [INFO] train episode 22422: reward = -58.56, steps = 41 15:50:49 [INFO] train episode 22423: reward = -86.95, steps = 27 15:50:53 [INFO] train episode 22424: reward = -74.77, steps = 39 15:50:55 [INFO] train episode 22425: reward = -66.95, steps = 28 15:50:59 [INFO] train episode 22426: reward = -40.23, steps = 32 15:51:01 [INFO] train episode 22427: reward = -79.24, steps = 30 15:51:03 [INFO] train episode 22428: reward = -50.52, steps = 24 15:51:06 [INFO] train episode 22429: reward = -60.85, steps = 27 15:51:11 [INFO] train episode 22430: reward = -145.50, steps = 65 15:51:16 [INFO] train episode 22431: reward = -93.93, steps = 56 15:51:19 [INFO] train episode 22432: reward = -51.80, steps = 32 15:51:23 [INFO] train episode 22433: reward = -81.82, steps = 40 15:51:26 [INFO] train episode 22434: reward = -120.06, steps = 32 15:51:28 [INFO] train episode 22435: reward = -73.14, steps = 24 15:51:30 [INFO] train episode 22436: reward = -68.96, steps = 19 15:51:32 [INFO] train episode 22437: reward = -78.00, steps = 26 15:51:34 [INFO] train episode 22438: reward = -41.17, steps = 21 15:51:39 [INFO] train episode 22439: reward = -116.57, steps = 55 15:51:41 [INFO] train episode 22440: reward = -71.47, steps = 24 15:51:44 [INFO] train episode 22441: reward = -72.54, steps = 43 15:51:48 [INFO] train episode 22442: reward = -77.64, steps = 38 15:51:51 [INFO] train episode 22443: reward = -51.96, steps = 29 15:51:54 [INFO] train episode 22444: reward = -103.61, steps = 38 15:51:57 [INFO] train episode 22445: reward = -74.79, steps = 32 15:51:59 [INFO] train episode 22446: reward = -48.53, steps = 24 15:52:02 [INFO] train episode 22447: reward = -50.29, steps = 31 15:52:04 [INFO] train episode 22448: reward = -57.98, steps = 22 15:52:07 [INFO] train episode 22449: reward = -66.62, steps = 40 15:52:09 [INFO] train episode 22450: reward = -60.21, steps = 21 15:52:12 [INFO] train episode 22451: reward = -81.56, steps = 28 15:52:14 [INFO] train episode 22452: reward = -77.34, steps = 28 15:52:16 [INFO] train episode 22453: reward = -47.65, steps = 23 15:52:19 [INFO] train episode 22454: reward = -39.51, steps = 22 15:52:21 [INFO] train episode 22455: reward = -57.42, steps = 27 15:52:26 [INFO] train episode 22456: reward = -102.99, steps = 64 15:52:30 [INFO] train episode 22457: reward = -72.05, steps = 38 15:52:32 [INFO] train episode 22458: reward = -65.60, steps = 25 15:52:35 [INFO] train episode 22459: reward = -59.16, steps = 29 15:52:39 [INFO] train episode 22460: reward = -71.91, steps = 53 15:52:43 [INFO] train episode 22461: reward = -90.03, steps = 45 15:52:46 [INFO] train episode 22462: reward = -52.22, steps = 28 15:52:51 [INFO] train episode 22463: reward = -92.67, steps = 57 15:52:54 [INFO] train episode 22464: reward = -56.23, steps = 34 15:52:56 [INFO] train episode 22465: reward = -60.29, steps = 20 15:52:58 [INFO] train episode 22466: reward = -69.12, steps = 27 15:53:00 [INFO] train episode 22467: reward = -66.10, steps = 23 15:53:03 [INFO] train episode 22468: reward = -89.29, steps = 33 15:53:08 [INFO] train episode 22469: reward = -154.32, steps = 48 15:53:11 [INFO] train episode 22470: reward = -89.59, steps = 41 15:53:13 [INFO] train episode 22471: reward = -50.41, steps = 21 15:53:16 [INFO] train episode 22472: reward = -68.31, steps = 36 15:53:18 [INFO] train episode 22473: reward = -76.78, steps = 20 15:53:20 [INFO] train episode 22474: reward = -53.99, steps = 23 15:53:23 [INFO] train episode 22475: reward = -106.55, steps = 29 15:53:24 [INFO] train episode 22476: reward = -88.47, steps = 19 15:53:30 [INFO] train episode 22477: reward = -149.28, steps = 68 15:53:33 [INFO] train episode 22478: reward = -92.79, steps = 32 15:53:35 [INFO] train episode 22479: reward = -82.62, steps = 23 15:53:38 [INFO] train episode 22480: reward = -75.05, steps = 28 15:53:41 [INFO] train episode 22481: reward = -49.86, steps = 40 15:53:48 [INFO] train episode 22482: reward = -191.03, steps = 62 15:53:50 [INFO] train episode 22483: reward = -66.90, steps = 24 15:53:53 [INFO] train episode 22484: reward = -120.93, steps = 41 15:53:56 [INFO] train episode 22485: reward = -66.86, steps = 20 15:54:00 [INFO] train episode 22486: reward = -99.57, steps = 55 15:54:02 [INFO] train episode 22487: reward = -51.52, steps = 22 15:54:05 [INFO] train episode 22488: reward = -59.82, steps = 35 15:54:08 [INFO] train episode 22489: reward = -72.64, steps = 34 15:54:11 [INFO] train episode 22490: reward = -70.30, steps = 28 15:54:15 [INFO] train episode 22491: reward = -84.12, steps = 45 15:54:18 [INFO] train episode 22492: reward = -76.39, steps = 41 15:54:21 [INFO] train episode 22493: reward = -95.37, steps = 27 15:54:23 [INFO] train episode 22494: reward = -73.75, steps = 25 15:54:27 [INFO] train episode 22495: reward = -52.79, steps = 49 15:54:30 [INFO] train episode 22496: reward = -85.24, steps = 33 15:54:34 [INFO] train episode 22497: reward = -72.17, steps = 47 15:54:38 [INFO] train episode 22498: reward = -78.01, steps = 37 15:54:40 [INFO] train episode 22499: reward = -80.17, steps = 29 15:54:43 [INFO] train episode 22500: reward = -80.45, steps = 32 15:54:45 [INFO] train episode 22501: reward = -71.63, steps = 19 15:54:48 [INFO] train episode 22502: reward = -36.27, steps = 35 15:54:50 [INFO] train episode 22503: reward = -72.78, steps = 19 15:54:52 [INFO] train episode 22504: reward = -88.09, steps = 26 15:54:55 [INFO] train episode 22505: reward = -65.69, steps = 28 15:54:56 [INFO] train episode 22506: reward = -78.53, steps = 21 15:54:59 [INFO] train episode 22507: reward = -51.13, steps = 30 15:55:02 [INFO] train episode 22508: reward = -67.85, steps = 26 15:55:05 [INFO] train episode 22509: reward = -65.92, steps = 35 15:55:07 [INFO] train episode 22510: reward = -97.18, steps = 29 15:55:10 [INFO] train episode 22511: reward = -69.96, steps = 24 15:55:11 [INFO] train episode 22512: reward = -49.76, steps = 20 15:55:14 [INFO] train episode 22513: reward = -81.80, steps = 29 15:55:17 [INFO] train episode 22514: reward = -114.23, steps = 35 15:55:19 [INFO] train episode 22515: reward = -65.57, steps = 23 15:55:21 [INFO] train episode 22516: reward = -118.53, steps = 21 15:55:23 [INFO] train episode 22517: reward = -154.22, steps = 25 15:55:27 [INFO] train episode 22518: reward = -78.53, steps = 42 15:55:30 [INFO] train episode 22519: reward = -93.71, steps = 32 15:55:33 [INFO] train episode 22520: reward = -71.86, steps = 31 15:55:35 [INFO] train episode 22521: reward = -100.98, steps = 22 15:55:39 [INFO] train episode 22522: reward = -109.04, steps = 45 15:55:44 [INFO] train episode 22523: reward = -122.47, steps = 64 15:55:47 [INFO] train episode 22524: reward = -67.76, steps = 29 15:55:49 [INFO] train episode 22525: reward = -49.20, steps = 22 15:55:52 [INFO] train episode 22526: reward = -64.61, steps = 37 15:55:55 [INFO] train episode 22527: reward = -93.36, steps = 32 15:55:59 [INFO] train episode 22528: reward = -137.12, steps = 49 15:56:03 [INFO] train episode 22529: reward = -112.46, steps = 47 15:56:07 [INFO] train episode 22530: reward = -82.61, steps = 34 15:56:10 [INFO] train episode 22531: reward = -131.25, steps = 45 15:56:12 [INFO] train episode 22532: reward = -37.08, steps = 23 15:56:14 [INFO] train episode 22533: reward = -58.98, steps = 22 15:56:17 [INFO] train episode 22534: reward = -76.94, steps = 29 15:56:19 [INFO] train episode 22535: reward = -71.27, steps = 28 15:56:22 [INFO] train episode 22536: reward = -57.61, steps = 24 15:56:24 [INFO] train episode 22537: reward = -85.88, steps = 19 15:56:26 [INFO] train episode 22538: reward = -54.11, steps = 22 15:56:30 [INFO] train episode 22539: reward = -101.84, steps = 54 15:56:32 [INFO] train episode 22540: reward = -70.64, steps = 23 15:56:36 [INFO] train episode 22541: reward = -115.20, steps = 42 15:56:38 [INFO] train episode 22542: reward = -64.62, steps = 24 15:56:40 [INFO] train episode 22543: reward = -76.99, steps = 20 15:56:45 [INFO] train episode 22544: reward = -91.67, steps = 45 15:56:47 [INFO] train episode 22545: reward = -76.59, steps = 30 15:56:50 [INFO] train episode 22546: reward = -74.01, steps = 25 15:56:53 [INFO] train episode 22547: reward = -99.13, steps = 34 15:56:56 [INFO] train episode 22548: reward = -77.68, steps = 40 15:56:59 [INFO] train episode 22549: reward = -72.17, steps = 25 15:57:01 [INFO] train episode 22550: reward = -59.06, steps = 21 15:57:04 [INFO] train episode 22551: reward = -66.28, steps = 38 15:57:06 [INFO] train episode 22552: reward = -103.27, steps = 22 15:57:08 [INFO] train episode 22553: reward = -82.42, steps = 21 15:57:12 [INFO] train episode 22554: reward = -74.12, steps = 43 15:57:13 [INFO] train episode 22555: reward = -67.39, steps = 21 15:57:17 [INFO] train episode 22556: reward = -59.99, steps = 40 15:57:20 [INFO] train episode 22557: reward = -116.89, steps = 39 15:57:23 [INFO] train episode 22558: reward = -53.72, steps = 30 15:57:26 [INFO] train episode 22559: reward = -127.21, steps = 35 15:57:31 [INFO] train episode 22560: reward = -97.51, steps = 47 15:57:34 [INFO] train episode 22561: reward = -54.92, steps = 39 15:57:36 [INFO] train episode 22562: reward = -66.97, steps = 18 15:57:38 [INFO] train episode 22563: reward = -84.63, steps = 26 15:57:39 [INFO] train episode 22564: reward = -78.40, steps = 19 15:57:41 [INFO] train episode 22565: reward = -123.85, steps = 21 15:57:44 [INFO] train episode 22566: reward = -56.55, steps = 21 15:57:46 [INFO] train episode 22567: reward = -65.58, steps = 25 15:57:48 [INFO] train episode 22568: reward = -73.54, steps = 21 15:57:52 [INFO] train episode 22569: reward = -55.18, steps = 49 15:57:55 [INFO] train episode 22570: reward = -75.31, steps = 39 15:57:59 [INFO] train episode 22571: reward = -97.53, steps = 41 15:58:02 [INFO] train episode 22572: reward = -95.15, steps = 37 15:58:04 [INFO] train episode 22573: reward = -102.99, steps = 21 15:58:07 [INFO] train episode 22574: reward = -61.16, steps = 27 15:58:08 [INFO] train episode 22575: reward = -52.10, steps = 20 15:58:10 [INFO] train episode 22576: reward = -42.58, steps = 22 15:58:14 [INFO] train episode 22577: reward = -99.07, steps = 46 15:58:19 [INFO] train episode 22578: reward = -88.24, steps = 50 15:58:22 [INFO] train episode 22579: reward = -90.63, steps = 33 15:58:24 [INFO] train episode 22580: reward = -58.85, steps = 26 15:58:26 [INFO] train episode 22581: reward = -59.28, steps = 25 15:58:28 [INFO] train episode 22582: reward = -77.12, steps = 22 15:58:30 [INFO] train episode 22583: reward = -72.57, steps = 20 15:58:33 [INFO] train episode 22584: reward = -67.02, steps = 25 15:58:35 [INFO] train episode 22585: reward = -77.82, steps = 26 15:58:38 [INFO] train episode 22586: reward = -88.91, steps = 35 15:58:40 [INFO] train episode 22587: reward = -69.05, steps = 23 15:58:42 [INFO] train episode 22588: reward = -63.76, steps = 19 15:58:45 [INFO] train episode 22589: reward = -70.20, steps = 38 15:58:47 [INFO] train episode 22590: reward = -100.91, steps = 23 15:58:51 [INFO] train episode 22591: reward = -59.30, steps = 37 15:58:53 [INFO] train episode 22592: reward = -120.90, steps = 25 15:58:55 [INFO] train episode 22593: reward = -55.40, steps = 27 15:58:58 [INFO] train episode 22594: reward = -83.43, steps = 25 15:59:00 [INFO] train episode 22595: reward = -49.16, steps = 21 15:59:02 [INFO] train episode 22596: reward = -102.90, steps = 33 15:59:06 [INFO] train episode 22597: reward = -81.42, steps = 33 15:59:08 [INFO] train episode 22598: reward = -82.37, steps = 21 15:59:09 [INFO] train episode 22599: reward = -81.18, steps = 18 15:59:14 [INFO] train episode 22600: reward = -109.18, steps = 50 15:59:15 [INFO] train episode 22601: reward = -72.95, steps = 19 15:59:18 [INFO] train episode 22602: reward = -60.24, steps = 22 15:59:20 [INFO] train episode 22603: reward = -41.36, steps = 23 15:59:24 [INFO] train episode 22604: reward = -78.32, steps = 40 15:59:26 [INFO] train episode 22605: reward = -72.02, steps = 19 15:59:29 [INFO] train episode 22606: reward = -57.66, steps = 40 15:59:33 [INFO] train episode 22607: reward = -96.14, steps = 42 15:59:36 [INFO] train episode 22608: reward = -84.64, steps = 31 15:59:41 [INFO] train episode 22609: reward = -103.15, steps = 47 15:59:45 [INFO] train episode 22610: reward = -101.68, steps = 48 15:59:48 [INFO] train episode 22611: reward = -57.77, steps = 31 15:59:50 [INFO] train episode 22612: reward = -56.75, steps = 23 15:59:53 [INFO] train episode 22613: reward = -76.40, steps = 41 15:59:56 [INFO] train episode 22614: reward = -74.32, steps = 28 16:00:00 [INFO] train episode 22615: reward = -95.55, steps = 42 16:00:02 [INFO] train episode 22616: reward = -65.28, steps = 21 16:00:04 [INFO] train episode 22617: reward = -59.78, steps = 24 16:00:07 [INFO] train episode 22618: reward = -64.85, steps = 41 16:00:10 [INFO] train episode 22619: reward = -56.50, steps = 26 16:00:14 [INFO] train episode 22620: reward = -79.90, steps = 42 16:00:15 [INFO] train episode 22621: reward = -53.73, steps = 22 16:00:17 [INFO] train episode 22622: reward = -68.94, steps = 21 16:00:19 [INFO] train episode 22623: reward = -77.24, steps = 23 16:00:23 [INFO] train episode 22624: reward = -99.12, steps = 43 16:00:27 [INFO] train episode 22625: reward = -56.62, steps = 40 16:00:30 [INFO] train episode 22626: reward = -67.40, steps = 39 16:00:33 [INFO] train episode 22627: reward = -68.96, steps = 29 16:00:36 [INFO] train episode 22628: reward = -87.27, steps = 37 16:00:39 [INFO] train episode 22629: reward = -114.28, steps = 28 16:00:41 [INFO] train episode 22630: reward = -77.74, steps = 22 16:00:43 [INFO] train episode 22631: reward = -85.06, steps = 28 16:00:47 [INFO] train episode 22632: reward = -94.37, steps = 36 16:00:50 [INFO] train episode 22633: reward = -102.54, steps = 41 16:00:53 [INFO] train episode 22634: reward = -69.72, steps = 31 16:00:56 [INFO] train episode 22635: reward = -56.77, steps = 32 16:00:59 [INFO] train episode 22636: reward = -84.52, steps = 40 16:01:02 [INFO] train episode 22637: reward = -50.03, steps = 29 16:01:04 [INFO] train episode 22638: reward = -103.76, steps = 24 16:01:06 [INFO] train episode 22639: reward = -46.86, steps = 23 16:01:10 [INFO] train episode 22640: reward = -72.34, steps = 50 16:01:14 [INFO] train episode 22641: reward = -62.99, steps = 37 16:01:17 [INFO] train episode 22642: reward = -104.38, steps = 34 16:01:19 [INFO] train episode 22643: reward = -93.41, steps = 21 16:01:21 [INFO] train episode 22644: reward = -53.16, steps = 24 16:01:25 [INFO] train episode 22645: reward = -103.78, steps = 43 16:01:27 [INFO] train episode 22646: reward = -56.96, steps = 25 16:01:30 [INFO] train episode 22647: reward = -91.40, steps = 43 16:01:34 [INFO] train episode 22648: reward = -108.58, steps = 39 16:01:38 [INFO] train episode 22649: reward = -94.55, steps = 43 16:01:40 [INFO] train episode 22650: reward = -103.08, steps = 28 16:01:43 [INFO] train episode 22651: reward = -98.10, steps = 31 16:01:46 [INFO] train episode 22652: reward = -72.11, steps = 27 16:01:48 [INFO] train episode 22653: reward = -72.33, steps = 26 16:01:50 [INFO] train episode 22654: reward = -87.41, steps = 26 16:01:56 [INFO] train episode 22655: reward = -97.01, steps = 65 16:01:58 [INFO] train episode 22656: reward = -51.40, steps = 21 16:02:01 [INFO] train episode 22657: reward = -75.67, steps = 30 16:02:03 [INFO] train episode 22658: reward = -92.31, steps = 33 16:02:06 [INFO] train episode 22659: reward = -77.84, steps = 29 16:02:11 [INFO] train episode 22660: reward = -71.50, steps = 52 16:02:13 [INFO] train episode 22661: reward = -49.90, steps = 21 16:02:15 [INFO] train episode 22662: reward = -55.84, steps = 22 16:02:16 [INFO] train episode 22663: reward = -92.50, steps = 20 16:02:18 [INFO] train episode 22664: reward = -52.23, steps = 19 16:02:21 [INFO] train episode 22665: reward = -50.06, steps = 32 16:02:24 [INFO] train episode 22666: reward = -84.42, steps = 29 16:02:30 [INFO] train episode 22667: reward = -149.72, steps = 69 16:02:33 [INFO] train episode 22668: reward = -89.60, steps = 36 16:02:39 [INFO] train episode 22669: reward = -125.71, steps = 53 16:02:41 [INFO] train episode 22670: reward = -63.51, steps = 21 16:02:42 [INFO] train episode 22671: reward = -58.58, steps = 20 16:02:44 [INFO] train episode 22672: reward = -74.00, steps = 20 16:02:46 [INFO] train episode 22673: reward = -46.05, steps = 20 16:02:50 [INFO] train episode 22674: reward = -77.80, steps = 41 16:02:53 [INFO] train episode 22675: reward = -76.20, steps = 31 16:02:57 [INFO] train episode 22676: reward = -130.73, steps = 42 16:02:59 [INFO] train episode 22677: reward = -76.17, steps = 27 16:03:01 [INFO] train episode 22678: reward = -105.31, steps = 20 16:03:05 [INFO] train episode 22679: reward = -66.50, steps = 47 16:03:07 [INFO] train episode 22680: reward = -78.96, steps = 29 16:03:10 [INFO] train episode 22681: reward = -60.50, steps = 34 16:03:13 [INFO] train episode 22682: reward = -79.94, steps = 21 16:03:17 [INFO] train episode 22683: reward = -75.69, steps = 56 16:03:20 [INFO] train episode 22684: reward = -60.64, steps = 30 16:03:23 [INFO] train episode 22685: reward = -138.08, steps = 41 16:03:27 [INFO] train episode 22686: reward = -102.48, steps = 37 16:03:29 [INFO] train episode 22687: reward = -71.90, steps = 21 16:03:33 [INFO] train episode 22688: reward = -100.56, steps = 43 16:03:37 [INFO] train episode 22689: reward = -60.39, steps = 47 16:03:42 [INFO] train episode 22690: reward = -135.75, steps = 57 16:03:45 [INFO] train episode 22691: reward = -72.72, steps = 25 16:03:48 [INFO] train episode 22692: reward = -119.23, steps = 36 16:03:51 [INFO] train episode 22693: reward = -66.33, steps = 32 16:03:53 [INFO] train episode 22694: reward = -69.85, steps = 26 16:03:55 [INFO] train episode 22695: reward = -90.77, steps = 19 16:03:58 [INFO] train episode 22696: reward = -70.28, steps = 36 16:03:59 [INFO] train episode 22697: reward = -112.66, steps = 20 16:04:03 [INFO] train episode 22698: reward = -114.26, steps = 40 16:04:05 [INFO] train episode 22699: reward = -59.45, steps = 22 16:04:08 [INFO] train episode 22700: reward = -69.17, steps = 34 16:04:12 [INFO] train episode 22701: reward = -123.78, steps = 50 16:04:15 [INFO] train episode 22702: reward = -80.24, steps = 29 16:04:17 [INFO] train episode 22703: reward = -59.52, steps = 21 16:04:19 [INFO] train episode 22704: reward = -92.48, steps = 21 16:04:22 [INFO] train episode 22705: reward = -131.49, steps = 37 16:04:26 [INFO] train episode 22706: reward = -49.56, steps = 41 16:04:29 [INFO] train episode 22707: reward = -89.96, steps = 41 16:04:32 [INFO] train episode 22708: reward = -98.93, steps = 30 16:04:35 [INFO] train episode 22709: reward = -67.46, steps = 32 16:04:39 [INFO] train episode 22710: reward = -156.97, steps = 46 16:04:43 [INFO] train episode 22711: reward = -111.33, steps = 47 16:04:45 [INFO] train episode 22712: reward = -58.26, steps = 21 16:04:50 [INFO] train episode 22713: reward = -95.64, steps = 56 16:04:52 [INFO] train episode 22714: reward = -48.64, steps = 22 16:04:54 [INFO] train episode 22715: reward = -54.38, steps = 19 16:04:56 [INFO] train episode 22716: reward = -71.96, steps = 20 16:05:00 [INFO] train episode 22717: reward = -140.86, steps = 45 16:05:03 [INFO] train episode 22718: reward = -102.75, steps = 33 16:05:05 [INFO] train episode 22719: reward = -48.51, steps = 23 16:05:07 [INFO] train episode 22720: reward = -59.23, steps = 23 16:05:08 [INFO] train episode 22721: reward = -76.39, steps = 13 16:05:10 [INFO] train episode 22722: reward = -64.25, steps = 18 16:05:14 [INFO] train episode 22723: reward = -85.40, steps = 43 16:05:21 [INFO] train episode 22724: reward = -133.27, steps = 86 16:05:24 [INFO] train episode 22725: reward = -51.93, steps = 23 16:05:26 [INFO] train episode 22726: reward = -60.40, steps = 26 16:05:28 [INFO] train episode 22727: reward = -107.49, steps = 23 16:05:34 [INFO] train episode 22728: reward = -180.37, steps = 66 16:05:36 [INFO] train episode 22729: reward = -67.86, steps = 24 16:05:39 [INFO] train episode 22730: reward = -61.40, steps = 20 16:05:44 [INFO] train episode 22731: reward = -121.81, steps = 62 16:05:46 [INFO] train episode 22732: reward = -62.98, steps = 28 16:05:49 [INFO] train episode 22733: reward = -52.99, steps = 31 16:05:52 [INFO] train episode 22734: reward = -110.77, steps = 32 16:05:54 [INFO] train episode 22735: reward = -94.15, steps = 25 16:05:57 [INFO] train episode 22736: reward = -90.05, steps = 27 16:06:02 [INFO] train episode 22737: reward = -114.53, steps = 63 16:06:04 [INFO] train episode 22738: reward = -120.46, steps = 28 16:06:06 [INFO] train episode 22739: reward = -67.47, steps = 20 16:06:08 [INFO] train episode 22740: reward = -60.23, steps = 25 16:06:11 [INFO] train episode 22741: reward = -86.13, steps = 21 16:06:14 [INFO] train episode 22742: reward = -76.06, steps = 34 16:06:15 [INFO] train episode 22743: reward = -96.07, steps = 22 16:06:17 [INFO] train episode 22744: reward = -69.62, steps = 20 16:06:20 [INFO] train episode 22745: reward = -39.52, steps = 32 16:06:22 [INFO] train episode 22746: reward = -74.16, steps = 20 16:06:23 [INFO] train episode 22747: reward = -103.50, steps = 19 16:06:27 [INFO] train episode 22748: reward = -91.19, steps = 37 16:06:29 [INFO] train episode 22749: reward = -79.01, steps = 25 16:06:31 [INFO] train episode 22750: reward = -92.38, steps = 19 16:06:33 [INFO] train episode 22751: reward = -96.77, steps = 19 16:06:36 [INFO] train episode 22752: reward = -55.00, steps = 32 16:06:38 [INFO] train episode 22753: reward = -114.26, steps = 29 16:06:40 [INFO] train episode 22754: reward = -66.55, steps = 20 16:06:42 [INFO] train episode 22755: reward = -96.78, steps = 19 16:06:44 [INFO] train episode 22756: reward = -51.55, steps = 22 16:06:47 [INFO] train episode 22757: reward = -86.49, steps = 33 16:06:49 [INFO] train episode 22758: reward = -91.78, steps = 21 16:06:52 [INFO] train episode 22759: reward = -120.79, steps = 41 16:06:55 [INFO] train episode 22760: reward = -98.39, steps = 30 16:06:58 [INFO] train episode 22761: reward = -96.78, steps = 33 16:07:01 [INFO] train episode 22762: reward = -96.23, steps = 36 16:07:04 [INFO] train episode 22763: reward = -79.96, steps = 26 16:07:06 [INFO] train episode 22764: reward = -85.21, steps = 29 16:07:08 [INFO] train episode 22765: reward = -56.94, steps = 27 16:07:12 [INFO] train episode 22766: reward = -86.42, steps = 42 16:07:16 [INFO] train episode 22767: reward = -99.90, steps = 37 16:07:18 [INFO] train episode 22768: reward = -61.55, steps = 23 16:07:20 [INFO] train episode 22769: reward = -73.82, steps = 25 16:07:24 [INFO] train episode 22770: reward = -52.87, steps = 42 16:07:26 [INFO] train episode 22771: reward = -115.96, steps = 24 16:07:28 [INFO] train episode 22772: reward = -72.60, steps = 30 16:07:30 [INFO] train episode 22773: reward = -88.39, steps = 23 16:07:34 [INFO] train episode 22774: reward = -86.26, steps = 37 16:07:37 [INFO] train episode 22775: reward = -70.24, steps = 35 16:07:39 [INFO] train episode 22776: reward = -97.45, steps = 24 16:07:41 [INFO] train episode 22777: reward = -45.63, steps = 27 16:07:45 [INFO] train episode 22778: reward = -78.30, steps = 35 16:07:48 [INFO] train episode 22779: reward = -78.16, steps = 36 16:07:52 [INFO] train episode 22780: reward = -63.45, steps = 52 16:07:55 [INFO] train episode 22781: reward = -115.49, steps = 29 16:07:57 [INFO] train episode 22782: reward = -108.95, steps = 28 16:08:02 [INFO] train episode 22783: reward = -94.26, steps = 54 16:08:04 [INFO] train episode 22784: reward = -53.22, steps = 25 16:08:06 [INFO] train episode 22785: reward = -79.70, steps = 19 16:08:08 [INFO] train episode 22786: reward = -66.41, steps = 21 16:08:10 [INFO] train episode 22787: reward = -53.11, steps = 21 16:08:13 [INFO] train episode 22788: reward = -78.61, steps = 41 16:08:16 [INFO] train episode 22789: reward = -115.98, steps = 33 16:08:18 [INFO] train episode 22790: reward = -84.50, steps = 22 16:08:21 [INFO] train episode 22791: reward = -83.32, steps = 28 16:08:24 [INFO] train episode 22792: reward = -96.44, steps = 33 16:08:27 [INFO] train episode 22793: reward = -68.48, steps = 34 16:08:33 [INFO] train episode 22794: reward = -128.03, steps = 59 16:08:36 [INFO] train episode 22795: reward = -60.73, steps = 29 16:08:38 [INFO] train episode 22796: reward = -52.67, steps = 28 16:08:41 [INFO] train episode 22797: reward = -59.68, steps = 26 16:08:44 [INFO] train episode 22798: reward = -66.13, steps = 42 16:08:47 [INFO] train episode 22799: reward = -99.38, steps = 33 16:08:50 [INFO] train episode 22800: reward = -102.45, steps = 27 16:08:53 [INFO] train episode 22801: reward = -126.22, steps = 39 16:08:56 [INFO] train episode 22802: reward = -98.79, steps = 32 16:08:59 [INFO] train episode 22803: reward = -73.41, steps = 30 16:09:01 [INFO] train episode 22804: reward = -70.27, steps = 28 16:09:05 [INFO] train episode 22805: reward = -113.74, steps = 39 16:09:07 [INFO] train episode 22806: reward = -61.01, steps = 25 16:09:10 [INFO] train episode 22807: reward = -55.93, steps = 33 16:09:14 [INFO] train episode 22808: reward = -131.98, steps = 52 16:09:17 [INFO] train episode 22809: reward = -42.05, steps = 33 16:09:19 [INFO] train episode 22810: reward = -67.04, steps = 19 16:09:21 [INFO] train episode 22811: reward = -58.43, steps = 21 16:09:23 [INFO] train episode 22812: reward = -63.32, steps = 21 16:09:25 [INFO] train episode 22813: reward = -68.86, steps = 22 16:09:28 [INFO] train episode 22814: reward = -71.06, steps = 36 16:09:31 [INFO] train episode 22815: reward = -50.57, steps = 36 16:09:34 [INFO] train episode 22816: reward = -59.06, steps = 31 16:09:36 [INFO] train episode 22817: reward = -82.32, steps = 27 16:09:40 [INFO] train episode 22818: reward = -75.33, steps = 40 16:09:43 [INFO] train episode 22819: reward = -96.15, steps = 29 16:09:45 [INFO] train episode 22820: reward = -66.31, steps = 24 16:09:47 [INFO] train episode 22821: reward = -49.10, steps = 27 16:09:50 [INFO] train episode 22822: reward = -82.54, steps = 36 16:09:52 [INFO] train episode 22823: reward = -68.15, steps = 20 16:09:54 [INFO] train episode 22824: reward = -55.71, steps = 22 16:09:57 [INFO] train episode 22825: reward = -52.91, steps = 36 16:09:59 [INFO] train episode 22826: reward = -63.81, steps = 18 16:10:01 [INFO] train episode 22827: reward = -86.39, steps = 20 16:10:03 [INFO] train episode 22828: reward = -52.58, steps = 28 16:10:05 [INFO] train episode 22829: reward = -62.86, steps = 24 16:10:08 [INFO] train episode 22830: reward = -95.55, steps = 27 16:10:10 [INFO] train episode 22831: reward = -103.02, steps = 30 16:10:12 [INFO] train episode 22832: reward = -74.22, steps = 25 16:10:15 [INFO] train episode 22833: reward = -136.46, steps = 31 16:10:18 [INFO] train episode 22834: reward = -79.04, steps = 30 16:10:21 [INFO] train episode 22835: reward = -93.19, steps = 31 16:10:25 [INFO] train episode 22836: reward = -113.42, steps = 44 16:10:27 [INFO] train episode 22837: reward = -93.61, steps = 30 16:10:30 [INFO] train episode 22838: reward = -64.39, steps = 39 16:10:33 [INFO] train episode 22839: reward = -64.25, steps = 25 16:10:35 [INFO] train episode 22840: reward = -61.91, steps = 22 16:10:37 [INFO] train episode 22841: reward = -49.67, steps = 23 16:10:40 [INFO] train episode 22842: reward = -119.29, steps = 41 16:10:45 [INFO] train episode 22843: reward = -133.41, steps = 57 16:10:49 [INFO] train episode 22844: reward = -96.26, steps = 38 16:10:52 [INFO] train episode 22845: reward = -91.57, steps = 30 16:10:54 [INFO] train episode 22846: reward = -101.90, steps = 32 16:10:56 [INFO] train episode 22847: reward = -70.89, steps = 20 16:10:59 [INFO] train episode 22848: reward = -81.83, steps = 33 16:11:01 [INFO] train episode 22849: reward = -51.65, steps = 21 16:11:04 [INFO] train episode 22850: reward = -102.16, steps = 34 16:11:07 [INFO] train episode 22851: reward = -75.42, steps = 31 16:11:09 [INFO] train episode 22852: reward = -81.50, steps = 23 16:11:11 [INFO] train episode 22853: reward = -55.55, steps = 20 16:11:12 [INFO] train episode 22854: reward = -85.80, steps = 21 16:11:15 [INFO] train episode 22855: reward = -78.72, steps = 27 16:11:17 [INFO] train episode 22856: reward = -96.07, steps = 26 16:11:20 [INFO] train episode 22857: reward = -63.88, steps = 32 16:11:24 [INFO] train episode 22858: reward = -67.22, steps = 42 16:11:28 [INFO] train episode 22859: reward = -106.65, steps = 42 16:11:32 [INFO] train episode 22860: reward = -88.44, steps = 47 16:11:36 [INFO] train episode 22861: reward = -44.16, steps = 39 16:11:39 [INFO] train episode 22862: reward = -119.61, steps = 34 16:11:42 [INFO] train episode 22863: reward = -104.70, steps = 33 16:11:44 [INFO] train episode 22864: reward = -53.48, steps = 25 16:11:46 [INFO] train episode 22865: reward = -65.54, steps = 24 16:11:49 [INFO] train episode 22866: reward = -82.81, steps = 31 16:11:54 [INFO] train episode 22867: reward = -111.18, steps = 56 16:11:57 [INFO] train episode 22868: reward = -79.14, steps = 34 16:11:59 [INFO] train episode 22869: reward = -62.01, steps = 24 16:12:01 [INFO] train episode 22870: reward = -66.12, steps = 24 16:12:04 [INFO] train episode 22871: reward = -86.73, steps = 38 16:12:07 [INFO] train episode 22872: reward = -108.53, steps = 33 16:12:10 [INFO] train episode 22873: reward = -75.89, steps = 29 16:12:13 [INFO] train episode 22874: reward = -123.87, steps = 37 16:12:15 [INFO] train episode 22875: reward = -77.49, steps = 26 16:12:18 [INFO] train episode 22876: reward = -50.51, steps = 33 16:12:22 [INFO] train episode 22877: reward = -114.56, steps = 49 16:12:25 [INFO] train episode 22878: reward = -43.77, steps = 31 16:12:28 [INFO] train episode 22879: reward = -72.10, steps = 27 16:12:32 [INFO] train episode 22880: reward = -65.05, steps = 52 16:12:34 [INFO] train episode 22881: reward = -84.54, steps = 25 16:12:36 [INFO] train episode 22882: reward = -56.26, steps = 23 16:12:40 [INFO] train episode 22883: reward = -92.75, steps = 42 16:12:44 [INFO] train episode 22884: reward = -97.66, steps = 38 16:12:46 [INFO] train episode 22885: reward = -69.07, steps = 25 16:12:49 [INFO] train episode 22886: reward = -52.35, steps = 31 16:12:51 [INFO] train episode 22887: reward = -71.39, steps = 26 16:12:57 [INFO] train episode 22888: reward = -153.09, steps = 65 16:13:01 [INFO] train episode 22889: reward = -104.45, steps = 45 16:13:06 [INFO] train episode 22890: reward = -88.54, steps = 59 16:13:09 [INFO] train episode 22891: reward = -95.99, steps = 38 16:13:13 [INFO] train episode 22892: reward = -81.09, steps = 40 16:13:16 [INFO] train episode 22893: reward = -67.85, steps = 37 16:13:19 [INFO] train episode 22894: reward = -75.55, steps = 39 16:13:21 [INFO] train episode 22895: reward = -95.47, steps = 24 16:13:23 [INFO] train episode 22896: reward = -70.36, steps = 21 16:13:26 [INFO] train episode 22897: reward = -106.55, steps = 31 16:13:30 [INFO] train episode 22898: reward = -76.37, steps = 41 16:13:33 [INFO] train episode 22899: reward = -98.51, steps = 33 16:13:35 [INFO] train episode 22900: reward = -84.56, steps = 23 16:13:39 [INFO] train episode 22901: reward = -163.62, steps = 44 16:13:41 [INFO] train episode 22902: reward = -96.07, steps = 30 16:13:45 [INFO] train episode 22903: reward = -70.85, steps = 34 16:13:46 [INFO] train episode 22904: reward = -73.06, steps = 20 16:13:48 [INFO] train episode 22905: reward = -77.93, steps = 23 16:13:52 [INFO] train episode 22906: reward = -97.93, steps = 42 16:13:56 [INFO] train episode 22907: reward = -123.69, steps = 49 16:13:59 [INFO] train episode 22908: reward = -61.69, steps = 29 16:14:01 [INFO] train episode 22909: reward = -55.53, steps = 19 16:14:04 [INFO] train episode 22910: reward = -111.64, steps = 31 16:14:06 [INFO] train episode 22911: reward = -66.94, steps = 33 16:14:09 [INFO] train episode 22912: reward = -61.47, steps = 30 16:14:12 [INFO] train episode 22913: reward = -100.06, steps = 35 16:14:15 [INFO] train episode 22914: reward = -83.93, steps = 32 16:14:18 [INFO] train episode 22915: reward = -56.34, steps = 30 16:14:22 [INFO] train episode 22916: reward = -57.95, steps = 44 16:14:24 [INFO] train episode 22917: reward = -110.14, steps = 20 16:14:27 [INFO] train episode 22918: reward = -54.81, steps = 31 16:14:29 [INFO] train episode 22919: reward = -95.71, steps = 23 16:14:31 [INFO] train episode 22920: reward = -56.18, steps = 21 16:14:34 [INFO] train episode 22921: reward = -45.48, steps = 38 16:14:38 [INFO] train episode 22922: reward = -103.64, steps = 37 16:14:42 [INFO] train episode 22923: reward = -126.52, steps = 57 16:14:45 [INFO] train episode 22924: reward = -106.88, steps = 30 16:14:47 [INFO] train episode 22925: reward = -64.98, steps = 20 16:14:51 [INFO] train episode 22926: reward = -54.18, steps = 40 16:14:53 [INFO] train episode 22927: reward = -74.14, steps = 21 16:14:55 [INFO] train episode 22928: reward = -115.05, steps = 34 16:14:59 [INFO] train episode 22929: reward = -79.34, steps = 45 16:15:03 [INFO] train episode 22930: reward = -71.07, steps = 47 16:15:05 [INFO] train episode 22931: reward = -79.42, steps = 23 16:15:08 [INFO] train episode 22932: reward = -126.81, steps = 26 16:15:13 [INFO] train episode 22933: reward = -106.42, steps = 58 16:15:15 [INFO] train episode 22934: reward = -60.37, steps = 26 16:15:18 [INFO] train episode 22935: reward = -93.39, steps = 37 16:15:21 [INFO] train episode 22936: reward = -63.16, steps = 23 16:15:23 [INFO] train episode 22937: reward = -59.04, steps = 30 16:15:26 [INFO] train episode 22938: reward = -108.92, steps = 28 16:15:28 [INFO] train episode 22939: reward = -72.25, steps = 28 16:15:32 [INFO] train episode 22940: reward = -107.17, steps = 42 16:15:35 [INFO] train episode 22941: reward = -79.09, steps = 28 16:15:36 [INFO] train episode 22942: reward = -125.67, steps = 18 16:15:38 [INFO] train episode 22943: reward = -58.96, steps = 20 16:15:41 [INFO] train episode 22944: reward = -72.76, steps = 28 16:15:44 [INFO] train episode 22945: reward = -76.72, steps = 39 16:15:46 [INFO] train episode 22946: reward = -55.84, steps = 21 16:15:49 [INFO] train episode 22947: reward = -69.58, steps = 32 16:15:50 [INFO] train episode 22948: reward = -55.81, steps = 20 16:15:52 [INFO] train episode 22949: reward = -51.46, steps = 22 16:15:54 [INFO] train episode 22950: reward = -62.08, steps = 21 16:15:57 [INFO] train episode 22951: reward = -36.65, steps = 25 16:15:59 [INFO] train episode 22952: reward = -104.13, steps = 32 16:16:02 [INFO] train episode 22953: reward = -67.97, steps = 28 16:16:05 [INFO] train episode 22954: reward = -129.32, steps = 29 16:16:09 [INFO] train episode 22955: reward = -109.46, steps = 47 16:16:12 [INFO] train episode 22956: reward = -70.09, steps = 32 16:16:14 [INFO] train episode 22957: reward = -42.71, steps = 26 16:16:16 [INFO] train episode 22958: reward = -82.91, steps = 25 16:16:18 [INFO] train episode 22959: reward = -40.49, steps = 22 16:16:21 [INFO] train episode 22960: reward = -60.62, steps = 32 16:16:23 [INFO] train episode 22961: reward = -75.93, steps = 22 16:16:25 [INFO] train episode 22962: reward = -121.83, steps = 28 16:16:28 [INFO] train episode 22963: reward = -75.50, steps = 28 16:16:31 [INFO] train episode 22964: reward = -86.18, steps = 29 16:16:34 [INFO] train episode 22965: reward = -40.32, steps = 41 16:16:37 [INFO] train episode 22966: reward = -54.85, steps = 28 16:16:39 [INFO] train episode 22967: reward = -81.43, steps = 24 16:16:41 [INFO] train episode 22968: reward = -90.89, steps = 20 16:16:42 [INFO] train episode 22969: reward = -52.72, steps = 21 16:16:44 [INFO] train episode 22970: reward = -87.78, steps = 20 16:16:47 [INFO] train episode 22971: reward = -132.97, steps = 28 16:16:50 [INFO] train episode 22972: reward = -92.97, steps = 33 16:16:53 [INFO] train episode 22973: reward = -106.89, steps = 35 16:16:55 [INFO] train episode 22974: reward = -79.47, steps = 26 16:16:59 [INFO] train episode 22975: reward = -80.08, steps = 42 16:17:01 [INFO] train episode 22976: reward = -86.71, steps = 26 16:17:05 [INFO] train episode 22977: reward = -69.21, steps = 36 16:17:09 [INFO] train episode 22978: reward = -83.78, steps = 53 16:17:12 [INFO] train episode 22979: reward = -77.82, steps = 35 16:17:16 [INFO] train episode 22980: reward = -49.69, steps = 29 16:17:18 [INFO] train episode 22981: reward = -63.09, steps = 22 16:17:20 [INFO] train episode 22982: reward = -52.62, steps = 26 16:17:25 [INFO] train episode 22983: reward = -110.28, steps = 51 16:17:28 [INFO] train episode 22984: reward = -139.04, steps = 43 16:17:32 [INFO] train episode 22985: reward = -103.08, steps = 35 16:17:35 [INFO] train episode 22986: reward = -124.93, steps = 40 16:17:38 [INFO] train episode 22987: reward = -105.49, steps = 34 16:17:40 [INFO] train episode 22988: reward = -132.27, steps = 20 16:17:43 [INFO] train episode 22989: reward = -106.20, steps = 37 16:17:45 [INFO] train episode 22990: reward = -60.93, steps = 22 16:17:47 [INFO] train episode 22991: reward = -68.73, steps = 21 16:17:50 [INFO] train episode 22992: reward = -103.11, steps = 28 16:17:52 [INFO] train episode 22993: reward = -76.20, steps = 28 16:17:56 [INFO] train episode 22994: reward = -137.69, steps = 49 16:17:58 [INFO] train episode 22995: reward = -85.44, steps = 20 16:18:00 [INFO] train episode 22996: reward = -75.93, steps = 24 16:18:04 [INFO] train episode 22997: reward = -74.43, steps = 40 16:18:07 [INFO] train episode 22998: reward = -50.93, steps = 27 16:18:09 [INFO] train episode 22999: reward = -48.39, steps = 28 16:18:12 [INFO] train episode 23000: reward = -71.62, steps = 34 16:18:15 [INFO] train episode 23001: reward = -39.12, steps = 34 16:18:17 [INFO] train episode 23002: reward = -60.27, steps = 28 16:18:20 [INFO] train episode 23003: reward = -87.73, steps = 29 16:18:22 [INFO] train episode 23004: reward = -72.20, steps = 21 16:18:24 [INFO] train episode 23005: reward = -74.22, steps = 23 16:18:28 [INFO] train episode 23006: reward = -79.96, steps = 49 16:18:30 [INFO] train episode 23007: reward = -63.04, steps = 25 16:18:34 [INFO] train episode 23008: reward = -143.82, steps = 42 16:18:38 [INFO] train episode 23009: reward = -63.15, steps = 38 16:18:41 [INFO] train episode 23010: reward = -93.63, steps = 37 16:18:44 [INFO] train episode 23011: reward = -39.73, steps = 35 16:18:47 [INFO] train episode 23012: reward = -54.86, steps = 26 16:18:52 [INFO] train episode 23013: reward = -157.42, steps = 64 16:18:55 [INFO] train episode 23014: reward = -92.69, steps = 21 16:18:57 [INFO] train episode 23015: reward = -79.76, steps = 29 16:18:59 [INFO] train episode 23016: reward = -55.00, steps = 24 16:19:02 [INFO] train episode 23017: reward = -88.10, steps = 31 16:19:05 [INFO] train episode 23018: reward = -81.69, steps = 35 16:19:08 [INFO] train episode 23019: reward = -127.23, steps = 43 16:19:12 [INFO] train episode 23020: reward = -106.90, steps = 41 16:19:14 [INFO] train episode 23021: reward = -66.50, steps = 23 16:19:16 [INFO] train episode 23022: reward = -77.39, steps = 21 16:19:19 [INFO] train episode 23023: reward = -53.75, steps = 24 16:19:24 [INFO] train episode 23024: reward = -129.40, steps = 58 16:19:27 [INFO] train episode 23025: reward = -73.97, steps = 34 16:19:29 [INFO] train episode 23026: reward = -56.39, steps = 21 16:19:31 [INFO] train episode 23027: reward = -131.08, steps = 21 16:19:34 [INFO] train episode 23028: reward = -75.49, steps = 38 16:19:36 [INFO] train episode 23029: reward = -81.06, steps = 24 16:19:38 [INFO] train episode 23030: reward = -56.88, steps = 27 16:19:41 [INFO] train episode 23031: reward = -98.34, steps = 28 16:19:44 [INFO] train episode 23032: reward = -55.56, steps = 31 16:19:46 [INFO] train episode 23033: reward = -56.80, steps = 28 16:19:49 [INFO] train episode 23034: reward = -62.42, steps = 33 16:19:52 [INFO] train episode 23035: reward = -106.11, steps = 27 16:19:53 [INFO] train episode 23036: reward = -55.73, steps = 20 16:19:57 [INFO] train episode 23037: reward = -95.90, steps = 45 16:20:00 [INFO] train episode 23038: reward = -69.10, steps = 32 16:20:03 [INFO] train episode 23039: reward = -71.37, steps = 35 16:20:06 [INFO] train episode 23040: reward = -74.51, steps = 35 16:20:11 [INFO] train episode 23041: reward = -85.00, steps = 43 16:20:14 [INFO] train episode 23042: reward = -75.76, steps = 33 16:20:16 [INFO] train episode 23043: reward = -68.71, steps = 27 16:20:19 [INFO] train episode 23044: reward = -60.42, steps = 34 16:20:21 [INFO] train episode 23045: reward = -112.88, steps = 20 16:20:24 [INFO] train episode 23046: reward = -106.78, steps = 27 16:20:26 [INFO] train episode 23047: reward = -68.36, steps = 23 16:20:29 [INFO] train episode 23048: reward = -85.99, steps = 36 16:20:32 [INFO] train episode 23049: reward = -81.55, steps = 31 16:20:34 [INFO] train episode 23050: reward = -44.06, steps = 21 16:20:37 [INFO] train episode 23051: reward = -53.90, steps = 38 16:20:39 [INFO] train episode 23052: reward = -73.10, steps = 29 16:20:43 [INFO] train episode 23053: reward = -87.71, steps = 38 16:20:45 [INFO] train episode 23054: reward = -70.48, steps = 27 16:20:48 [INFO] train episode 23055: reward = -76.37, steps = 28 16:20:50 [INFO] train episode 23056: reward = -57.65, steps = 19 16:20:52 [INFO] train episode 23057: reward = -67.21, steps = 22 16:20:56 [INFO] train episode 23058: reward = -72.37, steps = 36 16:20:58 [INFO] train episode 23059: reward = -44.18, steps = 23 16:21:00 [INFO] train episode 23060: reward = -89.85, steps = 22 16:21:03 [INFO] train episode 23061: reward = -94.25, steps = 30 16:21:07 [INFO] train episode 23062: reward = -90.38, steps = 39 16:21:09 [INFO] train episode 23063: reward = -63.15, steps = 24 16:21:13 [INFO] train episode 23064: reward = -125.09, steps = 38 16:21:16 [INFO] train episode 23065: reward = -95.50, steps = 36 16:21:19 [INFO] train episode 23066: reward = -93.35, steps = 34 16:21:23 [INFO] train episode 23067: reward = -92.29, steps = 34 16:21:26 [INFO] train episode 23068: reward = -95.15, steps = 36 16:21:28 [INFO] train episode 23069: reward = -48.02, steps = 25 16:21:31 [INFO] train episode 23070: reward = -83.20, steps = 32 16:21:33 [INFO] train episode 23071: reward = -76.20, steps = 22 16:21:35 [INFO] train episode 23072: reward = -77.88, steps = 25 16:21:37 [INFO] train episode 23073: reward = -44.59, steps = 22 16:21:40 [INFO] train episode 23074: reward = -85.93, steps = 33 16:21:44 [INFO] train episode 23075: reward = -131.28, steps = 44 16:21:49 [INFO] train episode 23076: reward = -118.43, steps = 54 16:21:52 [INFO] train episode 23077: reward = -97.02, steps = 38 16:21:54 [INFO] train episode 23078: reward = -67.26, steps = 22 16:21:57 [INFO] train episode 23079: reward = -62.96, steps = 26 16:22:00 [INFO] train episode 23080: reward = -91.07, steps = 39 16:22:04 [INFO] train episode 23081: reward = -99.18, steps = 44 16:22:06 [INFO] train episode 23082: reward = -44.92, steps = 21 16:22:09 [INFO] train episode 23083: reward = -59.70, steps = 42 16:22:13 [INFO] train episode 23084: reward = -87.81, steps = 40 16:22:15 [INFO] train episode 23085: reward = -65.67, steps = 21 16:22:17 [INFO] train episode 23086: reward = -63.17, steps = 20 16:22:20 [INFO] train episode 23087: reward = -128.39, steps = 39 16:22:22 [INFO] train episode 23088: reward = -59.45, steps = 23 16:22:24 [INFO] train episode 23089: reward = -63.73, steps = 26 16:22:29 [INFO] train episode 23090: reward = -121.07, steps = 45 16:22:30 [INFO] train episode 23091: reward = -51.05, steps = 20 16:22:32 [INFO] train episode 23092: reward = -36.72, steps = 21 16:22:35 [INFO] train episode 23093: reward = -89.84, steps = 34 16:22:38 [INFO] train episode 23094: reward = -93.33, steps = 33 16:22:41 [INFO] train episode 23095: reward = -71.53, steps = 32 16:22:44 [INFO] train episode 23096: reward = -61.56, steps = 31 16:22:47 [INFO] train episode 23097: reward = -86.34, steps = 39 16:22:50 [INFO] train episode 23098: reward = -59.30, steps = 23 16:22:51 [INFO] train episode 23099: reward = -71.18, steps = 22 16:22:54 [INFO] train episode 23100: reward = -67.45, steps = 31 16:22:58 [INFO] train episode 23101: reward = -109.82, steps = 42 16:23:02 [INFO] train episode 23102: reward = -120.33, steps = 40 16:23:04 [INFO] train episode 23103: reward = -59.45, steps = 26 16:23:06 [INFO] train episode 23104: reward = -69.49, steps = 26 16:23:10 [INFO] train episode 23105: reward = -87.82, steps = 34 16:23:14 [INFO] train episode 23106: reward = -122.49, steps = 52 16:23:17 [INFO] train episode 23107: reward = -60.54, steps = 23 16:23:19 [INFO] train episode 23108: reward = -79.45, steps = 25 16:23:22 [INFO] train episode 23109: reward = -86.37, steps = 38 16:23:24 [INFO] train episode 23110: reward = -80.18, steps = 20 16:23:27 [INFO] train episode 23111: reward = -106.15, steps = 35 16:23:30 [INFO] train episode 23112: reward = -72.72, steps = 29 16:23:31 [INFO] train episode 23113: reward = -53.46, steps = 21 16:23:37 [INFO] train episode 23114: reward = -80.93, steps = 56 16:23:39 [INFO] train episode 23115: reward = -54.78, steps = 27 16:23:41 [INFO] train episode 23116: reward = -45.80, steps = 23 16:23:43 [INFO] train episode 23117: reward = -51.27, steps = 26 16:23:46 [INFO] train episode 23118: reward = -94.04, steps = 34 16:23:50 [INFO] train episode 23119: reward = -95.07, steps = 37 16:23:55 [INFO] train episode 23120: reward = -140.33, steps = 58 16:23:58 [INFO] train episode 23121: reward = -84.41, steps = 33 16:24:00 [INFO] train episode 23122: reward = -84.30, steps = 25 16:24:04 [INFO] train episode 23123: reward = -71.21, steps = 45 16:24:06 [INFO] train episode 23124: reward = -75.73, steps = 20 16:24:08 [INFO] train episode 23125: reward = -80.79, steps = 23 16:24:10 [INFO] train episode 23126: reward = -97.37, steps = 23 16:24:12 [INFO] train episode 23127: reward = -146.00, steps = 27 16:24:18 [INFO] train episode 23128: reward = -149.10, steps = 66 16:24:25 [INFO] train episode 23129: reward = -163.35, steps = 77 16:24:28 [INFO] train episode 23130: reward = -82.08, steps = 34 16:24:30 [INFO] train episode 23131: reward = -79.30, steps = 20 16:24:31 [INFO] train episode 23132: reward = -125.55, steps = 19 16:24:34 [INFO] train episode 23133: reward = -56.41, steps = 32 16:24:36 [INFO] train episode 23134: reward = -97.33, steps = 18 16:24:39 [INFO] train episode 23135: reward = -96.03, steps = 35 16:24:43 [INFO] train episode 23136: reward = -84.40, steps = 42 16:24:47 [INFO] train episode 23137: reward = -103.22, steps = 48 16:24:50 [INFO] train episode 23138: reward = -110.43, steps = 37 16:24:53 [INFO] train episode 23139: reward = -93.29, steps = 39 16:24:56 [INFO] train episode 23140: reward = -49.40, steps = 30 16:25:00 [INFO] train episode 23141: reward = -81.06, steps = 40 16:25:03 [INFO] train episode 23142: reward = -122.93, steps = 31 16:25:05 [INFO] train episode 23143: reward = -81.85, steps = 25 16:25:09 [INFO] train episode 23144: reward = -84.60, steps = 39 16:25:11 [INFO] train episode 23145: reward = -61.64, steps = 26 16:25:13 [INFO] train episode 23146: reward = -41.91, steps = 19 16:25:15 [INFO] train episode 23147: reward = -54.09, steps = 21 16:25:21 [INFO] train episode 23148: reward = -135.39, steps = 65 16:25:24 [INFO] train episode 23149: reward = -57.94, steps = 40 16:25:26 [INFO] train episode 23150: reward = -85.12, steps = 23 16:25:28 [INFO] train episode 23151: reward = -53.44, steps = 19 16:25:31 [INFO] train episode 23152: reward = -61.77, steps = 35 16:25:33 [INFO] train episode 23153: reward = -71.88, steps = 23 16:25:35 [INFO] train episode 23154: reward = -68.41, steps = 22 16:25:37 [INFO] train episode 23155: reward = -68.09, steps = 23 16:25:39 [INFO] train episode 23156: reward = -53.64, steps = 25 16:25:42 [INFO] train episode 23157: reward = -68.67, steps = 31 16:25:44 [INFO] train episode 23158: reward = -51.79, steps = 24 16:25:47 [INFO] train episode 23159: reward = -86.58, steps = 30 16:25:49 [INFO] train episode 23160: reward = -70.51, steps = 23 16:25:51 [INFO] train episode 23161: reward = -68.77, steps = 28 16:25:55 [INFO] train episode 23162: reward = -88.82, steps = 44 16:25:57 [INFO] train episode 23163: reward = -86.22, steps = 25 16:25:59 [INFO] train episode 23164: reward = -75.19, steps = 18 16:26:04 [INFO] train episode 23165: reward = -106.38, steps = 52 16:26:06 [INFO] train episode 23166: reward = -54.56, steps = 22 16:26:11 [INFO] train episode 23167: reward = -163.48, steps = 58 16:26:14 [INFO] train episode 23168: reward = -101.00, steps = 34 16:26:17 [INFO] train episode 23169: reward = -89.85, steps = 25 16:26:19 [INFO] train episode 23170: reward = -62.27, steps = 25 16:26:22 [INFO] train episode 23171: reward = -92.29, steps = 41 16:26:25 [INFO] train episode 23172: reward = -60.86, steps = 30 16:26:28 [INFO] train episode 23173: reward = -84.27, steps = 32 16:26:31 [INFO] train episode 23174: reward = -61.13, steps = 40 16:26:33 [INFO] train episode 23175: reward = -70.45, steps = 20 16:26:35 [INFO] train episode 23176: reward = -46.04, steps = 21 16:26:38 [INFO] train episode 23177: reward = -76.02, steps = 25 16:26:41 [INFO] train episode 23178: reward = -114.85, steps = 38 16:26:44 [INFO] train episode 23179: reward = -94.45, steps = 32 16:26:47 [INFO] train episode 23180: reward = -72.68, steps = 36 16:26:51 [INFO] train episode 23181: reward = -36.63, steps = 41 16:26:53 [INFO] train episode 23182: reward = -101.68, steps = 28 16:26:57 [INFO] train episode 23183: reward = -73.84, steps = 51 16:26:59 [INFO] train episode 23184: reward = -67.26, steps = 24 16:27:04 [INFO] train episode 23185: reward = -106.94, steps = 51 16:27:07 [INFO] train episode 23186: reward = -76.26, steps = 32 16:27:10 [INFO] train episode 23187: reward = -106.93, steps = 41 16:27:13 [INFO] train episode 23188: reward = -78.29, steps = 30 16:27:18 [INFO] train episode 23189: reward = -121.73, steps = 56 16:27:25 [INFO] train episode 23190: reward = -136.32, steps = 82 16:27:29 [INFO] train episode 23191: reward = -94.50, steps = 40 16:27:31 [INFO] train episode 23192: reward = -65.04, steps = 30 16:27:34 [INFO] train episode 23193: reward = -72.04, steps = 26 16:27:36 [INFO] train episode 23194: reward = -58.61, steps = 31 16:27:40 [INFO] train episode 23195: reward = -75.86, steps = 37 16:27:42 [INFO] train episode 23196: reward = -59.96, steps = 27 16:27:45 [INFO] train episode 23197: reward = -66.73, steps = 28 16:27:47 [INFO] train episode 23198: reward = -110.79, steps = 27 16:27:50 [INFO] train episode 23199: reward = -162.52, steps = 31 16:27:52 [INFO] train episode 23200: reward = -71.12, steps = 29 16:27:55 [INFO] train episode 23201: reward = -69.53, steps = 29 16:27:57 [INFO] train episode 23202: reward = -68.21, steps = 22 16:28:00 [INFO] train episode 23203: reward = -67.93, steps = 29 16:28:03 [INFO] train episode 23204: reward = -69.79, steps = 37 16:28:07 [INFO] train episode 23205: reward = -98.66, steps = 53 16:28:10 [INFO] train episode 23206: reward = -77.46, steps = 29 16:28:13 [INFO] train episode 23207: reward = -68.84, steps = 38 16:28:16 [INFO] train episode 23208: reward = -77.87, steps = 31 16:28:18 [INFO] train episode 23209: reward = -79.23, steps = 20 16:28:22 [INFO] train episode 23210: reward = -99.24, steps = 45 16:28:24 [INFO] train episode 23211: reward = -102.73, steps = 21 16:28:26 [INFO] train episode 23212: reward = -98.08, steps = 23 16:28:29 [INFO] train episode 23213: reward = -60.39, steps = 28 16:28:32 [INFO] train episode 23214: reward = -102.06, steps = 36 16:28:34 [INFO] train episode 23215: reward = -46.63, steps = 25 16:28:38 [INFO] train episode 23216: reward = -89.55, steps = 41 16:28:40 [INFO] train episode 23217: reward = -77.25, steps = 31 16:28:44 [INFO] train episode 23218: reward = -65.36, steps = 40 16:28:47 [INFO] train episode 23219: reward = -95.69, steps = 28 16:28:50 [INFO] train episode 23220: reward = -81.64, steps = 38 16:28:53 [INFO] train episode 23221: reward = -96.46, steps = 35 16:28:57 [INFO] train episode 23222: reward = -72.06, steps = 42 16:29:04 [INFO] train episode 23223: reward = -89.03, steps = 64 16:29:06 [INFO] train episode 23224: reward = -72.27, steps = 23 16:29:08 [INFO] train episode 23225: reward = -53.66, steps = 24 16:29:11 [INFO] train episode 23226: reward = -69.68, steps = 35 16:29:14 [INFO] train episode 23227: reward = -67.17, steps = 33 16:29:17 [INFO] train episode 23228: reward = -34.04, steps = 29 16:29:21 [INFO] train episode 23229: reward = -73.84, steps = 47 16:29:25 [INFO] train episode 23230: reward = -106.62, steps = 51 16:29:28 [INFO] train episode 23231: reward = -59.03, steps = 30 16:29:29 [INFO] train episode 23232: reward = -80.71, steps = 19 16:29:32 [INFO] train episode 23233: reward = -80.35, steps = 27 16:29:37 [INFO] train episode 23234: reward = -110.71, steps = 57 16:29:40 [INFO] train episode 23235: reward = -88.25, steps = 38 16:29:43 [INFO] train episode 23236: reward = -67.55, steps = 25 16:29:45 [INFO] train episode 23237: reward = -43.55, steps = 22 16:29:48 [INFO] train episode 23238: reward = -88.85, steps = 36 16:29:50 [INFO] train episode 23239: reward = -43.73, steps = 22 16:29:53 [INFO] train episode 23240: reward = -64.51, steps = 30 16:29:54 [INFO] train episode 23241: reward = -79.37, steps = 20 16:29:56 [INFO] train episode 23242: reward = -53.30, steps = 22 16:29:59 [INFO] train episode 23243: reward = -81.20, steps = 25 16:30:00 [INFO] train episode 23244: reward = -74.51, steps = 20 16:30:05 [INFO] train episode 23245: reward = -114.68, steps = 45 16:30:08 [INFO] train episode 23246: reward = -67.93, steps = 42 16:30:12 [INFO] train episode 23247: reward = -105.78, steps = 49 16:30:15 [INFO] train episode 23248: reward = -91.73, steps = 34 16:30:17 [INFO] train episode 23249: reward = -118.16, steps = 17 16:30:19 [INFO] train episode 23250: reward = -68.42, steps = 25 16:30:23 [INFO] train episode 23251: reward = -51.09, steps = 37 16:30:25 [INFO] train episode 23252: reward = -56.52, steps = 31 16:30:28 [INFO] train episode 23253: reward = -71.97, steps = 38 16:30:30 [INFO] train episode 23254: reward = -102.85, steps = 22 16:30:32 [INFO] train episode 23255: reward = -60.48, steps = 16 16:30:34 [INFO] train episode 23256: reward = -69.20, steps = 24 16:30:36 [INFO] train episode 23257: reward = -91.92, steps = 18 16:30:39 [INFO] train episode 23258: reward = -90.27, steps = 28 16:30:41 [INFO] train episode 23259: reward = -65.44, steps = 24 16:30:45 [INFO] train episode 23260: reward = -45.71, steps = 41 16:30:47 [INFO] train episode 23261: reward = -79.43, steps = 33 16:30:49 [INFO] train episode 23262: reward = -61.31, steps = 21 16:30:53 [INFO] train episode 23263: reward = -167.31, steps = 38 16:30:56 [INFO] train episode 23264: reward = -108.19, steps = 32 16:30:57 [INFO] train episode 23265: reward = -64.75, steps = 21 16:30:59 [INFO] train episode 23266: reward = -87.10, steps = 22 16:31:02 [INFO] train episode 23267: reward = -81.21, steps = 28 16:31:05 [INFO] train episode 23268: reward = -57.33, steps = 31 16:31:06 [INFO] train episode 23269: reward = -47.54, steps = 21 16:31:08 [INFO] train episode 23270: reward = -50.28, steps = 20 16:31:11 [INFO] train episode 23271: reward = -54.63, steps = 23 16:31:14 [INFO] train episode 23272: reward = -21.52, steps = 39 16:31:17 [INFO] train episode 23273: reward = -92.47, steps = 39 16:31:20 [INFO] train episode 23274: reward = -58.70, steps = 26 16:31:23 [INFO] train episode 23275: reward = -162.08, steps = 45 16:31:26 [INFO] train episode 23276: reward = -100.77, steps = 24 16:31:28 [INFO] train episode 23277: reward = -66.78, steps = 28 16:31:31 [INFO] train episode 23278: reward = -68.50, steps = 27 16:31:33 [INFO] train episode 23279: reward = -61.86, steps = 31 16:31:36 [INFO] train episode 23280: reward = -66.57, steps = 26 16:31:37 [INFO] train episode 23281: reward = -73.36, steps = 20 16:31:40 [INFO] train episode 23282: reward = -85.69, steps = 33 16:31:43 [INFO] train episode 23283: reward = -63.00, steps = 30 16:31:46 [INFO] train episode 23284: reward = -57.98, steps = 26 16:31:48 [INFO] train episode 23285: reward = -66.30, steps = 23 16:31:51 [INFO] train episode 23286: reward = -87.27, steps = 39 16:31:54 [INFO] train episode 23287: reward = -75.27, steps = 31 16:31:58 [INFO] train episode 23288: reward = -90.53, steps = 42 16:32:03 [INFO] train episode 23289: reward = -95.07, steps = 50 16:32:05 [INFO] train episode 23290: reward = -67.33, steps = 24 16:32:07 [INFO] train episode 23291: reward = -70.22, steps = 20 16:32:10 [INFO] train episode 23292: reward = -81.67, steps = 44 16:32:13 [INFO] train episode 23293: reward = -71.11, steps = 29 16:32:16 [INFO] train episode 23294: reward = -72.17, steps = 30 16:32:18 [INFO] train episode 23295: reward = -49.14, steps = 25 16:32:20 [INFO] train episode 23296: reward = -63.01, steps = 21 16:32:22 [INFO] train episode 23297: reward = -49.64, steps = 25 16:32:24 [INFO] train episode 23298: reward = -58.83, steps = 20 16:32:26 [INFO] train episode 23299: reward = -69.94, steps = 27 16:32:28 [INFO] train episode 23300: reward = -68.08, steps = 20 16:32:31 [INFO] train episode 23301: reward = -50.14, steps = 29 16:32:34 [INFO] train episode 23302: reward = -82.70, steps = 30 16:32:38 [INFO] train episode 23303: reward = -81.72, steps = 45 16:32:40 [INFO] train episode 23304: reward = -77.97, steps = 25 16:32:43 [INFO] train episode 23305: reward = -45.24, steps = 36 16:32:45 [INFO] train episode 23306: reward = -57.15, steps = 31 16:32:49 [INFO] train episode 23307: reward = -59.07, steps = 35 16:32:52 [INFO] train episode 23308: reward = -46.94, steps = 29 16:32:54 [INFO] train episode 23309: reward = -105.10, steps = 28 16:32:57 [INFO] train episode 23310: reward = -64.72, steps = 37 16:33:03 [INFO] train episode 23311: reward = -82.91, steps = 57 16:33:06 [INFO] train episode 23312: reward = -75.78, steps = 42 16:33:09 [INFO] train episode 23313: reward = -87.00, steps = 32 16:33:13 [INFO] train episode 23314: reward = -81.10, steps = 45 16:33:15 [INFO] train episode 23315: reward = -100.66, steps = 23 16:33:19 [INFO] train episode 23316: reward = -74.32, steps = 44 16:33:23 [INFO] train episode 23317: reward = -114.22, steps = 46 16:33:25 [INFO] train episode 23318: reward = -59.31, steps = 25 16:33:27 [INFO] train episode 23319: reward = -82.25, steps = 20 16:33:30 [INFO] train episode 23320: reward = -47.84, steps = 31 16:33:34 [INFO] train episode 23321: reward = -51.73, steps = 47 16:33:37 [INFO] train episode 23322: reward = -96.53, steps = 34 16:33:42 [INFO] train episode 23323: reward = -122.34, steps = 51 16:33:44 [INFO] train episode 23324: reward = -84.54, steps = 31 16:33:47 [INFO] train episode 23325: reward = -52.12, steps = 26 16:33:49 [INFO] train episode 23326: reward = -50.69, steps = 20 16:33:51 [INFO] train episode 23327: reward = -62.45, steps = 23 16:33:53 [INFO] train episode 23328: reward = -59.21, steps = 23 16:33:57 [INFO] train episode 23329: reward = -59.21, steps = 37 16:34:00 [INFO] train episode 23330: reward = -101.02, steps = 41 16:34:02 [INFO] train episode 23331: reward = -54.78, steps = 24 16:34:06 [INFO] train episode 23332: reward = -53.92, steps = 39 16:34:08 [INFO] train episode 23333: reward = -118.93, steps = 27 16:34:10 [INFO] train episode 23334: reward = -69.86, steps = 22 16:34:12 [INFO] train episode 23335: reward = -51.48, steps = 22 16:34:15 [INFO] train episode 23336: reward = -77.26, steps = 25 16:34:17 [INFO] train episode 23337: reward = -60.86, steps = 27 16:34:21 [INFO] train episode 23338: reward = -110.06, steps = 50 16:34:25 [INFO] train episode 23339: reward = -67.45, steps = 36 16:34:27 [INFO] train episode 23340: reward = -74.02, steps = 31 16:34:30 [INFO] train episode 23341: reward = -142.97, steps = 26 16:34:35 [INFO] train episode 23342: reward = -106.42, steps = 64 16:34:38 [INFO] train episode 23343: reward = -68.81, steps = 32 16:34:42 [INFO] train episode 23344: reward = -103.97, steps = 43 16:34:45 [INFO] train episode 23345: reward = -89.66, steps = 31 16:34:47 [INFO] train episode 23346: reward = -75.90, steps = 21 16:34:49 [INFO] train episode 23347: reward = -91.72, steps = 20 16:34:52 [INFO] train episode 23348: reward = -51.43, steps = 41 16:34:55 [INFO] train episode 23349: reward = -76.50, steps = 22 16:34:59 [INFO] train episode 23350: reward = -76.21, steps = 45 16:35:03 [INFO] train episode 23351: reward = -89.64, steps = 40 16:35:06 [INFO] train episode 23352: reward = -73.49, steps = 29 16:35:07 [INFO] train episode 23353: reward = -78.20, steps = 21 16:35:11 [INFO] train episode 23354: reward = -80.11, steps = 37 16:35:14 [INFO] train episode 23355: reward = -62.30, steps = 38 16:35:17 [INFO] train episode 23356: reward = -54.30, steps = 30 16:35:20 [INFO] train episode 23357: reward = -105.73, steps = 37 16:35:23 [INFO] train episode 23358: reward = -48.54, steps = 29 16:35:26 [INFO] train episode 23359: reward = -96.78, steps = 37 16:35:29 [INFO] train episode 23360: reward = -113.97, steps = 31 16:35:31 [INFO] train episode 23361: reward = -89.32, steps = 24 16:35:33 [INFO] train episode 23362: reward = -55.30, steps = 18 16:35:35 [INFO] train episode 23363: reward = -64.87, steps = 22 16:35:37 [INFO] train episode 23364: reward = -43.42, steps = 26 16:35:39 [INFO] train episode 23365: reward = -46.99, steps = 26 16:35:42 [INFO] train episode 23366: reward = -65.09, steps = 32 16:35:48 [INFO] train episode 23367: reward = -95.28, steps = 65 16:35:51 [INFO] train episode 23368: reward = -57.87, steps = 36 16:35:54 [INFO] train episode 23369: reward = -78.78, steps = 31 16:35:56 [INFO] train episode 23370: reward = -71.04, steps = 25 16:35:58 [INFO] train episode 23371: reward = -49.47, steps = 30 16:36:01 [INFO] train episode 23372: reward = -87.00, steps = 27 16:36:04 [INFO] train episode 23373: reward = -84.93, steps = 27 16:36:06 [INFO] train episode 23374: reward = -60.96, steps = 33 16:36:11 [INFO] train episode 23375: reward = -64.60, steps = 51 16:36:13 [INFO] train episode 23376: reward = -67.87, steps = 25 16:36:16 [INFO] train episode 23377: reward = -86.37, steps = 29 16:36:18 [INFO] train episode 23378: reward = -128.51, steps = 24 16:36:25 [INFO] train episode 23379: reward = -146.65, steps = 77 16:36:27 [INFO] train episode 23380: reward = -61.25, steps = 27 16:36:32 [INFO] train episode 23381: reward = -91.11, steps = 61 16:36:35 [INFO] train episode 23382: reward = -88.77, steps = 26 16:36:37 [INFO] train episode 23383: reward = -56.88, steps = 26 16:36:41 [INFO] train episode 23384: reward = -64.09, steps = 41 16:36:43 [INFO] train episode 23385: reward = -79.70, steps = 30 16:36:47 [INFO] train episode 23386: reward = -49.99, steps = 35 16:36:49 [INFO] train episode 23387: reward = -166.09, steps = 32 16:36:55 [INFO] train episode 23388: reward = -120.06, steps = 58 16:36:58 [INFO] train episode 23389: reward = -64.47, steps = 41 16:37:01 [INFO] train episode 23390: reward = -107.52, steps = 34 16:37:04 [INFO] train episode 23391: reward = -88.37, steps = 38 16:37:07 [INFO] train episode 23392: reward = -57.17, steps = 29 16:37:09 [INFO] train episode 23393: reward = -46.83, steps = 22 16:37:12 [INFO] train episode 23394: reward = -84.41, steps = 29 16:37:13 [INFO] train episode 23395: reward = -56.51, steps = 19 16:37:16 [INFO] train episode 23396: reward = -68.22, steps = 35 16:37:18 [INFO] train episode 23397: reward = -64.22, steps = 20 16:37:23 [INFO] train episode 23398: reward = -60.64, steps = 50 16:37:27 [INFO] train episode 23399: reward = -68.93, steps = 47 16:37:29 [INFO] train episode 23400: reward = -101.80, steps = 20 16:37:32 [INFO] train episode 23401: reward = -107.54, steps = 35 16:37:34 [INFO] train episode 23402: reward = -53.71, steps = 27 16:37:38 [INFO] train episode 23403: reward = -72.48, steps = 39 16:37:40 [INFO] train episode 23404: reward = -59.49, steps = 23 16:37:45 [INFO] train episode 23405: reward = -127.11, steps = 59 16:37:48 [INFO] train episode 23406: reward = -70.23, steps = 33 16:37:53 [INFO] train episode 23407: reward = -83.81, steps = 52 16:37:55 [INFO] train episode 23408: reward = -47.13, steps = 20 16:37:58 [INFO] train episode 23409: reward = -68.76, steps = 27 16:38:00 [INFO] train episode 23410: reward = -57.37, steps = 25 16:38:04 [INFO] train episode 23411: reward = -104.11, steps = 41 16:38:07 [INFO] train episode 23412: reward = -101.86, steps = 41 16:38:10 [INFO] train episode 23413: reward = -110.03, steps = 31 16:38:14 [INFO] train episode 23414: reward = -84.22, steps = 48 16:38:17 [INFO] train episode 23415: reward = -39.84, steps = 30 16:38:20 [INFO] train episode 23416: reward = -62.42, steps = 32 16:38:28 [INFO] train episode 23417: reward = -127.21, steps = 92 16:38:32 [INFO] train episode 23418: reward = -58.82, steps = 41 16:38:34 [INFO] train episode 23419: reward = -65.03, steps = 30 16:38:39 [INFO] train episode 23420: reward = -118.07, steps = 48 16:38:42 [INFO] train episode 23421: reward = -59.66, steps = 43 16:38:45 [INFO] train episode 23422: reward = -71.01, steps = 29 16:38:49 [INFO] train episode 23423: reward = -90.53, steps = 41 16:38:52 [INFO] train episode 23424: reward = -79.51, steps = 33 16:38:55 [INFO] train episode 23425: reward = -99.79, steps = 36 16:38:59 [INFO] train episode 23426: reward = -52.25, steps = 47 16:39:03 [INFO] train episode 23427: reward = -109.48, steps = 47 16:39:07 [INFO] train episode 23428: reward = -58.80, steps = 44 16:39:09 [INFO] train episode 23429: reward = -65.12, steps = 22 16:39:13 [INFO] train episode 23430: reward = -111.43, steps = 47 16:39:15 [INFO] train episode 23431: reward = -56.46, steps = 24 16:39:20 [INFO] train episode 23432: reward = -74.58, steps = 48 16:39:25 [INFO] train episode 23433: reward = -122.46, steps = 58 16:39:28 [INFO] train episode 23434: reward = -110.05, steps = 32 16:39:30 [INFO] train episode 23435: reward = -116.69, steps = 33 16:39:33 [INFO] train episode 23436: reward = -79.65, steps = 24 16:39:35 [INFO] train episode 23437: reward = -109.77, steps = 19 16:39:39 [INFO] train episode 23438: reward = -90.53, steps = 48 16:39:41 [INFO] train episode 23439: reward = -54.43, steps = 22 16:39:44 [INFO] train episode 23440: reward = -132.47, steps = 30 16:39:47 [INFO] train episode 23441: reward = -78.38, steps = 41 16:39:50 [INFO] train episode 23442: reward = -63.69, steps = 36 16:39:52 [INFO] train episode 23443: reward = -99.84, steps = 19 16:39:56 [INFO] train episode 23444: reward = -73.64, steps = 40 16:39:58 [INFO] train episode 23445: reward = -65.39, steps = 21 16:40:00 [INFO] train episode 23446: reward = -101.20, steps = 30 16:40:05 [INFO] train episode 23447: reward = -81.06, steps = 49 16:40:08 [INFO] train episode 23448: reward = -110.71, steps = 34 16:40:12 [INFO] train episode 23449: reward = -113.21, steps = 53 16:40:16 [INFO] train episode 23450: reward = -99.30, steps = 42 16:40:19 [INFO] train episode 23451: reward = -66.47, steps = 34 16:40:21 [INFO] train episode 23452: reward = -73.49, steps = 24 16:40:25 [INFO] train episode 23453: reward = -72.86, steps = 41 16:40:27 [INFO] train episode 23454: reward = -65.64, steps = 25 16:40:29 [INFO] train episode 23455: reward = -77.27, steps = 24 16:40:33 [INFO] train episode 23456: reward = -64.43, steps = 35 16:40:36 [INFO] train episode 23457: reward = -88.90, steps = 35 16:40:39 [INFO] train episode 23458: reward = -63.01, steps = 42 16:40:43 [INFO] train episode 23459: reward = -57.15, steps = 39 16:40:45 [INFO] train episode 23460: reward = -47.47, steps = 23 16:40:48 [INFO] train episode 23461: reward = -145.94, steps = 27 16:40:51 [INFO] train episode 23462: reward = -68.41, steps = 35 16:40:58 [INFO] train episode 23463: reward = -65.92, steps = 70 16:41:01 [INFO] train episode 23464: reward = -51.50, steps = 35 16:41:04 [INFO] train episode 23465: reward = -78.30, steps = 36 16:41:07 [INFO] train episode 23466: reward = -61.50, steps = 36 16:41:09 [INFO] train episode 23467: reward = -48.54, steps = 21 16:41:12 [INFO] train episode 23468: reward = -59.08, steps = 33 16:41:16 [INFO] train episode 23469: reward = -76.45, steps = 41 16:41:20 [INFO] train episode 23470: reward = -65.92, steps = 48 16:41:22 [INFO] train episode 23471: reward = -67.71, steps = 20 16:41:25 [INFO] train episode 23472: reward = -84.43, steps = 43 16:41:28 [INFO] train episode 23473: reward = -87.16, steps = 35 16:41:33 [INFO] train episode 23474: reward = -164.70, steps = 48 16:41:36 [INFO] train episode 23475: reward = -107.26, steps = 35 16:41:40 [INFO] train episode 23476: reward = -87.07, steps = 50 16:41:43 [INFO] train episode 23477: reward = -43.00, steps = 29 16:41:48 [INFO] train episode 23478: reward = -85.96, steps = 54 16:41:52 [INFO] train episode 23479: reward = -170.72, steps = 45 16:41:56 [INFO] train episode 23480: reward = -63.65, steps = 42 16:41:59 [INFO] train episode 23481: reward = -86.31, steps = 40 16:42:01 [INFO] train episode 23482: reward = -31.18, steps = 27 16:42:06 [INFO] train episode 23483: reward = -69.10, steps = 50 16:42:10 [INFO] train episode 23484: reward = -92.26, steps = 41 16:42:12 [INFO] train episode 23485: reward = -81.19, steps = 30 16:42:15 [INFO] train episode 23486: reward = -39.40, steps = 34 16:42:18 [INFO] train episode 23487: reward = -78.94, steps = 35 16:42:22 [INFO] train episode 23488: reward = -87.55, steps = 40 16:42:24 [INFO] train episode 23489: reward = -66.49, steps = 22 16:42:28 [INFO] train episode 23490: reward = -78.37, steps = 42 16:42:31 [INFO] train episode 23491: reward = -86.75, steps = 35 16:42:33 [INFO] train episode 23492: reward = -63.65, steps = 27 16:42:36 [INFO] train episode 23493: reward = -80.34, steps = 31 16:42:40 [INFO] train episode 23494: reward = -60.10, steps = 38 16:42:41 [INFO] train episode 23495: reward = -76.63, steps = 19 16:42:44 [INFO] train episode 23496: reward = -58.36, steps = 26 16:42:47 [INFO] train episode 23497: reward = -78.70, steps = 38 16:42:49 [INFO] train episode 23498: reward = -61.26, steps = 26 16:42:55 [INFO] train episode 23499: reward = -100.84, steps = 60 16:42:58 [INFO] train episode 23500: reward = -89.51, steps = 29 16:43:00 [INFO] train episode 23501: reward = -59.81, steps = 24 16:43:04 [INFO] train episode 23502: reward = -90.55, steps = 50 16:43:08 [INFO] train episode 23503: reward = -159.82, steps = 48 16:43:11 [INFO] train episode 23504: reward = -50.27, steps = 31 16:43:15 [INFO] train episode 23505: reward = -67.73, steps = 35 16:43:19 [INFO] train episode 23506: reward = -108.94, steps = 49 16:43:23 [INFO] train episode 23507: reward = -150.86, steps = 48 16:43:26 [INFO] train episode 23508: reward = -40.49, steps = 24 16:43:31 [INFO] train episode 23509: reward = -116.16, steps = 56 16:43:33 [INFO] train episode 23510: reward = -40.65, steps = 30 16:43:36 [INFO] train episode 23511: reward = -63.62, steps = 28 16:43:38 [INFO] train episode 23512: reward = -71.95, steps = 30 16:43:45 [INFO] train episode 23513: reward = -103.30, steps = 62 16:43:48 [INFO] train episode 23514: reward = -44.75, steps = 37 16:43:51 [INFO] train episode 23515: reward = -51.76, steps = 36 16:43:57 [INFO] train episode 23516: reward = -68.93, steps = 64 16:44:01 [INFO] train episode 23517: reward = -46.38, steps = 40 16:44:04 [INFO] train episode 23518: reward = -89.18, steps = 35 16:44:06 [INFO] train episode 23519: reward = -72.91, steps = 29 16:44:09 [INFO] train episode 23520: reward = -93.29, steps = 39 16:44:11 [INFO] train episode 23521: reward = -71.47, steps = 21 16:44:15 [INFO] train episode 23522: reward = -65.46, steps = 41 16:44:17 [INFO] train episode 23523: reward = -89.67, steps = 23 16:44:20 [INFO] train episode 23524: reward = -114.88, steps = 35 16:44:23 [INFO] train episode 23525: reward = -63.93, steps = 27 16:44:27 [INFO] train episode 23526: reward = -130.67, steps = 47 16:44:35 [INFO] train episode 23527: reward = -204.16, steps = 96 16:44:38 [INFO] train episode 23528: reward = -85.72, steps = 32 16:44:42 [INFO] train episode 23529: reward = -59.04, steps = 47 16:44:44 [INFO] train episode 23530: reward = -61.43, steps = 25 16:44:47 [INFO] train episode 23531: reward = -56.19, steps = 27 16:44:51 [INFO] train episode 23532: reward = -126.13, steps = 43 16:44:53 [INFO] train episode 23533: reward = -46.64, steps = 22 16:44:56 [INFO] train episode 23534: reward = -78.60, steps = 35 16:45:00 [INFO] train episode 23535: reward = -96.49, steps = 43 16:45:01 [INFO] train episode 23536: reward = -63.28, steps = 20 16:45:04 [INFO] train episode 23537: reward = -66.17, steps = 29 16:45:07 [INFO] train episode 23538: reward = -84.84, steps = 24 16:45:10 [INFO] train episode 23539: reward = -88.68, steps = 37 16:45:15 [INFO] train episode 23540: reward = -72.02, steps = 60 16:45:18 [INFO] train episode 23541: reward = -78.89, steps = 33 16:45:20 [INFO] train episode 23542: reward = -85.95, steps = 25 16:45:23 [INFO] train episode 23543: reward = -75.42, steps = 33 16:45:26 [INFO] train episode 23544: reward = -63.15, steps = 30 16:45:29 [INFO] train episode 23545: reward = -106.60, steps = 40 16:45:34 [INFO] train episode 23546: reward = -128.18, steps = 55 16:45:39 [INFO] train episode 23547: reward = -77.72, steps = 50 16:45:42 [INFO] train episode 23548: reward = -62.17, steps = 42 16:45:45 [INFO] train episode 23549: reward = -81.34, steps = 27 16:45:48 [INFO] train episode 23550: reward = -75.01, steps = 38 16:45:50 [INFO] train episode 23551: reward = -110.06, steps = 23 16:45:52 [INFO] train episode 23552: reward = -51.73, steps = 28 16:45:58 [INFO] train episode 23553: reward = -99.26, steps = 62 16:46:00 [INFO] train episode 23554: reward = -60.15, steps = 25 16:46:03 [INFO] train episode 23555: reward = -89.79, steps = 39 16:46:05 [INFO] train episode 23556: reward = -66.08, steps = 23 16:46:08 [INFO] train episode 23557: reward = -68.48, steps = 26 16:46:12 [INFO] train episode 23558: reward = -68.25, steps = 48 16:46:14 [INFO] train episode 23559: reward = -75.27, steps = 25 16:46:18 [INFO] train episode 23560: reward = -142.73, steps = 45 16:46:21 [INFO] train episode 23561: reward = -54.18, steps = 28 16:46:23 [INFO] train episode 23562: reward = -29.43, steps = 31 16:46:27 [INFO] train episode 23563: reward = -70.68, steps = 38 16:46:32 [INFO] train episode 23564: reward = -79.63, steps = 62 16:46:35 [INFO] train episode 23565: reward = -60.52, steps = 29 16:46:37 [INFO] train episode 23566: reward = -79.14, steps = 27 16:46:40 [INFO] train episode 23567: reward = -85.71, steps = 23 16:46:44 [INFO] train episode 23568: reward = -57.82, steps = 41 16:46:48 [INFO] train episode 23569: reward = -83.15, steps = 44 16:46:49 [INFO] train episode 23570: reward = -57.77, steps = 18 16:46:53 [INFO] train episode 23571: reward = -135.64, steps = 44 16:46:56 [INFO] train episode 23572: reward = -34.74, steps = 33 16:46:59 [INFO] train episode 23573: reward = -65.28, steps = 26 16:47:02 [INFO] train episode 23574: reward = -57.46, steps = 36 16:47:03 [INFO] train episode 23575: reward = -57.74, steps = 20 16:47:08 [INFO] train episode 23576: reward = -60.52, steps = 48 16:47:10 [INFO] train episode 23577: reward = -77.14, steps = 25 16:47:14 [INFO] train episode 23578: reward = -97.63, steps = 49 16:47:17 [INFO] train episode 23579: reward = -57.82, steps = 33 16:47:21 [INFO] train episode 23580: reward = -61.70, steps = 37 16:47:24 [INFO] train episode 23581: reward = -95.47, steps = 44 16:47:27 [INFO] train episode 23582: reward = -68.54, steps = 34 16:47:31 [INFO] train episode 23583: reward = -88.65, steps = 34 16:47:34 [INFO] train episode 23584: reward = -72.15, steps = 30 16:47:36 [INFO] train episode 23585: reward = -67.87, steps = 23 16:47:39 [INFO] train episode 23586: reward = -123.88, steps = 35 16:47:41 [INFO] train episode 23587: reward = -66.20, steps = 21 16:47:45 [INFO] train episode 23588: reward = -120.15, steps = 47 16:47:47 [INFO] train episode 23589: reward = -65.28, steps = 22 16:47:50 [INFO] train episode 23590: reward = -50.59, steps = 31 16:47:53 [INFO] train episode 23591: reward = -63.67, steps = 36 16:47:57 [INFO] train episode 23592: reward = -50.00, steps = 42 16:48:01 [INFO] train episode 23593: reward = -100.83, steps = 40 16:48:05 [INFO] train episode 23594: reward = -74.31, steps = 46 16:48:09 [INFO] train episode 23595: reward = -93.19, steps = 43 16:48:13 [INFO] train episode 23596: reward = -104.43, steps = 54 16:48:17 [INFO] train episode 23597: reward = -68.94, steps = 42 16:48:19 [INFO] train episode 23598: reward = -87.29, steps = 23 16:48:22 [INFO] train episode 23599: reward = -58.43, steps = 33 16:48:26 [INFO] train episode 23600: reward = -63.85, steps = 39 16:48:28 [INFO] train episode 23601: reward = -56.87, steps = 23 16:48:30 [INFO] train episode 23602: reward = -61.25, steps = 27 16:48:34 [INFO] train episode 23603: reward = -105.96, steps = 51 16:48:37 [INFO] train episode 23604: reward = -65.29, steps = 22 16:48:40 [INFO] train episode 23605: reward = -46.63, steps = 33 16:48:44 [INFO] train episode 23606: reward = -81.52, steps = 45 16:48:47 [INFO] train episode 23607: reward = -92.73, steps = 39 16:48:49 [INFO] train episode 23608: reward = -127.63, steps = 19 16:48:53 [INFO] train episode 23609: reward = -43.41, steps = 37 16:48:58 [INFO] train episode 23610: reward = -132.14, steps = 56 16:49:02 [INFO] train episode 23611: reward = -95.79, steps = 43 16:49:05 [INFO] train episode 23612: reward = -119.90, steps = 36 16:49:08 [INFO] train episode 23613: reward = -80.63, steps = 38 16:49:11 [INFO] train episode 23614: reward = -61.58, steps = 32 16:49:13 [INFO] train episode 23615: reward = -53.69, steps = 22 16:49:17 [INFO] train episode 23616: reward = -70.06, steps = 42 16:49:21 [INFO] train episode 23617: reward = -42.86, steps = 44 16:49:23 [INFO] train episode 23618: reward = -65.60, steps = 26 16:49:26 [INFO] train episode 23619: reward = -55.69, steps = 34 16:49:33 [INFO] train episode 23620: reward = -76.16, steps = 78 16:49:38 [INFO] train episode 23621: reward = -87.70, steps = 43 16:49:40 [INFO] train episode 23622: reward = -55.02, steps = 21 16:49:42 [INFO] train episode 23623: reward = -62.32, steps = 21 16:49:46 [INFO] train episode 23624: reward = -68.58, steps = 43 16:49:49 [INFO] train episode 23625: reward = -46.13, steps = 41 16:49:52 [INFO] train episode 23626: reward = -86.75, steps = 37 16:49:57 [INFO] train episode 23627: reward = -71.69, steps = 53 16:50:00 [INFO] train episode 23628: reward = -58.00, steps = 34 16:50:05 [INFO] train episode 23629: reward = -116.78, steps = 49 16:50:08 [INFO] train episode 23630: reward = -49.98, steps = 41 16:50:12 [INFO] train episode 23631: reward = -81.15, steps = 41 16:50:15 [INFO] train episode 23632: reward = -58.60, steps = 41 16:50:19 [INFO] train episode 23633: reward = -123.12, steps = 42 16:50:22 [INFO] train episode 23634: reward = -78.01, steps = 25 16:50:26 [INFO] train episode 23635: reward = -83.23, steps = 51 16:50:29 [INFO] train episode 23636: reward = -51.29, steps = 29 16:50:34 [INFO] train episode 23637: reward = -59.42, steps = 54 16:50:36 [INFO] train episode 23638: reward = -67.96, steps = 26 16:50:39 [INFO] train episode 23639: reward = -86.95, steps = 28 16:50:40 [INFO] train episode 23640: reward = -101.26, steps = 20 16:50:43 [INFO] train episode 23641: reward = -50.86, steps = 34 16:50:47 [INFO] train episode 23642: reward = -83.01, steps = 39 16:50:54 [INFO] train episode 23643: reward = -97.73, steps = 75 16:50:58 [INFO] train episode 23644: reward = -44.20, steps = 37 16:51:01 [INFO] train episode 23645: reward = -65.87, steps = 44 16:51:04 [INFO] train episode 23646: reward = -53.48, steps = 33 16:51:08 [INFO] train episode 23647: reward = -74.41, steps = 43 16:51:13 [INFO] train episode 23648: reward = -109.69, steps = 50 16:51:15 [INFO] train episode 23649: reward = -82.79, steps = 23 16:51:17 [INFO] train episode 23650: reward = -61.98, steps = 28 16:51:21 [INFO] train episode 23651: reward = -108.64, steps = 37 16:51:24 [INFO] train episode 23652: reward = -70.58, steps = 36 16:51:28 [INFO] train episode 23653: reward = -157.44, steps = 46 16:51:31 [INFO] train episode 23654: reward = -58.78, steps = 29 16:51:34 [INFO] train episode 23655: reward = -41.39, steps = 43 16:51:38 [INFO] train episode 23656: reward = -108.40, steps = 39 16:51:40 [INFO] train episode 23657: reward = -52.95, steps = 19 16:51:43 [INFO] train episode 23658: reward = -89.43, steps = 30 16:51:44 [INFO] train episode 23659: reward = -43.88, steps = 20 16:51:48 [INFO] train episode 23660: reward = -47.64, steps = 40 16:51:52 [INFO] train episode 23661: reward = -111.65, steps = 44 16:51:56 [INFO] train episode 23662: reward = -105.46, steps = 40 16:51:59 [INFO] train episode 23663: reward = -57.08, steps = 34 16:52:03 [INFO] train episode 23664: reward = -75.35, steps = 50 16:52:05 [INFO] train episode 23665: reward = -57.81, steps = 24 16:52:08 [INFO] train episode 23666: reward = -78.07, steps = 37 16:52:11 [INFO] train episode 23667: reward = -69.79, steps = 31 16:52:13 [INFO] train episode 23668: reward = -67.44, steps = 22 16:52:16 [INFO] train episode 23669: reward = -29.36, steps = 23 16:52:18 [INFO] train episode 23670: reward = -73.49, steps = 34 16:52:23 [INFO] train episode 23671: reward = -111.92, steps = 56 16:52:27 [INFO] train episode 23672: reward = -47.10, steps = 46 16:52:30 [INFO] train episode 23673: reward = -45.83, steps = 30 16:52:33 [INFO] train episode 23674: reward = -74.30, steps = 27 16:52:38 [INFO] train episode 23675: reward = -132.59, steps = 49 16:52:42 [INFO] train episode 23676: reward = -42.68, steps = 45 16:52:45 [INFO] train episode 23677: reward = -89.28, steps = 28 16:52:50 [INFO] train episode 23678: reward = -174.07, steps = 56 16:52:53 [INFO] train episode 23679: reward = -51.50, steps = 34 16:52:56 [INFO] train episode 23680: reward = -38.76, steps = 37 16:52:59 [INFO] train episode 23681: reward = -82.75, steps = 40 16:53:03 [INFO] train episode 23682: reward = -52.59, steps = 39 16:53:05 [INFO] train episode 23683: reward = -70.74, steps = 20 16:53:10 [INFO] train episode 23684: reward = -87.58, steps = 55 16:53:13 [INFO] train episode 23685: reward = -64.10, steps = 34 16:53:17 [INFO] train episode 23686: reward = -35.47, steps = 50 16:53:20 [INFO] train episode 23687: reward = -75.25, steps = 33 16:53:22 [INFO] train episode 23688: reward = -43.37, steps = 24 16:53:25 [INFO] train episode 23689: reward = -74.75, steps = 29 16:53:28 [INFO] train episode 23690: reward = -70.24, steps = 38 16:53:30 [INFO] train episode 23691: reward = -95.57, steps = 19 16:53:33 [INFO] train episode 23692: reward = -62.52, steps = 32 16:53:35 [INFO] train episode 23693: reward = -68.57, steps = 24 16:53:38 [INFO] train episode 23694: reward = -43.14, steps = 34 16:53:41 [INFO] train episode 23695: reward = -45.72, steps = 34 16:53:45 [INFO] train episode 23696: reward = -48.53, steps = 40 16:53:49 [INFO] train episode 23697: reward = -67.61, steps = 53 16:53:52 [INFO] train episode 23698: reward = -59.38, steps = 26 16:53:55 [INFO] train episode 23699: reward = -63.01, steps = 29 16:53:57 [INFO] train episode 23700: reward = -49.74, steps = 29 16:54:01 [INFO] train episode 23701: reward = -95.48, steps = 47 16:54:04 [INFO] train episode 23702: reward = -71.29, steps = 30 16:54:08 [INFO] train episode 23703: reward = -166.97, steps = 48 16:54:10 [INFO] train episode 23704: reward = -41.46, steps = 23 16:54:12 [INFO] train episode 23705: reward = -65.43, steps = 20 16:54:16 [INFO] train episode 23706: reward = -62.32, steps = 38 16:54:20 [INFO] train episode 23707: reward = -92.63, steps = 47 16:54:22 [INFO] train episode 23708: reward = -36.33, steps = 22 16:54:27 [INFO] train episode 23709: reward = -108.35, steps = 54 16:54:30 [INFO] train episode 23710: reward = -92.97, steps = 42 16:54:35 [INFO] train episode 23711: reward = -97.42, steps = 50 16:54:40 [INFO] train episode 23712: reward = -115.41, steps = 52 16:54:43 [INFO] train episode 23713: reward = -72.29, steps = 42 16:54:45 [INFO] train episode 23714: reward = -63.06, steps = 21 16:54:48 [INFO] train episode 23715: reward = -93.62, steps = 34 16:54:51 [INFO] train episode 23716: reward = -93.97, steps = 31 16:54:53 [INFO] train episode 23717: reward = -68.20, steps = 25 16:54:56 [INFO] train episode 23718: reward = -44.32, steps = 25 16:55:00 [INFO] train episode 23719: reward = -86.99, steps = 47 16:55:02 [INFO] train episode 23720: reward = -73.16, steps = 21 16:55:04 [INFO] train episode 23721: reward = -82.10, steps = 30 16:55:08 [INFO] train episode 23722: reward = -85.49, steps = 38 16:55:11 [INFO] train episode 23723: reward = -68.46, steps = 41 16:55:15 [INFO] train episode 23724: reward = -64.93, steps = 35 16:55:17 [INFO] train episode 23725: reward = -53.48, steps = 21 16:55:19 [INFO] train episode 23726: reward = -59.92, steps = 29 16:55:23 [INFO] train episode 23727: reward = -125.98, steps = 43 16:55:26 [INFO] train episode 23728: reward = -51.44, steps = 37 16:55:30 [INFO] train episode 23729: reward = -110.06, steps = 41 16:55:33 [INFO] train episode 23730: reward = -33.83, steps = 27 16:55:37 [INFO] train episode 23731: reward = -94.81, steps = 39 16:55:39 [INFO] train episode 23732: reward = -58.51, steps = 24 16:55:43 [INFO] train episode 23733: reward = -62.70, steps = 47 16:55:47 [INFO] train episode 23734: reward = -150.42, steps = 46 16:55:51 [INFO] train episode 23735: reward = -73.04, steps = 46 16:55:56 [INFO] train episode 23736: reward = -64.20, steps = 50 16:55:57 [INFO] train episode 23737: reward = -59.63, steps = 20 16:56:00 [INFO] train episode 23738: reward = -58.48, steps = 25 16:56:03 [INFO] train episode 23739: reward = -73.50, steps = 33 16:56:05 [INFO] train episode 23740: reward = -85.79, steps = 26 16:56:10 [INFO] train episode 23741: reward = -64.65, steps = 53 16:56:13 [INFO] train episode 23742: reward = -57.08, steps = 35 16:56:18 [INFO] train episode 23743: reward = -56.14, steps = 54 16:56:20 [INFO] train episode 23744: reward = -114.48, steps = 19 16:56:23 [INFO] train episode 23745: reward = -82.02, steps = 39 16:56:26 [INFO] train episode 23746: reward = -85.37, steps = 39 16:56:28 [INFO] train episode 23747: reward = -62.76, steps = 21 16:56:33 [INFO] train episode 23748: reward = -56.29, steps = 55 16:56:36 [INFO] train episode 23749: reward = -45.17, steps = 23 16:56:39 [INFO] train episode 23750: reward = -60.49, steps = 33 16:56:43 [INFO] train episode 23751: reward = -73.22, steps = 53 16:56:46 [INFO] train episode 23752: reward = -55.17, steps = 37 16:56:50 [INFO] train episode 23753: reward = -81.46, steps = 43 16:56:54 [INFO] train episode 23754: reward = -91.73, steps = 39 16:56:56 [INFO] train episode 23755: reward = -54.73, steps = 27 16:57:00 [INFO] train episode 23756: reward = -104.31, steps = 44 16:57:04 [INFO] train episode 23757: reward = -67.44, steps = 42 16:57:07 [INFO] train episode 23758: reward = -96.97, steps = 35 16:57:10 [INFO] train episode 23759: reward = -96.40, steps = 31 16:57:14 [INFO] train episode 23760: reward = -96.02, steps = 49 16:57:17 [INFO] train episode 23761: reward = -106.21, steps = 27 16:57:19 [INFO] train episode 23762: reward = -43.80, steps = 33 16:57:23 [INFO] train episode 23763: reward = -55.33, steps = 39 16:57:28 [INFO] train episode 23764: reward = -89.20, steps = 59 16:57:33 [INFO] train episode 23765: reward = -47.40, steps = 48 16:57:35 [INFO] train episode 23766: reward = -72.63, steps = 23 16:57:38 [INFO] train episode 23767: reward = -53.69, steps = 39 16:57:42 [INFO] train episode 23768: reward = -107.17, steps = 36 16:57:44 [INFO] train episode 23769: reward = -43.43, steps = 29 16:57:48 [INFO] train episode 23770: reward = -121.89, steps = 43 16:57:50 [INFO] train episode 23771: reward = -69.63, steps = 19 16:57:52 [INFO] train episode 23772: reward = -56.65, steps = 24 16:57:55 [INFO] train episode 23773: reward = -61.86, steps = 40 16:57:59 [INFO] train episode 23774: reward = -109.94, steps = 36 16:58:02 [INFO] train episode 23775: reward = -146.35, steps = 43 16:58:06 [INFO] train episode 23776: reward = -110.68, steps = 40 16:58:10 [INFO] train episode 23777: reward = -87.87, steps = 45 16:58:14 [INFO] train episode 23778: reward = -62.42, steps = 45 16:58:16 [INFO] train episode 23779: reward = -71.67, steps = 19 16:58:22 [INFO] train episode 23780: reward = -103.63, steps = 71 16:58:24 [INFO] train episode 23781: reward = -65.69, steps = 21 16:58:27 [INFO] train episode 23782: reward = -48.33, steps = 32 16:58:29 [INFO] train episode 23783: reward = -70.79, steps = 31 16:58:34 [INFO] train episode 23784: reward = -58.15, steps = 36 16:58:36 [INFO] train episode 23785: reward = -93.63, steps = 22 16:58:39 [INFO] train episode 23786: reward = -69.13, steps = 38 16:58:41 [INFO] train episode 23787: reward = -71.07, steps = 23 16:58:45 [INFO] train episode 23788: reward = -95.80, steps = 41 16:58:47 [INFO] train episode 23789: reward = -55.17, steps = 23 16:58:54 [INFO] train episode 23790: reward = -214.78, steps = 82 16:58:57 [INFO] train episode 23791: reward = -42.95, steps = 35 16:58:59 [INFO] train episode 23792: reward = -88.90, steps = 22 16:59:02 [INFO] train episode 23793: reward = -66.23, steps = 29 16:59:04 [INFO] train episode 23794: reward = -72.42, steps = 21 16:59:08 [INFO] train episode 23795: reward = -57.10, steps = 43 16:59:12 [INFO] train episode 23796: reward = -81.83, steps = 48 16:59:16 [INFO] train episode 23797: reward = -108.65, steps = 51 16:59:19 [INFO] train episode 23798: reward = -61.69, steps = 31 16:59:23 [INFO] train episode 23799: reward = -74.33, steps = 38 16:59:25 [INFO] train episode 23800: reward = -46.89, steps = 31 16:59:29 [INFO] train episode 23801: reward = -38.87, steps = 42 16:59:31 [INFO] train episode 23802: reward = -57.28, steps = 22 16:59:36 [INFO] train episode 23803: reward = -97.66, steps = 55 16:59:38 [INFO] train episode 23804: reward = -72.90, steps = 24 16:59:42 [INFO] train episode 23805: reward = -95.57, steps = 46 16:59:46 [INFO] train episode 23806: reward = -73.69, steps = 40 16:59:50 [INFO] train episode 23807: reward = -60.25, steps = 50 16:59:52 [INFO] train episode 23808: reward = -62.18, steps = 24 16:59:56 [INFO] train episode 23809: reward = -51.85, steps = 42 16:59:59 [INFO] train episode 23810: reward = -46.72, steps = 27 17:00:01 [INFO] train episode 23811: reward = -38.77, steps = 27 17:00:04 [INFO] train episode 23812: reward = -83.71, steps = 30 17:00:07 [INFO] train episode 23813: reward = -92.94, steps = 31 17:00:11 [INFO] train episode 23814: reward = -107.80, steps = 46 17:00:13 [INFO] train episode 23815: reward = -46.82, steps = 22 17:00:17 [INFO] train episode 23816: reward = -70.60, steps = 44 17:00:20 [INFO] train episode 23817: reward = -93.97, steps = 41 17:00:23 [INFO] train episode 23818: reward = -91.53, steps = 34 17:00:26 [INFO] train episode 23819: reward = -59.62, steps = 25 17:00:29 [INFO] train episode 23820: reward = -51.35, steps = 35 17:00:33 [INFO] train episode 23821: reward = -84.68, steps = 51 17:00:37 [INFO] train episode 23822: reward = -83.46, steps = 44 17:00:40 [INFO] train episode 23823: reward = -71.77, steps = 29 17:00:43 [INFO] train episode 23824: reward = -55.97, steps = 35 17:00:48 [INFO] train episode 23825: reward = -117.81, steps = 53 17:00:50 [INFO] train episode 23826: reward = -46.19, steps = 26 17:00:53 [INFO] train episode 23827: reward = -56.89, steps = 30 17:00:56 [INFO] train episode 23828: reward = -88.46, steps = 37 17:01:00 [INFO] train episode 23829: reward = -50.99, steps = 36 17:01:04 [INFO] train episode 23830: reward = -71.67, steps = 50 17:01:10 [INFO] train episode 23831: reward = -93.33, steps = 67 17:01:13 [INFO] train episode 23832: reward = -51.84, steps = 40 17:01:17 [INFO] train episode 23833: reward = -78.60, steps = 45 17:01:21 [INFO] train episode 23834: reward = -91.13, steps = 46 17:01:25 [INFO] train episode 23835: reward = -73.81, steps = 46 17:01:29 [INFO] train episode 23836: reward = -70.95, steps = 31 17:01:31 [INFO] train episode 23837: reward = -59.19, steps = 26 17:01:34 [INFO] train episode 23838: reward = -56.84, steps = 24 17:01:36 [INFO] train episode 23839: reward = -54.00, steps = 25 17:01:41 [INFO] train episode 23840: reward = -115.70, steps = 60 17:01:46 [INFO] train episode 23841: reward = -75.86, steps = 53 17:01:51 [INFO] train episode 23842: reward = -106.97, steps = 50 17:01:53 [INFO] train episode 23843: reward = -63.05, steps = 27 17:01:56 [INFO] train episode 23844: reward = -67.73, steps = 29 17:01:59 [INFO] train episode 23845: reward = -62.01, steps = 39 17:02:03 [INFO] train episode 23846: reward = -92.15, steps = 43 17:02:06 [INFO] train episode 23847: reward = -54.31, steps = 34 17:02:08 [INFO] train episode 23848: reward = -54.24, steps = 21 17:02:11 [INFO] train episode 23849: reward = -68.94, steps = 34 17:02:14 [INFO] train episode 23850: reward = -61.88, steps = 29 17:02:16 [INFO] train episode 23851: reward = -59.82, steps = 24 17:02:18 [INFO] train episode 23852: reward = -56.18, steps = 22 17:02:23 [INFO] train episode 23853: reward = -143.81, steps = 54 17:02:27 [INFO] train episode 23854: reward = -108.91, steps = 54 17:02:30 [INFO] train episode 23855: reward = -84.21, steps = 24 17:02:33 [INFO] train episode 23856: reward = -90.86, steps = 33 17:02:37 [INFO] train episode 23857: reward = -70.04, steps = 48 17:02:41 [INFO] train episode 23858: reward = -78.53, steps = 41 17:02:45 [INFO] train episode 23859: reward = -87.71, steps = 47 17:02:47 [INFO] train episode 23860: reward = -49.83, steps = 19 17:02:51 [INFO] train episode 23861: reward = -85.43, steps = 46 17:02:58 [INFO] train episode 23862: reward = -123.59, steps = 73 17:03:01 [INFO] train episode 23863: reward = -56.93, steps = 43 17:03:06 [INFO] train episode 23864: reward = -115.59, steps = 52 17:03:09 [INFO] train episode 23865: reward = -95.26, steps = 38 17:03:12 [INFO] train episode 23866: reward = -55.00, steps = 29 17:03:14 [INFO] train episode 23867: reward = -95.56, steps = 25 17:03:16 [INFO] train episode 23868: reward = -93.05, steps = 20 17:03:19 [INFO] train episode 23869: reward = -47.62, steps = 35 17:03:25 [INFO] train episode 23870: reward = -126.59, steps = 62 17:03:27 [INFO] train episode 23871: reward = -75.94, steps = 25 17:03:30 [INFO] train episode 23872: reward = -84.60, steps = 27 17:03:33 [INFO] train episode 23873: reward = -46.94, steps = 39 17:03:35 [INFO] train episode 23874: reward = -59.38, steps = 22 17:03:38 [INFO] train episode 23875: reward = -109.15, steps = 34 17:03:41 [INFO] train episode 23876: reward = -68.94, steps = 36 17:03:44 [INFO] train episode 23877: reward = -42.23, steps = 33 17:03:47 [INFO] train episode 23878: reward = -83.10, steps = 32 17:03:51 [INFO] train episode 23879: reward = -124.17, steps = 42 17:03:53 [INFO] train episode 23880: reward = -66.74, steps = 23 17:03:57 [INFO] train episode 23881: reward = -45.79, steps = 41 17:04:01 [INFO] train episode 23882: reward = -73.43, steps = 47 17:04:03 [INFO] train episode 23883: reward = -49.84, steps = 25 17:04:06 [INFO] train episode 23884: reward = -70.97, steps = 27 17:04:09 [INFO] train episode 23885: reward = -89.33, steps = 36 17:04:13 [INFO] train episode 23886: reward = -69.10, steps = 44 17:04:15 [INFO] train episode 23887: reward = -62.29, steps = 24 17:04:19 [INFO] train episode 23888: reward = -115.87, steps = 50 17:04:21 [INFO] train episode 23889: reward = -41.41, steps = 23 17:04:24 [INFO] train episode 23890: reward = -98.70, steps = 25 17:04:28 [INFO] train episode 23891: reward = -47.90, steps = 35 17:04:33 [INFO] train episode 23892: reward = -123.31, steps = 61 17:04:35 [INFO] train episode 23893: reward = -106.80, steps = 20 17:04:38 [INFO] train episode 23894: reward = -93.09, steps = 29 17:04:40 [INFO] train episode 23895: reward = -66.17, steps = 29 17:04:44 [INFO] train episode 23896: reward = -67.54, steps = 36 17:04:48 [INFO] train episode 23897: reward = -99.22, steps = 46 17:04:51 [INFO] train episode 23898: reward = -71.59, steps = 36 17:04:53 [INFO] train episode 23899: reward = -59.39, steps = 21 17:04:56 [INFO] train episode 23900: reward = -91.99, steps = 39 17:04:59 [INFO] train episode 23901: reward = -74.93, steps = 35 17:05:02 [INFO] train episode 23902: reward = -59.11, steps = 37 17:05:06 [INFO] train episode 23903: reward = -61.29, steps = 41 17:05:08 [INFO] train episode 23904: reward = -44.32, steps = 24 17:05:10 [INFO] train episode 23905: reward = -62.54, steps = 22 17:05:13 [INFO] train episode 23906: reward = -63.46, steps = 31 17:05:15 [INFO] train episode 23907: reward = -67.46, steps = 25 17:05:19 [INFO] train episode 23908: reward = -59.26, steps = 44 17:05:22 [INFO] train episode 23909: reward = -77.16, steps = 36 17:05:26 [INFO] train episode 23910: reward = -40.00, steps = 41 17:05:29 [INFO] train episode 23911: reward = -117.69, steps = 39 17:05:31 [INFO] train episode 23912: reward = -83.34, steps = 23 17:05:33 [INFO] train episode 23913: reward = -63.61, steps = 20 17:05:36 [INFO] train episode 23914: reward = -75.59, steps = 29 17:05:38 [INFO] train episode 23915: reward = -66.35, steps = 23 17:05:40 [INFO] train episode 23916: reward = -53.86, steps = 23 17:05:43 [INFO] train episode 23917: reward = -76.99, steps = 36 17:05:47 [INFO] train episode 23918: reward = -64.38, steps = 44 17:05:49 [INFO] train episode 23919: reward = -78.73, steps = 19 17:05:52 [INFO] train episode 23920: reward = -35.82, steps = 36 17:05:54 [INFO] train episode 23921: reward = -59.08, steps = 22 17:05:58 [INFO] train episode 23922: reward = -121.88, steps = 48 17:06:00 [INFO] train episode 23923: reward = -79.26, steps = 18 17:06:03 [INFO] train episode 23924: reward = -59.06, steps = 39 17:06:07 [INFO] train episode 23925: reward = -85.34, steps = 44 17:06:11 [INFO] train episode 23926: reward = -73.17, steps = 43 17:06:16 [INFO] train episode 23927: reward = -97.40, steps = 61 17:06:21 [INFO] train episode 23928: reward = -99.22, steps = 57 17:06:25 [INFO] train episode 23929: reward = -76.70, steps = 48 17:06:28 [INFO] train episode 23930: reward = -85.86, steps = 32 17:06:30 [INFO] train episode 23931: reward = -62.46, steps = 21 17:06:33 [INFO] train episode 23932: reward = -65.56, steps = 29 17:06:36 [INFO] train episode 23933: reward = -44.42, steps = 41 17:06:39 [INFO] train episode 23934: reward = -85.81, steps = 32 17:06:42 [INFO] train episode 23935: reward = -62.15, steps = 36 17:06:49 [INFO] train episode 23936: reward = -196.84, steps = 70 17:06:52 [INFO] train episode 23937: reward = -55.57, steps = 42 17:06:58 [INFO] train episode 23938: reward = -140.88, steps = 68 17:07:00 [INFO] train episode 23939: reward = -59.60, steps = 22 17:07:03 [INFO] train episode 23940: reward = -49.74, steps = 33 17:07:06 [INFO] train episode 23941: reward = -57.88, steps = 34 17:07:08 [INFO] train episode 23942: reward = -69.80, steps = 20 17:07:11 [INFO] train episode 23943: reward = -53.00, steps = 32 17:07:14 [INFO] train episode 23944: reward = -57.79, steps = 30 17:07:18 [INFO] train episode 23945: reward = -76.62, steps = 45 17:07:20 [INFO] train episode 23946: reward = -70.55, steps = 19 17:07:25 [INFO] train episode 23947: reward = -99.92, steps = 46 17:07:27 [INFO] train episode 23948: reward = -53.16, steps = 23 17:07:30 [INFO] train episode 23949: reward = -106.28, steps = 31 17:07:32 [INFO] train episode 23950: reward = -48.88, steps = 23 17:07:35 [INFO] train episode 23951: reward = -66.88, steps = 37 17:07:40 [INFO] train episode 23952: reward = -81.00, steps = 54 17:07:44 [INFO] train episode 23953: reward = -145.37, steps = 50 17:07:49 [INFO] train episode 23954: reward = -92.89, steps = 58 17:07:52 [INFO] train episode 23955: reward = -56.59, steps = 26 17:07:56 [INFO] train episode 23956: reward = -78.12, steps = 46 17:08:01 [INFO] train episode 23957: reward = -143.46, steps = 52 17:08:03 [INFO] train episode 23958: reward = -54.09, steps = 26 17:08:06 [INFO] train episode 23959: reward = -55.76, steps = 34 17:08:10 [INFO] train episode 23960: reward = -36.01, steps = 38 17:08:12 [INFO] train episode 23961: reward = -61.62, steps = 23 17:08:15 [INFO] train episode 23962: reward = -56.59, steps = 39 17:08:18 [INFO] train episode 23963: reward = -64.55, steps = 36 17:08:21 [INFO] train episode 23964: reward = -71.84, steps = 37 17:08:23 [INFO] train episode 23965: reward = -72.44, steps = 23 17:08:29 [INFO] train episode 23966: reward = -99.12, steps = 61 17:08:32 [INFO] train episode 23967: reward = -42.87, steps = 32 17:08:35 [INFO] train episode 23968: reward = -47.41, steps = 36 17:08:39 [INFO] train episode 23969: reward = -55.90, steps = 39 17:08:42 [INFO] train episode 23970: reward = -87.56, steps = 30 17:08:44 [INFO] train episode 23971: reward = -66.60, steps = 27 17:08:47 [INFO] train episode 23972: reward = -66.36, steps = 30 17:08:50 [INFO] train episode 23973: reward = -82.85, steps = 37 17:08:53 [INFO] train episode 23974: reward = -55.10, steps = 37 17:08:56 [INFO] train episode 23975: reward = -50.35, steps = 32 17:09:00 [INFO] train episode 23976: reward = -50.07, steps = 40 17:09:03 [INFO] train episode 23977: reward = -96.72, steps = 28 17:09:07 [INFO] train episode 23978: reward = -112.83, steps = 51 17:09:10 [INFO] train episode 23979: reward = -76.69, steps = 28 17:09:16 [INFO] train episode 23980: reward = -140.58, steps = 73 17:09:19 [INFO] train episode 23981: reward = -86.43, steps = 36 17:09:23 [INFO] train episode 23982: reward = -66.46, steps = 38 17:09:26 [INFO] train episode 23983: reward = -31.18, steps = 34 17:09:28 [INFO] train episode 23984: reward = -42.76, steps = 32 17:09:32 [INFO] train episode 23985: reward = -94.22, steps = 36 17:09:35 [INFO] train episode 23986: reward = -79.27, steps = 36 17:09:37 [INFO] train episode 23987: reward = -45.43, steps = 21 17:09:40 [INFO] train episode 23988: reward = -52.97, steps = 34 17:09:44 [INFO] train episode 23989: reward = -47.05, steps = 45 17:09:47 [INFO] train episode 23990: reward = -97.09, steps = 27 17:09:52 [INFO] train episode 23991: reward = -68.18, steps = 57 17:09:55 [INFO] train episode 23992: reward = -44.87, steps = 34 17:09:59 [INFO] train episode 23993: reward = -48.42, steps = 43 17:10:02 [INFO] train episode 23994: reward = -81.73, steps = 33 17:10:06 [INFO] train episode 23995: reward = -105.97, steps = 46 17:10:13 [INFO] train episode 23996: reward = -157.46, steps = 78 17:10:15 [INFO] train episode 23997: reward = -59.85, steps = 21 17:10:18 [INFO] train episode 23998: reward = -89.11, steps = 39 17:10:22 [INFO] train episode 23999: reward = -60.48, steps = 24 17:10:25 [INFO] train episode 24000: reward = -84.74, steps = 43 17:10:28 [INFO] train episode 24001: reward = -61.92, steps = 26 17:10:32 [INFO] train episode 24002: reward = -60.71, steps = 54 17:10:36 [INFO] train episode 24003: reward = -51.30, steps = 45 17:10:41 [INFO] train episode 24004: reward = -86.63, steps = 47 17:10:44 [INFO] train episode 24005: reward = -73.33, steps = 33 17:10:46 [INFO] train episode 24006: reward = -75.03, steps = 30 17:10:50 [INFO] train episode 24007: reward = -39.62, steps = 38 17:10:58 [INFO] train episode 24008: reward = -147.03, steps = 89 17:11:01 [INFO] train episode 24009: reward = -89.32, steps = 43 17:11:05 [INFO] train episode 24010: reward = -63.85, steps = 36 17:11:08 [INFO] train episode 24011: reward = -59.58, steps = 35 17:11:10 [INFO] train episode 24012: reward = -68.25, steps = 21 17:11:14 [INFO] train episode 24013: reward = -87.89, steps = 43 17:11:17 [INFO] train episode 24014: reward = -89.56, steps = 39 17:11:20 [INFO] train episode 24015: reward = -75.04, steps = 28 17:11:22 [INFO] train episode 24016: reward = -64.77, steps = 28 17:11:26 [INFO] train episode 24017: reward = -84.66, steps = 44 17:11:28 [INFO] train episode 24018: reward = -52.71, steps = 22 17:11:31 [INFO] train episode 24019: reward = -41.85, steps = 32 17:11:34 [INFO] train episode 24020: reward = -62.70, steps = 31 17:11:37 [INFO] train episode 24021: reward = -105.02, steps = 36 17:11:41 [INFO] train episode 24022: reward = -72.44, steps = 41 17:11:43 [INFO] train episode 24023: reward = -54.13, steps = 25 17:11:46 [INFO] train episode 24024: reward = -88.42, steps = 34 17:11:51 [INFO] train episode 24025: reward = -63.85, steps = 52 17:11:54 [INFO] train episode 24026: reward = -143.33, steps = 34 17:11:57 [INFO] train episode 24027: reward = -64.42, steps = 33 17:12:02 [INFO] train episode 24028: reward = -68.84, steps = 52 17:12:06 [INFO] train episode 24029: reward = -86.85, steps = 46 17:12:09 [INFO] train episode 24030: reward = -53.24, steps = 39 17:12:11 [INFO] train episode 24031: reward = -56.37, steps = 20 17:12:14 [INFO] train episode 24032: reward = -59.94, steps = 32 17:12:17 [INFO] train episode 24033: reward = -49.26, steps = 35 17:12:20 [INFO] train episode 24034: reward = -109.27, steps = 30 17:12:22 [INFO] train episode 24035: reward = -44.84, steps = 29 17:12:25 [INFO] train episode 24036: reward = -82.89, steps = 28 17:12:27 [INFO] train episode 24037: reward = -72.59, steps = 24 17:12:29 [INFO] train episode 24038: reward = -52.23, steps = 23 17:12:32 [INFO] train episode 24039: reward = -44.17, steps = 28 17:12:36 [INFO] train episode 24040: reward = -53.85, steps = 47 17:12:40 [INFO] train episode 24041: reward = -45.61, steps = 42 17:12:44 [INFO] train episode 24042: reward = -62.19, steps = 44 17:12:48 [INFO] train episode 24043: reward = -80.40, steps = 49 17:12:52 [INFO] train episode 24044: reward = -59.21, steps = 36 17:12:55 [INFO] train episode 24045: reward = -49.50, steps = 32 17:12:57 [INFO] train episode 24046: reward = -54.61, steps = 29 17:13:02 [INFO] train episode 24047: reward = -51.45, steps = 53 17:13:04 [INFO] train episode 24048: reward = -91.51, steps = 30 17:13:07 [INFO] train episode 24049: reward = -83.52, steps = 23 17:13:09 [INFO] train episode 24050: reward = -90.45, steps = 24 17:13:13 [INFO] train episode 24051: reward = -63.52, steps = 47 17:13:16 [INFO] train episode 24052: reward = -78.36, steps = 38 17:13:24 [INFO] train episode 24053: reward = -94.19, steps = 70 17:13:25 [INFO] train episode 24054: reward = -126.31, steps = 18 17:13:28 [INFO] train episode 24055: reward = -70.30, steps = 25 17:13:31 [INFO] train episode 24056: reward = -68.25, steps = 38 17:13:34 [INFO] train episode 24057: reward = -65.28, steps = 30 17:13:37 [INFO] train episode 24058: reward = -57.73, steps = 37 17:13:41 [INFO] train episode 24059: reward = -85.98, steps = 38 17:13:44 [INFO] train episode 24060: reward = -93.31, steps = 32 17:13:47 [INFO] train episode 24061: reward = -121.60, steps = 42 17:13:50 [INFO] train episode 24062: reward = -66.12, steps = 29 17:13:53 [INFO] train episode 24063: reward = -53.91, steps = 32 17:13:56 [INFO] train episode 24064: reward = -67.44, steps = 35 17:14:00 [INFO] train episode 24065: reward = -52.50, steps = 44 17:14:02 [INFO] train episode 24066: reward = -51.95, steps = 26 17:14:06 [INFO] train episode 24067: reward = -66.39, steps = 36 17:14:08 [INFO] train episode 24068: reward = -79.15, steps = 30 17:14:11 [INFO] train episode 24069: reward = -78.57, steps = 32 17:14:15 [INFO] train episode 24070: reward = -49.91, steps = 35 17:14:19 [INFO] train episode 24071: reward = -60.27, steps = 55 17:14:22 [INFO] train episode 24072: reward = -45.26, steps = 32 17:14:25 [INFO] train episode 24073: reward = -97.86, steps = 27 17:14:27 [INFO] train episode 24074: reward = -45.09, steps = 26 17:14:32 [INFO] train episode 24075: reward = -64.26, steps = 50 17:14:37 [INFO] train episode 24076: reward = -69.79, steps = 55 17:14:40 [INFO] train episode 24077: reward = -78.23, steps = 34 17:14:42 [INFO] train episode 24078: reward = -60.52, steps = 26 17:14:45 [INFO] train episode 24079: reward = -67.82, steps = 37 17:14:49 [INFO] train episode 24080: reward = -35.99, steps = 35 17:14:52 [INFO] train episode 24081: reward = -65.33, steps = 33 17:14:54 [INFO] train episode 24082: reward = -99.01, steps = 31 17:14:59 [INFO] train episode 24083: reward = -69.61, steps = 55 17:15:03 [INFO] train episode 24084: reward = -26.54, steps = 44 17:15:07 [INFO] train episode 24085: reward = -46.24, steps = 41 17:15:10 [INFO] train episode 24086: reward = -68.98, steps = 37 17:15:13 [INFO] train episode 24087: reward = -64.54, steps = 38 17:15:16 [INFO] train episode 24088: reward = -71.43, steps = 33 17:15:19 [INFO] train episode 24089: reward = -70.61, steps = 29 17:15:23 [INFO] train episode 24090: reward = -54.55, steps = 41 17:15:26 [INFO] train episode 24091: reward = -60.07, steps = 34 17:15:29 [INFO] train episode 24092: reward = -85.46, steps = 39 17:15:32 [INFO] train episode 24093: reward = -78.83, steps = 22 17:15:35 [INFO] train episode 24094: reward = -104.48, steps = 39 17:15:38 [INFO] train episode 24095: reward = -60.05, steps = 31 17:15:40 [INFO] train episode 24096: reward = -75.04, steps = 22 17:15:44 [INFO] train episode 24097: reward = -64.73, steps = 42 17:15:46 [INFO] train episode 24098: reward = -42.98, steps = 23 17:15:48 [INFO] train episode 24099: reward = -68.85, steps = 23 17:15:51 [INFO] train episode 24100: reward = -72.35, steps = 29 17:15:53 [INFO] train episode 24101: reward = -67.22, steps = 24 17:15:56 [INFO] train episode 24102: reward = -57.42, steps = 27 17:15:59 [INFO] train episode 24103: reward = -86.94, steps = 37 17:16:01 [INFO] train episode 24104: reward = -50.13, steps = 29 17:16:03 [INFO] train episode 24105: reward = -70.16, steps = 21 17:16:08 [INFO] train episode 24106: reward = -138.35, steps = 59 17:16:12 [INFO] train episode 24107: reward = -86.92, steps = 39 17:16:15 [INFO] train episode 24108: reward = -61.51, steps = 33 17:16:17 [INFO] train episode 24109: reward = -39.49, steps = 26 17:16:21 [INFO] train episode 24110: reward = -68.44, steps = 31 17:16:24 [INFO] train episode 24111: reward = -76.36, steps = 29 17:16:26 [INFO] train episode 24112: reward = -53.12, steps = 29 17:16:31 [INFO] train episode 24113: reward = -122.46, steps = 50 17:16:33 [INFO] train episode 24114: reward = -73.74, steps = 20 17:16:35 [INFO] train episode 24115: reward = -66.26, steps = 23 17:16:38 [INFO] train episode 24116: reward = -48.53, steps = 36 17:16:40 [INFO] train episode 24117: reward = -80.87, steps = 21 17:16:43 [INFO] train episode 24118: reward = -39.84, steps = 36 17:16:46 [INFO] train episode 24119: reward = -54.23, steps = 25 17:16:48 [INFO] train episode 24120: reward = -53.48, steps = 25 17:16:50 [INFO] train episode 24121: reward = -53.99, steps = 28 17:16:52 [INFO] train episode 24122: reward = -70.74, steps = 21 17:16:56 [INFO] train episode 24123: reward = -138.09, steps = 44 17:17:00 [INFO] train episode 24124: reward = -50.33, steps = 38 17:17:05 [INFO] train episode 24125: reward = -122.98, steps = 54 17:17:06 [INFO] train episode 24126: reward = -91.89, steps = 14 17:17:08 [INFO] train episode 24127: reward = -58.29, steps = 28 17:17:12 [INFO] train episode 24128: reward = -117.85, steps = 40 17:17:14 [INFO] train episode 24129: reward = -68.21, steps = 29 17:17:18 [INFO] train episode 24130: reward = -66.33, steps = 39 17:17:22 [INFO] train episode 24131: reward = -98.63, steps = 41 17:17:25 [INFO] train episode 24132: reward = -61.84, steps = 33 17:17:27 [INFO] train episode 24133: reward = -62.58, steps = 21 17:17:29 [INFO] train episode 24134: reward = -102.87, steps = 26 17:17:33 [INFO] train episode 24135: reward = -143.64, steps = 40 17:17:35 [INFO] train episode 24136: reward = -58.00, steps = 23 17:17:37 [INFO] train episode 24137: reward = -74.61, steps = 26 17:17:41 [INFO] train episode 24138: reward = -77.08, steps = 38 17:17:42 [INFO] train episode 24139: reward = -51.05, steps = 21 17:17:45 [INFO] train episode 24140: reward = -44.82, steps = 31 17:17:50 [INFO] train episode 24141: reward = -53.84, steps = 50 17:17:52 [INFO] train episode 24142: reward = -59.08, steps = 22 17:17:54 [INFO] train episode 24143: reward = -71.67, steps = 23 17:17:57 [INFO] train episode 24144: reward = -61.26, steps = 35 17:18:01 [INFO] train episode 24145: reward = -77.57, steps = 41 17:18:05 [INFO] train episode 24146: reward = -127.62, steps = 43 17:18:08 [INFO] train episode 24147: reward = -70.56, steps = 37 17:18:12 [INFO] train episode 24148: reward = -63.94, steps = 41 17:18:14 [INFO] train episode 24149: reward = -79.62, steps = 25 17:18:17 [INFO] train episode 24150: reward = -68.73, steps = 37 17:18:20 [INFO] train episode 24151: reward = -79.71, steps = 33 17:18:23 [INFO] train episode 24152: reward = -87.71, steps = 29 17:18:26 [INFO] train episode 24153: reward = -130.24, steps = 32 17:18:30 [INFO] train episode 24154: reward = -56.50, steps = 42 17:18:33 [INFO] train episode 24155: reward = -51.43, steps = 33 17:18:37 [INFO] train episode 24156: reward = -74.43, steps = 49 17:18:39 [INFO] train episode 24157: reward = -80.17, steps = 18 17:18:41 [INFO] train episode 24158: reward = -66.26, steps = 25 17:18:44 [INFO] train episode 24159: reward = -90.53, steps = 26 17:18:47 [INFO] train episode 24160: reward = -50.30, steps = 40 17:18:50 [INFO] train episode 24161: reward = -50.81, steps = 29 17:18:53 [INFO] train episode 24162: reward = -61.54, steps = 40 17:18:56 [INFO] train episode 24163: reward = -53.41, steps = 26 17:19:00 [INFO] train episode 24164: reward = -82.76, steps = 49 17:19:03 [INFO] train episode 24165: reward = -71.51, steps = 28 17:19:05 [INFO] train episode 24166: reward = -73.86, steps = 19 17:19:07 [INFO] train episode 24167: reward = -52.36, steps = 28 17:19:09 [INFO] train episode 24168: reward = -47.30, steps = 25 17:19:13 [INFO] train episode 24169: reward = -56.22, steps = 32 17:19:15 [INFO] train episode 24170: reward = -75.53, steps = 26 17:19:18 [INFO] train episode 24171: reward = -42.20, steps = 27 17:19:21 [INFO] train episode 24172: reward = -60.64, steps = 31 17:19:24 [INFO] train episode 24173: reward = -84.84, steps = 37 17:19:27 [INFO] train episode 24174: reward = -63.57, steps = 35 17:19:30 [INFO] train episode 24175: reward = -77.62, steps = 27 17:19:33 [INFO] train episode 24176: reward = -108.83, steps = 34 17:19:38 [INFO] train episode 24177: reward = -62.54, steps = 54 17:19:41 [INFO] train episode 24178: reward = -49.93, steps = 37 17:19:43 [INFO] train episode 24179: reward = -91.82, steps = 29 17:19:46 [INFO] train episode 24180: reward = -28.95, steps = 21 17:19:49 [INFO] train episode 24181: reward = -78.54, steps = 42 17:19:53 [INFO] train episode 24182: reward = -54.65, steps = 45 17:19:55 [INFO] train episode 24183: reward = -59.81, steps = 23 17:19:58 [INFO] train episode 24184: reward = -71.51, steps = 34 17:19:59 [INFO] train episode 24185: reward = -63.15, steps = 12 17:20:03 [INFO] train episode 24186: reward = -123.44, steps = 39 17:20:06 [INFO] train episode 24187: reward = -36.00, steps = 31 17:20:09 [INFO] train episode 24188: reward = -70.76, steps = 38 17:20:12 [INFO] train episode 24189: reward = -39.98, steps = 31 17:20:14 [INFO] train episode 24190: reward = -69.68, steps = 28 17:20:18 [INFO] train episode 24191: reward = -48.57, steps = 31 17:20:21 [INFO] train episode 24192: reward = -61.10, steps = 38 17:20:24 [INFO] train episode 24193: reward = -55.14, steps = 34 17:20:28 [INFO] train episode 24194: reward = -68.29, steps = 46 17:20:31 [INFO] train episode 24195: reward = -48.46, steps = 39 17:20:34 [INFO] train episode 24196: reward = -86.07, steps = 29 17:20:37 [INFO] train episode 24197: reward = -60.83, steps = 35 17:20:41 [INFO] train episode 24198: reward = -48.97, steps = 37 17:20:43 [INFO] train episode 24199: reward = -96.47, steps = 28 17:20:47 [INFO] train episode 24200: reward = -78.04, steps = 44 17:20:49 [INFO] train episode 24201: reward = -99.70, steps = 22 17:20:53 [INFO] train episode 24202: reward = -59.18, steps = 37 17:20:56 [INFO] train episode 24203: reward = -69.12, steps = 26 17:20:59 [INFO] train episode 24204: reward = -82.59, steps = 39 17:21:03 [INFO] train episode 24205: reward = -86.84, steps = 32 17:21:07 [INFO] train episode 24206: reward = -40.38, steps = 44 17:21:10 [INFO] train episode 24207: reward = -54.89, steps = 31 17:21:14 [INFO] train episode 24208: reward = -112.78, steps = 41 17:21:16 [INFO] train episode 24209: reward = -51.88, steps = 24 17:21:19 [INFO] train episode 24210: reward = -74.01, steps = 35 17:21:27 [INFO] train episode 24211: reward = -95.93, steps = 86 17:21:29 [INFO] train episode 24212: reward = -70.28, steps = 20 17:21:31 [INFO] train episode 24213: reward = -65.30, steps = 20 17:21:34 [INFO] train episode 24214: reward = -35.30, steps = 39 17:21:37 [INFO] train episode 24215: reward = -72.67, steps = 36 17:21:40 [INFO] train episode 24216: reward = -54.46, steps = 24 17:21:43 [INFO] train episode 24217: reward = -42.82, steps = 31 17:21:45 [INFO] train episode 24218: reward = -52.88, steps = 22 17:21:49 [INFO] train episode 24219: reward = -63.73, steps = 55 17:21:52 [INFO] train episode 24220: reward = -64.07, steps = 24 17:21:56 [INFO] train episode 24221: reward = -85.78, steps = 53 17:21:59 [INFO] train episode 24222: reward = -42.85, steps = 30 17:22:02 [INFO] train episode 24223: reward = -65.59, steps = 28 17:22:04 [INFO] train episode 24224: reward = -102.98, steps = 21 17:22:07 [INFO] train episode 24225: reward = -45.00, steps = 38 17:22:10 [INFO] train episode 24226: reward = -51.00, steps = 37 17:22:12 [INFO] train episode 24227: reward = -66.07, steps = 28 17:22:17 [INFO] train episode 24228: reward = -81.37, steps = 37 17:22:21 [INFO] train episode 24229: reward = -107.06, steps = 43 17:22:22 [INFO] train episode 24230: reward = -46.54, steps = 22 17:22:27 [INFO] train episode 24231: reward = -91.64, steps = 58 17:22:33 [INFO] train episode 24232: reward = -95.51, steps = 57 17:22:35 [INFO] train episode 24233: reward = -56.14, steps = 23 17:22:38 [INFO] train episode 24234: reward = -51.33, steps = 34 17:22:40 [INFO] train episode 24235: reward = -60.93, steps = 21 17:22:42 [INFO] train episode 24236: reward = -67.16, steps = 31 17:22:47 [INFO] train episode 24237: reward = -123.49, steps = 56 17:22:51 [INFO] train episode 24238: reward = -82.03, steps = 38 17:22:52 [INFO] train episode 24239: reward = -74.18, steps = 20 17:22:54 [INFO] train episode 24240: reward = -46.19, steps = 23 17:22:58 [INFO] train episode 24241: reward = -80.66, steps = 40 17:23:01 [INFO] train episode 24242: reward = -56.57, steps = 30 17:23:04 [INFO] train episode 24243: reward = -54.13, steps = 38 17:23:06 [INFO] train episode 24244: reward = -61.61, steps = 22 17:23:08 [INFO] train episode 24245: reward = -63.18, steps = 23 17:23:10 [INFO] train episode 24246: reward = -45.53, steps = 21 17:23:12 [INFO] train episode 24247: reward = -50.96, steps = 27 17:23:15 [INFO] train episode 24248: reward = -23.83, steps = 34 17:23:19 [INFO] train episode 24249: reward = -42.35, steps = 39 17:23:21 [INFO] train episode 24250: reward = -33.48, steps = 24 17:23:25 [INFO] train episode 24251: reward = -107.24, steps = 52 17:23:30 [INFO] train episode 24252: reward = -85.79, steps = 57 17:23:33 [INFO] train episode 24253: reward = -71.51, steps = 25 17:23:34 [INFO] train episode 24254: reward = -76.94, steps = 19 17:23:39 [INFO] train episode 24255: reward = -62.83, steps = 45 17:23:42 [INFO] train episode 24256: reward = -77.17, steps = 39 17:23:45 [INFO] train episode 24257: reward = -58.55, steps = 31 17:23:49 [INFO] train episode 24258: reward = -82.41, steps = 57 17:23:53 [INFO] train episode 24259: reward = -95.76, steps = 39 17:23:55 [INFO] train episode 24260: reward = -74.68, steps = 26 17:23:59 [INFO] train episode 24261: reward = -59.89, steps = 36 17:24:02 [INFO] train episode 24262: reward = -64.41, steps = 41 17:24:06 [INFO] train episode 24263: reward = -48.36, steps = 41 17:24:09 [INFO] train episode 24264: reward = -98.61, steps = 35 17:24:12 [INFO] train episode 24265: reward = -83.38, steps = 36 17:24:15 [INFO] train episode 24266: reward = -60.24, steps = 37 17:24:18 [INFO] train episode 24267: reward = -63.12, steps = 27 17:24:21 [INFO] train episode 24268: reward = -73.70, steps = 30 17:24:25 [INFO] train episode 24269: reward = -98.90, steps = 56 17:24:28 [INFO] train episode 24270: reward = -40.95, steps = 21 17:24:31 [INFO] train episode 24271: reward = -74.29, steps = 37 17:24:34 [INFO] train episode 24272: reward = -68.56, steps = 34 17:24:37 [INFO] train episode 24273: reward = -68.16, steps = 33 17:24:41 [INFO] train episode 24274: reward = -105.91, steps = 45 17:24:44 [INFO] train episode 24275: reward = -57.12, steps = 35 17:24:47 [INFO] train episode 24276: reward = -72.82, steps = 32 17:24:49 [INFO] train episode 24277: reward = -60.20, steps = 27 17:24:53 [INFO] train episode 24278: reward = -82.21, steps = 39 17:24:54 [INFO] train episode 24279: reward = -54.47, steps = 20 17:24:57 [INFO] train episode 24280: reward = -82.27, steps = 34 17:25:01 [INFO] train episode 24281: reward = -49.87, steps = 36 17:25:04 [INFO] train episode 24282: reward = -43.64, steps = 41 17:25:07 [INFO] train episode 24283: reward = -71.20, steps = 24 17:25:11 [INFO] train episode 24284: reward = -38.03, steps = 41 17:25:13 [INFO] train episode 24285: reward = -73.25, steps = 19 17:25:16 [INFO] train episode 24286: reward = -47.69, steps = 35 17:25:21 [INFO] train episode 24287: reward = -83.71, steps = 59 17:25:23 [INFO] train episode 24288: reward = -51.04, steps = 24 17:25:25 [INFO] train episode 24289: reward = -88.15, steps = 21 17:25:29 [INFO] train episode 24290: reward = -71.17, steps = 41 17:25:33 [INFO] train episode 24291: reward = -75.64, steps = 44 17:25:37 [INFO] train episode 24292: reward = -75.08, steps = 52 17:25:42 [INFO] train episode 24293: reward = -123.74, steps = 53 17:25:44 [INFO] train episode 24294: reward = -62.98, steps = 31 17:25:49 [INFO] train episode 24295: reward = -44.92, steps = 46 17:25:52 [INFO] train episode 24296: reward = -63.92, steps = 42 17:25:56 [INFO] train episode 24297: reward = -77.04, steps = 46 17:25:59 [INFO] train episode 24298: reward = -60.51, steps = 33 17:26:02 [INFO] train episode 24299: reward = -95.61, steps = 29 17:26:05 [INFO] train episode 24300: reward = -41.99, steps = 34 17:26:09 [INFO] train episode 24301: reward = -66.85, steps = 44 17:26:12 [INFO] train episode 24302: reward = -67.64, steps = 35 17:26:15 [INFO] train episode 24303: reward = -60.78, steps = 37 17:26:18 [INFO] train episode 24304: reward = -61.37, steps = 32 17:26:20 [INFO] train episode 24305: reward = -55.92, steps = 25 17:26:23 [INFO] train episode 24306: reward = -40.27, steps = 24 17:26:25 [INFO] train episode 24307: reward = -60.20, steps = 32 17:26:28 [INFO] train episode 24308: reward = -139.42, steps = 34 17:26:30 [INFO] train episode 24309: reward = -75.92, steps = 21 17:26:34 [INFO] train episode 24310: reward = -61.31, steps = 47 17:26:38 [INFO] train episode 24311: reward = -38.30, steps = 38 17:26:40 [INFO] train episode 24312: reward = -76.88, steps = 27 17:26:43 [INFO] train episode 24313: reward = -83.97, steps = 34 17:26:48 [INFO] train episode 24314: reward = -66.80, steps = 49 17:26:50 [INFO] train episode 24315: reward = -53.31, steps = 23 17:26:53 [INFO] train episode 24316: reward = -61.70, steps = 28 17:26:56 [INFO] train episode 24317: reward = -39.79, steps = 37 17:26:58 [INFO] train episode 24318: reward = -53.62, steps = 30 17:27:02 [INFO] train episode 24319: reward = -101.31, steps = 42 17:27:07 [INFO] train episode 24320: reward = -82.88, steps = 50 17:27:09 [INFO] train episode 24321: reward = -49.40, steps = 21 17:27:12 [INFO] train episode 24322: reward = -68.47, steps = 31 17:27:15 [INFO] train episode 24323: reward = -62.24, steps = 41 17:27:18 [INFO] train episode 24324: reward = -76.65, steps = 33 17:27:20 [INFO] train episode 24325: reward = -83.02, steps = 19 17:27:22 [INFO] train episode 24326: reward = -50.33, steps = 21 17:27:27 [INFO] train episode 24327: reward = -192.79, steps = 53 17:27:29 [INFO] train episode 24328: reward = -59.13, steps = 19 17:27:31 [INFO] train episode 24329: reward = -45.09, steps = 26 17:27:33 [INFO] train episode 24330: reward = -62.03, steps = 26 17:27:35 [INFO] train episode 24331: reward = -51.02, steps = 25 17:27:38 [INFO] train episode 24332: reward = -54.53, steps = 27 17:27:41 [INFO] train episode 24333: reward = -64.12, steps = 35 17:27:44 [INFO] train episode 24334: reward = -58.20, steps = 36 17:27:46 [INFO] train episode 24335: reward = -56.78, steps = 20 17:27:50 [INFO] train episode 24336: reward = -64.16, steps = 41 17:27:51 [INFO] train episode 24337: reward = -67.12, steps = 19 17:27:54 [INFO] train episode 24338: reward = -58.63, steps = 31 17:27:57 [INFO] train episode 24339: reward = -57.07, steps = 33 17:27:59 [INFO] train episode 24340: reward = -57.19, steps = 21 17:28:03 [INFO] train episode 24341: reward = -105.10, steps = 48 17:28:07 [INFO] train episode 24342: reward = -90.36, steps = 33 17:28:12 [INFO] train episode 24343: reward = -101.92, steps = 65 17:28:16 [INFO] train episode 24344: reward = -55.20, steps = 37 17:28:18 [INFO] train episode 24345: reward = -129.09, steps = 20 17:28:22 [INFO] train episode 24346: reward = -52.96, steps = 44 17:28:24 [INFO] train episode 24347: reward = -80.40, steps = 29 17:28:27 [INFO] train episode 24348: reward = -80.04, steps = 29 17:28:29 [INFO] train episode 24349: reward = -85.13, steps = 24 17:28:33 [INFO] train episode 24350: reward = -80.81, steps = 45 17:28:37 [INFO] train episode 24351: reward = -75.31, steps = 43 17:28:41 [INFO] train episode 24352: reward = -91.02, steps = 44 17:28:43 [INFO] train episode 24353: reward = -93.12, steps = 24 17:28:47 [INFO] train episode 24354: reward = -78.69, steps = 55 17:28:50 [INFO] train episode 24355: reward = -65.59, steps = 28 17:28:55 [INFO] train episode 24356: reward = -90.25, steps = 51 17:28:56 [INFO] train episode 24357: reward = -86.06, steps = 20 17:29:00 [INFO] train episode 24358: reward = -111.31, steps = 49 17:29:03 [INFO] train episode 24359: reward = -73.12, steps = 22 17:29:09 [INFO] train episode 24360: reward = -146.92, steps = 61 17:29:11 [INFO] train episode 24361: reward = -76.67, steps = 27 17:29:14 [INFO] train episode 24362: reward = -73.27, steps = 30 17:29:17 [INFO] train episode 24363: reward = -70.49, steps = 37 17:29:21 [INFO] train episode 24364: reward = -62.18, steps = 46 17:29:24 [INFO] train episode 24365: reward = -82.05, steps = 35 17:29:27 [INFO] train episode 24366: reward = -83.74, steps = 23 17:29:29 [INFO] train episode 24367: reward = -46.63, steps = 25 17:29:33 [INFO] train episode 24368: reward = -62.81, steps = 47 17:29:35 [INFO] train episode 24369: reward = -83.94, steps = 24 17:29:39 [INFO] train episode 24370: reward = -84.37, steps = 38 17:29:41 [INFO] train episode 24371: reward = -48.10, steps = 24 17:29:44 [INFO] train episode 24372: reward = -77.07, steps = 37 17:29:46 [INFO] train episode 24373: reward = -57.71, steps = 26 17:29:48 [INFO] train episode 24374: reward = -48.13, steps = 25 17:29:50 [INFO] train episode 24375: reward = -53.13, steps = 23 17:29:54 [INFO] train episode 24376: reward = -92.35, steps = 41 17:29:57 [INFO] train episode 24377: reward = -69.51, steps = 33 17:30:01 [INFO] train episode 24378: reward = -57.96, steps = 43 17:30:05 [INFO] train episode 24379: reward = -66.86, steps = 42 17:30:08 [INFO] train episode 24380: reward = -98.25, steps = 45 17:30:12 [INFO] train episode 24381: reward = -72.46, steps = 33 17:30:15 [INFO] train episode 24382: reward = -42.24, steps = 38 17:30:18 [INFO] train episode 24383: reward = -69.13, steps = 34 17:30:20 [INFO] train episode 24384: reward = -58.00, steps = 23 17:30:23 [INFO] train episode 24385: reward = -103.08, steps = 40 17:30:27 [INFO] train episode 24386: reward = -87.28, steps = 30 17:30:29 [INFO] train episode 24387: reward = -47.29, steps = 28 17:30:32 [INFO] train episode 24388: reward = -66.00, steps = 40 17:30:34 [INFO] train episode 24389: reward = -56.49, steps = 22 17:30:38 [INFO] train episode 24390: reward = -70.57, steps = 36 17:30:42 [INFO] train episode 24391: reward = -63.39, steps = 47 17:30:47 [INFO] train episode 24392: reward = -80.89, steps = 58 17:30:50 [INFO] train episode 24393: reward = -64.08, steps = 28 17:30:53 [INFO] train episode 24394: reward = -56.81, steps = 32 17:30:56 [INFO] train episode 24395: reward = -62.89, steps = 37 17:31:00 [INFO] train episode 24396: reward = -51.61, steps = 47 17:31:06 [INFO] train episode 24397: reward = -72.89, steps = 53 17:31:08 [INFO] train episode 24398: reward = -52.04, steps = 21 17:31:11 [INFO] train episode 24399: reward = -58.35, steps = 42 17:31:14 [INFO] train episode 24400: reward = -64.30, steps = 26 17:31:18 [INFO] train episode 24401: reward = -127.43, steps = 40 17:31:21 [INFO] train episode 24402: reward = -60.58, steps = 41 17:31:23 [INFO] train episode 24403: reward = -71.13, steps = 21 17:31:26 [INFO] train episode 24404: reward = -70.91, steps = 36 17:31:30 [INFO] train episode 24405: reward = -113.66, steps = 42 17:31:33 [INFO] train episode 24406: reward = -59.68, steps = 31 17:31:35 [INFO] train episode 24407: reward = -57.69, steps = 19 17:31:38 [INFO] train episode 24408: reward = -53.37, steps = 36 17:31:41 [INFO] train episode 24409: reward = -73.56, steps = 27 17:31:43 [INFO] train episode 24410: reward = -68.96, steps = 30 17:31:47 [INFO] train episode 24411: reward = -83.44, steps = 44 17:31:51 [INFO] train episode 24412: reward = -84.95, steps = 33 17:31:54 [INFO] train episode 24413: reward = -58.47, steps = 34 17:31:56 [INFO] train episode 24414: reward = -46.87, steps = 32 17:32:00 [INFO] train episode 24415: reward = -112.52, steps = 41 17:32:02 [INFO] train episode 24416: reward = -59.86, steps = 22 17:32:05 [INFO] train episode 24417: reward = -83.73, steps = 33 17:32:09 [INFO] train episode 24418: reward = -36.15, steps = 36 17:32:12 [INFO] train episode 24419: reward = -98.42, steps = 39 17:32:15 [INFO] train episode 24420: reward = -72.82, steps = 36 17:32:17 [INFO] train episode 24421: reward = -67.82, steps = 22 17:32:20 [INFO] train episode 24422: reward = -47.78, steps = 34 17:32:23 [INFO] train episode 24423: reward = -49.89, steps = 24 17:32:25 [INFO] train episode 24424: reward = -52.29, steps = 24 17:32:27 [INFO] train episode 24425: reward = -88.33, steps = 19 17:32:31 [INFO] train episode 24426: reward = -76.43, steps = 56 17:32:34 [INFO] train episode 24427: reward = -56.07, steps = 27 17:32:36 [INFO] train episode 24428: reward = -60.64, steps = 28 17:32:38 [INFO] train episode 24429: reward = -87.72, steps = 22 17:32:44 [INFO] train episode 24430: reward = -79.69, steps = 57 17:32:46 [INFO] train episode 24431: reward = -67.47, steps = 30 17:32:51 [INFO] train episode 24432: reward = -83.13, steps = 54 17:32:55 [INFO] train episode 24433: reward = -45.36, steps = 40 17:32:59 [INFO] train episode 24434: reward = -42.50, steps = 38 17:33:03 [INFO] train episode 24435: reward = -85.46, steps = 45 17:33:07 [INFO] train episode 24436: reward = -53.83, steps = 37 17:33:10 [INFO] train episode 24437: reward = -55.65, steps = 41 17:33:13 [INFO] train episode 24438: reward = -70.69, steps = 38 17:33:15 [INFO] train episode 24439: reward = -78.59, steps = 18 17:33:18 [INFO] train episode 24440: reward = -78.20, steps = 33 17:33:22 [INFO] train episode 24441: reward = -70.95, steps = 38 17:33:24 [INFO] train episode 24442: reward = -77.93, steps = 33 17:33:29 [INFO] train episode 24443: reward = -71.98, steps = 52 17:33:33 [INFO] train episode 24444: reward = -66.22, steps = 39 17:33:35 [INFO] train episode 24445: reward = -81.52, steps = 28 17:33:38 [INFO] train episode 24446: reward = -58.89, steps = 30 17:33:42 [INFO] train episode 24447: reward = -95.11, steps = 41 17:33:47 [INFO] train episode 24448: reward = -106.42, steps = 59 17:33:50 [INFO] train episode 24449: reward = -64.78, steps = 27 17:33:52 [INFO] train episode 24450: reward = -118.20, steps = 26 17:33:54 [INFO] train episode 24451: reward = -46.19, steps = 24 17:33:57 [INFO] train episode 24452: reward = -86.05, steps = 36 17:34:01 [INFO] train episode 24453: reward = -88.96, steps = 35 17:34:06 [INFO] train episode 24454: reward = -88.07, steps = 47 17:34:10 [INFO] train episode 24455: reward = -64.38, steps = 44 17:34:13 [INFO] train episode 24456: reward = -92.41, steps = 34 17:34:18 [INFO] train episode 24457: reward = -77.20, steps = 55 17:34:22 [INFO] train episode 24458: reward = -39.31, steps = 43 17:34:25 [INFO] train episode 24459: reward = -37.93, steps = 27 17:34:27 [INFO] train episode 24460: reward = -66.40, steps = 25 17:34:31 [INFO] train episode 24461: reward = -54.92, steps = 44 17:34:34 [INFO] train episode 24462: reward = -117.83, steps = 35 17:34:38 [INFO] train episode 24463: reward = -82.45, steps = 45 17:34:40 [INFO] train episode 24464: reward = -63.38, steps = 27 17:34:45 [INFO] train episode 24465: reward = -60.74, steps = 50 17:34:48 [INFO] train episode 24466: reward = -51.56, steps = 34 17:34:50 [INFO] train episode 24467: reward = -50.98, steps = 31 17:34:54 [INFO] train episode 24468: reward = -106.71, steps = 43 17:34:57 [INFO] train episode 24469: reward = -51.62, steps = 29 17:35:01 [INFO] train episode 24470: reward = -92.90, steps = 45 17:35:06 [INFO] train episode 24471: reward = -91.00, steps = 58 17:35:10 [INFO] train episode 24472: reward = -79.65, steps = 42 17:35:13 [INFO] train episode 24473: reward = -54.17, steps = 33 17:35:16 [INFO] train episode 24474: reward = -66.31, steps = 36 17:35:20 [INFO] train episode 24475: reward = -117.25, steps = 51 17:35:23 [INFO] train episode 24476: reward = -83.90, steps = 31 17:35:25 [INFO] train episode 24477: reward = -83.92, steps = 24 17:35:29 [INFO] train episode 24478: reward = -71.30, steps = 35 17:35:31 [INFO] train episode 24479: reward = -72.91, steps = 23 17:35:33 [INFO] train episode 24480: reward = -64.11, steps = 25 17:35:39 [INFO] train episode 24481: reward = -132.69, steps = 71 17:35:43 [INFO] train episode 24482: reward = -69.33, steps = 48 17:35:46 [INFO] train episode 24483: reward = -65.09, steps = 34 17:35:48 [INFO] train episode 24484: reward = -77.84, steps = 25 17:35:51 [INFO] train episode 24485: reward = -91.98, steps = 34 17:35:55 [INFO] train episode 24486: reward = -102.49, steps = 42 17:35:58 [INFO] train episode 24487: reward = -56.38, steps = 34 17:36:00 [INFO] train episode 24488: reward = -69.55, steps = 22 17:36:03 [INFO] train episode 24489: reward = -77.31, steps = 29 17:36:06 [INFO] train episode 24490: reward = -53.40, steps = 35 17:36:08 [INFO] train episode 24491: reward = -50.90, steps = 29 17:36:11 [INFO] train episode 24492: reward = -49.88, steps = 35 17:36:13 [INFO] train episode 24493: reward = -53.17, steps = 23 17:36:16 [INFO] train episode 24494: reward = -59.81, steps = 25 17:36:19 [INFO] train episode 24495: reward = -89.48, steps = 32 17:36:22 [INFO] train episode 24496: reward = -66.04, steps = 31 17:36:24 [INFO] train episode 24497: reward = -56.73, steps = 32 17:36:28 [INFO] train episode 24498: reward = -75.10, steps = 34 17:36:30 [INFO] train episode 24499: reward = -61.46, steps = 33 17:36:34 [INFO] train episode 24500: reward = -83.98, steps = 30 17:36:40 [INFO] train episode 24501: reward = -173.79, steps = 70 17:36:44 [INFO] train episode 24502: reward = -60.83, steps = 45 17:36:47 [INFO] train episode 24503: reward = -71.20, steps = 40 17:36:52 [INFO] train episode 24504: reward = -73.41, steps = 46 17:36:57 [INFO] train episode 24505: reward = -77.68, steps = 57 17:37:02 [INFO] train episode 24506: reward = -95.05, steps = 54 17:37:07 [INFO] train episode 24507: reward = -96.35, steps = 53 17:37:11 [INFO] train episode 24508: reward = -83.74, steps = 38 17:37:14 [INFO] train episode 24509: reward = -62.29, steps = 35 17:37:17 [INFO] train episode 24510: reward = -70.14, steps = 38 17:37:21 [INFO] train episode 24511: reward = -40.68, steps = 40 17:37:24 [INFO] train episode 24512: reward = -55.04, steps = 33 17:37:27 [INFO] train episode 24513: reward = -65.96, steps = 32 17:37:31 [INFO] train episode 24514: reward = -97.25, steps = 40 17:37:33 [INFO] train episode 24515: reward = -52.60, steps = 25 17:37:36 [INFO] train episode 24516: reward = -62.32, steps = 33 17:37:42 [INFO] train episode 24517: reward = -151.59, steps = 67 17:37:45 [INFO] train episode 24518: reward = -31.84, steps = 33 17:37:47 [INFO] train episode 24519: reward = -58.36, steps = 21 17:37:51 [INFO] train episode 24520: reward = -152.46, steps = 45 17:37:54 [INFO] train episode 24521: reward = -71.75, steps = 38 17:37:57 [INFO] train episode 24522: reward = -57.47, steps = 35 17:38:00 [INFO] train episode 24523: reward = -62.62, steps = 27 17:38:02 [INFO] train episode 24524: reward = -112.48, steps = 22 17:38:07 [INFO] train episode 24525: reward = -77.81, steps = 64 17:38:10 [INFO] train episode 24526: reward = -69.20, steps = 28 17:38:12 [INFO] train episode 24527: reward = -71.75, steps = 28 17:38:15 [INFO] train episode 24528: reward = -69.20, steps = 32 17:38:19 [INFO] train episode 24529: reward = -47.66, steps = 39 17:38:22 [INFO] train episode 24530: reward = -86.64, steps = 44 17:38:25 [INFO] train episode 24531: reward = -61.97, steps = 27 17:38:28 [INFO] train episode 24532: reward = -83.03, steps = 35 17:38:31 [INFO] train episode 24533: reward = -63.62, steps = 38 17:38:35 [INFO] train episode 24534: reward = -99.77, steps = 37 17:38:39 [INFO] train episode 24535: reward = -67.88, steps = 46 17:38:40 [INFO] train episode 24536: reward = -60.81, steps = 18 17:38:46 [INFO] train episode 24537: reward = -80.45, steps = 59 17:38:49 [INFO] train episode 24538: reward = -48.46, steps = 37 17:38:52 [INFO] train episode 24539: reward = -44.34, steps = 34 17:38:55 [INFO] train episode 24540: reward = -52.12, steps = 33 17:38:59 [INFO] train episode 24541: reward = -120.38, steps = 47 17:39:01 [INFO] train episode 24542: reward = -67.70, steps = 22 17:39:04 [INFO] train episode 24543: reward = -85.72, steps = 30 17:39:06 [INFO] train episode 24544: reward = -121.41, steps = 27 17:39:10 [INFO] train episode 24545: reward = -98.77, steps = 45 17:39:13 [INFO] train episode 24546: reward = -83.30, steps = 29 17:39:18 [INFO] train episode 24547: reward = -89.08, steps = 51 17:39:21 [INFO] train episode 24548: reward = -101.85, steps = 36 17:39:23 [INFO] train episode 24549: reward = -65.59, steps = 18 17:39:25 [INFO] train episode 24550: reward = -66.77, steps = 30 17:39:30 [INFO] train episode 24551: reward = -83.86, steps = 49 17:39:33 [INFO] train episode 24552: reward = -72.75, steps = 35 17:39:36 [INFO] train episode 24553: reward = -71.24, steps = 29 17:39:40 [INFO] train episode 24554: reward = -56.45, steps = 50 17:39:42 [INFO] train episode 24555: reward = -66.74, steps = 28 17:39:45 [INFO] train episode 24556: reward = -87.69, steps = 30 17:39:48 [INFO] train episode 24557: reward = -73.64, steps = 34 17:39:50 [INFO] train episode 24558: reward = -57.39, steps = 23 17:39:54 [INFO] train episode 24559: reward = -75.30, steps = 38 17:39:59 [INFO] train episode 24560: reward = -70.34, steps = 56 17:40:01 [INFO] train episode 24561: reward = -98.99, steps = 21 17:40:03 [INFO] train episode 24562: reward = -48.80, steps = 27 17:40:07 [INFO] train episode 24563: reward = -76.17, steps = 42 17:40:12 [INFO] train episode 24564: reward = -107.71, steps = 52 17:40:14 [INFO] train episode 24565: reward = -58.82, steps = 27 17:40:18 [INFO] train episode 24566: reward = -82.51, steps = 43 17:40:23 [INFO] train episode 24567: reward = -97.64, steps = 52 17:40:25 [INFO] train episode 24568: reward = -64.57, steps = 19 17:40:27 [INFO] train episode 24569: reward = -81.14, steps = 32 17:40:31 [INFO] train episode 24570: reward = -71.98, steps = 36 17:40:32 [INFO] train episode 24571: reward = -53.41, steps = 18 17:40:35 [INFO] train episode 24572: reward = -59.95, steps = 29 17:40:39 [INFO] train episode 24573: reward = -54.67, steps = 40 17:40:40 [INFO] train episode 24574: reward = -88.61, steps = 19 17:40:42 [INFO] train episode 24575: reward = -83.08, steps = 25 17:40:47 [INFO] train episode 24576: reward = -85.92, steps = 49 17:40:49 [INFO] train episode 24577: reward = -66.32, steps = 20 17:40:53 [INFO] train episode 24578: reward = -68.92, steps = 46 17:40:56 [INFO] train episode 24579: reward = -47.74, steps = 31 17:40:59 [INFO] train episode 24580: reward = -47.54, steps = 36 17:41:02 [INFO] train episode 24581: reward = -88.15, steps = 36 17:41:05 [INFO] train episode 24582: reward = -36.59, steps = 35 17:41:08 [INFO] train episode 24583: reward = -76.90, steps = 29 17:41:10 [INFO] train episode 24584: reward = -73.35, steps = 25 17:41:13 [INFO] train episode 24585: reward = -78.19, steps = 29 17:41:16 [INFO] train episode 24586: reward = -76.22, steps = 38 17:41:18 [INFO] train episode 24587: reward = -53.84, steps = 27 17:41:21 [INFO] train episode 24588: reward = -44.94, steps = 32 17:41:23 [INFO] train episode 24589: reward = -82.29, steps = 26 17:41:26 [INFO] train episode 24590: reward = -55.49, steps = 35 17:41:31 [INFO] train episode 24591: reward = -94.49, steps = 47 17:41:35 [INFO] train episode 24592: reward = -115.25, steps = 35 17:41:37 [INFO] train episode 24593: reward = -52.36, steps = 24 17:41:41 [INFO] train episode 24594: reward = -65.63, steps = 39 17:41:44 [INFO] train episode 24595: reward = -91.98, steps = 31 17:41:48 [INFO] train episode 24596: reward = -56.51, steps = 42 17:41:52 [INFO] train episode 24597: reward = -65.44, steps = 38 17:41:57 [INFO] train episode 24598: reward = -119.84, steps = 48 17:41:58 [INFO] train episode 24599: reward = -82.57, steps = 20 17:42:01 [INFO] train episode 24600: reward = -56.13, steps = 24 17:42:04 [INFO] train episode 24601: reward = -54.70, steps = 30 17:42:08 [INFO] train episode 24602: reward = -53.85, steps = 39 17:42:12 [INFO] train episode 24603: reward = -52.82, steps = 40 17:42:17 [INFO] train episode 24604: reward = -78.23, steps = 58 17:42:24 [INFO] train episode 24605: reward = -125.47, steps = 73 17:42:27 [INFO] train episode 24606: reward = -49.41, steps = 23 17:42:30 [INFO] train episode 24607: reward = -60.97, steps = 36 17:42:34 [INFO] train episode 24608: reward = -56.27, steps = 37 17:42:36 [INFO] train episode 24609: reward = -43.39, steps = 23 17:42:38 [INFO] train episode 24610: reward = -46.56, steps = 21 17:42:42 [INFO] train episode 24611: reward = -80.40, steps = 28 17:42:44 [INFO] train episode 24612: reward = -42.14, steps = 26 17:42:49 [INFO] train episode 24613: reward = -94.61, steps = 45 17:42:53 [INFO] train episode 24614: reward = -75.44, steps = 48 17:42:56 [INFO] train episode 24615: reward = -81.94, steps = 31 17:43:01 [INFO] train episode 24616: reward = -87.83, steps = 48 17:43:04 [INFO] train episode 24617: reward = -62.92, steps = 18 17:43:06 [INFO] train episode 24618: reward = -58.77, steps = 29 17:43:09 [INFO] train episode 24619: reward = -52.71, steps = 33 17:43:12 [INFO] train episode 24620: reward = -70.30, steps = 35 17:43:15 [INFO] train episode 24621: reward = -32.65, steps = 32 17:43:20 [INFO] train episode 24622: reward = -96.60, steps = 50 17:43:22 [INFO] train episode 24623: reward = -50.81, steps = 25 17:43:27 [INFO] train episode 24624: reward = -108.05, steps = 60 17:43:30 [INFO] train episode 24625: reward = -89.62, steps = 38 17:43:32 [INFO] train episode 24626: reward = -68.80, steps = 19 17:43:36 [INFO] train episode 24627: reward = -123.22, steps = 47 17:43:38 [INFO] train episode 24628: reward = -71.99, steps = 23 17:43:41 [INFO] train episode 24629: reward = -79.16, steps = 27 17:43:45 [INFO] train episode 24630: reward = -72.81, steps = 47 17:43:48 [INFO] train episode 24631: reward = -46.25, steps = 31 17:43:51 [INFO] train episode 24632: reward = -53.95, steps = 37 17:43:53 [INFO] train episode 24633: reward = -75.64, steps = 29 17:43:57 [INFO] train episode 24634: reward = -94.25, steps = 38 17:44:00 [INFO] train episode 24635: reward = -95.70, steps = 36 17:44:07 [INFO] train episode 24636: reward = -90.91, steps = 75 17:44:12 [INFO] train episode 24637: reward = -129.38, steps = 58 17:44:17 [INFO] train episode 24638: reward = -123.82, steps = 67 17:44:21 [INFO] train episode 24639: reward = -53.43, steps = 43 17:44:23 [INFO] train episode 24640: reward = -62.21, steps = 23 17:44:25 [INFO] train episode 24641: reward = -54.19, steps = 25 17:44:30 [INFO] train episode 24642: reward = -101.59, steps = 55 17:44:34 [INFO] train episode 24643: reward = -76.04, steps = 46 17:44:39 [INFO] train episode 24644: reward = -125.68, steps = 50 17:44:42 [INFO] train episode 24645: reward = -64.87, steps = 33 17:44:46 [INFO] train episode 24646: reward = -68.32, steps = 50 17:44:48 [INFO] train episode 24647: reward = -37.81, steps = 24 17:44:51 [INFO] train episode 24648: reward = -50.07, steps = 37 17:44:56 [INFO] train episode 24649: reward = -124.07, steps = 51 17:45:00 [INFO] train episode 24650: reward = -77.19, steps = 44 17:45:03 [INFO] train episode 24651: reward = -51.00, steps = 42 17:45:07 [INFO] train episode 24652: reward = -61.28, steps = 43 17:45:10 [INFO] train episode 24653: reward = -69.05, steps = 27 17:45:13 [INFO] train episode 24654: reward = -84.82, steps = 34 17:45:15 [INFO] train episode 24655: reward = -42.29, steps = 30 17:45:20 [INFO] train episode 24656: reward = -102.41, steps = 52 17:45:26 [INFO] train episode 24657: reward = -101.43, steps = 71 17:45:28 [INFO] train episode 24658: reward = -52.31, steps = 21 17:45:30 [INFO] train episode 24659: reward = -67.81, steps = 25 17:45:34 [INFO] train episode 24660: reward = -91.86, steps = 43 17:45:37 [INFO] train episode 24661: reward = -115.11, steps = 31 17:45:39 [INFO] train episode 24662: reward = -82.94, steps = 25 17:45:42 [INFO] train episode 24663: reward = -72.13, steps = 36 17:45:46 [INFO] train episode 24664: reward = -80.24, steps = 40 17:45:49 [INFO] train episode 24665: reward = -80.71, steps = 40 17:45:52 [INFO] train episode 24666: reward = -56.02, steps = 33 17:45:54 [INFO] train episode 24667: reward = -63.26, steps = 26 17:45:59 [INFO] train episode 24668: reward = -56.57, steps = 44 17:46:01 [INFO] train episode 24669: reward = -67.28, steps = 23 17:46:03 [INFO] train episode 24670: reward = -76.51, steps = 25 17:46:05 [INFO] train episode 24671: reward = -46.46, steps = 23 17:46:07 [INFO] train episode 24672: reward = -93.96, steps = 21 17:46:09 [INFO] train episode 24673: reward = -89.01, steps = 24 17:46:14 [INFO] train episode 24674: reward = -52.04, steps = 50 17:46:18 [INFO] train episode 24675: reward = -75.52, steps = 54 17:46:20 [INFO] train episode 24676: reward = -54.10, steps = 22 17:46:22 [INFO] train episode 24677: reward = -98.81, steps = 22 17:46:25 [INFO] train episode 24678: reward = -33.93, steps = 28 17:46:29 [INFO] train episode 24679: reward = -70.34, steps = 44 17:46:32 [INFO] train episode 24680: reward = -114.58, steps = 39 17:46:36 [INFO] train episode 24681: reward = -59.47, steps = 40 17:46:41 [INFO] train episode 24682: reward = -98.51, steps = 53 17:46:43 [INFO] train episode 24683: reward = -89.00, steps = 27 17:46:48 [INFO] train episode 24684: reward = -147.74, steps = 53 17:46:52 [INFO] train episode 24685: reward = -86.46, steps = 55 17:46:56 [INFO] train episode 24686: reward = -78.39, steps = 42 17:47:02 [INFO] train episode 24687: reward = -99.56, steps = 60 17:47:03 [INFO] train episode 24688: reward = -58.17, steps = 20 17:47:07 [INFO] train episode 24689: reward = -70.48, steps = 44 17:47:09 [INFO] train episode 24690: reward = -77.30, steps = 28 17:47:15 [INFO] train episode 24691: reward = -140.14, steps = 61 17:47:19 [INFO] train episode 24692: reward = -64.86, steps = 43 17:47:23 [INFO] train episode 24693: reward = -82.44, steps = 50 17:47:27 [INFO] train episode 24694: reward = -81.74, steps = 49 17:47:30 [INFO] train episode 24695: reward = -63.29, steps = 28 17:47:32 [INFO] train episode 24696: reward = -27.88, steps = 27 17:47:37 [INFO] train episode 24697: reward = -47.29, steps = 51 17:47:41 [INFO] train episode 24698: reward = -112.09, steps = 51 17:47:44 [INFO] train episode 24699: reward = -47.02, steps = 33 17:47:46 [INFO] train episode 24700: reward = -51.37, steps = 26 17:47:49 [INFO] train episode 24701: reward = -72.08, steps = 29 17:47:51 [INFO] train episode 24702: reward = -58.32, steps = 21 17:47:54 [INFO] train episode 24703: reward = -58.40, steps = 43 17:47:59 [INFO] train episode 24704: reward = -95.98, steps = 49 17:48:04 [INFO] train episode 24705: reward = -59.94, steps = 57 17:48:08 [INFO] train episode 24706: reward = -49.82, steps = 37 17:48:13 [INFO] train episode 24707: reward = -84.45, steps = 45 17:48:15 [INFO] train episode 24708: reward = -64.85, steps = 25 17:48:18 [INFO] train episode 24709: reward = -57.92, steps = 27 17:48:22 [INFO] train episode 24710: reward = -162.91, steps = 39 17:48:26 [INFO] train episode 24711: reward = -89.87, steps = 38 17:48:30 [INFO] train episode 24712: reward = -67.18, steps = 49 17:48:35 [INFO] train episode 24713: reward = -97.27, steps = 48 17:48:38 [INFO] train episode 24714: reward = -58.13, steps = 29 17:48:42 [INFO] train episode 24715: reward = -87.81, steps = 44 17:48:47 [INFO] train episode 24716: reward = -82.51, steps = 47 17:48:50 [INFO] train episode 24717: reward = -80.45, steps = 29 17:48:53 [INFO] train episode 24718: reward = -35.92, steps = 33 17:48:56 [INFO] train episode 24719: reward = -54.01, steps = 26 17:49:00 [INFO] train episode 24720: reward = -47.60, steps = 38 17:49:03 [INFO] train episode 24721: reward = -70.11, steps = 22 17:49:07 [INFO] train episode 24722: reward = -138.28, steps = 43 17:49:13 [INFO] train episode 24723: reward = -107.19, steps = 60 17:49:16 [INFO] train episode 24724: reward = -90.07, steps = 31 17:49:20 [INFO] train episode 24725: reward = -49.76, steps = 34 17:49:22 [INFO] train episode 24726: reward = -68.16, steps = 22 17:49:27 [INFO] train episode 24727: reward = -98.84, steps = 48 17:49:31 [INFO] train episode 24728: reward = -72.21, steps = 40 17:49:34 [INFO] train episode 24729: reward = -68.66, steps = 35 17:49:39 [INFO] train episode 24730: reward = -73.80, steps = 44 17:49:44 [INFO] train episode 24731: reward = -89.51, steps = 53 17:49:48 [INFO] train episode 24732: reward = -68.99, steps = 46 17:49:51 [INFO] train episode 24733: reward = -61.83, steps = 33 17:49:54 [INFO] train episode 24734: reward = -75.03, steps = 33 17:49:57 [INFO] train episode 24735: reward = -84.05, steps = 34 17:50:00 [INFO] train episode 24736: reward = -50.43, steps = 31 17:50:03 [INFO] train episode 24737: reward = -71.55, steps = 33 17:50:07 [INFO] train episode 24738: reward = -79.28, steps = 41 17:50:12 [INFO] train episode 24739: reward = -75.56, steps = 53 17:50:15 [INFO] train episode 24740: reward = -55.21, steps = 22 17:50:18 [INFO] train episode 24741: reward = -64.42, steps = 31 17:50:24 [INFO] train episode 24742: reward = -49.78, steps = 53 17:50:26 [INFO] train episode 24743: reward = -75.99, steps = 24 17:50:30 [INFO] train episode 24744: reward = -65.25, steps = 37 17:50:35 [INFO] train episode 24745: reward = -69.86, steps = 38 17:50:38 [INFO] train episode 24746: reward = -79.27, steps = 33 17:50:42 [INFO] train episode 24747: reward = -77.40, steps = 49 17:50:45 [INFO] train episode 24748: reward = -92.11, steps = 43 17:50:49 [INFO] train episode 24749: reward = -88.85, steps = 40 17:50:53 [INFO] train episode 24750: reward = -86.67, steps = 41 17:50:55 [INFO] train episode 24751: reward = -104.62, steps = 21 17:50:57 [INFO] train episode 24752: reward = -64.86, steps = 32 17:51:00 [INFO] train episode 24753: reward = -87.09, steps = 26 17:51:04 [INFO] train episode 24754: reward = -91.35, steps = 54 17:51:07 [INFO] train episode 24755: reward = -50.03, steps = 21 17:51:10 [INFO] train episode 24756: reward = -66.20, steps = 46 17:51:15 [INFO] train episode 24757: reward = -65.13, steps = 50 17:51:17 [INFO] train episode 24758: reward = -68.54, steps = 22 17:51:20 [INFO] train episode 24759: reward = -72.97, steps = 39 17:51:22 [INFO] train episode 24760: reward = -61.62, steps = 22 17:51:25 [INFO] train episode 24761: reward = -56.70, steps = 29 17:51:28 [INFO] train episode 24762: reward = -88.94, steps = 33 17:51:31 [INFO] train episode 24763: reward = -65.69, steps = 38 17:51:33 [INFO] train episode 24764: reward = -68.82, steps = 24 17:51:39 [INFO] train episode 24765: reward = -92.55, steps = 63 17:51:43 [INFO] train episode 24766: reward = -46.93, steps = 50 17:51:46 [INFO] train episode 24767: reward = -75.75, steps = 36 17:51:48 [INFO] train episode 24768: reward = -56.37, steps = 26 17:51:52 [INFO] train episode 24769: reward = -88.70, steps = 38 17:51:55 [INFO] train episode 24770: reward = -70.34, steps = 42 17:51:59 [INFO] train episode 24771: reward = -65.68, steps = 42 17:52:01 [INFO] train episode 24772: reward = -84.29, steps = 23 17:52:05 [INFO] train episode 24773: reward = -72.79, steps = 37 17:52:09 [INFO] train episode 24774: reward = -101.31, steps = 46 17:52:12 [INFO] train episode 24775: reward = -51.02, steps = 31 17:52:14 [INFO] train episode 24776: reward = -42.56, steps = 22 17:52:16 [INFO] train episode 24777: reward = -60.49, steps = 25 17:52:18 [INFO] train episode 24778: reward = -64.50, steps = 25 17:52:21 [INFO] train episode 24779: reward = -55.31, steps = 28 17:52:23 [INFO] train episode 24780: reward = -59.06, steps = 28 17:52:27 [INFO] train episode 24781: reward = -77.73, steps = 34 17:52:29 [INFO] train episode 24782: reward = -70.18, steps = 26 17:52:31 [INFO] train episode 24783: reward = -84.02, steps = 26 17:52:34 [INFO] train episode 24784: reward = -59.95, steps = 30 17:52:37 [INFO] train episode 24785: reward = -108.74, steps = 35 17:52:39 [INFO] train episode 24786: reward = -46.10, steps = 30 17:52:45 [INFO] train episode 24787: reward = -103.55, steps = 66 17:52:48 [INFO] train episode 24788: reward = -54.75, steps = 32 17:52:51 [INFO] train episode 24789: reward = -61.06, steps = 35 17:52:53 [INFO] train episode 24790: reward = -72.77, steps = 24 17:52:57 [INFO] train episode 24791: reward = -60.27, steps = 40 17:53:00 [INFO] train episode 24792: reward = -63.97, steps = 28 17:53:02 [INFO] train episode 24793: reward = -109.31, steps = 29 17:53:05 [INFO] train episode 24794: reward = -79.91, steps = 34 17:53:09 [INFO] train episode 24795: reward = -76.23, steps = 44 17:53:12 [INFO] train episode 24796: reward = -64.67, steps = 40 17:53:18 [INFO] train episode 24797: reward = -103.91, steps = 60 17:53:21 [INFO] train episode 24798: reward = -53.68, steps = 34 17:53:24 [INFO] train episode 24799: reward = -60.71, steps = 36 17:53:25 [INFO] train episode 24800: reward = -55.87, steps = 19 17:53:27 [INFO] train episode 24801: reward = -87.27, steps = 22 17:53:30 [INFO] train episode 24802: reward = -60.68, steps = 34 17:53:34 [INFO] train episode 24803: reward = -55.15, steps = 34 17:53:38 [INFO] train episode 24804: reward = -57.14, steps = 46 17:53:40 [INFO] train episode 24805: reward = -86.66, steps = 33 17:53:45 [INFO] train episode 24806: reward = -108.02, steps = 57 17:53:49 [INFO] train episode 24807: reward = -50.71, steps = 34 17:53:52 [INFO] train episode 24808: reward = -74.62, steps = 39 17:53:56 [INFO] train episode 24809: reward = -88.86, steps = 41 17:53:59 [INFO] train episode 24810: reward = -53.36, steps = 36 17:54:03 [INFO] train episode 24811: reward = -74.69, steps = 46 17:54:07 [INFO] train episode 24812: reward = -61.30, steps = 37 17:54:09 [INFO] train episode 24813: reward = -63.23, steps = 30 17:54:12 [INFO] train episode 24814: reward = -82.71, steps = 30 17:54:16 [INFO] train episode 24815: reward = -64.35, steps = 45 17:54:19 [INFO] train episode 24816: reward = -72.81, steps = 39 17:54:23 [INFO] train episode 24817: reward = -115.92, steps = 34 17:54:26 [INFO] train episode 24818: reward = -49.31, steps = 44 17:54:31 [INFO] train episode 24819: reward = -119.76, steps = 55 17:54:35 [INFO] train episode 24820: reward = -78.20, steps = 44 17:54:38 [INFO] train episode 24821: reward = -63.64, steps = 34 17:54:43 [INFO] train episode 24822: reward = -47.83, steps = 47 17:54:45 [INFO] train episode 24823: reward = -102.84, steps = 33 17:54:49 [INFO] train episode 24824: reward = -39.03, steps = 36 17:54:52 [INFO] train episode 24825: reward = -32.43, steps = 36 17:54:54 [INFO] train episode 24826: reward = -48.54, steps = 24 17:54:56 [INFO] train episode 24827: reward = -100.09, steps = 18 17:55:02 [INFO] train episode 24828: reward = -67.27, steps = 55 17:55:05 [INFO] train episode 24829: reward = -74.25, steps = 35 17:55:07 [INFO] train episode 24830: reward = -69.72, steps = 27 17:55:10 [INFO] train episode 24831: reward = -119.29, steps = 29 17:55:14 [INFO] train episode 24832: reward = -134.86, steps = 50 17:55:18 [INFO] train episode 24833: reward = -48.50, steps = 44 17:55:22 [INFO] train episode 24834: reward = -75.04, steps = 46 17:55:26 [INFO] train episode 24835: reward = -65.10, steps = 35 17:55:30 [INFO] train episode 24836: reward = -86.78, steps = 43 17:55:33 [INFO] train episode 24837: reward = -66.43, steps = 34 17:55:35 [INFO] train episode 24838: reward = -82.03, steps = 29 17:55:37 [INFO] train episode 24839: reward = -78.45, steps = 24 17:55:40 [INFO] train episode 24840: reward = -57.52, steps = 23 17:55:42 [INFO] train episode 24841: reward = -79.41, steps = 30 17:55:46 [INFO] train episode 24842: reward = -58.73, steps = 32 17:55:49 [INFO] train episode 24843: reward = -81.02, steps = 44 17:55:53 [INFO] train episode 24844: reward = -75.15, steps = 39 17:55:56 [INFO] train episode 24845: reward = -78.01, steps = 37 17:56:00 [INFO] train episode 24846: reward = -66.14, steps = 33 17:56:03 [INFO] train episode 24847: reward = -69.65, steps = 37 17:56:05 [INFO] train episode 24848: reward = -68.69, steps = 21 17:56:08 [INFO] train episode 24849: reward = -83.87, steps = 37 17:56:10 [INFO] train episode 24850: reward = -58.32, steps = 26 17:56:13 [INFO] train episode 24851: reward = -52.54, steps = 35 17:56:16 [INFO] train episode 24852: reward = -55.35, steps = 24 17:56:18 [INFO] train episode 24853: reward = -64.65, steps = 24 17:56:21 [INFO] train episode 24854: reward = -73.77, steps = 29 17:56:24 [INFO] train episode 24855: reward = -77.84, steps = 39 17:56:27 [INFO] train episode 24856: reward = -96.41, steps = 36 17:56:29 [INFO] train episode 24857: reward = -43.02, steps = 26 17:56:32 [INFO] train episode 24858: reward = -66.64, steps = 29 17:56:35 [INFO] train episode 24859: reward = -67.29, steps = 25 17:56:39 [INFO] train episode 24860: reward = -59.21, steps = 49 17:56:44 [INFO] train episode 24861: reward = -110.49, steps = 66 17:56:48 [INFO] train episode 24862: reward = -61.80, steps = 41 17:56:51 [INFO] train episode 24863: reward = -84.52, steps = 32 17:56:53 [INFO] train episode 24864: reward = -74.67, steps = 23 17:56:56 [INFO] train episode 24865: reward = -53.72, steps = 36 17:57:01 [INFO] train episode 24866: reward = -116.49, steps = 51 17:57:03 [INFO] train episode 24867: reward = -75.34, steps = 26 17:57:06 [INFO] train episode 24868: reward = -96.17, steps = 28 17:57:10 [INFO] train episode 24869: reward = -56.42, steps = 41 17:57:13 [INFO] train episode 24870: reward = -38.51, steps = 43 17:57:16 [INFO] train episode 24871: reward = -74.07, steps = 34 17:57:19 [INFO] train episode 24872: reward = -69.92, steps = 37 17:57:23 [INFO] train episode 24873: reward = -51.02, steps = 36 17:57:27 [INFO] train episode 24874: reward = -115.56, steps = 42 17:57:29 [INFO] train episode 24875: reward = -50.38, steps = 24 17:57:33 [INFO] train episode 24876: reward = -125.65, steps = 47 17:57:36 [INFO] train episode 24877: reward = -81.77, steps = 35 17:57:38 [INFO] train episode 24878: reward = -72.41, steps = 24 17:57:41 [INFO] train episode 24879: reward = -44.10, steps = 31 17:57:45 [INFO] train episode 24880: reward = -66.09, steps = 44 17:57:47 [INFO] train episode 24881: reward = -74.59, steps = 23 17:57:49 [INFO] train episode 24882: reward = -67.67, steps = 21 17:57:51 [INFO] train episode 24883: reward = -51.67, steps = 23 17:57:55 [INFO] train episode 24884: reward = -52.22, steps = 43 17:58:00 [INFO] train episode 24885: reward = -87.09, steps = 49 17:58:05 [INFO] train episode 24886: reward = -130.40, steps = 59 17:58:09 [INFO] train episode 24887: reward = -98.67, steps = 51 17:58:12 [INFO] train episode 24888: reward = -70.06, steps = 28 17:58:15 [INFO] train episode 24889: reward = -32.68, steps = 34 17:58:19 [INFO] train episode 24890: reward = -86.53, steps = 43 17:58:22 [INFO] train episode 24891: reward = -66.08, steps = 38 17:58:26 [INFO] train episode 24892: reward = -97.34, steps = 41 17:58:28 [INFO] train episode 24893: reward = -77.63, steps = 23 17:58:31 [INFO] train episode 24894: reward = -49.28, steps = 41 17:58:35 [INFO] train episode 24895: reward = -97.79, steps = 45 17:58:38 [INFO] train episode 24896: reward = -45.90, steps = 29 17:58:40 [INFO] train episode 24897: reward = -39.54, steps = 26 17:58:42 [INFO] train episode 24898: reward = -92.97, steps = 20 17:58:45 [INFO] train episode 24899: reward = -75.25, steps = 27 17:58:47 [INFO] train episode 24900: reward = -75.80, steps = 22 17:58:49 [INFO] train episode 24901: reward = -58.16, steps = 24 17:58:54 [INFO] train episode 24902: reward = -111.26, steps = 54 17:58:57 [INFO] train episode 24903: reward = -74.73, steps = 33 17:59:01 [INFO] train episode 24904: reward = -38.65, steps = 43 17:59:04 [INFO] train episode 24905: reward = -98.41, steps = 30 17:59:07 [INFO] train episode 24906: reward = -84.45, steps = 36 17:59:11 [INFO] train episode 24907: reward = -94.81, steps = 44 17:59:13 [INFO] train episode 24908: reward = -63.05, steps = 23 17:59:15 [INFO] train episode 24909: reward = -103.11, steps = 25 17:59:19 [INFO] train episode 24910: reward = -74.43, steps = 46 17:59:22 [INFO] train episode 24911: reward = -64.56, steps = 30 17:59:24 [INFO] train episode 24912: reward = -63.73, steps = 21 17:59:26 [INFO] train episode 24913: reward = -65.93, steps = 31 17:59:30 [INFO] train episode 24914: reward = -74.61, steps = 40 17:59:32 [INFO] train episode 24915: reward = -79.74, steps = 21 17:59:35 [INFO] train episode 24916: reward = -63.52, steps = 41 17:59:37 [INFO] train episode 24917: reward = -70.98, steps = 19 17:59:41 [INFO] train episode 24918: reward = -59.39, steps = 42 17:59:44 [INFO] train episode 24919: reward = -84.54, steps = 42 17:59:47 [INFO] train episode 24920: reward = -87.93, steps = 35 17:59:51 [INFO] train episode 24921: reward = -51.83, steps = 35 17:59:54 [INFO] train episode 24922: reward = -53.28, steps = 36 17:59:57 [INFO] train episode 24923: reward = -99.21, steps = 36 17:59:59 [INFO] train episode 24924: reward = -53.33, steps = 23 18:00:04 [INFO] train episode 24925: reward = -140.62, steps = 57 18:00:07 [INFO] train episode 24926: reward = -76.28, steps = 34 18:00:09 [INFO] train episode 24927: reward = -44.24, steps = 26 18:00:12 [INFO] train episode 24928: reward = -84.05, steps = 37 18:00:15 [INFO] train episode 24929: reward = -59.99, steps = 34 18:00:19 [INFO] train episode 24930: reward = -42.68, steps = 36 18:00:24 [INFO] train episode 24931: reward = -72.85, steps = 59 18:00:26 [INFO] train episode 24932: reward = -72.24, steps = 26 18:00:28 [INFO] train episode 24933: reward = -62.87, steps = 21 18:00:30 [INFO] train episode 24934: reward = -45.30, steps = 22 18:00:32 [INFO] train episode 24935: reward = -52.21, steps = 21 18:00:35 [INFO] train episode 24936: reward = -66.26, steps = 33 18:00:37 [INFO] train episode 24937: reward = -53.15, steps = 22 18:00:39 [INFO] train episode 24938: reward = -76.24, steps = 22 18:00:43 [INFO] train episode 24939: reward = -41.51, steps = 40 18:00:45 [INFO] train episode 24940: reward = -65.65, steps = 25 18:00:47 [INFO] train episode 24941: reward = -105.53, steps = 32 18:00:49 [INFO] train episode 24942: reward = -71.45, steps = 18 18:00:54 [INFO] train episode 24943: reward = -148.81, steps = 45 18:00:57 [INFO] train episode 24944: reward = -83.69, steps = 35 18:01:00 [INFO] train episode 24945: reward = -100.47, steps = 37 18:01:02 [INFO] train episode 24946: reward = -64.17, steps = 25 18:01:07 [INFO] train episode 24947: reward = -63.28, steps = 48 18:01:09 [INFO] train episode 24948: reward = -70.07, steps = 24 18:01:12 [INFO] train episode 24949: reward = -59.21, steps = 29 18:01:14 [INFO] train episode 24950: reward = -123.94, steps = 25 18:01:17 [INFO] train episode 24951: reward = -61.45, steps = 33 18:01:19 [INFO] train episode 24952: reward = -100.38, steps = 26 18:01:21 [INFO] train episode 24953: reward = -84.98, steps = 28 18:01:24 [INFO] train episode 24954: reward = -50.30, steps = 30 18:01:29 [INFO] train episode 24955: reward = -140.34, steps = 48 18:01:31 [INFO] train episode 24956: reward = -52.37, steps = 29 18:01:33 [INFO] train episode 24957: reward = -66.20, steps = 23 18:01:37 [INFO] train episode 24958: reward = -69.69, steps = 41 18:01:39 [INFO] train episode 24959: reward = -56.37, steps = 25 18:01:43 [INFO] train episode 24960: reward = -97.31, steps = 48 18:01:45 [INFO] train episode 24961: reward = -88.22, steps = 22 18:01:51 [INFO] train episode 24962: reward = -77.00, steps = 63 18:01:54 [INFO] train episode 24963: reward = -64.06, steps = 36 18:01:56 [INFO] train episode 24964: reward = -64.03, steps = 27 18:02:00 [INFO] train episode 24965: reward = -104.91, steps = 36 18:02:03 [INFO] train episode 24966: reward = -120.96, steps = 39 18:02:06 [INFO] train episode 24967: reward = -52.98, steps = 29 18:02:10 [INFO] train episode 24968: reward = -53.37, steps = 41 18:02:12 [INFO] train episode 24969: reward = -86.05, steps = 23 18:02:14 [INFO] train episode 24970: reward = -98.67, steps = 26 18:02:18 [INFO] train episode 24971: reward = -57.36, steps = 38 18:02:21 [INFO] train episode 24972: reward = -74.95, steps = 40 18:02:24 [INFO] train episode 24973: reward = -128.31, steps = 26 18:02:28 [INFO] train episode 24974: reward = -97.49, steps = 50 18:02:32 [INFO] train episode 24975: reward = -50.25, steps = 45 18:02:34 [INFO] train episode 24976: reward = -81.61, steps = 24 18:02:38 [INFO] train episode 24977: reward = -93.79, steps = 38 18:02:41 [INFO] train episode 24978: reward = -89.34, steps = 32 18:02:44 [INFO] train episode 24979: reward = -142.87, steps = 40 18:02:47 [INFO] train episode 24980: reward = -68.28, steps = 31 18:02:51 [INFO] train episode 24981: reward = -40.37, steps = 41 18:02:53 [INFO] train episode 24982: reward = -41.89, steps = 22 18:02:56 [INFO] train episode 24983: reward = -68.02, steps = 32 18:02:59 [INFO] train episode 24984: reward = -67.11, steps = 35 18:03:03 [INFO] train episode 24985: reward = -71.02, steps = 40 18:03:06 [INFO] train episode 24986: reward = -102.15, steps = 33 18:03:10 [INFO] train episode 24987: reward = -119.26, steps = 46 18:03:12 [INFO] train episode 24988: reward = -66.26, steps = 26 18:03:16 [INFO] train episode 24989: reward = -100.96, steps = 45 18:03:18 [INFO] train episode 24990: reward = -50.85, steps = 19 18:03:21 [INFO] train episode 24991: reward = -81.08, steps = 31 18:03:27 [INFO] train episode 24992: reward = -118.26, steps = 65 18:03:30 [INFO] train episode 24993: reward = -114.35, steps = 29 18:03:32 [INFO] train episode 24994: reward = -62.86, steps = 29 18:03:36 [INFO] train episode 24995: reward = -38.13, steps = 38 18:03:40 [INFO] train episode 24996: reward = -73.45, steps = 42 18:03:42 [INFO] train episode 24997: reward = -76.16, steps = 28 18:03:45 [INFO] train episode 24998: reward = -44.32, steps = 29 18:03:48 [INFO] train episode 24999: reward = -96.32, steps = 35 18:03:50 [INFO] train episode 25000: reward = -72.98, steps = 19 18:03:53 [INFO] train episode 25001: reward = -60.24, steps = 28 18:03:57 [INFO] train episode 25002: reward = -108.31, steps = 48 18:04:00 [INFO] train episode 25003: reward = -81.14, steps = 35 18:04:03 [INFO] train episode 25004: reward = -79.33, steps = 36 18:04:05 [INFO] train episode 25005: reward = -76.96, steps = 26 18:04:08 [INFO] train episode 25006: reward = -54.10, steps = 25 18:04:10 [INFO] train episode 25007: reward = -97.07, steps = 24 18:04:12 [INFO] train episode 25008: reward = -82.91, steps = 23 18:04:14 [INFO] train episode 25009: reward = -42.39, steps = 20 18:04:16 [INFO] train episode 25010: reward = -94.79, steps = 24 18:04:19 [INFO] train episode 25011: reward = -62.72, steps = 25 18:04:22 [INFO] train episode 25012: reward = -60.32, steps = 44 18:04:24 [INFO] train episode 25013: reward = -66.17, steps = 20 18:04:28 [INFO] train episode 25014: reward = -115.80, steps = 42 18:04:30 [INFO] train episode 25015: reward = -61.16, steps = 23 18:04:33 [INFO] train episode 25016: reward = -65.27, steps = 39 18:04:36 [INFO] train episode 25017: reward = -63.23, steps = 32 18:04:40 [INFO] train episode 25018: reward = -69.98, steps = 39 18:04:42 [INFO] train episode 25019: reward = -87.48, steps = 33 18:04:46 [INFO] train episode 25020: reward = -51.40, steps = 31 18:04:49 [INFO] train episode 25021: reward = -72.32, steps = 39 18:04:51 [INFO] train episode 25022: reward = -79.43, steps = 20 18:04:53 [INFO] train episode 25023: reward = -88.66, steps = 33 18:04:56 [INFO] train episode 25024: reward = -64.09, steps = 34 18:05:00 [INFO] train episode 25025: reward = -71.86, steps = 39 18:05:05 [INFO] train episode 25026: reward = -87.97, steps = 52 18:05:08 [INFO] train episode 25027: reward = -99.64, steps = 37 18:05:10 [INFO] train episode 25028: reward = -58.77, steps = 21 18:05:13 [INFO] train episode 25029: reward = -62.89, steps = 38 18:05:15 [INFO] train episode 25030: reward = -82.54, steps = 25 18:05:17 [INFO] train episode 25031: reward = -59.10, steps = 17 18:05:19 [INFO] train episode 25032: reward = -60.92, steps = 23 18:05:22 [INFO] train episode 25033: reward = -76.18, steps = 32 18:05:26 [INFO] train episode 25034: reward = -87.38, steps = 39 18:05:31 [INFO] train episode 25035: reward = -112.01, steps = 61 18:05:34 [INFO] train episode 25036: reward = -80.89, steps = 33 18:05:36 [INFO] train episode 25037: reward = -47.41, steps = 24 18:05:39 [INFO] train episode 25038: reward = -88.95, steps = 31 18:05:41 [INFO] train episode 25039: reward = -52.48, steps = 25 18:05:45 [INFO] train episode 25040: reward = -56.39, steps = 41 18:05:48 [INFO] train episode 25041: reward = -66.58, steps = 36 18:05:52 [INFO] train episode 25042: reward = -87.71, steps = 45 18:05:56 [INFO] train episode 25043: reward = -117.26, steps = 41 18:05:59 [INFO] train episode 25044: reward = -78.81, steps = 38 18:06:02 [INFO] train episode 25045: reward = -78.71, steps = 37 18:06:06 [INFO] train episode 25046: reward = -59.48, steps = 32 18:06:08 [INFO] train episode 25047: reward = -63.12, steps = 32 18:06:14 [INFO] train episode 25048: reward = -173.11, steps = 66 18:06:17 [INFO] train episode 25049: reward = -74.04, steps = 37 18:06:20 [INFO] train episode 25050: reward = -67.26, steps = 32 18:06:22 [INFO] train episode 25051: reward = -69.44, steps = 21 18:06:24 [INFO] train episode 25052: reward = -58.70, steps = 22 18:06:27 [INFO] train episode 25053: reward = -48.26, steps = 36 18:06:30 [INFO] train episode 25054: reward = -57.52, steps = 28 18:06:33 [INFO] train episode 25055: reward = -50.41, steps = 35 18:06:36 [INFO] train episode 25056: reward = -78.37, steps = 38 18:06:40 [INFO] train episode 25057: reward = -98.09, steps = 34 18:06:42 [INFO] train episode 25058: reward = -68.29, steps = 31 18:06:48 [INFO] train episode 25059: reward = -115.02, steps = 52 18:06:50 [INFO] train episode 25060: reward = -60.38, steps = 24 18:06:52 [INFO] train episode 25061: reward = -82.16, steps = 26 18:06:55 [INFO] train episode 25062: reward = -64.70, steps = 28 18:06:57 [INFO] train episode 25063: reward = -58.42, steps = 23 18:07:00 [INFO] train episode 25064: reward = -63.57, steps = 36 18:07:03 [INFO] train episode 25065: reward = -63.95, steps = 31 18:07:06 [INFO] train episode 25066: reward = -85.57, steps = 33 18:07:09 [INFO] train episode 25067: reward = -47.51, steps = 32 18:07:13 [INFO] train episode 25068: reward = -33.72, steps = 38 18:07:16 [INFO] train episode 25069: reward = -66.65, steps = 41 18:07:18 [INFO] train episode 25070: reward = -59.24, steps = 25 18:07:22 [INFO] train episode 25071: reward = -73.76, steps = 47 18:07:25 [INFO] train episode 25072: reward = -36.55, steps = 23 18:07:29 [INFO] train episode 25073: reward = -73.34, steps = 42 18:07:34 [INFO] train episode 25074: reward = -101.85, steps = 65 18:07:36 [INFO] train episode 25075: reward = -75.90, steps = 20 18:07:39 [INFO] train episode 25076: reward = -71.91, steps = 40 18:07:42 [INFO] train episode 25077: reward = -44.42, steps = 35 18:07:45 [INFO] train episode 25078: reward = -49.84, steps = 22 18:07:48 [INFO] train episode 25079: reward = -78.34, steps = 37 18:07:51 [INFO] train episode 25080: reward = -118.30, steps = 34 18:07:53 [INFO] train episode 25081: reward = -59.95, steps = 24 18:07:55 [INFO] train episode 25082: reward = -81.24, steps = 26 18:07:58 [INFO] train episode 25083: reward = -38.39, steps = 37 18:08:01 [INFO] train episode 25084: reward = -69.39, steps = 29 18:08:05 [INFO] train episode 25085: reward = -59.03, steps = 39 18:08:07 [INFO] train episode 25086: reward = -85.35, steps = 34 18:08:10 [INFO] train episode 25087: reward = -64.72, steps = 33 18:08:14 [INFO] train episode 25088: reward = -99.87, steps = 43 18:08:18 [INFO] train episode 25089: reward = -71.75, steps = 46 18:08:21 [INFO] train episode 25090: reward = -75.23, steps = 28 18:08:24 [INFO] train episode 25091: reward = -71.19, steps = 36 18:08:27 [INFO] train episode 25092: reward = -81.58, steps = 37 18:08:29 [INFO] train episode 25093: reward = -67.80, steps = 25 18:08:33 [INFO] train episode 25094: reward = -60.01, steps = 40 18:08:38 [INFO] train episode 25095: reward = -61.50, steps = 50 18:08:39 [INFO] train episode 25096: reward = -77.65, steps = 18 18:08:41 [INFO] train episode 25097: reward = -86.59, steps = 19 18:08:46 [INFO] train episode 25098: reward = -122.88, steps = 63 18:08:48 [INFO] train episode 25099: reward = -83.03, steps = 20 18:08:55 [INFO] train episode 25100: reward = -205.35, steps = 81 18:08:58 [INFO] train episode 25101: reward = -77.52, steps = 29 18:09:00 [INFO] train episode 25102: reward = -71.18, steps = 26 18:09:03 [INFO] train episode 25103: reward = -64.99, steps = 30 18:09:05 [INFO] train episode 25104: reward = -73.72, steps = 20 18:09:08 [INFO] train episode 25105: reward = -63.42, steps = 30 18:09:11 [INFO] train episode 25106: reward = -99.85, steps = 46 18:09:14 [INFO] train episode 25107: reward = -50.77, steps = 35 18:09:17 [INFO] train episode 25108: reward = -108.69, steps = 33 18:09:21 [INFO] train episode 25109: reward = -42.09, steps = 44 18:09:24 [INFO] train episode 25110: reward = -60.07, steps = 36 18:09:28 [INFO] train episode 25111: reward = -71.77, steps = 36 18:09:30 [INFO] train episode 25112: reward = -96.43, steps = 23 18:09:33 [INFO] train episode 25113: reward = -72.87, steps = 37 18:09:36 [INFO] train episode 25114: reward = -53.26, steps = 32 18:09:39 [INFO] train episode 25115: reward = -88.86, steps = 32 18:09:41 [INFO] train episode 25116: reward = -45.96, steps = 21 18:09:43 [INFO] train episode 25117: reward = -100.07, steps = 21 18:09:45 [INFO] train episode 25118: reward = -56.71, steps = 22 18:09:48 [INFO] train episode 25119: reward = -64.29, steps = 36 18:09:52 [INFO] train episode 25120: reward = -94.88, steps = 41 18:09:55 [INFO] train episode 25121: reward = -80.47, steps = 34 18:09:58 [INFO] train episode 25122: reward = -43.54, steps = 32 18:10:01 [INFO] train episode 25123: reward = -79.80, steps = 32 18:10:05 [INFO] train episode 25124: reward = -58.97, steps = 43 18:10:07 [INFO] train episode 25125: reward = -68.13, steps = 27 18:10:09 [INFO] train episode 25126: reward = -92.83, steps = 19 18:10:14 [INFO] train episode 25127: reward = -130.24, steps = 52 18:10:16 [INFO] train episode 25128: reward = -71.85, steps = 23 18:10:17 [INFO] train episode 25129: reward = -92.43, steps = 18 18:10:21 [INFO] train episode 25130: reward = -110.65, steps = 47 18:10:24 [INFO] train episode 25131: reward = -63.85, steps = 24 18:10:26 [INFO] train episode 25132: reward = -57.58, steps = 21 18:10:28 [INFO] train episode 25133: reward = -66.23, steps = 28 18:10:31 [INFO] train episode 25134: reward = -42.62, steps = 25 18:10:33 [INFO] train episode 25135: reward = -46.78, steps = 23 18:10:35 [INFO] train episode 25136: reward = -107.61, steps = 20 18:10:37 [INFO] train episode 25137: reward = -131.37, steps = 26 18:10:41 [INFO] train episode 25138: reward = -59.28, steps = 41 18:10:44 [INFO] train episode 25139: reward = -72.65, steps = 38 18:10:46 [INFO] train episode 25140: reward = -55.65, steps = 22 18:10:49 [INFO] train episode 25141: reward = -76.88, steps = 31 18:10:51 [INFO] train episode 25142: reward = -60.10, steps = 26 18:10:53 [INFO] train episode 25143: reward = -45.55, steps = 24 18:10:56 [INFO] train episode 25144: reward = -70.21, steps = 28 18:10:59 [INFO] train episode 25145: reward = -65.33, steps = 31 18:11:01 [INFO] train episode 25146: reward = -49.61, steps = 22 18:11:06 [INFO] train episode 25147: reward = -44.64, steps = 61 18:11:10 [INFO] train episode 25148: reward = -184.82, steps = 52 18:11:14 [INFO] train episode 25149: reward = -100.21, steps = 44 18:11:16 [INFO] train episode 25150: reward = -61.06, steps = 21 18:11:18 [INFO] train episode 25151: reward = -78.34, steps = 23 18:11:20 [INFO] train episode 25152: reward = -45.49, steps = 23 18:11:23 [INFO] train episode 25153: reward = -75.15, steps = 35 18:11:26 [INFO] train episode 25154: reward = -58.96, steps = 27 18:11:30 [INFO] train episode 25155: reward = -73.58, steps = 44 18:11:33 [INFO] train episode 25156: reward = -63.02, steps = 33 18:11:37 [INFO] train episode 25157: reward = -92.36, steps = 48 18:11:40 [INFO] train episode 25158: reward = -86.18, steps = 39 18:11:43 [INFO] train episode 25159: reward = -80.79, steps = 32 18:11:46 [INFO] train episode 25160: reward = -82.17, steps = 29 18:11:49 [INFO] train episode 25161: reward = -52.61, steps = 31 18:11:51 [INFO] train episode 25162: reward = -49.61, steps = 22 18:11:53 [INFO] train episode 25163: reward = -78.26, steps = 31 18:11:56 [INFO] train episode 25164: reward = -84.57, steps = 36 18:11:59 [INFO] train episode 25165: reward = -87.22, steps = 36 18:12:01 [INFO] train episode 25166: reward = -70.43, steps = 20 18:12:05 [INFO] train episode 25167: reward = -93.56, steps = 35 18:12:07 [INFO] train episode 25168: reward = -46.39, steps = 22 18:12:09 [INFO] train episode 25169: reward = -45.09, steps = 31 18:12:12 [INFO] train episode 25170: reward = -69.24, steps = 30 18:12:16 [INFO] train episode 25171: reward = -136.88, steps = 45 18:12:18 [INFO] train episode 25172: reward = -53.94, steps = 25 18:12:20 [INFO] train episode 25173: reward = -48.00, steps = 21 18:12:22 [INFO] train episode 25174: reward = -52.38, steps = 21 18:12:25 [INFO] train episode 25175: reward = -77.08, steps = 33 18:12:27 [INFO] train episode 25176: reward = -91.35, steps = 20 18:12:29 [INFO] train episode 25177: reward = -96.36, steps = 28 18:12:33 [INFO] train episode 25178: reward = -74.96, steps = 39 18:12:35 [INFO] train episode 25179: reward = -52.33, steps = 30 18:12:40 [INFO] train episode 25180: reward = -91.35, steps = 40 18:12:42 [INFO] train episode 25181: reward = -58.66, steps = 29 18:12:46 [INFO] train episode 25182: reward = -57.21, steps = 46 18:12:49 [INFO] train episode 25183: reward = -65.63, steps = 33 18:12:52 [INFO] train episode 25184: reward = -67.55, steps = 28 18:12:54 [INFO] train episode 25185: reward = -58.91, steps = 23 18:12:57 [INFO] train episode 25186: reward = -70.70, steps = 35 18:13:00 [INFO] train episode 25187: reward = -66.04, steps = 29 18:13:02 [INFO] train episode 25188: reward = -56.93, steps = 21 18:13:05 [INFO] train episode 25189: reward = -51.06, steps = 39 18:13:07 [INFO] train episode 25190: reward = -53.53, steps = 20 18:13:08 [INFO] train episode 25191: reward = -80.78, steps = 19 18:13:12 [INFO] train episode 25192: reward = -55.27, steps = 35 18:13:16 [INFO] train episode 25193: reward = -153.31, steps = 46 18:13:18 [INFO] train episode 25194: reward = -101.54, steps = 29 18:13:20 [INFO] train episode 25195: reward = -40.66, steps = 21 18:13:25 [INFO] train episode 25196: reward = -175.27, steps = 61 18:13:30 [INFO] train episode 25197: reward = -88.39, steps = 55 18:13:33 [INFO] train episode 25198: reward = -55.31, steps = 34 18:13:35 [INFO] train episode 25199: reward = -74.32, steps = 22 18:13:38 [INFO] train episode 25200: reward = -87.42, steps = 33 18:13:41 [INFO] train episode 25201: reward = -81.35, steps = 37 18:13:44 [INFO] train episode 25202: reward = -111.46, steps = 35 18:13:46 [INFO] train episode 25203: reward = -73.92, steps = 22 18:13:48 [INFO] train episode 25204: reward = -47.21, steps = 22 18:13:52 [INFO] train episode 25205: reward = -60.40, steps = 40 18:13:55 [INFO] train episode 25206: reward = -83.88, steps = 34 18:13:58 [INFO] train episode 25207: reward = -68.14, steps = 38 18:14:00 [INFO] train episode 25208: reward = -70.97, steps = 20 18:14:04 [INFO] train episode 25209: reward = -83.35, steps = 43 18:14:08 [INFO] train episode 25210: reward = -89.01, steps = 52 18:14:10 [INFO] train episode 25211: reward = -31.88, steps = 24 18:14:14 [INFO] train episode 25212: reward = -81.68, steps = 35 18:14:15 [INFO] train episode 25213: reward = -67.99, steps = 21 18:14:18 [INFO] train episode 25214: reward = -77.69, steps = 24 18:14:21 [INFO] train episode 25215: reward = -89.11, steps = 42 18:14:26 [INFO] train episode 25216: reward = -125.25, steps = 59 18:14:31 [INFO] train episode 25217: reward = -100.89, steps = 46 18:14:32 [INFO] train episode 25218: reward = -60.86, steps = 20 18:14:34 [INFO] train episode 25219: reward = -60.24, steps = 21 18:14:37 [INFO] train episode 25220: reward = -93.04, steps = 34 18:14:40 [INFO] train episode 25221: reward = -64.45, steps = 26 18:14:43 [INFO] train episode 25222: reward = -95.99, steps = 39 18:14:46 [INFO] train episode 25223: reward = -71.68, steps = 26 18:14:51 [INFO] train episode 25224: reward = -60.03, steps = 66 18:14:54 [INFO] train episode 25225: reward = -94.34, steps = 30 18:14:56 [INFO] train episode 25226: reward = -47.77, steps = 30 18:14:58 [INFO] train episode 25227: reward = -59.33, steps = 18 18:15:02 [INFO] train episode 25228: reward = -95.33, steps = 39 18:15:04 [INFO] train episode 25229: reward = -70.35, steps = 32 18:15:06 [INFO] train episode 25230: reward = -74.98, steps = 20 18:15:09 [INFO] train episode 25231: reward = -58.40, steps = 37 18:15:12 [INFO] train episode 25232: reward = -99.57, steps = 36 18:15:17 [INFO] train episode 25233: reward = -95.06, steps = 53 18:15:20 [INFO] train episode 25234: reward = -97.22, steps = 30 18:15:22 [INFO] train episode 25235: reward = -56.23, steps = 25 18:15:24 [INFO] train episode 25236: reward = -88.74, steps = 25 18:15:27 [INFO] train episode 25237: reward = -79.74, steps = 26 18:15:30 [INFO] train episode 25238: reward = -39.63, steps = 33 18:15:34 [INFO] train episode 25239: reward = -59.30, steps = 41 18:15:38 [INFO] train episode 25240: reward = -84.69, steps = 37 18:15:42 [INFO] train episode 25241: reward = -116.87, steps = 49 18:15:44 [INFO] train episode 25242: reward = -68.26, steps = 30 18:15:47 [INFO] train episode 25243: reward = -59.19, steps = 32 18:15:50 [INFO] train episode 25244: reward = -83.84, steps = 29 18:15:53 [INFO] train episode 25245: reward = -74.87, steps = 33 18:15:56 [INFO] train episode 25246: reward = -83.69, steps = 39 18:15:59 [INFO] train episode 25247: reward = -78.92, steps = 32 18:16:02 [INFO] train episode 25248: reward = -64.73, steps = 31 18:16:04 [INFO] train episode 25249: reward = -79.87, steps = 28 18:16:06 [INFO] train episode 25250: reward = -104.28, steps = 20 18:16:09 [INFO] train episode 25251: reward = -56.07, steps = 28 18:16:11 [INFO] train episode 25252: reward = -103.67, steps = 29 18:16:14 [INFO] train episode 25253: reward = -86.60, steps = 34 18:16:16 [INFO] train episode 25254: reward = -92.49, steps = 19 18:16:18 [INFO] train episode 25255: reward = -54.25, steps = 28 18:16:22 [INFO] train episode 25256: reward = -100.06, steps = 35 18:16:24 [INFO] train episode 25257: reward = -63.16, steps = 23 18:16:27 [INFO] train episode 25258: reward = -91.24, steps = 43 18:16:30 [INFO] train episode 25259: reward = -60.54, steps = 25 18:16:35 [INFO] train episode 25260: reward = -110.99, steps = 62 18:16:38 [INFO] train episode 25261: reward = -56.08, steps = 27 18:16:40 [INFO] train episode 25262: reward = -63.40, steps = 25 18:16:43 [INFO] train episode 25263: reward = -73.68, steps = 36 18:16:48 [INFO] train episode 25264: reward = -64.10, steps = 56 18:16:50 [INFO] train episode 25265: reward = -60.88, steps = 31 18:16:54 [INFO] train episode 25266: reward = -76.26, steps = 32 18:16:55 [INFO] train episode 25267: reward = -83.04, steps = 21 18:16:59 [INFO] train episode 25268: reward = -129.84, steps = 36 18:17:05 [INFO] train episode 25269: reward = -97.98, steps = 72 18:17:08 [INFO] train episode 25270: reward = -94.73, steps = 44 18:17:12 [INFO] train episode 25271: reward = -73.41, steps = 37 18:17:14 [INFO] train episode 25272: reward = -101.84, steps = 22 18:17:17 [INFO] train episode 25273: reward = -35.08, steps = 32 18:17:19 [INFO] train episode 25274: reward = -72.97, steps = 23 18:17:21 [INFO] train episode 25275: reward = -81.02, steps = 23 18:17:23 [INFO] train episode 25276: reward = -42.21, steps = 22 18:17:27 [INFO] train episode 25277: reward = -111.98, steps = 43 18:17:30 [INFO] train episode 25278: reward = -59.98, steps = 41 18:17:33 [INFO] train episode 25279: reward = -104.22, steps = 35 18:17:36 [INFO] train episode 25280: reward = -69.50, steps = 35 18:17:40 [INFO] train episode 25281: reward = -64.97, steps = 45 18:17:43 [INFO] train episode 25282: reward = -58.59, steps = 29 18:17:45 [INFO] train episode 25283: reward = -94.48, steps = 26 18:17:49 [INFO] train episode 25284: reward = -82.52, steps = 40 18:17:54 [INFO] train episode 25285: reward = -141.33, steps = 63 18:17:57 [INFO] train episode 25286: reward = -84.46, steps = 34 18:18:00 [INFO] train episode 25287: reward = -56.88, steps = 25 18:18:04 [INFO] train episode 25288: reward = -79.24, steps = 53 18:18:06 [INFO] train episode 25289: reward = -105.25, steps = 25 18:18:08 [INFO] train episode 25290: reward = -60.16, steps = 22 18:18:12 [INFO] train episode 25291: reward = -124.01, steps = 38 18:18:14 [INFO] train episode 25292: reward = -60.82, steps = 21 18:18:16 [INFO] train episode 25293: reward = -61.37, steps = 30 18:18:19 [INFO] train episode 25294: reward = -46.23, steps = 35 18:18:24 [INFO] train episode 25295: reward = -55.79, steps = 54 18:18:28 [INFO] train episode 25296: reward = -50.58, steps = 34 18:18:31 [INFO] train episode 25297: reward = -96.86, steps = 27 18:18:35 [INFO] train episode 25298: reward = -74.83, steps = 44 18:18:38 [INFO] train episode 25299: reward = -150.17, steps = 41 18:18:42 [INFO] train episode 25300: reward = -102.98, steps = 45 18:18:45 [INFO] train episode 25301: reward = -51.43, steps = 34 18:18:48 [INFO] train episode 25302: reward = -82.71, steps = 31 18:18:51 [INFO] train episode 25303: reward = -56.30, steps = 30 18:18:54 [INFO] train episode 25304: reward = -54.47, steps = 37 18:18:58 [INFO] train episode 25305: reward = -60.58, steps = 49 18:19:01 [INFO] train episode 25306: reward = -51.23, steps = 27 18:19:06 [INFO] train episode 25307: reward = -71.32, steps = 65 18:19:09 [INFO] train episode 25308: reward = -57.56, steps = 28 18:19:11 [INFO] train episode 25309: reward = -65.48, steps = 25 18:19:14 [INFO] train episode 25310: reward = -103.68, steps = 31 18:19:18 [INFO] train episode 25311: reward = -66.37, steps = 43 18:19:20 [INFO] train episode 25312: reward = -97.57, steps = 19 18:19:22 [INFO] train episode 25313: reward = -42.37, steps = 27 18:19:25 [INFO] train episode 25314: reward = -63.60, steps = 25 18:19:27 [INFO] train episode 25315: reward = -61.29, steps = 25 18:19:30 [INFO] train episode 25316: reward = -57.20, steps = 32 18:19:31 [INFO] train episode 25317: reward = -44.48, steps = 20 18:19:34 [INFO] train episode 25318: reward = -82.83, steps = 30 18:19:38 [INFO] train episode 25319: reward = -91.52, steps = 45 18:19:42 [INFO] train episode 25320: reward = -89.44, steps = 42 18:19:45 [INFO] train episode 25321: reward = -78.02, steps = 40 18:19:47 [INFO] train episode 25322: reward = -52.65, steps = 22 18:19:50 [INFO] train episode 25323: reward = -70.38, steps = 36 18:19:54 [INFO] train episode 25324: reward = -65.06, steps = 34 18:19:56 [INFO] train episode 25325: reward = -100.38, steps = 29 18:19:59 [INFO] train episode 25326: reward = -103.19, steps = 38 18:20:01 [INFO] train episode 25327: reward = -57.83, steps = 20 18:20:05 [INFO] train episode 25328: reward = -82.01, steps = 39 18:20:06 [INFO] train episode 25329: reward = -66.75, steps = 20 18:20:09 [INFO] train episode 25330: reward = -73.57, steps = 28 18:20:11 [INFO] train episode 25331: reward = -75.38, steps = 24 18:20:13 [INFO] train episode 25332: reward = -78.46, steps = 23 18:20:15 [INFO] train episode 25333: reward = -72.30, steps = 25 18:20:18 [INFO] train episode 25334: reward = -93.78, steps = 29 18:20:21 [INFO] train episode 25335: reward = -59.77, steps = 31 18:20:23 [INFO] train episode 25336: reward = -52.11, steps = 26 18:20:26 [INFO] train episode 25337: reward = -93.69, steps = 28 18:20:28 [INFO] train episode 25338: reward = -48.99, steps = 29 18:20:31 [INFO] train episode 25339: reward = -65.76, steps = 30 18:20:33 [INFO] train episode 25340: reward = -89.90, steps = 20 18:20:36 [INFO] train episode 25341: reward = -69.46, steps = 36 18:20:38 [INFO] train episode 25342: reward = -80.31, steps = 24 18:20:41 [INFO] train episode 25343: reward = -67.05, steps = 21 18:20:45 [INFO] train episode 25344: reward = -86.10, steps = 54 18:20:47 [INFO] train episode 25345: reward = -55.36, steps = 25 18:20:50 [INFO] train episode 25346: reward = -84.74, steps = 33 18:20:55 [INFO] train episode 25347: reward = -43.88, steps = 48 18:20:57 [INFO] train episode 25348: reward = -55.94, steps = 21 18:21:02 [INFO] train episode 25349: reward = -76.17, steps = 49 18:21:05 [INFO] train episode 25350: reward = -100.63, steps = 28 18:21:09 [INFO] train episode 25351: reward = -63.98, steps = 39 18:21:11 [INFO] train episode 25352: reward = -88.15, steps = 20 18:21:13 [INFO] train episode 25353: reward = -42.89, steps = 27 18:21:16 [INFO] train episode 25354: reward = -57.19, steps = 28 18:21:18 [INFO] train episode 25355: reward = -92.62, steps = 23 18:21:21 [INFO] train episode 25356: reward = -79.74, steps = 26 18:21:23 [INFO] train episode 25357: reward = -74.19, steps = 32 18:21:28 [INFO] train episode 25358: reward = -85.44, steps = 41 18:21:30 [INFO] train episode 25359: reward = -65.49, steps = 25 18:21:32 [INFO] train episode 25360: reward = -97.37, steps = 21 18:21:35 [INFO] train episode 25361: reward = -91.54, steps = 31 18:21:38 [INFO] train episode 25362: reward = -85.68, steps = 41 18:21:41 [INFO] train episode 25363: reward = -86.45, steps = 33 18:21:45 [INFO] train episode 25364: reward = -109.48, steps = 44 18:21:47 [INFO] train episode 25365: reward = -75.42, steps = 27 18:21:50 [INFO] train episode 25366: reward = -62.65, steps = 20 18:21:52 [INFO] train episode 25367: reward = -92.15, steps = 24 18:21:54 [INFO] train episode 25368: reward = -81.89, steps = 23 18:21:57 [INFO] train episode 25369: reward = -82.49, steps = 35 18:21:59 [INFO] train episode 25370: reward = -87.16, steps = 23 18:22:03 [INFO] train episode 25371: reward = -71.01, steps = 46 18:22:06 [INFO] train episode 25372: reward = -78.85, steps = 31 18:22:08 [INFO] train episode 25373: reward = -63.15, steps = 25 18:22:12 [INFO] train episode 25374: reward = -69.78, steps = 53 18:22:17 [INFO] train episode 25375: reward = -52.16, steps = 57 18:22:21 [INFO] train episode 25376: reward = -152.45, steps = 43 18:22:23 [INFO] train episode 25377: reward = -67.73, steps = 19 18:22:25 [INFO] train episode 25378: reward = -75.34, steps = 17 18:22:28 [INFO] train episode 25379: reward = -105.03, steps = 41 18:22:30 [INFO] train episode 25380: reward = -128.49, steps = 23 18:22:33 [INFO] train episode 25381: reward = -102.58, steps = 32 18:22:35 [INFO] train episode 25382: reward = -64.88, steps = 26 18:22:39 [INFO] train episode 25383: reward = -71.32, steps = 33 18:22:41 [INFO] train episode 25384: reward = -60.36, steps = 29 18:22:43 [INFO] train episode 25385: reward = -58.41, steps = 19 18:22:46 [INFO] train episode 25386: reward = -52.43, steps = 38 18:22:48 [INFO] train episode 25387: reward = -78.18, steps = 23 18:22:52 [INFO] train episode 25388: reward = -90.72, steps = 41 18:22:54 [INFO] train episode 25389: reward = -49.56, steps = 20 18:22:55 [INFO] train episode 25390: reward = -55.10, steps = 19 18:22:58 [INFO] train episode 25391: reward = -54.28, steps = 24 18:22:59 [INFO] train episode 25392: reward = -78.09, steps = 21 18:23:01 [INFO] train episode 25393: reward = -90.97, steps = 20 18:23:03 [INFO] train episode 25394: reward = -68.49, steps = 25 18:23:07 [INFO] train episode 25395: reward = -68.82, steps = 36 18:23:08 [INFO] train episode 25396: reward = -80.21, steps = 21 18:23:11 [INFO] train episode 25397: reward = -65.97, steps = 19 18:23:13 [INFO] train episode 25398: reward = -44.29, steps = 27 18:23:15 [INFO] train episode 25399: reward = -42.77, steps = 23 18:23:17 [INFO] train episode 25400: reward = -44.89, steps = 29 18:23:20 [INFO] train episode 25401: reward = -102.16, steps = 26 18:23:21 [INFO] train episode 25402: reward = -44.28, steps = 20 18:23:23 [INFO] train episode 25403: reward = -95.48, steps = 19 18:23:27 [INFO] train episode 25404: reward = -51.39, steps = 35 18:23:29 [INFO] train episode 25405: reward = -54.81, steps = 24 18:23:31 [INFO] train episode 25406: reward = -58.72, steps = 28 18:23:34 [INFO] train episode 25407: reward = -80.02, steps = 29 18:23:36 [INFO] train episode 25408: reward = -70.38, steps = 23 18:23:39 [INFO] train episode 25409: reward = -95.67, steps = 38 18:23:42 [INFO] train episode 25410: reward = -71.13, steps = 37 18:23:44 [INFO] train episode 25411: reward = -76.16, steps = 22 18:23:48 [INFO] train episode 25412: reward = -72.54, steps = 38 18:23:50 [INFO] train episode 25413: reward = -61.18, steps = 24 18:23:52 [INFO] train episode 25414: reward = -64.40, steps = 21 18:23:55 [INFO] train episode 25415: reward = -51.81, steps = 37 18:23:57 [INFO] train episode 25416: reward = -71.35, steps = 22 18:24:00 [INFO] train episode 25417: reward = -70.10, steps = 34 18:24:02 [INFO] train episode 25418: reward = -110.95, steps = 19 18:24:04 [INFO] train episode 25419: reward = -56.51, steps = 20 18:24:07 [INFO] train episode 25420: reward = -72.69, steps = 38 18:24:10 [INFO] train episode 25421: reward = -76.08, steps = 36 18:24:12 [INFO] train episode 25422: reward = -47.44, steps = 21 18:24:14 [INFO] train episode 25423: reward = -62.61, steps = 22 18:24:16 [INFO] train episode 25424: reward = -62.17, steps = 25 18:24:20 [INFO] train episode 25425: reward = -58.11, steps = 39 18:24:23 [INFO] train episode 25426: reward = -79.01, steps = 33 18:24:25 [INFO] train episode 25427: reward = -74.92, steps = 22 18:24:27 [INFO] train episode 25428: reward = -61.49, steps = 24 18:24:29 [INFO] train episode 25429: reward = -58.48, steps = 19 18:24:32 [INFO] train episode 25430: reward = -65.73, steps = 28 18:24:35 [INFO] train episode 25431: reward = -90.43, steps = 36 18:24:37 [INFO] train episode 25432: reward = -97.92, steps = 19 18:24:39 [INFO] train episode 25433: reward = -73.52, steps = 29 18:24:42 [INFO] train episode 25434: reward = -125.58, steps = 32 18:24:45 [INFO] train episode 25435: reward = -82.50, steps = 28 18:24:48 [INFO] train episode 25436: reward = -87.29, steps = 39 18:24:51 [INFO] train episode 25437: reward = -55.59, steps = 38 18:24:55 [INFO] train episode 25438: reward = -107.44, steps = 41 18:24:57 [INFO] train episode 25439: reward = -59.88, steps = 25 18:25:00 [INFO] train episode 25440: reward = -126.47, steps = 35 18:25:02 [INFO] train episode 25441: reward = -92.76, steps = 25 18:25:06 [INFO] train episode 25442: reward = -106.98, steps = 33 18:25:10 [INFO] train episode 25443: reward = -96.62, steps = 49 18:25:13 [INFO] train episode 25444: reward = -112.30, steps = 36 18:25:15 [INFO] train episode 25445: reward = -82.62, steps = 26 18:25:18 [INFO] train episode 25446: reward = -80.88, steps = 28 18:25:21 [INFO] train episode 25447: reward = -72.87, steps = 31 18:25:24 [INFO] train episode 25448: reward = -49.14, steps = 34 18:25:26 [INFO] train episode 25449: reward = -58.12, steps = 24 18:25:29 [INFO] train episode 25450: reward = -66.14, steps = 34 18:25:32 [INFO] train episode 25451: reward = -94.19, steps = 33 18:25:34 [INFO] train episode 25452: reward = -75.58, steps = 23 18:25:36 [INFO] train episode 25453: reward = -67.93, steps = 22 18:25:39 [INFO] train episode 25454: reward = -78.65, steps = 35 18:25:41 [INFO] train episode 25455: reward = -67.46, steps = 25 18:25:44 [INFO] train episode 25456: reward = -45.30, steps = 37 18:25:48 [INFO] train episode 25457: reward = -55.79, steps = 41 18:25:50 [INFO] train episode 25458: reward = -75.73, steps = 19 18:25:51 [INFO] train episode 25459: reward = -86.00, steps = 18 18:25:53 [INFO] train episode 25460: reward = -54.03, steps = 20 18:25:55 [INFO] train episode 25461: reward = -100.06, steps = 22 18:25:59 [INFO] train episode 25462: reward = -43.08, steps = 44 18:26:01 [INFO] train episode 25463: reward = -55.54, steps = 20 18:26:02 [INFO] train episode 25464: reward = -75.27, steps = 19 18:26:04 [INFO] train episode 25465: reward = -48.54, steps = 20 18:26:07 [INFO] train episode 25466: reward = -69.38, steps = 32 18:26:09 [INFO] train episode 25467: reward = -86.82, steps = 19 18:26:11 [INFO] train episode 25468: reward = -56.65, steps = 25 18:26:14 [INFO] train episode 25469: reward = -59.53, steps = 33 18:26:16 [INFO] train episode 25470: reward = -60.20, steps = 19 18:26:18 [INFO] train episode 25471: reward = -50.25, steps = 29 18:26:21 [INFO] train episode 25472: reward = -102.14, steps = 24 18:26:23 [INFO] train episode 25473: reward = -57.97, steps = 28 18:26:26 [INFO] train episode 25474: reward = -55.02, steps = 26 18:26:28 [INFO] train episode 25475: reward = -50.45, steps = 21 18:26:31 [INFO] train episode 25476: reward = -77.25, steps = 39 18:26:33 [INFO] train episode 25477: reward = -88.04, steps = 23 18:26:35 [INFO] train episode 25478: reward = -82.96, steps = 24 18:26:41 [INFO] train episode 25479: reward = -136.12, steps = 58 18:26:44 [INFO] train episode 25480: reward = -60.47, steps = 33 18:26:48 [INFO] train episode 25481: reward = -78.74, steps = 52 18:26:51 [INFO] train episode 25482: reward = -107.61, steps = 29 18:26:54 [INFO] train episode 25483: reward = -51.45, steps = 28 18:26:57 [INFO] train episode 25484: reward = -64.58, steps = 39 18:27:01 [INFO] train episode 25485: reward = -107.99, steps = 38 18:27:03 [INFO] train episode 25486: reward = -60.30, steps = 28 18:27:07 [INFO] train episode 25487: reward = -73.08, steps = 43 18:27:09 [INFO] train episode 25488: reward = -48.17, steps = 27 18:27:11 [INFO] train episode 25489: reward = -70.64, steps = 19 18:27:14 [INFO] train episode 25490: reward = -81.26, steps = 36 18:27:16 [INFO] train episode 25491: reward = -117.43, steps = 22 18:27:20 [INFO] train episode 25492: reward = -102.22, steps = 31 18:27:22 [INFO] train episode 25493: reward = -68.90, steps = 25 18:27:24 [INFO] train episode 25494: reward = -77.72, steps = 29 18:27:27 [INFO] train episode 25495: reward = -67.23, steps = 31 18:27:29 [INFO] train episode 25496: reward = -60.01, steps = 19 18:27:31 [INFO] train episode 25497: reward = -113.20, steps = 19 18:27:34 [INFO] train episode 25498: reward = -78.89, steps = 30 18:27:36 [INFO] train episode 25499: reward = -147.37, steps = 31 18:27:38 [INFO] train episode 25500: reward = -66.47, steps = 22 18:27:41 [INFO] train episode 25501: reward = -96.17, steps = 36 18:27:43 [INFO] train episode 25502: reward = -85.40, steps = 22 18:27:45 [INFO] train episode 25503: reward = -53.75, steps = 19 18:27:48 [INFO] train episode 25504: reward = -84.56, steps = 30 18:27:52 [INFO] train episode 25505: reward = -95.15, steps = 42 18:27:54 [INFO] train episode 25506: reward = -60.92, steps = 26 18:27:56 [INFO] train episode 25507: reward = -48.15, steps = 23 18:27:58 [INFO] train episode 25508: reward = -60.35, steps = 25 18:28:04 [INFO] train episode 25509: reward = -89.58, steps = 57 18:28:06 [INFO] train episode 25510: reward = -45.98, steps = 21 18:28:07 [INFO] train episode 25511: reward = -60.75, steps = 20 18:28:10 [INFO] train episode 25512: reward = -64.35, steps = 30 18:28:13 [INFO] train episode 25513: reward = -82.61, steps = 25 18:28:15 [INFO] train episode 25514: reward = -77.35, steps = 21 18:28:18 [INFO] train episode 25515: reward = -79.50, steps = 31 18:28:21 [INFO] train episode 25516: reward = -84.92, steps = 25 18:28:23 [INFO] train episode 25517: reward = -49.47, steps = 20 18:28:25 [INFO] train episode 25518: reward = -58.25, steps = 29 18:28:27 [INFO] train episode 25519: reward = -49.59, steps = 22 18:28:30 [INFO] train episode 25520: reward = -65.07, steps = 28 18:28:32 [INFO] train episode 25521: reward = -53.67, steps = 27 18:28:34 [INFO] train episode 25522: reward = -66.41, steps = 20 18:28:37 [INFO] train episode 25523: reward = -70.06, steps = 30 18:28:40 [INFO] train episode 25524: reward = -75.02, steps = 32 18:28:42 [INFO] train episode 25525: reward = -73.51, steps = 19 18:28:44 [INFO] train episode 25526: reward = -46.78, steps = 30 18:28:47 [INFO] train episode 25527: reward = -73.06, steps = 34 18:28:50 [INFO] train episode 25528: reward = -45.76, steps = 29 18:28:54 [INFO] train episode 25529: reward = -115.04, steps = 35 18:28:55 [INFO] train episode 25530: reward = -73.71, steps = 20 18:28:57 [INFO] train episode 25531: reward = -60.16, steps = 19 18:28:59 [INFO] train episode 25532: reward = -52.69, steps = 22 18:29:02 [INFO] train episode 25533: reward = -73.82, steps = 28 18:29:04 [INFO] train episode 25534: reward = -59.19, steps = 21 18:29:07 [INFO] train episode 25535: reward = -55.17, steps = 33 18:29:10 [INFO] train episode 25536: reward = -74.03, steps = 31 18:29:13 [INFO] train episode 25537: reward = -44.28, steps = 36 18:29:15 [INFO] train episode 25538: reward = -86.76, steps = 19 18:29:18 [INFO] train episode 25539: reward = -53.41, steps = 31 18:29:21 [INFO] train episode 25540: reward = -80.19, steps = 38 18:29:25 [INFO] train episode 25541: reward = -116.55, steps = 42 18:29:27 [INFO] train episode 25542: reward = -93.68, steps = 21 18:29:30 [INFO] train episode 25543: reward = -91.13, steps = 31 18:29:34 [INFO] train episode 25544: reward = -71.85, steps = 46 18:29:37 [INFO] train episode 25545: reward = -99.11, steps = 36 18:29:39 [INFO] train episode 25546: reward = -51.26, steps = 22 18:29:42 [INFO] train episode 25547: reward = -78.51, steps = 38 18:29:44 [INFO] train episode 25548: reward = -64.06, steps = 20 18:29:48 [INFO] train episode 25549: reward = -73.86, steps = 45 18:29:50 [INFO] train episode 25550: reward = -77.15, steps = 19 18:29:53 [INFO] train episode 25551: reward = -64.35, steps = 36 18:29:55 [INFO] train episode 25552: reward = -62.54, steps = 19 18:29:57 [INFO] train episode 25553: reward = -74.35, steps = 22 18:29:59 [INFO] train episode 25554: reward = -94.41, steps = 20 18:30:03 [INFO] train episode 25555: reward = -95.51, steps = 44 18:30:05 [INFO] train episode 25556: reward = -95.30, steps = 25 18:30:08 [INFO] train episode 25557: reward = -39.16, steps = 35 18:30:11 [INFO] train episode 25558: reward = -87.87, steps = 28 18:30:13 [INFO] train episode 25559: reward = -81.05, steps = 19 18:30:14 [INFO] train episode 25560: reward = -75.57, steps = 21 18:30:17 [INFO] train episode 25561: reward = -73.50, steps = 28 18:30:21 [INFO] train episode 25562: reward = -70.81, steps = 28 18:30:23 [INFO] train episode 25563: reward = -90.40, steps = 24 18:30:26 [INFO] train episode 25564: reward = -77.17, steps = 39 18:30:29 [INFO] train episode 25565: reward = -89.71, steps = 29 18:30:32 [INFO] train episode 25566: reward = -124.03, steps = 42 18:30:35 [INFO] train episode 25567: reward = -80.10, steps = 28 18:30:37 [INFO] train episode 25568: reward = -64.45, steps = 22 18:30:40 [INFO] train episode 25569: reward = -83.03, steps = 31 18:30:42 [INFO] train episode 25570: reward = -39.05, steps = 18 18:30:43 [INFO] train episode 25571: reward = -79.64, steps = 19 18:30:47 [INFO] train episode 25572: reward = -68.36, steps = 37 18:30:48 [INFO] train episode 25573: reward = -51.25, steps = 23 18:30:51 [INFO] train episode 25574: reward = -94.70, steps = 19 18:30:52 [INFO] train episode 25575: reward = -46.67, steps = 22 18:30:55 [INFO] train episode 25576: reward = -98.82, steps = 33 18:30:57 [INFO] train episode 25577: reward = -54.40, steps = 24 18:30:59 [INFO] train episode 25578: reward = -87.25, steps = 20 18:31:01 [INFO] train episode 25579: reward = -62.83, steps = 23 18:31:03 [INFO] train episode 25580: reward = -90.42, steps = 21 18:31:07 [INFO] train episode 25581: reward = -96.72, steps = 42 18:31:10 [INFO] train episode 25582: reward = -79.22, steps = 28 18:31:12 [INFO] train episode 25583: reward = -80.54, steps = 22 18:31:15 [INFO] train episode 25584: reward = -84.25, steps = 42 18:31:18 [INFO] train episode 25585: reward = -84.18, steps = 35 18:31:21 [INFO] train episode 25586: reward = -67.90, steps = 24 18:31:23 [INFO] train episode 25587: reward = -73.92, steps = 20 18:31:26 [INFO] train episode 25588: reward = -133.97, steps = 35 18:31:30 [INFO] train episode 25589: reward = -93.61, steps = 44 18:31:31 [INFO] train episode 25590: reward = -55.23, steps = 19 18:31:35 [INFO] train episode 25591: reward = -92.19, steps = 44 18:31:37 [INFO] train episode 25592: reward = -44.33, steps = 26 18:31:40 [INFO] train episode 25593: reward = -76.48, steps = 23 18:31:43 [INFO] train episode 25594: reward = -84.45, steps = 37 18:31:45 [INFO] train episode 25595: reward = -59.22, steps = 20 18:31:49 [INFO] train episode 25596: reward = -59.04, steps = 43 18:31:51 [INFO] train episode 25597: reward = -85.42, steps = 24 18:31:52 [INFO] train episode 25598: reward = -45.43, steps = 18 18:31:55 [INFO] train episode 25599: reward = -69.92, steps = 24 18:31:56 [INFO] train episode 25600: reward = -61.90, steps = 19 18:31:59 [INFO] train episode 25601: reward = -63.97, steps = 25 18:32:01 [INFO] train episode 25602: reward = -60.39, steps = 22 18:32:02 [INFO] train episode 25603: reward = -72.17, steps = 20 18:32:04 [INFO] train episode 25604: reward = -71.08, steps = 22 18:32:09 [INFO] train episode 25605: reward = -139.14, steps = 46 18:32:11 [INFO] train episode 25606: reward = -52.58, steps = 23 18:32:14 [INFO] train episode 25607: reward = -59.90, steps = 31 18:32:16 [INFO] train episode 25608: reward = -85.34, steps = 23 18:32:18 [INFO] train episode 25609: reward = -86.82, steps = 20 18:32:20 [INFO] train episode 25610: reward = -67.95, steps = 28 18:32:23 [INFO] train episode 25611: reward = -112.56, steps = 26 18:32:25 [INFO] train episode 25612: reward = -60.83, steps = 30 18:32:28 [INFO] train episode 25613: reward = -54.52, steps = 28 18:32:32 [INFO] train episode 25614: reward = -64.00, steps = 45 18:32:35 [INFO] train episode 25615: reward = -61.89, steps = 30 18:32:38 [INFO] train episode 25616: reward = -72.36, steps = 35 18:32:42 [INFO] train episode 25617: reward = -122.55, steps = 43 18:32:44 [INFO] train episode 25618: reward = -86.02, steps = 28 18:32:48 [INFO] train episode 25619: reward = -71.28, steps = 38 18:32:50 [INFO] train episode 25620: reward = -94.71, steps = 28 18:32:52 [INFO] train episode 25621: reward = -37.66, steps = 20 18:32:55 [INFO] train episode 25622: reward = -91.69, steps = 35 18:32:57 [INFO] train episode 25623: reward = -77.27, steps = 23 18:32:59 [INFO] train episode 25624: reward = -47.98, steps = 27 18:33:04 [INFO] train episode 25625: reward = -168.34, steps = 51 18:33:08 [INFO] train episode 25626: reward = -92.87, steps = 49 18:33:11 [INFO] train episode 25627: reward = -91.19, steps = 33 18:33:14 [INFO] train episode 25628: reward = -74.68, steps = 32 18:33:18 [INFO] train episode 25629: reward = -76.01, steps = 32 18:33:20 [INFO] train episode 25630: reward = -55.05, steps = 21 18:33:22 [INFO] train episode 25631: reward = -73.51, steps = 24 18:33:24 [INFO] train episode 25632: reward = -55.58, steps = 23 18:33:27 [INFO] train episode 25633: reward = -114.82, steps = 35 18:33:30 [INFO] train episode 25634: reward = -90.25, steps = 35 18:33:36 [INFO] train episode 25635: reward = -202.38, steps = 68 18:33:38 [INFO] train episode 25636: reward = -64.37, steps = 21 18:33:40 [INFO] train episode 25637: reward = -117.52, steps = 22 18:33:42 [INFO] train episode 25638: reward = -84.79, steps = 27 18:33:44 [INFO] train episode 25639: reward = -60.72, steps = 21 18:33:46 [INFO] train episode 25640: reward = -102.12, steps = 25 18:33:49 [INFO] train episode 25641: reward = -68.69, steps = 25 18:33:51 [INFO] train episode 25642: reward = -72.25, steps = 22 18:33:54 [INFO] train episode 25643: reward = -40.87, steps = 35 18:33:56 [INFO] train episode 25644: reward = -73.35, steps = 27 18:33:58 [INFO] train episode 25645: reward = -59.65, steps = 22 18:34:00 [INFO] train episode 25646: reward = -59.96, steps = 20 18:34:03 [INFO] train episode 25647: reward = -66.82, steps = 36 18:34:06 [INFO] train episode 25648: reward = -67.72, steps = 28 18:34:10 [INFO] train episode 25649: reward = -97.43, steps = 47 18:34:12 [INFO] train episode 25650: reward = -75.36, steps = 26 18:34:15 [INFO] train episode 25651: reward = -49.77, steps = 26 18:34:18 [INFO] train episode 25652: reward = -109.99, steps = 41 18:34:21 [INFO] train episode 25653: reward = -190.66, steps = 34 18:34:23 [INFO] train episode 25654: reward = -53.04, steps = 20 18:34:25 [INFO] train episode 25655: reward = -92.30, steps = 23 18:34:28 [INFO] train episode 25656: reward = -57.66, steps = 32 18:34:30 [INFO] train episode 25657: reward = -94.44, steps = 18 18:34:32 [INFO] train episode 25658: reward = -59.30, steps = 25 18:34:35 [INFO] train episode 25659: reward = -110.63, steps = 39 18:34:38 [INFO] train episode 25660: reward = -55.25, steps = 22 18:34:40 [INFO] train episode 25661: reward = -90.58, steps = 20 18:34:42 [INFO] train episode 25662: reward = -69.51, steps = 21 18:34:43 [INFO] train episode 25663: reward = -79.10, steps = 21 18:34:45 [INFO] train episode 25664: reward = -47.79, steps = 21 18:34:48 [INFO] train episode 25665: reward = -61.93, steps = 28 18:34:51 [INFO] train episode 25666: reward = -150.72, steps = 33 18:34:53 [INFO] train episode 25667: reward = -63.98, steps = 23 18:34:55 [INFO] train episode 25668: reward = -64.42, steps = 23 18:34:57 [INFO] train episode 25669: reward = -72.57, steps = 24 18:35:00 [INFO] train episode 25670: reward = -115.29, steps = 29 18:35:02 [INFO] train episode 25671: reward = -78.80, steps = 21 18:35:05 [INFO] train episode 25672: reward = -73.53, steps = 34 18:35:07 [INFO] train episode 25673: reward = -82.05, steps = 25 18:35:09 [INFO] train episode 25674: reward = -76.69, steps = 21 18:35:12 [INFO] train episode 25675: reward = -81.35, steps = 34 18:35:14 [INFO] train episode 25676: reward = -87.48, steps = 22 18:35:16 [INFO] train episode 25677: reward = -74.06, steps = 24 18:35:18 [INFO] train episode 25678: reward = -36.61, steps = 22 18:35:21 [INFO] train episode 25679: reward = -105.96, steps = 34 18:35:23 [INFO] train episode 25680: reward = -43.38, steps = 24 18:35:27 [INFO] train episode 25681: reward = -68.21, steps = 42 18:35:31 [INFO] train episode 25682: reward = -134.91, steps = 41 18:35:34 [INFO] train episode 25683: reward = -90.83, steps = 39 18:35:36 [INFO] train episode 25684: reward = -77.68, steps = 22 18:35:38 [INFO] train episode 25685: reward = -77.38, steps = 20 18:35:40 [INFO] train episode 25686: reward = -102.58, steps = 28 18:35:43 [INFO] train episode 25687: reward = -115.07, steps = 29 18:35:45 [INFO] train episode 25688: reward = -61.35, steps = 19 18:35:47 [INFO] train episode 25689: reward = -61.07, steps = 24 18:35:49 [INFO] train episode 25690: reward = -105.28, steps = 20 18:35:51 [INFO] train episode 25691: reward = -51.02, steps = 23 18:35:53 [INFO] train episode 25692: reward = -51.33, steps = 20 18:35:55 [INFO] train episode 25693: reward = -80.83, steps = 29 18:35:57 [INFO] train episode 25694: reward = -94.64, steps = 19 18:35:59 [INFO] train episode 25695: reward = -58.24, steps = 18 18:36:03 [INFO] train episode 25696: reward = -121.19, steps = 42 18:36:05 [INFO] train episode 25697: reward = -100.20, steps = 34 18:36:09 [INFO] train episode 25698: reward = -78.28, steps = 35 18:36:10 [INFO] train episode 25699: reward = -86.68, steps = 22 18:36:13 [INFO] train episode 25700: reward = -79.66, steps = 20 18:36:15 [INFO] train episode 25701: reward = -77.49, steps = 21 18:36:18 [INFO] train episode 25702: reward = -81.43, steps = 30 18:36:21 [INFO] train episode 25703: reward = -81.01, steps = 39 18:36:24 [INFO] train episode 25704: reward = -66.02, steps = 24 18:36:25 [INFO] train episode 25705: reward = -81.89, steps = 21 18:36:28 [INFO] train episode 25706: reward = -51.20, steps = 31 18:36:31 [INFO] train episode 25707: reward = -165.68, steps = 31 18:36:35 [INFO] train episode 25708: reward = -58.66, steps = 43 18:36:39 [INFO] train episode 25709: reward = -101.88, steps = 40 18:36:42 [INFO] train episode 25710: reward = -86.02, steps = 33 18:36:45 [INFO] train episode 25711: reward = -96.97, steps = 41 18:36:47 [INFO] train episode 25712: reward = -54.78, steps = 23 18:36:49 [INFO] train episode 25713: reward = -64.53, steps = 20 18:36:52 [INFO] train episode 25714: reward = -71.72, steps = 22 18:36:55 [INFO] train episode 25715: reward = -112.86, steps = 42 18:36:57 [INFO] train episode 25716: reward = -69.71, steps = 24 18:36:59 [INFO] train episode 25717: reward = -94.59, steps = 22 18:37:02 [INFO] train episode 25718: reward = -51.09, steps = 28 18:37:05 [INFO] train episode 25719: reward = -79.98, steps = 32 18:37:07 [INFO] train episode 25720: reward = -63.70, steps = 20 18:37:09 [INFO] train episode 25721: reward = -61.94, steps = 20 18:37:13 [INFO] train episode 25722: reward = -95.12, steps = 42 18:37:15 [INFO] train episode 25723: reward = -64.20, steps = 26 18:37:16 [INFO] train episode 25724: reward = -79.43, steps = 19 18:37:19 [INFO] train episode 25725: reward = -70.04, steps = 23 18:37:21 [INFO] train episode 25726: reward = -46.39, steps = 25 18:37:25 [INFO] train episode 25727: reward = -88.68, steps = 44 18:37:29 [INFO] train episode 25728: reward = -73.59, steps = 47 18:37:32 [INFO] train episode 25729: reward = -77.67, steps = 35 18:37:34 [INFO] train episode 25730: reward = -70.35, steps = 19 18:37:37 [INFO] train episode 25731: reward = -71.52, steps = 31 18:37:41 [INFO] train episode 25732: reward = -89.72, steps = 42 18:37:42 [INFO] train episode 25733: reward = -80.27, steps = 19 18:37:44 [INFO] train episode 25734: reward = -44.39, steps = 21 18:37:47 [INFO] train episode 25735: reward = -71.11, steps = 28 18:37:49 [INFO] train episode 25736: reward = -65.35, steps = 31 18:37:52 [INFO] train episode 25737: reward = -70.01, steps = 24 18:37:54 [INFO] train episode 25738: reward = -62.64, steps = 24 18:37:58 [INFO] train episode 25739: reward = -98.51, steps = 43 18:38:00 [INFO] train episode 25740: reward = -53.44, steps = 23 18:38:02 [INFO] train episode 25741: reward = -74.14, steps = 22 18:38:04 [INFO] train episode 25742: reward = -80.61, steps = 26 18:38:06 [INFO] train episode 25743: reward = -59.13, steps = 23 18:38:08 [INFO] train episode 25744: reward = -82.55, steps = 19 18:38:11 [INFO] train episode 25745: reward = -83.97, steps = 29 18:38:13 [INFO] train episode 25746: reward = -47.73, steps = 21 18:38:15 [INFO] train episode 25747: reward = -89.75, steps = 21 18:38:16 [INFO] train episode 25748: reward = -64.25, steps = 21 18:38:19 [INFO] train episode 25749: reward = -80.22, steps = 35 18:38:22 [INFO] train episode 25750: reward = -95.38, steps = 27 18:38:24 [INFO] train episode 25751: reward = -95.57, steps = 26 18:38:26 [INFO] train episode 25752: reward = -55.96, steps = 20 18:38:31 [INFO] train episode 25753: reward = -90.68, steps = 53 18:38:34 [INFO] train episode 25754: reward = -85.60, steps = 33 18:38:36 [INFO] train episode 25755: reward = -66.45, steps = 21 18:38:38 [INFO] train episode 25756: reward = -88.20, steps = 20 18:38:40 [INFO] train episode 25757: reward = -100.56, steps = 24 18:38:41 [INFO] train episode 25758: reward = -47.93, steps = 20 18:38:44 [INFO] train episode 25759: reward = -47.55, steps = 27 18:38:46 [INFO] train episode 25760: reward = -61.60, steps = 20 18:38:49 [INFO] train episode 25761: reward = -85.12, steps = 37 18:38:51 [INFO] train episode 25762: reward = -79.49, steps = 20 18:38:53 [INFO] train episode 25763: reward = -53.21, steps = 23 18:38:55 [INFO] train episode 25764: reward = -83.55, steps = 20 18:38:58 [INFO] train episode 25765: reward = -68.99, steps = 31 18:39:00 [INFO] train episode 25766: reward = -95.18, steps = 26 18:39:02 [INFO] train episode 25767: reward = -48.99, steps = 21 18:39:04 [INFO] train episode 25768: reward = -61.15, steps = 18 18:39:06 [INFO] train episode 25769: reward = -52.86, steps = 20 18:39:10 [INFO] train episode 25770: reward = -97.43, steps = 44 18:39:13 [INFO] train episode 25771: reward = -53.37, steps = 27 18:39:15 [INFO] train episode 25772: reward = -73.79, steps = 27 18:39:19 [INFO] train episode 25773: reward = -109.80, steps = 36 18:39:23 [INFO] train episode 25774: reward = -92.06, steps = 42 18:39:24 [INFO] train episode 25775: reward = -72.03, steps = 20 18:39:26 [INFO] train episode 25776: reward = -48.90, steps = 19 18:39:28 [INFO] train episode 25777: reward = -94.06, steps = 18 18:39:31 [INFO] train episode 25778: reward = -94.62, steps = 37 18:39:34 [INFO] train episode 25779: reward = -100.98, steps = 35 18:39:37 [INFO] train episode 25780: reward = -84.66, steps = 22 18:39:39 [INFO] train episode 25781: reward = -56.90, steps = 24 18:39:41 [INFO] train episode 25782: reward = -56.65, steps = 25 18:39:43 [INFO] train episode 25783: reward = -70.23, steps = 20 18:39:45 [INFO] train episode 25784: reward = -57.60, steps = 19 18:39:48 [INFO] train episode 25785: reward = -81.60, steps = 33 18:39:50 [INFO] train episode 25786: reward = -60.89, steps = 29 18:39:52 [INFO] train episode 25787: reward = -119.21, steps = 20 18:39:55 [INFO] train episode 25788: reward = -95.83, steps = 28 18:39:57 [INFO] train episode 25789: reward = -92.35, steps = 25 18:39:59 [INFO] train episode 25790: reward = -84.65, steps = 20 18:40:01 [INFO] train episode 25791: reward = -38.97, steps = 25 18:40:04 [INFO] train episode 25792: reward = -42.47, steps = 32 18:40:06 [INFO] train episode 25793: reward = -55.02, steps = 23 18:40:08 [INFO] train episode 25794: reward = -46.79, steps = 20 18:40:10 [INFO] train episode 25795: reward = -60.83, steps = 23 18:40:13 [INFO] train episode 25796: reward = -62.24, steps = 35 18:40:16 [INFO] train episode 25797: reward = -76.32, steps = 27 18:40:18 [INFO] train episode 25798: reward = -84.90, steps = 33 18:40:21 [INFO] train episode 25799: reward = -98.79, steps = 34 18:40:24 [INFO] train episode 25800: reward = -72.53, steps = 28 18:40:26 [INFO] train episode 25801: reward = -68.63, steps = 19 18:40:28 [INFO] train episode 25802: reward = -44.40, steps = 26 18:40:31 [INFO] train episode 25803: reward = -51.38, steps = 27 18:40:33 [INFO] train episode 25804: reward = -66.38, steps = 19 18:40:35 [INFO] train episode 25805: reward = -61.80, steps = 22 18:40:37 [INFO] train episode 25806: reward = -52.45, steps = 19 18:40:39 [INFO] train episode 25807: reward = -79.41, steps = 22 18:40:42 [INFO] train episode 25808: reward = -53.26, steps = 28 18:40:43 [INFO] train episode 25809: reward = -80.62, steps = 22 18:40:45 [INFO] train episode 25810: reward = -94.96, steps = 19 18:40:48 [INFO] train episode 25811: reward = -55.52, steps = 29 18:40:50 [INFO] train episode 25812: reward = -64.42, steps = 25 18:40:52 [INFO] train episode 25813: reward = -97.09, steps = 20 18:40:54 [INFO] train episode 25814: reward = -74.18, steps = 31 18:40:58 [INFO] train episode 25815: reward = -73.79, steps = 30 18:41:00 [INFO] train episode 25816: reward = -60.04, steps = 31 18:41:02 [INFO] train episode 25817: reward = -58.95, steps = 21 18:41:04 [INFO] train episode 25818: reward = -78.34, steps = 20 18:41:06 [INFO] train episode 25819: reward = -101.85, steps = 22 18:41:08 [INFO] train episode 25820: reward = -49.58, steps = 20 18:41:11 [INFO] train episode 25821: reward = -105.70, steps = 37 18:41:13 [INFO] train episode 25822: reward = -83.40, steps = 24 18:41:17 [INFO] train episode 25823: reward = -77.90, steps = 31 18:41:18 [INFO] train episode 25824: reward = -62.80, steps = 21 18:41:20 [INFO] train episode 25825: reward = -50.79, steps = 23 18:41:22 [INFO] train episode 25826: reward = -61.74, steps = 20 18:41:24 [INFO] train episode 25827: reward = -60.73, steps = 22 18:41:26 [INFO] train episode 25828: reward = -55.60, steps = 20 18:41:29 [INFO] train episode 25829: reward = -122.36, steps = 38 18:41:32 [INFO] train episode 25830: reward = -85.80, steps = 25 18:41:34 [INFO] train episode 25831: reward = -62.83, steps = 22 18:41:36 [INFO] train episode 25832: reward = -60.55, steps = 20 18:41:38 [INFO] train episode 25833: reward = -54.03, steps = 19 18:41:39 [INFO] train episode 25834: reward = -73.59, steps = 19 18:41:42 [INFO] train episode 25835: reward = -86.93, steps = 31 18:41:44 [INFO] train episode 25836: reward = -38.81, steps = 21 18:41:48 [INFO] train episode 25837: reward = -53.19, steps = 39 18:41:51 [INFO] train episode 25838: reward = -47.48, steps = 41 18:41:53 [INFO] train episode 25839: reward = -70.30, steps = 20 18:41:56 [INFO] train episode 25840: reward = -55.98, steps = 30 18:41:58 [INFO] train episode 25841: reward = -83.98, steps = 28 18:42:01 [INFO] train episode 25842: reward = -74.94, steps = 36 18:42:05 [INFO] train episode 25843: reward = -75.62, steps = 34 18:42:07 [INFO] train episode 25844: reward = -70.86, steps = 21 18:42:09 [INFO] train episode 25845: reward = -99.90, steps = 19 18:42:11 [INFO] train episode 25846: reward = -97.88, steps = 20 18:42:15 [INFO] train episode 25847: reward = -40.77, steps = 40 18:42:17 [INFO] train episode 25848: reward = -79.71, steps = 26 18:42:20 [INFO] train episode 25849: reward = -78.84, steps = 33 18:42:23 [INFO] train episode 25850: reward = -102.14, steps = 28 18:42:26 [INFO] train episode 25851: reward = -74.10, steps = 33 18:42:27 [INFO] train episode 25852: reward = -81.10, steps = 20 18:42:29 [INFO] train episode 25853: reward = -57.57, steps = 21 18:42:31 [INFO] train episode 25854: reward = -57.20, steps = 20 18:42:33 [INFO] train episode 25855: reward = -74.44, steps = 20 18:42:35 [INFO] train episode 25856: reward = -64.29, steps = 22 18:42:39 [INFO] train episode 25857: reward = -87.25, steps = 44 18:42:42 [INFO] train episode 25858: reward = -87.55, steps = 27 18:42:44 [INFO] train episode 25859: reward = -98.00, steps = 27 18:42:46 [INFO] train episode 25860: reward = -94.48, steps = 24 18:42:48 [INFO] train episode 25861: reward = -62.41, steps = 19 18:42:50 [INFO] train episode 25862: reward = -76.71, steps = 19 18:42:52 [INFO] train episode 25863: reward = -95.48, steps = 24 18:42:54 [INFO] train episode 25864: reward = -92.46, steps = 24 18:42:57 [INFO] train episode 25865: reward = -72.04, steps = 29 18:42:59 [INFO] train episode 25866: reward = -81.00, steps = 26 18:43:01 [INFO] train episode 25867: reward = -50.76, steps = 21 18:43:03 [INFO] train episode 25868: reward = -83.46, steps = 25 18:43:05 [INFO] train episode 25869: reward = -86.41, steps = 26 18:43:08 [INFO] train episode 25870: reward = -110.52, steps = 28 18:43:12 [INFO] train episode 25871: reward = -110.04, steps = 38 18:43:14 [INFO] train episode 25872: reward = -68.05, steps = 25 18:43:16 [INFO] train episode 25873: reward = -60.48, steps = 19 18:43:19 [INFO] train episode 25874: reward = -83.85, steps = 36 18:43:21 [INFO] train episode 25875: reward = -61.08, steps = 26 18:43:24 [INFO] train episode 25876: reward = -75.24, steps = 28 18:43:26 [INFO] train episode 25877: reward = -46.87, steps = 20 18:43:28 [INFO] train episode 25878: reward = -51.52, steps = 28 18:43:31 [INFO] train episode 25879: reward = -83.01, steps = 33 18:43:33 [INFO] train episode 25880: reward = -71.18, steps = 19 18:43:35 [INFO] train episode 25881: reward = -45.14, steps = 21 18:43:37 [INFO] train episode 25882: reward = -61.94, steps = 27 18:43:40 [INFO] train episode 25883: reward = -90.38, steps = 32 18:43:43 [INFO] train episode 25884: reward = -50.42, steps = 22 18:43:45 [INFO] train episode 25885: reward = -68.31, steps = 26 18:43:47 [INFO] train episode 25886: reward = -66.24, steps = 20 18:43:50 [INFO] train episode 25887: reward = -65.20, steps = 35 18:43:52 [INFO] train episode 25888: reward = -65.40, steps = 20 18:43:54 [INFO] train episode 25889: reward = -60.73, steps = 23 18:43:55 [INFO] train episode 25890: reward = -65.66, steps = 19 18:43:57 [INFO] train episode 25891: reward = -63.00, steps = 21 18:43:59 [INFO] train episode 25892: reward = -61.93, steps = 22 18:44:01 [INFO] train episode 25893: reward = -76.41, steps = 21 18:44:04 [INFO] train episode 25894: reward = -100.33, steps = 29 18:44:06 [INFO] train episode 25895: reward = -64.96, steps = 23 18:44:07 [INFO] train episode 25896: reward = -76.30, steps = 18 18:44:09 [INFO] train episode 25897: reward = -117.64, steps = 23 18:44:12 [INFO] train episode 25898: reward = -76.77, steps = 29 18:44:14 [INFO] train episode 25899: reward = -46.27, steps = 20 18:44:16 [INFO] train episode 25900: reward = -100.55, steps = 22 18:44:18 [INFO] train episode 25901: reward = -72.90, steps = 19 18:44:20 [INFO] train episode 25902: reward = -87.12, steps = 27 18:44:25 [INFO] train episode 25903: reward = -81.94, steps = 47 18:44:28 [INFO] train episode 25904: reward = -123.10, steps = 39 18:44:30 [INFO] train episode 25905: reward = -53.83, steps = 20 18:44:32 [INFO] train episode 25906: reward = -48.61, steps = 22 18:44:34 [INFO] train episode 25907: reward = -58.91, steps = 19 18:44:37 [INFO] train episode 25908: reward = -76.69, steps = 38 18:44:39 [INFO] train episode 25909: reward = -67.75, steps = 21 18:44:41 [INFO] train episode 25910: reward = -138.26, steps = 21 18:44:43 [INFO] train episode 25911: reward = -94.50, steps = 23 18:44:45 [INFO] train episode 25912: reward = -64.39, steps = 19 18:44:47 [INFO] train episode 25913: reward = -74.51, steps = 21 18:44:49 [INFO] train episode 25914: reward = -88.60, steps = 26 18:44:51 [INFO] train episode 25915: reward = -79.00, steps = 20 18:44:53 [INFO] train episode 25916: reward = -62.33, steps = 19 18:44:55 [INFO] train episode 25917: reward = -86.57, steps = 24 18:44:57 [INFO] train episode 25918: reward = -83.96, steps = 19 18:44:59 [INFO] train episode 25919: reward = -93.70, steps = 31 18:45:03 [INFO] train episode 25920: reward = -68.85, steps = 37 18:45:05 [INFO] train episode 25921: reward = -85.54, steps = 19 18:45:08 [INFO] train episode 25922: reward = -42.75, steps = 22 18:45:10 [INFO] train episode 25923: reward = -65.98, steps = 31 18:45:12 [INFO] train episode 25924: reward = -68.09, steps = 20 18:45:16 [INFO] train episode 25925: reward = -63.24, steps = 42 18:45:18 [INFO] train episode 25926: reward = -84.76, steps = 22 18:45:21 [INFO] train episode 25927: reward = -165.00, steps = 34 18:45:24 [INFO] train episode 25928: reward = -89.80, steps = 29 18:45:26 [INFO] train episode 25929: reward = -72.76, steps = 26 18:45:28 [INFO] train episode 25930: reward = -90.29, steps = 23 18:45:31 [INFO] train episode 25931: reward = -70.23, steps = 30 18:45:34 [INFO] train episode 25932: reward = -65.19, steps = 30 18:45:36 [INFO] train episode 25933: reward = -80.97, steps = 29 18:45:38 [INFO] train episode 25934: reward = -63.92, steps = 18 18:45:41 [INFO] train episode 25935: reward = -120.84, steps = 35 18:45:43 [INFO] train episode 25936: reward = -83.63, steps = 25 18:45:45 [INFO] train episode 25937: reward = -54.27, steps = 21 18:45:49 [INFO] train episode 25938: reward = -81.82, steps = 36 18:45:50 [INFO] train episode 25939: reward = -70.69, steps = 19 18:45:54 [INFO] train episode 25940: reward = -101.25, steps = 44 18:45:57 [INFO] train episode 25941: reward = -61.48, steps = 28 18:46:00 [INFO] train episode 25942: reward = -67.13, steps = 36 18:46:03 [INFO] train episode 25943: reward = -57.95, steps = 31 18:46:05 [INFO] train episode 25944: reward = -64.96, steps = 25 18:46:07 [INFO] train episode 25945: reward = -55.42, steps = 19 18:46:08 [INFO] train episode 25946: reward = -72.04, steps = 18 18:46:10 [INFO] train episode 25947: reward = -118.46, steps = 20 18:46:13 [INFO] train episode 25948: reward = -64.83, steps = 25 18:46:14 [INFO] train episode 25949: reward = -127.93, steps = 19 18:46:16 [INFO] train episode 25950: reward = -61.44, steps = 22 18:46:18 [INFO] train episode 25951: reward = -87.33, steps = 25 18:46:21 [INFO] train episode 25952: reward = -83.36, steps = 24 18:46:23 [INFO] train episode 25953: reward = -69.54, steps = 23 18:46:26 [INFO] train episode 25954: reward = -90.48, steps = 38 18:46:29 [INFO] train episode 25955: reward = -53.99, steps = 30 18:46:32 [INFO] train episode 25956: reward = -90.71, steps = 27 18:46:35 [INFO] train episode 25957: reward = -81.89, steps = 35 18:46:37 [INFO] train episode 25958: reward = -51.69, steps = 26 18:46:39 [INFO] train episode 25959: reward = -78.96, steps = 19 18:46:42 [INFO] train episode 25960: reward = -74.41, steps = 36 18:46:44 [INFO] train episode 25961: reward = -77.11, steps = 19 18:46:46 [INFO] train episode 25962: reward = -75.76, steps = 20 18:46:49 [INFO] train episode 25963: reward = -162.52, steps = 40 18:46:51 [INFO] train episode 25964: reward = -63.56, steps = 20 18:46:53 [INFO] train episode 25965: reward = -103.50, steps = 23 18:46:56 [INFO] train episode 25966: reward = -125.58, steps = 35 18:46:59 [INFO] train episode 25967: reward = -149.70, steps = 27 18:47:01 [INFO] train episode 25968: reward = -63.40, steps = 27 18:47:05 [INFO] train episode 25969: reward = -108.23, steps = 36 18:47:07 [INFO] train episode 25970: reward = -82.26, steps = 29 18:47:09 [INFO] train episode 25971: reward = -47.42, steps = 19 18:47:11 [INFO] train episode 25972: reward = -82.38, steps = 20 18:47:12 [INFO] train episode 25973: reward = -60.96, steps = 17 18:47:15 [INFO] train episode 25974: reward = -101.63, steps = 27 18:47:17 [INFO] train episode 25975: reward = -72.05, steps = 22 18:47:19 [INFO] train episode 25976: reward = -83.32, steps = 19 18:47:21 [INFO] train episode 25977: reward = -121.67, steps = 21 18:47:24 [INFO] train episode 25978: reward = -106.53, steps = 36 18:47:26 [INFO] train episode 25979: reward = -79.38, steps = 25 18:47:28 [INFO] train episode 25980: reward = -48.07, steps = 24 18:47:30 [INFO] train episode 25981: reward = -59.42, steps = 19 18:47:34 [INFO] train episode 25982: reward = -54.09, steps = 37 18:47:36 [INFO] train episode 25983: reward = -61.59, steps = 22 18:47:38 [INFO] train episode 25984: reward = -81.22, steps = 30 18:47:41 [INFO] train episode 25985: reward = -73.90, steps = 30 18:47:43 [INFO] train episode 25986: reward = -77.35, steps = 21 18:47:45 [INFO] train episode 25987: reward = -69.11, steps = 27 18:47:47 [INFO] train episode 25988: reward = -62.19, steps = 23 18:47:52 [INFO] train episode 25989: reward = -197.60, steps = 55 18:47:55 [INFO] train episode 25990: reward = -70.30, steps = 31 18:47:57 [INFO] train episode 25991: reward = -56.71, steps = 23 18:48:00 [INFO] train episode 25992: reward = -82.46, steps = 27 18:48:02 [INFO] train episode 25993: reward = -59.54, steps = 27 18:48:05 [INFO] train episode 25994: reward = -62.48, steps = 22 18:48:08 [INFO] train episode 25995: reward = -61.31, steps = 32 18:48:10 [INFO] train episode 25996: reward = -60.90, steps = 22 18:48:13 [INFO] train episode 25997: reward = -85.43, steps = 34 18:48:15 [INFO] train episode 25998: reward = -46.30, steps = 20 18:48:17 [INFO] train episode 25999: reward = -59.65, steps = 25 18:48:20 [INFO] train episode 26000: reward = -81.71, steps = 32 18:48:22 [INFO] train episode 26001: reward = -128.28, steps = 28 18:48:25 [INFO] train episode 26002: reward = -62.56, steps = 25 18:48:27 [INFO] train episode 26003: reward = -112.26, steps = 29 18:48:29 [INFO] train episode 26004: reward = -46.82, steps = 24 18:48:31 [INFO] train episode 26005: reward = -67.02, steps = 19 18:48:33 [INFO] train episode 26006: reward = -54.09, steps = 22 18:48:35 [INFO] train episode 26007: reward = -80.77, steps = 22 18:48:37 [INFO] train episode 26008: reward = -45.79, steps = 22 18:48:39 [INFO] train episode 26009: reward = -56.17, steps = 21 18:48:42 [INFO] train episode 26010: reward = -72.84, steps = 27 18:48:44 [INFO] train episode 26011: reward = -128.40, steps = 21 18:48:46 [INFO] train episode 26012: reward = -80.39, steps = 23 18:48:48 [INFO] train episode 26013: reward = -52.72, steps = 24 18:48:50 [INFO] train episode 26014: reward = -76.22, steps = 24 18:48:53 [INFO] train episode 26015: reward = -84.41, steps = 30 18:48:55 [INFO] train episode 26016: reward = -58.39, steps = 21 18:48:58 [INFO] train episode 26017: reward = -71.33, steps = 35 18:49:02 [INFO] train episode 26018: reward = -89.63, steps = 44 18:49:04 [INFO] train episode 26019: reward = -133.35, steps = 25 18:49:07 [INFO] train episode 26020: reward = -57.88, steps = 26 18:49:09 [INFO] train episode 26021: reward = -39.35, steps = 24 18:49:11 [INFO] train episode 26022: reward = -70.10, steps = 26 18:49:14 [INFO] train episode 26023: reward = -110.09, steps = 25 18:49:16 [INFO] train episode 26024: reward = -39.04, steps = 21 18:49:18 [INFO] train episode 26025: reward = -53.33, steps = 21 18:49:20 [INFO] train episode 26026: reward = -68.25, steps = 27 18:49:23 [INFO] train episode 26027: reward = -94.19, steps = 28 18:49:25 [INFO] train episode 26028: reward = -79.34, steps = 28 18:49:27 [INFO] train episode 26029: reward = -88.35, steps = 21 18:49:30 [INFO] train episode 26030: reward = -81.20, steps = 29 18:49:33 [INFO] train episode 26031: reward = -77.59, steps = 27 18:49:35 [INFO] train episode 26032: reward = -56.79, steps = 25 18:49:36 [INFO] train episode 26033: reward = -48.05, steps = 19 18:49:39 [INFO] train episode 26034: reward = -92.78, steps = 26 18:49:41 [INFO] train episode 26035: reward = -122.34, steps = 25 18:49:43 [INFO] train episode 26036: reward = -65.28, steps = 22 18:49:45 [INFO] train episode 26037: reward = -80.74, steps = 23 18:49:48 [INFO] train episode 26038: reward = -59.04, steps = 28 18:49:50 [INFO] train episode 26039: reward = -61.95, steps = 30 18:49:53 [INFO] train episode 26040: reward = -127.39, steps = 33 18:49:55 [INFO] train episode 26041: reward = -56.04, steps = 23 18:49:58 [INFO] train episode 26042: reward = -71.24, steps = 28 18:49:59 [INFO] train episode 26043: reward = -66.05, steps = 19 18:50:03 [INFO] train episode 26044: reward = -87.86, steps = 41 18:50:06 [INFO] train episode 26045: reward = -112.01, steps = 29 18:50:08 [INFO] train episode 26046: reward = -43.90, steps = 21 18:50:09 [INFO] train episode 26047: reward = -88.20, steps = 19 18:50:11 [INFO] train episode 26048: reward = -53.28, steps = 20 18:50:13 [INFO] train episode 26049: reward = -70.45, steps = 22 18:50:16 [INFO] train episode 26050: reward = -60.78, steps = 28 18:50:17 [INFO] train episode 26051: reward = -90.43, steps = 19 18:50:20 [INFO] train episode 26052: reward = -62.65, steps = 22 18:50:21 [INFO] train episode 26053: reward = -81.79, steps = 21 18:50:24 [INFO] train episode 26054: reward = -78.36, steps = 25 18:50:26 [INFO] train episode 26055: reward = -55.97, steps = 30 18:50:28 [INFO] train episode 26056: reward = -67.41, steps = 21 18:50:31 [INFO] train episode 26057: reward = -81.88, steps = 38 18:50:34 [INFO] train episode 26058: reward = -66.26, steps = 24 18:50:36 [INFO] train episode 26059: reward = -46.01, steps = 24 18:50:38 [INFO] train episode 26060: reward = -143.00, steps = 20 18:50:40 [INFO] train episode 26061: reward = -62.59, steps = 19 18:50:42 [INFO] train episode 26062: reward = -79.84, steps = 27 18:50:44 [INFO] train episode 26063: reward = -68.70, steps = 24 18:50:47 [INFO] train episode 26064: reward = -95.92, steps = 31 18:50:50 [INFO] train episode 26065: reward = -46.32, steps = 29 18:50:52 [INFO] train episode 26066: reward = -140.23, steps = 19 18:50:55 [INFO] train episode 26067: reward = -64.66, steps = 32 18:50:56 [INFO] train episode 26068: reward = -71.88, steps = 20 18:50:59 [INFO] train episode 26069: reward = -63.86, steps = 29 18:51:02 [INFO] train episode 26070: reward = -56.07, steps = 27 18:51:05 [INFO] train episode 26071: reward = -65.01, steps = 29 18:51:06 [INFO] train episode 26072: reward = -105.17, steps = 20 18:51:09 [INFO] train episode 26073: reward = -46.12, steps = 21 18:51:12 [INFO] train episode 26074: reward = -93.90, steps = 37 18:51:14 [INFO] train episode 26075: reward = -46.97, steps = 21 18:51:17 [INFO] train episode 26076: reward = -87.64, steps = 31 18:51:18 [INFO] train episode 26077: reward = -47.38, steps = 20 18:51:20 [INFO] train episode 26078: reward = -58.94, steps = 20 18:51:22 [INFO] train episode 26079: reward = -71.35, steps = 25 18:51:25 [INFO] train episode 26080: reward = -107.60, steps = 21 18:51:27 [INFO] train episode 26081: reward = -52.91, steps = 19 18:51:29 [INFO] train episode 26082: reward = -74.43, steps = 25 18:51:32 [INFO] train episode 26083: reward = -83.41, steps = 33 18:51:35 [INFO] train episode 26084: reward = -76.50, steps = 34 18:51:37 [INFO] train episode 26085: reward = -74.86, steps = 28 18:51:40 [INFO] train episode 26086: reward = -92.39, steps = 29 18:51:43 [INFO] train episode 26087: reward = -62.65, steps = 29 18:51:45 [INFO] train episode 26088: reward = -46.72, steps = 20 18:51:48 [INFO] train episode 26089: reward = -111.18, steps = 41 18:51:51 [INFO] train episode 26090: reward = -59.61, steps = 35 18:51:54 [INFO] train episode 26091: reward = -67.91, steps = 24 18:51:56 [INFO] train episode 26092: reward = -65.26, steps = 24 18:51:59 [INFO] train episode 26093: reward = -93.18, steps = 33 18:52:01 [INFO] train episode 26094: reward = -45.77, steps = 19 18:52:03 [INFO] train episode 26095: reward = -48.83, steps = 23 18:52:05 [INFO] train episode 26096: reward = -69.62, steps = 19 18:52:07 [INFO] train episode 26097: reward = -87.72, steps = 28 18:52:10 [INFO] train episode 26098: reward = -75.43, steps = 25 18:52:12 [INFO] train episode 26099: reward = -38.41, steps = 26 18:52:15 [INFO] train episode 26100: reward = -56.45, steps = 32 18:52:18 [INFO] train episode 26101: reward = -109.27, steps = 33 18:52:20 [INFO] train episode 26102: reward = -57.94, steps = 19 18:52:22 [INFO] train episode 26103: reward = -58.34, steps = 22 18:52:24 [INFO] train episode 26104: reward = -62.84, steps = 28 18:52:26 [INFO] train episode 26105: reward = -64.57, steps = 21 18:52:29 [INFO] train episode 26106: reward = -87.16, steps = 26 18:52:31 [INFO] train episode 26107: reward = -118.71, steps = 27 18:52:33 [INFO] train episode 26108: reward = -80.46, steps = 20 18:52:36 [INFO] train episode 26109: reward = -55.54, steps = 27 18:52:38 [INFO] train episode 26110: reward = -46.73, steps = 25 18:52:41 [INFO] train episode 26111: reward = -66.30, steps = 34 18:52:43 [INFO] train episode 26112: reward = -66.09, steps = 27 18:52:46 [INFO] train episode 26113: reward = -65.43, steps = 21 18:52:48 [INFO] train episode 26114: reward = -96.30, steps = 28 18:52:50 [INFO] train episode 26115: reward = -100.91, steps = 19 18:52:54 [INFO] train episode 26116: reward = -71.48, steps = 38 18:52:56 [INFO] train episode 26117: reward = -55.77, steps = 27 18:52:58 [INFO] train episode 26118: reward = -79.22, steps = 24 18:53:00 [INFO] train episode 26119: reward = -45.52, steps = 23 18:53:04 [INFO] train episode 26120: reward = -91.72, steps = 37 18:53:06 [INFO] train episode 26121: reward = -78.04, steps = 21 18:53:09 [INFO] train episode 26122: reward = -65.59, steps = 30 18:53:10 [INFO] train episode 26123: reward = -71.73, steps = 20 18:53:14 [INFO] train episode 26124: reward = -45.18, steps = 35 18:53:15 [INFO] train episode 26125: reward = -68.00, steps = 19 18:53:17 [INFO] train episode 26126: reward = -72.64, steps = 22 18:53:20 [INFO] train episode 26127: reward = -76.11, steps = 28 18:53:22 [INFO] train episode 26128: reward = -87.89, steps = 20 18:53:24 [INFO] train episode 26129: reward = -62.05, steps = 21 18:53:25 [INFO] train episode 26130: reward = -52.51, steps = 19 18:53:27 [INFO] train episode 26131: reward = -109.44, steps = 19 18:53:31 [INFO] train episode 26132: reward = -80.05, steps = 39 18:53:33 [INFO] train episode 26133: reward = -82.62, steps = 26 18:53:35 [INFO] train episode 26134: reward = -53.38, steps = 27 18:53:38 [INFO] train episode 26135: reward = -55.87, steps = 25 18:53:41 [INFO] train episode 26136: reward = -91.39, steps = 30 18:53:44 [INFO] train episode 26137: reward = -71.27, steps = 37 18:53:45 [INFO] train episode 26138: reward = -73.22, steps = 18 18:53:47 [INFO] train episode 26139: reward = -91.74, steps = 22 18:53:49 [INFO] train episode 26140: reward = -53.69, steps = 21 18:53:52 [INFO] train episode 26141: reward = -113.27, steps = 27 18:53:56 [INFO] train episode 26142: reward = -97.92, steps = 42 18:53:58 [INFO] train episode 26143: reward = -71.38, steps = 23 18:54:00 [INFO] train episode 26144: reward = -89.13, steps = 19 18:54:04 [INFO] train episode 26145: reward = -90.84, steps = 42 18:54:06 [INFO] train episode 26146: reward = -62.76, steps = 27 18:54:08 [INFO] train episode 26147: reward = -82.03, steps = 19 18:54:09 [INFO] train episode 26148: reward = -47.41, steps = 20 18:54:12 [INFO] train episode 26149: reward = -98.60, steps = 23 18:54:14 [INFO] train episode 26150: reward = -53.27, steps = 20 18:54:16 [INFO] train episode 26151: reward = -92.62, steps = 24 18:54:17 [INFO] train episode 26152: reward = -51.37, steps = 19 18:54:19 [INFO] train episode 26153: reward = -105.09, steps = 21 18:54:22 [INFO] train episode 26154: reward = -70.11, steps = 25 18:54:24 [INFO] train episode 26155: reward = -44.77, steps = 25 18:54:28 [INFO] train episode 26156: reward = -83.41, steps = 41 18:54:30 [INFO] train episode 26157: reward = -120.97, steps = 21 18:54:33 [INFO] train episode 26158: reward = -69.45, steps = 38 18:54:35 [INFO] train episode 26159: reward = -83.94, steps = 19 18:54:37 [INFO] train episode 26160: reward = -64.33, steps = 25 18:54:39 [INFO] train episode 26161: reward = -59.19, steps = 19 18:54:41 [INFO] train episode 26162: reward = -110.25, steps = 27 18:54:43 [INFO] train episode 26163: reward = -63.16, steps = 22 18:54:45 [INFO] train episode 26164: reward = -66.64, steps = 20 18:54:48 [INFO] train episode 26165: reward = -73.01, steps = 29 18:54:51 [INFO] train episode 26166: reward = -78.83, steps = 30 18:54:53 [INFO] train episode 26167: reward = -102.81, steps = 23 18:54:54 [INFO] train episode 26168: reward = -77.65, steps = 18 18:54:57 [INFO] train episode 26169: reward = -51.47, steps = 34 18:54:59 [INFO] train episode 26170: reward = -44.85, steps = 23 18:55:02 [INFO] train episode 26171: reward = -66.48, steps = 23 18:55:04 [INFO] train episode 26172: reward = -83.79, steps = 20 18:55:06 [INFO] train episode 26173: reward = -42.74, steps = 21 18:55:08 [INFO] train episode 26174: reward = -65.92, steps = 25 18:55:10 [INFO] train episode 26175: reward = -92.00, steps = 29 18:55:13 [INFO] train episode 26176: reward = -50.30, steps = 29 18:55:15 [INFO] train episode 26177: reward = -94.22, steps = 26 18:55:19 [INFO] train episode 26178: reward = -82.91, steps = 33 18:55:21 [INFO] train episode 26179: reward = -82.47, steps = 24 18:55:23 [INFO] train episode 26180: reward = -78.62, steps = 22 18:55:24 [INFO] train episode 26181: reward = -72.25, steps = 18 18:55:26 [INFO] train episode 26182: reward = -48.57, steps = 22 18:55:28 [INFO] train episode 26183: reward = -51.15, steps = 24 18:55:31 [INFO] train episode 26184: reward = -161.68, steps = 24 18:55:34 [INFO] train episode 26185: reward = -78.90, steps = 28 18:55:35 [INFO] train episode 26186: reward = -68.50, steps = 19 18:55:37 [INFO] train episode 26187: reward = -77.91, steps = 19 18:55:39 [INFO] train episode 26188: reward = -80.47, steps = 25 18:55:43 [INFO] train episode 26189: reward = -61.96, steps = 44 18:55:45 [INFO] train episode 26190: reward = -66.27, steps = 19 18:55:47 [INFO] train episode 26191: reward = -92.30, steps = 22 18:55:49 [INFO] train episode 26192: reward = -70.92, steps = 22 18:55:51 [INFO] train episode 26193: reward = -81.65, steps = 25 18:55:53 [INFO] train episode 26194: reward = -117.06, steps = 18 18:55:56 [INFO] train episode 26195: reward = -67.06, steps = 31 18:55:57 [INFO] train episode 26196: reward = -51.09, steps = 21 18:55:59 [INFO] train episode 26197: reward = -71.46, steps = 20 18:56:02 [INFO] train episode 26198: reward = -104.46, steps = 34 18:56:04 [INFO] train episode 26199: reward = -72.93, steps = 19 18:56:07 [INFO] train episode 26200: reward = -96.04, steps = 26 18:56:09 [INFO] train episode 26201: reward = -35.85, steps = 23 18:56:11 [INFO] train episode 26202: reward = -69.80, steps = 23 18:56:15 [INFO] train episode 26203: reward = -68.92, steps = 41 18:56:17 [INFO] train episode 26204: reward = -58.89, steps = 26 18:56:19 [INFO] train episode 26205: reward = -42.97, steps = 26 18:56:22 [INFO] train episode 26206: reward = -59.97, steps = 29 18:56:24 [INFO] train episode 26207: reward = -50.17, steps = 21 18:56:28 [INFO] train episode 26208: reward = -112.13, steps = 52 18:56:32 [INFO] train episode 26209: reward = -98.57, steps = 39 18:56:33 [INFO] train episode 26210: reward = -71.25, steps = 20 18:56:35 [INFO] train episode 26211: reward = -71.77, steps = 19 18:56:37 [INFO] train episode 26212: reward = -78.32, steps = 18 18:56:41 [INFO] train episode 26213: reward = -72.95, steps = 38 18:56:43 [INFO] train episode 26214: reward = -84.89, steps = 25 18:56:45 [INFO] train episode 26215: reward = -56.93, steps = 27 18:56:48 [INFO] train episode 26216: reward = -94.72, steps = 29 18:56:50 [INFO] train episode 26217: reward = -73.60, steps = 30 18:56:53 [INFO] train episode 26218: reward = -152.48, steps = 32 18:56:57 [INFO] train episode 26219: reward = -38.76, steps = 28 18:56:59 [INFO] train episode 26220: reward = -55.25, steps = 23 18:57:01 [INFO] train episode 26221: reward = -75.39, steps = 24 18:57:03 [INFO] train episode 26222: reward = -57.55, steps = 24 18:57:06 [INFO] train episode 26223: reward = -108.47, steps = 26 18:57:08 [INFO] train episode 26224: reward = -48.31, steps = 28 18:57:11 [INFO] train episode 26225: reward = -56.17, steps = 35 18:57:13 [INFO] train episode 26226: reward = -50.01, steps = 20 18:57:15 [INFO] train episode 26227: reward = -78.40, steps = 20 18:57:17 [INFO] train episode 26228: reward = -64.44, steps = 20 18:57:19 [INFO] train episode 26229: reward = -84.08, steps = 21 18:57:22 [INFO] train episode 26230: reward = -73.97, steps = 39 18:57:24 [INFO] train episode 26231: reward = -55.18, steps = 21 18:57:27 [INFO] train episode 26232: reward = -107.54, steps = 27 18:57:30 [INFO] train episode 26233: reward = -47.96, steps = 27 18:57:33 [INFO] train episode 26234: reward = -113.38, steps = 36 18:57:35 [INFO] train episode 26235: reward = -52.48, steps = 29 18:57:38 [INFO] train episode 26236: reward = -95.45, steps = 29 18:57:40 [INFO] train episode 26237: reward = -56.96, steps = 20 18:57:43 [INFO] train episode 26238: reward = -77.87, steps = 33 18:57:44 [INFO] train episode 26239: reward = -72.13, steps = 21 18:57:47 [INFO] train episode 26240: reward = -62.01, steps = 25 18:57:50 [INFO] train episode 26241: reward = -78.03, steps = 30 18:57:51 [INFO] train episode 26242: reward = -77.09, steps = 18 18:57:53 [INFO] train episode 26243: reward = -70.78, steps = 26 18:57:55 [INFO] train episode 26244: reward = -57.32, steps = 22 18:57:57 [INFO] train episode 26245: reward = -65.38, steps = 18 18:57:59 [INFO] train episode 26246: reward = -73.97, steps = 21 18:58:01 [INFO] train episode 26247: reward = -58.57, steps = 20 18:58:03 [INFO] train episode 26248: reward = -91.60, steps = 27 18:58:05 [INFO] train episode 26249: reward = -77.91, steps = 19 18:58:09 [INFO] train episode 26250: reward = -77.11, steps = 40 18:58:12 [INFO] train episode 26251: reward = -103.94, steps = 42 18:58:16 [INFO] train episode 26252: reward = -69.34, steps = 43 18:58:19 [INFO] train episode 26253: reward = -73.65, steps = 25 18:58:20 [INFO] train episode 26254: reward = -123.69, steps = 19 18:58:24 [INFO] train episode 26255: reward = -92.82, steps = 39 18:58:27 [INFO] train episode 26256: reward = -101.01, steps = 37 18:58:29 [INFO] train episode 26257: reward = -56.14, steps = 22 18:58:31 [INFO] train episode 26258: reward = -73.29, steps = 30 18:58:33 [INFO] train episode 26259: reward = -77.82, steps = 22 18:58:37 [INFO] train episode 26260: reward = -95.10, steps = 41 18:58:41 [INFO] train episode 26261: reward = -106.46, steps = 38 18:58:43 [INFO] train episode 26262: reward = -71.78, steps = 21 18:58:45 [INFO] train episode 26263: reward = -69.29, steps = 26 18:58:47 [INFO] train episode 26264: reward = -75.64, steps = 28 18:58:49 [INFO] train episode 26265: reward = -76.10, steps = 21 18:58:52 [INFO] train episode 26266: reward = -42.88, steps = 31 18:58:55 [INFO] train episode 26267: reward = -93.79, steps = 35 18:58:57 [INFO] train episode 26268: reward = -61.16, steps = 22 18:59:00 [INFO] train episode 26269: reward = -59.60, steps = 27 18:59:02 [INFO] train episode 26270: reward = -70.34, steps = 21 18:59:03 [INFO] train episode 26271: reward = -85.97, steps = 19 18:59:06 [INFO] train episode 26272: reward = -96.77, steps = 31 18:59:09 [INFO] train episode 26273: reward = -110.91, steps = 35 18:59:12 [INFO] train episode 26274: reward = -81.60, steps = 37 18:59:15 [INFO] train episode 26275: reward = -125.34, steps = 24 18:59:17 [INFO] train episode 26276: reward = -44.43, steps = 32 18:59:20 [INFO] train episode 26277: reward = -104.09, steps = 33 18:59:25 [INFO] train episode 26278: reward = -195.97, steps = 50 18:59:27 [INFO] train episode 26279: reward = -149.28, steps = 19 18:59:29 [INFO] train episode 26280: reward = -71.09, steps = 20 18:59:31 [INFO] train episode 26281: reward = -113.22, steps = 22 18:59:33 [INFO] train episode 26282: reward = -60.21, steps = 32 18:59:35 [INFO] train episode 26283: reward = -73.74, steps = 21 18:59:37 [INFO] train episode 26284: reward = -83.40, steps = 23 18:59:41 [INFO] train episode 26285: reward = -153.56, steps = 34 18:59:44 [INFO] train episode 26286: reward = -79.78, steps = 35 18:59:45 [INFO] train episode 26287: reward = -58.70, steps = 19 18:59:48 [INFO] train episode 26288: reward = -104.17, steps = 34 18:59:50 [INFO] train episode 26289: reward = -103.49, steps = 19 18:59:53 [INFO] train episode 26290: reward = -109.01, steps = 25 18:59:55 [INFO] train episode 26291: reward = -64.57, steps = 24 18:59:57 [INFO] train episode 26292: reward = -120.96, steps = 19 18:59:59 [INFO] train episode 26293: reward = -64.30, steps = 21 19:00:01 [INFO] train episode 26294: reward = -84.80, steps = 27 19:00:03 [INFO] train episode 26295: reward = -120.18, steps = 25 19:00:05 [INFO] train episode 26296: reward = -50.19, steps = 22 19:00:08 [INFO] train episode 26297: reward = -72.94, steps = 33 19:00:10 [INFO] train episode 26298: reward = -53.33, steps = 21 19:00:13 [INFO] train episode 26299: reward = -47.87, steps = 25 19:00:15 [INFO] train episode 26300: reward = -106.77, steps = 26 19:00:17 [INFO] train episode 26301: reward = -82.13, steps = 20 19:00:18 [INFO] train episode 26302: reward = -70.59, steps = 21 19:00:20 [INFO] train episode 26303: reward = -68.10, steps = 18 19:00:22 [INFO] train episode 26304: reward = -75.72, steps = 24 19:00:24 [INFO] train episode 26305: reward = -65.71, steps = 27 19:00:26 [INFO] train episode 26306: reward = -140.93, steps = 19 19:00:28 [INFO] train episode 26307: reward = -72.04, steps = 19 19:00:31 [INFO] train episode 26308: reward = -58.09, steps = 28 19:00:32 [INFO] train episode 26309: reward = -76.96, steps = 19 19:00:34 [INFO] train episode 26310: reward = -70.30, steps = 21 19:00:36 [INFO] train episode 26311: reward = -56.01, steps = 25 19:00:38 [INFO] train episode 26312: reward = -62.53, steps = 23 19:00:40 [INFO] train episode 26313: reward = -103.80, steps = 22 19:00:42 [INFO] train episode 26314: reward = -65.71, steps = 22 19:00:46 [INFO] train episode 26315: reward = -91.39, steps = 33 19:00:47 [INFO] train episode 26316: reward = -71.95, steps = 19 19:00:49 [INFO] train episode 26317: reward = -86.85, steps = 19 19:00:51 [INFO] train episode 26318: reward = -67.86, steps = 24 19:00:54 [INFO] train episode 26319: reward = -58.95, steps = 30 19:00:56 [INFO] train episode 26320: reward = -73.80, steps = 27 19:00:58 [INFO] train episode 26321: reward = -46.83, steps = 24 19:01:00 [INFO] train episode 26322: reward = -57.61, steps = 20 19:01:04 [INFO] train episode 26323: reward = -150.74, steps = 40 19:01:06 [INFO] train episode 26324: reward = -92.37, steps = 23 19:01:08 [INFO] train episode 26325: reward = -127.66, steps = 20 19:01:10 [INFO] train episode 26326: reward = -47.87, steps = 23 19:01:12 [INFO] train episode 26327: reward = -91.01, steps = 27 19:01:14 [INFO] train episode 26328: reward = -60.82, steps = 26 19:01:17 [INFO] train episode 26329: reward = -76.92, steps = 30 19:01:20 [INFO] train episode 26330: reward = -78.13, steps = 26 19:01:21 [INFO] train episode 26331: reward = -51.88, steps = 21 19:01:24 [INFO] train episode 26332: reward = -77.80, steps = 26 19:01:25 [INFO] train episode 26333: reward = -90.90, steps = 19 19:01:27 [INFO] train episode 26334: reward = -84.54, steps = 22 19:01:29 [INFO] train episode 26335: reward = -89.06, steps = 21 19:01:31 [INFO] train episode 26336: reward = -73.78, steps = 27 19:01:34 [INFO] train episode 26337: reward = -119.41, steps = 21 19:01:36 [INFO] train episode 26338: reward = -133.29, steps = 23 19:01:38 [INFO] train episode 26339: reward = -55.37, steps = 26 19:01:40 [INFO] train episode 26340: reward = -85.93, steps = 22 19:01:44 [INFO] train episode 26341: reward = -45.99, steps = 44 19:01:45 [INFO] train episode 26342: reward = -69.99, steps = 19 19:01:48 [INFO] train episode 26343: reward = -87.20, steps = 29 19:01:51 [INFO] train episode 26344: reward = -71.33, steps = 25 19:01:52 [INFO] train episode 26345: reward = -65.04, steps = 19 19:01:54 [INFO] train episode 26346: reward = -156.84, steps = 26 19:01:56 [INFO] train episode 26347: reward = -47.80, steps = 20 19:01:58 [INFO] train episode 26348: reward = -58.80, steps = 19 19:02:02 [INFO] train episode 26349: reward = -130.75, steps = 42 19:02:04 [INFO] train episode 26350: reward = -50.77, steps = 22 19:02:06 [INFO] train episode 26351: reward = -66.29, steps = 25 19:02:08 [INFO] train episode 26352: reward = -80.92, steps = 23 19:02:10 [INFO] train episode 26353: reward = -77.12, steps = 19 19:02:12 [INFO] train episode 26354: reward = -60.53, steps = 21 19:02:14 [INFO] train episode 26355: reward = -77.17, steps = 22 19:02:16 [INFO] train episode 26356: reward = -104.63, steps = 29 19:02:19 [INFO] train episode 26357: reward = -74.87, steps = 23 19:02:20 [INFO] train episode 26358: reward = -63.15, steps = 21 19:02:23 [INFO] train episode 26359: reward = -81.58, steps = 19 19:02:25 [INFO] train episode 26360: reward = -84.02, steps = 21 19:02:28 [INFO] train episode 26361: reward = -109.68, steps = 37 19:02:30 [INFO] train episode 26362: reward = -46.43, steps = 27 19:02:32 [INFO] train episode 26363: reward = -110.15, steps = 26 19:02:34 [INFO] train episode 26364: reward = -79.39, steps = 19 19:02:37 [INFO] train episode 26365: reward = -69.12, steps = 32 19:02:40 [INFO] train episode 26366: reward = -84.00, steps = 29 19:02:43 [INFO] train episode 26367: reward = -113.71, steps = 32 19:02:45 [INFO] train episode 26368: reward = -102.37, steps = 25 19:02:48 [INFO] train episode 26369: reward = -63.18, steps = 29 19:02:51 [INFO] train episode 26370: reward = -97.95, steps = 30 19:02:54 [INFO] train episode 26371: reward = -96.66, steps = 30 19:02:56 [INFO] train episode 26372: reward = -81.38, steps = 22 19:02:59 [INFO] train episode 26373: reward = -66.56, steps = 26 19:03:01 [INFO] train episode 26374: reward = -50.01, steps = 20 19:03:03 [INFO] train episode 26375: reward = -60.94, steps = 31 19:03:06 [INFO] train episode 26376: reward = -73.98, steps = 24 19:03:07 [INFO] train episode 26377: reward = -75.62, steps = 20 19:03:09 [INFO] train episode 26378: reward = -75.46, steps = 20 19:03:12 [INFO] train episode 26379: reward = -58.06, steps = 28 19:03:15 [INFO] train episode 26380: reward = -62.27, steps = 29 19:03:18 [INFO] train episode 26381: reward = -63.67, steps = 36 19:03:19 [INFO] train episode 26382: reward = -78.97, steps = 18 19:03:21 [INFO] train episode 26383: reward = -102.15, steps = 23 19:03:23 [INFO] train episode 26384: reward = -41.55, steps = 20 19:03:25 [INFO] train episode 26385: reward = -83.01, steps = 25 19:03:28 [INFO] train episode 26386: reward = -87.29, steps = 30 19:03:30 [INFO] train episode 26387: reward = -67.33, steps = 19 19:03:32 [INFO] train episode 26388: reward = -80.08, steps = 27 19:03:34 [INFO] train episode 26389: reward = -88.62, steps = 20 19:03:36 [INFO] train episode 26390: reward = -119.70, steps = 24 19:03:39 [INFO] train episode 26391: reward = -48.54, steps = 32 19:03:41 [INFO] train episode 26392: reward = -61.77, steps = 20 19:03:43 [INFO] train episode 26393: reward = -45.52, steps = 20 19:03:45 [INFO] train episode 26394: reward = -87.09, steps = 27 19:03:48 [INFO] train episode 26395: reward = -65.12, steps = 26 19:03:51 [INFO] train episode 26396: reward = -86.77, steps = 43 19:03:53 [INFO] train episode 26397: reward = -50.31, steps = 23 19:03:56 [INFO] train episode 26398: reward = -55.90, steps = 26 19:04:00 [INFO] train episode 26399: reward = -109.39, steps = 45 19:04:03 [INFO] train episode 26400: reward = -64.59, steps = 35 19:04:06 [INFO] train episode 26401: reward = -76.58, steps = 37 19:04:09 [INFO] train episode 26402: reward = -111.67, steps = 38 19:04:12 [INFO] train episode 26403: reward = -72.95, steps = 32 19:04:14 [INFO] train episode 26404: reward = -80.98, steps = 20 19:04:16 [INFO] train episode 26405: reward = -71.09, steps = 28 19:04:19 [INFO] train episode 26406: reward = -83.38, steps = 20 19:04:20 [INFO] train episode 26407: reward = -83.11, steps = 19 19:04:23 [INFO] train episode 26408: reward = -65.57, steps = 30 19:04:25 [INFO] train episode 26409: reward = -40.96, steps = 22 19:04:26 [INFO] train episode 26410: reward = -76.02, steps = 20 19:04:29 [INFO] train episode 26411: reward = -50.53, steps = 22 19:04:30 [INFO] train episode 26412: reward = -85.07, steps = 18 19:04:33 [INFO] train episode 26413: reward = -79.87, steps = 31 19:04:36 [INFO] train episode 26414: reward = -56.56, steps = 23 19:04:38 [INFO] train episode 26415: reward = -59.50, steps = 20 19:04:39 [INFO] train episode 26416: reward = -50.69, steps = 20 19:04:42 [INFO] train episode 26417: reward = -50.03, steps = 26 19:04:45 [INFO] train episode 26418: reward = -90.36, steps = 33 19:04:47 [INFO] train episode 26419: reward = -109.23, steps = 25 19:04:49 [INFO] train episode 26420: reward = -90.88, steps = 22 19:04:52 [INFO] train episode 26421: reward = -109.86, steps = 32 19:04:55 [INFO] train episode 26422: reward = -105.17, steps = 29 19:04:57 [INFO] train episode 26423: reward = -97.99, steps = 28 19:04:59 [INFO] train episode 26424: reward = -68.48, steps = 21 19:05:02 [INFO] train episode 26425: reward = -125.46, steps = 29 19:05:04 [INFO] train episode 26426: reward = -138.79, steps = 24 19:05:06 [INFO] train episode 26427: reward = -58.28, steps = 22 19:05:09 [INFO] train episode 26428: reward = -49.98, steps = 28 19:05:11 [INFO] train episode 26429: reward = -84.73, steps = 25 19:05:13 [INFO] train episode 26430: reward = -83.80, steps = 30 19:05:16 [INFO] train episode 26431: reward = -63.36, steps = 28 19:05:18 [INFO] train episode 26432: reward = -77.93, steps = 23 19:05:20 [INFO] train episode 26433: reward = -76.52, steps = 22 19:05:22 [INFO] train episode 26434: reward = -96.79, steps = 28 19:05:24 [INFO] train episode 26435: reward = -66.10, steps = 19 19:05:26 [INFO] train episode 26436: reward = -113.56, steps = 23 19:05:29 [INFO] train episode 26437: reward = -65.52, steps = 24 19:05:31 [INFO] train episode 26438: reward = -70.03, steps = 24 19:05:33 [INFO] train episode 26439: reward = -48.21, steps = 23 19:05:34 [INFO] train episode 26440: reward = -95.14, steps = 19 19:05:36 [INFO] train episode 26441: reward = -43.32, steps = 22 19:05:38 [INFO] train episode 26442: reward = -96.45, steps = 20 19:05:40 [INFO] train episode 26443: reward = -62.82, steps = 21 19:05:42 [INFO] train episode 26444: reward = -83.11, steps = 18 19:05:45 [INFO] train episode 26445: reward = -62.63, steps = 22 19:05:47 [INFO] train episode 26446: reward = -82.62, steps = 21 19:05:48 [INFO] train episode 26447: reward = -49.74, steps = 21 19:05:50 [INFO] train episode 26448: reward = -52.77, steps = 18 19:05:52 [INFO] train episode 26449: reward = -52.05, steps = 21 19:05:54 [INFO] train episode 26450: reward = -47.32, steps = 22 19:05:56 [INFO] train episode 26451: reward = -53.46, steps = 24 19:05:58 [INFO] train episode 26452: reward = -62.26, steps = 23 19:06:00 [INFO] train episode 26453: reward = -100.76, steps = 21 19:06:02 [INFO] train episode 26454: reward = -66.13, steps = 23 19:06:04 [INFO] train episode 26455: reward = -91.46, steps = 19 19:06:06 [INFO] train episode 26456: reward = -49.35, steps = 23 19:06:08 [INFO] train episode 26457: reward = -63.00, steps = 23 19:06:11 [INFO] train episode 26458: reward = -67.11, steps = 37 19:06:15 [INFO] train episode 26459: reward = -93.56, steps = 37 19:06:18 [INFO] train episode 26460: reward = -84.94, steps = 39 19:06:20 [INFO] train episode 26461: reward = -66.31, steps = 18 19:06:23 [INFO] train episode 26462: reward = -100.22, steps = 36 19:06:25 [INFO] train episode 26463: reward = -94.49, steps = 21 19:06:28 [INFO] train episode 26464: reward = -95.76, steps = 32 19:06:30 [INFO] train episode 26465: reward = -97.28, steps = 23 19:06:33 [INFO] train episode 26466: reward = -162.98, steps = 26 19:06:36 [INFO] train episode 26467: reward = -47.54, steps = 33 19:06:38 [INFO] train episode 26468: reward = -71.67, steps = 23 19:06:40 [INFO] train episode 26469: reward = -71.90, steps = 27 19:06:42 [INFO] train episode 26470: reward = -91.64, steps = 22 19:06:47 [INFO] train episode 26471: reward = -116.70, steps = 44 19:06:49 [INFO] train episode 26472: reward = -82.36, steps = 21 19:06:50 [INFO] train episode 26473: reward = -60.98, steps = 21 19:06:52 [INFO] train episode 26474: reward = -70.70, steps = 24 19:06:55 [INFO] train episode 26475: reward = -66.97, steps = 30 19:06:58 [INFO] train episode 26476: reward = -89.07, steps = 34 19:07:01 [INFO] train episode 26477: reward = -50.48, steps = 34 19:07:03 [INFO] train episode 26478: reward = -48.77, steps = 21 19:07:06 [INFO] train episode 26479: reward = -61.95, steps = 27 19:07:09 [INFO] train episode 26480: reward = -80.55, steps = 34 19:07:11 [INFO] train episode 26481: reward = -82.07, steps = 27 19:07:13 [INFO] train episode 26482: reward = -82.43, steps = 19 19:07:15 [INFO] train episode 26483: reward = -35.53, steps = 23 19:07:17 [INFO] train episode 26484: reward = -117.81, steps = 19 19:07:19 [INFO] train episode 26485: reward = -95.64, steps = 23 19:07:21 [INFO] train episode 26486: reward = -53.44, steps = 21 19:07:23 [INFO] train episode 26487: reward = -50.22, steps = 22 19:07:26 [INFO] train episode 26488: reward = -66.66, steps = 29 19:07:28 [INFO] train episode 26489: reward = -42.35, steps = 21 19:07:29 [INFO] train episode 26490: reward = -57.52, steps = 22 19:07:31 [INFO] train episode 26491: reward = -128.44, steps = 22 19:07:33 [INFO] train episode 26492: reward = -61.98, steps = 21 19:07:35 [INFO] train episode 26493: reward = -87.54, steps = 19 19:07:38 [INFO] train episode 26494: reward = -71.09, steps = 25 19:07:40 [INFO] train episode 26495: reward = -77.30, steps = 29 19:07:42 [INFO] train episode 26496: reward = -57.19, steps = 23 19:07:46 [INFO] train episode 26497: reward = -66.70, steps = 39 19:07:47 [INFO] train episode 26498: reward = -56.71, steps = 20 19:07:50 [INFO] train episode 26499: reward = -74.91, steps = 30 19:07:54 [INFO] train episode 26500: reward = -75.50, steps = 36 19:07:56 [INFO] train episode 26501: reward = -42.51, steps = 22 19:07:58 [INFO] train episode 26502: reward = -54.16, steps = 22 19:08:01 [INFO] train episode 26503: reward = -54.29, steps = 39 19:08:03 [INFO] train episode 26504: reward = -74.55, steps = 20 19:08:05 [INFO] train episode 26505: reward = -49.46, steps = 25 19:08:08 [INFO] train episode 26506: reward = -55.68, steps = 33 19:08:10 [INFO] train episode 26507: reward = -52.79, steps = 20 19:08:14 [INFO] train episode 26508: reward = -128.20, steps = 43 19:08:15 [INFO] train episode 26509: reward = -59.58, steps = 19 19:08:18 [INFO] train episode 26510: reward = -86.33, steps = 25 19:08:20 [INFO] train episode 26511: reward = -54.18, steps = 27 19:08:22 [INFO] train episode 26512: reward = -60.62, steps = 22 19:08:24 [INFO] train episode 26513: reward = -58.85, steps = 22 19:08:27 [INFO] train episode 26514: reward = -86.45, steps = 34 19:08:30 [INFO] train episode 26515: reward = -72.63, steps = 28 19:08:31 [INFO] train episode 26516: reward = -65.82, steps = 22 19:08:33 [INFO] train episode 26517: reward = -37.91, steps = 18 19:08:35 [INFO] train episode 26518: reward = -60.52, steps = 23 19:08:37 [INFO] train episode 26519: reward = -67.59, steps = 24 19:08:42 [INFO] train episode 26520: reward = -78.57, steps = 37 19:08:44 [INFO] train episode 26521: reward = -59.12, steps = 29 19:08:46 [INFO] train episode 26522: reward = -48.67, steps = 18 19:08:48 [INFO] train episode 26523: reward = -63.07, steps = 23 19:08:50 [INFO] train episode 26524: reward = -55.62, steps = 22 19:08:52 [INFO] train episode 26525: reward = -62.39, steps = 19 19:08:53 [INFO] train episode 26526: reward = -57.29, steps = 19 19:08:56 [INFO] train episode 26527: reward = -110.93, steps = 29 19:08:59 [INFO] train episode 26528: reward = -74.33, steps = 28 19:09:01 [INFO] train episode 26529: reward = -74.80, steps = 30 19:09:03 [INFO] train episode 26530: reward = -70.52, steps = 20 19:09:05 [INFO] train episode 26531: reward = -59.79, steps = 21 19:09:07 [INFO] train episode 26532: reward = -60.83, steps = 26 19:09:09 [INFO] train episode 26533: reward = -66.94, steps = 20 19:09:12 [INFO] train episode 26534: reward = -64.44, steps = 29 19:09:14 [INFO] train episode 26535: reward = -95.38, steps = 19 19:09:16 [INFO] train episode 26536: reward = -84.74, steps = 29 19:09:18 [INFO] train episode 26537: reward = -54.93, steps = 20 19:09:20 [INFO] train episode 26538: reward = -46.71, steps = 19 19:09:22 [INFO] train episode 26539: reward = -69.17, steps = 25 19:09:24 [INFO] train episode 26540: reward = -119.45, steps = 19 19:09:27 [INFO] train episode 26541: reward = -119.96, steps = 37 19:09:29 [INFO] train episode 26542: reward = -72.23, steps = 21 19:09:31 [INFO] train episode 26543: reward = -45.77, steps = 22 19:09:33 [INFO] train episode 26544: reward = -156.63, steps = 19 19:09:35 [INFO] train episode 26545: reward = -51.71, steps = 18 19:09:36 [INFO] train episode 26546: reward = -98.61, steps = 20 19:09:39 [INFO] train episode 26547: reward = -157.15, steps = 34 19:09:42 [INFO] train episode 26548: reward = -75.84, steps = 28 19:09:44 [INFO] train episode 26549: reward = -73.99, steps = 31 19:09:47 [INFO] train episode 26550: reward = -112.69, steps = 27 19:09:50 [INFO] train episode 26551: reward = -103.93, steps = 36 19:09:54 [INFO] train episode 26552: reward = -92.57, steps = 39 19:09:58 [INFO] train episode 26553: reward = -102.37, steps = 48 19:10:00 [INFO] train episode 26554: reward = -81.95, steps = 24 19:10:03 [INFO] train episode 26555: reward = -73.00, steps = 35 19:10:05 [INFO] train episode 26556: reward = -67.52, steps = 20 19:10:07 [INFO] train episode 26557: reward = -113.54, steps = 27 19:10:11 [INFO] train episode 26558: reward = -193.55, steps = 46 19:10:13 [INFO] train episode 26559: reward = -70.18, steps = 18 19:10:17 [INFO] train episode 26560: reward = -104.21, steps = 52 19:10:20 [INFO] train episode 26561: reward = -69.32, steps = 19 19:10:22 [INFO] train episode 26562: reward = -66.31, steps = 26 19:10:25 [INFO] train episode 26563: reward = -111.64, steps = 33 19:10:27 [INFO] train episode 26564: reward = -52.46, steps = 21 19:10:29 [INFO] train episode 26565: reward = -48.98, steps = 33 19:10:31 [INFO] train episode 26566: reward = -65.89, steps = 19 19:10:33 [INFO] train episode 26567: reward = -97.04, steps = 22 19:10:36 [INFO] train episode 26568: reward = -61.56, steps = 32 19:10:40 [INFO] train episode 26569: reward = -112.78, steps = 40 19:10:42 [INFO] train episode 26570: reward = -58.62, steps = 24 19:10:45 [INFO] train episode 26571: reward = -56.13, steps = 35 19:10:47 [INFO] train episode 26572: reward = -83.32, steps = 29 19:10:49 [INFO] train episode 26573: reward = -76.23, steps = 20 19:10:52 [INFO] train episode 26574: reward = -47.15, steps = 27 19:10:54 [INFO] train episode 26575: reward = -65.19, steps = 21 19:10:56 [INFO] train episode 26576: reward = -70.29, steps = 19 19:10:58 [INFO] train episode 26577: reward = -67.74, steps = 24 19:11:01 [INFO] train episode 26578: reward = -92.65, steps = 39 19:11:03 [INFO] train episode 26579: reward = -63.95, steps = 20 19:11:05 [INFO] train episode 26580: reward = -143.34, steps = 30 19:11:08 [INFO] train episode 26581: reward = -63.39, steps = 24 19:11:11 [INFO] train episode 26582: reward = -79.05, steps = 36 19:11:15 [INFO] train episode 26583: reward = -97.27, steps = 43 19:11:16 [INFO] train episode 26584: reward = -75.16, steps = 18 19:11:20 [INFO] train episode 26585: reward = -165.96, steps = 39 19:11:22 [INFO] train episode 26586: reward = -42.11, steps = 22 19:11:24 [INFO] train episode 26587: reward = -53.06, steps = 19 19:11:26 [INFO] train episode 26588: reward = -86.72, steps = 23 19:11:28 [INFO] train episode 26589: reward = -39.57, steps = 24 19:11:30 [INFO] train episode 26590: reward = -79.14, steps = 27 19:11:32 [INFO] train episode 26591: reward = -68.16, steps = 24 19:11:34 [INFO] train episode 26592: reward = -60.99, steps = 21 19:11:38 [INFO] train episode 26593: reward = -138.19, steps = 39 19:11:41 [INFO] train episode 26594: reward = -47.52, steps = 20 19:11:42 [INFO] train episode 26595: reward = -64.78, steps = 19 19:11:45 [INFO] train episode 26596: reward = -75.56, steps = 37 19:11:47 [INFO] train episode 26597: reward = -74.65, steps = 19 19:11:49 [INFO] train episode 26598: reward = -93.38, steps = 22 19:11:51 [INFO] train episode 26599: reward = -75.59, steps = 19 19:11:53 [INFO] train episode 26600: reward = -53.54, steps = 31 19:11:55 [INFO] train episode 26601: reward = -97.86, steps = 20 19:11:58 [INFO] train episode 26602: reward = -59.88, steps = 31 19:12:02 [INFO] train episode 26603: reward = -102.95, steps = 38 19:12:03 [INFO] train episode 26604: reward = -41.17, steps = 19 19:12:06 [INFO] train episode 26605: reward = -32.78, steps = 27 19:12:07 [INFO] train episode 26606: reward = -63.50, steps = 21 19:12:09 [INFO] train episode 26607: reward = -70.07, steps = 21 19:12:14 [INFO] train episode 26608: reward = -116.11, steps = 48 19:12:17 [INFO] train episode 26609: reward = -61.79, steps = 32 19:12:19 [INFO] train episode 26610: reward = -68.98, steps = 29 19:12:22 [INFO] train episode 26611: reward = -109.63, steps = 39 19:12:25 [INFO] train episode 26612: reward = -89.30, steps = 27 19:12:27 [INFO] train episode 26613: reward = -71.92, steps = 26 19:12:30 [INFO] train episode 26614: reward = -82.74, steps = 25 19:12:32 [INFO] train episode 26615: reward = -70.73, steps = 28 19:12:34 [INFO] train episode 26616: reward = -104.52, steps = 25 19:12:37 [INFO] train episode 26617: reward = -84.99, steps = 30 19:12:40 [INFO] train episode 26618: reward = -99.71, steps = 26 19:12:42 [INFO] train episode 26619: reward = -86.89, steps = 27 19:12:44 [INFO] train episode 26620: reward = -69.56, steps = 20 19:12:46 [INFO] train episode 26621: reward = -108.13, steps = 27 19:12:48 [INFO] train episode 26622: reward = -64.54, steps = 19 19:12:50 [INFO] train episode 26623: reward = -72.41, steps = 23 19:12:53 [INFO] train episode 26624: reward = -63.24, steps = 33 19:12:55 [INFO] train episode 26625: reward = -60.26, steps = 24 19:12:58 [INFO] train episode 26626: reward = -44.68, steps = 36 19:13:02 [INFO] train episode 26627: reward = -70.35, steps = 34 19:13:03 [INFO] train episode 26628: reward = -59.21, steps = 20 19:13:05 [INFO] train episode 26629: reward = -126.44, steps = 19 19:13:07 [INFO] train episode 26630: reward = -64.44, steps = 24 19:13:09 [INFO] train episode 26631: reward = -61.71, steps = 20 19:13:11 [INFO] train episode 26632: reward = -106.69, steps = 24 19:13:13 [INFO] train episode 26633: reward = -75.20, steps = 21 19:13:15 [INFO] train episode 26634: reward = -40.96, steps = 20 19:13:18 [INFO] train episode 26635: reward = -35.40, steps = 33 19:13:20 [INFO] train episode 26636: reward = -73.88, steps = 28 19:13:23 [INFO] train episode 26637: reward = -59.24, steps = 26 19:13:24 [INFO] train episode 26638: reward = -96.79, steps = 20 19:13:27 [INFO] train episode 26639: reward = -91.69, steps = 29 19:13:29 [INFO] train episode 26640: reward = -65.04, steps = 27 19:13:32 [INFO] train episode 26641: reward = -65.56, steps = 29 19:13:34 [INFO] train episode 26642: reward = -42.50, steps = 25 19:13:36 [INFO] train episode 26643: reward = -97.81, steps = 22 19:13:38 [INFO] train episode 26644: reward = -61.17, steps = 24 19:13:40 [INFO] train episode 26645: reward = -76.51, steps = 20 19:13:42 [INFO] train episode 26646: reward = -112.04, steps = 20 19:13:45 [INFO] train episode 26647: reward = -78.51, steps = 35 19:13:47 [INFO] train episode 26648: reward = -97.24, steps = 26 19:13:50 [INFO] train episode 26649: reward = -84.95, steps = 29 19:13:53 [INFO] train episode 26650: reward = -59.77, steps = 37 19:13:55 [INFO] train episode 26651: reward = -49.59, steps = 19 19:13:57 [INFO] train episode 26652: reward = -57.51, steps = 23 19:13:59 [INFO] train episode 26653: reward = -157.52, steps = 19 19:14:01 [INFO] train episode 26654: reward = -60.37, steps = 20 19:14:03 [INFO] train episode 26655: reward = -71.10, steps = 31 19:14:07 [INFO] train episode 26656: reward = -76.09, steps = 37 19:14:09 [INFO] train episode 26657: reward = -121.42, steps = 31 19:14:11 [INFO] train episode 26658: reward = -48.56, steps = 21 19:14:13 [INFO] train episode 26659: reward = -66.12, steps = 23 19:14:16 [INFO] train episode 26660: reward = -89.33, steps = 29 19:14:18 [INFO] train episode 26661: reward = -77.40, steps = 28 19:14:21 [INFO] train episode 26662: reward = -80.66, steps = 27 19:14:23 [INFO] train episode 26663: reward = -84.70, steps = 23 19:14:26 [INFO] train episode 26664: reward = -83.02, steps = 35 19:14:28 [INFO] train episode 26665: reward = -61.12, steps = 24 19:14:30 [INFO] train episode 26666: reward = -87.91, steps = 25 19:14:34 [INFO] train episode 26667: reward = -87.90, steps = 32 19:14:37 [INFO] train episode 26668: reward = -93.71, steps = 35 19:14:40 [INFO] train episode 26669: reward = -73.43, steps = 23 19:14:42 [INFO] train episode 26670: reward = -66.85, steps = 21 19:14:45 [INFO] train episode 26671: reward = -128.36, steps = 44 19:14:47 [INFO] train episode 26672: reward = -58.28, steps = 21 19:14:50 [INFO] train episode 26673: reward = -69.44, steps = 31 19:14:52 [INFO] train episode 26674: reward = -34.22, steps = 26 19:14:54 [INFO] train episode 26675: reward = -99.64, steps = 20 19:14:57 [INFO] train episode 26676: reward = -74.70, steps = 25 19:15:00 [INFO] train episode 26677: reward = -49.15, steps = 41 19:15:04 [INFO] train episode 26678: reward = -88.84, steps = 38 19:15:05 [INFO] train episode 26679: reward = -99.96, steps = 18 19:15:08 [INFO] train episode 26680: reward = -51.00, steps = 29 19:15:10 [INFO] train episode 26681: reward = -39.49, steps = 20 19:15:12 [INFO] train episode 26682: reward = -109.28, steps = 24 19:15:16 [INFO] train episode 26683: reward = -86.76, steps = 37 19:15:19 [INFO] train episode 26684: reward = -124.90, steps = 43 19:15:23 [INFO] train episode 26685: reward = -60.23, steps = 34 19:15:25 [INFO] train episode 26686: reward = -74.50, steps = 30 19:15:27 [INFO] train episode 26687: reward = -88.42, steps = 22 19:15:30 [INFO] train episode 26688: reward = -63.16, steps = 24 19:15:32 [INFO] train episode 26689: reward = -77.71, steps = 21 19:15:35 [INFO] train episode 26690: reward = -131.28, steps = 34 19:15:37 [INFO] train episode 26691: reward = -68.10, steps = 22 19:15:39 [INFO] train episode 26692: reward = -74.12, steps = 21 19:15:42 [INFO] train episode 26693: reward = -93.50, steps = 37 19:15:43 [INFO] train episode 26694: reward = -44.63, steps = 18 19:15:48 [INFO] train episode 26695: reward = -83.27, steps = 45 19:15:50 [INFO] train episode 26696: reward = -64.10, steps = 28 19:15:52 [INFO] train episode 26697: reward = -67.56, steps = 28 19:15:54 [INFO] train episode 26698: reward = -53.96, steps = 20 19:15:56 [INFO] train episode 26699: reward = -80.20, steps = 19 19:15:58 [INFO] train episode 26700: reward = -49.04, steps = 24 19:16:00 [INFO] train episode 26701: reward = -77.61, steps = 23 19:16:02 [INFO] train episode 26702: reward = -68.44, steps = 18 19:16:05 [INFO] train episode 26703: reward = -73.55, steps = 33 19:16:08 [INFO] train episode 26704: reward = -88.96, steps = 38 19:16:10 [INFO] train episode 26705: reward = -57.00, steps = 20 19:16:12 [INFO] train episode 26706: reward = -77.41, steps = 23 19:16:15 [INFO] train episode 26707: reward = -77.06, steps = 32 19:16:17 [INFO] train episode 26708: reward = -98.49, steps = 23 19:16:19 [INFO] train episode 26709: reward = -39.61, steps = 24 19:16:23 [INFO] train episode 26710: reward = -81.27, steps = 38 19:16:25 [INFO] train episode 26711: reward = -79.50, steps = 27 19:16:27 [INFO] train episode 26712: reward = -72.90, steps = 24 19:16:30 [INFO] train episode 26713: reward = -86.69, steps = 30 19:16:32 [INFO] train episode 26714: reward = -84.25, steps = 25 19:16:34 [INFO] train episode 26715: reward = -68.20, steps = 20 19:16:37 [INFO] train episode 26716: reward = -108.13, steps = 31 19:16:40 [INFO] train episode 26717: reward = -65.36, steps = 41 19:16:42 [INFO] train episode 26718: reward = -106.13, steps = 17 19:16:46 [INFO] train episode 26719: reward = -100.73, steps = 41 19:16:47 [INFO] train episode 26720: reward = -93.32, steps = 22 19:16:51 [INFO] train episode 26721: reward = -122.63, steps = 38 19:16:53 [INFO] train episode 26722: reward = -57.34, steps = 22 19:16:56 [INFO] train episode 26723: reward = -105.65, steps = 32 19:16:58 [INFO] train episode 26724: reward = -90.81, steps = 24 19:17:01 [INFO] train episode 26725: reward = -69.54, steps = 30 19:17:03 [INFO] train episode 26726: reward = -66.85, steps = 30 19:17:05 [INFO] train episode 26727: reward = -88.72, steps = 22 19:17:09 [INFO] train episode 26728: reward = -71.14, steps = 36 19:17:11 [INFO] train episode 26729: reward = -62.36, steps = 23 19:17:13 [INFO] train episode 26730: reward = -42.55, steps = 20 19:17:14 [INFO] train episode 26731: reward = -66.12, steps = 20 19:17:17 [INFO] train episode 26732: reward = -108.60, steps = 32 19:17:19 [INFO] train episode 26733: reward = -60.52, steps = 26 19:17:21 [INFO] train episode 26734: reward = -90.56, steps = 20 19:17:23 [INFO] train episode 26735: reward = -65.26, steps = 19 19:17:25 [INFO] train episode 26736: reward = -97.51, steps = 25 19:17:28 [INFO] train episode 26737: reward = -67.00, steps = 35 19:17:31 [INFO] train episode 26738: reward = -58.73, steps = 19 19:17:35 [INFO] train episode 26739: reward = -91.07, steps = 42 19:17:36 [INFO] train episode 26740: reward = -63.60, steps = 20 19:17:39 [INFO] train episode 26741: reward = -61.60, steps = 25 19:17:42 [INFO] train episode 26742: reward = -115.25, steps = 33 19:17:44 [INFO] train episode 26743: reward = -88.88, steps = 30 19:17:46 [INFO] train episode 26744: reward = -120.44, steps = 21 19:17:49 [INFO] train episode 26745: reward = -60.09, steps = 25 19:17:50 [INFO] train episode 26746: reward = -57.14, steps = 19 19:17:52 [INFO] train episode 26747: reward = -65.92, steps = 25 19:17:54 [INFO] train episode 26748: reward = -63.73, steps = 21 19:17:58 [INFO] train episode 26749: reward = -83.77, steps = 36 19:18:00 [INFO] train episode 26750: reward = -53.60, steps = 23 19:18:02 [INFO] train episode 26751: reward = -48.45, steps = 26 19:18:04 [INFO] train episode 26752: reward = -75.94, steps = 18 19:18:06 [INFO] train episode 26753: reward = -54.74, steps = 20 19:18:08 [INFO] train episode 26754: reward = -120.67, steps = 31 19:18:10 [INFO] train episode 26755: reward = -91.69, steps = 19 19:18:13 [INFO] train episode 26756: reward = -88.80, steps = 28 19:18:14 [INFO] train episode 26757: reward = -113.15, steps = 20 19:18:17 [INFO] train episode 26758: reward = -94.64, steps = 28 19:18:19 [INFO] train episode 26759: reward = -74.99, steps = 27 19:18:21 [INFO] train episode 26760: reward = -62.19, steps = 23 19:18:24 [INFO] train episode 26761: reward = -66.16, steps = 29 19:18:27 [INFO] train episode 26762: reward = -139.12, steps = 37 19:18:29 [INFO] train episode 26763: reward = -41.99, steps = 20 19:18:32 [INFO] train episode 26764: reward = -135.01, steps = 31 19:18:34 [INFO] train episode 26765: reward = -48.67, steps = 24 19:18:36 [INFO] train episode 26766: reward = -68.50, steps = 25 19:18:38 [INFO] train episode 26767: reward = -100.93, steps = 19 19:18:41 [INFO] train episode 26768: reward = -96.21, steps = 34 19:18:44 [INFO] train episode 26769: reward = -134.61, steps = 35 19:18:49 [INFO] train episode 26770: reward = -140.19, steps = 56 19:18:52 [INFO] train episode 26771: reward = -59.77, steps = 31 19:18:54 [INFO] train episode 26772: reward = -52.61, steps = 19 19:18:56 [INFO] train episode 26773: reward = -82.19, steps = 23 19:18:57 [INFO] train episode 26774: reward = -46.68, steps = 18 19:18:59 [INFO] train episode 26775: reward = -105.16, steps = 24 19:19:02 [INFO] train episode 26776: reward = -49.82, steps = 21 19:19:03 [INFO] train episode 26777: reward = -50.17, steps = 21 19:19:06 [INFO] train episode 26778: reward = -51.38, steps = 25 19:19:08 [INFO] train episode 26779: reward = -72.47, steps = 21 19:19:10 [INFO] train episode 26780: reward = -89.39, steps = 29 19:19:12 [INFO] train episode 26781: reward = -64.74, steps = 23 19:19:15 [INFO] train episode 26782: reward = -75.09, steps = 30 19:19:17 [INFO] train episode 26783: reward = -39.28, steps = 26 19:19:21 [INFO] train episode 26784: reward = -77.48, steps = 42 19:19:23 [INFO] train episode 26785: reward = -88.30, steps = 21 19:19:25 [INFO] train episode 26786: reward = -59.28, steps = 20 19:19:27 [INFO] train episode 26787: reward = -93.50, steps = 28 19:19:29 [INFO] train episode 26788: reward = -62.96, steps = 26 19:19:34 [INFO] train episode 26789: reward = -92.34, steps = 48 19:19:36 [INFO] train episode 26790: reward = -64.21, steps = 21 19:19:38 [INFO] train episode 26791: reward = -53.40, steps = 21 19:19:40 [INFO] train episode 26792: reward = -83.89, steps = 20 19:19:42 [INFO] train episode 26793: reward = -112.38, steps = 32 19:19:44 [INFO] train episode 26794: reward = -96.67, steps = 19 19:19:47 [INFO] train episode 26795: reward = -89.26, steps = 30 19:19:50 [INFO] train episode 26796: reward = -64.86, steps = 27 19:19:51 [INFO] train episode 26797: reward = -57.48, steps = 20 19:19:53 [INFO] train episode 26798: reward = -75.53, steps = 21 19:19:55 [INFO] train episode 26799: reward = -45.84, steps = 24 19:19:57 [INFO] train episode 26800: reward = -69.39, steps = 24 19:19:59 [INFO] train episode 26801: reward = -91.57, steps = 19 19:20:01 [INFO] train episode 26802: reward = -59.80, steps = 24 19:20:03 [INFO] train episode 26803: reward = -78.59, steps = 23 19:20:07 [INFO] train episode 26804: reward = -73.33, steps = 33 19:20:08 [INFO] train episode 26805: reward = -59.23, steps = 18 19:20:10 [INFO] train episode 26806: reward = -81.32, steps = 27 19:20:13 [INFO] train episode 26807: reward = -95.83, steps = 25 19:20:15 [INFO] train episode 26808: reward = -66.76, steps = 25 19:20:19 [INFO] train episode 26809: reward = -83.21, steps = 51 19:20:21 [INFO] train episode 26810: reward = -57.00, steps = 20 19:20:24 [INFO] train episode 26811: reward = -44.72, steps = 23 19:20:28 [INFO] train episode 26812: reward = -126.38, steps = 49 19:20:30 [INFO] train episode 26813: reward = -67.18, steps = 20 19:20:32 [INFO] train episode 26814: reward = -65.45, steps = 23 19:20:35 [INFO] train episode 26815: reward = -55.87, steps = 33 19:20:37 [INFO] train episode 26816: reward = -84.05, steps = 23 19:20:40 [INFO] train episode 26817: reward = -79.21, steps = 27 19:20:43 [INFO] train episode 26818: reward = -73.29, steps = 27 19:20:45 [INFO] train episode 26819: reward = -77.87, steps = 24 19:20:48 [INFO] train episode 26820: reward = -79.67, steps = 39 19:20:51 [INFO] train episode 26821: reward = -85.99, steps = 27 19:20:54 [INFO] train episode 26822: reward = -70.03, steps = 38 19:20:58 [INFO] train episode 26823: reward = -66.59, steps = 35 19:21:01 [INFO] train episode 26824: reward = -75.66, steps = 22 19:21:03 [INFO] train episode 26825: reward = -88.31, steps = 27 19:21:05 [INFO] train episode 26826: reward = -63.18, steps = 20 19:21:08 [INFO] train episode 26827: reward = -100.65, steps = 25 19:21:10 [INFO] train episode 26828: reward = -68.91, steps = 25 19:21:12 [INFO] train episode 26829: reward = -55.59, steps = 25 19:21:15 [INFO] train episode 26830: reward = -51.63, steps = 24 19:21:17 [INFO] train episode 26831: reward = -107.61, steps = 21 19:21:20 [INFO] train episode 26832: reward = -65.34, steps = 30 19:21:22 [INFO] train episode 26833: reward = -61.64, steps = 31 19:21:24 [INFO] train episode 26834: reward = -76.89, steps = 20 19:21:26 [INFO] train episode 26835: reward = -55.96, steps = 26 19:21:30 [INFO] train episode 26836: reward = -86.45, steps = 31 19:21:32 [INFO] train episode 26837: reward = -56.92, steps = 28 19:21:34 [INFO] train episode 26838: reward = -68.46, steps = 20 19:21:36 [INFO] train episode 26839: reward = -53.19, steps = 25 19:21:38 [INFO] train episode 26840: reward = -62.07, steps = 21 19:21:40 [INFO] train episode 26841: reward = -84.66, steps = 28 19:21:43 [INFO] train episode 26842: reward = -74.98, steps = 31 19:21:45 [INFO] train episode 26843: reward = -59.81, steps = 19 19:21:49 [INFO] train episode 26844: reward = -64.98, steps = 43 19:21:52 [INFO] train episode 26845: reward = -104.04, steps = 35 19:21:55 [INFO] train episode 26846: reward = -78.71, steps = 37 19:21:57 [INFO] train episode 26847: reward = -41.42, steps = 20 19:21:59 [INFO] train episode 26848: reward = -65.66, steps = 27 19:22:02 [INFO] train episode 26849: reward = -98.20, steps = 29 19:22:04 [INFO] train episode 26850: reward = -59.53, steps = 20 19:22:07 [INFO] train episode 26851: reward = -65.87, steps = 31 19:22:10 [INFO] train episode 26852: reward = -75.34, steps = 43 19:22:13 [INFO] train episode 26853: reward = -98.14, steps = 26 19:22:15 [INFO] train episode 26854: reward = -91.99, steps = 24 19:22:17 [INFO] train episode 26855: reward = -97.37, steps = 29 19:22:20 [INFO] train episode 26856: reward = -59.45, steps = 27 19:22:22 [INFO] train episode 26857: reward = -167.26, steps = 20 19:22:26 [INFO] train episode 26858: reward = -90.70, steps = 40 19:22:28 [INFO] train episode 26859: reward = -41.77, steps = 26 19:22:30 [INFO] train episode 26860: reward = -85.28, steps = 22 19:22:32 [INFO] train episode 26861: reward = -67.87, steps = 20 19:22:34 [INFO] train episode 26862: reward = -73.16, steps = 26 19:22:36 [INFO] train episode 26863: reward = -74.55, steps = 19 19:22:39 [INFO] train episode 26864: reward = -79.67, steps = 29 19:22:42 [INFO] train episode 26865: reward = -88.42, steps = 29 19:22:43 [INFO] train episode 26866: reward = -55.18, steps = 20 19:22:46 [INFO] train episode 26867: reward = -59.05, steps = 25 19:22:48 [INFO] train episode 26868: reward = -59.83, steps = 26 19:22:50 [INFO] train episode 26869: reward = -53.99, steps = 23 19:22:54 [INFO] train episode 26870: reward = -67.36, steps = 36 19:22:57 [INFO] train episode 26871: reward = -101.03, steps = 41 19:22:59 [INFO] train episode 26872: reward = -39.34, steps = 23 19:23:01 [INFO] train episode 26873: reward = -78.16, steps = 24 19:23:04 [INFO] train episode 26874: reward = -56.28, steps = 26 19:23:05 [INFO] train episode 26875: reward = -59.94, steps = 20 19:23:07 [INFO] train episode 26876: reward = -76.77, steps = 20 19:23:10 [INFO] train episode 26877: reward = -74.19, steps = 23 19:23:11 [INFO] train episode 26878: reward = -70.25, steps = 21 19:23:13 [INFO] train episode 26879: reward = -52.40, steps = 19 19:23:17 [INFO] train episode 26880: reward = -95.42, steps = 44 19:23:19 [INFO] train episode 26881: reward = -102.24, steps = 26 19:23:21 [INFO] train episode 26882: reward = -110.28, steps = 22 19:23:24 [INFO] train episode 26883: reward = -67.87, steps = 27 19:23:27 [INFO] train episode 26884: reward = -51.12, steps = 30 19:23:29 [INFO] train episode 26885: reward = -65.21, steps = 23 19:23:32 [INFO] train episode 26886: reward = -80.69, steps = 32 19:23:35 [INFO] train episode 26887: reward = -39.24, steps = 38 19:23:37 [INFO] train episode 26888: reward = -77.55, steps = 20 19:23:39 [INFO] train episode 26889: reward = -44.08, steps = 24 19:23:41 [INFO] train episode 26890: reward = -107.06, steps = 18 19:23:43 [INFO] train episode 26891: reward = -74.25, steps = 21 19:23:48 [INFO] train episode 26892: reward = -91.75, steps = 54 19:23:51 [INFO] train episode 26893: reward = -39.95, steps = 30 19:23:53 [INFO] train episode 26894: reward = -74.38, steps = 24 19:23:56 [INFO] train episode 26895: reward = -72.52, steps = 32 19:23:59 [INFO] train episode 26896: reward = -90.81, steps = 31 19:24:01 [INFO] train episode 26897: reward = -77.01, steps = 28 19:24:04 [INFO] train episode 26898: reward = -73.88, steps = 31 19:24:06 [INFO] train episode 26899: reward = -77.83, steps = 24 19:24:08 [INFO] train episode 26900: reward = -101.51, steps = 27 19:24:11 [INFO] train episode 26901: reward = -85.03, steps = 28 19:24:13 [INFO] train episode 26902: reward = -68.86, steps = 22 19:24:15 [INFO] train episode 26903: reward = -67.97, steps = 18 19:24:17 [INFO] train episode 26904: reward = -63.06, steps = 22 19:24:18 [INFO] train episode 26905: reward = -49.88, steps = 19 19:24:21 [INFO] train episode 26906: reward = -129.21, steps = 38 19:24:24 [INFO] train episode 26907: reward = -48.51, steps = 26 19:24:26 [INFO] train episode 26908: reward = -42.40, steps = 24 19:24:29 [INFO] train episode 26909: reward = -139.70, steps = 29 19:24:32 [INFO] train episode 26910: reward = -53.34, steps = 38 19:24:34 [INFO] train episode 26911: reward = -61.60, steps = 25 19:24:37 [INFO] train episode 26912: reward = -67.37, steps = 23 19:24:39 [INFO] train episode 26913: reward = -66.62, steps = 31 19:24:42 [INFO] train episode 26914: reward = -98.18, steps = 35 19:24:45 [INFO] train episode 26915: reward = -65.22, steps = 25 19:24:48 [INFO] train episode 26916: reward = -92.28, steps = 34 19:24:51 [INFO] train episode 26917: reward = -59.91, steps = 28 19:24:54 [INFO] train episode 26918: reward = -60.11, steps = 41 19:24:56 [INFO] train episode 26919: reward = -55.87, steps = 18 19:24:59 [INFO] train episode 26920: reward = -60.67, steps = 36 19:25:02 [INFO] train episode 26921: reward = -72.80, steps = 27 19:25:05 [INFO] train episode 26922: reward = -76.07, steps = 30 19:25:07 [INFO] train episode 26923: reward = -49.95, steps = 27 19:25:11 [INFO] train episode 26924: reward = -157.92, steps = 49 19:25:13 [INFO] train episode 26925: reward = -51.96, steps = 24 19:25:15 [INFO] train episode 26926: reward = -67.09, steps = 23 19:25:18 [INFO] train episode 26927: reward = -93.87, steps = 29 19:25:21 [INFO] train episode 26928: reward = -57.39, steps = 33 19:25:24 [INFO] train episode 26929: reward = -55.33, steps = 28 19:25:26 [INFO] train episode 26930: reward = -51.25, steps = 23 19:25:29 [INFO] train episode 26931: reward = -117.46, steps = 39 19:25:31 [INFO] train episode 26932: reward = -82.49, steps = 20 19:25:33 [INFO] train episode 26933: reward = -44.64, steps = 18 19:25:35 [INFO] train episode 26934: reward = -69.73, steps = 21 19:25:37 [INFO] train episode 26935: reward = -74.46, steps = 18 19:25:39 [INFO] train episode 26936: reward = -47.20, steps = 25 19:25:41 [INFO] train episode 26937: reward = -46.79, steps = 21 19:25:42 [INFO] train episode 26938: reward = -101.91, steps = 18 19:25:44 [INFO] train episode 26939: reward = -55.94, steps = 21 19:25:47 [INFO] train episode 26940: reward = -58.53, steps = 35 19:25:49 [INFO] train episode 26941: reward = -100.48, steps = 17 19:25:52 [INFO] train episode 26942: reward = -93.30, steps = 35 19:25:54 [INFO] train episode 26943: reward = -56.09, steps = 20 19:25:57 [INFO] train episode 26944: reward = -59.32, steps = 25 19:26:00 [INFO] train episode 26945: reward = -60.78, steps = 35 19:26:02 [INFO] train episode 26946: reward = -45.83, steps = 31 19:26:05 [INFO] train episode 26947: reward = -50.72, steps = 30 19:26:07 [INFO] train episode 26948: reward = -51.41, steps = 18 19:26:09 [INFO] train episode 26949: reward = -88.65, steps = 27 19:26:12 [INFO] train episode 26950: reward = -65.03, steps = 26 19:26:13 [INFO] train episode 26951: reward = -142.50, steps = 20 19:26:15 [INFO] train episode 26952: reward = -66.43, steps = 20 19:26:18 [INFO] train episode 26953: reward = -84.57, steps = 34 19:26:21 [INFO] train episode 26954: reward = -234.96, steps = 34 19:26:24 [INFO] train episode 26955: reward = -31.34, steps = 23 19:26:27 [INFO] train episode 26956: reward = -58.62, steps = 28 19:26:29 [INFO] train episode 26957: reward = -63.95, steps = 21 19:26:32 [INFO] train episode 26958: reward = -61.63, steps = 34 19:26:34 [INFO] train episode 26959: reward = -48.49, steps = 20 19:26:37 [INFO] train episode 26960: reward = -59.39, steps = 37 19:26:40 [INFO] train episode 26961: reward = -59.43, steps = 24 19:26:42 [INFO] train episode 26962: reward = -66.38, steps = 22 19:26:44 [INFO] train episode 26963: reward = -91.12, steps = 24 19:26:48 [INFO] train episode 26964: reward = -56.24, steps = 48 19:26:50 [INFO] train episode 26965: reward = -87.85, steps = 20 19:26:53 [INFO] train episode 26966: reward = -67.38, steps = 30 19:26:55 [INFO] train episode 26967: reward = -48.14, steps = 26 19:26:57 [INFO] train episode 26968: reward = -78.29, steps = 21 19:26:59 [INFO] train episode 26969: reward = -84.09, steps = 21 19:27:02 [INFO] train episode 26970: reward = -63.27, steps = 24 19:27:04 [INFO] train episode 26971: reward = -67.37, steps = 23 19:27:06 [INFO] train episode 26972: reward = -83.77, steps = 32 19:27:09 [INFO] train episode 26973: reward = -81.13, steps = 33 19:27:11 [INFO] train episode 26974: reward = -121.44, steps = 26 19:27:14 [INFO] train episode 26975: reward = -62.36, steps = 32 19:27:17 [INFO] train episode 26976: reward = -70.71, steps = 22 19:27:19 [INFO] train episode 26977: reward = -81.01, steps = 24 19:27:20 [INFO] train episode 26978: reward = -77.02, steps = 19 19:27:22 [INFO] train episode 26979: reward = -75.65, steps = 25 19:27:24 [INFO] train episode 26980: reward = -68.47, steps = 21 19:27:27 [INFO] train episode 26981: reward = -87.87, steps = 29 19:27:29 [INFO] train episode 26982: reward = -79.01, steps = 25 19:27:31 [INFO] train episode 26983: reward = -76.97, steps = 20 19:27:34 [INFO] train episode 26984: reward = -86.32, steps = 29 19:27:36 [INFO] train episode 26985: reward = -66.94, steps = 21 19:27:38 [INFO] train episode 26986: reward = -76.71, steps = 26 19:27:40 [INFO] train episode 26987: reward = -56.66, steps = 27 19:27:42 [INFO] train episode 26988: reward = -82.45, steps = 19 19:27:44 [INFO] train episode 26989: reward = -99.32, steps = 26 19:27:47 [INFO] train episode 26990: reward = -68.64, steps = 31 19:27:49 [INFO] train episode 26991: reward = -84.44, steps = 22 19:27:51 [INFO] train episode 26992: reward = -68.94, steps = 20 19:27:53 [INFO] train episode 26993: reward = -94.80, steps = 26 19:27:55 [INFO] train episode 26994: reward = -65.44, steps = 22 19:27:58 [INFO] train episode 26995: reward = -60.68, steps = 29 19:28:00 [INFO] train episode 26996: reward = -83.51, steps = 26 19:28:02 [INFO] train episode 26997: reward = -55.66, steps = 21 19:28:05 [INFO] train episode 26998: reward = -89.74, steps = 34 19:28:09 [INFO] train episode 26999: reward = -82.96, steps = 36 19:28:11 [INFO] train episode 27000: reward = -128.38, steps = 33 19:28:15 [INFO] train episode 27001: reward = -69.87, steps = 39 19:28:19 [INFO] train episode 27002: reward = -88.68, steps = 45 19:28:21 [INFO] train episode 27003: reward = -36.05, steps = 26 19:28:25 [INFO] train episode 27004: reward = -70.12, steps = 40 19:28:26 [INFO] train episode 27005: reward = -73.56, steps = 20 19:28:30 [INFO] train episode 27006: reward = -90.87, steps = 40 19:28:32 [INFO] train episode 27007: reward = -76.64, steps = 20 19:28:35 [INFO] train episode 27008: reward = -101.01, steps = 36 19:28:38 [INFO] train episode 27009: reward = -94.59, steps = 26 19:28:40 [INFO] train episode 27010: reward = -121.92, steps = 24 19:28:42 [INFO] train episode 27011: reward = -53.58, steps = 30 19:28:45 [INFO] train episode 27012: reward = -78.16, steps = 28 19:28:47 [INFO] train episode 27013: reward = -71.82, steps = 23 19:28:49 [INFO] train episode 27014: reward = -76.35, steps = 22 19:28:51 [INFO] train episode 27015: reward = -42.26, steps = 27 19:28:54 [INFO] train episode 27016: reward = -93.43, steps = 31 19:28:58 [INFO] train episode 27017: reward = -74.46, steps = 38 19:28:59 [INFO] train episode 27018: reward = -71.90, steps = 18 19:29:01 [INFO] train episode 27019: reward = -91.27, steps = 19 19:29:03 [INFO] train episode 27020: reward = -126.46, steps = 21 19:29:05 [INFO] train episode 27021: reward = -77.66, steps = 18 19:29:07 [INFO] train episode 27022: reward = -69.21, steps = 20 19:29:10 [INFO] train episode 27023: reward = -56.33, steps = 34 19:29:13 [INFO] train episode 27024: reward = -75.17, steps = 29 19:29:15 [INFO] train episode 27025: reward = -72.65, steps = 21 19:29:17 [INFO] train episode 27026: reward = -75.21, steps = 25 19:29:21 [INFO] train episode 27027: reward = -106.30, steps = 36 19:29:23 [INFO] train episode 27028: reward = -44.10, steps = 20 19:29:25 [INFO] train episode 27029: reward = -78.70, steps = 21 19:29:27 [INFO] train episode 27030: reward = -82.23, steps = 25 19:29:31 [INFO] train episode 27031: reward = -86.26, steps = 35 19:29:32 [INFO] train episode 27032: reward = -137.16, steps = 17 19:29:35 [INFO] train episode 27033: reward = -86.93, steps = 36 19:29:37 [INFO] train episode 27034: reward = -41.41, steps = 25 19:29:39 [INFO] train episode 27035: reward = -81.80, steps = 24 19:29:41 [INFO] train episode 27036: reward = -69.51, steps = 20 19:29:45 [INFO] train episode 27037: reward = -92.90, steps = 38 19:29:48 [INFO] train episode 27038: reward = -75.31, steps = 32 19:29:49 [INFO] train episode 27039: reward = -53.36, steps = 20 19:29:52 [INFO] train episode 27040: reward = -111.26, steps = 31 19:29:54 [INFO] train episode 27041: reward = -79.46, steps = 26 19:29:57 [INFO] train episode 27042: reward = -120.08, steps = 32 19:30:02 [INFO] train episode 27043: reward = -89.79, steps = 50 19:30:04 [INFO] train episode 27044: reward = -84.62, steps = 22 19:30:06 [INFO] train episode 27045: reward = -44.91, steps = 29 19:30:08 [INFO] train episode 27046: reward = -61.88, steps = 22 19:30:10 [INFO] train episode 27047: reward = -85.82, steps = 20 19:30:13 [INFO] train episode 27048: reward = -30.15, steps = 38 19:30:17 [INFO] train episode 27049: reward = -61.19, steps = 43 19:30:20 [INFO] train episode 27050: reward = -69.93, steps = 27 19:30:22 [INFO] train episode 27051: reward = -87.97, steps = 24 19:30:25 [INFO] train episode 27052: reward = -143.41, steps = 39 19:30:27 [INFO] train episode 27053: reward = -109.42, steps = 18 19:30:29 [INFO] train episode 27054: reward = -98.64, steps = 26 19:30:33 [INFO] train episode 27055: reward = -79.79, steps = 41 19:30:35 [INFO] train episode 27056: reward = -59.33, steps = 22 19:30:37 [INFO] train episode 27057: reward = -53.81, steps = 21 19:30:39 [INFO] train episode 27058: reward = -63.70, steps = 24 19:30:41 [INFO] train episode 27059: reward = -78.68, steps = 25 19:30:44 [INFO] train episode 27060: reward = -83.77, steps = 39 19:30:47 [INFO] train episode 27061: reward = -72.23, steps = 27 19:30:49 [INFO] train episode 27062: reward = -125.16, steps = 19 19:30:51 [INFO] train episode 27063: reward = -81.68, steps = 29 19:30:56 [INFO] train episode 27064: reward = -120.94, steps = 55 19:30:58 [INFO] train episode 27065: reward = -59.75, steps = 21 19:30:59 [INFO] train episode 27066: reward = -84.05, steps = 19 19:31:03 [INFO] train episode 27067: reward = -91.25, steps = 40 19:31:06 [INFO] train episode 27068: reward = -99.44, steps = 38 19:31:09 [INFO] train episode 27069: reward = -57.35, steps = 24 19:31:12 [INFO] train episode 27070: reward = -69.38, steps = 34 19:31:13 [INFO] train episode 27071: reward = -93.23, steps = 19 19:31:17 [INFO] train episode 27072: reward = -101.13, steps = 49 19:31:20 [INFO] train episode 27073: reward = -97.65, steps = 25 19:31:22 [INFO] train episode 27074: reward = -54.87, steps = 22 19:31:25 [INFO] train episode 27075: reward = -53.47, steps = 32 19:31:26 [INFO] train episode 27076: reward = -77.69, steps = 20 19:31:29 [INFO] train episode 27077: reward = -77.61, steps = 25 19:31:32 [INFO] train episode 27078: reward = -101.23, steps = 34 19:31:34 [INFO] train episode 27079: reward = -72.59, steps = 28 19:31:37 [INFO] train episode 27080: reward = -126.42, steps = 26 19:31:40 [INFO] train episode 27081: reward = -59.28, steps = 34 19:31:41 [INFO] train episode 27082: reward = -52.99, steps = 20 19:31:44 [INFO] train episode 27083: reward = -48.34, steps = 25 19:31:46 [INFO] train episode 27084: reward = -86.46, steps = 32 19:31:48 [INFO] train episode 27085: reward = -71.43, steps = 20 19:31:51 [INFO] train episode 27086: reward = -78.50, steps = 27 19:31:53 [INFO] train episode 27087: reward = -51.49, steps = 20 19:31:55 [INFO] train episode 27088: reward = -80.20, steps = 28 19:31:57 [INFO] train episode 27089: reward = -82.32, steps = 22 19:31:59 [INFO] train episode 27090: reward = -58.04, steps = 19 19:32:01 [INFO] train episode 27091: reward = -65.01, steps = 20 19:32:05 [INFO] train episode 27092: reward = -151.31, steps = 52 19:32:07 [INFO] train episode 27093: reward = -51.24, steps = 20 19:32:10 [INFO] train episode 27094: reward = -50.32, steps = 29 19:32:12 [INFO] train episode 27095: reward = -69.51, steps = 24 19:32:15 [INFO] train episode 27096: reward = -50.90, steps = 22 19:32:17 [INFO] train episode 27097: reward = -65.47, steps = 20 19:32:18 [INFO] train episode 27098: reward = -89.18, steps = 20 19:32:22 [INFO] train episode 27099: reward = -123.92, steps = 47 19:32:26 [INFO] train episode 27100: reward = -94.18, steps = 43 19:32:28 [INFO] train episode 27101: reward = -71.15, steps = 18 19:32:29 [INFO] train episode 27102: reward = -53.50, steps = 14 19:32:31 [INFO] train episode 27103: reward = -81.02, steps = 21 19:32:33 [INFO] train episode 27104: reward = -93.06, steps = 26 19:32:35 [INFO] train episode 27105: reward = -40.01, steps = 24 19:32:38 [INFO] train episode 27106: reward = -95.99, steps = 26 19:32:40 [INFO] train episode 27107: reward = -66.68, steps = 29 19:32:43 [INFO] train episode 27108: reward = -68.82, steps = 19 19:32:44 [INFO] train episode 27109: reward = -56.72, steps = 21 19:32:47 [INFO] train episode 27110: reward = -78.72, steps = 33 19:32:49 [INFO] train episode 27111: reward = -71.62, steps = 20 19:32:51 [INFO] train episode 27112: reward = -71.38, steps = 23 19:32:54 [INFO] train episode 27113: reward = -85.92, steps = 31 19:32:56 [INFO] train episode 27114: reward = -83.79, steps = 28 19:33:00 [INFO] train episode 27115: reward = -86.03, steps = 37 19:33:02 [INFO] train episode 27116: reward = -65.61, steps = 25 19:33:04 [INFO] train episode 27117: reward = -69.99, steps = 22 19:33:06 [INFO] train episode 27118: reward = -76.42, steps = 27 19:33:08 [INFO] train episode 27119: reward = -61.10, steps = 20 19:33:11 [INFO] train episode 27120: reward = -82.22, steps = 28 19:33:13 [INFO] train episode 27121: reward = -66.57, steps = 26 19:33:16 [INFO] train episode 27122: reward = -72.24, steps = 28 19:33:19 [INFO] train episode 27123: reward = -60.88, steps = 36 19:33:20 [INFO] train episode 27124: reward = -82.21, steps = 20 19:33:24 [INFO] train episode 27125: reward = -102.63, steps = 38 19:33:26 [INFO] train episode 27126: reward = -60.06, steps = 27 19:33:29 [INFO] train episode 27127: reward = -93.71, steps = 29 19:33:31 [INFO] train episode 27128: reward = -115.26, steps = 27 19:33:34 [INFO] train episode 27129: reward = -119.51, steps = 33 19:33:37 [INFO] train episode 27130: reward = -53.54, steps = 25 19:33:39 [INFO] train episode 27131: reward = -56.67, steps = 26 19:33:41 [INFO] train episode 27132: reward = -71.89, steps = 28 19:33:43 [INFO] train episode 27133: reward = -64.50, steps = 17 19:33:45 [INFO] train episode 27134: reward = -107.13, steps = 30 19:33:48 [INFO] train episode 27135: reward = -66.15, steps = 28 19:33:51 [INFO] train episode 27136: reward = -85.33, steps = 26 19:33:55 [INFO] train episode 27137: reward = -112.82, steps = 47 19:33:58 [INFO] train episode 27138: reward = -79.88, steps = 35 19:34:00 [INFO] train episode 27139: reward = -44.36, steps = 23 19:34:02 [INFO] train episode 27140: reward = -58.66, steps = 27 19:34:05 [INFO] train episode 27141: reward = -71.19, steps = 34 19:34:07 [INFO] train episode 27142: reward = -79.37, steps = 19 19:34:10 [INFO] train episode 27143: reward = -61.94, steps = 30 19:34:12 [INFO] train episode 27144: reward = -60.17, steps = 26 19:34:15 [INFO] train episode 27145: reward = -75.95, steps = 36 19:34:18 [INFO] train episode 27146: reward = -45.13, steps = 31 19:34:20 [INFO] train episode 27147: reward = -63.71, steps = 20 19:34:22 [INFO] train episode 27148: reward = -77.01, steps = 24 19:34:27 [INFO] train episode 27149: reward = -176.73, steps = 54 19:34:29 [INFO] train episode 27150: reward = -106.14, steps = 21 19:34:31 [INFO] train episode 27151: reward = -82.70, steps = 27 19:34:34 [INFO] train episode 27152: reward = -46.15, steps = 32 19:34:38 [INFO] train episode 27153: reward = -81.34, steps = 35 19:34:40 [INFO] train episode 27154: reward = -97.16, steps = 23 19:34:44 [INFO] train episode 27155: reward = -46.62, steps = 39 19:34:46 [INFO] train episode 27156: reward = -62.56, steps = 21 19:34:48 [INFO] train episode 27157: reward = -61.73, steps = 25 19:34:52 [INFO] train episode 27158: reward = -107.52, steps = 51 19:34:55 [INFO] train episode 27159: reward = -45.03, steps = 29 19:34:57 [INFO] train episode 27160: reward = -66.40, steps = 20 19:35:01 [INFO] train episode 27161: reward = -162.93, steps = 42 19:35:04 [INFO] train episode 27162: reward = -69.78, steps = 41 19:35:06 [INFO] train episode 27163: reward = -81.70, steps = 22 19:35:08 [INFO] train episode 27164: reward = -62.75, steps = 18 19:35:12 [INFO] train episode 27165: reward = -123.41, steps = 37 19:35:15 [INFO] train episode 27166: reward = -95.24, steps = 25 19:35:17 [INFO] train episode 27167: reward = -59.83, steps = 28 19:35:19 [INFO] train episode 27168: reward = -109.72, steps = 20 19:35:22 [INFO] train episode 27169: reward = -86.56, steps = 37 19:35:24 [INFO] train episode 27170: reward = -65.94, steps = 24 19:35:29 [INFO] train episode 27171: reward = -156.17, steps = 50 19:35:31 [INFO] train episode 27172: reward = -81.56, steps = 22 19:35:34 [INFO] train episode 27173: reward = -43.76, steps = 32 19:35:37 [INFO] train episode 27174: reward = -59.79, steps = 38 19:35:42 [INFO] train episode 27175: reward = -81.38, steps = 59 19:35:44 [INFO] train episode 27176: reward = -58.92, steps = 17 19:35:47 [INFO] train episode 27177: reward = -98.76, steps = 43 19:35:49 [INFO] train episode 27178: reward = -94.95, steps = 20 19:35:52 [INFO] train episode 27179: reward = -47.64, steps = 31 19:35:55 [INFO] train episode 27180: reward = -108.05, steps = 34 19:35:57 [INFO] train episode 27181: reward = -68.84, steps = 23 19:36:00 [INFO] train episode 27182: reward = -66.05, steps = 32 19:36:02 [INFO] train episode 27183: reward = -44.75, steps = 23 19:36:07 [INFO] train episode 27184: reward = -83.78, steps = 51 19:36:10 [INFO] train episode 27185: reward = -60.68, steps = 37 19:36:13 [INFO] train episode 27186: reward = -97.91, steps = 41 19:36:17 [INFO] train episode 27187: reward = -71.55, steps = 31 19:36:18 [INFO] train episode 27188: reward = -57.86, steps = 19 19:36:20 [INFO] train episode 27189: reward = -77.76, steps = 24 19:36:23 [INFO] train episode 27190: reward = -76.98, steps = 25 19:36:25 [INFO] train episode 27191: reward = -92.76, steps = 27 19:36:28 [INFO] train episode 27192: reward = -106.72, steps = 34 19:36:32 [INFO] train episode 27193: reward = -66.05, steps = 48 19:36:36 [INFO] train episode 27194: reward = -63.32, steps = 40 19:36:40 [INFO] train episode 27195: reward = -166.34, steps = 44 19:36:42 [INFO] train episode 27196: reward = -85.96, steps = 20 19:36:44 [INFO] train episode 27197: reward = -41.73, steps = 28 19:36:47 [INFO] train episode 27198: reward = -74.59, steps = 30 19:36:50 [INFO] train episode 27199: reward = -66.47, steps = 32 19:36:52 [INFO] train episode 27200: reward = -70.13, steps = 20 19:36:54 [INFO] train episode 27201: reward = -73.69, steps = 21 19:36:56 [INFO] train episode 27202: reward = -46.94, steps = 24 19:36:58 [INFO] train episode 27203: reward = -70.96, steps = 23 19:37:00 [INFO] train episode 27204: reward = -79.64, steps = 31 19:37:03 [INFO] train episode 27205: reward = -129.00, steps = 30 19:37:06 [INFO] train episode 27206: reward = -81.02, steps = 26 19:37:09 [INFO] train episode 27207: reward = -43.19, steps = 43 19:37:12 [INFO] train episode 27208: reward = -38.44, steps = 32 19:37:15 [INFO] train episode 27209: reward = -82.31, steps = 27 19:37:19 [INFO] train episode 27210: reward = -94.09, steps = 53 19:37:22 [INFO] train episode 27211: reward = -68.88, steps = 29 19:37:24 [INFO] train episode 27212: reward = -97.49, steps = 22 19:37:27 [INFO] train episode 27213: reward = -68.17, steps = 38 19:37:30 [INFO] train episode 27214: reward = -79.05, steps = 33 19:37:33 [INFO] train episode 27215: reward = -87.49, steps = 31 19:37:36 [INFO] train episode 27216: reward = -99.09, steps = 30 19:37:38 [INFO] train episode 27217: reward = -59.02, steps = 28 19:37:41 [INFO] train episode 27218: reward = -63.90, steps = 26 19:37:43 [INFO] train episode 27219: reward = -78.44, steps = 28 19:37:46 [INFO] train episode 27220: reward = -85.40, steps = 29 19:37:47 [INFO] train episode 27221: reward = -58.67, steps = 20 19:37:49 [INFO] train episode 27222: reward = -60.11, steps = 22 19:37:53 [INFO] train episode 27223: reward = -64.46, steps = 43 19:37:56 [INFO] train episode 27224: reward = -114.27, steps = 30 19:37:58 [INFO] train episode 27225: reward = -58.12, steps = 21 19:38:00 [INFO] train episode 27226: reward = -71.74, steps = 24 19:38:03 [INFO] train episode 27227: reward = -49.55, steps = 29 19:38:04 [INFO] train episode 27228: reward = -87.86, steps = 21 19:38:08 [INFO] train episode 27229: reward = -87.83, steps = 32 19:38:11 [INFO] train episode 27230: reward = -79.52, steps = 27 19:38:14 [INFO] train episode 27231: reward = -73.98, steps = 35 19:38:16 [INFO] train episode 27232: reward = -65.91, steps = 21 19:38:19 [INFO] train episode 27233: reward = -64.46, steps = 38 19:38:21 [INFO] train episode 27234: reward = -65.48, steps = 24 19:38:24 [INFO] train episode 27235: reward = -69.39, steps = 38 19:38:27 [INFO] train episode 27236: reward = -78.10, steps = 30 19:38:31 [INFO] train episode 27237: reward = -51.04, steps = 44 19:38:33 [INFO] train episode 27238: reward = -77.66, steps = 20 19:38:36 [INFO] train episode 27239: reward = -41.23, steps = 34 19:38:38 [INFO] train episode 27240: reward = -73.73, steps = 23 19:38:40 [INFO] train episode 27241: reward = -71.47, steps = 25 19:38:43 [INFO] train episode 27242: reward = -61.18, steps = 26 19:38:45 [INFO] train episode 27243: reward = -72.04, steps = 29 19:38:47 [INFO] train episode 27244: reward = -57.86, steps = 18 19:38:49 [INFO] train episode 27245: reward = -55.06, steps = 26 19:38:51 [INFO] train episode 27246: reward = -93.18, steps = 22 19:38:53 [INFO] train episode 27247: reward = -33.04, steps = 20 19:38:56 [INFO] train episode 27248: reward = -64.14, steps = 31 19:38:58 [INFO] train episode 27249: reward = -87.35, steps = 19 19:39:00 [INFO] train episode 27250: reward = -53.48, steps = 25 19:39:02 [INFO] train episode 27251: reward = -80.19, steps = 26 19:39:04 [INFO] train episode 27252: reward = -71.80, steps = 23 19:39:07 [INFO] train episode 27253: reward = -140.43, steps = 30 19:39:10 [INFO] train episode 27254: reward = -89.95, steps = 32 19:39:12 [INFO] train episode 27255: reward = -50.85, steps = 22 19:39:14 [INFO] train episode 27256: reward = -89.04, steps = 22 19:39:17 [INFO] train episode 27257: reward = -62.41, steps = 30 19:39:19 [INFO] train episode 27258: reward = -54.51, steps = 27 19:39:22 [INFO] train episode 27259: reward = -75.42, steps = 28 19:39:23 [INFO] train episode 27260: reward = -125.22, steps = 18 19:39:26 [INFO] train episode 27261: reward = -57.95, steps = 26 19:39:28 [INFO] train episode 27262: reward = -101.22, steps = 32 19:39:33 [INFO] train episode 27263: reward = -126.01, steps = 45 19:39:35 [INFO] train episode 27264: reward = -67.79, steps = 25 19:39:39 [INFO] train episode 27265: reward = -82.60, steps = 38 19:39:42 [INFO] train episode 27266: reward = -91.89, steps = 37 19:39:44 [INFO] train episode 27267: reward = -118.45, steps = 27 19:39:46 [INFO] train episode 27268: reward = -81.21, steps = 24 19:39:49 [INFO] train episode 27269: reward = -57.79, steps = 23 19:39:52 [INFO] train episode 27270: reward = -81.55, steps = 37 19:39:55 [INFO] train episode 27271: reward = -109.51, steps = 30 19:39:58 [INFO] train episode 27272: reward = -110.39, steps = 33 19:40:00 [INFO] train episode 27273: reward = -56.47, steps = 21 19:40:02 [INFO] train episode 27274: reward = -48.57, steps = 22 19:40:04 [INFO] train episode 27275: reward = -66.08, steps = 24 19:40:07 [INFO] train episode 27276: reward = -93.49, steps = 25 19:40:09 [INFO] train episode 27277: reward = -52.02, steps = 22 19:40:11 [INFO] train episode 27278: reward = -47.05, steps = 33 19:40:13 [INFO] train episode 27279: reward = -60.15, steps = 18 19:40:17 [INFO] train episode 27280: reward = -87.50, steps = 43 19:40:19 [INFO] train episode 27281: reward = -72.86, steps = 20 19:40:22 [INFO] train episode 27282: reward = -49.26, steps = 31 19:40:25 [INFO] train episode 27283: reward = -57.37, steps = 35 19:40:27 [INFO] train episode 27284: reward = -76.32, steps = 22 19:40:29 [INFO] train episode 27285: reward = -100.55, steps = 27 19:40:33 [INFO] train episode 27286: reward = -112.96, steps = 44 19:40:36 [INFO] train episode 27287: reward = -46.16, steps = 32 19:40:40 [INFO] train episode 27288: reward = -145.07, steps = 44 19:40:42 [INFO] train episode 27289: reward = -68.61, steps = 25 19:40:46 [INFO] train episode 27290: reward = -82.56, steps = 38 19:40:50 [INFO] train episode 27291: reward = -129.18, steps = 49 19:40:52 [INFO] train episode 27292: reward = -71.64, steps = 22 19:40:55 [INFO] train episode 27293: reward = -102.97, steps = 26 19:40:57 [INFO] train episode 27294: reward = -79.40, steps = 26 19:41:00 [INFO] train episode 27295: reward = -113.67, steps = 31 19:41:03 [INFO] train episode 27296: reward = -54.61, steps = 31 19:41:06 [INFO] train episode 27297: reward = -62.31, steps = 28 19:41:08 [INFO] train episode 27298: reward = -43.35, steps = 23 19:41:11 [INFO] train episode 27299: reward = -67.13, steps = 24 19:41:13 [INFO] train episode 27300: reward = -71.34, steps = 30 19:41:16 [INFO] train episode 27301: reward = -80.35, steps = 26 19:41:19 [INFO] train episode 27302: reward = -108.26, steps = 35 19:41:21 [INFO] train episode 27303: reward = -51.98, steps = 31 19:41:23 [INFO] train episode 27304: reward = -79.38, steps = 19 19:41:26 [INFO] train episode 27305: reward = -65.54, steps = 35 19:41:29 [INFO] train episode 27306: reward = -93.39, steps = 23 19:41:31 [INFO] train episode 27307: reward = -50.72, steps = 31 19:41:33 [INFO] train episode 27308: reward = -96.51, steps = 24 19:41:36 [INFO] train episode 27309: reward = -54.33, steps = 32 19:41:39 [INFO] train episode 27310: reward = -76.76, steps = 33 19:41:41 [INFO] train episode 27311: reward = -77.36, steps = 21 19:41:43 [INFO] train episode 27312: reward = -93.82, steps = 20 19:41:46 [INFO] train episode 27313: reward = -75.45, steps = 32 19:41:49 [INFO] train episode 27314: reward = -73.70, steps = 26 19:41:51 [INFO] train episode 27315: reward = -74.08, steps = 23 19:41:53 [INFO] train episode 27316: reward = -62.33, steps = 31 19:41:56 [INFO] train episode 27317: reward = -45.61, steps = 31 19:42:01 [INFO] train episode 27318: reward = -79.48, steps = 47 19:42:03 [INFO] train episode 27319: reward = -63.42, steps = 28 19:42:06 [INFO] train episode 27320: reward = -60.72, steps = 28 19:42:10 [INFO] train episode 27321: reward = -145.75, steps = 46 19:42:13 [INFO] train episode 27322: reward = -82.65, steps = 38 19:42:15 [INFO] train episode 27323: reward = -149.22, steps = 21 19:42:18 [INFO] train episode 27324: reward = -73.99, steps = 29 19:42:23 [INFO] train episode 27325: reward = -110.82, steps = 61 19:42:26 [INFO] train episode 27326: reward = -45.25, steps = 25 19:42:28 [INFO] train episode 27327: reward = -67.38, steps = 30 19:42:31 [INFO] train episode 27328: reward = -57.49, steps = 27 19:42:33 [INFO] train episode 27329: reward = -60.90, steps = 24 19:42:36 [INFO] train episode 27330: reward = -119.98, steps = 27 19:42:39 [INFO] train episode 27331: reward = -42.68, steps = 31 19:42:42 [INFO] train episode 27332: reward = -110.39, steps = 38 19:42:44 [INFO] train episode 27333: reward = -65.20, steps = 21 19:42:46 [INFO] train episode 27334: reward = -75.59, steps = 26 19:42:49 [INFO] train episode 27335: reward = -54.63, steps = 26 19:42:52 [INFO] train episode 27336: reward = -73.56, steps = 33 19:42:55 [INFO] train episode 27337: reward = -57.65, steps = 32 19:42:58 [INFO] train episode 27338: reward = -60.06, steps = 36 19:43:00 [INFO] train episode 27339: reward = -64.72, steps = 21 19:43:02 [INFO] train episode 27340: reward = -45.70, steps = 23 19:43:04 [INFO] train episode 27341: reward = -60.59, steps = 21 19:43:07 [INFO] train episode 27342: reward = -100.37, steps = 29 19:43:09 [INFO] train episode 27343: reward = -79.26, steps = 21 19:43:11 [INFO] train episode 27344: reward = -78.62, steps = 23 19:43:14 [INFO] train episode 27345: reward = -90.65, steps = 36 19:43:18 [INFO] train episode 27346: reward = -88.64, steps = 43 19:43:20 [INFO] train episode 27347: reward = -99.80, steps = 31 19:43:24 [INFO] train episode 27348: reward = -80.26, steps = 38 19:43:27 [INFO] train episode 27349: reward = -187.18, steps = 27 19:43:29 [INFO] train episode 27350: reward = -52.85, steps = 24 19:43:31 [INFO] train episode 27351: reward = -64.72, steps = 26 19:43:35 [INFO] train episode 27352: reward = -80.78, steps = 41 19:43:37 [INFO] train episode 27353: reward = -74.92, steps = 21 19:43:39 [INFO] train episode 27354: reward = -65.45, steps = 21 19:43:41 [INFO] train episode 27355: reward = -79.53, steps = 19 19:43:44 [INFO] train episode 27356: reward = -129.83, steps = 35 19:43:47 [INFO] train episode 27357: reward = -90.45, steps = 35 19:43:49 [INFO] train episode 27358: reward = -76.87, steps = 24 19:43:53 [INFO] train episode 27359: reward = -80.75, steps = 48 19:43:55 [INFO] train episode 27360: reward = -82.88, steps = 20 19:43:58 [INFO] train episode 27361: reward = -71.02, steps = 31 19:44:00 [INFO] train episode 27362: reward = -52.42, steps = 23 19:44:02 [INFO] train episode 27363: reward = -58.02, steps = 24 19:44:05 [INFO] train episode 27364: reward = -46.34, steps = 19 19:44:07 [INFO] train episode 27365: reward = -116.75, steps = 23 19:44:09 [INFO] train episode 27366: reward = -87.12, steps = 20 19:44:11 [INFO] train episode 27367: reward = -66.25, steps = 23 19:44:15 [INFO] train episode 27368: reward = -50.31, steps = 38 19:44:17 [INFO] train episode 27369: reward = -86.13, steps = 19 19:44:19 [INFO] train episode 27370: reward = -92.04, steps = 23 19:44:21 [INFO] train episode 27371: reward = -77.35, steps = 20 19:44:24 [INFO] train episode 27372: reward = -110.71, steps = 41 19:44:27 [INFO] train episode 27373: reward = -102.78, steps = 31 19:44:30 [INFO] train episode 27374: reward = -99.88, steps = 24 19:44:32 [INFO] train episode 27375: reward = -81.77, steps = 20 19:44:34 [INFO] train episode 27376: reward = -80.35, steps = 20 19:44:37 [INFO] train episode 27377: reward = -64.01, steps = 34 19:44:40 [INFO] train episode 27378: reward = -55.74, steps = 34 19:44:42 [INFO] train episode 27379: reward = -44.36, steps = 23 19:44:45 [INFO] train episode 27380: reward = -64.38, steps = 38 19:44:47 [INFO] train episode 27381: reward = -71.20, steps = 22 19:44:52 [INFO] train episode 27382: reward = -92.80, steps = 46 19:44:54 [INFO] train episode 27383: reward = -51.32, steps = 22 19:44:56 [INFO] train episode 27384: reward = -63.30, steps = 19 19:44:59 [INFO] train episode 27385: reward = -84.28, steps = 44 19:45:03 [INFO] train episode 27386: reward = -50.29, steps = 34 19:45:05 [INFO] train episode 27387: reward = -127.57, steps = 26 19:45:08 [INFO] train episode 27388: reward = -85.36, steps = 29 19:45:10 [INFO] train episode 27389: reward = -42.02, steps = 28 19:45:12 [INFO] train episode 27390: reward = -62.53, steps = 22 19:45:16 [INFO] train episode 27391: reward = -85.56, steps = 44 19:45:19 [INFO] train episode 27392: reward = -90.06, steps = 31 19:45:21 [INFO] train episode 27393: reward = -70.65, steps = 20 19:45:23 [INFO] train episode 27394: reward = -123.78, steps = 21 19:45:25 [INFO] train episode 27395: reward = -77.13, steps = 25 19:45:29 [INFO] train episode 27396: reward = -172.99, steps = 49 19:45:32 [INFO] train episode 27397: reward = -48.33, steps = 27 19:45:34 [INFO] train episode 27398: reward = -56.32, steps = 29 19:45:37 [INFO] train episode 27399: reward = -95.62, steps = 27 19:45:39 [INFO] train episode 27400: reward = -120.73, steps = 20 19:45:41 [INFO] train episode 27401: reward = -103.80, steps = 20 19:45:43 [INFO] train episode 27402: reward = -93.42, steps = 23 19:45:45 [INFO] train episode 27403: reward = -84.31, steps = 23 19:45:47 [INFO] train episode 27404: reward = -65.92, steps = 20 19:45:50 [INFO] train episode 27405: reward = -105.99, steps = 34 19:45:52 [INFO] train episode 27406: reward = -97.79, steps = 23 19:45:55 [INFO] train episode 27407: reward = -87.63, steps = 27 19:45:57 [INFO] train episode 27408: reward = -59.09, steps = 29 19:45:59 [INFO] train episode 27409: reward = -55.71, steps = 23 19:46:02 [INFO] train episode 27410: reward = -64.02, steps = 34 19:46:05 [INFO] train episode 27411: reward = -52.20, steps = 31 19:46:08 [INFO] train episode 27412: reward = -67.68, steps = 34 19:46:10 [INFO] train episode 27413: reward = -48.49, steps = 25 19:46:12 [INFO] train episode 27414: reward = -141.66, steps = 23 19:46:14 [INFO] train episode 27415: reward = -86.35, steps = 18 19:46:18 [INFO] train episode 27416: reward = -58.21, steps = 42 19:46:20 [INFO] train episode 27417: reward = -61.19, steps = 20 19:46:24 [INFO] train episode 27418: reward = -156.51, steps = 46 19:46:28 [INFO] train episode 27419: reward = -100.06, steps = 43 19:46:30 [INFO] train episode 27420: reward = -55.89, steps = 21 19:46:31 [INFO] train episode 27421: reward = -108.70, steps = 20 19:46:33 [INFO] train episode 27422: reward = -45.80, steps = 21 19:46:36 [INFO] train episode 27423: reward = -98.33, steps = 26 19:46:38 [INFO] train episode 27424: reward = -84.70, steps = 20 19:46:42 [INFO] train episode 27425: reward = -132.21, steps = 47 19:46:44 [INFO] train episode 27426: reward = -61.69, steps = 20 19:46:47 [INFO] train episode 27427: reward = -82.57, steps = 35 19:46:50 [INFO] train episode 27428: reward = -68.60, steps = 29 19:46:52 [INFO] train episode 27429: reward = -68.12, steps = 24 19:46:55 [INFO] train episode 27430: reward = -92.60, steps = 30 19:46:57 [INFO] train episode 27431: reward = -65.37, steps = 27 19:46:59 [INFO] train episode 27432: reward = -78.22, steps = 23 19:47:01 [INFO] train episode 27433: reward = -73.68, steps = 19 19:47:06 [INFO] train episode 27434: reward = -132.91, steps = 39 19:47:09 [INFO] train episode 27435: reward = -45.66, steps = 34 19:47:11 [INFO] train episode 27436: reward = -61.99, steps = 19 19:47:13 [INFO] train episode 27437: reward = -79.54, steps = 28 19:47:16 [INFO] train episode 27438: reward = -46.42, steps = 33 19:47:18 [INFO] train episode 27439: reward = -94.39, steps = 21 19:47:20 [INFO] train episode 27440: reward = -116.72, steps = 20 19:47:22 [INFO] train episode 27441: reward = -89.33, steps = 19 19:47:24 [INFO] train episode 27442: reward = -88.64, steps = 22 19:47:27 [INFO] train episode 27443: reward = -68.62, steps = 33 19:47:30 [INFO] train episode 27444: reward = -105.54, steps = 38 19:47:32 [INFO] train episode 27445: reward = -77.32, steps = 23 19:47:36 [INFO] train episode 27446: reward = -93.11, steps = 44 19:47:40 [INFO] train episode 27447: reward = -88.95, steps = 39 19:47:43 [INFO] train episode 27448: reward = -63.49, steps = 36 19:47:45 [INFO] train episode 27449: reward = -55.36, steps = 27 19:47:50 [INFO] train episode 27450: reward = -137.99, steps = 51 19:47:54 [INFO] train episode 27451: reward = -95.72, steps = 42 19:47:57 [INFO] train episode 27452: reward = -98.38, steps = 38 19:48:01 [INFO] train episode 27453: reward = -90.67, steps = 41 19:48:03 [INFO] train episode 27454: reward = -75.75, steps = 26 19:48:05 [INFO] train episode 27455: reward = -96.81, steps = 30 19:48:08 [INFO] train episode 27456: reward = -98.82, steps = 19 19:48:09 [INFO] train episode 27457: reward = -96.61, steps = 19 19:48:12 [INFO] train episode 27458: reward = -77.98, steps = 30 19:48:14 [INFO] train episode 27459: reward = -67.38, steps = 26 19:48:18 [INFO] train episode 27460: reward = -54.63, steps = 41 19:48:21 [INFO] train episode 27461: reward = -116.90, steps = 38 19:48:25 [INFO] train episode 27462: reward = -84.14, steps = 43 19:48:27 [INFO] train episode 27463: reward = -76.46, steps = 19 19:48:29 [INFO] train episode 27464: reward = -75.95, steps = 31 19:48:32 [INFO] train episode 27465: reward = -37.27, steps = 24 19:48:34 [INFO] train episode 27466: reward = -49.51, steps = 24 19:48:36 [INFO] train episode 27467: reward = -67.78, steps = 23 19:48:38 [INFO] train episode 27468: reward = -59.56, steps = 22 19:48:42 [INFO] train episode 27469: reward = -100.03, steps = 37 19:48:45 [INFO] train episode 27470: reward = -79.62, steps = 41 19:48:47 [INFO] train episode 27471: reward = -86.24, steps = 20 19:48:50 [INFO] train episode 27472: reward = -64.18, steps = 30 19:48:54 [INFO] train episode 27473: reward = -86.21, steps = 49 19:48:56 [INFO] train episode 27474: reward = -103.35, steps = 24 19:48:59 [INFO] train episode 27475: reward = -95.23, steps = 24 19:49:02 [INFO] train episode 27476: reward = -78.01, steps = 36 19:49:04 [INFO] train episode 27477: reward = -69.71, steps = 22 19:49:06 [INFO] train episode 27478: reward = -65.13, steps = 25 19:49:08 [INFO] train episode 27479: reward = -81.03, steps = 20 19:49:10 [INFO] train episode 27480: reward = -83.66, steps = 25 19:49:13 [INFO] train episode 27481: reward = -119.49, steps = 29 19:49:17 [INFO] train episode 27482: reward = -129.11, steps = 47 19:49:19 [INFO] train episode 27483: reward = -41.03, steps = 22 19:49:21 [INFO] train episode 27484: reward = -73.89, steps = 28 19:49:23 [INFO] train episode 27485: reward = -106.90, steps = 24 19:49:25 [INFO] train episode 27486: reward = -87.03, steps = 18 19:49:27 [INFO] train episode 27487: reward = -77.39, steps = 22 19:49:31 [INFO] train episode 27488: reward = -140.70, steps = 44 19:49:33 [INFO] train episode 27489: reward = -72.45, steps = 24 19:49:36 [INFO] train episode 27490: reward = -54.79, steps = 37 19:49:42 [INFO] train episode 27491: reward = -143.31, steps = 57 19:49:44 [INFO] train episode 27492: reward = -104.57, steps = 26 19:49:46 [INFO] train episode 27493: reward = -116.04, steps = 22 19:49:48 [INFO] train episode 27494: reward = -72.95, steps = 25 19:49:51 [INFO] train episode 27495: reward = -67.14, steps = 26 19:49:52 [INFO] train episode 27496: reward = -53.52, steps = 18 19:49:54 [INFO] train episode 27497: reward = -81.22, steps = 24 19:49:57 [INFO] train episode 27498: reward = -52.78, steps = 28 19:49:59 [INFO] train episode 27499: reward = -153.19, steps = 19 19:50:02 [INFO] train episode 27500: reward = -85.54, steps = 23 19:50:04 [INFO] train episode 27501: reward = -56.94, steps = 21 19:50:06 [INFO] train episode 27502: reward = -73.75, steps = 25 19:50:09 [INFO] train episode 27503: reward = -73.81, steps = 39 19:50:11 [INFO] train episode 27504: reward = -89.36, steps = 20 19:50:14 [INFO] train episode 27505: reward = -83.48, steps = 27 19:50:17 [INFO] train episode 27506: reward = -33.32, steps = 34 19:50:20 [INFO] train episode 27507: reward = -60.12, steps = 33 19:50:22 [INFO] train episode 27508: reward = -78.50, steps = 24 19:50:24 [INFO] train episode 27509: reward = -51.43, steps = 21 19:50:26 [INFO] train episode 27510: reward = -62.01, steps = 29 19:50:28 [INFO] train episode 27511: reward = -63.58, steps = 22 19:50:31 [INFO] train episode 27512: reward = -85.34, steps = 31 19:50:34 [INFO] train episode 27513: reward = -64.08, steps = 26 19:50:37 [INFO] train episode 27514: reward = -51.83, steps = 27 19:50:39 [INFO] train episode 27515: reward = -70.25, steps = 29 19:50:41 [INFO] train episode 27516: reward = -94.19, steps = 23 19:50:43 [INFO] train episode 27517: reward = -42.53, steps = 21 19:50:46 [INFO] train episode 27518: reward = -83.47, steps = 29 19:50:48 [INFO] train episode 27519: reward = -74.59, steps = 24 19:50:51 [INFO] train episode 27520: reward = -114.62, steps = 31 19:50:53 [INFO] train episode 27521: reward = -94.43, steps = 28 19:50:57 [INFO] train episode 27522: reward = -118.96, steps = 41 19:50:59 [INFO] train episode 27523: reward = -129.12, steps = 20 19:51:01 [INFO] train episode 27524: reward = -55.23, steps = 21 19:51:03 [INFO] train episode 27525: reward = -74.42, steps = 26 19:51:05 [INFO] train episode 27526: reward = -54.47, steps = 26 19:51:10 [INFO] train episode 27527: reward = -93.95, steps = 49 19:51:12 [INFO] train episode 27528: reward = -59.58, steps = 23 19:51:15 [INFO] train episode 27529: reward = -57.73, steps = 29 19:51:17 [INFO] train episode 27530: reward = -78.53, steps = 22 19:51:19 [INFO] train episode 27531: reward = -79.47, steps = 30 19:51:23 [INFO] train episode 27532: reward = -136.77, steps = 35 19:51:26 [INFO] train episode 27533: reward = -83.84, steps = 29 19:51:28 [INFO] train episode 27534: reward = -53.74, steps = 29 19:51:31 [INFO] train episode 27535: reward = -28.53, steps = 38 19:51:35 [INFO] train episode 27536: reward = -69.47, steps = 37 19:51:37 [INFO] train episode 27537: reward = -47.56, steps = 23 19:51:39 [INFO] train episode 27538: reward = -89.90, steps = 19 19:51:42 [INFO] train episode 27539: reward = -73.68, steps = 29 19:51:47 [INFO] train episode 27540: reward = -164.39, steps = 63 19:51:49 [INFO] train episode 27541: reward = -59.24, steps = 24 19:51:53 [INFO] train episode 27542: reward = -79.72, steps = 44 19:51:55 [INFO] train episode 27543: reward = -40.04, steps = 20 19:51:57 [INFO] train episode 27544: reward = -59.56, steps = 16 19:51:59 [INFO] train episode 27545: reward = -51.70, steps = 20 19:52:02 [INFO] train episode 27546: reward = -74.76, steps = 41 19:52:06 [INFO] train episode 27547: reward = -76.16, steps = 36 19:52:09 [INFO] train episode 27548: reward = -54.79, steps = 36 19:52:11 [INFO] train episode 27549: reward = -56.23, steps = 21 19:52:13 [INFO] train episode 27550: reward = -98.02, steps = 24 19:52:15 [INFO] train episode 27551: reward = -56.53, steps = 22 19:52:18 [INFO] train episode 27552: reward = -134.23, steps = 32 19:52:21 [INFO] train episode 27553: reward = -35.28, steps = 31 19:52:23 [INFO] train episode 27554: reward = -99.58, steps = 22 19:52:25 [INFO] train episode 27555: reward = -38.26, steps = 26 19:52:27 [INFO] train episode 27556: reward = -81.68, steps = 21 19:52:29 [INFO] train episode 27557: reward = -50.64, steps = 21 19:52:31 [INFO] train episode 27558: reward = -58.33, steps = 20 19:52:33 [INFO] train episode 27559: reward = -76.41, steps = 22 19:52:35 [INFO] train episode 27560: reward = -125.20, steps = 20 19:52:37 [INFO] train episode 27561: reward = -59.80, steps = 18 19:52:39 [INFO] train episode 27562: reward = -63.34, steps = 30 19:52:43 [INFO] train episode 27563: reward = -80.85, steps = 42 19:52:45 [INFO] train episode 27564: reward = -69.54, steps = 25 19:52:48 [INFO] train episode 27565: reward = -78.01, steps = 21 19:52:51 [INFO] train episode 27566: reward = -50.86, steps = 37 19:52:53 [INFO] train episode 27567: reward = -56.84, steps = 20 19:52:56 [INFO] train episode 27568: reward = -122.19, steps = 37 19:52:57 [INFO] train episode 27569: reward = -66.96, steps = 18 19:53:00 [INFO] train episode 27570: reward = -293.45, steps = 23 19:53:02 [INFO] train episode 27571: reward = -87.15, steps = 19 19:53:05 [INFO] train episode 27572: reward = -71.06, steps = 30 19:53:09 [INFO] train episode 27573: reward = -97.75, steps = 44 19:53:12 [INFO] train episode 27574: reward = -123.38, steps = 39 19:53:16 [INFO] train episode 27575: reward = -75.36, steps = 42 19:53:18 [INFO] train episode 27576: reward = -65.54, steps = 20 19:53:22 [INFO] train episode 27577: reward = -125.40, steps = 41 19:53:25 [INFO] train episode 27578: reward = -47.81, steps = 34 19:53:27 [INFO] train episode 27579: reward = -80.07, steps = 23 19:53:30 [INFO] train episode 27580: reward = -51.44, steps = 34 19:53:33 [INFO] train episode 27581: reward = -69.62, steps = 37 19:53:37 [INFO] train episode 27582: reward = -86.65, steps = 37 19:53:39 [INFO] train episode 27583: reward = -61.24, steps = 27 19:53:42 [INFO] train episode 27584: reward = -72.90, steps = 27 19:53:43 [INFO] train episode 27585: reward = -99.60, steps = 20 19:53:46 [INFO] train episode 27586: reward = -62.54, steps = 29 19:53:48 [INFO] train episode 27587: reward = -111.92, steps = 26 19:53:52 [INFO] train episode 27588: reward = -108.75, steps = 41 19:53:56 [INFO] train episode 27589: reward = -60.03, steps = 37 19:53:59 [INFO] train episode 27590: reward = -120.16, steps = 36 19:54:01 [INFO] train episode 27591: reward = -47.67, steps = 19 19:54:04 [INFO] train episode 27592: reward = -80.29, steps = 32 19:54:06 [INFO] train episode 27593: reward = -58.41, steps = 19 19:54:07 [INFO] train episode 27594: reward = -53.69, steps = 20 19:54:11 [INFO] train episode 27595: reward = -63.44, steps = 37 19:54:14 [INFO] train episode 27596: reward = -110.63, steps = 36 19:54:17 [INFO] train episode 27597: reward = -73.38, steps = 34 19:54:20 [INFO] train episode 27598: reward = -81.94, steps = 29 19:54:23 [INFO] train episode 27599: reward = -59.76, steps = 31 19:54:25 [INFO] train episode 27600: reward = -54.55, steps = 21 19:54:27 [INFO] train episode 27601: reward = -68.68, steps = 25 19:54:32 [INFO] train episode 27602: reward = -111.88, steps = 51 19:54:35 [INFO] train episode 27603: reward = -78.60, steps = 33 19:54:36 [INFO] train episode 27604: reward = -83.89, steps = 18 19:54:38 [INFO] train episode 27605: reward = -63.13, steps = 21 19:54:43 [INFO] train episode 27606: reward = -95.34, steps = 52 19:54:46 [INFO] train episode 27607: reward = -71.77, steps = 35 19:54:49 [INFO] train episode 27608: reward = -61.87, steps = 27 19:54:52 [INFO] train episode 27609: reward = -72.41, steps = 38 19:54:55 [INFO] train episode 27610: reward = -64.99, steps = 28 19:54:57 [INFO] train episode 27611: reward = -78.22, steps = 23 19:55:00 [INFO] train episode 27612: reward = -89.90, steps = 34 19:55:03 [INFO] train episode 27613: reward = -50.17, steps = 30 19:55:05 [INFO] train episode 27614: reward = -60.21, steps = 19 19:55:07 [INFO] train episode 27615: reward = -58.82, steps = 26 19:55:09 [INFO] train episode 27616: reward = -60.14, steps = 21 19:55:11 [INFO] train episode 27617: reward = -81.07, steps = 22 19:55:13 [INFO] train episode 27618: reward = -66.42, steps = 27 19:55:17 [INFO] train episode 27619: reward = -77.90, steps = 35 19:55:19 [INFO] train episode 27620: reward = -85.10, steps = 26 19:55:22 [INFO] train episode 27621: reward = -77.46, steps = 31 19:55:25 [INFO] train episode 27622: reward = -67.50, steps = 32 19:55:27 [INFO] train episode 27623: reward = -120.76, steps = 19 19:55:28 [INFO] train episode 27624: reward = -59.45, steps = 21 19:55:31 [INFO] train episode 27625: reward = -102.11, steps = 30 19:55:34 [INFO] train episode 27626: reward = -59.86, steps = 29 19:55:36 [INFO] train episode 27627: reward = -26.17, steps = 29 19:55:38 [INFO] train episode 27628: reward = -71.13, steps = 21 19:55:42 [INFO] train episode 27629: reward = -46.63, steps = 45 19:55:44 [INFO] train episode 27630: reward = -84.81, steps = 25 19:55:48 [INFO] train episode 27631: reward = -113.11, steps = 39 19:55:51 [INFO] train episode 27632: reward = -107.44, steps = 41 19:55:53 [INFO] train episode 27633: reward = -49.36, steps = 22 19:55:55 [INFO] train episode 27634: reward = -63.53, steps = 19 19:55:59 [INFO] train episode 27635: reward = -100.37, steps = 34 19:56:01 [INFO] train episode 27636: reward = -88.90, steps = 22 19:56:04 [INFO] train episode 27637: reward = -61.41, steps = 32 19:56:06 [INFO] train episode 27638: reward = -49.20, steps = 19 19:56:07 [INFO] train episode 27639: reward = -95.94, steps = 14 19:56:11 [INFO] train episode 27640: reward = -99.20, steps = 45 19:56:13 [INFO] train episode 27641: reward = -52.51, steps = 21 19:56:16 [INFO] train episode 27642: reward = -100.75, steps = 33 19:56:18 [INFO] train episode 27643: reward = -45.96, steps = 24 19:56:20 [INFO] train episode 27644: reward = -80.00, steps = 27 19:56:23 [INFO] train episode 27645: reward = -71.74, steps = 24 19:56:25 [INFO] train episode 27646: reward = -61.56, steps = 24 19:56:27 [INFO] train episode 27647: reward = -118.61, steps = 32 19:56:30 [INFO] train episode 27648: reward = -92.71, steps = 28 19:56:32 [INFO] train episode 27649: reward = -48.75, steps = 22 19:56:34 [INFO] train episode 27650: reward = -67.88, steps = 20 19:56:36 [INFO] train episode 27651: reward = -89.02, steps = 24 19:56:39 [INFO] train episode 27652: reward = -106.07, steps = 32 19:56:42 [INFO] train episode 27653: reward = -59.90, steps = 32 19:56:45 [INFO] train episode 27654: reward = -90.00, steps = 31 19:56:47 [INFO] train episode 27655: reward = -84.77, steps = 31 19:56:50 [INFO] train episode 27656: reward = -50.82, steps = 31 19:56:52 [INFO] train episode 27657: reward = -97.15, steps = 22 19:56:54 [INFO] train episode 27658: reward = -88.93, steps = 24 19:56:57 [INFO] train episode 27659: reward = -50.26, steps = 31 19:56:59 [INFO] train episode 27660: reward = -57.83, steps = 26 19:57:02 [INFO] train episode 27661: reward = -74.05, steps = 31 19:57:04 [INFO] train episode 27662: reward = -56.54, steps = 22 19:57:06 [INFO] train episode 27663: reward = -67.24, steps = 19 19:57:08 [INFO] train episode 27664: reward = -65.12, steps = 23 19:57:11 [INFO] train episode 27665: reward = -40.69, steps = 35 19:57:15 [INFO] train episode 27666: reward = -82.00, steps = 42 19:57:19 [INFO] train episode 27667: reward = -43.97, steps = 40 19:57:20 [INFO] train episode 27668: reward = -100.45, steps = 19 19:57:25 [INFO] train episode 27669: reward = -95.40, steps = 46 19:57:28 [INFO] train episode 27670: reward = -146.88, steps = 33 19:57:30 [INFO] train episode 27671: reward = -46.69, steps = 20 19:57:32 [INFO] train episode 27672: reward = -63.58, steps = 23 19:57:34 [INFO] train episode 27673: reward = -70.19, steps = 23 19:57:37 [INFO] train episode 27674: reward = -72.35, steps = 30 19:57:40 [INFO] train episode 27675: reward = -68.77, steps = 41 19:57:42 [INFO] train episode 27676: reward = -55.82, steps = 21 19:57:45 [INFO] train episode 27677: reward = -70.05, steps = 20 19:57:46 [INFO] train episode 27678: reward = -70.58, steps = 20 19:57:49 [INFO] train episode 27679: reward = -46.03, steps = 29 19:57:51 [INFO] train episode 27680: reward = -50.56, steps = 24 19:57:54 [INFO] train episode 27681: reward = -76.52, steps = 36 19:57:57 [INFO] train episode 27682: reward = -65.75, steps = 27 19:57:59 [INFO] train episode 27683: reward = -78.48, steps = 20 19:58:01 [INFO] train episode 27684: reward = -56.11, steps = 21 19:58:03 [INFO] train episode 27685: reward = -146.35, steps = 23 19:58:06 [INFO] train episode 27686: reward = -94.72, steps = 39 19:58:08 [INFO] train episode 27687: reward = -53.41, steps = 19 19:58:10 [INFO] train episode 27688: reward = -73.16, steps = 24 19:58:13 [INFO] train episode 27689: reward = -90.03, steps = 28 19:58:15 [INFO] train episode 27690: reward = -79.90, steps = 27 19:58:20 [INFO] train episode 27691: reward = -80.98, steps = 42 19:58:22 [INFO] train episode 27692: reward = -53.25, steps = 27 19:58:25 [INFO] train episode 27693: reward = -113.45, steps = 37 19:58:27 [INFO] train episode 27694: reward = -44.41, steps = 22 19:58:31 [INFO] train episode 27695: reward = -96.55, steps = 42 19:58:33 [INFO] train episode 27696: reward = -90.74, steps = 22 19:58:38 [INFO] train episode 27697: reward = -82.61, steps = 49 19:58:41 [INFO] train episode 27698: reward = -103.74, steps = 30 19:58:44 [INFO] train episode 27699: reward = -109.67, steps = 40 19:58:46 [INFO] train episode 27700: reward = -63.23, steps = 20 19:58:48 [INFO] train episode 27701: reward = -88.91, steps = 18 19:58:51 [INFO] train episode 27702: reward = -83.03, steps = 29 19:58:54 [INFO] train episode 27703: reward = -91.27, steps = 34 19:58:58 [INFO] train episode 27704: reward = -73.53, steps = 38 19:59:00 [INFO] train episode 27705: reward = -83.89, steps = 23 19:59:02 [INFO] train episode 27706: reward = -42.86, steps = 26 19:59:04 [INFO] train episode 27707: reward = -49.09, steps = 19 19:59:08 [INFO] train episode 27708: reward = -123.92, steps = 39 19:59:11 [INFO] train episode 27709: reward = -59.84, steps = 33 19:59:14 [INFO] train episode 27710: reward = -81.33, steps = 33 19:59:16 [INFO] train episode 27711: reward = -96.80, steps = 27 19:59:20 [INFO] train episode 27712: reward = -59.78, steps = 33 19:59:22 [INFO] train episode 27713: reward = -74.16, steps = 26 19:59:26 [INFO] train episode 27714: reward = -130.88, steps = 33 19:59:29 [INFO] train episode 27715: reward = -147.01, steps = 38 19:59:32 [INFO] train episode 27716: reward = -105.60, steps = 30 19:59:34 [INFO] train episode 27717: reward = -46.55, steps = 21 19:59:36 [INFO] train episode 27718: reward = -76.04, steps = 23 19:59:38 [INFO] train episode 27719: reward = -106.23, steps = 25 19:59:40 [INFO] train episode 27720: reward = -63.13, steps = 26 19:59:43 [INFO] train episode 27721: reward = -65.17, steps = 24 19:59:45 [INFO] train episode 27722: reward = -40.78, steps = 22 19:59:47 [INFO] train episode 27723: reward = -70.30, steps = 33 19:59:50 [INFO] train episode 27724: reward = -114.39, steps = 24 19:59:52 [INFO] train episode 27725: reward = -63.08, steps = 24 19:59:55 [INFO] train episode 27726: reward = -104.85, steps = 34 19:59:58 [INFO] train episode 27727: reward = -75.97, steps = 40 20:00:00 [INFO] train episode 27728: reward = -61.72, steps = 22 20:00:04 [INFO] train episode 27729: reward = -123.57, steps = 36 20:00:06 [INFO] train episode 27730: reward = -66.48, steps = 21 20:00:08 [INFO] train episode 27731: reward = -51.84, steps = 23 20:00:09 [INFO] train episode 27732: reward = -63.88, steps = 20 20:00:11 [INFO] train episode 27733: reward = -80.72, steps = 21 20:00:14 [INFO] train episode 27734: reward = -65.74, steps = 31 20:00:17 [INFO] train episode 27735: reward = -66.93, steps = 32 20:00:19 [INFO] train episode 27736: reward = -45.54, steps = 20 20:00:21 [INFO] train episode 27737: reward = -56.24, steps = 25 20:00:23 [INFO] train episode 27738: reward = -51.75, steps = 22 20:00:26 [INFO] train episode 27739: reward = -55.13, steps = 34 20:00:28 [INFO] train episode 27740: reward = -57.00, steps = 20 20:00:30 [INFO] train episode 27741: reward = -71.33, steps = 20 20:00:34 [INFO] train episode 27742: reward = -83.48, steps = 41 20:00:37 [INFO] train episode 27743: reward = -109.84, steps = 35 20:00:40 [INFO] train episode 27744: reward = -98.55, steps = 35 20:00:43 [INFO] train episode 27745: reward = -68.47, steps = 31 20:00:46 [INFO] train episode 27746: reward = -147.99, steps = 31 20:00:49 [INFO] train episode 27747: reward = -109.16, steps = 38 20:00:53 [INFO] train episode 27748: reward = -58.44, steps = 33 20:00:56 [INFO] train episode 27749: reward = -74.45, steps = 38 20:00:59 [INFO] train episode 27750: reward = -38.55, steps = 30 20:01:02 [INFO] train episode 27751: reward = -95.80, steps = 25 20:01:06 [INFO] train episode 27752: reward = -93.39, steps = 40 20:01:11 [INFO] train episode 27753: reward = -52.95, steps = 52 20:01:13 [INFO] train episode 27754: reward = -107.36, steps = 22 20:01:15 [INFO] train episode 27755: reward = -88.12, steps = 22 20:01:19 [INFO] train episode 27756: reward = -103.42, steps = 42 20:01:21 [INFO] train episode 27757: reward = -83.78, steps = 18 20:01:23 [INFO] train episode 27758: reward = -64.94, steps = 19 20:01:26 [INFO] train episode 27759: reward = -112.70, steps = 33 20:01:28 [INFO] train episode 27760: reward = -45.64, steps = 21 20:01:32 [INFO] train episode 27761: reward = -118.44, steps = 57 20:01:34 [INFO] train episode 27762: reward = -67.25, steps = 20 20:01:37 [INFO] train episode 27763: reward = -63.90, steps = 33 20:01:41 [INFO] train episode 27764: reward = -84.65, steps = 38 20:01:43 [INFO] train episode 27765: reward = -47.80, steps = 21 20:01:45 [INFO] train episode 27766: reward = -38.38, steps = 27 20:01:47 [INFO] train episode 27767: reward = -59.16, steps = 23 20:01:51 [INFO] train episode 27768: reward = -60.01, steps = 44 20:01:53 [INFO] train episode 27769: reward = -50.61, steps = 22 20:01:56 [INFO] train episode 27770: reward = -58.62, steps = 25 20:01:59 [INFO] train episode 27771: reward = -101.38, steps = 27 20:02:01 [INFO] train episode 27772: reward = -49.87, steps = 25 20:02:04 [INFO] train episode 27773: reward = -79.55, steps = 28 20:02:06 [INFO] train episode 27774: reward = -68.57, steps = 28 20:02:08 [INFO] train episode 27775: reward = -95.39, steps = 20 20:02:10 [INFO] train episode 27776: reward = -72.93, steps = 28 20:02:13 [INFO] train episode 27777: reward = -86.25, steps = 28 20:02:17 [INFO] train episode 27778: reward = -140.35, steps = 47 20:02:20 [INFO] train episode 27779: reward = -60.17, steps = 33 20:02:23 [INFO] train episode 27780: reward = -89.34, steps = 40 20:02:25 [INFO] train episode 27781: reward = -61.17, steps = 22 20:02:29 [INFO] train episode 27782: reward = -94.23, steps = 34 20:02:31 [INFO] train episode 27783: reward = -100.60, steps = 29 20:02:33 [INFO] train episode 27784: reward = -66.33, steps = 20 20:02:35 [INFO] train episode 27785: reward = -87.28, steps = 22 20:02:37 [INFO] train episode 27786: reward = -85.96, steps = 19 20:02:41 [INFO] train episode 27787: reward = -86.12, steps = 40 20:02:44 [INFO] train episode 27788: reward = -65.40, steps = 35 20:02:47 [INFO] train episode 27789: reward = -104.79, steps = 20 20:02:49 [INFO] train episode 27790: reward = -93.63, steps = 20 20:02:52 [INFO] train episode 27791: reward = -38.21, steps = 33 20:02:57 [INFO] train episode 27792: reward = -152.08, steps = 58 20:02:59 [INFO] train episode 27793: reward = -64.05, steps = 29 20:03:01 [INFO] train episode 27794: reward = -63.40, steps = 23 20:03:04 [INFO] train episode 27795: reward = -111.19, steps = 24 20:03:06 [INFO] train episode 27796: reward = -69.06, steps = 17 20:03:07 [INFO] train episode 27797: reward = -67.58, steps = 21 20:03:11 [INFO] train episode 27798: reward = -43.02, steps = 37 20:03:13 [INFO] train episode 27799: reward = -67.05, steps = 31 20:03:15 [INFO] train episode 27800: reward = -57.29, steps = 23 20:03:17 [INFO] train episode 27801: reward = -97.15, steps = 19 20:03:19 [INFO] train episode 27802: reward = -84.46, steps = 20 20:03:22 [INFO] train episode 27803: reward = -67.21, steps = 29 20:03:24 [INFO] train episode 27804: reward = -71.29, steps = 26 20:03:26 [INFO] train episode 27805: reward = -84.25, steps = 22 20:03:28 [INFO] train episode 27806: reward = -72.12, steps = 20 20:03:29 [INFO] train episode 27807: reward = -83.33, steps = 19 20:03:32 [INFO] train episode 27808: reward = -65.89, steps = 33 20:03:36 [INFO] train episode 27809: reward = -68.73, steps = 42 20:03:39 [INFO] train episode 27810: reward = -68.80, steps = 31 20:03:43 [INFO] train episode 27811: reward = -90.35, steps = 44 20:03:45 [INFO] train episode 27812: reward = -97.10, steps = 24 20:03:47 [INFO] train episode 27813: reward = -122.84, steps = 26 20:03:49 [INFO] train episode 27814: reward = -82.98, steps = 22 20:03:52 [INFO] train episode 27815: reward = -70.37, steps = 24 20:03:55 [INFO] train episode 27816: reward = -48.13, steps = 34 20:03:57 [INFO] train episode 27817: reward = -61.47, steps = 29 20:03:59 [INFO] train episode 27818: reward = -57.82, steps = 21 20:04:03 [INFO] train episode 27819: reward = -69.05, steps = 45 20:04:05 [INFO] train episode 27820: reward = -54.57, steps = 23 20:04:07 [INFO] train episode 27821: reward = -75.28, steps = 21 20:04:09 [INFO] train episode 27822: reward = -65.04, steps = 19 20:04:12 [INFO] train episode 27823: reward = -82.00, steps = 37 20:04:14 [INFO] train episode 27824: reward = -96.41, steps = 25 20:04:17 [INFO] train episode 27825: reward = -75.29, steps = 27 20:04:19 [INFO] train episode 27826: reward = -92.72, steps = 26 20:04:21 [INFO] train episode 27827: reward = -69.18, steps = 28 20:04:25 [INFO] train episode 27828: reward = -68.64, steps = 37 20:04:27 [INFO] train episode 27829: reward = -60.55, steps = 21 20:04:29 [INFO] train episode 27830: reward = -95.97, steps = 27 20:04:32 [INFO] train episode 27831: reward = -108.83, steps = 29 20:04:35 [INFO] train episode 27832: reward = -85.13, steps = 38 20:04:37 [INFO] train episode 27833: reward = -74.66, steps = 19 20:04:40 [INFO] train episode 27834: reward = -86.29, steps = 32 20:04:42 [INFO] train episode 27835: reward = -71.40, steps = 21 20:04:44 [INFO] train episode 27836: reward = -47.80, steps = 20 20:04:47 [INFO] train episode 27837: reward = -80.66, steps = 29 20:04:49 [INFO] train episode 27838: reward = -55.31, steps = 22 20:04:51 [INFO] train episode 27839: reward = -68.86, steps = 29 20:04:54 [INFO] train episode 27840: reward = -98.78, steps = 34 20:04:58 [INFO] train episode 27841: reward = -62.78, steps = 30 20:05:01 [INFO] train episode 27842: reward = -102.74, steps = 31 20:05:03 [INFO] train episode 27843: reward = -77.35, steps = 26 20:05:06 [INFO] train episode 27844: reward = -98.08, steps = 34 20:05:09 [INFO] train episode 27845: reward = -179.83, steps = 35 20:05:13 [INFO] train episode 27846: reward = -63.45, steps = 40 20:05:16 [INFO] train episode 27847: reward = -82.80, steps = 30 20:05:18 [INFO] train episode 27848: reward = -96.05, steps = 20 20:05:20 [INFO] train episode 27849: reward = -71.40, steps = 20 20:05:22 [INFO] train episode 27850: reward = -113.42, steps = 24 20:05:24 [INFO] train episode 27851: reward = -54.46, steps = 31 20:05:27 [INFO] train episode 27852: reward = -87.30, steps = 31 20:05:30 [INFO] train episode 27853: reward = -70.06, steps = 33 20:05:33 [INFO] train episode 27854: reward = -74.09, steps = 30 20:05:35 [INFO] train episode 27855: reward = -63.29, steps = 22 20:05:37 [INFO] train episode 27856: reward = -56.82, steps = 20 20:05:39 [INFO] train episode 27857: reward = -83.01, steps = 28 20:05:41 [INFO] train episode 27858: reward = -56.10, steps = 20 20:05:43 [INFO] train episode 27859: reward = -61.74, steps = 19 20:05:45 [INFO] train episode 27860: reward = -99.97, steps = 28 20:05:48 [INFO] train episode 27861: reward = -101.24, steps = 31 20:05:50 [INFO] train episode 27862: reward = -56.49, steps = 25 20:05:52 [INFO] train episode 27863: reward = -44.84, steps = 18 20:05:54 [INFO] train episode 27864: reward = -47.96, steps = 21 20:05:58 [INFO] train episode 27865: reward = -111.31, steps = 49 20:06:00 [INFO] train episode 27866: reward = -74.66, steps = 22 20:06:03 [INFO] train episode 27867: reward = -102.07, steps = 32 20:06:07 [INFO] train episode 27868: reward = -104.85, steps = 42 20:06:09 [INFO] train episode 27869: reward = -43.85, steps = 22 20:06:11 [INFO] train episode 27870: reward = -99.17, steps = 30 20:06:14 [INFO] train episode 27871: reward = -60.73, steps = 32 20:06:16 [INFO] train episode 27872: reward = -69.20, steps = 28 20:06:20 [INFO] train episode 27873: reward = -62.41, steps = 36 20:06:22 [INFO] train episode 27874: reward = -60.74, steps = 20 20:06:23 [INFO] train episode 27875: reward = -56.38, steps = 19 20:06:25 [INFO] train episode 27876: reward = -91.74, steps = 18 20:06:27 [INFO] train episode 27877: reward = -45.71, steps = 20 20:06:30 [INFO] train episode 27878: reward = -96.64, steps = 37 20:06:32 [INFO] train episode 27879: reward = -92.56, steps = 22 20:06:34 [INFO] train episode 27880: reward = -76.06, steps = 23 20:06:38 [INFO] train episode 27881: reward = -95.87, steps = 43 20:06:42 [INFO] train episode 27882: reward = -68.62, steps = 43 20:06:46 [INFO] train episode 27883: reward = -63.89, steps = 49 20:06:48 [INFO] train episode 27884: reward = -87.32, steps = 25 20:06:50 [INFO] train episode 27885: reward = -70.22, steps = 23 20:06:53 [INFO] train episode 27886: reward = -59.63, steps = 20 20:06:55 [INFO] train episode 27887: reward = -71.29, steps = 23 20:06:57 [INFO] train episode 27888: reward = -60.63, steps = 22 20:06:59 [INFO] train episode 27889: reward = -54.19, steps = 22 20:07:00 [INFO] train episode 27890: reward = -120.95, steps = 18 20:07:03 [INFO] train episode 27891: reward = -153.03, steps = 37 20:07:05 [INFO] train episode 27892: reward = -55.29, steps = 22 20:07:09 [INFO] train episode 27893: reward = -75.93, steps = 34 20:07:11 [INFO] train episode 27894: reward = -68.82, steps = 25 20:07:14 [INFO] train episode 27895: reward = -86.54, steps = 37 20:07:16 [INFO] train episode 27896: reward = -58.12, steps = 20 20:07:18 [INFO] train episode 27897: reward = -100.11, steps = 21 20:07:20 [INFO] train episode 27898: reward = -65.58, steps = 30 20:07:22 [INFO] train episode 27899: reward = -56.01, steps = 19 20:07:25 [INFO] train episode 27900: reward = -79.31, steps = 30 20:07:28 [INFO] train episode 27901: reward = -61.09, steps = 37 20:07:30 [INFO] train episode 27902: reward = -68.43, steps = 24 20:07:35 [INFO] train episode 27903: reward = -107.06, steps = 52 20:07:37 [INFO] train episode 27904: reward = -38.36, steps = 26 20:07:40 [INFO] train episode 27905: reward = -108.68, steps = 34 20:07:44 [INFO] train episode 27906: reward = -56.08, steps = 38 20:07:45 [INFO] train episode 27907: reward = -66.50, steps = 19 20:07:47 [INFO] train episode 27908: reward = -50.00, steps = 22 20:07:50 [INFO] train episode 27909: reward = -72.10, steps = 30 20:07:54 [INFO] train episode 27910: reward = -84.92, steps = 37 20:07:56 [INFO] train episode 27911: reward = -59.74, steps = 26 20:08:00 [INFO] train episode 27912: reward = -75.00, steps = 36 20:08:03 [INFO] train episode 27913: reward = -54.20, steps = 34 20:08:05 [INFO] train episode 27914: reward = -58.98, steps = 22 20:08:08 [INFO] train episode 27915: reward = -92.49, steps = 40 20:08:10 [INFO] train episode 27916: reward = -82.52, steps = 18 20:08:13 [INFO] train episode 27917: reward = -95.06, steps = 35 20:08:15 [INFO] train episode 27918: reward = -103.57, steps = 23 20:08:17 [INFO] train episode 27919: reward = -51.31, steps = 18 20:08:19 [INFO] train episode 27920: reward = -41.88, steps = 20 20:08:21 [INFO] train episode 27921: reward = -56.79, steps = 31 20:08:25 [INFO] train episode 27922: reward = -60.40, steps = 38 20:08:26 [INFO] train episode 27923: reward = -68.88, steps = 19 20:08:28 [INFO] train episode 27924: reward = -73.87, steps = 21 20:08:32 [INFO] train episode 27925: reward = -58.74, steps = 31 20:08:33 [INFO] train episode 27926: reward = -125.76, steps = 19 20:08:35 [INFO] train episode 27927: reward = -106.27, steps = 20 20:08:37 [INFO] train episode 27928: reward = -67.71, steps = 20 20:08:41 [INFO] train episode 27929: reward = -124.54, steps = 39 20:08:43 [INFO] train episode 27930: reward = -68.69, steps = 29 20:08:48 [INFO] train episode 27931: reward = -92.37, steps = 44 20:08:50 [INFO] train episode 27932: reward = -58.11, steps = 23 20:08:52 [INFO] train episode 27933: reward = -45.98, steps = 20 20:08:55 [INFO] train episode 27934: reward = -68.46, steps = 34 20:08:56 [INFO] train episode 27935: reward = -105.19, steps = 18 20:08:58 [INFO] train episode 27936: reward = -80.04, steps = 19 20:09:01 [INFO] train episode 27937: reward = -43.85, steps = 33 20:09:05 [INFO] train episode 27938: reward = -63.80, steps = 37 20:09:08 [INFO] train episode 27939: reward = -72.63, steps = 32 20:09:10 [INFO] train episode 27940: reward = -58.08, steps = 22 20:09:13 [INFO] train episode 27941: reward = -51.86, steps = 40 20:09:16 [INFO] train episode 27942: reward = -95.31, steps = 33 20:09:18 [INFO] train episode 27943: reward = -55.28, steps = 20 20:09:20 [INFO] train episode 27944: reward = -82.27, steps = 22 20:09:22 [INFO] train episode 27945: reward = -69.39, steps = 23 20:09:24 [INFO] train episode 27946: reward = -29.44, steps = 26 20:09:26 [INFO] train episode 27947: reward = -47.82, steps = 22 20:09:28 [INFO] train episode 27948: reward = -68.94, steps = 21 20:09:30 [INFO] train episode 27949: reward = -95.31, steps = 24 20:09:32 [INFO] train episode 27950: reward = -56.40, steps = 20 20:09:36 [INFO] train episode 27951: reward = -87.10, steps = 41 20:09:39 [INFO] train episode 27952: reward = -60.33, steps = 28 20:09:41 [INFO] train episode 27953: reward = -84.15, steps = 26 20:09:43 [INFO] train episode 27954: reward = -77.85, steps = 22 20:09:45 [INFO] train episode 27955: reward = -86.10, steps = 21 20:09:47 [INFO] train episode 27956: reward = -85.83, steps = 31 20:09:51 [INFO] train episode 27957: reward = -64.31, steps = 39 20:09:53 [INFO] train episode 27958: reward = -53.26, steps = 24 20:09:57 [INFO] train episode 27959: reward = -129.66, steps = 41 20:10:00 [INFO] train episode 27960: reward = -92.87, steps = 41 20:10:02 [INFO] train episode 27961: reward = -87.83, steps = 21 20:10:05 [INFO] train episode 27962: reward = -67.70, steps = 30 20:10:07 [INFO] train episode 27963: reward = -96.30, steps = 24 20:10:09 [INFO] train episode 27964: reward = -55.44, steps = 22 20:10:11 [INFO] train episode 27965: reward = -82.65, steps = 20 20:10:14 [INFO] train episode 27966: reward = -57.65, steps = 31 20:10:16 [INFO] train episode 27967: reward = -62.57, steps = 27 20:10:18 [INFO] train episode 27968: reward = -59.49, steps = 22 20:10:20 [INFO] train episode 27969: reward = -55.32, steps = 21 20:10:23 [INFO] train episode 27970: reward = -73.54, steps = 40 20:10:26 [INFO] train episode 27971: reward = -61.63, steps = 21 20:10:28 [INFO] train episode 27972: reward = -40.04, steps = 23 20:10:29 [INFO] train episode 27973: reward = -78.44, steps = 18 20:10:31 [INFO] train episode 27974: reward = -46.12, steps = 20 20:10:35 [INFO] train episode 27975: reward = -146.41, steps = 39 20:10:39 [INFO] train episode 27976: reward = -96.65, steps = 45 20:10:42 [INFO] train episode 27977: reward = -50.90, steps = 28 20:10:43 [INFO] train episode 27978: reward = -68.89, steps = 19 20:10:47 [INFO] train episode 27979: reward = -52.81, steps = 37 20:10:51 [INFO] train episode 27980: reward = -88.65, steps = 38 20:10:53 [INFO] train episode 27981: reward = -67.86, steps = 31 20:10:55 [INFO] train episode 27982: reward = -90.35, steps = 20 20:10:58 [INFO] train episode 27983: reward = -81.16, steps = 29 20:11:00 [INFO] train episode 27984: reward = -38.75, steps = 26 20:11:02 [INFO] train episode 27985: reward = -56.71, steps = 21 20:11:04 [INFO] train episode 27986: reward = -81.02, steps = 20 20:11:07 [INFO] train episode 27987: reward = -61.25, steps = 30 20:11:09 [INFO] train episode 27988: reward = -101.31, steps = 21 20:11:11 [INFO] train episode 27989: reward = -75.06, steps = 31 20:11:14 [INFO] train episode 27990: reward = -69.52, steps = 25 20:11:17 [INFO] train episode 27991: reward = -53.39, steps = 31 20:11:18 [INFO] train episode 27992: reward = -56.34, steps = 19 20:11:20 [INFO] train episode 27993: reward = -165.53, steps = 22 20:11:25 [INFO] train episode 27994: reward = -86.33, steps = 50 20:11:28 [INFO] train episode 27995: reward = -82.09, steps = 42 20:11:32 [INFO] train episode 27996: reward = -44.50, steps = 34 20:11:35 [INFO] train episode 27997: reward = -108.98, steps = 37 20:11:37 [INFO] train episode 27998: reward = -67.91, steps = 20 20:11:38 [INFO] train episode 27999: reward = -60.88, steps = 19 20:11:40 [INFO] train episode 28000: reward = -67.53, steps = 24 20:11:43 [INFO] train episode 28001: reward = -124.74, steps = 29 20:11:46 [INFO] train episode 28002: reward = -120.37, steps = 38 20:11:49 [INFO] train episode 28003: reward = -87.91, steps = 28 20:11:51 [INFO] train episode 28004: reward = -73.75, steps = 25 20:11:54 [INFO] train episode 28005: reward = -46.52, steps = 28 20:11:56 [INFO] train episode 28006: reward = -92.14, steps = 20 20:11:58 [INFO] train episode 28007: reward = -62.33, steps = 23 20:12:00 [INFO] train episode 28008: reward = -52.65, steps = 22 20:12:02 [INFO] train episode 28009: reward = -79.45, steps = 29 20:12:05 [INFO] train episode 28010: reward = -78.60, steps = 24 20:12:08 [INFO] train episode 28011: reward = -93.24, steps = 36 20:12:12 [INFO] train episode 28012: reward = -68.75, steps = 49 20:12:15 [INFO] train episode 28013: reward = -77.74, steps = 32 20:12:17 [INFO] train episode 28014: reward = -49.12, steps = 25 20:12:19 [INFO] train episode 28015: reward = -82.26, steps = 22 20:12:21 [INFO] train episode 28016: reward = -68.51, steps = 22 20:12:23 [INFO] train episode 28017: reward = -66.57, steps = 21 20:12:27 [INFO] train episode 28018: reward = -85.75, steps = 40 20:12:29 [INFO] train episode 28019: reward = -73.49, steps = 25 20:12:34 [INFO] train episode 28020: reward = -237.53, steps = 55 20:12:39 [INFO] train episode 28021: reward = -106.91, steps = 51 20:12:42 [INFO] train episode 28022: reward = -61.59, steps = 31 20:12:44 [INFO] train episode 28023: reward = -43.87, steps = 28 20:12:46 [INFO] train episode 28024: reward = -127.13, steps = 22 20:12:49 [INFO] train episode 28025: reward = -93.22, steps = 29 20:12:51 [INFO] train episode 28026: reward = -82.20, steps = 23 20:12:53 [INFO] train episode 28027: reward = -86.72, steps = 20 20:12:55 [INFO] train episode 28028: reward = -99.74, steps = 19 20:12:57 [INFO] train episode 28029: reward = -48.44, steps = 30 20:13:00 [INFO] train episode 28030: reward = -61.96, steps = 31 20:13:02 [INFO] train episode 28031: reward = -93.12, steps = 25 20:13:05 [INFO] train episode 28032: reward = -95.56, steps = 31 20:13:07 [INFO] train episode 28033: reward = -72.09, steps = 20 20:13:10 [INFO] train episode 28034: reward = -70.34, steps = 33 20:13:12 [INFO] train episode 28035: reward = -75.63, steps = 21 20:13:14 [INFO] train episode 28036: reward = -56.07, steps = 25 20:13:16 [INFO] train episode 28037: reward = -82.14, steps = 25 20:13:18 [INFO] train episode 28038: reward = -90.27, steps = 20 20:13:21 [INFO] train episode 28039: reward = -72.22, steps = 27 20:13:23 [INFO] train episode 28040: reward = -100.80, steps = 22 20:13:26 [INFO] train episode 28041: reward = -117.75, steps = 41 20:13:29 [INFO] train episode 28042: reward = -88.10, steps = 33 20:13:31 [INFO] train episode 28043: reward = -78.55, steps = 20 20:13:36 [INFO] train episode 28044: reward = -89.11, steps = 56 20:13:40 [INFO] train episode 28045: reward = -106.90, steps = 40 20:13:44 [INFO] train episode 28046: reward = -154.96, steps = 49 20:13:48 [INFO] train episode 28047: reward = -67.66, steps = 28 20:13:50 [INFO] train episode 28048: reward = -100.70, steps = 32 20:13:53 [INFO] train episode 28049: reward = -70.30, steps = 32 20:13:56 [INFO] train episode 28050: reward = -94.05, steps = 36 20:13:58 [INFO] train episode 28051: reward = -61.33, steps = 19 20:14:00 [INFO] train episode 28052: reward = -87.97, steps = 19 20:14:02 [INFO] train episode 28053: reward = -81.42, steps = 24 20:14:04 [INFO] train episode 28054: reward = -71.65, steps = 16 20:14:06 [INFO] train episode 28055: reward = -46.95, steps = 19 20:14:07 [INFO] train episode 28056: reward = -57.36, steps = 20 20:14:10 [INFO] train episode 28057: reward = -105.52, steps = 28 20:14:12 [INFO] train episode 28058: reward = -75.83, steps = 19 20:14:14 [INFO] train episode 28059: reward = -64.97, steps = 32 20:14:18 [INFO] train episode 28060: reward = -73.32, steps = 29 20:14:20 [INFO] train episode 28061: reward = -168.53, steps = 24 20:14:22 [INFO] train episode 28062: reward = -70.99, steps = 31 20:14:24 [INFO] train episode 28063: reward = -88.62, steps = 20 20:14:26 [INFO] train episode 28064: reward = -71.79, steps = 20 20:14:29 [INFO] train episode 28065: reward = -57.20, steps = 35 20:14:31 [INFO] train episode 28066: reward = -81.91, steps = 19 20:14:34 [INFO] train episode 28067: reward = -59.09, steps = 27 20:14:35 [INFO] train episode 28068: reward = -63.35, steps = 19 20:14:37 [INFO] train episode 28069: reward = -45.14, steps = 21 20:14:39 [INFO] train episode 28070: reward = -92.41, steps = 23 20:14:41 [INFO] train episode 28071: reward = -155.91, steps = 22 20:14:44 [INFO] train episode 28072: reward = -73.81, steps = 34 20:14:48 [INFO] train episode 28073: reward = -69.39, steps = 41 20:14:52 [INFO] train episode 28074: reward = -83.83, steps = 39 20:14:54 [INFO] train episode 28075: reward = -106.06, steps = 26 20:14:56 [INFO] train episode 28076: reward = -55.93, steps = 21 20:14:59 [INFO] train episode 28077: reward = -41.45, steps = 34 20:15:02 [INFO] train episode 28078: reward = -91.92, steps = 29 20:15:04 [INFO] train episode 28079: reward = -74.09, steps = 28 20:15:07 [INFO] train episode 28080: reward = -66.71, steps = 24 20:15:09 [INFO] train episode 28081: reward = -102.55, steps = 27 20:15:12 [INFO] train episode 28082: reward = -69.81, steps = 26 20:15:14 [INFO] train episode 28083: reward = -88.95, steps = 24 20:15:17 [INFO] train episode 28084: reward = -66.67, steps = 35 20:15:19 [INFO] train episode 28085: reward = -66.18, steps = 21 20:15:21 [INFO] train episode 28086: reward = -67.99, steps = 19 20:15:25 [INFO] train episode 28087: reward = -118.87, steps = 49 20:15:27 [INFO] train episode 28088: reward = -57.26, steps = 22 20:15:31 [INFO] train episode 28089: reward = -96.30, steps = 43 20:15:33 [INFO] train episode 28090: reward = -39.99, steps = 21 20:15:36 [INFO] train episode 28091: reward = -74.71, steps = 27 20:15:40 [INFO] train episode 28092: reward = -102.60, steps = 43 20:15:42 [INFO] train episode 28093: reward = -100.29, steps = 28 20:15:45 [INFO] train episode 28094: reward = -53.87, steps = 32 20:15:47 [INFO] train episode 28095: reward = -61.87, steps = 20 20:15:49 [INFO] train episode 28096: reward = -70.05, steps = 19 20:15:51 [INFO] train episode 28097: reward = -75.70, steps = 20 20:15:54 [INFO] train episode 28098: reward = -75.54, steps = 32 20:15:56 [INFO] train episode 28099: reward = -56.61, steps = 23 20:16:00 [INFO] train episode 28100: reward = -82.87, steps = 41 20:16:03 [INFO] train episode 28101: reward = -83.18, steps = 43 20:16:05 [INFO] train episode 28102: reward = -50.08, steps = 19 20:16:08 [INFO] train episode 28103: reward = -60.15, steps = 32 20:16:10 [INFO] train episode 28104: reward = -68.84, steps = 19 20:16:12 [INFO] train episode 28105: reward = -75.51, steps = 22 20:16:14 [INFO] train episode 28106: reward = -66.41, steps = 24 20:16:18 [INFO] train episode 28107: reward = -49.71, steps = 36 20:16:19 [INFO] train episode 28108: reward = -64.79, steps = 20 20:16:21 [INFO] train episode 28109: reward = -69.18, steps = 22 20:16:24 [INFO] train episode 28110: reward = -121.63, steps = 32 20:16:26 [INFO] train episode 28111: reward = -85.58, steps = 19 20:16:28 [INFO] train episode 28112: reward = -66.80, steps = 26 20:16:30 [INFO] train episode 28113: reward = -65.95, steps = 22 20:16:33 [INFO] train episode 28114: reward = -106.77, steps = 24 20:16:35 [INFO] train episode 28115: reward = -75.63, steps = 26 20:16:37 [INFO] train episode 28116: reward = -82.57, steps = 24 20:16:40 [INFO] train episode 28117: reward = -113.89, steps = 33 20:16:42 [INFO] train episode 28118: reward = -78.71, steps = 27 20:16:46 [INFO] train episode 28119: reward = -104.39, steps = 27 20:16:49 [INFO] train episode 28120: reward = -64.92, steps = 33 20:16:51 [INFO] train episode 28121: reward = -75.72, steps = 28 20:16:53 [INFO] train episode 28122: reward = -64.56, steps = 21 20:16:55 [INFO] train episode 28123: reward = -57.96, steps = 20 20:16:59 [INFO] train episode 28124: reward = -75.77, steps = 39 20:17:01 [INFO] train episode 28125: reward = -92.16, steps = 32 20:17:05 [INFO] train episode 28126: reward = -96.27, steps = 36 20:17:07 [INFO] train episode 28127: reward = -95.44, steps = 20 20:17:09 [INFO] train episode 28128: reward = -75.88, steps = 32 20:17:11 [INFO] train episode 28129: reward = -83.37, steps = 20 20:17:14 [INFO] train episode 28130: reward = -125.71, steps = 37 20:17:16 [INFO] train episode 28131: reward = -56.96, steps = 21 20:17:18 [INFO] train episode 28132: reward = -86.88, steps = 21 20:17:21 [INFO] train episode 28133: reward = -72.71, steps = 30 20:17:25 [INFO] train episode 28134: reward = -67.91, steps = 42 20:17:27 [INFO] train episode 28135: reward = -62.25, steps = 25 20:17:29 [INFO] train episode 28136: reward = -74.52, steps = 20 20:17:32 [INFO] train episode 28137: reward = -92.17, steps = 34 20:17:35 [INFO] train episode 28138: reward = -95.42, steps = 39 20:17:39 [INFO] train episode 28139: reward = -69.66, steps = 35 20:17:41 [INFO] train episode 28140: reward = -52.38, steps = 25 20:17:43 [INFO] train episode 28141: reward = -87.54, steps = 23 20:17:46 [INFO] train episode 28142: reward = -92.37, steps = 31 20:17:48 [INFO] train episode 28143: reward = -72.87, steps = 22 20:17:50 [INFO] train episode 28144: reward = -51.54, steps = 25 20:17:52 [INFO] train episode 28145: reward = -45.27, steps = 21 20:17:55 [INFO] train episode 28146: reward = -45.62, steps = 40 20:17:58 [INFO] train episode 28147: reward = -54.19, steps = 26 20:18:01 [INFO] train episode 28148: reward = -83.49, steps = 38 20:18:03 [INFO] train episode 28149: reward = -63.88, steps = 18 20:18:06 [INFO] train episode 28150: reward = -107.98, steps = 45 20:18:10 [INFO] train episode 28151: reward = -107.78, steps = 39 20:18:13 [INFO] train episode 28152: reward = -35.41, steps = 28 20:18:15 [INFO] train episode 28153: reward = -69.06, steps = 26 20:18:17 [INFO] train episode 28154: reward = -110.33, steps = 20 20:18:18 [INFO] train episode 28155: reward = -81.73, steps = 19 20:18:21 [INFO] train episode 28156: reward = -74.92, steps = 29 20:18:23 [INFO] train episode 28157: reward = -83.10, steps = 20 20:18:26 [INFO] train episode 28158: reward = -91.40, steps = 32 20:18:27 [INFO] train episode 28159: reward = -89.98, steps = 19 20:18:30 [INFO] train episode 28160: reward = -87.73, steps = 31 20:18:32 [INFO] train episode 28161: reward = -58.99, steps = 20 20:18:34 [INFO] train episode 28162: reward = -79.17, steps = 25 20:18:37 [INFO] train episode 28163: reward = -65.83, steps = 37 20:18:39 [INFO] train episode 28164: reward = -87.94, steps = 19 20:18:42 [INFO] train episode 28165: reward = -60.23, steps = 33 20:18:45 [INFO] train episode 28166: reward = -52.37, steps = 29 20:18:47 [INFO] train episode 28167: reward = -58.21, steps = 19 20:18:49 [INFO] train episode 28168: reward = -74.11, steps = 25 20:18:52 [INFO] train episode 28169: reward = -74.59, steps = 30 20:18:54 [INFO] train episode 28170: reward = -47.45, steps = 28 20:18:56 [INFO] train episode 28171: reward = -85.52, steps = 24 20:18:59 [INFO] train episode 28172: reward = -69.27, steps = 19 20:19:01 [INFO] train episode 28173: reward = -73.92, steps = 26 20:19:03 [INFO] train episode 28174: reward = -65.51, steps = 25 20:19:05 [INFO] train episode 28175: reward = -50.13, steps = 21 20:19:07 [INFO] train episode 28176: reward = -53.94, steps = 19 20:19:08 [INFO] train episode 28177: reward = -81.45, steps = 18 20:19:10 [INFO] train episode 28178: reward = -42.40, steps = 22 20:19:13 [INFO] train episode 28179: reward = -72.80, steps = 31 20:19:17 [INFO] train episode 28180: reward = -70.64, steps = 35 20:19:18 [INFO] train episode 28181: reward = -90.82, steps = 20 20:19:22 [INFO] train episode 28182: reward = -109.73, steps = 49 20:19:25 [INFO] train episode 28183: reward = -74.47, steps = 26 20:19:27 [INFO] train episode 28184: reward = -48.95, steps = 31 20:19:31 [INFO] train episode 28185: reward = -116.53, steps = 31 20:19:32 [INFO] train episode 28186: reward = -96.53, steps = 19 20:19:34 [INFO] train episode 28187: reward = -139.72, steps = 20 20:19:36 [INFO] train episode 28188: reward = -49.85, steps = 24 20:19:38 [INFO] train episode 28189: reward = -96.86, steps = 18 20:19:42 [INFO] train episode 28190: reward = -95.26, steps = 35 20:19:45 [INFO] train episode 28191: reward = -139.84, steps = 32 20:19:46 [INFO] train episode 28192: reward = -110.21, steps = 20 20:19:50 [INFO] train episode 28193: reward = -66.19, steps = 29 20:19:53 [INFO] train episode 28194: reward = -120.67, steps = 37 20:19:57 [INFO] train episode 28195: reward = -103.60, steps = 45 20:20:01 [INFO] train episode 28196: reward = -100.49, steps = 46 20:20:04 [INFO] train episode 28197: reward = -66.78, steps = 28 20:20:06 [INFO] train episode 28198: reward = -76.64, steps = 26 20:20:09 [INFO] train episode 28199: reward = -82.09, steps = 28 20:20:12 [INFO] train episode 28200: reward = -66.62, steps = 35 20:20:14 [INFO] train episode 28201: reward = -58.18, steps = 23 20:20:17 [INFO] train episode 28202: reward = -87.52, steps = 34 20:20:20 [INFO] train episode 28203: reward = -59.94, steps = 27 20:20:23 [INFO] train episode 28204: reward = -77.09, steps = 34 20:20:26 [INFO] train episode 28205: reward = -109.41, steps = 31 20:20:28 [INFO] train episode 28206: reward = -88.52, steps = 27 20:20:30 [INFO] train episode 28207: reward = -85.79, steps = 27 20:20:33 [INFO] train episode 28208: reward = -122.32, steps = 29 20:20:36 [INFO] train episode 28209: reward = -126.83, steps = 33 20:20:40 [INFO] train episode 28210: reward = -146.43, steps = 36 20:20:43 [INFO] train episode 28211: reward = -84.28, steps = 38 20:20:46 [INFO] train episode 28212: reward = -104.88, steps = 27 20:20:49 [INFO] train episode 28213: reward = -51.36, steps = 38 20:20:51 [INFO] train episode 28214: reward = -54.15, steps = 26 20:20:54 [INFO] train episode 28215: reward = -71.63, steps = 27 20:20:58 [INFO] train episode 28216: reward = -84.02, steps = 27 20:21:00 [INFO] train episode 28217: reward = -98.54, steps = 24 20:21:03 [INFO] train episode 28218: reward = -65.59, steps = 31 20:21:06 [INFO] train episode 28219: reward = -53.59, steps = 32 20:21:09 [INFO] train episode 28220: reward = -87.91, steps = 34 20:21:14 [INFO] train episode 28221: reward = -82.73, steps = 41 20:21:17 [INFO] train episode 28222: reward = -77.37, steps = 35 20:21:20 [INFO] train episode 28223: reward = -143.42, steps = 30 20:21:23 [INFO] train episode 28224: reward = -98.77, steps = 40 20:21:26 [INFO] train episode 28225: reward = -75.92, steps = 32 20:21:28 [INFO] train episode 28226: reward = -75.80, steps = 23 20:21:31 [INFO] train episode 28227: reward = -91.11, steps = 29 20:21:34 [INFO] train episode 28228: reward = -89.89, steps = 38 20:21:36 [INFO] train episode 28229: reward = -40.75, steps = 24 20:21:38 [INFO] train episode 28230: reward = -86.71, steps = 22 20:21:40 [INFO] train episode 28231: reward = -73.40, steps = 23 20:21:42 [INFO] train episode 28232: reward = -95.33, steps = 21 20:21:44 [INFO] train episode 28233: reward = -69.55, steps = 28 20:21:47 [INFO] train episode 28234: reward = -83.13, steps = 23 20:21:50 [INFO] train episode 28235: reward = -75.34, steps = 31 20:21:51 [INFO] train episode 28236: reward = -120.02, steps = 20 20:21:53 [INFO] train episode 28237: reward = -93.50, steps = 22 20:21:57 [INFO] train episode 28238: reward = -76.60, steps = 41 20:21:59 [INFO] train episode 28239: reward = -63.97, steps = 27 20:22:02 [INFO] train episode 28240: reward = -90.97, steps = 27 20:22:06 [INFO] train episode 28241: reward = -79.61, steps = 50 20:22:08 [INFO] train episode 28242: reward = -76.17, steps = 24 20:22:11 [INFO] train episode 28243: reward = -91.45, steps = 25 20:22:13 [INFO] train episode 28244: reward = -65.75, steps = 23 20:22:15 [INFO] train episode 28245: reward = -93.50, steps = 27 20:22:17 [INFO] train episode 28246: reward = -62.94, steps = 24 20:22:20 [INFO] train episode 28247: reward = -107.33, steps = 33 20:22:22 [INFO] train episode 28248: reward = -61.05, steps = 20 20:22:26 [INFO] train episode 28249: reward = -113.95, steps = 49 20:22:29 [INFO] train episode 28250: reward = -73.98, steps = 26 20:22:31 [INFO] train episode 28251: reward = -78.27, steps = 19 20:22:35 [INFO] train episode 28252: reward = -66.08, steps = 45 20:22:37 [INFO] train episode 28253: reward = -82.10, steps = 18 20:22:38 [INFO] train episode 28254: reward = -99.15, steps = 18 20:22:40 [INFO] train episode 28255: reward = -75.75, steps = 21 20:22:44 [INFO] train episode 28256: reward = -128.35, steps = 38 20:22:46 [INFO] train episode 28257: reward = -57.31, steps = 20 20:22:48 [INFO] train episode 28258: reward = -94.37, steps = 23 20:22:50 [INFO] train episode 28259: reward = -92.30, steps = 26 20:22:53 [INFO] train episode 28260: reward = -128.07, steps = 23 20:22:57 [INFO] train episode 28261: reward = -72.09, steps = 46 20:23:00 [INFO] train episode 28262: reward = -85.21, steps = 31 20:23:02 [INFO] train episode 28263: reward = -83.08, steps = 23 20:23:04 [INFO] train episode 28264: reward = -55.04, steps = 22 20:23:06 [INFO] train episode 28265: reward = -97.65, steps = 22 20:23:08 [INFO] train episode 28266: reward = -93.63, steps = 24 20:23:10 [INFO] train episode 28267: reward = -71.06, steps = 23 20:23:13 [INFO] train episode 28268: reward = -91.24, steps = 27 20:23:15 [INFO] train episode 28269: reward = -92.47, steps = 21 20:23:17 [INFO] train episode 28270: reward = -61.23, steps = 23 20:23:20 [INFO] train episode 28271: reward = -59.05, steps = 37 20:23:22 [INFO] train episode 28272: reward = -78.20, steps = 24 20:23:26 [INFO] train episode 28273: reward = -97.14, steps = 45 20:23:28 [INFO] train episode 28274: reward = -170.18, steps = 21 20:23:32 [INFO] train episode 28275: reward = -72.39, steps = 37 20:23:33 [INFO] train episode 28276: reward = -101.68, steps = 20 20:23:36 [INFO] train episode 28277: reward = -103.80, steps = 32 20:23:38 [INFO] train episode 28278: reward = -109.92, steps = 19 20:23:40 [INFO] train episode 28279: reward = -90.29, steps = 25 20:23:43 [INFO] train episode 28280: reward = -53.94, steps = 21 20:23:45 [INFO] train episode 28281: reward = -71.39, steps = 24 20:23:47 [INFO] train episode 28282: reward = -69.58, steps = 31 20:23:49 [INFO] train episode 28283: reward = -77.15, steps = 18 20:23:52 [INFO] train episode 28284: reward = -93.52, steps = 28 20:23:56 [INFO] train episode 28285: reward = -76.31, steps = 46 20:23:58 [INFO] train episode 28286: reward = -46.36, steps = 20 20:24:01 [INFO] train episode 28287: reward = -153.44, steps = 29 20:24:02 [INFO] train episode 28288: reward = -143.10, steps = 22 20:24:05 [INFO] train episode 28289: reward = -59.67, steps = 34 20:24:08 [INFO] train episode 28290: reward = -97.89, steps = 34 20:24:13 [INFO] train episode 28291: reward = -151.41, steps = 50 20:24:15 [INFO] train episode 28292: reward = -42.15, steps = 27 20:24:19 [INFO] train episode 28293: reward = -65.41, steps = 35 20:24:20 [INFO] train episode 28294: reward = -89.20, steps = 18 20:24:24 [INFO] train episode 28295: reward = -73.17, steps = 37 20:24:26 [INFO] train episode 28296: reward = -160.55, steps = 30 20:24:28 [INFO] train episode 28297: reward = -63.21, steps = 21 20:24:31 [INFO] train episode 28298: reward = -60.49, steps = 32 20:24:33 [INFO] train episode 28299: reward = -103.89, steps = 20 20:24:36 [INFO] train episode 28300: reward = -82.25, steps = 30 20:24:39 [INFO] train episode 28301: reward = -63.46, steps = 28 20:24:41 [INFO] train episode 28302: reward = -82.65, steps = 32 20:24:43 [INFO] train episode 28303: reward = -71.17, steps = 19 20:24:46 [INFO] train episode 28304: reward = -51.07, steps = 25 20:24:48 [INFO] train episode 28305: reward = -79.12, steps = 23 20:24:50 [INFO] train episode 28306: reward = -53.21, steps = 25 20:24:53 [INFO] train episode 28307: reward = -56.86, steps = 36 20:24:57 [INFO] train episode 28308: reward = -61.41, steps = 47 20:24:59 [INFO] train episode 28309: reward = -83.64, steps = 24 20:25:02 [INFO] train episode 28310: reward = -139.51, steps = 30 20:25:05 [INFO] train episode 28311: reward = -57.24, steps = 33 20:25:07 [INFO] train episode 28312: reward = -67.40, steps = 22 20:25:11 [INFO] train episode 28313: reward = -85.38, steps = 39 20:25:13 [INFO] train episode 28314: reward = -61.92, steps = 23 20:25:16 [INFO] train episode 28315: reward = -100.80, steps = 34 20:25:18 [INFO] train episode 28316: reward = -98.34, steps = 29 20:25:21 [INFO] train episode 28317: reward = -69.69, steps = 27 20:25:23 [INFO] train episode 28318: reward = -50.49, steps = 25 20:25:25 [INFO] train episode 28319: reward = -62.26, steps = 20 20:25:27 [INFO] train episode 28320: reward = -50.99, steps = 20 20:25:30 [INFO] train episode 28321: reward = -97.46, steps = 36 20:25:33 [INFO] train episode 28322: reward = -71.56, steps = 38 20:25:36 [INFO] train episode 28323: reward = -70.16, steps = 25 20:25:38 [INFO] train episode 28324: reward = -69.21, steps = 21 20:25:39 [INFO] train episode 28325: reward = -85.72, steps = 19 20:25:43 [INFO] train episode 28326: reward = -52.52, steps = 32 20:25:46 [INFO] train episode 28327: reward = -40.87, steps = 29 20:25:48 [INFO] train episode 28328: reward = -88.91, steps = 23 20:25:50 [INFO] train episode 28329: reward = -95.79, steps = 24 20:25:52 [INFO] train episode 28330: reward = -51.29, steps = 22 20:25:54 [INFO] train episode 28331: reward = -100.42, steps = 21 20:25:56 [INFO] train episode 28332: reward = -57.21, steps = 21 20:25:58 [INFO] train episode 28333: reward = -65.09, steps = 22 20:26:01 [INFO] train episode 28334: reward = -82.65, steps = 36 20:26:02 [INFO] train episode 28335: reward = -89.69, steps = 16 20:26:05 [INFO] train episode 28336: reward = -72.83, steps = 30 20:26:07 [INFO] train episode 28337: reward = -49.66, steps = 24 20:26:09 [INFO] train episode 28338: reward = -61.07, steps = 22 20:26:11 [INFO] train episode 28339: reward = -54.17, steps = 21 20:26:14 [INFO] train episode 28340: reward = -109.12, steps = 26 20:26:15 [INFO] train episode 28341: reward = -104.77, steps = 20 20:26:18 [INFO] train episode 28342: reward = -83.38, steps = 31 20:26:21 [INFO] train episode 28343: reward = -66.66, steps = 35 20:26:23 [INFO] train episode 28344: reward = -67.43, steps = 24 20:26:26 [INFO] train episode 28345: reward = -68.55, steps = 31 20:26:29 [INFO] train episode 28346: reward = -111.46, steps = 27 20:26:32 [INFO] train episode 28347: reward = -70.06, steps = 31 20:26:35 [INFO] train episode 28348: reward = -97.65, steps = 39 20:26:38 [INFO] train episode 28349: reward = -51.50, steps = 34 20:26:41 [INFO] train episode 28350: reward = -147.73, steps = 32 20:26:43 [INFO] train episode 28351: reward = -61.74, steps = 20 20:26:46 [INFO] train episode 28352: reward = -113.35, steps = 40 20:26:49 [INFO] train episode 28353: reward = -126.37, steps = 29 20:26:51 [INFO] train episode 28354: reward = -65.60, steps = 22 20:26:54 [INFO] train episode 28355: reward = -60.44, steps = 33 20:26:56 [INFO] train episode 28356: reward = -85.38, steps = 30 20:26:58 [INFO] train episode 28357: reward = -103.90, steps = 19 20:27:00 [INFO] train episode 28358: reward = -62.68, steps = 19 20:27:03 [INFO] train episode 28359: reward = -90.73, steps = 30 20:27:07 [INFO] train episode 28360: reward = -63.88, steps = 48 20:27:10 [INFO] train episode 28361: reward = -64.42, steps = 35 20:27:12 [INFO] train episode 28362: reward = -77.42, steps = 20 20:27:15 [INFO] train episode 28363: reward = -66.62, steps = 28 20:27:17 [INFO] train episode 28364: reward = -54.33, steps = 26 20:27:20 [INFO] train episode 28365: reward = -82.87, steps = 37 20:27:22 [INFO] train episode 28366: reward = -74.81, steps = 20 20:27:25 [INFO] train episode 28367: reward = -83.44, steps = 37 20:27:30 [INFO] train episode 28368: reward = -115.04, steps = 49 20:27:33 [INFO] train episode 28369: reward = -84.99, steps = 35 20:27:36 [INFO] train episode 28370: reward = -81.85, steps = 32 20:27:39 [INFO] train episode 28371: reward = -104.48, steps = 32 20:27:43 [INFO] train episode 28372: reward = -116.63, steps = 51 20:27:46 [INFO] train episode 28373: reward = -125.19, steps = 32 20:27:48 [INFO] train episode 28374: reward = -109.27, steps = 26 20:27:52 [INFO] train episode 28375: reward = -99.68, steps = 43 20:27:54 [INFO] train episode 28376: reward = -71.11, steps = 27 20:27:58 [INFO] train episode 28377: reward = -141.60, steps = 37 20:28:00 [INFO] train episode 28378: reward = -80.43, steps = 27 20:28:03 [INFO] train episode 28379: reward = -76.74, steps = 29 20:28:08 [INFO] train episode 28380: reward = -139.65, steps = 55 20:28:10 [INFO] train episode 28381: reward = -71.04, steps = 26 20:28:13 [INFO] train episode 28382: reward = -62.67, steps = 36 20:28:15 [INFO] train episode 28383: reward = -106.42, steps = 24 20:28:17 [INFO] train episode 28384: reward = -115.52, steps = 24 20:28:22 [INFO] train episode 28385: reward = -183.80, steps = 52 20:28:24 [INFO] train episode 28386: reward = -75.81, steps = 22 20:28:27 [INFO] train episode 28387: reward = -56.41, steps = 26 20:28:29 [INFO] train episode 28388: reward = -74.64, steps = 28 20:28:32 [INFO] train episode 28389: reward = -91.15, steps = 32 20:28:34 [INFO] train episode 28390: reward = -117.84, steps = 26 20:28:39 [INFO] train episode 28391: reward = -93.66, steps = 43 20:28:41 [INFO] train episode 28392: reward = -81.25, steps = 23 20:28:44 [INFO] train episode 28393: reward = -97.53, steps = 38 20:28:46 [INFO] train episode 28394: reward = -60.22, steps = 21 20:28:48 [INFO] train episode 28395: reward = -63.50, steps = 19 20:28:50 [INFO] train episode 28396: reward = -94.27, steps = 23 20:28:52 [INFO] train episode 28397: reward = -92.12, steps = 22 20:28:55 [INFO] train episode 28398: reward = -91.51, steps = 29 20:28:57 [INFO] train episode 28399: reward = -87.21, steps = 20 20:28:59 [INFO] train episode 28400: reward = -64.00, steps = 25 20:29:01 [INFO] train episode 28401: reward = -61.03, steps = 29 20:29:04 [INFO] train episode 28402: reward = -95.58, steps = 26 20:29:08 [INFO] train episode 28403: reward = -83.93, steps = 40 20:29:10 [INFO] train episode 28404: reward = -68.54, steps = 18 20:29:13 [INFO] train episode 28405: reward = -83.49, steps = 37 20:29:16 [INFO] train episode 28406: reward = -68.83, steps = 26 20:29:17 [INFO] train episode 28407: reward = -81.33, steps = 20 20:29:20 [INFO] train episode 28408: reward = -59.71, steps = 23 20:29:22 [INFO] train episode 28409: reward = -116.03, steps = 29 20:29:25 [INFO] train episode 28410: reward = -59.41, steps = 36 20:29:28 [INFO] train episode 28411: reward = -84.70, steps = 26 20:29:30 [INFO] train episode 28412: reward = -95.59, steps = 27 20:29:34 [INFO] train episode 28413: reward = -62.84, steps = 36 20:29:37 [INFO] train episode 28414: reward = -65.19, steps = 32 20:29:39 [INFO] train episode 28415: reward = -108.82, steps = 32 20:29:41 [INFO] train episode 28416: reward = -79.38, steps = 22 20:29:44 [INFO] train episode 28417: reward = -49.15, steps = 24 20:29:47 [INFO] train episode 28418: reward = -91.82, steps = 30 20:29:49 [INFO] train episode 28419: reward = -73.61, steps = 32 20:29:52 [INFO] train episode 28420: reward = -73.33, steps = 28 20:29:54 [INFO] train episode 28421: reward = -102.23, steps = 20 20:29:56 [INFO] train episode 28422: reward = -86.72, steps = 25 20:29:58 [INFO] train episode 28423: reward = -75.38, steps = 21 20:30:00 [INFO] train episode 28424: reward = -71.84, steps = 23 20:30:02 [INFO] train episode 28425: reward = -121.51, steps = 23 20:30:06 [INFO] train episode 28426: reward = -77.75, steps = 39 20:30:10 [INFO] train episode 28427: reward = -110.43, steps = 48 20:30:13 [INFO] train episode 28428: reward = -52.88, steps = 35 20:30:16 [INFO] train episode 28429: reward = -82.08, steps = 38 20:30:18 [INFO] train episode 28430: reward = -61.24, steps = 21 20:30:20 [INFO] train episode 28431: reward = -59.18, steps = 24 20:30:22 [INFO] train episode 28432: reward = -78.47, steps = 22 20:30:24 [INFO] train episode 28433: reward = -62.23, steps = 20 20:30:26 [INFO] train episode 28434: reward = -53.90, steps = 21 20:30:28 [INFO] train episode 28435: reward = -64.57, steps = 22 20:30:31 [INFO] train episode 28436: reward = -114.65, steps = 33 20:30:33 [INFO] train episode 28437: reward = -86.90, steps = 23 20:30:36 [INFO] train episode 28438: reward = -129.75, steps = 35 20:30:38 [INFO] train episode 28439: reward = -50.53, steps = 18 20:30:40 [INFO] train episode 28440: reward = -71.85, steps = 23 20:30:42 [INFO] train episode 28441: reward = -61.49, steps = 20 20:30:45 [INFO] train episode 28442: reward = -70.35, steps = 32 20:30:47 [INFO] train episode 28443: reward = -53.53, steps = 26 20:30:49 [INFO] train episode 28444: reward = -45.27, steps = 21 20:30:52 [INFO] train episode 28445: reward = -93.33, steps = 30 20:30:55 [INFO] train episode 28446: reward = -85.90, steps = 28 20:30:57 [INFO] train episode 28447: reward = -57.31, steps = 29 20:30:59 [INFO] train episode 28448: reward = -78.39, steps = 21 20:31:01 [INFO] train episode 28449: reward = -55.71, steps = 19 20:31:04 [INFO] train episode 28450: reward = -54.56, steps = 32 20:31:06 [INFO] train episode 28451: reward = -69.29, steps = 20 20:31:09 [INFO] train episode 28452: reward = -45.95, steps = 32 20:31:11 [INFO] train episode 28453: reward = -71.35, steps = 25 20:31:15 [INFO] train episode 28454: reward = -116.41, steps = 44 20:31:18 [INFO] train episode 28455: reward = -112.22, steps = 33 20:31:21 [INFO] train episode 28456: reward = -89.81, steps = 37 20:31:25 [INFO] train episode 28457: reward = -137.03, steps = 45 20:31:27 [INFO] train episode 28458: reward = -56.10, steps = 21 20:31:31 [INFO] train episode 28459: reward = -85.39, steps = 38 20:31:32 [INFO] train episode 28460: reward = -90.29, steps = 19 20:31:36 [INFO] train episode 28461: reward = -88.40, steps = 31 20:31:40 [INFO] train episode 28462: reward = -63.30, steps = 44 20:31:42 [INFO] train episode 28463: reward = -53.90, steps = 26 20:31:46 [INFO] train episode 28464: reward = -63.38, steps = 38 20:31:47 [INFO] train episode 28465: reward = -59.58, steps = 20 20:31:50 [INFO] train episode 28466: reward = -77.35, steps = 30 20:31:52 [INFO] train episode 28467: reward = -65.38, steps = 19 20:31:54 [INFO] train episode 28468: reward = -68.15, steps = 24 20:31:57 [INFO] train episode 28469: reward = -77.64, steps = 34 20:31:59 [INFO] train episode 28470: reward = -105.92, steps = 25 20:32:02 [INFO] train episode 28471: reward = -36.19, steps = 37 20:32:04 [INFO] train episode 28472: reward = -65.81, steps = 20 20:32:06 [INFO] train episode 28473: reward = -93.20, steps = 26 20:32:08 [INFO] train episode 28474: reward = -72.78, steps = 20 20:32:12 [INFO] train episode 28475: reward = -103.17, steps = 41 20:32:14 [INFO] train episode 28476: reward = -65.24, steps = 21 20:32:16 [INFO] train episode 28477: reward = -86.08, steps = 23 20:32:18 [INFO] train episode 28478: reward = -63.08, steps = 22 20:32:22 [INFO] train episode 28479: reward = -95.45, steps = 39 20:32:24 [INFO] train episode 28480: reward = -66.19, steps = 30 20:32:27 [INFO] train episode 28481: reward = -72.73, steps = 27 20:32:31 [INFO] train episode 28482: reward = -67.77, steps = 38 20:32:33 [INFO] train episode 28483: reward = -85.42, steps = 30 20:32:35 [INFO] train episode 28484: reward = -122.73, steps = 26 20:32:40 [INFO] train episode 28485: reward = -116.26, steps = 46 20:32:42 [INFO] train episode 28486: reward = -81.60, steps = 23 20:32:44 [INFO] train episode 28487: reward = -84.24, steps = 26 20:32:47 [INFO] train episode 28488: reward = -121.22, steps = 29 20:32:49 [INFO] train episode 28489: reward = -88.89, steps = 24 20:32:51 [INFO] train episode 28490: reward = -69.90, steps = 24 20:32:53 [INFO] train episode 28491: reward = -49.40, steps = 20 20:32:56 [INFO] train episode 28492: reward = -71.61, steps = 32 20:32:59 [INFO] train episode 28493: reward = -109.85, steps = 36 20:33:02 [INFO] train episode 28494: reward = -122.34, steps = 23 20:33:06 [INFO] train episode 28495: reward = -57.92, steps = 49 20:33:09 [INFO] train episode 28496: reward = -76.62, steps = 38 20:33:12 [INFO] train episode 28497: reward = -137.16, steps = 35 20:33:14 [INFO] train episode 28498: reward = -72.93, steps = 23 20:33:17 [INFO] train episode 28499: reward = -83.23, steps = 20 20:33:19 [INFO] train episode 28500: reward = -44.37, steps = 28 20:33:21 [INFO] train episode 28501: reward = -65.56, steps = 24 20:33:24 [INFO] train episode 28502: reward = -77.22, steps = 32 20:33:26 [INFO] train episode 28503: reward = -92.50, steps = 20 20:33:29 [INFO] train episode 28504: reward = -106.58, steps = 29 20:33:32 [INFO] train episode 28505: reward = -68.72, steps = 40 20:33:35 [INFO] train episode 28506: reward = -91.37, steps = 26 20:33:37 [INFO] train episode 28507: reward = -73.32, steps = 25 20:33:40 [INFO] train episode 28508: reward = -31.87, steps = 31 20:33:42 [INFO] train episode 28509: reward = -69.55, steps = 31 20:33:44 [INFO] train episode 28510: reward = -111.80, steps = 19 20:33:46 [INFO] train episode 28511: reward = -60.24, steps = 26 20:33:50 [INFO] train episode 28512: reward = -92.72, steps = 40 20:33:54 [INFO] train episode 28513: reward = -87.57, steps = 34 20:33:56 [INFO] train episode 28514: reward = -62.77, steps = 24 20:33:59 [INFO] train episode 28515: reward = -110.38, steps = 37 20:34:01 [INFO] train episode 28516: reward = -72.46, steps = 22 20:34:04 [INFO] train episode 28517: reward = -123.86, steps = 28 20:34:06 [INFO] train episode 28518: reward = -68.30, steps = 28 20:34:08 [INFO] train episode 28519: reward = -62.92, steps = 21 20:34:11 [INFO] train episode 28520: reward = -77.66, steps = 28 20:34:14 [INFO] train episode 28521: reward = -76.71, steps = 35 20:34:16 [INFO] train episode 28522: reward = -145.90, steps = 22 20:34:18 [INFO] train episode 28523: reward = -46.79, steps = 24 20:34:20 [INFO] train episode 28524: reward = -76.26, steps = 27 20:34:22 [INFO] train episode 28525: reward = -99.27, steps = 17 20:34:24 [INFO] train episode 28526: reward = -72.80, steps = 19 20:34:26 [INFO] train episode 28527: reward = -46.24, steps = 21 20:34:29 [INFO] train episode 28528: reward = -105.61, steps = 43 20:34:33 [INFO] train episode 28529: reward = -43.51, steps = 28 20:34:35 [INFO] train episode 28530: reward = -72.72, steps = 32 20:34:37 [INFO] train episode 28531: reward = -62.18, steps = 20 20:34:39 [INFO] train episode 28532: reward = -34.29, steps = 21 20:34:41 [INFO] train episode 28533: reward = -66.23, steps = 21 20:34:43 [INFO] train episode 28534: reward = -68.42, steps = 20 20:34:45 [INFO] train episode 28535: reward = -67.51, steps = 27 20:34:47 [INFO] train episode 28536: reward = -58.43, steps = 21 20:34:50 [INFO] train episode 28537: reward = -103.65, steps = 28 20:34:52 [INFO] train episode 28538: reward = -72.21, steps = 24 20:34:54 [INFO] train episode 28539: reward = -91.40, steps = 20 20:34:56 [INFO] train episode 28540: reward = -153.38, steps = 20 20:34:59 [INFO] train episode 28541: reward = -94.44, steps = 26 20:35:02 [INFO] train episode 28542: reward = -84.31, steps = 33 20:35:04 [INFO] train episode 28543: reward = -86.62, steps = 30 20:35:06 [INFO] train episode 28544: reward = -100.39, steps = 21 20:35:08 [INFO] train episode 28545: reward = -92.81, steps = 22 20:35:11 [INFO] train episode 28546: reward = -87.70, steps = 30 20:35:14 [INFO] train episode 28547: reward = -41.92, steps = 35 20:35:17 [INFO] train episode 28548: reward = -64.99, steps = 32 20:35:19 [INFO] train episode 28549: reward = -105.47, steps = 22 20:35:22 [INFO] train episode 28550: reward = -44.34, steps = 33 20:35:24 [INFO] train episode 28551: reward = -99.28, steps = 19 20:35:26 [INFO] train episode 28552: reward = -91.14, steps = 18 20:35:28 [INFO] train episode 28553: reward = -72.13, steps = 25 20:35:30 [INFO] train episode 28554: reward = -47.36, steps = 25 20:35:33 [INFO] train episode 28555: reward = -61.35, steps = 35 20:35:36 [INFO] train episode 28556: reward = -93.46, steps = 32 20:35:38 [INFO] train episode 28557: reward = -95.20, steps = 20 20:35:40 [INFO] train episode 28558: reward = -74.32, steps = 23 20:35:43 [INFO] train episode 28559: reward = -71.28, steps = 33 20:35:46 [INFO] train episode 28560: reward = -66.08, steps = 30 20:35:50 [INFO] train episode 28561: reward = -118.08, steps = 42 20:35:52 [INFO] train episode 28562: reward = -67.09, steps = 22 20:35:55 [INFO] train episode 28563: reward = -33.26, steps = 39 20:35:58 [INFO] train episode 28564: reward = -111.12, steps = 31 20:36:00 [INFO] train episode 28565: reward = -68.16, steps = 22 20:36:02 [INFO] train episode 28566: reward = -60.24, steps = 21 20:36:04 [INFO] train episode 28567: reward = -107.66, steps = 24 20:36:07 [INFO] train episode 28568: reward = -87.60, steps = 31 20:36:09 [INFO] train episode 28569: reward = -80.67, steps = 28 20:36:11 [INFO] train episode 28570: reward = -71.92, steps = 26 20:36:14 [INFO] train episode 28571: reward = -106.44, steps = 24 20:36:17 [INFO] train episode 28572: reward = -94.57, steps = 35 20:36:20 [INFO] train episode 28573: reward = -128.71, steps = 34 20:36:22 [INFO] train episode 28574: reward = -68.86, steps = 20 20:36:25 [INFO] train episode 28575: reward = -99.98, steps = 32 20:36:27 [INFO] train episode 28576: reward = -72.45, steps = 24 20:36:30 [INFO] train episode 28577: reward = -44.79, steps = 34 20:36:32 [INFO] train episode 28578: reward = -88.17, steps = 23 20:36:34 [INFO] train episode 28579: reward = -58.83, steps = 23 20:36:37 [INFO] train episode 28580: reward = -63.43, steps = 31 20:36:40 [INFO] train episode 28581: reward = -53.61, steps = 36 20:36:44 [INFO] train episode 28582: reward = -178.18, steps = 45 20:36:47 [INFO] train episode 28583: reward = -39.44, steps = 39 20:36:49 [INFO] train episode 28584: reward = -56.35, steps = 21 20:36:52 [INFO] train episode 28585: reward = -87.71, steps = 26 20:36:54 [INFO] train episode 28586: reward = -86.00, steps = 19 20:36:57 [INFO] train episode 28587: reward = -133.85, steps = 36 20:36:59 [INFO] train episode 28588: reward = -37.99, steps = 20 20:37:02 [INFO] train episode 28589: reward = -55.10, steps = 40 20:37:04 [INFO] train episode 28590: reward = -68.09, steps = 19 20:37:07 [INFO] train episode 28591: reward = -72.73, steps = 27 20:37:10 [INFO] train episode 28592: reward = -130.76, steps = 44 20:37:14 [INFO] train episode 28593: reward = -82.70, steps = 40 20:37:16 [INFO] train episode 28594: reward = -73.10, steps = 21 20:37:17 [INFO] train episode 28595: reward = -41.93, steps = 19 20:37:20 [INFO] train episode 28596: reward = -84.11, steps = 25 20:37:24 [INFO] train episode 28597: reward = -224.37, steps = 48 20:37:26 [INFO] train episode 28598: reward = -53.83, steps = 23 20:37:29 [INFO] train episode 28599: reward = -72.94, steps = 25 20:37:32 [INFO] train episode 28600: reward = -67.66, steps = 29 20:37:34 [INFO] train episode 28601: reward = -142.57, steps = 24 20:37:36 [INFO] train episode 28602: reward = -62.80, steps = 20 20:37:38 [INFO] train episode 28603: reward = -59.71, steps = 22 20:37:41 [INFO] train episode 28604: reward = -64.51, steps = 34 20:37:44 [INFO] train episode 28605: reward = -50.10, steps = 31 20:37:47 [INFO] train episode 28606: reward = -67.57, steps = 32 20:37:52 [INFO] train episode 28607: reward = -87.55, steps = 51 20:37:56 [INFO] train episode 28608: reward = -89.60, steps = 45 20:37:58 [INFO] train episode 28609: reward = -82.16, steps = 23 20:38:00 [INFO] train episode 28610: reward = -98.48, steps = 22 20:38:02 [INFO] train episode 28611: reward = -62.58, steps = 22 20:38:06 [INFO] train episode 28612: reward = -59.51, steps = 44 20:38:09 [INFO] train episode 28613: reward = -90.28, steps = 36 20:38:11 [INFO] train episode 28614: reward = -69.50, steps = 25 20:38:14 [INFO] train episode 28615: reward = -54.57, steps = 21 20:38:16 [INFO] train episode 28616: reward = -104.50, steps = 20 20:38:18 [INFO] train episode 28617: reward = -92.05, steps = 22 20:38:19 [INFO] train episode 28618: reward = -52.61, steps = 20 20:38:22 [INFO] train episode 28619: reward = -77.05, steps = 32 20:38:25 [INFO] train episode 28620: reward = -80.33, steps = 29 20:38:27 [INFO] train episode 28621: reward = -57.81, steps = 24 20:38:29 [INFO] train episode 28622: reward = -95.81, steps = 21 20:38:31 [INFO] train episode 28623: reward = -110.32, steps = 27 20:38:33 [INFO] train episode 28624: reward = -58.51, steps = 20 20:38:35 [INFO] train episode 28625: reward = -66.69, steps = 23 20:38:38 [INFO] train episode 28626: reward = -98.24, steps = 32 20:38:40 [INFO] train episode 28627: reward = -85.77, steps = 19 20:38:42 [INFO] train episode 28628: reward = -71.33, steps = 22 20:38:44 [INFO] train episode 28629: reward = -68.24, steps = 22 20:38:47 [INFO] train episode 28630: reward = -89.53, steps = 33 20:38:51 [INFO] train episode 28631: reward = -238.80, steps = 40 20:38:53 [INFO] train episode 28632: reward = -72.32, steps = 21 20:38:55 [INFO] train episode 28633: reward = -61.35, steps = 23 20:38:57 [INFO] train episode 28634: reward = -131.36, steps = 25 20:38:59 [INFO] train episode 28635: reward = -68.26, steps = 24 20:39:02 [INFO] train episode 28636: reward = -106.71, steps = 26 20:39:05 [INFO] train episode 28637: reward = -55.07, steps = 32 20:39:07 [INFO] train episode 28638: reward = -123.53, steps = 23 20:39:09 [INFO] train episode 28639: reward = -90.16, steps = 21 20:39:11 [INFO] train episode 28640: reward = -63.10, steps = 23 20:39:13 [INFO] train episode 28641: reward = -71.14, steps = 31 20:39:15 [INFO] train episode 28642: reward = -55.14, steps = 20 20:39:17 [INFO] train episode 28643: reward = -70.32, steps = 17 20:39:19 [INFO] train episode 28644: reward = -83.75, steps = 24 20:39:21 [INFO] train episode 28645: reward = -70.10, steps = 24 20:39:23 [INFO] train episode 28646: reward = -73.42, steps = 20 20:39:26 [INFO] train episode 28647: reward = -73.49, steps = 35 20:39:29 [INFO] train episode 28648: reward = -82.83, steps = 30 20:39:31 [INFO] train episode 28649: reward = -83.49, steps = 19 20:39:33 [INFO] train episode 28650: reward = -46.21, steps = 28 20:39:35 [INFO] train episode 28651: reward = -52.54, steps = 21 20:39:37 [INFO] train episode 28652: reward = -104.88, steps = 22 20:39:39 [INFO] train episode 28653: reward = -80.61, steps = 22 20:39:41 [INFO] train episode 28654: reward = -66.19, steps = 27 20:39:44 [INFO] train episode 28655: reward = -131.42, steps = 25 20:39:45 [INFO] train episode 28656: reward = -92.26, steps = 19 20:39:48 [INFO] train episode 28657: reward = -44.37, steps = 32 20:39:50 [INFO] train episode 28658: reward = -72.96, steps = 18 20:39:52 [INFO] train episode 28659: reward = -77.60, steps = 21 20:39:55 [INFO] train episode 28660: reward = -67.65, steps = 31 20:39:57 [INFO] train episode 28661: reward = -77.70, steps = 22 20:40:00 [INFO] train episode 28662: reward = -81.86, steps = 36 20:40:01 [INFO] train episode 28663: reward = -76.43, steps = 19 20:40:03 [INFO] train episode 28664: reward = -47.27, steps = 19 20:40:06 [INFO] train episode 28665: reward = -99.76, steps = 32 20:40:08 [INFO] train episode 28666: reward = -72.19, steps = 19 20:40:10 [INFO] train episode 28667: reward = -91.75, steps = 19 20:40:12 [INFO] train episode 28668: reward = -83.82, steps = 25 20:40:14 [INFO] train episode 28669: reward = -62.93, steps = 26 20:40:17 [INFO] train episode 28670: reward = -85.98, steps = 33 20:40:19 [INFO] train episode 28671: reward = -84.26, steps = 21 20:40:21 [INFO] train episode 28672: reward = -77.34, steps = 22 20:40:25 [INFO] train episode 28673: reward = -116.93, steps = 40 20:40:28 [INFO] train episode 28674: reward = -104.61, steps = 28 20:40:31 [INFO] train episode 28675: reward = -74.12, steps = 32 20:40:34 [INFO] train episode 28676: reward = -63.07, steps = 38 20:40:36 [INFO] train episode 28677: reward = -57.07, steps = 21 20:40:39 [INFO] train episode 28678: reward = -76.21, steps = 23 20:40:40 [INFO] train episode 28679: reward = -139.00, steps = 19 20:40:43 [INFO] train episode 28680: reward = -66.32, steps = 27 20:40:45 [INFO] train episode 28681: reward = -101.05, steps = 22 20:40:47 [INFO] train episode 28682: reward = -83.02, steps = 19 20:40:48 [INFO] train episode 28683: reward = -55.14, steps = 21 20:40:50 [INFO] train episode 28684: reward = -92.27, steps = 19 20:40:52 [INFO] train episode 28685: reward = -61.10, steps = 25 20:40:54 [INFO] train episode 28686: reward = -73.86, steps = 21 20:40:56 [INFO] train episode 28687: reward = -65.77, steps = 23 20:40:58 [INFO] train episode 28688: reward = -34.10, steps = 21 20:41:02 [INFO] train episode 28689: reward = -74.24, steps = 31 20:41:03 [INFO] train episode 28690: reward = -64.09, steps = 18 20:41:07 [INFO] train episode 28691: reward = -73.98, steps = 39 20:41:09 [INFO] train episode 28692: reward = -64.09, steps = 22 20:41:10 [INFO] train episode 28693: reward = -87.78, steps = 19 20:41:13 [INFO] train episode 28694: reward = -89.01, steps = 27 20:41:16 [INFO] train episode 28695: reward = -109.72, steps = 29 20:41:19 [INFO] train episode 28696: reward = -125.77, steps = 36 20:41:21 [INFO] train episode 28697: reward = -70.05, steps = 22 20:41:23 [INFO] train episode 28698: reward = -112.55, steps = 30 20:41:25 [INFO] train episode 28699: reward = -52.85, steps = 18 20:41:27 [INFO] train episode 28700: reward = -58.21, steps = 22 20:41:29 [INFO] train episode 28701: reward = -79.58, steps = 27 20:41:31 [INFO] train episode 28702: reward = -44.38, steps = 22 20:41:35 [INFO] train episode 28703: reward = -102.81, steps = 36 20:41:37 [INFO] train episode 28704: reward = -92.52, steps = 26 20:41:40 [INFO] train episode 28705: reward = -82.32, steps = 27 20:41:42 [INFO] train episode 28706: reward = -74.64, steps = 27 20:41:44 [INFO] train episode 28707: reward = -60.40, steps = 19 20:41:46 [INFO] train episode 28708: reward = -156.75, steps = 25 20:41:48 [INFO] train episode 28709: reward = -84.85, steps = 19 20:41:51 [INFO] train episode 28710: reward = -79.15, steps = 28 20:41:54 [INFO] train episode 28711: reward = -94.94, steps = 35 20:41:55 [INFO] train episode 28712: reward = -74.59, steps = 20 20:41:57 [INFO] train episode 28713: reward = -89.70, steps = 22 20:41:59 [INFO] train episode 28714: reward = -74.82, steps = 24 20:42:01 [INFO] train episode 28715: reward = -65.92, steps = 21 20:42:04 [INFO] train episode 28716: reward = -117.19, steps = 25 20:42:06 [INFO] train episode 28717: reward = -45.72, steps = 20 20:42:08 [INFO] train episode 28718: reward = -50.37, steps = 24 20:42:10 [INFO] train episode 28719: reward = -63.80, steps = 27 20:42:13 [INFO] train episode 28720: reward = -65.91, steps = 31 20:42:15 [INFO] train episode 28721: reward = -69.60, steps = 26 20:42:17 [INFO] train episode 28722: reward = -57.50, steps = 26 20:42:20 [INFO] train episode 28723: reward = -101.47, steps = 32 20:42:22 [INFO] train episode 28724: reward = -128.30, steps = 17 20:42:24 [INFO] train episode 28725: reward = -86.00, steps = 21 20:42:26 [INFO] train episode 28726: reward = -75.13, steps = 24 20:42:29 [INFO] train episode 28727: reward = -109.72, steps = 35 20:42:31 [INFO] train episode 28728: reward = -70.37, steps = 19 20:42:34 [INFO] train episode 28729: reward = -106.71, steps = 39 20:42:39 [INFO] train episode 28730: reward = -87.81, steps = 42 20:42:41 [INFO] train episode 28731: reward = -73.09, steps = 22 20:42:43 [INFO] train episode 28732: reward = -114.70, steps = 34 20:42:48 [INFO] train episode 28733: reward = -102.22, steps = 47 20:42:49 [INFO] train episode 28734: reward = -105.07, steps = 19 20:42:52 [INFO] train episode 28735: reward = -57.63, steps = 29 20:42:55 [INFO] train episode 28736: reward = -78.91, steps = 32 20:42:57 [INFO] train episode 28737: reward = -122.22, steps = 23 20:43:00 [INFO] train episode 28738: reward = -63.49, steps = 28 20:43:03 [INFO] train episode 28739: reward = -77.33, steps = 35 20:43:05 [INFO] train episode 28740: reward = -60.67, steps = 28 20:43:08 [INFO] train episode 28741: reward = -66.05, steps = 28 20:43:09 [INFO] train episode 28742: reward = -97.03, steps = 17 20:43:13 [INFO] train episode 28743: reward = -125.02, steps = 36 20:43:15 [INFO] train episode 28744: reward = -58.86, steps = 20 20:43:17 [INFO] train episode 28745: reward = -43.28, steps = 21 20:43:18 [INFO] train episode 28746: reward = -93.89, steps = 20 20:43:20 [INFO] train episode 28747: reward = -66.62, steps = 20 20:43:23 [INFO] train episode 28748: reward = -91.22, steps = 32 20:43:27 [INFO] train episode 28749: reward = -125.18, steps = 37 20:43:30 [INFO] train episode 28750: reward = -72.17, steps = 29 20:43:32 [INFO] train episode 28751: reward = -80.77, steps = 24 20:43:35 [INFO] train episode 28752: reward = -107.65, steps = 24 20:43:36 [INFO] train episode 28753: reward = -73.60, steps = 20 20:43:38 [INFO] train episode 28754: reward = -59.87, steps = 24 20:43:41 [INFO] train episode 28755: reward = -60.46, steps = 33 20:43:43 [INFO] train episode 28756: reward = -94.02, steps = 20 20:43:46 [INFO] train episode 28757: reward = -139.33, steps = 23 20:43:47 [INFO] train episode 28758: reward = -67.54, steps = 19 20:43:49 [INFO] train episode 28759: reward = -79.59, steps = 21 20:43:51 [INFO] train episode 28760: reward = -68.51, steps = 20 20:43:53 [INFO] train episode 28761: reward = -73.53, steps = 29 20:43:55 [INFO] train episode 28762: reward = -47.51, steps = 22 20:43:59 [INFO] train episode 28763: reward = -70.50, steps = 43 20:44:02 [INFO] train episode 28764: reward = -82.37, steps = 33 20:44:04 [INFO] train episode 28765: reward = -82.89, steps = 19 20:44:07 [INFO] train episode 28766: reward = -70.22, steps = 33 20:44:10 [INFO] train episode 28767: reward = -81.30, steps = 32 20:44:12 [INFO] train episode 28768: reward = -66.42, steps = 21 20:44:13 [INFO] train episode 28769: reward = -115.15, steps = 19 20:44:18 [INFO] train episode 28770: reward = -110.66, steps = 48 20:44:21 [INFO] train episode 28771: reward = -56.72, steps = 31 20:44:22 [INFO] train episode 28772: reward = -48.38, steps = 20 20:44:25 [INFO] train episode 28773: reward = -105.42, steps = 36 20:44:27 [INFO] train episode 28774: reward = -89.52, steps = 18 20:44:30 [INFO] train episode 28775: reward = -84.33, steps = 36 20:44:32 [INFO] train episode 28776: reward = -68.71, steps = 23 20:44:35 [INFO] train episode 28777: reward = -73.99, steps = 25 20:44:37 [INFO] train episode 28778: reward = -64.34, steps = 23 20:44:39 [INFO] train episode 28779: reward = -101.93, steps = 20 20:44:42 [INFO] train episode 28780: reward = -63.44, steps = 38 20:44:47 [INFO] train episode 28781: reward = -100.05, steps = 55 20:44:49 [INFO] train episode 28782: reward = -84.46, steps = 23 20:44:51 [INFO] train episode 28783: reward = -114.49, steps = 26 20:44:53 [INFO] train episode 28784: reward = -51.11, steps = 20 20:44:56 [INFO] train episode 28785: reward = -146.64, steps = 36 20:45:01 [INFO] train episode 28786: reward = -73.86, steps = 49 20:45:03 [INFO] train episode 28787: reward = -58.38, steps = 24 20:45:05 [INFO] train episode 28788: reward = -79.54, steps = 27 20:45:08 [INFO] train episode 28789: reward = -68.86, steps = 25 20:45:09 [INFO] train episode 28790: reward = -77.80, steps = 20 20:45:11 [INFO] train episode 28791: reward = -51.77, steps = 21 20:45:13 [INFO] train episode 28792: reward = -80.56, steps = 20 20:45:16 [INFO] train episode 28793: reward = -112.29, steps = 34 20:45:20 [INFO] train episode 28794: reward = -81.11, steps = 45 20:45:22 [INFO] train episode 28795: reward = -86.43, steps = 23 20:45:24 [INFO] train episode 28796: reward = -89.41, steps = 19 20:45:26 [INFO] train episode 28797: reward = -55.72, steps = 28 20:45:28 [INFO] train episode 28798: reward = -70.30, steps = 22 20:45:30 [INFO] train episode 28799: reward = -68.66, steps = 20 20:45:32 [INFO] train episode 28800: reward = -120.98, steps = 20 20:45:34 [INFO] train episode 28801: reward = -74.06, steps = 24 20:45:37 [INFO] train episode 28802: reward = -38.66, steps = 31 20:45:40 [INFO] train episode 28803: reward = -63.47, steps = 38 20:45:42 [INFO] train episode 28804: reward = -57.83, steps = 22 20:45:44 [INFO] train episode 28805: reward = -71.73, steps = 20 20:45:46 [INFO] train episode 28806: reward = -65.66, steps = 19 20:45:48 [INFO] train episode 28807: reward = -85.98, steps = 24 20:45:52 [INFO] train episode 28808: reward = -101.07, steps = 48 20:45:55 [INFO] train episode 28809: reward = -65.29, steps = 25 20:45:56 [INFO] train episode 28810: reward = -54.01, steps = 21 20:45:59 [INFO] train episode 28811: reward = -84.50, steps = 27 20:46:01 [INFO] train episode 28812: reward = -60.33, steps = 23 20:46:03 [INFO] train episode 28813: reward = -62.37, steps = 21 20:46:06 [INFO] train episode 28814: reward = -70.52, steps = 34 20:46:07 [INFO] train episode 28815: reward = -82.93, steps = 20 20:46:11 [INFO] train episode 28816: reward = -67.74, steps = 34 20:46:13 [INFO] train episode 28817: reward = -71.62, steps = 29 20:46:17 [INFO] train episode 28818: reward = -116.32, steps = 42 20:46:19 [INFO] train episode 28819: reward = -58.77, steps = 23 20:46:21 [INFO] train episode 28820: reward = -47.15, steps = 19 20:46:23 [INFO] train episode 28821: reward = -86.94, steps = 24 20:46:25 [INFO] train episode 28822: reward = -82.19, steps = 21 20:46:29 [INFO] train episode 28823: reward = -59.02, steps = 32 20:46:30 [INFO] train episode 28824: reward = -77.03, steps = 20 20:46:32 [INFO] train episode 28825: reward = -94.94, steps = 18 20:46:34 [INFO] train episode 28826: reward = -80.84, steps = 23 20:46:36 [INFO] train episode 28827: reward = -79.11, steps = 27 20:46:38 [INFO] train episode 28828: reward = -75.23, steps = 22 20:46:40 [INFO] train episode 28829: reward = -50.07, steps = 23 20:46:44 [INFO] train episode 28830: reward = -50.37, steps = 34 20:46:45 [INFO] train episode 28831: reward = -69.66, steps = 17 20:46:47 [INFO] train episode 28832: reward = -46.08, steps = 21 20:46:49 [INFO] train episode 28833: reward = -62.88, steps = 19 20:46:51 [INFO] train episode 28834: reward = -71.54, steps = 26 20:46:54 [INFO] train episode 28835: reward = -115.77, steps = 34 20:46:56 [INFO] train episode 28836: reward = -159.43, steps = 18 20:46:57 [INFO] train episode 28837: reward = -77.38, steps = 20 20:47:01 [INFO] train episode 28838: reward = -73.51, steps = 32 20:47:03 [INFO] train episode 28839: reward = -43.69, steps = 21 20:47:05 [INFO] train episode 28840: reward = -132.18, steps = 33 20:47:07 [INFO] train episode 28841: reward = -43.17, steps = 25 20:47:10 [INFO] train episode 28842: reward = -89.39, steps = 33 20:47:13 [INFO] train episode 28843: reward = -66.96, steps = 28 20:47:14 [INFO] train episode 28844: reward = -50.46, steps = 19 20:47:17 [INFO] train episode 28845: reward = -62.93, steps = 22 20:47:19 [INFO] train episode 28846: reward = -70.35, steps = 22 20:47:21 [INFO] train episode 28847: reward = -51.98, steps = 20 20:47:23 [INFO] train episode 28848: reward = -85.44, steps = 24 20:47:25 [INFO] train episode 28849: reward = -70.51, steps = 22 20:47:27 [INFO] train episode 28850: reward = -96.90, steps = 26 20:47:29 [INFO] train episode 28851: reward = -74.61, steps = 24 20:47:31 [INFO] train episode 28852: reward = -113.38, steps = 21 20:47:33 [INFO] train episode 28853: reward = -119.56, steps = 20 20:47:35 [INFO] train episode 28854: reward = -89.97, steps = 29 20:47:39 [INFO] train episode 28855: reward = -109.63, steps = 39 20:47:41 [INFO] train episode 28856: reward = -65.55, steps = 25 20:47:42 [INFO] train episode 28857: reward = -128.82, steps = 17 20:47:46 [INFO] train episode 28858: reward = -37.81, steps = 38 20:47:48 [INFO] train episode 28859: reward = -41.78, steps = 24 20:47:51 [INFO] train episode 28860: reward = -72.71, steps = 28 20:47:52 [INFO] train episode 28861: reward = -77.88, steps = 20 20:47:54 [INFO] train episode 28862: reward = -65.62, steps = 21 20:47:57 [INFO] train episode 28863: reward = -70.55, steps = 30 20:48:00 [INFO] train episode 28864: reward = -56.80, steps = 31 20:48:05 [INFO] train episode 28865: reward = -154.84, steps = 59 20:48:08 [INFO] train episode 28866: reward = -85.35, steps = 27 20:48:09 [INFO] train episode 28867: reward = -90.77, steps = 21 20:48:12 [INFO] train episode 28868: reward = -78.15, steps = 30 20:48:14 [INFO] train episode 28869: reward = -50.54, steps = 25 20:48:16 [INFO] train episode 28870: reward = -88.38, steps = 25 20:48:19 [INFO] train episode 28871: reward = -123.20, steps = 34 20:48:22 [INFO] train episode 28872: reward = -137.43, steps = 28 20:48:24 [INFO] train episode 28873: reward = -84.35, steps = 20 20:48:27 [INFO] train episode 28874: reward = -48.66, steps = 34 20:48:30 [INFO] train episode 28875: reward = -73.46, steps = 28 20:48:31 [INFO] train episode 28876: reward = -50.32, steps = 20 20:48:33 [INFO] train episode 28877: reward = -70.47, steps = 20 20:48:35 [INFO] train episode 28878: reward = -78.32, steps = 24 20:48:39 [INFO] train episode 28879: reward = -84.34, steps = 30 20:48:41 [INFO] train episode 28880: reward = -55.69, steps = 25 20:48:44 [INFO] train episode 28881: reward = -80.23, steps = 32 20:48:46 [INFO] train episode 28882: reward = -92.28, steps = 23 20:48:48 [INFO] train episode 28883: reward = -107.75, steps = 26 20:48:51 [INFO] train episode 28884: reward = -75.49, steps = 39 20:48:54 [INFO] train episode 28885: reward = -51.96, steps = 33 20:48:57 [INFO] train episode 28886: reward = -99.29, steps = 33 20:48:59 [INFO] train episode 28887: reward = -47.66, steps = 26 20:49:01 [INFO] train episode 28888: reward = -55.33, steps = 20 20:49:03 [INFO] train episode 28889: reward = -66.69, steps = 24 20:49:07 [INFO] train episode 28890: reward = -143.19, steps = 36 20:49:08 [INFO] train episode 28891: reward = -73.88, steps = 21 20:49:11 [INFO] train episode 28892: reward = -64.01, steps = 28 20:49:13 [INFO] train episode 28893: reward = -79.77, steps = 24 20:49:17 [INFO] train episode 28894: reward = -74.59, steps = 38 20:49:21 [INFO] train episode 28895: reward = -90.97, steps = 42 20:49:23 [INFO] train episode 28896: reward = -71.85, steps = 20 20:49:25 [INFO] train episode 28897: reward = -148.87, steps = 20 20:49:28 [INFO] train episode 28898: reward = -68.10, steps = 30 20:49:29 [INFO] train episode 28899: reward = -100.30, steps = 19 20:49:32 [INFO] train episode 28900: reward = -68.92, steps = 32 20:49:35 [INFO] train episode 28901: reward = -65.38, steps = 37 20:49:39 [INFO] train episode 28902: reward = -101.94, steps = 40 20:49:41 [INFO] train episode 28903: reward = -63.16, steps = 22 20:49:42 [INFO] train episode 28904: reward = -95.98, steps = 18 20:49:45 [INFO] train episode 28905: reward = -53.09, steps = 24 20:49:47 [INFO] train episode 28906: reward = -64.73, steps = 20 20:49:49 [INFO] train episode 28907: reward = -66.54, steps = 23 20:49:51 [INFO] train episode 28908: reward = -76.59, steps = 22 20:49:53 [INFO] train episode 28909: reward = -69.16, steps = 32 20:49:56 [INFO] train episode 28910: reward = -61.16, steps = 23 20:49:58 [INFO] train episode 28911: reward = -71.47, steps = 21 20:50:00 [INFO] train episode 28912: reward = -103.66, steps = 19 20:50:02 [INFO] train episode 28913: reward = -61.65, steps = 26 20:50:04 [INFO] train episode 28914: reward = -78.39, steps = 20 20:50:07 [INFO] train episode 28915: reward = -114.02, steps = 35 20:50:10 [INFO] train episode 28916: reward = -79.03, steps = 28 20:50:12 [INFO] train episode 28917: reward = -61.55, steps = 20 20:50:13 [INFO] train episode 28918: reward = -112.72, steps = 18 20:50:18 [INFO] train episode 28919: reward = -110.75, steps = 42 20:50:19 [INFO] train episode 28920: reward = -73.80, steps = 20 20:50:22 [INFO] train episode 28921: reward = -61.72, steps = 31 20:50:25 [INFO] train episode 28922: reward = -62.05, steps = 27 20:50:27 [INFO] train episode 28923: reward = -91.32, steps = 25 20:50:30 [INFO] train episode 28924: reward = -93.30, steps = 32 20:50:32 [INFO] train episode 28925: reward = -77.69, steps = 26 20:50:35 [INFO] train episode 28926: reward = -61.27, steps = 23 20:50:38 [INFO] train episode 28927: reward = -53.04, steps = 36 20:50:40 [INFO] train episode 28928: reward = -71.93, steps = 26 20:50:43 [INFO] train episode 28929: reward = -85.63, steps = 30 20:50:46 [INFO] train episode 28930: reward = -61.80, steps = 28 20:50:48 [INFO] train episode 28931: reward = -63.42, steps = 29 20:50:50 [INFO] train episode 28932: reward = -77.61, steps = 20 20:50:53 [INFO] train episode 28933: reward = -172.53, steps = 32 20:50:55 [INFO] train episode 28934: reward = -71.17, steps = 21 20:50:59 [INFO] train episode 28935: reward = -97.36, steps = 38 20:51:01 [INFO] train episode 28936: reward = -69.12, steps = 21 20:51:02 [INFO] train episode 28937: reward = -58.95, steps = 20 20:51:05 [INFO] train episode 28938: reward = -60.87, steps = 24 20:51:07 [INFO] train episode 28939: reward = -71.29, steps = 23 20:51:10 [INFO] train episode 28940: reward = -79.71, steps = 32 20:51:12 [INFO] train episode 28941: reward = -96.66, steps = 28 20:51:15 [INFO] train episode 28942: reward = -68.60, steps = 30 20:51:17 [INFO] train episode 28943: reward = -77.43, steps = 24 20:51:20 [INFO] train episode 28944: reward = -57.67, steps = 34 20:51:23 [INFO] train episode 28945: reward = -68.18, steps = 35 20:51:26 [INFO] train episode 28946: reward = -125.36, steps = 30 20:51:29 [INFO] train episode 28947: reward = -73.86, steps = 25 20:51:32 [INFO] train episode 28948: reward = -64.12, steps = 32 20:51:34 [INFO] train episode 28949: reward = -58.72, steps = 22 20:51:36 [INFO] train episode 28950: reward = -132.36, steps = 30 20:51:38 [INFO] train episode 28951: reward = -48.09, steps = 20 20:51:41 [INFO] train episode 28952: reward = -59.24, steps = 33 20:51:43 [INFO] train episode 28953: reward = -61.97, steps = 19 20:51:45 [INFO] train episode 28954: reward = -81.78, steps = 26 20:51:48 [INFO] train episode 28955: reward = -38.21, steps = 28 20:51:50 [INFO] train episode 28956: reward = -90.53, steps = 27 20:51:52 [INFO] train episode 28957: reward = -83.99, steps = 25 20:51:55 [INFO] train episode 28958: reward = -97.82, steps = 32 20:51:59 [INFO] train episode 28959: reward = -81.16, steps = 35 20:52:02 [INFO] train episode 28960: reward = -69.85, steps = 34 20:52:04 [INFO] train episode 28961: reward = -81.98, steps = 22 20:52:07 [INFO] train episode 28962: reward = -47.48, steps = 34 20:52:09 [INFO] train episode 28963: reward = -76.16, steps = 27 20:52:11 [INFO] train episode 28964: reward = -64.00, steps = 21 20:52:15 [INFO] train episode 28965: reward = -60.64, steps = 39 20:52:16 [INFO] train episode 28966: reward = -56.57, steps = 20 20:52:20 [INFO] train episode 28967: reward = -67.25, steps = 37 20:52:22 [INFO] train episode 28968: reward = -63.11, steps = 24 20:52:25 [INFO] train episode 28969: reward = -56.80, steps = 31 20:52:28 [INFO] train episode 28970: reward = -81.23, steps = 28 20:52:30 [INFO] train episode 28971: reward = -73.22, steps = 29 20:52:33 [INFO] train episode 28972: reward = -62.87, steps = 24 20:52:35 [INFO] train episode 28973: reward = -55.81, steps = 24 20:52:37 [INFO] train episode 28974: reward = -57.68, steps = 21 20:52:39 [INFO] train episode 28975: reward = -87.23, steps = 30 20:52:41 [INFO] train episode 28976: reward = -60.04, steps = 22 20:52:44 [INFO] train episode 28977: reward = -53.40, steps = 35 20:52:46 [INFO] train episode 28978: reward = -63.60, steps = 21 20:52:49 [INFO] train episode 28979: reward = -97.03, steps = 21 20:52:50 [INFO] train episode 28980: reward = -90.38, steps = 20 20:52:53 [INFO] train episode 28981: reward = -73.23, steps = 30 20:52:55 [INFO] train episode 28982: reward = -49.20, steps = 24 20:52:57 [INFO] train episode 28983: reward = -92.23, steps = 21 20:52:59 [INFO] train episode 28984: reward = -42.75, steps = 24 20:53:01 [INFO] train episode 28985: reward = -64.90, steps = 22 20:53:04 [INFO] train episode 28986: reward = -56.42, steps = 30 20:53:06 [INFO] train episode 28987: reward = -70.60, steps = 26 20:53:08 [INFO] train episode 28988: reward = -67.30, steps = 20 20:53:10 [INFO] train episode 28989: reward = -60.48, steps = 21 20:53:12 [INFO] train episode 28990: reward = -101.27, steps = 19 20:53:13 [INFO] train episode 28991: reward = -102.17, steps = 22 20:53:17 [INFO] train episode 28992: reward = -147.68, steps = 42 20:53:19 [INFO] train episode 28993: reward = -136.49, steps = 19 20:53:22 [INFO] train episode 28994: reward = -78.04, steps = 29 20:53:24 [INFO] train episode 28995: reward = -58.58, steps = 28 20:53:26 [INFO] train episode 28996: reward = -73.19, steps = 24 20:53:28 [INFO] train episode 28997: reward = -80.38, steps = 20 20:53:31 [INFO] train episode 28998: reward = -53.12, steps = 33 20:53:33 [INFO] train episode 28999: reward = -61.09, steps = 24 20:53:35 [INFO] train episode 29000: reward = -91.89, steps = 22 20:53:37 [INFO] train episode 29001: reward = -85.07, steps = 18 20:53:41 [INFO] train episode 29002: reward = -136.47, steps = 46 20:53:43 [INFO] train episode 29003: reward = -107.50, steps = 24 20:53:45 [INFO] train episode 29004: reward = -91.23, steps = 23 20:53:47 [INFO] train episode 29005: reward = -73.41, steps = 24 20:53:49 [INFO] train episode 29006: reward = -56.95, steps = 24 20:53:51 [INFO] train episode 29007: reward = -75.05, steps = 21 20:53:54 [INFO] train episode 29008: reward = -65.67, steps = 24 20:53:55 [INFO] train episode 29009: reward = -89.58, steps = 19 20:53:59 [INFO] train episode 29010: reward = -101.11, steps = 44 20:54:02 [INFO] train episode 29011: reward = -114.26, steps = 37 20:54:05 [INFO] train episode 29012: reward = -100.62, steps = 32 20:54:08 [INFO] train episode 29013: reward = -49.42, steps = 31 20:54:10 [INFO] train episode 29014: reward = -46.22, steps = 20 20:54:12 [INFO] train episode 29015: reward = -81.89, steps = 29 20:54:14 [INFO] train episode 29016: reward = -59.61, steps = 22 20:54:18 [INFO] train episode 29017: reward = -88.96, steps = 44 20:54:20 [INFO] train episode 29018: reward = -88.86, steps = 23 20:54:23 [INFO] train episode 29019: reward = -109.98, steps = 33 20:54:25 [INFO] train episode 29020: reward = -67.41, steps = 20 20:54:29 [INFO] train episode 29021: reward = -113.94, steps = 46 20:54:31 [INFO] train episode 29022: reward = -58.63, steps = 22 20:54:33 [INFO] train episode 29023: reward = -60.58, steps = 21 20:54:35 [INFO] train episode 29024: reward = -54.43, steps = 21 20:54:37 [INFO] train episode 29025: reward = -67.24, steps = 18 20:54:38 [INFO] train episode 29026: reward = -78.96, steps = 20 20:54:40 [INFO] train episode 29027: reward = -138.46, steps = 19 20:54:43 [INFO] train episode 29028: reward = -90.56, steps = 26 20:54:46 [INFO] train episode 29029: reward = -125.56, steps = 40 20:54:48 [INFO] train episode 29030: reward = -59.79, steps = 25 20:54:51 [INFO] train episode 29031: reward = -86.26, steps = 28 20:54:53 [INFO] train episode 29032: reward = -79.49, steps = 26 20:54:56 [INFO] train episode 29033: reward = -95.96, steps = 37 20:55:00 [INFO] train episode 29034: reward = -94.91, steps = 37 20:55:02 [INFO] train episode 29035: reward = -86.83, steps = 22 20:55:05 [INFO] train episode 29036: reward = -71.64, steps = 41 20:55:07 [INFO] train episode 29037: reward = -53.19, steps = 22 20:55:10 [INFO] train episode 29038: reward = -50.60, steps = 29 20:55:12 [INFO] train episode 29039: reward = -65.65, steps = 23 20:55:16 [INFO] train episode 29040: reward = -63.19, steps = 30 20:55:18 [INFO] train episode 29041: reward = -70.42, steps = 24 20:55:21 [INFO] train episode 29042: reward = -60.71, steps = 31 20:55:24 [INFO] train episode 29043: reward = -81.94, steps = 33 20:55:26 [INFO] train episode 29044: reward = -85.44, steps = 31 20:55:28 [INFO] train episode 29045: reward = -61.51, steps = 22 20:55:30 [INFO] train episode 29046: reward = -80.21, steps = 18 20:55:33 [INFO] train episode 29047: reward = -92.21, steps = 23 20:55:35 [INFO] train episode 29048: reward = -53.20, steps = 24 20:55:37 [INFO] train episode 29049: reward = -77.46, steps = 21 20:55:38 [INFO] train episode 29050: reward = -88.66, steps = 19 20:55:40 [INFO] train episode 29051: reward = -43.83, steps = 24 20:55:44 [INFO] train episode 29052: reward = -62.95, steps = 42 20:55:47 [INFO] train episode 29053: reward = -92.25, steps = 27 20:55:50 [INFO] train episode 29054: reward = -57.13, steps = 38 20:55:52 [INFO] train episode 29055: reward = -40.88, steps = 21 20:55:55 [INFO] train episode 29056: reward = -101.45, steps = 27 20:55:57 [INFO] train episode 29057: reward = -68.64, steps = 29 20:55:59 [INFO] train episode 29058: reward = -76.52, steps = 19 20:56:03 [INFO] train episode 29059: reward = -101.34, steps = 41 20:56:06 [INFO] train episode 29060: reward = -72.22, steps = 31 20:56:10 [INFO] train episode 29061: reward = -68.82, steps = 45 20:56:13 [INFO] train episode 29062: reward = -91.17, steps = 45 20:56:17 [INFO] train episode 29063: reward = -89.81, steps = 37 20:56:19 [INFO] train episode 29064: reward = -86.02, steps = 28 20:56:22 [INFO] train episode 29065: reward = -95.35, steps = 24 20:56:24 [INFO] train episode 29066: reward = -47.54, steps = 29 20:56:26 [INFO] train episode 29067: reward = -184.13, steps = 19 20:56:28 [INFO] train episode 29068: reward = -66.95, steps = 23 20:56:30 [INFO] train episode 29069: reward = -35.65, steps = 23 20:56:32 [INFO] train episode 29070: reward = -58.28, steps = 20 20:56:34 [INFO] train episode 29071: reward = -47.23, steps = 21 20:56:37 [INFO] train episode 29072: reward = -58.40, steps = 23 20:56:40 [INFO] train episode 29073: reward = -45.18, steps = 37 20:56:42 [INFO] train episode 29074: reward = -64.07, steps = 29 20:56:44 [INFO] train episode 29075: reward = -55.03, steps = 21 20:56:46 [INFO] train episode 29076: reward = -67.61, steps = 20 20:56:50 [INFO] train episode 29077: reward = -67.40, steps = 40 20:56:52 [INFO] train episode 29078: reward = -58.72, steps = 23 20:56:54 [INFO] train episode 29079: reward = -102.47, steps = 21 20:56:56 [INFO] train episode 29080: reward = -88.29, steps = 21 20:56:58 [INFO] train episode 29081: reward = -39.33, steps = 20 20:57:00 [INFO] train episode 29082: reward = -64.81, steps = 24 20:57:02 [INFO] train episode 29083: reward = -99.87, steps = 25 20:57:04 [INFO] train episode 29084: reward = -52.92, steps = 24 20:57:06 [INFO] train episode 29085: reward = -63.39, steps = 22 20:57:09 [INFO] train episode 29086: reward = -64.45, steps = 26 20:57:11 [INFO] train episode 29087: reward = -48.95, steps = 22 20:57:14 [INFO] train episode 29088: reward = -72.88, steps = 35 20:57:18 [INFO] train episode 29089: reward = -68.22, steps = 43 20:57:20 [INFO] train episode 29090: reward = -53.10, steps = 25 20:57:22 [INFO] train episode 29091: reward = -95.37, steps = 21 20:57:27 [INFO] train episode 29092: reward = -103.45, steps = 49 20:57:30 [INFO] train episode 29093: reward = -64.86, steps = 35 20:57:33 [INFO] train episode 29094: reward = -88.61, steps = 37 20:57:36 [INFO] train episode 29095: reward = -64.76, steps = 35 20:57:38 [INFO] train episode 29096: reward = -64.03, steps = 21 20:57:40 [INFO] train episode 29097: reward = -64.44, steps = 25 20:57:42 [INFO] train episode 29098: reward = -79.36, steps = 19 20:57:45 [INFO] train episode 29099: reward = -95.33, steps = 32 20:57:47 [INFO] train episode 29100: reward = -74.89, steps = 19 20:57:49 [INFO] train episode 29101: reward = -115.82, steps = 22 20:57:51 [INFO] train episode 29102: reward = -57.88, steps = 24 20:57:53 [INFO] train episode 29103: reward = -56.28, steps = 24 20:57:57 [INFO] train episode 29104: reward = -46.22, steps = 49 20:57:59 [INFO] train episode 29105: reward = -55.81, steps = 19 20:58:01 [INFO] train episode 29106: reward = -68.13, steps = 19 20:58:04 [INFO] train episode 29107: reward = -57.90, steps = 32 20:58:06 [INFO] train episode 29108: reward = -65.94, steps = 24 20:58:07 [INFO] train episode 29109: reward = -65.75, steps = 19 20:58:10 [INFO] train episode 29110: reward = -85.99, steps = 27 20:58:13 [INFO] train episode 29111: reward = -75.09, steps = 26 20:58:17 [INFO] train episode 29112: reward = -104.78, steps = 38 20:58:18 [INFO] train episode 29113: reward = -56.76, steps = 21 20:58:21 [INFO] train episode 29114: reward = -102.27, steps = 30 20:58:24 [INFO] train episode 29115: reward = -74.63, steps = 34 20:58:27 [INFO] train episode 29116: reward = -61.72, steps = 30 20:58:28 [INFO] train episode 29117: reward = -76.19, steps = 19 20:58:31 [INFO] train episode 29118: reward = -46.18, steps = 24 20:58:34 [INFO] train episode 29119: reward = -85.27, steps = 32 20:58:36 [INFO] train episode 29120: reward = -71.46, steps = 23 20:58:39 [INFO] train episode 29121: reward = -75.00, steps = 36 20:58:41 [INFO] train episode 29122: reward = -73.85, steps = 22 20:58:45 [INFO] train episode 29123: reward = -146.91, steps = 48 20:58:47 [INFO] train episode 29124: reward = -69.47, steps = 19 20:58:50 [INFO] train episode 29125: reward = -64.75, steps = 39 20:58:53 [INFO] train episode 29126: reward = -96.70, steps = 30 20:58:56 [INFO] train episode 29127: reward = -92.08, steps = 32 20:58:58 [INFO] train episode 29128: reward = -54.10, steps = 22 20:58:59 [INFO] train episode 29129: reward = -124.32, steps = 18 20:59:02 [INFO] train episode 29130: reward = -89.24, steps = 33 20:59:04 [INFO] train episode 29131: reward = -56.99, steps = 20 20:59:08 [INFO] train episode 29132: reward = -54.24, steps = 39 20:59:10 [INFO] train episode 29133: reward = -59.90, steps = 25 20:59:12 [INFO] train episode 29134: reward = -45.39, steps = 20 20:59:15 [INFO] train episode 29135: reward = -64.39, steps = 34 20:59:17 [INFO] train episode 29136: reward = -77.65, steps = 29 20:59:20 [INFO] train episode 29137: reward = -66.87, steps = 28 20:59:23 [INFO] train episode 29138: reward = -71.41, steps = 36 20:59:26 [INFO] train episode 29139: reward = -85.54, steps = 32 20:59:28 [INFO] train episode 29140: reward = -55.44, steps = 20 20:59:29 [INFO] train episode 29141: reward = -97.22, steps = 20 20:59:32 [INFO] train episode 29142: reward = -133.48, steps = 29 20:59:34 [INFO] train episode 29143: reward = -81.88, steps = 26 20:59:36 [INFO] train episode 29144: reward = -71.36, steps = 20 20:59:39 [INFO] train episode 29145: reward = -58.42, steps = 26 20:59:41 [INFO] train episode 29146: reward = -52.80, steps = 22 20:59:44 [INFO] train episode 29147: reward = -96.59, steps = 33 20:59:46 [INFO] train episode 29148: reward = -80.33, steps = 28 20:59:49 [INFO] train episode 29149: reward = -91.46, steps = 36 20:59:53 [INFO] train episode 29150: reward = -72.17, steps = 33 20:59:55 [INFO] train episode 29151: reward = -75.82, steps = 21 20:59:58 [INFO] train episode 29152: reward = -146.03, steps = 38 21:00:02 [INFO] train episode 29153: reward = -114.80, steps = 41 21:00:04 [INFO] train episode 29154: reward = -94.55, steps = 22 21:00:06 [INFO] train episode 29155: reward = -98.94, steps = 21 21:00:08 [INFO] train episode 29156: reward = -52.52, steps = 28 21:00:11 [INFO] train episode 29157: reward = -59.22, steps = 35 21:00:14 [INFO] train episode 29158: reward = -62.53, steps = 25 21:00:16 [INFO] train episode 29159: reward = -58.90, steps = 23 21:00:18 [INFO] train episode 29160: reward = -72.94, steps = 23 21:00:20 [INFO] train episode 29161: reward = -92.54, steps = 30 21:00:23 [INFO] train episode 29162: reward = -66.35, steps = 29 21:00:25 [INFO] train episode 29163: reward = -75.00, steps = 24 21:00:27 [INFO] train episode 29164: reward = -86.57, steps = 24 21:00:30 [INFO] train episode 29165: reward = -52.02, steps = 29 21:00:32 [INFO] train episode 29166: reward = -60.24, steps = 29 21:00:36 [INFO] train episode 29167: reward = -57.30, steps = 40 21:00:40 [INFO] train episode 29168: reward = -101.75, steps = 50 21:00:43 [INFO] train episode 29169: reward = -62.18, steps = 21 21:00:45 [INFO] train episode 29170: reward = -68.13, steps = 30 21:00:48 [INFO] train episode 29171: reward = -79.27, steps = 25 21:00:50 [INFO] train episode 29172: reward = -59.57, steps = 29 21:00:54 [INFO] train episode 29173: reward = -106.63, steps = 41 21:00:58 [INFO] train episode 29174: reward = -149.04, steps = 42 21:01:01 [INFO] train episode 29175: reward = -77.49, steps = 27 21:01:03 [INFO] train episode 29176: reward = -50.95, steps = 32 21:01:05 [INFO] train episode 29177: reward = -61.76, steps = 20 21:01:07 [INFO] train episode 29178: reward = -68.76, steps = 21 21:01:11 [INFO] train episode 29179: reward = -112.31, steps = 31 21:01:13 [INFO] train episode 29180: reward = -67.90, steps = 27 21:01:15 [INFO] train episode 29181: reward = -97.05, steps = 21 21:01:18 [INFO] train episode 29182: reward = -70.08, steps = 31 21:01:20 [INFO] train episode 29183: reward = -91.71, steps = 24 21:01:22 [INFO] train episode 29184: reward = -48.10, steps = 23 21:01:24 [INFO] train episode 29185: reward = -148.91, steps = 20 21:01:26 [INFO] train episode 29186: reward = -73.40, steps = 25 21:01:28 [INFO] train episode 29187: reward = -73.92, steps = 22 21:01:30 [INFO] train episode 29188: reward = -59.67, steps = 20 21:01:33 [INFO] train episode 29189: reward = -59.43, steps = 22 21:01:35 [INFO] train episode 29190: reward = -73.15, steps = 28 21:01:38 [INFO] train episode 29191: reward = -41.41, steps = 28 21:01:41 [INFO] train episode 29192: reward = -87.43, steps = 44 21:01:44 [INFO] train episode 29193: reward = -77.21, steps = 26 21:01:46 [INFO] train episode 29194: reward = -60.04, steps = 19 21:01:48 [INFO] train episode 29195: reward = -54.29, steps = 23 21:01:51 [INFO] train episode 29196: reward = -77.68, steps = 31 21:01:53 [INFO] train episode 29197: reward = -44.44, steps = 22 21:01:56 [INFO] train episode 29198: reward = -97.16, steps = 31 21:01:59 [INFO] train episode 29199: reward = -58.51, steps = 33 21:02:02 [INFO] train episode 29200: reward = -129.32, steps = 38 21:02:06 [INFO] train episode 29201: reward = -72.11, steps = 39 21:02:09 [INFO] train episode 29202: reward = -98.33, steps = 37 21:02:12 [INFO] train episode 29203: reward = -105.12, steps = 35 21:02:14 [INFO] train episode 29204: reward = -80.58, steps = 22 21:02:16 [INFO] train episode 29205: reward = -49.37, steps = 23 21:02:19 [INFO] train episode 29206: reward = -54.40, steps = 34 21:02:22 [INFO] train episode 29207: reward = -46.40, steps = 29 21:02:24 [INFO] train episode 29208: reward = -41.09, steps = 24 21:02:26 [INFO] train episode 29209: reward = -50.54, steps = 20 21:02:29 [INFO] train episode 29210: reward = -63.19, steps = 33 21:02:31 [INFO] train episode 29211: reward = -86.48, steps = 25 21:02:33 [INFO] train episode 29212: reward = -95.04, steps = 21 21:02:36 [INFO] train episode 29213: reward = -89.69, steps = 24 21:02:38 [INFO] train episode 29214: reward = -82.47, steps = 21 21:02:40 [INFO] train episode 29215: reward = -50.70, steps = 21 21:02:42 [INFO] train episode 29216: reward = -61.54, steps = 25 21:02:45 [INFO] train episode 29217: reward = -63.37, steps = 28 21:02:47 [INFO] train episode 29218: reward = -76.12, steps = 19 21:02:49 [INFO] train episode 29219: reward = -108.69, steps = 27 21:02:53 [INFO] train episode 29220: reward = -89.02, steps = 41 21:02:55 [INFO] train episode 29221: reward = -97.62, steps = 20 21:02:57 [INFO] train episode 29222: reward = -59.68, steps = 26 21:02:59 [INFO] train episode 29223: reward = -53.42, steps = 20 21:03:01 [INFO] train episode 29224: reward = -90.27, steps = 24 21:03:03 [INFO] train episode 29225: reward = -62.82, steps = 22 21:03:06 [INFO] train episode 29226: reward = -134.18, steps = 31 21:03:08 [INFO] train episode 29227: reward = -90.67, steps = 26 21:03:14 [INFO] train episode 29228: reward = -125.89, steps = 61 21:03:17 [INFO] train episode 29229: reward = -37.50, steps = 29 21:03:19 [INFO] train episode 29230: reward = -80.68, steps = 23 21:03:20 [INFO] train episode 29231: reward = -62.49, steps = 19 21:03:22 [INFO] train episode 29232: reward = -58.97, steps = 23 21:03:25 [INFO] train episode 29233: reward = -87.51, steps = 33 21:03:28 [INFO] train episode 29234: reward = -80.23, steps = 24 21:03:31 [INFO] train episode 29235: reward = -67.09, steps = 41 21:03:33 [INFO] train episode 29236: reward = -52.18, steps = 22 21:03:36 [INFO] train episode 29237: reward = -69.70, steps = 35 21:03:38 [INFO] train episode 29238: reward = -89.01, steps = 23 21:03:42 [INFO] train episode 29239: reward = -80.25, steps = 44 21:03:45 [INFO] train episode 29240: reward = -72.29, steps = 32 21:03:50 [INFO] train episode 29241: reward = -98.47, steps = 54 21:03:53 [INFO] train episode 29242: reward = -54.94, steps = 33 21:03:55 [INFO] train episode 29243: reward = -60.07, steps = 23 21:03:57 [INFO] train episode 29244: reward = -67.64, steps = 20 21:03:59 [INFO] train episode 29245: reward = -67.79, steps = 23 21:04:02 [INFO] train episode 29246: reward = -66.22, steps = 27 21:04:04 [INFO] train episode 29247: reward = -134.92, steps = 28 21:04:07 [INFO] train episode 29248: reward = -65.75, steps = 33 21:04:10 [INFO] train episode 29249: reward = -67.54, steps = 27 21:04:13 [INFO] train episode 29250: reward = -59.93, steps = 30 21:04:15 [INFO] train episode 29251: reward = -60.55, steps = 25 21:04:18 [INFO] train episode 29252: reward = -67.09, steps = 22 21:04:20 [INFO] train episode 29253: reward = -76.78, steps = 22 21:04:22 [INFO] train episode 29254: reward = -39.45, steps = 29 21:04:26 [INFO] train episode 29255: reward = -74.12, steps = 44 21:04:29 [INFO] train episode 29256: reward = -63.14, steps = 32 21:04:32 [INFO] train episode 29257: reward = -101.64, steps = 31 21:04:34 [INFO] train episode 29258: reward = -62.25, steps = 25 21:04:36 [INFO] train episode 29259: reward = -186.68, steps = 21 21:04:40 [INFO] train episode 29260: reward = -76.22, steps = 40 21:04:42 [INFO] train episode 29261: reward = -80.16, steps = 28 21:04:46 [INFO] train episode 29262: reward = -117.90, steps = 40 21:04:49 [INFO] train episode 29263: reward = -60.48, steps = 35 21:04:51 [INFO] train episode 29264: reward = -96.27, steps = 28 21:04:55 [INFO] train episode 29265: reward = -66.02, steps = 45 21:04:57 [INFO] train episode 29266: reward = -57.49, steps = 20 21:05:01 [INFO] train episode 29267: reward = -106.78, steps = 39 21:05:02 [INFO] train episode 29268: reward = -104.68, steps = 18 21:05:04 [INFO] train episode 29269: reward = -71.01, steps = 22 21:05:07 [INFO] train episode 29270: reward = -68.15, steps = 26 21:05:09 [INFO] train episode 29271: reward = -68.54, steps = 25 21:05:12 [INFO] train episode 29272: reward = -93.71, steps = 29 21:05:15 [INFO] train episode 29273: reward = -106.22, steps = 37 21:05:17 [INFO] train episode 29274: reward = -73.03, steps = 22 21:05:20 [INFO] train episode 29275: reward = -71.41, steps = 26 21:05:24 [INFO] train episode 29276: reward = -119.02, steps = 40 21:05:26 [INFO] train episode 29277: reward = -78.35, steps = 21 21:05:28 [INFO] train episode 29278: reward = -37.53, steps = 23 21:05:31 [INFO] train episode 29279: reward = -55.25, steps = 36 21:05:33 [INFO] train episode 29280: reward = -91.60, steps = 25 21:05:35 [INFO] train episode 29281: reward = -99.96, steps = 22 21:05:38 [INFO] train episode 29282: reward = -49.72, steps = 27 21:05:43 [INFO] train episode 29283: reward = -108.11, steps = 61 21:05:46 [INFO] train episode 29284: reward = -80.22, steps = 30 21:05:50 [INFO] train episode 29285: reward = -65.66, steps = 46 21:05:52 [INFO] train episode 29286: reward = -68.56, steps = 23 21:05:54 [INFO] train episode 29287: reward = -52.49, steps = 24 21:05:57 [INFO] train episode 29288: reward = -83.22, steps = 21 21:05:59 [INFO] train episode 29289: reward = -81.38, steps = 23 21:06:01 [INFO] train episode 29290: reward = -46.87, steps = 25 21:06:03 [INFO] train episode 29291: reward = -93.22, steps = 19 21:06:05 [INFO] train episode 29292: reward = -79.53, steps = 26 21:06:08 [INFO] train episode 29293: reward = -44.07, steps = 31 21:06:10 [INFO] train episode 29294: reward = -82.91, steps = 21 21:06:14 [INFO] train episode 29295: reward = -63.72, steps = 52 21:06:16 [INFO] train episode 29296: reward = -54.86, steps = 25 21:06:18 [INFO] train episode 29297: reward = -62.79, steps = 19 21:06:20 [INFO] train episode 29298: reward = -65.72, steps = 25 21:06:22 [INFO] train episode 29299: reward = -83.21, steps = 20 21:06:24 [INFO] train episode 29300: reward = -95.70, steps = 21 21:06:27 [INFO] train episode 29301: reward = -107.10, steps = 29 21:06:29 [INFO] train episode 29302: reward = -68.34, steps = 19 21:06:31 [INFO] train episode 29303: reward = -79.74, steps = 28 21:06:34 [INFO] train episode 29304: reward = -83.88, steps = 32 21:06:37 [INFO] train episode 29305: reward = -45.07, steps = 25 21:06:39 [INFO] train episode 29306: reward = -95.67, steps = 29 21:06:41 [INFO] train episode 29307: reward = -76.75, steps = 19 21:06:44 [INFO] train episode 29308: reward = -94.53, steps = 37 21:06:47 [INFO] train episode 29309: reward = -71.56, steps = 26 21:06:50 [INFO] train episode 29310: reward = -83.10, steps = 33 21:06:54 [INFO] train episode 29311: reward = -78.54, steps = 48 21:06:57 [INFO] train episode 29312: reward = -175.44, steps = 33 21:06:59 [INFO] train episode 29313: reward = -105.77, steps = 20 21:07:01 [INFO] train episode 29314: reward = -57.84, steps = 21 21:07:05 [INFO] train episode 29315: reward = -54.02, steps = 47 21:07:08 [INFO] train episode 29316: reward = -72.66, steps = 20 21:07:10 [INFO] train episode 29317: reward = -113.01, steps = 21 21:07:12 [INFO] train episode 29318: reward = -77.30, steps = 22 21:07:15 [INFO] train episode 29319: reward = -73.19, steps = 40 21:07:17 [INFO] train episode 29320: reward = -56.31, steps = 26 21:07:20 [INFO] train episode 29321: reward = -63.97, steps = 26 21:07:25 [INFO] train episode 29322: reward = -124.75, steps = 48 21:07:27 [INFO] train episode 29323: reward = -53.24, steps = 29 21:07:30 [INFO] train episode 29324: reward = -100.43, steps = 33 21:07:33 [INFO] train episode 29325: reward = -59.78, steps = 28 21:07:35 [INFO] train episode 29326: reward = -97.27, steps = 20 21:07:37 [INFO] train episode 29327: reward = -72.26, steps = 27 21:07:41 [INFO] train episode 29328: reward = -53.19, steps = 43 21:07:44 [INFO] train episode 29329: reward = -34.99, steps = 28 21:07:46 [INFO] train episode 29330: reward = -57.22, steps = 20 21:07:49 [INFO] train episode 29331: reward = -61.37, steps = 36 21:07:52 [INFO] train episode 29332: reward = -60.84, steps = 33 21:07:54 [INFO] train episode 29333: reward = -77.17, steps = 18 21:07:57 [INFO] train episode 29334: reward = -89.11, steps = 32 21:08:00 [INFO] train episode 29335: reward = -85.61, steps = 33 21:08:02 [INFO] train episode 29336: reward = -77.74, steps = 19 21:08:03 [INFO] train episode 29337: reward = -53.39, steps = 19 21:08:07 [INFO] train episode 29338: reward = -62.77, steps = 36 21:08:11 [INFO] train episode 29339: reward = -87.22, steps = 43 21:08:14 [INFO] train episode 29340: reward = -38.61, steps = 33 21:08:16 [INFO] train episode 29341: reward = -64.60, steps = 23 21:08:19 [INFO] train episode 29342: reward = -65.43, steps = 34 21:08:24 [INFO] train episode 29343: reward = -107.57, steps = 57 21:08:27 [INFO] train episode 29344: reward = -53.18, steps = 25 21:08:29 [INFO] train episode 29345: reward = -53.16, steps = 34 21:08:32 [INFO] train episode 29346: reward = -69.33, steps = 30 21:08:34 [INFO] train episode 29347: reward = -83.68, steps = 26 21:08:36 [INFO] train episode 29348: reward = -55.45, steps = 19 21:08:39 [INFO] train episode 29349: reward = -102.70, steps = 29 21:08:42 [INFO] train episode 29350: reward = -110.84, steps = 31 21:08:44 [INFO] train episode 29351: reward = -53.58, steps = 20 21:08:46 [INFO] train episode 29352: reward = -79.77, steps = 21 21:08:49 [INFO] train episode 29353: reward = -78.62, steps = 29 21:08:50 [INFO] train episode 29354: reward = -68.93, steps = 19 21:08:53 [INFO] train episode 29355: reward = -63.12, steps = 24 21:08:54 [INFO] train episode 29356: reward = -52.76, steps = 21 21:08:56 [INFO] train episode 29357: reward = -42.95, steps = 19 21:08:58 [INFO] train episode 29358: reward = -67.11, steps = 21 21:09:01 [INFO] train episode 29359: reward = -66.81, steps = 24 21:09:03 [INFO] train episode 29360: reward = -80.42, steps = 29 21:09:05 [INFO] train episode 29361: reward = -84.19, steps = 23 21:09:07 [INFO] train episode 29362: reward = -40.84, steps = 25 21:09:10 [INFO] train episode 29363: reward = -82.01, steps = 25 21:09:13 [INFO] train episode 29364: reward = -64.87, steps = 34 21:09:15 [INFO] train episode 29365: reward = -87.22, steps = 24 21:09:19 [INFO] train episode 29366: reward = -91.55, steps = 37 21:09:21 [INFO] train episode 29367: reward = -60.50, steps = 22 21:09:22 [INFO] train episode 29368: reward = -65.85, steps = 20 21:09:25 [INFO] train episode 29369: reward = -94.94, steps = 24 21:09:27 [INFO] train episode 29370: reward = -79.15, steps = 24 21:09:28 [INFO] train episode 29371: reward = -56.33, steps = 19 21:09:30 [INFO] train episode 29372: reward = -70.61, steps = 18 21:09:32 [INFO] train episode 29373: reward = -58.73, steps = 19 21:09:34 [INFO] train episode 29374: reward = -120.45, steps = 22 21:09:37 [INFO] train episode 29375: reward = -78.08, steps = 32 21:09:40 [INFO] train episode 29376: reward = -72.80, steps = 35 21:09:42 [INFO] train episode 29377: reward = -73.71, steps = 23 21:09:44 [INFO] train episode 29378: reward = -51.73, steps = 24 21:09:46 [INFO] train episode 29379: reward = -54.78, steps = 24 21:09:48 [INFO] train episode 29380: reward = -110.95, steps = 21 21:09:51 [INFO] train episode 29381: reward = -91.66, steps = 27 21:09:56 [INFO] train episode 29382: reward = -98.35, steps = 55 21:09:58 [INFO] train episode 29383: reward = -77.06, steps = 28 21:10:01 [INFO] train episode 29384: reward = -84.78, steps = 27 21:10:03 [INFO] train episode 29385: reward = -65.78, steps = 23 21:10:05 [INFO] train episode 29386: reward = -41.42, steps = 22 21:10:09 [INFO] train episode 29387: reward = -96.85, steps = 36 21:10:11 [INFO] train episode 29388: reward = -101.96, steps = 21 21:10:13 [INFO] train episode 29389: reward = -71.13, steps = 25 21:10:15 [INFO] train episode 29390: reward = -111.71, steps = 23 21:10:17 [INFO] train episode 29391: reward = -47.89, steps = 21 21:10:19 [INFO] train episode 29392: reward = -46.29, steps = 27 21:10:22 [INFO] train episode 29393: reward = -64.82, steps = 29 21:10:24 [INFO] train episode 29394: reward = -116.07, steps = 20 21:10:27 [INFO] train episode 29395: reward = -83.72, steps = 31 21:10:28 [INFO] train episode 29396: reward = -74.45, steps = 20 21:10:30 [INFO] train episode 29397: reward = -67.56, steps = 20 21:10:33 [INFO] train episode 29398: reward = -63.56, steps = 30 21:10:35 [INFO] train episode 29399: reward = -72.37, steps = 25 21:10:37 [INFO] train episode 29400: reward = -95.13, steps = 19 21:10:39 [INFO] train episode 29401: reward = -87.55, steps = 24 21:10:41 [INFO] train episode 29402: reward = -81.03, steps = 24 21:10:44 [INFO] train episode 29403: reward = -94.11, steps = 33 21:10:48 [INFO] train episode 29404: reward = -57.55, steps = 40 21:10:51 [INFO] train episode 29405: reward = -88.24, steps = 38 21:10:54 [INFO] train episode 29406: reward = -79.89, steps = 25 21:10:58 [INFO] train episode 29407: reward = -78.80, steps = 39 21:10:59 [INFO] train episode 29408: reward = -40.12, steps = 20 21:11:02 [INFO] train episode 29409: reward = -65.73, steps = 23 21:11:03 [INFO] train episode 29410: reward = -79.83, steps = 20 21:11:06 [INFO] train episode 29411: reward = -79.82, steps = 28 21:11:08 [INFO] train episode 29412: reward = -52.20, steps = 20 21:11:10 [INFO] train episode 29413: reward = -57.22, steps = 30 21:11:13 [INFO] train episode 29414: reward = -85.03, steps = 24 21:11:16 [INFO] train episode 29415: reward = -72.35, steps = 40 21:11:18 [INFO] train episode 29416: reward = -85.99, steps = 19 21:11:20 [INFO] train episode 29417: reward = -50.31, steps = 27 21:11:23 [INFO] train episode 29418: reward = -73.13, steps = 30 21:11:26 [INFO] train episode 29419: reward = -81.96, steps = 32 21:11:29 [INFO] train episode 29420: reward = -71.74, steps = 28 21:11:31 [INFO] train episode 29421: reward = -87.49, steps = 21 21:11:32 [INFO] train episode 29422: reward = -80.20, steps = 17 21:11:36 [INFO] train episode 29423: reward = -108.24, steps = 44 21:11:38 [INFO] train episode 29424: reward = -42.98, steps = 26 21:11:42 [INFO] train episode 29425: reward = -73.82, steps = 41 21:11:46 [INFO] train episode 29426: reward = -60.11, steps = 37 21:11:48 [INFO] train episode 29427: reward = -86.87, steps = 26 21:11:50 [INFO] train episode 29428: reward = -46.22, steps = 20 21:11:52 [INFO] train episode 29429: reward = -52.96, steps = 20 21:11:53 [INFO] train episode 29430: reward = -82.35, steps = 19 21:11:57 [INFO] train episode 29431: reward = -98.67, steps = 40 21:11:59 [INFO] train episode 29432: reward = -76.66, steps = 21 21:12:02 [INFO] train episode 29433: reward = -51.94, steps = 34 21:12:05 [INFO] train episode 29434: reward = -83.94, steps = 32 21:12:08 [INFO] train episode 29435: reward = -60.99, steps = 38 21:12:11 [INFO] train episode 29436: reward = -57.48, steps = 26 21:12:12 [INFO] train episode 29437: reward = -70.01, steps = 20 21:12:15 [INFO] train episode 29438: reward = -86.44, steps = 24 21:12:16 [INFO] train episode 29439: reward = -96.10, steps = 20 21:12:20 [INFO] train episode 29440: reward = -71.08, steps = 36 21:12:24 [INFO] train episode 29441: reward = -66.69, steps = 46 21:12:26 [INFO] train episode 29442: reward = -81.42, steps = 24 21:12:28 [INFO] train episode 29443: reward = -52.29, steps = 19 21:12:30 [INFO] train episode 29444: reward = -68.86, steps = 25 21:12:32 [INFO] train episode 29445: reward = -64.96, steps = 18 21:12:34 [INFO] train episode 29446: reward = -49.40, steps = 27 21:12:37 [INFO] train episode 29447: reward = -66.04, steps = 31 21:12:39 [INFO] train episode 29448: reward = -49.04, steps = 19 21:12:41 [INFO] train episode 29449: reward = -28.55, steps = 29 21:12:43 [INFO] train episode 29450: reward = -102.29, steps = 17 21:12:45 [INFO] train episode 29451: reward = -163.94, steps = 20 21:12:47 [INFO] train episode 29452: reward = -59.37, steps = 26 21:12:49 [INFO] train episode 29453: reward = -65.93, steps = 22 21:12:52 [INFO] train episode 29454: reward = -70.01, steps = 22 21:12:54 [INFO] train episode 29455: reward = -65.08, steps = 24 21:12:56 [INFO] train episode 29456: reward = -68.17, steps = 26 21:12:59 [INFO] train episode 29457: reward = -61.98, steps = 26 21:13:05 [INFO] train episode 29458: reward = -140.71, steps = 70 21:13:08 [INFO] train episode 29459: reward = -57.02, steps = 20 21:13:10 [INFO] train episode 29460: reward = -72.81, steps = 21 21:13:12 [INFO] train episode 29461: reward = -73.97, steps = 25 21:13:14 [INFO] train episode 29462: reward = -84.44, steps = 27 21:13:16 [INFO] train episode 29463: reward = -44.12, steps = 19 21:13:19 [INFO] train episode 29464: reward = -101.19, steps = 39 21:13:22 [INFO] train episode 29465: reward = -78.18, steps = 28 21:13:25 [INFO] train episode 29466: reward = -64.12, steps = 25 21:13:26 [INFO] train episode 29467: reward = -58.34, steps = 18 21:13:28 [INFO] train episode 29468: reward = -40.79, steps = 21 21:13:30 [INFO] train episode 29469: reward = -59.37, steps = 21 21:13:32 [INFO] train episode 29470: reward = -61.17, steps = 29 21:13:35 [INFO] train episode 29471: reward = -64.64, steps = 24 21:13:36 [INFO] train episode 29472: reward = -81.09, steps = 20 21:13:40 [INFO] train episode 29473: reward = -71.72, steps = 38 21:13:42 [INFO] train episode 29474: reward = -88.69, steps = 21 21:13:45 [INFO] train episode 29475: reward = -50.09, steps = 31 21:13:47 [INFO] train episode 29476: reward = -55.67, steps = 23 21:13:49 [INFO] train episode 29477: reward = -55.55, steps = 20 21:13:51 [INFO] train episode 29478: reward = -40.42, steps = 30 21:13:53 [INFO] train episode 29479: reward = -51.37, steps = 20 21:13:55 [INFO] train episode 29480: reward = -66.33, steps = 22 21:13:58 [INFO] train episode 29481: reward = -82.81, steps = 31 21:14:01 [INFO] train episode 29482: reward = -83.84, steps = 29 21:14:03 [INFO] train episode 29483: reward = -53.44, steps = 25 21:14:06 [INFO] train episode 29484: reward = -80.33, steps = 30 21:14:09 [INFO] train episode 29485: reward = -95.25, steps = 40 21:14:13 [INFO] train episode 29486: reward = -76.89, steps = 38 21:14:15 [INFO] train episode 29487: reward = -67.56, steps = 29 21:14:17 [INFO] train episode 29488: reward = -70.51, steps = 24 21:14:19 [INFO] train episode 29489: reward = -63.95, steps = 18 21:14:22 [INFO] train episode 29490: reward = -76.43, steps = 30 21:14:24 [INFO] train episode 29491: reward = -54.32, steps = 25 21:14:25 [INFO] train episode 29492: reward = -59.12, steps = 18 21:14:27 [INFO] train episode 29493: reward = -97.76, steps = 20 21:14:29 [INFO] train episode 29494: reward = -76.80, steps = 21 21:14:31 [INFO] train episode 29495: reward = -167.14, steps = 20 21:14:33 [INFO] train episode 29496: reward = -66.79, steps = 20 21:14:35 [INFO] train episode 29497: reward = -62.10, steps = 22 21:14:39 [INFO] train episode 29498: reward = -64.18, steps = 48 21:14:43 [INFO] train episode 29499: reward = -45.63, steps = 44 21:14:47 [INFO] train episode 29500: reward = -54.02, steps = 46 21:14:50 [INFO] train episode 29501: reward = -82.93, steps = 27 21:14:53 [INFO] train episode 29502: reward = -67.77, steps = 31 21:14:54 [INFO] train episode 29503: reward = -56.82, steps = 20 21:14:58 [INFO] train episode 29504: reward = -68.31, steps = 47 21:15:00 [INFO] train episode 29505: reward = -69.33, steps = 24 21:15:04 [INFO] train episode 29506: reward = -77.07, steps = 31 21:15:07 [INFO] train episode 29507: reward = -143.46, steps = 37 21:15:09 [INFO] train episode 29508: reward = -105.12, steps = 27 21:15:11 [INFO] train episode 29509: reward = -58.03, steps = 21 21:15:13 [INFO] train episode 29510: reward = -60.15, steps = 24 21:15:16 [INFO] train episode 29511: reward = -113.03, steps = 31 21:15:18 [INFO] train episode 29512: reward = -43.62, steps = 22 21:15:23 [INFO] train episode 29513: reward = -54.21, steps = 49 21:15:25 [INFO] train episode 29514: reward = -65.20, steps = 29 21:15:27 [INFO] train episode 29515: reward = -80.13, steps = 20 21:15:29 [INFO] train episode 29516: reward = -64.14, steps = 25 21:15:32 [INFO] train episode 29517: reward = -68.28, steps = 30 21:15:36 [INFO] train episode 29518: reward = -85.99, steps = 41 21:15:38 [INFO] train episode 29519: reward = -75.10, steps = 29 21:15:41 [INFO] train episode 29520: reward = -55.37, steps = 23 21:15:43 [INFO] train episode 29521: reward = -72.86, steps = 25 21:15:45 [INFO] train episode 29522: reward = -46.33, steps = 26 21:15:48 [INFO] train episode 29523: reward = -63.89, steps = 28 21:15:50 [INFO] train episode 29524: reward = -46.22, steps = 24 21:15:52 [INFO] train episode 29525: reward = -49.55, steps = 20 21:15:54 [INFO] train episode 29526: reward = -56.97, steps = 21 21:15:57 [INFO] train episode 29527: reward = -62.05, steps = 31 21:16:01 [INFO] train episode 29528: reward = -40.13, steps = 45 21:16:05 [INFO] train episode 29529: reward = -70.36, steps = 33 21:16:09 [INFO] train episode 29530: reward = -61.77, steps = 40 21:16:10 [INFO] train episode 29531: reward = -38.59, steps = 21 21:16:13 [INFO] train episode 29532: reward = -83.27, steps = 27 21:16:16 [INFO] train episode 29533: reward = -44.05, steps = 33 21:16:20 [INFO] train episode 29534: reward = -91.59, steps = 46 21:16:22 [INFO] train episode 29535: reward = -43.86, steps = 27 21:16:25 [INFO] train episode 29536: reward = -113.59, steps = 28 21:16:28 [INFO] train episode 29537: reward = -89.22, steps = 24 21:16:31 [INFO] train episode 29538: reward = -51.35, steps = 44 21:16:34 [INFO] train episode 29539: reward = -60.35, steps = 24 21:16:36 [INFO] train episode 29540: reward = -61.96, steps = 24 21:16:39 [INFO] train episode 29541: reward = -78.15, steps = 35 21:16:41 [INFO] train episode 29542: reward = -44.54, steps = 24 21:16:45 [INFO] train episode 29543: reward = -59.87, steps = 35 21:16:47 [INFO] train episode 29544: reward = -71.32, steps = 32 21:16:51 [INFO] train episode 29545: reward = -112.27, steps = 45 21:16:54 [INFO] train episode 29546: reward = -89.77, steps = 24 21:16:57 [INFO] train episode 29547: reward = -74.93, steps = 42 21:17:00 [INFO] train episode 29548: reward = -56.63, steps = 20 21:17:03 [INFO] train episode 29549: reward = -50.89, steps = 43 21:17:05 [INFO] train episode 29550: reward = -50.09, steps = 20 21:17:07 [INFO] train episode 29551: reward = -126.25, steps = 19 21:17:09 [INFO] train episode 29552: reward = -77.31, steps = 24 21:17:11 [INFO] train episode 29553: reward = -57.89, steps = 19 21:17:14 [INFO] train episode 29554: reward = -53.23, steps = 30 21:17:16 [INFO] train episode 29555: reward = -73.24, steps = 24 21:17:19 [INFO] train episode 29556: reward = -100.15, steps = 36 21:17:22 [INFO] train episode 29557: reward = -74.39, steps = 33 21:17:25 [INFO] train episode 29558: reward = -52.18, steps = 28 21:17:26 [INFO] train episode 29559: reward = -79.39, steps = 20 21:17:30 [INFO] train episode 29560: reward = -51.46, steps = 42 21:17:32 [INFO] train episode 29561: reward = -51.32, steps = 21 21:17:35 [INFO] train episode 29562: reward = -37.89, steps = 29 21:17:37 [INFO] train episode 29563: reward = -36.64, steps = 24 21:17:39 [INFO] train episode 29564: reward = -65.83, steps = 24 21:17:43 [INFO] train episode 29565: reward = -58.18, steps = 40 21:17:46 [INFO] train episode 29566: reward = -49.05, steps = 33 21:17:48 [INFO] train episode 29567: reward = -83.69, steps = 23 21:17:50 [INFO] train episode 29568: reward = -63.53, steps = 25 21:17:53 [INFO] train episode 29569: reward = -58.77, steps = 35 21:17:55 [INFO] train episode 29570: reward = -76.19, steps = 22 21:17:57 [INFO] train episode 29571: reward = -91.26, steps = 20 21:17:59 [INFO] train episode 29572: reward = -77.46, steps = 26 21:18:01 [INFO] train episode 29573: reward = -48.67, steps = 20 21:18:03 [INFO] train episode 29574: reward = -82.06, steps = 20 21:18:05 [INFO] train episode 29575: reward = -42.74, steps = 23 21:18:07 [INFO] train episode 29576: reward = -122.44, steps = 22 21:18:10 [INFO] train episode 29577: reward = -107.07, steps = 35 21:18:14 [INFO] train episode 29578: reward = -61.98, steps = 45 21:18:16 [INFO] train episode 29579: reward = -91.08, steps = 25 21:18:19 [INFO] train episode 29580: reward = -106.03, steps = 28 21:18:22 [INFO] train episode 29581: reward = -58.70, steps = 31 21:18:24 [INFO] train episode 29582: reward = -40.06, steps = 25 21:18:27 [INFO] train episode 29583: reward = -57.96, steps = 34 21:18:29 [INFO] train episode 29584: reward = -65.03, steps = 28 21:18:32 [INFO] train episode 29585: reward = -60.01, steps = 31 21:18:34 [INFO] train episode 29586: reward = -37.53, steps = 22 21:18:38 [INFO] train episode 29587: reward = -83.16, steps = 42 21:18:40 [INFO] train episode 29588: reward = -79.05, steps = 25 21:18:42 [INFO] train episode 29589: reward = -83.41, steps = 19 21:18:45 [INFO] train episode 29590: reward = -96.65, steps = 34 21:18:49 [INFO] train episode 29591: reward = -72.51, steps = 48 21:18:51 [INFO] train episode 29592: reward = -62.33, steps = 21 21:18:55 [INFO] train episode 29593: reward = -62.99, steps = 41 21:18:58 [INFO] train episode 29594: reward = -56.50, steps = 31 21:19:01 [INFO] train episode 29595: reward = -53.62, steps = 34 21:19:04 [INFO] train episode 29596: reward = -39.23, steps = 29 21:19:08 [INFO] train episode 29597: reward = -147.83, steps = 47 21:19:11 [INFO] train episode 29598: reward = -84.61, steps = 30 21:19:13 [INFO] train episode 29599: reward = -82.26, steps = 30 21:19:15 [INFO] train episode 29600: reward = -87.84, steps = 20 21:19:18 [INFO] train episode 29601: reward = -67.04, steps = 27 21:19:19 [INFO] train episode 29602: reward = -63.33, steps = 20 21:19:22 [INFO] train episode 29603: reward = -56.91, steps = 27 21:19:24 [INFO] train episode 29604: reward = -69.83, steps = 21 21:19:26 [INFO] train episode 29605: reward = -75.20, steps = 23 21:19:30 [INFO] train episode 29606: reward = -72.88, steps = 40 21:19:31 [INFO] train episode 29607: reward = -65.51, steps = 19 21:19:33 [INFO] train episode 29608: reward = -47.04, steps = 22 21:19:35 [INFO] train episode 29609: reward = -126.95, steps = 20 21:19:38 [INFO] train episode 29610: reward = -63.88, steps = 31 21:19:40 [INFO] train episode 29611: reward = -78.44, steps = 29 21:19:43 [INFO] train episode 29612: reward = -88.00, steps = 29 21:19:45 [INFO] train episode 29613: reward = -200.60, steps = 19 21:19:47 [INFO] train episode 29614: reward = -68.80, steps = 28 21:19:49 [INFO] train episode 29615: reward = -64.12, steps = 20 21:19:51 [INFO] train episode 29616: reward = -62.61, steps = 18 21:19:52 [INFO] train episode 29617: reward = -57.62, steps = 19 21:19:55 [INFO] train episode 29618: reward = -80.88, steps = 33 21:19:58 [INFO] train episode 29619: reward = -42.78, steps = 24 21:19:59 [INFO] train episode 29620: reward = -81.61, steps = 19 21:20:03 [INFO] train episode 29621: reward = -36.39, steps = 40 21:20:07 [INFO] train episode 29622: reward = -63.74, steps = 41 21:20:09 [INFO] train episode 29623: reward = -94.29, steps = 24 21:20:12 [INFO] train episode 29624: reward = -69.67, steps = 27 21:20:13 [INFO] train episode 29625: reward = -74.41, steps = 21 21:20:17 [INFO] train episode 29626: reward = -40.93, steps = 36 21:20:20 [INFO] train episode 29627: reward = -127.76, steps = 33 21:20:23 [INFO] train episode 29628: reward = -50.62, steps = 35 21:20:25 [INFO] train episode 29629: reward = -59.65, steps = 21 21:20:28 [INFO] train episode 29630: reward = -60.75, steps = 39 21:20:33 [INFO] train episode 29631: reward = -73.18, steps = 50 21:20:37 [INFO] train episode 29632: reward = -107.25, steps = 41 21:20:39 [INFO] train episode 29633: reward = -63.10, steps = 22 21:20:40 [INFO] train episode 29634: reward = -62.03, steps = 18 21:20:42 [INFO] train episode 29635: reward = -62.71, steps = 18 21:20:45 [INFO] train episode 29636: reward = -99.11, steps = 27 21:20:48 [INFO] train episode 29637: reward = -62.52, steps = 34 21:20:51 [INFO] train episode 29638: reward = -69.69, steps = 40 21:20:55 [INFO] train episode 29639: reward = -67.58, steps = 33 21:20:57 [INFO] train episode 29640: reward = -59.21, steps = 26 21:21:00 [INFO] train episode 29641: reward = -57.85, steps = 27 21:21:03 [INFO] train episode 29642: reward = -73.09, steps = 30 21:21:07 [INFO] train episode 29643: reward = -78.81, steps = 34 21:21:11 [INFO] train episode 29644: reward = -71.21, steps = 43 21:21:14 [INFO] train episode 29645: reward = -58.41, steps = 35 21:21:17 [INFO] train episode 29646: reward = -75.91, steps = 33 21:21:20 [INFO] train episode 29647: reward = -101.23, steps = 25 21:21:22 [INFO] train episode 29648: reward = -63.24, steps = 30 21:21:25 [INFO] train episode 29649: reward = -59.83, steps = 22 21:21:28 [INFO] train episode 29650: reward = -78.70, steps = 34 21:21:31 [INFO] train episode 29651: reward = -85.40, steps = 45 21:21:34 [INFO] train episode 29652: reward = -79.19, steps = 33 21:21:37 [INFO] train episode 29653: reward = -47.15, steps = 26 21:21:39 [INFO] train episode 29654: reward = -57.11, steps = 29 21:21:44 [INFO] train episode 29655: reward = -130.36, steps = 52 21:21:47 [INFO] train episode 29656: reward = -43.90, steps = 36 21:21:51 [INFO] train episode 29657: reward = -64.20, steps = 40 21:21:53 [INFO] train episode 29658: reward = -74.33, steps = 25 21:21:54 [INFO] train episode 29659: reward = -65.96, steps = 19 21:21:57 [INFO] train episode 29660: reward = -54.54, steps = 25 21:22:01 [INFO] train episode 29661: reward = -82.54, steps = 41 21:22:04 [INFO] train episode 29662: reward = -73.76, steps = 27 21:22:06 [INFO] train episode 29663: reward = -105.17, steps = 25 21:22:08 [INFO] train episode 29664: reward = -58.49, steps = 28 21:22:11 [INFO] train episode 29665: reward = -88.11, steps = 29 21:22:14 [INFO] train episode 29666: reward = -53.65, steps = 25 21:22:16 [INFO] train episode 29667: reward = -85.42, steps = 21 21:22:18 [INFO] train episode 29668: reward = -65.24, steps = 28 21:22:20 [INFO] train episode 29669: reward = -63.82, steps = 26 21:22:22 [INFO] train episode 29670: reward = -91.85, steps = 22 21:22:25 [INFO] train episode 29671: reward = -48.67, steps = 28 21:22:27 [INFO] train episode 29672: reward = -80.82, steps = 23 21:22:30 [INFO] train episode 29673: reward = -39.48, steps = 32 21:22:32 [INFO] train episode 29674: reward = -58.33, steps = 20 21:22:34 [INFO] train episode 29675: reward = -95.03, steps = 21 21:22:36 [INFO] train episode 29676: reward = -68.37, steps = 25 21:22:40 [INFO] train episode 29677: reward = -88.52, steps = 41 21:22:43 [INFO] train episode 29678: reward = -54.22, steps = 32 21:22:44 [INFO] train episode 29679: reward = -139.39, steps = 19 21:22:47 [INFO] train episode 29680: reward = -28.76, steps = 28 21:22:49 [INFO] train episode 29681: reward = -44.42, steps = 19 21:22:51 [INFO] train episode 29682: reward = -68.85, steps = 19 21:22:53 [INFO] train episode 29683: reward = -81.93, steps = 26 21:22:55 [INFO] train episode 29684: reward = -68.58, steps = 24 21:22:58 [INFO] train episode 29685: reward = -134.88, steps = 34 21:23:00 [INFO] train episode 29686: reward = -77.68, steps = 20 21:23:02 [INFO] train episode 29687: reward = -72.13, steps = 23 21:23:06 [INFO] train episode 29688: reward = -76.50, steps = 39 21:23:10 [INFO] train episode 29689: reward = -82.83, steps = 47 21:23:11 [INFO] train episode 29690: reward = -56.34, steps = 17 21:23:13 [INFO] train episode 29691: reward = -77.17, steps = 24 21:23:16 [INFO] train episode 29692: reward = -131.52, steps = 26 21:23:18 [INFO] train episode 29693: reward = -51.15, steps = 24 21:23:20 [INFO] train episode 29694: reward = -56.49, steps = 21 21:23:22 [INFO] train episode 29695: reward = -81.75, steps = 27 21:23:25 [INFO] train episode 29696: reward = -85.54, steps = 27 21:23:27 [INFO] train episode 29697: reward = -90.96, steps = 28 21:23:29 [INFO] train episode 29698: reward = -57.08, steps = 20 21:23:31 [INFO] train episode 29699: reward = -75.84, steps = 26 21:23:34 [INFO] train episode 29700: reward = -83.66, steps = 27 21:23:37 [INFO] train episode 29701: reward = -82.43, steps = 31 21:23:40 [INFO] train episode 29702: reward = -54.33, steps = 35 21:23:42 [INFO] train episode 29703: reward = -96.48, steps = 22 21:23:44 [INFO] train episode 29704: reward = -65.37, steps = 25 21:23:47 [INFO] train episode 29705: reward = -88.63, steps = 39 21:23:49 [INFO] train episode 29706: reward = -47.00, steps = 24 21:23:53 [INFO] train episode 29707: reward = -90.19, steps = 32 21:23:55 [INFO] train episode 29708: reward = -74.11, steps = 30 21:23:59 [INFO] train episode 29709: reward = -105.34, steps = 37 21:24:00 [INFO] train episode 29710: reward = -79.69, steps = 20 21:24:02 [INFO] train episode 29711: reward = -71.39, steps = 19 21:24:04 [INFO] train episode 29712: reward = -43.98, steps = 19 21:24:06 [INFO] train episode 29713: reward = -56.34, steps = 22 21:24:10 [INFO] train episode 29714: reward = -108.40, steps = 44 21:24:12 [INFO] train episode 29715: reward = -75.75, steps = 24 21:24:15 [INFO] train episode 29716: reward = -97.80, steps = 31 21:24:17 [INFO] train episode 29717: reward = -64.19, steps = 26 21:24:19 [INFO] train episode 29718: reward = -84.12, steps = 19 21:24:20 [INFO] train episode 29719: reward = -57.58, steps = 19 21:24:22 [INFO] train episode 29720: reward = -81.44, steps = 21 21:24:24 [INFO] train episode 29721: reward = -76.26, steps = 19 21:24:26 [INFO] train episode 29722: reward = -105.22, steps = 25 21:24:29 [INFO] train episode 29723: reward = -36.68, steps = 33 21:24:31 [INFO] train episode 29724: reward = -66.91, steps = 22 21:24:34 [INFO] train episode 29725: reward = -60.19, steps = 30 21:24:36 [INFO] train episode 29726: reward = -50.59, steps = 24 21:24:39 [INFO] train episode 29727: reward = -78.86, steps = 30 21:24:42 [INFO] train episode 29728: reward = -44.28, steps = 28 21:24:44 [INFO] train episode 29729: reward = -72.20, steps = 29 21:24:47 [INFO] train episode 29730: reward = -80.68, steps = 25 21:24:49 [INFO] train episode 29731: reward = -54.09, steps = 21 21:24:51 [INFO] train episode 29732: reward = -75.29, steps = 26 21:24:54 [INFO] train episode 29733: reward = -89.59, steps = 36 21:24:58 [INFO] train episode 29734: reward = -69.02, steps = 32 21:25:00 [INFO] train episode 29735: reward = -48.82, steps = 26 21:25:03 [INFO] train episode 29736: reward = -38.66, steps = 29 21:25:05 [INFO] train episode 29737: reward = -57.09, steps = 27 21:25:07 [INFO] train episode 29738: reward = -112.69, steps = 19 21:25:10 [INFO] train episode 29739: reward = -101.71, steps = 36 21:25:13 [INFO] train episode 29740: reward = -94.50, steps = 32 21:25:15 [INFO] train episode 29741: reward = -57.41, steps = 20 21:25:18 [INFO] train episode 29742: reward = -65.08, steps = 27 21:25:20 [INFO] train episode 29743: reward = -69.60, steps = 28 21:25:22 [INFO] train episode 29744: reward = -46.68, steps = 22 21:25:25 [INFO] train episode 29745: reward = -60.41, steps = 29 21:25:28 [INFO] train episode 29746: reward = -122.43, steps = 45 21:25:32 [INFO] train episode 29747: reward = -61.76, steps = 34 21:25:34 [INFO] train episode 29748: reward = -62.62, steps = 20 21:25:36 [INFO] train episode 29749: reward = -20.21, steps = 24 21:25:38 [INFO] train episode 29750: reward = -52.19, steps = 20 21:25:39 [INFO] train episode 29751: reward = -42.20, steps = 21 21:25:42 [INFO] train episode 29752: reward = -89.75, steps = 28 21:25:44 [INFO] train episode 29753: reward = -50.94, steps = 27 21:25:47 [INFO] train episode 29754: reward = -102.46, steps = 26 21:25:49 [INFO] train episode 29755: reward = -99.58, steps = 21 21:25:51 [INFO] train episode 29756: reward = -56.93, steps = 18 21:25:53 [INFO] train episode 29757: reward = -59.79, steps = 24 21:25:56 [INFO] train episode 29758: reward = -54.13, steps = 35 21:25:58 [INFO] train episode 29759: reward = -94.71, steps = 22 21:26:00 [INFO] train episode 29760: reward = -50.56, steps = 23 21:26:03 [INFO] train episode 29761: reward = -94.72, steps = 38 21:26:06 [INFO] train episode 29762: reward = -45.01, steps = 27 21:26:08 [INFO] train episode 29763: reward = -66.99, steps = 21 21:26:10 [INFO] train episode 29764: reward = -58.95, steps = 21 21:26:11 [INFO] train episode 29765: reward = -58.85, steps = 20 21:26:14 [INFO] train episode 29766: reward = -78.49, steps = 25 21:26:16 [INFO] train episode 29767: reward = -66.35, steps = 23 21:26:18 [INFO] train episode 29768: reward = -50.69, steps = 25 21:26:20 [INFO] train episode 29769: reward = -77.27, steps = 23 21:26:23 [INFO] train episode 29770: reward = -95.32, steps = 26 21:26:24 [INFO] train episode 29771: reward = -68.89, steps = 20 21:26:27 [INFO] train episode 29772: reward = -137.52, steps = 32 21:26:30 [INFO] train episode 29773: reward = -78.30, steps = 29 21:26:33 [INFO] train episode 29774: reward = -68.51, steps = 30 21:26:35 [INFO] train episode 29775: reward = -50.60, steps = 25 21:26:38 [INFO] train episode 29776: reward = -57.13, steps = 32 21:26:41 [INFO] train episode 29777: reward = -83.76, steps = 40 21:26:43 [INFO] train episode 29778: reward = -76.50, steps = 22 21:26:47 [INFO] train episode 29779: reward = -80.23, steps = 43 21:26:50 [INFO] train episode 29780: reward = -54.30, steps = 24 21:26:52 [INFO] train episode 29781: reward = -74.40, steps = 25 21:26:54 [INFO] train episode 29782: reward = -97.91, steps = 19 21:26:56 [INFO] train episode 29783: reward = -79.27, steps = 20 21:26:58 [INFO] train episode 29784: reward = -68.81, steps = 25 21:27:00 [INFO] train episode 29785: reward = -62.47, steps = 20 21:27:02 [INFO] train episode 29786: reward = -60.16, steps = 22 21:27:03 [INFO] train episode 29787: reward = -66.92, steps = 18 21:27:06 [INFO] train episode 29788: reward = -81.46, steps = 27 21:27:07 [INFO] train episode 29789: reward = -65.41, steps = 20 21:27:11 [INFO] train episode 29790: reward = -108.18, steps = 39 21:27:14 [INFO] train episode 29791: reward = -58.98, steps = 31 21:27:16 [INFO] train episode 29792: reward = -61.46, steps = 29 21:27:18 [INFO] train episode 29793: reward = -73.79, steps = 18 21:27:20 [INFO] train episode 29794: reward = -50.39, steps = 25 21:27:23 [INFO] train episode 29795: reward = -94.91, steps = 35 21:27:27 [INFO] train episode 29796: reward = -123.71, steps = 38 21:27:29 [INFO] train episode 29797: reward = -72.84, steps = 18 21:27:31 [INFO] train episode 29798: reward = -51.06, steps = 23 21:27:35 [INFO] train episode 29799: reward = -81.83, steps = 43 21:27:37 [INFO] train episode 29800: reward = -55.26, steps = 32 21:27:41 [INFO] train episode 29801: reward = -48.75, steps = 37 21:27:43 [INFO] train episode 29802: reward = -36.95, steps = 22 21:27:45 [INFO] train episode 29803: reward = -77.19, steps = 23 21:27:47 [INFO] train episode 29804: reward = -109.68, steps = 19 21:27:49 [INFO] train episode 29805: reward = -116.01, steps = 22 21:27:52 [INFO] train episode 29806: reward = -44.82, steps = 37 21:27:57 [INFO] train episode 29807: reward = -40.53, steps = 50 21:28:01 [INFO] train episode 29808: reward = -68.50, steps = 39 21:28:03 [INFO] train episode 29809: reward = -46.00, steps = 24 21:28:05 [INFO] train episode 29810: reward = -44.24, steps = 20 21:28:07 [INFO] train episode 29811: reward = -81.22, steps = 24 21:28:09 [INFO] train episode 29812: reward = -63.11, steps = 25 21:28:11 [INFO] train episode 29813: reward = -83.59, steps = 21 21:28:14 [INFO] train episode 29814: reward = -162.48, steps = 33 21:28:17 [INFO] train episode 29815: reward = -74.54, steps = 36 21:28:19 [INFO] train episode 29816: reward = -72.72, steps = 22 21:28:21 [INFO] train episode 29817: reward = -60.56, steps = 19 21:28:23 [INFO] train episode 29818: reward = -73.73, steps = 28 21:28:25 [INFO] train episode 29819: reward = -65.21, steps = 26 21:28:28 [INFO] train episode 29820: reward = -140.10, steps = 36 21:28:31 [INFO] train episode 29821: reward = -52.67, steps = 24 21:28:34 [INFO] train episode 29822: reward = -71.88, steps = 34 21:28:37 [INFO] train episode 29823: reward = -63.76, steps = 31 21:28:40 [INFO] train episode 29824: reward = -92.82, steps = 34 21:28:43 [INFO] train episode 29825: reward = -67.29, steps = 43 21:28:47 [INFO] train episode 29826: reward = -62.40, steps = 36 21:28:49 [INFO] train episode 29827: reward = -55.46, steps = 20 21:28:51 [INFO] train episode 29828: reward = -49.48, steps = 21 21:28:53 [INFO] train episode 29829: reward = -35.58, steps = 25 21:28:55 [INFO] train episode 29830: reward = -33.80, steps = 20 21:28:57 [INFO] train episode 29831: reward = -51.48, steps = 25 21:28:59 [INFO] train episode 29832: reward = -76.16, steps = 19 21:29:01 [INFO] train episode 29833: reward = -66.01, steps = 19 21:29:03 [INFO] train episode 29834: reward = -66.95, steps = 25 21:29:06 [INFO] train episode 29835: reward = -57.46, steps = 27 21:29:08 [INFO] train episode 29836: reward = -62.54, steps = 26 21:29:10 [INFO] train episode 29837: reward = -67.81, steps = 21 21:29:13 [INFO] train episode 29838: reward = -71.98, steps = 28 21:29:15 [INFO] train episode 29839: reward = -71.97, steps = 29 21:29:18 [INFO] train episode 29840: reward = -73.55, steps = 35 21:29:21 [INFO] train episode 29841: reward = -51.79, steps = 24 21:29:24 [INFO] train episode 29842: reward = -86.65, steps = 33 21:29:26 [INFO] train episode 29843: reward = -74.80, steps = 24 21:29:30 [INFO] train episode 29844: reward = -93.77, steps = 47 21:29:32 [INFO] train episode 29845: reward = -67.44, steps = 23 21:29:35 [INFO] train episode 29846: reward = -71.66, steps = 27 21:29:36 [INFO] train episode 29847: reward = -83.99, steps = 20 21:29:39 [INFO] train episode 29848: reward = -56.33, steps = 29 21:29:42 [INFO] train episode 29849: reward = -104.77, steps = 31 21:29:44 [INFO] train episode 29850: reward = -51.50, steps = 20 21:29:46 [INFO] train episode 29851: reward = -69.10, steps = 21 21:29:49 [INFO] train episode 29852: reward = -70.70, steps = 32 21:29:50 [INFO] train episode 29853: reward = -59.55, steps = 18 21:29:52 [INFO] train episode 29854: reward = -61.10, steps = 20 21:29:55 [INFO] train episode 29855: reward = -61.35, steps = 27 21:29:57 [INFO] train episode 29856: reward = -79.18, steps = 24 21:29:59 [INFO] train episode 29857: reward = -141.19, steps = 25 21:30:01 [INFO] train episode 29858: reward = -41.99, steps = 21 21:30:03 [INFO] train episode 29859: reward = -45.40, steps = 29 21:30:06 [INFO] train episode 29860: reward = -61.25, steps = 29 21:30:10 [INFO] train episode 29861: reward = -74.44, steps = 39 21:30:12 [INFO] train episode 29862: reward = -96.92, steps = 21 21:30:13 [INFO] train episode 29863: reward = -63.19, steps = 20 21:30:15 [INFO] train episode 29864: reward = -113.22, steps = 19 21:30:19 [INFO] train episode 29865: reward = -142.20, steps = 45 21:30:21 [INFO] train episode 29866: reward = -66.40, steps = 26 21:30:26 [INFO] train episode 29867: reward = -38.12, steps = 54 21:30:29 [INFO] train episode 29868: reward = -78.98, steps = 30 21:30:31 [INFO] train episode 29869: reward = -40.93, steps = 20 21:30:33 [INFO] train episode 29870: reward = -66.40, steps = 19 21:30:35 [INFO] train episode 29871: reward = -35.41, steps = 22 21:30:37 [INFO] train episode 29872: reward = -76.85, steps = 26 21:30:39 [INFO] train episode 29873: reward = -77.60, steps = 25 21:30:41 [INFO] train episode 29874: reward = -55.80, steps = 20 21:30:44 [INFO] train episode 29875: reward = -50.71, steps = 25 21:30:46 [INFO] train episode 29876: reward = -52.41, steps = 21 21:30:49 [INFO] train episode 29877: reward = -68.28, steps = 37 21:30:51 [INFO] train episode 29878: reward = -92.78, steps = 26 21:30:54 [INFO] train episode 29879: reward = -68.72, steps = 27 21:30:57 [INFO] train episode 29880: reward = -32.44, steps = 29 21:30:59 [INFO] train episode 29881: reward = -91.71, steps = 22 21:31:02 [INFO] train episode 29882: reward = -61.85, steps = 26 21:31:04 [INFO] train episode 29883: reward = -60.43, steps = 28 21:31:07 [INFO] train episode 29884: reward = -72.33, steps = 27 21:31:09 [INFO] train episode 29885: reward = -77.78, steps = 25 21:31:11 [INFO] train episode 29886: reward = -75.15, steps = 23 21:31:13 [INFO] train episode 29887: reward = -71.46, steps = 18 21:31:15 [INFO] train episode 29888: reward = -32.54, steps = 21 21:31:18 [INFO] train episode 29889: reward = -84.99, steps = 31 21:31:19 [INFO] train episode 29890: reward = -57.08, steps = 21 21:31:22 [INFO] train episode 29891: reward = -44.18, steps = 23 21:31:25 [INFO] train episode 29892: reward = -49.24, steps = 34 21:31:27 [INFO] train episode 29893: reward = -65.87, steps = 19 21:31:29 [INFO] train episode 29894: reward = -76.52, steps = 21 21:31:31 [INFO] train episode 29895: reward = -71.07, steps = 28 21:31:35 [INFO] train episode 29896: reward = -83.08, steps = 30 21:31:36 [INFO] train episode 29897: reward = -69.22, steps = 19 21:31:39 [INFO] train episode 29898: reward = -82.12, steps = 26 21:31:41 [INFO] train episode 29899: reward = -32.85, steps = 26 21:31:44 [INFO] train episode 29900: reward = -73.36, steps = 25 21:31:47 [INFO] train episode 29901: reward = -55.00, steps = 23 21:31:49 [INFO] train episode 29902: reward = -93.28, steps = 18 21:31:51 [INFO] train episode 29903: reward = -75.24, steps = 25 21:31:53 [INFO] train episode 29904: reward = -97.55, steps = 19 21:31:56 [INFO] train episode 29905: reward = -78.99, steps = 27 21:31:58 [INFO] train episode 29906: reward = -48.90, steps = 21 21:32:00 [INFO] train episode 29907: reward = -75.34, steps = 20 21:32:02 [INFO] train episode 29908: reward = -90.38, steps = 19 21:32:04 [INFO] train episode 29909: reward = -61.54, steps = 29 21:32:07 [INFO] train episode 29910: reward = -68.44, steps = 22 21:32:09 [INFO] train episode 29911: reward = -78.59, steps = 25 21:32:12 [INFO] train episode 29912: reward = -66.53, steps = 30 21:32:14 [INFO] train episode 29913: reward = -88.20, steps = 22 21:32:18 [INFO] train episode 29914: reward = -60.90, steps = 34 21:32:21 [INFO] train episode 29915: reward = -44.75, steps = 34 21:32:23 [INFO] train episode 29916: reward = -112.92, steps = 27 21:32:25 [INFO] train episode 29917: reward = -57.21, steps = 19 21:32:30 [INFO] train episode 29918: reward = -89.74, steps = 34 21:32:32 [INFO] train episode 29919: reward = -71.02, steps = 24 21:32:37 [INFO] train episode 29920: reward = -70.46, steps = 48 21:32:39 [INFO] train episode 29921: reward = -69.86, steps = 24 21:32:42 [INFO] train episode 29922: reward = -70.70, steps = 24 21:32:45 [INFO] train episode 29923: reward = -60.63, steps = 28 21:32:48 [INFO] train episode 29924: reward = -34.59, steps = 31 21:32:49 [INFO] train episode 29925: reward = -80.97, steps = 18 21:32:54 [INFO] train episode 29926: reward = -67.58, steps = 50 21:32:56 [INFO] train episode 29927: reward = -61.29, steps = 28 21:33:00 [INFO] train episode 29928: reward = -75.93, steps = 38 21:33:02 [INFO] train episode 29929: reward = -67.82, steps = 20 21:33:05 [INFO] train episode 29930: reward = -59.25, steps = 27 21:33:07 [INFO] train episode 29931: reward = -65.92, steps = 29 21:33:10 [INFO] train episode 29932: reward = -65.89, steps = 27 21:33:13 [INFO] train episode 29933: reward = -82.68, steps = 38 21:33:16 [INFO] train episode 29934: reward = -83.59, steps = 31 21:33:18 [INFO] train episode 29935: reward = -98.58, steps = 20 21:33:21 [INFO] train episode 29936: reward = -76.02, steps = 39 21:33:25 [INFO] train episode 29937: reward = -92.48, steps = 41 21:33:27 [INFO] train episode 29938: reward = -40.11, steps = 22 21:33:29 [INFO] train episode 29939: reward = -81.57, steps = 26 21:33:32 [INFO] train episode 29940: reward = -39.77, steps = 32 21:33:35 [INFO] train episode 29941: reward = -60.37, steps = 30 21:33:37 [INFO] train episode 29942: reward = -63.76, steps = 21 21:33:39 [INFO] train episode 29943: reward = -66.42, steps = 19 21:33:40 [INFO] train episode 29944: reward = -108.53, steps = 20 21:33:44 [INFO] train episode 29945: reward = -107.45, steps = 41 21:33:46 [INFO] train episode 29946: reward = -62.34, steps = 22 21:33:48 [INFO] train episode 29947: reward = -73.39, steps = 26 21:33:50 [INFO] train episode 29948: reward = -53.68, steps = 20 21:33:53 [INFO] train episode 29949: reward = -40.28, steps = 24 21:33:56 [INFO] train episode 29950: reward = -87.21, steps = 42 21:33:58 [INFO] train episode 29951: reward = -69.96, steps = 23 21:34:01 [INFO] train episode 29952: reward = -32.44, steps = 25 21:34:04 [INFO] train episode 29953: reward = -82.10, steps = 24 21:34:06 [INFO] train episode 29954: reward = -65.72, steps = 26 21:34:09 [INFO] train episode 29955: reward = -96.78, steps = 31 21:34:11 [INFO] train episode 29956: reward = -67.89, steps = 25 21:34:13 [INFO] train episode 29957: reward = -90.04, steps = 22 21:34:15 [INFO] train episode 29958: reward = -58.34, steps = 21 21:34:18 [INFO] train episode 29959: reward = -79.11, steps = 30 21:34:24 [INFO] train episode 29960: reward = -194.22, steps = 72 21:34:27 [INFO] train episode 29961: reward = -82.88, steps = 21 21:34:28 [INFO] train episode 29962: reward = -56.10, steps = 19 21:34:31 [INFO] train episode 29963: reward = -69.62, steps = 35 21:34:33 [INFO] train episode 29964: reward = -52.19, steps = 22 21:34:36 [INFO] train episode 29965: reward = -61.66, steps = 23 21:34:38 [INFO] train episode 29966: reward = -67.65, steps = 29 21:34:40 [INFO] train episode 29967: reward = -105.04, steps = 22 21:34:44 [INFO] train episode 29968: reward = -81.08, steps = 39 21:34:47 [INFO] train episode 29969: reward = -89.04, steps = 32 21:34:49 [INFO] train episode 29970: reward = -133.75, steps = 25 21:34:51 [INFO] train episode 29971: reward = -48.47, steps = 24 21:34:53 [INFO] train episode 29972: reward = -61.61, steps = 25 21:34:56 [INFO] train episode 29973: reward = -75.73, steps = 27 21:34:58 [INFO] train episode 29974: reward = -52.49, steps = 20 21:35:00 [INFO] train episode 29975: reward = -65.59, steps = 20 21:35:03 [INFO] train episode 29976: reward = -108.40, steps = 39 21:35:05 [INFO] train episode 29977: reward = -110.27, steps = 21 21:35:08 [INFO] train episode 29978: reward = -62.46, steps = 26 21:35:11 [INFO] train episode 29979: reward = -99.65, steps = 31 21:35:13 [INFO] train episode 29980: reward = -107.35, steps = 25 21:35:16 [INFO] train episode 29981: reward = -87.89, steps = 28 21:35:18 [INFO] train episode 29982: reward = -42.00, steps = 23 21:35:22 [INFO] train episode 29983: reward = -50.56, steps = 42 21:35:25 [INFO] train episode 29984: reward = -93.31, steps = 39 21:35:27 [INFO] train episode 29985: reward = -70.23, steps = 20 21:35:29 [INFO] train episode 29986: reward = -84.41, steps = 29 21:35:31 [INFO] train episode 29987: reward = -47.48, steps = 20 21:35:34 [INFO] train episode 29988: reward = -34.08, steps = 31 21:35:37 [INFO] train episode 29989: reward = -56.21, steps = 24 21:35:38 [INFO] train episode 29990: reward = -63.94, steps = 20 21:35:41 [INFO] train episode 29991: reward = -54.76, steps = 25 21:35:44 [INFO] train episode 29992: reward = -73.03, steps = 34 21:35:46 [INFO] train episode 29993: reward = -62.30, steps = 22 21:35:48 [INFO] train episode 29994: reward = -94.18, steps = 21 21:35:50 [INFO] train episode 29995: reward = -48.04, steps = 20 21:35:52 [INFO] train episode 29996: reward = -112.62, steps = 28 21:35:56 [INFO] train episode 29997: reward = -84.86, steps = 38 21:35:58 [INFO] train episode 29998: reward = -81.36, steps = 30 21:36:01 [INFO] train episode 29999: reward = -74.55, steps = 28 21:36:04 [INFO] train episode 30000: reward = -50.10, steps = 35 21:36:06 [INFO] train episode 30001: reward = -116.11, steps = 21 21:36:08 [INFO] train episode 30002: reward = -66.29, steps = 22 21:36:12 [INFO] train episode 30003: reward = -80.24, steps = 37 21:36:15 [INFO] train episode 30004: reward = -80.45, steps = 41 21:36:18 [INFO] train episode 30005: reward = -57.10, steps = 28 21:36:20 [INFO] train episode 30006: reward = -54.29, steps = 21 21:36:24 [INFO] train episode 30007: reward = -89.76, steps = 50 21:36:27 [INFO] train episode 30008: reward = -90.19, steps = 25 21:36:29 [INFO] train episode 30009: reward = -51.19, steps = 29 21:36:32 [INFO] train episode 30010: reward = -65.97, steps = 35 21:36:35 [INFO] train episode 30011: reward = -83.04, steps = 33 21:36:39 [INFO] train episode 30012: reward = -88.03, steps = 34 21:36:41 [INFO] train episode 30013: reward = -88.85, steps = 27 21:36:43 [INFO] train episode 30014: reward = -33.22, steps = 21 21:36:45 [INFO] train episode 30015: reward = -41.49, steps = 24 21:36:47 [INFO] train episode 30016: reward = -73.43, steps = 19 21:36:50 [INFO] train episode 30017: reward = -90.75, steps = 39 21:36:52 [INFO] train episode 30018: reward = -80.70, steps = 20 21:36:54 [INFO] train episode 30019: reward = -67.93, steps = 19 21:36:56 [INFO] train episode 30020: reward = -92.31, steps = 19 21:36:58 [INFO] train episode 30021: reward = -78.05, steps = 22 21:37:01 [INFO] train episode 30022: reward = -83.40, steps = 28 21:37:04 [INFO] train episode 30023: reward = -104.18, steps = 28 21:37:07 [INFO] train episode 30024: reward = -77.84, steps = 35 21:37:10 [INFO] train episode 30025: reward = -44.72, steps = 33 21:37:12 [INFO] train episode 30026: reward = -85.79, steps = 21 21:37:15 [INFO] train episode 30027: reward = -76.03, steps = 28 21:37:17 [INFO] train episode 30028: reward = -77.93, steps = 25 21:37:19 [INFO] train episode 30029: reward = -61.18, steps = 28 21:37:22 [INFO] train episode 30030: reward = -106.18, steps = 26 21:37:25 [INFO] train episode 30031: reward = -71.85, steps = 32 21:37:27 [INFO] train episode 30032: reward = -41.47, steps = 23 21:37:29 [INFO] train episode 30033: reward = -69.85, steps = 20 21:37:31 [INFO] train episode 30034: reward = -49.40, steps = 20 21:37:34 [INFO] train episode 30035: reward = -64.56, steps = 33 21:37:37 [INFO] train episode 30036: reward = -68.62, steps = 30 21:37:38 [INFO] train episode 30037: reward = -88.17, steps = 19 21:37:42 [INFO] train episode 30038: reward = -65.53, steps = 37 21:37:44 [INFO] train episode 30039: reward = -66.14, steps = 21 21:37:49 [INFO] train episode 30040: reward = -68.76, steps = 51 21:37:51 [INFO] train episode 30041: reward = -64.25, steps = 23 21:37:54 [INFO] train episode 30042: reward = -58.92, steps = 41 21:37:57 [INFO] train episode 30043: reward = -64.88, steps = 33 21:38:01 [INFO] train episode 30044: reward = -58.55, steps = 36 21:38:04 [INFO] train episode 30045: reward = -91.34, steps = 33 21:38:06 [INFO] train episode 30046: reward = -106.20, steps = 19 21:38:08 [INFO] train episode 30047: reward = -70.12, steps = 19 21:38:09 [INFO] train episode 30048: reward = -53.36, steps = 20 21:38:13 [INFO] train episode 30049: reward = -96.99, steps = 42 21:38:16 [INFO] train episode 30050: reward = -22.04, steps = 35 21:38:18 [INFO] train episode 30051: reward = -98.20, steps = 20 21:38:20 [INFO] train episode 30052: reward = -48.88, steps = 20 21:38:22 [INFO] train episode 30053: reward = -60.89, steps = 24 21:38:24 [INFO] train episode 30054: reward = -50.82, steps = 19 21:38:26 [INFO] train episode 30055: reward = -46.94, steps = 20 21:38:28 [INFO] train episode 30056: reward = -78.19, steps = 19 21:38:30 [INFO] train episode 30057: reward = -81.41, steps = 28 21:38:32 [INFO] train episode 30058: reward = -70.49, steps = 20 21:38:34 [INFO] train episode 30059: reward = -59.65, steps = 22 21:38:37 [INFO] train episode 30060: reward = -81.08, steps = 24 21:38:39 [INFO] train episode 30061: reward = -43.70, steps = 25 21:38:41 [INFO] train episode 30062: reward = -37.43, steps = 26 21:38:43 [INFO] train episode 30063: reward = -43.81, steps = 19 21:38:46 [INFO] train episode 30064: reward = -67.97, steps = 35 21:38:48 [INFO] train episode 30065: reward = -66.35, steps = 22 21:38:50 [INFO] train episode 30066: reward = -153.12, steps = 24 21:38:53 [INFO] train episode 30067: reward = -72.48, steps = 21 21:38:55 [INFO] train episode 30068: reward = -66.21, steps = 28 21:38:57 [INFO] train episode 30069: reward = -76.44, steps = 19 21:39:00 [INFO] train episode 30070: reward = -72.34, steps = 33 21:39:02 [INFO] train episode 30071: reward = -74.53, steps = 19 21:39:05 [INFO] train episode 30072: reward = -49.02, steps = 30 21:39:07 [INFO] train episode 30073: reward = -83.36, steps = 32 21:39:10 [INFO] train episode 30074: reward = -156.96, steps = 26 21:39:12 [INFO] train episode 30075: reward = -130.82, steps = 19 21:39:14 [INFO] train episode 30076: reward = -55.30, steps = 21 21:39:18 [INFO] train episode 30077: reward = -105.15, steps = 49 21:39:20 [INFO] train episode 30078: reward = -57.87, steps = 20 21:39:22 [INFO] train episode 30079: reward = -92.37, steps = 27 21:39:25 [INFO] train episode 30080: reward = -39.36, steps = 28 21:39:28 [INFO] train episode 30081: reward = -81.40, steps = 31 21:39:32 [INFO] train episode 30082: reward = -125.72, steps = 42 21:39:34 [INFO] train episode 30083: reward = -85.11, steps = 19 21:39:36 [INFO] train episode 30084: reward = -95.84, steps = 25 21:39:38 [INFO] train episode 30085: reward = -76.74, steps = 20 21:39:42 [INFO] train episode 30086: reward = -84.48, steps = 43 21:39:46 [INFO] train episode 30087: reward = -57.27, steps = 42 21:39:48 [INFO] train episode 30088: reward = -52.82, steps = 33 21:39:51 [INFO] train episode 30089: reward = -53.41, steps = 33 21:39:53 [INFO] train episode 30090: reward = -91.43, steps = 19 21:39:55 [INFO] train episode 30091: reward = -66.97, steps = 18 21:39:58 [INFO] train episode 30092: reward = -67.42, steps = 33 21:40:01 [INFO] train episode 30093: reward = -46.04, steps = 25 21:40:04 [INFO] train episode 30094: reward = -47.10, steps = 30 21:40:06 [INFO] train episode 30095: reward = -42.44, steps = 24 21:40:09 [INFO] train episode 30096: reward = -69.95, steps = 32 21:40:12 [INFO] train episode 30097: reward = -76.05, steps = 30 21:40:13 [INFO] train episode 30098: reward = -59.38, steps = 19 21:40:15 [INFO] train episode 30099: reward = -59.47, steps = 21 21:40:18 [INFO] train episode 30100: reward = -76.27, steps = 19 21:40:21 [INFO] train episode 30101: reward = -107.70, steps = 42 21:40:23 [INFO] train episode 30102: reward = -63.52, steps = 23 21:40:26 [INFO] train episode 30103: reward = -106.57, steps = 26 21:40:27 [INFO] train episode 30104: reward = -72.26, steps = 18 21:40:29 [INFO] train episode 30105: reward = -107.63, steps = 19 21:40:33 [INFO] train episode 30106: reward = -68.79, steps = 43 21:40:35 [INFO] train episode 30107: reward = -51.62, steps = 20 21:40:37 [INFO] train episode 30108: reward = -56.09, steps = 19 21:40:40 [INFO] train episode 30109: reward = -86.04, steps = 31 21:40:43 [INFO] train episode 30110: reward = -111.47, steps = 40 21:40:45 [INFO] train episode 30111: reward = -104.98, steps = 19 21:40:47 [INFO] train episode 30112: reward = -60.98, steps = 21 21:40:51 [INFO] train episode 30113: reward = -80.97, steps = 38 21:40:52 [INFO] train episode 30114: reward = -114.46, steps = 21 21:40:55 [INFO] train episode 30115: reward = -58.86, steps = 27 21:40:57 [INFO] train episode 30116: reward = -104.78, steps = 20 21:40:59 [INFO] train episode 30117: reward = -48.09, steps = 27 21:41:02 [INFO] train episode 30118: reward = -134.62, steps = 35 21:41:04 [INFO] train episode 30119: reward = -119.01, steps = 20 21:41:06 [INFO] train episode 30120: reward = -68.07, steps = 19 21:41:08 [INFO] train episode 30121: reward = -65.26, steps = 26 21:41:12 [INFO] train episode 30122: reward = -40.92, steps = 50 21:41:14 [INFO] train episode 30123: reward = -44.45, steps = 19 21:41:17 [INFO] train episode 30124: reward = -58.76, steps = 31 21:41:20 [INFO] train episode 30125: reward = -140.65, steps = 39 21:41:24 [INFO] train episode 30126: reward = -43.39, steps = 34 21:41:26 [INFO] train episode 30127: reward = -61.80, steps = 28 21:41:28 [INFO] train episode 30128: reward = -53.80, steps = 27 21:41:32 [INFO] train episode 30129: reward = -85.01, steps = 42 21:41:34 [INFO] train episode 30130: reward = -92.36, steps = 22 21:41:36 [INFO] train episode 30131: reward = -45.91, steps = 28 21:41:39 [INFO] train episode 30132: reward = -53.18, steps = 26 21:41:43 [INFO] train episode 30133: reward = -104.30, steps = 44 21:41:45 [INFO] train episode 30134: reward = -41.28, steps = 24 21:41:49 [INFO] train episode 30135: reward = -39.44, steps = 40 21:41:50 [INFO] train episode 30136: reward = -65.03, steps = 19 21:41:53 [INFO] train episode 30137: reward = -78.50, steps = 30 21:41:56 [INFO] train episode 30138: reward = -82.71, steps = 32 21:41:59 [INFO] train episode 30139: reward = -70.24, steps = 29 21:42:03 [INFO] train episode 30140: reward = -109.92, steps = 41 21:42:05 [INFO] train episode 30141: reward = -54.28, steps = 21 21:42:07 [INFO] train episode 30142: reward = -80.86, steps = 30 21:42:09 [INFO] train episode 30143: reward = -88.62, steps = 20 21:42:11 [INFO] train episode 30144: reward = -87.07, steps = 20 21:42:13 [INFO] train episode 30145: reward = -67.14, steps = 23 21:42:15 [INFO] train episode 30146: reward = -94.50, steps = 21 21:42:18 [INFO] train episode 30147: reward = -48.71, steps = 37 21:42:20 [INFO] train episode 30148: reward = -52.16, steps = 20 21:42:24 [INFO] train episode 30149: reward = -82.74, steps = 41 21:42:26 [INFO] train episode 30150: reward = -74.19, steps = 25 21:42:29 [INFO] train episode 30151: reward = -77.49, steps = 28 21:42:32 [INFO] train episode 30152: reward = -119.72, steps = 31 21:42:36 [INFO] train episode 30153: reward = -82.65, steps = 49 21:42:38 [INFO] train episode 30154: reward = -57.89, steps = 20 21:42:40 [INFO] train episode 30155: reward = -60.33, steps = 20 21:42:42 [INFO] train episode 30156: reward = -58.76, steps = 28 21:42:44 [INFO] train episode 30157: reward = -53.54, steps = 17 21:42:46 [INFO] train episode 30158: reward = -46.52, steps = 19 21:42:48 [INFO] train episode 30159: reward = -66.41, steps = 26 21:42:50 [INFO] train episode 30160: reward = -119.45, steps = 21 21:42:53 [INFO] train episode 30161: reward = -48.47, steps = 38 21:42:55 [INFO] train episode 30162: reward = -36.06, steps = 23 21:42:58 [INFO] train episode 30163: reward = -64.35, steps = 24 21:43:00 [INFO] train episode 30164: reward = -77.05, steps = 24 21:43:02 [INFO] train episode 30165: reward = -64.92, steps = 19 21:43:05 [INFO] train episode 30166: reward = -62.00, steps = 23 21:43:07 [INFO] train episode 30167: reward = -36.45, steps = 26 21:43:09 [INFO] train episode 30168: reward = -42.46, steps = 21 21:43:11 [INFO] train episode 30169: reward = -38.03, steps = 23 21:43:12 [INFO] train episode 30170: reward = -85.45, steps = 18 21:43:15 [INFO] train episode 30171: reward = -91.18, steps = 34 21:43:17 [INFO] train episode 30172: reward = -96.09, steps = 21 21:43:21 [INFO] train episode 30173: reward = -49.68, steps = 40 21:43:23 [INFO] train episode 30174: reward = -74.18, steps = 21 21:43:26 [INFO] train episode 30175: reward = -53.27, steps = 41 21:43:28 [INFO] train episode 30176: reward = -60.04, steps = 23 21:43:31 [INFO] train episode 30177: reward = -47.04, steps = 26 21:43:33 [INFO] train episode 30178: reward = -73.26, steps = 26 21:43:37 [INFO] train episode 30179: reward = -124.28, steps = 37 21:43:39 [INFO] train episode 30180: reward = -67.00, steps = 24 21:43:41 [INFO] train episode 30181: reward = -46.23, steps = 30 21:43:44 [INFO] train episode 30182: reward = -78.81, steps = 26 21:43:46 [INFO] train episode 30183: reward = -68.67, steps = 26 21:43:48 [INFO] train episode 30184: reward = -41.71, steps = 27 21:43:51 [INFO] train episode 30185: reward = -85.10, steps = 27 21:43:53 [INFO] train episode 30186: reward = -51.83, steps = 20 21:43:56 [INFO] train episode 30187: reward = -76.02, steps = 36 21:43:58 [INFO] train episode 30188: reward = -57.80, steps = 28 21:44:00 [INFO] train episode 30189: reward = -120.87, steps = 20 21:44:03 [INFO] train episode 30190: reward = -106.49, steps = 28 21:44:05 [INFO] train episode 30191: reward = -77.08, steps = 29 21:44:08 [INFO] train episode 30192: reward = -92.89, steps = 25 21:44:12 [INFO] train episode 30193: reward = -91.95, steps = 50 21:44:15 [INFO] train episode 30194: reward = -55.69, steps = 30 21:44:17 [INFO] train episode 30195: reward = -87.81, steps = 31 21:44:21 [INFO] train episode 30196: reward = -62.64, steps = 37 21:44:24 [INFO] train episode 30197: reward = -75.39, steps = 34 21:44:26 [INFO] train episode 30198: reward = -63.86, steps = 26 21:44:28 [INFO] train episode 30199: reward = -117.88, steps = 19 21:44:30 [INFO] train episode 30200: reward = -69.58, steps = 19 21:44:34 [INFO] train episode 30201: reward = -107.60, steps = 51 21:44:37 [INFO] train episode 30202: reward = -57.48, steps = 27 21:44:38 [INFO] train episode 30203: reward = -78.17, steps = 20 21:44:41 [INFO] train episode 30204: reward = -67.29, steps = 30 21:44:44 [INFO] train episode 30205: reward = -63.02, steps = 24 21:44:47 [INFO] train episode 30206: reward = -71.22, steps = 35 21:44:49 [INFO] train episode 30207: reward = -51.37, steps = 22 21:44:50 [INFO] train episode 30208: reward = -58.44, steps = 20 21:44:52 [INFO] train episode 30209: reward = -89.12, steps = 23 21:44:56 [INFO] train episode 30210: reward = -67.68, steps = 32 21:44:58 [INFO] train episode 30211: reward = -54.78, steps = 23 21:44:59 [INFO] train episode 30212: reward = -65.28, steps = 20 21:45:02 [INFO] train episode 30213: reward = -70.67, steps = 26 21:45:04 [INFO] train episode 30214: reward = -74.43, steps = 27 21:45:08 [INFO] train episode 30215: reward = -82.19, steps = 41 21:45:11 [INFO] train episode 30216: reward = -85.36, steps = 25 21:45:14 [INFO] train episode 30217: reward = -75.61, steps = 20 21:45:17 [INFO] train episode 30218: reward = -61.86, steps = 30 21:45:21 [INFO] train episode 30219: reward = -94.95, steps = 44 21:45:24 [INFO] train episode 30220: reward = -80.66, steps = 40 21:45:26 [INFO] train episode 30221: reward = -66.83, steps = 22 21:45:29 [INFO] train episode 30222: reward = -79.51, steps = 27 21:45:32 [INFO] train episode 30223: reward = -81.17, steps = 27 21:45:35 [INFO] train episode 30224: reward = -93.58, steps = 25 21:45:39 [INFO] train episode 30225: reward = -69.38, steps = 47 21:45:42 [INFO] train episode 30226: reward = -88.19, steps = 33 21:45:45 [INFO] train episode 30227: reward = -71.09, steps = 21 21:45:48 [INFO] train episode 30228: reward = -29.01, steps = 27 21:45:51 [INFO] train episode 30229: reward = -59.51, steps = 21 21:45:54 [INFO] train episode 30230: reward = -65.90, steps = 31 21:45:57 [INFO] train episode 30231: reward = -68.47, steps = 33 21:46:00 [INFO] train episode 30232: reward = -51.88, steps = 23 21:46:03 [INFO] train episode 30233: reward = -67.28, steps = 22 21:46:05 [INFO] train episode 30234: reward = -76.39, steps = 22 21:46:07 [INFO] train episode 30235: reward = -80.54, steps = 27 21:46:10 [INFO] train episode 30236: reward = -50.63, steps = 29 21:46:13 [INFO] train episode 30237: reward = -105.56, steps = 30 21:46:15 [INFO] train episode 30238: reward = -79.65, steps = 20 21:46:18 [INFO] train episode 30239: reward = -74.92, steps = 24 21:46:20 [INFO] train episode 30240: reward = -96.81, steps = 20 21:46:24 [INFO] train episode 30241: reward = -72.98, steps = 40 21:46:26 [INFO] train episode 30242: reward = -63.78, steps = 26 21:46:29 [INFO] train episode 30243: reward = -56.18, steps = 23 21:46:31 [INFO] train episode 30244: reward = -72.83, steps = 20 21:46:35 [INFO] train episode 30245: reward = -72.13, steps = 35 21:46:38 [INFO] train episode 30246: reward = -65.08, steps = 32 21:46:40 [INFO] train episode 30247: reward = -51.51, steps = 27 21:46:42 [INFO] train episode 30248: reward = -75.12, steps = 20 21:46:45 [INFO] train episode 30249: reward = -68.66, steps = 21 21:46:47 [INFO] train episode 30250: reward = -66.04, steps = 19 21:46:50 [INFO] train episode 30251: reward = -74.06, steps = 26 21:46:52 [INFO] train episode 30252: reward = -56.14, steps = 26 21:46:54 [INFO] train episode 30253: reward = -59.97, steps = 20 21:46:57 [INFO] train episode 30254: reward = -64.26, steps = 31 21:47:00 [INFO] train episode 30255: reward = -68.61, steps = 33 21:47:03 [INFO] train episode 30256: reward = -54.43, steps = 24 21:47:05 [INFO] train episode 30257: reward = -59.77, steps = 21 21:47:08 [INFO] train episode 30258: reward = -112.22, steps = 32 21:47:10 [INFO] train episode 30259: reward = -69.22, steps = 19 21:47:12 [INFO] train episode 30260: reward = -59.77, steps = 21 21:47:18 [INFO] train episode 30261: reward = -161.69, steps = 72 21:47:22 [INFO] train episode 30262: reward = -101.11, steps = 37 21:47:24 [INFO] train episode 30263: reward = -64.69, steps = 21 21:47:27 [INFO] train episode 30264: reward = -52.13, steps = 33 21:47:30 [INFO] train episode 30265: reward = -76.93, steps = 39 21:47:32 [INFO] train episode 30266: reward = -69.55, steps = 22 21:47:34 [INFO] train episode 30267: reward = -48.10, steps = 19 21:47:36 [INFO] train episode 30268: reward = -68.03, steps = 19 21:47:41 [INFO] train episode 30269: reward = -63.37, steps = 26 21:47:43 [INFO] train episode 30270: reward = -65.97, steps = 20 21:47:48 [INFO] train episode 30271: reward = -87.45, steps = 38 21:47:50 [INFO] train episode 30272: reward = -58.30, steps = 21 21:47:52 [INFO] train episode 30273: reward = -55.68, steps = 20 21:47:55 [INFO] train episode 30274: reward = -52.35, steps = 24 21:48:00 [INFO] train episode 30275: reward = -71.47, steps = 45 21:48:03 [INFO] train episode 30276: reward = -47.55, steps = 26 21:48:04 [INFO] train episode 30277: reward = -38.77, steps = 19 21:48:06 [INFO] train episode 30278: reward = -58.40, steps = 21 21:48:09 [INFO] train episode 30279: reward = -71.39, steps = 36 21:48:12 [INFO] train episode 30280: reward = -67.40, steps = 32 21:48:15 [INFO] train episode 30281: reward = -51.06, steps = 34 21:48:18 [INFO] train episode 30282: reward = -73.66, steps = 29 21:48:20 [INFO] train episode 30283: reward = -51.94, steps = 20 21:48:22 [INFO] train episode 30284: reward = -60.14, steps = 21 21:48:24 [INFO] train episode 30285: reward = -65.09, steps = 20 21:48:26 [INFO] train episode 30286: reward = -57.82, steps = 25 21:48:28 [INFO] train episode 30287: reward = -55.79, steps = 25 21:48:31 [INFO] train episode 30288: reward = -55.19, steps = 39 21:48:34 [INFO] train episode 30289: reward = -86.57, steps = 29 21:48:38 [INFO] train episode 30290: reward = -58.09, steps = 37 21:48:39 [INFO] train episode 30291: reward = -109.26, steps = 20 21:48:41 [INFO] train episode 30292: reward = -75.46, steps = 21 21:48:44 [INFO] train episode 30293: reward = -80.44, steps = 27 21:48:46 [INFO] train episode 30294: reward = -53.77, steps = 30 21:48:49 [INFO] train episode 30295: reward = -77.27, steps = 30 21:48:51 [INFO] train episode 30296: reward = -70.60, steps = 19 21:48:53 [INFO] train episode 30297: reward = -55.04, steps = 19 21:48:54 [INFO] train episode 30298: reward = -71.20, steps = 20 21:48:57 [INFO] train episode 30299: reward = -90.10, steps = 32 21:48:59 [INFO] train episode 30300: reward = -81.21, steps = 21 21:49:02 [INFO] train episode 30301: reward = -62.07, steps = 27 21:49:06 [INFO] train episode 30302: reward = -107.47, steps = 50 21:49:08 [INFO] train episode 30303: reward = -71.20, steps = 21 21:49:11 [INFO] train episode 30304: reward = -56.78, steps = 27 21:49:13 [INFO] train episode 30305: reward = -44.13, steps = 24 21:49:15 [INFO] train episode 30306: reward = -98.78, steps = 21 21:49:18 [INFO] train episode 30307: reward = -57.85, steps = 34 21:49:20 [INFO] train episode 30308: reward = -91.01, steps = 23 21:49:23 [INFO] train episode 30309: reward = -52.93, steps = 25 21:49:26 [INFO] train episode 30310: reward = -66.99, steps = 28 21:49:28 [INFO] train episode 30311: reward = -66.53, steps = 25 21:49:31 [INFO] train episode 30312: reward = -106.14, steps = 37 21:49:33 [INFO] train episode 30313: reward = -47.28, steps = 26 21:49:37 [INFO] train episode 30314: reward = -49.03, steps = 46 21:49:40 [INFO] train episode 30315: reward = -85.11, steps = 23 21:49:42 [INFO] train episode 30316: reward = -63.34, steps = 20 21:49:45 [INFO] train episode 30317: reward = -70.07, steps = 34 21:49:46 [INFO] train episode 30318: reward = -30.54, steps = 19 21:49:48 [INFO] train episode 30319: reward = -57.38, steps = 23 21:49:51 [INFO] train episode 30320: reward = -61.61, steps = 24 21:49:53 [INFO] train episode 30321: reward = -70.34, steps = 33 21:49:56 [INFO] train episode 30322: reward = -52.36, steps = 29 21:49:59 [INFO] train episode 30323: reward = -88.92, steps = 25 21:50:02 [INFO] train episode 30324: reward = -54.84, steps = 44 21:50:05 [INFO] train episode 30325: reward = -50.22, steps = 32 21:50:08 [INFO] train episode 30326: reward = -110.85, steps = 36 21:50:11 [INFO] train episode 30327: reward = -105.00, steps = 35 21:50:14 [INFO] train episode 30328: reward = -87.98, steps = 25 21:50:17 [INFO] train episode 30329: reward = -73.00, steps = 34 21:50:19 [INFO] train episode 30330: reward = -109.91, steps = 31 21:50:21 [INFO] train episode 30331: reward = -49.57, steps = 19 21:50:23 [INFO] train episode 30332: reward = -86.81, steps = 24 21:50:26 [INFO] train episode 30333: reward = -84.11, steps = 34 21:50:29 [INFO] train episode 30334: reward = -27.78, steps = 32 21:50:31 [INFO] train episode 30335: reward = -86.11, steps = 22 21:50:34 [INFO] train episode 30336: reward = -86.26, steps = 35 21:50:37 [INFO] train episode 30337: reward = -79.00, steps = 23 21:50:39 [INFO] train episode 30338: reward = -91.60, steps = 26 21:50:41 [INFO] train episode 30339: reward = -64.85, steps = 23 21:50:43 [INFO] train episode 30340: reward = -83.67, steps = 19 21:50:46 [INFO] train episode 30341: reward = -166.46, steps = 41 21:50:50 [INFO] train episode 30342: reward = -85.11, steps = 32 21:50:52 [INFO] train episode 30343: reward = -69.21, steps = 31 21:50:56 [INFO] train episode 30344: reward = -90.43, steps = 43 21:50:59 [INFO] train episode 30345: reward = -88.27, steps = 27 21:51:02 [INFO] train episode 30346: reward = -109.20, steps = 35 21:51:05 [INFO] train episode 30347: reward = -64.22, steps = 27 21:51:07 [INFO] train episode 30348: reward = -64.28, steps = 28 21:51:11 [INFO] train episode 30349: reward = -66.95, steps = 38 21:51:13 [INFO] train episode 30350: reward = -27.43, steps = 26 21:51:16 [INFO] train episode 30351: reward = -134.86, steps = 39 21:51:19 [INFO] train episode 30352: reward = -59.29, steps = 32 21:51:22 [INFO] train episode 30353: reward = -51.63, steps = 31 21:51:24 [INFO] train episode 30354: reward = -46.31, steps = 20 21:51:26 [INFO] train episode 30355: reward = -87.27, steps = 20 21:51:28 [INFO] train episode 30356: reward = -63.42, steps = 28 21:51:30 [INFO] train episode 30357: reward = -68.10, steps = 25 21:51:32 [INFO] train episode 30358: reward = -62.83, steps = 22 21:51:37 [INFO] train episode 30359: reward = -95.71, steps = 53 21:51:40 [INFO] train episode 30360: reward = -81.46, steps = 30 21:51:42 [INFO] train episode 30361: reward = -73.82, steps = 20 21:51:44 [INFO] train episode 30362: reward = -49.39, steps = 18 21:51:46 [INFO] train episode 30363: reward = -56.25, steps = 19 21:51:48 [INFO] train episode 30364: reward = -62.62, steps = 23 21:51:50 [INFO] train episode 30365: reward = -50.07, steps = 21 21:51:54 [INFO] train episode 30366: reward = -85.53, steps = 24 21:51:58 [INFO] train episode 30367: reward = -103.76, steps = 32 21:52:00 [INFO] train episode 30368: reward = -137.15, steps = 31 21:52:04 [INFO] train episode 30369: reward = -67.91, steps = 39 21:52:06 [INFO] train episode 30370: reward = -48.49, steps = 25 21:52:09 [INFO] train episode 30371: reward = -23.19, steps = 34 21:52:12 [INFO] train episode 30372: reward = -39.82, steps = 23 21:52:15 [INFO] train episode 30373: reward = -59.06, steps = 23 21:52:18 [INFO] train episode 30374: reward = -30.48, steps = 30 21:52:20 [INFO] train episode 30375: reward = -71.42, steps = 23 21:52:22 [INFO] train episode 30376: reward = -194.49, steps = 24 21:52:24 [INFO] train episode 30377: reward = -78.31, steps = 22 21:52:26 [INFO] train episode 30378: reward = -61.74, steps = 28 21:52:29 [INFO] train episode 30379: reward = -78.08, steps = 27 21:52:32 [INFO] train episode 30380: reward = -105.35, steps = 25 21:52:35 [INFO] train episode 30381: reward = -38.14, steps = 25 21:52:37 [INFO] train episode 30382: reward = -107.54, steps = 24 21:52:39 [INFO] train episode 30383: reward = -79.61, steps = 20 21:52:41 [INFO] train episode 30384: reward = -109.60, steps = 24 21:52:43 [INFO] train episode 30385: reward = -58.56, steps = 27 21:52:46 [INFO] train episode 30386: reward = -66.66, steps = 27 21:52:49 [INFO] train episode 30387: reward = -106.64, steps = 24 21:52:53 [INFO] train episode 30388: reward = -82.66, steps = 36 21:52:55 [INFO] train episode 30389: reward = -62.08, steps = 19 21:52:57 [INFO] train episode 30390: reward = -68.18, steps = 26 21:52:59 [INFO] train episode 30391: reward = -81.49, steps = 19 21:53:02 [INFO] train episode 30392: reward = -97.20, steps = 29 21:53:04 [INFO] train episode 30393: reward = -90.47, steps = 28 21:53:06 [INFO] train episode 30394: reward = -88.81, steps = 20 21:53:09 [INFO] train episode 30395: reward = -53.65, steps = 29 21:53:11 [INFO] train episode 30396: reward = -246.16, steps = 28 21:53:13 [INFO] train episode 30397: reward = -104.53, steps = 19 21:53:16 [INFO] train episode 30398: reward = -66.84, steps = 30 21:53:17 [INFO] train episode 30399: reward = -52.18, steps = 20 21:53:21 [INFO] train episode 30400: reward = -42.66, steps = 38 21:53:24 [INFO] train episode 30401: reward = -60.20, steps = 26 21:53:27 [INFO] train episode 30402: reward = -64.89, steps = 38 21:53:29 [INFO] train episode 30403: reward = -64.58, steps = 23 21:53:31 [INFO] train episode 30404: reward = -49.89, steps = 23 21:53:33 [INFO] train episode 30405: reward = -58.92, steps = 21 21:53:35 [INFO] train episode 30406: reward = -84.47, steps = 31 21:53:38 [INFO] train episode 30407: reward = -94.61, steps = 26 21:53:40 [INFO] train episode 30408: reward = -44.67, steps = 19 21:53:42 [INFO] train episode 30409: reward = -80.63, steps = 26 21:53:45 [INFO] train episode 30410: reward = -73.02, steps = 30 21:53:47 [INFO] train episode 30411: reward = -57.90, steps = 21 21:53:50 [INFO] train episode 30412: reward = -46.18, steps = 28 21:53:54 [INFO] train episode 30413: reward = -64.46, steps = 36 21:53:59 [INFO] train episode 30414: reward = -101.69, steps = 44 21:54:02 [INFO] train episode 30415: reward = -55.46, steps = 33 21:54:05 [INFO] train episode 30416: reward = -56.70, steps = 30 21:54:08 [INFO] train episode 30417: reward = -61.15, steps = 27 21:54:10 [INFO] train episode 30418: reward = -79.01, steps = 19 21:54:14 [INFO] train episode 30419: reward = -88.07, steps = 38 21:54:20 [INFO] train episode 30420: reward = -113.62, steps = 55 21:54:22 [INFO] train episode 30421: reward = -51.88, steps = 20 21:54:24 [INFO] train episode 30422: reward = -123.47, steps = 27 21:54:27 [INFO] train episode 30423: reward = -93.46, steps = 28 21:54:29 [INFO] train episode 30424: reward = -61.13, steps = 23 21:54:32 [INFO] train episode 30425: reward = -51.44, steps = 31 21:54:35 [INFO] train episode 30426: reward = -60.89, steps = 19 21:54:37 [INFO] train episode 30427: reward = -73.74, steps = 28 21:54:41 [INFO] train episode 30428: reward = -90.28, steps = 41 21:54:43 [INFO] train episode 30429: reward = -62.85, steps = 19 21:54:47 [INFO] train episode 30430: reward = -83.20, steps = 32 21:54:49 [INFO] train episode 30431: reward = -132.71, steps = 28 21:54:52 [INFO] train episode 30432: reward = -69.34, steps = 24 21:54:55 [INFO] train episode 30433: reward = -75.67, steps = 25 21:54:57 [INFO] train episode 30434: reward = -56.65, steps = 20 21:55:00 [INFO] train episode 30435: reward = -62.06, steps = 37 21:55:03 [INFO] train episode 30436: reward = -68.71, steps = 25 21:55:06 [INFO] train episode 30437: reward = -91.64, steps = 38 21:55:08 [INFO] train episode 30438: reward = -88.49, steps = 23 21:55:11 [INFO] train episode 30439: reward = -60.62, steps = 21 21:55:12 [INFO] train episode 30440: reward = -63.48, steps = 20 21:55:17 [INFO] train episode 30441: reward = -110.04, steps = 55 21:55:20 [INFO] train episode 30442: reward = -116.92, steps = 29 21:55:22 [INFO] train episode 30443: reward = -47.20, steps = 20 21:55:26 [INFO] train episode 30444: reward = -167.44, steps = 38 21:55:29 [INFO] train episode 30445: reward = -109.28, steps = 34 21:55:32 [INFO] train episode 30446: reward = -30.37, steps = 32 21:55:34 [INFO] train episode 30447: reward = -60.68, steps = 21 21:55:35 [INFO] train episode 30448: reward = -59.60, steps = 20 21:55:38 [INFO] train episode 30449: reward = -68.01, steps = 29 21:55:40 [INFO] train episode 30450: reward = -77.76, steps = 21 21:55:44 [INFO] train episode 30451: reward = -98.84, steps = 44 21:55:46 [INFO] train episode 30452: reward = -107.68, steps = 28 21:55:49 [INFO] train episode 30453: reward = -77.93, steps = 35 21:55:52 [INFO] train episode 30454: reward = -71.54, steps = 29 21:55:56 [INFO] train episode 30455: reward = -45.09, steps = 49 21:55:59 [INFO] train episode 30456: reward = -84.73, steps = 29 21:56:01 [INFO] train episode 30457: reward = -90.08, steps = 24 21:56:03 [INFO] train episode 30458: reward = -86.80, steps = 22 21:56:06 [INFO] train episode 30459: reward = -50.46, steps = 31 21:56:08 [INFO] train episode 30460: reward = -57.79, steps = 22 21:56:10 [INFO] train episode 30461: reward = -79.42, steps = 33 21:56:12 [INFO] train episode 30462: reward = -80.99, steps = 19 21:56:14 [INFO] train episode 30463: reward = -81.48, steps = 23 21:56:17 [INFO] train episode 30464: reward = -62.16, steps = 26 21:56:20 [INFO] train episode 30465: reward = -119.16, steps = 30 21:56:23 [INFO] train episode 30466: reward = -73.76, steps = 31 21:56:27 [INFO] train episode 30467: reward = -50.39, steps = 35 21:56:31 [INFO] train episode 30468: reward = -104.11, steps = 38 21:56:35 [INFO] train episode 30469: reward = -84.90, steps = 36 21:56:37 [INFO] train episode 30470: reward = -59.78, steps = 24 21:56:40 [INFO] train episode 30471: reward = -98.18, steps = 23 21:56:42 [INFO] train episode 30472: reward = -137.39, steps = 20 21:56:44 [INFO] train episode 30473: reward = -72.64, steps = 20 21:56:47 [INFO] train episode 30474: reward = -63.06, steps = 34 21:56:49 [INFO] train episode 30475: reward = -82.13, steps = 21 21:56:51 [INFO] train episode 30476: reward = -58.17, steps = 21 21:56:54 [INFO] train episode 30477: reward = -69.81, steps = 27 21:56:56 [INFO] train episode 30478: reward = -50.23, steps = 21 21:56:58 [INFO] train episode 30479: reward = -75.23, steps = 19 21:57:00 [INFO] train episode 30480: reward = -60.96, steps = 24 21:57:03 [INFO] train episode 30481: reward = -100.32, steps = 29 21:57:04 [INFO] train episode 30482: reward = -63.31, steps = 21 21:57:07 [INFO] train episode 30483: reward = -82.11, steps = 31 21:57:11 [INFO] train episode 30484: reward = -65.41, steps = 38 21:57:15 [INFO] train episode 30485: reward = -55.64, steps = 41 21:57:17 [INFO] train episode 30486: reward = -90.53, steps = 23 21:57:19 [INFO] train episode 30487: reward = -99.93, steps = 20 21:57:22 [INFO] train episode 30488: reward = -62.26, steps = 21 21:57:24 [INFO] train episode 30489: reward = -57.59, steps = 22 21:57:27 [INFO] train episode 30490: reward = -84.65, steps = 20 21:57:31 [INFO] train episode 30491: reward = -80.76, steps = 32 21:57:33 [INFO] train episode 30492: reward = -62.29, steps = 22 21:57:37 [INFO] train episode 30493: reward = -95.34, steps = 35 21:57:41 [INFO] train episode 30494: reward = -119.66, steps = 37 21:57:44 [INFO] train episode 30495: reward = -109.00, steps = 31 21:57:47 [INFO] train episode 30496: reward = -63.91, steps = 36 21:57:50 [INFO] train episode 30497: reward = -74.88, steps = 20 21:57:52 [INFO] train episode 30498: reward = -107.12, steps = 28 21:57:55 [INFO] train episode 30499: reward = -40.07, steps = 32 21:57:58 [INFO] train episode 30500: reward = -89.16, steps = 27 21:58:00 [INFO] train episode 30501: reward = -49.56, steps = 19 21:58:02 [INFO] train episode 30502: reward = -54.78, steps = 22 21:58:06 [INFO] train episode 30503: reward = -83.89, steps = 40 21:58:08 [INFO] train episode 30504: reward = -50.41, steps = 20 21:58:11 [INFO] train episode 30505: reward = -93.80, steps = 21 21:58:14 [INFO] train episode 30506: reward = -69.67, steps = 32 21:58:16 [INFO] train episode 30507: reward = -46.18, steps = 22 21:58:19 [INFO] train episode 30508: reward = -67.15, steps = 26 21:58:21 [INFO] train episode 30509: reward = -76.58, steps = 22 21:58:24 [INFO] train episode 30510: reward = -50.25, steps = 23 21:58:28 [INFO] train episode 30511: reward = -123.70, steps = 37 21:58:30 [INFO] train episode 30512: reward = -44.17, steps = 23 21:58:33 [INFO] train episode 30513: reward = -51.24, steps = 25 21:58:36 [INFO] train episode 30514: reward = -88.57, steps = 32 21:58:38 [INFO] train episode 30515: reward = -92.06, steps = 19 21:58:41 [INFO] train episode 30516: reward = -67.18, steps = 33 21:58:45 [INFO] train episode 30517: reward = -147.03, steps = 33 21:58:48 [INFO] train episode 30518: reward = -111.82, steps = 40 21:58:50 [INFO] train episode 30519: reward = -66.19, steps = 19 21:58:53 [INFO] train episode 30520: reward = -77.48, steps = 30 21:58:55 [INFO] train episode 30521: reward = -89.61, steps = 20 21:58:58 [INFO] train episode 30522: reward = -149.94, steps = 33 21:59:02 [INFO] train episode 30523: reward = -66.57, steps = 36 21:59:05 [INFO] train episode 30524: reward = -56.00, steps = 27 21:59:07 [INFO] train episode 30525: reward = -105.36, steps = 22 21:59:09 [INFO] train episode 30526: reward = -90.89, steps = 26 21:59:11 [INFO] train episode 30527: reward = -91.62, steps = 20 21:59:13 [INFO] train episode 30528: reward = -88.74, steps = 23 21:59:17 [INFO] train episode 30529: reward = -49.79, steps = 44 21:59:20 [INFO] train episode 30530: reward = -54.52, steps = 29 21:59:21 [INFO] train episode 30531: reward = -104.80, steps = 21 21:59:23 [INFO] train episode 30532: reward = -67.74, steps = 20 21:59:25 [INFO] train episode 30533: reward = -94.79, steps = 24 21:59:27 [INFO] train episode 30534: reward = -61.70, steps = 21 21:59:30 [INFO] train episode 30535: reward = -186.02, steps = 28 21:59:31 [INFO] train episode 30536: reward = -60.21, steps = 20 21:59:34 [INFO] train episode 30537: reward = -52.26, steps = 27 21:59:37 [INFO] train episode 30538: reward = -44.88, steps = 32 21:59:40 [INFO] train episode 30539: reward = -87.79, steps = 33 21:59:42 [INFO] train episode 30540: reward = -40.91, steps = 21 21:59:44 [INFO] train episode 30541: reward = -62.54, steps = 20 21:59:47 [INFO] train episode 30542: reward = -84.67, steps = 36 21:59:48 [INFO] train episode 30543: reward = -82.42, steps = 19 21:59:51 [INFO] train episode 30544: reward = -64.34, steps = 25 21:59:54 [INFO] train episode 30545: reward = -101.38, steps = 35 21:59:56 [INFO] train episode 30546: reward = -82.25, steps = 22 21:59:59 [INFO] train episode 30547: reward = -78.62, steps = 36 22:00:03 [INFO] train episode 30548: reward = -164.69, steps = 46 22:00:05 [INFO] train episode 30549: reward = -39.12, steps = 27 22:00:08 [INFO] train episode 30550: reward = -68.90, steps = 26 22:00:10 [INFO] train episode 30551: reward = -54.07, steps = 19 22:00:12 [INFO] train episode 30552: reward = -74.91, steps = 25 22:00:14 [INFO] train episode 30553: reward = -96.08, steps = 19 22:00:15 [INFO] train episode 30554: reward = -51.65, steps = 20 22:00:18 [INFO] train episode 30555: reward = -67.15, steps = 28 22:00:20 [INFO] train episode 30556: reward = -38.79, steps = 23 22:00:22 [INFO] train episode 30557: reward = -77.72, steps = 20 22:00:24 [INFO] train episode 30558: reward = -58.41, steps = 23 22:00:27 [INFO] train episode 30559: reward = -78.25, steps = 31 22:00:29 [INFO] train episode 30560: reward = -50.76, steps = 27 22:00:32 [INFO] train episode 30561: reward = -64.37, steps = 30 22:00:34 [INFO] train episode 30562: reward = -90.73, steps = 21 22:00:35 [INFO] train episode 30563: reward = -66.83, steps = 21 22:00:38 [INFO] train episode 30564: reward = -75.94, steps = 29 22:00:41 [INFO] train episode 30565: reward = -98.17, steps = 35 22:00:44 [INFO] train episode 30566: reward = -71.22, steps = 32 22:00:47 [INFO] train episode 30567: reward = -89.02, steps = 31 22:00:49 [INFO] train episode 30568: reward = -86.63, steps = 27 22:00:51 [INFO] train episode 30569: reward = -74.84, steps = 25 22:00:54 [INFO] train episode 30570: reward = -88.38, steps = 23 22:00:56 [INFO] train episode 30571: reward = -104.37, steps = 26 22:00:59 [INFO] train episode 30572: reward = -133.55, steps = 32 22:01:01 [INFO] train episode 30573: reward = -47.29, steps = 27 22:01:03 [INFO] train episode 30574: reward = -70.99, steps = 20 22:01:05 [INFO] train episode 30575: reward = -59.35, steps = 20 22:01:07 [INFO] train episode 30576: reward = -60.71, steps = 25 22:01:10 [INFO] train episode 30577: reward = -54.05, steps = 30 22:01:12 [INFO] train episode 30578: reward = -64.45, steps = 19 22:01:15 [INFO] train episode 30579: reward = -95.79, steps = 38 22:01:18 [INFO] train episode 30580: reward = -109.94, steps = 28 22:01:20 [INFO] train episode 30581: reward = -76.07, steps = 27 22:01:24 [INFO] train episode 30582: reward = -92.96, steps = 39 22:01:25 [INFO] train episode 30583: reward = -128.30, steps = 20 22:01:28 [INFO] train episode 30584: reward = -85.81, steps = 27 22:01:32 [INFO] train episode 30585: reward = -62.92, steps = 33 22:01:34 [INFO] train episode 30586: reward = -75.77, steps = 27 22:01:37 [INFO] train episode 30587: reward = -94.85, steps = 31 22:01:40 [INFO] train episode 30588: reward = -96.63, steps = 41 22:01:43 [INFO] train episode 30589: reward = -110.63, steps = 25 22:01:45 [INFO] train episode 30590: reward = -90.21, steps = 22 22:01:48 [INFO] train episode 30591: reward = -61.26, steps = 36 22:01:51 [INFO] train episode 30592: reward = -46.75, steps = 30 22:01:52 [INFO] train episode 30593: reward = -70.36, steps = 20 22:01:54 [INFO] train episode 30594: reward = -36.79, steps = 19 22:01:56 [INFO] train episode 30595: reward = -89.13, steps = 25 22:01:59 [INFO] train episode 30596: reward = -80.99, steps = 32 22:02:01 [INFO] train episode 30597: reward = -56.43, steps = 20 22:02:03 [INFO] train episode 30598: reward = -115.26, steps = 24 22:02:05 [INFO] train episode 30599: reward = -49.83, steps = 19 22:02:07 [INFO] train episode 30600: reward = -86.73, steps = 19 22:02:08 [INFO] train episode 30601: reward = -70.30, steps = 18 22:02:11 [INFO] train episode 30602: reward = -83.29, steps = 27 22:02:13 [INFO] train episode 30603: reward = -59.95, steps = 20 22:02:14 [INFO] train episode 30604: reward = -63.17, steps = 18 22:02:17 [INFO] train episode 30605: reward = -92.46, steps = 22 22:02:20 [INFO] train episode 30606: reward = -160.68, steps = 36 22:02:23 [INFO] train episode 30607: reward = -104.26, steps = 19 22:02:26 [INFO] train episode 30608: reward = -46.17, steps = 28 22:02:28 [INFO] train episode 30609: reward = -105.59, steps = 20 22:02:31 [INFO] train episode 30610: reward = -86.14, steps = 29 22:02:35 [INFO] train episode 30611: reward = -149.71, steps = 32 22:02:38 [INFO] train episode 30612: reward = -93.29, steps = 27 22:02:41 [INFO] train episode 30613: reward = -124.64, steps = 20 22:02:44 [INFO] train episode 30614: reward = -128.45, steps = 37 22:02:50 [INFO] train episode 30615: reward = -79.93, steps = 43 22:02:52 [INFO] train episode 30616: reward = -99.32, steps = 20 22:02:54 [INFO] train episode 30617: reward = -38.47, steps = 25 22:02:56 [INFO] train episode 30618: reward = -69.69, steps = 18 22:02:59 [INFO] train episode 30619: reward = -76.42, steps = 22 22:03:01 [INFO] train episode 30620: reward = -58.03, steps = 22 22:03:05 [INFO] train episode 30621: reward = -87.18, steps = 34 22:03:09 [INFO] train episode 30622: reward = -65.45, steps = 45 22:03:12 [INFO] train episode 30623: reward = -104.35, steps = 26 22:03:15 [INFO] train episode 30624: reward = -61.52, steps = 34 22:03:17 [INFO] train episode 30625: reward = -56.75, steps = 19 22:03:21 [INFO] train episode 30626: reward = -86.75, steps = 37 22:03:23 [INFO] train episode 30627: reward = -68.61, steps = 29 22:03:26 [INFO] train episode 30628: reward = -58.06, steps = 31 22:03:28 [INFO] train episode 30629: reward = -90.59, steps = 20 22:03:30 [INFO] train episode 30630: reward = -86.62, steps = 20 22:03:36 [INFO] train episode 30631: reward = -189.23, steps = 48 22:03:38 [INFO] train episode 30632: reward = -54.10, steps = 22 22:03:41 [INFO] train episode 30633: reward = -75.55, steps = 34 22:03:45 [INFO] train episode 30634: reward = -69.51, steps = 36 22:03:47 [INFO] train episode 30635: reward = -63.05, steps = 26 22:03:49 [INFO] train episode 30636: reward = -76.30, steps = 23 22:03:52 [INFO] train episode 30637: reward = -126.80, steps = 24 22:03:56 [INFO] train episode 30638: reward = -56.29, steps = 31 22:03:58 [INFO] train episode 30639: reward = -98.98, steps = 28 22:04:01 [INFO] train episode 30640: reward = -86.81, steps = 28 22:04:05 [INFO] train episode 30641: reward = -49.97, steps = 38 22:04:09 [INFO] train episode 30642: reward = -126.02, steps = 36 22:04:11 [INFO] train episode 30643: reward = -87.74, steps = 26 22:04:15 [INFO] train episode 30644: reward = -75.71, steps = 40 22:04:18 [INFO] train episode 30645: reward = -92.82, steps = 29 22:04:21 [INFO] train episode 30646: reward = -84.59, steps = 28 22:04:23 [INFO] train episode 30647: reward = -60.95, steps = 21 22:04:25 [INFO] train episode 30648: reward = -62.10, steps = 24 22:04:28 [INFO] train episode 30649: reward = -53.64, steps = 23 22:04:31 [INFO] train episode 30650: reward = -81.75, steps = 28 22:04:33 [INFO] train episode 30651: reward = -33.78, steps = 29 22:04:36 [INFO] train episode 30652: reward = -41.78, steps = 31 22:04:38 [INFO] train episode 30653: reward = -89.47, steps = 19 22:04:42 [INFO] train episode 30654: reward = -124.73, steps = 42 22:04:44 [INFO] train episode 30655: reward = -95.99, steps = 20 22:04:49 [INFO] train episode 30656: reward = -63.88, steps = 35 22:04:51 [INFO] train episode 30657: reward = -53.66, steps = 24 22:04:53 [INFO] train episode 30658: reward = -82.66, steps = 24 22:04:55 [INFO] train episode 30659: reward = -101.92, steps = 21 22:04:57 [INFO] train episode 30660: reward = -86.28, steps = 18 22:04:59 [INFO] train episode 30661: reward = -63.53, steps = 18 22:05:02 [INFO] train episode 30662: reward = -107.80, steps = 27 22:05:04 [INFO] train episode 30663: reward = -66.20, steps = 18 22:05:06 [INFO] train episode 30664: reward = -46.16, steps = 25 22:05:09 [INFO] train episode 30665: reward = -95.51, steps = 22 22:05:11 [INFO] train episode 30666: reward = -58.91, steps = 26 22:05:13 [INFO] train episode 30667: reward = -75.53, steps = 26 22:05:16 [INFO] train episode 30668: reward = -53.95, steps = 26 22:05:18 [INFO] train episode 30669: reward = -49.67, steps = 33 22:05:21 [INFO] train episode 30670: reward = -84.97, steps = 29 22:05:24 [INFO] train episode 30671: reward = -46.24, steps = 22 22:05:25 [INFO] train episode 30672: reward = -109.30, steps = 18 22:05:27 [INFO] train episode 30673: reward = -96.73, steps = 23 22:05:29 [INFO] train episode 30674: reward = -85.02, steps = 21 22:05:31 [INFO] train episode 30675: reward = -74.33, steps = 18 22:05:34 [INFO] train episode 30676: reward = -91.19, steps = 22 22:05:36 [INFO] train episode 30677: reward = -79.94, steps = 25 22:05:40 [INFO] train episode 30678: reward = -63.51, steps = 35 22:05:44 [INFO] train episode 30679: reward = -54.47, steps = 35 22:05:46 [INFO] train episode 30680: reward = -61.01, steps = 27 22:05:50 [INFO] train episode 30681: reward = -78.81, steps = 40 22:05:54 [INFO] train episode 30682: reward = -69.78, steps = 34 22:05:57 [INFO] train episode 30683: reward = -36.06, steps = 29 22:06:00 [INFO] train episode 30684: reward = -99.23, steps = 27 22:06:02 [INFO] train episode 30685: reward = -79.38, steps = 19 22:06:04 [INFO] train episode 30686: reward = -77.89, steps = 20 22:06:06 [INFO] train episode 30687: reward = -54.24, steps = 20 22:06:10 [INFO] train episode 30688: reward = -86.53, steps = 41 22:06:14 [INFO] train episode 30689: reward = -38.04, steps = 38 22:06:17 [INFO] train episode 30690: reward = -100.17, steps = 35 22:06:21 [INFO] train episode 30691: reward = -98.05, steps = 33 22:06:25 [INFO] train episode 30692: reward = -109.48, steps = 40 22:06:27 [INFO] train episode 30693: reward = -60.91, steps = 17 22:06:30 [INFO] train episode 30694: reward = -100.99, steps = 20 22:06:32 [INFO] train episode 30695: reward = -99.89, steps = 19 22:06:35 [INFO] train episode 30696: reward = -60.70, steps = 30 22:06:39 [INFO] train episode 30697: reward = -94.83, steps = 37 22:06:41 [INFO] train episode 30698: reward = -63.78, steps = 20 22:06:45 [INFO] train episode 30699: reward = -73.78, steps = 36 22:06:49 [INFO] train episode 30700: reward = -59.47, steps = 38 22:06:52 [INFO] train episode 30701: reward = -81.85, steps = 29 22:06:54 [INFO] train episode 30702: reward = -42.91, steps = 22 22:06:57 [INFO] train episode 30703: reward = -57.85, steps = 30 22:07:01 [INFO] train episode 30704: reward = -61.13, steps = 33 22:07:05 [INFO] train episode 30705: reward = -63.95, steps = 40 22:07:07 [INFO] train episode 30706: reward = -76.55, steps = 20 22:07:10 [INFO] train episode 30707: reward = -72.16, steps = 33 22:07:14 [INFO] train episode 30708: reward = -81.84, steps = 43 22:07:18 [INFO] train episode 30709: reward = -146.06, steps = 37 22:07:21 [INFO] train episode 30710: reward = -82.04, steps = 29 22:07:22 [INFO] train episode 30711: reward = -94.53, steps = 13 22:07:26 [INFO] train episode 30712: reward = -71.95, steps = 34 22:07:29 [INFO] train episode 30713: reward = -65.46, steps = 24 22:07:32 [INFO] train episode 30714: reward = -60.95, steps = 21 22:07:36 [INFO] train episode 30715: reward = -56.61, steps = 34 22:07:40 [INFO] train episode 30716: reward = -53.30, steps = 42 22:07:42 [INFO] train episode 30717: reward = -60.55, steps = 19 22:07:45 [INFO] train episode 30718: reward = -73.12, steps = 21 22:07:47 [INFO] train episode 30719: reward = -55.07, steps = 24 22:07:50 [INFO] train episode 30720: reward = -51.88, steps = 35 22:07:52 [INFO] train episode 30721: reward = -64.24, steps = 18 22:07:56 [INFO] train episode 30722: reward = -65.40, steps = 35 22:07:59 [INFO] train episode 30723: reward = -82.40, steps = 32 22:08:02 [INFO] train episode 30724: reward = -65.43, steps = 38 22:08:04 [INFO] train episode 30725: reward = -135.52, steps = 19 22:08:09 [INFO] train episode 30726: reward = -98.97, steps = 37 22:08:11 [INFO] train episode 30727: reward = -60.67, steps = 29 22:08:14 [INFO] train episode 30728: reward = -85.59, steps = 20 22:08:16 [INFO] train episode 30729: reward = -90.88, steps = 19 22:08:19 [INFO] train episode 30730: reward = -144.13, steps = 37 22:08:23 [INFO] train episode 30731: reward = -75.93, steps = 35 22:08:27 [INFO] train episode 30732: reward = -81.35, steps = 44 22:08:29 [INFO] train episode 30733: reward = -79.08, steps = 19 22:08:32 [INFO] train episode 30734: reward = -85.62, steps = 36 22:08:35 [INFO] train episode 30735: reward = -56.54, steps = 26 22:08:38 [INFO] train episode 30736: reward = -59.79, steps = 31 22:08:41 [INFO] train episode 30737: reward = -78.59, steps = 34 22:08:43 [INFO] train episode 30738: reward = -66.86, steps = 19 22:08:45 [INFO] train episode 30739: reward = -53.57, steps = 21 22:08:50 [INFO] train episode 30740: reward = -81.08, steps = 57 22:08:52 [INFO] train episode 30741: reward = -57.95, steps = 20 22:08:55 [INFO] train episode 30742: reward = -134.48, steps = 26 22:08:57 [INFO] train episode 30743: reward = -47.95, steps = 26 22:08:59 [INFO] train episode 30744: reward = -74.63, steps = 24 22:09:02 [INFO] train episode 30745: reward = -67.21, steps = 31 22:09:04 [INFO] train episode 30746: reward = -59.99, steps = 18 22:09:07 [INFO] train episode 30747: reward = -108.89, steps = 20 22:09:10 [INFO] train episode 30748: reward = -42.88, steps = 38 22:09:15 [INFO] train episode 30749: reward = -21.03, steps = 41 22:09:21 [INFO] train episode 30750: reward = -122.67, steps = 49 22:09:23 [INFO] train episode 30751: reward = -58.68, steps = 20 22:09:27 [INFO] train episode 30752: reward = -84.53, steps = 27 22:09:30 [INFO] train episode 30753: reward = -55.90, steps = 19 22:09:33 [INFO] train episode 30754: reward = -69.06, steps = 24 22:09:35 [INFO] train episode 30755: reward = -53.46, steps = 20 22:09:38 [INFO] train episode 30756: reward = -106.28, steps = 26 22:09:45 [INFO] train episode 30757: reward = -60.11, steps = 52 22:09:49 [INFO] train episode 30758: reward = -107.41, steps = 33 22:09:52 [INFO] train episode 30759: reward = -55.46, steps = 24 22:09:55 [INFO] train episode 30760: reward = -55.15, steps = 37 22:09:59 [INFO] train episode 30761: reward = -64.78, steps = 38 22:10:03 [INFO] train episode 30762: reward = -81.63, steps = 35 22:10:05 [INFO] train episode 30763: reward = -68.86, steps = 24 22:10:07 [INFO] train episode 30764: reward = -71.21, steps = 22 22:10:11 [INFO] train episode 30765: reward = -68.05, steps = 30 22:10:13 [INFO] train episode 30766: reward = -61.31, steps = 22 22:10:16 [INFO] train episode 30767: reward = -76.87, steps = 26 22:10:18 [INFO] train episode 30768: reward = -132.34, steps = 27 22:10:21 [INFO] train episode 30769: reward = -54.23, steps = 24 22:10:23 [INFO] train episode 30770: reward = -68.75, steps = 28 22:10:26 [INFO] train episode 30771: reward = -70.38, steps = 22 22:10:30 [INFO] train episode 30772: reward = -74.73, steps = 41 22:10:33 [INFO] train episode 30773: reward = -103.88, steps = 36 22:10:36 [INFO] train episode 30774: reward = -65.99, steps = 35 22:10:38 [INFO] train episode 30775: reward = -109.04, steps = 27 22:10:41 [INFO] train episode 30776: reward = -58.47, steps = 30 22:10:44 [INFO] train episode 30777: reward = -97.04, steps = 24 22:10:46 [INFO] train episode 30778: reward = -62.51, steps = 22 22:10:48 [INFO] train episode 30779: reward = -101.04, steps = 21 22:10:50 [INFO] train episode 30780: reward = -85.46, steps = 22 22:10:54 [INFO] train episode 30781: reward = -122.73, steps = 39 22:10:57 [INFO] train episode 30782: reward = -72.00, steps = 28 22:10:59 [INFO] train episode 30783: reward = -53.63, steps = 30 22:11:02 [INFO] train episode 30784: reward = -77.53, steps = 19 22:11:04 [INFO] train episode 30785: reward = -48.98, steps = 21 22:11:07 [INFO] train episode 30786: reward = -62.18, steps = 37 22:11:09 [INFO] train episode 30787: reward = -66.88, steps = 20 22:11:11 [INFO] train episode 30788: reward = -65.52, steps = 18 22:11:12 [INFO] train episode 30789: reward = -57.06, steps = 19 22:11:15 [INFO] train episode 30790: reward = -70.05, steps = 27 22:11:17 [INFO] train episode 30791: reward = -100.26, steps = 21 22:11:20 [INFO] train episode 30792: reward = -70.81, steps = 31 22:11:24 [INFO] train episode 30793: reward = -79.04, steps = 36 22:11:27 [INFO] train episode 30794: reward = -106.98, steps = 30 22:11:31 [INFO] train episode 30795: reward = -99.45, steps = 34 22:11:34 [INFO] train episode 30796: reward = -114.97, steps = 32 22:11:37 [INFO] train episode 30797: reward = -112.57, steps = 23 22:11:39 [INFO] train episode 30798: reward = -55.57, steps = 19 22:11:41 [INFO] train episode 30799: reward = -45.34, steps = 22 22:11:44 [INFO] train episode 30800: reward = -98.07, steps = 29 22:11:47 [INFO] train episode 30801: reward = -65.40, steps = 33 22:11:49 [INFO] train episode 30802: reward = -81.62, steps = 19 22:11:52 [INFO] train episode 30803: reward = -96.78, steps = 26 22:11:55 [INFO] train episode 30804: reward = -86.56, steps = 21 22:11:58 [INFO] train episode 30805: reward = -49.55, steps = 33 22:12:00 [INFO] train episode 30806: reward = -93.08, steps = 19 22:12:03 [INFO] train episode 30807: reward = -62.79, steps = 21 22:12:06 [INFO] train episode 30808: reward = -77.06, steps = 25 22:12:08 [INFO] train episode 30809: reward = -62.37, steps = 19 22:12:12 [INFO] train episode 30810: reward = -95.91, steps = 41 22:12:16 [INFO] train episode 30811: reward = -78.71, steps = 32 22:12:18 [INFO] train episode 30812: reward = -101.98, steps = 20 22:12:20 [INFO] train episode 30813: reward = -116.32, steps = 19 22:12:23 [INFO] train episode 30814: reward = -89.79, steps = 36 22:12:25 [INFO] train episode 30815: reward = -60.31, steps = 18 22:12:27 [INFO] train episode 30816: reward = -75.90, steps = 23 22:12:32 [INFO] train episode 30817: reward = -91.85, steps = 50 22:12:34 [INFO] train episode 30818: reward = -100.14, steps = 21 22:12:36 [INFO] train episode 30819: reward = -58.32, steps = 21 22:12:39 [INFO] train episode 30820: reward = -73.20, steps = 31 22:12:41 [INFO] train episode 30821: reward = -50.34, steps = 27 22:12:44 [INFO] train episode 30822: reward = -109.87, steps = 37 22:12:47 [INFO] train episode 30823: reward = -54.90, steps = 29 22:12:51 [INFO] train episode 30824: reward = -91.83, steps = 36 22:12:53 [INFO] train episode 30825: reward = -91.66, steps = 24 22:12:57 [INFO] train episode 30826: reward = -72.65, steps = 33 22:12:59 [INFO] train episode 30827: reward = -69.79, steps = 19 22:13:02 [INFO] train episode 30828: reward = -67.26, steps = 34 22:13:06 [INFO] train episode 30829: reward = -30.08, steps = 41 22:13:09 [INFO] train episode 30830: reward = -102.48, steps = 21 22:13:11 [INFO] train episode 30831: reward = -103.35, steps = 23 22:13:16 [INFO] train episode 30832: reward = -194.91, steps = 52 22:13:18 [INFO] train episode 30833: reward = -69.79, steps = 31 22:13:20 [INFO] train episode 30834: reward = -122.39, steps = 20 22:13:22 [INFO] train episode 30835: reward = -92.31, steps = 22 22:13:24 [INFO] train episode 30836: reward = -168.16, steps = 20 22:13:27 [INFO] train episode 30837: reward = -92.49, steps = 29 22:13:29 [INFO] train episode 30838: reward = -79.24, steps = 22 22:13:31 [INFO] train episode 30839: reward = -64.47, steps = 25 22:13:35 [INFO] train episode 30840: reward = -122.85, steps = 51 22:13:37 [INFO] train episode 30841: reward = -109.49, steps = 20 22:13:40 [INFO] train episode 30842: reward = -87.24, steps = 25 22:13:42 [INFO] train episode 30843: reward = -76.97, steps = 24 22:13:44 [INFO] train episode 30844: reward = -86.35, steps = 20 22:13:46 [INFO] train episode 30845: reward = -77.90, steps = 24 22:13:48 [INFO] train episode 30846: reward = -86.63, steps = 25 22:13:51 [INFO] train episode 30847: reward = -110.56, steps = 37 22:13:54 [INFO] train episode 30848: reward = -67.39, steps = 24 22:13:56 [INFO] train episode 30849: reward = -69.18, steps = 25 22:14:00 [INFO] train episode 30850: reward = -60.84, steps = 37 22:14:02 [INFO] train episode 30851: reward = -44.56, steps = 30 22:14:04 [INFO] train episode 30852: reward = -67.82, steps = 23 22:14:07 [INFO] train episode 30853: reward = -51.62, steps = 29 22:14:09 [INFO] train episode 30854: reward = -89.26, steps = 21 22:14:11 [INFO] train episode 30855: reward = -69.65, steps = 27 22:14:15 [INFO] train episode 30856: reward = -78.12, steps = 41 22:14:18 [INFO] train episode 30857: reward = -91.90, steps = 31 22:14:20 [INFO] train episode 30858: reward = -65.92, steps = 20 22:14:22 [INFO] train episode 30859: reward = -55.75, steps = 22 22:14:24 [INFO] train episode 30860: reward = -73.49, steps = 28 22:14:27 [INFO] train episode 30861: reward = -32.56, steps = 31 22:14:30 [INFO] train episode 30862: reward = -59.95, steps = 26 22:14:34 [INFO] train episode 30863: reward = -89.91, steps = 32 22:14:37 [INFO] train episode 30864: reward = -84.87, steps = 25 22:14:41 [INFO] train episode 30865: reward = -91.78, steps = 31 22:14:43 [INFO] train episode 30866: reward = -118.17, steps = 26 22:14:48 [INFO] train episode 30867: reward = -127.45, steps = 44 22:14:51 [INFO] train episode 30868: reward = -103.18, steps = 30 22:14:54 [INFO] train episode 30869: reward = -58.88, steps = 22 22:14:57 [INFO] train episode 30870: reward = -87.53, steps = 36 22:14:59 [INFO] train episode 30871: reward = -67.39, steps = 21 22:15:01 [INFO] train episode 30872: reward = -54.86, steps = 21 22:15:05 [INFO] train episode 30873: reward = -78.65, steps = 38 22:15:07 [INFO] train episode 30874: reward = -98.59, steps = 17 22:15:10 [INFO] train episode 30875: reward = -100.91, steps = 28 22:15:14 [INFO] train episode 30876: reward = -97.58, steps = 37 22:15:16 [INFO] train episode 30877: reward = -57.74, steps = 20 22:15:19 [INFO] train episode 30878: reward = -105.89, steps = 33 22:15:21 [INFO] train episode 30879: reward = -120.18, steps = 20 22:15:24 [INFO] train episode 30880: reward = -48.72, steps = 28 22:15:27 [INFO] train episode 30881: reward = -70.44, steps = 34 22:15:31 [INFO] train episode 30882: reward = -86.99, steps = 38 22:15:35 [INFO] train episode 30883: reward = -85.99, steps = 35 22:15:37 [INFO] train episode 30884: reward = -48.61, steps = 27 22:15:39 [INFO] train episode 30885: reward = -53.69, steps = 21 22:15:41 [INFO] train episode 30886: reward = -69.55, steps = 20 22:15:43 [INFO] train episode 30887: reward = -49.28, steps = 25 22:15:46 [INFO] train episode 30888: reward = -86.31, steps = 25 22:15:49 [INFO] train episode 30889: reward = -47.68, steps = 29 22:15:52 [INFO] train episode 30890: reward = -78.89, steps = 25 22:15:54 [INFO] train episode 30891: reward = -63.80, steps = 21 22:15:57 [INFO] train episode 30892: reward = -99.41, steps = 33 22:15:59 [INFO] train episode 30893: reward = -91.83, steps = 24 22:16:01 [INFO] train episode 30894: reward = -64.49, steps = 19 22:16:04 [INFO] train episode 30895: reward = -128.44, steps = 26 22:16:07 [INFO] train episode 30896: reward = -61.03, steps = 34 22:16:10 [INFO] train episode 30897: reward = -88.94, steps = 39 22:16:14 [INFO] train episode 30898: reward = -78.14, steps = 39 22:16:16 [INFO] train episode 30899: reward = -61.40, steps = 27 22:16:19 [INFO] train episode 30900: reward = -167.01, steps = 21 22:16:22 [INFO] train episode 30901: reward = -80.58, steps = 34 22:16:24 [INFO] train episode 30902: reward = -38.53, steps = 20 22:16:26 [INFO] train episode 30903: reward = -93.44, steps = 22 22:16:29 [INFO] train episode 30904: reward = -102.92, steps = 37 22:16:32 [INFO] train episode 30905: reward = -68.02, steps = 26 22:16:34 [INFO] train episode 30906: reward = -71.46, steps = 30 22:16:37 [INFO] train episode 30907: reward = -34.02, steps = 27 22:16:40 [INFO] train episode 30908: reward = -122.36, steps = 28 22:16:42 [INFO] train episode 30909: reward = -115.83, steps = 25 22:16:45 [INFO] train episode 30910: reward = -71.34, steps = 29 22:16:47 [INFO] train episode 30911: reward = -100.70, steps = 18 22:16:49 [INFO] train episode 30912: reward = -85.45, steps = 22 22:16:51 [INFO] train episode 30913: reward = -92.12, steps = 20 22:16:54 [INFO] train episode 30914: reward = -92.84, steps = 31 22:16:56 [INFO] train episode 30915: reward = -89.84, steps = 23 22:16:59 [INFO] train episode 30916: reward = -68.85, steps = 28 22:17:01 [INFO] train episode 30917: reward = -74.57, steps = 19 22:17:04 [INFO] train episode 30918: reward = -85.90, steps = 35 22:17:08 [INFO] train episode 30919: reward = -48.12, steps = 34 22:17:11 [INFO] train episode 30920: reward = -105.40, steps = 31 22:17:13 [INFO] train episode 30921: reward = -90.47, steps = 20 22:17:16 [INFO] train episode 30922: reward = -53.67, steps = 31 22:17:19 [INFO] train episode 30923: reward = -58.88, steps = 30 22:17:21 [INFO] train episode 30924: reward = -79.03, steps = 22 22:17:23 [INFO] train episode 30925: reward = -52.73, steps = 20 22:17:28 [INFO] train episode 30926: reward = -81.67, steps = 46 22:17:30 [INFO] train episode 30927: reward = -53.36, steps = 22 22:17:33 [INFO] train episode 30928: reward = -47.40, steps = 30 22:17:35 [INFO] train episode 30929: reward = -44.10, steps = 22 22:17:40 [INFO] train episode 30930: reward = -63.74, steps = 44 22:17:44 [INFO] train episode 30931: reward = -96.16, steps = 51 22:17:47 [INFO] train episode 30932: reward = -77.93, steps = 24 22:17:51 [INFO] train episode 30933: reward = -66.94, steps = 31 22:17:53 [INFO] train episode 30934: reward = -90.09, steps = 23 22:17:56 [INFO] train episode 30935: reward = -63.35, steps = 36 22:17:58 [INFO] train episode 30936: reward = -71.08, steps = 20 22:18:01 [INFO] train episode 30937: reward = -88.89, steps = 28 22:18:03 [INFO] train episode 30938: reward = -74.14, steps = 19 22:18:07 [INFO] train episode 30939: reward = -34.24, steps = 34 22:18:11 [INFO] train episode 30940: reward = -61.19, steps = 44 22:18:15 [INFO] train episode 30941: reward = -174.06, steps = 52 22:18:17 [INFO] train episode 30942: reward = -77.50, steps = 24 22:18:21 [INFO] train episode 30943: reward = -104.23, steps = 37 22:18:26 [INFO] train episode 30944: reward = -107.46, steps = 33 22:18:28 [INFO] train episode 30945: reward = -73.36, steps = 23 22:18:30 [INFO] train episode 30946: reward = -59.71, steps = 21 22:18:33 [INFO] train episode 30947: reward = -91.45, steps = 19 22:18:36 [INFO] train episode 30948: reward = -125.77, steps = 36 22:18:38 [INFO] train episode 30949: reward = -53.97, steps = 22 22:18:40 [INFO] train episode 30950: reward = -102.10, steps = 18 22:18:43 [INFO] train episode 30951: reward = -152.23, steps = 31 22:18:45 [INFO] train episode 30952: reward = -95.59, steps = 24 22:18:48 [INFO] train episode 30953: reward = -82.87, steps = 26 22:18:51 [INFO] train episode 30954: reward = -75.41, steps = 33 22:18:53 [INFO] train episode 30955: reward = -69.13, steps = 20 22:18:55 [INFO] train episode 30956: reward = -65.12, steps = 20 22:18:58 [INFO] train episode 30957: reward = -65.21, steps = 39 22:19:01 [INFO] train episode 30958: reward = -63.12, steps = 28 22:19:04 [INFO] train episode 30959: reward = -67.90, steps = 24 22:19:08 [INFO] train episode 30960: reward = -104.51, steps = 36 22:19:10 [INFO] train episode 30961: reward = -65.01, steps = 21 22:19:14 [INFO] train episode 30962: reward = -104.59, steps = 38 22:19:15 [INFO] train episode 30963: reward = -65.23, steps = 18 22:19:20 [INFO] train episode 30964: reward = -94.96, steps = 41 22:19:22 [INFO] train episode 30965: reward = -55.53, steps = 24 22:19:25 [INFO] train episode 30966: reward = -71.09, steps = 25 22:19:28 [INFO] train episode 30967: reward = -87.48, steps = 33 22:19:30 [INFO] train episode 30968: reward = -79.18, steps = 18 22:19:33 [INFO] train episode 30969: reward = -101.11, steps = 38 22:19:35 [INFO] train episode 30970: reward = -140.95, steps = 19 22:19:39 [INFO] train episode 30971: reward = -86.21, steps = 34 22:19:42 [INFO] train episode 30972: reward = -92.64, steps = 32 22:19:45 [INFO] train episode 30973: reward = -75.78, steps = 34 22:19:47 [INFO] train episode 30974: reward = -112.95, steps = 18 22:19:49 [INFO] train episode 30975: reward = -58.77, steps = 27 22:19:53 [INFO] train episode 30976: reward = -116.39, steps = 41 22:19:57 [INFO] train episode 30977: reward = -119.09, steps = 37 22:20:00 [INFO] train episode 30978: reward = -81.50, steps = 34 22:20:03 [INFO] train episode 30979: reward = -28.35, steps = 29 22:20:05 [INFO] train episode 30980: reward = -81.82, steps = 22 22:20:08 [INFO] train episode 30981: reward = -44.76, steps = 31 22:20:10 [INFO] train episode 30982: reward = -55.44, steps = 19 22:20:13 [INFO] train episode 30983: reward = -100.16, steps = 35 22:20:16 [INFO] train episode 30984: reward = -64.92, steps = 33 22:20:20 [INFO] train episode 30985: reward = -85.50, steps = 39 22:20:22 [INFO] train episode 30986: reward = -56.43, steps = 23 22:20:25 [INFO] train episode 30987: reward = -86.04, steps = 28 22:20:27 [INFO] train episode 30988: reward = -67.66, steps = 19 22:20:29 [INFO] train episode 30989: reward = -73.95, steps = 22 22:20:31 [INFO] train episode 30990: reward = -48.94, steps = 19 22:20:34 [INFO] train episode 30991: reward = -70.12, steps = 27 22:20:36 [INFO] train episode 30992: reward = -150.09, steps = 21 22:20:40 [INFO] train episode 30993: reward = -78.15, steps = 43 22:20:42 [INFO] train episode 30994: reward = -42.79, steps = 20 22:20:44 [INFO] train episode 30995: reward = -41.33, steps = 25 22:20:48 [INFO] train episode 30996: reward = -91.24, steps = 43 22:20:52 [INFO] train episode 30997: reward = -68.32, steps = 33 22:20:54 [INFO] train episode 30998: reward = -54.14, steps = 18 22:20:56 [INFO] train episode 30999: reward = -71.86, steps = 25 22:20:59 [INFO] train episode 31000: reward = -89.61, steps = 27 22:21:02 [INFO] train episode 31001: reward = -50.88, steps = 22 22:21:07 [INFO] train episode 31002: reward = -134.42, steps = 38 22:21:09 [INFO] train episode 31003: reward = -73.03, steps = 20 22:21:12 [INFO] train episode 31004: reward = -73.07, steps = 25 22:21:14 [INFO] train episode 31005: reward = -49.35, steps = 19 22:21:19 [INFO] train episode 31006: reward = -74.64, steps = 46 22:21:22 [INFO] train episode 31007: reward = -66.87, steps = 30 22:21:24 [INFO] train episode 31008: reward = -66.98, steps = 23 22:21:27 [INFO] train episode 31009: reward = -124.82, steps = 27 22:21:31 [INFO] train episode 31010: reward = -66.84, steps = 32 22:21:33 [INFO] train episode 31011: reward = -102.20, steps = 27 22:21:36 [INFO] train episode 31012: reward = -49.12, steps = 20 22:21:39 [INFO] train episode 31013: reward = -102.18, steps = 32 22:21:42 [INFO] train episode 31014: reward = -78.32, steps = 34 22:21:44 [INFO] train episode 31015: reward = -102.12, steps = 20 22:21:49 [INFO] train episode 31016: reward = -88.23, steps = 54 22:21:51 [INFO] train episode 31017: reward = -83.65, steps = 23 22:21:54 [INFO] train episode 31018: reward = -55.40, steps = 31 22:21:57 [INFO] train episode 31019: reward = -116.39, steps = 31 22:21:59 [INFO] train episode 31020: reward = -99.21, steps = 20 22:22:01 [INFO] train episode 31021: reward = -87.78, steps = 18 22:22:04 [INFO] train episode 31022: reward = -73.19, steps = 21 22:22:06 [INFO] train episode 31023: reward = -60.08, steps = 22 22:22:09 [INFO] train episode 31024: reward = -68.51, steps = 33 22:22:12 [INFO] train episode 31025: reward = -78.66, steps = 37 22:22:15 [INFO] train episode 31026: reward = -47.84, steps = 32 22:22:18 [INFO] train episode 31027: reward = -73.14, steps = 29 22:22:20 [INFO] train episode 31028: reward = -66.77, steps = 23 22:22:23 [INFO] train episode 31029: reward = -118.75, steps = 24 22:22:25 [INFO] train episode 31030: reward = -51.24, steps = 22 22:22:27 [INFO] train episode 31031: reward = -43.07, steps = 26 22:22:30 [INFO] train episode 31032: reward = -76.69, steps = 24 22:22:32 [INFO] train episode 31033: reward = -76.97, steps = 19 22:22:33 [INFO] train episode 31034: reward = -89.96, steps = 20 22:22:37 [INFO] train episode 31035: reward = -203.28, steps = 37 22:22:41 [INFO] train episode 31036: reward = -59.22, steps = 35 22:22:43 [INFO] train episode 31037: reward = -53.07, steps = 26 22:22:45 [INFO] train episode 31038: reward = -77.54, steps = 19 22:22:47 [INFO] train episode 31039: reward = -70.58, steps = 21 22:22:49 [INFO] train episode 31040: reward = -77.15, steps = 30 22:22:51 [INFO] train episode 31041: reward = -42.76, steps = 18 22:22:54 [INFO] train episode 31042: reward = -83.27, steps = 24 22:22:57 [INFO] train episode 31043: reward = -66.64, steps = 30 22:22:59 [INFO] train episode 31044: reward = -78.69, steps = 19 22:23:02 [INFO] train episode 31045: reward = -47.74, steps = 27 22:23:04 [INFO] train episode 31046: reward = -106.19, steps = 21 22:23:06 [INFO] train episode 31047: reward = -87.58, steps = 23 22:23:09 [INFO] train episode 31048: reward = -60.37, steps = 32 22:23:12 [INFO] train episode 31049: reward = -109.37, steps = 26 22:23:16 [INFO] train episode 31050: reward = -64.78, steps = 36 22:23:18 [INFO] train episode 31051: reward = -155.46, steps = 24 22:23:21 [INFO] train episode 31052: reward = -96.76, steps = 33 22:23:23 [INFO] train episode 31053: reward = -153.50, steps = 24 22:23:26 [INFO] train episode 31054: reward = -74.45, steps = 28 22:23:30 [INFO] train episode 31055: reward = -57.09, steps = 35 22:23:33 [INFO] train episode 31056: reward = -106.59, steps = 28 22:23:35 [INFO] train episode 31057: reward = -88.22, steps = 19 22:23:37 [INFO] train episode 31058: reward = -117.95, steps = 26 22:23:39 [INFO] train episode 31059: reward = -56.28, steps = 20 22:23:41 [INFO] train episode 31060: reward = -79.19, steps = 19 22:23:44 [INFO] train episode 31061: reward = -82.33, steps = 31 22:23:45 [INFO] train episode 31062: reward = -84.71, steps = 20 22:23:49 [INFO] train episode 31063: reward = -88.60, steps = 35 22:23:53 [INFO] train episode 31064: reward = -83.97, steps = 40 22:23:56 [INFO] train episode 31065: reward = -71.41, steps = 23 22:23:58 [INFO] train episode 31066: reward = -52.68, steps = 25 22:24:00 [INFO] train episode 31067: reward = -49.51, steps = 20 22:24:04 [INFO] train episode 31068: reward = -39.77, steps = 40 22:24:06 [INFO] train episode 31069: reward = -69.40, steps = 19 22:24:10 [INFO] train episode 31070: reward = -97.15, steps = 34 22:24:12 [INFO] train episode 31071: reward = -82.26, steps = 30 22:24:14 [INFO] train episode 31072: reward = -99.58, steps = 19 22:24:17 [INFO] train episode 31073: reward = -85.71, steps = 23 22:24:18 [INFO] train episode 31074: reward = -78.13, steps = 20 22:24:21 [INFO] train episode 31075: reward = -102.56, steps = 19 22:24:25 [INFO] train episode 31076: reward = -89.51, steps = 38 22:24:27 [INFO] train episode 31077: reward = -54.00, steps = 21 22:24:31 [INFO] train episode 31078: reward = -78.49, steps = 35 22:24:33 [INFO] train episode 31079: reward = -78.37, steps = 23 22:24:35 [INFO] train episode 31080: reward = -50.86, steps = 28 22:24:37 [INFO] train episode 31081: reward = -80.65, steps = 21 22:24:40 [INFO] train episode 31082: reward = -64.58, steps = 26 22:24:44 [INFO] train episode 31083: reward = -157.61, steps = 45 22:24:48 [INFO] train episode 31084: reward = -96.25, steps = 42 22:24:51 [INFO] train episode 31085: reward = -83.90, steps = 35 22:24:55 [INFO] train episode 31086: reward = -78.69, steps = 35 22:24:57 [INFO] train episode 31087: reward = -70.03, steps = 26 22:24:59 [INFO] train episode 31088: reward = -54.66, steps = 21 22:25:02 [INFO] train episode 31089: reward = -60.47, steps = 22 22:25:05 [INFO] train episode 31090: reward = -75.88, steps = 32 22:25:07 [INFO] train episode 31091: reward = -63.83, steps = 26 22:25:11 [INFO] train episode 31092: reward = -99.40, steps = 39 22:25:13 [INFO] train episode 31093: reward = -65.41, steps = 26 22:25:17 [INFO] train episode 31094: reward = -50.14, steps = 41 22:25:20 [INFO] train episode 31095: reward = -40.00, steps = 21 22:25:25 [INFO] train episode 31096: reward = -128.13, steps = 59 22:25:29 [INFO] train episode 31097: reward = -70.16, steps = 34 22:25:31 [INFO] train episode 31098: reward = -57.94, steps = 23 22:25:33 [INFO] train episode 31099: reward = -65.56, steps = 25 22:25:37 [INFO] train episode 31100: reward = -125.18, steps = 35 22:25:39 [INFO] train episode 31101: reward = -45.97, steps = 21 22:25:41 [INFO] train episode 31102: reward = -93.93, steps = 21 22:25:43 [INFO] train episode 31103: reward = -113.02, steps = 27 22:25:47 [INFO] train episode 31104: reward = -63.41, steps = 40 22:25:49 [INFO] train episode 31105: reward = -84.03, steps = 21 22:25:52 [INFO] train episode 31106: reward = -136.43, steps = 34 22:25:55 [INFO] train episode 31107: reward = -128.11, steps = 27 22:25:57 [INFO] train episode 31108: reward = -58.23, steps = 20 22:26:00 [INFO] train episode 31109: reward = -71.50, steps = 29 22:26:03 [INFO] train episode 31110: reward = -96.35, steps = 38 22:26:05 [INFO] train episode 31111: reward = -67.09, steps = 20 22:26:08 [INFO] train episode 31112: reward = -65.04, steps = 27 22:26:10 [INFO] train episode 31113: reward = -73.99, steps = 20 22:26:14 [INFO] train episode 31114: reward = -79.23, steps = 38 22:26:16 [INFO] train episode 31115: reward = -71.86, steps = 19 22:26:18 [INFO] train episode 31116: reward = -84.89, steps = 24 22:26:20 [INFO] train episode 31117: reward = -109.90, steps = 20 22:26:23 [INFO] train episode 31118: reward = -199.75, steps = 34 22:26:26 [INFO] train episode 31119: reward = -108.61, steps = 31 22:26:30 [INFO] train episode 31120: reward = -31.93, steps = 34 22:26:32 [INFO] train episode 31121: reward = -69.94, steps = 19 22:26:34 [INFO] train episode 31122: reward = -64.94, steps = 20 22:26:36 [INFO] train episode 31123: reward = -88.81, steps = 23 22:26:40 [INFO] train episode 31124: reward = -190.51, steps = 44 22:26:42 [INFO] train episode 31125: reward = -105.13, steps = 24 22:26:44 [INFO] train episode 31126: reward = -46.73, steps = 22 22:26:48 [INFO] train episode 31127: reward = -97.52, steps = 36 22:26:52 [INFO] train episode 31128: reward = -34.45, steps = 36 22:26:53 [INFO] train episode 31129: reward = -85.97, steps = 19 22:26:56 [INFO] train episode 31130: reward = -52.39, steps = 26 22:26:59 [INFO] train episode 31131: reward = -58.73, steps = 26 22:27:01 [INFO] train episode 31132: reward = -107.32, steps = 25 22:27:03 [INFO] train episode 31133: reward = -62.27, steps = 19 22:27:06 [INFO] train episode 31134: reward = -76.74, steps = 27 22:27:08 [INFO] train episode 31135: reward = -80.00, steps = 22 22:27:10 [INFO] train episode 31136: reward = -79.86, steps = 19 22:27:12 [INFO] train episode 31137: reward = -82.28, steps = 21 22:27:15 [INFO] train episode 31138: reward = -87.57, steps = 35 22:27:18 [INFO] train episode 31139: reward = -66.94, steps = 33 22:27:21 [INFO] train episode 31140: reward = -35.95, steps = 28 22:27:25 [INFO] train episode 31141: reward = -103.64, steps = 41 22:27:27 [INFO] train episode 31142: reward = -72.29, steps = 19 22:27:30 [INFO] train episode 31143: reward = -79.41, steps = 30 22:27:34 [INFO] train episode 31144: reward = -71.27, steps = 37 22:27:37 [INFO] train episode 31145: reward = -113.53, steps = 28 22:27:40 [INFO] train episode 31146: reward = -106.31, steps = 35 22:27:42 [INFO] train episode 31147: reward = -75.46, steps = 18 22:27:45 [INFO] train episode 31148: reward = -91.22, steps = 29 22:27:47 [INFO] train episode 31149: reward = -65.16, steps = 19 22:27:49 [INFO] train episode 31150: reward = -140.45, steps = 31 22:27:53 [INFO] train episode 31151: reward = -88.95, steps = 31 22:27:54 [INFO] train episode 31152: reward = -87.49, steps = 19 22:27:58 [INFO] train episode 31153: reward = -96.86, steps = 31 22:28:02 [INFO] train episode 31154: reward = -65.14, steps = 39 22:28:04 [INFO] train episode 31155: reward = -71.47, steps = 25 22:28:06 [INFO] train episode 31156: reward = -46.58, steps = 20 22:28:10 [INFO] train episode 31157: reward = -65.14, steps = 38 22:28:14 [INFO] train episode 31158: reward = -115.71, steps = 42 22:28:18 [INFO] train episode 31159: reward = -63.01, steps = 46 22:28:20 [INFO] train episode 31160: reward = -59.52, steps = 20 22:28:24 [INFO] train episode 31161: reward = -98.21, steps = 38 22:28:26 [INFO] train episode 31162: reward = -82.56, steps = 22 22:28:28 [INFO] train episode 31163: reward = -61.81, steps = 21 22:28:30 [INFO] train episode 31164: reward = -96.24, steps = 19 22:28:32 [INFO] train episode 31165: reward = -81.26, steps = 24 22:28:36 [INFO] train episode 31166: reward = -81.62, steps = 33 22:28:39 [INFO] train episode 31167: reward = -113.85, steps = 30 22:28:42 [INFO] train episode 31168: reward = -160.16, steps = 28 22:28:43 [INFO] train episode 31169: reward = -90.46, steps = 15 22:28:47 [INFO] train episode 31170: reward = -77.01, steps = 44 22:28:51 [INFO] train episode 31171: reward = -83.62, steps = 35 22:28:54 [INFO] train episode 31172: reward = -64.58, steps = 29 22:28:56 [INFO] train episode 31173: reward = -88.06, steps = 26 22:28:58 [INFO] train episode 31174: reward = -103.94, steps = 20 22:29:00 [INFO] train episode 31175: reward = -55.75, steps = 22 22:29:03 [INFO] train episode 31176: reward = -47.69, steps = 28 22:29:06 [INFO] train episode 31177: reward = -108.34, steps = 23 22:29:09 [INFO] train episode 31178: reward = -91.31, steps = 28 22:29:11 [INFO] train episode 31179: reward = -78.10, steps = 19 22:29:14 [INFO] train episode 31180: reward = -69.77, steps = 32 22:29:17 [INFO] train episode 31181: reward = -68.81, steps = 24 22:29:19 [INFO] train episode 31182: reward = -80.54, steps = 20 22:29:21 [INFO] train episode 31183: reward = -72.50, steps = 20 22:29:23 [INFO] train episode 31184: reward = -78.29, steps = 32 22:29:26 [INFO] train episode 31185: reward = -101.17, steps = 27 22:29:28 [INFO] train episode 31186: reward = -75.11, steps = 19 22:29:31 [INFO] train episode 31187: reward = -65.60, steps = 27 22:29:34 [INFO] train episode 31188: reward = -64.41, steps = 35 22:29:36 [INFO] train episode 31189: reward = -68.67, steps = 26 22:29:39 [INFO] train episode 31190: reward = -147.68, steps = 30 22:29:41 [INFO] train episode 31191: reward = -84.25, steps = 19 22:29:44 [INFO] train episode 31192: reward = -70.82, steps = 29 22:29:47 [INFO] train episode 31193: reward = -70.83, steps = 32 22:29:49 [INFO] train episode 31194: reward = -107.15, steps = 19 22:29:51 [INFO] train episode 31195: reward = -97.29, steps = 21 22:29:53 [INFO] train episode 31196: reward = -50.83, steps = 23 22:29:56 [INFO] train episode 31197: reward = -102.41, steps = 34 22:30:01 [INFO] train episode 31198: reward = -74.76, steps = 45 22:30:03 [INFO] train episode 31199: reward = -80.58, steps = 26 22:30:07 [INFO] train episode 31200: reward = -109.05, steps = 33 22:30:09 [INFO] train episode 31201: reward = -71.43, steps = 25 22:30:11 [INFO] train episode 31202: reward = -76.65, steps = 20 22:30:13 [INFO] train episode 31203: reward = -95.65, steps = 19 22:30:14 [INFO] train episode 31204: reward = -99.29, steps = 19 22:30:16 [INFO] train episode 31205: reward = -84.89, steps = 21 22:30:19 [INFO] train episode 31206: reward = -96.91, steps = 26 22:30:22 [INFO] train episode 31207: reward = -54.84, steps = 29 22:30:26 [INFO] train episode 31208: reward = -117.83, steps = 50 22:30:29 [INFO] train episode 31209: reward = -64.42, steps = 26 22:30:32 [INFO] train episode 31210: reward = -130.34, steps = 33 22:30:35 [INFO] train episode 31211: reward = -57.06, steps = 29 22:30:39 [INFO] train episode 31212: reward = -72.22, steps = 45 22:30:42 [INFO] train episode 31213: reward = -86.36, steps = 19 22:30:45 [INFO] train episode 31214: reward = -76.54, steps = 27 22:30:48 [INFO] train episode 31215: reward = -142.33, steps = 36 22:30:50 [INFO] train episode 31216: reward = -107.38, steps = 21 22:30:51 [INFO] train episode 31217: reward = -59.33, steps = 19 22:30:57 [INFO] train episode 31218: reward = -171.71, steps = 58 22:31:00 [INFO] train episode 31219: reward = -138.02, steps = 27 22:31:02 [INFO] train episode 31220: reward = -71.46, steps = 19 22:31:04 [INFO] train episode 31221: reward = -96.49, steps = 24 22:31:06 [INFO] train episode 31222: reward = -71.28, steps = 21 22:31:09 [INFO] train episode 31223: reward = -48.39, steps = 30 22:31:11 [INFO] train episode 31224: reward = -88.62, steps = 20 22:31:16 [INFO] train episode 31225: reward = -148.48, steps = 41 22:31:19 [INFO] train episode 31226: reward = -86.44, steps = 34 22:31:21 [INFO] train episode 31227: reward = -70.38, steps = 19 22:31:24 [INFO] train episode 31228: reward = -36.03, steps = 29 22:31:27 [INFO] train episode 31229: reward = -31.59, steps = 30 22:31:30 [INFO] train episode 31230: reward = -139.97, steps = 30 22:31:33 [INFO] train episode 31231: reward = -71.80, steps = 26 22:31:35 [INFO] train episode 31232: reward = -56.63, steps = 21 22:31:37 [INFO] train episode 31233: reward = -49.62, steps = 21 22:31:39 [INFO] train episode 31234: reward = -78.88, steps = 19 22:31:42 [INFO] train episode 31235: reward = -59.37, steps = 32 22:31:44 [INFO] train episode 31236: reward = -65.52, steps = 22 22:31:47 [INFO] train episode 31237: reward = -79.00, steps = 31 22:31:50 [INFO] train episode 31238: reward = -147.72, steps = 24 22:31:53 [INFO] train episode 31239: reward = -188.03, steps = 33 22:31:56 [INFO] train episode 31240: reward = -111.30, steps = 24 22:32:00 [INFO] train episode 31241: reward = -87.79, steps = 39 22:32:03 [INFO] train episode 31242: reward = -102.39, steps = 40 22:32:06 [INFO] train episode 31243: reward = -75.22, steps = 27 22:32:10 [INFO] train episode 31244: reward = -69.30, steps = 36 22:32:12 [INFO] train episode 31245: reward = -73.25, steps = 21 22:32:20 [INFO] train episode 31246: reward = -528.51, steps = 84 22:32:22 [INFO] train episode 31247: reward = -96.62, steps = 26 22:32:24 [INFO] train episode 31248: reward = -90.70, steps = 20 22:32:27 [INFO] train episode 31249: reward = -52.06, steps = 30 22:32:30 [INFO] train episode 31250: reward = -48.87, steps = 34 22:32:33 [INFO] train episode 31251: reward = -97.51, steps = 29 22:32:35 [INFO] train episode 31252: reward = -75.12, steps = 25 22:32:38 [INFO] train episode 31253: reward = -58.61, steps = 33 22:32:42 [INFO] train episode 31254: reward = -81.58, steps = 37 22:32:44 [INFO] train episode 31255: reward = -81.24, steps = 25 22:32:46 [INFO] train episode 31256: reward = -58.96, steps = 23 22:32:50 [INFO] train episode 31257: reward = -111.05, steps = 37 22:32:52 [INFO] train episode 31258: reward = -65.23, steps = 20 22:32:55 [INFO] train episode 31259: reward = -83.05, steps = 35 22:32:59 [INFO] train episode 31260: reward = -51.56, steps = 48 22:33:02 [INFO] train episode 31261: reward = -96.65, steps = 23 22:33:05 [INFO] train episode 31262: reward = -102.00, steps = 27 22:33:07 [INFO] train episode 31263: reward = -51.84, steps = 24 22:33:09 [INFO] train episode 31264: reward = -73.44, steps = 27 22:33:13 [INFO] train episode 31265: reward = -49.21, steps = 33 22:33:16 [INFO] train episode 31266: reward = -148.29, steps = 36 22:33:18 [INFO] train episode 31267: reward = -71.50, steps = 21 22:33:20 [INFO] train episode 31268: reward = -144.73, steps = 23 22:33:23 [INFO] train episode 31269: reward = -98.33, steps = 24 22:33:28 [INFO] train episode 31270: reward = -127.92, steps = 58 22:33:31 [INFO] train episode 31271: reward = -69.75, steps = 27 22:33:35 [INFO] train episode 31272: reward = -69.93, steps = 44 22:33:40 [INFO] train episode 31273: reward = -57.99, steps = 47 22:33:42 [INFO] train episode 31274: reward = -64.94, steps = 23 22:33:44 [INFO] train episode 31275: reward = -54.37, steps = 20 22:33:47 [INFO] train episode 31276: reward = -107.97, steps = 26 22:33:49 [INFO] train episode 31277: reward = -93.26, steps = 29 22:33:52 [INFO] train episode 31278: reward = -53.50, steps = 21 22:33:57 [INFO] train episode 31279: reward = -84.51, steps = 52 22:33:59 [INFO] train episode 31280: reward = -104.28, steps = 22 22:34:03 [INFO] train episode 31281: reward = -108.98, steps = 37 22:34:06 [INFO] train episode 31282: reward = -66.23, steps = 37 22:34:08 [INFO] train episode 31283: reward = -62.49, steps = 23 22:34:10 [INFO] train episode 31284: reward = -89.55, steps = 20 22:34:13 [INFO] train episode 31285: reward = -81.17, steps = 21 22:34:15 [INFO] train episode 31286: reward = -54.82, steps = 20 22:34:17 [INFO] train episode 31287: reward = -103.03, steps = 24 22:34:19 [INFO] train episode 31288: reward = -87.01, steps = 21 22:34:23 [INFO] train episode 31289: reward = -85.87, steps = 41 22:34:25 [INFO] train episode 31290: reward = -64.85, steps = 21 22:34:28 [INFO] train episode 31291: reward = -76.38, steps = 30 22:34:30 [INFO] train episode 31292: reward = -94.56, steps = 24 22:34:33 [INFO] train episode 31293: reward = -62.53, steps = 31 22:34:37 [INFO] train episode 31294: reward = -75.65, steps = 37 22:34:39 [INFO] train episode 31295: reward = -65.11, steps = 24 22:34:42 [INFO] train episode 31296: reward = -71.97, steps = 26 22:34:47 [INFO] train episode 31297: reward = -212.28, steps = 55 22:34:50 [INFO] train episode 31298: reward = -107.48, steps = 30 22:34:54 [INFO] train episode 31299: reward = -96.44, steps = 39 22:34:57 [INFO] train episode 31300: reward = -101.65, steps = 27 22:35:00 [INFO] train episode 31301: reward = -51.12, steps = 27 22:35:04 [INFO] train episode 31302: reward = -114.24, steps = 40 22:35:07 [INFO] train episode 31303: reward = -97.17, steps = 33 22:35:10 [INFO] train episode 31304: reward = -66.27, steps = 28 22:35:12 [INFO] train episode 31305: reward = -113.66, steps = 25 22:35:16 [INFO] train episode 31306: reward = -137.87, steps = 39 22:35:21 [INFO] train episode 31307: reward = -81.10, steps = 54 22:35:25 [INFO] train episode 31308: reward = -50.00, steps = 37 22:35:28 [INFO] train episode 31309: reward = -114.50, steps = 27 22:35:30 [INFO] train episode 31310: reward = -73.29, steps = 22 22:35:34 [INFO] train episode 31311: reward = -85.47, steps = 39 22:35:36 [INFO] train episode 31312: reward = -100.17, steps = 23 22:35:38 [INFO] train episode 31313: reward = -92.00, steps = 20 22:35:41 [INFO] train episode 31314: reward = -60.38, steps = 33 22:35:44 [INFO] train episode 31315: reward = -58.60, steps = 24 22:35:46 [INFO] train episode 31316: reward = -65.36, steps = 21 22:35:48 [INFO] train episode 31317: reward = -88.79, steps = 21 22:35:50 [INFO] train episode 31318: reward = -84.74, steps = 29 22:35:52 [INFO] train episode 31319: reward = -95.85, steps = 19 22:35:55 [INFO] train episode 31320: reward = -129.50, steps = 24 22:35:58 [INFO] train episode 31321: reward = -71.21, steps = 40 22:36:01 [INFO] train episode 31322: reward = -67.21, steps = 27 22:36:04 [INFO] train episode 31323: reward = -83.15, steps = 27 22:36:06 [INFO] train episode 31324: reward = -73.49, steps = 17 22:36:07 [INFO] train episode 31325: reward = -69.91, steps = 20 22:36:10 [INFO] train episode 31326: reward = -118.82, steps = 31 22:36:14 [INFO] train episode 31327: reward = -124.73, steps = 35 22:36:17 [INFO] train episode 31328: reward = -99.58, steps = 34 22:36:19 [INFO] train episode 31329: reward = -107.62, steps = 22 22:36:21 [INFO] train episode 31330: reward = -63.06, steps = 20 22:36:25 [INFO] train episode 31331: reward = -145.86, steps = 47 22:36:28 [INFO] train episode 31332: reward = -53.65, steps = 26 22:36:30 [INFO] train episode 31333: reward = -84.83, steps = 20 22:36:32 [INFO] train episode 31334: reward = -85.68, steps = 26 22:36:35 [INFO] train episode 31335: reward = -75.79, steps = 23 22:36:36 [INFO] train episode 31336: reward = -83.05, steps = 16 22:36:38 [INFO] train episode 31337: reward = -113.39, steps = 19 22:36:41 [INFO] train episode 31338: reward = -51.24, steps = 24 22:36:43 [INFO] train episode 31339: reward = -61.13, steps = 19 22:36:45 [INFO] train episode 31340: reward = -58.25, steps = 22 22:36:49 [INFO] train episode 31341: reward = -102.81, steps = 42 22:36:52 [INFO] train episode 31342: reward = -59.02, steps = 30 22:36:55 [INFO] train episode 31343: reward = -115.38, steps = 33 22:36:57 [INFO] train episode 31344: reward = -84.36, steps = 19 22:37:00 [INFO] train episode 31345: reward = -96.37, steps = 36 22:37:04 [INFO] train episode 31346: reward = -58.56, steps = 35 22:37:07 [INFO] train episode 31347: reward = -126.94, steps = 31 22:37:12 [INFO] train episode 31348: reward = -85.27, steps = 45 22:37:14 [INFO] train episode 31349: reward = -67.35, steps = 20 22:37:17 [INFO] train episode 31350: reward = -82.46, steps = 34 22:37:19 [INFO] train episode 31351: reward = -125.31, steps = 20 22:37:22 [INFO] train episode 31352: reward = -76.52, steps = 30 22:37:25 [INFO] train episode 31353: reward = -99.04, steps = 34 22:37:27 [INFO] train episode 31354: reward = -67.26, steps = 21 22:37:30 [INFO] train episode 31355: reward = -159.32, steps = 22 22:37:32 [INFO] train episode 31356: reward = -70.08, steps = 23 22:37:34 [INFO] train episode 31357: reward = -99.67, steps = 21 22:37:36 [INFO] train episode 31358: reward = -81.49, steps = 22 22:37:38 [INFO] train episode 31359: reward = -68.73, steps = 23 22:37:42 [INFO] train episode 31360: reward = -69.34, steps = 31 22:37:44 [INFO] train episode 31361: reward = -84.83, steps = 23 22:37:46 [INFO] train episode 31362: reward = -88.11, steps = 19 22:37:48 [INFO] train episode 31363: reward = -69.18, steps = 25 22:37:51 [INFO] train episode 31364: reward = -87.11, steps = 28 22:37:54 [INFO] train episode 31365: reward = -70.12, steps = 28 22:37:56 [INFO] train episode 31366: reward = -75.77, steps = 21 22:37:59 [INFO] train episode 31367: reward = -96.76, steps = 33 22:38:01 [INFO] train episode 31368: reward = -53.37, steps = 20 22:38:03 [INFO] train episode 31369: reward = -72.84, steps = 20 22:38:05 [INFO] train episode 31370: reward = -73.24, steps = 22 22:38:08 [INFO] train episode 31371: reward = -64.68, steps = 31 22:38:10 [INFO] train episode 31372: reward = -81.67, steps = 19 22:38:12 [INFO] train episode 31373: reward = -56.77, steps = 22 22:38:16 [INFO] train episode 31374: reward = -100.62, steps = 41 22:38:18 [INFO] train episode 31375: reward = -120.85, steps = 19 22:38:20 [INFO] train episode 31376: reward = -88.63, steps = 23 22:38:23 [INFO] train episode 31377: reward = -104.45, steps = 28 22:38:25 [INFO] train episode 31378: reward = -92.08, steps = 23 22:38:28 [INFO] train episode 31379: reward = -95.26, steps = 30 22:38:30 [INFO] train episode 31380: reward = -61.79, steps = 22 22:38:33 [INFO] train episode 31381: reward = -98.21, steps = 29 22:38:36 [INFO] train episode 31382: reward = -87.57, steps = 23 22:38:38 [INFO] train episode 31383: reward = -79.44, steps = 26 22:38:42 [INFO] train episode 31384: reward = -105.22, steps = 34 22:38:44 [INFO] train episode 31385: reward = -98.51, steps = 19 22:38:47 [INFO] train episode 31386: reward = -75.93, steps = 28 22:38:50 [INFO] train episode 31387: reward = -57.92, steps = 37 22:38:55 [INFO] train episode 31388: reward = -173.93, steps = 48 22:38:56 [INFO] train episode 31389: reward = -98.73, steps = 18 22:38:59 [INFO] train episode 31390: reward = -88.95, steps = 21 22:39:02 [INFO] train episode 31391: reward = -110.44, steps = 34 22:39:05 [INFO] train episode 31392: reward = -87.12, steps = 31 22:39:09 [INFO] train episode 31393: reward = -88.36, steps = 36 22:39:10 [INFO] train episode 31394: reward = -136.53, steps = 17 22:39:15 [INFO] train episode 31395: reward = -149.88, steps = 45 22:39:18 [INFO] train episode 31396: reward = -86.59, steps = 31 22:39:23 [INFO] train episode 31397: reward = -95.68, steps = 48 22:39:26 [INFO] train episode 31398: reward = -119.91, steps = 35 22:39:29 [INFO] train episode 31399: reward = -87.38, steps = 26 22:39:31 [INFO] train episode 31400: reward = -95.08, steps = 20 22:39:32 [INFO] train episode 31401: reward = -111.72, steps = 19 22:39:36 [INFO] train episode 31402: reward = -89.41, steps = 31 22:39:39 [INFO] train episode 31403: reward = -102.96, steps = 36 22:39:41 [INFO] train episode 31404: reward = -50.03, steps = 23 22:39:43 [INFO] train episode 31405: reward = -141.81, steps = 24 22:39:46 [INFO] train episode 31406: reward = -128.38, steps = 21 22:39:50 [INFO] train episode 31407: reward = -213.56, steps = 46 22:39:53 [INFO] train episode 31408: reward = -107.38, steps = 29 22:39:55 [INFO] train episode 31409: reward = -58.59, steps = 20 22:39:58 [INFO] train episode 31410: reward = -94.83, steps = 35 22:40:02 [INFO] train episode 31411: reward = -102.41, steps = 32 22:40:04 [INFO] train episode 31412: reward = -86.78, steps = 29 22:40:09 [INFO] train episode 31413: reward = -99.16, steps = 46 22:40:12 [INFO] train episode 31414: reward = -139.79, steps = 36 22:40:17 [INFO] train episode 31415: reward = -136.27, steps = 39 22:40:19 [INFO] train episode 31416: reward = -81.08, steps = 26 22:40:21 [INFO] train episode 31417: reward = -64.25, steps = 22 22:40:24 [INFO] train episode 31418: reward = -92.76, steps = 24 22:40:27 [INFO] train episode 31419: reward = -119.19, steps = 34 22:40:29 [INFO] train episode 31420: reward = -68.42, steps = 19 22:40:32 [INFO] train episode 31421: reward = -85.33, steps = 29 22:40:34 [INFO] train episode 31422: reward = -73.17, steps = 20 22:40:36 [INFO] train episode 31423: reward = -88.71, steps = 24 22:40:38 [INFO] train episode 31424: reward = -65.07, steps = 20 22:40:41 [INFO] train episode 31425: reward = -90.19, steps = 32 22:40:47 [INFO] train episode 31426: reward = -111.22, steps = 56 22:40:52 [INFO] train episode 31427: reward = -140.07, steps = 59 22:40:54 [INFO] train episode 31428: reward = -56.42, steps = 19 22:40:57 [INFO] train episode 31429: reward = -114.45, steps = 32 22:41:00 [INFO] train episode 31430: reward = -120.39, steps = 29 22:41:04 [INFO] train episode 31431: reward = -94.92, steps = 41 22:41:07 [INFO] train episode 31432: reward = -76.11, steps = 24 22:41:10 [INFO] train episode 31433: reward = -49.83, steps = 32 22:41:12 [INFO] train episode 31434: reward = -63.78, steps = 20 22:41:15 [INFO] train episode 31435: reward = -42.78, steps = 28 22:41:17 [INFO] train episode 31436: reward = -65.28, steps = 20 22:41:19 [INFO] train episode 31437: reward = -65.71, steps = 20 22:41:21 [INFO] train episode 31438: reward = -49.23, steps = 25 22:41:23 [INFO] train episode 31439: reward = -78.36, steps = 20 22:41:25 [INFO] train episode 31440: reward = -100.59, steps = 19 22:41:27 [INFO] train episode 31441: reward = -52.97, steps = 19 22:41:29 [INFO] train episode 31442: reward = -92.35, steps = 19 22:41:32 [INFO] train episode 31443: reward = -84.40, steps = 23 22:41:35 [INFO] train episode 31444: reward = -65.15, steps = 28 22:41:38 [INFO] train episode 31445: reward = -120.80, steps = 32 22:41:40 [INFO] train episode 31446: reward = -69.72, steps = 20 22:41:44 [INFO] train episode 31447: reward = -136.46, steps = 41 22:41:47 [INFO] train episode 31448: reward = -99.88, steps = 31 22:41:49 [INFO] train episode 31449: reward = -98.50, steps = 20 22:41:54 [INFO] train episode 31450: reward = -138.24, steps = 54 22:41:57 [INFO] train episode 31451: reward = -105.46, steps = 30 22:42:00 [INFO] train episode 31452: reward = -66.75, steps = 29 22:42:03 [INFO] train episode 31453: reward = -99.15, steps = 33 22:42:06 [INFO] train episode 31454: reward = -113.68, steps = 30 22:42:08 [INFO] train episode 31455: reward = -94.38, steps = 22 22:42:10 [INFO] train episode 31456: reward = -53.72, steps = 20 22:42:12 [INFO] train episode 31457: reward = -99.75, steps = 19 22:42:14 [INFO] train episode 31458: reward = -48.19, steps = 21 22:42:18 [INFO] train episode 31459: reward = -100.10, steps = 29 22:42:21 [INFO] train episode 31460: reward = -47.39, steps = 30 22:42:23 [INFO] train episode 31461: reward = -83.92, steps = 27 22:42:26 [INFO] train episode 31462: reward = -88.47, steps = 24 22:42:28 [INFO] train episode 31463: reward = -95.39, steps = 19 22:42:31 [INFO] train episode 31464: reward = -148.14, steps = 35 22:42:34 [INFO] train episode 31465: reward = -81.94, steps = 30 22:42:37 [INFO] train episode 31466: reward = -95.81, steps = 22 22:42:39 [INFO] train episode 31467: reward = -110.04, steps = 19 22:42:41 [INFO] train episode 31468: reward = -72.13, steps = 20 22:42:44 [INFO] train episode 31469: reward = -111.70, steps = 34 22:42:47 [INFO] train episode 31470: reward = -148.41, steps = 32 22:42:49 [INFO] train episode 31471: reward = -83.81, steps = 19 22:42:52 [INFO] train episode 31472: reward = -134.68, steps = 33 22:42:57 [INFO] train episode 31473: reward = -85.28, steps = 49 22:43:00 [INFO] train episode 31474: reward = -81.39, steps = 33 22:43:03 [INFO] train episode 31475: reward = -147.38, steps = 21 22:43:05 [INFO] train episode 31476: reward = -121.55, steps = 23 22:43:07 [INFO] train episode 31477: reward = -76.34, steps = 28 22:43:11 [INFO] train episode 31478: reward = -139.75, steps = 31 22:43:12 [INFO] train episode 31479: reward = -78.53, steps = 19 22:43:14 [INFO] train episode 31480: reward = -55.11, steps = 17 22:43:16 [INFO] train episode 31481: reward = -100.95, steps = 19 22:43:18 [INFO] train episode 31482: reward = -67.31, steps = 19 22:43:20 [INFO] train episode 31483: reward = -154.17, steps = 28 22:43:22 [INFO] train episode 31484: reward = -73.50, steps = 21 22:43:24 [INFO] train episode 31485: reward = -89.34, steps = 19 22:43:26 [INFO] train episode 31486: reward = -82.51, steps = 19 22:43:29 [INFO] train episode 31487: reward = -70.83, steps = 24 22:43:31 [INFO] train episode 31488: reward = -157.09, steps = 17 22:43:33 [INFO] train episode 31489: reward = -66.05, steps = 24 22:43:36 [INFO] train episode 31490: reward = -62.94, steps = 30 22:43:38 [INFO] train episode 31491: reward = -132.27, steps = 23 22:43:41 [INFO] train episode 31492: reward = -153.92, steps = 31 22:43:47 [INFO] train episode 31493: reward = -142.78, steps = 53 22:43:49 [INFO] train episode 31494: reward = -77.43, steps = 20 22:43:52 [INFO] train episode 31495: reward = -78.21, steps = 35 22:43:54 [INFO] train episode 31496: reward = -99.87, steps = 20 22:43:57 [INFO] train episode 31497: reward = -87.82, steps = 29 22:43:59 [INFO] train episode 31498: reward = -67.92, steps = 25 22:44:01 [INFO] train episode 31499: reward = -63.25, steps = 20 22:44:03 [INFO] train episode 31500: reward = -98.09, steps = 20 22:44:07 [INFO] train episode 31501: reward = -61.64, steps = 36 22:44:08 [INFO] train episode 31502: reward = -112.17, steps = 18 22:44:11 [INFO] train episode 31503: reward = -48.66, steps = 27 22:44:14 [INFO] train episode 31504: reward = -90.49, steps = 26 22:44:18 [INFO] train episode 31505: reward = -74.31, steps = 44 22:44:20 [INFO] train episode 31506: reward = -81.38, steps = 20 22:44:23 [INFO] train episode 31507: reward = -91.30, steps = 24 22:44:25 [INFO] train episode 31508: reward = -90.60, steps = 24 22:44:30 [INFO] train episode 31509: reward = -158.91, steps = 56 22:44:32 [INFO] train episode 31510: reward = -63.24, steps = 20 22:44:35 [INFO] train episode 31511: reward = -95.53, steps = 28 22:44:37 [INFO] train episode 31512: reward = -77.56, steps = 18 22:44:40 [INFO] train episode 31513: reward = -71.94, steps = 33 22:44:43 [INFO] train episode 31514: reward = -99.61, steps = 28 22:44:45 [INFO] train episode 31515: reward = -72.79, steps = 20 22:44:47 [INFO] train episode 31516: reward = -113.20, steps = 19 22:44:49 [INFO] train episode 31517: reward = -78.70, steps = 24 22:44:51 [INFO] train episode 31518: reward = -88.61, steps = 24 22:44:55 [INFO] train episode 31519: reward = -148.52, steps = 32 22:44:57 [INFO] train episode 31520: reward = -51.68, steps = 20 22:45:00 [INFO] train episode 31521: reward = -88.46, steps = 26 22:45:02 [INFO] train episode 31522: reward = -73.24, steps = 24 22:45:05 [INFO] train episode 31523: reward = -151.36, steps = 30 22:45:07 [INFO] train episode 31524: reward = -62.91, steps = 24 22:45:10 [INFO] train episode 31525: reward = -86.82, steps = 30 22:45:12 [INFO] train episode 31526: reward = -66.72, steps = 25 22:45:14 [INFO] train episode 31527: reward = -71.86, steps = 21 22:45:16 [INFO] train episode 31528: reward = -89.96, steps = 19 22:45:18 [INFO] train episode 31529: reward = -62.52, steps = 22 22:45:21 [INFO] train episode 31530: reward = -60.29, steps = 26 22:45:24 [INFO] train episode 31531: reward = -62.82, steps = 35 22:45:27 [INFO] train episode 31532: reward = -107.74, steps = 28 22:45:28 [INFO] train episode 31533: reward = -75.05, steps = 19 22:45:32 [INFO] train episode 31534: reward = -150.40, steps = 37 22:45:34 [INFO] train episode 31535: reward = -62.01, steps = 21 22:45:37 [INFO] train episode 31536: reward = -95.08, steps = 28 22:45:40 [INFO] train episode 31537: reward = -137.38, steps = 31 22:45:43 [INFO] train episode 31538: reward = -97.15, steps = 35 22:45:46 [INFO] train episode 31539: reward = -69.54, steps = 25 22:45:50 [INFO] train episode 31540: reward = -114.91, steps = 37 22:45:52 [INFO] train episode 31541: reward = -82.06, steps = 19 22:45:54 [INFO] train episode 31542: reward = -102.38, steps = 25 22:45:56 [INFO] train episode 31543: reward = -76.66, steps = 20 22:45:58 [INFO] train episode 31544: reward = -110.22, steps = 19 22:46:00 [INFO] train episode 31545: reward = -63.06, steps = 21 22:46:02 [INFO] train episode 31546: reward = -73.36, steps = 20 22:46:04 [INFO] train episode 31547: reward = -112.85, steps = 22 22:46:07 [INFO] train episode 31548: reward = -97.86, steps = 25 22:46:09 [INFO] train episode 31549: reward = -121.65, steps = 19 22:46:11 [INFO] train episode 31550: reward = -86.71, steps = 21 22:46:14 [INFO] train episode 31551: reward = -95.09, steps = 35 22:46:17 [INFO] train episode 31552: reward = -78.02, steps = 21 22:46:19 [INFO] train episode 31553: reward = -150.37, steps = 20 22:46:21 [INFO] train episode 31554: reward = -70.83, steps = 28 22:46:24 [INFO] train episode 31555: reward = -82.64, steps = 32 22:46:26 [INFO] train episode 31556: reward = -60.89, steps = 18 22:46:30 [INFO] train episode 31557: reward = -82.60, steps = 31 22:46:32 [INFO] train episode 31558: reward = -83.98, steps = 22 22:46:34 [INFO] train episode 31559: reward = -76.77, steps = 18 22:46:37 [INFO] train episode 31560: reward = -77.04, steps = 30 22:46:39 [INFO] train episode 31561: reward = -56.27, steps = 24 22:46:42 [INFO] train episode 31562: reward = -108.97, steps = 23 22:46:45 [INFO] train episode 31563: reward = -73.37, steps = 26 22:46:47 [INFO] train episode 31564: reward = -50.49, steps = 21 22:46:50 [INFO] train episode 31565: reward = -108.41, steps = 35 22:46:52 [INFO] train episode 31566: reward = -52.73, steps = 21 22:46:55 [INFO] train episode 31567: reward = -114.71, steps = 26 22:46:58 [INFO] train episode 31568: reward = -82.48, steps = 30 22:47:00 [INFO] train episode 31569: reward = -75.04, steps = 21 22:47:03 [INFO] train episode 31570: reward = -73.80, steps = 29 22:47:07 [INFO] train episode 31571: reward = -213.81, steps = 45 22:47:09 [INFO] train episode 31572: reward = -93.45, steps = 22 22:47:15 [INFO] train episode 31573: reward = -127.66, steps = 55 22:47:17 [INFO] train episode 31574: reward = -45.43, steps = 19 22:47:19 [INFO] train episode 31575: reward = -78.76, steps = 20 22:47:21 [INFO] train episode 31576: reward = -65.32, steps = 20 22:47:23 [INFO] train episode 31577: reward = -157.19, steps = 22 22:47:27 [INFO] train episode 31578: reward = -119.71, steps = 37 22:47:30 [INFO] train episode 31579: reward = -98.18, steps = 39 22:47:33 [INFO] train episode 31580: reward = -65.83, steps = 28 22:47:35 [INFO] train episode 31581: reward = -83.07, steps = 23 22:47:37 [INFO] train episode 31582: reward = -76.71, steps = 22 22:47:40 [INFO] train episode 31583: reward = -146.67, steps = 28 22:47:42 [INFO] train episode 31584: reward = -113.46, steps = 21 22:47:44 [INFO] train episode 31585: reward = -95.05, steps = 27 22:47:47 [INFO] train episode 31586: reward = -92.90, steps = 29 22:47:50 [INFO] train episode 31587: reward = -76.39, steps = 26 22:47:51 [INFO] train episode 31588: reward = -81.09, steps = 19 22:47:54 [INFO] train episode 31589: reward = -122.63, steps = 33 22:47:57 [INFO] train episode 31590: reward = -56.87, steps = 26 22:47:59 [INFO] train episode 31591: reward = -60.00, steps = 18 22:48:01 [INFO] train episode 31592: reward = -52.53, steps = 26 22:48:03 [INFO] train episode 31593: reward = -70.15, steps = 19 22:48:05 [INFO] train episode 31594: reward = -72.76, steps = 24 22:48:08 [INFO] train episode 31595: reward = -108.53, steps = 24 22:48:10 [INFO] train episode 31596: reward = -89.98, steps = 27 22:48:12 [INFO] train episode 31597: reward = -58.06, steps = 20 22:48:15 [INFO] train episode 31598: reward = -97.79, steps = 23 22:48:18 [INFO] train episode 31599: reward = -81.61, steps = 36 22:48:20 [INFO] train episode 31600: reward = -79.27, steps = 24 22:48:22 [INFO] train episode 31601: reward = -107.96, steps = 22 22:48:25 [INFO] train episode 31602: reward = -66.61, steps = 24 22:48:27 [INFO] train episode 31603: reward = -93.25, steps = 24 22:48:29 [INFO] train episode 31604: reward = -70.25, steps = 24 22:48:32 [INFO] train episode 31605: reward = -88.20, steps = 24 22:48:34 [INFO] train episode 31606: reward = -110.21, steps = 19 22:48:35 [INFO] train episode 31607: reward = -83.43, steps = 19 22:48:37 [INFO] train episode 31608: reward = -145.41, steps = 17 22:48:39 [INFO] train episode 31609: reward = -92.72, steps = 23 22:48:42 [INFO] train episode 31610: reward = -108.39, steps = 28 22:48:44 [INFO] train episode 31611: reward = -89.16, steps = 18 22:48:46 [INFO] train episode 31612: reward = -115.99, steps = 29 22:48:49 [INFO] train episode 31613: reward = -107.82, steps = 22 22:48:52 [INFO] train episode 31614: reward = -85.82, steps = 33 22:48:55 [INFO] train episode 31615: reward = -109.96, steps = 31 22:48:58 [INFO] train episode 31616: reward = -83.17, steps = 26 22:49:00 [INFO] train episode 31617: reward = -86.19, steps = 27 22:49:02 [INFO] train episode 31618: reward = -77.53, steps = 22 22:49:06 [INFO] train episode 31619: reward = -128.02, steps = 40 22:49:10 [INFO] train episode 31620: reward = -111.66, steps = 37 22:49:12 [INFO] train episode 31621: reward = -114.57, steps = 24 22:49:15 [INFO] train episode 31622: reward = -92.59, steps = 26 22:49:17 [INFO] train episode 31623: reward = -56.17, steps = 20 22:49:21 [INFO] train episode 31624: reward = -161.37, steps = 41 22:49:24 [INFO] train episode 31625: reward = -86.51, steps = 34 22:49:26 [INFO] train episode 31626: reward = -68.45, steps = 20 22:49:29 [INFO] train episode 31627: reward = -130.04, steps = 26 22:49:34 [INFO] train episode 31628: reward = -122.27, steps = 49 22:49:36 [INFO] train episode 31629: reward = -79.45, steps = 20 22:49:37 [INFO] train episode 31630: reward = -78.94, steps = 17 22:49:40 [INFO] train episode 31631: reward = -72.41, steps = 27 22:49:46 [INFO] train episode 31632: reward = -134.31, steps = 60 22:49:48 [INFO] train episode 31633: reward = -75.83, steps = 21 22:49:50 [INFO] train episode 31634: reward = -133.56, steps = 20 22:49:54 [INFO] train episode 31635: reward = -137.61, steps = 35 22:49:56 [INFO] train episode 31636: reward = -91.80, steps = 21 22:49:58 [INFO] train episode 31637: reward = -166.95, steps = 15 22:50:02 [INFO] train episode 31638: reward = -77.42, steps = 36 22:50:04 [INFO] train episode 31639: reward = -78.82, steps = 20 22:50:06 [INFO] train episode 31640: reward = -110.23, steps = 25 22:50:10 [INFO] train episode 31641: reward = -179.25, steps = 35 22:50:12 [INFO] train episode 31642: reward = -60.62, steps = 20 22:50:15 [INFO] train episode 31643: reward = -63.88, steps = 31 22:50:17 [INFO] train episode 31644: reward = -77.25, steps = 21 22:50:20 [INFO] train episode 31645: reward = -116.23, steps = 31 22:50:22 [INFO] train episode 31646: reward = -64.01, steps = 20 22:50:25 [INFO] train episode 31647: reward = -161.30, steps = 33 22:50:27 [INFO] train episode 31648: reward = -75.12, steps = 18 22:50:29 [INFO] train episode 31649: reward = -70.11, steps = 19 22:50:31 [INFO] train episode 31650: reward = -88.41, steps = 26 22:50:33 [INFO] train episode 31651: reward = -103.20, steps = 20 22:50:36 [INFO] train episode 31652: reward = -65.43, steps = 27 22:50:40 [INFO] train episode 31653: reward = -144.89, steps = 32 22:50:42 [INFO] train episode 31654: reward = -85.69, steps = 20 22:50:46 [INFO] train episode 31655: reward = -96.64, steps = 48 22:50:48 [INFO] train episode 31656: reward = -150.47, steps = 20 22:50:50 [INFO] train episode 31657: reward = -105.67, steps = 25 22:50:53 [INFO] train episode 31658: reward = -103.16, steps = 31 22:50:56 [INFO] train episode 31659: reward = -61.34, steps = 20 22:50:58 [INFO] train episode 31660: reward = -87.61, steps = 23 22:51:00 [INFO] train episode 31661: reward = -150.48, steps = 20 22:51:02 [INFO] train episode 31662: reward = -106.56, steps = 21 22:51:04 [INFO] train episode 31663: reward = -67.89, steps = 25 22:51:07 [INFO] train episode 31664: reward = -80.96, steps = 29 22:51:09 [INFO] train episode 31665: reward = -63.36, steps = 22 22:51:11 [INFO] train episode 31666: reward = -117.51, steps = 18 22:51:13 [INFO] train episode 31667: reward = -64.50, steps = 24 22:51:15 [INFO] train episode 31668: reward = -107.36, steps = 21 22:51:17 [INFO] train episode 31669: reward = -46.80, steps = 21 22:51:19 [INFO] train episode 31670: reward = -189.40, steps = 21 22:51:22 [INFO] train episode 31671: reward = -104.56, steps = 26 22:51:25 [INFO] train episode 31672: reward = -164.64, steps = 30 22:51:28 [INFO] train episode 31673: reward = -107.03, steps = 30 22:51:30 [INFO] train episode 31674: reward = -83.04, steps = 21 22:51:32 [INFO] train episode 31675: reward = -89.74, steps = 21 22:51:35 [INFO] train episode 31676: reward = -105.02, steps = 36 22:51:37 [INFO] train episode 31677: reward = -96.56, steps = 21 22:51:40 [INFO] train episode 31678: reward = -92.42, steps = 32 22:51:44 [INFO] train episode 31679: reward = -92.18, steps = 42 22:51:48 [INFO] train episode 31680: reward = -137.57, steps = 36 22:51:50 [INFO] train episode 31681: reward = -83.04, steps = 22 22:51:54 [INFO] train episode 31682: reward = -77.81, steps = 35 22:51:58 [INFO] train episode 31683: reward = -191.57, steps = 53 22:52:00 [INFO] train episode 31684: reward = -59.32, steps = 19 22:52:02 [INFO] train episode 31685: reward = -87.30, steps = 19 22:52:04 [INFO] train episode 31686: reward = -205.99, steps = 18 22:52:06 [INFO] train episode 31687: reward = -66.17, steps = 21 22:52:08 [INFO] train episode 31688: reward = -92.67, steps = 21 22:52:12 [INFO] train episode 31689: reward = -103.49, steps = 35 22:52:13 [INFO] train episode 31690: reward = -77.71, steps = 19 22:52:17 [INFO] train episode 31691: reward = -106.78, steps = 37 22:52:20 [INFO] train episode 31692: reward = -46.52, steps = 30 22:52:23 [INFO] train episode 31693: reward = -98.91, steps = 27 22:52:25 [INFO] train episode 31694: reward = -102.64, steps = 20 22:52:28 [INFO] train episode 31695: reward = -93.30, steps = 31 22:52:30 [INFO] train episode 31696: reward = -93.26, steps = 20 22:52:33 [INFO] train episode 31697: reward = -88.42, steps = 30 22:52:37 [INFO] train episode 31698: reward = -165.58, steps = 41 22:52:40 [INFO] train episode 31699: reward = -85.55, steps = 27 22:52:43 [INFO] train episode 31700: reward = -134.41, steps = 33 22:52:47 [INFO] train episode 31701: reward = -146.53, steps = 33 22:52:50 [INFO] train episode 31702: reward = -78.86, steps = 31 22:52:52 [INFO] train episode 31703: reward = -85.54, steps = 25 22:52:54 [INFO] train episode 31704: reward = -125.17, steps = 23 22:52:56 [INFO] train episode 31705: reward = -98.74, steps = 22 22:52:59 [INFO] train episode 31706: reward = -179.69, steps = 26 22:53:02 [INFO] train episode 31707: reward = -91.10, steps = 36 22:53:05 [INFO] train episode 31708: reward = -101.36, steps = 20 22:53:07 [INFO] train episode 31709: reward = -78.56, steps = 24 22:53:10 [INFO] train episode 31710: reward = -71.81, steps = 27 22:53:12 [INFO] train episode 31711: reward = -116.01, steps = 18 22:53:14 [INFO] train episode 31712: reward = -122.12, steps = 30 22:53:17 [INFO] train episode 31713: reward = -163.71, steps = 24 22:53:20 [INFO] train episode 31714: reward = -158.05, steps = 30 22:53:22 [INFO] train episode 31715: reward = -68.95, steps = 19 22:53:26 [INFO] train episode 31716: reward = -119.49, steps = 44 22:53:28 [INFO] train episode 31717: reward = -81.98, steps = 31 22:53:31 [INFO] train episode 31718: reward = -82.99, steps = 24 22:53:34 [INFO] train episode 31719: reward = -146.65, steps = 34 22:53:36 [INFO] train episode 31720: reward = -87.15, steps = 20 22:53:39 [INFO] train episode 31721: reward = -56.07, steps = 27 22:53:41 [INFO] train episode 31722: reward = -161.27, steps = 28 22:53:44 [INFO] train episode 31723: reward = -74.64, steps = 26 22:53:46 [INFO] train episode 31724: reward = -116.47, steps = 24 22:53:48 [INFO] train episode 31725: reward = -93.13, steps = 22 22:53:50 [INFO] train episode 31726: reward = -100.54, steps = 20 22:53:52 [INFO] train episode 31727: reward = -145.60, steps = 22 22:53:55 [INFO] train episode 31728: reward = -148.28, steps = 26 22:53:57 [INFO] train episode 31729: reward = -73.25, steps = 22 22:53:59 [INFO] train episode 31730: reward = -68.65, steps = 20 22:54:01 [INFO] train episode 31731: reward = -104.28, steps = 19 22:54:03 [INFO] train episode 31732: reward = -79.40, steps = 25 22:54:05 [INFO] train episode 31733: reward = -45.66, steps = 20 22:54:07 [INFO] train episode 31734: reward = -72.05, steps = 20 22:54:11 [INFO] train episode 31735: reward = -91.11, steps = 36 22:54:14 [INFO] train episode 31736: reward = -117.98, steps = 37 22:54:16 [INFO] train episode 31737: reward = -80.58, steps = 19 22:54:18 [INFO] train episode 31738: reward = -71.33, steps = 19 22:54:20 [INFO] train episode 31739: reward = -75.07, steps = 21 22:54:22 [INFO] train episode 31740: reward = -108.43, steps = 22 22:54:25 [INFO] train episode 31741: reward = -64.44, steps = 25 22:54:28 [INFO] train episode 31742: reward = -84.69, steps = 29 22:54:30 [INFO] train episode 31743: reward = -127.91, steps = 22 22:54:33 [INFO] train episode 31744: reward = -119.49, steps = 25 22:54:36 [INFO] train episode 31745: reward = -124.62, steps = 33 22:54:40 [INFO] train episode 31746: reward = -107.04, steps = 38 22:54:42 [INFO] train episode 31747: reward = -113.88, steps = 19 22:54:44 [INFO] train episode 31748: reward = -71.33, steps = 20 22:54:47 [INFO] train episode 31749: reward = -74.10, steps = 20 22:54:49 [INFO] train episode 31750: reward = -92.18, steps = 23 22:54:51 [INFO] train episode 31751: reward = -115.60, steps = 22 22:54:55 [INFO] train episode 31752: reward = -122.34, steps = 37 22:54:57 [INFO] train episode 31753: reward = -71.14, steps = 23 22:55:02 [INFO] train episode 31754: reward = -76.61, steps = 34 22:55:04 [INFO] train episode 31755: reward = -122.37, steps = 20 22:55:07 [INFO] train episode 31756: reward = -93.13, steps = 22 22:55:09 [INFO] train episode 31757: reward = -102.85, steps = 27 22:55:11 [INFO] train episode 31758: reward = -115.98, steps = 19 22:55:14 [INFO] train episode 31759: reward = -126.40, steps = 30 22:55:16 [INFO] train episode 31760: reward = -123.42, steps = 25 22:55:19 [INFO] train episode 31761: reward = -142.94, steps = 20 22:55:21 [INFO] train episode 31762: reward = -53.81, steps = 20 22:55:23 [INFO] train episode 31763: reward = -81.52, steps = 20 22:55:25 [INFO] train episode 31764: reward = -76.26, steps = 20 22:55:27 [INFO] train episode 31765: reward = -76.09, steps = 19 22:55:28 [INFO] train episode 31766: reward = -61.48, steps = 18 22:55:31 [INFO] train episode 31767: reward = -133.06, steps = 29 22:55:34 [INFO] train episode 31768: reward = -134.05, steps = 27 22:55:37 [INFO] train episode 31769: reward = -144.35, steps = 40 22:55:41 [INFO] train episode 31770: reward = -105.06, steps = 32 22:55:43 [INFO] train episode 31771: reward = -75.67, steps = 20 22:55:45 [INFO] train episode 31772: reward = -74.46, steps = 19 22:55:47 [INFO] train episode 31773: reward = -100.83, steps = 23 22:55:49 [INFO] train episode 31774: reward = -77.46, steps = 20 22:55:51 [INFO] train episode 31775: reward = -77.39, steps = 21 22:55:53 [INFO] train episode 31776: reward = -82.59, steps = 20 22:55:56 [INFO] train episode 31777: reward = -96.73, steps = 32 22:55:59 [INFO] train episode 31778: reward = -96.50, steps = 20 22:56:01 [INFO] train episode 31779: reward = -157.38, steps = 21 22:56:04 [INFO] train episode 31780: reward = -79.27, steps = 20 22:56:06 [INFO] train episode 31781: reward = -123.85, steps = 19 22:56:08 [INFO] train episode 31782: reward = -88.43, steps = 24 22:56:12 [INFO] train episode 31783: reward = -119.16, steps = 32 22:56:15 [INFO] train episode 31784: reward = -102.39, steps = 26 22:56:18 [INFO] train episode 31785: reward = -122.60, steps = 19 22:56:20 [INFO] train episode 31786: reward = -65.00, steps = 19 22:56:23 [INFO] train episode 31787: reward = -88.63, steps = 20 22:56:26 [INFO] train episode 31788: reward = -67.04, steps = 24 22:56:28 [INFO] train episode 31789: reward = -64.64, steps = 20 22:56:31 [INFO] train episode 31790: reward = -104.02, steps = 26 22:56:34 [INFO] train episode 31791: reward = -112.38, steps = 30 22:56:36 [INFO] train episode 31792: reward = -75.38, steps = 21 22:56:39 [INFO] train episode 31793: reward = -74.33, steps = 30 22:56:42 [INFO] train episode 31794: reward = -155.08, steps = 21 22:56:45 [INFO] train episode 31795: reward = -72.03, steps = 23 22:56:49 [INFO] train episode 31796: reward = -138.26, steps = 35 22:56:52 [INFO] train episode 31797: reward = -79.70, steps = 38 22:56:56 [INFO] train episode 31798: reward = -98.78, steps = 36 22:56:58 [INFO] train episode 31799: reward = -72.70, steps = 24 22:57:01 [INFO] train episode 31800: reward = -123.05, steps = 19 22:57:03 [INFO] train episode 31801: reward = -77.37, steps = 25 22:57:05 [INFO] train episode 31802: reward = -62.95, steps = 20 22:57:07 [INFO] train episode 31803: reward = -108.02, steps = 19 22:57:09 [INFO] train episode 31804: reward = -63.18, steps = 20 22:57:11 [INFO] train episode 31805: reward = -76.58, steps = 20 22:57:14 [INFO] train episode 31806: reward = -98.31, steps = 24 22:57:18 [INFO] train episode 31807: reward = -85.88, steps = 35 22:57:21 [INFO] train episode 31808: reward = -91.93, steps = 21 22:57:24 [INFO] train episode 31809: reward = -107.14, steps = 34 22:57:26 [INFO] train episode 31810: reward = -87.61, steps = 19 22:57:28 [INFO] train episode 31811: reward = -79.70, steps = 21 22:57:31 [INFO] train episode 31812: reward = -54.48, steps = 21 22:57:33 [INFO] train episode 31813: reward = -185.12, steps = 25 22:57:38 [INFO] train episode 31814: reward = -215.11, steps = 55 22:57:41 [INFO] train episode 31815: reward = -89.81, steps = 26 22:57:43 [INFO] train episode 31816: reward = -151.72, steps = 23 22:57:45 [INFO] train episode 31817: reward = -104.96, steps = 19 22:57:46 [INFO] train episode 31818: reward = -83.04, steps = 20 22:57:48 [INFO] train episode 31819: reward = -91.54, steps = 22 22:57:50 [INFO] train episode 31820: reward = -160.55, steps = 19 22:57:52 [INFO] train episode 31821: reward = -108.38, steps = 22 22:57:55 [INFO] train episode 31822: reward = -70.01, steps = 20 22:57:58 [INFO] train episode 31823: reward = -65.60, steps = 33 22:58:01 [INFO] train episode 31824: reward = -174.60, steps = 26 22:58:03 [INFO] train episode 31825: reward = -92.77, steps = 19 22:58:05 [INFO] train episode 31826: reward = -56.92, steps = 20 22:58:08 [INFO] train episode 31827: reward = -91.36, steps = 24 22:58:10 [INFO] train episode 31828: reward = -68.79, steps = 20 22:58:12 [INFO] train episode 31829: reward = -82.99, steps = 22 22:58:15 [INFO] train episode 31830: reward = -66.26, steps = 19 22:58:18 [INFO] train episode 31831: reward = -79.93, steps = 34 22:58:20 [INFO] train episode 31832: reward = -62.59, steps = 21 22:58:21 [INFO] train episode 31833: reward = -69.58, steps = 19 22:58:23 [INFO] train episode 31834: reward = -44.06, steps = 19 22:58:25 [INFO] train episode 31835: reward = -109.11, steps = 25 22:58:27 [INFO] train episode 31836: reward = -63.91, steps = 20 22:58:29 [INFO] train episode 31837: reward = -77.41, steps = 23 22:58:32 [INFO] train episode 31838: reward = -121.21, steps = 22 22:58:33 [INFO] train episode 31839: reward = -79.59, steps = 19 22:58:35 [INFO] train episode 31840: reward = -106.29, steps = 19 22:58:38 [INFO] train episode 31841: reward = -60.66, steps = 29 22:58:39 [INFO] train episode 31842: reward = -93.56, steps = 19 22:58:42 [INFO] train episode 31843: reward = -125.04, steps = 29 22:58:44 [INFO] train episode 31844: reward = -98.36, steps = 29 22:58:48 [INFO] train episode 31845: reward = -123.20, steps = 31 22:58:51 [INFO] train episode 31846: reward = -98.22, steps = 34 22:58:53 [INFO] train episode 31847: reward = -89.66, steps = 28 22:58:57 [INFO] train episode 31848: reward = -121.84, steps = 40 22:58:58 [INFO] train episode 31849: reward = -87.90, steps = 19 22:59:00 [INFO] train episode 31850: reward = -113.71, steps = 22 22:59:02 [INFO] train episode 31851: reward = -83.00, steps = 22 22:59:05 [INFO] train episode 31852: reward = -85.25, steps = 25 22:59:08 [INFO] train episode 31853: reward = -86.28, steps = 31 22:59:10 [INFO] train episode 31854: reward = -95.57, steps = 25 22:59:12 [INFO] train episode 31855: reward = -51.95, steps = 26 22:59:14 [INFO] train episode 31856: reward = -126.71, steps = 20 22:59:17 [INFO] train episode 31857: reward = -107.19, steps = 29 22:59:20 [INFO] train episode 31858: reward = -129.52, steps = 34 22:59:22 [INFO] train episode 31859: reward = -97.06, steps = 25 22:59:24 [INFO] train episode 31860: reward = -76.37, steps = 18 22:59:26 [INFO] train episode 31861: reward = -92.18, steps = 19 22:59:27 [INFO] train episode 31862: reward = -101.72, steps = 20 22:59:29 [INFO] train episode 31863: reward = -113.49, steps = 20 22:59:31 [INFO] train episode 31864: reward = -75.73, steps = 19 22:59:33 [INFO] train episode 31865: reward = -124.06, steps = 25 22:59:36 [INFO] train episode 31866: reward = -88.65, steps = 20 22:59:38 [INFO] train episode 31867: reward = -72.28, steps = 24 22:59:40 [INFO] train episode 31868: reward = -85.76, steps = 20 22:59:42 [INFO] train episode 31869: reward = -77.01, steps = 18 22:59:44 [INFO] train episode 31870: reward = -102.14, steps = 32 22:59:47 [INFO] train episode 31871: reward = -117.33, steps = 25 22:59:49 [INFO] train episode 31872: reward = -87.37, steps = 22 22:59:51 [INFO] train episode 31873: reward = -78.59, steps = 23 22:59:52 [INFO] train episode 31874: reward = -71.21, steps = 19 22:59:54 [INFO] train episode 31875: reward = -76.40, steps = 19 22:59:57 [INFO] train episode 31876: reward = -72.42, steps = 29 23:00:00 [INFO] train episode 31877: reward = -119.25, steps = 30 23:00:03 [INFO] train episode 31878: reward = -63.08, steps = 32 23:00:04 [INFO] train episode 31879: reward = -56.11, steps = 19 23:00:07 [INFO] train episode 31880: reward = -109.89, steps = 31 23:00:09 [INFO] train episode 31881: reward = -103.77, steps = 19 23:00:12 [INFO] train episode 31882: reward = -99.03, steps = 30 23:00:14 [INFO] train episode 31883: reward = -178.26, steps = 20 23:00:15 [INFO] train episode 31884: reward = -95.14, steps = 19 23:00:17 [INFO] train episode 31885: reward = -84.44, steps = 22 23:00:19 [INFO] train episode 31886: reward = -100.44, steps = 24 23:00:21 [INFO] train episode 31887: reward = -110.79, steps = 20 23:00:24 [INFO] train episode 31888: reward = -127.60, steps = 27 23:00:26 [INFO] train episode 31889: reward = -106.72, steps = 25 23:00:29 [INFO] train episode 31890: reward = -87.99, steps = 35 23:00:31 [INFO] train episode 31891: reward = -86.12, steps = 25 23:00:34 [INFO] train episode 31892: reward = -110.97, steps = 27 23:00:36 [INFO] train episode 31893: reward = -158.30, steps = 28 23:00:38 [INFO] train episode 31894: reward = -82.82, steps = 20 23:00:40 [INFO] train episode 31895: reward = -108.09, steps = 23 23:00:43 [INFO] train episode 31896: reward = -75.77, steps = 29 23:00:45 [INFO] train episode 31897: reward = -171.13, steps = 21 23:00:47 [INFO] train episode 31898: reward = -72.92, steps = 21 23:00:49 [INFO] train episode 31899: reward = -117.61, steps = 19 23:00:50 [INFO] train episode 31900: reward = -94.92, steps = 18 23:00:52 [INFO] train episode 31901: reward = -93.77, steps = 19 23:00:54 [INFO] train episode 31902: reward = -54.70, steps = 20 23:00:56 [INFO] train episode 31903: reward = -98.91, steps = 24 23:00:58 [INFO] train episode 31904: reward = -67.91, steps = 23 23:01:00 [INFO] train episode 31905: reward = -94.39, steps = 21 23:01:03 [INFO] train episode 31906: reward = -88.53, steps = 25 23:01:05 [INFO] train episode 31907: reward = -110.57, steps = 30 23:01:09 [INFO] train episode 31908: reward = -95.18, steps = 37 23:01:11 [INFO] train episode 31909: reward = -118.63, steps = 23 23:01:14 [INFO] train episode 31910: reward = -103.43, steps = 34 23:01:16 [INFO] train episode 31911: reward = -96.22, steps = 20 23:01:18 [INFO] train episode 31912: reward = -65.56, steps = 20 23:01:21 [INFO] train episode 31913: reward = -52.05, steps = 37 23:01:23 [INFO] train episode 31914: reward = -89.91, steps = 19 23:01:24 [INFO] train episode 31915: reward = -72.63, steps = 20 23:01:27 [INFO] train episode 31916: reward = -92.50, steps = 27 23:01:29 [INFO] train episode 31917: reward = -85.13, steps = 26 23:01:33 [INFO] train episode 31918: reward = -115.41, steps = 34 23:01:34 [INFO] train episode 31919: reward = -88.26, steps = 18 23:01:36 [INFO] train episode 31920: reward = -112.86, steps = 18 23:01:38 [INFO] train episode 31921: reward = -96.63, steps = 20 23:01:40 [INFO] train episode 31922: reward = -126.59, steps = 29 23:01:43 [INFO] train episode 31923: reward = -137.61, steps = 30 23:01:45 [INFO] train episode 31924: reward = -65.17, steps = 19 23:01:47 [INFO] train episode 31925: reward = -118.44, steps = 20 23:01:49 [INFO] train episode 31926: reward = -55.78, steps = 26 23:01:51 [INFO] train episode 31927: reward = -114.28, steps = 21 23:01:54 [INFO] train episode 31928: reward = -125.61, steps = 29 23:01:56 [INFO] train episode 31929: reward = -89.56, steps = 20 23:01:58 [INFO] train episode 31930: reward = -99.09, steps = 25 23:02:01 [INFO] train episode 31931: reward = -94.49, steps = 30 23:02:02 [INFO] train episode 31932: reward = -128.89, steps = 21 23:02:05 [INFO] train episode 31933: reward = -86.11, steps = 26 23:02:07 [INFO] train episode 31934: reward = -113.03, steps = 24 23:02:10 [INFO] train episode 31935: reward = -85.80, steps = 27 23:02:13 [INFO] train episode 31936: reward = -89.50, steps = 36 23:02:15 [INFO] train episode 31937: reward = -72.64, steps = 19 23:02:17 [INFO] train episode 31938: reward = -80.64, steps = 27 23:02:20 [INFO] train episode 31939: reward = -167.10, steps = 25 23:02:22 [INFO] train episode 31940: reward = -88.96, steps = 23 23:02:24 [INFO] train episode 31941: reward = -86.92, steps = 18 23:02:27 [INFO] train episode 31942: reward = -149.86, steps = 43 23:02:30 [INFO] train episode 31943: reward = -56.58, steps = 27 23:02:32 [INFO] train episode 31944: reward = -96.96, steps = 21 23:02:34 [INFO] train episode 31945: reward = -141.92, steps = 19 23:02:36 [INFO] train episode 31946: reward = -77.11, steps = 20 23:02:38 [INFO] train episode 31947: reward = -64.26, steps = 20 23:02:40 [INFO] train episode 31948: reward = -75.21, steps = 19 23:02:42 [INFO] train episode 31949: reward = -54.90, steps = 21 23:02:44 [INFO] train episode 31950: reward = -109.24, steps = 22 23:02:46 [INFO] train episode 31951: reward = -70.19, steps = 24 23:02:48 [INFO] train episode 31952: reward = -64.37, steps = 19 23:02:50 [INFO] train episode 31953: reward = -120.42, steps = 20 23:02:52 [INFO] train episode 31954: reward = -65.85, steps = 23 23:02:54 [INFO] train episode 31955: reward = -69.50, steps = 28 23:02:56 [INFO] train episode 31956: reward = -62.73, steps = 20 23:03:00 [INFO] train episode 31957: reward = -65.82, steps = 37 23:03:02 [INFO] train episode 31958: reward = -108.26, steps = 28 23:03:04 [INFO] train episode 31959: reward = -78.26, steps = 23 23:03:07 [INFO] train episode 31960: reward = -53.33, steps = 26 23:03:09 [INFO] train episode 31961: reward = -90.38, steps = 30 23:03:11 [INFO] train episode 31962: reward = -129.66, steps = 22 23:03:14 [INFO] train episode 31963: reward = -100.58, steps = 21 23:03:16 [INFO] train episode 31964: reward = -89.15, steps = 22 23:03:20 [INFO] train episode 31965: reward = -103.41, steps = 37 23:03:22 [INFO] train episode 31966: reward = -92.59, steps = 21 23:03:24 [INFO] train episode 31967: reward = -40.66, steps = 22 23:03:26 [INFO] train episode 31968: reward = -127.31, steps = 19 23:03:28 [INFO] train episode 31969: reward = -126.11, steps = 26 23:03:30 [INFO] train episode 31970: reward = -83.88, steps = 20 23:03:34 [INFO] train episode 31971: reward = -133.62, steps = 38 23:03:38 [INFO] train episode 31972: reward = -111.16, steps = 40 23:03:40 [INFO] train episode 31973: reward = -86.32, steps = 19 23:03:42 [INFO] train episode 31974: reward = -96.43, steps = 19 23:03:44 [INFO] train episode 31975: reward = -141.86, steps = 20 23:03:46 [INFO] train episode 31976: reward = -68.59, steps = 21 23:03:48 [INFO] train episode 31977: reward = -70.03, steps = 19 23:03:50 [INFO] train episode 31978: reward = -57.94, steps = 22 23:03:53 [INFO] train episode 31979: reward = -81.30, steps = 28 23:03:56 [INFO] train episode 31980: reward = -102.27, steps = 33 23:03:58 [INFO] train episode 31981: reward = -82.87, steps = 20 23:04:00 [INFO] train episode 31982: reward = -50.22, steps = 20 23:04:02 [INFO] train episode 31983: reward = -94.19, steps = 25 23:04:04 [INFO] train episode 31984: reward = -93.02, steps = 19 23:04:06 [INFO] train episode 31985: reward = -55.86, steps = 19 23:04:08 [INFO] train episode 31986: reward = -40.40, steps = 20 23:04:10 [INFO] train episode 31987: reward = -65.47, steps = 26 23:04:12 [INFO] train episode 31988: reward = -73.13, steps = 20 23:04:16 [INFO] train episode 31989: reward = -160.50, steps = 46 23:04:19 [INFO] train episode 31990: reward = -125.82, steps = 23 23:04:22 [INFO] train episode 31991: reward = -64.94, steps = 34 23:04:24 [INFO] train episode 31992: reward = -93.40, steps = 24 23:04:27 [INFO] train episode 31993: reward = -140.61, steps = 27 23:04:28 [INFO] train episode 31994: reward = -106.64, steps = 17 23:04:30 [INFO] train episode 31995: reward = -115.33, steps = 19 23:04:32 [INFO] train episode 31996: reward = -78.08, steps = 25 23:04:34 [INFO] train episode 31997: reward = -77.19, steps = 22 23:04:37 [INFO] train episode 31998: reward = -98.92, steps = 30 23:04:39 [INFO] train episode 31999: reward = -81.72, steps = 20 23:04:41 [INFO] train episode 32000: reward = -87.27, steps = 20 23:04:43 [INFO] train episode 32001: reward = -79.24, steps = 20 23:04:45 [INFO] train episode 32002: reward = -72.26, steps = 21 23:04:47 [INFO] train episode 32003: reward = -92.27, steps = 26 23:04:49 [INFO] train episode 32004: reward = -87.68, steps = 20 23:04:51 [INFO] train episode 32005: reward = -98.02, steps = 19 23:04:53 [INFO] train episode 32006: reward = -56.55, steps = 21 23:04:55 [INFO] train episode 32007: reward = -129.12, steps = 23 23:04:56 [INFO] train episode 32008: reward = -84.83, steps = 19 23:05:00 [INFO] train episode 32009: reward = -83.48, steps = 31 23:05:02 [INFO] train episode 32010: reward = -67.92, steps = 22 23:05:06 [INFO] train episode 32011: reward = -109.60, steps = 52 23:05:08 [INFO] train episode 32012: reward = -110.33, steps = 18 23:05:11 [INFO] train episode 32013: reward = -79.76, steps = 35 23:05:13 [INFO] train episode 32014: reward = -82.94, steps = 25 23:05:16 [INFO] train episode 32015: reward = -128.57, steps = 21 23:05:19 [INFO] train episode 32016: reward = -112.45, steps = 34 23:05:21 [INFO] train episode 32017: reward = -66.04, steps = 30 23:05:23 [INFO] train episode 32018: reward = -109.67, steps = 23 23:05:25 [INFO] train episode 32019: reward = -77.92, steps = 21 23:05:27 [INFO] train episode 32020: reward = -60.39, steps = 19 23:05:29 [INFO] train episode 32021: reward = -78.78, steps = 22 23:05:32 [INFO] train episode 32022: reward = -117.71, steps = 30 23:05:34 [INFO] train episode 32023: reward = -78.08, steps = 26 23:05:37 [INFO] train episode 32024: reward = -81.05, steps = 27 23:05:40 [INFO] train episode 32025: reward = -88.30, steps = 31 23:05:42 [INFO] train episode 32026: reward = -97.06, steps = 23 23:05:44 [INFO] train episode 32027: reward = -113.17, steps = 19 23:05:46 [INFO] train episode 32028: reward = -108.88, steps = 24 23:05:48 [INFO] train episode 32029: reward = -40.78, steps = 17 23:05:51 [INFO] train episode 32030: reward = -67.98, steps = 32 23:05:53 [INFO] train episode 32031: reward = -85.29, steps = 22 23:05:54 [INFO] train episode 32032: reward = -86.05, steps = 19 23:05:56 [INFO] train episode 32033: reward = -81.49, steps = 22 23:05:58 [INFO] train episode 32034: reward = -190.60, steps = 18 23:06:00 [INFO] train episode 32035: reward = -102.11, steps = 19 23:06:01 [INFO] train episode 32036: reward = -109.08, steps = 19 23:06:05 [INFO] train episode 32037: reward = -160.96, steps = 36 23:06:07 [INFO] train episode 32038: reward = -33.64, steps = 30 23:06:09 [INFO] train episode 32039: reward = -171.89, steps = 19 23:06:12 [INFO] train episode 32040: reward = -101.95, steps = 26 23:06:13 [INFO] train episode 32041: reward = -68.38, steps = 19 23:06:16 [INFO] train episode 32042: reward = -188.32, steps = 30 23:06:18 [INFO] train episode 32043: reward = -66.90, steps = 19 23:06:19 [INFO] train episode 32044: reward = -125.81, steps = 18 23:06:22 [INFO] train episode 32045: reward = -94.54, steps = 22 23:06:23 [INFO] train episode 32046: reward = -110.89, steps = 19 23:06:25 [INFO] train episode 32047: reward = -67.71, steps = 19 23:06:27 [INFO] train episode 32048: reward = -107.98, steps = 25 23:06:30 [INFO] train episode 32049: reward = -92.42, steps = 27 23:06:32 [INFO] train episode 32050: reward = -92.03, steps = 23 23:06:34 [INFO] train episode 32051: reward = -144.76, steps = 27 23:06:37 [INFO] train episode 32052: reward = -89.16, steps = 26 23:06:39 [INFO] train episode 32053: reward = -106.58, steps = 25 23:06:41 [INFO] train episode 32054: reward = -83.83, steps = 19 23:06:43 [INFO] train episode 32055: reward = -122.98, steps = 18 23:06:45 [INFO] train episode 32056: reward = -98.66, steps = 31 23:06:47 [INFO] train episode 32057: reward = -119.63, steps = 20 23:06:50 [INFO] train episode 32058: reward = -105.88, steps = 37 23:06:52 [INFO] train episode 32059: reward = -74.54, steps = 18 23:06:55 [INFO] train episode 32060: reward = -124.23, steps = 33 23:06:57 [INFO] train episode 32061: reward = -63.41, steps = 24 23:07:00 [INFO] train episode 32062: reward = -68.25, steps = 29 23:07:02 [INFO] train episode 32063: reward = -119.14, steps = 23 23:07:05 [INFO] train episode 32064: reward = -129.51, steps = 29 23:07:07 [INFO] train episode 32065: reward = -97.45, steps = 27 23:07:10 [INFO] train episode 32066: reward = -144.82, steps = 31 23:07:12 [INFO] train episode 32067: reward = -83.74, steps = 23 23:07:14 [INFO] train episode 32068: reward = -93.11, steps = 21 23:07:16 [INFO] train episode 32069: reward = -116.63, steps = 21 23:07:18 [INFO] train episode 32070: reward = -100.00, steps = 19 23:07:21 [INFO] train episode 32071: reward = -89.93, steps = 34 23:07:23 [INFO] train episode 32072: reward = -74.37, steps = 29 23:07:26 [INFO] train episode 32073: reward = -63.32, steps = 26 23:07:28 [INFO] train episode 32074: reward = -120.58, steps = 26 23:07:30 [INFO] train episode 32075: reward = -77.32, steps = 23 23:07:32 [INFO] train episode 32076: reward = -84.38, steps = 21 23:07:36 [INFO] train episode 32077: reward = -114.62, steps = 48 23:07:38 [INFO] train episode 32078: reward = -120.87, steps = 20 23:07:42 [INFO] train episode 32079: reward = -158.16, steps = 34 23:07:43 [INFO] train episode 32080: reward = -126.74, steps = 22 23:07:46 [INFO] train episode 32081: reward = -67.69, steps = 24 23:07:48 [INFO] train episode 32082: reward = -89.11, steps = 24 23:07:50 [INFO] train episode 32083: reward = -117.46, steps = 25 23:07:53 [INFO] train episode 32084: reward = -149.33, steps = 30 23:07:55 [INFO] train episode 32085: reward = -88.15, steps = 23 23:07:56 [INFO] train episode 32086: reward = -70.00, steps = 19 23:07:59 [INFO] train episode 32087: reward = -156.32, steps = 28 23:08:01 [INFO] train episode 32088: reward = -127.60, steps = 24 23:08:04 [INFO] train episode 32089: reward = -61.23, steps = 28 23:08:06 [INFO] train episode 32090: reward = -86.16, steps = 21 23:08:08 [INFO] train episode 32091: reward = -139.73, steps = 26 23:08:10 [INFO] train episode 32092: reward = -77.39, steps = 23 23:08:13 [INFO] train episode 32093: reward = -128.40, steps = 30 23:08:15 [INFO] train episode 32094: reward = -58.03, steps = 20 23:08:17 [INFO] train episode 32095: reward = -76.61, steps = 18 23:08:19 [INFO] train episode 32096: reward = -91.50, steps = 24 23:08:21 [INFO] train episode 32097: reward = -93.01, steps = 25 23:08:24 [INFO] train episode 32098: reward = -88.97, steps = 30 23:08:26 [INFO] train episode 32099: reward = -67.25, steps = 25 23:08:28 [INFO] train episode 32100: reward = -119.21, steps = 19 23:08:30 [INFO] train episode 32101: reward = -63.51, steps = 21 23:08:32 [INFO] train episode 32102: reward = -120.42, steps = 23 23:08:35 [INFO] train episode 32103: reward = -128.32, steps = 23 23:08:37 [INFO] train episode 32104: reward = -93.80, steps = 26 23:08:40 [INFO] train episode 32105: reward = -113.60, steps = 25 23:08:42 [INFO] train episode 32106: reward = -90.43, steps = 21 23:08:44 [INFO] train episode 32107: reward = -60.82, steps = 19 23:08:46 [INFO] train episode 32108: reward = -92.90, steps = 22 23:08:48 [INFO] train episode 32109: reward = -103.80, steps = 22 23:08:50 [INFO] train episode 32110: reward = -57.89, steps = 22 23:08:52 [INFO] train episode 32111: reward = -74.98, steps = 17 23:08:54 [INFO] train episode 32112: reward = -124.17, steps = 28 23:08:56 [INFO] train episode 32113: reward = -102.51, steps = 20 23:08:58 [INFO] train episode 32114: reward = -181.01, steps = 24 23:09:01 [INFO] train episode 32115: reward = -99.01, steps = 34 23:09:03 [INFO] train episode 32116: reward = -71.31, steps = 19 23:09:05 [INFO] train episode 32117: reward = -77.10, steps = 19 23:09:08 [INFO] train episode 32118: reward = -91.20, steps = 21 23:09:11 [INFO] train episode 32119: reward = -87.40, steps = 30 23:09:13 [INFO] train episode 32120: reward = -86.68, steps = 21 23:09:15 [INFO] train episode 32121: reward = -87.05, steps = 20 23:09:17 [INFO] train episode 32122: reward = -136.99, steps = 19 23:09:19 [INFO] train episode 32123: reward = -69.23, steps = 20 23:09:20 [INFO] train episode 32124: reward = -68.79, steps = 19 23:09:23 [INFO] train episode 32125: reward = -50.87, steps = 31 23:09:26 [INFO] train episode 32126: reward = -109.93, steps = 30 23:09:28 [INFO] train episode 32127: reward = -111.00, steps = 26 23:09:30 [INFO] train episode 32128: reward = -131.65, steps = 22 23:09:33 [INFO] train episode 32129: reward = -86.79, steps = 26 23:09:35 [INFO] train episode 32130: reward = -99.88, steps = 22 23:09:36 [INFO] train episode 32131: reward = -69.76, steps = 20 23:09:38 [INFO] train episode 32132: reward = -52.99, steps = 21 23:09:40 [INFO] train episode 32133: reward = -66.98, steps = 19 23:09:42 [INFO] train episode 32134: reward = -136.79, steps = 23 23:09:44 [INFO] train episode 32135: reward = -56.46, steps = 19 23:09:47 [INFO] train episode 32136: reward = -82.33, steps = 36 23:09:49 [INFO] train episode 32137: reward = -66.69, steps = 23 23:09:52 [INFO] train episode 32138: reward = -133.54, steps = 25 23:09:54 [INFO] train episode 32139: reward = -90.31, steps = 26 23:09:56 [INFO] train episode 32140: reward = -104.10, steps = 24 23:09:58 [INFO] train episode 32141: reward = -124.85, steps = 20 23:10:00 [INFO] train episode 32142: reward = -105.86, steps = 25 23:10:03 [INFO] train episode 32143: reward = -97.20, steps = 24 23:10:05 [INFO] train episode 32144: reward = -162.52, steps = 30 23:10:08 [INFO] train episode 32145: reward = -92.30, steps = 33 23:10:10 [INFO] train episode 32146: reward = -81.37, steps = 23 23:10:14 [INFO] train episode 32147: reward = -154.47, steps = 31 23:10:16 [INFO] train episode 32148: reward = -121.96, steps = 26 23:10:18 [INFO] train episode 32149: reward = -120.50, steps = 19 23:10:20 [INFO] train episode 32150: reward = -89.67, steps = 30 23:10:24 [INFO] train episode 32151: reward = -112.81, steps = 37 23:10:25 [INFO] train episode 32152: reward = -76.79, steps = 18 23:10:27 [INFO] train episode 32153: reward = -127.39, steps = 17 23:10:30 [INFO] train episode 32154: reward = -86.61, steps = 35 23:10:33 [INFO] train episode 32155: reward = -127.13, steps = 34 23:10:37 [INFO] train episode 32156: reward = -147.47, steps = 37 23:10:38 [INFO] train episode 32157: reward = -104.73, steps = 20 23:10:40 [INFO] train episode 32158: reward = -102.48, steps = 21 23:10:43 [INFO] train episode 32159: reward = -61.20, steps = 27 23:10:45 [INFO] train episode 32160: reward = -87.31, steps = 19 23:10:47 [INFO] train episode 32161: reward = -60.82, steps = 21 23:10:49 [INFO] train episode 32162: reward = -152.91, steps = 21 23:10:51 [INFO] train episode 32163: reward = -94.57, steps = 20 23:10:52 [INFO] train episode 32164: reward = -138.03, steps = 17 23:10:56 [INFO] train episode 32165: reward = -75.37, steps = 38 23:10:58 [INFO] train episode 32166: reward = -124.58, steps = 25 23:11:01 [INFO] train episode 32167: reward = -113.08, steps = 31 23:11:04 [INFO] train episode 32168: reward = -120.34, steps = 30 23:11:06 [INFO] train episode 32169: reward = -64.42, steps = 20 23:11:08 [INFO] train episode 32170: reward = -78.51, steps = 21 23:11:10 [INFO] train episode 32171: reward = -71.48, steps = 21 23:11:11 [INFO] train episode 32172: reward = -67.15, steps = 19 23:11:14 [INFO] train episode 32173: reward = -81.22, steps = 24 23:11:15 [INFO] train episode 32174: reward = -70.10, steps = 19 23:11:17 [INFO] train episode 32175: reward = -59.37, steps = 21 23:11:19 [INFO] train episode 32176: reward = -79.33, steps = 19 23:11:21 [INFO] train episode 32177: reward = -57.08, steps = 21 23:11:24 [INFO] train episode 32178: reward = -69.67, steps = 25 23:11:26 [INFO] train episode 32179: reward = -101.09, steps = 19 23:11:28 [INFO] train episode 32180: reward = -121.46, steps = 24 23:11:31 [INFO] train episode 32181: reward = -106.72, steps = 30 23:11:33 [INFO] train episode 32182: reward = -79.02, steps = 21 23:11:35 [INFO] train episode 32183: reward = -88.82, steps = 19 23:11:38 [INFO] train episode 32184: reward = -182.99, steps = 28 23:11:41 [INFO] train episode 32185: reward = -78.36, steps = 28 23:11:43 [INFO] train episode 32186: reward = -72.08, steps = 25 23:11:45 [INFO] train episode 32187: reward = -74.19, steps = 20 23:11:48 [INFO] train episode 32188: reward = -119.68, steps = 36 23:11:50 [INFO] train episode 32189: reward = -121.24, steps = 26 23:11:52 [INFO] train episode 32190: reward = -71.99, steps = 18 23:11:54 [INFO] train episode 32191: reward = -73.73, steps = 20 23:11:56 [INFO] train episode 32192: reward = -78.83, steps = 22 23:11:58 [INFO] train episode 32193: reward = -108.94, steps = 21 23:12:00 [INFO] train episode 32194: reward = -68.53, steps = 19 23:12:03 [INFO] train episode 32195: reward = -132.42, steps = 32 23:12:04 [INFO] train episode 32196: reward = -115.46, steps = 19 23:12:07 [INFO] train episode 32197: reward = -47.29, steps = 33 23:12:10 [INFO] train episode 32198: reward = -45.81, steps = 30 23:12:12 [INFO] train episode 32199: reward = -97.68, steps = 20 23:12:14 [INFO] train episode 32200: reward = -113.61, steps = 23 23:12:17 [INFO] train episode 32201: reward = -102.91, steps = 28 23:12:19 [INFO] train episode 32202: reward = -150.21, steps = 21 23:12:20 [INFO] train episode 32203: reward = -61.34, steps = 19 23:12:23 [INFO] train episode 32204: reward = -71.23, steps = 31 23:12:25 [INFO] train episode 32205: reward = -141.53, steps = 19 23:12:26 [INFO] train episode 32206: reward = -81.22, steps = 19 23:12:29 [INFO] train episode 32207: reward = -86.13, steps = 20 23:12:31 [INFO] train episode 32208: reward = -178.63, steps = 30 23:12:33 [INFO] train episode 32209: reward = -84.91, steps = 20 23:12:36 [INFO] train episode 32210: reward = -97.36, steps = 23 23:12:38 [INFO] train episode 32211: reward = -78.40, steps = 23 23:12:40 [INFO] train episode 32212: reward = -74.85, steps = 22 23:12:42 [INFO] train episode 32213: reward = -103.84, steps = 27 23:12:44 [INFO] train episode 32214: reward = -71.61, steps = 18 23:12:46 [INFO] train episode 32215: reward = -107.42, steps = 22 23:12:49 [INFO] train episode 32216: reward = -119.88, steps = 32 23:12:51 [INFO] train episode 32217: reward = -127.58, steps = 26 23:12:53 [INFO] train episode 32218: reward = -49.70, steps = 21 23:12:55 [INFO] train episode 32219: reward = -90.76, steps = 20 23:12:57 [INFO] train episode 32220: reward = -108.36, steps = 24 23:12:59 [INFO] train episode 32221: reward = -122.21, steps = 21 23:13:01 [INFO] train episode 32222: reward = -73.41, steps = 20 23:13:04 [INFO] train episode 32223: reward = -115.07, steps = 27 23:13:06 [INFO] train episode 32224: reward = -124.34, steps = 21 23:13:08 [INFO] train episode 32225: reward = -78.71, steps = 23 23:13:09 [INFO] train episode 32226: reward = -74.60, steps = 20 23:13:13 [INFO] train episode 32227: reward = -118.53, steps = 34 23:13:14 [INFO] train episode 32228: reward = -84.91, steps = 20 23:13:16 [INFO] train episode 32229: reward = -79.96, steps = 21 23:13:19 [INFO] train episode 32230: reward = -60.51, steps = 21 23:13:20 [INFO] train episode 32231: reward = -107.39, steps = 19 23:13:24 [INFO] train episode 32232: reward = -99.18, steps = 37 23:13:26 [INFO] train episode 32233: reward = -74.88, steps = 30 23:13:29 [INFO] train episode 32234: reward = -42.81, steps = 30 23:13:31 [INFO] train episode 32235: reward = -102.67, steps = 20 23:13:33 [INFO] train episode 32236: reward = -107.72, steps = 21 23:13:35 [INFO] train episode 32237: reward = -94.58, steps = 24 23:13:38 [INFO] train episode 32238: reward = -79.39, steps = 32 23:13:40 [INFO] train episode 32239: reward = -106.49, steps = 23 23:13:42 [INFO] train episode 32240: reward = -117.37, steps = 20 23:13:44 [INFO] train episode 32241: reward = -77.16, steps = 19 23:13:46 [INFO] train episode 32242: reward = -75.46, steps = 25 23:13:48 [INFO] train episode 32243: reward = -100.76, steps = 19 23:13:50 [INFO] train episode 32244: reward = -82.19, steps = 25 23:13:53 [INFO] train episode 32245: reward = -110.42, steps = 22 23:13:55 [INFO] train episode 32246: reward = -84.17, steps = 25 23:13:57 [INFO] train episode 32247: reward = -77.45, steps = 19 23:13:58 [INFO] train episode 32248: reward = -88.02, steps = 20 23:14:01 [INFO] train episode 32249: reward = -87.12, steps = 23 23:14:03 [INFO] train episode 32250: reward = -104.65, steps = 24 23:14:05 [INFO] train episode 32251: reward = -68.67, steps = 20 23:14:06 [INFO] train episode 32252: reward = -75.19, steps = 19 23:14:09 [INFO] train episode 32253: reward = -78.63, steps = 20 23:14:11 [INFO] train episode 32254: reward = -73.31, steps = 26 23:14:15 [INFO] train episode 32255: reward = -150.31, steps = 41 23:14:16 [INFO] train episode 32256: reward = -76.95, steps = 19 23:14:19 [INFO] train episode 32257: reward = -78.89, steps = 23 23:14:20 [INFO] train episode 32258: reward = -101.01, steps = 16 23:14:24 [INFO] train episode 32259: reward = -83.52, steps = 44 23:14:27 [INFO] train episode 32260: reward = -184.85, steps = 23 23:14:28 [INFO] train episode 32261: reward = -148.54, steps = 19 23:14:32 [INFO] train episode 32262: reward = -212.64, steps = 42 23:14:34 [INFO] train episode 32263: reward = -69.24, steps = 21 23:14:36 [INFO] train episode 32264: reward = -103.29, steps = 20 23:14:40 [INFO] train episode 32265: reward = -69.31, steps = 41 23:14:42 [INFO] train episode 32266: reward = -63.91, steps = 22 23:14:45 [INFO] train episode 32267: reward = -84.87, steps = 27 23:14:47 [INFO] train episode 32268: reward = -77.78, steps = 19 23:14:49 [INFO] train episode 32269: reward = -108.62, steps = 27 23:14:53 [INFO] train episode 32270: reward = -125.65, steps = 34 23:14:54 [INFO] train episode 32271: reward = -68.73, steps = 19 23:14:56 [INFO] train episode 32272: reward = -97.03, steps = 22 23:14:58 [INFO] train episode 32273: reward = -136.93, steps = 18 23:15:01 [INFO] train episode 32274: reward = -98.83, steps = 24 23:15:03 [INFO] train episode 32275: reward = -69.34, steps = 21 23:15:04 [INFO] train episode 32276: reward = -105.82, steps = 18 23:15:07 [INFO] train episode 32277: reward = -101.14, steps = 33 23:15:10 [INFO] train episode 32278: reward = -153.76, steps = 25 23:15:12 [INFO] train episode 32279: reward = -83.21, steps = 29 23:15:14 [INFO] train episode 32280: reward = -91.75, steps = 20 23:15:19 [INFO] train episode 32281: reward = -143.05, steps = 47 23:15:22 [INFO] train episode 32282: reward = -118.31, steps = 32 23:15:24 [INFO] train episode 32283: reward = -145.77, steps = 25 23:15:26 [INFO] train episode 32284: reward = -80.59, steps = 19 23:15:28 [INFO] train episode 32285: reward = -159.24, steps = 23 23:15:29 [INFO] train episode 32286: reward = -105.38, steps = 20 23:15:31 [INFO] train episode 32287: reward = -87.59, steps = 19 23:15:34 [INFO] train episode 32288: reward = -98.51, steps = 20 23:15:35 [INFO] train episode 32289: reward = -93.84, steps = 18 23:15:38 [INFO] train episode 32290: reward = -88.49, steps = 26 23:15:40 [INFO] train episode 32291: reward = -85.18, steps = 24 23:15:42 [INFO] train episode 32292: reward = -86.81, steps = 19 23:15:44 [INFO] train episode 32293: reward = -148.03, steps = 31 23:15:46 [INFO] train episode 32294: reward = -202.81, steps = 21 23:15:49 [INFO] train episode 32295: reward = -103.94, steps = 28 23:15:52 [INFO] train episode 32296: reward = -89.28, steps = 30 23:15:56 [INFO] train episode 32297: reward = -194.62, steps = 42 23:15:57 [INFO] train episode 32298: reward = -100.94, steps = 20 23:15:59 [INFO] train episode 32299: reward = -85.36, steps = 20 23:16:01 [INFO] train episode 32300: reward = -55.96, steps = 21 23:16:03 [INFO] train episode 32301: reward = -83.94, steps = 19 23:16:05 [INFO] train episode 32302: reward = -53.07, steps = 26 23:16:08 [INFO] train episode 32303: reward = -88.64, steps = 25 23:16:10 [INFO] train episode 32304: reward = -60.45, steps = 20 23:16:11 [INFO] train episode 32305: reward = -85.98, steps = 19 23:16:15 [INFO] train episode 32306: reward = -94.89, steps = 36 23:16:17 [INFO] train episode 32307: reward = -117.57, steps = 20 23:16:18 [INFO] train episode 32308: reward = -93.43, steps = 20 23:16:20 [INFO] train episode 32309: reward = -85.21, steps = 21 23:16:22 [INFO] train episode 32310: reward = -107.76, steps = 20 23:16:24 [INFO] train episode 32311: reward = -73.17, steps = 18 23:16:27 [INFO] train episode 32312: reward = -157.93, steps = 33 23:16:29 [INFO] train episode 32313: reward = -116.83, steps = 23 23:16:31 [INFO] train episode 32314: reward = -157.73, steps = 22 23:16:34 [INFO] train episode 32315: reward = -67.38, steps = 28 23:16:35 [INFO] train episode 32316: reward = -97.50, steps = 19 23:16:37 [INFO] train episode 32317: reward = -73.73, steps = 19 23:16:39 [INFO] train episode 32318: reward = -142.44, steps = 25 23:16:43 [INFO] train episode 32319: reward = -111.45, steps = 31 23:16:45 [INFO] train episode 32320: reward = -92.99, steps = 22 23:16:46 [INFO] train episode 32321: reward = -90.63, steps = 20 23:16:49 [INFO] train episode 32322: reward = -101.46, steps = 27 23:16:51 [INFO] train episode 32323: reward = -59.60, steps = 22 23:16:54 [INFO] train episode 32324: reward = -204.93, steps = 31 23:16:56 [INFO] train episode 32325: reward = -94.02, steps = 22 23:16:58 [INFO] train episode 32326: reward = -85.67, steps = 19 23:16:59 [INFO] train episode 32327: reward = -78.88, steps = 20 23:17:02 [INFO] train episode 32328: reward = -119.14, steps = 29 23:17:04 [INFO] train episode 32329: reward = -98.07, steps = 25 23:17:07 [INFO] train episode 32330: reward = -79.59, steps = 27 23:17:08 [INFO] train episode 32331: reward = -57.24, steps = 20 23:17:10 [INFO] train episode 32332: reward = -94.11, steps = 19 23:17:13 [INFO] train episode 32333: reward = -129.43, steps = 28 23:17:15 [INFO] train episode 32334: reward = -95.20, steps = 19 23:17:17 [INFO] train episode 32335: reward = -99.39, steps = 21 23:17:20 [INFO] train episode 32336: reward = -130.81, steps = 33 23:17:21 [INFO] train episode 32337: reward = -61.30, steps = 20 23:17:23 [INFO] train episode 32338: reward = -86.87, steps = 23 23:17:26 [INFO] train episode 32339: reward = -104.54, steps = 34 23:17:28 [INFO] train episode 32340: reward = -135.43, steps = 19 23:17:30 [INFO] train episode 32341: reward = -95.48, steps = 20 23:17:32 [INFO] train episode 32342: reward = -113.93, steps = 23 23:17:36 [INFO] train episode 32343: reward = -131.01, steps = 39 23:17:40 [INFO] train episode 32344: reward = -75.25, steps = 37 23:17:42 [INFO] train episode 32345: reward = -100.70, steps = 24 23:17:44 [INFO] train episode 32346: reward = -80.29, steps = 25 23:17:47 [INFO] train episode 32347: reward = -164.36, steps = 26 23:17:49 [INFO] train episode 32348: reward = -72.56, steps = 18 23:17:50 [INFO] train episode 32349: reward = -68.75, steps = 20 23:17:52 [INFO] train episode 32350: reward = -67.73, steps = 19 23:17:54 [INFO] train episode 32351: reward = -90.37, steps = 23 23:17:57 [INFO] train episode 32352: reward = -135.50, steps = 29 23:17:58 [INFO] train episode 32353: reward = -80.96, steps = 19 23:18:00 [INFO] train episode 32354: reward = -75.31, steps = 20 23:18:02 [INFO] train episode 32355: reward = -156.88, steps = 20 23:18:04 [INFO] train episode 32356: reward = -78.85, steps = 20 23:18:07 [INFO] train episode 32357: reward = -100.29, steps = 27 23:18:09 [INFO] train episode 32358: reward = -103.17, steps = 21 23:18:12 [INFO] train episode 32359: reward = -65.26, steps = 35 23:18:14 [INFO] train episode 32360: reward = -107.00, steps = 29 23:18:17 [INFO] train episode 32361: reward = -79.86, steps = 26 23:18:18 [INFO] train episode 32362: reward = -174.75, steps = 20 23:18:21 [INFO] train episode 32363: reward = -66.65, steps = 20 23:18:22 [INFO] train episode 32364: reward = -49.82, steps = 19 23:18:24 [INFO] train episode 32365: reward = -152.98, steps = 20 23:18:26 [INFO] train episode 32366: reward = -184.58, steps = 23 23:18:28 [INFO] train episode 32367: reward = -101.97, steps = 19 23:18:30 [INFO] train episode 32368: reward = -76.66, steps = 19 23:18:31 [INFO] train episode 32369: reward = -69.79, steps = 22 23:18:33 [INFO] train episode 32370: reward = -108.40, steps = 19 23:18:35 [INFO] train episode 32371: reward = -94.46, steps = 25 23:18:38 [INFO] train episode 32372: reward = -86.72, steps = 18 23:18:41 [INFO] train episode 32373: reward = -138.12, steps = 35 23:18:43 [INFO] train episode 32374: reward = -108.08, steps = 27 23:18:46 [INFO] train episode 32375: reward = -162.82, steps = 32 23:18:48 [INFO] train episode 32376: reward = -72.69, steps = 24 23:18:51 [INFO] train episode 32377: reward = -183.16, steps = 34 23:18:53 [INFO] train episode 32378: reward = -107.53, steps = 18 23:18:56 [INFO] train episode 32379: reward = -123.43, steps = 23 23:18:58 [INFO] train episode 32380: reward = -91.47, steps = 27 23:19:01 [INFO] train episode 32381: reward = -69.81, steps = 28 23:19:04 [INFO] train episode 32382: reward = -95.82, steps = 30 23:19:06 [INFO] train episode 32383: reward = -118.13, steps = 20 23:19:08 [INFO] train episode 32384: reward = -87.52, steps = 26 23:19:11 [INFO] train episode 32385: reward = -99.49, steps = 29 23:19:13 [INFO] train episode 32386: reward = -83.35, steps = 20 23:19:15 [INFO] train episode 32387: reward = -85.10, steps = 19 23:19:17 [INFO] train episode 32388: reward = -90.51, steps = 25 23:19:18 [INFO] train episode 32389: reward = -131.76, steps = 19 23:19:20 [INFO] train episode 32390: reward = -82.20, steps = 20 23:19:22 [INFO] train episode 32391: reward = -130.19, steps = 20 23:19:24 [INFO] train episode 32392: reward = -91.63, steps = 19 23:19:26 [INFO] train episode 32393: reward = -62.05, steps = 19 23:19:28 [INFO] train episode 32394: reward = -82.17, steps = 19 23:19:30 [INFO] train episode 32395: reward = -125.65, steps = 18 23:19:32 [INFO] train episode 32396: reward = -128.54, steps = 28 23:19:35 [INFO] train episode 32397: reward = -90.80, steps = 27 23:19:36 [INFO] train episode 32398: reward = -124.82, steps = 21 23:19:40 [INFO] train episode 32399: reward = -120.19, steps = 37 23:19:42 [INFO] train episode 32400: reward = -129.72, steps = 26 23:19:45 [INFO] train episode 32401: reward = -122.92, steps = 27 23:19:47 [INFO] train episode 32402: reward = -136.07, steps = 19 23:19:49 [INFO] train episode 32403: reward = -117.42, steps = 25 23:19:52 [INFO] train episode 32404: reward = -81.13, steps = 37 23:19:54 [INFO] train episode 32405: reward = -90.11, steps = 20 23:19:56 [INFO] train episode 32406: reward = -181.20, steps = 20 23:19:58 [INFO] train episode 32407: reward = -153.02, steps = 23 23:20:00 [INFO] train episode 32408: reward = -78.56, steps = 21 23:20:02 [INFO] train episode 32409: reward = -94.44, steps = 20 23:20:04 [INFO] train episode 32410: reward = -80.38, steps = 28 23:20:06 [INFO] train episode 32411: reward = -83.29, steps = 20 23:20:08 [INFO] train episode 32412: reward = -102.36, steps = 22 23:20:10 [INFO] train episode 32413: reward = -128.11, steps = 20 23:20:12 [INFO] train episode 32414: reward = -134.06, steps = 25 23:20:16 [INFO] train episode 32415: reward = -167.30, steps = 46 23:20:18 [INFO] train episode 32416: reward = -119.10, steps = 20 23:20:20 [INFO] train episode 32417: reward = -81.13, steps = 20 23:20:22 [INFO] train episode 32418: reward = -90.58, steps = 20 23:20:24 [INFO] train episode 32419: reward = -57.75, steps = 18 23:20:26 [INFO] train episode 32420: reward = -134.78, steps = 26 23:20:29 [INFO] train episode 32421: reward = -91.23, steps = 28 23:20:30 [INFO] train episode 32422: reward = -95.05, steps = 18 23:20:32 [INFO] train episode 32423: reward = -65.78, steps = 20 23:20:35 [INFO] train episode 32424: reward = -107.68, steps = 23 23:20:37 [INFO] train episode 32425: reward = -61.94, steps = 22 23:20:39 [INFO] train episode 32426: reward = -106.12, steps = 19 23:20:41 [INFO] train episode 32427: reward = -104.97, steps = 20 23:20:44 [INFO] train episode 32428: reward = -150.62, steps = 23 23:20:47 [INFO] train episode 32429: reward = -99.46, steps = 33 23:20:51 [INFO] train episode 32430: reward = -66.86, steps = 28 23:20:54 [INFO] train episode 32431: reward = -64.10, steps = 19 23:20:56 [INFO] train episode 32432: reward = -86.79, steps = 20 23:20:59 [INFO] train episode 32433: reward = -118.32, steps = 24 23:21:02 [INFO] train episode 32434: reward = -59.54, steps = 23 23:21:04 [INFO] train episode 32435: reward = -97.82, steps = 24 23:21:06 [INFO] train episode 32436: reward = -85.00, steps = 21 23:21:08 [INFO] train episode 32437: reward = -68.80, steps = 22 23:21:10 [INFO] train episode 32438: reward = -81.61, steps = 19 23:21:14 [INFO] train episode 32439: reward = -132.07, steps = 39 23:21:16 [INFO] train episode 32440: reward = -97.82, steps = 19 23:21:18 [INFO] train episode 32441: reward = -78.88, steps = 20 23:21:21 [INFO] train episode 32442: reward = -99.07, steps = 33 23:21:25 [INFO] train episode 32443: reward = -205.75, steps = 39 23:21:27 [INFO] train episode 32444: reward = -74.95, steps = 19 23:21:29 [INFO] train episode 32445: reward = -82.45, steps = 26 23:21:32 [INFO] train episode 32446: reward = -115.02, steps = 33 23:21:34 [INFO] train episode 32447: reward = -71.01, steps = 19 23:21:36 [INFO] train episode 32448: reward = -81.57, steps = 29 23:21:39 [INFO] train episode 32449: reward = -107.24, steps = 23 23:21:40 [INFO] train episode 32450: reward = -111.73, steps = 20 23:21:43 [INFO] train episode 32451: reward = -83.32, steps = 28 23:21:45 [INFO] train episode 32452: reward = -87.67, steps = 21 23:21:49 [INFO] train episode 32453: reward = -72.68, steps = 27 23:21:52 [INFO] train episode 32454: reward = -91.67, steps = 32 23:21:54 [INFO] train episode 32455: reward = -62.26, steps = 21 23:21:56 [INFO] train episode 32456: reward = -68.17, steps = 18 23:21:58 [INFO] train episode 32457: reward = -84.43, steps = 20 23:22:00 [INFO] train episode 32458: reward = -113.61, steps = 19 23:22:02 [INFO] train episode 32459: reward = -93.14, steps = 21 23:22:05 [INFO] train episode 32460: reward = -139.96, steps = 21 23:22:09 [INFO] train episode 32461: reward = -106.64, steps = 33 23:22:13 [INFO] train episode 32462: reward = -186.61, steps = 32 23:22:15 [INFO] train episode 32463: reward = -111.23, steps = 19 23:22:18 [INFO] train episode 32464: reward = -97.52, steps = 29 23:22:21 [INFO] train episode 32465: reward = -121.64, steps = 34 23:22:23 [INFO] train episode 32466: reward = -82.03, steps = 25 23:22:26 [INFO] train episode 32467: reward = -104.34, steps = 25 23:22:27 [INFO] train episode 32468: reward = -102.77, steps = 19 23:22:29 [INFO] train episode 32469: reward = -76.59, steps = 19 23:22:31 [INFO] train episode 32470: reward = -69.62, steps = 24 23:22:33 [INFO] train episode 32471: reward = -95.15, steps = 23 23:22:35 [INFO] train episode 32472: reward = -58.51, steps = 23 23:22:38 [INFO] train episode 32473: reward = -135.39, steps = 23 23:22:39 [INFO] train episode 32474: reward = -43.05, steps = 18 23:22:41 [INFO] train episode 32475: reward = -111.10, steps = 20 23:22:43 [INFO] train episode 32476: reward = -61.06, steps = 22 23:22:47 [INFO] train episode 32477: reward = -57.40, steps = 34 23:22:48 [INFO] train episode 32478: reward = -85.84, steps = 22 23:22:51 [INFO] train episode 32479: reward = -114.97, steps = 28 23:22:53 [INFO] train episode 32480: reward = -56.36, steps = 19 23:22:55 [INFO] train episode 32481: reward = -107.58, steps = 20 23:22:57 [INFO] train episode 32482: reward = -100.50, steps = 26 23:22:59 [INFO] train episode 32483: reward = -88.82, steps = 21 23:23:02 [INFO] train episode 32484: reward = -104.03, steps = 27 23:23:03 [INFO] train episode 32485: reward = -70.95, steps = 20 23:23:06 [INFO] train episode 32486: reward = -64.00, steps = 34 23:23:08 [INFO] train episode 32487: reward = -110.95, steps = 21 23:23:11 [INFO] train episode 32488: reward = -98.57, steps = 26 23:23:15 [INFO] train episode 32489: reward = -83.04, steps = 26 23:23:17 [INFO] train episode 32490: reward = -92.17, steps = 25 23:23:19 [INFO] train episode 32491: reward = -69.32, steps = 22 23:23:21 [INFO] train episode 32492: reward = -76.81, steps = 19 23:23:24 [INFO] train episode 32493: reward = -95.03, steps = 32 23:23:26 [INFO] train episode 32494: reward = -51.73, steps = 21 23:23:28 [INFO] train episode 32495: reward = -100.98, steps = 21 23:23:31 [INFO] train episode 32496: reward = -95.24, steps = 25 23:23:34 [INFO] train episode 32497: reward = -73.00, steps = 30 23:23:37 [INFO] train episode 32498: reward = -93.96, steps = 27 23:23:39 [INFO] train episode 32499: reward = -62.16, steps = 20 23:23:41 [INFO] train episode 32500: reward = -121.01, steps = 24 23:23:46 [INFO] train episode 32501: reward = -168.33, steps = 48 23:23:47 [INFO] train episode 32502: reward = -79.31, steps = 20 23:23:50 [INFO] train episode 32503: reward = -152.31, steps = 29 23:23:55 [INFO] train episode 32504: reward = -137.10, steps = 39 23:23:58 [INFO] train episode 32505: reward = -75.50, steps = 24 23:24:00 [INFO] train episode 32506: reward = -89.89, steps = 20 23:24:02 [INFO] train episode 32507: reward = -120.96, steps = 18 23:24:03 [INFO] train episode 32508: reward = -92.26, steps = 20 23:24:07 [INFO] train episode 32509: reward = -83.17, steps = 41 23:24:09 [INFO] train episode 32510: reward = -109.49, steps = 21 23:24:12 [INFO] train episode 32511: reward = -36.21, steps = 21 23:24:14 [INFO] train episode 32512: reward = -114.43, steps = 27 23:24:17 [INFO] train episode 32513: reward = -90.21, steps = 28 23:24:19 [INFO] train episode 32514: reward = -87.99, steps = 20 23:24:21 [INFO] train episode 32515: reward = -92.05, steps = 19 23:24:24 [INFO] train episode 32516: reward = -178.07, steps = 25 23:24:28 [INFO] train episode 32517: reward = -131.42, steps = 45 23:24:32 [INFO] train episode 32518: reward = -115.91, steps = 30 23:24:34 [INFO] train episode 32519: reward = -102.64, steps = 27 23:24:38 [INFO] train episode 32520: reward = -66.62, steps = 24 23:24:40 [INFO] train episode 32521: reward = -34.77, steps = 19 23:24:42 [INFO] train episode 32522: reward = -44.51, steps = 19 23:24:44 [INFO] train episode 32523: reward = -64.60, steps = 21 23:24:47 [INFO] train episode 32524: reward = -132.66, steps = 28 23:24:53 [INFO] train episode 32525: reward = -120.47, steps = 63 23:24:56 [INFO] train episode 32526: reward = -115.85, steps = 32 23:24:59 [INFO] train episode 32527: reward = -114.13, steps = 30 23:25:01 [INFO] train episode 32528: reward = -106.40, steps = 20 23:25:04 [INFO] train episode 32529: reward = -55.42, steps = 30 23:25:08 [INFO] train episode 32530: reward = -76.32, steps = 31 23:25:10 [INFO] train episode 32531: reward = -93.43, steps = 19 23:25:14 [INFO] train episode 32532: reward = -127.62, steps = 37 23:25:16 [INFO] train episode 32533: reward = -76.82, steps = 21 23:25:18 [INFO] train episode 32534: reward = -93.85, steps = 20 23:25:20 [INFO] train episode 32535: reward = -93.58, steps = 21 23:25:23 [INFO] train episode 32536: reward = -154.22, steps = 32 23:25:25 [INFO] train episode 32537: reward = -101.29, steps = 23 23:25:27 [INFO] train episode 32538: reward = -85.12, steps = 19 23:25:29 [INFO] train episode 32539: reward = -134.30, steps = 22 23:25:31 [INFO] train episode 32540: reward = -83.86, steps = 20 23:25:33 [INFO] train episode 32541: reward = -81.30, steps = 22 23:25:35 [INFO] train episode 32542: reward = -111.66, steps = 20 23:25:37 [INFO] train episode 32543: reward = -68.46, steps = 22 23:25:39 [INFO] train episode 32544: reward = -138.93, steps = 19 23:25:41 [INFO] train episode 32545: reward = -148.23, steps = 21 23:25:43 [INFO] train episode 32546: reward = -104.95, steps = 22 23:25:47 [INFO] train episode 32547: reward = -106.32, steps = 34 23:25:48 [INFO] train episode 32548: reward = -88.40, steps = 20 23:25:51 [INFO] train episode 32549: reward = -61.39, steps = 26 23:25:53 [INFO] train episode 32550: reward = -80.18, steps = 24 23:25:56 [INFO] train episode 32551: reward = -107.83, steps = 30 23:25:58 [INFO] train episode 32552: reward = -68.87, steps = 29 23:26:01 [INFO] train episode 32553: reward = -128.65, steps = 25 23:26:03 [INFO] train episode 32554: reward = -108.49, steps = 20 23:26:06 [INFO] train episode 32555: reward = -56.55, steps = 35 23:26:08 [INFO] train episode 32556: reward = -85.66, steps = 24 23:26:12 [INFO] train episode 32557: reward = -106.18, steps = 31 23:26:14 [INFO] train episode 32558: reward = -106.43, steps = 21 23:26:16 [INFO] train episode 32559: reward = -120.05, steps = 19 23:26:20 [INFO] train episode 32560: reward = -107.92, steps = 39 23:26:22 [INFO] train episode 32561: reward = -117.28, steps = 23 23:26:24 [INFO] train episode 32562: reward = -61.57, steps = 20 23:26:26 [INFO] train episode 32563: reward = -72.04, steps = 21 23:26:30 [INFO] train episode 32564: reward = -73.91, steps = 39 23:26:32 [INFO] train episode 32565: reward = -111.69, steps = 19 23:26:34 [INFO] train episode 32566: reward = -56.73, steps = 29 23:26:40 [INFO] train episode 32567: reward = -117.62, steps = 41 23:26:43 [INFO] train episode 32568: reward = -60.21, steps = 21 23:26:45 [INFO] train episode 32569: reward = -61.45, steps = 25 23:26:47 [INFO] train episode 32570: reward = -116.09, steps = 18 23:26:49 [INFO] train episode 32571: reward = -91.58, steps = 23 23:26:52 [INFO] train episode 32572: reward = -102.49, steps = 25 23:26:54 [INFO] train episode 32573: reward = -126.22, steps = 23 23:26:57 [INFO] train episode 32574: reward = -83.76, steps = 21 23:26:59 [INFO] train episode 32575: reward = -117.25, steps = 21 23:27:01 [INFO] train episode 32576: reward = -111.19, steps = 21 23:27:03 [INFO] train episode 32577: reward = -62.12, steps = 19 23:27:05 [INFO] train episode 32578: reward = -136.58, steps = 27 23:27:07 [INFO] train episode 32579: reward = -128.95, steps = 22 23:27:09 [INFO] train episode 32580: reward = -141.76, steps = 20 23:27:12 [INFO] train episode 32581: reward = -104.22, steps = 24 23:27:15 [INFO] train episode 32582: reward = -201.06, steps = 23 23:27:18 [INFO] train episode 32583: reward = -108.28, steps = 29 23:27:20 [INFO] train episode 32584: reward = -102.38, steps = 23 23:27:23 [INFO] train episode 32585: reward = -87.15, steps = 24 23:27:27 [INFO] train episode 32586: reward = -193.23, steps = 41 23:27:31 [INFO] train episode 32587: reward = -177.26, steps = 46 23:27:34 [INFO] train episode 32588: reward = -106.40, steps = 28 23:27:36 [INFO] train episode 32589: reward = -108.69, steps = 24 23:27:38 [INFO] train episode 32590: reward = -98.71, steps = 19 23:27:40 [INFO] train episode 32591: reward = -87.64, steps = 21 23:27:41 [INFO] train episode 32592: reward = -58.59, steps = 19 23:27:43 [INFO] train episode 32593: reward = -125.64, steps = 22 23:27:45 [INFO] train episode 32594: reward = -64.40, steps = 20 23:27:49 [INFO] train episode 32595: reward = -109.48, steps = 39 23:27:51 [INFO] train episode 32596: reward = -50.21, steps = 23 23:27:54 [INFO] train episode 32597: reward = -143.99, steps = 31 23:27:55 [INFO] train episode 32598: reward = -71.10, steps = 19 23:27:57 [INFO] train episode 32599: reward = -87.01, steps = 21 23:28:01 [INFO] train episode 32600: reward = -128.45, steps = 36 23:28:03 [INFO] train episode 32601: reward = -132.73, steps = 21 23:28:05 [INFO] train episode 32602: reward = -43.88, steps = 23 23:28:08 [INFO] train episode 32603: reward = -131.80, steps = 30 23:28:11 [INFO] train episode 32604: reward = -160.82, steps = 30 23:28:13 [INFO] train episode 32605: reward = -110.93, steps = 24 23:28:15 [INFO] train episode 32606: reward = -83.22, steps = 21 23:28:17 [INFO] train episode 32607: reward = -72.75, steps = 21 23:28:20 [INFO] train episode 32608: reward = -103.16, steps = 25 23:28:21 [INFO] train episode 32609: reward = -69.36, steps = 19 23:28:26 [INFO] train episode 32610: reward = -188.36, steps = 46 23:28:28 [INFO] train episode 32611: reward = -129.70, steps = 20 23:28:29 [INFO] train episode 32612: reward = -94.86, steps = 20 23:28:31 [INFO] train episode 32613: reward = -122.34, steps = 19 23:28:34 [INFO] train episode 32614: reward = -143.65, steps = 27 23:28:36 [INFO] train episode 32615: reward = -152.52, steps = 21 23:28:38 [INFO] train episode 32616: reward = -108.28, steps = 19 23:28:39 [INFO] train episode 32617: reward = -55.41, steps = 18 23:28:42 [INFO] train episode 32618: reward = -81.51, steps = 21 23:28:43 [INFO] train episode 32619: reward = -74.29, steps = 20 23:28:46 [INFO] train episode 32620: reward = -141.50, steps = 34 23:28:48 [INFO] train episode 32621: reward = -119.53, steps = 19 23:28:52 [INFO] train episode 32622: reward = -173.72, steps = 45 23:28:54 [INFO] train episode 32623: reward = -61.17, steps = 20 23:28:56 [INFO] train episode 32624: reward = -61.39, steps = 19 23:28:58 [INFO] train episode 32625: reward = -163.31, steps = 19 23:29:01 [INFO] train episode 32626: reward = -109.80, steps = 22 23:29:03 [INFO] train episode 32627: reward = -93.89, steps = 24 23:29:06 [INFO] train episode 32628: reward = -81.74, steps = 26 23:29:08 [INFO] train episode 32629: reward = -120.92, steps = 25 23:29:10 [INFO] train episode 32630: reward = -123.47, steps = 18 23:29:13 [INFO] train episode 32631: reward = -123.48, steps = 27 23:29:15 [INFO] train episode 32632: reward = -100.14, steps = 28 23:29:18 [INFO] train episode 32633: reward = -102.85, steps = 26 23:29:20 [INFO] train episode 32634: reward = -63.52, steps = 20 23:29:22 [INFO] train episode 32635: reward = -107.92, steps = 22 23:29:24 [INFO] train episode 32636: reward = -96.89, steps = 21 23:29:25 [INFO] train episode 32637: reward = -93.12, steps = 20 23:29:27 [INFO] train episode 32638: reward = -69.59, steps = 19 23:29:29 [INFO] train episode 32639: reward = -80.94, steps = 22 23:29:31 [INFO] train episode 32640: reward = -122.61, steps = 20 23:29:34 [INFO] train episode 32641: reward = -127.31, steps = 28 23:29:36 [INFO] train episode 32642: reward = -89.94, steps = 23 23:29:38 [INFO] train episode 32643: reward = -64.18, steps = 23 23:29:40 [INFO] train episode 32644: reward = -74.87, steps = 24 23:29:42 [INFO] train episode 32645: reward = -65.60, steps = 21 23:29:44 [INFO] train episode 32646: reward = -65.52, steps = 21 23:29:46 [INFO] train episode 32647: reward = -78.46, steps = 22 23:29:48 [INFO] train episode 32648: reward = -126.67, steps = 21 23:29:52 [INFO] train episode 32649: reward = -120.62, steps = 31 23:29:54 [INFO] train episode 32650: reward = -97.50, steps = 22 23:29:56 [INFO] train episode 32651: reward = -83.04, steps = 18 23:29:58 [INFO] train episode 32652: reward = -122.18, steps = 19 23:30:03 [INFO] train episode 32653: reward = -215.45, steps = 50 23:30:05 [INFO] train episode 32654: reward = -68.86, steps = 20 23:30:09 [INFO] train episode 32655: reward = -159.03, steps = 35 23:30:11 [INFO] train episode 32656: reward = -72.39, steps = 24 23:30:13 [INFO] train episode 32657: reward = -65.85, steps = 19 23:30:16 [INFO] train episode 32658: reward = -105.47, steps = 26 23:30:18 [INFO] train episode 32659: reward = -59.93, steps = 22 23:30:21 [INFO] train episode 32660: reward = -219.13, steps = 19 23:30:23 [INFO] train episode 32661: reward = -93.01, steps = 25 23:30:26 [INFO] train episode 32662: reward = -71.40, steps = 36 23:30:29 [INFO] train episode 32663: reward = -69.99, steps = 26 23:30:31 [INFO] train episode 32664: reward = -37.23, steps = 23 23:30:33 [INFO] train episode 32665: reward = -113.84, steps = 23 23:30:36 [INFO] train episode 32666: reward = -69.64, steps = 25 23:30:38 [INFO] train episode 32667: reward = -113.61, steps = 20 23:30:40 [INFO] train episode 32668: reward = -71.12, steps = 26 23:30:43 [INFO] train episode 32669: reward = -110.42, steps = 39 23:30:47 [INFO] train episode 32670: reward = -102.52, steps = 31 23:30:49 [INFO] train episode 32671: reward = -93.00, steps = 28 23:30:52 [INFO] train episode 32672: reward = -124.53, steps = 23 23:30:54 [INFO] train episode 32673: reward = -88.85, steps = 23 23:30:57 [INFO] train episode 32674: reward = -131.59, steps = 29 23:30:59 [INFO] train episode 32675: reward = -89.08, steps = 30 23:31:02 [INFO] train episode 32676: reward = -95.12, steps = 22 23:31:03 [INFO] train episode 32677: reward = -75.67, steps = 19 23:31:06 [INFO] train episode 32678: reward = -103.64, steps = 33 23:31:09 [INFO] train episode 32679: reward = -67.38, steps = 25 23:31:11 [INFO] train episode 32680: reward = -68.57, steps = 18 23:31:13 [INFO] train episode 32681: reward = -109.86, steps = 20 23:31:16 [INFO] train episode 32682: reward = -121.96, steps = 38 23:31:18 [INFO] train episode 32683: reward = -131.58, steps = 20 23:31:21 [INFO] train episode 32684: reward = -68.19, steps = 27 23:31:23 [INFO] train episode 32685: reward = -88.32, steps = 21 23:31:25 [INFO] train episode 32686: reward = -93.89, steps = 24 23:31:28 [INFO] train episode 32687: reward = -102.30, steps = 24 23:31:29 [INFO] train episode 32688: reward = -102.95, steps = 19 23:31:31 [INFO] train episode 32689: reward = -120.96, steps = 20 23:31:33 [INFO] train episode 32690: reward = -83.37, steps = 20 23:31:35 [INFO] train episode 32691: reward = -93.50, steps = 23 23:31:38 [INFO] train episode 32692: reward = -96.43, steps = 21 23:31:42 [INFO] train episode 32693: reward = -162.56, steps = 45 23:31:46 [INFO] train episode 32694: reward = -92.97, steps = 36 23:31:48 [INFO] train episode 32695: reward = -102.30, steps = 22 23:31:51 [INFO] train episode 32696: reward = -135.47, steps = 33 23:31:55 [INFO] train episode 32697: reward = -91.33, steps = 30 23:31:58 [INFO] train episode 32698: reward = -145.73, steps = 36 23:32:01 [INFO] train episode 32699: reward = -132.50, steps = 27 23:32:03 [INFO] train episode 32700: reward = -99.66, steps = 24 23:32:06 [INFO] train episode 32701: reward = -94.14, steps = 28 23:32:07 [INFO] train episode 32702: reward = -120.97, steps = 19 23:32:09 [INFO] train episode 32703: reward = -87.94, steps = 19 23:32:12 [INFO] train episode 32704: reward = -100.21, steps = 28 23:32:14 [INFO] train episode 32705: reward = -61.02, steps = 21 23:32:18 [INFO] train episode 32706: reward = -85.98, steps = 34 23:32:20 [INFO] train episode 32707: reward = -187.42, steps = 31 23:32:23 [INFO] train episode 32708: reward = -75.34, steps = 27 23:32:25 [INFO] train episode 32709: reward = -119.66, steps = 23 23:32:27 [INFO] train episode 32710: reward = -65.35, steps = 20 23:32:29 [INFO] train episode 32711: reward = -85.62, steps = 23 23:32:31 [INFO] train episode 32712: reward = -155.69, steps = 21 23:32:34 [INFO] train episode 32713: reward = -117.01, steps = 40 23:32:36 [INFO] train episode 32714: reward = -158.74, steps = 19 23:32:38 [INFO] train episode 32715: reward = -107.04, steps = 20 23:32:40 [INFO] train episode 32716: reward = -83.29, steps = 25 23:32:42 [INFO] train episode 32717: reward = -114.93, steps = 25 23:32:44 [INFO] train episode 32718: reward = -134.12, steps = 20 23:32:47 [INFO] train episode 32719: reward = -85.92, steps = 23 23:32:49 [INFO] train episode 32720: reward = -78.11, steps = 22 23:32:50 [INFO] train episode 32721: reward = -113.09, steps = 19 23:32:52 [INFO] train episode 32722: reward = -93.32, steps = 20 23:32:54 [INFO] train episode 32723: reward = -68.24, steps = 18 23:32:55 [INFO] train episode 32724: reward = -102.17, steps = 18 23:32:57 [INFO] train episode 32725: reward = -91.88, steps = 20 23:32:59 [INFO] train episode 32726: reward = -119.69, steps = 22 23:33:01 [INFO] train episode 32727: reward = -123.17, steps = 23 23:33:04 [INFO] train episode 32728: reward = -108.60, steps = 21 23:33:05 [INFO] train episode 32729: reward = -79.43, steps = 20 23:33:08 [INFO] train episode 32730: reward = -79.89, steps = 34 23:33:10 [INFO] train episode 32731: reward = -180.21, steps = 23 23:33:12 [INFO] train episode 32732: reward = -95.60, steps = 18 23:33:14 [INFO] train episode 32733: reward = -128.93, steps = 19 23:33:17 [INFO] train episode 32734: reward = -116.25, steps = 33 23:33:19 [INFO] train episode 32735: reward = -159.06, steps = 25 23:33:22 [INFO] train episode 32736: reward = -136.51, steps = 27 23:33:25 [INFO] train episode 32737: reward = -101.72, steps = 29 23:33:28 [INFO] train episode 32738: reward = -153.05, steps = 38 23:33:31 [INFO] train episode 32739: reward = -87.48, steps = 34 23:33:33 [INFO] train episode 32740: reward = -87.21, steps = 20 23:33:36 [INFO] train episode 32741: reward = -74.33, steps = 25 23:33:38 [INFO] train episode 32742: reward = -87.64, steps = 23 23:33:40 [INFO] train episode 32743: reward = -64.43, steps = 23 23:33:42 [INFO] train episode 32744: reward = -85.11, steps = 20 23:33:44 [INFO] train episode 32745: reward = -154.58, steps = 29 23:33:46 [INFO] train episode 32746: reward = -138.27, steps = 23 23:33:48 [INFO] train episode 32747: reward = -108.82, steps = 20 23:33:50 [INFO] train episode 32748: reward = -90.19, steps = 20 23:33:52 [INFO] train episode 32749: reward = -80.30, steps = 22 23:33:55 [INFO] train episode 32750: reward = -80.51, steps = 26 23:33:57 [INFO] train episode 32751: reward = -94.54, steps = 22 23:33:59 [INFO] train episode 32752: reward = -67.77, steps = 25 23:34:01 [INFO] train episode 32753: reward = -81.06, steps = 25 23:34:03 [INFO] train episode 32754: reward = -63.13, steps = 18 23:34:05 [INFO] train episode 32755: reward = -83.93, steps = 19 23:34:07 [INFO] train episode 32756: reward = -85.11, steps = 22 23:34:09 [INFO] train episode 32757: reward = -95.30, steps = 24 23:34:12 [INFO] train episode 32758: reward = -104.58, steps = 34 23:34:14 [INFO] train episode 32759: reward = -63.26, steps = 20 23:34:16 [INFO] train episode 32760: reward = -84.00, steps = 20 23:34:18 [INFO] train episode 32761: reward = -53.42, steps = 20 23:34:20 [INFO] train episode 32762: reward = -64.11, steps = 24 23:34:22 [INFO] train episode 32763: reward = -87.92, steps = 22 23:34:24 [INFO] train episode 32764: reward = -72.04, steps = 22 23:34:27 [INFO] train episode 32765: reward = -89.76, steps = 20 23:34:30 [INFO] train episode 32766: reward = -133.35, steps = 35 23:34:31 [INFO] train episode 32767: reward = -95.35, steps = 19 23:34:34 [INFO] train episode 32768: reward = -84.51, steps = 25 23:34:36 [INFO] train episode 32769: reward = -100.40, steps = 25 23:34:38 [INFO] train episode 32770: reward = -73.07, steps = 19 23:34:39 [INFO] train episode 32771: reward = -87.64, steps = 20 23:34:41 [INFO] train episode 32772: reward = -74.52, steps = 18 23:34:43 [INFO] train episode 32773: reward = -108.00, steps = 20 23:34:46 [INFO] train episode 32774: reward = -62.08, steps = 23 23:34:48 [INFO] train episode 32775: reward = -103.40, steps = 30 23:34:50 [INFO] train episode 32776: reward = -88.61, steps = 22 23:34:52 [INFO] train episode 32777: reward = -77.05, steps = 19 23:34:55 [INFO] train episode 32778: reward = -82.60, steps = 36 23:34:57 [INFO] train episode 32779: reward = -115.99, steps = 19 23:35:00 [INFO] train episode 32780: reward = -93.67, steps = 29 23:35:01 [INFO] train episode 32781: reward = -54.76, steps = 18 23:35:03 [INFO] train episode 32782: reward = -89.90, steps = 21 23:35:05 [INFO] train episode 32783: reward = -120.79, steps = 22 23:35:07 [INFO] train episode 32784: reward = -73.04, steps = 21 23:35:09 [INFO] train episode 32785: reward = -62.67, steps = 19 23:35:11 [INFO] train episode 32786: reward = -85.58, steps = 28 23:35:14 [INFO] train episode 32787: reward = -98.29, steps = 30 23:35:16 [INFO] train episode 32788: reward = -99.02, steps = 21 23:35:19 [INFO] train episode 32789: reward = -177.76, steps = 23 23:35:21 [INFO] train episode 32790: reward = -101.16, steps = 19 23:35:23 [INFO] train episode 32791: reward = -57.18, steps = 21 23:35:24 [INFO] train episode 32792: reward = -75.10, steps = 18 23:35:26 [INFO] train episode 32793: reward = -88.06, steps = 20 23:35:28 [INFO] train episode 32794: reward = -60.09, steps = 18 23:35:30 [INFO] train episode 32795: reward = -101.07, steps = 22 23:35:32 [INFO] train episode 32796: reward = -123.52, steps = 19 23:35:34 [INFO] train episode 32797: reward = -101.18, steps = 19 23:35:36 [INFO] train episode 32798: reward = -97.95, steps = 27 23:35:38 [INFO] train episode 32799: reward = -126.59, steps = 24 23:35:41 [INFO] train episode 32800: reward = -149.92, steps = 25 23:35:42 [INFO] train episode 32801: reward = -58.73, steps = 20 23:35:45 [INFO] train episode 32802: reward = -144.23, steps = 28 23:35:48 [INFO] train episode 32803: reward = -85.25, steps = 28 23:35:50 [INFO] train episode 32804: reward = -165.06, steps = 24 23:35:54 [INFO] train episode 32805: reward = -143.12, steps = 32 23:35:57 [INFO] train episode 32806: reward = -126.51, steps = 26 23:35:59 [INFO] train episode 32807: reward = -80.58, steps = 20 23:36:01 [INFO] train episode 32808: reward = -71.60, steps = 18 23:36:03 [INFO] train episode 32809: reward = -146.73, steps = 19 23:36:06 [INFO] train episode 32810: reward = -176.58, steps = 31 23:36:08 [INFO] train episode 32811: reward = -125.77, steps = 21 23:36:12 [INFO] train episode 32812: reward = -78.68, steps = 27 23:36:13 [INFO] train episode 32813: reward = -94.60, steps = 19 23:36:15 [INFO] train episode 32814: reward = -98.31, steps = 20 23:36:17 [INFO] train episode 32815: reward = -78.85, steps = 20 23:36:19 [INFO] train episode 32816: reward = -120.87, steps = 24 23:36:22 [INFO] train episode 32817: reward = -91.83, steps = 23 23:36:25 [INFO] train episode 32818: reward = -91.13, steps = 34 23:36:27 [INFO] train episode 32819: reward = -71.95, steps = 20 23:36:30 [INFO] train episode 32820: reward = -88.31, steps = 23 23:36:32 [INFO] train episode 32821: reward = -44.22, steps = 19 23:36:37 [INFO] train episode 32822: reward = -161.15, steps = 48 23:36:40 [INFO] train episode 32823: reward = -97.09, steps = 31 23:36:41 [INFO] train episode 32824: reward = -66.75, steps = 20 23:36:43 [INFO] train episode 32825: reward = -80.49, steps = 18 23:36:46 [INFO] train episode 32826: reward = -175.28, steps = 24 23:36:48 [INFO] train episode 32827: reward = -89.67, steps = 26 23:36:51 [INFO] train episode 32828: reward = -58.16, steps = 32 23:36:54 [INFO] train episode 32829: reward = -101.18, steps = 33 23:36:56 [INFO] train episode 32830: reward = -73.77, steps = 18 23:36:58 [INFO] train episode 32831: reward = -74.10, steps = 19 23:37:00 [INFO] train episode 32832: reward = -173.12, steps = 21 23:37:02 [INFO] train episode 32833: reward = -81.15, steps = 22 23:37:05 [INFO] train episode 32834: reward = -57.16, steps = 22 23:37:06 [INFO] train episode 32835: reward = -87.32, steps = 20 23:37:08 [INFO] train episode 32836: reward = -155.75, steps = 22 23:37:10 [INFO] train episode 32837: reward = -40.75, steps = 22 23:37:13 [INFO] train episode 32838: reward = -72.77, steps = 26 23:37:15 [INFO] train episode 32839: reward = -101.45, steps = 30 23:37:18 [INFO] train episode 32840: reward = -79.27, steps = 35 23:37:21 [INFO] train episode 32841: reward = -108.45, steps = 21 23:37:23 [INFO] train episode 32842: reward = -88.96, steps = 27 23:37:26 [INFO] train episode 32843: reward = -146.51, steps = 32 23:37:28 [INFO] train episode 32844: reward = -81.44, steps = 24 23:37:30 [INFO] train episode 32845: reward = -96.64, steps = 18 23:37:32 [INFO] train episode 32846: reward = -99.50, steps = 20 23:37:34 [INFO] train episode 32847: reward = -110.30, steps = 25 23:37:36 [INFO] train episode 32848: reward = -70.19, steps = 19 23:37:38 [INFO] train episode 32849: reward = -97.23, steps = 21 23:37:40 [INFO] train episode 32850: reward = -108.52, steps = 22 23:37:42 [INFO] train episode 32851: reward = -75.73, steps = 27 23:37:47 [INFO] train episode 32852: reward = -169.12, steps = 57 23:37:49 [INFO] train episode 32853: reward = -118.70, steps = 21 23:37:51 [INFO] train episode 32854: reward = -71.82, steps = 24 23:37:54 [INFO] train episode 32855: reward = -88.59, steps = 29 23:37:56 [INFO] train episode 32856: reward = -83.04, steps = 27 23:37:59 [INFO] train episode 32857: reward = -78.34, steps = 30 23:38:01 [INFO] train episode 32858: reward = -110.19, steps = 29 23:38:04 [INFO] train episode 32859: reward = -118.74, steps = 27 23:38:06 [INFO] train episode 32860: reward = -89.60, steps = 27 23:38:09 [INFO] train episode 32861: reward = -86.32, steps = 27 23:38:13 [INFO] train episode 32862: reward = -185.95, steps = 42 23:38:15 [INFO] train episode 32863: reward = -75.89, steps = 26 23:38:18 [INFO] train episode 32864: reward = -124.15, steps = 33 23:38:21 [INFO] train episode 32865: reward = -113.45, steps = 34 23:38:23 [INFO] train episode 32866: reward = -76.22, steps = 27 23:38:27 [INFO] train episode 32867: reward = -108.43, steps = 34 23:38:29 [INFO] train episode 32868: reward = -129.39, steps = 33 23:38:32 [INFO] train episode 32869: reward = -109.43, steps = 27 23:38:34 [INFO] train episode 32870: reward = -64.65, steps = 21 23:38:36 [INFO] train episode 32871: reward = -82.57, steps = 24 23:38:39 [INFO] train episode 32872: reward = -92.03, steps = 31 23:38:42 [INFO] train episode 32873: reward = -102.76, steps = 31 23:38:44 [INFO] train episode 32874: reward = -82.70, steps = 23 23:38:47 [INFO] train episode 32875: reward = -82.09, steps = 33 23:38:49 [INFO] train episode 32876: reward = -116.27, steps = 23 23:38:52 [INFO] train episode 32877: reward = -114.77, steps = 37 23:38:55 [INFO] train episode 32878: reward = -120.12, steps = 24 23:38:56 [INFO] train episode 32879: reward = -54.00, steps = 20 23:38:58 [INFO] train episode 32880: reward = -89.00, steps = 22 23:39:01 [INFO] train episode 32881: reward = -140.07, steps = 28 23:39:05 [INFO] train episode 32882: reward = -89.12, steps = 37 23:39:06 [INFO] train episode 32883: reward = -80.69, steps = 20 23:39:08 [INFO] train episode 32884: reward = -89.84, steps = 20 23:39:10 [INFO] train episode 32885: reward = -105.00, steps = 26 23:39:12 [INFO] train episode 32886: reward = -121.34, steps = 21 23:39:16 [INFO] train episode 32887: reward = -177.95, steps = 38 23:39:18 [INFO] train episode 32888: reward = -52.44, steps = 19 23:39:20 [INFO] train episode 32889: reward = -49.27, steps = 24 23:39:23 [INFO] train episode 32890: reward = -184.95, steps = 32 23:39:25 [INFO] train episode 32891: reward = -121.85, steps = 26 23:39:29 [INFO] train episode 32892: reward = -124.57, steps = 34 23:39:31 [INFO] train episode 32893: reward = -88.14, steps = 22 23:39:33 [INFO] train episode 32894: reward = -129.60, steps = 19 23:39:36 [INFO] train episode 32895: reward = -130.14, steps = 31 23:39:38 [INFO] train episode 32896: reward = -81.94, steps = 19 23:39:39 [INFO] train episode 32897: reward = -115.96, steps = 19 23:39:42 [INFO] train episode 32898: reward = -64.57, steps = 28 23:39:45 [INFO] train episode 32899: reward = -113.10, steps = 36 23:39:47 [INFO] train episode 32900: reward = -160.39, steps = 25 23:39:49 [INFO] train episode 32901: reward = -88.93, steps = 23 23:39:52 [INFO] train episode 32902: reward = -114.08, steps = 29 23:39:54 [INFO] train episode 32903: reward = -88.53, steps = 20 23:39:56 [INFO] train episode 32904: reward = -109.35, steps = 20 23:39:58 [INFO] train episode 32905: reward = -101.77, steps = 28 23:40:01 [INFO] train episode 32906: reward = -109.40, steps = 29 23:40:02 [INFO] train episode 32907: reward = -87.81, steps = 19 23:40:05 [INFO] train episode 32908: reward = -166.91, steps = 29 23:40:07 [INFO] train episode 32909: reward = -89.25, steps = 18 23:40:09 [INFO] train episode 32910: reward = -99.48, steps = 21 23:40:11 [INFO] train episode 32911: reward = -57.01, steps = 19 23:40:15 [INFO] train episode 32912: reward = -208.67, steps = 47 23:40:17 [INFO] train episode 32913: reward = -133.72, steps = 29 23:40:19 [INFO] train episode 32914: reward = -88.33, steps = 18 23:40:23 [INFO] train episode 32915: reward = -179.42, steps = 42 23:40:25 [INFO] train episode 32916: reward = -103.72, steps = 21 23:40:27 [INFO] train episode 32917: reward = -156.34, steps = 22 23:40:29 [INFO] train episode 32918: reward = -90.51, steps = 19 23:40:30 [INFO] train episode 32919: reward = -74.16, steps = 20 23:40:33 [INFO] train episode 32920: reward = -109.10, steps = 26 23:40:35 [INFO] train episode 32921: reward = -60.21, steps = 31 23:40:38 [INFO] train episode 32922: reward = -73.12, steps = 27 23:40:41 [INFO] train episode 32923: reward = -67.90, steps = 28 23:40:44 [INFO] train episode 32924: reward = -103.64, steps = 36 23:40:46 [INFO] train episode 32925: reward = -71.73, steps = 24 23:40:49 [INFO] train episode 32926: reward = -50.78, steps = 29 23:40:51 [INFO] train episode 32927: reward = -102.15, steps = 21 23:40:53 [INFO] train episode 32928: reward = -106.40, steps = 24 23:40:55 [INFO] train episode 32929: reward = -105.42, steps = 23 23:40:57 [INFO] train episode 32930: reward = -82.44, steps = 22 23:40:59 [INFO] train episode 32931: reward = -162.58, steps = 18 23:41:01 [INFO] train episode 32932: reward = -72.24, steps = 20 23:41:03 [INFO] train episode 32933: reward = -103.88, steps = 27 23:41:06 [INFO] train episode 32934: reward = -86.12, steps = 30 23:41:07 [INFO] train episode 32935: reward = -88.30, steps = 20 23:41:11 [INFO] train episode 32936: reward = -111.30, steps = 37 23:41:13 [INFO] train episode 32937: reward = -80.86, steps = 24 23:41:15 [INFO] train episode 32938: reward = -106.44, steps = 22 23:41:17 [INFO] train episode 32939: reward = -95.66, steps = 22 23:41:19 [INFO] train episode 32940: reward = -42.85, steps = 23 23:41:22 [INFO] train episode 32941: reward = -104.03, steps = 31 23:41:24 [INFO] train episode 32942: reward = -78.97, steps = 19 23:41:25 [INFO] train episode 32943: reward = -87.48, steps = 20 23:41:27 [INFO] train episode 32944: reward = -119.70, steps = 20 23:41:29 [INFO] train episode 32945: reward = -63.61, steps = 19 23:41:33 [INFO] train episode 32946: reward = -135.24, steps = 39 23:41:35 [INFO] train episode 32947: reward = -72.96, steps = 23 23:41:38 [INFO] train episode 32948: reward = -99.70, steps = 35 23:41:40 [INFO] train episode 32949: reward = -86.75, steps = 20 23:41:42 [INFO] train episode 32950: reward = -101.55, steps = 26 23:41:44 [INFO] train episode 32951: reward = -91.42, steps = 20 23:41:47 [INFO] train episode 32952: reward = -96.41, steps = 30 23:41:48 [INFO] train episode 32953: reward = -73.64, steps = 19 23:41:51 [INFO] train episode 32954: reward = -89.42, steps = 24 23:41:53 [INFO] train episode 32955: reward = -111.81, steps = 28 23:41:55 [INFO] train episode 32956: reward = -60.53, steps = 21 23:41:58 [INFO] train episode 32957: reward = -115.95, steps = 36 23:42:00 [INFO] train episode 32958: reward = -107.26, steps = 23 23:42:02 [INFO] train episode 32959: reward = -108.55, steps = 21 23:42:05 [INFO] train episode 32960: reward = -74.26, steps = 26 23:42:07 [INFO] train episode 32961: reward = -84.85, steps = 26 23:42:09 [INFO] train episode 32962: reward = -106.59, steps = 20 23:42:11 [INFO] train episode 32963: reward = -111.47, steps = 28 23:42:13 [INFO] train episode 32964: reward = -72.35, steps = 20 23:42:15 [INFO] train episode 32965: reward = -128.73, steps = 19 23:42:17 [INFO] train episode 32966: reward = -87.04, steps = 23 23:42:19 [INFO] train episode 32967: reward = -143.28, steps = 20 23:42:22 [INFO] train episode 32968: reward = -125.05, steps = 26 23:42:24 [INFO] train episode 32969: reward = -62.55, steps = 20 23:42:27 [INFO] train episode 32970: reward = -77.63, steps = 25 23:42:28 [INFO] train episode 32971: reward = -101.45, steps = 19 23:42:30 [INFO] train episode 32972: reward = -58.01, steps = 18 23:42:33 [INFO] train episode 32973: reward = -94.54, steps = 31 23:42:36 [INFO] train episode 32974: reward = -128.52, steps = 27 23:42:39 [INFO] train episode 32975: reward = -150.19, steps = 35 23:42:41 [INFO] train episode 32976: reward = -131.19, steps = 22 23:42:43 [INFO] train episode 32977: reward = -107.46, steps = 23 23:42:47 [INFO] train episode 32978: reward = -132.56, steps = 49 23:42:49 [INFO] train episode 32979: reward = -164.97, steps = 23 23:42:53 [INFO] train episode 32980: reward = -155.53, steps = 32 23:42:55 [INFO] train episode 32981: reward = -81.67, steps = 20 23:42:56 [INFO] train episode 32982: reward = -79.72, steps = 21 23:42:59 [INFO] train episode 32983: reward = -65.40, steps = 23 23:43:01 [INFO] train episode 32984: reward = -158.29, steps = 21 23:43:02 [INFO] train episode 32985: reward = -74.74, steps = 20 23:43:05 [INFO] train episode 32986: reward = -115.86, steps = 30 23:43:08 [INFO] train episode 32987: reward = -116.17, steps = 37 23:43:11 [INFO] train episode 32988: reward = -151.82, steps = 32 23:43:13 [INFO] train episode 32989: reward = -98.13, steps = 23 23:43:16 [INFO] train episode 32990: reward = -74.03, steps = 24 23:43:18 [INFO] train episode 32991: reward = -93.60, steps = 26 23:43:20 [INFO] train episode 32992: reward = -82.23, steps = 19 23:43:22 [INFO] train episode 32993: reward = -79.31, steps = 22 23:43:23 [INFO] train episode 32994: reward = -96.61, steps = 20 23:43:26 [INFO] train episode 32995: reward = -84.84, steps = 21 23:43:28 [INFO] train episode 32996: reward = -74.98, steps = 25 23:43:31 [INFO] train episode 32997: reward = -42.70, steps = 27 23:43:33 [INFO] train episode 32998: reward = -88.82, steps = 32 23:43:36 [INFO] train episode 32999: reward = -78.14, steps = 30 23:43:38 [INFO] train episode 33000: reward = -114.78, steps = 26 23:43:41 [INFO] train episode 33001: reward = -92.96, steps = 29 23:43:43 [INFO] train episode 33002: reward = -81.57, steps = 19 23:43:45 [INFO] train episode 33003: reward = -79.71, steps = 26 23:43:47 [INFO] train episode 33004: reward = -75.55, steps = 20 23:43:49 [INFO] train episode 33005: reward = -86.44, steps = 20 23:43:51 [INFO] train episode 33006: reward = -83.80, steps = 21 23:43:55 [INFO] train episode 33007: reward = -106.45, steps = 44 23:43:59 [INFO] train episode 33008: reward = -140.16, steps = 47 23:44:02 [INFO] train episode 33009: reward = -111.47, steps = 25 23:44:03 [INFO] train episode 33010: reward = -114.02, steps = 20 23:44:05 [INFO] train episode 33011: reward = -89.59, steps = 22 23:44:09 [INFO] train episode 33012: reward = -143.64, steps = 44 23:44:12 [INFO] train episode 33013: reward = -90.18, steps = 33 23:44:14 [INFO] train episode 33014: reward = -92.60, steps = 18 23:44:16 [INFO] train episode 33015: reward = -63.24, steps = 21 23:44:19 [INFO] train episode 33016: reward = -186.34, steps = 41 23:44:23 [INFO] train episode 33017: reward = -97.96, steps = 35 23:44:25 [INFO] train episode 33018: reward = -90.01, steps = 24 23:44:26 [INFO] train episode 33019: reward = -69.11, steps = 19 23:44:29 [INFO] train episode 33020: reward = -76.94, steps = 24 23:44:31 [INFO] train episode 33021: reward = -111.76, steps = 26 23:44:33 [INFO] train episode 33022: reward = -70.78, steps = 20 23:44:35 [INFO] train episode 33023: reward = -143.83, steps = 21 23:44:37 [INFO] train episode 33024: reward = -86.45, steps = 19 23:44:39 [INFO] train episode 33025: reward = -169.82, steps = 19 23:44:41 [INFO] train episode 33026: reward = -170.06, steps = 25 23:44:42 [INFO] train episode 33027: reward = -89.15, steps = 19 23:44:46 [INFO] train episode 33028: reward = -122.54, steps = 34 23:44:48 [INFO] train episode 33029: reward = -136.12, steps = 26 23:44:53 [INFO] train episode 33030: reward = -173.49, steps = 54 23:44:55 [INFO] train episode 33031: reward = -171.82, steps = 20 23:44:57 [INFO] train episode 33032: reward = -79.31, steps = 19 23:44:59 [INFO] train episode 33033: reward = -84.94, steps = 26 23:45:02 [INFO] train episode 33034: reward = -71.31, steps = 25 23:45:06 [INFO] train episode 33035: reward = -101.24, steps = 42 23:45:08 [INFO] train episode 33036: reward = -130.50, steps = 21 23:45:10 [INFO] train episode 33037: reward = -136.43, steps = 24 23:45:12 [INFO] train episode 33038: reward = -106.51, steps = 21 23:45:13 [INFO] train episode 33039: reward = -119.82, steps = 18 23:45:16 [INFO] train episode 33040: reward = -87.22, steps = 30 23:45:18 [INFO] train episode 33041: reward = -68.50, steps = 25 23:45:20 [INFO] train episode 33042: reward = -85.80, steps = 19 23:45:22 [INFO] train episode 33043: reward = -102.31, steps = 21 23:45:24 [INFO] train episode 33044: reward = -62.69, steps = 21 23:45:28 [INFO] train episode 33045: reward = -109.17, steps = 28 23:45:31 [INFO] train episode 33046: reward = -130.01, steps = 32 23:45:32 [INFO] train episode 33047: reward = -51.22, steps = 14 23:45:34 [INFO] train episode 33048: reward = -143.57, steps = 24 23:45:36 [INFO] train episode 33049: reward = -110.01, steps = 26 23:45:38 [INFO] train episode 33050: reward = -66.29, steps = 19 23:45:40 [INFO] train episode 33051: reward = -107.48, steps = 19 23:45:42 [INFO] train episode 33052: reward = -130.71, steps = 21 23:45:45 [INFO] train episode 33053: reward = -161.64, steps = 38 23:45:47 [INFO] train episode 33054: reward = -112.08, steps = 20 23:45:49 [INFO] train episode 33055: reward = -86.07, steps = 25 23:45:52 [INFO] train episode 33056: reward = -116.24, steps = 28 23:45:54 [INFO] train episode 33057: reward = -136.02, steps = 28 23:45:57 [INFO] train episode 33058: reward = -110.70, steps = 19 23:45:58 [INFO] train episode 33059: reward = -85.02, steps = 20 23:46:03 [INFO] train episode 33060: reward = -154.94, steps = 51 23:46:05 [INFO] train episode 33061: reward = -67.42, steps = 19 23:46:07 [INFO] train episode 33062: reward = -72.33, steps = 23 23:46:09 [INFO] train episode 33063: reward = -54.51, steps = 19 23:46:11 [INFO] train episode 33064: reward = -69.95, steps = 25 23:46:13 [INFO] train episode 33065: reward = -96.01, steps = 20 23:46:15 [INFO] train episode 33066: reward = -90.28, steps = 20 23:46:18 [INFO] train episode 33067: reward = -142.10, steps = 30 23:46:20 [INFO] train episode 33068: reward = -54.53, steps = 23 23:46:22 [INFO] train episode 33069: reward = -70.23, steps = 20 23:46:24 [INFO] train episode 33070: reward = -82.04, steps = 23 23:46:26 [INFO] train episode 33071: reward = -124.29, steps = 30 23:46:28 [INFO] train episode 33072: reward = -77.98, steps = 16 23:46:30 [INFO] train episode 33073: reward = -84.95, steps = 21 23:46:32 [INFO] train episode 33074: reward = -122.30, steps = 21 23:46:35 [INFO] train episode 33075: reward = -100.95, steps = 28 23:46:36 [INFO] train episode 33076: reward = -121.63, steps = 19 23:46:39 [INFO] train episode 33077: reward = -84.98, steps = 23 23:46:41 [INFO] train episode 33078: reward = -109.73, steps = 23 23:46:43 [INFO] train episode 33079: reward = -103.19, steps = 22 23:46:44 [INFO] train episode 33080: reward = -90.11, steps = 19 23:46:47 [INFO] train episode 33081: reward = -134.17, steps = 25 23:46:49 [INFO] train episode 33082: reward = -167.54, steps = 19 23:46:50 [INFO] train episode 33083: reward = -70.71, steps = 18 23:46:53 [INFO] train episode 33084: reward = -106.00, steps = 29 23:46:55 [INFO] train episode 33085: reward = -89.23, steps = 21 23:46:57 [INFO] train episode 33086: reward = -102.89, steps = 20 23:46:59 [INFO] train episode 33087: reward = -101.51, steps = 29 23:47:04 [INFO] train episode 33088: reward = -213.57, steps = 46 23:47:07 [INFO] train episode 33089: reward = -112.70, steps = 38 23:47:09 [INFO] train episode 33090: reward = -76.53, steps = 23 23:47:11 [INFO] train episode 33091: reward = -107.64, steps = 20 23:47:13 [INFO] train episode 33092: reward = -150.54, steps = 24 23:47:15 [INFO] train episode 33093: reward = -93.09, steps = 20 23:47:17 [INFO] train episode 33094: reward = -104.01, steps = 20 23:47:19 [INFO] train episode 33095: reward = -197.74, steps = 21 23:47:21 [INFO] train episode 33096: reward = -78.67, steps = 21 23:47:23 [INFO] train episode 33097: reward = -78.23, steps = 20 23:47:27 [INFO] train episode 33098: reward = -132.21, steps = 40 23:47:30 [INFO] train episode 33099: reward = -145.85, steps = 40 23:47:32 [INFO] train episode 33100: reward = -122.96, steps = 20 23:47:34 [INFO] train episode 33101: reward = -86.63, steps = 23 23:47:36 [INFO] train episode 33102: reward = -117.29, steps = 20 23:47:39 [INFO] train episode 33103: reward = -110.12, steps = 30 23:47:42 [INFO] train episode 33104: reward = -89.98, steps = 31 23:47:45 [INFO] train episode 33105: reward = -88.59, steps = 37 23:47:47 [INFO] train episode 33106: reward = -77.48, steps = 19 23:47:49 [INFO] train episode 33107: reward = -92.01, steps = 25 23:47:51 [INFO] train episode 33108: reward = -79.17, steps = 21 23:47:54 [INFO] train episode 33109: reward = -85.66, steps = 32 23:47:57 [INFO] train episode 33110: reward = -84.75, steps = 25 23:47:59 [INFO] train episode 33111: reward = -119.63, steps = 24 23:48:01 [INFO] train episode 33112: reward = -87.78, steps = 23 23:48:03 [INFO] train episode 33113: reward = -168.35, steps = 27 23:48:06 [INFO] train episode 33114: reward = -93.51, steps = 26 23:48:08 [INFO] train episode 33115: reward = -133.39, steps = 24 23:48:10 [INFO] train episode 33116: reward = -114.68, steps = 24 23:48:12 [INFO] train episode 33117: reward = -119.39, steps = 19 23:48:14 [INFO] train episode 33118: reward = -72.64, steps = 24 23:48:16 [INFO] train episode 33119: reward = -94.18, steps = 20 23:48:19 [INFO] train episode 33120: reward = -105.29, steps = 26 23:48:20 [INFO] train episode 33121: reward = -63.95, steps = 19 23:48:22 [INFO] train episode 33122: reward = -88.32, steps = 21 23:48:24 [INFO] train episode 33123: reward = -101.39, steps = 18 23:48:29 [INFO] train episode 33124: reward = -156.12, steps = 41 23:48:31 [INFO] train episode 33125: reward = -54.03, steps = 19 23:48:33 [INFO] train episode 33126: reward = -105.38, steps = 23 23:48:35 [INFO] train episode 33127: reward = -88.78, steps = 24 23:48:38 [INFO] train episode 33128: reward = -117.87, steps = 34 23:48:40 [INFO] train episode 33129: reward = -124.58, steps = 24 23:48:42 [INFO] train episode 33130: reward = -151.79, steps = 20 23:48:46 [INFO] train episode 33131: reward = -97.19, steps = 28 23:48:48 [INFO] train episode 33132: reward = -47.82, steps = 25 23:48:52 [INFO] train episode 33133: reward = -96.25, steps = 27 23:48:54 [INFO] train episode 33134: reward = -61.18, steps = 23 23:48:57 [INFO] train episode 33135: reward = -109.75, steps = 29 23:49:00 [INFO] train episode 33136: reward = -110.67, steps = 31 23:49:03 [INFO] train episode 33137: reward = -81.09, steps = 33 23:49:05 [INFO] train episode 33138: reward = -113.73, steps = 21 23:49:09 [INFO] train episode 33139: reward = -98.38, steps = 34 23:49:11 [INFO] train episode 33140: reward = -92.93, steps = 24 23:49:14 [INFO] train episode 33141: reward = -92.15, steps = 29 23:49:17 [INFO] train episode 33142: reward = -119.47, steps = 27 23:49:19 [INFO] train episode 33143: reward = -87.13, steps = 22 23:49:22 [INFO] train episode 33144: reward = -86.19, steps = 26 23:49:25 [INFO] train episode 33145: reward = -97.07, steps = 22 23:49:28 [INFO] train episode 33146: reward = -104.99, steps = 39 23:49:30 [INFO] train episode 33147: reward = -86.71, steps = 20 23:49:32 [INFO] train episode 33148: reward = -69.30, steps = 18 23:49:34 [INFO] train episode 33149: reward = -73.58, steps = 21 23:49:36 [INFO] train episode 33150: reward = -85.14, steps = 19 23:49:38 [INFO] train episode 33151: reward = -57.71, steps = 19 23:49:41 [INFO] train episode 33152: reward = -135.02, steps = 22 23:49:44 [INFO] train episode 33153: reward = -125.87, steps = 31 23:49:46 [INFO] train episode 33154: reward = -77.70, steps = 25 23:49:49 [INFO] train episode 33155: reward = -127.42, steps = 33 23:49:52 [INFO] train episode 33156: reward = -168.00, steps = 25 23:49:55 [INFO] train episode 33157: reward = -100.85, steps = 35 23:49:57 [INFO] train episode 33158: reward = -75.07, steps = 20 23:49:59 [INFO] train episode 33159: reward = -65.72, steps = 20 23:50:01 [INFO] train episode 33160: reward = -68.17, steps = 20 23:50:03 [INFO] train episode 33161: reward = -57.08, steps = 22 23:50:05 [INFO] train episode 33162: reward = -130.05, steps = 20 23:50:08 [INFO] train episode 33163: reward = -69.76, steps = 26 23:50:10 [INFO] train episode 33164: reward = -153.37, steps = 20 23:50:12 [INFO] train episode 33165: reward = -64.33, steps = 20 23:50:13 [INFO] train episode 33166: reward = -112.00, steps = 20 23:50:17 [INFO] train episode 33167: reward = -86.31, steps = 26 23:50:19 [INFO] train episode 33168: reward = -94.26, steps = 20 23:50:22 [INFO] train episode 33169: reward = -70.10, steps = 33 23:50:27 [INFO] train episode 33170: reward = -99.00, steps = 48 23:50:31 [INFO] train episode 33171: reward = -109.04, steps = 29 23:50:33 [INFO] train episode 33172: reward = -113.42, steps = 18 23:50:38 [INFO] train episode 33173: reward = -96.42, steps = 32 23:50:41 [INFO] train episode 33174: reward = -135.29, steps = 21 23:50:44 [INFO] train episode 33175: reward = -135.79, steps = 23 23:50:46 [INFO] train episode 33176: reward = -89.16, steps = 21 23:50:49 [INFO] train episode 33177: reward = -145.46, steps = 21 23:50:52 [INFO] train episode 33178: reward = -161.86, steps = 23 23:50:55 [INFO] train episode 33179: reward = -48.20, steps = 26 23:50:59 [INFO] train episode 33180: reward = -64.08, steps = 28 23:51:02 [INFO] train episode 33181: reward = -87.86, steps = 20 23:51:06 [INFO] train episode 33182: reward = -82.47, steps = 32 23:51:08 [INFO] train episode 33183: reward = -95.40, steps = 27 23:51:10 [INFO] train episode 33184: reward = -83.55, steps = 20 23:51:15 [INFO] train episode 33185: reward = -174.44, steps = 48 23:51:17 [INFO] train episode 33186: reward = -92.51, steps = 19 23:51:20 [INFO] train episode 33187: reward = -109.19, steps = 26 23:51:22 [INFO] train episode 33188: reward = -72.33, steps = 21 23:51:27 [INFO] train episode 33189: reward = -157.59, steps = 49 23:51:31 [INFO] train episode 33190: reward = -251.25, steps = 47 23:51:33 [INFO] train episode 33191: reward = -79.82, steps = 20 23:51:35 [INFO] train episode 33192: reward = -74.43, steps = 18 23:51:37 [INFO] train episode 33193: reward = -124.90, steps = 21 23:51:40 [INFO] train episode 33194: reward = -121.10, steps = 29 23:51:43 [INFO] train episode 33195: reward = -106.74, steps = 22 23:51:45 [INFO] train episode 33196: reward = -166.23, steps = 25 23:51:49 [INFO] train episode 33197: reward = -204.16, steps = 44 23:51:51 [INFO] train episode 33198: reward = -137.32, steps = 20 23:51:54 [INFO] train episode 33199: reward = -106.34, steps = 26 23:51:59 [INFO] train episode 33200: reward = -123.11, steps = 40 23:52:01 [INFO] train episode 33201: reward = -105.03, steps = 22 23:52:04 [INFO] train episode 33202: reward = -94.61, steps = 42 23:52:06 [INFO] train episode 33203: reward = -69.30, steps = 22 23:52:08 [INFO] train episode 33204: reward = -194.17, steps = 19 23:52:10 [INFO] train episode 33205: reward = -92.88, steps = 22 23:52:13 [INFO] train episode 33206: reward = -65.03, steps = 26 23:52:15 [INFO] train episode 33207: reward = -144.06, steps = 20 23:52:19 [INFO] train episode 33208: reward = -102.39, steps = 34 23:52:21 [INFO] train episode 33209: reward = -128.43, steps = 27 23:52:25 [INFO] train episode 33210: reward = -169.03, steps = 34 23:52:27 [INFO] train episode 33211: reward = -89.24, steps = 22 23:52:30 [INFO] train episode 33212: reward = -112.45, steps = 32 23:52:33 [INFO] train episode 33213: reward = -94.19, steps = 29 23:52:35 [INFO] train episode 33214: reward = -65.72, steps = 18 23:52:37 [INFO] train episode 33215: reward = -62.67, steps = 19 23:52:39 [INFO] train episode 33216: reward = -97.57, steps = 21 23:52:41 [INFO] train episode 33217: reward = -107.24, steps = 20 23:52:44 [INFO] train episode 33218: reward = -80.01, steps = 26 23:52:49 [INFO] train episode 33219: reward = -175.44, steps = 52 23:52:52 [INFO] train episode 33220: reward = -115.41, steps = 25 23:52:54 [INFO] train episode 33221: reward = -108.55, steps = 20 23:52:57 [INFO] train episode 33222: reward = -78.58, steps = 24 23:52:59 [INFO] train episode 33223: reward = -142.31, steps = 21 23:53:03 [INFO] train episode 33224: reward = -227.03, steps = 42 23:53:05 [INFO] train episode 33225: reward = -63.02, steps = 21 23:53:07 [INFO] train episode 33226: reward = -117.14, steps = 19 23:53:09 [INFO] train episode 33227: reward = -113.81, steps = 26 23:53:14 [INFO] train episode 33228: reward = -95.52, steps = 39 23:53:17 [INFO] train episode 33229: reward = -135.55, steps = 38 23:53:19 [INFO] train episode 33230: reward = -71.53, steps = 18 23:53:21 [INFO] train episode 33231: reward = -78.21, steps = 19 23:53:24 [INFO] train episode 33232: reward = -128.81, steps = 25 23:53:25 [INFO] train episode 33233: reward = -56.45, steps = 18 23:53:27 [INFO] train episode 33234: reward = -125.59, steps = 17 23:53:30 [INFO] train episode 33235: reward = -140.60, steps = 25 23:53:31 [INFO] train episode 33236: reward = -126.03, steps = 18 23:53:33 [INFO] train episode 33237: reward = -73.04, steps = 19 23:53:35 [INFO] train episode 33238: reward = -109.22, steps = 25 23:53:37 [INFO] train episode 33239: reward = -104.93, steps = 20 23:53:40 [INFO] train episode 33240: reward = -182.19, steps = 26 23:53:43 [INFO] train episode 33241: reward = -120.34, steps = 33 23:53:46 [INFO] train episode 33242: reward = -70.54, steps = 25 23:53:49 [INFO] train episode 33243: reward = -137.01, steps = 31 23:53:51 [INFO] train episode 33244: reward = -77.21, steps = 19 23:53:53 [INFO] train episode 33245: reward = -67.41, steps = 20 23:53:55 [INFO] train episode 33246: reward = -101.04, steps = 19 23:53:58 [INFO] train episode 33247: reward = -89.90, steps = 38 23:54:00 [INFO] train episode 33248: reward = -84.28, steps = 20 23:54:03 [INFO] train episode 33249: reward = -110.42, steps = 24 23:54:07 [INFO] train episode 33250: reward = -101.98, steps = 36 23:54:09 [INFO] train episode 33251: reward = -56.81, steps = 25 23:54:12 [INFO] train episode 33252: reward = -192.03, steps = 31 23:54:15 [INFO] train episode 33253: reward = -103.52, steps = 26 23:54:17 [INFO] train episode 33254: reward = -58.66, steps = 21 23:54:19 [INFO] train episode 33255: reward = -95.57, steps = 27 23:54:22 [INFO] train episode 33256: reward = -136.17, steps = 23 23:54:25 [INFO] train episode 33257: reward = -101.38, steps = 33 23:54:28 [INFO] train episode 33258: reward = -57.04, steps = 25 23:54:30 [INFO] train episode 33259: reward = -90.76, steps = 26 23:54:32 [INFO] train episode 33260: reward = -98.16, steps = 23 23:54:35 [INFO] train episode 33261: reward = -81.96, steps = 33 23:54:38 [INFO] train episode 33262: reward = -80.54, steps = 21 23:54:41 [INFO] train episode 33263: reward = -84.83, steps = 28 23:54:43 [INFO] train episode 33264: reward = -73.36, steps = 24 23:54:46 [INFO] train episode 33265: reward = -133.51, steps = 28 23:54:48 [INFO] train episode 33266: reward = -145.91, steps = 20 23:54:50 [INFO] train episode 33267: reward = -86.66, steps = 20 23:54:52 [INFO] train episode 33268: reward = -71.04, steps = 22 23:54:55 [INFO] train episode 33269: reward = -107.21, steps = 35 23:54:58 [INFO] train episode 33270: reward = -106.99, steps = 21 23:55:00 [INFO] train episode 33271: reward = -106.98, steps = 24 23:55:02 [INFO] train episode 33272: reward = -109.66, steps = 25 23:55:04 [INFO] train episode 33273: reward = -84.46, steps = 20 23:55:06 [INFO] train episode 33274: reward = -47.23, steps = 18 23:55:09 [INFO] train episode 33275: reward = -91.89, steps = 24 23:55:10 [INFO] train episode 33276: reward = -104.72, steps = 19 23:55:13 [INFO] train episode 33277: reward = -74.06, steps = 23 23:55:15 [INFO] train episode 33278: reward = -90.50, steps = 25 23:55:18 [INFO] train episode 33279: reward = -63.08, steps = 32 23:55:20 [INFO] train episode 33280: reward = -111.84, steps = 23 23:55:22 [INFO] train episode 33281: reward = -118.59, steps = 19 23:55:24 [INFO] train episode 33282: reward = -98.80, steps = 30 23:55:26 [INFO] train episode 33283: reward = -107.94, steps = 19 23:55:28 [INFO] train episode 33284: reward = -81.65, steps = 15 23:55:30 [INFO] train episode 33285: reward = -150.33, steps = 30 23:55:32 [INFO] train episode 33286: reward = -64.15, steps = 20 23:55:37 [INFO] train episode 33287: reward = -117.79, steps = 46 23:55:39 [INFO] train episode 33288: reward = -82.18, steps = 20 23:55:42 [INFO] train episode 33289: reward = -113.04, steps = 38 23:55:44 [INFO] train episode 33290: reward = -97.50, steps = 19 23:55:46 [INFO] train episode 33291: reward = -74.06, steps = 22 23:55:47 [INFO] train episode 33292: reward = -78.28, steps = 19 23:55:51 [INFO] train episode 33293: reward = -122.59, steps = 38 23:55:53 [INFO] train episode 33294: reward = -109.51, steps = 19 23:55:56 [INFO] train episode 33295: reward = -62.79, steps = 30 23:55:58 [INFO] train episode 33296: reward = -81.43, steps = 24 23:56:00 [INFO] train episode 33297: reward = -89.82, steps = 26 23:56:02 [INFO] train episode 33298: reward = -128.51, steps = 25 23:56:04 [INFO] train episode 33299: reward = -96.77, steps = 21 23:56:07 [INFO] train episode 33300: reward = -132.81, steps = 29 23:56:09 [INFO] train episode 33301: reward = -101.53, steps = 27 23:56:11 [INFO] train episode 33302: reward = -59.63, steps = 22 23:56:13 [INFO] train episode 33303: reward = -89.98, steps = 19 23:56:17 [INFO] train episode 33304: reward = -122.93, steps = 39 23:56:18 [INFO] train episode 33305: reward = -100.43, steps = 20 23:56:20 [INFO] train episode 33306: reward = -81.61, steps = 18 23:56:22 [INFO] train episode 33307: reward = -72.35, steps = 12 23:56:25 [INFO] train episode 33308: reward = -167.93, steps = 44 23:56:28 [INFO] train episode 33309: reward = -97.46, steps = 32 23:56:30 [INFO] train episode 33310: reward = -46.21, steps = 21 23:56:33 [INFO] train episode 33311: reward = -153.43, steps = 32 23:56:35 [INFO] train episode 33312: reward = -56.29, steps = 24 23:56:39 [INFO] train episode 33313: reward = -111.30, steps = 33 23:56:41 [INFO] train episode 33314: reward = -202.04, steps = 22 23:56:44 [INFO] train episode 33315: reward = -139.54, steps = 37 23:56:48 [INFO] train episode 33316: reward = -153.11, steps = 41 23:56:50 [INFO] train episode 33317: reward = -115.92, steps = 20 23:56:51 [INFO] train episode 33318: reward = -86.71, steps = 20 23:56:53 [INFO] train episode 33319: reward = -116.12, steps = 23 23:56:57 [INFO] train episode 33320: reward = -111.64, steps = 34 23:56:59 [INFO] train episode 33321: reward = -121.35, steps = 20 23:57:02 [INFO] train episode 33322: reward = -164.06, steps = 41 23:57:04 [INFO] train episode 33323: reward = -56.62, steps = 18 23:57:07 [INFO] train episode 33324: reward = -146.32, steps = 33 23:57:09 [INFO] train episode 33325: reward = -94.92, steps = 23 23:57:12 [INFO] train episode 33326: reward = -82.35, steps = 24 23:57:13 [INFO] train episode 33327: reward = -98.37, steps = 20 23:57:16 [INFO] train episode 33328: reward = -179.44, steps = 28 23:57:18 [INFO] train episode 33329: reward = -76.58, steps = 19 23:57:19 [INFO] train episode 33330: reward = -68.97, steps = 19 23:57:21 [INFO] train episode 33331: reward = -125.65, steps = 23 23:57:24 [INFO] train episode 33332: reward = -103.68, steps = 26 23:57:26 [INFO] train episode 33333: reward = -87.43, steps = 21 23:57:28 [INFO] train episode 33334: reward = -105.68, steps = 25 23:57:31 [INFO] train episode 33335: reward = -115.36, steps = 28 23:57:33 [INFO] train episode 33336: reward = -68.26, steps = 27 23:57:36 [INFO] train episode 33337: reward = -89.73, steps = 30 23:57:38 [INFO] train episode 33338: reward = -88.35, steps = 22 23:57:41 [INFO] train episode 33339: reward = -80.46, steps = 31 23:57:43 [INFO] train episode 33340: reward = -86.49, steps = 20 23:57:45 [INFO] train episode 33341: reward = -80.44, steps = 24 23:57:47 [INFO] train episode 33342: reward = -122.87, steps = 23 23:57:49 [INFO] train episode 33343: reward = -92.19, steps = 19 23:57:54 [INFO] train episode 33344: reward = -121.72, steps = 50 23:57:56 [INFO] train episode 33345: reward = -147.48, steps = 29 23:57:58 [INFO] train episode 33346: reward = -113.09, steps = 19 23:58:00 [INFO] train episode 33347: reward = -71.36, steps = 22 23:58:02 [INFO] train episode 33348: reward = -82.53, steps = 25 23:58:05 [INFO] train episode 33349: reward = -89.45, steps = 26 23:58:07 [INFO] train episode 33350: reward = -99.48, steps = 19 23:58:09 [INFO] train episode 33351: reward = -79.33, steps = 15 23:58:10 [INFO] train episode 33352: reward = -84.18, steps = 18 23:58:12 [INFO] train episode 33353: reward = -114.70, steps = 19 23:58:14 [INFO] train episode 33354: reward = -120.71, steps = 19 23:58:16 [INFO] train episode 33355: reward = -69.24, steps = 20 23:58:18 [INFO] train episode 33356: reward = -118.72, steps = 24 23:58:20 [INFO] train episode 33357: reward = -77.39, steps = 18 23:58:22 [INFO] train episode 33358: reward = -80.35, steps = 22 23:58:25 [INFO] train episode 33359: reward = -88.74, steps = 36 23:58:27 [INFO] train episode 33360: reward = -111.28, steps = 22 23:58:30 [INFO] train episode 33361: reward = -170.08, steps = 39 23:58:33 [INFO] train episode 33362: reward = -115.96, steps = 27 23:58:35 [INFO] train episode 33363: reward = -65.66, steps = 19 23:58:37 [INFO] train episode 33364: reward = -185.52, steps = 22 23:58:39 [INFO] train episode 33365: reward = -71.70, steps = 23 23:58:41 [INFO] train episode 33366: reward = -93.07, steps = 20 23:58:43 [INFO] train episode 33367: reward = -91.09, steps = 25 23:58:46 [INFO] train episode 33368: reward = -96.49, steps = 31 23:58:48 [INFO] train episode 33369: reward = -56.99, steps = 21 23:58:50 [INFO] train episode 33370: reward = -70.25, steps = 21 23:58:54 [INFO] train episode 33371: reward = -122.99, steps = 46 23:58:56 [INFO] train episode 33372: reward = -82.47, steps = 20 23:58:59 [INFO] train episode 33373: reward = -75.02, steps = 34 23:59:02 [INFO] train episode 33374: reward = -96.83, steps = 29 23:59:04 [INFO] train episode 33375: reward = -90.18, steps = 31 23:59:06 [INFO] train episode 33376: reward = -105.37, steps = 22 23:59:09 [INFO] train episode 33377: reward = -104.22, steps = 29 23:59:11 [INFO] train episode 33378: reward = -105.04, steps = 17 23:59:13 [INFO] train episode 33379: reward = -80.94, steps = 21 23:59:16 [INFO] train episode 33380: reward = -126.51, steps = 28 23:59:18 [INFO] train episode 33381: reward = -130.07, steps = 22 23:59:22 [INFO] train episode 33382: reward = -112.50, steps = 37 23:59:25 [INFO] train episode 33383: reward = -114.50, steps = 24 23:59:27 [INFO] train episode 33384: reward = -91.88, steps = 20 23:59:29 [INFO] train episode 33385: reward = -106.62, steps = 22 23:59:32 [INFO] train episode 33386: reward = -79.65, steps = 20 23:59:35 [INFO] train episode 33387: reward = -103.32, steps = 36 23:59:37 [INFO] train episode 33388: reward = -107.49, steps = 20 23:59:39 [INFO] train episode 33389: reward = -73.72, steps = 21 23:59:42 [INFO] train episode 33390: reward = -120.31, steps = 26 23:59:44 [INFO] train episode 33391: reward = -111.41, steps = 27 23:59:47 [INFO] train episode 33392: reward = -108.11, steps = 27 23:59:49 [INFO] train episode 33393: reward = -100.75, steps = 22 23:59:52 [INFO] train episode 33394: reward = -113.17, steps = 25 23:59:54 [INFO] train episode 33395: reward = -74.65, steps = 19 23:59:58 [INFO] train episode 33396: reward = -152.19, steps = 37 00:00:00 [INFO] train episode 33397: reward = -81.56, steps = 28 00:00:04 [INFO] train episode 33398: reward = -95.89, steps = 34 00:00:08 [INFO] train episode 33399: reward = -92.71, steps = 40 00:00:10 [INFO] train episode 33400: reward = -133.91, steps = 20 00:00:12 [INFO] train episode 33401: reward = -99.58, steps = 28 00:00:15 [INFO] train episode 33402: reward = -87.25, steps = 24 00:00:19 [INFO] train episode 33403: reward = -73.77, steps = 44 00:00:21 [INFO] train episode 33404: reward = -110.72, steps = 26 00:00:25 [INFO] train episode 33405: reward = -107.18, steps = 35 00:00:27 [INFO] train episode 33406: reward = -101.32, steps = 31 00:00:30 [INFO] train episode 33407: reward = -93.09, steps = 33 00:00:34 [INFO] train episode 33408: reward = -107.67, steps = 36 00:00:36 [INFO] train episode 33409: reward = -63.74, steps = 24 00:00:38 [INFO] train episode 33410: reward = -77.96, steps = 20 00:00:41 [INFO] train episode 33411: reward = -91.95, steps = 27 00:00:43 [INFO] train episode 33412: reward = -72.65, steps = 27 00:00:47 [INFO] train episode 33413: reward = -105.32, steps = 39 00:00:49 [INFO] train episode 33414: reward = -117.48, steps = 22 00:00:52 [INFO] train episode 33415: reward = -75.27, steps = 30 00:00:54 [INFO] train episode 33416: reward = -67.17, steps = 23 00:00:57 [INFO] train episode 33417: reward = -135.68, steps = 33 00:00:59 [INFO] train episode 33418: reward = -81.02, steps = 23 00:01:01 [INFO] train episode 33419: reward = -85.78, steps = 19 00:01:03 [INFO] train episode 33420: reward = -81.26, steps = 23 00:01:05 [INFO] train episode 33421: reward = -79.27, steps = 20 00:01:08 [INFO] train episode 33422: reward = -172.14, steps = 33 00:01:10 [INFO] train episode 33423: reward = -99.92, steps = 25 00:01:14 [INFO] train episode 33424: reward = -97.18, steps = 22 00:01:16 [INFO] train episode 33425: reward = -67.11, steps = 25 00:01:18 [INFO] train episode 33426: reward = -99.01, steps = 21 00:01:21 [INFO] train episode 33427: reward = -149.30, steps = 28 00:01:23 [INFO] train episode 33428: reward = -68.30, steps = 21 00:01:25 [INFO] train episode 33429: reward = -90.55, steps = 30 00:01:28 [INFO] train episode 33430: reward = -106.21, steps = 32 00:01:32 [INFO] train episode 33431: reward = -91.32, steps = 34 00:01:33 [INFO] train episode 33432: reward = -91.43, steps = 18 00:01:36 [INFO] train episode 33433: reward = -76.91, steps = 25 00:01:37 [INFO] train episode 33434: reward = -122.27, steps = 18 00:01:39 [INFO] train episode 33435: reward = -86.46, steps = 20 00:01:42 [INFO] train episode 33436: reward = -109.35, steps = 33 00:01:44 [INFO] train episode 33437: reward = -171.29, steps = 23 00:01:47 [INFO] train episode 33438: reward = -83.57, steps = 29 00:01:50 [INFO] train episode 33439: reward = -123.94, steps = 30 00:01:52 [INFO] train episode 33440: reward = -93.29, steps = 21 00:01:55 [INFO] train episode 33441: reward = -113.95, steps = 34 00:01:58 [INFO] train episode 33442: reward = -125.49, steps = 28 00:02:00 [INFO] train episode 33443: reward = -134.37, steps = 20 00:02:02 [INFO] train episode 33444: reward = -83.74, steps = 22 00:02:05 [INFO] train episode 33445: reward = -82.90, steps = 27 00:02:09 [INFO] train episode 33446: reward = -118.92, steps = 44 00:02:11 [INFO] train episode 33447: reward = -84.49, steps = 20 00:02:13 [INFO] train episode 33448: reward = -86.27, steps = 21 00:02:14 [INFO] train episode 33449: reward = -93.30, steps = 19 00:02:16 [INFO] train episode 33450: reward = -91.82, steps = 19 00:02:19 [INFO] train episode 33451: reward = -66.29, steps = 30 00:02:21 [INFO] train episode 33452: reward = -85.45, steps = 20 00:02:23 [INFO] train episode 33453: reward = -112.19, steps = 22 00:02:25 [INFO] train episode 33454: reward = -92.13, steps = 21 00:02:30 [INFO] train episode 33455: reward = -165.06, steps = 42 00:02:32 [INFO] train episode 33456: reward = -80.03, steps = 24 00:02:34 [INFO] train episode 33457: reward = -90.07, steps = 20 00:02:36 [INFO] train episode 33458: reward = -83.03, steps = 21 00:02:39 [INFO] train episode 33459: reward = -64.53, steps = 24 00:02:42 [INFO] train episode 33460: reward = -222.89, steps = 33 00:02:45 [INFO] train episode 33461: reward = -120.18, steps = 25 00:02:47 [INFO] train episode 33462: reward = -91.96, steps = 19 00:02:50 [INFO] train episode 33463: reward = -114.22, steps = 31 00:02:52 [INFO] train episode 33464: reward = -66.71, steps = 19 00:02:54 [INFO] train episode 33465: reward = -62.06, steps = 19 00:02:56 [INFO] train episode 33466: reward = -52.98, steps = 20 00:02:59 [INFO] train episode 33467: reward = -73.25, steps = 24 00:03:02 [INFO] train episode 33468: reward = -72.43, steps = 31 00:03:04 [INFO] train episode 33469: reward = -126.90, steps = 21 00:03:08 [INFO] train episode 33470: reward = -131.10, steps = 34 00:03:11 [INFO] train episode 33471: reward = -104.80, steps = 30 00:03:13 [INFO] train episode 33472: reward = -94.05, steps = 22 00:03:16 [INFO] train episode 33473: reward = -82.67, steps = 25 00:03:19 [INFO] train episode 33474: reward = -120.82, steps = 21 00:03:21 [INFO] train episode 33475: reward = -106.46, steps = 21 00:03:25 [INFO] train episode 33476: reward = -170.85, steps = 44 00:03:29 [INFO] train episode 33477: reward = -113.64, steps = 36 00:03:31 [INFO] train episode 33478: reward = -84.11, steps = 22 00:03:33 [INFO] train episode 33479: reward = -97.39, steps = 28 00:03:36 [INFO] train episode 33480: reward = -55.32, steps = 24 00:03:39 [INFO] train episode 33481: reward = -144.80, steps = 41 00:03:41 [INFO] train episode 33482: reward = -75.46, steps = 19 00:03:43 [INFO] train episode 33483: reward = -102.59, steps = 20 00:03:45 [INFO] train episode 33484: reward = -111.29, steps = 21 00:03:47 [INFO] train episode 33485: reward = -87.87, steps = 20 00:03:49 [INFO] train episode 33486: reward = -118.04, steps = 20 00:03:51 [INFO] train episode 33487: reward = -92.05, steps = 26 00:03:53 [INFO] train episode 33488: reward = -71.84, steps = 20 00:03:55 [INFO] train episode 33489: reward = -85.00, steps = 23 00:03:57 [INFO] train episode 33490: reward = -53.45, steps = 19 00:04:01 [INFO] train episode 33491: reward = -85.32, steps = 39 00:04:03 [INFO] train episode 33492: reward = -97.17, steps = 21 00:04:06 [INFO] train episode 33493: reward = -110.82, steps = 39 00:04:08 [INFO] train episode 33494: reward = -77.47, steps = 19 00:04:10 [INFO] train episode 33495: reward = -69.20, steps = 17 00:04:13 [INFO] train episode 33496: reward = -105.98, steps = 31 00:04:14 [INFO] train episode 33497: reward = -111.94, steps = 19 00:04:16 [INFO] train episode 33498: reward = -147.62, steps = 24 00:04:19 [INFO] train episode 33499: reward = -130.41, steps = 29 00:04:21 [INFO] train episode 33500: reward = -65.47, steps = 20 00:04:24 [INFO] train episode 33501: reward = -101.65, steps = 22 00:04:26 [INFO] train episode 33502: reward = -108.79, steps = 20 00:04:28 [INFO] train episode 33503: reward = -85.60, steps = 20 00:04:30 [INFO] train episode 33504: reward = -67.17, steps = 23 00:04:32 [INFO] train episode 33505: reward = -100.31, steps = 26 00:04:35 [INFO] train episode 33506: reward = -83.46, steps = 26 00:04:37 [INFO] train episode 33507: reward = -62.65, steps = 25 00:04:39 [INFO] train episode 33508: reward = -99.30, steps = 20 00:04:41 [INFO] train episode 33509: reward = -185.24, steps = 26 00:04:43 [INFO] train episode 33510: reward = -87.44, steps = 20 00:04:45 [INFO] train episode 33511: reward = -85.35, steps = 19 00:04:47 [INFO] train episode 33512: reward = -79.02, steps = 24 00:04:49 [INFO] train episode 33513: reward = -129.32, steps = 21 00:04:51 [INFO] train episode 33514: reward = -97.69, steps = 24 00:04:54 [INFO] train episode 33515: reward = -76.71, steps = 28 00:04:59 [INFO] train episode 33516: reward = -185.43, steps = 43 00:05:02 [INFO] train episode 33517: reward = -96.09, steps = 29 00:05:04 [INFO] train episode 33518: reward = -72.16, steps = 22 00:05:06 [INFO] train episode 33519: reward = -71.06, steps = 22 00:05:08 [INFO] train episode 33520: reward = -58.92, steps = 21 00:05:10 [INFO] train episode 33521: reward = -96.17, steps = 22 00:05:12 [INFO] train episode 33522: reward = -86.55, steps = 19 00:05:16 [INFO] train episode 33523: reward = -172.15, steps = 33 00:05:18 [INFO] train episode 33524: reward = -76.63, steps = 19 00:05:20 [INFO] train episode 33525: reward = -108.92, steps = 25 00:05:23 [INFO] train episode 33526: reward = -95.12, steps = 29 00:05:26 [INFO] train episode 33527: reward = -122.01, steps = 28 00:05:28 [INFO] train episode 33528: reward = -164.91, steps = 20 00:05:31 [INFO] train episode 33529: reward = -76.90, steps = 21 00:05:34 [INFO] train episode 33530: reward = -111.47, steps = 29 00:05:37 [INFO] train episode 33531: reward = -114.09, steps = 32 00:05:43 [INFO] train episode 33532: reward = -168.12, steps = 51 00:05:46 [INFO] train episode 33533: reward = -74.22, steps = 27 00:05:48 [INFO] train episode 33534: reward = -135.64, steps = 24 00:05:50 [INFO] train episode 33535: reward = -56.39, steps = 21 00:05:52 [INFO] train episode 33536: reward = -63.26, steps = 19 00:05:55 [INFO] train episode 33537: reward = -89.58, steps = 30 00:05:57 [INFO] train episode 33538: reward = -111.12, steps = 21 00:05:59 [INFO] train episode 33539: reward = -84.74, steps = 21 00:06:01 [INFO] train episode 33540: reward = -105.99, steps = 19 00:06:05 [INFO] train episode 33541: reward = -150.73, steps = 37 00:06:07 [INFO] train episode 33542: reward = -85.37, steps = 18 00:06:09 [INFO] train episode 33543: reward = -74.15, steps = 20 00:06:12 [INFO] train episode 33544: reward = -100.00, steps = 31 00:06:14 [INFO] train episode 33545: reward = -81.69, steps = 20 00:06:17 [INFO] train episode 33546: reward = -84.60, steps = 20 00:06:20 [INFO] train episode 33547: reward = -71.87, steps = 24 00:06:21 [INFO] train episode 33548: reward = -105.04, steps = 20 00:06:24 [INFO] train episode 33549: reward = -54.74, steps = 23 00:06:26 [INFO] train episode 33550: reward = -67.54, steps = 21 00:06:29 [INFO] train episode 33551: reward = -152.23, steps = 29 00:06:31 [INFO] train episode 33552: reward = -119.11, steps = 21 00:06:33 [INFO] train episode 33553: reward = -84.87, steps = 22 00:06:37 [INFO] train episode 33554: reward = -144.05, steps = 42 00:06:41 [INFO] train episode 33555: reward = -138.58, steps = 46 00:06:44 [INFO] train episode 33556: reward = -148.70, steps = 35 00:06:47 [INFO] train episode 33557: reward = -121.21, steps = 27 00:06:49 [INFO] train episode 33558: reward = -100.72, steps = 18 00:06:51 [INFO] train episode 33559: reward = -103.56, steps = 21 00:06:53 [INFO] train episode 33560: reward = -99.92, steps = 27 00:06:57 [INFO] train episode 33561: reward = -137.24, steps = 40 00:06:59 [INFO] train episode 33562: reward = -70.60, steps = 19 00:07:02 [INFO] train episode 33563: reward = -113.62, steps = 22 00:07:04 [INFO] train episode 33564: reward = -63.12, steps = 22 00:07:06 [INFO] train episode 33565: reward = -59.72, steps = 22 00:07:08 [INFO] train episode 33566: reward = -106.00, steps = 18 00:07:11 [INFO] train episode 33567: reward = -64.62, steps = 21 00:07:13 [INFO] train episode 33568: reward = -93.88, steps = 23 00:07:15 [INFO] train episode 33569: reward = -86.11, steps = 20 00:07:18 [INFO] train episode 33570: reward = -85.18, steps = 36 00:07:20 [INFO] train episode 33571: reward = -67.57, steps = 21 00:07:22 [INFO] train episode 33572: reward = -77.96, steps = 20 00:07:24 [INFO] train episode 33573: reward = -100.58, steps = 25 00:07:28 [INFO] train episode 33574: reward = -88.50, steps = 32 00:07:30 [INFO] train episode 33575: reward = -159.10, steps = 25 00:07:33 [INFO] train episode 33576: reward = -89.01, steps = 23 00:07:35 [INFO] train episode 33577: reward = -138.78, steps = 27 00:07:38 [INFO] train episode 33578: reward = -89.98, steps = 29 00:07:40 [INFO] train episode 33579: reward = -79.83, steps = 20 00:07:42 [INFO] train episode 33580: reward = -103.65, steps = 22 00:07:44 [INFO] train episode 33581: reward = -86.66, steps = 21 00:07:46 [INFO] train episode 33582: reward = -53.62, steps = 19 00:07:48 [INFO] train episode 33583: reward = -140.24, steps = 20 00:07:50 [INFO] train episode 33584: reward = -79.69, steps = 23 00:07:52 [INFO] train episode 33585: reward = -69.69, steps = 19 00:07:54 [INFO] train episode 33586: reward = -98.25, steps = 21 00:07:56 [INFO] train episode 33587: reward = -51.78, steps = 21 00:07:57 [INFO] train episode 33588: reward = -59.03, steps = 20 00:07:59 [INFO] train episode 33589: reward = -65.56, steps = 22 00:08:02 [INFO] train episode 33590: reward = -65.20, steps = 29 00:08:04 [INFO] train episode 33591: reward = -80.23, steps = 16 00:08:06 [INFO] train episode 33592: reward = -99.85, steps = 22 00:08:08 [INFO] train episode 33593: reward = -71.57, steps = 25 00:08:10 [INFO] train episode 33594: reward = -129.38, steps = 19 00:08:12 [INFO] train episode 33595: reward = -77.34, steps = 20 00:08:13 [INFO] train episode 33596: reward = -115.17, steps = 20 00:08:15 [INFO] train episode 33597: reward = -96.84, steps = 21 00:08:19 [INFO] train episode 33598: reward = -100.79, steps = 38 00:08:22 [INFO] train episode 33599: reward = -96.22, steps = 29 00:08:24 [INFO] train episode 33600: reward = -91.80, steps = 19 00:08:27 [INFO] train episode 33601: reward = -103.81, steps = 40 00:08:29 [INFO] train episode 33602: reward = -53.18, steps = 20 00:08:32 [INFO] train episode 33603: reward = -69.80, steps = 32 00:08:33 [INFO] train episode 33604: reward = -137.55, steps = 19 00:08:36 [INFO] train episode 33605: reward = -93.95, steps = 20 00:08:39 [INFO] train episode 33606: reward = -91.31, steps = 36 00:08:41 [INFO] train episode 33607: reward = -92.17, steps = 20 00:08:43 [INFO] train episode 33608: reward = -127.87, steps = 25 00:08:46 [INFO] train episode 33609: reward = -127.96, steps = 33 00:08:48 [INFO] train episode 33610: reward = -121.53, steps = 24 00:08:50 [INFO] train episode 33611: reward = -135.50, steps = 24 00:08:53 [INFO] train episode 33612: reward = -140.86, steps = 28 00:08:55 [INFO] train episode 33613: reward = -126.62, steps = 25 00:09:01 [INFO] train episode 33614: reward = -189.30, steps = 58 00:09:02 [INFO] train episode 33615: reward = -73.28, steps = 20 00:09:04 [INFO] train episode 33616: reward = -100.08, steps = 19 00:09:07 [INFO] train episode 33617: reward = -69.05, steps = 26 00:09:09 [INFO] train episode 33618: reward = -99.95, steps = 24 00:09:12 [INFO] train episode 33619: reward = -154.49, steps = 30 00:09:14 [INFO] train episode 33620: reward = -107.45, steps = 26 00:09:16 [INFO] train episode 33621: reward = -98.10, steps = 22 00:09:18 [INFO] train episode 33622: reward = -102.17, steps = 26 00:09:20 [INFO] train episode 33623: reward = -94.91, steps = 19 00:09:22 [INFO] train episode 33624: reward = -70.19, steps = 21 00:09:24 [INFO] train episode 33625: reward = -94.72, steps = 21 00:09:28 [INFO] train episode 33626: reward = -119.30, steps = 40 00:09:30 [INFO] train episode 33627: reward = -76.59, steps = 21 00:09:32 [INFO] train episode 33628: reward = -67.86, steps = 23 00:09:34 [INFO] train episode 33629: reward = -75.31, steps = 23 00:09:36 [INFO] train episode 33630: reward = -76.21, steps = 24 00:09:39 [INFO] train episode 33631: reward = -124.15, steps = 31 00:09:42 [INFO] train episode 33632: reward = -91.78, steps = 33 00:09:44 [INFO] train episode 33633: reward = -84.57, steps = 20 00:09:46 [INFO] train episode 33634: reward = -107.01, steps = 19 00:09:49 [INFO] train episode 33635: reward = -96.75, steps = 32 00:09:52 [INFO] train episode 33636: reward = -124.79, steps = 32 00:09:54 [INFO] train episode 33637: reward = -75.43, steps = 25 00:09:57 [INFO] train episode 33638: reward = -82.29, steps = 37 00:09:59 [INFO] train episode 33639: reward = -80.88, steps = 21 00:10:02 [INFO] train episode 33640: reward = -150.23, steps = 24 00:10:04 [INFO] train episode 33641: reward = -94.62, steps = 30 00:10:09 [INFO] train episode 33642: reward = -88.31, steps = 58 00:10:11 [INFO] train episode 33643: reward = -82.41, steps = 18 00:10:14 [INFO] train episode 33644: reward = -78.60, steps = 31 00:10:16 [INFO] train episode 33645: reward = -85.16, steps = 27 00:10:19 [INFO] train episode 33646: reward = -136.27, steps = 29 00:10:21 [INFO] train episode 33647: reward = -79.99, steps = 22 00:10:23 [INFO] train episode 33648: reward = -97.63, steps = 23 00:10:25 [INFO] train episode 33649: reward = -64.82, steps = 18 00:10:27 [INFO] train episode 33650: reward = -65.68, steps = 21 00:10:28 [INFO] train episode 33651: reward = -187.66, steps = 20 00:10:30 [INFO] train episode 33652: reward = -142.33, steps = 21 00:10:33 [INFO] train episode 33653: reward = -83.84, steps = 22 00:10:35 [INFO] train episode 33654: reward = -102.16, steps = 23 00:10:39 [INFO] train episode 33655: reward = -132.57, steps = 41 00:10:42 [INFO] train episode 33656: reward = -67.53, steps = 27 00:10:44 [INFO] train episode 33657: reward = -75.07, steps = 22 00:10:47 [INFO] train episode 33658: reward = -117.13, steps = 32 00:10:49 [INFO] train episode 33659: reward = -65.71, steps = 22 00:10:52 [INFO] train episode 33660: reward = -110.59, steps = 38 00:10:55 [INFO] train episode 33661: reward = -73.23, steps = 24 00:10:58 [INFO] train episode 33662: reward = -85.03, steps = 33 00:11:02 [INFO] train episode 33663: reward = -166.80, steps = 49 00:11:04 [INFO] train episode 33664: reward = -86.69, steps = 27 00:11:07 [INFO] train episode 33665: reward = -78.18, steps = 23 00:11:10 [INFO] train episode 33666: reward = -108.99, steps = 43 00:11:12 [INFO] train episode 33667: reward = -99.86, steps = 14 00:11:14 [INFO] train episode 33668: reward = -56.79, steps = 27 00:11:16 [INFO] train episode 33669: reward = -71.52, steps = 21 00:11:18 [INFO] train episode 33670: reward = -100.39, steps = 23 00:11:20 [INFO] train episode 33671: reward = -77.81, steps = 20 00:11:22 [INFO] train episode 33672: reward = -107.19, steps = 19 00:11:24 [INFO] train episode 33673: reward = -51.12, steps = 22 00:11:26 [INFO] train episode 33674: reward = -130.46, steps = 19 00:11:28 [INFO] train episode 33675: reward = -68.24, steps = 20 00:11:29 [INFO] train episode 33676: reward = -87.52, steps = 19 00:11:34 [INFO] train episode 33677: reward = -141.66, steps = 46 00:11:35 [INFO] train episode 33678: reward = -99.02, steps = 21 00:11:38 [INFO] train episode 33679: reward = -76.41, steps = 25 00:11:41 [INFO] train episode 33680: reward = -103.55, steps = 31 00:11:43 [INFO] train episode 33681: reward = -62.02, steps = 19 00:11:45 [INFO] train episode 33682: reward = -83.05, steps = 22 00:11:46 [INFO] train episode 33683: reward = -71.14, steps = 21 00:11:49 [INFO] train episode 33684: reward = -109.76, steps = 26 00:11:51 [INFO] train episode 33685: reward = -76.49, steps = 30 00:11:54 [INFO] train episode 33686: reward = -74.66, steps = 25 00:11:57 [INFO] train episode 33687: reward = -113.25, steps = 33 00:12:00 [INFO] train episode 33688: reward = -115.23, steps = 31 00:12:02 [INFO] train episode 33689: reward = -96.50, steps = 20 00:12:04 [INFO] train episode 33690: reward = -72.00, steps = 20 00:12:06 [INFO] train episode 33691: reward = -151.52, steps = 27 00:12:09 [INFO] train episode 33692: reward = -70.02, steps = 30 00:12:11 [INFO] train episode 33693: reward = -87.38, steps = 25 00:12:15 [INFO] train episode 33694: reward = -103.70, steps = 41 00:12:17 [INFO] train episode 33695: reward = -96.96, steps = 25 00:12:19 [INFO] train episode 33696: reward = -59.24, steps = 18 00:12:22 [INFO] train episode 33697: reward = -143.35, steps = 31 00:12:24 [INFO] train episode 33698: reward = -85.40, steps = 22 00:12:26 [INFO] train episode 33699: reward = -82.49, steps = 22 00:12:28 [INFO] train episode 33700: reward = -93.37, steps = 19 00:12:31 [INFO] train episode 33701: reward = -53.83, steps = 22 00:12:38 [INFO] train episode 33702: reward = -93.94, steps = 48 00:12:40 [INFO] train episode 33703: reward = -73.61, steps = 19 00:12:43 [INFO] train episode 33704: reward = -92.36, steps = 19 00:12:46 [INFO] train episode 33705: reward = -68.96, steps = 29 00:12:49 [INFO] train episode 33706: reward = -112.30, steps = 26 00:12:52 [INFO] train episode 33707: reward = -84.03, steps = 24 00:12:56 [INFO] train episode 33708: reward = -118.67, steps = 34 00:12:59 [INFO] train episode 33709: reward = -78.97, steps = 26 00:13:02 [INFO] train episode 33710: reward = -58.53, steps = 22 00:13:05 [INFO] train episode 33711: reward = -134.33, steps = 22 00:13:07 [INFO] train episode 33712: reward = -144.52, steps = 16 00:13:09 [INFO] train episode 33713: reward = -51.23, steps = 23 00:13:13 [INFO] train episode 33714: reward = -98.74, steps = 33 00:13:16 [INFO] train episode 33715: reward = -96.82, steps = 20 00:13:21 [INFO] train episode 33716: reward = -168.81, steps = 38 00:13:23 [INFO] train episode 33717: reward = -89.17, steps = 20 00:13:29 [INFO] train episode 33718: reward = -144.89, steps = 45 00:13:32 [INFO] train episode 33719: reward = -125.83, steps = 21 00:13:35 [INFO] train episode 33720: reward = -102.18, steps = 24 00:13:38 [INFO] train episode 33721: reward = -57.83, steps = 22 00:13:41 [INFO] train episode 33722: reward = -132.07, steps = 32 00:13:44 [INFO] train episode 33723: reward = -106.84, steps = 21 00:13:47 [INFO] train episode 33724: reward = -84.06, steps = 25 00:13:50 [INFO] train episode 33725: reward = -63.96, steps = 29 00:13:52 [INFO] train episode 33726: reward = -63.30, steps = 20 00:13:55 [INFO] train episode 33727: reward = -70.26, steps = 21 00:13:57 [INFO] train episode 33728: reward = -92.93, steps = 22 00:14:02 [INFO] train episode 33729: reward = -175.61, steps = 29 00:14:05 [INFO] train episode 33730: reward = -64.83, steps = 23 00:14:07 [INFO] train episode 33731: reward = -61.01, steps = 20 00:14:10 [INFO] train episode 33732: reward = -63.64, steps = 26 00:14:13 [INFO] train episode 33733: reward = -134.57, steps = 28 00:14:15 [INFO] train episode 33734: reward = -71.16, steps = 18 00:14:18 [INFO] train episode 33735: reward = -91.92, steps = 24 00:14:24 [INFO] train episode 33736: reward = -121.45, steps = 41 00:14:26 [INFO] train episode 33737: reward = -120.70, steps = 18 00:14:28 [INFO] train episode 33738: reward = -84.75, steps = 18 00:14:31 [INFO] train episode 33739: reward = -142.90, steps = 25 00:14:33 [INFO] train episode 33740: reward = -98.14, steps = 22 00:14:36 [INFO] train episode 33741: reward = -95.54, steps = 24 00:14:39 [INFO] train episode 33742: reward = -71.52, steps = 27 00:14:42 [INFO] train episode 33743: reward = -79.07, steps = 23 00:14:44 [INFO] train episode 33744: reward = -70.04, steps = 23 00:14:47 [INFO] train episode 33745: reward = -139.37, steps = 24 00:14:51 [INFO] train episode 33746: reward = -111.15, steps = 33 00:14:55 [INFO] train episode 33747: reward = -75.44, steps = 37 00:14:57 [INFO] train episode 33748: reward = -52.99, steps = 25 00:15:00 [INFO] train episode 33749: reward = -76.93, steps = 19 00:15:02 [INFO] train episode 33750: reward = -75.50, steps = 19 00:15:04 [INFO] train episode 33751: reward = -106.54, steps = 20 00:15:06 [INFO] train episode 33752: reward = -61.44, steps = 19 00:15:09 [INFO] train episode 33753: reward = -77.75, steps = 28 00:15:13 [INFO] train episode 33754: reward = -64.91, steps = 37 00:15:17 [INFO] train episode 33755: reward = -110.41, steps = 31 00:15:19 [INFO] train episode 33756: reward = -99.81, steps = 22 00:15:22 [INFO] train episode 33757: reward = -65.55, steps = 21 00:15:25 [INFO] train episode 33758: reward = -62.51, steps = 25 00:15:27 [INFO] train episode 33759: reward = -87.41, steps = 24 00:15:29 [INFO] train episode 33760: reward = -89.86, steps = 19 00:15:32 [INFO] train episode 33761: reward = -88.42, steps = 19 00:15:35 [INFO] train episode 33762: reward = -95.97, steps = 35 00:15:38 [INFO] train episode 33763: reward = -67.11, steps = 20 00:15:40 [INFO] train episode 33764: reward = -117.15, steps = 24 00:15:43 [INFO] train episode 33765: reward = -85.98, steps = 26 00:15:46 [INFO] train episode 33766: reward = -106.17, steps = 25 00:15:49 [INFO] train episode 33767: reward = -82.94, steps = 22 00:15:51 [INFO] train episode 33768: reward = -81.54, steps = 24 00:15:54 [INFO] train episode 33769: reward = -121.58, steps = 29 00:15:57 [INFO] train episode 33770: reward = -96.10, steps = 29 00:16:01 [INFO] train episode 33771: reward = -78.42, steps = 32 00:16:04 [INFO] train episode 33772: reward = -105.52, steps = 28 00:16:06 [INFO] train episode 33773: reward = -86.02, steps = 19 00:16:12 [INFO] train episode 33774: reward = -248.89, steps = 53 00:16:14 [INFO] train episode 33775: reward = -62.57, steps = 18 00:16:17 [INFO] train episode 33776: reward = -87.03, steps = 22 00:16:19 [INFO] train episode 33777: reward = -74.56, steps = 20 00:16:21 [INFO] train episode 33778: reward = -89.47, steps = 20 00:16:25 [INFO] train episode 33779: reward = -62.17, steps = 29 00:16:27 [INFO] train episode 33780: reward = -106.76, steps = 21 00:16:31 [INFO] train episode 33781: reward = -111.14, steps = 36 00:16:34 [INFO] train episode 33782: reward = -99.03, steps = 25 00:16:37 [INFO] train episode 33783: reward = -88.31, steps = 25 00:16:39 [INFO] train episode 33784: reward = -70.93, steps = 21 00:16:42 [INFO] train episode 33785: reward = -145.17, steps = 27 00:16:47 [INFO] train episode 33786: reward = -133.88, steps = 40 00:16:49 [INFO] train episode 33787: reward = -94.88, steps = 23 00:16:53 [INFO] train episode 33788: reward = -96.55, steps = 36 00:16:56 [INFO] train episode 33789: reward = -109.17, steps = 24 00:16:59 [INFO] train episode 33790: reward = -79.76, steps = 28 00:17:05 [INFO] train episode 33791: reward = -62.79, steps = 45 00:17:07 [INFO] train episode 33792: reward = -71.84, steps = 22 00:17:10 [INFO] train episode 33793: reward = -94.64, steps = 27 00:17:15 [INFO] train episode 33794: reward = -128.70, steps = 46 00:17:17 [INFO] train episode 33795: reward = -84.98, steps = 21 00:17:24 [INFO] train episode 33796: reward = -130.17, steps = 54 00:17:27 [INFO] train episode 33797: reward = -77.69, steps = 25 00:17:29 [INFO] train episode 33798: reward = -71.21, steps = 20 00:17:31 [INFO] train episode 33799: reward = -91.64, steps = 20 00:17:33 [INFO] train episode 33800: reward = -100.30, steps = 19 00:17:36 [INFO] train episode 33801: reward = -57.82, steps = 29 00:17:39 [INFO] train episode 33802: reward = -92.66, steps = 19 00:17:42 [INFO] train episode 33803: reward = -82.68, steps = 25 00:17:47 [INFO] train episode 33804: reward = -85.34, steps = 39 00:17:50 [INFO] train episode 33805: reward = -146.13, steps = 29 00:17:53 [INFO] train episode 33806: reward = -93.52, steps = 22 00:17:55 [INFO] train episode 33807: reward = -62.06, steps = 22 00:17:58 [INFO] train episode 33808: reward = -105.73, steps = 24 00:18:01 [INFO] train episode 33809: reward = -132.39, steps = 31 00:18:05 [INFO] train episode 33810: reward = -98.07, steps = 35 00:18:08 [INFO] train episode 33811: reward = -83.49, steps = 20 00:18:11 [INFO] train episode 33812: reward = -124.97, steps = 28 00:18:13 [INFO] train episode 33813: reward = -93.81, steps = 19 00:18:15 [INFO] train episode 33814: reward = -87.00, steps = 22 00:18:18 [INFO] train episode 33815: reward = -91.47, steps = 26 00:18:21 [INFO] train episode 33816: reward = -100.42, steps = 26 00:18:23 [INFO] train episode 33817: reward = -69.07, steps = 20 00:18:28 [INFO] train episode 33818: reward = -124.78, steps = 43 00:18:31 [INFO] train episode 33819: reward = -80.79, steps = 28 00:18:35 [INFO] train episode 33820: reward = -158.49, steps = 39 00:18:38 [INFO] train episode 33821: reward = -81.10, steps = 19 00:18:41 [INFO] train episode 33822: reward = -93.94, steps = 29 00:18:44 [INFO] train episode 33823: reward = -111.20, steps = 33 00:18:48 [INFO] train episode 33824: reward = -86.42, steps = 31 00:18:52 [INFO] train episode 33825: reward = -87.94, steps = 36 00:18:54 [INFO] train episode 33826: reward = -87.48, steps = 21 00:18:56 [INFO] train episode 33827: reward = -107.49, steps = 22 00:18:59 [INFO] train episode 33828: reward = -93.06, steps = 26 00:19:02 [INFO] train episode 33829: reward = -61.34, steps = 19 00:19:03 [INFO] train episode 33830: reward = -80.66, steps = 18 00:19:06 [INFO] train episode 33831: reward = -79.22, steps = 20 00:19:08 [INFO] train episode 33832: reward = -109.92, steps = 22 00:19:11 [INFO] train episode 33833: reward = -76.40, steps = 26 00:19:13 [INFO] train episode 33834: reward = -67.28, steps = 20 00:19:15 [INFO] train episode 33835: reward = -72.72, steps = 19 00:19:19 [INFO] train episode 33836: reward = -61.91, steps = 35 00:19:23 [INFO] train episode 33837: reward = -79.58, steps = 41 00:19:26 [INFO] train episode 33838: reward = -88.55, steps = 23 00:19:29 [INFO] train episode 33839: reward = -168.56, steps = 28 00:19:32 [INFO] train episode 33840: reward = -75.23, steps = 28 00:19:35 [INFO] train episode 33841: reward = -93.65, steps = 24 00:19:37 [INFO] train episode 33842: reward = -116.55, steps = 22 00:19:41 [INFO] train episode 33843: reward = -110.34, steps = 34 00:19:43 [INFO] train episode 33844: reward = -89.34, steps = 22 00:19:47 [INFO] train episode 33845: reward = -129.52, steps = 31 00:19:50 [INFO] train episode 33846: reward = -94.45, steps = 29 00:19:54 [INFO] train episode 33847: reward = -90.77, steps = 34 00:19:57 [INFO] train episode 33848: reward = -117.66, steps = 23 00:19:59 [INFO] train episode 33849: reward = -72.36, steps = 24 00:20:07 [INFO] train episode 33850: reward = -214.19, steps = 65 00:20:09 [INFO] train episode 33851: reward = -71.46, steps = 20 00:20:11 [INFO] train episode 33852: reward = -76.18, steps = 19 00:20:13 [INFO] train episode 33853: reward = -99.06, steps = 20 00:20:16 [INFO] train episode 33854: reward = -95.74, steps = 23 00:20:19 [INFO] train episode 33855: reward = -66.12, steps = 28 00:20:21 [INFO] train episode 33856: reward = -142.23, steps = 17 00:20:23 [INFO] train episode 33857: reward = -93.71, steps = 24 00:20:27 [INFO] train episode 33858: reward = -135.99, steps = 33 00:20:31 [INFO] train episode 33859: reward = -87.15, steps = 33 00:20:33 [INFO] train episode 33860: reward = -84.85, steps = 25 00:20:36 [INFO] train episode 33861: reward = -126.96, steps = 23 00:20:38 [INFO] train episode 33862: reward = -90.40, steps = 21 00:20:41 [INFO] train episode 33863: reward = -63.37, steps = 20 00:20:43 [INFO] train episode 33864: reward = -66.78, steps = 19 00:20:46 [INFO] train episode 33865: reward = -143.77, steps = 24 00:20:48 [INFO] train episode 33866: reward = -87.29, steps = 18 00:20:51 [INFO] train episode 33867: reward = -58.42, steps = 26 00:20:53 [INFO] train episode 33868: reward = -126.23, steps = 20 00:20:57 [INFO] train episode 33869: reward = -98.24, steps = 31 00:21:00 [INFO] train episode 33870: reward = -101.11, steps = 22 00:21:02 [INFO] train episode 33871: reward = -84.14, steps = 20 00:21:04 [INFO] train episode 33872: reward = -102.77, steps = 18 00:21:09 [INFO] train episode 33873: reward = -83.36, steps = 31 00:21:11 [INFO] train episode 33874: reward = -92.21, steps = 23 00:21:14 [INFO] train episode 33875: reward = -98.83, steps = 22 00:21:17 [INFO] train episode 33876: reward = -93.96, steps = 20 00:21:20 [INFO] train episode 33877: reward = -109.20, steps = 26 00:21:24 [INFO] train episode 33878: reward = -66.22, steps = 24 00:21:26 [INFO] train episode 33879: reward = -113.68, steps = 20 00:21:29 [INFO] train episode 33880: reward = -64.87, steps = 22 00:21:34 [INFO] train episode 33881: reward = -123.14, steps = 41 00:21:36 [INFO] train episode 33882: reward = -82.23, steps = 20 00:21:38 [INFO] train episode 33883: reward = -103.58, steps = 22 00:21:42 [INFO] train episode 33884: reward = -68.51, steps = 33 00:21:46 [INFO] train episode 33885: reward = -86.63, steps = 33 00:21:48 [INFO] train episode 33886: reward = -77.98, steps = 20 00:21:50 [INFO] train episode 33887: reward = -64.85, steps = 20 00:21:53 [INFO] train episode 33888: reward = -97.94, steps = 26 00:21:56 [INFO] train episode 33889: reward = -83.87, steps = 27 00:22:00 [INFO] train episode 33890: reward = -115.59, steps = 37 00:22:03 [INFO] train episode 33891: reward = -79.64, steps = 21 00:22:05 [INFO] train episode 33892: reward = -49.34, steps = 20 00:22:08 [INFO] train episode 33893: reward = -82.96, steps = 24 00:22:11 [INFO] train episode 33894: reward = -93.01, steps = 29 00:22:14 [INFO] train episode 33895: reward = -76.58, steps = 21 00:22:16 [INFO] train episode 33896: reward = -66.93, steps = 19 00:22:19 [INFO] train episode 33897: reward = -152.63, steps = 28 00:22:21 [INFO] train episode 33898: reward = -78.51, steps = 21 00:22:23 [INFO] train episode 33899: reward = -91.23, steps = 19 00:22:29 [INFO] train episode 33900: reward = -127.66, steps = 49 00:22:32 [INFO] train episode 33901: reward = -76.34, steps = 29 00:22:38 [INFO] train episode 33902: reward = -80.62, steps = 46 00:22:40 [INFO] train episode 33903: reward = -67.33, steps = 20 00:22:43 [INFO] train episode 33904: reward = -96.98, steps = 20 00:22:46 [INFO] train episode 33905: reward = -71.97, steps = 23 00:22:49 [INFO] train episode 33906: reward = -90.68, steps = 29 00:22:56 [INFO] train episode 33907: reward = -174.38, steps = 46 00:23:00 [INFO] train episode 33908: reward = -54.34, steps = 32 00:23:03 [INFO] train episode 33909: reward = -92.80, steps = 20 00:23:06 [INFO] train episode 33910: reward = -68.72, steps = 26 00:23:09 [INFO] train episode 33911: reward = -90.01, steps = 28 00:23:12 [INFO] train episode 33912: reward = -97.28, steps = 21 00:23:15 [INFO] train episode 33913: reward = -92.29, steps = 34 00:23:18 [INFO] train episode 33914: reward = -85.34, steps = 23 00:23:21 [INFO] train episode 33915: reward = -97.55, steps = 24 00:23:24 [INFO] train episode 33916: reward = -140.87, steps = 29 00:23:27 [INFO] train episode 33917: reward = -48.73, steps = 25 00:23:31 [INFO] train episode 33918: reward = -95.10, steps = 31 00:23:33 [INFO] train episode 33919: reward = -106.80, steps = 18 00:23:35 [INFO] train episode 33920: reward = -64.54, steps = 25 00:23:38 [INFO] train episode 33921: reward = -87.39, steps = 18 00:23:42 [INFO] train episode 33922: reward = -89.21, steps = 37 00:23:44 [INFO] train episode 33923: reward = -98.52, steps = 22 00:23:47 [INFO] train episode 33924: reward = -65.91, steps = 26 00:23:52 [INFO] train episode 33925: reward = -90.83, steps = 41 00:23:55 [INFO] train episode 33926: reward = -75.96, steps = 23 00:23:59 [INFO] train episode 33927: reward = -80.30, steps = 35 00:24:02 [INFO] train episode 33928: reward = -88.16, steps = 21 00:24:04 [INFO] train episode 33929: reward = -83.94, steps = 24 00:24:07 [INFO] train episode 33930: reward = -74.01, steps = 24 00:24:10 [INFO] train episode 33931: reward = -101.54, steps = 25 00:24:12 [INFO] train episode 33932: reward = -125.30, steps = 22 00:24:17 [INFO] train episode 33933: reward = -210.78, steps = 45 00:24:20 [INFO] train episode 33934: reward = -88.33, steps = 20 00:24:23 [INFO] train episode 33935: reward = -56.69, steps = 20 00:24:25 [INFO] train episode 33936: reward = -75.12, steps = 27 00:24:28 [INFO] train episode 33937: reward = -63.39, steps = 21 00:24:31 [INFO] train episode 33938: reward = -85.21, steps = 20 00:24:33 [INFO] train episode 33939: reward = -78.39, steps = 25 00:24:36 [INFO] train episode 33940: reward = -122.28, steps = 28 00:24:40 [INFO] train episode 33941: reward = -108.24, steps = 32 00:24:42 [INFO] train episode 33942: reward = -114.74, steps = 21 00:24:45 [INFO] train episode 33943: reward = -68.89, steps = 27 00:24:47 [INFO] train episode 33944: reward = -91.71, steps = 19 00:24:50 [INFO] train episode 33945: reward = -63.79, steps = 25 00:24:53 [INFO] train episode 33946: reward = -146.25, steps = 36 00:24:57 [INFO] train episode 33947: reward = -114.79, steps = 35 00:24:59 [INFO] train episode 33948: reward = -81.27, steps = 20 00:25:03 [INFO] train episode 33949: reward = -142.78, steps = 40 00:25:05 [INFO] train episode 33950: reward = -113.47, steps = 21 00:25:08 [INFO] train episode 33951: reward = -103.99, steps = 25 00:25:11 [INFO] train episode 33952: reward = -73.19, steps = 24 00:25:13 [INFO] train episode 33953: reward = -73.04, steps = 25 00:25:16 [INFO] train episode 33954: reward = -71.36, steps = 31 00:25:19 [INFO] train episode 33955: reward = -92.82, steps = 20 00:25:22 [INFO] train episode 33956: reward = -102.14, steps = 30 00:25:24 [INFO] train episode 33957: reward = -115.44, steps = 22 00:25:26 [INFO] train episode 33958: reward = -131.72, steps = 26 00:25:28 [INFO] train episode 33959: reward = -90.72, steps = 18 00:25:30 [INFO] train episode 33960: reward = -124.24, steps = 22 00:25:33 [INFO] train episode 33961: reward = -88.83, steps = 27 00:25:34 [INFO] train episode 33962: reward = -85.65, steps = 20 00:25:37 [INFO] train episode 33963: reward = -104.08, steps = 19 00:25:39 [INFO] train episode 33964: reward = -115.05, steps = 21 00:25:42 [INFO] train episode 33965: reward = -88.23, steps = 35 00:25:43 [INFO] train episode 33966: reward = -94.85, steps = 20 00:25:45 [INFO] train episode 33967: reward = -105.45, steps = 21 00:25:47 [INFO] train episode 33968: reward = -139.89, steps = 21 00:25:49 [INFO] train episode 33969: reward = -74.01, steps = 22 00:25:53 [INFO] train episode 33970: reward = -146.02, steps = 29 00:25:55 [INFO] train episode 33971: reward = -96.65, steps = 20 00:25:57 [INFO] train episode 33972: reward = -60.04, steps = 22 00:25:59 [INFO] train episode 33973: reward = -123.37, steps = 26 00:26:01 [INFO] train episode 33974: reward = -62.94, steps = 21 00:26:04 [INFO] train episode 33975: reward = -105.39, steps = 32 00:26:07 [INFO] train episode 33976: reward = -62.87, steps = 26 00:26:10 [INFO] train episode 33977: reward = -110.54, steps = 31 00:26:12 [INFO] train episode 33978: reward = -77.76, steps = 26 00:26:14 [INFO] train episode 33979: reward = -190.53, steps = 23 00:26:18 [INFO] train episode 33980: reward = -136.86, steps = 39 00:26:20 [INFO] train episode 33981: reward = -113.90, steps = 25 00:26:22 [INFO] train episode 33982: reward = -102.33, steps = 26 00:26:25 [INFO] train episode 33983: reward = -107.30, steps = 37 00:26:28 [INFO] train episode 33984: reward = -76.68, steps = 19 00:26:29 [INFO] train episode 33985: reward = -80.53, steps = 14 00:26:32 [INFO] train episode 33986: reward = -151.53, steps = 34 00:26:34 [INFO] train episode 33987: reward = -116.51, steps = 21 00:26:36 [INFO] train episode 33988: reward = -153.55, steps = 24 00:26:38 [INFO] train episode 33989: reward = -73.43, steps = 25 00:26:41 [INFO] train episode 33990: reward = -86.20, steps = 28 00:26:43 [INFO] train episode 33991: reward = -66.49, steps = 20 00:26:46 [INFO] train episode 33992: reward = -54.99, steps = 30 00:26:49 [INFO] train episode 33993: reward = -101.38, steps = 35 00:26:51 [INFO] train episode 33994: reward = -52.03, steps = 27 00:26:53 [INFO] train episode 33995: reward = -78.76, steps = 20 00:26:56 [INFO] train episode 33996: reward = -100.47, steps = 28 00:26:58 [INFO] train episode 33997: reward = -106.25, steps = 22 00:27:01 [INFO] train episode 33998: reward = -88.73, steps = 33 00:27:03 [INFO] train episode 33999: reward = -81.22, steps = 26 00:27:05 [INFO] train episode 34000: reward = -94.35, steps = 26 00:27:08 [INFO] train episode 34001: reward = -145.67, steps = 28 00:27:10 [INFO] train episode 34002: reward = -52.10, steps = 19 00:27:12 [INFO] train episode 34003: reward = -106.94, steps = 25 00:27:14 [INFO] train episode 34004: reward = -111.71, steps = 26 00:27:17 [INFO] train episode 34005: reward = -72.13, steps = 27 00:27:20 [INFO] train episode 34006: reward = -118.95, steps = 30 00:27:21 [INFO] train episode 34007: reward = -87.22, steps = 19 00:27:24 [INFO] train episode 34008: reward = -78.30, steps = 23 00:27:26 [INFO] train episode 34009: reward = -94.57, steps = 26 00:27:30 [INFO] train episode 34010: reward = -146.37, steps = 42 00:27:32 [INFO] train episode 34011: reward = -47.80, steps = 30 00:27:35 [INFO] train episode 34012: reward = -130.40, steps = 24 00:27:37 [INFO] train episode 34013: reward = -120.18, steps = 26 00:27:40 [INFO] train episode 34014: reward = -67.21, steps = 30 00:27:42 [INFO] train episode 34015: reward = -112.59, steps = 22 00:27:46 [INFO] train episode 34016: reward = -133.81, steps = 45 00:27:49 [INFO] train episode 34017: reward = -103.65, steps = 38 00:27:51 [INFO] train episode 34018: reward = -136.04, steps = 21 00:27:53 [INFO] train episode 34019: reward = -99.27, steps = 25 00:27:56 [INFO] train episode 34020: reward = -85.97, steps = 25 00:27:59 [INFO] train episode 34021: reward = -122.89, steps = 34 00:28:01 [INFO] train episode 34022: reward = -138.18, steps = 31 00:28:04 [INFO] train episode 34023: reward = -101.66, steps = 30 00:28:07 [INFO] train episode 34024: reward = -116.81, steps = 31 00:28:10 [INFO] train episode 34025: reward = -111.36, steps = 24 00:28:12 [INFO] train episode 34026: reward = -80.36, steps = 19 00:28:14 [INFO] train episode 34027: reward = -97.01, steps = 19 00:28:16 [INFO] train episode 34028: reward = -100.90, steps = 22 00:28:18 [INFO] train episode 34029: reward = -65.41, steps = 25 00:28:20 [INFO] train episode 34030: reward = -77.73, steps = 23 00:28:22 [INFO] train episode 34031: reward = -90.91, steps = 20 00:28:24 [INFO] train episode 34032: reward = -69.84, steps = 23 00:28:26 [INFO] train episode 34033: reward = -88.56, steps = 20 00:28:28 [INFO] train episode 34034: reward = -105.82, steps = 19 00:28:29 [INFO] train episode 34035: reward = -59.59, steps = 17 00:28:33 [INFO] train episode 34036: reward = -112.68, steps = 46 00:28:37 [INFO] train episode 34037: reward = -126.01, steps = 36 00:28:41 [INFO] train episode 34038: reward = -143.66, steps = 40 00:28:42 [INFO] train episode 34039: reward = -58.34, steps = 20 00:28:44 [INFO] train episode 34040: reward = -74.30, steps = 21 00:28:46 [INFO] train episode 34041: reward = -89.09, steps = 22 00:28:48 [INFO] train episode 34042: reward = -98.73, steps = 23 00:28:52 [INFO] train episode 34043: reward = -156.55, steps = 36 00:28:54 [INFO] train episode 34044: reward = -65.99, steps = 25 00:28:57 [INFO] train episode 34045: reward = -92.26, steps = 31 00:28:59 [INFO] train episode 34046: reward = -123.73, steps = 23 00:29:01 [INFO] train episode 34047: reward = -140.68, steps = 25 00:29:04 [INFO] train episode 34048: reward = -68.49, steps = 22 00:29:08 [INFO] train episode 34049: reward = -86.07, steps = 44 00:29:10 [INFO] train episode 34050: reward = -61.75, steps = 25 00:29:12 [INFO] train episode 34051: reward = -98.50, steps = 22 00:29:15 [INFO] train episode 34052: reward = -101.75, steps = 32 00:29:17 [INFO] train episode 34053: reward = -70.40, steps = 18 00:29:19 [INFO] train episode 34054: reward = -111.32, steps = 29 00:29:22 [INFO] train episode 34055: reward = -88.24, steps = 29 00:29:26 [INFO] train episode 34056: reward = -196.79, steps = 49 00:29:30 [INFO] train episode 34057: reward = -160.28, steps = 42 00:29:32 [INFO] train episode 34058: reward = -120.89, steps = 22 00:29:34 [INFO] train episode 34059: reward = -77.33, steps = 23 00:29:37 [INFO] train episode 34060: reward = -64.65, steps = 26 00:29:39 [INFO] train episode 34061: reward = -97.59, steps = 21 00:29:41 [INFO] train episode 34062: reward = -125.74, steps = 21 00:29:43 [INFO] train episode 34063: reward = -73.77, steps = 27 00:29:47 [INFO] train episode 34064: reward = -81.12, steps = 36 00:29:50 [INFO] train episode 34065: reward = -90.65, steps = 23 00:29:54 [INFO] train episode 34066: reward = -182.05, steps = 51 00:29:59 [INFO] train episode 34067: reward = -122.84, steps = 54 00:30:02 [INFO] train episode 34068: reward = -56.20, steps = 21 00:30:05 [INFO] train episode 34069: reward = -85.25, steps = 27 00:30:09 [INFO] train episode 34070: reward = -62.65, steps = 29 00:30:12 [INFO] train episode 34071: reward = -79.59, steps = 38 00:30:15 [INFO] train episode 34072: reward = -134.55, steps = 31 00:30:18 [INFO] train episode 34073: reward = -101.60, steps = 21 00:30:21 [INFO] train episode 34074: reward = -154.33, steps = 25 00:30:24 [INFO] train episode 34075: reward = -93.10, steps = 33 00:30:26 [INFO] train episode 34076: reward = -67.11, steps = 19 00:30:29 [INFO] train episode 34077: reward = -121.83, steps = 23 00:30:32 [INFO] train episode 34078: reward = -69.43, steps = 24 00:30:34 [INFO] train episode 34079: reward = -99.89, steps = 21 00:30:38 [INFO] train episode 34080: reward = -123.84, steps = 47 00:30:41 [INFO] train episode 34081: reward = -63.06, steps = 28 00:30:43 [INFO] train episode 34082: reward = -81.41, steps = 24 00:30:47 [INFO] train episode 34083: reward = -86.67, steps = 35 00:30:53 [INFO] train episode 34084: reward = -132.90, steps = 68 00:30:55 [INFO] train episode 34085: reward = -91.85, steps = 19 00:30:57 [INFO] train episode 34086: reward = -79.06, steps = 25 00:31:00 [INFO] train episode 34087: reward = -97.25, steps = 27 00:31:04 [INFO] train episode 34088: reward = -121.79, steps = 35 00:31:06 [INFO] train episode 34089: reward = -91.36, steps = 29 00:31:10 [INFO] train episode 34090: reward = -139.33, steps = 29 00:31:12 [INFO] train episode 34091: reward = -111.05, steps = 21 00:31:14 [INFO] train episode 34092: reward = -54.58, steps = 21 00:31:16 [INFO] train episode 34093: reward = -66.04, steps = 20 00:31:19 [INFO] train episode 34094: reward = -145.17, steps = 22 00:31:22 [INFO] train episode 34095: reward = -79.31, steps = 27 00:31:25 [INFO] train episode 34096: reward = -68.44, steps = 23 00:31:27 [INFO] train episode 34097: reward = -54.97, steps = 25 00:31:29 [INFO] train episode 34098: reward = -115.12, steps = 20 00:31:31 [INFO] train episode 34099: reward = -51.84, steps = 25 00:31:33 [INFO] train episode 34100: reward = -80.39, steps = 23 00:31:36 [INFO] train episode 34101: reward = -132.59, steps = 25 00:31:38 [INFO] train episode 34102: reward = -89.86, steps = 27 00:31:42 [INFO] train episode 34103: reward = -77.44, steps = 37 00:31:44 [INFO] train episode 34104: reward = -117.69, steps = 32 00:31:49 [INFO] train episode 34105: reward = -175.34, steps = 49 00:31:51 [INFO] train episode 34106: reward = -67.04, steps = 26 00:31:54 [INFO] train episode 34107: reward = -120.72, steps = 28 00:31:57 [INFO] train episode 34108: reward = -65.64, steps = 28 00:31:59 [INFO] train episode 34109: reward = -74.94, steps = 23 00:32:02 [INFO] train episode 34110: reward = -75.48, steps = 33 00:32:05 [INFO] train episode 34111: reward = -67.60, steps = 28 00:32:07 [INFO] train episode 34112: reward = -62.19, steps = 21 00:32:08 [INFO] train episode 34113: reward = -67.54, steps = 19 00:32:10 [INFO] train episode 34114: reward = -52.89, steps = 21 00:32:14 [INFO] train episode 34115: reward = -119.67, steps = 42 00:32:16 [INFO] train episode 34116: reward = -82.21, steps = 21 00:32:18 [INFO] train episode 34117: reward = -58.40, steps = 19 00:32:20 [INFO] train episode 34118: reward = -44.86, steps = 20 00:32:22 [INFO] train episode 34119: reward = -130.58, steps = 28 00:32:25 [INFO] train episode 34120: reward = -141.02, steps = 28 00:32:27 [INFO] train episode 34121: reward = -116.66, steps = 33 00:32:30 [INFO] train episode 34122: reward = -103.86, steps = 29 00:32:33 [INFO] train episode 34123: reward = -90.86, steps = 25 00:32:35 [INFO] train episode 34124: reward = -88.32, steps = 28 00:32:37 [INFO] train episode 34125: reward = -102.60, steps = 22 00:32:39 [INFO] train episode 34126: reward = -73.57, steps = 22 00:32:42 [INFO] train episode 34127: reward = -48.66, steps = 23 00:32:43 [INFO] train episode 34128: reward = -77.11, steps = 16 00:32:47 [INFO] train episode 34129: reward = -85.61, steps = 35 00:32:49 [INFO] train episode 34130: reward = -98.54, steps = 31 00:32:52 [INFO] train episode 34131: reward = -98.76, steps = 25 00:32:53 [INFO] train episode 34132: reward = -99.28, steps = 18 00:32:56 [INFO] train episode 34133: reward = -49.83, steps = 30 00:32:58 [INFO] train episode 34134: reward = -134.80, steps = 21 00:33:01 [INFO] train episode 34135: reward = -181.57, steps = 30 00:33:03 [INFO] train episode 34136: reward = -71.15, steps = 21 00:33:05 [INFO] train episode 34137: reward = -70.62, steps = 20 00:33:07 [INFO] train episode 34138: reward = -76.38, steps = 20 00:33:09 [INFO] train episode 34139: reward = -75.45, steps = 27 00:33:11 [INFO] train episode 34140: reward = -43.31, steps = 27 00:33:14 [INFO] train episode 34141: reward = -151.33, steps = 28 00:33:18 [INFO] train episode 34142: reward = -108.89, steps = 49 00:33:20 [INFO] train episode 34143: reward = -95.41, steps = 22 00:33:23 [INFO] train episode 34144: reward = -118.45, steps = 33 00:33:25 [INFO] train episode 34145: reward = -63.15, steps = 22 00:33:28 [INFO] train episode 34146: reward = -114.64, steps = 27 00:33:30 [INFO] train episode 34147: reward = -72.27, steps = 21 00:33:32 [INFO] train episode 34148: reward = -95.61, steps = 31 00:33:36 [INFO] train episode 34149: reward = -143.16, steps = 36 00:33:39 [INFO] train episode 34150: reward = -78.99, steps = 38 00:33:41 [INFO] train episode 34151: reward = -94.53, steps = 19 00:33:43 [INFO] train episode 34152: reward = -80.64, steps = 19 00:33:45 [INFO] train episode 34153: reward = -83.39, steps = 19 00:33:47 [INFO] train episode 34154: reward = -82.96, steps = 21 00:33:50 [INFO] train episode 34155: reward = -203.48, steps = 36 00:33:53 [INFO] train episode 34156: reward = -73.66, steps = 24 00:33:55 [INFO] train episode 34157: reward = -67.30, steps = 20 00:33:57 [INFO] train episode 34158: reward = -74.66, steps = 24 00:33:59 [INFO] train episode 34159: reward = -77.04, steps = 26 00:34:01 [INFO] train episode 34160: reward = -95.98, steps = 20 00:34:04 [INFO] train episode 34161: reward = -59.46, steps = 39 00:34:06 [INFO] train episode 34162: reward = -77.61, steps = 22 00:34:11 [INFO] train episode 34163: reward = -70.30, steps = 44 00:34:13 [INFO] train episode 34164: reward = -116.89, steps = 31 00:34:16 [INFO] train episode 34165: reward = -77.52, steps = 23 00:34:18 [INFO] train episode 34166: reward = -85.16, steps = 24 00:34:22 [INFO] train episode 34167: reward = -76.21, steps = 39 00:34:24 [INFO] train episode 34168: reward = -110.39, steps = 24 00:34:27 [INFO] train episode 34169: reward = -58.94, steps = 24 00:34:30 [INFO] train episode 34170: reward = -78.98, steps = 42 00:34:32 [INFO] train episode 34171: reward = -78.76, steps = 21 00:34:36 [INFO] train episode 34172: reward = -98.80, steps = 36 00:34:38 [INFO] train episode 34173: reward = -93.70, steps = 23 00:34:40 [INFO] train episode 34174: reward = -84.67, steps = 27 00:34:42 [INFO] train episode 34175: reward = -57.44, steps = 21 00:34:44 [INFO] train episode 34176: reward = -88.32, steps = 19 00:34:47 [INFO] train episode 34177: reward = -78.96, steps = 32 00:34:49 [INFO] train episode 34178: reward = -111.00, steps = 18 00:34:51 [INFO] train episode 34179: reward = -87.42, steps = 24 00:34:54 [INFO] train episode 34180: reward = -68.86, steps = 27 00:34:56 [INFO] train episode 34181: reward = -56.10, steps = 20 00:34:59 [INFO] train episode 34182: reward = -82.45, steps = 36 00:35:01 [INFO] train episode 34183: reward = -120.54, steps = 25 00:35:04 [INFO] train episode 34184: reward = -75.99, steps = 27 00:35:07 [INFO] train episode 34185: reward = -63.50, steps = 31 00:35:09 [INFO] train episode 34186: reward = -89.39, steps = 25 00:35:11 [INFO] train episode 34187: reward = -56.06, steps = 19 00:35:13 [INFO] train episode 34188: reward = -52.35, steps = 26 00:35:15 [INFO] train episode 34189: reward = -56.92, steps = 26 00:35:19 [INFO] train episode 34190: reward = -124.57, steps = 39 00:35:23 [INFO] train episode 34191: reward = -72.85, steps = 36 00:35:24 [INFO] train episode 34192: reward = -73.41, steps = 19 00:35:27 [INFO] train episode 34193: reward = -96.14, steps = 30 00:35:29 [INFO] train episode 34194: reward = -118.91, steps = 23 00:35:31 [INFO] train episode 34195: reward = -104.35, steps = 21 00:35:33 [INFO] train episode 34196: reward = -135.31, steps = 21 00:35:37 [INFO] train episode 34197: reward = -84.55, steps = 43 00:35:39 [INFO] train episode 34198: reward = -94.69, steps = 22 00:35:42 [INFO] train episode 34199: reward = -117.22, steps = 30 00:35:45 [INFO] train episode 34200: reward = -92.28, steps = 26 00:35:47 [INFO] train episode 34201: reward = -66.19, steps = 24 00:35:49 [INFO] train episode 34202: reward = -105.14, steps = 31 00:35:52 [INFO] train episode 34203: reward = -53.65, steps = 28 00:35:55 [INFO] train episode 34204: reward = -59.51, steps = 27 00:35:58 [INFO] train episode 34205: reward = -99.98, steps = 32 00:36:00 [INFO] train episode 34206: reward = -98.29, steps = 24 00:36:02 [INFO] train episode 34207: reward = -133.67, steps = 20 00:36:04 [INFO] train episode 34208: reward = -88.49, steps = 25 00:36:06 [INFO] train episode 34209: reward = -91.32, steps = 24 00:36:09 [INFO] train episode 34210: reward = -58.77, steps = 32 00:36:11 [INFO] train episode 34211: reward = -80.60, steps = 20 00:36:14 [INFO] train episode 34212: reward = -92.67, steps = 34 00:36:17 [INFO] train episode 34213: reward = -87.25, steps = 35 00:36:19 [INFO] train episode 34214: reward = -88.95, steps = 20 00:36:21 [INFO] train episode 34215: reward = -96.64, steps = 23 00:36:23 [INFO] train episode 34216: reward = -152.13, steps = 19 00:36:26 [INFO] train episode 34217: reward = -90.30, steps = 31 00:36:28 [INFO] train episode 34218: reward = -82.91, steps = 19 00:36:29 [INFO] train episode 34219: reward = -64.23, steps = 20 00:36:31 [INFO] train episode 34220: reward = -65.18, steps = 22 00:36:34 [INFO] train episode 34221: reward = -47.16, steps = 26 00:36:37 [INFO] train episode 34222: reward = -77.82, steps = 30 00:36:38 [INFO] train episode 34223: reward = -131.60, steps = 18 00:36:40 [INFO] train episode 34224: reward = -63.74, steps = 19 00:36:43 [INFO] train episode 34225: reward = -93.92, steps = 35 00:36:45 [INFO] train episode 34226: reward = -94.37, steps = 19 00:36:47 [INFO] train episode 34227: reward = -103.74, steps = 25 00:36:49 [INFO] train episode 34228: reward = -96.52, steps = 20 00:36:51 [INFO] train episode 34229: reward = -86.95, steps = 20 00:36:54 [INFO] train episode 34230: reward = -71.37, steps = 28 00:36:56 [INFO] train episode 34231: reward = -87.05, steps = 20 00:36:58 [INFO] train episode 34232: reward = -75.45, steps = 27 00:37:01 [INFO] train episode 34233: reward = -108.23, steps = 25 00:37:03 [INFO] train episode 34234: reward = -61.25, steps = 21 00:37:05 [INFO] train episode 34235: reward = -70.30, steps = 31 00:37:07 [INFO] train episode 34236: reward = -100.72, steps = 18 00:37:09 [INFO] train episode 34237: reward = -52.54, steps = 20 00:37:11 [INFO] train episode 34238: reward = -89.93, steps = 22 00:37:13 [INFO] train episode 34239: reward = -59.05, steps = 19 00:37:16 [INFO] train episode 34240: reward = -103.61, steps = 35 00:37:18 [INFO] train episode 34241: reward = -143.58, steps = 24 00:37:20 [INFO] train episode 34242: reward = -117.59, steps = 18 00:37:23 [INFO] train episode 34243: reward = -41.52, steps = 23 00:37:25 [INFO] train episode 34244: reward = -112.49, steps = 21 00:37:27 [INFO] train episode 34245: reward = -69.74, steps = 21 00:37:29 [INFO] train episode 34246: reward = -84.72, steps = 29 00:37:31 [INFO] train episode 34247: reward = -80.97, steps = 23 00:37:33 [INFO] train episode 34248: reward = -103.16, steps = 19 00:37:35 [INFO] train episode 34249: reward = -83.87, steps = 26 00:37:37 [INFO] train episode 34250: reward = -118.63, steps = 20 00:37:39 [INFO] train episode 34251: reward = -74.04, steps = 23 00:37:41 [INFO] train episode 34252: reward = -90.18, steps = 22 00:37:45 [INFO] train episode 34253: reward = -84.59, steps = 38 00:37:48 [INFO] train episode 34254: reward = -125.70, steps = 39 00:37:52 [INFO] train episode 34255: reward = -153.24, steps = 37 00:37:55 [INFO] train episode 34256: reward = -68.39, steps = 35 00:37:58 [INFO] train episode 34257: reward = -111.76, steps = 36 00:38:00 [INFO] train episode 34258: reward = -74.16, steps = 21 00:38:03 [INFO] train episode 34259: reward = -47.60, steps = 34 00:38:05 [INFO] train episode 34260: reward = -112.49, steps = 19 00:38:07 [INFO] train episode 34261: reward = -80.99, steps = 25 00:38:11 [INFO] train episode 34262: reward = -118.39, steps = 40 00:38:13 [INFO] train episode 34263: reward = -102.27, steps = 28 00:38:15 [INFO] train episode 34264: reward = -85.25, steps = 21 00:38:17 [INFO] train episode 34265: reward = -90.86, steps = 18 00:38:19 [INFO] train episode 34266: reward = -125.93, steps = 23 00:38:22 [INFO] train episode 34267: reward = -87.51, steps = 26 00:38:25 [INFO] train episode 34268: reward = -143.29, steps = 42 00:38:27 [INFO] train episode 34269: reward = -80.79, steps = 21 00:38:29 [INFO] train episode 34270: reward = -96.84, steps = 19 00:38:31 [INFO] train episode 34271: reward = -90.88, steps = 24 00:38:33 [INFO] train episode 34272: reward = -112.00, steps = 20 00:38:36 [INFO] train episode 34273: reward = -111.13, steps = 25 00:38:38 [INFO] train episode 34274: reward = -102.13, steps = 25 00:38:40 [INFO] train episode 34275: reward = -160.58, steps = 24 00:38:43 [INFO] train episode 34276: reward = -99.57, steps = 30 00:38:46 [INFO] train episode 34277: reward = -99.94, steps = 25 00:38:48 [INFO] train episode 34278: reward = -55.99, steps = 21 00:38:50 [INFO] train episode 34279: reward = -79.87, steps = 21 00:38:52 [INFO] train episode 34280: reward = -87.29, steps = 20 00:38:54 [INFO] train episode 34281: reward = -88.65, steps = 21 00:38:57 [INFO] train episode 34282: reward = -98.82, steps = 28 00:38:59 [INFO] train episode 34283: reward = -93.61, steps = 23 00:39:02 [INFO] train episode 34284: reward = -92.88, steps = 39 00:39:05 [INFO] train episode 34285: reward = -102.99, steps = 34 00:39:07 [INFO] train episode 34286: reward = -74.65, steps = 24 00:39:13 [INFO] train episode 34287: reward = -142.10, steps = 59 00:39:15 [INFO] train episode 34288: reward = -111.72, steps = 24 00:39:18 [INFO] train episode 34289: reward = -65.93, steps = 35 00:39:20 [INFO] train episode 34290: reward = -119.33, steps = 21 00:39:23 [INFO] train episode 34291: reward = -76.28, steps = 32 00:39:25 [INFO] train episode 34292: reward = -121.27, steps = 20 00:39:27 [INFO] train episode 34293: reward = -132.20, steps = 29 00:39:30 [INFO] train episode 34294: reward = -83.03, steps = 28 00:39:32 [INFO] train episode 34295: reward = -181.76, steps = 25 00:39:35 [INFO] train episode 34296: reward = -106.15, steps = 35 00:39:38 [INFO] train episode 34297: reward = -61.49, steps = 31 00:39:41 [INFO] train episode 34298: reward = -183.98, steps = 31 00:39:43 [INFO] train episode 34299: reward = -101.35, steps = 20 00:39:45 [INFO] train episode 34300: reward = -54.33, steps = 21 00:39:47 [INFO] train episode 34301: reward = -124.31, steps = 26 00:39:51 [INFO] train episode 34302: reward = -117.52, steps = 39 00:39:53 [INFO] train episode 34303: reward = -68.59, steps = 26 00:39:55 [INFO] train episode 34304: reward = -102.10, steps = 20 00:39:59 [INFO] train episode 34305: reward = -58.26, steps = 34 00:40:01 [INFO] train episode 34306: reward = -122.89, steps = 19 00:40:05 [INFO] train episode 34307: reward = -97.46, steps = 37 00:40:08 [INFO] train episode 34308: reward = -71.25, steps = 35 00:40:11 [INFO] train episode 34309: reward = -82.80, steps = 27 00:40:16 [INFO] train episode 34310: reward = -181.88, steps = 49 00:40:19 [INFO] train episode 34311: reward = -82.05, steps = 32 00:40:22 [INFO] train episode 34312: reward = -53.36, steps = 20 00:40:26 [INFO] train episode 34313: reward = -78.21, steps = 35 00:40:31 [INFO] train episode 34314: reward = -108.54, steps = 41 00:40:33 [INFO] train episode 34315: reward = -77.93, steps = 24 00:40:35 [INFO] train episode 34316: reward = -73.21, steps = 20 00:40:38 [INFO] train episode 34317: reward = -98.32, steps = 41 00:40:41 [INFO] train episode 34318: reward = -61.49, steps = 25 00:40:43 [INFO] train episode 34319: reward = -119.66, steps = 22 00:40:45 [INFO] train episode 34320: reward = -63.86, steps = 27 00:40:48 [INFO] train episode 34321: reward = -106.17, steps = 33 00:40:50 [INFO] train episode 34322: reward = -101.22, steps = 22 00:40:52 [INFO] train episode 34323: reward = -76.48, steps = 23 00:40:54 [INFO] train episode 34324: reward = -86.53, steps = 25 00:40:59 [INFO] train episode 34325: reward = -70.37, steps = 44 00:41:01 [INFO] train episode 34326: reward = -100.29, steps = 24 00:41:03 [INFO] train episode 34327: reward = -115.13, steps = 27 00:41:06 [INFO] train episode 34328: reward = -131.68, steps = 25 00:41:07 [INFO] train episode 34329: reward = -53.60, steps = 22 00:41:09 [INFO] train episode 34330: reward = -68.90, steps = 23 00:41:11 [INFO] train episode 34331: reward = -72.47, steps = 20 00:41:16 [INFO] train episode 34332: reward = -158.21, steps = 50 00:41:19 [INFO] train episode 34333: reward = -115.13, steps = 39 00:41:21 [INFO] train episode 34334: reward = -64.69, steps = 24 00:41:24 [INFO] train episode 34335: reward = -46.69, steps = 29 00:41:26 [INFO] train episode 34336: reward = -92.60, steps = 24 00:41:28 [INFO] train episode 34337: reward = -77.15, steps = 25 00:41:31 [INFO] train episode 34338: reward = -96.65, steps = 21 00:41:33 [INFO] train episode 34339: reward = -62.88, steps = 32 00:41:35 [INFO] train episode 34340: reward = -72.98, steps = 18 00:41:38 [INFO] train episode 34341: reward = -78.42, steps = 34 00:41:40 [INFO] train episode 34342: reward = -95.37, steps = 22 00:41:44 [INFO] train episode 34343: reward = -129.88, steps = 49 00:41:47 [INFO] train episode 34344: reward = -64.60, steps = 33 00:41:49 [INFO] train episode 34345: reward = -127.03, steps = 23 00:41:51 [INFO] train episode 34346: reward = -98.75, steps = 21 00:41:54 [INFO] train episode 34347: reward = -81.70, steps = 34 00:41:56 [INFO] train episode 34348: reward = -65.50, steps = 23 00:41:59 [INFO] train episode 34349: reward = -119.74, steps = 29 00:42:01 [INFO] train episode 34350: reward = -77.69, steps = 23 00:42:05 [INFO] train episode 34351: reward = -140.24, steps = 38 00:42:06 [INFO] train episode 34352: reward = -94.03, steps = 20 00:42:11 [INFO] train episode 34353: reward = -145.36, steps = 48 00:42:14 [INFO] train episode 34354: reward = -130.41, steps = 37 00:42:15 [INFO] train episode 34355: reward = -82.52, steps = 19 00:42:18 [INFO] train episode 34356: reward = -60.65, steps = 29 00:42:23 [INFO] train episode 34357: reward = -173.97, steps = 48 00:42:25 [INFO] train episode 34358: reward = -55.50, steps = 22 00:42:27 [INFO] train episode 34359: reward = -108.68, steps = 34 00:42:30 [INFO] train episode 34360: reward = -137.38, steps = 28 00:42:32 [INFO] train episode 34361: reward = -93.64, steps = 21 00:42:36 [INFO] train episode 34362: reward = -102.63, steps = 40 00:42:38 [INFO] train episode 34363: reward = -74.86, steps = 23 00:42:40 [INFO] train episode 34364: reward = -76.57, steps = 22 00:42:42 [INFO] train episode 34365: reward = -117.48, steps = 20 00:42:45 [INFO] train episode 34366: reward = -70.93, steps = 33 00:42:47 [INFO] train episode 34367: reward = -77.04, steps = 22 00:42:50 [INFO] train episode 34368: reward = -94.17, steps = 42 00:42:53 [INFO] train episode 34369: reward = -68.09, steps = 22 00:42:56 [INFO] train episode 34370: reward = -72.41, steps = 37 00:42:58 [INFO] train episode 34371: reward = -164.19, steps = 24 00:43:00 [INFO] train episode 34372: reward = -130.63, steps = 20 00:43:01 [INFO] train episode 34373: reward = -109.73, steps = 19 00:43:03 [INFO] train episode 34374: reward = -106.22, steps = 20 00:43:06 [INFO] train episode 34375: reward = -74.27, steps = 28 00:43:08 [INFO] train episode 34376: reward = -105.04, steps = 29 00:43:10 [INFO] train episode 34377: reward = -145.35, steps = 21 00:43:14 [INFO] train episode 34378: reward = -69.53, steps = 38 00:43:15 [INFO] train episode 34379: reward = -108.03, steps = 15 00:43:17 [INFO] train episode 34380: reward = -106.86, steps = 26 00:43:19 [INFO] train episode 34381: reward = -64.28, steps = 22 00:43:22 [INFO] train episode 34382: reward = -56.98, steps = 26 00:43:25 [INFO] train episode 34383: reward = -70.95, steps = 29 00:43:27 [INFO] train episode 34384: reward = -75.04, steps = 19 00:43:30 [INFO] train episode 34385: reward = -151.03, steps = 35 00:43:32 [INFO] train episode 34386: reward = -76.31, steps = 24 00:43:35 [INFO] train episode 34387: reward = -73.09, steps = 37 00:43:37 [INFO] train episode 34388: reward = -88.28, steps = 22 00:43:39 [INFO] train episode 34389: reward = -99.28, steps = 24 00:43:42 [INFO] train episode 34390: reward = -80.97, steps = 25 00:43:43 [INFO] train episode 34391: reward = -56.28, steps = 21 00:43:48 [INFO] train episode 34392: reward = -132.70, steps = 50 00:43:50 [INFO] train episode 34393: reward = -80.70, steps = 21 00:43:53 [INFO] train episode 34394: reward = -70.60, steps = 38 00:43:55 [INFO] train episode 34395: reward = -52.19, steps = 20 00:43:57 [INFO] train episode 34396: reward = -99.51, steps = 27 00:44:01 [INFO] train episode 34397: reward = -112.51, steps = 38 00:44:03 [INFO] train episode 34398: reward = -111.45, steps = 27 00:44:07 [INFO] train episode 34399: reward = -96.00, steps = 42 00:44:09 [INFO] train episode 34400: reward = -40.91, steps = 31 00:44:11 [INFO] train episode 34401: reward = -60.03, steps = 21 00:44:14 [INFO] train episode 34402: reward = -98.96, steps = 22 00:44:16 [INFO] train episode 34403: reward = -192.93, steps = 32 00:44:19 [INFO] train episode 34404: reward = -87.71, steps = 25 00:44:21 [INFO] train episode 34405: reward = -90.39, steps = 24 00:44:24 [INFO] train episode 34406: reward = -125.25, steps = 30 00:44:26 [INFO] train episode 34407: reward = -72.61, steps = 30 00:44:31 [INFO] train episode 34408: reward = -128.77, steps = 48 00:44:33 [INFO] train episode 34409: reward = -86.78, steps = 18 00:44:36 [INFO] train episode 34410: reward = -90.30, steps = 28 00:44:38 [INFO] train episode 34411: reward = -81.32, steps = 22 00:44:40 [INFO] train episode 34412: reward = -110.15, steps = 18 00:44:42 [INFO] train episode 34413: reward = -117.93, steps = 19 00:44:44 [INFO] train episode 34414: reward = -68.75, steps = 20 00:44:46 [INFO] train episode 34415: reward = -86.37, steps = 25 00:44:50 [INFO] train episode 34416: reward = -50.08, steps = 27 00:44:52 [INFO] train episode 34417: reward = -57.66, steps = 22 00:44:54 [INFO] train episode 34418: reward = -127.90, steps = 25 00:44:56 [INFO] train episode 34419: reward = -64.88, steps = 23 00:44:59 [INFO] train episode 34420: reward = -71.33, steps = 36 00:45:02 [INFO] train episode 34421: reward = -67.57, steps = 22 00:45:03 [INFO] train episode 34422: reward = -68.07, steps = 20 00:45:06 [INFO] train episode 34423: reward = -70.88, steps = 27 00:45:08 [INFO] train episode 34424: reward = -54.74, steps = 21 00:45:11 [INFO] train episode 34425: reward = -75.89, steps = 26 00:45:13 [INFO] train episode 34426: reward = -66.17, steps = 23 00:45:15 [INFO] train episode 34427: reward = -82.96, steps = 15 00:45:18 [INFO] train episode 34428: reward = -164.48, steps = 34 00:45:26 [INFO] train episode 34429: reward = -156.87, steps = 79 00:45:28 [INFO] train episode 34430: reward = -87.19, steps = 23 00:45:33 [INFO] train episode 34431: reward = -74.58, steps = 48 00:45:35 [INFO] train episode 34432: reward = -52.96, steps = 18 00:45:38 [INFO] train episode 34433: reward = -62.04, steps = 33 00:45:41 [INFO] train episode 34434: reward = -94.47, steps = 32 00:45:43 [INFO] train episode 34435: reward = -83.65, steps = 24 00:45:45 [INFO] train episode 34436: reward = -119.67, steps = 21 00:45:49 [INFO] train episode 34437: reward = -128.66, steps = 34 00:45:51 [INFO] train episode 34438: reward = -90.70, steps = 25 00:45:53 [INFO] train episode 34439: reward = -83.43, steps = 24 00:45:56 [INFO] train episode 34440: reward = -85.01, steps = 30 00:45:58 [INFO] train episode 34441: reward = -122.05, steps = 19 00:46:00 [INFO] train episode 34442: reward = -78.91, steps = 27 00:46:02 [INFO] train episode 34443: reward = -75.28, steps = 23 00:46:05 [INFO] train episode 34444: reward = -98.23, steps = 29 00:46:06 [INFO] train episode 34445: reward = -49.81, steps = 19 00:46:08 [INFO] train episode 34446: reward = -43.03, steps = 22 00:46:10 [INFO] train episode 34447: reward = -47.41, steps = 22 00:46:13 [INFO] train episode 34448: reward = -69.53, steps = 33 00:46:16 [INFO] train episode 34449: reward = -155.60, steps = 29 00:46:20 [INFO] train episode 34450: reward = -96.25, steps = 39 00:46:21 [INFO] train episode 34451: reward = -88.22, steps = 15 00:46:23 [INFO] train episode 34452: reward = -69.55, steps = 22 00:46:27 [INFO] train episode 34453: reward = -64.33, steps = 44 00:46:29 [INFO] train episode 34454: reward = -64.36, steps = 23 00:46:32 [INFO] train episode 34455: reward = -108.78, steps = 22 00:46:34 [INFO] train episode 34456: reward = -68.19, steps = 21 00:46:37 [INFO] train episode 34457: reward = -70.86, steps = 31 00:46:38 [INFO] train episode 34458: reward = -100.27, steps = 20 00:46:42 [INFO] train episode 34459: reward = -123.02, steps = 39 00:46:44 [INFO] train episode 34460: reward = -91.98, steps = 24 00:46:46 [INFO] train episode 34461: reward = -104.94, steps = 21 00:46:48 [INFO] train episode 34462: reward = -94.39, steps = 24 00:46:50 [INFO] train episode 34463: reward = -80.51, steps = 21 00:46:53 [INFO] train episode 34464: reward = -65.98, steps = 28 00:46:57 [INFO] train episode 34465: reward = -100.77, steps = 46 00:46:59 [INFO] train episode 34466: reward = -129.11, steps = 21 00:47:02 [INFO] train episode 34467: reward = -98.37, steps = 35 00:47:04 [INFO] train episode 34468: reward = -101.59, steps = 23 00:47:07 [INFO] train episode 34469: reward = -145.75, steps = 31 00:47:10 [INFO] train episode 34470: reward = -57.12, steps = 30 00:47:12 [INFO] train episode 34471: reward = -68.79, steps = 33 00:47:15 [INFO] train episode 34472: reward = -116.21, steps = 30 00:47:18 [INFO] train episode 34473: reward = -67.60, steps = 38 00:47:21 [INFO] train episode 34474: reward = -51.22, steps = 20 00:47:23 [INFO] train episode 34475: reward = -75.54, steps = 24 00:47:25 [INFO] train episode 34476: reward = -58.11, steps = 26 00:47:27 [INFO] train episode 34477: reward = -82.82, steps = 19 00:47:29 [INFO] train episode 34478: reward = -66.88, steps = 21 00:47:31 [INFO] train episode 34479: reward = -109.63, steps = 31 00:47:35 [INFO] train episode 34480: reward = -98.00, steps = 37 00:47:39 [INFO] train episode 34481: reward = -47.98, steps = 32 00:47:45 [INFO] train episode 34482: reward = -204.65, steps = 69 00:47:47 [INFO] train episode 34483: reward = -74.47, steps = 19 00:47:50 [INFO] train episode 34484: reward = -104.42, steps = 33 00:47:54 [INFO] train episode 34485: reward = -99.78, steps = 35 00:47:57 [INFO] train episode 34486: reward = -98.96, steps = 25 00:48:00 [INFO] train episode 34487: reward = -58.44, steps = 36 00:48:03 [INFO] train episode 34488: reward = -90.38, steps = 24 00:48:05 [INFO] train episode 34489: reward = -74.08, steps = 24 00:48:07 [INFO] train episode 34490: reward = -119.28, steps = 20 00:48:10 [INFO] train episode 34491: reward = -82.57, steps = 33 00:48:13 [INFO] train episode 34492: reward = -88.74, steps = 33 00:48:16 [INFO] train episode 34493: reward = -68.08, steps = 28 00:48:18 [INFO] train episode 34494: reward = -111.54, steps = 21 00:48:20 [INFO] train episode 34495: reward = -87.11, steps = 27 00:48:23 [INFO] train episode 34496: reward = -80.38, steps = 24 00:48:25 [INFO] train episode 34497: reward = -106.94, steps = 24 00:48:28 [INFO] train episode 34498: reward = -90.19, steps = 31 00:48:31 [INFO] train episode 34499: reward = -101.17, steps = 25 00:48:34 [INFO] train episode 34500: reward = -83.74, steps = 28 00:48:37 [INFO] train episode 34501: reward = -123.15, steps = 33 00:48:40 [INFO] train episode 34502: reward = -148.21, steps = 36 00:48:43 [INFO] train episode 34503: reward = -67.40, steps = 30 00:48:46 [INFO] train episode 34504: reward = -87.43, steps = 29 00:48:48 [INFO] train episode 34505: reward = -143.72, steps = 20 00:48:51 [INFO] train episode 34506: reward = -91.47, steps = 28 00:48:53 [INFO] train episode 34507: reward = -122.51, steps = 22 00:48:55 [INFO] train episode 34508: reward = -122.76, steps = 24 00:48:59 [INFO] train episode 34509: reward = -90.61, steps = 39 00:49:01 [INFO] train episode 34510: reward = -89.21, steps = 27 00:49:04 [INFO] train episode 34511: reward = -77.64, steps = 24 00:49:07 [INFO] train episode 34512: reward = -95.83, steps = 32 00:49:09 [INFO] train episode 34513: reward = -61.81, steps = 22 00:49:10 [INFO] train episode 34514: reward = -134.60, steps = 16 00:49:13 [INFO] train episode 34515: reward = -115.46, steps = 27 00:49:17 [INFO] train episode 34516: reward = -150.66, steps = 38 00:49:19 [INFO] train episode 34517: reward = -92.14, steps = 19 00:49:25 [INFO] train episode 34518: reward = -247.09, steps = 55 00:49:27 [INFO] train episode 34519: reward = -80.40, steps = 22 00:49:30 [INFO] train episode 34520: reward = -125.34, steps = 26 00:49:32 [INFO] train episode 34521: reward = -66.09, steps = 22 00:49:35 [INFO] train episode 34522: reward = -57.73, steps = 27 00:49:38 [INFO] train episode 34523: reward = -89.10, steps = 26 00:49:41 [INFO] train episode 34524: reward = -91.91, steps = 29 00:49:43 [INFO] train episode 34525: reward = -82.72, steps = 21 00:49:45 [INFO] train episode 34526: reward = -94.26, steps = 20 00:49:47 [INFO] train episode 34527: reward = -87.57, steps = 22 00:49:50 [INFO] train episode 34528: reward = -83.87, steps = 36 00:49:52 [INFO] train episode 34529: reward = -110.51, steps = 20 00:49:56 [INFO] train episode 34530: reward = -120.42, steps = 38 00:49:59 [INFO] train episode 34531: reward = -74.76, steps = 35 00:50:01 [INFO] train episode 34532: reward = -62.61, steps = 19 00:50:02 [INFO] train episode 34533: reward = -90.75, steps = 9 00:50:04 [INFO] train episode 34534: reward = -85.72, steps = 25 00:50:07 [INFO] train episode 34535: reward = -74.96, steps = 24 00:50:09 [INFO] train episode 34536: reward = -72.85, steps = 25 00:50:12 [INFO] train episode 34537: reward = -60.97, steps = 22 00:50:14 [INFO] train episode 34538: reward = -95.05, steps = 29 00:50:18 [INFO] train episode 34539: reward = -148.32, steps = 31 00:50:20 [INFO] train episode 34540: reward = -108.47, steps = 20 00:50:22 [INFO] train episode 34541: reward = -68.59, steps = 20 00:50:24 [INFO] train episode 34542: reward = -53.38, steps = 20 00:50:27 [INFO] train episode 34543: reward = -77.33, steps = 37 00:50:29 [INFO] train episode 34544: reward = -70.33, steps = 19 00:50:34 [INFO] train episode 34545: reward = -161.23, steps = 50 00:50:37 [INFO] train episode 34546: reward = -90.72, steps = 28 00:50:40 [INFO] train episode 34547: reward = -93.71, steps = 30 00:50:43 [INFO] train episode 34548: reward = -50.67, steps = 31 00:50:45 [INFO] train episode 34549: reward = -104.12, steps = 22 00:50:47 [INFO] train episode 34550: reward = -87.35, steps = 19 00:50:49 [INFO] train episode 34551: reward = -118.75, steps = 30 00:50:51 [INFO] train episode 34552: reward = -44.55, steps = 21 00:50:54 [INFO] train episode 34553: reward = -86.12, steps = 30 00:50:57 [INFO] train episode 34554: reward = -97.16, steps = 26 00:51:00 [INFO] train episode 34555: reward = -152.11, steps = 33 00:51:02 [INFO] train episode 34556: reward = -77.90, steps = 21 00:51:05 [INFO] train episode 34557: reward = -80.18, steps = 27 00:51:07 [INFO] train episode 34558: reward = -89.29, steps = 26 00:51:10 [INFO] train episode 34559: reward = -84.96, steps = 24 00:51:12 [INFO] train episode 34560: reward = -105.13, steps = 20 00:51:14 [INFO] train episode 34561: reward = -61.91, steps = 19 00:51:16 [INFO] train episode 34562: reward = -74.18, steps = 21 00:51:20 [INFO] train episode 34563: reward = -119.52, steps = 35 00:51:22 [INFO] train episode 34564: reward = -96.28, steps = 22 00:51:26 [INFO] train episode 34565: reward = -90.30, steps = 42 00:51:31 [INFO] train episode 34566: reward = -121.66, steps = 47 00:51:34 [INFO] train episode 34567: reward = -95.16, steps = 27 00:51:36 [INFO] train episode 34568: reward = -49.93, steps = 21 00:51:40 [INFO] train episode 34569: reward = -66.09, steps = 37 00:51:42 [INFO] train episode 34570: reward = -64.89, steps = 25 00:51:44 [INFO] train episode 34571: reward = -94.75, steps = 23 00:51:46 [INFO] train episode 34572: reward = -71.69, steps = 20 00:51:49 [INFO] train episode 34573: reward = -59.99, steps = 23 00:51:51 [INFO] train episode 34574: reward = -89.90, steps = 19 00:51:55 [INFO] train episode 34575: reward = -292.28, steps = 45 00:51:57 [INFO] train episode 34576: reward = -29.68, steps = 21 00:52:01 [INFO] train episode 34577: reward = -101.77, steps = 45 00:52:08 [INFO] train episode 34578: reward = -107.54, steps = 52 00:52:10 [INFO] train episode 34579: reward = -69.03, steps = 20 00:52:12 [INFO] train episode 34580: reward = -107.11, steps = 25 00:52:17 [INFO] train episode 34581: reward = -58.74, steps = 43 00:52:19 [INFO] train episode 34582: reward = -68.39, steps = 25 00:52:22 [INFO] train episode 34583: reward = -87.57, steps = 37 00:52:25 [INFO] train episode 34584: reward = -87.32, steps = 20 00:52:28 [INFO] train episode 34585: reward = -92.13, steps = 32 00:52:30 [INFO] train episode 34586: reward = -51.03, steps = 21 00:52:32 [INFO] train episode 34587: reward = -69.40, steps = 22 00:52:34 [INFO] train episode 34588: reward = -86.63, steps = 28 00:52:38 [INFO] train episode 34589: reward = -159.64, steps = 45 00:52:41 [INFO] train episode 34590: reward = -109.43, steps = 27 00:52:43 [INFO] train episode 34591: reward = -75.13, steps = 20 00:52:45 [INFO] train episode 34592: reward = -135.29, steps = 24 00:52:48 [INFO] train episode 34593: reward = -74.45, steps = 24 00:52:51 [INFO] train episode 34594: reward = -86.95, steps = 30 00:52:54 [INFO] train episode 34595: reward = -55.72, steps = 30 00:52:55 [INFO] train episode 34596: reward = -82.54, steps = 17 00:52:58 [INFO] train episode 34597: reward = -91.91, steps = 26 00:53:00 [INFO] train episode 34598: reward = -105.85, steps = 23 00:53:03 [INFO] train episode 34599: reward = -81.63, steps = 26 00:53:05 [INFO] train episode 34600: reward = -68.23, steps = 20 00:53:07 [INFO] train episode 34601: reward = -66.83, steps = 28 00:53:11 [INFO] train episode 34602: reward = -135.20, steps = 37 00:53:13 [INFO] train episode 34603: reward = -111.28, steps = 28 00:53:15 [INFO] train episode 34604: reward = -97.57, steps = 20 00:53:18 [INFO] train episode 34605: reward = -129.76, steps = 29 00:53:21 [INFO] train episode 34606: reward = -99.58, steps = 26 00:53:22 [INFO] train episode 34607: reward = -82.87, steps = 20 00:53:24 [INFO] train episode 34608: reward = -74.02, steps = 19 00:53:26 [INFO] train episode 34609: reward = -118.52, steps = 23 00:53:29 [INFO] train episode 34610: reward = -57.46, steps = 29 00:53:31 [INFO] train episode 34611: reward = -80.56, steps = 23 00:53:34 [INFO] train episode 34612: reward = -120.98, steps = 25 00:53:37 [INFO] train episode 34613: reward = -134.39, steps = 34 00:53:40 [INFO] train episode 34614: reward = -122.68, steps = 31 00:53:43 [INFO] train episode 34615: reward = -192.34, steps = 37 00:53:45 [INFO] train episode 34616: reward = -224.31, steps = 26 00:53:52 [INFO] train episode 34617: reward = -272.61, steps = 72 00:53:54 [INFO] train episode 34618: reward = -72.20, steps = 24 00:53:56 [INFO] train episode 34619: reward = -77.05, steps = 19 00:53:58 [INFO] train episode 34620: reward = -68.64, steps = 25 00:54:00 [INFO] train episode 34621: reward = -90.66, steps = 20 00:54:03 [INFO] train episode 34622: reward = -79.33, steps = 30 00:54:06 [INFO] train episode 34623: reward = -104.17, steps = 37 00:54:09 [INFO] train episode 34624: reward = -45.01, steps = 22 00:54:10 [INFO] train episode 34625: reward = -77.78, steps = 18 00:54:12 [INFO] train episode 34626: reward = -111.05, steps = 21 00:54:15 [INFO] train episode 34627: reward = -101.96, steps = 26 00:54:17 [INFO] train episode 34628: reward = -47.08, steps = 24 00:54:19 [INFO] train episode 34629: reward = -107.70, steps = 21 00:54:23 [INFO] train episode 34630: reward = -74.64, steps = 38 00:54:26 [INFO] train episode 34631: reward = -70.70, steps = 29 00:54:31 [INFO] train episode 34632: reward = -117.32, steps = 59 00:54:34 [INFO] train episode 34633: reward = -69.88, steps = 37 00:54:37 [INFO] train episode 34634: reward = -83.96, steps = 29 00:54:39 [INFO] train episode 34635: reward = -102.81, steps = 22 00:54:42 [INFO] train episode 34636: reward = -101.74, steps = 30 00:54:44 [INFO] train episode 34637: reward = -58.28, steps = 20 00:54:46 [INFO] train episode 34638: reward = -68.70, steps = 20 00:54:48 [INFO] train episode 34639: reward = -51.56, steps = 21 00:54:49 [INFO] train episode 34640: reward = -64.89, steps = 19 00:54:51 [INFO] train episode 34641: reward = -82.39, steps = 20 00:54:54 [INFO] train episode 34642: reward = -65.70, steps = 27 00:54:57 [INFO] train episode 34643: reward = -71.63, steps = 33 00:55:00 [INFO] train episode 34644: reward = -103.58, steps = 29 00:55:04 [INFO] train episode 34645: reward = -94.71, steps = 43 00:55:05 [INFO] train episode 34646: reward = -57.41, steps = 21 00:55:07 [INFO] train episode 34647: reward = -75.76, steps = 22 00:55:11 [INFO] train episode 34648: reward = -53.21, steps = 35 00:55:13 [INFO] train episode 34649: reward = -164.54, steps = 33 00:55:17 [INFO] train episode 34650: reward = -106.23, steps = 31 00:55:21 [INFO] train episode 34651: reward = -95.00, steps = 45 00:55:23 [INFO] train episode 34652: reward = -97.21, steps = 28 00:55:26 [INFO] train episode 34653: reward = -56.89, steps = 28 00:55:28 [INFO] train episode 34654: reward = -70.82, steps = 27 00:55:31 [INFO] train episode 34655: reward = -124.52, steps = 29 00:55:33 [INFO] train episode 34656: reward = -81.08, steps = 24 00:55:38 [INFO] train episode 34657: reward = -141.32, steps = 49 00:55:39 [INFO] train episode 34658: reward = -56.04, steps = 18 00:55:43 [INFO] train episode 34659: reward = -114.88, steps = 43 00:55:45 [INFO] train episode 34660: reward = -53.52, steps = 20 00:55:48 [INFO] train episode 34661: reward = -99.10, steps = 30 00:55:50 [INFO] train episode 34662: reward = -98.81, steps = 21 00:55:52 [INFO] train episode 34663: reward = -46.08, steps = 22 00:55:55 [INFO] train episode 34664: reward = -83.42, steps = 25 00:55:57 [INFO] train episode 34665: reward = -70.22, steps = 31 00:56:00 [INFO] train episode 34666: reward = -97.46, steps = 25 00:56:01 [INFO] train episode 34667: reward = -118.31, steps = 17 00:56:04 [INFO] train episode 34668: reward = -94.53, steps = 25 00:56:06 [INFO] train episode 34669: reward = -58.35, steps = 20 00:56:08 [INFO] train episode 34670: reward = -124.83, steps = 29 00:56:12 [INFO] train episode 34671: reward = -93.88, steps = 42 00:56:14 [INFO] train episode 34672: reward = -69.56, steps = 20 00:56:16 [INFO] train episode 34673: reward = -51.23, steps = 21 00:56:18 [INFO] train episode 34674: reward = -90.13, steps = 25 00:56:21 [INFO] train episode 34675: reward = -89.52, steps = 36 00:56:26 [INFO] train episode 34676: reward = -207.21, steps = 57 00:56:28 [INFO] train episode 34677: reward = -82.76, steps = 23 00:56:30 [INFO] train episode 34678: reward = -96.20, steps = 22 00:56:34 [INFO] train episode 34679: reward = -105.11, steps = 41 00:56:37 [INFO] train episode 34680: reward = -65.01, steps = 29 00:56:39 [INFO] train episode 34681: reward = -100.05, steps = 18 00:56:41 [INFO] train episode 34682: reward = -60.86, steps = 20 00:56:43 [INFO] train episode 34683: reward = -67.85, steps = 27 00:56:45 [INFO] train episode 34684: reward = -52.77, steps = 24 00:56:47 [INFO] train episode 34685: reward = -78.81, steps = 24 00:56:51 [INFO] train episode 34686: reward = -151.63, steps = 38 00:56:52 [INFO] train episode 34687: reward = -70.98, steps = 20 00:56:55 [INFO] train episode 34688: reward = -73.23, steps = 21 00:57:01 [INFO] train episode 34689: reward = -184.66, steps = 67 00:57:04 [INFO] train episode 34690: reward = -95.50, steps = 40 00:57:07 [INFO] train episode 34691: reward = -174.80, steps = 34 00:57:11 [INFO] train episode 34692: reward = -117.02, steps = 36 00:57:13 [INFO] train episode 34693: reward = -85.42, steps = 21 00:57:15 [INFO] train episode 34694: reward = -68.48, steps = 29 00:57:17 [INFO] train episode 34695: reward = -152.24, steps = 15 00:57:19 [INFO] train episode 34696: reward = -89.75, steps = 21 00:57:20 [INFO] train episode 34697: reward = -77.22, steps = 22 00:57:24 [INFO] train episode 34698: reward = -99.87, steps = 45 00:57:27 [INFO] train episode 34699: reward = -73.23, steps = 25 00:57:29 [INFO] train episode 34700: reward = -72.88, steps = 24 00:57:31 [INFO] train episode 34701: reward = -67.67, steps = 21 00:57:33 [INFO] train episode 34702: reward = -119.63, steps = 25 00:57:36 [INFO] train episode 34703: reward = -90.42, steps = 28 00:57:38 [INFO] train episode 34704: reward = -65.80, steps = 19 00:57:40 [INFO] train episode 34705: reward = -132.74, steps = 31 00:57:43 [INFO] train episode 34706: reward = -56.82, steps = 20 00:57:47 [INFO] train episode 34707: reward = -110.95, steps = 46 00:57:49 [INFO] train episode 34708: reward = -185.38, steps = 27 00:57:51 [INFO] train episode 34709: reward = -62.32, steps = 21 00:57:53 [INFO] train episode 34710: reward = -113.17, steps = 28 00:57:57 [INFO] train episode 34711: reward = -140.07, steps = 37 00:58:01 [INFO] train episode 34712: reward = -127.13, steps = 42 00:58:04 [INFO] train episode 34713: reward = -92.69, steps = 31 00:58:05 [INFO] train episode 34714: reward = -80.32, steps = 18 00:58:07 [INFO] train episode 34715: reward = -113.43, steps = 18 00:58:09 [INFO] train episode 34716: reward = -78.49, steps = 20 00:58:11 [INFO] train episode 34717: reward = -76.01, steps = 20 00:58:14 [INFO] train episode 34718: reward = -89.19, steps = 43 00:58:18 [INFO] train episode 34719: reward = -117.74, steps = 32 00:58:19 [INFO] train episode 34720: reward = -89.76, steps = 19 00:58:22 [INFO] train episode 34721: reward = -94.31, steps = 30 00:58:25 [INFO] train episode 34722: reward = -102.29, steps = 33 00:58:29 [INFO] train episode 34723: reward = -126.57, steps = 45 00:58:32 [INFO] train episode 34724: reward = -109.64, steps = 29 00:58:35 [INFO] train episode 34725: reward = -76.64, steps = 24 00:58:37 [INFO] train episode 34726: reward = -119.56, steps = 26 00:58:40 [INFO] train episode 34727: reward = -75.79, steps = 27 00:58:42 [INFO] train episode 34728: reward = -174.88, steps = 25 00:58:45 [INFO] train episode 34729: reward = -92.50, steps = 31 00:58:49 [INFO] train episode 34730: reward = -134.45, steps = 39 00:58:54 [INFO] train episode 34731: reward = -124.08, steps = 55 00:58:58 [INFO] train episode 34732: reward = -147.91, steps = 39 00:59:00 [INFO] train episode 34733: reward = -71.47, steps = 20 00:59:02 [INFO] train episode 34734: reward = -88.42, steps = 24 00:59:05 [INFO] train episode 34735: reward = -80.79, steps = 33 00:59:07 [INFO] train episode 34736: reward = -67.99, steps = 22 00:59:10 [INFO] train episode 34737: reward = -118.66, steps = 34 00:59:15 [INFO] train episode 34738: reward = -153.56, steps = 52 00:59:17 [INFO] train episode 34739: reward = -92.95, steps = 24 00:59:21 [INFO] train episode 34740: reward = -121.37, steps = 41 00:59:23 [INFO] train episode 34741: reward = -98.50, steps = 22 00:59:25 [INFO] train episode 34742: reward = -74.90, steps = 21 00:59:27 [INFO] train episode 34743: reward = -87.16, steps = 25 00:59:30 [INFO] train episode 34744: reward = -52.05, steps = 24 00:59:31 [INFO] train episode 34745: reward = -89.34, steps = 20 00:59:34 [INFO] train episode 34746: reward = -99.64, steps = 26 00:59:36 [INFO] train episode 34747: reward = -139.22, steps = 24 00:59:39 [INFO] train episode 34748: reward = -60.35, steps = 31 00:59:42 [INFO] train episode 34749: reward = -104.68, steps = 32 00:59:44 [INFO] train episode 34750: reward = -66.24, steps = 21 00:59:46 [INFO] train episode 34751: reward = -100.75, steps = 20 00:59:49 [INFO] train episode 34752: reward = -66.74, steps = 30 00:59:52 [INFO] train episode 34753: reward = -165.11, steps = 38 00:59:54 [INFO] train episode 34754: reward = -92.63, steps = 24 00:59:58 [INFO] train episode 34755: reward = -40.95, steps = 35 01:00:00 [INFO] train episode 34756: reward = -61.05, steps = 23 01:00:02 [INFO] train episode 34757: reward = -74.78, steps = 25 01:00:06 [INFO] train episode 34758: reward = -77.13, steps = 45 01:00:08 [INFO] train episode 34759: reward = -88.03, steps = 27 01:00:13 [INFO] train episode 34760: reward = -119.26, steps = 50 01:00:16 [INFO] train episode 34761: reward = -99.85, steps = 21 01:00:18 [INFO] train episode 34762: reward = -70.05, steps = 27 01:00:21 [INFO] train episode 34763: reward = -51.71, steps = 19 01:00:24 [INFO] train episode 34764: reward = -97.15, steps = 31 01:00:27 [INFO] train episode 34765: reward = -65.87, steps = 29 01:00:31 [INFO] train episode 34766: reward = -126.26, steps = 36 01:00:38 [INFO] train episode 34767: reward = -121.46, steps = 57 01:00:42 [INFO] train episode 34768: reward = -105.88, steps = 40 01:00:44 [INFO] train episode 34769: reward = -92.25, steps = 26 01:00:47 [INFO] train episode 34770: reward = -56.54, steps = 33 01:00:49 [INFO] train episode 34771: reward = -83.44, steps = 19 01:00:51 [INFO] train episode 34772: reward = -95.40, steps = 24 01:00:54 [INFO] train episode 34773: reward = -102.02, steps = 20 01:00:58 [INFO] train episode 34774: reward = -222.79, steps = 42 01:01:00 [INFO] train episode 34775: reward = -154.31, steps = 22 01:01:04 [INFO] train episode 34776: reward = -105.29, steps = 35 01:01:06 [INFO] train episode 34777: reward = -85.99, steps = 21 01:01:08 [INFO] train episode 34778: reward = -109.48, steps = 19 01:01:12 [INFO] train episode 34779: reward = -109.31, steps = 39 01:01:14 [INFO] train episode 34780: reward = -78.72, steps = 22 01:01:16 [INFO] train episode 34781: reward = -108.69, steps = 24 01:01:19 [INFO] train episode 34782: reward = -90.66, steps = 24 01:01:23 [INFO] train episode 34783: reward = -78.14, steps = 46 01:01:26 [INFO] train episode 34784: reward = -90.89, steps = 38 01:01:30 [INFO] train episode 34785: reward = -124.53, steps = 39 01:01:35 [INFO] train episode 34786: reward = -112.06, steps = 56 01:01:37 [INFO] train episode 34787: reward = -49.04, steps = 21 01:01:41 [INFO] train episode 34788: reward = -107.98, steps = 37 01:01:44 [INFO] train episode 34789: reward = -94.88, steps = 37 01:01:45 [INFO] train episode 34790: reward = -84.18, steps = 17 01:01:49 [INFO] train episode 34791: reward = -116.51, steps = 36 01:01:52 [INFO] train episode 34792: reward = -112.19, steps = 33 01:01:55 [INFO] train episode 34793: reward = -120.18, steps = 36 01:01:57 [INFO] train episode 34794: reward = -82.42, steps = 20 01:01:59 [INFO] train episode 34795: reward = -92.84, steps = 19 01:02:03 [INFO] train episode 34796: reward = -112.04, steps = 43 01:02:06 [INFO] train episode 34797: reward = -94.90, steps = 28 01:02:08 [INFO] train episode 34798: reward = -75.00, steps = 26 01:02:10 [INFO] train episode 34799: reward = -92.32, steps = 23 01:02:13 [INFO] train episode 34800: reward = -75.43, steps = 29 01:02:14 [INFO] train episode 34801: reward = -85.61, steps = 19 01:02:16 [INFO] train episode 34802: reward = -56.50, steps = 20 01:02:18 [INFO] train episode 34803: reward = -88.33, steps = 21 01:02:22 [INFO] train episode 34804: reward = -126.94, steps = 34 01:02:24 [INFO] train episode 34805: reward = -58.84, steps = 29 01:02:26 [INFO] train episode 34806: reward = -66.60, steps = 21 01:02:28 [INFO] train episode 34807: reward = -83.48, steps = 28 01:02:31 [INFO] train episode 34808: reward = -60.92, steps = 22 01:02:33 [INFO] train episode 34809: reward = -54.42, steps = 23 01:02:35 [INFO] train episode 34810: reward = -80.50, steps = 24 01:02:39 [INFO] train episode 34811: reward = -126.92, steps = 36 01:02:41 [INFO] train episode 34812: reward = -67.30, steps = 20 01:02:44 [INFO] train episode 34813: reward = -59.18, steps = 29 01:02:47 [INFO] train episode 34814: reward = -74.95, steps = 26 01:02:53 [INFO] train episode 34815: reward = -103.19, steps = 56 01:02:55 [INFO] train episode 34816: reward = -89.41, steps = 24 01:02:57 [INFO] train episode 34817: reward = -66.97, steps = 20 01:03:00 [INFO] train episode 34818: reward = -47.79, steps = 29 01:03:02 [INFO] train episode 34819: reward = -100.77, steps = 21 01:03:03 [INFO] train episode 34820: reward = -59.14, steps = 20 01:03:05 [INFO] train episode 34821: reward = -87.74, steps = 21 01:03:08 [INFO] train episode 34822: reward = -61.28, steps = 36 01:03:10 [INFO] train episode 34823: reward = -46.40, steps = 23 01:03:12 [INFO] train episode 34824: reward = -69.38, steps = 19 01:03:15 [INFO] train episode 34825: reward = -117.82, steps = 24 01:03:17 [INFO] train episode 34826: reward = -137.12, steps = 27 01:03:19 [INFO] train episode 34827: reward = -133.89, steps = 28 01:03:22 [INFO] train episode 34828: reward = -106.34, steps = 33 01:03:25 [INFO] train episode 34829: reward = -91.63, steps = 24 01:03:27 [INFO] train episode 34830: reward = -118.81, steps = 18 01:03:29 [INFO] train episode 34831: reward = -81.15, steps = 25 01:03:33 [INFO] train episode 34832: reward = -125.75, steps = 36 01:03:37 [INFO] train episode 34833: reward = -100.46, steps = 40 01:03:39 [INFO] train episode 34834: reward = -64.19, steps = 22 01:03:43 [INFO] train episode 34835: reward = -121.61, steps = 43 01:03:46 [INFO] train episode 34836: reward = -126.12, steps = 29 01:03:48 [INFO] train episode 34837: reward = -78.07, steps = 22 01:03:50 [INFO] train episode 34838: reward = -129.49, steps = 22 01:03:52 [INFO] train episode 34839: reward = -103.21, steps = 25 01:03:56 [INFO] train episode 34840: reward = -105.81, steps = 33 01:03:58 [INFO] train episode 34841: reward = -31.75, steps = 23 01:04:00 [INFO] train episode 34842: reward = -76.62, steps = 26 01:04:02 [INFO] train episode 34843: reward = -64.89, steps = 18 01:04:04 [INFO] train episode 34844: reward = -60.06, steps = 20 01:04:07 [INFO] train episode 34845: reward = -66.57, steps = 34 01:04:09 [INFO] train episode 34846: reward = -129.03, steps = 24 01:04:11 [INFO] train episode 34847: reward = -73.55, steps = 22 01:04:14 [INFO] train episode 34848: reward = -99.12, steps = 37 01:04:17 [INFO] train episode 34849: reward = -91.33, steps = 26 01:04:19 [INFO] train episode 34850: reward = -123.38, steps = 30 01:04:23 [INFO] train episode 34851: reward = -126.54, steps = 40 01:04:25 [INFO] train episode 34852: reward = -81.57, steps = 23 01:04:27 [INFO] train episode 34853: reward = -71.06, steps = 20 01:04:30 [INFO] train episode 34854: reward = -102.58, steps = 34 01:04:32 [INFO] train episode 34855: reward = -74.76, steps = 22 01:04:34 [INFO] train episode 34856: reward = -90.76, steps = 19 01:04:36 [INFO] train episode 34857: reward = -123.84, steps = 25 01:04:40 [INFO] train episode 34858: reward = -78.83, steps = 37 01:04:41 [INFO] train episode 34859: reward = -69.37, steps = 15 01:04:42 [INFO] train episode 34860: reward = -94.11, steps = 16 01:04:46 [INFO] train episode 34861: reward = -90.30, steps = 43 01:04:49 [INFO] train episode 34862: reward = -80.64, steps = 25 01:04:50 [INFO] train episode 34863: reward = -51.11, steps = 21 01:04:54 [INFO] train episode 34864: reward = -92.76, steps = 32 01:04:55 [INFO] train episode 34865: reward = -122.65, steps = 19 01:04:57 [INFO] train episode 34866: reward = -69.06, steps = 21 01:05:01 [INFO] train episode 34867: reward = -82.00, steps = 37 01:05:03 [INFO] train episode 34868: reward = -82.20, steps = 22 01:05:06 [INFO] train episode 34869: reward = -111.24, steps = 31 01:05:09 [INFO] train episode 34870: reward = -78.51, steps = 29 01:05:11 [INFO] train episode 34871: reward = -80.55, steps = 18 01:05:13 [INFO] train episode 34872: reward = -68.41, steps = 22 01:05:16 [INFO] train episode 34873: reward = -63.16, steps = 34 01:05:18 [INFO] train episode 34874: reward = -67.19, steps = 28 01:05:20 [INFO] train episode 34875: reward = -88.00, steps = 21 01:05:22 [INFO] train episode 34876: reward = -105.93, steps = 24 01:05:24 [INFO] train episode 34877: reward = -76.33, steps = 27 01:05:27 [INFO] train episode 34878: reward = -72.00, steps = 21 01:05:29 [INFO] train episode 34879: reward = -56.35, steps = 20 01:05:31 [INFO] train episode 34880: reward = -68.48, steps = 24 01:05:33 [INFO] train episode 34881: reward = -72.28, steps = 26 01:05:35 [INFO] train episode 34882: reward = -96.39, steps = 23 01:05:37 [INFO] train episode 34883: reward = -56.79, steps = 26 01:05:40 [INFO] train episode 34884: reward = -102.88, steps = 27 01:05:42 [INFO] train episode 34885: reward = -105.25, steps = 22 01:05:44 [INFO] train episode 34886: reward = -64.51, steps = 20 01:05:46 [INFO] train episode 34887: reward = -118.13, steps = 25 01:05:48 [INFO] train episode 34888: reward = -55.97, steps = 23 01:05:53 [INFO] train episode 34889: reward = -133.73, steps = 52 01:05:55 [INFO] train episode 34890: reward = -74.80, steps = 23 01:05:56 [INFO] train episode 34891: reward = -85.59, steps = 21 01:06:00 [INFO] train episode 34892: reward = -91.30, steps = 34 01:06:02 [INFO] train episode 34893: reward = -85.04, steps = 24 01:06:05 [INFO] train episode 34894: reward = -113.39, steps = 33 01:06:09 [INFO] train episode 34895: reward = -128.21, steps = 43 01:06:11 [INFO] train episode 34896: reward = -81.96, steps = 20 01:06:13 [INFO] train episode 34897: reward = -74.13, steps = 24 01:06:16 [INFO] train episode 34898: reward = -94.80, steps = 31 01:06:19 [INFO] train episode 34899: reward = -165.90, steps = 35 01:06:20 [INFO] train episode 34900: reward = -66.44, steps = 19 01:06:23 [INFO] train episode 34901: reward = -61.04, steps = 24 01:06:26 [INFO] train episode 34902: reward = -44.09, steps = 40 01:06:29 [INFO] train episode 34903: reward = -97.82, steps = 33 01:06:31 [INFO] train episode 34904: reward = -78.83, steps = 21 01:06:34 [INFO] train episode 34905: reward = -129.02, steps = 31 01:06:37 [INFO] train episode 34906: reward = -92.03, steps = 33 01:06:39 [INFO] train episode 34907: reward = -101.96, steps = 23 01:06:41 [INFO] train episode 34908: reward = -70.41, steps = 24 01:06:44 [INFO] train episode 34909: reward = -106.36, steps = 31 01:06:46 [INFO] train episode 34910: reward = -79.71, steps = 22 01:06:50 [INFO] train episode 34911: reward = -89.05, steps = 42 01:06:54 [INFO] train episode 34912: reward = -129.68, steps = 45 01:06:56 [INFO] train episode 34913: reward = -57.31, steps = 23 01:06:58 [INFO] train episode 34914: reward = -62.10, steps = 21 01:07:00 [INFO] train episode 34915: reward = -73.49, steps = 20 01:07:02 [INFO] train episode 34916: reward = -74.15, steps = 27 01:07:04 [INFO] train episode 34917: reward = -89.09, steps = 20 01:07:06 [INFO] train episode 34918: reward = -105.73, steps = 20 01:07:08 [INFO] train episode 34919: reward = -60.79, steps = 20 01:07:10 [INFO] train episode 34920: reward = -83.07, steps = 26 01:07:13 [INFO] train episode 34921: reward = -66.91, steps = 35 01:07:15 [INFO] train episode 34922: reward = -79.83, steps = 20 01:07:19 [INFO] train episode 34923: reward = -156.34, steps = 40 01:07:21 [INFO] train episode 34924: reward = -81.04, steps = 25 01:07:23 [INFO] train episode 34925: reward = -59.81, steps = 24 01:07:26 [INFO] train episode 34926: reward = -128.86, steps = 29 01:07:29 [INFO] train episode 34927: reward = -107.46, steps = 31 01:07:31 [INFO] train episode 34928: reward = -62.19, steps = 21 01:07:34 [INFO] train episode 34929: reward = -56.74, steps = 36 01:07:36 [INFO] train episode 34930: reward = -57.12, steps = 24 01:07:39 [INFO] train episode 34931: reward = -55.33, steps = 35 01:07:42 [INFO] train episode 34932: reward = -120.21, steps = 28 01:07:44 [INFO] train episode 34933: reward = -70.97, steps = 23 01:07:46 [INFO] train episode 34934: reward = -64.03, steps = 24 01:07:48 [INFO] train episode 34935: reward = -138.17, steps = 25 01:07:52 [INFO] train episode 34936: reward = -127.07, steps = 43 01:07:54 [INFO] train episode 34937: reward = -49.27, steps = 18 01:07:56 [INFO] train episode 34938: reward = -89.48, steps = 19 01:07:58 [INFO] train episode 34939: reward = -73.28, steps = 21 01:08:00 [INFO] train episode 34940: reward = -141.41, steps = 22 01:08:03 [INFO] train episode 34941: reward = -82.24, steps = 30 01:08:05 [INFO] train episode 34942: reward = -93.03, steps = 21 01:08:08 [INFO] train episode 34943: reward = -158.37, steps = 37 01:08:10 [INFO] train episode 34944: reward = -76.10, steps = 22 01:08:12 [INFO] train episode 34945: reward = -99.35, steps = 20 01:08:14 [INFO] train episode 34946: reward = -71.70, steps = 19 01:08:16 [INFO] train episode 34947: reward = -63.23, steps = 20 01:08:18 [INFO] train episode 34948: reward = -94.08, steps = 19 01:08:20 [INFO] train episode 34949: reward = -83.81, steps = 24 01:08:22 [INFO] train episode 34950: reward = -90.73, steps = 22 01:08:25 [INFO] train episode 34951: reward = -96.63, steps = 36 01:08:27 [INFO] train episode 34952: reward = -76.53, steps = 21 01:08:29 [INFO] train episode 34953: reward = -170.71, steps = 20 01:08:31 [INFO] train episode 34954: reward = -74.71, steps = 23 01:08:33 [INFO] train episode 34955: reward = -148.29, steps = 25 01:08:36 [INFO] train episode 34956: reward = -237.81, steps = 33 01:08:38 [INFO] train episode 34957: reward = -156.36, steps = 22 01:08:41 [INFO] train episode 34958: reward = -84.48, steps = 30 01:08:43 [INFO] train episode 34959: reward = -70.67, steps = 24 01:08:46 [INFO] train episode 34960: reward = -149.03, steps = 37 01:08:48 [INFO] train episode 34961: reward = -84.38, steps = 18 01:08:50 [INFO] train episode 34962: reward = -118.30, steps = 20 01:08:51 [INFO] train episode 34963: reward = -81.17, steps = 18 01:08:53 [INFO] train episode 34964: reward = -91.74, steps = 17 01:08:55 [INFO] train episode 34965: reward = -84.01, steps = 22 01:08:58 [INFO] train episode 34966: reward = -56.38, steps = 30 01:09:02 [INFO] train episode 34967: reward = -118.28, steps = 39 01:09:03 [INFO] train episode 34968: reward = -69.58, steps = 20 01:09:06 [INFO] train episode 34969: reward = -73.84, steps = 26 01:09:09 [INFO] train episode 34970: reward = -92.21, steps = 33 01:09:11 [INFO] train episode 34971: reward = -43.36, steps = 31 01:09:14 [INFO] train episode 34972: reward = -176.22, steps = 29 01:09:16 [INFO] train episode 34973: reward = -70.16, steps = 23 01:09:19 [INFO] train episode 34974: reward = -84.41, steps = 32 01:09:21 [INFO] train episode 34975: reward = -85.18, steps = 22 01:09:23 [INFO] train episode 34976: reward = -110.97, steps = 25 01:09:25 [INFO] train episode 34977: reward = -94.13, steps = 22 01:09:28 [INFO] train episode 34978: reward = -96.67, steps = 27 01:09:30 [INFO] train episode 34979: reward = -107.37, steps = 25 01:09:32 [INFO] train episode 34980: reward = -112.94, steps = 24 01:09:36 [INFO] train episode 34981: reward = -150.41, steps = 42 01:09:40 [INFO] train episode 34982: reward = -82.48, steps = 49 01:09:43 [INFO] train episode 34983: reward = -79.45, steps = 28 01:09:45 [INFO] train episode 34984: reward = -80.41, steps = 24 01:09:47 [INFO] train episode 34985: reward = -73.18, steps = 25 01:09:49 [INFO] train episode 34986: reward = -83.05, steps = 21 01:09:53 [INFO] train episode 34987: reward = -95.66, steps = 37 01:09:56 [INFO] train episode 34988: reward = -94.02, steps = 36 01:09:58 [INFO] train episode 34989: reward = -98.03, steps = 28 01:10:01 [INFO] train episode 34990: reward = -99.73, steps = 34 01:10:03 [INFO] train episode 34991: reward = -71.14, steps = 22 01:10:05 [INFO] train episode 34992: reward = -68.54, steps = 18 01:10:08 [INFO] train episode 34993: reward = -201.04, steps = 27 01:10:11 [INFO] train episode 34994: reward = -119.53, steps = 32 01:10:12 [INFO] train episode 34995: reward = -56.61, steps = 22 01:10:18 [INFO] train episode 34996: reward = -108.76, steps = 70 01:10:21 [INFO] train episode 34997: reward = -183.15, steps = 27 01:10:23 [INFO] train episode 34998: reward = -110.53, steps = 20 01:10:25 [INFO] train episode 34999: reward = -60.29, steps = 26 01:10:27 [INFO] train episode 35000: reward = -58.87, steps = 21 01:10:30 [INFO] train episode 35001: reward = -145.91, steps = 27 01:10:32 [INFO] train episode 35002: reward = -103.20, steps = 24 01:10:34 [INFO] train episode 35003: reward = -96.41, steps = 29 01:10:37 [INFO] train episode 35004: reward = -49.56, steps = 36 01:10:41 [INFO] train episode 35005: reward = -82.99, steps = 32 01:10:44 [INFO] train episode 35006: reward = -122.26, steps = 38 01:10:46 [INFO] train episode 35007: reward = -100.33, steps = 24 01:10:49 [INFO] train episode 35008: reward = -126.89, steps = 26 01:10:51 [INFO] train episode 35009: reward = -89.15, steps = 20 01:10:55 [INFO] train episode 35010: reward = -59.28, steps = 40 01:10:59 [INFO] train episode 35011: reward = -121.78, steps = 39 01:11:01 [INFO] train episode 35012: reward = -81.13, steps = 22 01:11:03 [INFO] train episode 35013: reward = -106.26, steps = 21 01:11:06 [INFO] train episode 35014: reward = -54.12, steps = 36 01:11:08 [INFO] train episode 35015: reward = -69.99, steps = 21 01:11:10 [INFO] train episode 35016: reward = -61.83, steps = 23 01:11:13 [INFO] train episode 35017: reward = -101.60, steps = 34 01:11:15 [INFO] train episode 35018: reward = -57.54, steps = 20 01:11:17 [INFO] train episode 35019: reward = -88.92, steps = 21 01:11:19 [INFO] train episode 35020: reward = -58.06, steps = 23 01:11:22 [INFO] train episode 35021: reward = -73.83, steps = 31 01:11:24 [INFO] train episode 35022: reward = -68.33, steps = 22 01:11:26 [INFO] train episode 35023: reward = -44.18, steps = 24 01:11:29 [INFO] train episode 35024: reward = -176.30, steps = 29 01:11:32 [INFO] train episode 35025: reward = -83.34, steps = 39 01:11:35 [INFO] train episode 35026: reward = -155.70, steps = 31 01:11:39 [INFO] train episode 35027: reward = -104.01, steps = 31 01:11:42 [INFO] train episode 35028: reward = -101.51, steps = 31 01:11:44 [INFO] train episode 35029: reward = -47.00, steps = 23 01:11:46 [INFO] train episode 35030: reward = -85.93, steps = 22 01:11:48 [INFO] train episode 35031: reward = -57.50, steps = 20 01:11:53 [INFO] train episode 35032: reward = -109.80, steps = 36 01:11:57 [INFO] train episode 35033: reward = -193.73, steps = 37 01:12:00 [INFO] train episode 35034: reward = -65.22, steps = 23 01:12:02 [INFO] train episode 35035: reward = -98.85, steps = 18 01:12:03 [INFO] train episode 35036: reward = -147.02, steps = 17 01:12:06 [INFO] train episode 35037: reward = -73.69, steps = 27 01:12:09 [INFO] train episode 35038: reward = -91.62, steps = 25 01:12:11 [INFO] train episode 35039: reward = -150.07, steps = 24 01:12:14 [INFO] train episode 35040: reward = -121.00, steps = 28 01:12:16 [INFO] train episode 35041: reward = -92.30, steps = 20 01:12:18 [INFO] train episode 35042: reward = -74.98, steps = 23 01:12:20 [INFO] train episode 35043: reward = -73.33, steps = 21 01:12:23 [INFO] train episode 35044: reward = -96.93, steps = 29 01:12:29 [INFO] train episode 35045: reward = -143.75, steps = 54 01:12:31 [INFO] train episode 35046: reward = -55.31, steps = 22 01:12:34 [INFO] train episode 35047: reward = -66.01, steps = 30 01:12:36 [INFO] train episode 35048: reward = -82.69, steps = 19 01:12:39 [INFO] train episode 35049: reward = -106.39, steps = 34 01:12:41 [INFO] train episode 35050: reward = -74.91, steps = 25 01:12:43 [INFO] train episode 35051: reward = -69.42, steps = 20 01:12:45 [INFO] train episode 35052: reward = -79.30, steps = 21 01:12:47 [INFO] train episode 35053: reward = -86.77, steps = 22 01:12:50 [INFO] train episode 35054: reward = -171.01, steps = 25 01:12:52 [INFO] train episode 35055: reward = -76.48, steps = 26 01:12:54 [INFO] train episode 35056: reward = -71.34, steps = 24 01:12:58 [INFO] train episode 35057: reward = -143.74, steps = 38 01:13:01 [INFO] train episode 35058: reward = -85.94, steps = 40 01:13:03 [INFO] train episode 35059: reward = -79.78, steps = 19 01:13:06 [INFO] train episode 35060: reward = -77.64, steps = 35 01:13:10 [INFO] train episode 35061: reward = -111.43, steps = 41 01:13:13 [INFO] train episode 35062: reward = -163.84, steps = 44 01:13:15 [INFO] train episode 35063: reward = -64.25, steps = 18 01:13:18 [INFO] train episode 35064: reward = -86.44, steps = 27 01:13:20 [INFO] train episode 35065: reward = -84.30, steps = 19 01:13:23 [INFO] train episode 35066: reward = -81.69, steps = 38 01:13:25 [INFO] train episode 35067: reward = -133.13, steps = 27 01:13:27 [INFO] train episode 35068: reward = -124.58, steps = 20 01:13:31 [INFO] train episode 35069: reward = -109.60, steps = 49 01:13:35 [INFO] train episode 35070: reward = -105.02, steps = 37 01:13:39 [INFO] train episode 35071: reward = -175.01, steps = 48 01:13:43 [INFO] train episode 35072: reward = -71.69, steps = 49 01:13:45 [INFO] train episode 35073: reward = -49.97, steps = 20 01:13:47 [INFO] train episode 35074: reward = -118.06, steps = 24 01:13:49 [INFO] train episode 35075: reward = -79.17, steps = 20 01:13:52 [INFO] train episode 35076: reward = -146.70, steps = 29 01:13:54 [INFO] train episode 35077: reward = -118.56, steps = 20 01:13:55 [INFO] train episode 35078: reward = -107.62, steps = 20 01:13:57 [INFO] train episode 35079: reward = -88.70, steps = 24 01:14:00 [INFO] train episode 35080: reward = -73.94, steps = 21 01:14:02 [INFO] train episode 35081: reward = -127.67, steps = 21 01:14:04 [INFO] train episode 35082: reward = -136.64, steps = 22 01:14:06 [INFO] train episode 35083: reward = -89.19, steps = 20 01:14:09 [INFO] train episode 35084: reward = -113.02, steps = 36 01:14:12 [INFO] train episode 35085: reward = -154.97, steps = 30 01:14:14 [INFO] train episode 35086: reward = -97.82, steps = 23 01:14:17 [INFO] train episode 35087: reward = -122.17, steps = 35 01:14:20 [INFO] train episode 35088: reward = -53.19, steps = 34 01:14:22 [INFO] train episode 35089: reward = -73.01, steps = 22 01:14:24 [INFO] train episode 35090: reward = -70.50, steps = 18 01:14:26 [INFO] train episode 35091: reward = -150.32, steps = 26 01:14:29 [INFO] train episode 35092: reward = -52.00, steps = 34 01:14:32 [INFO] train episode 35093: reward = -113.00, steps = 28 01:14:34 [INFO] train episode 35094: reward = -69.11, steps = 22 01:14:36 [INFO] train episode 35095: reward = -104.36, steps = 32 01:14:40 [INFO] train episode 35096: reward = -95.72, steps = 39 01:14:42 [INFO] train episode 35097: reward = -81.77, steps = 20 01:14:46 [INFO] train episode 35098: reward = -118.85, steps = 43 01:14:48 [INFO] train episode 35099: reward = -115.95, steps = 26 01:14:50 [INFO] train episode 35100: reward = -71.02, steps = 22 01:14:53 [INFO] train episode 35101: reward = -98.45, steps = 37 01:14:56 [INFO] train episode 35102: reward = -103.23, steps = 29 01:14:58 [INFO] train episode 35103: reward = -65.13, steps = 23 01:15:00 [INFO] train episode 35104: reward = -74.51, steps = 27 01:15:02 [INFO] train episode 35105: reward = -97.45, steps = 19 01:15:04 [INFO] train episode 35106: reward = -102.31, steps = 18 01:15:06 [INFO] train episode 35107: reward = -71.22, steps = 22 01:15:08 [INFO] train episode 35108: reward = -69.80, steps = 20 01:15:12 [INFO] train episode 35109: reward = -97.88, steps = 51 01:15:14 [INFO] train episode 35110: reward = -84.38, steps = 19 01:15:16 [INFO] train episode 35111: reward = -71.63, steps = 22 01:15:18 [INFO] train episode 35112: reward = -98.32, steps = 18 01:15:19 [INFO] train episode 35113: reward = -73.66, steps = 19 01:15:21 [INFO] train episode 35114: reward = -112.56, steps = 20 01:15:23 [INFO] train episode 35115: reward = -78.61, steps = 17 01:15:25 [INFO] train episode 35116: reward = -90.13, steps = 21 01:15:27 [INFO] train episode 35117: reward = -87.32, steps = 25 01:15:29 [INFO] train episode 35118: reward = -79.33, steps = 26 01:15:32 [INFO] train episode 35119: reward = -72.49, steps = 25 01:15:34 [INFO] train episode 35120: reward = -84.82, steps = 32 01:15:37 [INFO] train episode 35121: reward = -73.80, steps = 26 01:15:38 [INFO] train episode 35122: reward = -66.98, steps = 20 01:15:42 [INFO] train episode 35123: reward = -108.25, steps = 36 01:15:44 [INFO] train episode 35124: reward = -75.83, steps = 25 01:15:46 [INFO] train episode 35125: reward = -97.06, steps = 23 01:15:49 [INFO] train episode 35126: reward = -59.04, steps = 30 01:15:51 [INFO] train episode 35127: reward = -80.73, steps = 22 01:15:54 [INFO] train episode 35128: reward = -93.63, steps = 34 01:15:55 [INFO] train episode 35129: reward = -77.00, steps = 19 01:15:57 [INFO] train episode 35130: reward = -72.07, steps = 21 01:16:00 [INFO] train episode 35131: reward = -59.11, steps = 30 01:16:02 [INFO] train episode 35132: reward = -69.47, steps = 23 01:16:08 [INFO] train episode 35133: reward = -265.96, steps = 62 01:16:11 [INFO] train episode 35134: reward = -110.20, steps = 39 01:16:14 [INFO] train episode 35135: reward = -67.97, steps = 29 01:16:16 [INFO] train episode 35136: reward = -67.46, steps = 28 01:16:19 [INFO] train episode 35137: reward = -75.67, steps = 25 01:16:22 [INFO] train episode 35138: reward = -112.13, steps = 38 01:16:25 [INFO] train episode 35139: reward = -81.32, steps = 32 01:16:27 [INFO] train episode 35140: reward = -79.16, steps = 19 01:16:29 [INFO] train episode 35141: reward = -135.76, steps = 23 01:16:31 [INFO] train episode 35142: reward = -126.04, steps = 34 01:16:34 [INFO] train episode 35143: reward = -91.57, steps = 22 01:16:36 [INFO] train episode 35144: reward = -114.08, steps = 24 01:16:39 [INFO] train episode 35145: reward = -72.79, steps = 30 01:16:40 [INFO] train episode 35146: reward = -82.66, steps = 20 01:16:42 [INFO] train episode 35147: reward = -86.77, steps = 21 01:16:44 [INFO] train episode 35148: reward = -158.27, steps = 20 01:16:48 [INFO] train episode 35149: reward = -132.13, steps = 36 01:16:50 [INFO] train episode 35150: reward = -71.72, steps = 29 01:16:52 [INFO] train episode 35151: reward = -72.74, steps = 22 01:16:56 [INFO] train episode 35152: reward = -95.77, steps = 32 01:16:59 [INFO] train episode 35153: reward = -98.74, steps = 33 01:17:02 [INFO] train episode 35154: reward = -106.79, steps = 35 01:17:04 [INFO] train episode 35155: reward = -69.24, steps = 20 01:17:06 [INFO] train episode 35156: reward = -95.44, steps = 26 01:17:09 [INFO] train episode 35157: reward = -84.34, steps = 21 01:17:11 [INFO] train episode 35158: reward = -121.60, steps = 21 01:17:13 [INFO] train episode 35159: reward = -102.35, steps = 25 01:17:15 [INFO] train episode 35160: reward = -94.61, steps = 22 01:17:18 [INFO] train episode 35161: reward = -105.82, steps = 36 01:17:22 [INFO] train episode 35162: reward = -132.15, steps = 47 01:17:24 [INFO] train episode 35163: reward = -102.01, steps = 18 01:17:26 [INFO] train episode 35164: reward = -119.30, steps = 19 01:17:28 [INFO] train episode 35165: reward = -125.85, steps = 21 01:17:29 [INFO] train episode 35166: reward = -80.47, steps = 19 01:17:31 [INFO] train episode 35167: reward = -98.74, steps = 23 01:17:33 [INFO] train episode 35168: reward = -88.21, steps = 20 01:17:36 [INFO] train episode 35169: reward = -68.48, steps = 35 01:17:38 [INFO] train episode 35170: reward = -54.70, steps = 23 01:17:42 [INFO] train episode 35171: reward = -60.66, steps = 37 01:17:44 [INFO] train episode 35172: reward = -58.16, steps = 22 01:17:46 [INFO] train episode 35173: reward = -64.85, steps = 23 01:17:48 [INFO] train episode 35174: reward = -83.78, steps = 26 01:17:51 [INFO] train episode 35175: reward = -65.15, steps = 27 01:17:53 [INFO] train episode 35176: reward = -80.27, steps = 23 01:17:56 [INFO] train episode 35177: reward = -78.61, steps = 33 01:17:58 [INFO] train episode 35178: reward = -63.34, steps = 26 01:18:00 [INFO] train episode 35179: reward = -94.63, steps = 20 01:18:03 [INFO] train episode 35180: reward = -82.16, steps = 31 01:18:06 [INFO] train episode 35181: reward = -126.32, steps = 41 01:18:09 [INFO] train episode 35182: reward = -57.78, steps = 30 01:18:11 [INFO] train episode 35183: reward = -56.76, steps = 23 01:18:14 [INFO] train episode 35184: reward = -99.59, steps = 23 01:18:15 [INFO] train episode 35185: reward = -79.71, steps = 22 01:18:19 [INFO] train episode 35186: reward = -85.81, steps = 40 01:18:22 [INFO] train episode 35187: reward = -69.68, steps = 31 01:18:24 [INFO] train episode 35188: reward = -89.03, steps = 26 01:18:26 [INFO] train episode 35189: reward = -55.94, steps = 21 01:18:28 [INFO] train episode 35190: reward = -53.29, steps = 25 01:18:30 [INFO] train episode 35191: reward = -80.55, steps = 21 01:18:32 [INFO] train episode 35192: reward = -82.04, steps = 20 01:18:34 [INFO] train episode 35193: reward = -80.79, steps = 22 01:18:36 [INFO] train episode 35194: reward = -72.82, steps = 20 01:18:38 [INFO] train episode 35195: reward = -132.67, steps = 23 01:18:40 [INFO] train episode 35196: reward = -107.99, steps = 26 01:18:42 [INFO] train episode 35197: reward = -68.94, steps = 22 01:18:44 [INFO] train episode 35198: reward = -77.12, steps = 22 01:18:46 [INFO] train episode 35199: reward = -73.60, steps = 21 01:18:48 [INFO] train episode 35200: reward = -102.36, steps = 23 01:18:51 [INFO] train episode 35201: reward = -82.04, steps = 25 01:18:53 [INFO] train episode 35202: reward = -72.03, steps = 20 01:18:55 [INFO] train episode 35203: reward = -82.46, steps = 24 01:18:57 [INFO] train episode 35204: reward = -50.18, steps = 22 01:19:00 [INFO] train episode 35205: reward = -189.89, steps = 41 01:19:04 [INFO] train episode 35206: reward = -170.69, steps = 33 01:19:06 [INFO] train episode 35207: reward = -82.37, steps = 26 01:19:08 [INFO] train episode 35208: reward = -126.50, steps = 19 01:19:10 [INFO] train episode 35209: reward = -65.19, steps = 18 01:19:12 [INFO] train episode 35210: reward = -80.99, steps = 22 01:19:14 [INFO] train episode 35211: reward = -127.40, steps = 29 01:19:17 [INFO] train episode 35212: reward = -52.24, steps = 35 01:19:20 [INFO] train episode 35213: reward = -120.76, steps = 27 01:19:23 [INFO] train episode 35214: reward = -124.97, steps = 38 01:19:25 [INFO] train episode 35215: reward = -58.91, steps = 21 01:19:28 [INFO] train episode 35216: reward = -79.89, steps = 34 01:19:31 [INFO] train episode 35217: reward = -91.59, steps = 29 01:19:32 [INFO] train episode 35218: reward = -111.38, steps = 19 01:19:35 [INFO] train episode 35219: reward = -68.19, steps = 24 01:19:37 [INFO] train episode 35220: reward = -89.41, steps = 18 01:19:39 [INFO] train episode 35221: reward = -67.62, steps = 28 01:19:41 [INFO] train episode 35222: reward = -79.72, steps = 23 01:19:45 [INFO] train episode 35223: reward = -105.54, steps = 48 01:19:47 [INFO] train episode 35224: reward = -81.40, steps = 20 01:19:49 [INFO] train episode 35225: reward = -46.99, steps = 23 01:19:51 [INFO] train episode 35226: reward = -90.46, steps = 20 01:19:54 [INFO] train episode 35227: reward = -92.20, steps = 20 01:19:56 [INFO] train episode 35228: reward = -86.11, steps = 21 01:19:58 [INFO] train episode 35229: reward = -78.70, steps = 24 01:20:00 [INFO] train episode 35230: reward = -66.05, steps = 24 01:20:03 [INFO] train episode 35231: reward = -93.31, steps = 28 01:20:05 [INFO] train episode 35232: reward = -99.87, steps = 22 01:20:07 [INFO] train episode 35233: reward = -83.72, steps = 30 01:20:09 [INFO] train episode 35234: reward = -73.37, steps = 20 01:20:12 [INFO] train episode 35235: reward = -76.68, steps = 29 01:20:14 [INFO] train episode 35236: reward = -70.56, steps = 21 01:20:16 [INFO] train episode 35237: reward = -39.04, steps = 24 01:20:19 [INFO] train episode 35238: reward = -86.22, steps = 40 01:20:21 [INFO] train episode 35239: reward = -95.90, steps = 19 01:20:23 [INFO] train episode 35240: reward = -58.86, steps = 22 01:20:24 [INFO] train episode 35241: reward = -83.07, steps = 17 01:20:27 [INFO] train episode 35242: reward = -44.17, steps = 21 01:20:29 [INFO] train episode 35243: reward = -52.58, steps = 27 01:20:32 [INFO] train episode 35244: reward = -52.16, steps = 39 01:20:38 [INFO] train episode 35245: reward = -166.68, steps = 63 01:20:40 [INFO] train episode 35246: reward = -163.98, steps = 24 01:20:44 [INFO] train episode 35247: reward = -100.83, steps = 44 01:20:46 [INFO] train episode 35248: reward = -90.71, steps = 20 01:20:48 [INFO] train episode 35249: reward = -58.44, steps = 22 01:20:51 [INFO] train episode 35250: reward = -117.38, steps = 41 01:20:53 [INFO] train episode 35251: reward = -110.71, steps = 24 01:20:56 [INFO] train episode 35252: reward = -80.01, steps = 28 01:20:59 [INFO] train episode 35253: reward = -53.13, steps = 27 01:21:03 [INFO] train episode 35254: reward = -57.88, steps = 31 01:21:05 [INFO] train episode 35255: reward = -48.61, steps = 21 01:21:08 [INFO] train episode 35256: reward = -69.34, steps = 32 01:21:11 [INFO] train episode 35257: reward = -61.13, steps = 30 01:21:14 [INFO] train episode 35258: reward = -76.33, steps = 37 01:21:16 [INFO] train episode 35259: reward = -77.48, steps = 20 01:21:20 [INFO] train episode 35260: reward = -61.22, steps = 36 01:21:22 [INFO] train episode 35261: reward = -156.53, steps = 26 01:21:25 [INFO] train episode 35262: reward = -115.59, steps = 37 01:21:30 [INFO] train episode 35263: reward = -162.13, steps = 53 01:21:35 [INFO] train episode 35264: reward = -104.30, steps = 51 01:21:39 [INFO] train episode 35265: reward = -123.64, steps = 40 01:21:41 [INFO] train episode 35266: reward = -73.48, steps = 24 01:21:44 [INFO] train episode 35267: reward = -104.02, steps = 26 01:21:46 [INFO] train episode 35268: reward = -90.56, steps = 27 01:21:49 [INFO] train episode 35269: reward = -79.03, steps = 24 01:21:52 [INFO] train episode 35270: reward = -162.26, steps = 36 01:21:54 [INFO] train episode 35271: reward = -97.05, steps = 20 01:21:57 [INFO] train episode 35272: reward = -84.12, steps = 24 01:22:00 [INFO] train episode 35273: reward = -81.80, steps = 33 01:22:02 [INFO] train episode 35274: reward = -90.32, steps = 20 01:22:05 [INFO] train episode 35275: reward = -142.86, steps = 25 01:22:08 [INFO] train episode 35276: reward = -102.00, steps = 31 01:22:10 [INFO] train episode 35277: reward = -129.01, steps = 21 01:22:12 [INFO] train episode 35278: reward = -79.47, steps = 21 01:22:14 [INFO] train episode 35279: reward = -69.53, steps = 21 01:22:16 [INFO] train episode 35280: reward = -104.66, steps = 26 01:22:18 [INFO] train episode 35281: reward = -79.76, steps = 22 01:22:20 [INFO] train episode 35282: reward = -85.50, steps = 19 01:22:23 [INFO] train episode 35283: reward = -127.71, steps = 34 01:22:25 [INFO] train episode 35284: reward = -76.42, steps = 20 01:22:28 [INFO] train episode 35285: reward = -162.73, steps = 30 01:22:30 [INFO] train episode 35286: reward = -90.24, steps = 19 01:22:34 [INFO] train episode 35287: reward = -131.97, steps = 34 01:22:38 [INFO] train episode 35288: reward = -89.23, steps = 37 01:22:41 [INFO] train episode 35289: reward = -57.72, steps = 22 01:22:44 [INFO] train episode 35290: reward = -139.65, steps = 35 01:22:47 [INFO] train episode 35291: reward = -56.89, steps = 24 01:22:49 [INFO] train episode 35292: reward = -79.32, steps = 21 01:22:55 [INFO] train episode 35293: reward = -102.38, steps = 40 01:22:58 [INFO] train episode 35294: reward = -59.43, steps = 24 01:23:02 [INFO] train episode 35295: reward = -41.59, steps = 29 01:23:07 [INFO] train episode 35296: reward = -67.03, steps = 41 01:23:12 [INFO] train episode 35297: reward = -99.89, steps = 24 01:23:15 [INFO] train episode 35298: reward = -107.04, steps = 30 01:23:18 [INFO] train episode 35299: reward = -130.50, steps = 39 01:23:20 [INFO] train episode 35300: reward = -115.09, steps = 23 01:23:23 [INFO] train episode 35301: reward = -58.21, steps = 23 01:23:26 [INFO] train episode 35302: reward = -97.20, steps = 26 01:23:29 [INFO] train episode 35303: reward = -79.26, steps = 37 01:23:32 [INFO] train episode 35304: reward = -81.38, steps = 21 01:23:34 [INFO] train episode 35305: reward = -109.59, steps = 27 01:23:37 [INFO] train episode 35306: reward = -48.81, steps = 29 01:23:39 [INFO] train episode 35307: reward = -105.16, steps = 22 01:23:42 [INFO] train episode 35308: reward = -50.43, steps = 25 01:23:44 [INFO] train episode 35309: reward = -111.05, steps = 24 01:23:48 [INFO] train episode 35310: reward = -126.86, steps = 38 01:23:50 [INFO] train episode 35311: reward = -64.90, steps = 23 01:23:52 [INFO] train episode 35312: reward = -91.42, steps = 21 01:23:56 [INFO] train episode 35313: reward = -90.95, steps = 38 01:23:58 [INFO] train episode 35314: reward = -62.54, steps = 26 01:24:02 [INFO] train episode 35315: reward = -79.49, steps = 28 01:24:06 [INFO] train episode 35316: reward = -99.04, steps = 44 01:24:09 [INFO] train episode 35317: reward = -45.37, steps = 26 01:24:11 [INFO] train episode 35318: reward = -76.92, steps = 23 01:24:17 [INFO] train episode 35319: reward = -152.61, steps = 56 01:24:20 [INFO] train episode 35320: reward = -56.63, steps = 26 01:24:22 [INFO] train episode 35321: reward = -67.03, steps = 20 01:24:26 [INFO] train episode 35322: reward = -48.68, steps = 36 01:24:28 [INFO] train episode 35323: reward = -62.70, steps = 23 01:24:30 [INFO] train episode 35324: reward = -87.24, steps = 20 01:24:32 [INFO] train episode 35325: reward = -72.58, steps = 22 01:24:35 [INFO] train episode 35326: reward = -78.62, steps = 32 01:24:37 [INFO] train episode 35327: reward = -92.19, steps = 20 01:24:39 [INFO] train episode 35328: reward = -100.39, steps = 21 01:24:42 [INFO] train episode 35329: reward = -84.86, steps = 29 01:24:46 [INFO] train episode 35330: reward = -150.46, steps = 43 01:24:51 [INFO] train episode 35331: reward = -187.63, steps = 51 01:24:53 [INFO] train episode 35332: reward = -75.05, steps = 21 01:24:56 [INFO] train episode 35333: reward = -65.64, steps = 31 01:25:00 [INFO] train episode 35334: reward = -195.78, steps = 47 01:25:02 [INFO] train episode 35335: reward = -80.19, steps = 19 01:25:04 [INFO] train episode 35336: reward = -64.00, steps = 21 01:25:06 [INFO] train episode 35337: reward = -71.03, steps = 24 01:25:09 [INFO] train episode 35338: reward = -74.11, steps = 23 01:25:11 [INFO] train episode 35339: reward = -107.60, steps = 31 01:25:14 [INFO] train episode 35340: reward = -72.44, steps = 23 01:25:17 [INFO] train episode 35341: reward = -174.03, steps = 40 01:25:20 [INFO] train episode 35342: reward = -144.75, steps = 22 01:25:24 [INFO] train episode 35343: reward = -123.09, steps = 42 01:25:28 [INFO] train episode 35344: reward = -68.00, steps = 34 01:25:30 [INFO] train episode 35345: reward = -74.23, steps = 27 01:25:32 [INFO] train episode 35346: reward = -77.79, steps = 20 01:25:35 [INFO] train episode 35347: reward = -91.59, steps = 29 01:25:38 [INFO] train episode 35348: reward = -95.35, steps = 24 01:25:39 [INFO] train episode 35349: reward = -77.78, steps = 19 01:25:41 [INFO] train episode 35350: reward = -84.23, steps = 23 01:25:45 [INFO] train episode 35351: reward = -87.37, steps = 36 01:25:46 [INFO] train episode 35352: reward = -117.63, steps = 21 01:25:49 [INFO] train episode 35353: reward = -106.41, steps = 27 01:25:51 [INFO] train episode 35354: reward = -70.62, steps = 26 01:25:53 [INFO] train episode 35355: reward = -91.56, steps = 23 01:25:55 [INFO] train episode 35356: reward = -73.55, steps = 21 01:25:57 [INFO] train episode 35357: reward = -142.78, steps = 22 01:25:59 [INFO] train episode 35358: reward = -151.85, steps = 21 01:26:01 [INFO] train episode 35359: reward = -123.50, steps = 25 01:26:03 [INFO] train episode 35360: reward = -78.05, steps = 20 01:26:05 [INFO] train episode 35361: reward = -90.77, steps = 24 01:26:08 [INFO] train episode 35362: reward = -72.81, steps = 34 01:26:12 [INFO] train episode 35363: reward = -163.59, steps = 37 01:26:14 [INFO] train episode 35364: reward = -91.51, steps = 22 01:26:16 [INFO] train episode 35365: reward = -129.81, steps = 24 01:26:22 [INFO] train episode 35366: reward = -73.86, steps = 58 01:26:24 [INFO] train episode 35367: reward = -70.46, steps = 21 01:26:26 [INFO] train episode 35368: reward = -113.98, steps = 23 01:26:29 [INFO] train episode 35369: reward = -104.15, steps = 33 01:26:35 [INFO] train episode 35370: reward = -161.79, steps = 70 01:26:37 [INFO] train episode 35371: reward = -65.90, steps = 20 01:26:43 [INFO] train episode 35372: reward = -187.08, steps = 68 01:26:46 [INFO] train episode 35373: reward = -153.77, steps = 32 01:26:48 [INFO] train episode 35374: reward = -85.92, steps = 21 01:26:52 [INFO] train episode 35375: reward = -143.83, steps = 46 01:26:54 [INFO] train episode 35376: reward = -96.06, steps = 19 01:26:55 [INFO] train episode 35377: reward = -56.67, steps = 19 01:27:01 [INFO] train episode 35378: reward = -224.98, steps = 62 01:27:04 [INFO] train episode 35379: reward = -127.02, steps = 23 01:27:05 [INFO] train episode 35380: reward = -63.96, steps = 21 01:27:07 [INFO] train episode 35381: reward = -75.83, steps = 20 01:27:09 [INFO] train episode 35382: reward = -80.63, steps = 20 01:27:13 [INFO] train episode 35383: reward = -113.91, steps = 39 01:27:15 [INFO] train episode 35384: reward = -116.43, steps = 31 01:27:19 [INFO] train episode 35385: reward = -92.93, steps = 44 01:27:21 [INFO] train episode 35386: reward = -87.67, steps = 19 01:27:24 [INFO] train episode 35387: reward = -98.57, steps = 34 01:27:27 [INFO] train episode 35388: reward = -74.84, steps = 27 01:27:28 [INFO] train episode 35389: reward = -87.98, steps = 19 01:27:31 [INFO] train episode 35390: reward = -62.32, steps = 29 01:27:33 [INFO] train episode 35391: reward = -68.79, steps = 20 01:27:38 [INFO] train episode 35392: reward = -116.14, steps = 58 01:27:40 [INFO] train episode 35393: reward = -79.10, steps = 20 01:27:42 [INFO] train episode 35394: reward = -60.36, steps = 22 01:27:45 [INFO] train episode 35395: reward = -66.77, steps = 33 01:27:47 [INFO] train episode 35396: reward = -66.12, steps = 24 01:27:50 [INFO] train episode 35397: reward = -85.08, steps = 30 01:27:53 [INFO] train episode 35398: reward = -88.02, steps = 37 01:27:56 [INFO] train episode 35399: reward = -100.87, steps = 36 01:27:59 [INFO] train episode 35400: reward = -67.58, steps = 26 01:28:01 [INFO] train episode 35401: reward = -31.94, steps = 29 01:28:05 [INFO] train episode 35402: reward = -158.78, steps = 41 01:28:08 [INFO] train episode 35403: reward = -142.87, steps = 30 01:28:10 [INFO] train episode 35404: reward = -83.78, steps = 28 01:28:13 [INFO] train episode 35405: reward = -41.52, steps = 24 01:28:15 [INFO] train episode 35406: reward = -87.87, steps = 28 01:28:17 [INFO] train episode 35407: reward = -79.43, steps = 25 01:28:19 [INFO] train episode 35408: reward = -137.63, steps = 23 01:28:21 [INFO] train episode 35409: reward = -131.47, steps = 19 01:28:23 [INFO] train episode 35410: reward = -77.46, steps = 22 01:28:25 [INFO] train episode 35411: reward = -59.59, steps = 20 01:28:29 [INFO] train episode 35412: reward = -98.60, steps = 42 01:28:31 [INFO] train episode 35413: reward = -58.58, steps = 23 01:28:33 [INFO] train episode 35414: reward = -64.46, steps = 26 01:28:35 [INFO] train episode 35415: reward = -141.20, steps = 22 01:28:37 [INFO] train episode 35416: reward = -93.34, steps = 22 01:28:40 [INFO] train episode 35417: reward = -83.52, steps = 26 01:28:42 [INFO] train episode 35418: reward = -98.07, steps = 28 01:28:44 [INFO] train episode 35419: reward = -111.55, steps = 21 01:28:46 [INFO] train episode 35420: reward = -83.99, steps = 20 01:28:48 [INFO] train episode 35421: reward = -107.68, steps = 26 01:28:50 [INFO] train episode 35422: reward = -92.33, steps = 23 01:28:53 [INFO] train episode 35423: reward = -127.48, steps = 32 01:28:55 [INFO] train episode 35424: reward = -111.91, steps = 19 01:28:57 [INFO] train episode 35425: reward = -47.69, steps = 20 01:29:00 [INFO] train episode 35426: reward = -73.27, steps = 28 01:29:01 [INFO] train episode 35427: reward = -67.03, steps = 19 01:29:04 [INFO] train episode 35428: reward = -75.08, steps = 21 01:29:06 [INFO] train episode 35429: reward = -110.07, steps = 19 01:29:08 [INFO] train episode 35430: reward = -56.45, steps = 24 01:29:10 [INFO] train episode 35431: reward = -69.36, steps = 20 01:29:12 [INFO] train episode 35432: reward = -64.41, steps = 24 01:29:14 [INFO] train episode 35433: reward = -66.57, steps = 23 01:29:16 [INFO] train episode 35434: reward = -94.33, steps = 21 01:29:19 [INFO] train episode 35435: reward = -61.20, steps = 26 01:29:21 [INFO] train episode 35436: reward = -57.29, steps = 22 01:29:23 [INFO] train episode 35437: reward = -62.91, steps = 20 01:29:25 [INFO] train episode 35438: reward = -97.93, steps = 21 01:29:28 [INFO] train episode 35439: reward = -106.90, steps = 31 01:29:30 [INFO] train episode 35440: reward = -95.44, steps = 26 01:29:33 [INFO] train episode 35441: reward = -104.32, steps = 25 01:29:35 [INFO] train episode 35442: reward = -79.48, steps = 26 01:29:37 [INFO] train episode 35443: reward = -80.43, steps = 22 01:29:40 [INFO] train episode 35444: reward = -76.96, steps = 27 01:29:42 [INFO] train episode 35445: reward = -92.23, steps = 22 01:29:44 [INFO] train episode 35446: reward = -80.47, steps = 22 01:29:46 [INFO] train episode 35447: reward = -76.24, steps = 24 01:29:49 [INFO] train episode 35448: reward = -91.96, steps = 27 01:29:51 [INFO] train episode 35449: reward = -149.15, steps = 30 01:29:55 [INFO] train episode 35450: reward = -176.95, steps = 46 01:29:57 [INFO] train episode 35451: reward = -69.40, steps = 20 01:30:00 [INFO] train episode 35452: reward = -107.76, steps = 34 01:30:03 [INFO] train episode 35453: reward = -91.79, steps = 28 01:30:05 [INFO] train episode 35454: reward = -66.21, steps = 25 01:30:09 [INFO] train episode 35455: reward = -115.92, steps = 43 01:30:12 [INFO] train episode 35456: reward = -84.06, steps = 31 01:30:14 [INFO] train episode 35457: reward = -67.36, steps = 25 01:30:16 [INFO] train episode 35458: reward = -54.01, steps = 21 01:30:18 [INFO] train episode 35459: reward = -117.00, steps = 26 01:30:21 [INFO] train episode 35460: reward = -57.49, steps = 26 01:30:23 [INFO] train episode 35461: reward = -64.59, steps = 20 01:30:25 [INFO] train episode 35462: reward = -49.91, steps = 22 01:30:27 [INFO] train episode 35463: reward = -97.78, steps = 24 01:30:29 [INFO] train episode 35464: reward = -81.16, steps = 21 01:30:31 [INFO] train episode 35465: reward = -61.87, steps = 21 01:30:33 [INFO] train episode 35466: reward = -93.13, steps = 20 01:30:35 [INFO] train episode 35467: reward = -133.58, steps = 29 01:30:37 [INFO] train episode 35468: reward = -110.19, steps = 20 01:30:40 [INFO] train episode 35469: reward = -52.53, steps = 30 01:30:42 [INFO] train episode 35470: reward = -101.11, steps = 21 01:30:44 [INFO] train episode 35471: reward = -113.55, steps = 20 01:30:46 [INFO] train episode 35472: reward = -74.35, steps = 22 01:30:48 [INFO] train episode 35473: reward = -88.80, steps = 25 01:30:51 [INFO] train episode 35474: reward = -60.40, steps = 26 01:30:54 [INFO] train episode 35475: reward = -129.69, steps = 31 01:30:56 [INFO] train episode 35476: reward = -86.10, steps = 21 01:30:58 [INFO] train episode 35477: reward = -132.21, steps = 25 01:31:00 [INFO] train episode 35478: reward = -77.17, steps = 20 01:31:02 [INFO] train episode 35479: reward = -93.44, steps = 28 01:31:04 [INFO] train episode 35480: reward = -52.94, steps = 22 01:31:06 [INFO] train episode 35481: reward = -107.08, steps = 19 01:31:08 [INFO] train episode 35482: reward = -82.21, steps = 26 01:31:13 [INFO] train episode 35483: reward = -132.36, steps = 44 01:31:17 [INFO] train episode 35484: reward = -118.39, steps = 50 01:31:19 [INFO] train episode 35485: reward = -58.44, steps = 20 01:31:21 [INFO] train episode 35486: reward = -95.62, steps = 25 01:31:23 [INFO] train episode 35487: reward = -97.28, steps = 23 01:31:28 [INFO] train episode 35488: reward = -147.40, steps = 52 01:31:30 [INFO] train episode 35489: reward = -79.12, steps = 20 01:31:32 [INFO] train episode 35490: reward = -72.40, steps = 25 01:31:34 [INFO] train episode 35491: reward = -166.82, steps = 22 01:31:36 [INFO] train episode 35492: reward = -87.74, steps = 20 01:31:38 [INFO] train episode 35493: reward = -77.36, steps = 27 01:31:41 [INFO] train episode 35494: reward = -55.18, steps = 27 01:31:44 [INFO] train episode 35495: reward = -86.77, steps = 36 01:31:46 [INFO] train episode 35496: reward = -96.27, steps = 22 01:31:50 [INFO] train episode 35497: reward = -75.08, steps = 41 01:31:51 [INFO] train episode 35498: reward = -88.24, steps = 18 01:31:54 [INFO] train episode 35499: reward = -107.34, steps = 33 01:31:56 [INFO] train episode 35500: reward = -82.22, steps = 20 01:32:00 [INFO] train episode 35501: reward = -74.01, steps = 40 01:32:02 [INFO] train episode 35502: reward = -92.20, steps = 23 01:32:04 [INFO] train episode 35503: reward = -105.59, steps = 20 01:32:06 [INFO] train episode 35504: reward = -54.62, steps = 27 01:32:08 [INFO] train episode 35505: reward = -95.66, steps = 20 01:32:10 [INFO] train episode 35506: reward = -93.49, steps = 22 01:32:12 [INFO] train episode 35507: reward = -63.10, steps = 21 01:32:15 [INFO] train episode 35508: reward = -136.95, steps = 33 01:32:17 [INFO] train episode 35509: reward = -77.82, steps = 21 01:32:20 [INFO] train episode 35510: reward = -63.73, steps = 27 01:32:23 [INFO] train episode 35511: reward = -89.03, steps = 30 01:32:25 [INFO] train episode 35512: reward = -54.99, steps = 25 01:32:27 [INFO] train episode 35513: reward = -102.84, steps = 20 01:32:29 [INFO] train episode 35514: reward = -76.78, steps = 18 01:32:31 [INFO] train episode 35515: reward = -84.03, steps = 29 01:32:37 [INFO] train episode 35516: reward = -146.70, steps = 53 01:32:39 [INFO] train episode 35517: reward = -76.38, steps = 23 01:32:40 [INFO] train episode 35518: reward = -108.00, steps = 20 01:32:43 [INFO] train episode 35519: reward = -135.46, steps = 30 01:32:45 [INFO] train episode 35520: reward = -72.24, steps = 22 01:32:47 [INFO] train episode 35521: reward = -116.91, steps = 23 01:32:51 [INFO] train episode 35522: reward = -87.31, steps = 39 01:32:53 [INFO] train episode 35523: reward = -88.36, steps = 23 01:32:56 [INFO] train episode 35524: reward = -128.93, steps = 31 01:33:01 [INFO] train episode 35525: reward = -169.03, steps = 57 01:33:03 [INFO] train episode 35526: reward = -117.63, steps = 20 01:33:05 [INFO] train episode 35527: reward = -118.29, steps = 19 01:33:07 [INFO] train episode 35528: reward = -75.26, steps = 18 01:33:08 [INFO] train episode 35529: reward = -78.03, steps = 19 01:33:11 [INFO] train episode 35530: reward = -113.30, steps = 33 01:33:14 [INFO] train episode 35531: reward = -126.59, steps = 27 01:33:15 [INFO] train episode 35532: reward = -82.08, steps = 12 01:33:18 [INFO] train episode 35533: reward = -67.74, steps = 34 01:33:20 [INFO] train episode 35534: reward = -67.86, steps = 24 01:33:22 [INFO] train episode 35535: reward = -84.05, steps = 23 01:33:25 [INFO] train episode 35536: reward = -147.83, steps = 23 01:33:27 [INFO] train episode 35537: reward = -123.18, steps = 29 01:33:29 [INFO] train episode 35538: reward = -70.03, steps = 20 01:33:31 [INFO] train episode 35539: reward = -72.40, steps = 20 01:33:33 [INFO] train episode 35540: reward = -71.33, steps = 21 01:33:35 [INFO] train episode 35541: reward = -88.27, steps = 21 01:33:37 [INFO] train episode 35542: reward = -137.24, steps = 27 01:33:40 [INFO] train episode 35543: reward = -97.24, steps = 29 01:33:42 [INFO] train episode 35544: reward = -77.04, steps = 24 01:33:44 [INFO] train episode 35545: reward = -97.22, steps = 23 01:33:47 [INFO] train episode 35546: reward = -128.16, steps = 28 01:33:49 [INFO] train episode 35547: reward = -113.25, steps = 28 01:33:51 [INFO] train episode 35548: reward = -83.35, steps = 26 01:33:54 [INFO] train episode 35549: reward = -73.87, steps = 28 01:33:58 [INFO] train episode 35550: reward = -154.13, steps = 44 01:34:01 [INFO] train episode 35551: reward = -119.36, steps = 30 01:34:03 [INFO] train episode 35552: reward = -106.04, steps = 23 01:34:05 [INFO] train episode 35553: reward = -85.34, steps = 28 01:34:08 [INFO] train episode 35554: reward = -93.62, steps = 30 01:34:10 [INFO] train episode 35555: reward = -69.01, steps = 24 01:34:13 [INFO] train episode 35556: reward = -136.37, steps = 28 01:34:16 [INFO] train episode 35557: reward = -92.38, steps = 29 01:34:17 [INFO] train episode 35558: reward = -109.19, steps = 20 01:34:20 [INFO] train episode 35559: reward = -107.29, steps = 30 01:34:22 [INFO] train episode 35560: reward = -70.70, steps = 27 01:34:25 [INFO] train episode 35561: reward = -52.59, steps = 28 01:34:27 [INFO] train episode 35562: reward = -105.10, steps = 24 01:34:31 [INFO] train episode 35563: reward = -135.45, steps = 43 01:34:33 [INFO] train episode 35564: reward = -127.56, steps = 21 01:34:36 [INFO] train episode 35565: reward = -57.95, steps = 30 01:34:38 [INFO] train episode 35566: reward = -96.09, steps = 25 01:34:40 [INFO] train episode 35567: reward = -109.57, steps = 22 01:34:42 [INFO] train episode 35568: reward = -67.78, steps = 27 01:34:45 [INFO] train episode 35569: reward = -74.42, steps = 31 01:34:47 [INFO] train episode 35570: reward = -61.05, steps = 19 01:34:50 [INFO] train episode 35571: reward = -105.90, steps = 37 01:34:53 [INFO] train episode 35572: reward = -98.01, steps = 27 01:34:55 [INFO] train episode 35573: reward = -57.42, steps = 22 01:34:57 [INFO] train episode 35574: reward = -88.67, steps = 19 01:34:59 [INFO] train episode 35575: reward = -132.93, steps = 27 01:35:02 [INFO] train episode 35576: reward = -79.70, steps = 25 01:35:05 [INFO] train episode 35577: reward = -90.43, steps = 34 01:35:06 [INFO] train episode 35578: reward = -77.42, steps = 20 01:35:09 [INFO] train episode 35579: reward = -91.59, steps = 33 01:35:12 [INFO] train episode 35580: reward = -96.31, steps = 28 01:35:14 [INFO] train episode 35581: reward = -98.12, steps = 21 01:35:16 [INFO] train episode 35582: reward = -136.35, steps = 19 01:35:19 [INFO] train episode 35583: reward = -55.51, steps = 30 01:35:22 [INFO] train episode 35584: reward = -106.58, steps = 35 01:35:25 [INFO] train episode 35585: reward = -85.99, steps = 28 01:35:27 [INFO] train episode 35586: reward = -118.53, steps = 21 01:35:29 [INFO] train episode 35587: reward = -133.59, steps = 29 01:35:32 [INFO] train episode 35588: reward = -48.31, steps = 26 01:35:34 [INFO] train episode 35589: reward = -106.06, steps = 25 01:35:36 [INFO] train episode 35590: reward = -103.15, steps = 19 01:35:38 [INFO] train episode 35591: reward = -83.49, steps = 21 01:35:42 [INFO] train episode 35592: reward = -96.81, steps = 40 01:35:47 [INFO] train episode 35593: reward = -185.63, steps = 66 01:35:50 [INFO] train episode 35594: reward = -92.80, steps = 26 01:35:52 [INFO] train episode 35595: reward = -79.84, steps = 24 01:35:54 [INFO] train episode 35596: reward = -78.59, steps = 23 01:35:56 [INFO] train episode 35597: reward = -77.77, steps = 21 01:35:58 [INFO] train episode 35598: reward = -76.30, steps = 23 01:36:00 [INFO] train episode 35599: reward = -93.89, steps = 21 01:36:05 [INFO] train episode 35600: reward = -150.54, steps = 62 01:36:08 [INFO] train episode 35601: reward = -81.03, steps = 20 01:36:09 [INFO] train episode 35602: reward = -95.30, steps = 17 01:36:11 [INFO] train episode 35603: reward = -63.75, steps = 18 01:36:12 [INFO] train episode 35604: reward = -75.05, steps = 18 01:36:14 [INFO] train episode 35605: reward = -82.05, steps = 19 01:36:17 [INFO] train episode 35606: reward = -51.43, steps = 27 01:36:18 [INFO] train episode 35607: reward = -75.90, steps = 22 01:36:20 [INFO] train episode 35608: reward = -58.59, steps = 22 01:36:23 [INFO] train episode 35609: reward = -69.19, steps = 28 01:36:26 [INFO] train episode 35610: reward = -69.77, steps = 27 01:36:29 [INFO] train episode 35611: reward = -117.18, steps = 36 01:36:31 [INFO] train episode 35612: reward = -78.12, steps = 24 01:36:33 [INFO] train episode 35613: reward = -58.34, steps = 21 01:36:35 [INFO] train episode 35614: reward = -83.78, steps = 24 01:36:37 [INFO] train episode 35615: reward = -80.37, steps = 21 01:36:39 [INFO] train episode 35616: reward = -93.88, steps = 21 01:36:42 [INFO] train episode 35617: reward = -105.17, steps = 29 01:36:44 [INFO] train episode 35618: reward = -130.66, steps = 19 01:36:46 [INFO] train episode 35619: reward = -112.21, steps = 26 01:36:48 [INFO] train episode 35620: reward = -70.54, steps = 23 01:36:51 [INFO] train episode 35621: reward = -76.50, steps = 31 01:36:54 [INFO] train episode 35622: reward = -71.88, steps = 38 01:36:56 [INFO] train episode 35623: reward = -67.42, steps = 21 01:36:58 [INFO] train episode 35624: reward = -69.94, steps = 22 01:37:01 [INFO] train episode 35625: reward = -74.73, steps = 30 01:37:03 [INFO] train episode 35626: reward = -49.13, steps = 22 01:37:05 [INFO] train episode 35627: reward = -85.86, steps = 19 01:37:07 [INFO] train episode 35628: reward = -113.14, steps = 25 01:37:09 [INFO] train episode 35629: reward = -81.12, steps = 19 01:37:11 [INFO] train episode 35630: reward = -111.61, steps = 20 01:37:12 [INFO] train episode 35631: reward = -107.73, steps = 18 01:37:15 [INFO] train episode 35632: reward = -97.07, steps = 30 01:37:21 [INFO] train episode 35633: reward = -176.92, steps = 64 01:37:25 [INFO] train episode 35634: reward = -144.07, steps = 43 01:37:29 [INFO] train episode 35635: reward = -141.06, steps = 54 01:37:32 [INFO] train episode 35636: reward = -94.49, steps = 25 01:37:35 [INFO] train episode 35637: reward = -120.99, steps = 39 01:37:38 [INFO] train episode 35638: reward = -118.21, steps = 31 01:37:42 [INFO] train episode 35639: reward = -169.63, steps = 45 01:37:44 [INFO] train episode 35640: reward = -61.50, steps = 24 01:37:47 [INFO] train episode 35641: reward = -89.31, steps = 24 01:37:49 [INFO] train episode 35642: reward = -115.52, steps = 24 01:37:51 [INFO] train episode 35643: reward = -75.44, steps = 30 01:37:54 [INFO] train episode 35644: reward = -110.15, steps = 33 01:37:56 [INFO] train episode 35645: reward = -99.92, steps = 21 01:37:59 [INFO] train episode 35646: reward = -123.09, steps = 33 01:38:02 [INFO] train episode 35647: reward = -108.66, steps = 30 01:38:05 [INFO] train episode 35648: reward = -128.20, steps = 28 01:38:07 [INFO] train episode 35649: reward = -68.63, steps = 24 01:38:09 [INFO] train episode 35650: reward = -79.78, steps = 20 01:38:11 [INFO] train episode 35651: reward = -68.41, steps = 25 01:38:13 [INFO] train episode 35652: reward = -69.48, steps = 19 01:38:16 [INFO] train episode 35653: reward = -65.76, steps = 31 01:38:18 [INFO] train episode 35654: reward = -77.49, steps = 25 01:38:21 [INFO] train episode 35655: reward = -78.21, steps = 21 01:38:23 [INFO] train episode 35656: reward = -79.57, steps = 21 01:38:26 [INFO] train episode 35657: reward = -160.17, steps = 38 01:38:28 [INFO] train episode 35658: reward = -61.40, steps = 27 01:38:30 [INFO] train episode 35659: reward = -124.21, steps = 20 01:38:32 [INFO] train episode 35660: reward = -79.39, steps = 18 01:38:34 [INFO] train episode 35661: reward = -99.06, steps = 24 01:38:36 [INFO] train episode 35662: reward = -85.51, steps = 24 01:38:39 [INFO] train episode 35663: reward = -119.97, steps = 31 01:38:41 [INFO] train episode 35664: reward = -74.11, steps = 18 01:38:43 [INFO] train episode 35665: reward = -95.46, steps = 21 01:38:45 [INFO] train episode 35666: reward = -104.02, steps = 30 01:38:48 [INFO] train episode 35667: reward = -71.03, steps = 31 01:38:50 [INFO] train episode 35668: reward = -59.92, steps = 19 01:38:51 [INFO] train episode 35669: reward = -125.41, steps = 18 01:38:54 [INFO] train episode 35670: reward = -64.28, steps = 27 01:38:56 [INFO] train episode 35671: reward = -109.98, steps = 25 01:38:58 [INFO] train episode 35672: reward = -57.46, steps = 22 01:39:01 [INFO] train episode 35673: reward = -146.71, steps = 24 01:39:03 [INFO] train episode 35674: reward = -98.37, steps = 30 01:39:06 [INFO] train episode 35675: reward = -70.13, steps = 25 01:39:08 [INFO] train episode 35676: reward = -143.61, steps = 29 01:39:12 [INFO] train episode 35677: reward = -132.86, steps = 36 01:39:14 [INFO] train episode 35678: reward = -76.61, steps = 21 01:39:16 [INFO] train episode 35679: reward = -65.83, steps = 21 01:39:18 [INFO] train episode 35680: reward = -63.93, steps = 29 01:39:21 [INFO] train episode 35681: reward = -87.47, steps = 36 01:39:24 [INFO] train episode 35682: reward = -145.08, steps = 26 01:39:26 [INFO] train episode 35683: reward = -95.62, steps = 19 01:39:28 [INFO] train episode 35684: reward = -88.61, steps = 27 01:39:30 [INFO] train episode 35685: reward = -151.25, steps = 20 01:39:32 [INFO] train episode 35686: reward = -89.51, steps = 20 01:39:34 [INFO] train episode 35687: reward = -69.23, steps = 22 01:39:36 [INFO] train episode 35688: reward = -58.46, steps = 22 01:39:39 [INFO] train episode 35689: reward = -94.71, steps = 35 01:39:41 [INFO] train episode 35690: reward = -124.31, steps = 29 01:39:45 [INFO] train episode 35691: reward = -221.23, steps = 36 01:39:47 [INFO] train episode 35692: reward = -86.54, steps = 28 01:39:49 [INFO] train episode 35693: reward = -63.55, steps = 20 01:39:52 [INFO] train episode 35694: reward = -105.31, steps = 35 01:39:56 [INFO] train episode 35695: reward = -96.35, steps = 44 01:39:59 [INFO] train episode 35696: reward = -69.98, steps = 29 01:40:01 [INFO] train episode 35697: reward = -125.46, steps = 28 01:40:04 [INFO] train episode 35698: reward = -117.50, steps = 27 01:40:05 [INFO] train episode 35699: reward = -80.51, steps = 19 01:40:07 [INFO] train episode 35700: reward = -59.77, steps = 19 01:40:09 [INFO] train episode 35701: reward = -55.27, steps = 24 01:40:11 [INFO] train episode 35702: reward = -94.63, steps = 20 01:40:13 [INFO] train episode 35703: reward = -91.48, steps = 26 01:40:17 [INFO] train episode 35704: reward = -110.96, steps = 36 01:40:19 [INFO] train episode 35705: reward = -82.04, steps = 20 01:40:21 [INFO] train episode 35706: reward = -108.75, steps = 26 01:40:23 [INFO] train episode 35707: reward = -91.12, steps = 20 01:40:25 [INFO] train episode 35708: reward = -63.40, steps = 24 01:40:27 [INFO] train episode 35709: reward = -85.50, steps = 21 01:40:29 [INFO] train episode 35710: reward = -84.79, steps = 20 01:40:31 [INFO] train episode 35711: reward = -96.26, steps = 22 01:40:33 [INFO] train episode 35712: reward = -166.00, steps = 19 01:40:36 [INFO] train episode 35713: reward = -109.74, steps = 41 01:40:38 [INFO] train episode 35714: reward = -67.46, steps = 20 01:40:40 [INFO] train episode 35715: reward = -84.10, steps = 19 01:40:42 [INFO] train episode 35716: reward = -89.40, steps = 20 01:40:45 [INFO] train episode 35717: reward = -96.24, steps = 41 01:40:49 [INFO] train episode 35718: reward = -113.73, steps = 33 01:40:51 [INFO] train episode 35719: reward = -105.39, steps = 27 01:40:53 [INFO] train episode 35720: reward = -59.19, steps = 27 01:40:55 [INFO] train episode 35721: reward = -75.46, steps = 20 01:40:57 [INFO] train episode 35722: reward = -94.40, steps = 25 01:41:01 [INFO] train episode 35723: reward = -120.66, steps = 41 01:41:04 [INFO] train episode 35724: reward = -94.38, steps = 26 01:41:06 [INFO] train episode 35725: reward = -106.55, steps = 23 01:41:08 [INFO] train episode 35726: reward = -82.76, steps = 26 01:41:11 [INFO] train episode 35727: reward = -91.63, steps = 26 01:41:15 [INFO] train episode 35728: reward = -83.90, steps = 34 01:41:17 [INFO] train episode 35729: reward = -74.88, steps = 23 01:41:19 [INFO] train episode 35730: reward = -71.37, steps = 22 01:41:21 [INFO] train episode 35731: reward = -88.08, steps = 31 01:41:25 [INFO] train episode 35732: reward = -83.52, steps = 39 01:41:27 [INFO] train episode 35733: reward = -94.56, steps = 21 01:41:30 [INFO] train episode 35734: reward = -110.76, steps = 29 01:41:33 [INFO] train episode 35735: reward = -105.05, steps = 43 01:41:36 [INFO] train episode 35736: reward = -191.40, steps = 27 01:41:38 [INFO] train episode 35737: reward = -62.29, steps = 24 01:41:40 [INFO] train episode 35738: reward = -90.33, steps = 23 01:41:43 [INFO] train episode 35739: reward = -84.36, steps = 27 01:41:45 [INFO] train episode 35740: reward = -94.67, steps = 27 01:41:47 [INFO] train episode 35741: reward = -69.38, steps = 19 01:41:48 [INFO] train episode 35742: reward = -111.47, steps = 17 01:41:50 [INFO] train episode 35743: reward = -88.68, steps = 18 01:41:52 [INFO] train episode 35744: reward = -84.00, steps = 21 01:41:54 [INFO] train episode 35745: reward = -82.87, steps = 19 01:41:56 [INFO] train episode 35746: reward = -89.10, steps = 21 01:41:58 [INFO] train episode 35747: reward = -112.67, steps = 20 01:41:59 [INFO] train episode 35748: reward = -100.25, steps = 19 01:42:01 [INFO] train episode 35749: reward = -92.56, steps = 20 01:42:03 [INFO] train episode 35750: reward = -63.87, steps = 20 01:42:05 [INFO] train episode 35751: reward = -63.25, steps = 27 01:42:07 [INFO] train episode 35752: reward = -66.12, steps = 16 01:42:09 [INFO] train episode 35753: reward = -53.07, steps = 21 01:42:12 [INFO] train episode 35754: reward = -133.05, steps = 32 01:42:14 [INFO] train episode 35755: reward = -69.79, steps = 21 01:42:16 [INFO] train episode 35756: reward = -72.95, steps = 29 01:42:19 [INFO] train episode 35757: reward = -76.99, steps = 28 01:42:22 [INFO] train episode 35758: reward = -109.15, steps = 34 01:42:23 [INFO] train episode 35759: reward = -73.86, steps = 20 01:42:26 [INFO] train episode 35760: reward = -87.21, steps = 24 01:42:28 [INFO] train episode 35761: reward = -73.95, steps = 22 01:42:31 [INFO] train episode 35762: reward = -99.78, steps = 33 01:42:33 [INFO] train episode 35763: reward = -107.22, steps = 23 01:42:35 [INFO] train episode 35764: reward = -84.94, steps = 23 01:42:37 [INFO] train episode 35765: reward = -79.99, steps = 20 01:42:39 [INFO] train episode 35766: reward = -113.40, steps = 25 01:42:43 [INFO] train episode 35767: reward = -69.92, steps = 40 01:42:46 [INFO] train episode 35768: reward = -99.85, steps = 37 01:42:49 [INFO] train episode 35769: reward = -91.32, steps = 29 01:42:52 [INFO] train episode 35770: reward = -136.42, steps = 34 01:42:54 [INFO] train episode 35771: reward = -116.69, steps = 22 01:42:56 [INFO] train episode 35772: reward = -90.53, steps = 24 01:43:00 [INFO] train episode 35773: reward = -80.95, steps = 44 01:43:02 [INFO] train episode 35774: reward = -64.86, steps = 23 01:43:04 [INFO] train episode 35775: reward = -69.19, steps = 21 01:43:06 [INFO] train episode 35776: reward = -71.40, steps = 23 01:43:08 [INFO] train episode 35777: reward = -96.49, steps = 21 01:43:12 [INFO] train episode 35778: reward = -193.38, steps = 47 01:43:16 [INFO] train episode 35779: reward = -95.98, steps = 37 01:43:21 [INFO] train episode 35780: reward = -166.73, steps = 56 01:43:23 [INFO] train episode 35781: reward = -83.23, steps = 24 01:43:25 [INFO] train episode 35782: reward = -81.22, steps = 20 01:43:26 [INFO] train episode 35783: reward = -100.47, steps = 20 01:43:30 [INFO] train episode 35784: reward = -71.45, steps = 41 01:43:32 [INFO] train episode 35785: reward = -86.01, steps = 21 01:43:34 [INFO] train episode 35786: reward = -146.87, steps = 19 01:43:36 [INFO] train episode 35787: reward = -77.34, steps = 24 01:43:39 [INFO] train episode 35788: reward = -89.63, steps = 31 01:43:41 [INFO] train episode 35789: reward = -107.21, steps = 28 01:43:43 [INFO] train episode 35790: reward = -60.90, steps = 20 01:43:46 [INFO] train episode 35791: reward = -92.66, steps = 41 01:43:49 [INFO] train episode 35792: reward = -43.65, steps = 24 01:43:51 [INFO] train episode 35793: reward = -45.84, steps = 19 01:43:53 [INFO] train episode 35794: reward = -69.52, steps = 26 01:43:55 [INFO] train episode 35795: reward = -64.35, steps = 21 01:43:57 [INFO] train episode 35796: reward = -75.25, steps = 21 01:43:59 [INFO] train episode 35797: reward = -111.97, steps = 25 01:44:01 [INFO] train episode 35798: reward = -85.90, steps = 22 01:44:04 [INFO] train episode 35799: reward = -98.62, steps = 31 01:44:06 [INFO] train episode 35800: reward = -113.54, steps = 23 01:44:11 [INFO] train episode 35801: reward = -139.06, steps = 43 01:44:13 [INFO] train episode 35802: reward = -79.09, steps = 26 01:44:15 [INFO] train episode 35803: reward = -113.82, steps = 21 01:44:17 [INFO] train episode 35804: reward = -130.30, steps = 28 01:44:20 [INFO] train episode 35805: reward = -90.98, steps = 30 01:44:23 [INFO] train episode 35806: reward = -157.86, steps = 34 01:44:26 [INFO] train episode 35807: reward = -107.99, steps = 36 01:44:28 [INFO] train episode 35808: reward = -89.16, steps = 22 01:44:31 [INFO] train episode 35809: reward = -122.30, steps = 25 01:44:34 [INFO] train episode 35810: reward = -90.84, steps = 41 01:44:36 [INFO] train episode 35811: reward = -87.81, steps = 26 01:44:39 [INFO] train episode 35812: reward = -76.44, steps = 31 01:44:41 [INFO] train episode 35813: reward = -114.81, steps = 17 01:44:43 [INFO] train episode 35814: reward = -128.15, steps = 21 01:44:45 [INFO] train episode 35815: reward = -89.92, steps = 19 01:44:46 [INFO] train episode 35816: reward = -86.19, steps = 21 01:44:50 [INFO] train episode 35817: reward = -99.22, steps = 43 01:44:54 [INFO] train episode 35818: reward = -162.38, steps = 44 01:44:56 [INFO] train episode 35819: reward = -85.23, steps = 19 01:44:59 [INFO] train episode 35820: reward = -107.55, steps = 26 01:45:04 [INFO] train episode 35821: reward = -140.35, steps = 51 01:45:05 [INFO] train episode 35822: reward = -66.08, steps = 21 01:45:08 [INFO] train episode 35823: reward = -66.09, steps = 25 01:45:09 [INFO] train episode 35824: reward = -107.02, steps = 19 01:45:12 [INFO] train episode 35825: reward = -97.48, steps = 20 01:45:14 [INFO] train episode 35826: reward = -83.44, steps = 24 01:45:19 [INFO] train episode 35827: reward = -169.99, steps = 56 01:45:20 [INFO] train episode 35828: reward = -110.82, steps = 20 01:45:23 [INFO] train episode 35829: reward = -81.79, steps = 35 01:45:26 [INFO] train episode 35830: reward = -192.10, steps = 30 01:45:28 [INFO] train episode 35831: reward = -146.43, steps = 22 01:45:32 [INFO] train episode 35832: reward = -58.39, steps = 41 01:45:34 [INFO] train episode 35833: reward = -123.66, steps = 21 01:45:36 [INFO] train episode 35834: reward = -74.82, steps = 23 01:45:38 [INFO] train episode 35835: reward = -64.47, steps = 22 01:45:41 [INFO] train episode 35836: reward = -119.48, steps = 32 01:45:43 [INFO] train episode 35837: reward = -83.85, steps = 22 01:45:45 [INFO] train episode 35838: reward = -83.78, steps = 23 01:45:51 [INFO] train episode 35839: reward = -244.84, steps = 70 01:45:53 [INFO] train episode 35840: reward = -150.54, steps = 23 01:45:55 [INFO] train episode 35841: reward = -147.64, steps = 17 01:45:59 [INFO] train episode 35842: reward = -116.06, steps = 46 01:46:01 [INFO] train episode 35843: reward = -64.44, steps = 21 01:46:03 [INFO] train episode 35844: reward = -80.67, steps = 22 01:46:05 [INFO] train episode 35845: reward = -90.09, steps = 19 01:46:07 [INFO] train episode 35846: reward = -102.49, steps = 19 01:46:09 [INFO] train episode 35847: reward = -136.30, steps = 25 01:46:11 [INFO] train episode 35848: reward = -70.00, steps = 28 01:46:13 [INFO] train episode 35849: reward = -107.15, steps = 20 01:46:16 [INFO] train episode 35850: reward = -83.86, steps = 33 01:46:18 [INFO] train episode 35851: reward = -44.74, steps = 20 01:46:20 [INFO] train episode 35852: reward = -57.23, steps = 23 01:46:23 [INFO] train episode 35853: reward = -83.82, steps = 32 01:46:25 [INFO] train episode 35854: reward = -77.80, steps = 20 01:46:27 [INFO] train episode 35855: reward = -116.95, steps = 26 01:46:30 [INFO] train episode 35856: reward = -58.95, steps = 37 01:46:32 [INFO] train episode 35857: reward = -94.00, steps = 20 01:46:36 [INFO] train episode 35858: reward = -247.06, steps = 43 01:46:39 [INFO] train episode 35859: reward = -111.08, steps = 29 01:46:40 [INFO] train episode 35860: reward = -101.44, steps = 18 01:46:42 [INFO] train episode 35861: reward = -57.01, steps = 22 01:46:44 [INFO] train episode 35862: reward = -64.87, steps = 26 01:46:47 [INFO] train episode 35863: reward = -105.06, steps = 26 01:46:50 [INFO] train episode 35864: reward = -128.29, steps = 31 01:46:54 [INFO] train episode 35865: reward = -88.92, steps = 44 01:46:56 [INFO] train episode 35866: reward = -48.49, steps = 22 01:46:58 [INFO] train episode 35867: reward = -92.41, steps = 24 01:47:00 [INFO] train episode 35868: reward = -162.56, steps = 29 01:47:03 [INFO] train episode 35869: reward = -71.08, steps = 24 01:47:09 [INFO] train episode 35870: reward = -106.31, steps = 65 01:47:11 [INFO] train episode 35871: reward = -71.86, steps = 21 01:47:13 [INFO] train episode 35872: reward = -81.41, steps = 20 01:47:15 [INFO] train episode 35873: reward = -79.78, steps = 21 01:47:17 [INFO] train episode 35874: reward = -57.17, steps = 26 01:47:19 [INFO] train episode 35875: reward = -107.76, steps = 26 01:47:22 [INFO] train episode 35876: reward = -70.26, steps = 23 01:47:24 [INFO] train episode 35877: reward = -69.45, steps = 20 01:47:26 [INFO] train episode 35878: reward = -83.92, steps = 22 01:47:27 [INFO] train episode 35879: reward = -99.88, steps = 19 01:47:29 [INFO] train episode 35880: reward = -112.92, steps = 19 01:47:31 [INFO] train episode 35881: reward = -55.28, steps = 24 01:47:33 [INFO] train episode 35882: reward = -70.96, steps = 19 01:47:35 [INFO] train episode 35883: reward = -114.35, steps = 22 01:47:40 [INFO] train episode 35884: reward = -217.55, steps = 58 01:47:42 [INFO] train episode 35885: reward = -59.35, steps = 20 01:47:44 [INFO] train episode 35886: reward = -120.69, steps = 26 01:47:47 [INFO] train episode 35887: reward = -61.87, steps = 26 01:47:49 [INFO] train episode 35888: reward = -82.83, steps = 24 01:47:51 [INFO] train episode 35889: reward = -110.26, steps = 23 01:47:53 [INFO] train episode 35890: reward = -70.91, steps = 29 01:47:55 [INFO] train episode 35891: reward = -79.93, steps = 20 01:47:57 [INFO] train episode 35892: reward = -49.26, steps = 19 01:48:01 [INFO] train episode 35893: reward = -41.64, steps = 41 01:48:02 [INFO] train episode 35894: reward = -49.46, steps = 19 01:48:06 [INFO] train episode 35895: reward = -49.08, steps = 36 01:48:07 [INFO] train episode 35896: reward = -76.06, steps = 19 01:48:10 [INFO] train episode 35897: reward = -158.04, steps = 28 01:48:12 [INFO] train episode 35898: reward = -119.30, steps = 24 01:48:14 [INFO] train episode 35899: reward = -72.07, steps = 24 01:48:17 [INFO] train episode 35900: reward = -96.36, steps = 28 01:48:19 [INFO] train episode 35901: reward = -176.98, steps = 22 01:48:20 [INFO] train episode 35902: reward = -81.60, steps = 18 01:48:22 [INFO] train episode 35903: reward = -79.66, steps = 20 01:48:24 [INFO] train episode 35904: reward = -78.04, steps = 26 01:48:27 [INFO] train episode 35905: reward = -62.47, steps = 26 01:48:30 [INFO] train episode 35906: reward = -110.51, steps = 32 01:48:33 [INFO] train episode 35907: reward = -99.43, steps = 40 01:48:35 [INFO] train episode 35908: reward = -122.00, steps = 24 01:48:39 [INFO] train episode 35909: reward = -99.74, steps = 36 01:48:41 [INFO] train episode 35910: reward = -86.15, steps = 29 01:48:43 [INFO] train episode 35911: reward = -71.38, steps = 28 01:48:46 [INFO] train episode 35912: reward = -76.39, steps = 21 01:48:48 [INFO] train episode 35913: reward = -151.09, steps = 25 01:48:50 [INFO] train episode 35914: reward = -78.17, steps = 20 01:48:52 [INFO] train episode 35915: reward = -130.23, steps = 27 01:48:55 [INFO] train episode 35916: reward = -98.59, steps = 34 01:48:57 [INFO] train episode 35917: reward = -93.39, steps = 19 01:48:59 [INFO] train episode 35918: reward = -171.76, steps = 24 01:49:02 [INFO] train episode 35919: reward = -72.16, steps = 27 01:49:04 [INFO] train episode 35920: reward = -55.94, steps = 29 01:49:06 [INFO] train episode 35921: reward = -89.12, steps = 21 01:49:08 [INFO] train episode 35922: reward = -92.86, steps = 24 01:49:10 [INFO] train episode 35923: reward = -66.18, steps = 23 01:49:14 [INFO] train episode 35924: reward = -67.62, steps = 38 01:49:15 [INFO] train episode 35925: reward = -90.11, steps = 21 01:49:18 [INFO] train episode 35926: reward = -96.19, steps = 26 01:49:21 [INFO] train episode 35927: reward = -141.36, steps = 33 01:49:23 [INFO] train episode 35928: reward = -96.46, steps = 20 01:49:25 [INFO] train episode 35929: reward = -119.62, steps = 21 01:49:27 [INFO] train episode 35930: reward = -77.76, steps = 24 01:49:29 [INFO] train episode 35931: reward = -139.31, steps = 31 01:49:31 [INFO] train episode 35932: reward = -57.10, steps = 24 01:49:34 [INFO] train episode 35933: reward = -92.18, steps = 28 01:49:37 [INFO] train episode 35934: reward = -94.07, steps = 32 01:49:41 [INFO] train episode 35935: reward = -82.26, steps = 44 01:49:43 [INFO] train episode 35936: reward = -84.36, steps = 26 01:49:45 [INFO] train episode 35937: reward = -65.38, steps = 21 01:49:47 [INFO] train episode 35938: reward = -89.82, steps = 21 01:49:50 [INFO] train episode 35939: reward = -150.70, steps = 29 01:49:53 [INFO] train episode 35940: reward = -95.93, steps = 39 01:49:56 [INFO] train episode 35941: reward = -101.11, steps = 33 01:49:59 [INFO] train episode 35942: reward = -111.38, steps = 36 01:50:02 [INFO] train episode 35943: reward = -102.53, steps = 31 01:50:05 [INFO] train episode 35944: reward = -99.43, steps = 21 01:50:08 [INFO] train episode 35945: reward = -173.93, steps = 38 01:50:11 [INFO] train episode 35946: reward = -83.08, steps = 27 01:50:13 [INFO] train episode 35947: reward = -75.89, steps = 21 01:50:15 [INFO] train episode 35948: reward = -126.18, steps = 25 01:50:17 [INFO] train episode 35949: reward = -88.37, steps = 20 01:50:18 [INFO] train episode 35950: reward = -45.82, steps = 20 01:50:20 [INFO] train episode 35951: reward = -89.11, steps = 21 01:50:22 [INFO] train episode 35952: reward = -105.20, steps = 20 01:50:25 [INFO] train episode 35953: reward = -80.18, steps = 23 01:50:29 [INFO] train episode 35954: reward = -143.78, steps = 53 01:50:31 [INFO] train episode 35955: reward = -80.26, steps = 21 01:50:33 [INFO] train episode 35956: reward = -97.18, steps = 25 01:50:35 [INFO] train episode 35957: reward = -60.51, steps = 21 01:50:37 [INFO] train episode 35958: reward = -107.94, steps = 20 01:50:41 [INFO] train episode 35959: reward = -65.77, steps = 40 01:50:43 [INFO] train episode 35960: reward = -71.58, steps = 31 01:50:46 [INFO] train episode 35961: reward = -83.58, steps = 29 01:50:48 [INFO] train episode 35962: reward = -100.20, steps = 26 01:50:51 [INFO] train episode 35963: reward = -95.13, steps = 31 01:50:53 [INFO] train episode 35964: reward = -77.63, steps = 21 01:50:55 [INFO] train episode 35965: reward = -88.13, steps = 21 01:50:58 [INFO] train episode 35966: reward = -66.77, steps = 24 01:51:00 [INFO] train episode 35967: reward = -66.76, steps = 25 01:51:02 [INFO] train episode 35968: reward = -89.26, steps = 24 01:51:04 [INFO] train episode 35969: reward = -65.87, steps = 22 01:51:06 [INFO] train episode 35970: reward = -104.77, steps = 20 01:51:09 [INFO] train episode 35971: reward = -127.04, steps = 31 01:51:11 [INFO] train episode 35972: reward = -138.41, steps = 24 01:51:13 [INFO] train episode 35973: reward = -63.75, steps = 18 01:51:15 [INFO] train episode 35974: reward = -102.73, steps = 25 01:51:18 [INFO] train episode 35975: reward = -56.39, steps = 29 01:51:20 [INFO] train episode 35976: reward = -102.34, steps = 23 01:51:22 [INFO] train episode 35977: reward = -94.04, steps = 21 01:51:24 [INFO] train episode 35978: reward = -76.69, steps = 24 01:51:26 [INFO] train episode 35979: reward = -102.51, steps = 27 01:51:29 [INFO] train episode 35980: reward = -91.50, steps = 25 01:51:31 [INFO] train episode 35981: reward = -84.15, steps = 21 01:51:34 [INFO] train episode 35982: reward = -117.22, steps = 30 01:51:36 [INFO] train episode 35983: reward = -118.97, steps = 32 01:51:39 [INFO] train episode 35984: reward = -63.57, steps = 27 01:51:41 [INFO] train episode 35985: reward = -175.44, steps = 20 01:51:46 [INFO] train episode 35986: reward = -181.77, steps = 54 01:51:47 [INFO] train episode 35987: reward = -107.21, steps = 20 01:51:50 [INFO] train episode 35988: reward = -111.41, steps = 28 01:51:52 [INFO] train episode 35989: reward = -80.66, steps = 21 01:51:53 [INFO] train episode 35990: reward = -84.75, steps = 20 01:51:55 [INFO] train episode 35991: reward = -72.28, steps = 23 01:51:57 [INFO] train episode 35992: reward = -83.48, steps = 21 01:51:59 [INFO] train episode 35993: reward = -91.05, steps = 19 01:52:02 [INFO] train episode 35994: reward = -128.28, steps = 31 01:52:05 [INFO] train episode 35995: reward = -57.25, steps = 29 01:52:07 [INFO] train episode 35996: reward = -55.97, steps = 20 01:52:08 [INFO] train episode 35997: reward = -89.27, steps = 20 01:52:11 [INFO] train episode 35998: reward = -68.56, steps = 27 01:52:15 [INFO] train episode 35999: reward = -103.23, steps = 47 01:52:17 [INFO] train episode 36000: reward = -112.36, steps = 23 01:52:19 [INFO] train episode 36001: reward = -84.34, steps = 18 01:52:21 [INFO] train episode 36002: reward = -127.48, steps = 21 01:52:24 [INFO] train episode 36003: reward = -56.59, steps = 40 01:52:26 [INFO] train episode 36004: reward = -35.50, steps = 22 01:52:28 [INFO] train episode 36005: reward = -106.35, steps = 23 01:52:30 [INFO] train episode 36006: reward = -123.47, steps = 21 01:52:32 [INFO] train episode 36007: reward = -107.58, steps = 19 01:52:34 [INFO] train episode 36008: reward = -76.51, steps = 18 01:52:36 [INFO] train episode 36009: reward = -136.61, steps = 23 01:52:38 [INFO] train episode 36010: reward = -144.06, steps = 20 01:52:40 [INFO] train episode 36011: reward = -117.17, steps = 22 01:52:42 [INFO] train episode 36012: reward = -107.26, steps = 30 01:52:47 [INFO] train episode 36013: reward = -148.42, steps = 48 01:52:49 [INFO] train episode 36014: reward = -173.70, steps = 22 01:52:51 [INFO] train episode 36015: reward = -75.31, steps = 23 01:52:53 [INFO] train episode 36016: reward = -97.77, steps = 20 01:52:55 [INFO] train episode 36017: reward = -77.13, steps = 20 01:52:58 [INFO] train episode 36018: reward = -93.76, steps = 38 01:53:00 [INFO] train episode 36019: reward = -104.16, steps = 27 01:53:03 [INFO] train episode 36020: reward = -104.10, steps = 18 01:53:04 [INFO] train episode 36021: reward = -97.35, steps = 19 01:53:06 [INFO] train episode 36022: reward = -70.16, steps = 19 01:53:08 [INFO] train episode 36023: reward = -106.83, steps = 21 01:53:11 [INFO] train episode 36024: reward = -55.04, steps = 33 01:53:13 [INFO] train episode 36025: reward = -70.16, steps = 24 01:53:15 [INFO] train episode 36026: reward = -93.06, steps = 25 01:53:18 [INFO] train episode 36027: reward = -105.89, steps = 24 01:53:21 [INFO] train episode 36028: reward = -102.59, steps = 36 01:53:23 [INFO] train episode 36029: reward = -68.90, steps = 25 01:53:27 [INFO] train episode 36030: reward = -152.29, steps = 44 01:53:30 [INFO] train episode 36031: reward = -97.32, steps = 35 01:53:32 [INFO] train episode 36032: reward = -169.95, steps = 20 01:53:34 [INFO] train episode 36033: reward = -76.42, steps = 21 01:53:36 [INFO] train episode 36034: reward = -100.22, steps = 27 01:53:38 [INFO] train episode 36035: reward = -117.25, steps = 25 01:53:41 [INFO] train episode 36036: reward = -86.52, steps = 29 01:53:43 [INFO] train episode 36037: reward = -58.13, steps = 19 01:53:45 [INFO] train episode 36038: reward = -53.42, steps = 20 01:53:47 [INFO] train episode 36039: reward = -100.75, steps = 28 01:53:49 [INFO] train episode 36040: reward = -86.36, steps = 22 01:53:51 [INFO] train episode 36041: reward = -120.11, steps = 19 01:53:53 [INFO] train episode 36042: reward = -169.97, steps = 29 01:53:57 [INFO] train episode 36043: reward = -184.34, steps = 33 01:53:59 [INFO] train episode 36044: reward = -87.04, steps = 25 01:54:01 [INFO] train episode 36045: reward = -56.39, steps = 20 01:54:04 [INFO] train episode 36046: reward = -112.75, steps = 37 01:54:06 [INFO] train episode 36047: reward = -87.62, steps = 23 01:54:08 [INFO] train episode 36048: reward = -97.86, steps = 21 01:54:10 [INFO] train episode 36049: reward = -111.79, steps = 20 01:54:12 [INFO] train episode 36050: reward = -79.45, steps = 25 01:54:14 [INFO] train episode 36051: reward = -103.21, steps = 20 01:54:16 [INFO] train episode 36052: reward = -40.22, steps = 22 01:54:18 [INFO] train episode 36053: reward = -106.82, steps = 19 01:54:19 [INFO] train episode 36054: reward = -89.86, steps = 19 01:54:21 [INFO] train episode 36055: reward = -65.66, steps = 20 01:54:23 [INFO] train episode 36056: reward = -104.95, steps = 20 01:54:25 [INFO] train episode 36057: reward = -120.00, steps = 27 01:54:27 [INFO] train episode 36058: reward = -79.06, steps = 22 01:54:29 [INFO] train episode 36059: reward = -100.39, steps = 19 01:54:31 [INFO] train episode 36060: reward = -85.31, steps = 22 01:54:34 [INFO] train episode 36061: reward = -96.77, steps = 33 01:54:36 [INFO] train episode 36062: reward = -89.15, steps = 19 01:54:39 [INFO] train episode 36063: reward = -114.39, steps = 32 01:54:41 [INFO] train episode 36064: reward = -108.62, steps = 21 01:54:43 [INFO] train episode 36065: reward = -144.77, steps = 24 01:54:46 [INFO] train episode 36066: reward = -104.47, steps = 26 01:54:48 [INFO] train episode 36067: reward = -78.63, steps = 26 01:54:50 [INFO] train episode 36068: reward = -64.15, steps = 21 01:54:52 [INFO] train episode 36069: reward = -109.91, steps = 23 01:54:55 [INFO] train episode 36070: reward = -100.36, steps = 39 01:54:57 [INFO] train episode 36071: reward = -102.79, steps = 19 01:55:02 [INFO] train episode 36072: reward = -153.07, steps = 48 01:55:03 [INFO] train episode 36073: reward = -119.40, steps = 21 01:55:04 [INFO] train episode 36074: reward = -114.80, steps = 11 01:55:07 [INFO] train episode 36075: reward = -116.91, steps = 25 01:55:09 [INFO] train episode 36076: reward = -41.64, steps = 20 01:55:12 [INFO] train episode 36077: reward = -77.47, steps = 37 01:55:15 [INFO] train episode 36078: reward = -109.63, steps = 33 01:55:17 [INFO] train episode 36079: reward = -73.07, steps = 25 01:55:19 [INFO] train episode 36080: reward = -67.62, steps = 20 01:55:21 [INFO] train episode 36081: reward = -139.46, steps = 19 01:55:25 [INFO] train episode 36082: reward = -167.57, steps = 47 01:55:29 [INFO] train episode 36083: reward = -122.43, steps = 41 01:55:32 [INFO] train episode 36084: reward = -138.59, steps = 37 01:55:34 [INFO] train episode 36085: reward = -62.95, steps = 26 01:55:37 [INFO] train episode 36086: reward = -128.75, steps = 32 01:55:40 [INFO] train episode 36087: reward = -121.17, steps = 32 01:55:42 [INFO] train episode 36088: reward = -110.82, steps = 19 01:55:44 [INFO] train episode 36089: reward = -106.67, steps = 27 01:55:46 [INFO] train episode 36090: reward = -73.65, steps = 26 01:55:48 [INFO] train episode 36091: reward = -61.12, steps = 17 01:55:50 [INFO] train episode 36092: reward = -136.53, steps = 19 01:55:52 [INFO] train episode 36093: reward = -101.85, steps = 24 01:55:54 [INFO] train episode 36094: reward = -78.67, steps = 21 01:55:56 [INFO] train episode 36095: reward = -60.14, steps = 24 01:55:59 [INFO] train episode 36096: reward = -80.17, steps = 21 01:56:02 [INFO] train episode 36097: reward = -153.90, steps = 35 01:56:04 [INFO] train episode 36098: reward = -130.08, steps = 25 01:56:06 [INFO] train episode 36099: reward = -147.61, steps = 24 01:56:09 [INFO] train episode 36100: reward = -65.66, steps = 25 01:56:11 [INFO] train episode 36101: reward = -94.23, steps = 24 01:56:13 [INFO] train episode 36102: reward = -86.97, steps = 26 01:56:17 [INFO] train episode 36103: reward = -125.33, steps = 41 01:56:20 [INFO] train episode 36104: reward = -155.27, steps = 40 01:56:23 [INFO] train episode 36105: reward = -73.33, steps = 32 01:56:25 [INFO] train episode 36106: reward = -126.70, steps = 20 01:56:27 [INFO] train episode 36107: reward = -71.45, steps = 18 01:56:29 [INFO] train episode 36108: reward = -86.51, steps = 25 01:56:31 [INFO] train episode 36109: reward = -118.14, steps = 22 01:56:33 [INFO] train episode 36110: reward = -61.46, steps = 22 01:56:35 [INFO] train episode 36111: reward = -98.82, steps = 19 01:56:37 [INFO] train episode 36112: reward = -70.39, steps = 20 01:56:39 [INFO] train episode 36113: reward = -119.39, steps = 21 01:56:41 [INFO] train episode 36114: reward = -98.06, steps = 19 01:56:44 [INFO] train episode 36115: reward = -69.55, steps = 34 01:56:45 [INFO] train episode 36116: reward = -72.31, steps = 19 01:56:49 [INFO] train episode 36117: reward = -113.96, steps = 36 01:56:50 [INFO] train episode 36118: reward = -86.53, steps = 21 01:56:52 [INFO] train episode 36119: reward = -89.41, steps = 22 01:56:54 [INFO] train episode 36120: reward = -66.16, steps = 22 01:56:58 [INFO] train episode 36121: reward = -86.35, steps = 42 01:57:00 [INFO] train episode 36122: reward = -82.19, steps = 18 01:57:02 [INFO] train episode 36123: reward = -103.79, steps = 27 01:57:04 [INFO] train episode 36124: reward = -126.91, steps = 21 01:57:06 [INFO] train episode 36125: reward = -86.10, steps = 24 01:57:08 [INFO] train episode 36126: reward = -50.48, steps = 22 01:57:11 [INFO] train episode 36127: reward = -132.17, steps = 31 01:57:15 [INFO] train episode 36128: reward = -146.51, steps = 42 01:57:17 [INFO] train episode 36129: reward = -66.59, steps = 23 01:57:19 [INFO] train episode 36130: reward = -66.51, steps = 25 01:57:23 [INFO] train episode 36131: reward = -120.41, steps = 39 01:57:24 [INFO] train episode 36132: reward = -103.96, steps = 21 01:57:28 [INFO] train episode 36133: reward = -80.07, steps = 40 01:57:30 [INFO] train episode 36134: reward = -74.67, steps = 20 01:57:32 [INFO] train episode 36135: reward = -61.71, steps = 21 01:57:35 [INFO] train episode 36136: reward = -238.62, steps = 30 01:57:37 [INFO] train episode 36137: reward = -77.07, steps = 24 01:57:39 [INFO] train episode 36138: reward = -101.10, steps = 29 01:57:43 [INFO] train episode 36139: reward = -168.08, steps = 37 01:57:47 [INFO] train episode 36140: reward = -100.12, steps = 48 01:57:49 [INFO] train episode 36141: reward = -79.41, steps = 25 01:57:53 [INFO] train episode 36142: reward = -89.36, steps = 38 01:57:55 [INFO] train episode 36143: reward = -116.98, steps = 27 01:57:57 [INFO] train episode 36144: reward = -120.93, steps = 20 01:57:59 [INFO] train episode 36145: reward = -90.84, steps = 29 01:58:01 [INFO] train episode 36146: reward = -65.30, steps = 19 01:58:04 [INFO] train episode 36147: reward = -70.22, steps = 25 01:58:06 [INFO] train episode 36148: reward = -111.44, steps = 23 01:58:08 [INFO] train episode 36149: reward = -57.52, steps = 21 01:58:10 [INFO] train episode 36150: reward = -168.93, steps = 31 01:58:12 [INFO] train episode 36151: reward = -92.58, steps = 20 01:58:15 [INFO] train episode 36152: reward = -161.37, steps = 30 01:58:17 [INFO] train episode 36153: reward = -85.75, steps = 23 01:58:20 [INFO] train episode 36154: reward = -147.47, steps = 29 01:58:21 [INFO] train episode 36155: reward = -117.43, steps = 20 01:58:25 [INFO] train episode 36156: reward = -167.83, steps = 39 01:58:27 [INFO] train episode 36157: reward = -97.69, steps = 23 01:58:30 [INFO] train episode 36158: reward = -57.63, steps = 32 01:58:32 [INFO] train episode 36159: reward = -117.57, steps = 27 01:58:34 [INFO] train episode 36160: reward = -73.69, steps = 22 01:58:36 [INFO] train episode 36161: reward = -113.66, steps = 23 01:58:39 [INFO] train episode 36162: reward = -104.48, steps = 25 01:58:40 [INFO] train episode 36163: reward = -92.77, steps = 19 01:58:43 [INFO] train episode 36164: reward = -124.88, steps = 24 01:58:45 [INFO] train episode 36165: reward = -75.01, steps = 29 01:58:47 [INFO] train episode 36166: reward = -130.97, steps = 22 01:58:49 [INFO] train episode 36167: reward = -106.59, steps = 26 01:58:51 [INFO] train episode 36168: reward = -63.85, steps = 19 01:58:54 [INFO] train episode 36169: reward = -136.13, steps = 22 01:58:56 [INFO] train episode 36170: reward = -62.03, steps = 25 01:58:58 [INFO] train episode 36171: reward = -80.67, steps = 23 01:59:00 [INFO] train episode 36172: reward = -43.15, steps = 20 01:59:02 [INFO] train episode 36173: reward = -92.93, steps = 25 01:59:04 [INFO] train episode 36174: reward = -77.41, steps = 23 01:59:06 [INFO] train episode 36175: reward = -67.48, steps = 21 01:59:09 [INFO] train episode 36176: reward = -90.41, steps = 23 01:59:11 [INFO] train episode 36177: reward = -73.96, steps = 23 01:59:12 [INFO] train episode 36178: reward = -69.26, steps = 18 01:59:14 [INFO] train episode 36179: reward = -62.77, steps = 20 01:59:17 [INFO] train episode 36180: reward = -100.73, steps = 29 01:59:19 [INFO] train episode 36181: reward = -117.85, steps = 30 01:59:21 [INFO] train episode 36182: reward = -100.12, steps = 21 01:59:23 [INFO] train episode 36183: reward = -136.15, steps = 23 01:59:26 [INFO] train episode 36184: reward = -93.74, steps = 32 01:59:29 [INFO] train episode 36185: reward = -127.59, steps = 31 01:59:31 [INFO] train episode 36186: reward = -110.38, steps = 20 01:59:33 [INFO] train episode 36187: reward = -82.66, steps = 21 01:59:35 [INFO] train episode 36188: reward = -116.81, steps = 20 01:59:37 [INFO] train episode 36189: reward = -112.48, steps = 24 01:59:40 [INFO] train episode 36190: reward = -137.88, steps = 33 01:59:43 [INFO] train episode 36191: reward = -154.43, steps = 34 01:59:45 [INFO] train episode 36192: reward = -83.53, steps = 24 01:59:48 [INFO] train episode 36193: reward = -178.85, steps = 41 01:59:50 [INFO] train episode 36194: reward = -68.56, steps = 19 01:59:52 [INFO] train episode 36195: reward = -80.22, steps = 24 01:59:55 [INFO] train episode 36196: reward = -134.25, steps = 28 01:59:57 [INFO] train episode 36197: reward = -106.09, steps = 20 01:59:59 [INFO] train episode 36198: reward = -74.10, steps = 19 02:00:02 [INFO] train episode 36199: reward = -114.78, steps = 33 02:00:03 [INFO] train episode 36200: reward = -70.80, steps = 20 02:00:06 [INFO] train episode 36201: reward = -111.07, steps = 25 02:00:07 [INFO] train episode 36202: reward = -60.78, steps = 20 02:00:10 [INFO] train episode 36203: reward = -152.84, steps = 27 02:00:14 [INFO] train episode 36204: reward = -100.73, steps = 42 02:00:16 [INFO] train episode 36205: reward = -96.90, steps = 29 02:00:19 [INFO] train episode 36206: reward = -90.27, steps = 29 02:00:20 [INFO] train episode 36207: reward = -96.96, steps = 18 02:00:22 [INFO] train episode 36208: reward = -78.48, steps = 20 02:00:24 [INFO] train episode 36209: reward = -105.63, steps = 24 02:00:27 [INFO] train episode 36210: reward = -103.77, steps = 30 02:00:29 [INFO] train episode 36211: reward = -81.56, steps = 19 02:00:32 [INFO] train episode 36212: reward = -131.23, steps = 30 02:00:34 [INFO] train episode 36213: reward = -121.36, steps = 24 02:00:37 [INFO] train episode 36214: reward = -97.46, steps = 29 02:00:39 [INFO] train episode 36215: reward = -86.79, steps = 21 02:00:41 [INFO] train episode 36216: reward = -94.32, steps = 28 02:00:43 [INFO] train episode 36217: reward = -85.20, steps = 25 02:00:46 [INFO] train episode 36218: reward = -82.74, steps = 21 02:00:48 [INFO] train episode 36219: reward = -88.30, steps = 23 02:00:51 [INFO] train episode 36220: reward = -136.94, steps = 38 02:00:53 [INFO] train episode 36221: reward = -72.96, steps = 20 02:00:56 [INFO] train episode 36222: reward = -90.55, steps = 32 02:00:58 [INFO] train episode 36223: reward = -143.68, steps = 26 02:01:00 [INFO] train episode 36224: reward = -103.58, steps = 22 02:01:02 [INFO] train episode 36225: reward = -52.60, steps = 22 02:01:05 [INFO] train episode 36226: reward = -72.51, steps = 26 02:01:08 [INFO] train episode 36227: reward = -198.58, steps = 38 02:01:10 [INFO] train episode 36228: reward = -74.12, steps = 20 02:01:12 [INFO] train episode 36229: reward = -60.34, steps = 23 02:01:14 [INFO] train episode 36230: reward = -59.38, steps = 25 02:01:16 [INFO] train episode 36231: reward = -145.97, steps = 21 02:01:19 [INFO] train episode 36232: reward = -133.12, steps = 27 02:01:23 [INFO] train episode 36233: reward = -180.66, steps = 45 02:01:25 [INFO] train episode 36234: reward = -96.12, steps = 25 02:01:29 [INFO] train episode 36235: reward = -163.12, steps = 45 02:01:34 [INFO] train episode 36236: reward = -124.63, steps = 54 02:01:37 [INFO] train episode 36237: reward = -122.32, steps = 35 02:01:39 [INFO] train episode 36238: reward = -61.68, steps = 23 02:01:41 [INFO] train episode 36239: reward = -76.85, steps = 23 02:01:43 [INFO] train episode 36240: reward = -62.12, steps = 21 02:01:45 [INFO] train episode 36241: reward = -82.73, steps = 25 02:01:47 [INFO] train episode 36242: reward = -64.99, steps = 25 02:01:50 [INFO] train episode 36243: reward = -56.30, steps = 22 02:01:52 [INFO] train episode 36244: reward = -80.87, steps = 20 02:01:54 [INFO] train episode 36245: reward = -129.12, steps = 24 02:01:56 [INFO] train episode 36246: reward = -95.44, steps = 20 02:01:59 [INFO] train episode 36247: reward = -139.68, steps = 31 02:02:02 [INFO] train episode 36248: reward = -41.66, steps = 33 02:02:04 [INFO] train episode 36249: reward = -55.89, steps = 22 02:02:06 [INFO] train episode 36250: reward = -76.92, steps = 21 02:02:09 [INFO] train episode 36251: reward = -72.23, steps = 35 02:02:11 [INFO] train episode 36252: reward = -62.67, steps = 26 02:02:14 [INFO] train episode 36253: reward = -157.54, steps = 28 02:02:16 [INFO] train episode 36254: reward = -87.87, steps = 21 02:02:17 [INFO] train episode 36255: reward = -91.60, steps = 16 02:02:19 [INFO] train episode 36256: reward = -54.23, steps = 25 02:02:21 [INFO] train episode 36257: reward = -115.38, steps = 19 02:02:24 [INFO] train episode 36258: reward = -85.66, steps = 26 02:02:27 [INFO] train episode 36259: reward = -69.99, steps = 31 02:02:29 [INFO] train episode 36260: reward = -65.54, steps = 27 02:02:33 [INFO] train episode 36261: reward = -138.48, steps = 46 02:02:35 [INFO] train episode 36262: reward = -61.99, steps = 19 02:02:39 [INFO] train episode 36263: reward = -138.21, steps = 47 02:02:43 [INFO] train episode 36264: reward = -64.62, steps = 38 02:02:45 [INFO] train episode 36265: reward = -90.69, steps = 21 02:02:47 [INFO] train episode 36266: reward = -108.49, steps = 28 02:02:49 [INFO] train episode 36267: reward = -86.95, steps = 19 02:02:51 [INFO] train episode 36268: reward = -113.07, steps = 22 02:02:53 [INFO] train episode 36269: reward = -107.54, steps = 27 02:02:56 [INFO] train episode 36270: reward = -102.23, steps = 33 02:02:59 [INFO] train episode 36271: reward = -129.55, steps = 23 02:03:01 [INFO] train episode 36272: reward = -124.69, steps = 27 02:03:03 [INFO] train episode 36273: reward = -71.10, steps = 20 02:03:04 [INFO] train episode 36274: reward = -124.69, steps = 20 02:03:09 [INFO] train episode 36275: reward = -168.79, steps = 47 02:03:13 [INFO] train episode 36276: reward = -167.32, steps = 49 02:03:15 [INFO] train episode 36277: reward = -87.55, steps = 22 02:03:18 [INFO] train episode 36278: reward = -152.18, steps = 28 02:03:21 [INFO] train episode 36279: reward = -161.32, steps = 38 02:03:23 [INFO] train episode 36280: reward = -96.73, steps = 19 02:03:26 [INFO] train episode 36281: reward = -77.11, steps = 33 02:03:28 [INFO] train episode 36282: reward = -59.01, steps = 23 02:03:30 [INFO] train episode 36283: reward = -82.03, steps = 19 02:03:32 [INFO] train episode 36284: reward = -136.95, steps = 21 02:03:34 [INFO] train episode 36285: reward = -81.23, steps = 19 02:03:35 [INFO] train episode 36286: reward = -116.97, steps = 18 02:03:38 [INFO] train episode 36287: reward = -110.56, steps = 33 02:03:40 [INFO] train episode 36288: reward = -99.46, steps = 19 02:03:43 [INFO] train episode 36289: reward = -120.15, steps = 36 02:03:45 [INFO] train episode 36290: reward = -83.43, steps = 24 02:03:50 [INFO] train episode 36291: reward = -104.04, steps = 48 02:03:52 [INFO] train episode 36292: reward = -84.41, steps = 25 02:03:55 [INFO] train episode 36293: reward = -112.01, steps = 31 02:03:56 [INFO] train episode 36294: reward = -89.24, steps = 19 02:04:00 [INFO] train episode 36295: reward = -86.64, steps = 36 02:04:01 [INFO] train episode 36296: reward = -73.51, steps = 19 02:04:04 [INFO] train episode 36297: reward = -85.56, steps = 22 02:04:06 [INFO] train episode 36298: reward = -61.54, steps = 31 02:04:09 [INFO] train episode 36299: reward = -111.03, steps = 32 02:04:12 [INFO] train episode 36300: reward = -190.79, steps = 33 02:04:15 [INFO] train episode 36301: reward = -107.62, steps = 29 02:04:17 [INFO] train episode 36302: reward = -99.88, steps = 33 02:04:20 [INFO] train episode 36303: reward = -64.23, steps = 27 02:04:22 [INFO] train episode 36304: reward = -109.79, steps = 21 02:04:25 [INFO] train episode 36305: reward = -140.98, steps = 30 02:04:27 [INFO] train episode 36306: reward = -126.06, steps = 27 02:04:29 [INFO] train episode 36307: reward = -74.55, steps = 19 02:04:31 [INFO] train episode 36308: reward = -73.08, steps = 21 02:04:33 [INFO] train episode 36309: reward = -131.48, steps = 24 02:04:36 [INFO] train episode 36310: reward = -104.54, steps = 28 02:04:38 [INFO] train episode 36311: reward = -109.24, steps = 22 02:04:40 [INFO] train episode 36312: reward = -77.89, steps = 26 02:04:42 [INFO] train episode 36313: reward = -92.35, steps = 29 02:04:45 [INFO] train episode 36314: reward = -91.32, steps = 26 02:04:47 [INFO] train episode 36315: reward = -86.91, steps = 19 02:04:49 [INFO] train episode 36316: reward = -57.24, steps = 24 02:04:52 [INFO] train episode 36317: reward = -75.52, steps = 21 02:04:54 [INFO] train episode 36318: reward = -77.29, steps = 27 02:04:56 [INFO] train episode 36319: reward = -101.06, steps = 24 02:04:58 [INFO] train episode 36320: reward = -143.66, steps = 24 02:05:00 [INFO] train episode 36321: reward = -76.04, steps = 20 02:05:02 [INFO] train episode 36322: reward = -84.89, steps = 20 02:05:04 [INFO] train episode 36323: reward = -122.41, steps = 27 02:05:06 [INFO] train episode 36324: reward = -113.52, steps = 21 02:05:09 [INFO] train episode 36325: reward = -76.52, steps = 27 02:05:11 [INFO] train episode 36326: reward = -79.36, steps = 23 02:05:13 [INFO] train episode 36327: reward = -94.71, steps = 21 02:05:15 [INFO] train episode 36328: reward = -82.89, steps = 20 02:05:16 [INFO] train episode 36329: reward = -94.24, steps = 19 02:05:19 [INFO] train episode 36330: reward = -149.35, steps = 29 02:05:23 [INFO] train episode 36331: reward = -157.73, steps = 45 02:05:25 [INFO] train episode 36332: reward = -128.52, steps = 26 02:05:27 [INFO] train episode 36333: reward = -69.81, steps = 20 02:05:29 [INFO] train episode 36334: reward = -91.30, steps = 23 02:05:31 [INFO] train episode 36335: reward = -126.21, steps = 19 02:05:33 [INFO] train episode 36336: reward = -126.50, steps = 28 02:05:37 [INFO] train episode 36337: reward = -86.87, steps = 43 02:05:40 [INFO] train episode 36338: reward = -62.58, steps = 27 02:05:42 [INFO] train episode 36339: reward = -58.67, steps = 21 02:05:43 [INFO] train episode 36340: reward = -82.48, steps = 19 02:05:46 [INFO] train episode 36341: reward = -90.03, steps = 28 02:05:48 [INFO] train episode 36342: reward = -50.68, steps = 25 02:05:50 [INFO] train episode 36343: reward = -82.01, steps = 19 02:05:52 [INFO] train episode 36344: reward = -73.51, steps = 26 02:05:54 [INFO] train episode 36345: reward = -115.03, steps = 19 02:05:56 [INFO] train episode 36346: reward = -40.21, steps = 22 02:05:57 [INFO] train episode 36347: reward = -113.84, steps = 16 02:06:00 [INFO] train episode 36348: reward = -92.18, steps = 28 02:06:02 [INFO] train episode 36349: reward = -71.44, steps = 20 02:06:04 [INFO] train episode 36350: reward = -76.12, steps = 29 02:06:07 [INFO] train episode 36351: reward = -104.42, steps = 36 02:06:10 [INFO] train episode 36352: reward = -67.44, steps = 28 02:06:13 [INFO] train episode 36353: reward = -75.50, steps = 28 02:06:15 [INFO] train episode 36354: reward = -103.99, steps = 30 02:06:18 [INFO] train episode 36355: reward = -73.58, steps = 31 02:06:21 [INFO] train episode 36356: reward = -94.73, steps = 33 02:06:25 [INFO] train episode 36357: reward = -112.44, steps = 42 02:06:27 [INFO] train episode 36358: reward = -68.72, steps = 25 02:06:29 [INFO] train episode 36359: reward = -68.90, steps = 18 02:06:31 [INFO] train episode 36360: reward = -117.90, steps = 19 02:06:34 [INFO] train episode 36361: reward = -88.77, steps = 37 02:06:36 [INFO] train episode 36362: reward = -82.78, steps = 24 02:06:38 [INFO] train episode 36363: reward = -58.52, steps = 19 02:06:40 [INFO] train episode 36364: reward = -86.44, steps = 24 02:06:44 [INFO] train episode 36365: reward = -171.41, steps = 49 02:06:47 [INFO] train episode 36366: reward = -70.21, steps = 26 02:06:50 [INFO] train episode 36367: reward = -115.37, steps = 33 02:06:52 [INFO] train episode 36368: reward = -56.35, steps = 24 02:06:54 [INFO] train episode 36369: reward = -86.54, steps = 21 02:06:56 [INFO] train episode 36370: reward = -62.72, steps = 22 02:06:58 [INFO] train episode 36371: reward = -115.84, steps = 21 02:07:01 [INFO] train episode 36372: reward = -112.87, steps = 38 02:07:04 [INFO] train episode 36373: reward = -98.10, steps = 24 02:07:05 [INFO] train episode 36374: reward = -104.00, steps = 19 02:07:07 [INFO] train episode 36375: reward = -132.33, steps = 20 02:07:09 [INFO] train episode 36376: reward = -58.71, steps = 23 02:07:12 [INFO] train episode 36377: reward = -74.87, steps = 29 02:07:19 [INFO] train episode 36378: reward = -195.25, steps = 79 02:07:21 [INFO] train episode 36379: reward = -79.11, steps = 22 02:07:23 [INFO] train episode 36380: reward = -132.58, steps = 22 02:07:25 [INFO] train episode 36381: reward = -95.35, steps = 27 02:07:28 [INFO] train episode 36382: reward = -117.68, steps = 26 02:07:32 [INFO] train episode 36383: reward = -154.70, steps = 53 02:07:34 [INFO] train episode 36384: reward = -141.93, steps = 20 02:07:36 [INFO] train episode 36385: reward = -74.34, steps = 21 02:07:38 [INFO] train episode 36386: reward = -81.42, steps = 20 02:07:41 [INFO] train episode 36387: reward = -64.46, steps = 40 02:07:45 [INFO] train episode 36388: reward = -119.76, steps = 33 02:07:47 [INFO] train episode 36389: reward = -85.04, steps = 20 02:07:50 [INFO] train episode 36390: reward = -102.91, steps = 33 02:07:52 [INFO] train episode 36391: reward = -56.85, steps = 21 02:07:55 [INFO] train episode 36392: reward = -121.70, steps = 41 02:07:57 [INFO] train episode 36393: reward = -194.41, steps = 19 02:07:59 [INFO] train episode 36394: reward = -77.21, steps = 22 02:08:01 [INFO] train episode 36395: reward = -63.95, steps = 26 02:08:04 [INFO] train episode 36396: reward = -143.14, steps = 28 02:08:06 [INFO] train episode 36397: reward = -148.68, steps = 20 02:08:08 [INFO] train episode 36398: reward = -92.82, steps = 29 02:08:10 [INFO] train episode 36399: reward = -90.22, steps = 23 02:08:12 [INFO] train episode 36400: reward = -84.06, steps = 22 02:08:14 [INFO] train episode 36401: reward = -98.81, steps = 22 02:08:16 [INFO] train episode 36402: reward = -91.94, steps = 19 02:08:18 [INFO] train episode 36403: reward = -246.44, steps = 27 02:08:21 [INFO] train episode 36404: reward = -53.80, steps = 28 02:08:23 [INFO] train episode 36405: reward = -62.91, steps = 23 02:08:25 [INFO] train episode 36406: reward = -82.64, steps = 19 02:08:27 [INFO] train episode 36407: reward = -73.62, steps = 21 02:08:29 [INFO] train episode 36408: reward = -67.29, steps = 20 02:08:30 [INFO] train episode 36409: reward = -112.01, steps = 19 02:08:32 [INFO] train episode 36410: reward = -75.89, steps = 18 02:08:35 [INFO] train episode 36411: reward = -49.15, steps = 39 02:08:39 [INFO] train episode 36412: reward = -79.31, steps = 30 02:08:40 [INFO] train episode 36413: reward = -99.30, steps = 21 02:08:43 [INFO] train episode 36414: reward = -83.99, steps = 23 02:08:45 [INFO] train episode 36415: reward = -117.20, steps = 30 02:08:47 [INFO] train episode 36416: reward = -98.60, steps = 19 02:08:50 [INFO] train episode 36417: reward = -97.94, steps = 35 02:08:52 [INFO] train episode 36418: reward = -150.66, steps = 26 02:08:55 [INFO] train episode 36419: reward = -86.36, steps = 28 02:08:58 [INFO] train episode 36420: reward = -122.00, steps = 32 02:09:00 [INFO] train episode 36421: reward = -84.41, steps = 19 02:09:02 [INFO] train episode 36422: reward = -90.04, steps = 26 02:09:04 [INFO] train episode 36423: reward = -78.15, steps = 21 02:09:07 [INFO] train episode 36424: reward = -146.13, steps = 39 02:09:10 [INFO] train episode 36425: reward = -127.95, steps = 28 02:09:13 [INFO] train episode 36426: reward = -149.66, steps = 27 02:09:15 [INFO] train episode 36427: reward = -119.06, steps = 24 02:09:16 [INFO] train episode 36428: reward = -104.21, steps = 21 02:09:18 [INFO] train episode 36429: reward = -83.79, steps = 22 02:09:20 [INFO] train episode 36430: reward = -59.31, steps = 22 02:09:22 [INFO] train episode 36431: reward = -60.78, steps = 19 02:09:25 [INFO] train episode 36432: reward = -97.22, steps = 36 02:09:27 [INFO] train episode 36433: reward = -99.51, steps = 21 02:09:30 [INFO] train episode 36434: reward = -91.12, steps = 23 02:09:31 [INFO] train episode 36435: reward = -84.27, steps = 20 02:09:33 [INFO] train episode 36436: reward = -66.17, steps = 19 02:09:36 [INFO] train episode 36437: reward = -156.90, steps = 29 02:09:38 [INFO] train episode 36438: reward = -67.34, steps = 22 02:09:40 [INFO] train episode 36439: reward = -77.91, steps = 31 02:09:42 [INFO] train episode 36440: reward = -120.79, steps = 21 02:09:46 [INFO] train episode 36441: reward = -173.75, steps = 37 02:09:48 [INFO] train episode 36442: reward = -84.09, steps = 22 02:09:52 [INFO] train episode 36443: reward = -166.05, steps = 44 02:09:54 [INFO] train episode 36444: reward = -50.08, steps = 29 02:09:58 [INFO] train episode 36445: reward = -46.14, steps = 42 02:10:00 [INFO] train episode 36446: reward = -53.06, steps = 21 02:10:03 [INFO] train episode 36447: reward = -85.97, steps = 37 02:10:05 [INFO] train episode 36448: reward = -100.07, steps = 23 02:10:07 [INFO] train episode 36449: reward = -76.07, steps = 23 02:10:11 [INFO] train episode 36450: reward = -89.92, steps = 40 02:10:13 [INFO] train episode 36451: reward = -73.62, steps = 20 02:10:15 [INFO] train episode 36452: reward = -133.86, steps = 23 02:10:17 [INFO] train episode 36453: reward = -113.77, steps = 19 02:10:19 [INFO] train episode 36454: reward = -85.25, steps = 22 02:10:21 [INFO] train episode 36455: reward = -79.00, steps = 25 02:10:23 [INFO] train episode 36456: reward = -141.70, steps = 26 02:10:25 [INFO] train episode 36457: reward = -76.52, steps = 20 02:10:27 [INFO] train episode 36458: reward = -94.59, steps = 23 02:10:30 [INFO] train episode 36459: reward = -47.06, steps = 37 02:10:34 [INFO] train episode 36460: reward = -214.16, steps = 44 02:10:36 [INFO] train episode 36461: reward = -93.06, steps = 20 02:10:39 [INFO] train episode 36462: reward = -72.69, steps = 31 02:10:41 [INFO] train episode 36463: reward = -42.14, steps = 16 02:10:43 [INFO] train episode 36464: reward = -71.81, steps = 19 02:10:45 [INFO] train episode 36465: reward = -87.20, steps = 19 02:10:47 [INFO] train episode 36466: reward = -66.19, steps = 20 02:10:48 [INFO] train episode 36467: reward = -89.21, steps = 21 02:10:51 [INFO] train episode 36468: reward = -66.37, steps = 22 02:10:53 [INFO] train episode 36469: reward = -111.50, steps = 28 02:10:55 [INFO] train episode 36470: reward = -67.51, steps = 21 02:10:57 [INFO] train episode 36471: reward = -94.83, steps = 25 02:11:01 [INFO] train episode 36472: reward = -132.56, steps = 36 02:11:04 [INFO] train episode 36473: reward = -87.90, steps = 38 02:11:06 [INFO] train episode 36474: reward = -98.23, steps = 21 02:11:09 [INFO] train episode 36475: reward = -95.16, steps = 33 02:11:11 [INFO] train episode 36476: reward = -69.17, steps = 21 02:11:13 [INFO] train episode 36477: reward = -61.18, steps = 27 02:11:17 [INFO] train episode 36478: reward = -90.92, steps = 42 02:11:18 [INFO] train episode 36479: reward = -92.13, steps = 19 02:11:20 [INFO] train episode 36480: reward = -105.44, steps = 20 02:11:23 [INFO] train episode 36481: reward = -125.43, steps = 22 02:11:24 [INFO] train episode 36482: reward = -95.21, steps = 19 02:11:27 [INFO] train episode 36483: reward = -69.50, steps = 29 02:11:29 [INFO] train episode 36484: reward = -91.64, steps = 21 02:11:31 [INFO] train episode 36485: reward = -156.59, steps = 23 02:11:33 [INFO] train episode 36486: reward = -90.84, steps = 22 02:11:34 [INFO] train episode 36487: reward = -148.79, steps = 19 02:11:38 [INFO] train episode 36488: reward = -155.39, steps = 41 02:11:40 [INFO] train episode 36489: reward = -75.04, steps = 19 02:11:44 [INFO] train episode 36490: reward = -169.63, steps = 43 02:11:45 [INFO] train episode 36491: reward = -93.50, steps = 20 02:11:48 [INFO] train episode 36492: reward = -58.19, steps = 29 02:11:50 [INFO] train episode 36493: reward = -60.32, steps = 20 02:11:51 [INFO] train episode 36494: reward = -61.75, steps = 19 02:11:53 [INFO] train episode 36495: reward = -49.47, steps = 20 02:11:56 [INFO] train episode 36496: reward = -95.07, steps = 23 02:11:59 [INFO] train episode 36497: reward = -103.20, steps = 33 02:12:01 [INFO] train episode 36498: reward = -113.27, steps = 23 02:12:03 [INFO] train episode 36499: reward = -127.83, steps = 24 02:12:04 [INFO] train episode 36500: reward = -85.71, steps = 19 02:12:06 [INFO] train episode 36501: reward = -66.70, steps = 21 02:12:08 [INFO] train episode 36502: reward = -81.54, steps = 19 02:12:10 [INFO] train episode 36503: reward = -86.60, steps = 23 02:12:12 [INFO] train episode 36504: reward = -88.06, steps = 19 02:12:14 [INFO] train episode 36505: reward = -67.71, steps = 21 02:12:17 [INFO] train episode 36506: reward = -75.57, steps = 36 02:12:19 [INFO] train episode 36507: reward = -98.59, steps = 19 02:12:21 [INFO] train episode 36508: reward = -116.96, steps = 22 02:12:23 [INFO] train episode 36509: reward = -49.26, steps = 23 02:12:25 [INFO] train episode 36510: reward = -87.29, steps = 19 02:12:27 [INFO] train episode 36511: reward = -108.62, steps = 21 02:12:31 [INFO] train episode 36512: reward = -73.84, steps = 53 02:12:34 [INFO] train episode 36513: reward = -149.52, steps = 28 02:12:36 [INFO] train episode 36514: reward = -72.39, steps = 21 02:12:38 [INFO] train episode 36515: reward = -105.91, steps = 18 02:12:40 [INFO] train episode 36516: reward = -84.89, steps = 30 02:12:42 [INFO] train episode 36517: reward = -109.92, steps = 23 02:12:45 [INFO] train episode 36518: reward = -69.53, steps = 22 02:12:47 [INFO] train episode 36519: reward = -75.01, steps = 24 02:12:49 [INFO] train episode 36520: reward = -102.32, steps = 28 02:12:52 [INFO] train episode 36521: reward = -96.35, steps = 25 02:12:54 [INFO] train episode 36522: reward = -77.42, steps = 25 02:12:56 [INFO] train episode 36523: reward = -101.08, steps = 21 02:13:00 [INFO] train episode 36524: reward = -154.41, steps = 39 02:13:03 [INFO] train episode 36525: reward = -90.19, steps = 35 02:13:04 [INFO] train episode 36526: reward = -89.16, steps = 20 02:13:07 [INFO] train episode 36527: reward = -66.29, steps = 24 02:13:09 [INFO] train episode 36528: reward = -115.88, steps = 33 02:13:11 [INFO] train episode 36529: reward = -87.98, steps = 24 02:13:13 [INFO] train episode 36530: reward = -109.20, steps = 22 02:13:15 [INFO] train episode 36531: reward = -153.56, steps = 19 02:13:17 [INFO] train episode 36532: reward = -133.56, steps = 20 02:13:19 [INFO] train episode 36533: reward = -95.61, steps = 22 02:13:22 [INFO] train episode 36534: reward = -100.09, steps = 28 02:13:26 [INFO] train episode 36535: reward = -179.52, steps = 46 02:13:28 [INFO] train episode 36536: reward = -81.25, steps = 25 02:13:30 [INFO] train episode 36537: reward = -100.66, steps = 18 02:13:32 [INFO] train episode 36538: reward = -107.16, steps = 23 02:13:34 [INFO] train episode 36539: reward = -94.95, steps = 25 02:13:38 [INFO] train episode 36540: reward = -71.59, steps = 31 02:13:43 [INFO] train episode 36541: reward = -190.09, steps = 63 02:13:45 [INFO] train episode 36542: reward = -98.81, steps = 23 02:13:49 [INFO] train episode 36543: reward = -92.05, steps = 37 02:13:52 [INFO] train episode 36544: reward = -145.79, steps = 32 02:13:54 [INFO] train episode 36545: reward = -106.96, steps = 21 02:13:56 [INFO] train episode 36546: reward = -205.57, steps = 30 02:13:58 [INFO] train episode 36547: reward = -76.91, steps = 26 02:14:02 [INFO] train episode 36548: reward = -109.87, steps = 36 02:14:04 [INFO] train episode 36549: reward = -82.99, steps = 22 02:14:06 [INFO] train episode 36550: reward = -103.01, steps = 26 02:14:08 [INFO] train episode 36551: reward = -62.63, steps = 25 02:14:11 [INFO] train episode 36552: reward = -118.79, steps = 26 02:14:12 [INFO] train episode 36553: reward = -115.50, steps = 19 02:14:15 [INFO] train episode 36554: reward = -75.04, steps = 26 02:14:17 [INFO] train episode 36555: reward = -63.47, steps = 25 02:14:19 [INFO] train episode 36556: reward = -147.18, steps = 20 02:14:21 [INFO] train episode 36557: reward = -74.76, steps = 23 02:14:24 [INFO] train episode 36558: reward = -84.24, steps = 28 02:14:26 [INFO] train episode 36559: reward = -73.62, steps = 28 02:14:28 [INFO] train episode 36560: reward = -140.53, steps = 26 02:14:33 [INFO] train episode 36561: reward = -112.93, steps = 38 02:14:36 [INFO] train episode 36562: reward = -112.05, steps = 26 02:14:39 [INFO] train episode 36563: reward = -100.69, steps = 34 02:14:42 [INFO] train episode 36564: reward = -57.70, steps = 22 02:14:44 [INFO] train episode 36565: reward = -65.87, steps = 24 02:14:47 [INFO] train episode 36566: reward = -77.54, steps = 21 02:14:48 [INFO] train episode 36567: reward = -84.22, steps = 18 02:14:50 [INFO] train episode 36568: reward = -118.07, steps = 23 02:14:53 [INFO] train episode 36569: reward = -101.84, steps = 31 02:14:56 [INFO] train episode 36570: reward = -95.30, steps = 26 02:14:58 [INFO] train episode 36571: reward = -70.22, steps = 19 02:15:00 [INFO] train episode 36572: reward = -108.15, steps = 18 02:15:02 [INFO] train episode 36573: reward = -71.57, steps = 23 02:15:04 [INFO] train episode 36574: reward = -103.06, steps = 24 02:15:06 [INFO] train episode 36575: reward = -172.73, steps = 23 02:15:08 [INFO] train episode 36576: reward = -101.81, steps = 21 02:15:10 [INFO] train episode 36577: reward = -151.83, steps = 23 02:15:12 [INFO] train episode 36578: reward = -102.62, steps = 20 02:15:14 [INFO] train episode 36579: reward = -88.25, steps = 18 02:15:16 [INFO] train episode 36580: reward = -87.48, steps = 22 02:15:18 [INFO] train episode 36581: reward = -99.55, steps = 21 02:15:20 [INFO] train episode 36582: reward = -115.26, steps = 21 02:15:22 [INFO] train episode 36583: reward = -68.20, steps = 21 02:15:24 [INFO] train episode 36584: reward = -68.10, steps = 20 02:15:26 [INFO] train episode 36585: reward = -82.15, steps = 29 02:15:28 [INFO] train episode 36586: reward = -99.87, steps = 23 02:15:30 [INFO] train episode 36587: reward = -57.40, steps = 25 02:15:33 [INFO] train episode 36588: reward = -72.16, steps = 25 02:15:36 [INFO] train episode 36589: reward = -84.12, steps = 26 02:15:38 [INFO] train episode 36590: reward = -99.87, steps = 20 02:15:41 [INFO] train episode 36591: reward = -120.55, steps = 24 02:15:45 [INFO] train episode 36592: reward = -103.65, steps = 41 02:15:47 [INFO] train episode 36593: reward = -94.15, steps = 22 02:15:49 [INFO] train episode 36594: reward = -83.74, steps = 26 02:15:52 [INFO] train episode 36595: reward = -61.71, steps = 19 02:15:53 [INFO] train episode 36596: reward = -49.87, steps = 21 02:15:55 [INFO] train episode 36597: reward = -94.92, steps = 22 02:15:57 [INFO] train episode 36598: reward = -71.79, steps = 20 02:15:59 [INFO] train episode 36599: reward = -138.87, steps = 19 02:16:01 [INFO] train episode 36600: reward = -120.06, steps = 26 02:16:05 [INFO] train episode 36601: reward = -137.30, steps = 32 02:16:07 [INFO] train episode 36602: reward = -91.83, steps = 19 02:16:10 [INFO] train episode 36603: reward = -87.74, steps = 27 02:16:13 [INFO] train episode 36604: reward = -110.47, steps = 25 02:16:15 [INFO] train episode 36605: reward = -83.47, steps = 25 02:16:18 [INFO] train episode 36606: reward = -118.88, steps = 28 02:16:21 [INFO] train episode 36607: reward = -146.36, steps = 41 02:16:24 [INFO] train episode 36608: reward = -102.69, steps = 30 02:16:26 [INFO] train episode 36609: reward = -137.90, steps = 22 02:16:28 [INFO] train episode 36610: reward = -132.38, steps = 20 02:16:30 [INFO] train episode 36611: reward = -75.34, steps = 22 02:16:34 [INFO] train episode 36612: reward = -127.23, steps = 40 02:16:35 [INFO] train episode 36613: reward = -113.48, steps = 20 02:16:39 [INFO] train episode 36614: reward = -144.92, steps = 43 02:16:43 [INFO] train episode 36615: reward = -118.93, steps = 34 02:16:46 [INFO] train episode 36616: reward = -58.74, steps = 23 02:16:48 [INFO] train episode 36617: reward = -144.89, steps = 20 02:16:49 [INFO] train episode 36618: reward = -133.26, steps = 18 02:16:51 [INFO] train episode 36619: reward = -68.91, steps = 20 02:16:55 [INFO] train episode 36620: reward = -115.50, steps = 44 02:16:57 [INFO] train episode 36621: reward = -142.92, steps = 19 02:17:00 [INFO] train episode 36622: reward = -114.96, steps = 30 02:17:02 [INFO] train episode 36623: reward = -118.30, steps = 22 02:17:04 [INFO] train episode 36624: reward = -89.84, steps = 25 02:17:06 [INFO] train episode 36625: reward = -68.77, steps = 19 02:17:08 [INFO] train episode 36626: reward = -93.07, steps = 26 02:17:12 [INFO] train episode 36627: reward = -130.85, steps = 43 02:17:14 [INFO] train episode 36628: reward = -103.07, steps = 22 02:17:16 [INFO] train episode 36629: reward = -135.54, steps = 25 02:17:19 [INFO] train episode 36630: reward = -161.90, steps = 28 02:17:22 [INFO] train episode 36631: reward = -124.74, steps = 38 02:17:26 [INFO] train episode 36632: reward = -116.19, steps = 42 02:17:29 [INFO] train episode 36633: reward = -127.12, steps = 37 02:17:31 [INFO] train episode 36634: reward = -100.28, steps = 20 02:17:33 [INFO] train episode 36635: reward = -90.10, steps = 20 02:17:35 [INFO] train episode 36636: reward = -86.65, steps = 25 02:17:37 [INFO] train episode 36637: reward = -64.20, steps = 19 02:17:39 [INFO] train episode 36638: reward = -95.31, steps = 19 02:17:40 [INFO] train episode 36639: reward = -79.10, steps = 21 02:17:42 [INFO] train episode 36640: reward = -87.37, steps = 23 02:17:44 [INFO] train episode 36641: reward = -103.41, steps = 20 02:17:46 [INFO] train episode 36642: reward = -102.60, steps = 20 02:17:49 [INFO] train episode 36643: reward = -67.41, steps = 30 02:17:51 [INFO] train episode 36644: reward = -83.52, steps = 23 02:17:54 [INFO] train episode 36645: reward = -97.06, steps = 32 02:17:56 [INFO] train episode 36646: reward = -46.77, steps = 21 02:18:01 [INFO] train episode 36647: reward = -106.46, steps = 60 02:18:03 [INFO] train episode 36648: reward = -146.39, steps = 19 02:18:05 [INFO] train episode 36649: reward = -151.84, steps = 21 02:18:08 [INFO] train episode 36650: reward = -86.72, steps = 38 02:18:12 [INFO] train episode 36651: reward = -86.23, steps = 39 02:18:14 [INFO] train episode 36652: reward = -86.23, steps = 23 02:18:17 [INFO] train episode 36653: reward = -52.21, steps = 21 02:18:19 [INFO] train episode 36654: reward = -88.01, steps = 19 02:18:21 [INFO] train episode 36655: reward = -109.35, steps = 23 02:18:23 [INFO] train episode 36656: reward = -135.92, steps = 24 02:18:26 [INFO] train episode 36657: reward = -51.99, steps = 32 02:18:29 [INFO] train episode 36658: reward = -105.53, steps = 36 02:18:32 [INFO] train episode 36659: reward = -110.56, steps = 27 02:18:33 [INFO] train episode 36660: reward = -75.23, steps = 19 02:18:35 [INFO] train episode 36661: reward = -78.87, steps = 19 02:18:37 [INFO] train episode 36662: reward = -104.33, steps = 23 02:18:41 [INFO] train episode 36663: reward = -63.10, steps = 32 02:18:43 [INFO] train episode 36664: reward = -96.55, steps = 23 02:18:45 [INFO] train episode 36665: reward = -57.78, steps = 27 02:18:47 [INFO] train episode 36666: reward = -61.84, steps = 20 02:18:50 [INFO] train episode 36667: reward = -131.81, steps = 38 02:18:53 [INFO] train episode 36668: reward = -125.67, steps = 33 02:18:56 [INFO] train episode 36669: reward = -149.02, steps = 28 02:18:58 [INFO] train episode 36670: reward = -119.62, steps = 26 02:19:01 [INFO] train episode 36671: reward = -95.73, steps = 25 02:19:03 [INFO] train episode 36672: reward = -125.05, steps = 22 02:19:04 [INFO] train episode 36673: reward = -161.85, steps = 18 02:19:06 [INFO] train episode 36674: reward = -72.15, steps = 20 02:19:10 [INFO] train episode 36675: reward = -111.88, steps = 40 02:19:12 [INFO] train episode 36676: reward = -90.19, steps = 22 02:19:14 [INFO] train episode 36677: reward = -82.82, steps = 19 02:19:16 [INFO] train episode 36678: reward = -100.61, steps = 31 02:19:21 [INFO] train episode 36679: reward = -58.88, steps = 28 02:19:23 [INFO] train episode 36680: reward = -116.64, steps = 22 02:19:26 [INFO] train episode 36681: reward = -116.60, steps = 25 02:19:27 [INFO] train episode 36682: reward = -95.64, steps = 19 02:19:29 [INFO] train episode 36683: reward = -81.76, steps = 15 02:19:31 [INFO] train episode 36684: reward = -164.17, steps = 21 02:19:35 [INFO] train episode 36685: reward = -101.18, steps = 23 02:19:39 [INFO] train episode 36686: reward = -142.66, steps = 22 02:19:42 [INFO] train episode 36687: reward = -91.05, steps = 20 02:19:45 [INFO] train episode 36688: reward = -84.70, steps = 20 02:19:48 [INFO] train episode 36689: reward = -130.15, steps = 19 02:19:51 [INFO] train episode 36690: reward = -105.59, steps = 19 02:19:58 [INFO] train episode 36691: reward = -67.00, steps = 36 02:20:03 [INFO] train episode 36692: reward = -93.63, steps = 26 02:20:08 [INFO] train episode 36693: reward = -154.68, steps = 30 02:20:13 [INFO] train episode 36694: reward = -200.83, steps = 37 02:20:16 [INFO] train episode 36695: reward = -92.38, steps = 19 02:20:22 [INFO] train episode 36696: reward = -116.96, steps = 39 02:20:27 [INFO] train episode 36697: reward = -96.79, steps = 29 02:20:31 [INFO] train episode 36698: reward = -91.41, steps = 22 02:20:34 [INFO] train episode 36699: reward = -102.58, steps = 20 02:20:37 [INFO] train episode 36700: reward = -133.94, steps = 31 02:20:39 [INFO] train episode 36701: reward = -173.60, steps = 20 02:20:42 [INFO] train episode 36702: reward = -167.69, steps = 38 02:20:43 [INFO] train episode 36703: reward = -96.73, steps = 19 02:20:46 [INFO] train episode 36704: reward = -49.75, steps = 22 02:20:50 [INFO] train episode 36705: reward = -94.78, steps = 44 02:20:51 [INFO] train episode 36706: reward = -103.27, steps = 19 02:20:55 [INFO] train episode 36707: reward = -77.56, steps = 46 02:20:58 [INFO] train episode 36708: reward = -87.17, steps = 26 02:21:00 [INFO] train episode 36709: reward = -119.79, steps = 21 02:21:02 [INFO] train episode 36710: reward = -80.86, steps = 19 02:21:04 [INFO] train episode 36711: reward = -78.11, steps = 19 02:21:07 [INFO] train episode 36712: reward = -183.56, steps = 32 02:21:09 [INFO] train episode 36713: reward = -60.14, steps = 19 02:21:11 [INFO] train episode 36714: reward = -123.36, steps = 19 02:21:13 [INFO] train episode 36715: reward = -115.15, steps = 21 02:21:18 [INFO] train episode 36716: reward = -214.44, steps = 52 02:21:19 [INFO] train episode 36717: reward = -114.87, steps = 19 02:21:22 [INFO] train episode 36718: reward = -82.13, steps = 31 02:21:24 [INFO] train episode 36719: reward = -111.33, steps = 23 02:21:27 [INFO] train episode 36720: reward = -93.85, steps = 34 02:21:31 [INFO] train episode 36721: reward = -139.88, steps = 40 02:21:33 [INFO] train episode 36722: reward = -66.30, steps = 33 02:21:35 [INFO] train episode 36723: reward = -121.81, steps = 19 02:21:38 [INFO] train episode 36724: reward = -144.47, steps = 29 02:21:42 [INFO] train episode 36725: reward = -89.55, steps = 44 02:21:43 [INFO] train episode 36726: reward = -88.95, steps = 20 02:21:46 [INFO] train episode 36727: reward = -55.57, steps = 27 02:21:48 [INFO] train episode 36728: reward = -57.77, steps = 21 02:21:50 [INFO] train episode 36729: reward = -96.00, steps = 26 02:21:52 [INFO] train episode 36730: reward = -76.58, steps = 27 02:21:54 [INFO] train episode 36731: reward = -44.76, steps = 21 02:21:57 [INFO] train episode 36732: reward = -96.95, steps = 23 02:21:59 [INFO] train episode 36733: reward = -62.13, steps = 25 02:22:00 [INFO] train episode 36734: reward = -78.88, steps = 19 02:22:03 [INFO] train episode 36735: reward = -69.98, steps = 30 02:22:05 [INFO] train episode 36736: reward = -55.25, steps = 25 02:22:08 [INFO] train episode 36737: reward = -92.33, steps = 30 02:22:09 [INFO] train episode 36738: reward = -81.89, steps = 20 02:22:12 [INFO] train episode 36739: reward = -97.82, steps = 22 02:22:14 [INFO] train episode 36740: reward = -86.16, steps = 29 02:22:16 [INFO] train episode 36741: reward = -53.14, steps = 27 02:22:19 [INFO] train episode 36742: reward = -119.05, steps = 28 02:22:22 [INFO] train episode 36743: reward = -82.24, steps = 35 02:22:25 [INFO] train episode 36744: reward = -148.00, steps = 37 02:22:27 [INFO] train episode 36745: reward = -150.35, steps = 19 02:22:30 [INFO] train episode 36746: reward = -117.81, steps = 30 02:22:32 [INFO] train episode 36747: reward = -133.72, steps = 23 02:22:34 [INFO] train episode 36748: reward = -123.49, steps = 25 02:22:35 [INFO] train episode 36749: reward = -67.25, steps = 20 02:22:38 [INFO] train episode 36750: reward = -174.23, steps = 24 02:22:41 [INFO] train episode 36751: reward = -77.04, steps = 36 02:22:43 [INFO] train episode 36752: reward = -51.16, steps = 19 02:22:45 [INFO] train episode 36753: reward = -60.38, steps = 20 02:22:47 [INFO] train episode 36754: reward = -69.78, steps = 23 02:22:50 [INFO] train episode 36755: reward = -101.79, steps = 37 02:22:52 [INFO] train episode 36756: reward = -120.02, steps = 28 02:22:54 [INFO] train episode 36757: reward = -66.58, steps = 25 02:22:57 [INFO] train episode 36758: reward = -138.50, steps = 27 02:22:59 [INFO] train episode 36759: reward = -124.79, steps = 22 02:23:02 [INFO] train episode 36760: reward = -129.94, steps = 35 02:23:05 [INFO] train episode 36761: reward = -107.76, steps = 35 02:23:07 [INFO] train episode 36762: reward = -103.84, steps = 27 02:23:10 [INFO] train episode 36763: reward = -96.13, steps = 20 02:23:13 [INFO] train episode 36764: reward = -141.78, steps = 42 02:23:15 [INFO] train episode 36765: reward = -77.47, steps = 21 02:23:19 [INFO] train episode 36766: reward = -78.69, steps = 45 02:23:21 [INFO] train episode 36767: reward = -83.79, steps = 24 02:23:25 [INFO] train episode 36768: reward = -144.83, steps = 41 02:23:28 [INFO] train episode 36769: reward = -101.83, steps = 32 02:23:30 [INFO] train episode 36770: reward = -79.09, steps = 30 02:23:33 [INFO] train episode 36771: reward = -99.73, steps = 24 02:23:35 [INFO] train episode 36772: reward = -106.11, steps = 24 02:23:38 [INFO] train episode 36773: reward = -77.15, steps = 41 02:23:40 [INFO] train episode 36774: reward = -131.91, steps = 20 02:23:42 [INFO] train episode 36775: reward = -104.04, steps = 21 02:23:44 [INFO] train episode 36776: reward = -88.09, steps = 25 02:23:48 [INFO] train episode 36777: reward = -171.86, steps = 34 02:23:51 [INFO] train episode 36778: reward = -112.73, steps = 37 02:23:53 [INFO] train episode 36779: reward = -154.44, steps = 20 02:23:55 [INFO] train episode 36780: reward = -98.10, steps = 28 02:24:00 [INFO] train episode 36781: reward = -109.95, steps = 54 02:24:02 [INFO] train episode 36782: reward = -63.90, steps = 31 02:24:05 [INFO] train episode 36783: reward = -111.98, steps = 19 02:24:07 [INFO] train episode 36784: reward = -77.57, steps = 26 02:24:09 [INFO] train episode 36785: reward = -144.77, steps = 30 02:24:12 [INFO] train episode 36786: reward = -86.10, steps = 26 02:24:14 [INFO] train episode 36787: reward = -107.48, steps = 32 02:24:16 [INFO] train episode 36788: reward = -80.96, steps = 23 02:24:20 [INFO] train episode 36789: reward = -207.37, steps = 42 02:24:22 [INFO] train episode 36790: reward = -107.98, steps = 22 02:24:25 [INFO] train episode 36791: reward = -231.21, steps = 30 02:24:27 [INFO] train episode 36792: reward = -81.12, steps = 30 02:24:29 [INFO] train episode 36793: reward = -88.56, steps = 21 02:24:32 [INFO] train episode 36794: reward = -78.95, steps = 26 02:24:34 [INFO] train episode 36795: reward = -98.75, steps = 26 02:24:36 [INFO] train episode 36796: reward = -70.80, steps = 22 02:24:38 [INFO] train episode 36797: reward = -108.89, steps = 26 02:24:40 [INFO] train episode 36798: reward = -92.61, steps = 24 02:24:42 [INFO] train episode 36799: reward = -102.76, steps = 20 02:24:45 [INFO] train episode 36800: reward = -87.39, steps = 33 02:24:49 [INFO] train episode 36801: reward = -172.72, steps = 41 02:24:50 [INFO] train episode 36802: reward = -73.90, steps = 20 02:24:52 [INFO] train episode 36803: reward = -137.78, steps = 20 02:24:54 [INFO] train episode 36804: reward = -102.91, steps = 21 02:24:56 [INFO] train episode 36805: reward = -60.23, steps = 21 02:24:58 [INFO] train episode 36806: reward = -67.76, steps = 22 02:25:00 [INFO] train episode 36807: reward = -88.62, steps = 25 02:25:02 [INFO] train episode 36808: reward = -54.62, steps = 19 02:25:04 [INFO] train episode 36809: reward = -72.76, steps = 21 02:25:06 [INFO] train episode 36810: reward = -107.56, steps = 22 02:25:09 [INFO] train episode 36811: reward = -77.83, steps = 33 02:25:11 [INFO] train episode 36812: reward = -95.71, steps = 24 02:25:13 [INFO] train episode 36813: reward = -98.04, steps = 22 02:25:15 [INFO] train episode 36814: reward = -132.65, steps = 24 02:25:17 [INFO] train episode 36815: reward = -114.82, steps = 24 02:25:22 [INFO] train episode 36816: reward = -214.05, steps = 53 02:25:24 [INFO] train episode 36817: reward = -79.91, steps = 22 02:25:26 [INFO] train episode 36818: reward = -82.23, steps = 21 02:25:28 [INFO] train episode 36819: reward = -115.33, steps = 25 02:25:31 [INFO] train episode 36820: reward = -79.66, steps = 30 02:25:33 [INFO] train episode 36821: reward = -67.34, steps = 23 02:25:36 [INFO] train episode 36822: reward = -74.29, steps = 37 02:25:39 [INFO] train episode 36823: reward = -134.41, steps = 33 02:25:43 [INFO] train episode 36824: reward = -80.58, steps = 41 02:25:44 [INFO] train episode 36825: reward = -73.05, steps = 19 02:25:46 [INFO] train episode 36826: reward = -60.39, steps = 20 02:25:48 [INFO] train episode 36827: reward = -85.12, steps = 22 02:25:50 [INFO] train episode 36828: reward = -107.89, steps = 20 02:25:52 [INFO] train episode 36829: reward = -90.94, steps = 24 02:25:54 [INFO] train episode 36830: reward = -93.80, steps = 25 02:25:57 [INFO] train episode 36831: reward = -89.15, steps = 25 02:25:58 [INFO] train episode 36832: reward = -60.62, steps = 20 02:26:01 [INFO] train episode 36833: reward = -91.48, steps = 28 02:26:04 [INFO] train episode 36834: reward = -141.16, steps = 27 02:26:07 [INFO] train episode 36835: reward = -97.28, steps = 33 02:26:09 [INFO] train episode 36836: reward = -90.74, steps = 31 02:26:11 [INFO] train episode 36837: reward = -82.57, steps = 22 02:26:13 [INFO] train episode 36838: reward = -110.90, steps = 20 02:26:17 [INFO] train episode 36839: reward = -93.87, steps = 42 02:26:19 [INFO] train episode 36840: reward = -106.86, steps = 30 02:26:22 [INFO] train episode 36841: reward = -165.89, steps = 28 02:26:23 [INFO] train episode 36842: reward = -62.41, steps = 19 02:26:26 [INFO] train episode 36843: reward = -89.15, steps = 30 02:26:29 [INFO] train episode 36844: reward = -84.09, steps = 27 02:26:31 [INFO] train episode 36845: reward = -76.25, steps = 20 02:26:33 [INFO] train episode 36846: reward = -138.09, steps = 23 02:26:34 [INFO] train episode 36847: reward = -91.76, steps = 22 02:26:36 [INFO] train episode 36848: reward = -79.41, steps = 22 02:26:39 [INFO] train episode 36849: reward = -123.46, steps = 25 02:26:40 [INFO] train episode 36850: reward = -78.01, steps = 20 02:26:43 [INFO] train episode 36851: reward = -60.58, steps = 26 02:26:45 [INFO] train episode 36852: reward = -94.31, steps = 21 02:26:47 [INFO] train episode 36853: reward = -110.95, steps = 20 02:26:48 [INFO] train episode 36854: reward = -90.42, steps = 19 02:26:51 [INFO] train episode 36855: reward = -85.12, steps = 29 02:26:53 [INFO] train episode 36856: reward = -91.60, steps = 29 02:26:56 [INFO] train episode 36857: reward = -76.04, steps = 32 02:26:58 [INFO] train episode 36858: reward = -58.40, steps = 21 02:27:01 [INFO] train episode 36859: reward = -57.04, steps = 35 02:27:04 [INFO] train episode 36860: reward = -122.33, steps = 26 02:27:06 [INFO] train episode 36861: reward = -104.90, steps = 33 02:27:08 [INFO] train episode 36862: reward = -68.08, steps = 21 02:27:10 [INFO] train episode 36863: reward = -65.37, steps = 22 02:27:12 [INFO] train episode 36864: reward = -82.26, steps = 20 02:27:14 [INFO] train episode 36865: reward = -71.98, steps = 25 02:27:18 [INFO] train episode 36866: reward = -103.07, steps = 44 02:27:21 [INFO] train episode 36867: reward = -115.90, steps = 30 02:27:24 [INFO] train episode 36868: reward = -79.31, steps = 36 02:27:26 [INFO] train episode 36869: reward = -84.57, steps = 20 02:27:28 [INFO] train episode 36870: reward = -163.85, steps = 22 02:27:29 [INFO] train episode 36871: reward = -113.47, steps = 20 02:27:32 [INFO] train episode 36872: reward = -89.25, steps = 26 02:27:36 [INFO] train episode 36873: reward = -176.02, steps = 43 02:27:39 [INFO] train episode 36874: reward = -181.33, steps = 40 02:27:41 [INFO] train episode 36875: reward = -96.22, steps = 23 02:27:43 [INFO] train episode 36876: reward = -73.29, steps = 19 02:27:45 [INFO] train episode 36877: reward = -57.80, steps = 21 02:27:47 [INFO] train episode 36878: reward = -59.65, steps = 29 02:27:50 [INFO] train episode 36879: reward = -58.24, steps = 27 02:27:52 [INFO] train episode 36880: reward = -160.07, steps = 24 02:27:54 [INFO] train episode 36881: reward = -155.37, steps = 23 02:27:57 [INFO] train episode 36882: reward = -82.92, steps = 32 02:27:59 [INFO] train episode 36883: reward = -56.55, steps = 28 02:28:01 [INFO] train episode 36884: reward = -72.61, steps = 20 02:28:03 [INFO] train episode 36885: reward = -55.10, steps = 19 02:28:05 [INFO] train episode 36886: reward = -72.66, steps = 21 02:28:08 [INFO] train episode 36887: reward = -102.08, steps = 40 02:28:10 [INFO] train episode 36888: reward = -83.08, steps = 18 02:28:13 [INFO] train episode 36889: reward = -112.54, steps = 43 02:28:15 [INFO] train episode 36890: reward = -117.53, steps = 22 02:28:18 [INFO] train episode 36891: reward = -94.90, steps = 34 02:28:21 [INFO] train episode 36892: reward = -79.98, steps = 26 02:28:23 [INFO] train episode 36893: reward = -110.28, steps = 19 02:28:26 [INFO] train episode 36894: reward = -154.72, steps = 39 02:28:28 [INFO] train episode 36895: reward = -91.30, steps = 21 02:28:30 [INFO] train episode 36896: reward = -69.47, steps = 21 02:28:33 [INFO] train episode 36897: reward = -169.51, steps = 44 02:28:36 [INFO] train episode 36898: reward = -78.02, steps = 26 02:28:38 [INFO] train episode 36899: reward = -99.65, steps = 22 02:28:40 [INFO] train episode 36900: reward = -66.70, steps = 22 02:28:42 [INFO] train episode 36901: reward = -67.49, steps = 20 02:28:43 [INFO] train episode 36902: reward = -75.90, steps = 21 02:28:45 [INFO] train episode 36903: reward = -71.17, steps = 21 02:28:47 [INFO] train episode 36904: reward = -101.24, steps = 27 02:28:52 [INFO] train episode 36905: reward = -169.50, steps = 50 02:28:56 [INFO] train episode 36906: reward = -136.58, steps = 42 02:28:59 [INFO] train episode 36907: reward = -71.16, steps = 26 02:29:01 [INFO] train episode 36908: reward = -76.37, steps = 23 02:29:03 [INFO] train episode 36909: reward = -92.43, steps = 22 02:29:05 [INFO] train episode 36910: reward = -114.74, steps = 22 02:29:10 [INFO] train episode 36911: reward = -134.67, steps = 45 02:29:12 [INFO] train episode 36912: reward = -151.37, steps = 32 02:29:15 [INFO] train episode 36913: reward = -85.51, steps = 26 02:29:17 [INFO] train episode 36914: reward = -78.67, steps = 30 02:29:20 [INFO] train episode 36915: reward = -110.02, steps = 26 02:29:22 [INFO] train episode 36916: reward = -69.56, steps = 23 02:29:24 [INFO] train episode 36917: reward = -111.66, steps = 22 02:29:26 [INFO] train episode 36918: reward = -88.54, steps = 25 02:29:29 [INFO] train episode 36919: reward = -49.36, steps = 30 02:29:30 [INFO] train episode 36920: reward = -87.46, steps = 20 02:29:32 [INFO] train episode 36921: reward = -103.49, steps = 23 02:29:35 [INFO] train episode 36922: reward = -150.89, steps = 30 02:29:37 [INFO] train episode 36923: reward = -114.57, steps = 20 02:29:39 [INFO] train episode 36924: reward = -73.38, steps = 21 02:29:40 [INFO] train episode 36925: reward = -116.60, steps = 20 02:29:43 [INFO] train episode 36926: reward = -91.86, steps = 22 02:29:45 [INFO] train episode 36927: reward = -147.02, steps = 26 02:29:47 [INFO] train episode 36928: reward = -127.47, steps = 27 02:29:49 [INFO] train episode 36929: reward = -86.61, steps = 22 02:29:51 [INFO] train episode 36930: reward = -83.73, steps = 19 02:29:55 [INFO] train episode 36931: reward = -112.56, steps = 46 02:29:57 [INFO] train episode 36932: reward = -94.51, steps = 29 02:29:59 [INFO] train episode 36933: reward = -49.54, steps = 20 02:30:01 [INFO] train episode 36934: reward = -107.91, steps = 20 02:30:03 [INFO] train episode 36935: reward = -124.32, steps = 20 02:30:04 [INFO] train episode 36936: reward = -84.80, steps = 20 02:30:06 [INFO] train episode 36937: reward = -70.93, steps = 20 02:30:08 [INFO] train episode 36938: reward = -73.60, steps = 21 02:30:10 [INFO] train episode 36939: reward = -132.43, steps = 21 02:30:12 [INFO] train episode 36940: reward = -77.00, steps = 30 02:30:16 [INFO] train episode 36941: reward = -142.79, steps = 32 02:30:18 [INFO] train episode 36942: reward = -91.83, steps = 25 02:30:20 [INFO] train episode 36943: reward = -105.10, steps = 20 02:30:22 [INFO] train episode 36944: reward = -129.89, steps = 28 02:30:24 [INFO] train episode 36945: reward = -133.95, steps = 26 02:30:26 [INFO] train episode 36946: reward = -81.06, steps = 23 02:30:28 [INFO] train episode 36947: reward = -107.41, steps = 22 02:30:30 [INFO] train episode 36948: reward = -48.69, steps = 22 02:30:33 [INFO] train episode 36949: reward = -130.03, steps = 28 02:30:34 [INFO] train episode 36950: reward = -78.25, steps = 19 02:30:37 [INFO] train episode 36951: reward = -110.00, steps = 32 02:30:39 [INFO] train episode 36952: reward = -140.95, steps = 20 02:30:41 [INFO] train episode 36953: reward = -124.73, steps = 20 02:30:43 [INFO] train episode 36954: reward = -136.37, steps = 33 02:30:47 [INFO] train episode 36955: reward = -122.87, steps = 31 02:30:48 [INFO] train episode 36956: reward = -98.92, steps = 21 02:30:50 [INFO] train episode 36957: reward = -93.75, steps = 22 02:30:52 [INFO] train episode 36958: reward = -73.68, steps = 20 02:30:54 [INFO] train episode 36959: reward = -125.70, steps = 21 02:30:55 [INFO] train episode 36960: reward = -72.00, steps = 18 02:30:57 [INFO] train episode 36961: reward = -49.77, steps = 21 02:30:59 [INFO] train episode 36962: reward = -106.36, steps = 19 02:31:02 [INFO] train episode 36963: reward = -73.27, steps = 34 02:31:04 [INFO] train episode 36964: reward = -68.22, steps = 20 02:31:07 [INFO] train episode 36965: reward = -79.87, steps = 29 02:31:09 [INFO] train episode 36966: reward = -108.09, steps = 20 02:31:10 [INFO] train episode 36967: reward = -80.29, steps = 22 02:31:12 [INFO] train episode 36968: reward = -51.48, steps = 22 02:31:14 [INFO] train episode 36969: reward = -98.44, steps = 18 02:31:16 [INFO] train episode 36970: reward = -69.29, steps = 26 02:31:18 [INFO] train episode 36971: reward = -83.30, steps = 19 02:31:21 [INFO] train episode 36972: reward = -104.05, steps = 26 02:31:23 [INFO] train episode 36973: reward = -132.44, steps = 28 02:31:25 [INFO] train episode 36974: reward = -113.89, steps = 27 02:31:28 [INFO] train episode 36975: reward = -94.88, steps = 32 02:31:30 [INFO] train episode 36976: reward = -85.83, steps = 22 02:31:32 [INFO] train episode 36977: reward = -75.73, steps = 24 02:31:34 [INFO] train episode 36978: reward = -101.99, steps = 23 02:31:36 [INFO] train episode 36979: reward = -109.64, steps = 22 02:31:38 [INFO] train episode 36980: reward = -90.18, steps = 19 02:31:40 [INFO] train episode 36981: reward = -112.56, steps = 27 02:31:42 [INFO] train episode 36982: reward = -93.83, steps = 20 02:31:44 [INFO] train episode 36983: reward = -57.87, steps = 23 02:31:47 [INFO] train episode 36984: reward = -108.95, steps = 31 02:31:49 [INFO] train episode 36985: reward = -104.23, steps = 18 02:31:52 [INFO] train episode 36986: reward = -140.79, steps = 33 02:31:55 [INFO] train episode 36987: reward = -74.89, steps = 29 02:31:57 [INFO] train episode 36988: reward = -100.09, steps = 19 02:32:00 [INFO] train episode 36989: reward = -104.42, steps = 40 02:32:02 [INFO] train episode 36990: reward = -72.83, steps = 19 02:32:03 [INFO] train episode 36991: reward = -91.28, steps = 19 02:32:06 [INFO] train episode 36992: reward = -74.77, steps = 25 02:32:08 [INFO] train episode 36993: reward = -76.95, steps = 28 02:32:11 [INFO] train episode 36994: reward = -150.36, steps = 30 02:32:13 [INFO] train episode 36995: reward = -63.58, steps = 20 02:32:14 [INFO] train episode 36996: reward = -76.38, steps = 20 02:32:16 [INFO] train episode 36997: reward = -83.23, steps = 24 02:32:21 [INFO] train episode 36998: reward = -161.04, steps = 47 02:32:23 [INFO] train episode 36999: reward = -82.93, steps = 27 02:32:25 [INFO] train episode 37000: reward = -94.42, steps = 19 02:32:27 [INFO] train episode 37001: reward = -80.71, steps = 25 02:32:29 [INFO] train episode 37002: reward = -93.45, steps = 23 02:32:31 [INFO] train episode 37003: reward = -100.29, steps = 19 02:32:33 [INFO] train episode 37004: reward = -85.95, steps = 29 02:32:36 [INFO] train episode 37005: reward = -71.29, steps = 28 02:32:38 [INFO] train episode 37006: reward = -50.04, steps = 22 02:32:40 [INFO] train episode 37007: reward = -62.07, steps = 25 02:32:46 [INFO] train episode 37008: reward = -191.15, steps = 60 02:32:48 [INFO] train episode 37009: reward = -102.98, steps = 29 02:32:50 [INFO] train episode 37010: reward = -107.16, steps = 20 02:32:52 [INFO] train episode 37011: reward = -85.65, steps = 23 02:32:54 [INFO] train episode 37012: reward = -95.56, steps = 25 02:32:56 [INFO] train episode 37013: reward = -79.17, steps = 21 02:33:00 [INFO] train episode 37014: reward = -110.73, steps = 49 02:33:02 [INFO] train episode 37015: reward = -90.01, steps = 19 02:33:04 [INFO] train episode 37016: reward = -93.67, steps = 25 02:33:06 [INFO] train episode 37017: reward = -48.98, steps = 20 02:33:09 [INFO] train episode 37018: reward = -72.52, steps = 27 02:33:11 [INFO] train episode 37019: reward = -62.63, steps = 26 02:33:13 [INFO] train episode 37020: reward = -151.08, steps = 25 02:33:15 [INFO] train episode 37021: reward = -85.97, steps = 22 02:33:18 [INFO] train episode 37022: reward = -70.61, steps = 29 02:33:20 [INFO] train episode 37023: reward = -75.61, steps = 23 02:33:22 [INFO] train episode 37024: reward = -98.72, steps = 30 02:33:24 [INFO] train episode 37025: reward = -93.55, steps = 20 02:33:26 [INFO] train episode 37026: reward = -88.03, steps = 22 02:33:28 [INFO] train episode 37027: reward = -123.22, steps = 21 02:33:30 [INFO] train episode 37028: reward = -82.67, steps = 19 02:33:32 [INFO] train episode 37029: reward = -96.20, steps = 22 02:33:34 [INFO] train episode 37030: reward = -96.40, steps = 27 02:33:36 [INFO] train episode 37031: reward = -107.70, steps = 21 02:33:38 [INFO] train episode 37032: reward = -63.92, steps = 25 02:33:40 [INFO] train episode 37033: reward = -62.44, steps = 20 02:33:44 [INFO] train episode 37034: reward = -103.63, steps = 39 02:33:46 [INFO] train episode 37035: reward = -132.62, steps = 31 02:33:48 [INFO] train episode 37036: reward = -78.00, steps = 21 02:33:54 [INFO] train episode 37037: reward = -121.17, steps = 65 02:33:56 [INFO] train episode 37038: reward = -93.74, steps = 20 02:33:57 [INFO] train episode 37039: reward = -143.96, steps = 23 02:34:00 [INFO] train episode 37040: reward = -97.87, steps = 23 02:34:02 [INFO] train episode 37041: reward = -39.13, steps = 20 02:34:04 [INFO] train episode 37042: reward = -72.02, steps = 27 02:34:06 [INFO] train episode 37043: reward = -51.64, steps = 29 02:34:08 [INFO] train episode 37044: reward = -64.56, steps = 24 02:34:11 [INFO] train episode 37045: reward = -95.19, steps = 25 02:34:13 [INFO] train episode 37046: reward = -99.64, steps = 24 02:34:15 [INFO] train episode 37047: reward = -89.10, steps = 25 02:34:17 [INFO] train episode 37048: reward = -118.81, steps = 21 02:34:20 [INFO] train episode 37049: reward = -80.23, steps = 36 02:34:22 [INFO] train episode 37050: reward = -142.73, steps = 18 02:34:25 [INFO] train episode 37051: reward = -145.00, steps = 40 02:34:28 [INFO] train episode 37052: reward = -121.94, steps = 36 02:34:30 [INFO] train episode 37053: reward = -92.89, steps = 18 02:34:32 [INFO] train episode 37054: reward = -82.28, steps = 19 02:34:34 [INFO] train episode 37055: reward = -113.25, steps = 26 02:34:36 [INFO] train episode 37056: reward = -124.80, steps = 21 02:34:38 [INFO] train episode 37057: reward = -109.80, steps = 21 02:34:40 [INFO] train episode 37058: reward = -70.00, steps = 22 02:34:42 [INFO] train episode 37059: reward = -117.57, steps = 21 02:34:45 [INFO] train episode 37060: reward = -138.43, steps = 37 02:34:49 [INFO] train episode 37061: reward = -97.36, steps = 33 02:34:50 [INFO] train episode 37062: reward = -96.93, steps = 16 02:34:52 [INFO] train episode 37063: reward = -76.52, steps = 23 02:34:54 [INFO] train episode 37064: reward = -68.93, steps = 20 02:34:55 [INFO] train episode 37065: reward = -77.85, steps = 18 02:34:57 [INFO] train episode 37066: reward = -59.36, steps = 24 02:34:59 [INFO] train episode 37067: reward = -100.32, steps = 25 02:35:02 [INFO] train episode 37068: reward = -91.31, steps = 25 02:35:04 [INFO] train episode 37069: reward = -98.17, steps = 21 02:35:07 [INFO] train episode 37070: reward = -67.83, steps = 32 02:35:09 [INFO] train episode 37071: reward = -91.44, steps = 20 02:35:11 [INFO] train episode 37072: reward = -92.46, steps = 22 02:35:13 [INFO] train episode 37073: reward = -99.68, steps = 24 02:35:15 [INFO] train episode 37074: reward = -101.95, steps = 23 02:35:16 [INFO] train episode 37075: reward = -117.35, steps = 20 02:35:19 [INFO] train episode 37076: reward = -67.31, steps = 23 02:35:21 [INFO] train episode 37077: reward = -82.96, steps = 22 02:35:23 [INFO] train episode 37078: reward = -89.04, steps = 24 02:35:27 [INFO] train episode 37079: reward = -187.83, steps = 48 02:35:29 [INFO] train episode 37080: reward = -51.70, steps = 20 02:35:31 [INFO] train episode 37081: reward = -81.11, steps = 27 02:35:35 [INFO] train episode 37082: reward = -113.71, steps = 45 02:35:38 [INFO] train episode 37083: reward = -157.19, steps = 27 02:35:41 [INFO] train episode 37084: reward = -87.21, steps = 39 02:35:43 [INFO] train episode 37085: reward = -144.47, steps = 20 02:35:45 [INFO] train episode 37086: reward = -86.33, steps = 24 02:35:47 [INFO] train episode 37087: reward = -71.39, steps = 30 02:35:52 [INFO] train episode 37088: reward = -111.09, steps = 50 02:35:54 [INFO] train episode 37089: reward = -100.32, steps = 28 02:35:57 [INFO] train episode 37090: reward = -109.37, steps = 37 02:35:59 [INFO] train episode 37091: reward = -83.90, steps = 23 02:36:02 [INFO] train episode 37092: reward = -127.42, steps = 32 02:36:04 [INFO] train episode 37093: reward = -76.84, steps = 19 02:36:07 [INFO] train episode 37094: reward = -86.02, steps = 30 02:36:09 [INFO] train episode 37095: reward = -48.86, steps = 28 02:36:12 [INFO] train episode 37096: reward = -117.01, steps = 28 02:36:15 [INFO] train episode 37097: reward = -102.55, steps = 39 02:36:17 [INFO] train episode 37098: reward = -63.30, steps = 19 02:36:19 [INFO] train episode 37099: reward = -71.12, steps = 25 02:36:21 [INFO] train episode 37100: reward = -60.25, steps = 21 02:36:22 [INFO] train episode 37101: reward = -106.52, steps = 19 02:36:25 [INFO] train episode 37102: reward = -117.07, steps = 26 02:36:28 [INFO] train episode 37103: reward = -140.17, steps = 40 02:36:32 [INFO] train episode 37104: reward = -116.03, steps = 40 02:36:33 [INFO] train episode 37105: reward = -98.64, steps = 20 02:36:35 [INFO] train episode 37106: reward = -69.06, steps = 23 02:36:37 [INFO] train episode 37107: reward = -61.13, steps = 21 02:36:39 [INFO] train episode 37108: reward = -205.85, steps = 23 02:36:41 [INFO] train episode 37109: reward = -77.40, steps = 22 02:36:44 [INFO] train episode 37110: reward = -140.62, steps = 34 02:36:46 [INFO] train episode 37111: reward = -52.15, steps = 23 02:36:48 [INFO] train episode 37112: reward = -90.54, steps = 19 02:36:51 [INFO] train episode 37113: reward = -58.76, steps = 31 02:36:53 [INFO] train episode 37114: reward = -104.18, steps = 28 02:36:56 [INFO] train episode 37115: reward = -120.47, steps = 28 02:36:58 [INFO] train episode 37116: reward = -124.53, steps = 21 02:36:59 [INFO] train episode 37117: reward = -78.34, steps = 19 02:37:01 [INFO] train episode 37118: reward = -109.93, steps = 22 02:37:04 [INFO] train episode 37119: reward = -103.51, steps = 33 02:37:06 [INFO] train episode 37120: reward = -101.04, steps = 24 02:37:08 [INFO] train episode 37121: reward = -168.71, steps = 23 02:37:10 [INFO] train episode 37122: reward = -67.37, steps = 23 02:37:15 [INFO] train episode 37123: reward = -112.70, steps = 46 02:37:17 [INFO] train episode 37124: reward = -80.26, steps = 23 02:37:20 [INFO] train episode 37125: reward = -79.79, steps = 35 02:37:24 [INFO] train episode 37126: reward = -85.90, steps = 49 02:37:27 [INFO] train episode 37127: reward = -125.54, steps = 40 02:37:30 [INFO] train episode 37128: reward = -114.89, steps = 23 02:37:31 [INFO] train episode 37129: reward = -78.79, steps = 20 02:37:34 [INFO] train episode 37130: reward = -110.64, steps = 26 02:37:36 [INFO] train episode 37131: reward = -54.05, steps = 19 02:37:39 [INFO] train episode 37132: reward = -85.92, steps = 30 02:37:40 [INFO] train episode 37133: reward = -108.76, steps = 22 02:37:43 [INFO] train episode 37134: reward = -97.48, steps = 26 02:37:45 [INFO] train episode 37135: reward = -152.02, steps = 27 02:37:47 [INFO] train episode 37136: reward = -111.08, steps = 23 02:37:51 [INFO] train episode 37137: reward = -117.15, steps = 37 02:37:52 [INFO] train episode 37138: reward = -76.83, steps = 21 02:37:55 [INFO] train episode 37139: reward = -92.98, steps = 31 02:37:57 [INFO] train episode 37140: reward = -109.72, steps = 23 02:37:59 [INFO] train episode 37141: reward = -104.69, steps = 21 02:38:02 [INFO] train episode 37142: reward = -40.30, steps = 29 02:38:04 [INFO] train episode 37143: reward = -120.24, steps = 24 02:38:06 [INFO] train episode 37144: reward = -80.40, steps = 20 02:38:08 [INFO] train episode 37145: reward = -156.61, steps = 24 02:38:10 [INFO] train episode 37146: reward = -61.94, steps = 22 02:38:12 [INFO] train episode 37147: reward = -143.71, steps = 23 02:38:14 [INFO] train episode 37148: reward = -85.34, steps = 30 02:38:19 [INFO] train episode 37149: reward = -123.12, steps = 52 02:38:20 [INFO] train episode 37150: reward = -96.77, steps = 19 02:38:22 [INFO] train episode 37151: reward = -63.93, steps = 20 02:38:24 [INFO] train episode 37152: reward = -86.03, steps = 25 02:38:27 [INFO] train episode 37153: reward = -102.51, steps = 32 02:38:29 [INFO] train episode 37154: reward = -124.63, steps = 24 02:38:31 [INFO] train episode 37155: reward = -90.72, steps = 22 02:38:34 [INFO] train episode 37156: reward = -63.84, steps = 27 02:38:36 [INFO] train episode 37157: reward = -90.96, steps = 22 02:38:38 [INFO] train episode 37158: reward = -78.15, steps = 23 02:38:40 [INFO] train episode 37159: reward = -78.59, steps = 27 02:38:42 [INFO] train episode 37160: reward = -63.45, steps = 28 02:38:44 [INFO] train episode 37161: reward = -75.13, steps = 24 02:38:47 [INFO] train episode 37162: reward = -75.95, steps = 31 02:38:51 [INFO] train episode 37163: reward = -146.07, steps = 42 02:38:53 [INFO] train episode 37164: reward = -89.39, steps = 19 02:38:57 [INFO] train episode 37165: reward = -100.45, steps = 45 02:38:59 [INFO] train episode 37166: reward = -150.48, steps = 19 02:39:00 [INFO] train episode 37167: reward = -96.01, steps = 19 02:39:02 [INFO] train episode 37168: reward = -122.94, steps = 20 02:39:04 [INFO] train episode 37169: reward = -67.18, steps = 27 02:39:07 [INFO] train episode 37170: reward = -62.47, steps = 21 02:39:09 [INFO] train episode 37171: reward = -124.01, steps = 22 02:39:11 [INFO] train episode 37172: reward = -127.02, steps = 29 02:39:13 [INFO] train episode 37173: reward = -67.11, steps = 26 02:39:15 [INFO] train episode 37174: reward = -97.83, steps = 19 02:39:17 [INFO] train episode 37175: reward = -78.19, steps = 20 02:39:18 [INFO] train episode 37176: reward = -121.06, steps = 18 02:39:21 [INFO] train episode 37177: reward = -113.87, steps = 31 02:39:23 [INFO] train episode 37178: reward = -129.14, steps = 18 02:39:25 [INFO] train episode 37179: reward = -85.62, steps = 23 02:39:27 [INFO] train episode 37180: reward = -85.79, steps = 23 02:39:29 [INFO] train episode 37181: reward = -86.89, steps = 23 02:39:31 [INFO] train episode 37182: reward = -60.53, steps = 23 02:39:33 [INFO] train episode 37183: reward = -128.92, steps = 21 02:39:34 [INFO] train episode 37184: reward = -75.47, steps = 18 02:39:36 [INFO] train episode 37185: reward = -74.98, steps = 19 02:39:38 [INFO] train episode 37186: reward = -83.31, steps = 22 02:39:40 [INFO] train episode 37187: reward = -82.04, steps = 18 02:39:42 [INFO] train episode 37188: reward = -70.38, steps = 27 02:39:46 [INFO] train episode 37189: reward = -144.96, steps = 42 02:39:47 [INFO] train episode 37190: reward = -112.23, steps = 19 02:39:50 [INFO] train episode 37191: reward = -135.78, steps = 31 02:39:52 [INFO] train episode 37192: reward = -72.21, steps = 23 02:39:55 [INFO] train episode 37193: reward = -132.30, steps = 28 02:39:56 [INFO] train episode 37194: reward = -78.11, steps = 20 02:39:58 [INFO] train episode 37195: reward = -94.30, steps = 22 02:40:00 [INFO] train episode 37196: reward = -158.74, steps = 21 02:40:02 [INFO] train episode 37197: reward = -89.61, steps = 21 02:40:04 [INFO] train episode 37198: reward = -82.82, steps = 25 02:40:06 [INFO] train episode 37199: reward = -73.27, steps = 21 02:40:08 [INFO] train episode 37200: reward = -55.88, steps = 24 02:40:11 [INFO] train episode 37201: reward = -72.65, steps = 31 02:40:14 [INFO] train episode 37202: reward = -89.35, steps = 28 02:40:15 [INFO] train episode 37203: reward = -73.38, steps = 18 02:40:17 [INFO] train episode 37204: reward = -109.21, steps = 23 02:40:20 [INFO] train episode 37205: reward = -86.85, steps = 30 02:40:22 [INFO] train episode 37206: reward = -60.32, steps = 24 02:40:23 [INFO] train episode 37207: reward = -97.38, steps = 19 02:40:26 [INFO] train episode 37208: reward = -57.56, steps = 22 02:40:29 [INFO] train episode 37209: reward = -114.49, steps = 25 02:40:30 [INFO] train episode 37210: reward = -126.70, steps = 21 02:40:32 [INFO] train episode 37211: reward = -76.01, steps = 20 02:40:35 [INFO] train episode 37212: reward = -90.27, steps = 30 02:40:37 [INFO] train episode 37213: reward = -60.65, steps = 21 02:40:38 [INFO] train episode 37214: reward = -71.02, steps = 20 02:40:43 [INFO] train episode 37215: reward = -185.81, steps = 52 02:40:45 [INFO] train episode 37216: reward = -63.82, steps = 24 02:40:47 [INFO] train episode 37217: reward = -77.29, steps = 19 02:40:50 [INFO] train episode 37218: reward = -61.09, steps = 30 02:40:51 [INFO] train episode 37219: reward = -81.51, steps = 19 02:40:53 [INFO] train episode 37220: reward = -78.86, steps = 20 02:40:55 [INFO] train episode 37221: reward = -73.93, steps = 19 02:40:57 [INFO] train episode 37222: reward = -93.60, steps = 29 02:41:00 [INFO] train episode 37223: reward = -68.54, steps = 27 02:41:02 [INFO] train episode 37224: reward = -96.67, steps = 18 02:41:04 [INFO] train episode 37225: reward = -117.54, steps = 23 02:41:06 [INFO] train episode 37226: reward = -204.72, steps = 29 02:41:10 [INFO] train episode 37227: reward = -106.33, steps = 42 02:41:12 [INFO] train episode 37228: reward = -55.62, steps = 19 02:41:14 [INFO] train episode 37229: reward = -86.06, steps = 28 02:41:17 [INFO] train episode 37230: reward = -146.17, steps = 34 02:41:19 [INFO] train episode 37231: reward = -78.65, steps = 21 02:41:21 [INFO] train episode 37232: reward = -132.78, steps = 19 02:41:22 [INFO] train episode 37233: reward = -65.80, steps = 20 02:41:26 [INFO] train episode 37234: reward = -86.65, steps = 36 02:41:27 [INFO] train episode 37235: reward = -80.70, steps = 20 02:41:29 [INFO] train episode 37236: reward = -75.51, steps = 23 02:41:32 [INFO] train episode 37237: reward = -77.99, steps = 27 02:41:35 [INFO] train episode 37238: reward = -163.12, steps = 39 02:41:38 [INFO] train episode 37239: reward = -52.85, steps = 27 02:41:39 [INFO] train episode 37240: reward = -124.22, steps = 22 02:41:42 [INFO] train episode 37241: reward = -117.67, steps = 24 02:41:43 [INFO] train episode 37242: reward = -89.66, steps = 20 02:41:45 [INFO] train episode 37243: reward = -117.88, steps = 20 02:41:48 [INFO] train episode 37244: reward = -122.75, steps = 32 02:41:50 [INFO] train episode 37245: reward = -73.42, steps = 19 02:41:52 [INFO] train episode 37246: reward = -70.76, steps = 26 02:41:54 [INFO] train episode 37247: reward = -120.15, steps = 24 02:41:57 [INFO] train episode 37248: reward = -60.10, steps = 27 02:41:58 [INFO] train episode 37249: reward = -130.90, steps = 20 02:42:02 [INFO] train episode 37250: reward = -78.75, steps = 35 02:42:05 [INFO] train episode 37251: reward = -78.50, steps = 33 02:42:07 [INFO] train episode 37252: reward = -125.77, steps = 20 02:42:09 [INFO] train episode 37253: reward = -115.45, steps = 28 02:42:11 [INFO] train episode 37254: reward = -72.25, steps = 20 02:42:13 [INFO] train episode 37255: reward = -80.64, steps = 25 02:42:16 [INFO] train episode 37256: reward = -94.61, steps = 42 02:42:19 [INFO] train episode 37257: reward = -99.02, steps = 24 02:42:21 [INFO] train episode 37258: reward = -155.58, steps = 20 02:42:23 [INFO] train episode 37259: reward = -109.22, steps = 29 02:42:25 [INFO] train episode 37260: reward = -127.44, steps = 19 02:42:28 [INFO] train episode 37261: reward = -153.74, steps = 35 02:42:30 [INFO] train episode 37262: reward = -64.92, steps = 27 02:42:33 [INFO] train episode 37263: reward = -115.59, steps = 31 02:42:35 [INFO] train episode 37264: reward = -67.17, steps = 26 02:42:38 [INFO] train episode 37265: reward = -68.45, steps = 30 02:42:42 [INFO] train episode 37266: reward = -159.42, steps = 40 02:42:45 [INFO] train episode 37267: reward = -142.37, steps = 40 02:42:47 [INFO] train episode 37268: reward = -95.16, steps = 23 02:42:49 [INFO] train episode 37269: reward = -86.71, steps = 24 02:42:52 [INFO] train episode 37270: reward = -67.79, steps = 25 02:42:54 [INFO] train episode 37271: reward = -66.06, steps = 25 02:42:56 [INFO] train episode 37272: reward = -89.83, steps = 27 02:43:00 [INFO] train episode 37273: reward = -85.17, steps = 47 02:43:02 [INFO] train episode 37274: reward = -106.59, steps = 23 02:43:04 [INFO] train episode 37275: reward = -65.06, steps = 20 02:43:06 [INFO] train episode 37276: reward = -102.30, steps = 23 02:43:08 [INFO] train episode 37277: reward = -129.16, steps = 19 02:43:11 [INFO] train episode 37278: reward = -125.73, steps = 33 02:43:13 [INFO] train episode 37279: reward = -117.45, steps = 30 02:43:15 [INFO] train episode 37280: reward = -119.57, steps = 19 02:43:19 [INFO] train episode 37281: reward = -88.01, steps = 39 02:43:21 [INFO] train episode 37282: reward = -170.45, steps = 21 02:43:24 [INFO] train episode 37283: reward = -114.41, steps = 32 02:43:27 [INFO] train episode 37284: reward = -97.15, steps = 32 02:43:30 [INFO] train episode 37285: reward = -245.20, steps = 39 02:43:32 [INFO] train episode 37286: reward = -75.23, steps = 21 02:43:34 [INFO] train episode 37287: reward = -60.00, steps = 21 02:43:36 [INFO] train episode 37288: reward = -129.57, steps = 23 02:43:38 [INFO] train episode 37289: reward = -60.71, steps = 20 02:43:41 [INFO] train episode 37290: reward = -80.07, steps = 41 02:43:45 [INFO] train episode 37291: reward = -75.49, steps = 46 02:43:47 [INFO] train episode 37292: reward = -78.59, steps = 24 02:43:49 [INFO] train episode 37293: reward = -82.85, steps = 25 02:43:52 [INFO] train episode 37294: reward = -62.81, steps = 25 02:43:56 [INFO] train episode 37295: reward = -149.02, steps = 44 02:43:58 [INFO] train episode 37296: reward = -104.85, steps = 28 02:44:00 [INFO] train episode 37297: reward = -73.50, steps = 18 02:44:02 [INFO] train episode 37298: reward = -52.12, steps = 29 02:44:04 [INFO] train episode 37299: reward = -61.46, steps = 25 02:44:06 [INFO] train episode 37300: reward = -117.00, steps = 20 02:44:08 [INFO] train episode 37301: reward = -104.74, steps = 19 02:44:10 [INFO] train episode 37302: reward = -69.14, steps = 21 02:44:13 [INFO] train episode 37303: reward = -115.79, steps = 32 02:44:15 [INFO] train episode 37304: reward = -60.94, steps = 26 02:44:17 [INFO] train episode 37305: reward = -198.06, steps = 25 02:44:19 [INFO] train episode 37306: reward = -58.27, steps = 22 02:44:23 [INFO] train episode 37307: reward = -134.00, steps = 48 02:44:25 [INFO] train episode 37308: reward = -85.20, steps = 22 02:44:29 [INFO] train episode 37309: reward = -127.82, steps = 45 02:44:32 [INFO] train episode 37310: reward = -129.55, steps = 37 02:44:35 [INFO] train episode 37311: reward = -94.57, steps = 29 02:44:38 [INFO] train episode 37312: reward = -95.25, steps = 32 02:44:39 [INFO] train episode 37313: reward = -98.46, steps = 17 02:44:41 [INFO] train episode 37314: reward = -99.43, steps = 19 02:44:43 [INFO] train episode 37315: reward = -74.14, steps = 16 02:44:46 [INFO] train episode 37316: reward = -92.19, steps = 39 02:44:49 [INFO] train episode 37317: reward = -102.08, steps = 40 02:44:51 [INFO] train episode 37318: reward = -76.97, steps = 19 02:44:53 [INFO] train episode 37319: reward = -77.92, steps = 23 02:44:55 [INFO] train episode 37320: reward = -137.42, steps = 22 02:44:57 [INFO] train episode 37321: reward = -71.40, steps = 24 02:45:00 [INFO] train episode 37322: reward = -143.45, steps = 30 02:45:02 [INFO] train episode 37323: reward = -119.34, steps = 21 02:45:04 [INFO] train episode 37324: reward = -111.21, steps = 23 02:45:07 [INFO] train episode 37325: reward = -125.56, steps = 34 02:45:09 [INFO] train episode 37326: reward = -58.02, steps = 32 02:45:13 [INFO] train episode 37327: reward = -105.58, steps = 43 02:45:15 [INFO] train episode 37328: reward = -125.02, steps = 20 02:45:19 [INFO] train episode 37329: reward = -83.87, steps = 47 02:45:21 [INFO] train episode 37330: reward = -140.48, steps = 19 02:45:23 [INFO] train episode 37331: reward = -80.63, steps = 24 02:45:25 [INFO] train episode 37332: reward = -101.90, steps = 22 02:45:28 [INFO] train episode 37333: reward = -162.57, steps = 39 02:45:31 [INFO] train episode 37334: reward = -107.75, steps = 26 02:45:33 [INFO] train episode 37335: reward = -129.94, steps = 20 02:45:35 [INFO] train episode 37336: reward = -55.15, steps = 29 02:45:38 [INFO] train episode 37337: reward = -111.92, steps = 31 02:45:39 [INFO] train episode 37338: reward = -75.49, steps = 20 02:45:42 [INFO] train episode 37339: reward = -96.41, steps = 27 02:45:44 [INFO] train episode 37340: reward = -72.79, steps = 21 02:45:46 [INFO] train episode 37341: reward = -89.97, steps = 25 02:45:48 [INFO] train episode 37342: reward = -54.45, steps = 21 02:45:50 [INFO] train episode 37343: reward = -67.70, steps = 20 02:45:51 [INFO] train episode 37344: reward = -113.99, steps = 21 02:45:53 [INFO] train episode 37345: reward = -59.39, steps = 23 02:45:55 [INFO] train episode 37346: reward = -67.87, steps = 21 02:45:57 [INFO] train episode 37347: reward = -105.88, steps = 18 02:45:59 [INFO] train episode 37348: reward = -52.07, steps = 26 02:46:01 [INFO] train episode 37349: reward = -82.98, steps = 22 02:46:03 [INFO] train episode 37350: reward = -78.51, steps = 20 02:46:07 [INFO] train episode 37351: reward = -81.73, steps = 43 02:46:11 [INFO] train episode 37352: reward = -141.38, steps = 44 02:46:14 [INFO] train episode 37353: reward = -101.65, steps = 32 02:46:16 [INFO] train episode 37354: reward = -79.21, steps = 21 02:46:18 [INFO] train episode 37355: reward = -71.59, steps = 20 02:46:20 [INFO] train episode 37356: reward = -86.66, steps = 21 02:46:22 [INFO] train episode 37357: reward = -80.60, steps = 27 02:46:24 [INFO] train episode 37358: reward = -110.70, steps = 20 02:46:26 [INFO] train episode 37359: reward = -82.37, steps = 22 02:46:28 [INFO] train episode 37360: reward = -85.42, steps = 20 02:46:29 [INFO] train episode 37361: reward = -79.43, steps = 23 02:46:31 [INFO] train episode 37362: reward = -77.12, steps = 22 02:46:34 [INFO] train episode 37363: reward = -73.47, steps = 22 02:46:36 [INFO] train episode 37364: reward = -121.57, steps = 31 02:46:38 [INFO] train episode 37365: reward = -117.79, steps = 23 02:46:40 [INFO] train episode 37366: reward = -87.23, steps = 21 02:46:44 [INFO] train episode 37367: reward = -35.23, steps = 40 02:46:47 [INFO] train episode 37368: reward = -109.60, steps = 41 02:46:50 [INFO] train episode 37369: reward = -99.44, steps = 27 02:46:52 [INFO] train episode 37370: reward = -97.72, steps = 31 02:46:54 [INFO] train episode 37371: reward = -73.53, steps = 22 02:46:56 [INFO] train episode 37372: reward = -106.06, steps = 18 02:46:59 [INFO] train episode 37373: reward = -66.17, steps = 35 02:47:02 [INFO] train episode 37374: reward = -43.95, steps = 37 02:47:04 [INFO] train episode 37375: reward = -65.73, steps = 26 02:47:07 [INFO] train episode 37376: reward = -56.76, steps = 23 02:47:09 [INFO] train episode 37377: reward = -67.22, steps = 23 02:47:12 [INFO] train episode 37378: reward = -72.05, steps = 43 02:47:14 [INFO] train episode 37379: reward = -113.22, steps = 21 02:47:17 [INFO] train episode 37380: reward = -104.29, steps = 30 02:47:19 [INFO] train episode 37381: reward = -76.73, steps = 20 02:47:22 [INFO] train episode 37382: reward = -44.72, steps = 36 02:47:24 [INFO] train episode 37383: reward = -118.77, steps = 29 02:47:26 [INFO] train episode 37384: reward = -87.57, steps = 22 02:47:28 [INFO] train episode 37385: reward = -63.43, steps = 25 02:47:31 [INFO] train episode 37386: reward = -62.52, steps = 33 02:47:35 [INFO] train episode 37387: reward = -168.22, steps = 41 02:47:37 [INFO] train episode 37388: reward = -117.47, steps = 20 02:47:39 [INFO] train episode 37389: reward = -81.37, steps = 28 02:47:42 [INFO] train episode 37390: reward = -71.16, steps = 30 02:47:44 [INFO] train episode 37391: reward = -89.96, steps = 23 02:47:47 [INFO] train episode 37392: reward = -155.10, steps = 39 02:47:49 [INFO] train episode 37393: reward = -60.02, steps = 20 02:47:51 [INFO] train episode 37394: reward = -113.37, steps = 22 02:47:53 [INFO] train episode 37395: reward = -96.48, steps = 24 02:47:55 [INFO] train episode 37396: reward = -93.48, steps = 20 02:47:57 [INFO] train episode 37397: reward = -87.47, steps = 23 02:47:59 [INFO] train episode 37398: reward = -82.52, steps = 19 02:48:01 [INFO] train episode 37399: reward = -97.27, steps = 27 02:48:03 [INFO] train episode 37400: reward = -81.38, steps = 25 02:48:05 [INFO] train episode 37401: reward = -79.47, steps = 18 02:48:08 [INFO] train episode 37402: reward = -75.20, steps = 37 02:48:12 [INFO] train episode 37403: reward = -79.02, steps = 40 02:48:14 [INFO] train episode 37404: reward = -80.52, steps = 22 02:48:17 [INFO] train episode 37405: reward = -85.68, steps = 42 02:48:19 [INFO] train episode 37406: reward = -78.11, steps = 21 02:48:21 [INFO] train episode 37407: reward = -86.59, steps = 22 02:48:23 [INFO] train episode 37408: reward = -71.63, steps = 27 02:48:26 [INFO] train episode 37409: reward = -76.17, steps = 25 02:48:28 [INFO] train episode 37410: reward = -84.64, steps = 24 02:48:33 [INFO] train episode 37411: reward = -102.69, steps = 61 02:48:36 [INFO] train episode 37412: reward = -104.49, steps = 36 02:48:38 [INFO] train episode 37413: reward = -128.87, steps = 25 02:48:40 [INFO] train episode 37414: reward = -99.80, steps = 23 02:48:44 [INFO] train episode 37415: reward = -174.92, steps = 36 02:48:47 [INFO] train episode 37416: reward = -97.78, steps = 45 02:48:49 [INFO] train episode 37417: reward = -45.98, steps = 21 02:48:51 [INFO] train episode 37418: reward = -66.31, steps = 25 02:48:53 [INFO] train episode 37419: reward = -90.99, steps = 22 02:48:56 [INFO] train episode 37420: reward = -70.73, steps = 28 02:49:00 [INFO] train episode 37421: reward = -85.16, steps = 42 02:49:03 [INFO] train episode 37422: reward = -88.89, steps = 27 02:49:07 [INFO] train episode 37423: reward = -182.73, steps = 45 02:49:09 [INFO] train episode 37424: reward = -74.20, steps = 28 02:49:12 [INFO] train episode 37425: reward = -59.88, steps = 28 02:49:14 [INFO] train episode 37426: reward = -66.00, steps = 23 02:49:17 [INFO] train episode 37427: reward = -169.07, steps = 36 02:49:20 [INFO] train episode 37428: reward = -72.73, steps = 28 02:49:22 [INFO] train episode 37429: reward = -67.89, steps = 26 02:49:26 [INFO] train episode 37430: reward = -108.70, steps = 44 02:49:29 [INFO] train episode 37431: reward = -65.78, steps = 37 02:49:31 [INFO] train episode 37432: reward = -69.05, steps = 20 02:49:33 [INFO] train episode 37433: reward = -86.18, steps = 23 02:49:36 [INFO] train episode 37434: reward = -74.49, steps = 32 02:49:38 [INFO] train episode 37435: reward = -102.72, steps = 30 02:49:40 [INFO] train episode 37436: reward = -65.86, steps = 23 02:49:43 [INFO] train episode 37437: reward = -72.36, steps = 38 02:49:46 [INFO] train episode 37438: reward = -137.04, steps = 29 02:49:48 [INFO] train episode 37439: reward = -64.50, steps = 22 02:49:51 [INFO] train episode 37440: reward = -110.67, steps = 28 02:49:53 [INFO] train episode 37441: reward = -78.08, steps = 24 02:49:54 [INFO] train episode 37442: reward = -112.30, steps = 21 02:49:56 [INFO] train episode 37443: reward = -71.47, steps = 20 02:50:00 [INFO] train episode 37444: reward = -155.13, steps = 41 02:50:03 [INFO] train episode 37445: reward = -109.51, steps = 37 02:50:05 [INFO] train episode 37446: reward = -70.18, steps = 21 02:50:08 [INFO] train episode 37447: reward = -51.12, steps = 32 02:50:10 [INFO] train episode 37448: reward = -156.41, steps = 21 02:50:11 [INFO] train episode 37449: reward = -61.78, steps = 20 02:50:14 [INFO] train episode 37450: reward = -89.08, steps = 35 02:50:18 [INFO] train episode 37451: reward = -132.76, steps = 43 02:50:22 [INFO] train episode 37452: reward = -23.95, steps = 39 02:50:23 [INFO] train episode 37453: reward = -73.14, steps = 19 02:50:25 [INFO] train episode 37454: reward = -111.30, steps = 20 02:50:28 [INFO] train episode 37455: reward = -154.62, steps = 34 02:50:30 [INFO] train episode 37456: reward = -40.23, steps = 19 02:50:31 [INFO] train episode 37457: reward = -115.27, steps = 21 02:50:34 [INFO] train episode 37458: reward = -129.87, steps = 24 02:50:36 [INFO] train episode 37459: reward = -84.00, steps = 23 02:50:38 [INFO] train episode 37460: reward = -80.23, steps = 29 02:50:41 [INFO] train episode 37461: reward = -41.13, steps = 27 02:50:43 [INFO] train episode 37462: reward = -64.67, steps = 21 02:50:46 [INFO] train episode 37463: reward = -55.26, steps = 41 02:50:48 [INFO] train episode 37464: reward = -75.93, steps = 22 02:50:51 [INFO] train episode 37465: reward = -68.45, steps = 29 02:50:53 [INFO] train episode 37466: reward = -110.99, steps = 22 02:50:54 [INFO] train episode 37467: reward = -86.55, steps = 21 02:50:58 [INFO] train episode 37468: reward = -99.23, steps = 31 02:51:00 [INFO] train episode 37469: reward = -123.25, steps = 30 02:51:04 [INFO] train episode 37470: reward = -173.45, steps = 43 02:51:08 [INFO] train episode 37471: reward = -68.89, steps = 41 02:51:09 [INFO] train episode 37472: reward = -105.68, steps = 19 02:51:11 [INFO] train episode 37473: reward = -64.07, steps = 22 02:51:15 [INFO] train episode 37474: reward = -169.83, steps = 36 02:51:17 [INFO] train episode 37475: reward = -131.24, steps = 25 02:51:19 [INFO] train episode 37476: reward = -95.07, steps = 20 02:51:21 [INFO] train episode 37477: reward = -110.48, steps = 23 02:51:24 [INFO] train episode 37478: reward = -76.02, steps = 34 02:51:26 [INFO] train episode 37479: reward = -58.80, steps = 29 02:51:29 [INFO] train episode 37480: reward = -50.88, steps = 29 02:51:36 [INFO] train episode 37481: reward = -151.95, steps = 86 02:51:39 [INFO] train episode 37482: reward = -130.80, steps = 31 02:51:42 [INFO] train episode 37483: reward = -79.33, steps = 31 02:51:44 [INFO] train episode 37484: reward = -79.19, steps = 22 02:51:46 [INFO] train episode 37485: reward = -168.62, steps = 21 02:51:48 [INFO] train episode 37486: reward = -85.56, steps = 26 02:51:50 [INFO] train episode 37487: reward = -64.47, steps = 20 02:51:52 [INFO] train episode 37488: reward = -57.01, steps = 32 02:51:56 [INFO] train episode 37489: reward = -86.72, steps = 24 02:51:58 [INFO] train episode 37490: reward = -126.18, steps = 23 02:52:00 [INFO] train episode 37491: reward = -47.38, steps = 24 02:52:02 [INFO] train episode 37492: reward = -62.89, steps = 23 02:52:06 [INFO] train episode 37493: reward = -79.94, steps = 52 02:52:08 [INFO] train episode 37494: reward = -92.28, steps = 22 02:52:12 [INFO] train episode 37495: reward = -72.46, steps = 39 02:52:13 [INFO] train episode 37496: reward = -78.76, steps = 19 02:52:15 [INFO] train episode 37497: reward = -54.35, steps = 20 02:52:19 [INFO] train episode 37498: reward = -86.48, steps = 50 02:52:21 [INFO] train episode 37499: reward = -110.62, steps = 24 02:52:24 [INFO] train episode 37500: reward = -83.80, steps = 26 02:52:25 [INFO] train episode 37501: reward = -70.35, steps = 22 02:52:28 [INFO] train episode 37502: reward = -75.56, steps = 22 02:52:30 [INFO] train episode 37503: reward = -60.46, steps = 22 02:52:31 [INFO] train episode 37504: reward = -70.23, steps = 20 02:52:34 [INFO] train episode 37505: reward = -40.41, steps = 36 02:52:36 [INFO] train episode 37506: reward = -70.05, steps = 20 02:52:38 [INFO] train episode 37507: reward = -73.60, steps = 23 02:52:40 [INFO] train episode 37508: reward = -117.80, steps = 25 02:52:42 [INFO] train episode 37509: reward = -75.26, steps = 19 02:52:45 [INFO] train episode 37510: reward = -90.11, steps = 28 02:52:48 [INFO] train episode 37511: reward = -140.75, steps = 35 02:52:50 [INFO] train episode 37512: reward = -99.11, steps = 28 02:52:52 [INFO] train episode 37513: reward = -145.52, steps = 25 02:52:54 [INFO] train episode 37514: reward = -79.03, steps = 17 02:52:56 [INFO] train episode 37515: reward = -68.05, steps = 25 02:52:58 [INFO] train episode 37516: reward = -68.33, steps = 25 02:53:01 [INFO] train episode 37517: reward = -75.82, steps = 30 02:53:03 [INFO] train episode 37518: reward = -94.68, steps = 20 02:53:06 [INFO] train episode 37519: reward = -75.96, steps = 35 02:53:08 [INFO] train episode 37520: reward = -78.08, steps = 26 02:53:10 [INFO] train episode 37521: reward = -42.87, steps = 20 02:53:13 [INFO] train episode 37522: reward = -61.28, steps = 34 02:53:15 [INFO] train episode 37523: reward = -58.25, steps = 22 02:53:17 [INFO] train episode 37524: reward = -63.60, steps = 28 02:53:19 [INFO] train episode 37525: reward = -54.68, steps = 22 02:53:22 [INFO] train episode 37526: reward = -102.76, steps = 27 02:53:23 [INFO] train episode 37527: reward = -183.48, steps = 21 02:53:25 [INFO] train episode 37528: reward = -48.52, steps = 22 02:53:28 [INFO] train episode 37529: reward = -51.58, steps = 36 02:53:31 [INFO] train episode 37530: reward = -66.14, steps = 23 02:53:33 [INFO] train episode 37531: reward = -53.49, steps = 25 02:53:36 [INFO] train episode 37532: reward = -128.11, steps = 32 02:53:38 [INFO] train episode 37533: reward = -52.47, steps = 29 02:53:40 [INFO] train episode 37534: reward = -90.23, steps = 24 02:53:43 [INFO] train episode 37535: reward = -82.14, steps = 27 02:53:45 [INFO] train episode 37536: reward = -83.33, steps = 28 02:53:47 [INFO] train episode 37537: reward = -123.16, steps = 19 02:53:49 [INFO] train episode 37538: reward = -90.13, steps = 23 02:53:51 [INFO] train episode 37539: reward = -95.49, steps = 26 02:53:54 [INFO] train episode 37540: reward = -81.32, steps = 24 02:53:55 [INFO] train episode 37541: reward = -94.49, steps = 19 02:53:57 [INFO] train episode 37542: reward = -57.81, steps = 22 02:54:00 [INFO] train episode 37543: reward = -95.72, steps = 37 02:54:03 [INFO] train episode 37544: reward = -94.68, steps = 23 02:54:06 [INFO] train episode 37545: reward = -110.13, steps = 31 02:54:08 [INFO] train episode 37546: reward = -78.84, steps = 29 02:54:11 [INFO] train episode 37547: reward = -68.94, steps = 30 02:54:12 [INFO] train episode 37548: reward = -122.40, steps = 21 02:54:16 [INFO] train episode 37549: reward = -177.59, steps = 45 02:54:18 [INFO] train episode 37550: reward = -65.65, steps = 20 02:54:21 [INFO] train episode 37551: reward = -79.69, steps = 30 02:54:23 [INFO] train episode 37552: reward = -91.14, steps = 26 02:54:25 [INFO] train episode 37553: reward = -73.68, steps = 21 02:54:27 [INFO] train episode 37554: reward = -73.61, steps = 19 02:54:29 [INFO] train episode 37555: reward = -75.35, steps = 21 02:54:32 [INFO] train episode 37556: reward = -142.64, steps = 41 02:54:34 [INFO] train episode 37557: reward = -85.25, steps = 22 02:54:37 [INFO] train episode 37558: reward = -55.27, steps = 37 02:54:40 [INFO] train episode 37559: reward = -82.71, steps = 26 02:54:42 [INFO] train episode 37560: reward = -136.41, steps = 25 02:54:44 [INFO] train episode 37561: reward = -96.54, steps = 20 02:54:45 [INFO] train episode 37562: reward = -80.66, steps = 20 02:54:48 [INFO] train episode 37563: reward = -107.00, steps = 24 02:54:50 [INFO] train episode 37564: reward = -58.05, steps = 23 02:54:52 [INFO] train episode 37565: reward = -58.91, steps = 24 02:54:55 [INFO] train episode 37566: reward = -64.25, steps = 32 02:54:58 [INFO] train episode 37567: reward = -76.79, steps = 33 02:55:01 [INFO] train episode 37568: reward = -83.87, steps = 31 02:55:03 [INFO] train episode 37569: reward = -86.29, steps = 21 02:55:06 [INFO] train episode 37570: reward = -123.00, steps = 36 02:55:09 [INFO] train episode 37571: reward = -29.64, steps = 34 02:55:11 [INFO] train episode 37572: reward = -84.34, steps = 24 02:55:13 [INFO] train episode 37573: reward = -59.34, steps = 20 02:55:15 [INFO] train episode 37574: reward = -81.61, steps = 23 02:55:17 [INFO] train episode 37575: reward = -121.08, steps = 26 02:55:19 [INFO] train episode 37576: reward = -114.71, steps = 20 02:55:21 [INFO] train episode 37577: reward = -71.59, steps = 21 02:55:24 [INFO] train episode 37578: reward = -76.11, steps = 36 02:55:26 [INFO] train episode 37579: reward = -102.61, steps = 22 02:55:29 [INFO] train episode 37580: reward = -65.92, steps = 31 02:55:31 [INFO] train episode 37581: reward = -49.03, steps = 21 02:55:33 [INFO] train episode 37582: reward = -132.23, steps = 31 02:55:36 [INFO] train episode 37583: reward = -74.67, steps = 29 02:55:37 [INFO] train episode 37584: reward = -53.33, steps = 19 02:55:41 [INFO] train episode 37585: reward = -63.20, steps = 33 02:55:42 [INFO] train episode 37586: reward = -76.69, steps = 20 02:55:44 [INFO] train episode 37587: reward = -101.76, steps = 20 02:55:48 [INFO] train episode 37588: reward = -67.50, steps = 42 02:55:51 [INFO] train episode 37589: reward = -90.80, steps = 35 02:55:52 [INFO] train episode 37590: reward = -109.34, steps = 20 02:55:55 [INFO] train episode 37591: reward = -62.19, steps = 19 02:55:58 [INFO] train episode 37592: reward = -42.00, steps = 38 02:56:00 [INFO] train episode 37593: reward = -59.40, steps = 24 02:56:02 [INFO] train episode 37594: reward = -63.73, steps = 25 02:56:05 [INFO] train episode 37595: reward = -123.06, steps = 35 02:56:07 [INFO] train episode 37596: reward = -106.83, steps = 27 02:56:09 [INFO] train episode 37597: reward = -92.62, steps = 20 02:56:12 [INFO] train episode 37598: reward = -53.31, steps = 25 02:56:13 [INFO] train episode 37599: reward = -83.66, steps = 19 02:56:15 [INFO] train episode 37600: reward = -72.96, steps = 20 02:56:17 [INFO] train episode 37601: reward = -75.08, steps = 25 02:56:20 [INFO] train episode 37602: reward = -83.75, steps = 29 02:56:23 [INFO] train episode 37603: reward = -112.98, steps = 34 02:56:24 [INFO] train episode 37604: reward = -96.81, steps = 17 02:56:26 [INFO] train episode 37605: reward = -110.76, steps = 21 02:56:29 [INFO] train episode 37606: reward = -113.40, steps = 27 02:56:30 [INFO] train episode 37607: reward = -78.25, steps = 20 02:56:32 [INFO] train episode 37608: reward = -125.46, steps = 26 02:56:36 [INFO] train episode 37609: reward = -67.10, steps = 47 02:56:38 [INFO] train episode 37610: reward = -90.75, steps = 21 02:56:41 [INFO] train episode 37611: reward = -114.28, steps = 29 02:56:43 [INFO] train episode 37612: reward = -75.91, steps = 20 02:56:45 [INFO] train episode 37613: reward = -63.11, steps = 21 02:56:47 [INFO] train episode 37614: reward = -62.17, steps = 28 02:56:51 [INFO] train episode 37615: reward = -165.71, steps = 43 02:56:54 [INFO] train episode 37616: reward = -93.62, steps = 37 02:56:57 [INFO] train episode 37617: reward = -53.54, steps = 29 02:56:59 [INFO] train episode 37618: reward = -56.80, steps = 18 02:57:02 [INFO] train episode 37619: reward = -79.14, steps = 35 02:57:04 [INFO] train episode 37620: reward = -68.14, steps = 26 02:57:06 [INFO] train episode 37621: reward = -107.99, steps = 23 02:57:08 [INFO] train episode 37622: reward = -64.22, steps = 24 02:57:10 [INFO] train episode 37623: reward = -95.98, steps = 25 02:57:12 [INFO] train episode 37624: reward = -78.56, steps = 21 02:57:16 [INFO] train episode 37625: reward = -93.14, steps = 35 02:57:18 [INFO] train episode 37626: reward = -76.14, steps = 23 02:57:20 [INFO] train episode 37627: reward = -81.72, steps = 24 02:57:23 [INFO] train episode 37628: reward = -126.95, steps = 36 02:57:24 [INFO] train episode 37629: reward = -56.60, steps = 20 02:57:27 [INFO] train episode 37630: reward = -70.63, steps = 27 02:57:29 [INFO] train episode 37631: reward = -86.32, steps = 21 02:57:31 [INFO] train episode 37632: reward = -110.34, steps = 20 02:57:33 [INFO] train episode 37633: reward = -92.50, steps = 30 02:57:35 [INFO] train episode 37634: reward = -101.00, steps = 24 02:57:39 [INFO] train episode 37635: reward = -158.34, steps = 37 02:57:41 [INFO] train episode 37636: reward = -47.67, steps = 20 02:57:43 [INFO] train episode 37637: reward = -34.11, steps = 25 02:57:46 [INFO] train episode 37638: reward = -73.01, steps = 29 02:57:49 [INFO] train episode 37639: reward = -59.42, steps = 32 02:57:52 [INFO] train episode 37640: reward = -81.81, steps = 34 02:57:54 [INFO] train episode 37641: reward = -50.91, steps = 21 02:57:56 [INFO] train episode 37642: reward = -51.12, steps = 27 02:57:59 [INFO] train episode 37643: reward = -84.77, steps = 35 02:58:02 [INFO] train episode 37644: reward = -57.52, steps = 36 02:58:05 [INFO] train episode 37645: reward = -57.30, steps = 33 02:58:08 [INFO] train episode 37646: reward = -64.79, steps = 33 02:58:11 [INFO] train episode 37647: reward = -60.33, steps = 29 02:58:12 [INFO] train episode 37648: reward = -71.65, steps = 20 02:58:15 [INFO] train episode 37649: reward = -66.76, steps = 37 02:58:18 [INFO] train episode 37650: reward = -86.02, steps = 27 02:58:21 [INFO] train episode 37651: reward = -88.04, steps = 35 02:58:23 [INFO] train episode 37652: reward = -81.43, steps = 20 02:58:27 [INFO] train episode 37653: reward = -82.80, steps = 47 02:58:30 [INFO] train episode 37654: reward = -39.27, steps = 31 02:58:33 [INFO] train episode 37655: reward = -159.64, steps = 35 02:58:34 [INFO] train episode 37656: reward = -61.55, steps = 18 02:58:36 [INFO] train episode 37657: reward = -70.45, steps = 21 02:58:39 [INFO] train episode 37658: reward = -97.95, steps = 34 02:58:42 [INFO] train episode 37659: reward = -128.81, steps = 34 02:58:44 [INFO] train episode 37660: reward = -84.89, steps = 25 02:58:49 [INFO] train episode 37661: reward = -113.08, steps = 54 02:58:51 [INFO] train episode 37662: reward = -145.68, steps = 24 02:58:53 [INFO] train episode 37663: reward = -104.94, steps = 19 02:58:57 [INFO] train episode 37664: reward = -71.93, steps = 47 02:59:00 [INFO] train episode 37665: reward = -145.24, steps = 30 02:59:01 [INFO] train episode 37666: reward = -59.71, steps = 20 02:59:04 [INFO] train episode 37667: reward = -70.71, steps = 28 02:59:06 [INFO] train episode 37668: reward = -66.03, steps = 21 02:59:10 [INFO] train episode 37669: reward = -128.28, steps = 41 02:59:12 [INFO] train episode 37670: reward = -72.51, steps = 24 02:59:14 [INFO] train episode 37671: reward = -88.52, steps = 27 02:59:17 [INFO] train episode 37672: reward = -84.38, steps = 28 02:59:18 [INFO] train episode 37673: reward = -78.34, steps = 21 02:59:20 [INFO] train episode 37674: reward = -45.51, steps = 23 02:59:22 [INFO] train episode 37675: reward = -99.93, steps = 20 02:59:25 [INFO] train episode 37676: reward = -86.79, steps = 27 02:59:28 [INFO] train episode 37677: reward = -76.09, steps = 31 02:59:31 [INFO] train episode 37678: reward = -78.74, steps = 39 02:59:33 [INFO] train episode 37679: reward = -77.42, steps = 21 02:59:37 [INFO] train episode 37680: reward = -149.05, steps = 48 02:59:40 [INFO] train episode 37681: reward = -75.92, steps = 29 02:59:41 [INFO] train episode 37682: reward = -64.84, steps = 20 02:59:43 [INFO] train episode 37683: reward = -123.26, steps = 20 02:59:45 [INFO] train episode 37684: reward = -52.12, steps = 25 02:59:47 [INFO] train episode 37685: reward = -58.41, steps = 19 02:59:48 [INFO] train episode 37686: reward = -132.49, steps = 19 02:59:52 [INFO] train episode 37687: reward = -118.79, steps = 38 02:59:55 [INFO] train episode 37688: reward = -77.49, steps = 30 02:59:58 [INFO] train episode 37689: reward = -85.79, steps = 34 03:00:00 [INFO] train episode 37690: reward = -56.32, steps = 23 03:00:02 [INFO] train episode 37691: reward = -58.14, steps = 29 03:00:04 [INFO] train episode 37692: reward = -72.92, steps = 27 03:00:06 [INFO] train episode 37693: reward = -69.30, steps = 24 03:00:09 [INFO] train episode 37694: reward = -69.14, steps = 30 03:00:11 [INFO] train episode 37695: reward = -55.06, steps = 20 03:00:14 [INFO] train episode 37696: reward = -107.32, steps = 29 03:00:16 [INFO] train episode 37697: reward = -58.29, steps = 28 03:00:19 [INFO] train episode 37698: reward = -39.11, steps = 42 03:00:22 [INFO] train episode 37699: reward = -53.32, steps = 30 03:00:25 [INFO] train episode 37700: reward = -78.79, steps = 35 03:00:30 [INFO] train episode 37701: reward = -143.23, steps = 53 03:00:33 [INFO] train episode 37702: reward = -80.96, steps = 26 03:00:35 [INFO] train episode 37703: reward = -70.14, steps = 20 03:00:37 [INFO] train episode 37704: reward = -88.47, steps = 24 03:00:39 [INFO] train episode 37705: reward = -51.93, steps = 24 03:00:41 [INFO] train episode 37706: reward = -66.42, steps = 23 03:00:43 [INFO] train episode 37707: reward = -143.65, steps = 21 03:00:45 [INFO] train episode 37708: reward = -93.40, steps = 24 03:00:47 [INFO] train episode 37709: reward = -104.30, steps = 24 03:00:51 [INFO] train episode 37710: reward = -96.10, steps = 45 03:00:53 [INFO] train episode 37711: reward = -78.03, steps = 25 03:00:56 [INFO] train episode 37712: reward = -132.72, steps = 37 03:00:58 [INFO] train episode 37713: reward = -39.46, steps = 24 03:01:01 [INFO] train episode 37714: reward = -110.36, steps = 31 03:01:04 [INFO] train episode 37715: reward = -67.79, steps = 31 03:01:06 [INFO] train episode 37716: reward = -68.01, steps = 24 03:01:08 [INFO] train episode 37717: reward = -34.69, steps = 17 03:01:11 [INFO] train episode 37718: reward = -65.53, steps = 41 03:01:13 [INFO] train episode 37719: reward = -57.04, steps = 19 03:01:17 [INFO] train episode 37720: reward = -83.66, steps = 40 03:01:19 [INFO] train episode 37721: reward = -108.02, steps = 24 03:01:21 [INFO] train episode 37722: reward = -114.88, steps = 21 03:01:22 [INFO] train episode 37723: reward = -83.00, steps = 20 03:01:25 [INFO] train episode 37724: reward = -87.58, steps = 26 03:01:26 [INFO] train episode 37725: reward = -104.74, steps = 19 03:01:28 [INFO] train episode 37726: reward = -57.38, steps = 22 03:01:30 [INFO] train episode 37727: reward = -42.02, steps = 20 03:01:33 [INFO] train episode 37728: reward = -66.79, steps = 28 03:01:36 [INFO] train episode 37729: reward = -89.62, steps = 35 03:01:38 [INFO] train episode 37730: reward = -49.23, steps = 22 03:01:41 [INFO] train episode 37731: reward = -116.30, steps = 42 03:01:43 [INFO] train episode 37732: reward = -75.33, steps = 20 03:01:46 [INFO] train episode 37733: reward = -46.17, steps = 34 03:01:50 [INFO] train episode 37734: reward = -220.19, steps = 49 03:01:52 [INFO] train episode 37735: reward = -83.47, steps = 22 03:01:55 [INFO] train episode 37736: reward = -59.89, steps = 32 03:01:57 [INFO] train episode 37737: reward = -86.82, steps = 22 03:01:59 [INFO] train episode 37738: reward = -91.85, steps = 25 03:02:01 [INFO] train episode 37739: reward = -104.59, steps = 24 03:02:03 [INFO] train episode 37740: reward = -81.23, steps = 23 03:02:05 [INFO] train episode 37741: reward = -96.54, steps = 22 03:02:08 [INFO] train episode 37742: reward = -65.01, steps = 26 03:02:11 [INFO] train episode 37743: reward = -43.24, steps = 37 03:02:12 [INFO] train episode 37744: reward = -62.48, steps = 20 03:02:16 [INFO] train episode 37745: reward = -126.80, steps = 44 03:02:20 [INFO] train episode 37746: reward = -54.10, steps = 37 03:02:22 [INFO] train episode 37747: reward = -174.02, steps = 30 03:02:25 [INFO] train episode 37748: reward = -96.93, steps = 32 03:02:27 [INFO] train episode 37749: reward = -72.43, steps = 24 03:02:29 [INFO] train episode 37750: reward = -69.66, steps = 18 03:02:31 [INFO] train episode 37751: reward = -56.91, steps = 22 03:02:33 [INFO] train episode 37752: reward = -191.66, steps = 25 03:02:35 [INFO] train episode 37753: reward = -68.08, steps = 21 03:02:37 [INFO] train episode 37754: reward = -74.77, steps = 23 03:02:39 [INFO] train episode 37755: reward = -131.71, steps = 20 03:02:41 [INFO] train episode 37756: reward = -61.82, steps = 25 03:02:44 [INFO] train episode 37757: reward = -82.49, steps = 32 03:02:47 [INFO] train episode 37758: reward = -64.55, steps = 36 03:02:50 [INFO] train episode 37759: reward = -67.45, steps = 32 03:02:52 [INFO] train episode 37760: reward = -120.74, steps = 22 03:02:54 [INFO] train episode 37761: reward = -82.53, steps = 19 03:02:56 [INFO] train episode 37762: reward = -89.98, steps = 21 03:02:58 [INFO] train episode 37763: reward = -56.55, steps = 29 03:03:00 [INFO] train episode 37764: reward = -66.71, steps = 22 03:03:02 [INFO] train episode 37765: reward = -107.39, steps = 26 03:03:07 [INFO] train episode 37766: reward = -113.87, steps = 45 03:03:09 [INFO] train episode 37767: reward = -111.95, steps = 21 03:03:11 [INFO] train episode 37768: reward = -48.65, steps = 23 03:03:13 [INFO] train episode 37769: reward = -48.70, steps = 26 03:03:15 [INFO] train episode 37770: reward = -78.61, steps = 25 03:03:17 [INFO] train episode 37771: reward = -53.79, steps = 25 03:03:19 [INFO] train episode 37772: reward = -138.70, steps = 19 03:03:21 [INFO] train episode 37773: reward = -96.73, steps = 30 03:03:25 [INFO] train episode 37774: reward = -67.20, steps = 25 03:03:27 [INFO] train episode 37775: reward = -89.33, steps = 25 03:03:31 [INFO] train episode 37776: reward = -126.21, steps = 43 03:03:33 [INFO] train episode 37777: reward = -56.15, steps = 21 03:03:36 [INFO] train episode 37778: reward = -58.62, steps = 42 03:03:38 [INFO] train episode 37779: reward = -117.18, steps = 25 03:03:41 [INFO] train episode 37780: reward = -77.62, steps = 21 03:03:42 [INFO] train episode 37781: reward = -107.74, steps = 19 03:03:46 [INFO] train episode 37782: reward = -114.93, steps = 47 03:03:49 [INFO] train episode 37783: reward = -75.59, steps = 30 03:03:51 [INFO] train episode 37784: reward = -52.91, steps = 21 03:03:53 [INFO] train episode 37785: reward = -79.90, steps = 29 03:03:57 [INFO] train episode 37786: reward = -72.43, steps = 36 03:03:59 [INFO] train episode 37787: reward = -81.92, steps = 30 03:04:01 [INFO] train episode 37788: reward = -65.07, steps = 25 03:04:03 [INFO] train episode 37789: reward = -79.05, steps = 19 03:04:05 [INFO] train episode 37790: reward = -98.71, steps = 19 03:04:07 [INFO] train episode 37791: reward = -125.88, steps = 25 03:04:10 [INFO] train episode 37792: reward = -76.29, steps = 36 03:04:12 [INFO] train episode 37793: reward = -103.33, steps = 21 03:04:16 [INFO] train episode 37794: reward = -117.20, steps = 44 03:04:18 [INFO] train episode 37795: reward = -47.06, steps = 23 03:04:20 [INFO] train episode 37796: reward = -68.36, steps = 27 03:04:23 [INFO] train episode 37797: reward = -69.90, steps = 31 03:04:26 [INFO] train episode 37798: reward = -97.89, steps = 38 03:04:29 [INFO] train episode 37799: reward = -59.02, steps = 22 03:04:31 [INFO] train episode 37800: reward = -41.71, steps = 24 03:04:34 [INFO] train episode 37801: reward = -123.46, steps = 35 03:04:36 [INFO] train episode 37802: reward = -59.62, steps = 26 03:04:38 [INFO] train episode 37803: reward = -93.79, steps = 22 03:04:41 [INFO] train episode 37804: reward = -55.45, steps = 34 03:04:44 [INFO] train episode 37805: reward = -35.89, steps = 39 03:04:48 [INFO] train episode 37806: reward = -44.66, steps = 42 03:04:50 [INFO] train episode 37807: reward = -97.26, steps = 22 03:04:52 [INFO] train episode 37808: reward = -67.86, steps = 20 03:04:53 [INFO] train episode 37809: reward = -71.49, steps = 19 03:04:55 [INFO] train episode 37810: reward = -91.27, steps = 19 03:04:59 [INFO] train episode 37811: reward = -87.53, steps = 44 03:05:03 [INFO] train episode 37812: reward = -48.74, steps = 44 03:05:05 [INFO] train episode 37813: reward = -49.25, steps = 24 03:05:07 [INFO] train episode 37814: reward = -91.35, steps = 21 03:05:11 [INFO] train episode 37815: reward = -120.63, steps = 42 03:05:14 [INFO] train episode 37816: reward = -95.88, steps = 36 03:05:16 [INFO] train episode 37817: reward = -76.98, steps = 20 03:05:18 [INFO] train episode 37818: reward = -108.35, steps = 21 03:05:20 [INFO] train episode 37819: reward = -65.27, steps = 25 03:05:22 [INFO] train episode 37820: reward = -41.90, steps = 21 03:05:25 [INFO] train episode 37821: reward = -164.30, steps = 35 03:05:26 [INFO] train episode 37822: reward = -67.69, steps = 20 03:05:29 [INFO] train episode 37823: reward = -98.53, steps = 27 03:05:31 [INFO] train episode 37824: reward = -121.52, steps = 21 03:05:33 [INFO] train episode 37825: reward = -142.05, steps = 27 03:05:35 [INFO] train episode 37826: reward = -70.81, steps = 20 03:05:37 [INFO] train episode 37827: reward = -76.32, steps = 19 03:05:39 [INFO] train episode 37828: reward = -68.25, steps = 27 03:05:41 [INFO] train episode 37829: reward = -54.62, steps = 19 03:05:43 [INFO] train episode 37830: reward = -119.46, steps = 27 03:05:46 [INFO] train episode 37831: reward = -40.67, steps = 33 03:05:48 [INFO] train episode 37832: reward = -56.43, steps = 22 03:05:51 [INFO] train episode 37833: reward = -80.84, steps = 27 03:05:54 [INFO] train episode 37834: reward = -77.59, steps = 37 03:05:56 [INFO] train episode 37835: reward = -62.33, steps = 20 03:05:58 [INFO] train episode 37836: reward = -113.81, steps = 29 03:06:01 [INFO] train episode 37837: reward = -64.30, steps = 39 03:06:04 [INFO] train episode 37838: reward = -80.16, steps = 21 03:06:05 [INFO] train episode 37839: reward = -62.10, steps = 20 03:06:09 [INFO] train episode 37840: reward = -43.29, steps = 45 03:06:14 [INFO] train episode 37841: reward = -125.77, steps = 51 03:06:20 [INFO] train episode 37842: reward = -153.16, steps = 60 03:06:22 [INFO] train episode 37843: reward = -71.31, steps = 26 03:06:27 [INFO] train episode 37844: reward = -134.59, steps = 63 03:06:30 [INFO] train episode 37845: reward = -69.90, steps = 37 03:06:33 [INFO] train episode 37846: reward = -73.33, steps = 27 03:06:36 [INFO] train episode 37847: reward = -102.76, steps = 31 03:06:38 [INFO] train episode 37848: reward = -92.29, steps = 27 03:06:40 [INFO] train episode 37849: reward = -53.76, steps = 20 03:06:42 [INFO] train episode 37850: reward = -128.98, steps = 25 03:06:44 [INFO] train episode 37851: reward = -54.24, steps = 19 03:06:46 [INFO] train episode 37852: reward = -58.10, steps = 22 03:06:49 [INFO] train episode 37853: reward = -81.53, steps = 36 03:06:52 [INFO] train episode 37854: reward = -64.18, steps = 28 03:06:55 [INFO] train episode 37855: reward = -78.78, steps = 44 03:06:58 [INFO] train episode 37856: reward = -68.99, steps = 31 03:07:01 [INFO] train episode 37857: reward = -150.92, steps = 37 03:07:03 [INFO] train episode 37858: reward = -80.28, steps = 21 03:07:05 [INFO] train episode 37859: reward = -148.99, steps = 20 03:07:08 [INFO] train episode 37860: reward = -56.02, steps = 30 03:07:10 [INFO] train episode 37861: reward = -81.03, steps = 23 03:07:13 [INFO] train episode 37862: reward = -69.92, steps = 37 03:07:18 [INFO] train episode 37863: reward = -171.55, steps = 67 03:07:21 [INFO] train episode 37864: reward = -80.05, steps = 26 03:07:22 [INFO] train episode 37865: reward = -51.48, steps = 20 03:07:25 [INFO] train episode 37866: reward = -65.68, steps = 22 03:07:27 [INFO] train episode 37867: reward = -65.73, steps = 32 03:07:29 [INFO] train episode 37868: reward = -109.75, steps = 20 03:07:31 [INFO] train episode 37869: reward = -106.34, steps = 24 03:07:33 [INFO] train episode 37870: reward = -90.76, steps = 20 03:07:35 [INFO] train episode 37871: reward = -68.28, steps = 21 03:07:38 [INFO] train episode 37872: reward = -111.54, steps = 38 03:07:41 [INFO] train episode 37873: reward = -59.85, steps = 26 03:07:42 [INFO] train episode 37874: reward = -57.94, steps = 19 03:07:47 [INFO] train episode 37875: reward = -125.49, steps = 54 03:07:48 [INFO] train episode 37876: reward = -144.07, steps = 19 03:07:51 [INFO] train episode 37877: reward = -71.11, steps = 33 03:07:54 [INFO] train episode 37878: reward = -68.95, steps = 28 03:07:56 [INFO] train episode 37879: reward = -108.06, steps = 22 03:07:58 [INFO] train episode 37880: reward = -40.38, steps = 23 03:08:00 [INFO] train episode 37881: reward = -76.36, steps = 24 03:08:04 [INFO] train episode 37882: reward = -90.52, steps = 41 03:08:06 [INFO] train episode 37883: reward = -89.64, steps = 29 03:08:10 [INFO] train episode 37884: reward = -83.31, steps = 43 03:08:13 [INFO] train episode 37885: reward = -51.66, steps = 35 03:08:17 [INFO] train episode 37886: reward = -70.66, steps = 40 03:08:18 [INFO] train episode 37887: reward = -107.54, steps = 22 03:08:21 [INFO] train episode 37888: reward = -91.63, steps = 27 03:08:23 [INFO] train episode 37889: reward = -73.29, steps = 27 03:08:27 [INFO] train episode 37890: reward = -60.56, steps = 39 03:08:29 [INFO] train episode 37891: reward = -72.64, steps = 21 03:08:31 [INFO] train episode 37892: reward = -142.59, steps = 25 03:08:33 [INFO] train episode 37893: reward = -47.01, steps = 26 03:08:36 [INFO] train episode 37894: reward = -95.94, steps = 28 03:08:38 [INFO] train episode 37895: reward = -61.91, steps = 23 03:08:40 [INFO] train episode 37896: reward = -96.34, steps = 20 03:08:44 [INFO] train episode 37897: reward = -130.18, steps = 51 03:08:46 [INFO] train episode 37898: reward = -115.04, steps = 19 03:08:49 [INFO] train episode 37899: reward = -50.31, steps = 31 03:08:51 [INFO] train episode 37900: reward = -64.53, steps = 28 03:08:55 [INFO] train episode 37901: reward = -104.63, steps = 37 03:08:57 [INFO] train episode 37902: reward = -38.03, steps = 20 03:08:59 [INFO] train episode 37903: reward = -111.26, steps = 28 03:09:01 [INFO] train episode 37904: reward = -93.16, steps = 21 03:09:04 [INFO] train episode 37905: reward = -135.44, steps = 30 03:09:07 [INFO] train episode 37906: reward = -71.90, steps = 39 03:09:12 [INFO] train episode 37907: reward = -171.95, steps = 43 03:09:14 [INFO] train episode 37908: reward = -109.19, steps = 22 03:09:16 [INFO] train episode 37909: reward = -79.22, steps = 21 03:09:19 [INFO] train episode 37910: reward = -67.31, steps = 39 03:09:21 [INFO] train episode 37911: reward = -60.78, steps = 24 03:09:23 [INFO] train episode 37912: reward = -68.79, steps = 22 03:09:28 [INFO] train episode 37913: reward = -130.17, steps = 58 03:09:32 [INFO] train episode 37914: reward = -86.51, steps = 47 03:09:34 [INFO] train episode 37915: reward = -85.22, steps = 20 03:09:35 [INFO] train episode 37916: reward = -85.57, steps = 11 03:09:39 [INFO] train episode 37917: reward = -129.20, steps = 53 03:09:41 [INFO] train episode 37918: reward = -81.07, steps = 20 03:09:44 [INFO] train episode 37919: reward = -63.29, steps = 31 03:09:46 [INFO] train episode 37920: reward = -61.91, steps = 24 03:09:48 [INFO] train episode 37921: reward = -94.77, steps = 20 03:09:50 [INFO] train episode 37922: reward = -83.01, steps = 30 03:09:52 [INFO] train episode 37923: reward = -101.18, steps = 22 03:09:54 [INFO] train episode 37924: reward = -93.21, steps = 22 03:09:58 [INFO] train episode 37925: reward = -93.35, steps = 47 03:10:01 [INFO] train episode 37926: reward = -84.63, steps = 32 03:10:03 [INFO] train episode 37927: reward = -79.65, steps = 27 03:10:05 [INFO] train episode 37928: reward = -66.88, steps = 19 03:10:08 [INFO] train episode 37929: reward = -55.18, steps = 28 03:10:09 [INFO] train episode 37930: reward = -135.61, steps = 20 03:10:12 [INFO] train episode 37931: reward = -89.38, steps = 27 03:10:17 [INFO] train episode 37932: reward = -124.73, steps = 69 03:10:20 [INFO] train episode 37933: reward = -82.44, steps = 22 03:10:21 [INFO] train episode 37934: reward = -81.59, steps = 21 03:10:23 [INFO] train episode 37935: reward = -65.78, steps = 19 03:10:25 [INFO] train episode 37936: reward = -64.14, steps = 21 03:10:27 [INFO] train episode 37937: reward = -76.95, steps = 23 03:10:30 [INFO] train episode 37938: reward = -77.15, steps = 31 03:10:33 [INFO] train episode 37939: reward = -101.01, steps = 38 03:10:35 [INFO] train episode 37940: reward = -94.48, steps = 26 03:10:38 [INFO] train episode 37941: reward = -43.48, steps = 33 03:10:40 [INFO] train episode 37942: reward = -58.98, steps = 23 03:10:43 [INFO] train episode 37943: reward = -79.61, steps = 32 03:10:45 [INFO] train episode 37944: reward = -87.32, steps = 21 03:10:49 [INFO] train episode 37945: reward = -32.59, steps = 41 03:10:52 [INFO] train episode 37946: reward = -94.24, steps = 34 03:10:54 [INFO] train episode 37947: reward = -83.09, steps = 28 03:10:58 [INFO] train episode 37948: reward = -52.10, steps = 40 03:11:01 [INFO] train episode 37949: reward = -77.18, steps = 42 03:11:03 [INFO] train episode 37950: reward = -83.95, steps = 19 03:11:06 [INFO] train episode 37951: reward = -149.24, steps = 33 03:11:08 [INFO] train episode 37952: reward = -82.62, steps = 23 03:11:11 [INFO] train episode 37953: reward = -48.13, steps = 35 03:11:16 [INFO] train episode 37954: reward = -151.96, steps = 58 03:11:18 [INFO] train episode 37955: reward = -72.91, steps = 22 03:11:19 [INFO] train episode 37956: reward = -60.54, steps = 22 03:11:22 [INFO] train episode 37957: reward = -96.66, steps = 29 03:11:24 [INFO] train episode 37958: reward = -69.68, steps = 21 03:11:29 [INFO] train episode 37959: reward = -150.47, steps = 58 03:11:31 [INFO] train episode 37960: reward = -74.84, steps = 19 03:11:33 [INFO] train episode 37961: reward = -76.59, steps = 24 03:11:34 [INFO] train episode 37962: reward = -89.50, steps = 19 03:11:37 [INFO] train episode 37963: reward = -52.44, steps = 25 03:11:39 [INFO] train episode 37964: reward = -72.74, steps = 22 03:11:41 [INFO] train episode 37965: reward = -85.21, steps = 24 03:11:43 [INFO] train episode 37966: reward = -54.43, steps = 23 03:11:45 [INFO] train episode 37967: reward = -58.74, steps = 29 03:11:48 [INFO] train episode 37968: reward = -78.18, steps = 30 03:11:52 [INFO] train episode 37969: reward = -80.04, steps = 46 03:11:55 [INFO] train episode 37970: reward = -124.78, steps = 27 03:11:58 [INFO] train episode 37971: reward = -65.99, steps = 36 03:12:01 [INFO] train episode 37972: reward = -87.85, steps = 35 03:12:03 [INFO] train episode 37973: reward = -69.36, steps = 21 03:12:05 [INFO] train episode 37974: reward = -76.63, steps = 21 03:12:07 [INFO] train episode 37975: reward = -76.89, steps = 20 03:12:09 [INFO] train episode 37976: reward = -68.05, steps = 26 03:12:11 [INFO] train episode 37977: reward = -88.86, steps = 20 03:12:14 [INFO] train episode 37978: reward = -112.33, steps = 34 03:12:16 [INFO] train episode 37979: reward = -56.24, steps = 23 03:12:19 [INFO] train episode 37980: reward = -40.45, steps = 35 03:12:21 [INFO] train episode 37981: reward = -51.23, steps = 20 03:12:25 [INFO] train episode 37982: reward = -101.04, steps = 47 03:12:27 [INFO] train episode 37983: reward = -63.94, steps = 21 03:12:30 [INFO] train episode 37984: reward = -145.45, steps = 40 03:12:33 [INFO] train episode 37985: reward = -99.56, steps = 25 03:12:35 [INFO] train episode 37986: reward = -76.23, steps = 28 03:12:37 [INFO] train episode 37987: reward = -79.78, steps = 22 03:12:40 [INFO] train episode 37988: reward = -54.09, steps = 28 03:12:41 [INFO] train episode 37989: reward = -57.66, steps = 20 03:12:45 [INFO] train episode 37990: reward = -102.89, steps = 38 03:12:48 [INFO] train episode 37991: reward = -95.47, steps = 35 03:12:50 [INFO] train episode 37992: reward = -72.31, steps = 18 03:12:52 [INFO] train episode 37993: reward = -46.33, steps = 25 03:12:54 [INFO] train episode 37994: reward = -68.44, steps = 26 03:12:57 [INFO] train episode 37995: reward = -138.10, steps = 39 03:13:00 [INFO] train episode 37996: reward = -51.19, steps = 19 03:13:02 [INFO] train episode 37997: reward = -64.10, steps = 34 03:13:05 [INFO] train episode 37998: reward = -70.47, steps = 26 03:13:08 [INFO] train episode 37999: reward = -87.48, steps = 36 03:13:10 [INFO] train episode 38000: reward = -95.69, steps = 28 03:13:14 [INFO] train episode 38001: reward = -86.47, steps = 39 03:13:16 [INFO] train episode 38002: reward = -79.80, steps = 21 03:13:19 [INFO] train episode 38003: reward = -58.89, steps = 34 03:13:21 [INFO] train episode 38004: reward = -71.87, steps = 21 03:13:23 [INFO] train episode 38005: reward = -150.13, steps = 31 03:13:26 [INFO] train episode 38006: reward = -67.70, steps = 33 03:13:28 [INFO] train episode 38007: reward = -102.96, steps = 18 03:13:32 [INFO] train episode 38008: reward = -111.41, steps = 44 03:13:35 [INFO] train episode 38009: reward = -50.10, steps = 35 03:13:36 [INFO] train episode 38010: reward = -86.21, steps = 19 03:13:38 [INFO] train episode 38011: reward = -47.35, steps = 24 03:13:40 [INFO] train episode 38012: reward = -94.02, steps = 19 03:13:42 [INFO] train episode 38013: reward = -66.50, steps = 21 03:13:44 [INFO] train episode 38014: reward = -57.37, steps = 29 03:13:46 [INFO] train episode 38015: reward = -68.86, steps = 19 03:13:49 [INFO] train episode 38016: reward = -72.91, steps = 26 03:13:51 [INFO] train episode 38017: reward = -117.80, steps = 33 03:13:55 [INFO] train episode 38018: reward = -77.37, steps = 36 03:13:56 [INFO] train episode 38019: reward = -72.26, steps = 20 03:13:59 [INFO] train episode 38020: reward = -70.19, steps = 35 03:14:02 [INFO] train episode 38021: reward = -52.99, steps = 26 03:14:05 [INFO] train episode 38022: reward = -43.08, steps = 35 03:14:07 [INFO] train episode 38023: reward = -102.44, steps = 28 03:14:09 [INFO] train episode 38024: reward = -137.70, steps = 19 03:14:12 [INFO] train episode 38025: reward = -76.26, steps = 33 03:14:15 [INFO] train episode 38026: reward = -90.94, steps = 33 03:14:18 [INFO] train episode 38027: reward = -68.58, steps = 36 03:14:20 [INFO] train episode 38028: reward = -49.66, steps = 27 03:14:24 [INFO] train episode 38029: reward = -96.52, steps = 48 03:14:27 [INFO] train episode 38030: reward = -74.08, steps = 27 03:14:29 [INFO] train episode 38031: reward = -63.03, steps = 20 03:14:30 [INFO] train episode 38032: reward = -58.67, steps = 20 03:14:32 [INFO] train episode 38033: reward = -61.14, steps = 17 03:14:36 [INFO] train episode 38034: reward = -84.08, steps = 42 03:14:39 [INFO] train episode 38035: reward = -46.45, steps = 41 03:14:42 [INFO] train episode 38036: reward = -90.42, steps = 32 03:14:44 [INFO] train episode 38037: reward = -59.43, steps = 21 03:14:46 [INFO] train episode 38038: reward = -60.46, steps = 21 03:14:48 [INFO] train episode 38039: reward = -97.77, steps = 19 03:14:49 [INFO] train episode 38040: reward = -52.34, steps = 21 03:14:52 [INFO] train episode 38041: reward = -45.81, steps = 20 03:14:53 [INFO] train episode 38042: reward = -73.61, steps = 20 03:14:56 [INFO] train episode 38043: reward = -43.69, steps = 26 03:14:59 [INFO] train episode 38044: reward = -58.06, steps = 31 03:15:05 [INFO] train episode 38045: reward = -168.60, steps = 73 03:15:07 [INFO] train episode 38046: reward = -95.97, steps = 21 03:15:09 [INFO] train episode 38047: reward = -117.05, steps = 22 03:15:11 [INFO] train episode 38048: reward = -85.45, steps = 25 03:15:13 [INFO] train episode 38049: reward = -55.01, steps = 21 03:15:15 [INFO] train episode 38050: reward = -52.50, steps = 20 03:15:18 [INFO] train episode 38051: reward = -89.08, steps = 35 03:15:20 [INFO] train episode 38052: reward = -38.57, steps = 28 03:15:24 [INFO] train episode 38053: reward = -131.49, steps = 33 03:15:26 [INFO] train episode 38054: reward = -69.47, steps = 21 03:15:27 [INFO] train episode 38055: reward = -69.42, steps = 19 03:15:30 [INFO] train episode 38056: reward = -48.51, steps = 30 03:15:32 [INFO] train episode 38057: reward = -93.12, steps = 26 03:15:34 [INFO] train episode 38058: reward = -76.24, steps = 20 03:15:36 [INFO] train episode 38059: reward = -70.24, steps = 24 03:15:40 [INFO] train episode 38060: reward = -61.09, steps = 41 03:15:42 [INFO] train episode 38061: reward = -111.24, steps = 25 03:15:45 [INFO] train episode 38062: reward = -45.56, steps = 38 03:15:48 [INFO] train episode 38063: reward = -56.14, steps = 38 03:15:52 [INFO] train episode 38064: reward = -110.01, steps = 45 03:15:54 [INFO] train episode 38065: reward = -57.02, steps = 24 03:15:56 [INFO] train episode 38066: reward = -98.53, steps = 20 03:15:59 [INFO] train episode 38067: reward = -96.18, steps = 35 03:16:02 [INFO] train episode 38068: reward = -84.34, steps = 28 03:16:04 [INFO] train episode 38069: reward = -80.38, steps = 24 03:16:07 [INFO] train episode 38070: reward = -90.13, steps = 32 03:16:12 [INFO] train episode 38071: reward = -111.81, steps = 64 03:16:14 [INFO] train episode 38072: reward = -76.19, steps = 19 03:16:17 [INFO] train episode 38073: reward = -83.43, steps = 39 03:16:20 [INFO] train episode 38074: reward = -83.98, steps = 26 03:16:22 [INFO] train episode 38075: reward = -74.45, steps = 26 03:16:24 [INFO] train episode 38076: reward = -83.79, steps = 21 03:16:26 [INFO] train episode 38077: reward = -115.54, steps = 23 03:16:28 [INFO] train episode 38078: reward = -100.52, steps = 25 03:16:31 [INFO] train episode 38079: reward = -77.41, steps = 32 03:16:33 [INFO] train episode 38080: reward = -92.80, steps = 23 03:16:35 [INFO] train episode 38081: reward = -94.78, steps = 28 03:16:38 [INFO] train episode 38082: reward = -59.86, steps = 27 03:16:41 [INFO] train episode 38083: reward = -76.83, steps = 35 03:16:44 [INFO] train episode 38084: reward = -114.24, steps = 34 03:16:46 [INFO] train episode 38085: reward = -92.17, steps = 26 03:16:50 [INFO] train episode 38086: reward = -93.27, steps = 45 03:16:52 [INFO] train episode 38087: reward = -66.75, steps = 22 03:16:55 [INFO] train episode 38088: reward = -78.86, steps = 27 03:16:57 [INFO] train episode 38089: reward = -84.58, steps = 30 03:17:01 [INFO] train episode 38090: reward = -72.72, steps = 38 03:17:03 [INFO] train episode 38091: reward = -103.57, steps = 20 03:17:05 [INFO] train episode 38092: reward = -90.01, steps = 27 03:17:07 [INFO] train episode 38093: reward = -90.45, steps = 19 03:17:09 [INFO] train episode 38094: reward = -71.05, steps = 29 03:17:11 [INFO] train episode 38095: reward = -72.22, steps = 23 03:17:14 [INFO] train episode 38096: reward = -78.83, steps = 35 03:17:16 [INFO] train episode 38097: reward = -71.35, steps = 21 03:17:19 [INFO] train episode 38098: reward = -64.01, steps = 33 03:17:22 [INFO] train episode 38099: reward = -60.37, steps = 27 03:17:24 [INFO] train episode 38100: reward = -80.57, steps = 26 03:17:27 [INFO] train episode 38101: reward = -84.84, steps = 33 03:17:28 [INFO] train episode 38102: reward = -57.65, steps = 20 03:17:30 [INFO] train episode 38103: reward = -77.22, steps = 19 03:17:33 [INFO] train episode 38104: reward = -68.09, steps = 31 03:17:36 [INFO] train episode 38105: reward = -70.67, steps = 31 03:17:38 [INFO] train episode 38106: reward = -74.22, steps = 21 03:17:40 [INFO] train episode 38107: reward = -98.68, steps = 32 03:17:43 [INFO] train episode 38108: reward = -91.80, steps = 26 03:17:45 [INFO] train episode 38109: reward = -115.10, steps = 33 03:17:51 [INFO] train episode 38110: reward = -148.89, steps = 57 03:17:54 [INFO] train episode 38111: reward = -85.79, steps = 33 03:17:57 [INFO] train episode 38112: reward = -49.31, steps = 31 03:17:59 [INFO] train episode 38113: reward = -69.38, steps = 20 03:18:00 [INFO] train episode 38114: reward = -106.34, steps = 20 03:18:05 [INFO] train episode 38115: reward = -38.38, steps = 48 03:18:09 [INFO] train episode 38116: reward = -86.18, steps = 45 03:18:12 [INFO] train episode 38117: reward = -174.42, steps = 35 03:18:14 [INFO] train episode 38118: reward = -69.03, steps = 22 03:18:17 [INFO] train episode 38119: reward = -95.14, steps = 40 03:18:19 [INFO] train episode 38120: reward = -59.95, steps = 23 03:18:22 [INFO] train episode 38121: reward = -52.49, steps = 27 03:18:24 [INFO] train episode 38122: reward = -79.55, steps = 21 03:18:27 [INFO] train episode 38123: reward = -70.86, steps = 35 03:18:28 [INFO] train episode 38124: reward = -62.06, steps = 20 03:18:33 [INFO] train episode 38125: reward = -94.58, steps = 51 03:18:35 [INFO] train episode 38126: reward = -64.83, steps = 25 03:18:37 [INFO] train episode 38127: reward = -87.06, steps = 21 03:18:40 [INFO] train episode 38128: reward = -73.81, steps = 29 03:18:41 [INFO] train episode 38129: reward = -51.23, steps = 20 03:18:45 [INFO] train episode 38130: reward = -94.02, steps = 39 03:18:47 [INFO] train episode 38131: reward = -148.88, steps = 23 03:18:50 [INFO] train episode 38132: reward = -108.97, steps = 29 03:18:53 [INFO] train episode 38133: reward = -125.48, steps = 38 03:18:56 [INFO] train episode 38134: reward = -73.21, steps = 36 03:18:59 [INFO] train episode 38135: reward = -91.21, steps = 33 03:19:01 [INFO] train episode 38136: reward = -55.22, steps = 24 03:19:04 [INFO] train episode 38137: reward = -65.00, steps = 38 03:19:07 [INFO] train episode 38138: reward = -73.58, steps = 33 03:19:09 [INFO] train episode 38139: reward = -81.52, steps = 19 03:19:13 [INFO] train episode 38140: reward = -81.74, steps = 41 03:19:16 [INFO] train episode 38141: reward = -98.29, steps = 41 03:19:20 [INFO] train episode 38142: reward = -64.96, steps = 47 03:19:22 [INFO] train episode 38143: reward = -63.45, steps = 28 03:19:24 [INFO] train episode 38144: reward = -92.70, steps = 19 03:19:27 [INFO] train episode 38145: reward = -113.74, steps = 35 03:19:30 [INFO] train episode 38146: reward = -80.50, steps = 28 03:19:32 [INFO] train episode 38147: reward = -80.99, steps = 20 03:19:34 [INFO] train episode 38148: reward = -93.80, steps = 30 03:19:38 [INFO] train episode 38149: reward = -90.87, steps = 46 03:19:42 [INFO] train episode 38150: reward = -74.04, steps = 41 03:19:45 [INFO] train episode 38151: reward = -58.92, steps = 32 03:19:46 [INFO] train episode 38152: reward = -92.59, steps = 19 03:19:49 [INFO] train episode 38153: reward = -99.09, steps = 26 03:19:52 [INFO] train episode 38154: reward = -135.59, steps = 39 03:19:56 [INFO] train episode 38155: reward = -112.91, steps = 44 03:19:58 [INFO] train episode 38156: reward = -55.36, steps = 19 03:20:00 [INFO] train episode 38157: reward = -57.82, steps = 27 03:20:02 [INFO] train episode 38158: reward = -63.22, steps = 21 03:20:05 [INFO] train episode 38159: reward = -65.99, steps = 36 03:20:10 [INFO] train episode 38160: reward = -157.44, steps = 50 03:20:11 [INFO] train episode 38161: reward = -69.62, steps = 20 03:20:16 [INFO] train episode 38162: reward = -68.43, steps = 45 03:20:18 [INFO] train episode 38163: reward = -87.64, steps = 28 03:20:20 [INFO] train episode 38164: reward = -80.17, steps = 22 03:20:22 [INFO] train episode 38165: reward = -76.24, steps = 19 03:20:25 [INFO] train episode 38166: reward = -108.40, steps = 41 03:20:30 [INFO] train episode 38167: reward = -77.09, steps = 46 03:20:31 [INFO] train episode 38168: reward = -73.17, steps = 21 03:20:35 [INFO] train episode 38169: reward = -155.83, steps = 44 03:20:38 [INFO] train episode 38170: reward = -100.84, steps = 27 03:20:40 [INFO] train episode 38171: reward = -120.38, steps = 22 03:20:42 [INFO] train episode 38172: reward = -88.09, steps = 26 03:20:45 [INFO] train episode 38173: reward = -108.02, steps = 24 03:20:47 [INFO] train episode 38174: reward = -80.88, steps = 21 03:20:49 [INFO] train episode 38175: reward = -81.01, steps = 23 03:20:52 [INFO] train episode 38176: reward = -70.33, steps = 31 03:20:54 [INFO] train episode 38177: reward = -35.12, steps = 26 03:20:57 [INFO] train episode 38178: reward = -71.24, steps = 28 03:21:00 [INFO] train episode 38179: reward = -77.25, steps = 25 03:21:02 [INFO] train episode 38180: reward = -68.26, steps = 21 03:21:07 [INFO] train episode 38181: reward = -150.52, steps = 48 03:21:11 [INFO] train episode 38182: reward = -67.19, steps = 39 03:21:14 [INFO] train episode 38183: reward = -116.63, steps = 34 03:21:17 [INFO] train episode 38184: reward = -90.85, steps = 26 03:21:21 [INFO] train episode 38185: reward = -63.59, steps = 42 03:21:23 [INFO] train episode 38186: reward = -154.56, steps = 20 03:21:25 [INFO] train episode 38187: reward = -74.31, steps = 23 03:21:28 [INFO] train episode 38188: reward = -59.62, steps = 33 03:21:30 [INFO] train episode 38189: reward = -93.60, steps = 23 03:21:32 [INFO] train episode 38190: reward = -130.39, steps = 19 03:21:36 [INFO] train episode 38191: reward = -113.91, steps = 41 03:21:40 [INFO] train episode 38192: reward = -94.44, steps = 43 03:21:42 [INFO] train episode 38193: reward = -75.32, steps = 26 03:21:45 [INFO] train episode 38194: reward = -68.81, steps = 24 03:21:51 [INFO] train episode 38195: reward = -119.46, steps = 71 03:21:55 [INFO] train episode 38196: reward = -125.96, steps = 41 03:21:57 [INFO] train episode 38197: reward = -60.13, steps = 26 03:22:01 [INFO] train episode 38198: reward = -77.43, steps = 36 03:22:05 [INFO] train episode 38199: reward = -80.75, steps = 54 03:22:07 [INFO] train episode 38200: reward = -61.56, steps = 21 03:22:10 [INFO] train episode 38201: reward = -91.30, steps = 34 03:22:14 [INFO] train episode 38202: reward = -102.56, steps = 41 03:22:17 [INFO] train episode 38203: reward = -130.25, steps = 30 03:22:19 [INFO] train episode 38204: reward = -110.10, steps = 19 03:22:22 [INFO] train episode 38205: reward = -39.27, steps = 37 03:22:24 [INFO] train episode 38206: reward = -71.45, steps = 25 03:22:26 [INFO] train episode 38207: reward = -70.49, steps = 18 03:22:31 [INFO] train episode 38208: reward = -117.06, steps = 46 03:22:32 [INFO] train episode 38209: reward = -60.61, steps = 22 03:22:36 [INFO] train episode 38210: reward = -129.69, steps = 33 03:22:38 [INFO] train episode 38211: reward = -72.06, steps = 26 03:22:41 [INFO] train episode 38212: reward = -93.59, steps = 38 03:22:45 [INFO] train episode 38213: reward = -80.17, steps = 43 03:22:48 [INFO] train episode 38214: reward = -54.98, steps = 22 03:22:50 [INFO] train episode 38215: reward = -59.57, steps = 25 03:22:52 [INFO] train episode 38216: reward = -54.42, steps = 26 03:22:55 [INFO] train episode 38217: reward = -46.83, steps = 28 03:22:57 [INFO] train episode 38218: reward = -65.78, steps = 21 03:22:59 [INFO] train episode 38219: reward = -42.70, steps = 23 03:23:00 [INFO] train episode 38220: reward = -73.04, steps = 19 03:23:03 [INFO] train episode 38221: reward = -120.40, steps = 30 03:23:07 [INFO] train episode 38222: reward = -82.93, steps = 44 03:23:10 [INFO] train episode 38223: reward = -61.12, steps = 34 03:23:13 [INFO] train episode 38224: reward = -140.22, steps = 34 03:23:15 [INFO] train episode 38225: reward = -68.82, steps = 19 03:23:18 [INFO] train episode 38226: reward = -97.84, steps = 33 03:23:20 [INFO] train episode 38227: reward = -75.73, steps = 22 03:23:23 [INFO] train episode 38228: reward = -75.31, steps = 32 03:23:26 [INFO] train episode 38229: reward = -109.05, steps = 33 03:23:29 [INFO] train episode 38230: reward = -103.89, steps = 37 03:23:31 [INFO] train episode 38231: reward = -95.55, steps = 19 03:23:35 [INFO] train episode 38232: reward = -97.03, steps = 41 03:23:37 [INFO] train episode 38233: reward = -68.23, steps = 21 03:23:40 [INFO] train episode 38234: reward = -92.02, steps = 32 03:23:42 [INFO] train episode 38235: reward = -54.41, steps = 22 03:23:45 [INFO] train episode 38236: reward = -76.93, steps = 36 03:23:48 [INFO] train episode 38237: reward = -43.38, steps = 26 03:23:50 [INFO] train episode 38238: reward = -70.42, steps = 19 03:23:52 [INFO] train episode 38239: reward = -68.56, steps = 23 03:23:54 [INFO] train episode 38240: reward = -102.48, steps = 19 03:23:56 [INFO] train episode 38241: reward = -70.35, steps = 19 03:23:58 [INFO] train episode 38242: reward = -63.81, steps = 22 03:24:00 [INFO] train episode 38243: reward = -80.40, steps = 25 03:24:03 [INFO] train episode 38244: reward = -114.69, steps = 29 03:24:05 [INFO] train episode 38245: reward = -88.37, steps = 19 03:24:07 [INFO] train episode 38246: reward = -59.57, steps = 29 03:24:09 [INFO] train episode 38247: reward = -47.11, steps = 21 03:24:12 [INFO] train episode 38248: reward = -66.38, steps = 27 03:24:14 [INFO] train episode 38249: reward = -114.43, steps = 23 03:24:16 [INFO] train episode 38250: reward = -54.06, steps = 32 03:24:19 [INFO] train episode 38251: reward = -46.60, steps = 27 03:24:20 [INFO] train episode 38252: reward = -106.79, steps = 18 03:24:24 [INFO] train episode 38253: reward = -76.54, steps = 41 03:24:27 [INFO] train episode 38254: reward = -105.79, steps = 33 03:24:29 [INFO] train episode 38255: reward = -75.97, steps = 24 03:24:31 [INFO] train episode 38256: reward = -86.19, steps = 21 03:24:34 [INFO] train episode 38257: reward = -89.64, steps = 34 03:24:37 [INFO] train episode 38258: reward = -99.31, steps = 34 03:24:40 [INFO] train episode 38259: reward = -74.70, steps = 28 03:24:42 [INFO] train episode 38260: reward = -106.62, steps = 24 03:24:46 [INFO] train episode 38261: reward = -204.02, steps = 39 03:24:48 [INFO] train episode 38262: reward = -76.50, steps = 23 03:24:50 [INFO] train episode 38263: reward = -52.88, steps = 32 03:24:52 [INFO] train episode 38264: reward = -74.00, steps = 23 03:24:56 [INFO] train episode 38265: reward = -60.08, steps = 35 03:24:59 [INFO] train episode 38266: reward = -74.38, steps = 37 03:25:02 [INFO] train episode 38267: reward = -132.45, steps = 34 03:25:06 [INFO] train episode 38268: reward = -75.50, steps = 43 03:25:09 [INFO] train episode 38269: reward = -102.31, steps = 33 03:25:11 [INFO] train episode 38270: reward = -61.20, steps = 20 03:25:13 [INFO] train episode 38271: reward = -77.35, steps = 23 03:25:15 [INFO] train episode 38272: reward = -87.37, steps = 25 03:25:19 [INFO] train episode 38273: reward = -85.19, steps = 42 03:25:20 [INFO] train episode 38274: reward = -68.83, steps = 19 03:25:22 [INFO] train episode 38275: reward = -59.75, steps = 20 03:25:25 [INFO] train episode 38276: reward = -77.62, steps = 36 03:25:27 [INFO] train episode 38277: reward = -83.83, steps = 19 03:25:31 [INFO] train episode 38278: reward = -55.13, steps = 45 03:25:33 [INFO] train episode 38279: reward = -64.99, steps = 20 03:25:37 [INFO] train episode 38280: reward = -70.35, steps = 48 03:25:41 [INFO] train episode 38281: reward = -177.20, steps = 42 03:25:42 [INFO] train episode 38282: reward = -60.97, steps = 19 03:25:44 [INFO] train episode 38283: reward = -96.99, steps = 21 03:25:49 [INFO] train episode 38284: reward = -79.67, steps = 52 03:25:51 [INFO] train episode 38285: reward = -51.53, steps = 26 03:25:54 [INFO] train episode 38286: reward = -79.24, steps = 28 03:25:56 [INFO] train episode 38287: reward = -43.93, steps = 33 03:25:59 [INFO] train episode 38288: reward = -40.03, steps = 33 03:26:01 [INFO] train episode 38289: reward = -104.37, steps = 21 03:26:03 [INFO] train episode 38290: reward = -77.14, steps = 24 03:26:06 [INFO] train episode 38291: reward = -46.27, steps = 25 03:26:08 [INFO] train episode 38292: reward = -67.95, steps = 20 03:26:12 [INFO] train episode 38293: reward = -86.92, steps = 45 03:26:14 [INFO] train episode 38294: reward = -66.43, steps = 24 03:26:18 [INFO] train episode 38295: reward = -82.34, steps = 52 03:26:20 [INFO] train episode 38296: reward = -50.74, steps = 23 03:26:22 [INFO] train episode 38297: reward = -95.50, steps = 21 03:26:24 [INFO] train episode 38298: reward = -76.50, steps = 22 03:26:27 [INFO] train episode 38299: reward = -77.93, steps = 29 03:26:29 [INFO] train episode 38300: reward = -82.88, steps = 27 03:26:31 [INFO] train episode 38301: reward = -55.89, steps = 24 03:26:33 [INFO] train episode 38302: reward = -70.42, steps = 20 03:26:34 [INFO] train episode 38303: reward = -73.79, steps = 16 03:26:36 [INFO] train episode 38304: reward = -68.66, steps = 25 03:26:40 [INFO] train episode 38305: reward = -119.62, steps = 36 03:26:42 [INFO] train episode 38306: reward = -66.81, steps = 19 03:26:45 [INFO] train episode 38307: reward = -41.20, steps = 33 03:26:48 [INFO] train episode 38308: reward = -77.73, steps = 34 03:26:52 [INFO] train episode 38309: reward = -79.79, steps = 48 03:26:56 [INFO] train episode 38310: reward = -108.07, steps = 37 03:26:59 [INFO] train episode 38311: reward = -118.95, steps = 33 03:27:03 [INFO] train episode 38312: reward = -134.91, steps = 50 03:27:05 [INFO] train episode 38313: reward = -79.25, steps = 20 03:27:09 [INFO] train episode 38314: reward = -75.51, steps = 50 03:27:12 [INFO] train episode 38315: reward = -69.48, steps = 22 03:27:13 [INFO] train episode 38316: reward = -126.51, steps = 20 03:27:15 [INFO] train episode 38317: reward = -105.29, steps = 20 03:27:17 [INFO] train episode 38318: reward = -70.61, steps = 22 03:27:20 [INFO] train episode 38319: reward = -55.66, steps = 33 03:27:22 [INFO] train episode 38320: reward = -60.03, steps = 19 03:27:25 [INFO] train episode 38321: reward = -156.93, steps = 36 03:27:28 [INFO] train episode 38322: reward = -106.23, steps = 39 03:27:31 [INFO] train episode 38323: reward = -61.63, steps = 32 03:27:35 [INFO] train episode 38324: reward = -177.28, steps = 42 03:27:37 [INFO] train episode 38325: reward = -64.13, steps = 25 03:27:40 [INFO] train episode 38326: reward = -80.72, steps = 39 03:27:44 [INFO] train episode 38327: reward = -134.35, steps = 38 03:27:47 [INFO] train episode 38328: reward = -44.87, steps = 33 03:27:49 [INFO] train episode 38329: reward = -76.19, steps = 30 03:27:51 [INFO] train episode 38330: reward = -93.45, steps = 22 03:27:53 [INFO] train episode 38331: reward = -99.98, steps = 23 03:27:55 [INFO] train episode 38332: reward = -96.19, steps = 22 03:27:58 [INFO] train episode 38333: reward = -113.86, steps = 28 03:28:00 [INFO] train episode 38334: reward = -79.53, steps = 23 03:28:02 [INFO] train episode 38335: reward = -50.36, steps = 24 03:28:05 [INFO] train episode 38336: reward = -100.88, steps = 42 03:28:09 [INFO] train episode 38337: reward = -95.00, steps = 43 03:28:11 [INFO] train episode 38338: reward = -49.32, steps = 21 03:28:14 [INFO] train episode 38339: reward = -90.90, steps = 31 03:28:16 [INFO] train episode 38340: reward = -125.70, steps = 24 03:28:19 [INFO] train episode 38341: reward = -83.83, steps = 34 03:28:21 [INFO] train episode 38342: reward = -84.74, steps = 21 03:28:24 [INFO] train episode 38343: reward = -79.87, steps = 32 03:28:26 [INFO] train episode 38344: reward = -106.55, steps = 23 03:28:28 [INFO] train episode 38345: reward = -59.02, steps = 22 03:28:30 [INFO] train episode 38346: reward = -61.20, steps = 26 03:28:32 [INFO] train episode 38347: reward = -82.00, steps = 25 03:28:35 [INFO] train episode 38348: reward = -86.95, steps = 25 03:28:37 [INFO] train episode 38349: reward = -71.35, steps = 28 03:28:39 [INFO] train episode 38350: reward = -79.94, steps = 21 03:28:43 [INFO] train episode 38351: reward = -86.64, steps = 51 03:28:45 [INFO] train episode 38352: reward = -99.51, steps = 21 03:28:48 [INFO] train episode 38353: reward = -83.21, steps = 32 03:28:51 [INFO] train episode 38354: reward = -70.23, steps = 37 03:28:54 [INFO] train episode 38355: reward = -90.27, steps = 35 03:28:56 [INFO] train episode 38356: reward = -85.51, steps = 20 03:28:59 [INFO] train episode 38357: reward = -60.53, steps = 34 03:29:03 [INFO] train episode 38358: reward = -55.17, steps = 37 03:29:06 [INFO] train episode 38359: reward = -105.20, steps = 37 03:29:08 [INFO] train episode 38360: reward = -65.32, steps = 18 03:29:10 [INFO] train episode 38361: reward = -83.10, steps = 27 03:29:14 [INFO] train episode 38362: reward = -58.26, steps = 41 03:29:16 [INFO] train episode 38363: reward = -50.52, steps = 20 03:29:19 [INFO] train episode 38364: reward = -108.03, steps = 34 03:29:22 [INFO] train episode 38365: reward = -93.08, steps = 30 03:29:23 [INFO] train episode 38366: reward = -110.66, steps = 19 03:29:25 [INFO] train episode 38367: reward = -62.44, steps = 23 03:29:28 [INFO] train episode 38368: reward = -93.06, steps = 28 03:29:31 [INFO] train episode 38369: reward = -118.96, steps = 34 03:29:32 [INFO] train episode 38370: reward = -78.09, steps = 20 03:29:38 [INFO] train episode 38371: reward = -162.98, steps = 48 03:29:39 [INFO] train episode 38372: reward = -95.72, steps = 19 03:29:41 [INFO] train episode 38373: reward = -49.47, steps = 21 03:29:43 [INFO] train episode 38374: reward = -103.60, steps = 20 03:29:45 [INFO] train episode 38375: reward = -41.15, steps = 27 03:29:49 [INFO] train episode 38376: reward = -57.65, steps = 43 03:29:51 [INFO] train episode 38377: reward = -57.40, steps = 18 03:29:54 [INFO] train episode 38378: reward = -125.94, steps = 43 03:29:57 [INFO] train episode 38379: reward = -70.48, steps = 29 03:30:00 [INFO] train episode 38380: reward = -62.20, steps = 37 03:30:02 [INFO] train episode 38381: reward = -78.65, steps = 20 03:30:04 [INFO] train episode 38382: reward = -71.94, steps = 21 03:30:06 [INFO] train episode 38383: reward = -58.53, steps = 27 03:30:10 [INFO] train episode 38384: reward = -54.81, steps = 40 03:30:12 [INFO] train episode 38385: reward = -86.02, steps = 32 03:30:15 [INFO] train episode 38386: reward = -98.37, steps = 33 03:30:18 [INFO] train episode 38387: reward = -72.95, steps = 32 03:30:20 [INFO] train episode 38388: reward = -77.70, steps = 20 03:30:22 [INFO] train episode 38389: reward = -80.41, steps = 28 03:30:26 [INFO] train episode 38390: reward = -71.59, steps = 40 03:30:28 [INFO] train episode 38391: reward = -64.29, steps = 23 03:30:33 [INFO] train episode 38392: reward = -173.86, steps = 54 03:30:34 [INFO] train episode 38393: reward = -98.99, steps = 20 03:30:37 [INFO] train episode 38394: reward = -83.47, steps = 27 03:30:40 [INFO] train episode 38395: reward = -108.92, steps = 33 03:30:42 [INFO] train episode 38396: reward = -76.30, steps = 20 03:30:45 [INFO] train episode 38397: reward = -35.36, steps = 34 03:30:47 [INFO] train episode 38398: reward = -76.95, steps = 22 03:30:49 [INFO] train episode 38399: reward = -86.19, steps = 29 03:30:52 [INFO] train episode 38400: reward = -65.87, steps = 31 03:30:54 [INFO] train episode 38401: reward = -94.76, steps = 19 03:30:58 [INFO] train episode 38402: reward = -91.93, steps = 41 03:31:00 [INFO] train episode 38403: reward = -81.71, steps = 26 03:31:02 [INFO] train episode 38404: reward = -66.49, steps = 23 03:31:04 [INFO] train episode 38405: reward = -54.68, steps = 26 03:31:06 [INFO] train episode 38406: reward = -103.65, steps = 21 03:31:07 [INFO] train episode 38407: reward = -67.05, steps = 18 03:31:09 [INFO] train episode 38408: reward = -98.83, steps = 20 03:31:12 [INFO] train episode 38409: reward = -132.25, steps = 29 03:31:14 [INFO] train episode 38410: reward = -82.34, steps = 21 03:31:16 [INFO] train episode 38411: reward = -72.79, steps = 22 03:31:18 [INFO] train episode 38412: reward = -83.24, steps = 20 03:31:20 [INFO] train episode 38413: reward = -83.51, steps = 24 03:31:25 [INFO] train episode 38414: reward = -128.92, steps = 63 03:31:29 [INFO] train episode 38415: reward = -75.41, steps = 41 03:31:31 [INFO] train episode 38416: reward = -47.10, steps = 20 03:31:33 [INFO] train episode 38417: reward = -74.79, steps = 25 03:31:34 [INFO] train episode 38418: reward = -56.45, steps = 19 03:31:36 [INFO] train episode 38419: reward = -70.67, steps = 20 03:31:38 [INFO] train episode 38420: reward = -97.45, steps = 18 03:31:41 [INFO] train episode 38421: reward = -85.35, steps = 37 03:31:43 [INFO] train episode 38422: reward = -79.28, steps = 27 03:31:45 [INFO] train episode 38423: reward = -55.51, steps = 21 03:31:47 [INFO] train episode 38424: reward = -65.16, steps = 21 03:31:50 [INFO] train episode 38425: reward = -99.25, steps = 32 03:31:52 [INFO] train episode 38426: reward = -98.44, steps = 21 03:31:54 [INFO] train episode 38427: reward = -127.23, steps = 23 03:31:56 [INFO] train episode 38428: reward = -57.26, steps = 31 03:31:58 [INFO] train episode 38429: reward = -101.23, steps = 24 03:32:02 [INFO] train episode 38430: reward = -81.26, steps = 32 03:32:03 [INFO] train episode 38431: reward = -106.32, steps = 20 03:32:06 [INFO] train episode 38432: reward = -107.75, steps = 26 03:32:08 [INFO] train episode 38433: reward = -151.29, steps = 31 03:32:10 [INFO] train episode 38434: reward = -77.83, steps = 23 03:32:14 [INFO] train episode 38435: reward = -92.82, steps = 42 03:32:16 [INFO] train episode 38436: reward = -85.55, steps = 22 03:32:18 [INFO] train episode 38437: reward = -79.11, steps = 20 03:32:20 [INFO] train episode 38438: reward = -56.31, steps = 26 03:32:22 [INFO] train episode 38439: reward = -113.64, steps = 23 03:32:24 [INFO] train episode 38440: reward = -78.96, steps = 21 03:32:26 [INFO] train episode 38441: reward = -82.65, steps = 23 03:32:30 [INFO] train episode 38442: reward = -61.88, steps = 33 03:32:31 [INFO] train episode 38443: reward = -57.72, steps = 20 03:32:34 [INFO] train episode 38444: reward = -100.87, steps = 22 03:32:37 [INFO] train episode 38445: reward = -94.50, steps = 30 03:32:40 [INFO] train episode 38446: reward = -75.38, steps = 40 03:32:45 [INFO] train episode 38447: reward = -173.87, steps = 57 03:32:48 [INFO] train episode 38448: reward = -94.71, steps = 37 03:32:50 [INFO] train episode 38449: reward = -121.89, steps = 20 03:32:52 [INFO] train episode 38450: reward = -70.26, steps = 22 03:32:54 [INFO] train episode 38451: reward = -73.42, steps = 26 03:32:57 [INFO] train episode 38452: reward = -66.34, steps = 25 03:33:00 [INFO] train episode 38453: reward = -63.11, steps = 43 03:33:02 [INFO] train episode 38454: reward = -91.26, steps = 24 03:33:06 [INFO] train episode 38455: reward = -78.07, steps = 41 03:33:09 [INFO] train episode 38456: reward = -81.68, steps = 39 03:33:12 [INFO] train episode 38457: reward = -83.59, steps = 26 03:33:14 [INFO] train episode 38458: reward = -121.81, steps = 31 03:33:16 [INFO] train episode 38459: reward = -77.14, steps = 20 03:33:20 [INFO] train episode 38460: reward = -129.88, steps = 44 03:33:23 [INFO] train episode 38461: reward = -99.50, steps = 25 03:33:26 [INFO] train episode 38462: reward = -163.94, steps = 42 03:33:30 [INFO] train episode 38463: reward = -120.14, steps = 51 03:33:32 [INFO] train episode 38464: reward = -46.79, steps = 21 03:33:35 [INFO] train episode 38465: reward = -86.54, steps = 36 03:33:38 [INFO] train episode 38466: reward = -106.72, steps = 29 03:33:41 [INFO] train episode 38467: reward = -116.17, steps = 29 03:33:44 [INFO] train episode 38468: reward = -100.55, steps = 42 03:33:48 [INFO] train episode 38469: reward = -59.05, steps = 43 03:33:51 [INFO] train episode 38470: reward = -81.16, steps = 34 03:33:53 [INFO] train episode 38471: reward = -82.77, steps = 24 03:33:56 [INFO] train episode 38472: reward = -77.36, steps = 38 03:33:58 [INFO] train episode 38473: reward = -70.99, steps = 17 03:33:59 [INFO] train episode 38474: reward = -47.52, steps = 20 03:34:01 [INFO] train episode 38475: reward = -80.75, steps = 14 03:34:02 [INFO] train episode 38476: reward = -65.75, steps = 20 03:34:04 [INFO] train episode 38477: reward = -58.24, steps = 21 03:34:07 [INFO] train episode 38478: reward = -87.02, steps = 36 03:34:10 [INFO] train episode 38479: reward = -68.35, steps = 23 03:34:13 [INFO] train episode 38480: reward = -71.08, steps = 37 03:34:15 [INFO] train episode 38481: reward = -55.40, steps = 19 03:34:17 [INFO] train episode 38482: reward = -83.06, steps = 29 03:34:21 [INFO] train episode 38483: reward = -106.42, steps = 39 03:34:23 [INFO] train episode 38484: reward = -76.43, steps = 24 03:34:24 [INFO] train episode 38485: reward = -75.02, steps = 19 03:34:29 [INFO] train episode 38486: reward = -92.87, steps = 49 03:34:34 [INFO] train episode 38487: reward = -133.48, steps = 59 03:34:36 [INFO] train episode 38488: reward = -66.47, steps = 28 03:34:41 [INFO] train episode 38489: reward = -78.47, steps = 49 03:34:44 [INFO] train episode 38490: reward = -77.12, steps = 37 03:34:46 [INFO] train episode 38491: reward = -73.28, steps = 24 03:34:51 [INFO] train episode 38492: reward = -85.67, steps = 55 03:34:53 [INFO] train episode 38493: reward = -70.55, steps = 18 03:34:55 [INFO] train episode 38494: reward = -50.05, steps = 31 03:34:57 [INFO] train episode 38495: reward = -80.99, steps = 21 03:34:59 [INFO] train episode 38496: reward = -79.22, steps = 18 03:35:01 [INFO] train episode 38497: reward = -71.23, steps = 26 03:35:04 [INFO] train episode 38498: reward = -93.52, steps = 35 03:35:06 [INFO] train episode 38499: reward = -83.85, steps = 23 03:35:10 [INFO] train episode 38500: reward = -96.30, steps = 44 03:35:12 [INFO] train episode 38501: reward = -57.31, steps = 20 03:35:14 [INFO] train episode 38502: reward = -56.72, steps = 22 03:35:16 [INFO] train episode 38503: reward = -62.37, steps = 24 03:35:18 [INFO] train episode 38504: reward = -67.04, steps = 29 03:35:20 [INFO] train episode 38505: reward = -80.18, steps = 20 03:35:24 [INFO] train episode 38506: reward = -47.67, steps = 32 03:35:26 [INFO] train episode 38507: reward = -60.56, steps = 22 03:35:28 [INFO] train episode 38508: reward = -86.59, steps = 30 03:35:31 [INFO] train episode 38509: reward = -89.73, steps = 25 03:35:34 [INFO] train episode 38510: reward = -59.24, steps = 42 03:35:37 [INFO] train episode 38511: reward = -93.04, steps = 34 03:35:39 [INFO] train episode 38512: reward = -63.96, steps = 21 03:35:42 [INFO] train episode 38513: reward = -58.86, steps = 33 03:35:44 [INFO] train episode 38514: reward = -73.90, steps = 20 03:35:45 [INFO] train episode 38515: reward = -84.53, steps = 20 03:35:48 [INFO] train episode 38516: reward = -74.05, steps = 20 03:35:49 [INFO] train episode 38517: reward = -82.45, steps = 20 03:35:51 [INFO] train episode 38518: reward = -65.66, steps = 19 03:35:53 [INFO] train episode 38519: reward = -62.24, steps = 24 03:35:55 [INFO] train episode 38520: reward = -123.09, steps = 23 03:35:59 [INFO] train episode 38521: reward = -121.38, steps = 43 03:36:01 [INFO] train episode 38522: reward = -83.81, steps = 28 03:36:06 [INFO] train episode 38523: reward = -78.61, steps = 53 03:36:08 [INFO] train episode 38524: reward = -61.19, steps = 21 03:36:10 [INFO] train episode 38525: reward = -54.63, steps = 25 03:36:13 [INFO] train episode 38526: reward = -101.93, steps = 40 03:36:16 [INFO] train episode 38527: reward = -67.93, steps = 28 03:36:20 [INFO] train episode 38528: reward = -96.71, steps = 42 03:36:22 [INFO] train episode 38529: reward = -69.13, steps = 20 03:36:23 [INFO] train episode 38530: reward = -135.36, steps = 20 03:36:25 [INFO] train episode 38531: reward = -56.86, steps = 20 03:36:27 [INFO] train episode 38532: reward = -71.78, steps = 24 03:36:29 [INFO] train episode 38533: reward = -60.20, steps = 19 03:36:35 [INFO] train episode 38534: reward = -136.31, steps = 70 03:36:37 [INFO] train episode 38535: reward = -189.74, steps = 22 03:36:40 [INFO] train episode 38536: reward = -69.37, steps = 39 03:36:43 [INFO] train episode 38537: reward = -74.51, steps = 30 03:36:45 [INFO] train episode 38538: reward = -70.09, steps = 21 03:36:48 [INFO] train episode 38539: reward = -87.38, steps = 34 03:36:55 [INFO] train episode 38540: reward = -265.19, steps = 75 03:36:57 [INFO] train episode 38541: reward = -149.11, steps = 26 03:36:59 [INFO] train episode 38542: reward = -80.02, steps = 28 03:37:01 [INFO] train episode 38543: reward = -53.76, steps = 21 03:37:03 [INFO] train episode 38544: reward = -72.58, steps = 22 03:37:05 [INFO] train episode 38545: reward = -69.60, steps = 20 03:37:08 [INFO] train episode 38546: reward = -61.58, steps = 33 03:37:12 [INFO] train episode 38547: reward = -45.91, steps = 44 03:37:15 [INFO] train episode 38548: reward = -94.89, steps = 38 03:37:18 [INFO] train episode 38549: reward = -93.53, steps = 32 03:37:21 [INFO] train episode 38550: reward = -52.44, steps = 39 03:37:24 [INFO] train episode 38551: reward = -56.30, steps = 26 03:37:25 [INFO] train episode 38552: reward = -102.16, steps = 20 03:37:29 [INFO] train episode 38553: reward = -94.97, steps = 43 03:37:32 [INFO] train episode 38554: reward = -57.79, steps = 30 03:37:34 [INFO] train episode 38555: reward = -58.44, steps = 30 03:37:36 [INFO] train episode 38556: reward = -111.28, steps = 26 03:37:39 [INFO] train episode 38557: reward = -66.58, steps = 29 03:37:41 [INFO] train episode 38558: reward = -60.76, steps = 24 03:37:43 [INFO] train episode 38559: reward = -75.08, steps = 21 03:37:46 [INFO] train episode 38560: reward = -57.38, steps = 27 03:37:47 [INFO] train episode 38561: reward = -58.79, steps = 21 03:37:50 [INFO] train episode 38562: reward = -119.87, steps = 33 03:37:53 [INFO] train episode 38563: reward = -43.67, steps = 26 03:37:55 [INFO] train episode 38564: reward = -76.35, steps = 22 03:37:57 [INFO] train episode 38565: reward = -52.96, steps = 28 03:37:59 [INFO] train episode 38566: reward = -49.96, steps = 19 03:38:01 [INFO] train episode 38567: reward = -94.51, steps = 25 03:38:04 [INFO] train episode 38568: reward = -111.88, steps = 35 03:38:08 [INFO] train episode 38569: reward = -72.26, steps = 40 03:38:10 [INFO] train episode 38570: reward = -83.12, steps = 20 03:38:13 [INFO] train episode 38571: reward = -51.05, steps = 44 03:38:18 [INFO] train episode 38572: reward = -86.62, steps = 43 03:38:22 [INFO] train episode 38573: reward = -111.44, steps = 49 03:38:24 [INFO] train episode 38574: reward = -86.84, steps = 23 03:38:28 [INFO] train episode 38575: reward = -118.77, steps = 48 03:38:31 [INFO] train episode 38576: reward = -99.72, steps = 25 03:38:35 [INFO] train episode 38577: reward = -135.81, steps = 45 03:38:37 [INFO] train episode 38578: reward = -50.67, steps = 20 03:38:40 [INFO] train episode 38579: reward = -89.56, steps = 45 03:38:42 [INFO] train episode 38580: reward = -66.02, steps = 20 03:38:46 [INFO] train episode 38581: reward = -86.63, steps = 36 03:38:48 [INFO] train episode 38582: reward = -83.07, steps = 24 03:38:50 [INFO] train episode 38583: reward = -70.28, steps = 25 03:38:53 [INFO] train episode 38584: reward = -138.38, steps = 35 03:38:55 [INFO] train episode 38585: reward = -78.49, steps = 20 03:38:58 [INFO] train episode 38586: reward = -77.39, steps = 37 03:39:04 [INFO] train episode 38587: reward = -70.54, steps = 67 03:39:07 [INFO] train episode 38588: reward = -31.93, steps = 33 03:39:11 [INFO] train episode 38589: reward = -109.43, steps = 41 03:39:14 [INFO] train episode 38590: reward = -65.41, steps = 38 03:39:16 [INFO] train episode 38591: reward = -86.34, steps = 23 03:39:18 [INFO] train episode 38592: reward = -48.45, steps = 21 03:39:21 [INFO] train episode 38593: reward = -80.27, steps = 34 03:39:24 [INFO] train episode 38594: reward = -106.69, steps = 33 03:39:26 [INFO] train episode 38595: reward = -43.42, steps = 23 03:39:27 [INFO] train episode 38596: reward = -86.02, steps = 19 03:39:30 [INFO] train episode 38597: reward = -77.38, steps = 34 03:39:34 [INFO] train episode 38598: reward = -117.40, steps = 33 03:39:36 [INFO] train episode 38599: reward = -65.95, steps = 31 03:39:39 [INFO] train episode 38600: reward = -67.06, steps = 34 03:39:41 [INFO] train episode 38601: reward = -80.52, steps = 20 03:39:45 [INFO] train episode 38602: reward = -131.14, steps = 52 03:39:49 [INFO] train episode 38603: reward = -53.44, steps = 36 03:39:51 [INFO] train episode 38604: reward = -73.94, steps = 23 03:39:53 [INFO] train episode 38605: reward = -56.30, steps = 22 03:39:55 [INFO] train episode 38606: reward = -101.77, steps = 22 03:39:57 [INFO] train episode 38607: reward = -108.27, steps = 28 03:40:00 [INFO] train episode 38608: reward = -77.27, steps = 31 03:40:03 [INFO] train episode 38609: reward = -101.19, steps = 35 03:40:05 [INFO] train episode 38610: reward = -74.68, steps = 24 03:40:08 [INFO] train episode 38611: reward = -69.75, steps = 29 03:40:10 [INFO] train episode 38612: reward = -91.76, steps = 20 03:40:11 [INFO] train episode 38613: reward = -98.16, steps = 21 03:40:14 [INFO] train episode 38614: reward = -67.84, steps = 32 03:40:16 [INFO] train episode 38615: reward = -57.46, steps = 19 03:40:17 [INFO] train episode 38616: reward = -90.47, steps = 18 03:40:20 [INFO] train episode 38617: reward = -79.92, steps = 29 03:40:22 [INFO] train episode 38618: reward = -99.71, steps = 16 03:40:23 [INFO] train episode 38619: reward = -89.16, steps = 19 03:40:26 [INFO] train episode 38620: reward = -63.14, steps = 32 03:40:30 [INFO] train episode 38621: reward = -68.66, steps = 48 03:40:33 [INFO] train episode 38622: reward = -128.17, steps = 31 03:40:36 [INFO] train episode 38623: reward = -69.45, steps = 28 03:40:40 [INFO] train episode 38624: reward = -86.52, steps = 48 03:40:44 [INFO] train episode 38625: reward = -63.50, steps = 45 03:40:46 [INFO] train episode 38626: reward = -82.54, steps = 19 03:40:48 [INFO] train episode 38627: reward = -67.98, steps = 27 03:40:50 [INFO] train episode 38628: reward = -70.41, steps = 20 03:40:55 [INFO] train episode 38629: reward = -77.86, steps = 55 03:40:57 [INFO] train episode 38630: reward = -98.27, steps = 22 03:40:59 [INFO] train episode 38631: reward = -122.00, steps = 28 03:41:02 [INFO] train episode 38632: reward = -66.70, steps = 36 03:41:06 [INFO] train episode 38633: reward = -60.70, steps = 38 03:41:08 [INFO] train episode 38634: reward = -146.85, steps = 23 03:41:10 [INFO] train episode 38635: reward = -53.90, steps = 23 03:41:13 [INFO] train episode 38636: reward = -87.38, steps = 28 03:41:17 [INFO] train episode 38637: reward = -98.53, steps = 41 03:41:19 [INFO] train episode 38638: reward = -63.87, steps = 24 03:41:21 [INFO] train episode 38639: reward = -43.45, steps = 21 03:41:23 [INFO] train episode 38640: reward = -74.42, steps = 24 03:41:25 [INFO] train episode 38641: reward = -51.30, steps = 20 03:41:27 [INFO] train episode 38642: reward = -62.80, steps = 21 03:41:29 [INFO] train episode 38643: reward = -92.99, steps = 32 03:41:32 [INFO] train episode 38644: reward = -62.41, steps = 30 03:41:35 [INFO] train episode 38645: reward = -73.25, steps = 38 03:41:38 [INFO] train episode 38646: reward = -104.96, steps = 32 03:41:40 [INFO] train episode 38647: reward = -73.15, steps = 21 03:41:42 [INFO] train episode 38648: reward = -91.13, steps = 23 03:41:44 [INFO] train episode 38649: reward = -72.62, steps = 20 03:41:48 [INFO] train episode 38650: reward = -56.03, steps = 44 03:41:54 [INFO] train episode 38651: reward = -174.10, steps = 78 03:41:58 [INFO] train episode 38652: reward = -65.11, steps = 30 03:42:00 [INFO] train episode 38653: reward = -121.42, steps = 28 03:42:02 [INFO] train episode 38654: reward = -86.30, steps = 29 03:42:05 [INFO] train episode 38655: reward = -143.30, steps = 25 03:42:07 [INFO] train episode 38656: reward = -85.35, steps = 22 03:42:11 [INFO] train episode 38657: reward = -220.95, steps = 54 03:42:15 [INFO] train episode 38658: reward = -92.46, steps = 36 03:42:18 [INFO] train episode 38659: reward = -21.34, steps = 36 03:42:22 [INFO] train episode 38660: reward = -126.47, steps = 46 03:42:24 [INFO] train episode 38661: reward = -76.11, steps = 20 03:42:25 [INFO] train episode 38662: reward = -73.71, steps = 20 03:42:27 [INFO] train episode 38663: reward = -77.56, steps = 23 03:42:30 [INFO] train episode 38664: reward = -80.07, steps = 25 03:42:33 [INFO] train episode 38665: reward = -62.98, steps = 36 03:42:38 [INFO] train episode 38666: reward = -118.33, steps = 50 03:42:40 [INFO] train episode 38667: reward = -67.39, steps = 30 03:42:42 [INFO] train episode 38668: reward = -57.06, steps = 16 03:42:45 [INFO] train episode 38669: reward = -49.23, steps = 33 03:42:47 [INFO] train episode 38670: reward = -56.37, steps = 22 03:42:49 [INFO] train episode 38671: reward = -53.61, steps = 26 03:42:53 [INFO] train episode 38672: reward = -72.47, steps = 39 03:42:54 [INFO] train episode 38673: reward = -68.15, steps = 17 03:42:57 [INFO] train episode 38674: reward = -84.98, steps = 35 03:42:59 [INFO] train episode 38675: reward = -80.39, steps = 23 03:43:03 [INFO] train episode 38676: reward = -38.81, steps = 34 03:43:05 [INFO] train episode 38677: reward = -82.44, steps = 24 03:43:07 [INFO] train episode 38678: reward = -93.01, steps = 20 03:43:09 [INFO] train episode 38679: reward = -200.03, steps = 27 03:43:11 [INFO] train episode 38680: reward = -96.51, steps = 21 03:43:13 [INFO] train episode 38681: reward = -88.89, steps = 22 03:43:16 [INFO] train episode 38682: reward = -100.48, steps = 31 03:43:19 [INFO] train episode 38683: reward = -47.04, steps = 30 03:43:22 [INFO] train episode 38684: reward = -120.97, steps = 35 03:43:25 [INFO] train episode 38685: reward = -78.59, steps = 39 03:43:28 [INFO] train episode 38686: reward = -57.73, steps = 32 03:43:31 [INFO] train episode 38687: reward = -70.91, steps = 22 03:43:33 [INFO] train episode 38688: reward = -70.80, steps = 23 03:43:35 [INFO] train episode 38689: reward = -150.56, steps = 20 03:43:38 [INFO] train episode 38690: reward = -55.68, steps = 20 03:43:40 [INFO] train episode 38691: reward = -76.24, steps = 29 03:43:42 [INFO] train episode 38692: reward = -103.30, steps = 23 03:43:45 [INFO] train episode 38693: reward = -109.62, steps = 25 03:43:47 [INFO] train episode 38694: reward = -74.19, steps = 26 03:43:49 [INFO] train episode 38695: reward = -136.38, steps = 18 03:43:52 [INFO] train episode 38696: reward = -71.12, steps = 39 03:43:55 [INFO] train episode 38697: reward = -76.10, steps = 20 03:43:56 [INFO] train episode 38698: reward = -73.93, steps = 18 03:44:00 [INFO] train episode 38699: reward = -101.56, steps = 39 03:44:02 [INFO] train episode 38700: reward = -111.96, steps = 25 03:44:05 [INFO] train episode 38701: reward = -85.86, steps = 29 03:44:08 [INFO] train episode 38702: reward = -101.95, steps = 45 03:44:13 [INFO] train episode 38703: reward = -59.33, steps = 33 03:44:14 [INFO] train episode 38704: reward = -93.71, steps = 17 03:44:18 [INFO] train episode 38705: reward = -88.84, steps = 39 03:44:20 [INFO] train episode 38706: reward = -41.01, steps = 21 03:44:23 [INFO] train episode 38707: reward = -83.07, steps = 43 03:44:26 [INFO] train episode 38708: reward = -161.35, steps = 24 03:44:29 [INFO] train episode 38709: reward = -99.34, steps = 35 03:44:32 [INFO] train episode 38710: reward = -62.06, steps = 35 03:44:36 [INFO] train episode 38711: reward = -89.65, steps = 38 03:44:40 [INFO] train episode 38712: reward = -139.42, steps = 53 03:44:43 [INFO] train episode 38713: reward = -87.56, steps = 25 03:44:47 [INFO] train episode 38714: reward = -55.13, steps = 39 03:44:49 [INFO] train episode 38715: reward = -76.28, steps = 23 03:44:51 [INFO] train episode 38716: reward = -65.09, steps = 23 03:44:53 [INFO] train episode 38717: reward = -70.29, steps = 30 03:44:55 [INFO] train episode 38718: reward = -70.93, steps = 19 03:44:58 [INFO] train episode 38719: reward = -59.58, steps = 29 03:45:03 [INFO] train episode 38720: reward = -75.96, steps = 46 03:45:07 [INFO] train episode 38721: reward = -79.18, steps = 42 03:45:09 [INFO] train episode 38722: reward = -49.61, steps = 27 03:45:11 [INFO] train episode 38723: reward = -71.91, steps = 23 03:45:13 [INFO] train episode 38724: reward = -58.43, steps = 22 03:45:16 [INFO] train episode 38725: reward = -75.17, steps = 28 03:45:19 [INFO] train episode 38726: reward = -57.91, steps = 29 03:45:21 [INFO] train episode 38727: reward = -71.17, steps = 28 03:45:25 [INFO] train episode 38728: reward = -103.82, steps = 38 03:45:27 [INFO] train episode 38729: reward = -137.14, steps = 24 03:45:29 [INFO] train episode 38730: reward = -67.08, steps = 19 03:45:32 [INFO] train episode 38731: reward = -89.93, steps = 42 03:45:35 [INFO] train episode 38732: reward = -59.90, steps = 23 03:45:38 [INFO] train episode 38733: reward = -65.00, steps = 33 03:45:40 [INFO] train episode 38734: reward = -95.26, steps = 27 03:45:43 [INFO] train episode 38735: reward = -82.03, steps = 29 03:45:47 [INFO] train episode 38736: reward = -52.96, steps = 45 03:45:49 [INFO] train episode 38737: reward = -63.61, steps = 24 03:45:51 [INFO] train episode 38738: reward = -85.32, steps = 18 03:45:54 [INFO] train episode 38739: reward = -149.41, steps = 32 03:45:56 [INFO] train episode 38740: reward = -59.99, steps = 22 03:45:58 [INFO] train episode 38741: reward = -91.57, steps = 20 03:46:02 [INFO] train episode 38742: reward = -98.10, steps = 39 03:46:04 [INFO] train episode 38743: reward = -72.27, steps = 20 03:46:06 [INFO] train episode 38744: reward = -91.60, steps = 29 03:46:09 [INFO] train episode 38745: reward = -109.12, steps = 24 03:46:11 [INFO] train episode 38746: reward = -75.67, steps = 27 03:46:13 [INFO] train episode 38747: reward = -95.71, steps = 19 03:46:15 [INFO] train episode 38748: reward = -61.46, steps = 20 03:46:17 [INFO] train episode 38749: reward = -50.54, steps = 24 03:46:20 [INFO] train episode 38750: reward = -63.95, steps = 24 03:46:22 [INFO] train episode 38751: reward = -71.50, steps = 23 03:46:25 [INFO] train episode 38752: reward = -96.92, steps = 29 03:46:28 [INFO] train episode 38753: reward = -59.90, steps = 32 03:46:31 [INFO] train episode 38754: reward = -77.38, steps = 29 03:46:33 [INFO] train episode 38755: reward = -75.19, steps = 26 03:46:35 [INFO] train episode 38756: reward = -112.43, steps = 20 03:46:37 [INFO] train episode 38757: reward = -86.55, steps = 20 03:46:40 [INFO] train episode 38758: reward = -78.97, steps = 23 03:46:42 [INFO] train episode 38759: reward = -72.84, steps = 29 03:46:45 [INFO] train episode 38760: reward = -95.77, steps = 22 03:46:48 [INFO] train episode 38761: reward = -127.75, steps = 33 03:46:51 [INFO] train episode 38762: reward = -94.89, steps = 26 03:46:53 [INFO] train episode 38763: reward = -89.74, steps = 21 03:46:55 [INFO] train episode 38764: reward = -131.52, steps = 23 03:46:57 [INFO] train episode 38765: reward = -92.84, steps = 26 03:47:00 [INFO] train episode 38766: reward = -96.65, steps = 24 03:47:03 [INFO] train episode 38767: reward = -87.10, steps = 26 03:47:05 [INFO] train episode 38768: reward = -63.13, steps = 23 03:47:08 [INFO] train episode 38769: reward = -75.44, steps = 35 03:47:11 [INFO] train episode 38770: reward = -92.00, steps = 25 03:47:13 [INFO] train episode 38771: reward = -82.96, steps = 19 03:47:14 [INFO] train episode 38772: reward = -77.69, steps = 20 03:47:18 [INFO] train episode 38773: reward = -78.61, steps = 27 03:47:20 [INFO] train episode 38774: reward = -68.75, steps = 20 03:47:22 [INFO] train episode 38775: reward = -83.73, steps = 21 03:47:25 [INFO] train episode 38776: reward = -78.02, steps = 30 03:47:27 [INFO] train episode 38777: reward = -64.64, steps = 21 03:47:30 [INFO] train episode 38778: reward = -64.34, steps = 31 03:47:33 [INFO] train episode 38779: reward = -67.34, steps = 42 03:47:37 [INFO] train episode 38780: reward = -86.26, steps = 33 03:47:40 [INFO] train episode 38781: reward = -88.83, steps = 35 03:47:42 [INFO] train episode 38782: reward = -59.15, steps = 21 03:47:44 [INFO] train episode 38783: reward = -67.62, steps = 21 03:47:46 [INFO] train episode 38784: reward = -51.60, steps = 22 03:47:50 [INFO] train episode 38785: reward = -115.64, steps = 40 03:47:53 [INFO] train episode 38786: reward = -61.40, steps = 38 03:47:57 [INFO] train episode 38787: reward = -120.97, steps = 29 03:47:59 [INFO] train episode 38788: reward = -63.12, steps = 29 03:48:01 [INFO] train episode 38789: reward = -68.49, steps = 20 03:48:04 [INFO] train episode 38790: reward = -87.73, steps = 32 03:48:08 [INFO] train episode 38791: reward = -123.25, steps = 42 03:48:10 [INFO] train episode 38792: reward = -122.44, steps = 23 03:48:13 [INFO] train episode 38793: reward = -75.00, steps = 29 03:48:16 [INFO] train episode 38794: reward = -76.76, steps = 24 03:48:18 [INFO] train episode 38795: reward = -96.10, steps = 27 03:48:22 [INFO] train episode 38796: reward = -145.22, steps = 48 03:48:25 [INFO] train episode 38797: reward = -88.78, steps = 22 03:48:28 [INFO] train episode 38798: reward = -52.10, steps = 33 03:48:33 [INFO] train episode 38799: reward = -74.56, steps = 53 03:48:35 [INFO] train episode 38800: reward = -109.47, steps = 21 03:48:39 [INFO] train episode 38801: reward = -83.66, steps = 41 03:48:42 [INFO] train episode 38802: reward = -85.16, steps = 31 03:48:45 [INFO] train episode 38803: reward = -99.65, steps = 26 03:48:49 [INFO] train episode 38804: reward = -71.14, steps = 37 03:48:51 [INFO] train episode 38805: reward = -79.46, steps = 22 03:48:53 [INFO] train episode 38806: reward = -102.62, steps = 19 03:48:58 [INFO] train episode 38807: reward = -189.91, steps = 62 03:49:01 [INFO] train episode 38808: reward = -48.71, steps = 23 03:49:03 [INFO] train episode 38809: reward = -55.50, steps = 22 03:49:07 [INFO] train episode 38810: reward = -206.33, steps = 43 03:49:10 [INFO] train episode 38811: reward = -55.05, steps = 28 03:49:12 [INFO] train episode 38812: reward = -144.82, steps = 22 03:49:14 [INFO] train episode 38813: reward = -91.25, steps = 21 03:49:17 [INFO] train episode 38814: reward = -67.97, steps = 31 03:49:20 [INFO] train episode 38815: reward = -99.48, steps = 33 03:49:23 [INFO] train episode 38816: reward = -93.29, steps = 33 03:49:26 [INFO] train episode 38817: reward = -79.88, steps = 35 03:49:29 [INFO] train episode 38818: reward = -83.68, steps = 29 03:49:34 [INFO] train episode 38819: reward = -160.77, steps = 49 03:49:35 [INFO] train episode 38820: reward = -77.52, steps = 19 03:49:37 [INFO] train episode 38821: reward = -141.10, steps = 19 03:49:40 [INFO] train episode 38822: reward = -57.08, steps = 26 03:49:44 [INFO] train episode 38823: reward = -76.45, steps = 39 03:49:45 [INFO] train episode 38824: reward = -87.08, steps = 20 03:49:48 [INFO] train episode 38825: reward = -75.74, steps = 30 03:49:50 [INFO] train episode 38826: reward = -88.71, steps = 20 03:49:52 [INFO] train episode 38827: reward = -75.34, steps = 24 03:49:57 [INFO] train episode 38828: reward = -66.98, steps = 47 03:50:00 [INFO] train episode 38829: reward = -89.81, steps = 31 03:50:02 [INFO] train episode 38830: reward = -73.68, steps = 24 03:50:04 [INFO] train episode 38831: reward = -99.44, steps = 24 03:50:10 [INFO] train episode 38832: reward = -76.35, steps = 57 03:50:11 [INFO] train episode 38833: reward = -118.35, steps = 19 03:50:15 [INFO] train episode 38834: reward = -69.24, steps = 37 03:50:17 [INFO] train episode 38835: reward = -62.46, steps = 20 03:50:21 [INFO] train episode 38836: reward = -65.58, steps = 38 03:50:23 [INFO] train episode 38837: reward = -74.39, steps = 26 03:50:26 [INFO] train episode 38838: reward = -68.48, steps = 20 03:50:30 [INFO] train episode 38839: reward = -103.13, steps = 41 03:50:32 [INFO] train episode 38840: reward = -61.58, steps = 24 03:50:35 [INFO] train episode 38841: reward = -44.28, steps = 31 03:50:38 [INFO] train episode 38842: reward = -89.66, steps = 26 03:50:40 [INFO] train episode 38843: reward = -95.15, steps = 27 03:50:45 [INFO] train episode 38844: reward = -144.53, steps = 52 03:50:47 [INFO] train episode 38845: reward = -72.36, steps = 19 03:50:52 [INFO] train episode 38846: reward = -93.66, steps = 46 03:50:54 [INFO] train episode 38847: reward = -86.52, steps = 23 03:50:58 [INFO] train episode 38848: reward = -90.91, steps = 43 03:51:02 [INFO] train episode 38849: reward = -72.55, steps = 42 03:51:05 [INFO] train episode 38850: reward = -142.70, steps = 34 03:51:07 [INFO] train episode 38851: reward = -73.94, steps = 24 03:51:12 [INFO] train episode 38852: reward = -74.28, steps = 49 03:51:15 [INFO] train episode 38853: reward = -105.59, steps = 37 03:51:19 [INFO] train episode 38854: reward = -82.25, steps = 44 03:51:21 [INFO] train episode 38855: reward = -127.39, steps = 19 03:51:24 [INFO] train episode 38856: reward = -91.15, steps = 33 03:51:26 [INFO] train episode 38857: reward = -84.29, steps = 20 03:51:29 [INFO] train episode 38858: reward = -68.55, steps = 25 03:51:31 [INFO] train episode 38859: reward = -64.21, steps = 22 03:51:34 [INFO] train episode 38860: reward = -111.09, steps = 40 03:51:37 [INFO] train episode 38861: reward = -71.50, steps = 25 03:51:39 [INFO] train episode 38862: reward = -99.38, steps = 22 03:51:41 [INFO] train episode 38863: reward = -77.36, steps = 21 03:51:44 [INFO] train episode 38864: reward = -68.99, steps = 33 03:51:47 [INFO] train episode 38865: reward = -85.62, steps = 29 03:51:52 [INFO] train episode 38866: reward = -139.98, steps = 61 03:51:54 [INFO] train episode 38867: reward = -71.12, steps = 19 03:51:56 [INFO] train episode 38868: reward = -56.54, steps = 25 03:51:59 [INFO] train episode 38869: reward = -86.54, steps = 23 03:52:01 [INFO] train episode 38870: reward = -87.34, steps = 25 03:52:03 [INFO] train episode 38871: reward = -72.93, steps = 20 03:52:06 [INFO] train episode 38872: reward = -87.43, steps = 31 03:52:09 [INFO] train episode 38873: reward = -94.77, steps = 37 03:52:15 [INFO] train episode 38874: reward = -134.62, steps = 56 03:52:20 [INFO] train episode 38875: reward = -118.40, steps = 58 03:52:23 [INFO] train episode 38876: reward = -59.61, steps = 29 03:52:27 [INFO] train episode 38877: reward = -112.25, steps = 45 03:52:30 [INFO] train episode 38878: reward = -111.04, steps = 37 03:52:33 [INFO] train episode 38879: reward = -53.32, steps = 24 03:52:35 [INFO] train episode 38880: reward = -100.48, steps = 24 03:52:38 [INFO] train episode 38881: reward = -100.86, steps = 36 03:52:40 [INFO] train episode 38882: reward = -83.54, steps = 20 03:52:42 [INFO] train episode 38883: reward = -52.14, steps = 23 03:52:44 [INFO] train episode 38884: reward = -106.49, steps = 19 03:52:46 [INFO] train episode 38885: reward = -80.92, steps = 22 03:52:49 [INFO] train episode 38886: reward = -109.97, steps = 21 03:52:51 [INFO] train episode 38887: reward = -42.51, steps = 25 03:52:53 [INFO] train episode 38888: reward = -96.12, steps = 21 03:52:55 [INFO] train episode 38889: reward = -68.75, steps = 21 03:52:59 [INFO] train episode 38890: reward = -91.25, steps = 42 03:53:01 [INFO] train episode 38891: reward = -92.51, steps = 20 03:53:03 [INFO] train episode 38892: reward = -93.50, steps = 23 03:53:06 [INFO] train episode 38893: reward = -50.29, steps = 29 03:53:08 [INFO] train episode 38894: reward = -63.35, steps = 24 03:53:11 [INFO] train episode 38895: reward = -87.56, steps = 30 03:53:13 [INFO] train episode 38896: reward = -74.11, steps = 21 03:53:18 [INFO] train episode 38897: reward = -96.92, steps = 52 03:53:20 [INFO] train episode 38898: reward = -144.43, steps = 20 03:53:22 [INFO] train episode 38899: reward = -69.89, steps = 23 03:53:26 [INFO] train episode 38900: reward = -47.24, steps = 38 03:53:32 [INFO] train episode 38901: reward = -87.01, steps = 62 03:53:34 [INFO] train episode 38902: reward = -76.33, steps = 21 03:53:37 [INFO] train episode 38903: reward = -241.88, steps = 27 03:53:41 [INFO] train episode 38904: reward = -86.13, steps = 40 03:53:43 [INFO] train episode 38905: reward = -71.53, steps = 22 03:53:45 [INFO] train episode 38906: reward = -85.11, steps = 20 03:53:49 [INFO] train episode 38907: reward = -97.75, steps = 48 03:53:52 [INFO] train episode 38908: reward = -91.71, steps = 31 03:53:55 [INFO] train episode 38909: reward = -61.94, steps = 27 03:53:57 [INFO] train episode 38910: reward = -77.36, steps = 19 03:54:01 [INFO] train episode 38911: reward = -137.31, steps = 40 03:54:05 [INFO] train episode 38912: reward = -114.12, steps = 35 03:54:08 [INFO] train episode 38913: reward = -69.65, steps = 31 03:54:12 [INFO] train episode 38914: reward = -99.74, steps = 40 03:54:14 [INFO] train episode 38915: reward = -66.60, steps = 30 03:54:18 [INFO] train episode 38916: reward = -80.91, steps = 35 03:54:20 [INFO] train episode 38917: reward = -34.71, steps = 23 03:54:24 [INFO] train episode 38918: reward = -94.52, steps = 42 03:54:28 [INFO] train episode 38919: reward = -55.70, steps = 33 03:54:30 [INFO] train episode 38920: reward = -84.77, steps = 21 03:54:33 [INFO] train episode 38921: reward = -69.39, steps = 34 03:54:36 [INFO] train episode 38922: reward = -67.72, steps = 25 03:54:39 [INFO] train episode 38923: reward = -68.97, steps = 25 03:54:42 [INFO] train episode 38924: reward = -68.93, steps = 38 03:54:45 [INFO] train episode 38925: reward = -58.09, steps = 24 03:54:46 [INFO] train episode 38926: reward = -68.07, steps = 19 03:54:49 [INFO] train episode 38927: reward = -109.05, steps = 21 03:54:51 [INFO] train episode 38928: reward = -91.82, steps = 27 03:54:54 [INFO] train episode 38929: reward = -116.80, steps = 21 03:55:00 [INFO] train episode 38930: reward = -180.40, steps = 61 03:55:02 [INFO] train episode 38931: reward = -85.49, steps = 28 03:55:07 [INFO] train episode 38932: reward = -78.23, steps = 47 03:55:09 [INFO] train episode 38933: reward = -60.36, steps = 23 03:55:12 [INFO] train episode 38934: reward = -55.73, steps = 24 03:55:15 [INFO] train episode 38935: reward = -62.02, steps = 34 03:55:17 [INFO] train episode 38936: reward = -58.34, steps = 23 03:55:20 [INFO] train episode 38937: reward = -112.86, steps = 25 03:55:25 [INFO] train episode 38938: reward = -112.42, steps = 55 03:55:27 [INFO] train episode 38939: reward = -95.47, steps = 29 03:55:30 [INFO] train episode 38940: reward = -71.18, steps = 19 03:55:32 [INFO] train episode 38941: reward = -94.49, steps = 20 03:55:34 [INFO] train episode 38942: reward = -54.00, steps = 24 03:55:36 [INFO] train episode 38943: reward = -55.66, steps = 22 03:55:41 [INFO] train episode 38944: reward = -73.65, steps = 51 03:55:43 [INFO] train episode 38945: reward = -60.28, steps = 23 03:55:46 [INFO] train episode 38946: reward = -78.94, steps = 29 03:55:50 [INFO] train episode 38947: reward = -95.50, steps = 43 03:55:52 [INFO] train episode 38948: reward = -82.58, steps = 20 03:55:55 [INFO] train episode 38949: reward = -114.54, steps = 30 03:55:57 [INFO] train episode 38950: reward = -89.00, steps = 20 03:55:59 [INFO] train episode 38951: reward = -116.71, steps = 20 03:56:01 [INFO] train episode 38952: reward = -113.22, steps = 29 03:56:05 [INFO] train episode 38953: reward = -63.21, steps = 32 03:56:07 [INFO] train episode 38954: reward = -73.00, steps = 20 03:56:09 [INFO] train episode 38955: reward = -64.61, steps = 26 03:56:12 [INFO] train episode 38956: reward = -87.37, steps = 29 03:56:14 [INFO] train episode 38957: reward = -87.79, steps = 18 03:56:20 [INFO] train episode 38958: reward = -169.31, steps = 71 03:56:23 [INFO] train episode 38959: reward = -56.99, steps = 19 03:56:25 [INFO] train episode 38960: reward = -82.41, steps = 30 03:56:29 [INFO] train episode 38961: reward = -105.97, steps = 38 03:56:33 [INFO] train episode 38962: reward = -106.51, steps = 42 03:56:35 [INFO] train episode 38963: reward = -53.55, steps = 20 03:56:37 [INFO] train episode 38964: reward = -90.48, steps = 20 03:56:40 [INFO] train episode 38965: reward = -93.19, steps = 21 03:56:42 [INFO] train episode 38966: reward = -86.75, steps = 25 03:56:46 [INFO] train episode 38967: reward = -53.79, steps = 30 03:56:48 [INFO] train episode 38968: reward = -77.89, steps = 21 03:56:52 [INFO] train episode 38969: reward = -83.84, steps = 45 03:56:56 [INFO] train episode 38970: reward = -74.11, steps = 37 03:57:00 [INFO] train episode 38971: reward = -130.35, steps = 39 03:57:03 [INFO] train episode 38972: reward = -131.32, steps = 35 03:57:05 [INFO] train episode 38973: reward = -94.86, steps = 19 03:57:07 [INFO] train episode 38974: reward = -74.67, steps = 21 03:57:09 [INFO] train episode 38975: reward = -71.23, steps = 20 03:57:13 [INFO] train episode 38976: reward = -89.54, steps = 43 03:57:17 [INFO] train episode 38977: reward = -98.61, steps = 30 03:57:22 [INFO] train episode 38978: reward = -141.56, steps = 57 03:57:25 [INFO] train episode 38979: reward = -94.29, steps = 35 03:57:27 [INFO] train episode 38980: reward = -93.37, steps = 19 03:57:29 [INFO] train episode 38981: reward = -82.09, steps = 21 03:57:33 [INFO] train episode 38982: reward = -70.49, steps = 36 03:57:35 [INFO] train episode 38983: reward = -68.39, steps = 20 03:57:37 [INFO] train episode 38984: reward = -75.78, steps = 23 03:57:41 [INFO] train episode 38985: reward = -77.50, steps = 41 03:57:46 [INFO] train episode 38986: reward = -85.30, steps = 53 03:57:51 [INFO] train episode 38987: reward = -108.87, steps = 51 03:57:53 [INFO] train episode 38988: reward = -72.55, steps = 18 03:57:58 [INFO] train episode 38989: reward = -32.48, steps = 43 03:58:00 [INFO] train episode 38990: reward = -46.09, steps = 22 03:58:02 [INFO] train episode 38991: reward = -88.59, steps = 23 03:58:04 [INFO] train episode 38992: reward = -62.79, steps = 19 03:58:09 [INFO] train episode 38993: reward = -96.34, steps = 48 03:58:11 [INFO] train episode 38994: reward = -97.06, steps = 22 03:58:13 [INFO] train episode 38995: reward = -92.87, steps = 20 03:58:16 [INFO] train episode 38996: reward = -57.04, steps = 34 03:58:19 [INFO] train episode 38997: reward = -77.74, steps = 28 03:58:21 [INFO] train episode 38998: reward = -99.33, steps = 20 03:58:23 [INFO] train episode 38999: reward = -82.29, steps = 21 03:58:27 [INFO] train episode 39000: reward = -102.84, steps = 39 03:58:30 [INFO] train episode 39001: reward = -93.13, steps = 33 03:58:33 [INFO] train episode 39002: reward = -83.64, steps = 22 03:58:35 [INFO] train episode 39003: reward = -59.10, steps = 28 03:58:38 [INFO] train episode 39004: reward = -123.93, steps = 26 03:58:40 [INFO] train episode 39005: reward = -52.88, steps = 21 03:58:43 [INFO] train episode 39006: reward = -63.82, steps = 31 03:58:46 [INFO] train episode 39007: reward = -52.18, steps = 28 03:58:50 [INFO] train episode 39008: reward = -120.05, steps = 34 03:58:53 [INFO] train episode 39009: reward = -43.12, steps = 30 03:58:55 [INFO] train episode 39010: reward = -79.24, steps = 22 03:58:59 [INFO] train episode 39011: reward = -91.40, steps = 45 03:59:01 [INFO] train episode 39012: reward = -79.67, steps = 22 03:59:03 [INFO] train episode 39013: reward = -96.46, steps = 23 03:59:06 [INFO] train episode 39014: reward = -58.55, steps = 22 03:59:08 [INFO] train episode 39015: reward = -84.25, steps = 23 03:59:11 [INFO] train episode 39016: reward = -69.18, steps = 34 03:59:15 [INFO] train episode 39017: reward = -81.44, steps = 38 03:59:18 [INFO] train episode 39018: reward = -57.52, steps = 27 03:59:20 [INFO] train episode 39019: reward = -99.22, steps = 24 03:59:25 [INFO] train episode 39020: reward = -38.97, steps = 37 03:59:27 [INFO] train episode 39021: reward = -102.74, steps = 20 03:59:29 [INFO] train episode 39022: reward = -125.79, steps = 20 03:59:33 [INFO] train episode 39023: reward = -68.50, steps = 40 03:59:39 [INFO] train episode 39024: reward = -164.58, steps = 67 03:59:46 [INFO] train episode 39025: reward = -143.14, steps = 68 03:59:48 [INFO] train episode 39026: reward = -80.70, steps = 17 03:59:51 [INFO] train episode 39027: reward = -42.42, steps = 33 03:59:55 [INFO] train episode 39028: reward = -177.94, steps = 44 03:59:58 [INFO] train episode 39029: reward = -63.54, steps = 24 04:00:00 [INFO] train episode 39030: reward = -62.66, steps = 17 04:00:02 [INFO] train episode 39031: reward = -65.35, steps = 20 04:00:06 [INFO] train episode 39032: reward = -104.77, steps = 33 04:00:08 [INFO] train episode 39033: reward = -71.37, steps = 22 04:00:10 [INFO] train episode 39034: reward = -85.57, steps = 20 04:00:14 [INFO] train episode 39035: reward = -101.89, steps = 45 04:00:16 [INFO] train episode 39036: reward = -74.07, steps = 22 04:00:18 [INFO] train episode 39037: reward = -78.20, steps = 21 04:00:23 [INFO] train episode 39038: reward = -139.15, steps = 49 04:00:26 [INFO] train episode 39039: reward = -41.46, steps = 36 04:00:28 [INFO] train episode 39040: reward = -85.78, steps = 20 04:00:31 [INFO] train episode 39041: reward = -78.34, steps = 34 04:00:34 [INFO] train episode 39042: reward = -77.72, steps = 22 04:00:38 [INFO] train episode 39043: reward = -72.11, steps = 46 04:00:40 [INFO] train episode 39044: reward = -68.92, steps = 14 04:00:42 [INFO] train episode 39045: reward = -73.27, steps = 19 04:00:45 [INFO] train episode 39046: reward = -73.12, steps = 35 04:00:47 [INFO] train episode 39047: reward = -82.65, steps = 22 04:00:50 [INFO] train episode 39048: reward = -115.32, steps = 34 04:00:55 [INFO] train episode 39049: reward = -69.65, steps = 47 04:00:57 [INFO] train episode 39050: reward = -70.68, steps = 24 04:01:02 [INFO] train episode 39051: reward = -53.48, steps = 51 04:01:03 [INFO] train episode 39052: reward = -104.47, steps = 18 04:01:06 [INFO] train episode 39053: reward = -68.59, steps = 22 04:01:09 [INFO] train episode 39054: reward = -66.28, steps = 39 04:01:11 [INFO] train episode 39055: reward = -87.93, steps = 19 04:01:13 [INFO] train episode 39056: reward = -88.03, steps = 18 04:01:15 [INFO] train episode 39057: reward = -90.65, steps = 21 04:01:17 [INFO] train episode 39058: reward = -81.87, steps = 20 04:01:19 [INFO] train episode 39059: reward = -41.18, steps = 28 04:01:23 [INFO] train episode 39060: reward = -83.00, steps = 38 04:01:26 [INFO] train episode 39061: reward = -83.50, steps = 34 04:01:28 [INFO] train episode 39062: reward = -48.53, steps = 18 04:01:32 [INFO] train episode 39063: reward = -55.68, steps = 43 04:01:35 [INFO] train episode 39064: reward = -112.29, steps = 30 04:01:38 [INFO] train episode 39065: reward = -113.17, steps = 32 04:01:40 [INFO] train episode 39066: reward = -62.45, steps = 22 04:01:41 [INFO] train episode 39067: reward = -84.59, steps = 19 04:01:44 [INFO] train episode 39068: reward = -125.93, steps = 24 04:01:46 [INFO] train episode 39069: reward = -92.98, steps = 26 04:01:50 [INFO] train episode 39070: reward = -69.02, steps = 39 04:01:52 [INFO] train episode 39071: reward = -71.08, steps = 28 04:01:56 [INFO] train episode 39072: reward = -67.82, steps = 45 04:01:59 [INFO] train episode 39073: reward = -65.79, steps = 28 04:02:01 [INFO] train episode 39074: reward = -125.50, steps = 22 04:02:03 [INFO] train episode 39075: reward = -72.14, steps = 19 04:02:06 [INFO] train episode 39076: reward = -210.78, steps = 30 04:02:08 [INFO] train episode 39077: reward = -56.90, steps = 23 04:02:10 [INFO] train episode 39078: reward = -69.75, steps = 21 04:02:13 [INFO] train episode 39079: reward = -69.67, steps = 37 04:02:15 [INFO] train episode 39080: reward = -86.84, steps = 25 04:02:17 [INFO] train episode 39081: reward = -57.41, steps = 19 04:02:19 [INFO] train episode 39082: reward = -82.20, steps = 25 04:02:21 [INFO] train episode 39083: reward = -75.69, steps = 20 04:02:23 [INFO] train episode 39084: reward = -71.96, steps = 21 04:02:26 [INFO] train episode 39085: reward = -130.00, steps = 30 04:02:29 [INFO] train episode 39086: reward = -81.81, steps = 43 04:02:32 [INFO] train episode 39087: reward = -95.73, steps = 26 04:02:37 [INFO] train episode 39088: reward = -74.09, steps = 49 04:02:39 [INFO] train episode 39089: reward = -82.36, steps = 23 04:02:42 [INFO] train episode 39090: reward = -71.51, steps = 39 04:02:46 [INFO] train episode 39091: reward = -90.39, steps = 45 04:02:49 [INFO] train episode 39092: reward = -71.40, steps = 30 04:02:53 [INFO] train episode 39093: reward = -81.94, steps = 50 04:02:57 [INFO] train episode 39094: reward = -83.17, steps = 43 04:02:59 [INFO] train episode 39095: reward = -93.33, steps = 20 04:03:02 [INFO] train episode 39096: reward = -55.00, steps = 30 04:03:05 [INFO] train episode 39097: reward = -115.33, steps = 35 04:03:09 [INFO] train episode 39098: reward = -52.77, steps = 39 04:03:12 [INFO] train episode 39099: reward = -56.95, steps = 32 04:03:14 [INFO] train episode 39100: reward = -88.30, steps = 22 04:03:15 [INFO] train episode 39101: reward = -64.73, steps = 19 04:03:17 [INFO] train episode 39102: reward = -59.78, steps = 25 04:03:19 [INFO] train episode 39103: reward = -109.12, steps = 20 04:03:22 [INFO] train episode 39104: reward = -80.02, steps = 32 04:03:26 [INFO] train episode 39105: reward = -103.40, steps = 48 04:03:28 [INFO] train episode 39106: reward = -69.79, steps = 24 04:03:32 [INFO] train episode 39107: reward = -86.15, steps = 43 04:03:35 [INFO] train episode 39108: reward = -58.33, steps = 33 04:03:40 [INFO] train episode 39109: reward = -195.55, steps = 59 04:03:45 [INFO] train episode 39110: reward = -82.77, steps = 53 04:03:49 [INFO] train episode 39111: reward = -145.48, steps = 44 04:03:51 [INFO] train episode 39112: reward = -65.11, steps = 22 04:03:54 [INFO] train episode 39113: reward = -53.33, steps = 31 04:03:57 [INFO] train episode 39114: reward = -69.35, steps = 41 04:04:01 [INFO] train episode 39115: reward = -95.84, steps = 41 04:04:04 [INFO] train episode 39116: reward = -83.35, steps = 40 04:04:06 [INFO] train episode 39117: reward = -95.67, steps = 22 04:04:10 [INFO] train episode 39118: reward = -97.23, steps = 44 04:04:13 [INFO] train episode 39119: reward = -65.08, steps = 35 04:04:16 [INFO] train episode 39120: reward = -62.81, steps = 38 04:04:20 [INFO] train episode 39121: reward = -77.25, steps = 45 04:04:24 [INFO] train episode 39122: reward = -39.32, steps = 46 04:04:27 [INFO] train episode 39123: reward = -91.64, steps = 30 04:04:29 [INFO] train episode 39124: reward = -61.76, steps = 25 04:04:31 [INFO] train episode 39125: reward = -62.49, steps = 17 04:04:32 [INFO] train episode 39126: reward = -60.36, steps = 19 04:04:34 [INFO] train episode 39127: reward = -77.64, steps = 22 04:04:36 [INFO] train episode 39128: reward = -80.77, steps = 27 04:04:39 [INFO] train episode 39129: reward = -52.69, steps = 27 04:04:40 [INFO] train episode 39130: reward = -68.59, steps = 18 04:04:45 [INFO] train episode 39131: reward = -136.41, steps = 48 04:04:48 [INFO] train episode 39132: reward = -57.81, steps = 36 04:04:53 [INFO] train episode 39133: reward = -207.56, steps = 69 04:04:56 [INFO] train episode 39134: reward = -85.46, steps = 23 04:04:58 [INFO] train episode 39135: reward = -49.67, steps = 22 04:05:01 [INFO] train episode 39136: reward = -85.16, steps = 31 04:05:04 [INFO] train episode 39137: reward = -149.00, steps = 35 04:05:06 [INFO] train episode 39138: reward = -83.50, steps = 24 04:05:10 [INFO] train episode 39139: reward = -163.80, steps = 49 04:05:12 [INFO] train episode 39140: reward = -86.94, steps = 23 04:05:16 [INFO] train episode 39141: reward = -83.21, steps = 38 04:05:18 [INFO] train episode 39142: reward = -102.14, steps = 25 04:05:21 [INFO] train episode 39143: reward = -84.36, steps = 33 04:05:23 [INFO] train episode 39144: reward = -91.79, steps = 22 04:05:24 [INFO] train episode 39145: reward = -58.46, steps = 20 04:05:29 [INFO] train episode 39146: reward = -144.00, steps = 57 04:05:31 [INFO] train episode 39147: reward = -77.61, steps = 21 04:05:33 [INFO] train episode 39148: reward = -88.28, steps = 20 04:05:35 [INFO] train episode 39149: reward = -61.79, steps = 27 04:05:37 [INFO] train episode 39150: reward = -69.64, steps = 21 04:05:39 [INFO] train episode 39151: reward = -85.26, steps = 22 04:05:41 [INFO] train episode 39152: reward = -96.21, steps = 20 04:05:47 [INFO] train episode 39153: reward = -68.52, steps = 65 04:05:49 [INFO] train episode 39154: reward = -77.32, steps = 23 04:05:50 [INFO] train episode 39155: reward = -80.28, steps = 19 04:05:53 [INFO] train episode 39156: reward = -94.86, steps = 25 04:05:56 [INFO] train episode 39157: reward = -51.83, steps = 31 04:05:59 [INFO] train episode 39158: reward = -57.60, steps = 33 04:06:03 [INFO] train episode 39159: reward = -87.37, steps = 38 04:06:06 [INFO] train episode 39160: reward = -89.53, steps = 35 04:06:07 [INFO] train episode 39161: reward = -82.62, steps = 20 04:06:11 [INFO] train episode 39162: reward = -83.00, steps = 38 04:06:13 [INFO] train episode 39163: reward = -45.28, steps = 25 04:06:15 [INFO] train episode 39164: reward = -68.28, steps = 24 04:06:18 [INFO] train episode 39165: reward = -47.43, steps = 35 04:06:22 [INFO] train episode 39166: reward = -101.76, steps = 43 04:06:24 [INFO] train episode 39167: reward = -76.22, steps = 25 04:06:27 [INFO] train episode 39168: reward = -33.64, steps = 41 04:06:29 [INFO] train episode 39169: reward = -62.00, steps = 23 04:06:32 [INFO] train episode 39170: reward = -58.14, steps = 26 04:06:33 [INFO] train episode 39171: reward = -89.10, steps = 20 04:06:36 [INFO] train episode 39172: reward = -40.71, steps = 22 04:06:39 [INFO] train episode 39173: reward = -107.85, steps = 44 04:06:43 [INFO] train episode 39174: reward = -106.23, steps = 40 04:06:46 [INFO] train episode 39175: reward = -61.11, steps = 31 04:06:47 [INFO] train episode 39176: reward = -82.95, steps = 20 04:06:50 [INFO] train episode 39177: reward = -63.88, steps = 30 04:06:52 [INFO] train episode 39178: reward = -49.33, steps = 26 04:06:56 [INFO] train episode 39179: reward = -87.87, steps = 42 04:06:58 [INFO] train episode 39180: reward = -77.34, steps = 28 04:07:03 [INFO] train episode 39181: reward = -61.61, steps = 49 04:07:05 [INFO] train episode 39182: reward = -81.23, steps = 28 04:07:09 [INFO] train episode 39183: reward = -66.38, steps = 41 04:07:12 [INFO] train episode 39184: reward = -71.47, steps = 31 04:07:14 [INFO] train episode 39185: reward = -77.41, steps = 34 04:07:18 [INFO] train episode 39186: reward = -160.84, steps = 40 04:07:20 [INFO] train episode 39187: reward = -98.85, steps = 28 04:07:22 [INFO] train episode 39188: reward = -80.37, steps = 19 04:07:26 [INFO] train episode 39189: reward = -136.28, steps = 45 04:07:29 [INFO] train episode 39190: reward = -69.97, steps = 31 04:07:31 [INFO] train episode 39191: reward = -73.73, steps = 20 04:07:33 [INFO] train episode 39192: reward = -73.03, steps = 29 04:07:35 [INFO] train episode 39193: reward = -74.20, steps = 21 04:07:39 [INFO] train episode 39194: reward = -96.37, steps = 40 04:07:46 [INFO] train episode 39195: reward = -189.41, steps = 85 04:07:48 [INFO] train episode 39196: reward = -99.86, steps = 22 04:07:52 [INFO] train episode 39197: reward = -94.88, steps = 45 04:07:54 [INFO] train episode 39198: reward = -62.66, steps = 24 04:07:57 [INFO] train episode 39199: reward = -94.28, steps = 30 04:07:59 [INFO] train episode 39200: reward = -94.16, steps = 25 04:08:01 [INFO] train episode 39201: reward = -62.84, steps = 20 04:08:03 [INFO] train episode 39202: reward = -81.02, steps = 31 04:08:06 [INFO] train episode 39203: reward = -21.44, steps = 33 04:08:08 [INFO] train episode 39204: reward = -41.22, steps = 25 04:08:12 [INFO] train episode 39205: reward = -112.55, steps = 40 04:08:14 [INFO] train episode 39206: reward = -52.80, steps = 26 04:08:19 [INFO] train episode 39207: reward = -123.25, steps = 52 04:08:21 [INFO] train episode 39208: reward = -76.12, steps = 30 04:08:24 [INFO] train episode 39209: reward = -68.29, steps = 26 04:08:28 [INFO] train episode 39210: reward = -101.20, steps = 47 04:08:31 [INFO] train episode 39211: reward = -115.86, steps = 36 04:08:33 [INFO] train episode 39212: reward = -37.47, steps = 20 04:08:38 [INFO] train episode 39213: reward = -145.37, steps = 56 04:08:42 [INFO] train episode 39214: reward = -90.34, steps = 49 04:08:45 [INFO] train episode 39215: reward = -72.66, steps = 30 04:08:47 [INFO] train episode 39216: reward = -99.56, steps = 20 04:08:49 [INFO] train episode 39217: reward = -46.79, steps = 22 04:08:53 [INFO] train episode 39218: reward = -35.07, steps = 42 04:08:55 [INFO] train episode 39219: reward = -86.25, steps = 24 04:08:58 [INFO] train episode 39220: reward = -115.47, steps = 34 04:09:02 [INFO] train episode 39221: reward = -91.52, steps = 37 04:09:04 [INFO] train episode 39222: reward = -102.35, steps = 31 04:09:06 [INFO] train episode 39223: reward = -71.61, steps = 21 04:09:09 [INFO] train episode 39224: reward = -33.84, steps = 33 04:09:12 [INFO] train episode 39225: reward = -63.15, steps = 29 04:09:14 [INFO] train episode 39226: reward = -57.71, steps = 30 04:09:17 [INFO] train episode 39227: reward = -91.43, steps = 28 04:09:19 [INFO] train episode 39228: reward = -81.66, steps = 25 04:09:21 [INFO] train episode 39229: reward = -70.93, steps = 23 04:09:24 [INFO] train episode 39230: reward = -68.25, steps = 29 04:09:28 [INFO] train episode 39231: reward = -145.86, steps = 44 04:09:32 [INFO] train episode 39232: reward = -47.23, steps = 46 04:09:36 [INFO] train episode 39233: reward = -31.37, steps = 48 04:09:38 [INFO] train episode 39234: reward = -110.95, steps = 20 04:09:40 [INFO] train episode 39235: reward = -93.15, steps = 27 04:09:42 [INFO] train episode 39236: reward = -79.18, steps = 24 04:09:45 [INFO] train episode 39237: reward = -38.96, steps = 35 04:09:47 [INFO] train episode 39238: reward = -70.59, steps = 22 04:09:49 [INFO] train episode 39239: reward = -73.36, steps = 25 04:09:52 [INFO] train episode 39240: reward = -70.16, steps = 26 04:09:53 [INFO] train episode 39241: reward = -75.34, steps = 20 04:09:57 [INFO] train episode 39242: reward = -145.62, steps = 41 04:10:00 [INFO] train episode 39243: reward = -66.36, steps = 33 04:10:03 [INFO] train episode 39244: reward = -37.85, steps = 36 04:10:06 [INFO] train episode 39245: reward = -102.34, steps = 34 04:10:08 [INFO] train episode 39246: reward = -70.38, steps = 29 04:10:12 [INFO] train episode 39247: reward = -125.55, steps = 45 04:10:17 [INFO] train episode 39248: reward = -136.34, steps = 53 04:10:20 [INFO] train episode 39249: reward = -92.01, steps = 39 04:10:23 [INFO] train episode 39250: reward = -104.69, steps = 26 04:10:25 [INFO] train episode 39251: reward = -50.37, steps = 24 04:10:26 [INFO] train episode 39252: reward = -79.40, steps = 21 04:10:32 [INFO] train episode 39253: reward = -138.29, steps = 65 04:10:35 [INFO] train episode 39254: reward = -73.74, steps = 35 04:10:37 [INFO] train episode 39255: reward = -48.86, steps = 22 04:10:39 [INFO] train episode 39256: reward = -99.74, steps = 22 04:10:43 [INFO] train episode 39257: reward = -54.02, steps = 44 04:10:54 [INFO] train episode 39258: reward = -246.40, steps = 124 04:10:56 [INFO] train episode 39259: reward = -109.84, steps = 31 04:11:00 [INFO] train episode 39260: reward = -102.93, steps = 40 04:11:03 [INFO] train episode 39261: reward = -76.17, steps = 37 04:11:04 [INFO] train episode 39262: reward = -48.71, steps = 20 04:11:07 [INFO] train episode 39263: reward = -80.82, steps = 23 04:11:10 [INFO] train episode 39264: reward = -89.96, steps = 31 04:11:12 [INFO] train episode 39265: reward = -100.70, steps = 28 04:11:14 [INFO] train episode 39266: reward = -52.05, steps = 26 04:11:16 [INFO] train episode 39267: reward = -52.00, steps = 26 04:11:19 [INFO] train episode 39268: reward = -53.32, steps = 27 04:11:21 [INFO] train episode 39269: reward = -89.72, steps = 23 04:11:25 [INFO] train episode 39270: reward = -73.50, steps = 42 04:11:29 [INFO] train episode 39271: reward = -65.77, steps = 46 04:11:31 [INFO] train episode 39272: reward = -104.78, steps = 28 04:11:34 [INFO] train episode 39273: reward = -99.31, steps = 32 04:11:36 [INFO] train episode 39274: reward = -56.64, steps = 23 04:11:39 [INFO] train episode 39275: reward = -128.62, steps = 31 04:11:42 [INFO] train episode 39276: reward = -63.27, steps = 24 04:11:44 [INFO] train episode 39277: reward = -71.16, steps = 27 04:11:46 [INFO] train episode 39278: reward = -85.36, steps = 21 04:11:53 [INFO] train episode 39279: reward = -145.81, steps = 85 04:11:55 [INFO] train episode 39280: reward = -74.11, steps = 20 04:11:58 [INFO] train episode 39281: reward = -45.30, steps = 38 04:12:01 [INFO] train episode 39282: reward = -57.75, steps = 28 04:12:03 [INFO] train episode 39283: reward = -66.77, steps = 29 04:12:06 [INFO] train episode 39284: reward = -69.55, steps = 30 04:12:09 [INFO] train episode 39285: reward = -102.03, steps = 44 04:12:13 [INFO] train episode 39286: reward = -129.64, steps = 36 04:12:15 [INFO] train episode 39287: reward = -83.55, steps = 22 04:12:17 [INFO] train episode 39288: reward = -58.48, steps = 25 04:12:19 [INFO] train episode 39289: reward = -71.25, steps = 20 04:12:22 [INFO] train episode 39290: reward = -91.75, steps = 39 04:12:25 [INFO] train episode 39291: reward = -51.58, steps = 28 04:12:28 [INFO] train episode 39292: reward = -141.15, steps = 38 04:12:30 [INFO] train episode 39293: reward = -41.78, steps = 27 04:12:33 [INFO] train episode 39294: reward = -82.88, steps = 24 04:12:35 [INFO] train episode 39295: reward = -112.70, steps = 30 04:12:39 [INFO] train episode 39296: reward = -96.67, steps = 38 04:12:43 [INFO] train episode 39297: reward = -100.83, steps = 42 04:12:45 [INFO] train episode 39298: reward = -97.14, steps = 28 04:12:49 [INFO] train episode 39299: reward = -128.47, steps = 42 04:12:51 [INFO] train episode 39300: reward = -78.09, steps = 22 04:12:54 [INFO] train episode 39301: reward = -104.79, steps = 43 04:12:57 [INFO] train episode 39302: reward = -55.90, steps = 27 04:12:59 [INFO] train episode 39303: reward = -85.51, steps = 24 04:13:03 [INFO] train episode 39304: reward = -58.22, steps = 43 04:13:04 [INFO] train episode 39305: reward = -110.63, steps = 19 04:13:08 [INFO] train episode 39306: reward = -113.83, steps = 40 04:13:11 [INFO] train episode 39307: reward = -96.74, steps = 33 04:13:14 [INFO] train episode 39308: reward = -113.98, steps = 39 04:13:20 [INFO] train episode 39309: reward = -86.90, steps = 62 04:13:21 [INFO] train episode 39310: reward = -59.14, steps = 20 04:13:23 [INFO] train episode 39311: reward = -102.36, steps = 24 04:13:25 [INFO] train episode 39312: reward = -62.18, steps = 24 04:13:29 [INFO] train episode 39313: reward = -72.45, steps = 37 04:13:31 [INFO] train episode 39314: reward = -91.76, steps = 20 04:13:34 [INFO] train episode 39315: reward = -95.88, steps = 37 04:13:36 [INFO] train episode 39316: reward = -80.13, steps = 25 04:13:39 [INFO] train episode 39317: reward = -166.85, steps = 36 04:13:42 [INFO] train episode 39318: reward = -69.67, steps = 27 04:13:43 [INFO] train episode 39319: reward = -105.43, steps = 23 04:13:46 [INFO] train episode 39320: reward = -114.97, steps = 22 04:13:49 [INFO] train episode 39321: reward = -58.08, steps = 34 04:13:51 [INFO] train episode 39322: reward = -68.95, steps = 32 04:13:53 [INFO] train episode 39323: reward = -74.85, steps = 20 04:13:55 [INFO] train episode 39324: reward = -103.91, steps = 22 04:13:58 [INFO] train episode 39325: reward = -89.37, steps = 34 04:14:02 [INFO] train episode 39326: reward = -83.21, steps = 40 04:14:05 [INFO] train episode 39327: reward = -59.15, steps = 34 04:14:07 [INFO] train episode 39328: reward = -89.25, steps = 23 04:14:10 [INFO] train episode 39329: reward = -75.11, steps = 43 04:14:12 [INFO] train episode 39330: reward = -71.99, steps = 25 04:14:16 [INFO] train episode 39331: reward = -68.91, steps = 37 04:14:18 [INFO] train episode 39332: reward = -88.81, steps = 24 04:14:20 [INFO] train episode 39333: reward = -77.22, steps = 23 04:14:22 [INFO] train episode 39334: reward = -107.37, steps = 22 04:14:24 [INFO] train episode 39335: reward = -52.17, steps = 20 04:14:26 [INFO] train episode 39336: reward = -39.39, steps = 30 04:14:28 [INFO] train episode 39337: reward = -62.76, steps = 25 04:14:30 [INFO] train episode 39338: reward = -71.08, steps = 19 04:14:35 [INFO] train episode 39339: reward = -69.18, steps = 40 04:14:36 [INFO] train episode 39340: reward = -72.37, steps = 20 04:14:39 [INFO] train episode 39341: reward = -70.64, steps = 34 04:14:43 [INFO] train episode 39342: reward = -93.45, steps = 44 04:14:45 [INFO] train episode 39343: reward = -99.96, steps = 17 04:14:46 [INFO] train episode 39344: reward = -62.29, steps = 20 04:14:49 [INFO] train episode 39345: reward = -105.39, steps = 25 04:14:52 [INFO] train episode 39346: reward = -132.35, steps = 41 04:14:55 [INFO] train episode 39347: reward = -64.06, steps = 24 04:14:57 [INFO] train episode 39348: reward = -77.28, steps = 28 04:15:00 [INFO] train episode 39349: reward = -66.78, steps = 37 04:15:02 [INFO] train episode 39350: reward = -69.90, steps = 19 04:15:05 [INFO] train episode 39351: reward = -106.38, steps = 35 04:15:08 [INFO] train episode 39352: reward = -116.74, steps = 35 04:15:11 [INFO] train episode 39353: reward = -66.15, steps = 37 04:15:16 [INFO] train episode 39354: reward = -121.59, steps = 54 04:15:18 [INFO] train episode 39355: reward = -77.49, steps = 21 04:15:20 [INFO] train episode 39356: reward = -95.57, steps = 26 04:15:23 [INFO] train episode 39357: reward = -81.71, steps = 31 04:15:26 [INFO] train episode 39358: reward = -91.55, steps = 33 04:15:30 [INFO] train episode 39359: reward = -95.41, steps = 47 04:15:31 [INFO] train episode 39360: reward = -76.15, steps = 19 04:15:35 [INFO] train episode 39361: reward = -66.43, steps = 47 04:15:38 [INFO] train episode 39362: reward = -49.71, steps = 29 04:15:42 [INFO] train episode 39363: reward = -72.14, steps = 52 04:15:45 [INFO] train episode 39364: reward = -60.96, steps = 33 04:15:48 [INFO] train episode 39365: reward = -55.52, steps = 30 04:15:51 [INFO] train episode 39366: reward = -52.11, steps = 38 04:15:53 [INFO] train episode 39367: reward = -42.65, steps = 23 04:15:55 [INFO] train episode 39368: reward = -72.13, steps = 20 04:15:58 [INFO] train episode 39369: reward = -75.90, steps = 27 04:16:00 [INFO] train episode 39370: reward = -94.34, steps = 26 04:16:03 [INFO] train episode 39371: reward = -28.93, steps = 34 04:16:05 [INFO] train episode 39372: reward = -89.68, steps = 25 04:16:07 [INFO] train episode 39373: reward = -60.71, steps = 32 04:16:12 [INFO] train episode 39374: reward = -43.80, steps = 48 04:16:16 [INFO] train episode 39375: reward = -104.54, steps = 49 04:16:20 [INFO] train episode 39376: reward = -87.49, steps = 48 04:16:22 [INFO] train episode 39377: reward = -56.58, steps = 24 04:16:24 [INFO] train episode 39378: reward = -77.63, steps = 25 04:16:28 [INFO] train episode 39379: reward = -70.46, steps = 34 04:16:30 [INFO] train episode 39380: reward = -118.09, steps = 24 04:16:33 [INFO] train episode 39381: reward = -66.14, steps = 36 04:16:37 [INFO] train episode 39382: reward = -74.82, steps = 49 04:16:42 [INFO] train episode 39383: reward = -125.33, steps = 50 04:16:43 [INFO] train episode 39384: reward = -59.95, steps = 21 04:16:45 [INFO] train episode 39385: reward = -141.90, steps = 21 04:16:48 [INFO] train episode 39386: reward = -123.96, steps = 29 04:16:50 [INFO] train episode 39387: reward = -80.60, steps = 24 04:16:52 [INFO] train episode 39388: reward = -74.23, steps = 31 04:16:56 [INFO] train episode 39389: reward = -78.22, steps = 37 04:17:01 [INFO] train episode 39390: reward = -120.56, steps = 57 04:17:03 [INFO] train episode 39391: reward = -100.44, steps = 21 04:17:06 [INFO] train episode 39392: reward = -44.73, steps = 35 04:17:07 [INFO] train episode 39393: reward = -69.78, steps = 20 04:17:12 [INFO] train episode 39394: reward = -140.63, steps = 54 04:17:16 [INFO] train episode 39395: reward = -59.04, steps = 41 04:17:19 [INFO] train episode 39396: reward = -84.13, steps = 42 04:17:24 [INFO] train episode 39397: reward = -111.87, steps = 51 04:17:28 [INFO] train episode 39398: reward = -93.39, steps = 40 04:17:31 [INFO] train episode 39399: reward = -61.13, steps = 30 04:17:32 [INFO] train episode 39400: reward = -98.95, steps = 21 04:17:35 [INFO] train episode 39401: reward = -77.55, steps = 34 04:17:37 [INFO] train episode 39402: reward = -96.70, steps = 19 04:17:39 [INFO] train episode 39403: reward = -104.53, steps = 22 04:17:42 [INFO] train episode 39404: reward = -37.78, steps = 40 04:17:45 [INFO] train episode 39405: reward = -47.65, steps = 30 04:17:49 [INFO] train episode 39406: reward = -131.93, steps = 39 04:17:52 [INFO] train episode 39407: reward = -84.65, steps = 37 04:17:56 [INFO] train episode 39408: reward = -159.18, steps = 49 04:18:01 [INFO] train episode 39409: reward = -156.99, steps = 53 04:18:02 [INFO] train episode 39410: reward = -95.72, steps = 19 04:18:05 [INFO] train episode 39411: reward = -78.05, steps = 32 04:18:08 [INFO] train episode 39412: reward = -53.50, steps = 37 04:18:11 [INFO] train episode 39413: reward = -83.55, steps = 35 04:18:15 [INFO] train episode 39414: reward = -86.88, steps = 45 04:18:17 [INFO] train episode 39415: reward = -46.54, steps = 24 04:18:19 [INFO] train episode 39416: reward = -76.05, steps = 19 04:18:21 [INFO] train episode 39417: reward = -97.54, steps = 29 04:18:26 [INFO] train episode 39418: reward = -97.08, steps = 50 04:18:28 [INFO] train episode 39419: reward = -93.56, steps = 29 04:18:31 [INFO] train episode 39420: reward = -58.72, steps = 34 04:18:33 [INFO] train episode 39421: reward = -129.84, steps = 19 04:18:36 [INFO] train episode 39422: reward = -54.01, steps = 38 04:18:39 [INFO] train episode 39423: reward = -92.76, steps = 27 04:18:45 [INFO] train episode 39424: reward = -138.20, steps = 75 04:18:49 [INFO] train episode 39425: reward = -143.41, steps = 41 04:18:51 [INFO] train episode 39426: reward = -104.01, steps = 28 04:18:55 [INFO] train episode 39427: reward = -100.42, steps = 44 04:18:57 [INFO] train episode 39428: reward = -77.77, steps = 23 04:19:01 [INFO] train episode 39429: reward = -137.36, steps = 44 04:19:04 [INFO] train episode 39430: reward = -72.53, steps = 42 04:19:07 [INFO] train episode 39431: reward = -90.22, steps = 29 04:19:08 [INFO] train episode 39432: reward = -63.62, steps = 18 04:19:12 [INFO] train episode 39433: reward = -95.86, steps = 42 04:19:14 [INFO] train episode 39434: reward = -89.96, steps = 23 04:19:16 [INFO] train episode 39435: reward = -46.14, steps = 20 04:19:20 [INFO] train episode 39436: reward = -58.27, steps = 45 04:19:22 [INFO] train episode 39437: reward = -60.44, steps = 26 04:19:25 [INFO] train episode 39438: reward = -101.28, steps = 31 04:19:27 [INFO] train episode 39439: reward = -68.63, steps = 22 04:19:30 [INFO] train episode 39440: reward = -114.91, steps = 35 04:19:32 [INFO] train episode 39441: reward = -60.62, steps = 29 04:19:35 [INFO] train episode 39442: reward = -135.92, steps = 29 04:19:37 [INFO] train episode 39443: reward = -61.63, steps = 20 04:19:39 [INFO] train episode 39444: reward = -101.27, steps = 22 04:19:41 [INFO] train episode 39445: reward = -37.22, steps = 26 04:19:45 [INFO] train episode 39446: reward = -43.89, steps = 47 04:19:47 [INFO] train episode 39447: reward = -108.37, steps = 24 04:19:49 [INFO] train episode 39448: reward = -96.37, steps = 22 04:19:52 [INFO] train episode 39449: reward = -72.34, steps = 37 04:19:56 [INFO] train episode 39450: reward = -68.36, steps = 38 04:19:59 [INFO] train episode 39451: reward = -82.60, steps = 42 04:20:01 [INFO] train episode 39452: reward = -80.66, steps = 27 04:20:07 [INFO] train episode 39453: reward = -102.09, steps = 63 04:20:10 [INFO] train episode 39454: reward = -79.62, steps = 37 04:20:15 [INFO] train episode 39455: reward = -126.95, steps = 56 04:20:19 [INFO] train episode 39456: reward = -61.23, steps = 43 04:20:21 [INFO] train episode 39457: reward = -93.80, steps = 20 04:20:25 [INFO] train episode 39458: reward = -147.29, steps = 41 04:20:28 [INFO] train episode 39459: reward = -56.77, steps = 38 04:20:31 [INFO] train episode 39460: reward = -111.33, steps = 27 04:20:34 [INFO] train episode 39461: reward = -70.44, steps = 43 04:20:37 [INFO] train episode 39462: reward = -68.72, steps = 32 04:20:40 [INFO] train episode 39463: reward = -94.63, steps = 34 04:20:43 [INFO] train episode 39464: reward = -47.53, steps = 27 04:20:44 [INFO] train episode 39465: reward = -76.89, steps = 19 04:20:49 [INFO] train episode 39466: reward = -115.76, steps = 48 04:20:51 [INFO] train episode 39467: reward = -65.77, steps = 23 04:20:53 [INFO] train episode 39468: reward = -77.33, steps = 32 04:20:59 [INFO] train episode 39469: reward = -56.41, steps = 56 04:21:02 [INFO] train episode 39470: reward = -51.14, steps = 30 04:21:05 [INFO] train episode 39471: reward = -75.45, steps = 33 04:21:08 [INFO] train episode 39472: reward = -83.16, steps = 33 04:21:10 [INFO] train episode 39473: reward = -79.40, steps = 21 04:21:14 [INFO] train episode 39474: reward = -41.59, steps = 34 04:21:16 [INFO] train episode 39475: reward = -105.05, steps = 23 04:21:18 [INFO] train episode 39476: reward = -62.21, steps = 27 04:21:20 [INFO] train episode 39477: reward = -63.61, steps = 19 04:21:24 [INFO] train episode 39478: reward = -82.30, steps = 38 04:21:26 [INFO] train episode 39479: reward = -59.08, steps = 33 04:21:30 [INFO] train episode 39480: reward = -201.25, steps = 37 04:21:33 [INFO] train episode 39481: reward = -58.99, steps = 38 04:21:39 [INFO] train episode 39482: reward = -108.98, steps = 66 04:21:42 [INFO] train episode 39483: reward = -103.91, steps = 33 04:21:45 [INFO] train episode 39484: reward = -119.95, steps = 37 04:21:47 [INFO] train episode 39485: reward = -87.11, steps = 21 04:21:49 [INFO] train episode 39486: reward = -114.71, steps = 21 04:21:51 [INFO] train episode 39487: reward = -87.44, steps = 21 04:21:52 [INFO] train episode 39488: reward = -98.13, steps = 20 04:21:55 [INFO] train episode 39489: reward = -81.86, steps = 36 04:21:58 [INFO] train episode 39490: reward = -70.49, steps = 34 04:22:02 [INFO] train episode 39491: reward = -86.10, steps = 34 04:22:03 [INFO] train episode 39492: reward = -96.06, steps = 22 04:22:07 [INFO] train episode 39493: reward = -98.51, steps = 38 04:22:10 [INFO] train episode 39494: reward = -108.56, steps = 42 04:22:14 [INFO] train episode 39495: reward = -60.67, steps = 39 04:22:16 [INFO] train episode 39496: reward = -30.06, steps = 31 04:22:18 [INFO] train episode 39497: reward = -96.31, steps = 22 04:22:21 [INFO] train episode 39498: reward = -97.25, steps = 24 04:22:22 [INFO] train episode 39499: reward = -39.43, steps = 22 04:22:25 [INFO] train episode 39500: reward = -82.38, steps = 27 04:22:27 [INFO] train episode 39501: reward = -55.30, steps = 28 04:22:30 [INFO] train episode 39502: reward = -76.06, steps = 39 04:22:32 [INFO] train episode 39503: reward = -69.25, steps = 19 04:22:37 [INFO] train episode 39504: reward = -72.86, steps = 57 04:22:39 [INFO] train episode 39505: reward = -83.34, steps = 24 04:22:41 [INFO] train episode 39506: reward = -56.88, steps = 21 04:22:43 [INFO] train episode 39507: reward = -87.87, steps = 19 04:22:46 [INFO] train episode 39508: reward = -74.30, steps = 41 04:22:50 [INFO] train episode 39509: reward = -72.22, steps = 38 04:22:53 [INFO] train episode 39510: reward = -111.39, steps = 30 04:22:55 [INFO] train episode 39511: reward = -58.51, steps = 33 04:22:59 [INFO] train episode 39512: reward = -90.96, steps = 42 04:23:01 [INFO] train episode 39513: reward = -82.29, steps = 25 04:23:03 [INFO] train episode 39514: reward = -79.39, steps = 17 04:23:06 [INFO] train episode 39515: reward = -63.46, steps = 30 04:23:08 [INFO] train episode 39516: reward = -105.48, steps = 28 04:23:13 [INFO] train episode 39517: reward = -116.79, steps = 53 04:23:15 [INFO] train episode 39518: reward = -77.45, steps = 28 04:23:19 [INFO] train episode 39519: reward = -65.61, steps = 38 04:23:24 [INFO] train episode 39520: reward = -119.84, steps = 56 04:23:27 [INFO] train episode 39521: reward = -78.26, steps = 42 04:23:29 [INFO] train episode 39522: reward = -87.32, steps = 23 04:23:31 [INFO] train episode 39523: reward = -68.60, steps = 20 04:23:36 [INFO] train episode 39524: reward = -87.24, steps = 50 04:23:40 [INFO] train episode 39525: reward = -119.15, steps = 52 04:23:44 [INFO] train episode 39526: reward = -81.20, steps = 38 04:23:46 [INFO] train episode 39527: reward = -39.65, steps = 29 04:23:49 [INFO] train episode 39528: reward = -78.53, steps = 31 04:23:51 [INFO] train episode 39529: reward = -53.77, steps = 23 04:23:56 [INFO] train episode 39530: reward = -91.04, steps = 61 04:23:58 [INFO] train episode 39531: reward = -52.26, steps = 21 04:24:02 [INFO] train episode 39532: reward = -173.95, steps = 50 04:24:05 [INFO] train episode 39533: reward = -172.38, steps = 30 04:24:08 [INFO] train episode 39534: reward = -55.47, steps = 30 04:24:10 [INFO] train episode 39535: reward = -85.99, steps = 22 04:24:12 [INFO] train episode 39536: reward = -44.71, steps = 29 04:24:15 [INFO] train episode 39537: reward = -68.85, steps = 34 04:24:18 [INFO] train episode 39538: reward = -76.04, steps = 24 04:24:20 [INFO] train episode 39539: reward = -55.14, steps = 29 04:24:22 [INFO] train episode 39540: reward = -62.03, steps = 22 04:24:24 [INFO] train episode 39541: reward = -73.98, steps = 28 04:24:28 [INFO] train episode 39542: reward = -88.99, steps = 34 04:24:30 [INFO] train episode 39543: reward = -86.90, steps = 26 04:24:33 [INFO] train episode 39544: reward = -38.70, steps = 35 04:24:38 [INFO] train episode 39545: reward = -214.61, steps = 59 04:24:40 [INFO] train episode 39546: reward = -71.20, steps = 22 04:24:43 [INFO] train episode 39547: reward = -87.93, steps = 27 04:24:46 [INFO] train episode 39548: reward = -53.81, steps = 40 04:24:53 [INFO] train episode 39549: reward = -179.55, steps = 88 04:24:59 [INFO] train episode 39550: reward = -65.87, steps = 62 04:25:01 [INFO] train episode 39551: reward = -124.27, steps = 18 04:25:04 [INFO] train episode 39552: reward = -142.61, steps = 45 04:25:08 [INFO] train episode 39553: reward = -70.63, steps = 38 04:25:10 [INFO] train episode 39554: reward = -75.45, steps = 33 04:25:15 [INFO] train episode 39555: reward = -69.61, steps = 45 04:25:17 [INFO] train episode 39556: reward = -74.35, steps = 25 04:25:21 [INFO] train episode 39557: reward = -81.29, steps = 55 04:25:24 [INFO] train episode 39558: reward = -44.01, steps = 25 04:25:27 [INFO] train episode 39559: reward = -32.46, steps = 42 04:25:30 [INFO] train episode 39560: reward = -41.41, steps = 23 04:25:32 [INFO] train episode 39561: reward = -73.29, steps = 34 04:25:34 [INFO] train episode 39562: reward = -65.79, steps = 24 04:25:36 [INFO] train episode 39563: reward = -87.61, steps = 22 04:25:40 [INFO] train episode 39564: reward = -35.33, steps = 38 04:25:42 [INFO] train episode 39565: reward = -94.69, steps = 23 04:25:45 [INFO] train episode 39566: reward = -14.10, steps = 37 04:25:48 [INFO] train episode 39567: reward = -69.74, steps = 32 04:25:50 [INFO] train episode 39568: reward = -121.60, steps = 24 04:25:52 [INFO] train episode 39569: reward = -100.06, steps = 31 04:25:59 [INFO] train episode 39570: reward = -61.31, steps = 83 04:26:02 [INFO] train episode 39571: reward = -100.49, steps = 24 04:26:05 [INFO] train episode 39572: reward = -57.35, steps = 22 04:26:07 [INFO] train episode 39573: reward = -61.29, steps = 27 04:26:11 [INFO] train episode 39574: reward = -127.32, steps = 48 04:26:14 [INFO] train episode 39575: reward = -102.41, steps = 34 04:26:16 [INFO] train episode 39576: reward = -84.60, steps = 22 04:26:18 [INFO] train episode 39577: reward = -72.99, steps = 28 04:26:22 [INFO] train episode 39578: reward = -60.81, steps = 48 04:26:24 [INFO] train episode 39579: reward = -102.04, steps = 22 04:26:26 [INFO] train episode 39580: reward = -43.02, steps = 25 04:26:30 [INFO] train episode 39581: reward = -123.20, steps = 44 04:26:33 [INFO] train episode 39582: reward = -82.47, steps = 32 04:26:35 [INFO] train episode 39583: reward = -97.96, steps = 23 04:26:37 [INFO] train episode 39584: reward = -79.98, steps = 17 04:26:40 [INFO] train episode 39585: reward = -69.59, steps = 35 04:26:44 [INFO] train episode 39586: reward = -114.38, steps = 55 04:26:47 [INFO] train episode 39587: reward = -50.98, steps = 28 04:26:49 [INFO] train episode 39588: reward = -51.73, steps = 20 04:26:52 [INFO] train episode 39589: reward = -98.80, steps = 35 04:26:54 [INFO] train episode 39590: reward = -49.80, steps = 23 04:26:57 [INFO] train episode 39591: reward = -63.19, steps = 39 04:26:59 [INFO] train episode 39592: reward = -102.01, steps = 27 04:27:02 [INFO] train episode 39593: reward = -77.62, steps = 35 04:27:05 [INFO] train episode 39594: reward = -56.99, steps = 31 04:27:07 [INFO] train episode 39595: reward = -94.91, steps = 20 04:27:11 [INFO] train episode 39596: reward = -80.24, steps = 46 04:27:13 [INFO] train episode 39597: reward = -106.19, steps = 24 04:27:17 [INFO] train episode 39598: reward = -53.35, steps = 41 04:27:19 [INFO] train episode 39599: reward = -71.37, steps = 24 04:27:21 [INFO] train episode 39600: reward = -62.28, steps = 32 04:27:24 [INFO] train episode 39601: reward = -79.59, steps = 20 04:27:26 [INFO] train episode 39602: reward = -73.87, steps = 30 04:27:28 [INFO] train episode 39603: reward = -70.41, steps = 20 04:27:31 [INFO] train episode 39604: reward = -63.10, steps = 35 04:27:33 [INFO] train episode 39605: reward = -56.73, steps = 24 04:27:35 [INFO] train episode 39606: reward = -57.79, steps = 21 04:27:38 [INFO] train episode 39607: reward = -47.78, steps = 34 04:27:41 [INFO] train episode 39608: reward = -71.66, steps = 34 04:27:45 [INFO] train episode 39609: reward = -106.57, steps = 53 04:27:48 [INFO] train episode 39610: reward = -68.98, steps = 36 04:27:51 [INFO] train episode 39611: reward = -77.53, steps = 29 04:27:55 [INFO] train episode 39612: reward = -159.74, steps = 42 04:27:59 [INFO] train episode 39613: reward = -127.31, steps = 46 04:28:02 [INFO] train episode 39614: reward = -82.07, steps = 36 04:28:05 [INFO] train episode 39615: reward = -74.28, steps = 34 04:28:08 [INFO] train episode 39616: reward = -64.55, steps = 34 04:28:10 [INFO] train episode 39617: reward = -69.96, steps = 27 04:28:13 [INFO] train episode 39618: reward = -104.96, steps = 38 04:28:16 [INFO] train episode 39619: reward = -84.05, steps = 33 04:28:20 [INFO] train episode 39620: reward = -70.62, steps = 40 04:28:27 [INFO] train episode 39621: reward = -159.90, steps = 86 04:28:29 [INFO] train episode 39622: reward = -103.25, steps = 22 04:28:31 [INFO] train episode 39623: reward = -75.33, steps = 30 04:28:34 [INFO] train episode 39624: reward = -68.12, steps = 32 04:28:36 [INFO] train episode 39625: reward = -57.20, steps = 24 04:28:39 [INFO] train episode 39626: reward = -74.94, steps = 27 04:28:41 [INFO] train episode 39627: reward = -71.99, steps = 20 04:28:44 [INFO] train episode 39628: reward = -68.13, steps = 32 04:28:46 [INFO] train episode 39629: reward = -60.15, steps = 31 04:28:49 [INFO] train episode 39630: reward = -54.23, steps = 33 04:28:51 [INFO] train episode 39631: reward = -110.33, steps = 26 04:28:53 [INFO] train episode 39632: reward = -70.39, steps = 19 04:28:58 [INFO] train episode 39633: reward = -111.53, steps = 45 04:29:01 [INFO] train episode 39634: reward = -36.29, steps = 30 04:29:04 [INFO] train episode 39635: reward = -120.83, steps = 31 04:29:07 [INFO] train episode 39636: reward = -80.83, steps = 30 04:29:08 [INFO] train episode 39637: reward = -73.31, steps = 21 04:29:12 [INFO] train episode 39638: reward = -66.27, steps = 40 04:29:14 [INFO] train episode 39639: reward = -72.18, steps = 20 04:29:16 [INFO] train episode 39640: reward = -55.67, steps = 24 04:29:19 [INFO] train episode 39641: reward = -62.82, steps = 32 04:29:22 [INFO] train episode 39642: reward = -62.45, steps = 37 04:29:25 [INFO] train episode 39643: reward = -86.00, steps = 35 04:29:28 [INFO] train episode 39644: reward = -83.94, steps = 40 04:29:31 [INFO] train episode 39645: reward = -39.93, steps = 35 04:29:35 [INFO] train episode 39646: reward = -57.47, steps = 41 04:29:37 [INFO] train episode 39647: reward = -81.14, steps = 27 04:29:41 [INFO] train episode 39648: reward = -98.44, steps = 39 04:29:44 [INFO] train episode 39649: reward = -135.62, steps = 34 04:29:47 [INFO] train episode 39650: reward = -61.55, steps = 36 04:29:49 [INFO] train episode 39651: reward = -43.56, steps = 18 04:29:52 [INFO] train episode 39652: reward = -86.14, steps = 38 04:29:54 [INFO] train episode 39653: reward = -85.48, steps = 24 04:30:00 [INFO] train episode 39654: reward = -105.80, steps = 71 04:30:02 [INFO] train episode 39655: reward = -82.66, steps = 26 04:30:05 [INFO] train episode 39656: reward = -77.44, steps = 36 04:30:07 [INFO] train episode 39657: reward = -71.45, steps = 20 04:30:09 [INFO] train episode 39658: reward = -80.83, steps = 19 04:30:13 [INFO] train episode 39659: reward = -115.84, steps = 49 04:30:15 [INFO] train episode 39660: reward = -77.92, steps = 19 04:30:16 [INFO] train episode 39661: reward = -77.54, steps = 17 04:30:22 [INFO] train episode 39662: reward = -116.73, steps = 63 04:30:25 [INFO] train episode 39663: reward = -123.97, steps = 39 04:30:27 [INFO] train episode 39664: reward = -66.86, steps = 23 04:30:31 [INFO] train episode 39665: reward = -113.03, steps = 46 04:30:35 [INFO] train episode 39666: reward = -83.70, steps = 38 04:30:37 [INFO] train episode 39667: reward = -90.64, steps = 26 04:30:40 [INFO] train episode 39668: reward = -94.25, steps = 40 04:30:43 [INFO] train episode 39669: reward = -80.31, steps = 31 04:30:45 [INFO] train episode 39670: reward = -77.13, steps = 19 04:30:47 [INFO] train episode 39671: reward = -73.94, steps = 28 04:30:51 [INFO] train episode 39672: reward = -54.06, steps = 36 04:30:54 [INFO] train episode 39673: reward = -98.00, steps = 39 04:30:57 [INFO] train episode 39674: reward = -115.46, steps = 37 04:31:01 [INFO] train episode 39675: reward = -43.39, steps = 42 04:31:03 [INFO] train episode 39676: reward = -62.91, steps = 22 04:31:07 [INFO] train episode 39677: reward = -92.81, steps = 45 04:31:10 [INFO] train episode 39678: reward = -50.12, steps = 36 04:31:12 [INFO] train episode 39679: reward = -78.02, steps = 24 04:31:14 [INFO] train episode 39680: reward = -66.66, steps = 22 04:31:15 [INFO] train episode 39681: reward = -75.53, steps = 19 04:31:17 [INFO] train episode 39682: reward = -81.69, steps = 26 04:31:20 [INFO] train episode 39683: reward = -65.41, steps = 35 04:31:24 [INFO] train episode 39684: reward = -84.96, steps = 41 04:31:26 [INFO] train episode 39685: reward = -40.05, steps = 24 04:31:28 [INFO] train episode 39686: reward = -74.24, steps = 24 04:31:31 [INFO] train episode 39687: reward = -78.93, steps = 30 04:31:34 [INFO] train episode 39688: reward = -64.94, steps = 40 04:31:36 [INFO] train episode 39689: reward = -58.24, steps = 23 04:31:40 [INFO] train episode 39690: reward = -121.83, steps = 44 04:31:43 [INFO] train episode 39691: reward = -94.25, steps = 36 04:31:46 [INFO] train episode 39692: reward = -38.77, steps = 30 04:31:49 [INFO] train episode 39693: reward = -70.43, steps = 31 04:31:51 [INFO] train episode 39694: reward = -100.89, steps = 27 04:31:55 [INFO] train episode 39695: reward = -83.11, steps = 35 04:31:56 [INFO] train episode 39696: reward = -84.23, steps = 19 04:31:58 [INFO] train episode 39697: reward = -117.20, steps = 21 04:32:02 [INFO] train episode 39698: reward = -114.33, steps = 41 04:32:04 [INFO] train episode 39699: reward = -71.37, steps = 25 04:32:07 [INFO] train episode 39700: reward = -96.80, steps = 32 04:32:09 [INFO] train episode 39701: reward = -107.89, steps = 26 04:32:12 [INFO] train episode 39702: reward = -36.68, steps = 32 04:32:15 [INFO] train episode 39703: reward = -18.03, steps = 38 04:32:17 [INFO] train episode 39704: reward = -53.40, steps = 21 04:32:19 [INFO] train episode 39705: reward = -37.29, steps = 19 04:32:22 [INFO] train episode 39706: reward = -84.83, steps = 38 04:32:24 [INFO] train episode 39707: reward = -56.63, steps = 29 04:32:28 [INFO] train episode 39708: reward = -69.13, steps = 37 04:32:31 [INFO] train episode 39709: reward = -42.29, steps = 35 04:32:35 [INFO] train episode 39710: reward = -169.75, steps = 55 04:32:37 [INFO] train episode 39711: reward = -77.37, steps = 20 04:32:39 [INFO] train episode 39712: reward = -69.74, steps = 23 04:32:42 [INFO] train episode 39713: reward = -69.71, steps = 31 04:32:44 [INFO] train episode 39714: reward = -69.44, steps = 17 04:32:47 [INFO] train episode 39715: reward = -108.96, steps = 36 04:32:52 [INFO] train episode 39716: reward = -74.11, steps = 57 04:32:55 [INFO] train episode 39717: reward = -80.74, steps = 43 04:32:59 [INFO] train episode 39718: reward = -106.76, steps = 35 04:33:02 [INFO] train episode 39719: reward = -122.50, steps = 43 04:33:05 [INFO] train episode 39720: reward = -80.87, steps = 28 04:33:09 [INFO] train episode 39721: reward = -150.93, steps = 49 04:33:12 [INFO] train episode 39722: reward = -86.86, steps = 35 04:33:16 [INFO] train episode 39723: reward = -96.45, steps = 42 04:33:18 [INFO] train episode 39724: reward = -73.92, steps = 21 04:33:20 [INFO] train episode 39725: reward = -84.27, steps = 22 04:33:22 [INFO] train episode 39726: reward = -60.10, steps = 35 04:33:26 [INFO] train episode 39727: reward = -86.31, steps = 42 04:33:28 [INFO] train episode 39728: reward = -99.19, steps = 18 04:33:30 [INFO] train episode 39729: reward = -54.70, steps = 29 04:33:35 [INFO] train episode 39730: reward = -98.12, steps = 50 04:33:38 [INFO] train episode 39731: reward = -68.35, steps = 40 04:33:40 [INFO] train episode 39732: reward = -82.55, steps = 19 04:33:41 [INFO] train episode 39733: reward = -81.65, steps = 20 04:33:43 [INFO] train episode 39734: reward = -130.87, steps = 22 04:33:47 [INFO] train episode 39735: reward = -55.40, steps = 37 04:33:49 [INFO] train episode 39736: reward = -43.35, steps = 21 04:33:50 [INFO] train episode 39737: reward = -76.20, steps = 20 04:33:55 [INFO] train episode 39738: reward = -133.92, steps = 55 04:33:58 [INFO] train episode 39739: reward = -82.22, steps = 41 04:34:00 [INFO] train episode 39740: reward = -91.29, steps = 21 04:34:02 [INFO] train episode 39741: reward = -103.65, steps = 23 04:34:05 [INFO] train episode 39742: reward = -37.56, steps = 32 04:34:07 [INFO] train episode 39743: reward = -81.98, steps = 23 04:34:11 [INFO] train episode 39744: reward = -98.48, steps = 43 04:34:13 [INFO] train episode 39745: reward = -84.33, steps = 28 04:34:15 [INFO] train episode 39746: reward = -88.84, steps = 19 04:34:18 [INFO] train episode 39747: reward = -92.07, steps = 38 04:34:22 [INFO] train episode 39748: reward = -70.71, steps = 49 04:34:24 [INFO] train episode 39749: reward = -53.34, steps = 22 04:34:26 [INFO] train episode 39750: reward = -121.53, steps = 18 04:34:28 [INFO] train episode 39751: reward = -83.51, steps = 21 04:34:31 [INFO] train episode 39752: reward = -75.17, steps = 34 04:34:35 [INFO] train episode 39753: reward = -80.25, steps = 41 04:34:38 [INFO] train episode 39754: reward = -124.37, steps = 36 04:34:40 [INFO] train episode 39755: reward = -56.66, steps = 20 04:34:43 [INFO] train episode 39756: reward = -34.26, steps = 27 04:34:44 [INFO] train episode 39757: reward = -81.07, steps = 20 04:34:47 [INFO] train episode 39758: reward = -92.69, steps = 31 04:34:52 [INFO] train episode 39759: reward = -124.57, steps = 55 04:34:55 [INFO] train episode 39760: reward = -63.62, steps = 31 04:34:57 [INFO] train episode 39761: reward = -88.83, steps = 32 04:35:00 [INFO] train episode 39762: reward = -39.62, steps = 33 04:35:02 [INFO] train episode 39763: reward = -75.38, steps = 24 04:35:04 [INFO] train episode 39764: reward = -84.24, steps = 26 04:35:09 [INFO] train episode 39765: reward = -65.23, steps = 46 04:35:10 [INFO] train episode 39766: reward = -80.51, steps = 17 04:35:13 [INFO] train episode 39767: reward = -91.18, steps = 29 04:35:15 [INFO] train episode 39768: reward = -75.01, steps = 31 04:35:17 [INFO] train episode 39769: reward = -68.64, steps = 24 04:35:19 [INFO] train episode 39770: reward = -72.49, steps = 21 04:35:23 [INFO] train episode 39771: reward = -101.42, steps = 45 04:35:26 [INFO] train episode 39772: reward = -95.48, steps = 28 04:35:30 [INFO] train episode 39773: reward = -108.90, steps = 49 04:35:32 [INFO] train episode 39774: reward = -81.99, steps = 27 04:35:35 [INFO] train episode 39775: reward = -56.70, steps = 39 04:35:38 [INFO] train episode 39776: reward = -98.35, steps = 20 04:35:42 [INFO] train episode 39777: reward = -54.45, steps = 50 04:35:44 [INFO] train episode 39778: reward = -54.92, steps = 23 04:35:46 [INFO] train episode 39779: reward = -71.47, steps = 30 04:35:49 [INFO] train episode 39780: reward = -42.01, steps = 29 04:35:52 [INFO] train episode 39781: reward = -97.07, steps = 35 04:35:57 [INFO] train episode 39782: reward = -78.28, steps = 57 04:36:01 [INFO] train episode 39783: reward = -70.85, steps = 45 04:36:03 [INFO] train episode 39784: reward = -107.13, steps = 25 04:36:06 [INFO] train episode 39785: reward = -57.40, steps = 40 04:36:08 [INFO] train episode 39786: reward = -95.09, steps = 26 04:36:15 [INFO] train episode 39787: reward = -148.76, steps = 74 04:36:19 [INFO] train episode 39788: reward = -70.81, steps = 46 04:36:23 [INFO] train episode 39789: reward = -132.26, steps = 50 04:36:27 [INFO] train episode 39790: reward = -67.86, steps = 50 04:36:30 [INFO] train episode 39791: reward = -91.10, steps = 36 04:36:32 [INFO] train episode 39792: reward = -75.25, steps = 22 04:36:37 [INFO] train episode 39793: reward = -134.25, steps = 53 04:36:39 [INFO] train episode 39794: reward = -67.07, steps = 25 04:36:43 [INFO] train episode 39795: reward = -93.69, steps = 43 04:36:46 [INFO] train episode 39796: reward = -82.70, steps = 41 04:36:48 [INFO] train episode 39797: reward = -81.65, steps = 20 04:36:52 [INFO] train episode 39798: reward = -100.67, steps = 39 04:36:55 [INFO] train episode 39799: reward = -46.43, steps = 37 04:36:59 [INFO] train episode 39800: reward = -78.08, steps = 46 04:37:01 [INFO] train episode 39801: reward = -42.34, steps = 26 04:37:03 [INFO] train episode 39802: reward = -58.41, steps = 20 04:37:07 [INFO] train episode 39803: reward = -62.06, steps = 43 04:37:13 [INFO] train episode 39804: reward = -158.41, steps = 71 04:37:15 [INFO] train episode 39805: reward = -61.15, steps = 24 04:37:18 [INFO] train episode 39806: reward = -60.30, steps = 33 04:37:21 [INFO] train episode 39807: reward = -65.15, steps = 42 04:37:25 [INFO] train episode 39808: reward = -100.94, steps = 42 04:37:26 [INFO] train episode 39809: reward = -102.03, steps = 21 04:37:30 [INFO] train episode 39810: reward = -66.48, steps = 29 04:37:32 [INFO] train episode 39811: reward = -69.23, steps = 21 04:37:35 [INFO] train episode 39812: reward = -37.80, steps = 35 04:37:38 [INFO] train episode 39813: reward = -85.84, steps = 36 04:37:42 [INFO] train episode 39814: reward = -99.26, steps = 46 04:37:44 [INFO] train episode 39815: reward = -99.52, steps = 19 04:37:47 [INFO] train episode 39816: reward = -96.21, steps = 42 04:37:50 [INFO] train episode 39817: reward = -94.18, steps = 34 04:37:53 [INFO] train episode 39818: reward = -64.82, steps = 26 04:37:57 [INFO] train episode 39819: reward = -82.75, steps = 53 04:38:01 [INFO] train episode 39820: reward = -52.94, steps = 47 04:38:03 [INFO] train episode 39821: reward = -61.00, steps = 23 04:38:05 [INFO] train episode 39822: reward = -81.13, steps = 24 04:38:08 [INFO] train episode 39823: reward = -82.26, steps = 33 04:38:11 [INFO] train episode 39824: reward = -86.13, steps = 31 04:38:14 [INFO] train episode 39825: reward = -96.75, steps = 37 04:38:15 [INFO] train episode 39826: reward = -48.66, steps = 18 04:38:17 [INFO] train episode 39827: reward = -91.80, steps = 17 04:38:19 [INFO] train episode 39828: reward = -83.55, steps = 17 04:38:21 [INFO] train episode 39829: reward = -56.77, steps = 26 04:38:24 [INFO] train episode 39830: reward = -84.70, steps = 33 04:38:26 [INFO] train episode 39831: reward = -169.35, steps = 21 04:38:33 [INFO] train episode 39832: reward = -207.14, steps = 89 04:38:36 [INFO] train episode 39833: reward = -62.86, steps = 35 04:38:38 [INFO] train episode 39834: reward = -89.04, steps = 19 04:38:41 [INFO] train episode 39835: reward = -125.75, steps = 38 04:38:43 [INFO] train episode 39836: reward = -76.21, steps = 20 04:38:45 [INFO] train episode 39837: reward = -47.65, steps = 21 04:38:48 [INFO] train episode 39838: reward = -105.00, steps = 30 04:38:50 [INFO] train episode 39839: reward = -54.06, steps = 23 04:38:52 [INFO] train episode 39840: reward = -72.73, steps = 30 04:38:55 [INFO] train episode 39841: reward = -137.95, steps = 34 04:38:59 [INFO] train episode 39842: reward = -114.66, steps = 45 04:39:04 [INFO] train episode 39843: reward = -74.84, steps = 56 04:39:07 [INFO] train episode 39844: reward = -63.67, steps = 28 04:39:10 [INFO] train episode 39845: reward = -32.94, steps = 38 04:39:14 [INFO] train episode 39846: reward = -104.26, steps = 44 04:39:16 [INFO] train episode 39847: reward = -62.07, steps = 23 04:39:19 [INFO] train episode 39848: reward = -54.92, steps = 36 04:39:21 [INFO] train episode 39849: reward = -74.48, steps = 20 04:39:24 [INFO] train episode 39850: reward = -38.62, steps = 38 04:39:26 [INFO] train episode 39851: reward = -90.48, steps = 20 04:39:29 [INFO] train episode 39852: reward = -41.59, steps = 32 04:39:32 [INFO] train episode 39853: reward = -65.57, steps = 35 04:39:34 [INFO] train episode 39854: reward = -93.97, steps = 25 04:39:39 [INFO] train episode 39855: reward = -128.22, steps = 59 04:39:44 [INFO] train episode 39856: reward = -166.00, steps = 60 04:39:46 [INFO] train episode 39857: reward = -49.01, steps = 25 04:39:48 [INFO] train episode 39858: reward = -53.86, steps = 23 04:39:51 [INFO] train episode 39859: reward = -70.30, steps = 31 04:39:55 [INFO] train episode 39860: reward = -123.12, steps = 41 04:39:57 [INFO] train episode 39861: reward = -111.67, steps = 29 04:40:00 [INFO] train episode 39862: reward = -62.95, steps = 25 04:40:03 [INFO] train episode 39863: reward = -52.68, steps = 39 04:40:06 [INFO] train episode 39864: reward = -41.02, steps = 37 04:40:09 [INFO] train episode 39865: reward = -47.94, steps = 35 04:40:13 [INFO] train episode 39866: reward = -65.97, steps = 46 04:40:16 [INFO] train episode 39867: reward = -63.03, steps = 29 04:40:18 [INFO] train episode 39868: reward = -60.46, steps = 28 04:40:22 [INFO] train episode 39869: reward = -62.52, steps = 33 04:40:25 [INFO] train episode 39870: reward = -42.06, steps = 34 04:40:28 [INFO] train episode 39871: reward = -42.68, steps = 32 04:40:30 [INFO] train episode 39872: reward = -31.14, steps = 31 04:40:36 [INFO] train episode 39873: reward = -49.31, steps = 64 04:40:39 [INFO] train episode 39874: reward = -52.76, steps = 37 04:40:41 [INFO] train episode 39875: reward = -63.58, steps = 18 04:40:44 [INFO] train episode 39876: reward = -69.64, steps = 34 04:40:47 [INFO] train episode 39877: reward = -80.86, steps = 38 04:40:50 [INFO] train episode 39878: reward = -126.00, steps = 34 04:40:52 [INFO] train episode 39879: reward = -64.87, steps = 27 04:40:56 [INFO] train episode 39880: reward = -68.41, steps = 39 04:40:58 [INFO] train episode 39881: reward = -87.80, steps = 21 04:41:01 [INFO] train episode 39882: reward = -93.36, steps = 35 04:41:03 [INFO] train episode 39883: reward = -54.73, steps = 21 04:41:06 [INFO] train episode 39884: reward = -65.24, steps = 41 04:41:11 [INFO] train episode 39885: reward = -91.90, steps = 54 04:41:13 [INFO] train episode 39886: reward = -87.14, steps = 22 04:41:17 [INFO] train episode 39887: reward = -88.13, steps = 52 04:41:21 [INFO] train episode 39888: reward = -128.73, steps = 44 04:41:24 [INFO] train episode 39889: reward = -78.81, steps = 41 04:41:27 [INFO] train episode 39890: reward = -54.00, steps = 28 04:41:30 [INFO] train episode 39891: reward = -47.02, steps = 34 04:41:32 [INFO] train episode 39892: reward = -65.61, steps = 20 04:41:34 [INFO] train episode 39893: reward = -88.18, steps = 24 04:41:36 [INFO] train episode 39894: reward = -92.02, steps = 31 04:41:40 [INFO] train episode 39895: reward = -89.60, steps = 46 04:41:43 [INFO] train episode 39896: reward = -90.00, steps = 31 04:41:45 [INFO] train episode 39897: reward = -68.60, steps = 23 04:41:47 [INFO] train episode 39898: reward = -68.64, steps = 25 04:41:51 [INFO] train episode 39899: reward = -82.76, steps = 41 04:41:55 [INFO] train episode 39900: reward = -101.02, steps = 49 04:42:00 [INFO] train episode 39901: reward = -88.50, steps = 61 04:42:05 [INFO] train episode 39902: reward = -32.65, steps = 51 04:42:06 [INFO] train episode 39903: reward = -46.91, steps = 19 04:42:08 [INFO] train episode 39904: reward = -88.05, steps = 20 04:42:10 [INFO] train episode 39905: reward = -89.38, steps = 18 04:42:14 [INFO] train episode 39906: reward = -62.97, steps = 55 04:42:17 [INFO] train episode 39907: reward = -52.74, steps = 28 04:42:20 [INFO] train episode 39908: reward = -55.74, steps = 31 04:42:23 [INFO] train episode 39909: reward = -83.10, steps = 45 04:42:27 [INFO] train episode 39910: reward = -60.98, steps = 42 04:42:29 [INFO] train episode 39911: reward = -87.72, steps = 30 04:42:34 [INFO] train episode 39912: reward = -64.25, steps = 50 04:42:42 [INFO] train episode 39913: reward = -129.74, steps = 92 04:42:46 [INFO] train episode 39914: reward = -107.79, steps = 45 04:42:50 [INFO] train episode 39915: reward = -143.98, steps = 51 04:42:54 [INFO] train episode 39916: reward = -56.22, steps = 41 04:42:58 [INFO] train episode 39917: reward = -52.57, steps = 44 04:43:01 [INFO] train episode 39918: reward = -75.80, steps = 35 04:43:03 [INFO] train episode 39919: reward = -79.40, steps = 26 04:43:06 [INFO] train episode 39920: reward = -61.23, steps = 35 04:43:09 [INFO] train episode 39921: reward = -57.13, steps = 30 04:43:14 [INFO] train episode 39922: reward = -76.46, steps = 52 04:43:16 [INFO] train episode 39923: reward = -71.51, steps = 26 04:43:19 [INFO] train episode 39924: reward = -64.55, steps = 33 04:43:21 [INFO] train episode 39925: reward = -58.98, steps = 25 04:43:25 [INFO] train episode 39926: reward = -80.84, steps = 49 04:43:28 [INFO] train episode 39927: reward = -49.13, steps = 25 04:43:31 [INFO] train episode 39928: reward = -63.65, steps = 42 04:43:36 [INFO] train episode 39929: reward = -57.44, steps = 51 04:43:41 [INFO] train episode 39930: reward = -130.03, steps = 64 04:43:44 [INFO] train episode 39931: reward = -48.86, steps = 38 04:43:47 [INFO] train episode 39932: reward = -74.97, steps = 29 04:43:51 [INFO] train episode 39933: reward = -39.50, steps = 45 04:43:55 [INFO] train episode 39934: reward = -93.53, steps = 51 04:43:58 [INFO] train episode 39935: reward = -78.33, steps = 36 04:44:02 [INFO] train episode 39936: reward = -68.04, steps = 37 04:44:04 [INFO] train episode 39937: reward = -42.89, steps = 27 04:44:06 [INFO] train episode 39938: reward = -56.39, steps = 24 04:44:10 [INFO] train episode 39939: reward = -96.16, steps = 45 04:44:13 [INFO] train episode 39940: reward = -89.53, steps = 30 04:44:16 [INFO] train episode 39941: reward = -69.39, steps = 39 04:44:18 [INFO] train episode 39942: reward = -94.00, steps = 28 04:44:21 [INFO] train episode 39943: reward = -66.85, steps = 26 04:44:23 [INFO] train episode 39944: reward = -85.79, steps = 24 04:44:30 [INFO] train episode 39945: reward = -158.40, steps = 88 04:44:33 [INFO] train episode 39946: reward = -37.86, steps = 37 04:44:35 [INFO] train episode 39947: reward = -51.69, steps = 23 04:44:39 [INFO] train episode 39948: reward = -70.20, steps = 40 04:44:41 [INFO] train episode 39949: reward = -79.93, steps = 21 04:44:43 [INFO] train episode 39950: reward = -154.85, steps = 20 04:44:45 [INFO] train episode 39951: reward = -32.70, steps = 28 04:44:49 [INFO] train episode 39952: reward = -80.81, steps = 45 04:44:52 [INFO] train episode 39953: reward = -143.51, steps = 41 04:44:57 [INFO] train episode 39954: reward = -109.68, steps = 45 04:44:59 [INFO] train episode 39955: reward = -45.41, steps = 31 04:45:01 [INFO] train episode 39956: reward = -61.40, steps = 25 04:45:03 [INFO] train episode 39957: reward = -80.70, steps = 24 04:45:11 [INFO] train episode 39958: reward = -172.23, steps = 81 04:45:15 [INFO] train episode 39959: reward = -60.70, steps = 46 04:45:18 [INFO] train episode 39960: reward = -30.44, steps = 37 04:45:22 [INFO] train episode 39961: reward = -64.06, steps = 56 04:45:27 [INFO] train episode 39962: reward = -134.83, steps = 46 04:45:28 [INFO] train episode 39963: reward = -108.70, steps = 23 04:45:32 [INFO] train episode 39964: reward = -50.86, steps = 35 04:45:36 [INFO] train episode 39965: reward = -62.35, steps = 53 04:45:38 [INFO] train episode 39966: reward = -121.34, steps = 25 04:45:41 [INFO] train episode 39967: reward = -87.72, steps = 38 04:45:48 [INFO] train episode 39968: reward = -143.35, steps = 72 04:45:52 [INFO] train episode 39969: reward = -145.09, steps = 48 04:45:55 [INFO] train episode 39970: reward = -52.04, steps = 45 04:45:59 [INFO] train episode 39971: reward = -81.82, steps = 38 04:46:01 [INFO] train episode 39972: reward = -34.18, steps = 24 04:46:04 [INFO] train episode 39973: reward = -159.56, steps = 30 04:46:06 [INFO] train episode 39974: reward = -71.17, steps = 20 04:46:08 [INFO] train episode 39975: reward = -48.23, steps = 23 04:46:11 [INFO] train episode 39976: reward = -51.53, steps = 32 04:46:12 [INFO] train episode 39977: reward = -68.99, steps = 17 04:46:15 [INFO] train episode 39978: reward = -47.38, steps = 29 04:46:19 [INFO] train episode 39979: reward = -109.91, steps = 48 04:46:21 [INFO] train episode 39980: reward = -53.79, steps = 20 04:46:23 [INFO] train episode 39981: reward = -89.08, steps = 27 04:46:25 [INFO] train episode 39982: reward = -100.32, steps = 27 04:46:29 [INFO] train episode 39983: reward = -91.77, steps = 44 04:46:31 [INFO] train episode 39984: reward = -69.76, steps = 23 04:46:35 [INFO] train episode 39985: reward = -93.00, steps = 48 04:46:40 [INFO] train episode 39986: reward = -140.74, steps = 55 04:46:42 [INFO] train episode 39987: reward = -73.29, steps = 22 04:46:46 [INFO] train episode 39988: reward = -134.54, steps = 39 04:46:48 [INFO] train episode 39989: reward = -75.08, steps = 19 04:46:51 [INFO] train episode 39990: reward = -123.97, steps = 38 04:46:53 [INFO] train episode 39991: reward = -80.99, steps = 30 04:46:55 [INFO] train episode 39992: reward = -65.45, steps = 19 04:46:57 [INFO] train episode 39993: reward = -99.74, steps = 24 04:46:59 [INFO] train episode 39994: reward = -66.39, steps = 21 04:47:01 [INFO] train episode 39995: reward = -37.77, steps = 23 04:47:03 [INFO] train episode 39996: reward = -86.23, steps = 24 04:47:08 [INFO] train episode 39997: reward = -81.24, steps = 59 04:47:10 [INFO] train episode 39998: reward = -84.69, steps = 23 04:47:13 [INFO] train episode 39999: reward = -51.11, steps = 35 04:47:16 [INFO] train episode 40000: reward = -74.96, steps = 30 04:47:18 [INFO] train episode 40001: reward = -104.85, steps = 25 04:47:20 [INFO] train episode 40002: reward = -66.56, steps = 22 04:47:22 [INFO] train episode 40003: reward = -92.36, steps = 25 04:47:25 [INFO] train episode 40004: reward = -87.73, steps = 31 04:47:28 [INFO] train episode 40005: reward = -61.72, steps = 35 04:47:32 [INFO] train episode 40006: reward = -42.66, steps = 45 04:47:33 [INFO] train episode 40007: reward = -80.70, steps = 22 04:47:37 [INFO] train episode 40008: reward = -47.28, steps = 37 04:47:39 [INFO] train episode 40009: reward = -58.84, steps = 26 04:47:41 [INFO] train episode 40010: reward = -90.57, steps = 22 04:47:44 [INFO] train episode 40011: reward = -99.48, steps = 35 04:47:47 [INFO] train episode 40012: reward = -66.77, steps = 39 04:47:51 [INFO] train episode 40013: reward = -76.42, steps = 38 04:47:55 [INFO] train episode 40014: reward = -65.82, steps = 49 04:47:57 [INFO] train episode 40015: reward = -72.89, steps = 30 04:48:04 [INFO] train episode 40016: reward = -90.59, steps = 79 04:48:08 [INFO] train episode 40017: reward = -102.67, steps = 48 04:48:11 [INFO] train episode 40018: reward = -84.84, steps = 34 04:48:14 [INFO] train episode 40019: reward = -142.88, steps = 32 04:48:17 [INFO] train episode 40020: reward = -46.99, steps = 36 04:48:24 [INFO] train episode 40021: reward = -167.80, steps = 76 04:48:26 [INFO] train episode 40022: reward = -46.89, steps = 28 04:48:28 [INFO] train episode 40023: reward = -49.89, steps = 21 04:48:30 [INFO] train episode 40024: reward = -52.47, steps = 21 04:48:33 [INFO] train episode 40025: reward = -57.18, steps = 41 04:48:37 [INFO] train episode 40026: reward = -129.00, steps = 42 04:48:41 [INFO] train episode 40027: reward = -101.84, steps = 50 04:48:46 [INFO] train episode 40028: reward = -83.85, steps = 48 04:48:47 [INFO] train episode 40029: reward = -82.48, steps = 21 04:48:49 [INFO] train episode 40030: reward = -59.97, steps = 22 04:48:53 [INFO] train episode 40031: reward = -62.79, steps = 42 04:48:57 [INFO] train episode 40032: reward = -98.27, steps = 36 04:49:00 [INFO] train episode 40033: reward = -147.05, steps = 29 04:49:02 [INFO] train episode 40034: reward = -58.22, steps = 34 04:49:04 [INFO] train episode 40035: reward = -53.13, steps = 24 04:49:08 [INFO] train episode 40036: reward = -99.72, steps = 38 04:49:10 [INFO] train episode 40037: reward = -46.84, steps = 24 04:49:14 [INFO] train episode 40038: reward = -153.20, steps = 49 04:49:18 [INFO] train episode 40039: reward = -106.78, steps = 50 04:49:21 [INFO] train episode 40040: reward = -60.67, steps = 32 04:49:29 [INFO] train episode 40041: reward = -228.74, steps = 90 04:49:31 [INFO] train episode 40042: reward = -43.01, steps = 28 04:49:34 [INFO] train episode 40043: reward = -40.84, steps = 27 04:49:37 [INFO] train episode 40044: reward = -88.89, steps = 34 04:49:39 [INFO] train episode 40045: reward = -70.16, steps = 23 04:49:41 [INFO] train episode 40046: reward = -82.71, steps = 30 04:49:47 [INFO] train episode 40047: reward = -180.64, steps = 63 04:49:49 [INFO] train episode 40048: reward = -98.22, steps = 26 04:49:51 [INFO] train episode 40049: reward = -63.07, steps = 25 04:49:55 [INFO] train episode 40050: reward = -32.39, steps = 43 04:49:57 [INFO] train episode 40051: reward = -74.21, steps = 21 04:49:59 [INFO] train episode 40052: reward = -63.79, steps = 22 04:50:03 [INFO] train episode 40053: reward = -111.12, steps = 53 04:50:06 [INFO] train episode 40054: reward = -91.04, steps = 33 04:50:08 [INFO] train episode 40055: reward = -75.79, steps = 20 04:50:12 [INFO] train episode 40056: reward = -42.56, steps = 46 04:50:17 [INFO] train episode 40057: reward = -128.34, steps = 65 04:50:20 [INFO] train episode 40058: reward = -89.67, steps = 33 04:50:24 [INFO] train episode 40059: reward = -100.55, steps = 51 04:50:27 [INFO] train episode 40060: reward = -64.59, steps = 26 04:50:31 [INFO] train episode 40061: reward = -82.61, steps = 45 04:50:34 [INFO] train episode 40062: reward = -106.62, steps = 42 04:50:37 [INFO] train episode 40063: reward = -65.16, steps = 26 04:50:39 [INFO] train episode 40064: reward = -83.65, steps = 23 04:50:42 [INFO] train episode 40065: reward = -60.69, steps = 35 04:50:45 [INFO] train episode 40066: reward = -77.47, steps = 32 04:50:48 [INFO] train episode 40067: reward = -98.52, steps = 43 04:50:50 [INFO] train episode 40068: reward = -69.62, steps = 22 04:50:53 [INFO] train episode 40069: reward = -62.75, steps = 31 04:50:56 [INFO] train episode 40070: reward = -101.56, steps = 33 04:50:57 [INFO] train episode 40071: reward = -85.63, steps = 20 04:51:01 [INFO] train episode 40072: reward = -58.80, steps = 36 04:51:05 [INFO] train episode 40073: reward = -79.35, steps = 52 04:51:08 [INFO] train episode 40074: reward = -128.46, steps = 30 04:51:10 [INFO] train episode 40075: reward = -67.18, steps = 28 04:51:16 [INFO] train episode 40076: reward = -81.92, steps = 69 04:51:22 [INFO] train episode 40077: reward = -89.89, steps = 66 04:51:25 [INFO] train episode 40078: reward = -85.99, steps = 37 04:51:28 [INFO] train episode 40079: reward = -71.91, steps = 35 04:51:29 [INFO] train episode 40080: reward = -86.02, steps = 21 04:51:32 [INFO] train episode 40081: reward = -62.79, steps = 32 04:51:36 [INFO] train episode 40082: reward = -39.85, steps = 46 04:51:39 [INFO] train episode 40083: reward = -62.12, steps = 35 04:51:47 [INFO] train episode 40084: reward = -158.77, steps = 82 04:51:50 [INFO] train episode 40085: reward = -57.76, steps = 34 04:51:52 [INFO] train episode 40086: reward = -57.41, steps = 21 04:51:56 [INFO] train episode 40087: reward = -91.33, steps = 45 04:51:58 [INFO] train episode 40088: reward = -52.11, steps = 23 04:52:01 [INFO] train episode 40089: reward = -45.87, steps = 42 04:52:06 [INFO] train episode 40090: reward = -128.68, steps = 51 04:52:08 [INFO] train episode 40091: reward = -82.51, steps = 23 04:52:11 [INFO] train episode 40092: reward = -60.05, steps = 37 04:52:13 [INFO] train episode 40093: reward = -39.68, steps = 22 04:52:16 [INFO] train episode 40094: reward = -43.39, steps = 39 04:52:20 [INFO] train episode 40095: reward = -39.35, steps = 38 04:52:24 [INFO] train episode 40096: reward = -121.37, steps = 52 04:52:27 [INFO] train episode 40097: reward = -67.94, steps = 42 04:52:31 [INFO] train episode 40098: reward = -52.15, steps = 38 04:52:33 [INFO] train episode 40099: reward = -72.33, steps = 33 04:52:36 [INFO] train episode 40100: reward = -64.43, steps = 30 04:52:40 [INFO] train episode 40101: reward = -58.98, steps = 37 04:52:42 [INFO] train episode 40102: reward = -55.53, steps = 31 04:52:46 [INFO] train episode 40103: reward = -89.50, steps = 43 04:52:50 [INFO] train episode 40104: reward = -67.48, steps = 42 04:52:53 [INFO] train episode 40105: reward = -164.26, steps = 39 04:52:55 [INFO] train episode 40106: reward = -59.56, steps = 23 04:52:57 [INFO] train episode 40107: reward = -82.86, steps = 22 04:52:59 [INFO] train episode 40108: reward = -83.58, steps = 20 04:53:02 [INFO] train episode 40109: reward = -31.00, steps = 42 04:53:05 [INFO] train episode 40110: reward = -60.70, steps = 25 04:53:07 [INFO] train episode 40111: reward = -49.06, steps = 25 04:53:10 [INFO] train episode 40112: reward = -43.26, steps = 37 04:53:12 [INFO] train episode 40113: reward = -56.73, steps = 21 04:53:16 [INFO] train episode 40114: reward = -43.95, steps = 44 04:53:20 [INFO] train episode 40115: reward = -58.92, steps = 44 04:53:21 [INFO] train episode 40116: reward = -84.56, steps = 22 04:53:25 [INFO] train episode 40117: reward = -91.62, steps = 35 04:53:26 [INFO] train episode 40118: reward = -95.28, steps = 19 04:53:31 [INFO] train episode 40119: reward = -77.24, steps = 54 04:53:33 [INFO] train episode 40120: reward = -98.88, steps = 24 04:53:36 [INFO] train episode 40121: reward = -50.24, steps = 40 04:53:39 [INFO] train episode 40122: reward = -39.44, steps = 30 04:53:41 [INFO] train episode 40123: reward = -64.22, steps = 25 04:53:47 [INFO] train episode 40124: reward = -107.88, steps = 64 04:53:51 [INFO] train episode 40125: reward = -67.75, steps = 52 04:53:53 [INFO] train episode 40126: reward = -69.67, steps = 21 04:53:55 [INFO] train episode 40127: reward = -96.74, steps = 21 04:53:58 [INFO] train episode 40128: reward = -66.85, steps = 31 04:54:01 [INFO] train episode 40129: reward = -84.89, steps = 43 04:54:03 [INFO] train episode 40130: reward = -117.29, steps = 19 04:54:05 [INFO] train episode 40131: reward = -54.78, steps = 23 04:54:10 [INFO] train episode 40132: reward = -102.03, steps = 58 04:54:14 [INFO] train episode 40133: reward = -94.04, steps = 45 04:54:17 [INFO] train episode 40134: reward = -80.66, steps = 32 04:54:20 [INFO] train episode 40135: reward = -69.41, steps = 45 04:54:23 [INFO] train episode 40136: reward = -89.63, steps = 31 04:54:26 [INFO] train episode 40137: reward = -87.08, steps = 25 04:54:29 [INFO] train episode 40138: reward = -119.79, steps = 31 04:54:31 [INFO] train episode 40139: reward = -75.05, steps = 25 04:54:34 [INFO] train episode 40140: reward = -50.56, steps = 34 04:54:36 [INFO] train episode 40141: reward = -67.03, steps = 23 04:54:39 [INFO] train episode 40142: reward = -107.88, steps = 22 04:54:42 [INFO] train episode 40143: reward = -97.82, steps = 36 04:54:46 [INFO] train episode 40144: reward = -72.30, steps = 43 04:54:48 [INFO] train episode 40145: reward = -59.42, steps = 30 04:54:50 [INFO] train episode 40146: reward = -55.56, steps = 22 04:54:53 [INFO] train episode 40147: reward = -49.79, steps = 33 04:54:56 [INFO] train episode 40148: reward = -94.61, steps = 34 04:55:00 [INFO] train episode 40149: reward = -59.40, steps = 47 04:55:02 [INFO] train episode 40150: reward = -62.24, steps = 27 04:55:06 [INFO] train episode 40151: reward = -68.24, steps = 40 04:55:10 [INFO] train episode 40152: reward = -91.77, steps = 57 04:55:13 [INFO] train episode 40153: reward = -54.04, steps = 33 04:55:17 [INFO] train episode 40154: reward = -111.01, steps = 36 04:55:20 [INFO] train episode 40155: reward = -33.07, steps = 36 04:55:23 [INFO] train episode 40156: reward = -116.61, steps = 36 04:55:25 [INFO] train episode 40157: reward = -79.02, steps = 24 04:55:27 [INFO] train episode 40158: reward = -49.41, steps = 21 04:55:30 [INFO] train episode 40159: reward = -72.87, steps = 35 04:55:32 [INFO] train episode 40160: reward = -75.03, steps = 25 04:55:35 [INFO] train episode 40161: reward = -90.65, steps = 38 04:55:39 [INFO] train episode 40162: reward = -83.63, steps = 38 04:55:41 [INFO] train episode 40163: reward = -129.08, steps = 24 04:55:45 [INFO] train episode 40164: reward = -116.27, steps = 52 04:55:47 [INFO] train episode 40165: reward = -85.48, steps = 23 04:55:49 [INFO] train episode 40166: reward = -57.39, steps = 22 04:55:51 [INFO] train episode 40167: reward = -55.48, steps = 19 04:55:53 [INFO] train episode 40168: reward = -49.72, steps = 20 04:55:54 [INFO] train episode 40169: reward = -100.39, steps = 18 04:55:57 [INFO] train episode 40170: reward = -79.94, steps = 27 04:56:00 [INFO] train episode 40171: reward = -63.98, steps = 42 04:56:03 [INFO] train episode 40172: reward = -84.99, steps = 34 04:56:07 [INFO] train episode 40173: reward = -89.70, steps = 40 04:56:10 [INFO] train episode 40174: reward = -38.47, steps = 42 04:56:14 [INFO] train episode 40175: reward = -101.73, steps = 39 04:56:16 [INFO] train episode 40176: reward = -70.64, steps = 23 04:56:18 [INFO] train episode 40177: reward = -73.72, steps = 24 04:56:21 [INFO] train episode 40178: reward = -159.05, steps = 37 04:56:24 [INFO] train episode 40179: reward = -86.55, steps = 39 04:56:26 [INFO] train episode 40180: reward = -70.75, steps = 19 04:56:30 [INFO] train episode 40181: reward = -84.83, steps = 45 04:56:33 [INFO] train episode 40182: reward = -106.86, steps = 30 04:56:37 [INFO] train episode 40183: reward = -70.26, steps = 44 04:56:41 [INFO] train episode 40184: reward = -89.15, steps = 50 04:56:43 [INFO] train episode 40185: reward = -76.62, steps = 30 04:56:46 [INFO] train episode 40186: reward = -82.42, steps = 30 04:56:48 [INFO] train episode 40187: reward = -76.61, steps = 22 04:56:50 [INFO] train episode 40188: reward = -92.24, steps = 23 04:56:54 [INFO] train episode 40189: reward = -111.76, steps = 47 04:56:57 [INFO] train episode 40190: reward = -53.50, steps = 36 04:57:00 [INFO] train episode 40191: reward = -53.92, steps = 33 04:57:09 [INFO] train episode 40192: reward = -188.31, steps = 97 04:57:12 [INFO] train episode 40193: reward = -94.39, steps = 41 04:57:14 [INFO] train episode 40194: reward = -45.86, steps = 17 04:57:16 [INFO] train episode 40195: reward = -141.83, steps = 26 04:57:20 [INFO] train episode 40196: reward = -90.53, steps = 49 04:57:25 [INFO] train episode 40197: reward = -112.72, steps = 59 04:57:29 [INFO] train episode 40198: reward = -104.86, steps = 41 04:57:32 [INFO] train episode 40199: reward = -97.76, steps = 36 04:57:34 [INFO] train episode 40200: reward = -74.78, steps = 22 04:57:37 [INFO] train episode 40201: reward = -70.54, steps = 26 04:57:40 [INFO] train episode 40202: reward = -37.91, steps = 38 04:57:45 [INFO] train episode 40203: reward = -80.30, steps = 50 04:57:49 [INFO] train episode 40204: reward = -109.30, steps = 49 04:57:50 [INFO] train episode 40205: reward = -62.93, steps = 20 04:57:54 [INFO] train episode 40206: reward = -99.30, steps = 41 04:57:56 [INFO] train episode 40207: reward = -62.81, steps = 26 04:57:59 [INFO] train episode 40208: reward = -72.75, steps = 31 04:58:01 [INFO] train episode 40209: reward = -141.90, steps = 26 04:58:04 [INFO] train episode 40210: reward = -48.62, steps = 32 04:58:06 [INFO] train episode 40211: reward = -95.91, steps = 30 04:58:11 [INFO] train episode 40212: reward = -118.20, steps = 46 04:58:14 [INFO] train episode 40213: reward = -41.58, steps = 44 04:58:18 [INFO] train episode 40214: reward = -43.91, steps = 49 04:58:23 [INFO] train episode 40215: reward = -74.33, steps = 51 04:58:26 [INFO] train episode 40216: reward = -124.67, steps = 34 04:58:28 [INFO] train episode 40217: reward = -70.54, steps = 25 04:58:33 [INFO] train episode 40218: reward = -31.07, steps = 55 04:58:35 [INFO] train episode 40219: reward = -79.32, steps = 29 04:58:40 [INFO] train episode 40220: reward = -99.84, steps = 59 04:58:44 [INFO] train episode 40221: reward = -76.10, steps = 39 04:58:48 [INFO] train episode 40222: reward = -105.52, steps = 52 04:58:54 [INFO] train episode 40223: reward = -121.56, steps = 67 04:58:56 [INFO] train episode 40224: reward = -85.05, steps = 24 04:59:02 [INFO] train episode 40225: reward = -128.08, steps = 72 04:59:04 [INFO] train episode 40226: reward = -63.87, steps = 20 04:59:06 [INFO] train episode 40227: reward = -52.35, steps = 24 04:59:08 [INFO] train episode 40228: reward = -80.92, steps = 25 04:59:11 [INFO] train episode 40229: reward = -94.33, steps = 37 04:59:15 [INFO] train episode 40230: reward = -114.01, steps = 39 04:59:19 [INFO] train episode 40231: reward = -80.53, steps = 48 04:59:21 [INFO] train episode 40232: reward = -74.71, steps = 20 04:59:24 [INFO] train episode 40233: reward = -66.32, steps = 37 04:59:27 [INFO] train episode 40234: reward = -85.77, steps = 41 04:59:30 [INFO] train episode 40235: reward = -66.36, steps = 21 04:59:33 [INFO] train episode 40236: reward = -50.49, steps = 40 04:59:37 [INFO] train episode 40237: reward = -34.53, steps = 47 04:59:41 [INFO] train episode 40238: reward = -123.02, steps = 48 04:59:42 [INFO] train episode 40239: reward = -74.95, steps = 17 04:59:46 [INFO] train episode 40240: reward = -75.73, steps = 35 04:59:47 [INFO] train episode 40241: reward = -63.08, steps = 20 04:59:49 [INFO] train episode 40242: reward = -111.11, steps = 21 04:59:51 [INFO] train episode 40243: reward = -72.98, steps = 17 04:59:55 [INFO] train episode 40244: reward = -132.92, steps = 55 04:59:59 [INFO] train episode 40245: reward = -52.82, steps = 47 05:00:03 [INFO] train episode 40246: reward = -47.63, steps = 36 05:00:05 [INFO] train episode 40247: reward = -60.60, steps = 30 05:00:08 [INFO] train episode 40248: reward = -89.26, steps = 34 05:00:10 [INFO] train episode 40249: reward = -79.89, steps = 23 05:00:12 [INFO] train episode 40250: reward = -74.77, steps = 19 05:00:13 [INFO] train episode 40251: reward = -71.63, steps = 20 05:00:17 [INFO] train episode 40252: reward = -55.90, steps = 35 05:00:22 [INFO] train episode 40253: reward = -111.39, steps = 55 05:00:26 [INFO] train episode 40254: reward = -83.51, steps = 41 05:00:28 [INFO] train episode 40255: reward = -76.04, steps = 32 05:00:31 [INFO] train episode 40256: reward = -51.88, steps = 38 05:00:35 [INFO] train episode 40257: reward = -71.14, steps = 37 05:00:37 [INFO] train episode 40258: reward = -85.36, steps = 25 05:00:39 [INFO] train episode 40259: reward = -57.95, steps = 19 05:00:43 [INFO] train episode 40260: reward = -51.60, steps = 48 05:00:45 [INFO] train episode 40261: reward = -88.77, steps = 26 05:00:47 [INFO] train episode 40262: reward = -56.52, steps = 24 05:00:51 [INFO] train episode 40263: reward = -63.41, steps = 36 05:00:54 [INFO] train episode 40264: reward = -47.46, steps = 36 05:00:56 [INFO] train episode 40265: reward = -55.62, steps = 25 05:00:59 [INFO] train episode 40266: reward = -51.10, steps = 32 05:01:00 [INFO] train episode 40267: reward = -59.21, steps = 21 05:01:05 [INFO] train episode 40268: reward = -78.79, steps = 44 05:01:06 [INFO] train episode 40269: reward = -59.28, steps = 22 05:01:10 [INFO] train episode 40270: reward = -86.12, steps = 37 05:01:13 [INFO] train episode 40271: reward = -88.02, steps = 47 05:01:16 [INFO] train episode 40272: reward = -56.74, steps = 33 05:01:20 [INFO] train episode 40273: reward = -115.66, steps = 41 05:01:22 [INFO] train episode 40274: reward = -71.17, steps = 20 05:01:25 [INFO] train episode 40275: reward = -70.66, steps = 38 05:01:29 [INFO] train episode 40276: reward = -78.55, steps = 49 05:01:31 [INFO] train episode 40277: reward = -62.45, steps = 27 05:01:33 [INFO] train episode 40278: reward = -121.87, steps = 22 05:01:37 [INFO] train episode 40279: reward = -90.05, steps = 39 05:01:39 [INFO] train episode 40280: reward = -53.80, steps = 23 05:01:42 [INFO] train episode 40281: reward = -22.42, steps = 35 05:01:47 [INFO] train episode 40282: reward = -157.81, steps = 64 05:01:50 [INFO] train episode 40283: reward = -48.72, steps = 34 05:01:53 [INFO] train episode 40284: reward = -70.19, steps = 26 05:01:54 [INFO] train episode 40285: reward = -39.65, steps = 18 05:01:56 [INFO] train episode 40286: reward = -88.74, steps = 17 05:01:59 [INFO] train episode 40287: reward = -81.41, steps = 33 05:02:01 [INFO] train episode 40288: reward = -65.96, steps = 34 05:02:05 [INFO] train episode 40289: reward = -72.16, steps = 43 05:02:09 [INFO] train episode 40290: reward = -79.96, steps = 38 05:02:11 [INFO] train episode 40291: reward = -61.28, steps = 31 05:02:14 [INFO] train episode 40292: reward = -87.54, steps = 36 05:02:16 [INFO] train episode 40293: reward = -51.27, steps = 25 05:02:20 [INFO] train episode 40294: reward = -85.87, steps = 44 05:02:22 [INFO] train episode 40295: reward = -55.84, steps = 22 05:02:24 [INFO] train episode 40296: reward = -79.40, steps = 21 05:02:29 [INFO] train episode 40297: reward = -73.62, steps = 55 05:02:32 [INFO] train episode 40298: reward = -51.12, steps = 41 05:02:36 [INFO] train episode 40299: reward = -30.64, steps = 40 05:02:38 [INFO] train episode 40300: reward = -49.85, steps = 29 05:02:42 [INFO] train episode 40301: reward = -84.55, steps = 39 05:02:44 [INFO] train episode 40302: reward = -125.01, steps = 27 05:02:48 [INFO] train episode 40303: reward = -101.80, steps = 44 05:02:50 [INFO] train episode 40304: reward = -65.94, steps = 27 05:02:52 [INFO] train episode 40305: reward = -61.02, steps = 19 05:02:57 [INFO] train episode 40306: reward = -83.97, steps = 49 05:03:01 [INFO] train episode 40307: reward = -122.37, steps = 54 05:03:04 [INFO] train episode 40308: reward = -96.20, steps = 30 05:03:07 [INFO] train episode 40309: reward = -110.24, steps = 40 05:03:10 [INFO] train episode 40310: reward = -50.97, steps = 34 05:03:13 [INFO] train episode 40311: reward = -95.85, steps = 25 05:03:17 [INFO] train episode 40312: reward = -95.26, steps = 40 05:03:19 [INFO] train episode 40313: reward = -45.42, steps = 30 05:03:21 [INFO] train episode 40314: reward = -57.69, steps = 18 05:03:24 [INFO] train episode 40315: reward = -82.26, steps = 42 05:03:27 [INFO] train episode 40316: reward = -71.39, steps = 29 05:03:31 [INFO] train episode 40317: reward = -66.83, steps = 43 05:03:33 [INFO] train episode 40318: reward = -64.25, steps = 32 05:03:37 [INFO] train episode 40319: reward = -24.01, steps = 48 05:03:40 [INFO] train episode 40320: reward = -72.56, steps = 27 05:03:43 [INFO] train episode 40321: reward = -81.33, steps = 34 05:03:47 [INFO] train episode 40322: reward = -120.17, steps = 47 05:03:51 [INFO] train episode 40323: reward = -137.49, steps = 42 05:03:54 [INFO] train episode 40324: reward = -68.68, steps = 36 05:03:57 [INFO] train episode 40325: reward = -153.90, steps = 40 05:04:00 [INFO] train episode 40326: reward = -95.04, steps = 30 05:04:02 [INFO] train episode 40327: reward = -96.12, steps = 20 05:04:07 [INFO] train episode 40328: reward = -100.92, steps = 62 05:04:10 [INFO] train episode 40329: reward = -114.08, steps = 35 05:04:13 [INFO] train episode 40330: reward = -115.76, steps = 39 05:04:15 [INFO] train episode 40331: reward = -62.28, steps = 22 05:04:19 [INFO] train episode 40332: reward = -140.65, steps = 43 05:04:21 [INFO] train episode 40333: reward = -61.69, steps = 19 05:04:23 [INFO] train episode 40334: reward = -70.03, steps = 31 05:04:25 [INFO] train episode 40335: reward = -55.86, steps = 24 05:04:27 [INFO] train episode 40336: reward = -56.40, steps = 17 05:04:29 [INFO] train episode 40337: reward = -112.59, steps = 33 05:04:32 [INFO] train episode 40338: reward = -67.14, steps = 29 05:04:35 [INFO] train episode 40339: reward = -67.05, steps = 28 05:04:38 [INFO] train episode 40340: reward = -106.77, steps = 35 05:04:40 [INFO] train episode 40341: reward = -30.36, steps = 23 05:04:41 [INFO] train episode 40342: reward = -55.56, steps = 20 05:04:44 [INFO] train episode 40343: reward = -79.67, steps = 28 05:04:46 [INFO] train episode 40344: reward = -77.42, steps = 31 05:04:50 [INFO] train episode 40345: reward = -87.25, steps = 34 05:04:51 [INFO] train episode 40346: reward = -67.24, steps = 20 05:04:55 [INFO] train episode 40347: reward = -70.06, steps = 41 05:04:58 [INFO] train episode 40348: reward = -81.40, steps = 44 05:05:01 [INFO] train episode 40349: reward = -61.31, steps = 25 05:05:05 [INFO] train episode 40350: reward = -44.73, steps = 46 05:05:07 [INFO] train episode 40351: reward = -77.27, steps = 20 05:05:11 [INFO] train episode 40352: reward = -79.34, steps = 46 05:05:13 [INFO] train episode 40353: reward = -111.34, steps = 27 05:05:15 [INFO] train episode 40354: reward = -68.41, steps = 23 05:05:19 [INFO] train episode 40355: reward = -93.11, steps = 40 05:05:21 [INFO] train episode 40356: reward = -38.64, steps = 27 05:05:24 [INFO] train episode 40357: reward = -93.34, steps = 35 05:05:28 [INFO] train episode 40358: reward = -69.67, steps = 43 05:05:31 [INFO] train episode 40359: reward = -67.55, steps = 39 05:05:35 [INFO] train episode 40360: reward = -123.91, steps = 47 05:05:39 [INFO] train episode 40361: reward = -82.56, steps = 47 05:05:42 [INFO] train episode 40362: reward = -57.16, steps = 32 05:05:47 [INFO] train episode 40363: reward = -207.46, steps = 58 05:05:50 [INFO] train episode 40364: reward = -65.34, steps = 37 05:05:52 [INFO] train episode 40365: reward = -66.10, steps = 18 05:05:54 [INFO] train episode 40366: reward = -59.64, steps = 30 05:05:58 [INFO] train episode 40367: reward = -42.03, steps = 43 05:06:00 [INFO] train episode 40368: reward = -64.87, steps = 22 05:06:04 [INFO] train episode 40369: reward = -112.71, steps = 42 05:06:06 [INFO] train episode 40370: reward = -67.93, steps = 17 05:06:10 [INFO] train episode 40371: reward = -73.49, steps = 42 05:06:13 [INFO] train episode 40372: reward = -52.74, steps = 35 05:06:15 [INFO] train episode 40373: reward = -86.87, steps = 31 05:06:17 [INFO] train episode 40374: reward = -75.25, steps = 22 05:06:19 [INFO] train episode 40375: reward = -53.37, steps = 26 05:06:23 [INFO] train episode 40376: reward = -103.54, steps = 34 05:06:26 [INFO] train episode 40377: reward = -65.39, steps = 36 05:06:28 [INFO] train episode 40378: reward = -50.59, steps = 33 05:06:31 [INFO] train episode 40379: reward = -82.35, steps = 26 05:06:34 [INFO] train episode 40380: reward = -63.35, steps = 40 05:06:36 [INFO] train episode 40381: reward = -92.12, steps = 24 05:06:39 [INFO] train episode 40382: reward = -102.31, steps = 25 05:06:41 [INFO] train episode 40383: reward = -43.22, steps = 28 05:06:44 [INFO] train episode 40384: reward = -86.37, steps = 31 05:06:47 [INFO] train episode 40385: reward = -44.61, steps = 39 05:06:49 [INFO] train episode 40386: reward = -122.17, steps = 27 05:06:52 [INFO] train episode 40387: reward = -49.66, steps = 35 05:06:55 [INFO] train episode 40388: reward = -44.03, steps = 22 05:06:57 [INFO] train episode 40389: reward = -62.17, steps = 29 05:07:00 [INFO] train episode 40390: reward = -51.69, steps = 32 05:07:03 [INFO] train episode 40391: reward = -50.53, steps = 34 05:07:05 [INFO] train episode 40392: reward = -52.39, steps = 23 05:07:07 [INFO] train episode 40393: reward = -61.90, steps = 24 05:07:09 [INFO] train episode 40394: reward = -121.43, steps = 25 05:07:11 [INFO] train episode 40395: reward = -64.62, steps = 25 05:07:14 [INFO] train episode 40396: reward = -134.09, steps = 25 05:07:17 [INFO] train episode 40397: reward = -52.16, steps = 44 05:07:19 [INFO] train episode 40398: reward = -61.83, steps = 20 05:07:22 [INFO] train episode 40399: reward = -97.83, steps = 32 05:07:26 [INFO] train episode 40400: reward = -55.06, steps = 42 05:07:28 [INFO] train episode 40401: reward = -74.44, steps = 25 05:07:29 [INFO] train episode 40402: reward = -47.92, steps = 17 05:07:33 [INFO] train episode 40403: reward = -119.23, steps = 40 05:07:35 [INFO] train episode 40404: reward = -78.93, steps = 34 05:07:39 [INFO] train episode 40405: reward = -89.43, steps = 43 05:07:43 [INFO] train episode 40406: reward = -67.29, steps = 45 05:07:45 [INFO] train episode 40407: reward = -76.74, steps = 26 05:07:50 [INFO] train episode 40408: reward = -128.93, steps = 59 05:07:52 [INFO] train episode 40409: reward = -72.69, steps = 21 05:07:55 [INFO] train episode 40410: reward = -107.61, steps = 32 05:07:59 [INFO] train episode 40411: reward = -74.59, steps = 44 05:08:01 [INFO] train episode 40412: reward = -68.59, steps = 21 05:08:03 [INFO] train episode 40413: reward = -68.22, steps = 31 05:08:05 [INFO] train episode 40414: reward = -60.30, steps = 23 05:08:08 [INFO] train episode 40415: reward = -64.68, steps = 35 05:08:11 [INFO] train episode 40416: reward = -83.57, steps = 27 05:08:14 [INFO] train episode 40417: reward = -89.68, steps = 29 05:08:16 [INFO] train episode 40418: reward = -67.61, steps = 32 05:08:19 [INFO] train episode 40419: reward = -80.79, steps = 30 05:08:23 [INFO] train episode 40420: reward = -156.35, steps = 48 05:08:29 [INFO] train episode 40421: reward = -197.13, steps = 67 05:08:31 [INFO] train episode 40422: reward = -110.11, steps = 30 05:08:33 [INFO] train episode 40423: reward = -101.89, steps = 23 05:08:37 [INFO] train episode 40424: reward = -44.66, steps = 38 05:08:40 [INFO] train episode 40425: reward = -90.56, steps = 38 05:08:42 [INFO] train episode 40426: reward = -124.35, steps = 31 05:08:47 [INFO] train episode 40427: reward = -63.66, steps = 51 05:08:50 [INFO] train episode 40428: reward = -147.49, steps = 37 05:08:54 [INFO] train episode 40429: reward = -55.53, steps = 37 05:08:59 [INFO] train episode 40430: reward = -60.40, steps = 51 05:09:03 [INFO] train episode 40431: reward = -118.05, steps = 46 05:09:07 [INFO] train episode 40432: reward = -101.73, steps = 43 05:09:13 [INFO] train episode 40433: reward = -162.78, steps = 76 05:09:16 [INFO] train episode 40434: reward = -98.87, steps = 32 05:09:18 [INFO] train episode 40435: reward = -125.65, steps = 21 05:09:22 [INFO] train episode 40436: reward = -107.02, steps = 47 05:09:24 [INFO] train episode 40437: reward = -88.14, steps = 26 05:09:27 [INFO] train episode 40438: reward = -156.50, steps = 35 05:09:30 [INFO] train episode 40439: reward = -56.97, steps = 32 05:09:32 [INFO] train episode 40440: reward = -107.08, steps = 28 05:09:36 [INFO] train episode 40441: reward = -120.03, steps = 39 05:09:38 [INFO] train episode 40442: reward = -54.38, steps = 17 05:09:40 [INFO] train episode 40443: reward = -103.59, steps = 24 05:09:42 [INFO] train episode 40444: reward = -78.65, steps = 28 05:09:44 [INFO] train episode 40445: reward = -50.72, steps = 27 05:09:47 [INFO] train episode 40446: reward = -150.79, steps = 28 05:09:49 [INFO] train episode 40447: reward = -60.39, steps = 22 05:09:51 [INFO] train episode 40448: reward = -81.91, steps = 23 05:09:54 [INFO] train episode 40449: reward = -75.86, steps = 37 05:09:58 [INFO] train episode 40450: reward = -37.06, steps = 45 05:09:59 [INFO] train episode 40451: reward = -49.47, steps = 18 05:10:01 [INFO] train episode 40452: reward = -81.94, steps = 19 05:10:04 [INFO] train episode 40453: reward = -68.51, steps = 30 05:10:08 [INFO] train episode 40454: reward = -108.66, steps = 51 05:10:10 [INFO] train episode 40455: reward = -72.88, steps = 20 05:10:13 [INFO] train episode 40456: reward = -87.60, steps = 36 05:10:15 [INFO] train episode 40457: reward = -108.36, steps = 22 05:10:17 [INFO] train episode 40458: reward = -42.54, steps = 19 05:10:19 [INFO] train episode 40459: reward = -47.36, steps = 32 05:10:23 [INFO] train episode 40460: reward = -59.11, steps = 39 05:10:27 [INFO] train episode 40461: reward = -96.11, steps = 43 05:10:28 [INFO] train episode 40462: reward = -48.17, steps = 19 05:10:32 [INFO] train episode 40463: reward = -81.21, steps = 38 05:10:35 [INFO] train episode 40464: reward = -99.73, steps = 39 05:10:38 [INFO] train episode 40465: reward = -75.30, steps = 28 05:10:41 [INFO] train episode 40466: reward = -22.57, steps = 40 05:10:44 [INFO] train episode 40467: reward = -120.29, steps = 29 05:10:47 [INFO] train episode 40468: reward = -67.76, steps = 40 05:10:49 [INFO] train episode 40469: reward = -97.72, steps = 22 05:10:54 [INFO] train episode 40470: reward = -125.87, steps = 58 05:10:58 [INFO] train episode 40471: reward = -58.27, steps = 41 05:11:00 [INFO] train episode 40472: reward = -67.50, steps = 31 05:11:03 [INFO] train episode 40473: reward = -50.61, steps = 31 05:11:06 [INFO] train episode 40474: reward = -74.58, steps = 36 05:11:08 [INFO] train episode 40475: reward = -88.78, steps = 19 05:11:11 [INFO] train episode 40476: reward = -73.29, steps = 40 05:11:14 [INFO] train episode 40477: reward = -59.93, steps = 27 05:11:17 [INFO] train episode 40478: reward = -89.05, steps = 35 05:11:18 [INFO] train episode 40479: reward = -81.01, steps = 19 05:11:23 [INFO] train episode 40480: reward = -107.15, steps = 57 05:11:25 [INFO] train episode 40481: reward = -82.71, steps = 20 05:11:29 [INFO] train episode 40482: reward = -106.32, steps = 47 05:11:31 [INFO] train episode 40483: reward = -62.09, steps = 23 05:11:34 [INFO] train episode 40484: reward = -98.25, steps = 37 05:11:37 [INFO] train episode 40485: reward = -107.12, steps = 27 05:11:40 [INFO] train episode 40486: reward = -78.40, steps = 41 05:11:42 [INFO] train episode 40487: reward = -85.13, steps = 18 05:11:47 [INFO] train episode 40488: reward = -75.62, steps = 54 05:11:50 [INFO] train episode 40489: reward = -86.85, steps = 32 05:11:52 [INFO] train episode 40490: reward = -114.39, steps = 27 05:11:55 [INFO] train episode 40491: reward = -72.79, steps = 28 05:11:59 [INFO] train episode 40492: reward = -58.82, steps = 46 05:12:02 [INFO] train episode 40493: reward = -72.20, steps = 40 05:12:04 [INFO] train episode 40494: reward = -71.39, steps = 19 05:12:06 [INFO] train episode 40495: reward = -64.49, steps = 25 05:12:08 [INFO] train episode 40496: reward = -114.59, steps = 22 05:12:12 [INFO] train episode 40497: reward = -93.77, steps = 39 05:12:14 [INFO] train episode 40498: reward = -90.80, steps = 31 05:12:17 [INFO] train episode 40499: reward = -107.70, steps = 31 05:12:19 [INFO] train episode 40500: reward = -73.68, steps = 23 05:12:22 [INFO] train episode 40501: reward = -119.67, steps = 46 05:12:25 [INFO] train episode 40502: reward = -57.82, steps = 25 05:12:28 [INFO] train episode 40503: reward = -55.04, steps = 33 05:12:31 [INFO] train episode 40504: reward = -89.02, steps = 42 05:12:33 [INFO] train episode 40505: reward = -77.17, steps = 20 05:12:37 [INFO] train episode 40506: reward = -128.95, steps = 49 05:12:39 [INFO] train episode 40507: reward = -68.11, steps = 19 05:12:41 [INFO] train episode 40508: reward = -50.72, steps = 27 05:12:44 [INFO] train episode 40509: reward = -84.94, steps = 21 05:12:46 [INFO] train episode 40510: reward = -70.90, steps = 30 05:12:49 [INFO] train episode 40511: reward = -83.49, steps = 30 05:12:51 [INFO] train episode 40512: reward = -49.44, steps = 25 05:12:53 [INFO] train episode 40513: reward = -111.48, steps = 21 05:12:57 [INFO] train episode 40514: reward = -117.77, steps = 45 05:12:59 [INFO] train episode 40515: reward = -68.26, steps = 30 05:13:03 [INFO] train episode 40516: reward = -83.11, steps = 37 05:13:05 [INFO] train episode 40517: reward = -91.33, steps = 27 05:13:08 [INFO] train episode 40518: reward = -58.12, steps = 36 05:13:12 [INFO] train episode 40519: reward = -112.24, steps = 46 05:13:17 [INFO] train episode 40520: reward = -198.79, steps = 55 05:13:19 [INFO] train episode 40521: reward = -135.44, steps = 34 05:13:22 [INFO] train episode 40522: reward = -120.22, steps = 36 05:13:25 [INFO] train episode 40523: reward = -93.11, steps = 33 05:13:28 [INFO] train episode 40524: reward = -123.84, steps = 30 05:13:31 [INFO] train episode 40525: reward = -93.68, steps = 32 05:13:33 [INFO] train episode 40526: reward = -59.06, steps = 22 05:13:35 [INFO] train episode 40527: reward = -65.60, steps = 25 05:13:37 [INFO] train episode 40528: reward = -51.78, steps = 23 05:13:40 [INFO] train episode 40529: reward = -99.96, steps = 34 05:13:42 [INFO] train episode 40530: reward = -108.37, steps = 26 05:13:45 [INFO] train episode 40531: reward = -122.40, steps = 29 05:13:47 [INFO] train episode 40532: reward = -147.77, steps = 27 05:13:50 [INFO] train episode 40533: reward = -39.60, steps = 34 05:13:53 [INFO] train episode 40534: reward = -59.71, steps = 29 05:13:56 [INFO] train episode 40535: reward = -103.75, steps = 33 05:13:58 [INFO] train episode 40536: reward = -130.56, steps = 27 05:14:00 [INFO] train episode 40537: reward = -88.59, steps = 23 05:14:03 [INFO] train episode 40538: reward = -107.32, steps = 37 05:14:05 [INFO] train episode 40539: reward = -94.11, steps = 19 05:14:07 [INFO] train episode 40540: reward = -50.86, steps = 21 05:14:08 [INFO] train episode 40541: reward = -85.75, steps = 19 05:14:10 [INFO] train episode 40542: reward = -83.18, steps = 23 05:14:13 [INFO] train episode 40543: reward = -102.02, steps = 30 05:14:15 [INFO] train episode 40544: reward = -96.04, steps = 26 05:14:19 [INFO] train episode 40545: reward = -57.54, steps = 43 05:14:21 [INFO] train episode 40546: reward = -81.26, steps = 22 05:14:23 [INFO] train episode 40547: reward = -89.21, steps = 22 05:14:25 [INFO] train episode 40548: reward = -88.73, steps = 26 05:14:31 [INFO] train episode 40549: reward = -119.94, steps = 72 05:14:34 [INFO] train episode 40550: reward = -84.50, steps = 36 05:14:39 [INFO] train episode 40551: reward = -108.56, steps = 45 05:14:41 [INFO] train episode 40552: reward = -79.58, steps = 20 05:14:43 [INFO] train episode 40553: reward = -81.06, steps = 21 05:14:44 [INFO] train episode 40554: reward = -61.86, steps = 19 05:14:47 [INFO] train episode 40555: reward = -89.35, steps = 25 05:14:51 [INFO] train episode 40556: reward = -102.41, steps = 42 05:14:54 [INFO] train episode 40557: reward = -76.40, steps = 42 05:14:57 [INFO] train episode 40558: reward = -88.06, steps = 30 05:15:00 [INFO] train episode 40559: reward = -151.48, steps = 37 05:15:03 [INFO] train episode 40560: reward = -59.50, steps = 34 05:15:05 [INFO] train episode 40561: reward = -64.26, steps = 28 05:15:08 [INFO] train episode 40562: reward = -88.37, steps = 25 05:15:11 [INFO] train episode 40563: reward = -150.56, steps = 42 05:15:13 [INFO] train episode 40564: reward = -60.65, steps = 18 05:15:17 [INFO] train episode 40565: reward = -118.37, steps = 48 05:15:19 [INFO] train episode 40566: reward = -46.38, steps = 30 05:15:23 [INFO] train episode 40567: reward = -91.82, steps = 37 05:15:24 [INFO] train episode 40568: reward = -68.19, steps = 20 05:15:27 [INFO] train episode 40569: reward = -63.75, steps = 27 05:15:31 [INFO] train episode 40570: reward = -63.80, steps = 57 05:15:33 [INFO] train episode 40571: reward = -148.40, steps = 20 05:15:37 [INFO] train episode 40572: reward = -77.42, steps = 48 05:15:41 [INFO] train episode 40573: reward = -102.67, steps = 40 05:15:44 [INFO] train episode 40574: reward = -126.05, steps = 44 05:15:47 [INFO] train episode 40575: reward = -97.39, steps = 27 05:15:50 [INFO] train episode 40576: reward = -98.39, steps = 44 05:15:53 [INFO] train episode 40577: reward = -50.04, steps = 31 05:15:57 [INFO] train episode 40578: reward = -81.76, steps = 42 05:15:59 [INFO] train episode 40579: reward = -67.67, steps = 23 05:16:01 [INFO] train episode 40580: reward = -63.09, steps = 27 05:16:03 [INFO] train episode 40581: reward = -68.59, steps = 25 05:16:06 [INFO] train episode 40582: reward = -80.72, steps = 26 05:16:09 [INFO] train episode 40583: reward = -52.77, steps = 35 05:16:11 [INFO] train episode 40584: reward = -58.96, steps = 21 05:16:13 [INFO] train episode 40585: reward = -60.71, steps = 22 05:16:16 [INFO] train episode 40586: reward = -40.25, steps = 43 05:16:20 [INFO] train episode 40587: reward = -58.62, steps = 48 05:16:24 [INFO] train episode 40588: reward = -97.66, steps = 36 05:16:26 [INFO] train episode 40589: reward = -41.10, steps = 24 05:16:28 [INFO] train episode 40590: reward = -118.26, steps = 22 05:16:30 [INFO] train episode 40591: reward = -64.30, steps = 22 05:16:34 [INFO] train episode 40592: reward = -134.14, steps = 49 05:16:35 [INFO] train episode 40593: reward = -81.75, steps = 19 05:16:37 [INFO] train episode 40594: reward = -110.70, steps = 23 05:16:40 [INFO] train episode 40595: reward = -62.99, steps = 30 05:16:43 [INFO] train episode 40596: reward = -83.51, steps = 37 05:16:45 [INFO] train episode 40597: reward = -70.55, steps = 22 05:16:47 [INFO] train episode 40598: reward = -46.33, steps = 20 05:16:49 [INFO] train episode 40599: reward = -73.03, steps = 24 05:16:52 [INFO] train episode 40600: reward = -88.56, steps = 40 05:16:56 [INFO] train episode 40601: reward = -68.32, steps = 38 05:16:58 [INFO] train episode 40602: reward = -85.09, steps = 20 05:17:01 [INFO] train episode 40603: reward = -60.00, steps = 43 05:17:04 [INFO] train episode 40604: reward = -112.15, steps = 29 05:17:07 [INFO] train episode 40605: reward = -67.07, steps = 39 05:17:11 [INFO] train episode 40606: reward = -129.18, steps = 38 05:17:12 [INFO] train episode 40607: reward = -97.39, steps = 20 05:17:15 [INFO] train episode 40608: reward = -104.94, steps = 27 05:17:19 [INFO] train episode 40609: reward = -59.25, steps = 52 05:17:20 [INFO] train episode 40610: reward = -59.19, steps = 15 05:17:22 [INFO] train episode 40611: reward = -128.56, steps = 19 05:17:24 [INFO] train episode 40612: reward = -62.97, steps = 24 05:17:26 [INFO] train episode 40613: reward = -78.62, steps = 19 05:17:30 [INFO] train episode 40614: reward = -81.74, steps = 37 05:17:33 [INFO] train episode 40615: reward = -63.02, steps = 31 05:17:35 [INFO] train episode 40616: reward = -84.96, steps = 27 05:17:37 [INFO] train episode 40617: reward = -67.90, steps = 21 05:17:39 [INFO] train episode 40618: reward = -79.07, steps = 24 05:17:43 [INFO] train episode 40619: reward = -86.93, steps = 46 05:17:47 [INFO] train episode 40620: reward = -121.31, steps = 48 05:17:49 [INFO] train episode 40621: reward = -55.00, steps = 24 05:17:52 [INFO] train episode 40622: reward = -78.80, steps = 30 05:17:55 [INFO] train episode 40623: reward = -30.39, steps = 33 05:17:59 [INFO] train episode 40624: reward = -121.70, steps = 45 05:18:01 [INFO] train episode 40625: reward = -72.54, steps = 29 05:18:03 [INFO] train episode 40626: reward = -50.61, steps = 22 05:18:05 [INFO] train episode 40627: reward = -82.28, steps = 18 05:18:07 [INFO] train episode 40628: reward = -141.83, steps = 30 05:18:11 [INFO] train episode 40629: reward = -129.46, steps = 42 05:18:13 [INFO] train episode 40630: reward = -49.72, steps = 24 05:18:16 [INFO] train episode 40631: reward = -54.68, steps = 26 05:18:18 [INFO] train episode 40632: reward = -122.80, steps = 32 05:18:21 [INFO] train episode 40633: reward = -52.49, steps = 37 05:18:23 [INFO] train episode 40634: reward = -55.71, steps = 18 05:18:25 [INFO] train episode 40635: reward = -74.21, steps = 21 05:18:28 [INFO] train episode 40636: reward = -102.69, steps = 37 05:18:31 [INFO] train episode 40637: reward = -101.86, steps = 28 05:18:34 [INFO] train episode 40638: reward = -82.84, steps = 42 05:18:37 [INFO] train episode 40639: reward = -113.68, steps = 31 05:18:39 [INFO] train episode 40640: reward = -48.80, steps = 25 05:18:42 [INFO] train episode 40641: reward = -63.19, steps = 30 05:18:45 [INFO] train episode 40642: reward = -103.73, steps = 34 05:18:46 [INFO] train episode 40643: reward = -93.81, steps = 16 05:18:50 [INFO] train episode 40644: reward = -86.96, steps = 43 05:18:52 [INFO] train episode 40645: reward = -84.46, steps = 21 05:18:54 [INFO] train episode 40646: reward = -79.51, steps = 23 05:18:55 [INFO] train episode 40647: reward = -86.36, steps = 20 05:18:59 [INFO] train episode 40648: reward = -63.10, steps = 48 05:19:03 [INFO] train episode 40649: reward = -120.01, steps = 39 05:19:07 [INFO] train episode 40650: reward = -47.73, steps = 41 05:19:09 [INFO] train episode 40651: reward = -114.63, steps = 27 05:19:12 [INFO] train episode 40652: reward = -97.65, steps = 37 05:19:14 [INFO] train episode 40653: reward = -84.47, steps = 26 05:19:17 [INFO] train episode 40654: reward = -127.52, steps = 37 05:19:20 [INFO] train episode 40655: reward = -121.19, steps = 32 05:19:23 [INFO] train episode 40656: reward = -100.11, steps = 32 05:19:26 [INFO] train episode 40657: reward = -76.48, steps = 31 05:19:29 [INFO] train episode 40658: reward = -78.57, steps = 39 05:19:32 [INFO] train episode 40659: reward = -75.37, steps = 35 05:19:35 [INFO] train episode 40660: reward = -77.15, steps = 27 05:19:37 [INFO] train episode 40661: reward = -152.25, steps = 22 05:19:39 [INFO] train episode 40662: reward = -113.97, steps = 31 05:19:43 [INFO] train episode 40663: reward = -127.77, steps = 40 05:19:45 [INFO] train episode 40664: reward = -83.42, steps = 23 05:19:48 [INFO] train episode 40665: reward = -159.64, steps = 37 05:19:49 [INFO] train episode 40666: reward = -125.81, steps = 21 05:19:52 [INFO] train episode 40667: reward = -85.44, steps = 22 05:19:54 [INFO] train episode 40668: reward = -61.83, steps = 23 05:19:57 [INFO] train episode 40669: reward = -79.61, steps = 34 05:20:00 [INFO] train episode 40670: reward = -135.51, steps = 39 05:20:02 [INFO] train episode 40671: reward = -96.82, steps = 21 05:20:04 [INFO] train episode 40672: reward = -71.80, steps = 24 05:20:07 [INFO] train episode 40673: reward = -99.31, steps = 31 05:20:09 [INFO] train episode 40674: reward = -70.93, steps = 21 05:20:11 [INFO] train episode 40675: reward = -77.17, steps = 25 05:20:13 [INFO] train episode 40676: reward = -53.47, steps = 25 05:20:15 [INFO] train episode 40677: reward = -83.51, steps = 18 05:20:17 [INFO] train episode 40678: reward = -136.99, steps = 26 05:20:19 [INFO] train episode 40679: reward = -71.05, steps = 22 05:20:22 [INFO] train episode 40680: reward = -103.02, steps = 26 05:20:25 [INFO] train episode 40681: reward = -82.82, steps = 39 05:20:28 [INFO] train episode 40682: reward = -65.21, steps = 34 05:20:31 [INFO] train episode 40683: reward = -128.45, steps = 28 05:20:35 [INFO] train episode 40684: reward = -65.92, steps = 48 05:20:38 [INFO] train episode 40685: reward = -52.72, steps = 34 05:20:40 [INFO] train episode 40686: reward = -57.84, steps = 25 05:20:42 [INFO] train episode 40687: reward = -141.68, steps = 26 05:20:44 [INFO] train episode 40688: reward = -73.38, steps = 22 05:20:46 [INFO] train episode 40689: reward = -124.91, steps = 21 05:20:48 [INFO] train episode 40690: reward = -58.91, steps = 21 05:20:50 [INFO] train episode 40691: reward = -68.12, steps = 20 05:20:52 [INFO] train episode 40692: reward = -78.04, steps = 22 05:20:54 [INFO] train episode 40693: reward = -109.02, steps = 18 05:20:57 [INFO] train episode 40694: reward = -119.96, steps = 24 05:21:00 [INFO] train episode 40695: reward = -105.68, steps = 34 05:21:04 [INFO] train episode 40696: reward = -95.22, steps = 44 05:21:07 [INFO] train episode 40697: reward = -91.23, steps = 37 05:21:09 [INFO] train episode 40698: reward = -57.82, steps = 19 05:21:11 [INFO] train episode 40699: reward = -69.63, steps = 24 05:21:15 [INFO] train episode 40700: reward = -71.81, steps = 31 05:21:17 [INFO] train episode 40701: reward = -57.08, steps = 23 05:21:19 [INFO] train episode 40702: reward = -84.55, steps = 25 05:21:21 [INFO] train episode 40703: reward = -37.09, steps = 21 05:21:25 [INFO] train episode 40704: reward = -101.24, steps = 59 05:21:29 [INFO] train episode 40705: reward = -126.38, steps = 36 05:21:31 [INFO] train episode 40706: reward = -66.28, steps = 25 05:21:33 [INFO] train episode 40707: reward = -51.97, steps = 25 05:21:35 [INFO] train episode 40708: reward = -120.28, steps = 29 05:21:38 [INFO] train episode 40709: reward = -80.84, steps = 28 05:21:41 [INFO] train episode 40710: reward = -38.72, steps = 37 05:21:45 [INFO] train episode 40711: reward = -99.73, steps = 47 05:21:47 [INFO] train episode 40712: reward = -91.10, steps = 22 05:21:49 [INFO] train episode 40713: reward = -66.73, steps = 24 05:21:53 [INFO] train episode 40714: reward = -179.82, steps = 50 05:21:55 [INFO] train episode 40715: reward = -78.94, steps = 24 05:21:58 [INFO] train episode 40716: reward = -131.85, steps = 28 05:22:00 [INFO] train episode 40717: reward = -50.98, steps = 20 05:22:03 [INFO] train episode 40718: reward = -45.53, steps = 32 05:22:06 [INFO] train episode 40719: reward = -45.77, steps = 42 05:22:08 [INFO] train episode 40720: reward = -80.10, steps = 27 05:22:11 [INFO] train episode 40721: reward = -78.54, steps = 26 05:22:13 [INFO] train episode 40722: reward = -64.17, steps = 22 05:22:14 [INFO] train episode 40723: reward = -50.77, steps = 22 05:22:18 [INFO] train episode 40724: reward = -105.06, steps = 38 05:22:20 [INFO] train episode 40725: reward = -54.10, steps = 20 05:22:22 [INFO] train episode 40726: reward = -73.39, steps = 24 05:22:24 [INFO] train episode 40727: reward = -49.55, steps = 30 05:22:27 [INFO] train episode 40728: reward = -88.79, steps = 28 05:22:29 [INFO] train episode 40729: reward = -71.37, steps = 26 05:22:31 [INFO] train episode 40730: reward = -79.81, steps = 20 05:22:33 [INFO] train episode 40731: reward = -84.46, steps = 26 05:22:35 [INFO] train episode 40732: reward = -63.92, steps = 19 05:22:39 [INFO] train episode 40733: reward = -91.23, steps = 41 05:22:41 [INFO] train episode 40734: reward = -46.00, steps = 26 05:22:44 [INFO] train episode 40735: reward = -53.67, steps = 31 05:22:46 [INFO] train episode 40736: reward = -129.85, steps = 28 05:22:48 [INFO] train episode 40737: reward = -103.19, steps = 23 05:22:52 [INFO] train episode 40738: reward = -101.62, steps = 40 05:22:54 [INFO] train episode 40739: reward = -60.91, steps = 22 05:22:56 [INFO] train episode 40740: reward = -60.15, steps = 28 05:22:58 [INFO] train episode 40741: reward = -153.70, steps = 26 05:23:00 [INFO] train episode 40742: reward = -91.77, steps = 21 05:23:03 [INFO] train episode 40743: reward = -84.70, steps = 30 05:23:05 [INFO] train episode 40744: reward = -70.72, steps = 28 05:23:07 [INFO] train episode 40745: reward = -79.70, steps = 19 05:23:09 [INFO] train episode 40746: reward = -89.90, steps = 26 05:23:12 [INFO] train episode 40747: reward = -63.21, steps = 33 05:23:15 [INFO] train episode 40748: reward = -69.34, steps = 22 05:23:17 [INFO] train episode 40749: reward = -63.99, steps = 26 05:23:23 [INFO] train episode 40750: reward = -282.67, steps = 69 05:23:28 [INFO] train episode 40751: reward = -106.64, steps = 56 05:23:30 [INFO] train episode 40752: reward = -92.10, steps = 28 05:23:34 [INFO] train episode 40753: reward = -57.47, steps = 48 05:23:37 [INFO] train episode 40754: reward = -92.94, steps = 26 05:23:39 [INFO] train episode 40755: reward = -87.19, steps = 19 05:23:41 [INFO] train episode 40756: reward = -67.92, steps = 26 05:23:43 [INFO] train episode 40757: reward = -58.88, steps = 21 05:23:45 [INFO] train episode 40758: reward = -45.52, steps = 21 05:23:46 [INFO] train episode 40759: reward = -85.60, steps = 21 05:23:48 [INFO] train episode 40760: reward = -62.52, steps = 14 05:23:49 [INFO] train episode 40761: reward = -93.85, steps = 20 05:23:52 [INFO] train episode 40762: reward = -85.95, steps = 29 05:23:55 [INFO] train episode 40763: reward = -61.80, steps = 27 05:23:56 [INFO] train episode 40764: reward = -54.09, steps = 19 05:23:58 [INFO] train episode 40765: reward = -52.02, steps = 22 05:24:00 [INFO] train episode 40766: reward = -68.55, steps = 21 05:24:03 [INFO] train episode 40767: reward = -93.32, steps = 32 05:24:05 [INFO] train episode 40768: reward = -104.52, steps = 30 05:24:08 [INFO] train episode 40769: reward = -47.06, steps = 26 05:24:09 [INFO] train episode 40770: reward = -75.43, steps = 17 05:24:12 [INFO] train episode 40771: reward = -131.29, steps = 29 05:24:15 [INFO] train episode 40772: reward = -138.98, steps = 43 05:24:18 [INFO] train episode 40773: reward = -98.80, steps = 25 05:24:19 [INFO] train episode 40774: reward = -67.89, steps = 21 05:24:22 [INFO] train episode 40775: reward = -123.90, steps = 28 05:24:24 [INFO] train episode 40776: reward = -100.52, steps = 24 05:24:27 [INFO] train episode 40777: reward = -115.06, steps = 27 05:24:30 [INFO] train episode 40778: reward = -121.53, steps = 37 05:24:34 [INFO] train episode 40779: reward = -119.83, steps = 50 05:24:38 [INFO] train episode 40780: reward = -100.77, steps = 34 05:24:41 [INFO] train episode 40781: reward = -56.91, steps = 38 05:24:44 [INFO] train episode 40782: reward = -71.43, steps = 29 05:24:47 [INFO] train episode 40783: reward = -97.53, steps = 44 05:24:50 [INFO] train episode 40784: reward = -173.28, steps = 28 05:24:52 [INFO] train episode 40785: reward = -40.48, steps = 23 05:24:55 [INFO] train episode 40786: reward = -85.12, steps = 34 05:24:57 [INFO] train episode 40787: reward = -74.17, steps = 21 05:25:01 [INFO] train episode 40788: reward = -224.82, steps = 50 05:25:03 [INFO] train episode 40789: reward = -122.59, steps = 22 05:25:05 [INFO] train episode 40790: reward = -80.62, steps = 23 05:25:07 [INFO] train episode 40791: reward = -86.09, steps = 25 05:25:10 [INFO] train episode 40792: reward = -101.72, steps = 40 05:25:14 [INFO] train episode 40793: reward = -120.71, steps = 40 05:25:16 [INFO] train episode 40794: reward = -101.01, steps = 24 05:25:18 [INFO] train episode 40795: reward = -86.16, steps = 25 05:25:22 [INFO] train episode 40796: reward = -94.87, steps = 42 05:25:24 [INFO] train episode 40797: reward = -107.34, steps = 30 05:25:27 [INFO] train episode 40798: reward = -44.68, steps = 30 05:25:30 [INFO] train episode 40799: reward = -77.97, steps = 29 05:25:32 [INFO] train episode 40800: reward = -77.18, steps = 20 05:25:35 [INFO] train episode 40801: reward = -119.86, steps = 38 05:25:36 [INFO] train episode 40802: reward = -91.78, steps = 19 05:25:39 [INFO] train episode 40803: reward = -153.33, steps = 36 05:25:41 [INFO] train episode 40804: reward = -101.48, steps = 23 05:25:44 [INFO] train episode 40805: reward = -109.22, steps = 25 05:25:47 [INFO] train episode 40806: reward = -126.61, steps = 33 05:25:49 [INFO] train episode 40807: reward = -126.95, steps = 31 05:25:51 [INFO] train episode 40808: reward = -95.65, steps = 26 05:25:55 [INFO] train episode 40809: reward = -107.42, steps = 40 05:25:58 [INFO] train episode 40810: reward = -87.01, steps = 39 05:26:02 [INFO] train episode 40811: reward = -133.05, steps = 39 05:26:05 [INFO] train episode 40812: reward = -95.31, steps = 35 05:26:07 [INFO] train episode 40813: reward = -93.68, steps = 20 05:26:09 [INFO] train episode 40814: reward = -108.94, steps = 21 05:26:11 [INFO] train episode 40815: reward = -48.44, steps = 20 05:26:13 [INFO] train episode 40816: reward = -154.97, steps = 29 05:26:16 [INFO] train episode 40817: reward = -45.00, steps = 22 05:26:19 [INFO] train episode 40818: reward = -157.27, steps = 38 05:26:21 [INFO] train episode 40819: reward = -116.22, steps = 28 05:26:23 [INFO] train episode 40820: reward = -83.84, steps = 20 05:26:25 [INFO] train episode 40821: reward = -63.40, steps = 23 05:26:26 [INFO] train episode 40822: reward = -81.12, steps = 19 05:26:29 [INFO] train episode 40823: reward = -63.80, steps = 31 05:26:36 [INFO] train episode 40824: reward = -221.87, steps = 74 05:26:38 [INFO] train episode 40825: reward = -109.58, steps = 22 05:26:43 [INFO] train episode 40826: reward = -136.24, steps = 64 05:26:46 [INFO] train episode 40827: reward = -143.93, steps = 39 05:26:49 [INFO] train episode 40828: reward = -88.99, steps = 25 05:26:51 [INFO] train episode 40829: reward = -87.02, steps = 24 05:26:54 [INFO] train episode 40830: reward = -132.75, steps = 35 05:26:56 [INFO] train episode 40831: reward = -72.66, steps = 22 05:26:59 [INFO] train episode 40832: reward = -158.70, steps = 35 05:27:00 [INFO] train episode 40833: reward = -64.40, steps = 15 05:27:05 [INFO] train episode 40834: reward = -135.88, steps = 47 05:27:07 [INFO] train episode 40835: reward = -132.68, steps = 28 05:27:09 [INFO] train episode 40836: reward = -90.35, steps = 25 05:27:12 [INFO] train episode 40837: reward = -65.09, steps = 35 05:27:14 [INFO] train episode 40838: reward = -69.39, steps = 29 05:27:17 [INFO] train episode 40839: reward = -102.08, steps = 28 05:27:19 [INFO] train episode 40840: reward = -81.42, steps = 22 05:27:22 [INFO] train episode 40841: reward = -97.08, steps = 26 05:27:23 [INFO] train episode 40842: reward = -50.71, steps = 17 05:27:25 [INFO] train episode 40843: reward = -107.25, steps = 23 05:27:28 [INFO] train episode 40844: reward = -107.96, steps = 38 05:27:30 [INFO] train episode 40845: reward = -70.15, steps = 23 05:27:32 [INFO] train episode 40846: reward = -59.87, steps = 22 05:27:35 [INFO] train episode 40847: reward = -86.71, steps = 36 05:27:37 [INFO] train episode 40848: reward = -76.92, steps = 23 05:27:39 [INFO] train episode 40849: reward = -98.89, steps = 20 05:27:43 [INFO] train episode 40850: reward = -125.36, steps = 49 05:27:46 [INFO] train episode 40851: reward = -170.05, steps = 28 05:27:48 [INFO] train episode 40852: reward = -76.52, steps = 21 05:27:51 [INFO] train episode 40853: reward = -67.52, steps = 33 05:27:53 [INFO] train episode 40854: reward = -95.85, steps = 21 05:27:55 [INFO] train episode 40855: reward = -48.49, steps = 23 05:27:58 [INFO] train episode 40856: reward = -119.95, steps = 43 05:28:01 [INFO] train episode 40857: reward = -38.62, steps = 26 05:28:03 [INFO] train episode 40858: reward = -99.25, steps = 23 05:28:04 [INFO] train episode 40859: reward = -84.80, steps = 21 05:28:06 [INFO] train episode 40860: reward = -121.96, steps = 18 05:28:10 [INFO] train episode 40861: reward = -128.69, steps = 41 05:28:12 [INFO] train episode 40862: reward = -75.16, steps = 20 05:28:13 [INFO] train episode 40863: reward = -72.63, steps = 21 05:28:16 [INFO] train episode 40864: reward = -91.00, steps = 31 05:28:18 [INFO] train episode 40865: reward = -107.52, steps = 25 05:28:21 [INFO] train episode 40866: reward = -117.15, steps = 30 05:28:24 [INFO] train episode 40867: reward = -124.87, steps = 35 05:28:26 [INFO] train episode 40868: reward = -109.25, steps = 26 05:28:30 [INFO] train episode 40869: reward = -90.62, steps = 39 05:28:32 [INFO] train episode 40870: reward = -109.53, steps = 32 05:28:37 [INFO] train episode 40871: reward = -158.89, steps = 50 05:28:41 [INFO] train episode 40872: reward = -172.88, steps = 50 05:28:43 [INFO] train episode 40873: reward = -115.46, steps = 19 05:28:46 [INFO] train episode 40874: reward = -63.12, steps = 42 05:28:50 [INFO] train episode 40875: reward = -52.45, steps = 43 05:28:52 [INFO] train episode 40876: reward = -102.98, steps = 19 05:28:56 [INFO] train episode 40877: reward = -126.75, steps = 39 05:28:58 [INFO] train episode 40878: reward = -97.77, steps = 27 05:29:02 [INFO] train episode 40879: reward = -107.10, steps = 37 05:29:04 [INFO] train episode 40880: reward = -74.84, steps = 28 05:29:08 [INFO] train episode 40881: reward = -119.51, steps = 41 05:29:11 [INFO] train episode 40882: reward = -90.19, steps = 31 05:29:13 [INFO] train episode 40883: reward = -105.30, steps = 27 05:29:16 [INFO] train episode 40884: reward = -84.48, steps = 31 05:29:18 [INFO] train episode 40885: reward = -66.11, steps = 24 05:29:21 [INFO] train episode 40886: reward = -77.09, steps = 36 05:29:23 [INFO] train episode 40887: reward = -98.56, steps = 23 05:29:25 [INFO] train episode 40888: reward = -153.15, steps = 21 05:29:28 [INFO] train episode 40889: reward = -123.08, steps = 31 05:29:31 [INFO] train episode 40890: reward = -116.09, steps = 40 05:29:34 [INFO] train episode 40891: reward = -102.09, steps = 36 05:29:37 [INFO] train episode 40892: reward = -89.96, steps = 29 05:29:39 [INFO] train episode 40893: reward = -81.48, steps = 24 05:29:42 [INFO] train episode 40894: reward = -102.74, steps = 39 05:29:45 [INFO] train episode 40895: reward = -47.65, steps = 23 05:29:47 [INFO] train episode 40896: reward = -110.05, steps = 24 05:29:49 [INFO] train episode 40897: reward = -95.09, steps = 29 05:29:52 [INFO] train episode 40898: reward = -77.07, steps = 32 05:29:54 [INFO] train episode 40899: reward = -63.86, steps = 24 05:29:56 [INFO] train episode 40900: reward = -63.37, steps = 18 05:29:57 [INFO] train episode 40901: reward = -41.96, steps = 18 05:29:59 [INFO] train episode 40902: reward = -103.03, steps = 22 05:30:02 [INFO] train episode 40903: reward = -73.04, steps = 26 05:30:04 [INFO] train episode 40904: reward = -131.52, steps = 31 05:30:07 [INFO] train episode 40905: reward = -122.58, steps = 34 05:30:10 [INFO] train episode 40906: reward = -89.77, steps = 27 05:30:12 [INFO] train episode 40907: reward = -65.15, steps = 25 05:30:14 [INFO] train episode 40908: reward = -125.43, steps = 26 05:30:17 [INFO] train episode 40909: reward = -87.18, steps = 28 05:30:19 [INFO] train episode 40910: reward = -60.81, steps = 22 05:30:21 [INFO] train episode 40911: reward = -69.09, steps = 25 05:30:23 [INFO] train episode 40912: reward = -104.15, steps = 28 05:30:25 [INFO] train episode 40913: reward = -71.90, steps = 26 05:30:28 [INFO] train episode 40914: reward = -181.91, steps = 36 05:30:32 [INFO] train episode 40915: reward = -36.49, steps = 40 05:30:34 [INFO] train episode 40916: reward = -44.54, steps = 21 05:30:36 [INFO] train episode 40917: reward = -132.22, steps = 25 05:30:38 [INFO] train episode 40918: reward = -79.70, steps = 26 05:30:40 [INFO] train episode 40919: reward = -46.30, steps = 21 05:30:44 [INFO] train episode 40920: reward = -81.65, steps = 42 05:30:46 [INFO] train episode 40921: reward = -124.78, steps = 29 05:30:49 [INFO] train episode 40922: reward = -100.63, steps = 27 05:30:52 [INFO] train episode 40923: reward = -82.44, steps = 35 05:30:55 [INFO] train episode 40924: reward = -120.14, steps = 35 05:30:57 [INFO] train episode 40925: reward = -99.36, steps = 23 05:31:00 [INFO] train episode 40926: reward = -91.02, steps = 33 05:31:03 [INFO] train episode 40927: reward = -69.63, steps = 33 05:31:05 [INFO] train episode 40928: reward = -112.16, steps = 27 05:31:08 [INFO] train episode 40929: reward = -94.01, steps = 26 05:31:10 [INFO] train episode 40930: reward = -110.17, steps = 24 05:31:12 [INFO] train episode 40931: reward = -57.23, steps = 22 05:31:14 [INFO] train episode 40932: reward = -84.58, steps = 30 05:31:16 [INFO] train episode 40933: reward = -81.08, steps = 22 05:31:19 [INFO] train episode 40934: reward = -121.74, steps = 34 05:31:21 [INFO] train episode 40935: reward = -84.00, steps = 25 05:31:23 [INFO] train episode 40936: reward = -124.81, steps = 22 05:31:26 [INFO] train episode 40937: reward = -81.16, steps = 29 05:31:27 [INFO] train episode 40938: reward = -51.02, steps = 18 05:31:31 [INFO] train episode 40939: reward = -116.07, steps = 40 05:31:33 [INFO] train episode 40940: reward = -77.61, steps = 30 05:31:36 [INFO] train episode 40941: reward = -81.25, steps = 26 05:31:37 [INFO] train episode 40942: reward = -81.99, steps = 20 05:31:40 [INFO] train episode 40943: reward = -132.57, steps = 30 05:31:44 [INFO] train episode 40944: reward = -125.38, steps = 43 05:31:45 [INFO] train episode 40945: reward = -102.53, steps = 21 05:31:49 [INFO] train episode 40946: reward = -166.43, steps = 33 05:31:51 [INFO] train episode 40947: reward = -127.82, steps = 26 05:31:54 [INFO] train episode 40948: reward = -89.45, steps = 32 05:31:56 [INFO] train episode 40949: reward = -118.81, steps = 25 05:31:58 [INFO] train episode 40950: reward = -59.83, steps = 21 05:32:00 [INFO] train episode 40951: reward = -157.27, steps = 27 05:32:02 [INFO] train episode 40952: reward = -113.65, steps = 18 05:32:04 [INFO] train episode 40953: reward = -79.67, steps = 28 05:32:07 [INFO] train episode 40954: reward = -99.46, steps = 29 05:32:09 [INFO] train episode 40955: reward = -86.50, steps = 26 05:32:12 [INFO] train episode 40956: reward = -117.62, steps = 33 05:32:14 [INFO] train episode 40957: reward = -105.06, steps = 17 05:32:16 [INFO] train episode 40958: reward = -77.40, steps = 23 05:32:21 [INFO] train episode 40959: reward = -117.39, steps = 67 05:32:23 [INFO] train episode 40960: reward = -121.14, steps = 19 05:32:26 [INFO] train episode 40961: reward = -54.95, steps = 32 05:32:29 [INFO] train episode 40962: reward = -162.88, steps = 39 05:32:32 [INFO] train episode 40963: reward = -105.01, steps = 32 05:32:34 [INFO] train episode 40964: reward = -111.41, steps = 21 05:32:36 [INFO] train episode 40965: reward = -46.96, steps = 22 05:32:40 [INFO] train episode 40966: reward = -65.76, steps = 44 05:32:43 [INFO] train episode 40967: reward = -137.05, steps = 32 05:32:48 [INFO] train episode 40968: reward = -281.97, steps = 57 05:32:50 [INFO] train episode 40969: reward = -107.39, steps = 27 05:32:52 [INFO] train episode 40970: reward = -29.16, steps = 23 05:32:55 [INFO] train episode 40971: reward = -153.83, steps = 26 05:32:57 [INFO] train episode 40972: reward = -121.89, steps = 29 05:33:00 [INFO] train episode 40973: reward = -88.11, steps = 33 05:33:02 [INFO] train episode 40974: reward = -77.68, steps = 21 05:33:05 [INFO] train episode 40975: reward = -113.17, steps = 32 05:33:07 [INFO] train episode 40976: reward = -73.23, steps = 20 05:33:12 [INFO] train episode 40977: reward = -310.60, steps = 61 05:33:14 [INFO] train episode 40978: reward = -88.84, steps = 22 05:33:16 [INFO] train episode 40979: reward = -128.87, steps = 23 05:33:20 [INFO] train episode 40980: reward = -97.68, steps = 42 05:33:22 [INFO] train episode 40981: reward = -105.82, steps = 26 05:33:24 [INFO] train episode 40982: reward = -72.43, steps = 32 05:33:27 [INFO] train episode 40983: reward = -83.59, steps = 20 05:33:29 [INFO] train episode 40984: reward = -117.17, steps = 30 05:33:34 [INFO] train episode 40985: reward = -68.49, steps = 58 05:33:36 [INFO] train episode 40986: reward = -56.84, steps = 26 05:33:39 [INFO] train episode 40987: reward = -132.84, steps = 31 05:33:42 [INFO] train episode 40988: reward = -95.59, steps = 30 05:33:44 [INFO] train episode 40989: reward = -68.83, steps = 27 05:33:47 [INFO] train episode 40990: reward = -82.23, steps = 31 05:33:49 [INFO] train episode 40991: reward = -79.26, steps = 23 05:33:52 [INFO] train episode 40992: reward = -57.35, steps = 36 05:33:53 [INFO] train episode 40993: reward = -129.85, steps = 21 05:33:55 [INFO] train episode 40994: reward = -59.47, steps = 19 05:33:58 [INFO] train episode 40995: reward = -60.46, steps = 30 05:34:00 [INFO] train episode 40996: reward = -77.21, steps = 26 05:34:02 [INFO] train episode 40997: reward = -94.05, steps = 22 05:34:04 [INFO] train episode 40998: reward = -111.96, steps = 21 05:34:06 [INFO] train episode 40999: reward = -85.19, steps = 26 05:34:10 [INFO] train episode 41000: reward = -183.33, steps = 52 05:34:13 [INFO] train episode 41001: reward = -82.90, steps = 31 05:34:16 [INFO] train episode 41002: reward = -95.37, steps = 24 05:34:17 [INFO] train episode 41003: reward = -63.46, steps = 21 05:34:21 [INFO] train episode 41004: reward = -52.92, steps = 40 05:34:26 [INFO] train episode 41005: reward = -81.03, steps = 61 05:34:28 [INFO] train episode 41006: reward = -73.18, steps = 21 05:34:30 [INFO] train episode 41007: reward = -76.06, steps = 22 05:34:33 [INFO] train episode 41008: reward = -86.25, steps = 39 05:34:37 [INFO] train episode 41009: reward = -56.41, steps = 43 05:34:39 [INFO] train episode 41010: reward = -92.87, steps = 20 05:34:41 [INFO] train episode 41011: reward = -90.64, steps = 21 05:34:45 [INFO] train episode 41012: reward = -70.57, steps = 39 05:34:47 [INFO] train episode 41013: reward = -91.37, steps = 23 05:34:49 [INFO] train episode 41014: reward = -121.93, steps = 26 05:34:51 [INFO] train episode 41015: reward = -72.79, steps = 19 05:34:55 [INFO] train episode 41016: reward = -178.68, steps = 44 05:34:57 [INFO] train episode 41017: reward = -93.06, steps = 25 05:34:59 [INFO] train episode 41018: reward = -77.81, steps = 24 05:35:01 [INFO] train episode 41019: reward = -42.05, steps = 20 05:35:03 [INFO] train episode 41020: reward = -88.85, steps = 25 05:35:05 [INFO] train episode 41021: reward = -115.04, steps = 26 05:35:08 [INFO] train episode 41022: reward = -74.86, steps = 37 05:35:10 [INFO] train episode 41023: reward = -100.67, steps = 19 05:35:13 [INFO] train episode 41024: reward = -87.01, steps = 29 05:35:15 [INFO] train episode 41025: reward = -271.25, steps = 25 05:35:17 [INFO] train episode 41026: reward = -96.04, steps = 29 05:35:20 [INFO] train episode 41027: reward = -91.06, steps = 27 05:35:26 [INFO] train episode 41028: reward = -202.19, steps = 71 05:35:27 [INFO] train episode 41029: reward = -111.14, steps = 20 05:35:29 [INFO] train episode 41030: reward = -66.47, steps = 25 05:35:32 [INFO] train episode 41031: reward = -144.48, steps = 29 05:35:34 [INFO] train episode 41032: reward = -85.15, steps = 24 05:35:36 [INFO] train episode 41033: reward = -78.74, steps = 22 05:35:39 [INFO] train episode 41034: reward = -141.28, steps = 37 05:35:42 [INFO] train episode 41035: reward = -86.12, steps = 29 05:35:44 [INFO] train episode 41036: reward = -44.54, steps = 22 05:35:45 [INFO] train episode 41037: reward = -97.72, steps = 19 05:35:47 [INFO] train episode 41038: reward = -79.00, steps = 22 05:35:50 [INFO] train episode 41039: reward = -82.65, steps = 32 05:35:53 [INFO] train episode 41040: reward = -155.55, steps = 36 05:35:55 [INFO] train episode 41041: reward = -91.13, steps = 18 05:35:58 [INFO] train episode 41042: reward = -89.36, steps = 32 05:36:01 [INFO] train episode 41043: reward = -126.96, steps = 34 05:36:05 [INFO] train episode 41044: reward = -144.43, steps = 48 05:36:07 [INFO] train episode 41045: reward = -61.90, steps = 18 05:36:09 [INFO] train episode 41046: reward = -117.17, steps = 24 05:36:11 [INFO] train episode 41047: reward = -65.56, steps = 27 05:36:13 [INFO] train episode 41048: reward = -73.55, steps = 20 05:36:15 [INFO] train episode 41049: reward = -125.09, steps = 31 05:36:18 [INFO] train episode 41050: reward = -48.94, steps = 24 05:36:21 [INFO] train episode 41051: reward = -90.26, steps = 32 05:36:22 [INFO] train episode 41052: reward = -87.08, steps = 18 05:36:24 [INFO] train episode 41053: reward = -248.81, steps = 26 05:36:27 [INFO] train episode 41054: reward = -110.87, steps = 25 05:36:28 [INFO] train episode 41055: reward = -68.32, steps = 22 05:36:31 [INFO] train episode 41056: reward = -83.69, steps = 25 05:36:33 [INFO] train episode 41057: reward = -126.26, steps = 34 05:36:36 [INFO] train episode 41058: reward = -90.57, steps = 25 05:36:38 [INFO] train episode 41059: reward = -110.02, steps = 17 05:36:40 [INFO] train episode 41060: reward = -106.48, steps = 26 05:36:41 [INFO] train episode 41061: reward = -98.43, steps = 19 05:36:44 [INFO] train episode 41062: reward = -124.01, steps = 35 05:36:48 [INFO] train episode 41063: reward = -146.31, steps = 48 05:36:52 [INFO] train episode 41064: reward = -129.61, steps = 42 05:36:55 [INFO] train episode 41065: reward = -47.18, steps = 25 05:36:57 [INFO] train episode 41066: reward = -190.45, steps = 27 05:36:59 [INFO] train episode 41067: reward = -81.83, steps = 27 05:37:01 [INFO] train episode 41068: reward = -96.25, steps = 20 05:37:03 [INFO] train episode 41069: reward = -125.89, steps = 27 05:37:05 [INFO] train episode 41070: reward = -74.97, steps = 23 05:37:07 [INFO] train episode 41071: reward = -102.01, steps = 20 05:37:10 [INFO] train episode 41072: reward = -132.73, steps = 29 05:37:13 [INFO] train episode 41073: reward = -101.20, steps = 38 05:37:15 [INFO] train episode 41074: reward = -46.63, steps = 25 05:37:17 [INFO] train episode 41075: reward = -74.37, steps = 20 05:37:19 [INFO] train episode 41076: reward = -56.44, steps = 24 05:37:21 [INFO] train episode 41077: reward = -109.31, steps = 22 05:37:25 [INFO] train episode 41078: reward = -109.81, steps = 46 05:37:27 [INFO] train episode 41079: reward = -73.04, steps = 20 05:37:29 [INFO] train episode 41080: reward = -49.38, steps = 20 05:37:31 [INFO] train episode 41081: reward = -112.91, steps = 22 05:37:33 [INFO] train episode 41082: reward = -60.05, steps = 20 05:37:35 [INFO] train episode 41083: reward = -144.30, steps = 28 05:37:38 [INFO] train episode 41084: reward = -117.16, steps = 34 05:37:40 [INFO] train episode 41085: reward = -155.05, steps = 22 05:37:43 [INFO] train episode 41086: reward = -114.72, steps = 25 05:37:45 [INFO] train episode 41087: reward = -143.35, steps = 30 05:37:47 [INFO] train episode 41088: reward = -78.43, steps = 24 05:37:49 [INFO] train episode 41089: reward = -112.15, steps = 22 05:37:51 [INFO] train episode 41090: reward = -80.22, steps = 23 05:37:53 [INFO] train episode 41091: reward = -102.16, steps = 23 05:37:56 [INFO] train episode 41092: reward = -90.61, steps = 32 05:37:58 [INFO] train episode 41093: reward = -41.42, steps = 22 05:38:00 [INFO] train episode 41094: reward = -56.89, steps = 21 05:38:02 [INFO] train episode 41095: reward = -106.83, steps = 28 05:38:06 [INFO] train episode 41096: reward = -68.84, steps = 43 05:38:08 [INFO] train episode 41097: reward = -91.07, steps = 23 05:38:11 [INFO] train episode 41098: reward = -80.56, steps = 29 05:38:13 [INFO] train episode 41099: reward = -96.63, steps = 30 05:38:15 [INFO] train episode 41100: reward = -99.44, steps = 26 05:38:18 [INFO] train episode 41101: reward = -124.98, steps = 36 05:38:21 [INFO] train episode 41102: reward = -77.57, steps = 35 05:38:23 [INFO] train episode 41103: reward = -83.93, steps = 24 05:38:26 [INFO] train episode 41104: reward = -110.48, steps = 30 05:38:28 [INFO] train episode 41105: reward = -80.24, steps = 20 05:38:30 [INFO] train episode 41106: reward = -50.23, steps = 23 05:38:33 [INFO] train episode 41107: reward = -60.95, steps = 34 05:38:36 [INFO] train episode 41108: reward = -44.09, steps = 40 05:38:38 [INFO] train episode 41109: reward = -59.96, steps = 23 05:38:40 [INFO] train episode 41110: reward = -87.33, steps = 24 05:38:43 [INFO] train episode 41111: reward = -89.62, steps = 25 05:38:45 [INFO] train episode 41112: reward = -111.72, steps = 28 05:38:48 [INFO] train episode 41113: reward = -150.64, steps = 31 05:38:52 [INFO] train episode 41114: reward = -115.21, steps = 43 05:38:54 [INFO] train episode 41115: reward = -80.82, steps = 28 05:38:56 [INFO] train episode 41116: reward = -100.92, steps = 28 05:38:58 [INFO] train episode 41117: reward = -97.26, steps = 20 05:39:02 [INFO] train episode 41118: reward = -126.90, steps = 38 05:39:05 [INFO] train episode 41119: reward = -118.36, steps = 36 05:39:07 [INFO] train episode 41120: reward = -81.44, steps = 23 05:39:09 [INFO] train episode 41121: reward = -79.80, steps = 24 05:39:11 [INFO] train episode 41122: reward = -69.22, steps = 31 05:39:18 [INFO] train episode 41123: reward = -174.73, steps = 79 05:39:20 [INFO] train episode 41124: reward = -44.69, steps = 25 05:39:23 [INFO] train episode 41125: reward = -80.60, steps = 26 05:39:27 [INFO] train episode 41126: reward = -150.06, steps = 49 05:39:30 [INFO] train episode 41127: reward = -136.76, steps = 35 05:39:33 [INFO] train episode 41128: reward = -117.44, steps = 35 05:39:35 [INFO] train episode 41129: reward = -139.71, steps = 21 05:39:38 [INFO] train episode 41130: reward = -81.86, steps = 27 05:39:40 [INFO] train episode 41131: reward = -138.02, steps = 28 05:39:42 [INFO] train episode 41132: reward = -73.99, steps = 21 05:39:44 [INFO] train episode 41133: reward = -115.91, steps = 25 05:39:47 [INFO] train episode 41134: reward = -74.11, steps = 28 05:39:49 [INFO] train episode 41135: reward = -109.64, steps = 30 05:39:50 [INFO] train episode 41136: reward = -94.88, steps = 15 05:39:53 [INFO] train episode 41137: reward = -109.02, steps = 36 05:39:55 [INFO] train episode 41138: reward = -80.30, steps = 22 05:39:57 [INFO] train episode 41139: reward = -90.15, steps = 21 05:39:59 [INFO] train episode 41140: reward = -74.24, steps = 27 05:40:02 [INFO] train episode 41141: reward = -99.59, steps = 28 05:40:04 [INFO] train episode 41142: reward = -141.05, steps = 19 05:40:06 [INFO] train episode 41143: reward = -89.70, steps = 27 05:40:09 [INFO] train episode 41144: reward = -101.17, steps = 36 05:40:11 [INFO] train episode 41145: reward = -54.67, steps = 27 05:40:13 [INFO] train episode 41146: reward = -76.56, steps = 19 05:40:15 [INFO] train episode 41147: reward = -98.77, steps = 21 05:40:17 [INFO] train episode 41148: reward = -215.07, steps = 26 05:40:19 [INFO] train episode 41149: reward = -86.83, steps = 23 05:40:23 [INFO] train episode 41150: reward = -112.64, steps = 29 05:40:25 [INFO] train episode 41151: reward = -90.51, steps = 26 05:40:27 [INFO] train episode 41152: reward = -84.21, steps = 22 05:40:29 [INFO] train episode 41153: reward = -84.93, steps = 25 05:40:31 [INFO] train episode 41154: reward = -74.70, steps = 20 05:40:33 [INFO] train episode 41155: reward = -106.46, steps = 22 05:40:35 [INFO] train episode 41156: reward = -148.96, steps = 20 05:40:37 [INFO] train episode 41157: reward = -95.31, steps = 26 05:40:40 [INFO] train episode 41158: reward = -73.41, steps = 31 05:40:42 [INFO] train episode 41159: reward = -63.69, steps = 31 05:40:44 [INFO] train episode 41160: reward = -57.35, steps = 22 05:40:46 [INFO] train episode 41161: reward = -99.08, steps = 26 05:40:48 [INFO] train episode 41162: reward = -75.75, steps = 21 05:40:51 [INFO] train episode 41163: reward = -84.01, steps = 23 05:40:53 [INFO] train episode 41164: reward = -133.89, steps = 29 05:40:56 [INFO] train episode 41165: reward = -120.32, steps = 28 05:40:58 [INFO] train episode 41166: reward = -109.90, steps = 34 05:41:02 [INFO] train episode 41167: reward = -136.27, steps = 46 05:41:05 [INFO] train episode 41168: reward = -147.53, steps = 31 05:41:08 [INFO] train episode 41169: reward = -87.35, steps = 35 05:41:10 [INFO] train episode 41170: reward = -96.97, steps = 18 05:41:12 [INFO] train episode 41171: reward = -59.35, steps = 26 05:41:14 [INFO] train episode 41172: reward = -81.16, steps = 26 05:41:17 [INFO] train episode 41173: reward = -136.05, steps = 27 05:41:18 [INFO] train episode 41174: reward = -55.36, steps = 18 05:41:20 [INFO] train episode 41175: reward = -49.75, steps = 22 05:41:22 [INFO] train episode 41176: reward = -68.12, steps = 23 05:41:25 [INFO] train episode 41177: reward = -202.34, steps = 29 05:41:27 [INFO] train episode 41178: reward = -89.63, steps = 24 05:41:29 [INFO] train episode 41179: reward = -101.69, steps = 27 05:41:31 [INFO] train episode 41180: reward = -139.00, steps = 24 05:41:33 [INFO] train episode 41181: reward = -119.48, steps = 20 05:41:35 [INFO] train episode 41182: reward = -147.66, steps = 29 05:41:38 [INFO] train episode 41183: reward = -89.53, steps = 26 05:41:40 [INFO] train episode 41184: reward = -169.00, steps = 23 05:41:42 [INFO] train episode 41185: reward = -126.75, steps = 25 05:41:44 [INFO] train episode 41186: reward = -82.50, steps = 26 05:41:47 [INFO] train episode 41187: reward = -73.99, steps = 27 05:41:49 [INFO] train episode 41188: reward = -75.01, steps = 22 05:41:52 [INFO] train episode 41189: reward = -108.72, steps = 38 05:41:54 [INFO] train episode 41190: reward = -136.77, steps = 28 05:41:57 [INFO] train episode 41191: reward = -89.01, steps = 25 05:41:59 [INFO] train episode 41192: reward = -83.17, steps = 29 05:42:01 [INFO] train episode 41193: reward = -92.57, steps = 22 05:42:04 [INFO] train episode 41194: reward = -127.89, steps = 29 05:42:06 [INFO] train episode 41195: reward = -82.46, steps = 26 05:42:09 [INFO] train episode 41196: reward = -132.89, steps = 38 05:42:11 [INFO] train episode 41197: reward = -66.36, steps = 22 05:42:13 [INFO] train episode 41198: reward = -73.79, steps = 20 05:42:15 [INFO] train episode 41199: reward = -79.84, steps = 22 05:42:16 [INFO] train episode 41200: reward = -91.83, steps = 18 05:42:18 [INFO] train episode 41201: reward = -84.27, steps = 20 05:42:20 [INFO] train episode 41202: reward = -68.95, steps = 26 05:42:22 [INFO] train episode 41203: reward = -132.31, steps = 18 05:42:24 [INFO] train episode 41204: reward = -84.90, steps = 23 05:42:27 [INFO] train episode 41205: reward = -46.01, steps = 34 05:42:29 [INFO] train episode 41206: reward = -71.84, steps = 18 05:42:30 [INFO] train episode 41207: reward = -83.32, steps = 18 05:42:33 [INFO] train episode 41208: reward = -115.19, steps = 28 05:42:35 [INFO] train episode 41209: reward = -120.33, steps = 25 05:42:37 [INFO] train episode 41210: reward = -113.23, steps = 30 05:42:41 [INFO] train episode 41211: reward = -76.25, steps = 33 05:42:43 [INFO] train episode 41212: reward = -153.80, steps = 32 05:42:46 [INFO] train episode 41213: reward = -108.82, steps = 31 05:42:48 [INFO] train episode 41214: reward = -72.13, steps = 19 05:42:50 [INFO] train episode 41215: reward = -81.32, steps = 24 05:42:52 [INFO] train episode 41216: reward = -80.61, steps = 22 05:42:54 [INFO] train episode 41217: reward = -132.46, steps = 27 05:42:58 [INFO] train episode 41218: reward = -94.67, steps = 38 05:43:00 [INFO] train episode 41219: reward = -85.17, steps = 30 05:43:03 [INFO] train episode 41220: reward = -77.11, steps = 35 05:43:05 [INFO] train episode 41221: reward = -79.90, steps = 24 05:43:07 [INFO] train episode 41222: reward = -78.28, steps = 23 05:43:10 [INFO] train episode 41223: reward = -145.75, steps = 34 05:43:13 [INFO] train episode 41224: reward = -122.77, steps = 24 05:43:15 [INFO] train episode 41225: reward = -79.59, steps = 21 05:43:16 [INFO] train episode 41226: reward = -128.65, steps = 13 05:43:18 [INFO] train episode 41227: reward = -115.81, steps = 26 05:43:21 [INFO] train episode 41228: reward = -136.03, steps = 30 05:43:23 [INFO] train episode 41229: reward = -97.91, steps = 22 05:43:26 [INFO] train episode 41230: reward = -144.90, steps = 38 05:43:29 [INFO] train episode 41231: reward = -171.66, steps = 32 05:43:31 [INFO] train episode 41232: reward = -107.99, steps = 24 05:43:33 [INFO] train episode 41233: reward = -98.69, steps = 20 05:43:35 [INFO] train episode 41234: reward = -65.76, steps = 19 05:43:36 [INFO] train episode 41235: reward = -72.37, steps = 20 05:43:38 [INFO] train episode 41236: reward = -77.33, steps = 23 05:43:42 [INFO] train episode 41237: reward = -94.47, steps = 41 05:43:44 [INFO] train episode 41238: reward = -79.45, steps = 18 05:43:46 [INFO] train episode 41239: reward = -98.93, steps = 23 05:43:48 [INFO] train episode 41240: reward = -52.43, steps = 28 05:43:51 [INFO] train episode 41241: reward = -78.38, steps = 30 05:43:54 [INFO] train episode 41242: reward = -104.41, steps = 38 05:43:55 [INFO] train episode 41243: reward = -97.31, steps = 18 05:43:58 [INFO] train episode 41244: reward = -220.27, steps = 38 05:44:03 [INFO] train episode 41245: reward = -214.08, steps = 47 05:44:04 [INFO] train episode 41246: reward = -103.87, steps = 18 05:44:06 [INFO] train episode 41247: reward = -93.75, steps = 19 05:44:08 [INFO] train episode 41248: reward = -93.86, steps = 26 05:44:10 [INFO] train episode 41249: reward = -110.71, steps = 24 05:44:12 [INFO] train episode 41250: reward = -94.98, steps = 19 05:44:14 [INFO] train episode 41251: reward = -45.30, steps = 22 05:44:17 [INFO] train episode 41252: reward = -81.91, steps = 30 05:44:20 [INFO] train episode 41253: reward = -47.83, steps = 35 05:44:24 [INFO] train episode 41254: reward = -186.17, steps = 46 05:44:27 [INFO] train episode 41255: reward = -128.98, steps = 36 05:44:29 [INFO] train episode 41256: reward = -138.21, steps = 24 05:44:32 [INFO] train episode 41257: reward = -57.80, steps = 34 05:44:34 [INFO] train episode 41258: reward = -121.66, steps = 28 05:44:37 [INFO] train episode 41259: reward = -61.73, steps = 37 05:44:39 [INFO] train episode 41260: reward = -51.14, steps = 17 05:44:42 [INFO] train episode 41261: reward = -176.38, steps = 35 05:44:44 [INFO] train episode 41262: reward = -111.88, steps = 21 05:44:46 [INFO] train episode 41263: reward = -105.77, steps = 25 05:44:48 [INFO] train episode 41264: reward = -130.94, steps = 22 05:44:50 [INFO] train episode 41265: reward = -65.32, steps = 18 05:44:52 [INFO] train episode 41266: reward = -161.21, steps = 25 05:44:54 [INFO] train episode 41267: reward = -138.99, steps = 29 05:44:56 [INFO] train episode 41268: reward = -124.75, steps = 22 05:44:59 [INFO] train episode 41269: reward = -110.65, steps = 31 05:45:01 [INFO] train episode 41270: reward = -99.85, steps = 23 05:45:03 [INFO] train episode 41271: reward = -62.13, steps = 21 05:45:05 [INFO] train episode 41272: reward = -83.34, steps = 23 05:45:07 [INFO] train episode 41273: reward = -77.45, steps = 22 05:45:09 [INFO] train episode 41274: reward = -76.84, steps = 23 05:45:11 [INFO] train episode 41275: reward = -86.24, steps = 23 05:45:14 [INFO] train episode 41276: reward = -170.13, steps = 41 05:45:17 [INFO] train episode 41277: reward = -186.13, steps = 29 05:45:21 [INFO] train episode 41278: reward = -80.08, steps = 41 05:45:22 [INFO] train episode 41279: reward = -121.89, steps = 17 05:45:24 [INFO] train episode 41280: reward = -76.91, steps = 19 05:45:26 [INFO] train episode 41281: reward = -84.11, steps = 22 05:45:29 [INFO] train episode 41282: reward = -103.43, steps = 39 05:45:31 [INFO] train episode 41283: reward = -80.01, steps = 25 05:45:33 [INFO] train episode 41284: reward = -66.01, steps = 20 05:45:35 [INFO] train episode 41285: reward = -88.26, steps = 18 05:45:37 [INFO] train episode 41286: reward = -73.41, steps = 28 05:45:40 [INFO] train episode 41287: reward = -178.14, steps = 31 05:45:42 [INFO] train episode 41288: reward = -86.90, steps = 24 05:45:44 [INFO] train episode 41289: reward = -64.21, steps = 21 05:45:46 [INFO] train episode 41290: reward = -121.28, steps = 26 05:45:48 [INFO] train episode 41291: reward = -101.21, steps = 23 05:45:50 [INFO] train episode 41292: reward = -75.04, steps = 22 05:45:53 [INFO] train episode 41293: reward = -84.13, steps = 37 05:45:56 [INFO] train episode 41294: reward = -145.36, steps = 37 05:46:00 [INFO] train episode 41295: reward = -58.24, steps = 38 05:46:01 [INFO] train episode 41296: reward = -131.69, steps = 19 05:46:04 [INFO] train episode 41297: reward = -107.10, steps = 18 05:46:06 [INFO] train episode 41298: reward = -57.72, steps = 25 05:46:09 [INFO] train episode 41299: reward = -144.11, steps = 35 05:46:11 [INFO] train episode 41300: reward = -115.26, steps = 18 05:46:13 [INFO] train episode 41301: reward = -118.70, steps = 31 05:46:15 [INFO] train episode 41302: reward = -120.14, steps = 20 05:46:17 [INFO] train episode 41303: reward = -68.89, steps = 27 05:46:20 [INFO] train episode 41304: reward = -135.87, steps = 28 05:46:22 [INFO] train episode 41305: reward = -89.97, steps = 22 05:46:24 [INFO] train episode 41306: reward = -51.81, steps = 25 05:46:26 [INFO] train episode 41307: reward = -60.74, steps = 20 05:46:28 [INFO] train episode 41308: reward = -128.63, steps = 24 05:46:30 [INFO] train episode 41309: reward = -51.79, steps = 25 05:46:32 [INFO] train episode 41310: reward = -67.27, steps = 19 05:46:34 [INFO] train episode 41311: reward = -117.32, steps = 25 05:46:36 [INFO] train episode 41312: reward = -82.54, steps = 26 05:46:39 [INFO] train episode 41313: reward = -174.73, steps = 25 05:46:41 [INFO] train episode 41314: reward = -176.83, steps = 27 05:46:43 [INFO] train episode 41315: reward = -93.30, steps = 24 05:46:46 [INFO] train episode 41316: reward = -97.77, steps = 27 05:46:48 [INFO] train episode 41317: reward = -75.93, steps = 23 05:46:49 [INFO] train episode 41318: reward = -87.87, steps = 23 05:46:52 [INFO] train episode 41319: reward = -100.16, steps = 32 05:46:54 [INFO] train episode 41320: reward = -71.87, steps = 20 05:46:56 [INFO] train episode 41321: reward = -51.28, steps = 20 05:46:58 [INFO] train episode 41322: reward = -78.54, steps = 26 05:47:00 [INFO] train episode 41323: reward = -144.45, steps = 21 05:47:02 [INFO] train episode 41324: reward = -130.39, steps = 25 05:47:04 [INFO] train episode 41325: reward = -88.95, steps = 23 05:47:06 [INFO] train episode 41326: reward = -82.69, steps = 20 05:47:08 [INFO] train episode 41327: reward = -95.16, steps = 23 05:47:10 [INFO] train episode 41328: reward = -63.27, steps = 23 05:47:13 [INFO] train episode 41329: reward = -146.01, steps = 36 05:47:16 [INFO] train episode 41330: reward = -86.18, steps = 36 05:47:19 [INFO] train episode 41331: reward = -107.60, steps = 33 05:47:23 [INFO] train episode 41332: reward = -137.54, steps = 49 05:47:27 [INFO] train episode 41333: reward = -80.91, steps = 33 05:47:28 [INFO] train episode 41334: reward = -75.89, steps = 22 05:47:30 [INFO] train episode 41335: reward = -102.63, steps = 20 05:47:32 [INFO] train episode 41336: reward = -128.50, steps = 23 05:47:35 [INFO] train episode 41337: reward = -201.25, steps = 33 05:47:38 [INFO] train episode 41338: reward = -90.75, steps = 33 05:47:39 [INFO] train episode 41339: reward = -33.86, steps = 20 05:47:42 [INFO] train episode 41340: reward = -154.88, steps = 27 05:47:45 [INFO] train episode 41341: reward = -61.17, steps = 36 05:47:47 [INFO] train episode 41342: reward = -63.45, steps = 20 05:47:49 [INFO] train episode 41343: reward = -115.56, steps = 25 05:47:51 [INFO] train episode 41344: reward = -74.64, steps = 27 05:47:54 [INFO] train episode 41345: reward = -50.56, steps = 34 05:47:56 [INFO] train episode 41346: reward = -105.67, steps = 22 05:47:58 [INFO] train episode 41347: reward = -120.45, steps = 22 05:48:00 [INFO] train episode 41348: reward = -73.46, steps = 21 05:48:03 [INFO] train episode 41349: reward = -111.16, steps = 31 05:48:05 [INFO] train episode 41350: reward = -144.44, steps = 23 05:48:07 [INFO] train episode 41351: reward = -115.30, steps = 29 05:48:10 [INFO] train episode 41352: reward = -90.58, steps = 26 05:48:12 [INFO] train episode 41353: reward = -81.77, steps = 32 05:48:15 [INFO] train episode 41354: reward = -112.97, steps = 25 05:48:17 [INFO] train episode 41355: reward = -91.82, steps = 28 05:48:19 [INFO] train episode 41356: reward = -59.17, steps = 27 05:48:22 [INFO] train episode 41357: reward = -118.96, steps = 27 05:48:24 [INFO] train episode 41358: reward = -94.56, steps = 28 05:48:27 [INFO] train episode 41359: reward = -72.99, steps = 35 05:48:29 [INFO] train episode 41360: reward = -90.27, steps = 22 05:48:31 [INFO] train episode 41361: reward = -101.77, steps = 18 05:48:34 [INFO] train episode 41362: reward = -126.42, steps = 37 05:48:36 [INFO] train episode 41363: reward = -108.54, steps = 24 05:48:39 [INFO] train episode 41364: reward = -130.49, steps = 30 05:48:41 [INFO] train episode 41365: reward = -122.35, steps = 27 05:48:44 [INFO] train episode 41366: reward = -75.77, steps = 30 05:48:46 [INFO] train episode 41367: reward = -98.24, steps = 29 05:48:49 [INFO] train episode 41368: reward = -101.03, steps = 26 05:48:52 [INFO] train episode 41369: reward = -105.34, steps = 40 05:48:55 [INFO] train episode 41370: reward = -110.22, steps = 28 05:48:59 [INFO] train episode 41371: reward = -129.19, steps = 43 05:49:01 [INFO] train episode 41372: reward = -77.56, steps = 24 05:49:03 [INFO] train episode 41373: reward = -51.47, steps = 24 05:49:05 [INFO] train episode 41374: reward = -92.96, steps = 20 05:49:08 [INFO] train episode 41375: reward = -140.57, steps = 41 05:49:12 [INFO] train episode 41376: reward = -165.54, steps = 40 05:49:14 [INFO] train episode 41377: reward = -141.73, steps = 24 05:49:16 [INFO] train episode 41378: reward = -103.48, steps = 25 05:49:19 [INFO] train episode 41379: reward = -198.76, steps = 30 05:49:21 [INFO] train episode 41380: reward = -88.70, steps = 22 05:49:23 [INFO] train episode 41381: reward = -87.10, steps = 22 05:49:25 [INFO] train episode 41382: reward = -92.75, steps = 24 05:49:27 [INFO] train episode 41383: reward = -58.19, steps = 22 05:49:29 [INFO] train episode 41384: reward = -102.26, steps = 25 05:49:31 [INFO] train episode 41385: reward = -82.45, steps = 27 05:49:34 [INFO] train episode 41386: reward = -102.06, steps = 30 05:49:36 [INFO] train episode 41387: reward = -82.81, steps = 19 05:49:38 [INFO] train episode 41388: reward = -88.29, steps = 26 05:49:40 [INFO] train episode 41389: reward = -74.78, steps = 24 05:49:42 [INFO] train episode 41390: reward = -84.36, steps = 26 05:49:45 [INFO] train episode 41391: reward = -131.89, steps = 35 05:49:47 [INFO] train episode 41392: reward = -57.65, steps = 20 05:49:49 [INFO] train episode 41393: reward = -92.11, steps = 21 05:49:51 [INFO] train episode 41394: reward = -62.09, steps = 23 05:49:53 [INFO] train episode 41395: reward = -59.59, steps = 22 05:49:55 [INFO] train episode 41396: reward = -91.74, steps = 27 05:49:58 [INFO] train episode 41397: reward = -114.91, steps = 30 05:50:01 [INFO] train episode 41398: reward = -49.78, steps = 44 05:50:03 [INFO] train episode 41399: reward = -90.97, steps = 21 05:50:05 [INFO] train episode 41400: reward = -72.90, steps = 23 05:50:07 [INFO] train episode 41401: reward = -96.49, steps = 23 05:50:11 [INFO] train episode 41402: reward = -174.67, steps = 42 05:50:13 [INFO] train episode 41403: reward = -63.18, steps = 28 05:50:15 [INFO] train episode 41404: reward = -107.17, steps = 20 05:50:17 [INFO] train episode 41405: reward = -80.01, steps = 24 05:50:20 [INFO] train episode 41406: reward = -119.09, steps = 26 05:50:22 [INFO] train episode 41407: reward = -95.11, steps = 24 05:50:24 [INFO] train episode 41408: reward = -103.57, steps = 28 05:50:26 [INFO] train episode 41409: reward = -81.61, steps = 24 05:50:28 [INFO] train episode 41410: reward = -125.89, steps = 22 05:50:29 [INFO] train episode 41411: reward = -96.75, steps = 17 05:50:32 [INFO] train episode 41412: reward = -129.28, steps = 34 05:50:35 [INFO] train episode 41413: reward = -71.81, steps = 32 05:50:38 [INFO] train episode 41414: reward = -88.20, steps = 28 05:50:40 [INFO] train episode 41415: reward = -152.66, steps = 27 05:50:43 [INFO] train episode 41416: reward = -140.49, steps = 30 05:50:45 [INFO] train episode 41417: reward = -146.31, steps = 22 05:50:47 [INFO] train episode 41418: reward = -141.32, steps = 30 05:50:49 [INFO] train episode 41419: reward = -103.71, steps = 20 05:50:52 [INFO] train episode 41420: reward = -65.56, steps = 32 05:50:55 [INFO] train episode 41421: reward = -120.24, steps = 33 05:50:57 [INFO] train episode 41422: reward = -106.27, steps = 24 05:50:59 [INFO] train episode 41423: reward = -122.85, steps = 30 05:51:01 [INFO] train episode 41424: reward = -129.73, steps = 24 05:51:04 [INFO] train episode 41425: reward = -148.22, steps = 30 05:51:06 [INFO] train episode 41426: reward = -72.03, steps = 22 05:51:09 [INFO] train episode 41427: reward = -95.51, steps = 32 05:51:11 [INFO] train episode 41428: reward = -96.56, steps = 25 05:51:15 [INFO] train episode 41429: reward = -151.22, steps = 47 05:51:18 [INFO] train episode 41430: reward = -99.27, steps = 36 05:51:20 [INFO] train episode 41431: reward = -70.22, steps = 23 05:51:24 [INFO] train episode 41432: reward = -80.74, steps = 43 05:51:27 [INFO] train episode 41433: reward = -102.14, steps = 34 05:51:29 [INFO] train episode 41434: reward = -68.53, steps = 23 05:51:31 [INFO] train episode 41435: reward = -94.78, steps = 27 05:51:34 [INFO] train episode 41436: reward = -80.06, steps = 28 05:51:39 [INFO] train episode 41437: reward = -103.38, steps = 55 05:51:41 [INFO] train episode 41438: reward = -48.96, steps = 31 05:51:46 [INFO] train episode 41439: reward = -136.53, steps = 43 05:51:47 [INFO] train episode 41440: reward = -124.89, steps = 16 05:51:49 [INFO] train episode 41441: reward = -123.13, steps = 19 05:51:51 [INFO] train episode 41442: reward = -161.14, steps = 28 05:51:54 [INFO] train episode 41443: reward = -71.57, steps = 34 05:51:56 [INFO] train episode 41444: reward = -95.86, steps = 22 05:51:59 [INFO] train episode 41445: reward = -86.73, steps = 29 05:52:01 [INFO] train episode 41446: reward = -164.02, steps = 34 05:52:04 [INFO] train episode 41447: reward = -100.98, steps = 28 05:52:06 [INFO] train episode 41448: reward = -104.33, steps = 30 05:52:09 [INFO] train episode 41449: reward = -139.61, steps = 31 05:52:12 [INFO] train episode 41450: reward = -91.68, steps = 30 05:52:14 [INFO] train episode 41451: reward = -141.76, steps = 25 05:52:16 [INFO] train episode 41452: reward = -121.61, steps = 30 05:52:19 [INFO] train episode 41453: reward = -107.70, steps = 25 05:52:20 [INFO] train episode 41454: reward = -74.90, steps = 19 05:52:23 [INFO] train episode 41455: reward = -115.93, steps = 31 05:52:26 [INFO] train episode 41456: reward = -57.10, steps = 29 05:52:27 [INFO] train episode 41457: reward = -70.18, steps = 17 05:52:29 [INFO] train episode 41458: reward = -94.69, steps = 27 05:52:32 [INFO] train episode 41459: reward = -120.28, steps = 26 05:52:33 [INFO] train episode 41460: reward = -90.33, steps = 21 05:52:36 [INFO] train episode 41461: reward = -114.55, steps = 27 05:52:38 [INFO] train episode 41462: reward = -107.56, steps = 26 05:52:40 [INFO] train episode 41463: reward = -51.04, steps = 19 05:52:42 [INFO] train episode 41464: reward = -74.70, steps = 18 05:52:44 [INFO] train episode 41465: reward = -129.11, steps = 26 05:52:46 [INFO] train episode 41466: reward = -110.11, steps = 27 05:52:48 [INFO] train episode 41467: reward = -88.94, steps = 23 05:52:51 [INFO] train episode 41468: reward = -131.48, steps = 28 05:52:52 [INFO] train episode 41469: reward = -70.11, steps = 20 05:52:54 [INFO] train episode 41470: reward = -84.58, steps = 25 05:52:56 [INFO] train episode 41471: reward = -126.58, steps = 23 05:52:59 [INFO] train episode 41472: reward = -91.33, steps = 21 05:53:01 [INFO] train episode 41473: reward = -108.65, steps = 34 05:53:03 [INFO] train episode 41474: reward = -66.36, steps = 19 05:53:05 [INFO] train episode 41475: reward = -110.82, steps = 26 05:53:07 [INFO] train episode 41476: reward = -80.71, steps = 22 05:53:09 [INFO] train episode 41477: reward = -148.68, steps = 27 05:53:12 [INFO] train episode 41478: reward = -112.47, steps = 24 05:53:14 [INFO] train episode 41479: reward = -100.61, steps = 21 05:53:16 [INFO] train episode 41480: reward = -86.53, steps = 22 05:53:18 [INFO] train episode 41481: reward = -97.46, steps = 29 05:53:21 [INFO] train episode 41482: reward = -72.07, steps = 39 05:53:24 [INFO] train episode 41483: reward = -116.77, steps = 27 05:53:25 [INFO] train episode 41484: reward = -73.83, steps = 20 05:53:28 [INFO] train episode 41485: reward = -100.66, steps = 29 05:53:30 [INFO] train episode 41486: reward = -30.87, steps = 22 05:53:33 [INFO] train episode 41487: reward = -80.42, steps = 30 05:53:34 [INFO] train episode 41488: reward = -64.34, steps = 21 05:53:37 [INFO] train episode 41489: reward = -82.19, steps = 25 05:53:39 [INFO] train episode 41490: reward = -72.35, steps = 22 05:53:41 [INFO] train episode 41491: reward = -108.43, steps = 28 05:53:43 [INFO] train episode 41492: reward = -65.44, steps = 20 05:53:45 [INFO] train episode 41493: reward = -98.72, steps = 22 05:53:48 [INFO] train episode 41494: reward = -59.42, steps = 32 05:53:51 [INFO] train episode 41495: reward = -49.04, steps = 35 05:53:53 [INFO] train episode 41496: reward = -83.31, steps = 23 05:53:55 [INFO] train episode 41497: reward = -174.01, steps = 34 05:53:58 [INFO] train episode 41498: reward = -72.76, steps = 31 05:54:02 [INFO] train episode 41499: reward = -131.55, steps = 41 05:54:04 [INFO] train episode 41500: reward = -149.94, steps = 24 05:54:06 [INFO] train episode 41501: reward = -94.40, steps = 19 05:54:08 [INFO] train episode 41502: reward = -91.17, steps = 23 05:54:09 [INFO] train episode 41503: reward = -87.56, steps = 22 05:54:11 [INFO] train episode 41504: reward = -75.32, steps = 25 05:54:14 [INFO] train episode 41505: reward = -59.22, steps = 29 05:54:17 [INFO] train episode 41506: reward = -143.05, steps = 30 05:54:19 [INFO] train episode 41507: reward = -96.12, steps = 27 05:54:21 [INFO] train episode 41508: reward = -81.98, steps = 21 05:54:23 [INFO] train episode 41509: reward = -83.30, steps = 26 05:54:28 [INFO] train episode 41510: reward = -199.57, steps = 50 05:54:30 [INFO] train episode 41511: reward = -207.21, steps = 25 05:54:33 [INFO] train episode 41512: reward = -143.64, steps = 33 05:54:36 [INFO] train episode 41513: reward = -135.77, steps = 27 05:54:38 [INFO] train episode 41514: reward = -100.83, steps = 23 05:54:40 [INFO] train episode 41515: reward = -194.99, steps = 23 05:54:42 [INFO] train episode 41516: reward = -87.34, steps = 22 05:54:45 [INFO] train episode 41517: reward = -89.33, steps = 32 05:54:47 [INFO] train episode 41518: reward = -62.55, steps = 27 05:54:50 [INFO] train episode 41519: reward = -88.71, steps = 27 05:54:52 [INFO] train episode 41520: reward = -93.49, steps = 21 05:54:54 [INFO] train episode 41521: reward = -102.98, steps = 19 05:54:57 [INFO] train episode 41522: reward = -115.03, steps = 43 05:54:59 [INFO] train episode 41523: reward = -59.64, steps = 20 05:55:01 [INFO] train episode 41524: reward = -91.27, steps = 21 05:55:03 [INFO] train episode 41525: reward = -104.17, steps = 25 05:55:06 [INFO] train episode 41526: reward = -133.23, steps = 30 05:55:08 [INFO] train episode 41527: reward = -96.69, steps = 27 05:55:11 [INFO] train episode 41528: reward = -71.10, steps = 34 05:55:15 [INFO] train episode 41529: reward = -91.31, steps = 48 05:55:17 [INFO] train episode 41530: reward = -79.70, steps = 28 05:55:19 [INFO] train episode 41531: reward = -127.10, steps = 19 05:55:21 [INFO] train episode 41532: reward = -89.39, steps = 20 05:55:23 [INFO] train episode 41533: reward = -85.07, steps = 19 05:55:25 [INFO] train episode 41534: reward = -73.35, steps = 21 05:55:27 [INFO] train episode 41535: reward = -97.55, steps = 31 05:55:29 [INFO] train episode 41536: reward = -54.94, steps = 21 05:55:32 [INFO] train episode 41537: reward = -119.80, steps = 33 05:55:34 [INFO] train episode 41538: reward = -54.08, steps = 27 05:55:37 [INFO] train episode 41539: reward = -108.51, steps = 27 05:55:38 [INFO] train episode 41540: reward = -69.87, steps = 18 05:55:41 [INFO] train episode 41541: reward = -170.97, steps = 25 05:55:43 [INFO] train episode 41542: reward = -63.09, steps = 27 05:55:46 [INFO] train episode 41543: reward = -80.59, steps = 34 05:55:48 [INFO] train episode 41544: reward = -40.29, steps = 27 05:55:50 [INFO] train episode 41545: reward = -67.64, steps = 28 05:55:53 [INFO] train episode 41546: reward = -128.08, steps = 20 05:55:54 [INFO] train episode 41547: reward = -66.73, steps = 21 05:55:59 [INFO] train episode 41548: reward = -220.55, steps = 51 05:56:00 [INFO] train episode 41549: reward = -115.70, steps = 20 05:56:02 [INFO] train episode 41550: reward = -63.85, steps = 19 05:56:05 [INFO] train episode 41551: reward = -110.45, steps = 38 05:56:07 [INFO] train episode 41552: reward = -84.95, steps = 26 05:56:09 [INFO] train episode 41553: reward = -61.91, steps = 20 05:56:13 [INFO] train episode 41554: reward = -95.86, steps = 42 05:56:16 [INFO] train episode 41555: reward = -45.75, steps = 32 05:56:18 [INFO] train episode 41556: reward = -130.10, steps = 28 05:56:20 [INFO] train episode 41557: reward = -126.98, steps = 27 05:56:22 [INFO] train episode 41558: reward = -66.69, steps = 21 05:56:30 [INFO] train episode 41559: reward = -120.30, steps = 85 05:56:31 [INFO] train episode 41560: reward = -132.03, steps = 19 05:56:35 [INFO] train episode 41561: reward = -146.07, steps = 40 05:56:37 [INFO] train episode 41562: reward = -78.59, steps = 28 05:56:40 [INFO] train episode 41563: reward = -78.07, steps = 34 05:56:42 [INFO] train episode 41564: reward = -116.18, steps = 19 05:56:46 [INFO] train episode 41565: reward = -139.14, steps = 41 05:56:47 [INFO] train episode 41566: reward = -65.85, steps = 18 05:56:49 [INFO] train episode 41567: reward = -89.26, steps = 20 05:56:51 [INFO] train episode 41568: reward = -80.07, steps = 28 05:56:54 [INFO] train episode 41569: reward = -53.15, steps = 32 05:56:57 [INFO] train episode 41570: reward = -87.68, steps = 31 05:56:59 [INFO] train episode 41571: reward = -67.34, steps = 25 05:57:01 [INFO] train episode 41572: reward = -59.09, steps = 22 05:57:04 [INFO] train episode 41573: reward = -105.65, steps = 37 05:57:06 [INFO] train episode 41574: reward = -150.70, steps = 21 05:57:09 [INFO] train episode 41575: reward = -77.02, steps = 39 05:57:12 [INFO] train episode 41576: reward = -111.43, steps = 22 05:57:14 [INFO] train episode 41577: reward = -79.33, steps = 26 05:57:17 [INFO] train episode 41578: reward = -84.38, steps = 39 05:57:19 [INFO] train episode 41579: reward = -56.37, steps = 19 05:57:21 [INFO] train episode 41580: reward = -114.06, steps = 23 05:57:23 [INFO] train episode 41581: reward = -122.04, steps = 27 05:57:27 [INFO] train episode 41582: reward = -110.40, steps = 40 05:57:30 [INFO] train episode 41583: reward = -95.91, steps = 24 05:57:33 [INFO] train episode 41584: reward = -91.05, steps = 37 05:57:34 [INFO] train episode 41585: reward = -66.08, steps = 15 05:57:36 [INFO] train episode 41586: reward = -80.46, steps = 20 05:57:38 [INFO] train episode 41587: reward = -89.75, steps = 23 05:57:41 [INFO] train episode 41588: reward = -116.03, steps = 37 05:57:43 [INFO] train episode 41589: reward = -97.59, steps = 26 05:57:46 [INFO] train episode 41590: reward = -149.78, steps = 23 05:57:48 [INFO] train episode 41591: reward = -105.60, steps = 28 05:57:49 [INFO] train episode 41592: reward = -77.50, steps = 18 05:57:52 [INFO] train episode 41593: reward = -141.37, steps = 31 05:57:54 [INFO] train episode 41594: reward = -104.38, steps = 19 05:57:56 [INFO] train episode 41595: reward = -91.19, steps = 32 05:57:59 [INFO] train episode 41596: reward = -124.86, steps = 26 05:58:01 [INFO] train episode 41597: reward = -85.72, steps = 20 05:58:04 [INFO] train episode 41598: reward = -97.77, steps = 44 05:58:08 [INFO] train episode 41599: reward = -69.98, steps = 42 05:58:11 [INFO] train episode 41600: reward = -182.89, steps = 35 05:58:13 [INFO] train episode 41601: reward = -110.19, steps = 27 05:58:15 [INFO] train episode 41602: reward = -64.67, steps = 20 05:58:18 [INFO] train episode 41603: reward = -121.07, steps = 31 05:58:20 [INFO] train episode 41604: reward = -122.78, steps = 29 05:58:22 [INFO] train episode 41605: reward = -82.11, steps = 24 05:58:25 [INFO] train episode 41606: reward = -154.39, steps = 33 05:58:27 [INFO] train episode 41607: reward = -121.36, steps = 23 05:58:29 [INFO] train episode 41608: reward = -107.84, steps = 23 05:58:32 [INFO] train episode 41609: reward = -76.45, steps = 29 05:58:34 [INFO] train episode 41610: reward = -84.45, steps = 22 05:58:37 [INFO] train episode 41611: reward = -148.04, steps = 31 05:58:39 [INFO] train episode 41612: reward = -155.48, steps = 23 05:58:40 [INFO] train episode 41613: reward = -64.09, steps = 21 05:58:42 [INFO] train episode 41614: reward = -118.70, steps = 20 05:58:45 [INFO] train episode 41615: reward = -143.30, steps = 30 05:58:48 [INFO] train episode 41616: reward = -179.83, steps = 37 05:58:50 [INFO] train episode 41617: reward = -97.30, steps = 24 05:58:53 [INFO] train episode 41618: reward = -123.32, steps = 32 05:58:57 [INFO] train episode 41619: reward = -113.52, steps = 41 05:58:58 [INFO] train episode 41620: reward = -93.10, steps = 22 05:59:01 [INFO] train episode 41621: reward = -64.23, steps = 26 05:59:03 [INFO] train episode 41622: reward = -70.31, steps = 29 05:59:07 [INFO] train episode 41623: reward = -150.30, steps = 43 05:59:09 [INFO] train episode 41624: reward = -92.39, steps = 20 05:59:11 [INFO] train episode 41625: reward = -67.33, steps = 25 05:59:14 [INFO] train episode 41626: reward = -110.35, steps = 34 05:59:16 [INFO] train episode 41627: reward = -95.39, steps = 23 05:59:19 [INFO] train episode 41628: reward = -134.05, steps = 27 05:59:20 [INFO] train episode 41629: reward = -112.75, steps = 21 05:59:22 [INFO] train episode 41630: reward = -61.33, steps = 23 05:59:24 [INFO] train episode 41631: reward = -80.02, steps = 24 05:59:27 [INFO] train episode 41632: reward = -107.91, steps = 27 05:59:29 [INFO] train episode 41633: reward = -146.09, steps = 31 05:59:32 [INFO] train episode 41634: reward = -79.76, steps = 29 05:59:34 [INFO] train episode 41635: reward = -126.17, steps = 25 05:59:37 [INFO] train episode 41636: reward = -50.53, steps = 35 05:59:40 [INFO] train episode 41637: reward = -79.94, steps = 31 05:59:42 [INFO] train episode 41638: reward = -91.08, steps = 21 05:59:44 [INFO] train episode 41639: reward = -103.53, steps = 28 05:59:47 [INFO] train episode 41640: reward = -81.85, steps = 36 05:59:50 [INFO] train episode 41641: reward = -122.69, steps = 34 05:59:52 [INFO] train episode 41642: reward = -86.72, steps = 19 05:59:54 [INFO] train episode 41643: reward = -52.50, steps = 20 05:59:55 [INFO] train episode 41644: reward = -97.54, steps = 19 05:59:57 [INFO] train episode 41645: reward = -58.71, steps = 22 06:00:00 [INFO] train episode 41646: reward = -99.42, steps = 31 06:00:03 [INFO] train episode 41647: reward = -114.38, steps = 34 06:00:07 [INFO] train episode 41648: reward = -90.95, steps = 40 06:00:08 [INFO] train episode 41649: reward = -52.71, steps = 21 06:00:11 [INFO] train episode 41650: reward = -122.68, steps = 32 06:00:13 [INFO] train episode 41651: reward = -133.14, steps = 28 06:00:17 [INFO] train episode 41652: reward = -134.88, steps = 39 06:00:20 [INFO] train episode 41653: reward = -88.63, steps = 29 06:00:22 [INFO] train episode 41654: reward = -152.59, steps = 23 06:00:24 [INFO] train episode 41655: reward = -100.43, steps = 20 06:00:27 [INFO] train episode 41656: reward = -127.27, steps = 30 06:00:29 [INFO] train episode 41657: reward = -89.16, steps = 26 06:00:31 [INFO] train episode 41658: reward = -74.21, steps = 25 06:00:33 [INFO] train episode 41659: reward = -132.98, steps = 21 06:00:36 [INFO] train episode 41660: reward = -106.90, steps = 37 06:00:39 [INFO] train episode 41661: reward = -136.11, steps = 32 06:00:42 [INFO] train episode 41662: reward = -88.05, steps = 36 06:00:44 [INFO] train episode 41663: reward = -76.38, steps = 21 06:00:47 [INFO] train episode 41664: reward = -138.27, steps = 33 06:00:49 [INFO] train episode 41665: reward = -131.08, steps = 23 06:00:51 [INFO] train episode 41666: reward = -58.95, steps = 23 06:00:53 [INFO] train episode 41667: reward = -72.22, steps = 24 06:00:56 [INFO] train episode 41668: reward = -133.62, steps = 26 06:00:58 [INFO] train episode 41669: reward = -91.51, steps = 26 06:00:59 [INFO] train episode 41670: reward = -72.01, steps = 18 06:01:01 [INFO] train episode 41671: reward = -97.87, steps = 22 06:01:03 [INFO] train episode 41672: reward = -49.65, steps = 21 06:01:05 [INFO] train episode 41673: reward = -57.28, steps = 25 06:01:08 [INFO] train episode 41674: reward = -153.37, steps = 36 06:01:11 [INFO] train episode 41675: reward = -96.19, steps = 27 06:01:13 [INFO] train episode 41676: reward = -163.42, steps = 28 06:01:16 [INFO] train episode 41677: reward = -132.08, steps = 32 06:01:19 [INFO] train episode 41678: reward = -179.17, steps = 42 06:01:21 [INFO] train episode 41679: reward = -90.54, steps = 18 06:01:23 [INFO] train episode 41680: reward = -185.90, steps = 24 06:01:25 [INFO] train episode 41681: reward = -44.21, steps = 23 06:01:27 [INFO] train episode 41682: reward = -67.02, steps = 22 06:01:30 [INFO] train episode 41683: reward = -143.66, steps = 34 06:01:32 [INFO] train episode 41684: reward = -65.80, steps = 22 06:01:34 [INFO] train episode 41685: reward = -67.49, steps = 22 06:01:36 [INFO] train episode 41686: reward = -107.19, steps = 32 06:01:38 [INFO] train episode 41687: reward = -59.41, steps = 21 06:01:41 [INFO] train episode 41688: reward = -61.15, steps = 30 06:01:43 [INFO] train episode 41689: reward = -52.47, steps = 23 06:01:45 [INFO] train episode 41690: reward = -113.55, steps = 29 06:01:47 [INFO] train episode 41691: reward = -77.21, steps = 19 06:01:49 [INFO] train episode 41692: reward = -99.26, steps = 20 06:01:51 [INFO] train episode 41693: reward = -88.37, steps = 26 06:01:53 [INFO] train episode 41694: reward = -64.85, steps = 20 06:01:54 [INFO] train episode 41695: reward = -139.74, steps = 20 06:01:57 [INFO] train episode 41696: reward = -47.56, steps = 26 06:02:00 [INFO] train episode 41697: reward = -88.90, steps = 33 06:02:02 [INFO] train episode 41698: reward = -78.79, steps = 27 06:02:06 [INFO] train episode 41699: reward = -159.55, steps = 52 06:02:10 [INFO] train episode 41700: reward = -104.02, steps = 38 06:02:13 [INFO] train episode 41701: reward = -79.27, steps = 30 06:02:15 [INFO] train episode 41702: reward = -98.13, steps = 30 06:02:18 [INFO] train episode 41703: reward = -126.10, steps = 31 06:02:20 [INFO] train episode 41704: reward = -67.69, steps = 23 06:02:22 [INFO] train episode 41705: reward = -110.89, steps = 26 06:02:25 [INFO] train episode 41706: reward = -88.08, steps = 39 06:02:27 [INFO] train episode 41707: reward = -84.37, steps = 20 06:02:30 [INFO] train episode 41708: reward = -149.61, steps = 39 06:02:34 [INFO] train episode 41709: reward = -66.11, steps = 43 06:02:38 [INFO] train episode 41710: reward = -124.24, steps = 39 06:02:40 [INFO] train episode 41711: reward = -91.35, steps = 24 06:02:42 [INFO] train episode 41712: reward = -75.81, steps = 27 06:02:45 [INFO] train episode 41713: reward = -100.13, steps = 24 06:02:48 [INFO] train episode 41714: reward = -127.98, steps = 36 06:02:50 [INFO] train episode 41715: reward = -53.56, steps = 24 06:02:52 [INFO] train episode 41716: reward = -115.88, steps = 22 06:02:53 [INFO] train episode 41717: reward = -93.77, steps = 20 06:02:55 [INFO] train episode 41718: reward = -64.09, steps = 24 06:02:57 [INFO] train episode 41719: reward = -62.46, steps = 20 06:03:01 [INFO] train episode 41720: reward = -91.80, steps = 39 06:03:03 [INFO] train episode 41721: reward = -67.02, steps = 24 06:03:05 [INFO] train episode 41722: reward = -106.09, steps = 29 06:03:08 [INFO] train episode 41723: reward = -86.31, steps = 29 06:03:11 [INFO] train episode 41724: reward = -87.53, steps = 25 06:03:13 [INFO] train episode 41725: reward = -138.33, steps = 33 06:03:16 [INFO] train episode 41726: reward = -90.43, steps = 26 06:03:18 [INFO] train episode 41727: reward = -67.95, steps = 23 06:03:20 [INFO] train episode 41728: reward = -139.08, steps = 22 06:03:22 [INFO] train episode 41729: reward = -64.79, steps = 26 06:03:24 [INFO] train episode 41730: reward = -88.70, steps = 21 06:03:28 [INFO] train episode 41731: reward = -95.79, steps = 45 06:03:30 [INFO] train episode 41732: reward = -91.64, steps = 25 06:03:32 [INFO] train episode 41733: reward = -87.84, steps = 24 06:03:35 [INFO] train episode 41734: reward = -123.61, steps = 38 06:03:39 [INFO] train episode 41735: reward = -103.47, steps = 40 06:03:40 [INFO] train episode 41736: reward = -102.52, steps = 17 06:03:42 [INFO] train episode 41737: reward = -71.14, steps = 22 06:03:45 [INFO] train episode 41738: reward = -97.01, steps = 32 06:03:48 [INFO] train episode 41739: reward = -100.56, steps = 21 06:03:51 [INFO] train episode 41740: reward = -125.51, steps = 40 06:03:53 [INFO] train episode 41741: reward = -158.86, steps = 30 06:03:55 [INFO] train episode 41742: reward = -156.25, steps = 20 06:03:58 [INFO] train episode 41743: reward = -97.30, steps = 37 06:04:00 [INFO] train episode 41744: reward = -79.51, steps = 23 06:04:02 [INFO] train episode 41745: reward = -59.34, steps = 21 06:04:04 [INFO] train episode 41746: reward = -72.46, steps = 20 06:04:05 [INFO] train episode 41747: reward = -87.39, steps = 15 06:04:07 [INFO] train episode 41748: reward = -82.55, steps = 20 06:04:12 [INFO] train episode 41749: reward = -79.59, steps = 56 06:04:14 [INFO] train episode 41750: reward = -113.82, steps = 28 06:04:16 [INFO] train episode 41751: reward = -63.67, steps = 29 06:04:18 [INFO] train episode 41752: reward = -126.10, steps = 23 06:04:21 [INFO] train episode 41753: reward = -92.81, steps = 26 06:04:24 [INFO] train episode 41754: reward = -102.17, steps = 32 06:04:27 [INFO] train episode 41755: reward = -136.13, steps = 38 06:04:30 [INFO] train episode 41756: reward = -94.06, steps = 34 06:04:32 [INFO] train episode 41757: reward = -88.59, steps = 24 06:04:34 [INFO] train episode 41758: reward = -94.79, steps = 27 06:04:36 [INFO] train episode 41759: reward = -56.31, steps = 21 06:04:39 [INFO] train episode 41760: reward = -102.74, steps = 29 06:04:41 [INFO] train episode 41761: reward = -99.77, steps = 31 06:04:44 [INFO] train episode 41762: reward = -92.60, steps = 26 06:04:46 [INFO] train episode 41763: reward = -108.54, steps = 31 06:04:50 [INFO] train episode 41764: reward = -177.42, steps = 40 06:04:52 [INFO] train episode 41765: reward = -75.40, steps = 21 06:04:54 [INFO] train episode 41766: reward = -103.03, steps = 29 06:04:57 [INFO] train episode 41767: reward = -119.51, steps = 27 06:05:00 [INFO] train episode 41768: reward = -94.14, steps = 34 06:05:01 [INFO] train episode 41769: reward = -77.84, steps = 21 06:05:04 [INFO] train episode 41770: reward = -126.90, steps = 30 06:05:06 [INFO] train episode 41771: reward = -109.62, steps = 19 06:05:09 [INFO] train episode 41772: reward = -84.92, steps = 38 06:05:11 [INFO] train episode 41773: reward = -108.14, steps = 22 06:05:14 [INFO] train episode 41774: reward = -72.19, steps = 29 06:05:16 [INFO] train episode 41775: reward = -84.09, steps = 23 06:05:18 [INFO] train episode 41776: reward = -77.72, steps = 25 06:05:24 [INFO] train episode 41777: reward = -168.26, steps = 71 06:05:26 [INFO] train episode 41778: reward = -60.78, steps = 26 06:05:31 [INFO] train episode 41779: reward = -141.77, steps = 53 06:05:33 [INFO] train episode 41780: reward = -91.85, steps = 25 06:05:36 [INFO] train episode 41781: reward = -108.78, steps = 33 06:05:38 [INFO] train episode 41782: reward = -71.62, steps = 26 06:05:40 [INFO] train episode 41783: reward = -84.15, steps = 21 06:05:42 [INFO] train episode 41784: reward = -77.93, steps = 26 06:05:44 [INFO] train episode 41785: reward = -72.07, steps = 20 06:05:46 [INFO] train episode 41786: reward = -109.01, steps = 22 06:05:48 [INFO] train episode 41787: reward = -114.57, steps = 29 06:05:51 [INFO] train episode 41788: reward = -168.11, steps = 32 06:05:54 [INFO] train episode 41789: reward = -114.67, steps = 26 06:05:57 [INFO] train episode 41790: reward = -156.13, steps = 37 06:06:02 [INFO] train episode 41791: reward = -116.39, steps = 57 06:06:04 [INFO] train episode 41792: reward = -72.24, steps = 20 06:06:06 [INFO] train episode 41793: reward = -103.40, steps = 24 06:06:08 [INFO] train episode 41794: reward = -71.24, steps = 27 06:06:11 [INFO] train episode 41795: reward = -113.81, steps = 27 06:06:13 [INFO] train episode 41796: reward = -118.73, steps = 24 06:06:16 [INFO] train episode 41797: reward = -58.06, steps = 37 06:06:20 [INFO] train episode 41798: reward = -142.37, steps = 42 06:06:21 [INFO] train episode 41799: reward = -116.89, steps = 19 06:06:24 [INFO] train episode 41800: reward = -86.36, steps = 27 06:06:27 [INFO] train episode 41801: reward = -97.34, steps = 28 06:06:28 [INFO] train episode 41802: reward = -72.27, steps = 21 06:06:30 [INFO] train episode 41803: reward = -88.73, steps = 24 06:06:33 [INFO] train episode 41804: reward = -100.61, steps = 31 06:06:35 [INFO] train episode 41805: reward = -107.15, steps = 22 06:06:37 [INFO] train episode 41806: reward = -72.09, steps = 22 06:06:39 [INFO] train episode 41807: reward = -126.18, steps = 27 06:06:43 [INFO] train episode 41808: reward = -60.46, steps = 37 06:06:45 [INFO] train episode 41809: reward = -84.29, steps = 26 06:06:47 [INFO] train episode 41810: reward = -77.44, steps = 23 06:06:49 [INFO] train episode 41811: reward = -105.82, steps = 24 06:06:52 [INFO] train episode 41812: reward = -144.89, steps = 40 06:06:56 [INFO] train episode 41813: reward = -110.63, steps = 39 06:06:58 [INFO] train episode 41814: reward = -111.88, steps = 29 06:07:01 [INFO] train episode 41815: reward = -91.74, steps = 31 06:07:03 [INFO] train episode 41816: reward = -80.36, steps = 23 06:07:05 [INFO] train episode 41817: reward = -84.81, steps = 27 06:07:07 [INFO] train episode 41818: reward = -53.63, steps = 22 06:07:11 [INFO] train episode 41819: reward = -168.89, steps = 42 06:07:14 [INFO] train episode 41820: reward = -112.17, steps = 36 06:07:18 [INFO] train episode 41821: reward = -174.37, steps = 48 06:07:21 [INFO] train episode 41822: reward = -102.06, steps = 29 06:07:24 [INFO] train episode 41823: reward = -72.25, steps = 35 06:07:26 [INFO] train episode 41824: reward = -122.64, steps = 22 06:07:30 [INFO] train episode 41825: reward = -139.97, steps = 44 06:07:32 [INFO] train episode 41826: reward = -151.90, steps = 29 06:07:34 [INFO] train episode 41827: reward = -98.62, steps = 22 06:07:36 [INFO] train episode 41828: reward = -53.93, steps = 22 06:07:38 [INFO] train episode 41829: reward = -88.18, steps = 25 06:07:42 [INFO] train episode 41830: reward = -110.24, steps = 42 06:07:44 [INFO] train episode 41831: reward = -104.34, steps = 27 06:07:47 [INFO] train episode 41832: reward = -109.49, steps = 36 06:07:49 [INFO] train episode 41833: reward = -116.12, steps = 26 06:07:52 [INFO] train episode 41834: reward = -94.32, steps = 26 06:07:55 [INFO] train episode 41835: reward = -132.24, steps = 36 06:07:57 [INFO] train episode 41836: reward = -71.95, steps = 21 06:07:59 [INFO] train episode 41837: reward = -144.12, steps = 27 06:08:01 [INFO] train episode 41838: reward = -86.95, steps = 22 06:08:03 [INFO] train episode 41839: reward = -109.67, steps = 27 06:08:06 [INFO] train episode 41840: reward = -87.93, steps = 37 06:08:09 [INFO] train episode 41841: reward = -98.45, steps = 24 06:08:12 [INFO] train episode 41842: reward = -90.09, steps = 37 06:08:14 [INFO] train episode 41843: reward = -61.75, steps = 29 06:08:16 [INFO] train episode 41844: reward = -75.06, steps = 21 06:08:18 [INFO] train episode 41845: reward = -90.48, steps = 26 06:08:22 [INFO] train episode 41846: reward = -162.68, steps = 42 06:08:23 [INFO] train episode 41847: reward = -100.40, steps = 15 06:08:26 [INFO] train episode 41848: reward = -66.22, steps = 35 06:08:28 [INFO] train episode 41849: reward = -109.45, steps = 20 06:08:30 [INFO] train episode 41850: reward = -105.35, steps = 22 06:08:32 [INFO] train episode 41851: reward = -79.84, steps = 25 06:08:34 [INFO] train episode 41852: reward = -114.49, steps = 19 06:08:37 [INFO] train episode 41853: reward = -88.46, steps = 30 06:08:39 [INFO] train episode 41854: reward = -75.09, steps = 23 06:08:41 [INFO] train episode 41855: reward = -95.11, steps = 24 06:08:43 [INFO] train episode 41856: reward = -77.16, steps = 25 06:08:46 [INFO] train episode 41857: reward = -113.84, steps = 34 06:08:49 [INFO] train episode 41858: reward = -73.92, steps = 31 06:08:52 [INFO] train episode 41859: reward = -106.10, steps = 28 06:08:55 [INFO] train episode 41860: reward = -84.90, steps = 37 06:08:59 [INFO] train episode 41861: reward = -150.13, steps = 50 06:09:01 [INFO] train episode 41862: reward = -77.17, steps = 19 06:09:03 [INFO] train episode 41863: reward = -108.85, steps = 19 06:09:06 [INFO] train episode 41864: reward = -132.00, steps = 36 06:09:09 [INFO] train episode 41865: reward = -87.05, steps = 30 06:09:11 [INFO] train episode 41866: reward = -84.19, steps = 25 06:09:12 [INFO] train episode 41867: reward = -108.10, steps = 19 06:09:14 [INFO] train episode 41868: reward = -121.22, steps = 25 06:09:17 [INFO] train episode 41869: reward = -146.92, steps = 30 06:09:20 [INFO] train episode 41870: reward = -63.50, steps = 25 06:09:22 [INFO] train episode 41871: reward = -107.09, steps = 24 06:09:24 [INFO] train episode 41872: reward = -84.98, steps = 27 06:09:28 [INFO] train episode 41873: reward = -109.96, steps = 51 06:09:30 [INFO] train episode 41874: reward = -57.16, steps = 23 06:09:33 [INFO] train episode 41875: reward = -85.09, steps = 37 06:09:36 [INFO] train episode 41876: reward = -103.95, steps = 30 06:09:39 [INFO] train episode 41877: reward = -109.92, steps = 32 06:09:42 [INFO] train episode 41878: reward = -109.40, steps = 35 06:09:44 [INFO] train episode 41879: reward = -58.76, steps = 21 06:09:46 [INFO] train episode 41880: reward = -59.76, steps = 23 06:09:49 [INFO] train episode 41881: reward = -88.51, steps = 43 06:09:52 [INFO] train episode 41882: reward = -93.34, steps = 21 06:09:54 [INFO] train episode 41883: reward = -97.66, steps = 29 06:09:57 [INFO] train episode 41884: reward = -120.58, steps = 38 06:09:59 [INFO] train episode 41885: reward = -99.50, steps = 26 06:10:01 [INFO] train episode 41886: reward = -70.02, steps = 24 06:10:04 [INFO] train episode 41887: reward = -83.32, steps = 31 06:10:06 [INFO] train episode 41888: reward = -37.94, steps = 27 06:10:10 [INFO] train episode 41889: reward = -200.26, steps = 36 06:10:12 [INFO] train episode 41890: reward = -55.59, steps = 30 06:10:14 [INFO] train episode 41891: reward = -138.67, steps = 18 06:10:16 [INFO] train episode 41892: reward = -77.99, steps = 23 06:10:18 [INFO] train episode 41893: reward = -81.65, steps = 25 06:10:20 [INFO] train episode 41894: reward = -73.64, steps = 21 06:10:22 [INFO] train episode 41895: reward = -114.63, steps = 28 06:10:25 [INFO] train episode 41896: reward = -90.85, steps = 26 06:10:27 [INFO] train episode 41897: reward = -92.25, steps = 32 06:10:29 [INFO] train episode 41898: reward = -85.29, steps = 22 06:10:31 [INFO] train episode 41899: reward = -88.65, steps = 24 06:10:33 [INFO] train episode 41900: reward = -125.56, steps = 24 06:10:35 [INFO] train episode 41901: reward = -81.24, steps = 20 06:10:37 [INFO] train episode 41902: reward = -91.19, steps = 19 06:10:40 [INFO] train episode 41903: reward = -81.11, steps = 32 06:10:43 [INFO] train episode 41904: reward = -104.08, steps = 38 06:10:45 [INFO] train episode 41905: reward = -61.21, steps = 20 06:10:47 [INFO] train episode 41906: reward = -93.67, steps = 27 06:10:50 [INFO] train episode 41907: reward = -100.36, steps = 28 06:10:51 [INFO] train episode 41908: reward = -56.43, steps = 18 06:10:53 [INFO] train episode 41909: reward = -103.95, steps = 24 06:10:57 [INFO] train episode 41910: reward = -110.13, steps = 34 06:10:59 [INFO] train episode 41911: reward = -88.91, steps = 22 06:11:01 [INFO] train episode 41912: reward = -108.45, steps = 30 06:11:03 [INFO] train episode 41913: reward = -76.29, steps = 23 06:11:05 [INFO] train episode 41914: reward = -67.37, steps = 24 06:11:07 [INFO] train episode 41915: reward = -84.74, steps = 23 06:11:11 [INFO] train episode 41916: reward = -114.94, steps = 45 06:11:13 [INFO] train episode 41917: reward = -83.69, steps = 25 06:11:16 [INFO] train episode 41918: reward = -81.31, steps = 27 06:11:18 [INFO] train episode 41919: reward = -78.69, steps = 28 06:11:20 [INFO] train episode 41920: reward = -81.21, steps = 24 06:11:22 [INFO] train episode 41921: reward = -115.52, steps = 26 06:11:24 [INFO] train episode 41922: reward = -62.04, steps = 23 06:11:27 [INFO] train episode 41923: reward = -56.82, steps = 29 06:11:30 [INFO] train episode 41924: reward = -122.95, steps = 30 06:11:33 [INFO] train episode 41925: reward = -150.93, steps = 40 06:11:36 [INFO] train episode 41926: reward = -84.65, steps = 32 06:11:38 [INFO] train episode 41927: reward = -86.24, steps = 21 06:11:40 [INFO] train episode 41928: reward = -64.79, steps = 21 06:11:43 [INFO] train episode 41929: reward = -91.58, steps = 26 06:11:45 [INFO] train episode 41930: reward = -128.24, steps = 30 06:11:48 [INFO] train episode 41931: reward = -109.29, steps = 25 06:11:50 [INFO] train episode 41932: reward = -77.88, steps = 23 06:11:52 [INFO] train episode 41933: reward = -89.88, steps = 28 06:11:55 [INFO] train episode 41934: reward = -150.55, steps = 39 06:11:57 [INFO] train episode 41935: reward = -110.12, steps = 21 06:12:00 [INFO] train episode 41936: reward = -86.82, steps = 30 06:12:02 [INFO] train episode 41937: reward = -101.60, steps = 29 06:12:08 [INFO] train episode 41938: reward = -191.81, steps = 66 06:12:10 [INFO] train episode 41939: reward = -84.15, steps = 23 06:12:13 [INFO] train episode 41940: reward = -87.47, steps = 35 06:12:15 [INFO] train episode 41941: reward = -48.08, steps = 20 06:12:17 [INFO] train episode 41942: reward = -70.97, steps = 27 06:12:20 [INFO] train episode 41943: reward = -114.60, steps = 30 06:12:22 [INFO] train episode 41944: reward = -70.30, steps = 24 06:12:24 [INFO] train episode 41945: reward = -98.27, steps = 27 06:12:26 [INFO] train episode 41946: reward = -95.30, steps = 23 06:12:29 [INFO] train episode 41947: reward = -104.99, steps = 29 06:12:31 [INFO] train episode 41948: reward = -97.90, steps = 24 06:12:34 [INFO] train episode 41949: reward = -64.58, steps = 37 06:12:37 [INFO] train episode 41950: reward = -74.79, steps = 35 06:12:39 [INFO] train episode 41951: reward = -143.00, steps = 26 06:12:41 [INFO] train episode 41952: reward = -79.01, steps = 21 06:12:43 [INFO] train episode 41953: reward = -65.92, steps = 22 06:12:47 [INFO] train episode 41954: reward = -89.06, steps = 33 06:12:50 [INFO] train episode 41955: reward = -65.45, steps = 36 06:12:52 [INFO] train episode 41956: reward = -97.45, steps = 25 06:12:54 [INFO] train episode 41957: reward = -95.98, steps = 24 06:12:56 [INFO] train episode 41958: reward = -74.42, steps = 21 06:12:57 [INFO] train episode 41959: reward = -63.99, steps = 20 06:12:59 [INFO] train episode 41960: reward = -53.98, steps = 22 06:13:03 [INFO] train episode 41961: reward = -119.19, steps = 36 06:13:05 [INFO] train episode 41962: reward = -68.31, steps = 21 06:13:06 [INFO] train episode 41963: reward = -68.96, steps = 19 06:13:08 [INFO] train episode 41964: reward = -76.89, steps = 19 06:13:11 [INFO] train episode 41965: reward = -165.98, steps = 43 06:13:13 [INFO] train episode 41966: reward = -103.58, steps = 22 06:13:15 [INFO] train episode 41967: reward = -204.39, steps = 21 06:13:17 [INFO] train episode 41968: reward = -90.70, steps = 23 06:13:20 [INFO] train episode 41969: reward = -98.25, steps = 26 06:13:21 [INFO] train episode 41970: reward = -61.04, steps = 21 06:13:23 [INFO] train episode 41971: reward = -110.10, steps = 19 06:13:25 [INFO] train episode 41972: reward = -69.64, steps = 25 06:13:28 [INFO] train episode 41973: reward = -135.51, steps = 27 06:13:29 [INFO] train episode 41974: reward = -95.46, steps = 19 06:13:31 [INFO] train episode 41975: reward = -77.11, steps = 20 06:13:34 [INFO] train episode 41976: reward = -92.40, steps = 32 06:13:36 [INFO] train episode 41977: reward = -109.95, steps = 26 06:13:39 [INFO] train episode 41978: reward = -89.63, steps = 29 06:13:41 [INFO] train episode 41979: reward = -80.30, steps = 26 06:13:43 [INFO] train episode 41980: reward = -45.26, steps = 22 06:13:45 [INFO] train episode 41981: reward = -71.14, steps = 30 06:13:47 [INFO] train episode 41982: reward = -78.77, steps = 21 06:13:50 [INFO] train episode 41983: reward = -136.92, steps = 28 06:13:52 [INFO] train episode 41984: reward = -99.30, steps = 29 06:13:54 [INFO] train episode 41985: reward = -80.58, steps = 22 06:13:56 [INFO] train episode 41986: reward = -83.81, steps = 20 06:13:59 [INFO] train episode 41987: reward = -151.07, steps = 40 06:14:02 [INFO] train episode 41988: reward = -52.60, steps = 28 06:14:03 [INFO] train episode 41989: reward = -89.15, steps = 20 06:14:06 [INFO] train episode 41990: reward = -89.98, steps = 21 06:14:08 [INFO] train episode 41991: reward = -118.21, steps = 25 06:14:10 [INFO] train episode 41992: reward = -123.37, steps = 29 06:14:13 [INFO] train episode 41993: reward = -151.47, steps = 37 06:14:15 [INFO] train episode 41994: reward = -60.41, steps = 21 06:14:18 [INFO] train episode 41995: reward = -118.97, steps = 32 06:14:20 [INFO] train episode 41996: reward = -84.66, steps = 20 06:14:24 [INFO] train episode 41997: reward = -142.55, steps = 52 06:14:27 [INFO] train episode 41998: reward = -114.42, steps = 35 06:14:29 [INFO] train episode 41999: reward = -102.97, steps = 25 06:14:33 [INFO] train episode 42000: reward = -90.09, steps = 26 06:14:35 [INFO] train episode 42001: reward = -65.08, steps = 26 06:14:38 [INFO] train episode 42002: reward = -71.49, steps = 32 06:14:41 [INFO] train episode 42003: reward = -47.20, steps = 30 06:14:43 [INFO] train episode 42004: reward = -93.24, steps = 24 06:14:45 [INFO] train episode 42005: reward = -112.06, steps = 25 06:14:47 [INFO] train episode 42006: reward = -124.98, steps = 20 06:14:49 [INFO] train episode 42007: reward = -111.10, steps = 31 06:14:53 [INFO] train episode 42008: reward = -123.37, steps = 33 06:14:55 [INFO] train episode 42009: reward = -96.24, steps = 24 06:14:57 [INFO] train episode 42010: reward = -90.55, steps = 24 06:15:00 [INFO] train episode 42011: reward = -108.65, steps = 34 06:15:04 [INFO] train episode 42012: reward = -104.75, steps = 47 06:15:05 [INFO] train episode 42013: reward = -76.10, steps = 22 06:15:08 [INFO] train episode 42014: reward = -96.95, steps = 27 06:15:11 [INFO] train episode 42015: reward = -106.97, steps = 35 06:15:13 [INFO] train episode 42016: reward = -87.51, steps = 19 06:15:15 [INFO] train episode 42017: reward = -67.29, steps = 23 06:15:16 [INFO] train episode 42018: reward = -42.41, steps = 20 06:15:18 [INFO] train episode 42019: reward = -90.12, steps = 21 06:15:20 [INFO] train episode 42020: reward = -80.12, steps = 21 06:15:22 [INFO] train episode 42021: reward = -97.36, steps = 19 06:15:24 [INFO] train episode 42022: reward = -97.43, steps = 23 06:15:26 [INFO] train episode 42023: reward = -86.21, steps = 28 06:15:30 [INFO] train episode 42024: reward = -70.71, steps = 37 06:15:31 [INFO] train episode 42025: reward = -81.78, steps = 22 06:15:34 [INFO] train episode 42026: reward = -132.07, steps = 30 06:15:37 [INFO] train episode 42027: reward = -130.29, steps = 32 06:15:40 [INFO] train episode 42028: reward = -138.75, steps = 36 06:15:42 [INFO] train episode 42029: reward = -74.09, steps = 25 06:15:44 [INFO] train episode 42030: reward = -121.38, steps = 22 06:15:46 [INFO] train episode 42031: reward = -72.53, steps = 27 06:15:49 [INFO] train episode 42032: reward = -135.52, steps = 25 06:15:51 [INFO] train episode 42033: reward = -107.33, steps = 27 06:15:52 [INFO] train episode 42034: reward = -62.35, steps = 19 06:15:54 [INFO] train episode 42035: reward = -131.31, steps = 23 06:15:57 [INFO] train episode 42036: reward = -72.78, steps = 26 06:16:00 [INFO] train episode 42037: reward = -83.48, steps = 34 06:16:03 [INFO] train episode 42038: reward = -126.08, steps = 32 06:16:06 [INFO] train episode 42039: reward = -171.08, steps = 40 06:16:09 [INFO] train episode 42040: reward = -79.55, steps = 33 06:16:12 [INFO] train episode 42041: reward = -71.64, steps = 27 06:16:14 [INFO] train episode 42042: reward = -121.06, steps = 25 06:16:15 [INFO] train episode 42043: reward = -84.64, steps = 19 06:16:17 [INFO] train episode 42044: reward = -105.73, steps = 25 06:16:19 [INFO] train episode 42045: reward = -76.86, steps = 22 06:16:22 [INFO] train episode 42046: reward = -97.73, steps = 27 06:16:24 [INFO] train episode 42047: reward = -86.29, steps = 22 06:16:28 [INFO] train episode 42048: reward = -184.75, steps = 44 06:16:30 [INFO] train episode 42049: reward = -74.57, steps = 30 06:16:32 [INFO] train episode 42050: reward = -76.86, steps = 19 06:16:34 [INFO] train episode 42051: reward = -91.24, steps = 21 06:16:36 [INFO] train episode 42052: reward = -113.58, steps = 24 06:16:38 [INFO] train episode 42053: reward = -120.57, steps = 28 06:16:40 [INFO] train episode 42054: reward = -49.99, steps = 19 06:16:44 [INFO] train episode 42055: reward = -178.96, steps = 41 06:16:46 [INFO] train episode 42056: reward = -55.07, steps = 22 06:16:48 [INFO] train episode 42057: reward = -71.75, steps = 22 06:16:51 [INFO] train episode 42058: reward = -106.31, steps = 40 06:16:53 [INFO] train episode 42059: reward = -98.15, steps = 30 06:16:57 [INFO] train episode 42060: reward = -174.86, steps = 42 06:16:59 [INFO] train episode 42061: reward = -47.69, steps = 19 06:17:01 [INFO] train episode 42062: reward = -122.50, steps = 19 06:17:03 [INFO] train episode 42063: reward = -82.06, steps = 23 06:17:04 [INFO] train episode 42064: reward = -50.97, steps = 20 06:17:06 [INFO] train episode 42065: reward = -95.50, steps = 21 06:17:09 [INFO] train episode 42066: reward = -68.24, steps = 31 06:17:11 [INFO] train episode 42067: reward = -95.15, steps = 26 06:17:14 [INFO] train episode 42068: reward = -137.46, steps = 29 06:17:16 [INFO] train episode 42069: reward = -104.40, steps = 20 06:17:18 [INFO] train episode 42070: reward = -62.08, steps = 27 06:17:20 [INFO] train episode 42071: reward = -106.17, steps = 27 06:17:23 [INFO] train episode 42072: reward = -107.06, steps = 22 06:17:25 [INFO] train episode 42073: reward = -77.47, steps = 19 06:17:27 [INFO] train episode 42074: reward = -71.52, steps = 23 06:17:29 [INFO] train episode 42075: reward = -123.90, steps = 23 06:17:31 [INFO] train episode 42076: reward = -84.90, steps = 28 06:17:34 [INFO] train episode 42077: reward = -141.29, steps = 28 06:17:37 [INFO] train episode 42078: reward = -136.32, steps = 34 06:17:39 [INFO] train episode 42079: reward = -66.50, steps = 28 06:17:42 [INFO] train episode 42080: reward = -78.28, steps = 30 06:17:44 [INFO] train episode 42081: reward = -129.03, steps = 26 06:17:46 [INFO] train episode 42082: reward = -69.75, steps = 26 06:17:49 [INFO] train episode 42083: reward = -113.85, steps = 36 06:17:51 [INFO] train episode 42084: reward = -102.27, steps = 21 06:17:53 [INFO] train episode 42085: reward = -55.36, steps = 27 06:17:56 [INFO] train episode 42086: reward = -52.65, steps = 26 06:17:57 [INFO] train episode 42087: reward = -119.29, steps = 20 06:17:59 [INFO] train episode 42088: reward = -107.95, steps = 25 06:18:02 [INFO] train episode 42089: reward = -101.62, steps = 28 06:18:05 [INFO] train episode 42090: reward = -114.98, steps = 32 06:18:07 [INFO] train episode 42091: reward = -81.39, steps = 22 06:18:09 [INFO] train episode 42092: reward = -138.15, steps = 32 06:18:12 [INFO] train episode 42093: reward = -147.11, steps = 31 06:18:15 [INFO] train episode 42094: reward = -91.69, steps = 35 06:18:17 [INFO] train episode 42095: reward = -54.59, steps = 21 06:18:19 [INFO] train episode 42096: reward = -68.73, steps = 22 06:18:21 [INFO] train episode 42097: reward = -80.38, steps = 19 06:18:22 [INFO] train episode 42098: reward = -71.14, steps = 21 06:18:25 [INFO] train episode 42099: reward = -65.61, steps = 28 06:18:27 [INFO] train episode 42100: reward = -68.50, steps = 18 06:18:29 [INFO] train episode 42101: reward = -83.34, steps = 27 06:18:31 [INFO] train episode 42102: reward = -83.90, steps = 23 06:18:33 [INFO] train episode 42103: reward = -72.54, steps = 24 06:18:37 [INFO] train episode 42104: reward = -66.06, steps = 37 06:18:38 [INFO] train episode 42105: reward = -102.14, steps = 21 06:18:40 [INFO] train episode 42106: reward = -87.57, steps = 25 06:18:43 [INFO] train episode 42107: reward = -105.83, steps = 25 06:18:45 [INFO] train episode 42108: reward = -117.81, steps = 28 06:18:48 [INFO] train episode 42109: reward = -85.94, steps = 34 06:18:51 [INFO] train episode 42110: reward = -153.26, steps = 31 06:18:54 [INFO] train episode 42111: reward = -126.49, steps = 33 06:18:56 [INFO] train episode 42112: reward = -91.69, steps = 24 06:18:59 [INFO] train episode 42113: reward = -98.18, steps = 33 06:19:01 [INFO] train episode 42114: reward = -91.22, steps = 30 06:19:04 [INFO] train episode 42115: reward = -97.79, steps = 30 06:19:07 [INFO] train episode 42116: reward = -50.92, steps = 32 06:19:09 [INFO] train episode 42117: reward = -88.62, steps = 22 06:19:12 [INFO] train episode 42118: reward = -96.75, steps = 31 06:19:14 [INFO] train episode 42119: reward = -72.72, steps = 23 06:19:15 [INFO] train episode 42120: reward = -147.67, steps = 18 06:19:17 [INFO] train episode 42121: reward = -91.42, steps = 21 06:19:19 [INFO] train episode 42122: reward = -110.83, steps = 25 06:19:21 [INFO] train episode 42123: reward = -71.11, steps = 21 06:19:23 [INFO] train episode 42124: reward = -72.50, steps = 22 06:19:25 [INFO] train episode 42125: reward = -117.71, steps = 27 06:19:27 [INFO] train episode 42126: reward = -82.31, steps = 18 06:19:29 [INFO] train episode 42127: reward = -85.62, steps = 29 06:19:31 [INFO] train episode 42128: reward = -77.51, steps = 19 06:19:33 [INFO] train episode 42129: reward = -69.72, steps = 24 06:19:35 [INFO] train episode 42130: reward = -82.49, steps = 23 06:19:37 [INFO] train episode 42131: reward = -88.06, steps = 24 06:19:39 [INFO] train episode 42132: reward = -57.18, steps = 20 06:19:41 [INFO] train episode 42133: reward = -153.32, steps = 22 06:19:43 [INFO] train episode 42134: reward = -60.62, steps = 20 06:19:45 [INFO] train episode 42135: reward = -80.86, steps = 22 06:19:47 [INFO] train episode 42136: reward = -63.73, steps = 27 06:19:50 [INFO] train episode 42137: reward = -68.06, steps = 29 06:19:52 [INFO] train episode 42138: reward = -114.15, steps = 27 06:19:54 [INFO] train episode 42139: reward = -73.85, steps = 23 06:19:58 [INFO] train episode 42140: reward = -76.19, steps = 42 06:20:00 [INFO] train episode 42141: reward = -80.81, steps = 24 06:20:02 [INFO] train episode 42142: reward = -96.84, steps = 21 06:20:04 [INFO] train episode 42143: reward = -87.63, steps = 24 06:20:06 [INFO] train episode 42144: reward = -89.39, steps = 27 06:20:08 [INFO] train episode 42145: reward = -65.73, steps = 20 06:20:10 [INFO] train episode 42146: reward = -85.07, steps = 22 06:20:13 [INFO] train episode 42147: reward = -129.01, steps = 28 06:20:15 [INFO] train episode 42148: reward = -109.24, steps = 25 06:20:18 [INFO] train episode 42149: reward = -101.46, steps = 28 06:20:19 [INFO] train episode 42150: reward = -48.61, steps = 15 06:20:21 [INFO] train episode 42151: reward = -90.86, steps = 20 06:20:23 [INFO] train episode 42152: reward = -157.88, steps = 28 06:20:27 [INFO] train episode 42153: reward = -107.63, steps = 38 06:20:29 [INFO] train episode 42154: reward = -69.96, steps = 32 06:20:31 [INFO] train episode 42155: reward = -77.22, steps = 18 06:20:33 [INFO] train episode 42156: reward = -76.81, steps = 19 06:20:35 [INFO] train episode 42157: reward = -103.25, steps = 32 06:20:38 [INFO] train episode 42158: reward = -99.35, steps = 25 06:20:39 [INFO] train episode 42159: reward = -102.15, steps = 21 06:20:41 [INFO] train episode 42160: reward = -58.17, steps = 23 06:20:45 [INFO] train episode 42161: reward = -144.99, steps = 35 06:20:47 [INFO] train episode 42162: reward = -56.85, steps = 21 06:20:49 [INFO] train episode 42163: reward = -138.21, steps = 33 06:20:51 [INFO] train episode 42164: reward = -66.10, steps = 19 06:20:54 [INFO] train episode 42165: reward = -53.04, steps = 22 06:20:56 [INFO] train episode 42166: reward = -95.44, steps = 20 06:20:58 [INFO] train episode 42167: reward = -97.57, steps = 20 06:21:01 [INFO] train episode 42168: reward = -113.98, steps = 31 06:21:03 [INFO] train episode 42169: reward = -137.69, steps = 27 06:21:07 [INFO] train episode 42170: reward = -97.77, steps = 38 06:21:09 [INFO] train episode 42171: reward = -104.93, steps = 25 06:21:11 [INFO] train episode 42172: reward = -55.22, steps = 21 06:21:14 [INFO] train episode 42173: reward = -84.00, steps = 25 06:21:15 [INFO] train episode 42174: reward = -85.44, steps = 19 06:21:18 [INFO] train episode 42175: reward = -72.74, steps = 25 06:21:20 [INFO] train episode 42176: reward = -131.29, steps = 22 06:21:23 [INFO] train episode 42177: reward = -125.65, steps = 32 06:21:24 [INFO] train episode 42178: reward = -62.74, steps = 20 06:21:26 [INFO] train episode 42179: reward = -69.03, steps = 20 06:21:29 [INFO] train episode 42180: reward = -94.29, steps = 38 06:21:31 [INFO] train episode 42181: reward = -86.57, steps = 23 06:21:33 [INFO] train episode 42182: reward = -71.61, steps = 22 06:21:35 [INFO] train episode 42183: reward = -59.46, steps = 23 06:21:38 [INFO] train episode 42184: reward = -94.58, steps = 30 06:21:41 [INFO] train episode 42185: reward = -115.65, steps = 38 06:21:44 [INFO] train episode 42186: reward = -137.05, steps = 40 06:21:48 [INFO] train episode 42187: reward = -106.38, steps = 37 06:21:50 [INFO] train episode 42188: reward = -87.74, steps = 27 06:21:52 [INFO] train episode 42189: reward = -81.59, steps = 23 06:21:55 [INFO] train episode 42190: reward = -102.26, steps = 31 06:21:56 [INFO] train episode 42191: reward = -61.57, steps = 18 06:21:59 [INFO] train episode 42192: reward = -75.36, steps = 33 06:22:01 [INFO] train episode 42193: reward = -66.61, steps = 23 06:22:03 [INFO] train episode 42194: reward = -132.57, steps = 21 06:22:05 [INFO] train episode 42195: reward = -75.75, steps = 23 06:22:08 [INFO] train episode 42196: reward = -76.31, steps = 30 06:22:10 [INFO] train episode 42197: reward = -149.97, steps = 27 06:22:12 [INFO] train episode 42198: reward = -50.46, steps = 19 06:22:14 [INFO] train episode 42199: reward = -60.31, steps = 23 06:22:16 [INFO] train episode 42200: reward = -82.34, steps = 24 06:22:17 [INFO] train episode 42201: reward = -90.32, steps = 18 06:22:20 [INFO] train episode 42202: reward = -78.14, steps = 23 06:22:21 [INFO] train episode 42203: reward = -107.85, steps = 22 06:22:23 [INFO] train episode 42204: reward = -94.50, steps = 21 06:22:25 [INFO] train episode 42205: reward = -101.72, steps = 23 06:22:27 [INFO] train episode 42206: reward = -126.26, steps = 19 06:22:29 [INFO] train episode 42207: reward = -63.23, steps = 20 06:22:31 [INFO] train episode 42208: reward = -33.90, steps = 24 06:22:32 [INFO] train episode 42209: reward = -77.58, steps = 21 06:22:35 [INFO] train episode 42210: reward = -93.87, steps = 21 06:22:38 [INFO] train episode 42211: reward = -68.87, steps = 35 06:22:42 [INFO] train episode 42212: reward = -98.68, steps = 45 06:22:45 [INFO] train episode 42213: reward = -76.29, steps = 37 06:22:47 [INFO] train episode 42214: reward = -83.39, steps = 26 06:22:49 [INFO] train episode 42215: reward = -66.34, steps = 24 06:22:52 [INFO] train episode 42216: reward = -93.76, steps = 30 06:22:55 [INFO] train episode 42217: reward = -53.32, steps = 38 06:22:58 [INFO] train episode 42218: reward = -92.82, steps = 29 06:23:00 [INFO] train episode 42219: reward = -52.42, steps = 24 06:23:02 [INFO] train episode 42220: reward = -49.73, steps = 25 06:23:04 [INFO] train episode 42221: reward = -125.69, steps = 22 06:23:06 [INFO] train episode 42222: reward = -98.73, steps = 22 06:23:09 [INFO] train episode 42223: reward = -149.80, steps = 30 06:23:12 [INFO] train episode 42224: reward = -81.33, steps = 27 06:23:14 [INFO] train episode 42225: reward = -38.13, steps = 23 06:23:15 [INFO] train episode 42226: reward = -73.61, steps = 22 06:23:18 [INFO] train episode 42227: reward = -76.04, steps = 27 06:23:20 [INFO] train episode 42228: reward = -83.00, steps = 22 06:23:22 [INFO] train episode 42229: reward = -83.97, steps = 27 06:23:24 [INFO] train episode 42230: reward = -135.74, steps = 24 06:23:27 [INFO] train episode 42231: reward = -79.68, steps = 34 06:23:29 [INFO] train episode 42232: reward = -101.34, steps = 22 06:23:31 [INFO] train episode 42233: reward = -113.84, steps = 20 06:23:33 [INFO] train episode 42234: reward = -74.97, steps = 22 06:23:36 [INFO] train episode 42235: reward = -80.56, steps = 32 06:23:38 [INFO] train episode 42236: reward = -57.11, steps = 24 06:23:40 [INFO] train episode 42237: reward = -59.29, steps = 18 06:23:44 [INFO] train episode 42238: reward = -102.54, steps = 38 06:23:48 [INFO] train episode 42239: reward = -123.05, steps = 48 06:23:50 [INFO] train episode 42240: reward = -71.50, steps = 20 06:23:52 [INFO] train episode 42241: reward = -86.77, steps = 27 06:23:56 [INFO] train episode 42242: reward = -105.65, steps = 39 06:23:58 [INFO] train episode 42243: reward = -78.32, steps = 21 06:24:00 [INFO] train episode 42244: reward = -69.07, steps = 19 06:24:03 [INFO] train episode 42245: reward = -86.43, steps = 27 06:24:04 [INFO] train episode 42246: reward = -74.87, steps = 20 06:24:06 [INFO] train episode 42247: reward = -69.26, steps = 20 06:24:08 [INFO] train episode 42248: reward = -80.26, steps = 18 06:24:10 [INFO] train episode 42249: reward = -66.35, steps = 22 06:24:13 [INFO] train episode 42250: reward = -72.17, steps = 27 06:24:15 [INFO] train episode 42251: reward = -101.28, steps = 21 06:24:18 [INFO] train episode 42252: reward = -95.35, steps = 32 06:24:20 [INFO] train episode 42253: reward = -107.28, steps = 19 06:24:23 [INFO] train episode 42254: reward = -79.21, steps = 23 06:24:25 [INFO] train episode 42255: reward = -114.80, steps = 24 06:24:28 [INFO] train episode 42256: reward = -88.65, steps = 32 06:24:30 [INFO] train episode 42257: reward = -79.67, steps = 22 06:24:32 [INFO] train episode 42258: reward = -64.45, steps = 25 06:24:35 [INFO] train episode 42259: reward = -106.62, steps = 31 06:24:37 [INFO] train episode 42260: reward = -52.55, steps = 20 06:24:39 [INFO] train episode 42261: reward = -52.37, steps = 20 06:24:41 [INFO] train episode 42262: reward = -108.45, steps = 26 06:24:44 [INFO] train episode 42263: reward = -106.79, steps = 37 06:24:47 [INFO] train episode 42264: reward = -145.49, steps = 26 06:24:50 [INFO] train episode 42265: reward = -69.20, steps = 24 06:24:51 [INFO] train episode 42266: reward = -118.19, steps = 19 06:24:54 [INFO] train episode 42267: reward = -46.83, steps = 24 06:24:57 [INFO] train episode 42268: reward = -124.00, steps = 33 06:25:00 [INFO] train episode 42269: reward = -104.27, steps = 34 06:25:02 [INFO] train episode 42270: reward = -95.45, steps = 30 06:25:05 [INFO] train episode 42271: reward = -71.67, steps = 24 06:25:07 [INFO] train episode 42272: reward = -61.16, steps = 23 06:25:09 [INFO] train episode 42273: reward = -96.24, steps = 32 06:25:11 [INFO] train episode 42274: reward = -59.02, steps = 17 06:25:13 [INFO] train episode 42275: reward = -71.84, steps = 21 06:25:14 [INFO] train episode 42276: reward = -137.47, steps = 19 06:25:17 [INFO] train episode 42277: reward = -92.21, steps = 25 06:25:18 [INFO] train episode 42278: reward = -62.44, steps = 22 06:25:21 [INFO] train episode 42279: reward = -88.42, steps = 24 06:25:23 [INFO] train episode 42280: reward = -84.81, steps = 23 06:25:27 [INFO] train episode 42281: reward = -97.76, steps = 45 06:25:28 [INFO] train episode 42282: reward = -68.77, steps = 18 06:25:32 [INFO] train episode 42283: reward = -106.51, steps = 40 06:25:34 [INFO] train episode 42284: reward = -88.84, steps = 24 06:25:36 [INFO] train episode 42285: reward = -79.88, steps = 26 06:25:38 [INFO] train episode 42286: reward = -57.62, steps = 18 06:25:40 [INFO] train episode 42287: reward = -75.28, steps = 22 06:25:42 [INFO] train episode 42288: reward = -61.74, steps = 23 06:25:44 [INFO] train episode 42289: reward = -85.12, steps = 19 06:25:46 [INFO] train episode 42290: reward = -66.77, steps = 23 06:25:47 [INFO] train episode 42291: reward = -92.63, steps = 18 06:25:49 [INFO] train episode 42292: reward = -92.22, steps = 24 06:25:51 [INFO] train episode 42293: reward = -76.70, steps = 25 06:25:54 [INFO] train episode 42294: reward = -87.39, steps = 26 06:25:57 [INFO] train episode 42295: reward = -79.49, steps = 32 06:25:58 [INFO] train episode 42296: reward = -62.12, steps = 19 06:26:00 [INFO] train episode 42297: reward = -94.33, steps = 22 06:26:02 [INFO] train episode 42298: reward = -117.38, steps = 25 06:26:05 [INFO] train episode 42299: reward = -79.16, steps = 21 06:26:08 [INFO] train episode 42300: reward = -79.20, steps = 31 06:26:11 [INFO] train episode 42301: reward = -64.29, steps = 32 06:26:13 [INFO] train episode 42302: reward = -83.64, steps = 26 06:26:15 [INFO] train episode 42303: reward = -86.90, steps = 23 06:26:17 [INFO] train episode 42304: reward = -96.91, steps = 18 06:26:19 [INFO] train episode 42305: reward = -127.83, steps = 32 06:26:21 [INFO] train episode 42306: reward = -83.63, steps = 20 06:26:23 [INFO] train episode 42307: reward = -62.74, steps = 19 06:26:26 [INFO] train episode 42308: reward = -158.67, steps = 37 06:26:28 [INFO] train episode 42309: reward = -77.34, steps = 23 06:26:30 [INFO] train episode 42310: reward = -39.14, steps = 19 06:26:32 [INFO] train episode 42311: reward = -92.95, steps = 26 06:26:34 [INFO] train episode 42312: reward = -112.62, steps = 26 06:26:36 [INFO] train episode 42313: reward = -65.06, steps = 20 06:26:39 [INFO] train episode 42314: reward = -170.83, steps = 33 06:26:41 [INFO] train episode 42315: reward = -50.35, steps = 18 06:26:43 [INFO] train episode 42316: reward = -87.40, steps = 29 06:26:45 [INFO] train episode 42317: reward = -35.45, steps = 21 06:26:47 [INFO] train episode 42318: reward = -54.24, steps = 25 06:26:49 [INFO] train episode 42319: reward = -67.73, steps = 19 06:26:51 [INFO] train episode 42320: reward = -82.83, steps = 23 06:26:53 [INFO] train episode 42321: reward = -71.71, steps = 20 06:26:55 [INFO] train episode 42322: reward = -108.69, steps = 27 06:27:00 [INFO] train episode 42323: reward = -184.89, steps = 50 06:27:03 [INFO] train episode 42324: reward = -101.43, steps = 37 06:27:04 [INFO] train episode 42325: reward = -91.60, steps = 19 06:27:07 [INFO] train episode 42326: reward = -138.05, steps = 33 06:27:09 [INFO] train episode 42327: reward = -64.08, steps = 22 06:27:12 [INFO] train episode 42328: reward = -138.48, steps = 32 06:27:15 [INFO] train episode 42329: reward = -107.41, steps = 33 06:27:17 [INFO] train episode 42330: reward = -121.32, steps = 20 06:27:18 [INFO] train episode 42331: reward = -98.69, steps = 21 06:27:20 [INFO] train episode 42332: reward = -78.08, steps = 21 06:27:23 [INFO] train episode 42333: reward = -116.41, steps = 36 06:27:25 [INFO] train episode 42334: reward = -87.29, steps = 19 06:27:27 [INFO] train episode 42335: reward = -104.31, steps = 25 06:27:30 [INFO] train episode 42336: reward = -75.19, steps = 26 06:27:32 [INFO] train episode 42337: reward = -109.88, steps = 27 06:27:34 [INFO] train episode 42338: reward = -86.24, steps = 27 06:27:36 [INFO] train episode 42339: reward = -78.90, steps = 19 06:27:38 [INFO] train episode 42340: reward = -70.25, steps = 18 06:27:40 [INFO] train episode 42341: reward = -96.47, steps = 29 06:27:44 [INFO] train episode 42342: reward = -74.02, steps = 41 06:27:46 [INFO] train episode 42343: reward = -108.74, steps = 25 06:27:50 [INFO] train episode 42344: reward = -130.55, steps = 38 06:27:52 [INFO] train episode 42345: reward = -86.11, steps = 26 06:27:54 [INFO] train episode 42346: reward = -76.83, steps = 28 06:27:56 [INFO] train episode 42347: reward = -70.95, steps = 20 06:27:58 [INFO] train episode 42348: reward = -106.19, steps = 27 06:28:01 [INFO] train episode 42349: reward = -76.24, steps = 23 06:28:03 [INFO] train episode 42350: reward = -81.82, steps = 22 06:28:05 [INFO] train episode 42351: reward = -91.94, steps = 33 06:28:09 [INFO] train episode 42352: reward = -97.09, steps = 46 06:28:12 [INFO] train episode 42353: reward = -104.16, steps = 32 06:28:15 [INFO] train episode 42354: reward = -75.72, steps = 37 06:28:18 [INFO] train episode 42355: reward = -110.58, steps = 26 06:28:20 [INFO] train episode 42356: reward = -113.78, steps = 24 06:28:22 [INFO] train episode 42357: reward = -106.75, steps = 28 06:28:24 [INFO] train episode 42358: reward = -75.16, steps = 22 06:28:26 [INFO] train episode 42359: reward = -73.52, steps = 25 06:28:29 [INFO] train episode 42360: reward = -105.70, steps = 28 06:28:31 [INFO] train episode 42361: reward = -68.13, steps = 27 06:28:34 [INFO] train episode 42362: reward = -65.09, steps = 23 06:28:36 [INFO] train episode 42363: reward = -67.44, steps = 24 06:28:38 [INFO] train episode 42364: reward = -86.35, steps = 27 06:28:40 [INFO] train episode 42365: reward = -65.02, steps = 20 06:28:42 [INFO] train episode 42366: reward = -72.13, steps = 20 06:28:45 [INFO] train episode 42367: reward = -60.79, steps = 37 06:28:47 [INFO] train episode 42368: reward = -54.96, steps = 20 06:28:49 [INFO] train episode 42369: reward = -117.19, steps = 26 06:28:51 [INFO] train episode 42370: reward = -73.82, steps = 23 06:28:53 [INFO] train episode 42371: reward = -80.31, steps = 18 06:28:55 [INFO] train episode 42372: reward = -142.69, steps = 23 06:28:58 [INFO] train episode 42373: reward = -76.96, steps = 32 06:29:01 [INFO] train episode 42374: reward = -40.55, steps = 25 06:29:03 [INFO] train episode 42375: reward = -46.92, steps = 19 06:29:05 [INFO] train episode 42376: reward = -89.22, steps = 25 06:29:08 [INFO] train episode 42377: reward = -106.36, steps = 30 06:29:11 [INFO] train episode 42378: reward = -58.57, steps = 21 06:29:13 [INFO] train episode 42379: reward = -84.25, steps = 24 06:29:15 [INFO] train episode 42380: reward = -65.19, steps = 19 06:29:18 [INFO] train episode 42381: reward = -109.93, steps = 31 06:29:20 [INFO] train episode 42382: reward = -101.54, steps = 26 06:29:22 [INFO] train episode 42383: reward = -61.71, steps = 20 06:29:24 [INFO] train episode 42384: reward = -47.84, steps = 20 06:29:27 [INFO] train episode 42385: reward = -104.06, steps = 26 06:29:32 [INFO] train episode 42386: reward = -132.35, steps = 43 06:29:34 [INFO] train episode 42387: reward = -86.42, steps = 27 06:29:36 [INFO] train episode 42388: reward = -76.46, steps = 22 06:29:38 [INFO] train episode 42389: reward = -71.33, steps = 20 06:29:40 [INFO] train episode 42390: reward = -62.64, steps = 18 06:29:43 [INFO] train episode 42391: reward = -95.61, steps = 30 06:29:46 [INFO] train episode 42392: reward = -56.41, steps = 32 06:29:49 [INFO] train episode 42393: reward = -112.92, steps = 34 06:29:52 [INFO] train episode 42394: reward = -80.01, steps = 24 06:29:54 [INFO] train episode 42395: reward = -124.10, steps = 25 06:29:57 [INFO] train episode 42396: reward = -94.58, steps = 31 06:30:00 [INFO] train episode 42397: reward = -76.19, steps = 32 06:30:03 [INFO] train episode 42398: reward = -55.80, steps = 26 06:30:05 [INFO] train episode 42399: reward = -82.19, steps = 27 06:30:07 [INFO] train episode 42400: reward = -68.31, steps = 20 06:30:10 [INFO] train episode 42401: reward = -68.33, steps = 26 06:30:12 [INFO] train episode 42402: reward = -127.30, steps = 26 06:30:15 [INFO] train episode 42403: reward = -74.37, steps = 29 06:30:17 [INFO] train episode 42404: reward = -65.25, steps = 19 06:30:19 [INFO] train episode 42405: reward = -97.64, steps = 21 06:30:21 [INFO] train episode 42406: reward = -74.66, steps = 20 06:30:23 [INFO] train episode 42407: reward = -74.52, steps = 25 06:30:25 [INFO] train episode 42408: reward = -73.96, steps = 18 06:30:27 [INFO] train episode 42409: reward = -47.86, steps = 24 06:30:29 [INFO] train episode 42410: reward = -99.60, steps = 23 06:30:31 [INFO] train episode 42411: reward = -92.23, steps = 20 06:30:34 [INFO] train episode 42412: reward = -105.61, steps = 34 06:30:37 [INFO] train episode 42413: reward = -112.98, steps = 25 06:30:39 [INFO] train episode 42414: reward = -90.60, steps = 24 06:30:41 [INFO] train episode 42415: reward = -106.19, steps = 19 06:30:43 [INFO] train episode 42416: reward = -70.19, steps = 24 06:30:45 [INFO] train episode 42417: reward = -120.04, steps = 23 06:30:48 [INFO] train episode 42418: reward = -79.60, steps = 25 06:30:50 [INFO] train episode 42419: reward = -90.83, steps = 28 06:30:53 [INFO] train episode 42420: reward = -139.30, steps = 26 06:30:56 [INFO] train episode 42421: reward = -101.56, steps = 28 06:30:58 [INFO] train episode 42422: reward = -56.69, steps = 22 06:31:00 [INFO] train episode 42423: reward = -63.58, steps = 18 06:31:02 [INFO] train episode 42424: reward = -77.32, steps = 27 06:31:06 [INFO] train episode 42425: reward = -77.04, steps = 39 06:31:08 [INFO] train episode 42426: reward = -90.73, steps = 24 06:31:11 [INFO] train episode 42427: reward = -91.39, steps = 24 06:31:13 [INFO] train episode 42428: reward = -51.96, steps = 19 06:31:15 [INFO] train episode 42429: reward = -82.91, steps = 20 06:31:17 [INFO] train episode 42430: reward = -126.51, steps = 25 06:31:19 [INFO] train episode 42431: reward = -100.61, steps = 26 06:31:23 [INFO] train episode 42432: reward = -95.53, steps = 36 06:31:25 [INFO] train episode 42433: reward = -115.92, steps = 26 06:31:28 [INFO] train episode 42434: reward = -95.54, steps = 29 06:31:30 [INFO] train episode 42435: reward = -91.78, steps = 21 06:31:32 [INFO] train episode 42436: reward = -122.66, steps = 25 06:31:34 [INFO] train episode 42437: reward = -50.62, steps = 21 06:31:36 [INFO] train episode 42438: reward = -48.65, steps = 21 06:31:39 [INFO] train episode 42439: reward = -115.58, steps = 25 06:31:41 [INFO] train episode 42440: reward = -60.00, steps = 20 06:31:43 [INFO] train episode 42441: reward = -85.22, steps = 22 06:31:45 [INFO] train episode 42442: reward = -95.22, steps = 22 06:31:47 [INFO] train episode 42443: reward = -97.51, steps = 23 06:31:50 [INFO] train episode 42444: reward = -110.46, steps = 24 06:31:51 [INFO] train episode 42445: reward = -77.94, steps = 18 06:31:54 [INFO] train episode 42446: reward = -83.61, steps = 24 06:31:56 [INFO] train episode 42447: reward = -99.43, steps = 28 06:31:58 [INFO] train episode 42448: reward = -54.89, steps = 22 06:32:03 [INFO] train episode 42449: reward = -153.02, steps = 42 06:32:05 [INFO] train episode 42450: reward = -71.32, steps = 23 06:32:08 [INFO] train episode 42451: reward = -93.14, steps = 29 06:32:11 [INFO] train episode 42452: reward = -86.10, steps = 35 06:32:13 [INFO] train episode 42453: reward = -73.82, steps = 23 06:32:16 [INFO] train episode 42454: reward = -141.83, steps = 24 06:32:18 [INFO] train episode 42455: reward = -100.62, steps = 25 06:32:20 [INFO] train episode 42456: reward = -84.43, steps = 18 06:32:22 [INFO] train episode 42457: reward = -50.30, steps = 19 06:32:24 [INFO] train episode 42458: reward = -71.91, steps = 25 06:32:26 [INFO] train episode 42459: reward = -124.85, steps = 25 06:32:29 [INFO] train episode 42460: reward = -97.17, steps = 25 06:32:31 [INFO] train episode 42461: reward = -79.17, steps = 20 06:32:32 [INFO] train episode 42462: reward = -80.66, steps = 20 06:32:34 [INFO] train episode 42463: reward = -121.23, steps = 23 06:32:37 [INFO] train episode 42464: reward = -94.84, steps = 23 06:32:40 [INFO] train episode 42465: reward = -105.41, steps = 27 06:32:42 [INFO] train episode 42466: reward = -80.96, steps = 24 06:32:44 [INFO] train episode 42467: reward = -81.31, steps = 26 06:32:47 [INFO] train episode 42468: reward = -81.65, steps = 27 06:32:49 [INFO] train episode 42469: reward = -105.56, steps = 19 06:32:51 [INFO] train episode 42470: reward = -115.34, steps = 25 06:32:53 [INFO] train episode 42471: reward = -72.43, steps = 21 06:32:56 [INFO] train episode 42472: reward = -98.21, steps = 24 06:32:57 [INFO] train episode 42473: reward = -67.37, steps = 16 06:32:59 [INFO] train episode 42474: reward = -69.78, steps = 21 06:33:01 [INFO] train episode 42475: reward = -98.50, steps = 22 06:33:03 [INFO] train episode 42476: reward = -82.35, steps = 19 06:33:05 [INFO] train episode 42477: reward = -71.28, steps = 19 06:33:07 [INFO] train episode 42478: reward = -88.34, steps = 22 06:33:10 [INFO] train episode 42479: reward = -34.80, steps = 29 06:33:15 [INFO] train episode 42480: reward = -116.43, steps = 41 06:33:17 [INFO] train episode 42481: reward = -69.57, steps = 24 06:33:20 [INFO] train episode 42482: reward = -83.72, steps = 22 06:33:22 [INFO] train episode 42483: reward = -89.59, steps = 22 06:33:24 [INFO] train episode 42484: reward = -47.93, steps = 21 06:33:26 [INFO] train episode 42485: reward = -95.03, steps = 28 06:33:29 [INFO] train episode 42486: reward = -85.79, steps = 24 06:33:32 [INFO] train episode 42487: reward = -80.75, steps = 29 06:33:34 [INFO] train episode 42488: reward = -98.54, steps = 23 06:33:36 [INFO] train episode 42489: reward = -121.11, steps = 27 06:33:39 [INFO] train episode 42490: reward = -68.57, steps = 24 06:33:41 [INFO] train episode 42491: reward = -145.35, steps = 29 06:33:43 [INFO] train episode 42492: reward = -64.06, steps = 19 06:33:46 [INFO] train episode 42493: reward = -86.95, steps = 29 06:33:48 [INFO] train episode 42494: reward = -54.17, steps = 19 06:33:50 [INFO] train episode 42495: reward = -101.37, steps = 31 06:33:52 [INFO] train episode 42496: reward = -55.53, steps = 24 06:33:54 [INFO] train episode 42497: reward = -46.02, steps = 24 06:33:56 [INFO] train episode 42498: reward = -67.04, steps = 20 06:33:59 [INFO] train episode 42499: reward = -93.86, steps = 27 06:34:01 [INFO] train episode 42500: reward = -99.32, steps = 24 06:34:03 [INFO] train episode 42501: reward = -82.44, steps = 25 06:34:05 [INFO] train episode 42502: reward = -93.97, steps = 21 06:34:07 [INFO] train episode 42503: reward = -59.73, steps = 20 06:34:08 [INFO] train episode 42504: reward = -106.68, steps = 21 06:34:10 [INFO] train episode 42505: reward = -54.52, steps = 20 06:34:12 [INFO] train episode 42506: reward = -97.22, steps = 25 06:34:14 [INFO] train episode 42507: reward = -84.88, steps = 18 06:34:16 [INFO] train episode 42508: reward = -74.43, steps = 26 06:34:18 [INFO] train episode 42509: reward = -45.84, steps = 21 06:34:20 [INFO] train episode 42510: reward = -97.63, steps = 22 06:34:23 [INFO] train episode 42511: reward = -121.50, steps = 38 06:34:25 [INFO] train episode 42512: reward = -98.92, steps = 19 06:34:27 [INFO] train episode 42513: reward = -103.97, steps = 24 06:34:29 [INFO] train episode 42514: reward = -69.37, steps = 22 06:34:31 [INFO] train episode 42515: reward = -74.18, steps = 24 06:34:34 [INFO] train episode 42516: reward = -123.81, steps = 29 06:34:37 [INFO] train episode 42517: reward = -100.16, steps = 32 06:34:40 [INFO] train episode 42518: reward = -95.42, steps = 33 06:34:42 [INFO] train episode 42519: reward = -96.77, steps = 25 06:34:44 [INFO] train episode 42520: reward = -73.65, steps = 25 06:34:46 [INFO] train episode 42521: reward = -79.75, steps = 22 06:34:48 [INFO] train episode 42522: reward = -68.20, steps = 19 06:34:50 [INFO] train episode 42523: reward = -63.66, steps = 29 06:34:53 [INFO] train episode 42524: reward = -73.20, steps = 27 06:34:55 [INFO] train episode 42525: reward = -90.06, steps = 23 06:34:57 [INFO] train episode 42526: reward = -144.66, steps = 28 06:35:00 [INFO] train episode 42527: reward = -108.40, steps = 28 06:35:02 [INFO] train episode 42528: reward = -76.55, steps = 23 06:35:03 [INFO] train episode 42529: reward = -67.73, steps = 17 06:35:05 [INFO] train episode 42530: reward = -78.11, steps = 21 06:35:08 [INFO] train episode 42531: reward = -76.56, steps = 25 06:35:10 [INFO] train episode 42532: reward = -91.69, steps = 24 06:35:12 [INFO] train episode 42533: reward = -94.30, steps = 19 06:35:14 [INFO] train episode 42534: reward = -98.87, steps = 19 06:35:15 [INFO] train episode 42535: reward = -57.09, steps = 21 06:35:17 [INFO] train episode 42536: reward = -79.35, steps = 20 06:35:19 [INFO] train episode 42537: reward = -61.90, steps = 26 06:35:22 [INFO] train episode 42538: reward = -79.51, steps = 20 06:35:24 [INFO] train episode 42539: reward = -74.15, steps = 25 06:35:25 [INFO] train episode 42540: reward = -49.70, steps = 20 06:35:28 [INFO] train episode 42541: reward = -64.85, steps = 34 06:35:30 [INFO] train episode 42542: reward = -62.84, steps = 21 06:35:33 [INFO] train episode 42543: reward = -66.03, steps = 27 06:35:34 [INFO] train episode 42544: reward = -61.95, steps = 22 06:35:36 [INFO] train episode 42545: reward = -71.75, steps = 22 06:35:39 [INFO] train episode 42546: reward = -75.06, steps = 22 06:35:41 [INFO] train episode 42547: reward = -110.81, steps = 27 06:35:43 [INFO] train episode 42548: reward = -91.19, steps = 26 06:35:45 [INFO] train episode 42549: reward = -83.70, steps = 21 06:35:47 [INFO] train episode 42550: reward = -64.08, steps = 20 06:35:50 [INFO] train episode 42551: reward = -111.55, steps = 35 06:35:52 [INFO] train episode 42552: reward = -114.73, steps = 29 06:35:55 [INFO] train episode 42553: reward = -78.89, steps = 23 06:35:57 [INFO] train episode 42554: reward = -95.66, steps = 34 06:35:59 [INFO] train episode 42555: reward = -81.96, steps = 22 06:36:01 [INFO] train episode 42556: reward = -62.33, steps = 17 06:36:03 [INFO] train episode 42557: reward = -93.79, steps = 27 06:36:05 [INFO] train episode 42558: reward = -68.47, steps = 24 06:36:07 [INFO] train episode 42559: reward = -52.77, steps = 26 06:36:10 [INFO] train episode 42560: reward = -80.22, steps = 27 06:36:13 [INFO] train episode 42561: reward = -113.04, steps = 30 06:36:15 [INFO] train episode 42562: reward = -92.53, steps = 26 06:36:17 [INFO] train episode 42563: reward = -74.76, steps = 21 06:36:18 [INFO] train episode 42564: reward = -60.94, steps = 20 06:36:20 [INFO] train episode 42565: reward = -80.70, steps = 19 06:36:22 [INFO] train episode 42566: reward = -89.46, steps = 27 06:36:25 [INFO] train episode 42567: reward = -70.82, steps = 21 06:36:28 [INFO] train episode 42568: reward = -89.82, steps = 36 06:36:29 [INFO] train episode 42569: reward = -72.80, steps = 19 06:36:31 [INFO] train episode 42570: reward = -80.50, steps = 25 06:36:33 [INFO] train episode 42571: reward = -70.82, steps = 21 06:36:35 [INFO] train episode 42572: reward = -75.97, steps = 22 06:36:38 [INFO] train episode 42573: reward = -92.67, steps = 27 06:36:39 [INFO] train episode 42574: reward = -82.55, steps = 19 06:36:41 [INFO] train episode 42575: reward = -53.43, steps = 19 06:36:44 [INFO] train episode 42576: reward = -84.02, steps = 31 06:36:46 [INFO] train episode 42577: reward = -49.58, steps = 21 06:36:48 [INFO] train episode 42578: reward = -128.82, steps = 22 06:36:50 [INFO] train episode 42579: reward = -52.08, steps = 20 06:36:51 [INFO] train episode 42580: reward = -68.57, steps = 19 06:36:53 [INFO] train episode 42581: reward = -105.52, steps = 25 06:36:55 [INFO] train episode 42582: reward = -84.80, steps = 19 06:36:57 [INFO] train episode 42583: reward = -95.29, steps = 23 06:36:59 [INFO] train episode 42584: reward = -126.70, steps = 19 06:37:01 [INFO] train episode 42585: reward = -80.63, steps = 25 06:37:03 [INFO] train episode 42586: reward = -58.29, steps = 19 06:37:04 [INFO] train episode 42587: reward = -74.46, steps = 19 06:37:06 [INFO] train episode 42588: reward = -92.88, steps = 23 06:37:08 [INFO] train episode 42589: reward = -70.12, steps = 22 06:37:11 [INFO] train episode 42590: reward = -117.16, steps = 34 06:37:14 [INFO] train episode 42591: reward = -130.33, steps = 29 06:37:17 [INFO] train episode 42592: reward = -71.21, steps = 28 06:37:19 [INFO] train episode 42593: reward = -115.16, steps = 29 06:37:21 [INFO] train episode 42594: reward = -85.53, steps = 26 06:37:24 [INFO] train episode 42595: reward = -43.57, steps = 27 06:37:26 [INFO] train episode 42596: reward = -90.28, steps = 28 06:37:28 [INFO] train episode 42597: reward = -64.25, steps = 19 06:37:30 [INFO] train episode 42598: reward = -71.85, steps = 26 06:37:32 [INFO] train episode 42599: reward = -45.87, steps = 23 06:37:34 [INFO] train episode 42600: reward = -99.13, steps = 22 06:37:37 [INFO] train episode 42601: reward = -71.77, steps = 32 06:37:39 [INFO] train episode 42602: reward = -78.13, steps = 23 06:37:41 [INFO] train episode 42603: reward = -59.60, steps = 20 06:37:43 [INFO] train episode 42604: reward = -66.00, steps = 22 06:37:45 [INFO] train episode 42605: reward = -94.31, steps = 23 06:37:47 [INFO] train episode 42606: reward = -70.44, steps = 20 06:37:49 [INFO] train episode 42607: reward = -118.16, steps = 26 06:37:51 [INFO] train episode 42608: reward = -60.35, steps = 21 06:37:53 [INFO] train episode 42609: reward = -65.91, steps = 24 06:37:55 [INFO] train episode 42610: reward = -76.55, steps = 22 06:37:57 [INFO] train episode 42611: reward = -77.32, steps = 21 06:37:59 [INFO] train episode 42612: reward = -93.38, steps = 22 06:38:01 [INFO] train episode 42613: reward = -58.81, steps = 22 06:38:05 [INFO] train episode 42614: reward = -252.67, steps = 38 06:38:06 [INFO] train episode 42615: reward = -59.30, steps = 21 06:38:09 [INFO] train episode 42616: reward = -107.65, steps = 27 06:38:10 [INFO] train episode 42617: reward = -130.05, steps = 21 06:38:13 [INFO] train episode 42618: reward = -69.32, steps = 24 06:38:15 [INFO] train episode 42619: reward = -86.46, steps = 23 06:38:17 [INFO] train episode 42620: reward = -125.34, steps = 29 06:38:19 [INFO] train episode 42621: reward = -85.85, steps = 23 06:38:21 [INFO] train episode 42622: reward = -105.94, steps = 20 06:38:23 [INFO] train episode 42623: reward = -89.06, steps = 23 06:38:25 [INFO] train episode 42624: reward = -87.96, steps = 23 06:38:27 [INFO] train episode 42625: reward = -73.05, steps = 18 06:38:29 [INFO] train episode 42626: reward = -83.13, steps = 25 06:38:31 [INFO] train episode 42627: reward = -81.31, steps = 22 06:38:33 [INFO] train episode 42628: reward = -105.96, steps = 23 06:38:35 [INFO] train episode 42629: reward = -66.28, steps = 22 06:38:37 [INFO] train episode 42630: reward = -57.52, steps = 27 06:38:39 [INFO] train episode 42631: reward = -96.48, steps = 22 06:38:41 [INFO] train episode 42632: reward = -59.55, steps = 19 06:38:43 [INFO] train episode 42633: reward = -92.35, steps = 26 06:38:45 [INFO] train episode 42634: reward = -71.50, steps = 23 06:38:47 [INFO] train episode 42635: reward = -28.64, steps = 20 06:38:49 [INFO] train episode 42636: reward = -58.62, steps = 20 06:38:51 [INFO] train episode 42637: reward = -69.29, steps = 22 06:38:54 [INFO] train episode 42638: reward = -69.62, steps = 31 06:38:55 [INFO] train episode 42639: reward = -81.12, steps = 21 06:38:58 [INFO] train episode 42640: reward = -103.59, steps = 23 06:38:59 [INFO] train episode 42641: reward = -89.21, steps = 19 06:39:01 [INFO] train episode 42642: reward = -86.32, steps = 19 06:39:04 [INFO] train episode 42643: reward = -56.76, steps = 34 06:39:06 [INFO] train episode 42644: reward = -42.74, steps = 23 06:39:08 [INFO] train episode 42645: reward = -105.37, steps = 24 06:39:10 [INFO] train episode 42646: reward = -77.44, steps = 21 06:39:12 [INFO] train episode 42647: reward = -94.98, steps = 28 06:39:14 [INFO] train episode 42648: reward = -39.32, steps = 23 06:39:16 [INFO] train episode 42649: reward = -77.33, steps = 19 06:39:18 [INFO] train episode 42650: reward = -70.62, steps = 20 06:39:20 [INFO] train episode 42651: reward = -101.74, steps = 25 06:39:23 [INFO] train episode 42652: reward = -84.85, steps = 29 06:39:25 [INFO] train episode 42653: reward = -87.52, steps = 26 06:39:27 [INFO] train episode 42654: reward = -80.09, steps = 25 06:39:30 [INFO] train episode 42655: reward = -97.45, steps = 30 06:39:32 [INFO] train episode 42656: reward = -93.35, steps = 26 06:39:34 [INFO] train episode 42657: reward = -93.70, steps = 19 06:39:36 [INFO] train episode 42658: reward = -69.46, steps = 19 06:39:37 [INFO] train episode 42659: reward = -78.84, steps = 20 06:39:39 [INFO] train episode 42660: reward = -104.98, steps = 25 06:39:42 [INFO] train episode 42661: reward = -77.09, steps = 26 06:39:44 [INFO] train episode 42662: reward = -63.16, steps = 24 06:39:46 [INFO] train episode 42663: reward = -90.84, steps = 22 06:39:48 [INFO] train episode 42664: reward = -90.08, steps = 22 06:39:49 [INFO] train episode 42665: reward = -63.73, steps = 19 06:39:52 [INFO] train episode 42666: reward = -115.93, steps = 26 06:39:54 [INFO] train episode 42667: reward = -100.90, steps = 19 06:39:56 [INFO] train episode 42668: reward = -96.34, steps = 24 06:39:59 [INFO] train episode 42669: reward = -133.18, steps = 35 06:40:00 [INFO] train episode 42670: reward = -143.90, steps = 18 06:40:03 [INFO] train episode 42671: reward = -98.97, steps = 32 06:40:05 [INFO] train episode 42672: reward = -46.41, steps = 21 06:40:08 [INFO] train episode 42673: reward = -148.29, steps = 35 06:40:10 [INFO] train episode 42674: reward = -122.68, steps = 20 06:40:12 [INFO] train episode 42675: reward = -67.61, steps = 20 06:40:14 [INFO] train episode 42676: reward = -106.42, steps = 22 06:40:16 [INFO] train episode 42677: reward = -56.06, steps = 27 06:40:18 [INFO] train episode 42678: reward = -65.43, steps = 28 06:40:20 [INFO] train episode 42679: reward = -74.22, steps = 20 06:40:22 [INFO] train episode 42680: reward = -92.03, steps = 20 06:40:24 [INFO] train episode 42681: reward = -52.20, steps = 24 06:40:26 [INFO] train episode 42682: reward = -76.99, steps = 24 06:40:29 [INFO] train episode 42683: reward = -116.92, steps = 29 06:40:31 [INFO] train episode 42684: reward = -59.41, steps = 20 06:40:33 [INFO] train episode 42685: reward = -148.67, steps = 24 06:40:36 [INFO] train episode 42686: reward = -84.52, steps = 37 06:40:38 [INFO] train episode 42687: reward = -74.42, steps = 29 06:40:40 [INFO] train episode 42688: reward = -83.64, steps = 18 06:40:42 [INFO] train episode 42689: reward = -68.75, steps = 22 06:40:44 [INFO] train episode 42690: reward = -43.55, steps = 23 06:40:46 [INFO] train episode 42691: reward = -83.41, steps = 19 06:40:48 [INFO] train episode 42692: reward = -107.99, steps = 28 06:40:51 [INFO] train episode 42693: reward = -89.52, steps = 21 06:40:53 [INFO] train episode 42694: reward = -71.22, steps = 21 06:40:55 [INFO] train episode 42695: reward = -79.55, steps = 30 06:40:58 [INFO] train episode 42696: reward = -45.90, steps = 34 06:41:00 [INFO] train episode 42697: reward = -93.90, steps = 20 06:41:01 [INFO] train episode 42698: reward = -85.51, steps = 13 06:41:03 [INFO] train episode 42699: reward = -83.97, steps = 22 06:41:05 [INFO] train episode 42700: reward = -84.03, steps = 19 06:41:07 [INFO] train episode 42701: reward = -90.13, steps = 22 06:41:10 [INFO] train episode 42702: reward = -118.24, steps = 35 06:41:12 [INFO] train episode 42703: reward = -72.50, steps = 23 06:41:14 [INFO] train episode 42704: reward = -63.81, steps = 19 06:41:16 [INFO] train episode 42705: reward = -55.57, steps = 23 06:41:18 [INFO] train episode 42706: reward = -73.92, steps = 23 06:41:20 [INFO] train episode 42707: reward = -60.51, steps = 20 06:41:21 [INFO] train episode 42708: reward = -97.49, steps = 19 06:41:23 [INFO] train episode 42709: reward = -68.30, steps = 23 06:41:25 [INFO] train episode 42710: reward = -118.60, steps = 19 06:41:26 [INFO] train episode 42711: reward = -68.72, steps = 16 06:41:29 [INFO] train episode 42712: reward = -70.42, steps = 26 06:41:30 [INFO] train episode 42713: reward = -67.70, steps = 19 06:41:33 [INFO] train episode 42714: reward = -77.01, steps = 25 06:41:34 [INFO] train episode 42715: reward = -56.86, steps = 23 06:41:36 [INFO] train episode 42716: reward = -63.67, steps = 19 06:41:38 [INFO] train episode 42717: reward = -79.21, steps = 23 06:41:40 [INFO] train episode 42718: reward = -103.57, steps = 19 06:41:42 [INFO] train episode 42719: reward = -55.70, steps = 26 06:41:44 [INFO] train episode 42720: reward = -48.80, steps = 19 06:41:46 [INFO] train episode 42721: reward = -65.98, steps = 20 06:41:47 [INFO] train episode 42722: reward = -76.81, steps = 20 06:41:49 [INFO] train episode 42723: reward = -40.74, steps = 20 06:41:51 [INFO] train episode 42724: reward = -92.95, steps = 26 06:41:53 [INFO] train episode 42725: reward = -82.88, steps = 21 06:41:55 [INFO] train episode 42726: reward = -104.43, steps = 23 06:41:57 [INFO] train episode 42727: reward = -64.56, steps = 23 06:42:00 [INFO] train episode 42728: reward = -72.22, steps = 23 06:42:01 [INFO] train episode 42729: reward = -53.23, steps = 21 06:42:03 [INFO] train episode 42730: reward = -70.00, steps = 21 06:42:05 [INFO] train episode 42731: reward = -73.52, steps = 19 06:42:08 [INFO] train episode 42732: reward = -95.39, steps = 32 06:42:10 [INFO] train episode 42733: reward = -78.21, steps = 23 06:42:12 [INFO] train episode 42734: reward = -87.08, steps = 26 06:42:14 [INFO] train episode 42735: reward = -60.52, steps = 21 06:42:16 [INFO] train episode 42736: reward = -66.90, steps = 20 06:42:18 [INFO] train episode 42737: reward = -97.96, steps = 22 06:42:19 [INFO] train episode 42738: reward = -98.93, steps = 20 06:42:21 [INFO] train episode 42739: reward = -54.06, steps = 22 06:42:23 [INFO] train episode 42740: reward = -60.94, steps = 21 06:42:25 [INFO] train episode 42741: reward = -99.95, steps = 24 06:42:27 [INFO] train episode 42742: reward = -79.66, steps = 29 06:42:30 [INFO] train episode 42743: reward = -128.26, steps = 27 06:42:32 [INFO] train episode 42744: reward = -68.91, steps = 22 06:42:34 [INFO] train episode 42745: reward = -86.49, steps = 22 06:42:36 [INFO] train episode 42746: reward = -88.87, steps = 26 06:42:38 [INFO] train episode 42747: reward = -59.81, steps = 20 06:42:40 [INFO] train episode 42748: reward = -92.44, steps = 25 06:42:42 [INFO] train episode 42749: reward = -48.71, steps = 23 06:42:44 [INFO] train episode 42750: reward = -55.68, steps = 26 06:42:46 [INFO] train episode 42751: reward = -78.36, steps = 21 06:42:49 [INFO] train episode 42752: reward = -61.74, steps = 22 06:42:51 [INFO] train episode 42753: reward = -102.82, steps = 24 06:42:52 [INFO] train episode 42754: reward = -30.33, steps = 22 06:42:54 [INFO] train episode 42755: reward = -60.63, steps = 23 06:42:57 [INFO] train episode 42756: reward = -98.45, steps = 31 06:42:58 [INFO] train episode 42757: reward = -70.00, steps = 17 06:43:00 [INFO] train episode 42758: reward = -63.55, steps = 20 06:43:03 [INFO] train episode 42759: reward = -134.22, steps = 30 06:43:05 [INFO] train episode 42760: reward = -105.20, steps = 26 06:43:08 [INFO] train episode 42761: reward = -121.81, steps = 29 06:43:10 [INFO] train episode 42762: reward = -58.72, steps = 25 06:43:12 [INFO] train episode 42763: reward = -93.13, steps = 28 06:43:14 [INFO] train episode 42764: reward = -91.90, steps = 21 06:43:16 [INFO] train episode 42765: reward = -80.27, steps = 21 06:43:18 [INFO] train episode 42766: reward = -90.26, steps = 19 06:43:20 [INFO] train episode 42767: reward = -106.79, steps = 21 06:43:22 [INFO] train episode 42768: reward = -63.95, steps = 21 06:43:23 [INFO] train episode 42769: reward = -76.58, steps = 19 06:43:25 [INFO] train episode 42770: reward = -69.28, steps = 19 06:43:27 [INFO] train episode 42771: reward = -110.84, steps = 27 06:43:29 [INFO] train episode 42772: reward = -97.68, steps = 28 06:43:31 [INFO] train episode 42773: reward = -89.82, steps = 20 06:43:33 [INFO] train episode 42774: reward = -99.45, steps = 25 06:43:35 [INFO] train episode 42775: reward = -92.74, steps = 22 06:43:37 [INFO] train episode 42776: reward = -89.63, steps = 19 06:43:39 [INFO] train episode 42777: reward = -120.54, steps = 23 06:43:42 [INFO] train episode 42778: reward = -108.48, steps = 20 06:43:44 [INFO] train episode 42779: reward = -59.90, steps = 25 06:43:46 [INFO] train episode 42780: reward = -54.17, steps = 21 06:43:47 [INFO] train episode 42781: reward = -95.04, steps = 20 06:43:50 [INFO] train episode 42782: reward = -51.37, steps = 31 06:43:52 [INFO] train episode 42783: reward = -72.04, steps = 25 06:43:54 [INFO] train episode 42784: reward = -95.38, steps = 24 06:43:57 [INFO] train episode 42785: reward = -117.18, steps = 26 06:43:58 [INFO] train episode 42786: reward = -87.03, steps = 19 06:44:00 [INFO] train episode 42787: reward = -58.91, steps = 20 06:44:02 [INFO] train episode 42788: reward = -94.52, steps = 19 06:44:03 [INFO] train episode 42789: reward = -73.56, steps = 18 06:44:05 [INFO] train episode 42790: reward = -65.92, steps = 26 06:44:08 [INFO] train episode 42791: reward = -86.22, steps = 27 06:44:10 [INFO] train episode 42792: reward = -86.89, steps = 25 06:44:12 [INFO] train episode 42793: reward = -73.47, steps = 20 06:44:14 [INFO] train episode 42794: reward = -93.05, steps = 29 06:44:16 [INFO] train episode 42795: reward = -51.85, steps = 22 06:44:18 [INFO] train episode 42796: reward = -99.81, steps = 18 06:44:20 [INFO] train episode 42797: reward = -69.72, steps = 25 06:44:23 [INFO] train episode 42798: reward = -102.44, steps = 27 06:44:24 [INFO] train episode 42799: reward = -45.88, steps = 19 06:44:26 [INFO] train episode 42800: reward = -69.86, steps = 20 06:44:28 [INFO] train episode 42801: reward = -83.10, steps = 26 06:44:30 [INFO] train episode 42802: reward = -80.29, steps = 22 06:44:32 [INFO] train episode 42803: reward = -75.02, steps = 20 06:44:34 [INFO] train episode 42804: reward = -69.80, steps = 21 06:44:36 [INFO] train episode 42805: reward = -59.90, steps = 24 06:44:38 [INFO] train episode 42806: reward = -99.90, steps = 22 06:44:40 [INFO] train episode 42807: reward = -75.58, steps = 20 06:44:41 [INFO] train episode 42808: reward = -76.47, steps = 20 06:44:43 [INFO] train episode 42809: reward = -50.43, steps = 22 06:44:46 [INFO] train episode 42810: reward = -111.87, steps = 29 06:44:48 [INFO] train episode 42811: reward = -79.01, steps = 27 06:44:50 [INFO] train episode 42812: reward = -80.29, steps = 23 06:44:52 [INFO] train episode 42813: reward = -58.05, steps = 26 06:44:55 [INFO] train episode 42814: reward = -72.65, steps = 26 06:44:57 [INFO] train episode 42815: reward = -83.39, steps = 20 06:44:59 [INFO] train episode 42816: reward = -143.02, steps = 30 06:45:01 [INFO] train episode 42817: reward = -94.57, steps = 25 06:45:03 [INFO] train episode 42818: reward = -75.74, steps = 19 06:45:05 [INFO] train episode 42819: reward = -67.93, steps = 18 06:45:06 [INFO] train episode 42820: reward = -102.19, steps = 20 06:45:08 [INFO] train episode 42821: reward = -60.28, steps = 21 06:45:10 [INFO] train episode 42822: reward = -77.30, steps = 19 06:45:12 [INFO] train episode 42823: reward = -39.52, steps = 20 06:45:16 [INFO] train episode 42824: reward = -81.10, steps = 44 06:45:17 [INFO] train episode 42825: reward = -43.37, steps = 19 06:45:19 [INFO] train episode 42826: reward = -89.00, steps = 23 06:45:21 [INFO] train episode 42827: reward = -75.01, steps = 19 06:45:22 [INFO] train episode 42828: reward = -104.38, steps = 19 06:45:25 [INFO] train episode 42829: reward = -102.01, steps = 22 06:45:27 [INFO] train episode 42830: reward = -55.30, steps = 24 06:45:29 [INFO] train episode 42831: reward = -48.54, steps = 27 06:45:31 [INFO] train episode 42832: reward = -67.80, steps = 19 06:45:33 [INFO] train episode 42833: reward = -79.89, steps = 26 06:45:35 [INFO] train episode 42834: reward = -111.86, steps = 24 06:45:37 [INFO] train episode 42835: reward = -59.49, steps = 20 06:45:39 [INFO] train episode 42836: reward = -60.87, steps = 27 06:45:41 [INFO] train episode 42837: reward = -75.18, steps = 19 06:45:44 [INFO] train episode 42838: reward = -76.68, steps = 32 06:45:46 [INFO] train episode 42839: reward = -116.12, steps = 33 06:45:48 [INFO] train episode 42840: reward = -57.56, steps = 24 06:45:50 [INFO] train episode 42841: reward = -97.96, steps = 18 06:45:52 [INFO] train episode 42842: reward = -79.96, steps = 21 06:45:53 [INFO] train episode 42843: reward = -54.38, steps = 19 06:45:57 [INFO] train episode 42844: reward = -83.63, steps = 33 06:45:59 [INFO] train episode 42845: reward = -94.26, steps = 24 06:46:01 [INFO] train episode 42846: reward = -144.36, steps = 24 06:46:03 [INFO] train episode 42847: reward = -99.81, steps = 26 06:46:05 [INFO] train episode 42848: reward = -113.69, steps = 19 06:46:06 [INFO] train episode 42849: reward = -75.29, steps = 19 06:46:09 [INFO] train episode 42850: reward = -85.07, steps = 32 06:46:11 [INFO] train episode 42851: reward = -95.02, steps = 23 06:46:13 [INFO] train episode 42852: reward = -97.15, steps = 22 06:46:15 [INFO] train episode 42853: reward = -81.46, steps = 19 06:46:17 [INFO] train episode 42854: reward = -73.02, steps = 19 06:46:19 [INFO] train episode 42855: reward = -109.86, steps = 29 06:46:22 [INFO] train episode 42856: reward = -139.01, steps = 35 06:46:24 [INFO] train episode 42857: reward = -75.62, steps = 22 06:46:27 [INFO] train episode 42858: reward = -132.32, steps = 31 06:46:30 [INFO] train episode 42859: reward = -101.65, steps = 35 06:46:32 [INFO] train episode 42860: reward = -120.76, steps = 20 06:46:35 [INFO] train episode 42861: reward = -104.72, steps = 33 06:46:37 [INFO] train episode 42862: reward = -119.43, steps = 26 06:46:40 [INFO] train episode 42863: reward = -64.07, steps = 24 06:46:41 [INFO] train episode 42864: reward = -70.19, steps = 22 06:46:43 [INFO] train episode 42865: reward = -74.53, steps = 21 06:46:47 [INFO] train episode 42866: reward = -75.28, steps = 36 06:46:49 [INFO] train episode 42867: reward = -112.76, steps = 23 06:46:51 [INFO] train episode 42868: reward = -96.44, steps = 22 06:46:53 [INFO] train episode 42869: reward = -71.18, steps = 25 06:46:55 [INFO] train episode 42870: reward = -89.81, steps = 20 06:46:56 [INFO] train episode 42871: reward = -122.27, steps = 20 06:46:58 [INFO] train episode 42872: reward = -74.25, steps = 22 06:47:00 [INFO] train episode 42873: reward = -75.03, steps = 20 06:47:02 [INFO] train episode 42874: reward = -92.99, steps = 20 06:47:04 [INFO] train episode 42875: reward = -89.71, steps = 25 06:47:05 [INFO] train episode 42876: reward = -120.83, steps = 12 06:47:08 [INFO] train episode 42877: reward = -83.28, steps = 27 06:47:09 [INFO] train episode 42878: reward = -76.80, steps = 22 06:47:11 [INFO] train episode 42879: reward = -63.98, steps = 22 06:47:13 [INFO] train episode 42880: reward = -78.63, steps = 19 06:47:15 [INFO] train episode 42881: reward = -86.95, steps = 20 06:47:17 [INFO] train episode 42882: reward = -101.23, steps = 23 06:47:19 [INFO] train episode 42883: reward = -98.28, steps = 22 06:47:21 [INFO] train episode 42884: reward = -72.28, steps = 25 06:47:23 [INFO] train episode 42885: reward = -65.76, steps = 21 06:47:25 [INFO] train episode 42886: reward = -80.27, steps = 19 06:47:26 [INFO] train episode 42887: reward = -64.16, steps = 19 06:47:28 [INFO] train episode 42888: reward = -60.64, steps = 24 06:47:31 [INFO] train episode 42889: reward = -85.97, steps = 31 06:47:33 [INFO] train episode 42890: reward = -113.38, steps = 21 06:47:35 [INFO] train episode 42891: reward = -95.34, steps = 21 06:47:37 [INFO] train episode 42892: reward = -68.42, steps = 21 06:47:39 [INFO] train episode 42893: reward = -80.12, steps = 22 06:47:40 [INFO] train episode 42894: reward = -69.27, steps = 18 06:47:42 [INFO] train episode 42895: reward = -115.69, steps = 19 06:47:44 [INFO] train episode 42896: reward = -64.56, steps = 23 06:47:46 [INFO] train episode 42897: reward = -82.05, steps = 19 06:47:47 [INFO] train episode 42898: reward = -51.25, steps = 19 06:47:50 [INFO] train episode 42899: reward = -78.55, steps = 29 06:47:53 [INFO] train episode 42900: reward = -54.65, steps = 31 06:47:55 [INFO] train episode 42901: reward = -101.11, steps = 24 06:47:56 [INFO] train episode 42902: reward = -138.33, steps = 21 06:47:59 [INFO] train episode 42903: reward = -80.85, steps = 29 06:48:01 [INFO] train episode 42904: reward = -77.99, steps = 23 06:48:03 [INFO] train episode 42905: reward = -75.82, steps = 19 06:48:05 [INFO] train episode 42906: reward = -91.40, steps = 23 06:48:07 [INFO] train episode 42907: reward = -90.37, steps = 19 06:48:09 [INFO] train episode 42908: reward = -109.40, steps = 28 06:48:11 [INFO] train episode 42909: reward = -79.46, steps = 22 06:48:13 [INFO] train episode 42910: reward = -40.15, steps = 20 06:48:15 [INFO] train episode 42911: reward = -79.44, steps = 25 06:48:17 [INFO] train episode 42912: reward = -91.14, steps = 25 06:48:19 [INFO] train episode 42913: reward = -45.38, steps = 21 06:48:21 [INFO] train episode 42914: reward = -70.42, steps = 19 06:48:22 [INFO] train episode 42915: reward = -92.46, steps = 20 06:48:24 [INFO] train episode 42916: reward = -57.34, steps = 20 06:48:26 [INFO] train episode 42917: reward = -74.73, steps = 26 06:48:29 [INFO] train episode 42918: reward = -73.88, steps = 24 06:48:30 [INFO] train episode 42919: reward = -121.73, steps = 18 06:48:32 [INFO] train episode 42920: reward = -70.32, steps = 28 06:48:34 [INFO] train episode 42921: reward = -105.44, steps = 19 06:48:37 [INFO] train episode 42922: reward = -109.23, steps = 26 06:48:38 [INFO] train episode 42923: reward = -77.15, steps = 19 06:48:40 [INFO] train episode 42924: reward = -76.42, steps = 23 06:48:43 [INFO] train episode 42925: reward = -81.53, steps = 34 06:48:45 [INFO] train episode 42926: reward = -57.14, steps = 24 06:48:49 [INFO] train episode 42927: reward = -133.37, steps = 40 06:48:51 [INFO] train episode 42928: reward = -92.51, steps = 23 06:48:53 [INFO] train episode 42929: reward = -92.36, steps = 20 06:48:54 [INFO] train episode 42930: reward = -43.97, steps = 19 06:48:57 [INFO] train episode 42931: reward = -45.28, steps = 25 06:48:58 [INFO] train episode 42932: reward = -87.37, steps = 20 06:49:00 [INFO] train episode 42933: reward = -76.96, steps = 22 06:49:02 [INFO] train episode 42934: reward = -64.59, steps = 23 06:49:04 [INFO] train episode 42935: reward = -73.57, steps = 21 06:49:06 [INFO] train episode 42936: reward = -92.42, steps = 23 06:49:08 [INFO] train episode 42937: reward = -44.40, steps = 21 06:49:10 [INFO] train episode 42938: reward = -65.22, steps = 19 06:49:12 [INFO] train episode 42939: reward = -65.62, steps = 28 06:49:14 [INFO] train episode 42940: reward = -67.87, steps = 19 06:49:16 [INFO] train episode 42941: reward = -90.46, steps = 23 06:49:17 [INFO] train episode 42942: reward = -93.70, steps = 19 06:49:19 [INFO] train episode 42943: reward = -68.62, steps = 21 06:49:21 [INFO] train episode 42944: reward = -70.81, steps = 19 06:49:23 [INFO] train episode 42945: reward = -43.48, steps = 20 06:49:25 [INFO] train episode 42946: reward = -60.47, steps = 21 06:49:27 [INFO] train episode 42947: reward = -165.19, steps = 21 06:49:29 [INFO] train episode 42948: reward = -114.31, steps = 20 06:49:31 [INFO] train episode 42949: reward = -96.64, steps = 31 06:49:33 [INFO] train episode 42950: reward = -145.70, steps = 19 06:49:35 [INFO] train episode 42951: reward = -77.04, steps = 20 06:49:36 [INFO] train episode 42952: reward = -78.22, steps = 19 06:49:38 [INFO] train episode 42953: reward = -70.26, steps = 20 06:49:40 [INFO] train episode 42954: reward = -92.07, steps = 22 06:49:44 [INFO] train episode 42955: reward = -71.79, steps = 36 06:49:46 [INFO] train episode 42956: reward = -137.94, steps = 28 06:49:48 [INFO] train episode 42957: reward = -59.67, steps = 31 06:49:50 [INFO] train episode 42958: reward = -79.05, steps = 22 06:49:52 [INFO] train episode 42959: reward = -53.99, steps = 20 06:49:54 [INFO] train episode 42960: reward = -115.70, steps = 27 06:49:57 [INFO] train episode 42961: reward = -53.95, steps = 22 06:49:59 [INFO] train episode 42962: reward = -87.42, steps = 31 06:50:01 [INFO] train episode 42963: reward = -117.21, steps = 22 06:50:03 [INFO] train episode 42964: reward = -112.83, steps = 22 06:50:05 [INFO] train episode 42965: reward = -71.48, steps = 19 06:50:06 [INFO] train episode 42966: reward = -68.02, steps = 19 06:50:08 [INFO] train episode 42967: reward = -131.43, steps = 26 06:50:10 [INFO] train episode 42968: reward = -33.15, steps = 21 06:50:12 [INFO] train episode 42969: reward = -89.33, steps = 21 06:50:14 [INFO] train episode 42970: reward = -111.81, steps = 24 06:50:17 [INFO] train episode 42971: reward = -143.13, steps = 27 06:50:18 [INFO] train episode 42972: reward = -123.08, steps = 19 06:50:20 [INFO] train episode 42973: reward = -97.86, steps = 25 06:50:23 [INFO] train episode 42974: reward = -98.51, steps = 26 06:50:24 [INFO] train episode 42975: reward = -63.57, steps = 22 06:50:26 [INFO] train episode 42976: reward = -72.33, steps = 19 06:50:28 [INFO] train episode 42977: reward = -64.08, steps = 22 06:50:31 [INFO] train episode 42978: reward = -76.31, steps = 29 06:50:33 [INFO] train episode 42979: reward = -88.38, steps = 23 06:50:34 [INFO] train episode 42980: reward = -74.93, steps = 19 06:50:37 [INFO] train episode 42981: reward = -67.44, steps = 24 06:50:39 [INFO] train episode 42982: reward = -78.45, steps = 24 06:50:41 [INFO] train episode 42983: reward = -109.49, steps = 29 06:50:44 [INFO] train episode 42984: reward = -79.66, steps = 28 06:50:46 [INFO] train episode 42985: reward = -66.83, steps = 22 06:50:49 [INFO] train episode 42986: reward = -55.88, steps = 37 06:50:51 [INFO] train episode 42987: reward = -103.04, steps = 24 06:50:53 [INFO] train episode 42988: reward = -104.22, steps = 22 06:50:55 [INFO] train episode 42989: reward = -74.15, steps = 20 06:50:56 [INFO] train episode 42990: reward = -82.28, steps = 20 06:50:58 [INFO] train episode 42991: reward = -67.76, steps = 20 06:51:00 [INFO] train episode 42992: reward = -93.45, steps = 19 06:51:03 [INFO] train episode 42993: reward = -76.39, steps = 34 06:51:05 [INFO] train episode 42994: reward = -81.98, steps = 20 06:51:06 [INFO] train episode 42995: reward = -63.61, steps = 21 06:51:08 [INFO] train episode 42996: reward = -66.71, steps = 18 06:51:10 [INFO] train episode 42997: reward = -59.88, steps = 28 06:51:14 [INFO] train episode 42998: reward = -147.83, steps = 38 06:51:16 [INFO] train episode 42999: reward = -70.25, steps = 24 06:51:20 [INFO] train episode 43000: reward = -102.93, steps = 51 06:51:22 [INFO] train episode 43001: reward = -78.98, steps = 20 06:51:24 [INFO] train episode 43002: reward = -44.46, steps = 24 06:51:26 [INFO] train episode 43003: reward = -89.26, steps = 19 06:51:28 [INFO] train episode 43004: reward = -79.37, steps = 21 06:51:30 [INFO] train episode 43005: reward = -98.33, steps = 25 06:51:32 [INFO] train episode 43006: reward = -68.23, steps = 20 06:51:34 [INFO] train episode 43007: reward = -72.68, steps = 23 06:51:36 [INFO] train episode 43008: reward = -74.76, steps = 21 06:51:38 [INFO] train episode 43009: reward = -97.83, steps = 25 06:51:39 [INFO] train episode 43010: reward = -83.88, steps = 18 06:51:41 [INFO] train episode 43011: reward = -84.60, steps = 21 06:51:43 [INFO] train episode 43012: reward = -74.10, steps = 19 06:51:45 [INFO] train episode 43013: reward = -33.23, steps = 20 06:51:47 [INFO] train episode 43014: reward = -87.49, steps = 22 06:51:49 [INFO] train episode 43015: reward = -48.73, steps = 20 06:51:51 [INFO] train episode 43016: reward = -72.06, steps = 26 06:51:53 [INFO] train episode 43017: reward = -106.86, steps = 21 06:51:54 [INFO] train episode 43018: reward = -57.55, steps = 22 06:51:56 [INFO] train episode 43019: reward = -71.74, steps = 19 06:51:58 [INFO] train episode 43020: reward = -130.95, steps = 19 06:52:00 [INFO] train episode 43021: reward = -75.52, steps = 26 06:52:03 [INFO] train episode 43022: reward = -72.14, steps = 29 06:52:05 [INFO] train episode 43023: reward = -85.05, steps = 24 06:52:07 [INFO] train episode 43024: reward = -60.52, steps = 20 06:52:08 [INFO] train episode 43025: reward = -46.89, steps = 20 06:52:10 [INFO] train episode 43026: reward = -66.28, steps = 20 06:52:13 [INFO] train episode 43027: reward = -64.71, steps = 22 06:52:14 [INFO] train episode 43028: reward = -99.68, steps = 21 06:52:16 [INFO] train episode 43029: reward = -75.84, steps = 19 06:52:18 [INFO] train episode 43030: reward = -86.43, steps = 21 06:52:21 [INFO] train episode 43031: reward = -69.69, steps = 28 06:52:22 [INFO] train episode 43032: reward = -74.10, steps = 21 06:52:25 [INFO] train episode 43033: reward = -85.64, steps = 25 06:52:27 [INFO] train episode 43034: reward = -71.84, steps = 24 06:52:28 [INFO] train episode 43035: reward = -61.62, steps = 19 06:52:30 [INFO] train episode 43036: reward = -101.17, steps = 20 06:52:32 [INFO] train episode 43037: reward = -100.56, steps = 22 06:52:34 [INFO] train episode 43038: reward = -61.60, steps = 20 06:52:36 [INFO] train episode 43039: reward = -61.94, steps = 21 06:52:38 [INFO] train episode 43040: reward = -46.93, steps = 22 06:52:40 [INFO] train episode 43041: reward = -83.78, steps = 20 06:52:42 [INFO] train episode 43042: reward = -53.58, steps = 27 06:52:44 [INFO] train episode 43043: reward = -68.59, steps = 18 06:52:46 [INFO] train episode 43044: reward = -92.11, steps = 30 06:52:49 [INFO] train episode 43045: reward = -117.85, steps = 32 06:52:51 [INFO] train episode 43046: reward = -112.97, steps = 22 06:52:53 [INFO] train episode 43047: reward = -95.74, steps = 18 06:52:55 [INFO] train episode 43048: reward = -81.00, steps = 27 06:52:57 [INFO] train episode 43049: reward = -46.70, steps = 21 06:52:58 [INFO] train episode 43050: reward = -130.43, steps = 18 06:53:00 [INFO] train episode 43051: reward = -61.14, steps = 21 06:53:02 [INFO] train episode 43052: reward = -105.33, steps = 20 06:53:03 [INFO] train episode 43053: reward = -74.73, steps = 19 06:53:05 [INFO] train episode 43054: reward = -54.20, steps = 20 06:53:07 [INFO] train episode 43055: reward = -72.70, steps = 20 06:53:09 [INFO] train episode 43056: reward = -92.42, steps = 19 06:53:11 [INFO] train episode 43057: reward = -92.52, steps = 19 06:53:12 [INFO] train episode 43058: reward = -77.16, steps = 20 06:53:14 [INFO] train episode 43059: reward = -91.11, steps = 20 06:53:16 [INFO] train episode 43060: reward = -86.49, steps = 20 06:53:18 [INFO] train episode 43061: reward = -84.46, steps = 23 06:53:19 [INFO] train episode 43062: reward = -78.07, steps = 20 06:53:22 [INFO] train episode 43063: reward = -66.41, steps = 24 06:53:24 [INFO] train episode 43064: reward = -98.31, steps = 29 06:53:26 [INFO] train episode 43065: reward = -49.64, steps = 18 06:53:27 [INFO] train episode 43066: reward = -106.76, steps = 19 06:53:30 [INFO] train episode 43067: reward = -67.42, steps = 28 06:53:32 [INFO] train episode 43068: reward = -78.30, steps = 19 06:53:33 [INFO] train episode 43069: reward = -67.18, steps = 19 06:53:35 [INFO] train episode 43070: reward = -80.61, steps = 22 06:53:37 [INFO] train episode 43071: reward = -66.30, steps = 19 06:53:39 [INFO] train episode 43072: reward = -78.19, steps = 18 06:53:41 [INFO] train episode 43073: reward = -103.39, steps = 22 06:53:42 [INFO] train episode 43074: reward = -27.99, steps = 20 06:53:44 [INFO] train episode 43075: reward = -48.38, steps = 21 06:53:46 [INFO] train episode 43076: reward = -71.09, steps = 28 06:53:49 [INFO] train episode 43077: reward = -77.31, steps = 26 06:53:51 [INFO] train episode 43078: reward = -63.32, steps = 21 06:53:52 [INFO] train episode 43079: reward = -53.88, steps = 19 06:53:54 [INFO] train episode 43080: reward = -104.64, steps = 21 06:53:56 [INFO] train episode 43081: reward = -71.87, steps = 17 06:53:58 [INFO] train episode 43082: reward = -75.50, steps = 25 06:54:00 [INFO] train episode 43083: reward = -92.02, steps = 26 06:54:02 [INFO] train episode 43084: reward = -48.24, steps = 22 06:54:04 [INFO] train episode 43085: reward = -69.60, steps = 24 06:54:06 [INFO] train episode 43086: reward = -90.93, steps = 27 06:54:08 [INFO] train episode 43087: reward = -53.66, steps = 23 06:54:11 [INFO] train episode 43088: reward = -99.89, steps = 30 06:54:13 [INFO] train episode 43089: reward = -113.35, steps = 21 06:54:16 [INFO] train episode 43090: reward = -84.25, steps = 32 06:54:18 [INFO] train episode 43091: reward = -93.93, steps = 21 06:54:19 [INFO] train episode 43092: reward = -78.57, steps = 19 06:54:22 [INFO] train episode 43093: reward = -92.44, steps = 37 06:54:25 [INFO] train episode 43094: reward = -103.87, steps = 26 06:54:27 [INFO] train episode 43095: reward = -105.73, steps = 20 06:54:29 [INFO] train episode 43096: reward = -70.27, steps = 21 06:54:30 [INFO] train episode 43097: reward = -58.71, steps = 22 06:54:33 [INFO] train episode 43098: reward = -62.30, steps = 26 06:54:34 [INFO] train episode 43099: reward = -93.75, steps = 18 06:54:36 [INFO] train episode 43100: reward = -54.13, steps = 23 06:54:39 [INFO] train episode 43101: reward = -69.48, steps = 29 06:54:41 [INFO] train episode 43102: reward = -75.69, steps = 25 06:54:43 [INFO] train episode 43103: reward = -46.10, steps = 21 06:54:45 [INFO] train episode 43104: reward = -102.09, steps = 20 06:54:47 [INFO] train episode 43105: reward = -48.13, steps = 21 06:54:49 [INFO] train episode 43106: reward = -102.21, steps = 19 06:54:50 [INFO] train episode 43107: reward = -64.88, steps = 23 06:54:52 [INFO] train episode 43108: reward = -40.94, steps = 20 06:54:54 [INFO] train episode 43109: reward = -76.79, steps = 19 06:54:56 [INFO] train episode 43110: reward = -38.78, steps = 20 06:54:58 [INFO] train episode 43111: reward = -94.84, steps = 20 06:55:00 [INFO] train episode 43112: reward = -69.89, steps = 25 06:55:02 [INFO] train episode 43113: reward = -54.51, steps = 19 06:55:04 [INFO] train episode 43114: reward = -97.89, steps = 17 06:55:06 [INFO] train episode 43115: reward = -59.50, steps = 21 06:55:08 [INFO] train episode 43116: reward = -70.40, steps = 18 06:55:09 [INFO] train episode 43117: reward = -68.99, steps = 21 06:55:11 [INFO] train episode 43118: reward = -88.85, steps = 21 06:55:13 [INFO] train episode 43119: reward = -49.12, steps = 18 06:55:15 [INFO] train episode 43120: reward = -77.31, steps = 24 06:55:17 [INFO] train episode 43121: reward = -94.89, steps = 20 06:55:19 [INFO] train episode 43122: reward = -101.36, steps = 19 06:55:20 [INFO] train episode 43123: reward = -76.04, steps = 19 06:55:22 [INFO] train episode 43124: reward = -72.73, steps = 20 06:55:24 [INFO] train episode 43125: reward = -80.98, steps = 24 06:55:26 [INFO] train episode 43126: reward = -72.59, steps = 20 06:55:28 [INFO] train episode 43127: reward = -48.90, steps = 24 06:55:31 [INFO] train episode 43128: reward = -83.12, steps = 29 06:55:32 [INFO] train episode 43129: reward = -67.62, steps = 20 06:55:34 [INFO] train episode 43130: reward = -97.77, steps = 21 06:55:36 [INFO] train episode 43131: reward = -84.74, steps = 20 06:55:37 [INFO] train episode 43132: reward = -59.90, steps = 19 06:55:40 [INFO] train episode 43133: reward = -69.47, steps = 24 06:55:41 [INFO] train episode 43134: reward = -91.97, steps = 22 06:55:43 [INFO] train episode 43135: reward = -90.68, steps = 22 06:55:46 [INFO] train episode 43136: reward = -88.82, steps = 27 06:55:48 [INFO] train episode 43137: reward = -75.28, steps = 18 06:55:50 [INFO] train episode 43138: reward = -71.30, steps = 22 06:55:51 [INFO] train episode 43139: reward = -64.89, steps = 22 06:55:54 [INFO] train episode 43140: reward = -64.09, steps = 26 06:55:55 [INFO] train episode 43141: reward = -65.67, steps = 18 06:55:57 [INFO] train episode 43142: reward = -72.78, steps = 23 06:55:59 [INFO] train episode 43143: reward = -77.40, steps = 20 06:56:01 [INFO] train episode 43144: reward = -64.39, steps = 25 06:56:03 [INFO] train episode 43145: reward = -51.58, steps = 21 06:56:05 [INFO] train episode 43146: reward = -107.50, steps = 23 06:56:07 [INFO] train episode 43147: reward = -81.97, steps = 21 06:56:09 [INFO] train episode 43148: reward = -45.02, steps = 23 06:56:11 [INFO] train episode 43149: reward = -63.47, steps = 23 06:56:13 [INFO] train episode 43150: reward = -84.42, steps = 28 06:56:15 [INFO] train episode 43151: reward = -115.19, steps = 23 06:56:18 [INFO] train episode 43152: reward = -67.89, steps = 30 06:56:20 [INFO] train episode 43153: reward = -80.95, steps = 23 06:56:23 [INFO] train episode 43154: reward = -66.49, steps = 31 06:56:25 [INFO] train episode 43155: reward = -72.27, steps = 27 06:56:27 [INFO] train episode 43156: reward = -55.34, steps = 20 06:56:28 [INFO] train episode 43157: reward = -81.83, steps = 19 06:56:30 [INFO] train episode 43158: reward = -45.26, steps = 22 06:56:32 [INFO] train episode 43159: reward = -84.76, steps = 25 06:56:35 [INFO] train episode 43160: reward = -78.50, steps = 30 06:56:37 [INFO] train episode 43161: reward = -52.21, steps = 20 06:56:39 [INFO] train episode 43162: reward = -84.88, steps = 21 06:56:41 [INFO] train episode 43163: reward = -69.14, steps = 20 06:56:42 [INFO] train episode 43164: reward = -79.16, steps = 19 06:56:45 [INFO] train episode 43165: reward = -87.69, steps = 27 06:56:46 [INFO] train episode 43166: reward = -58.43, steps = 22 06:56:48 [INFO] train episode 43167: reward = -49.29, steps = 18 06:56:50 [INFO] train episode 43168: reward = -62.15, steps = 19 06:56:52 [INFO] train episode 43169: reward = -87.03, steps = 17 06:56:54 [INFO] train episode 43170: reward = -102.92, steps = 30 06:56:56 [INFO] train episode 43171: reward = -62.05, steps = 27 06:56:58 [INFO] train episode 43172: reward = -96.37, steps = 20 06:57:00 [INFO] train episode 43173: reward = -62.78, steps = 21 06:57:02 [INFO] train episode 43174: reward = -79.49, steps = 20 06:57:04 [INFO] train episode 43175: reward = -70.10, steps = 27 06:57:06 [INFO] train episode 43176: reward = -77.10, steps = 20 06:57:08 [INFO] train episode 43177: reward = -51.28, steps = 25 06:57:10 [INFO] train episode 43178: reward = -100.47, steps = 20 06:57:12 [INFO] train episode 43179: reward = -91.65, steps = 20 06:57:13 [INFO] train episode 43180: reward = -98.30, steps = 22 06:57:15 [INFO] train episode 43181: reward = -78.08, steps = 15 06:57:16 [INFO] train episode 43182: reward = -109.11, steps = 19 06:57:18 [INFO] train episode 43183: reward = -72.66, steps = 22 06:57:21 [INFO] train episode 43184: reward = -68.82, steps = 21 06:57:23 [INFO] train episode 43185: reward = -84.78, steps = 23 06:57:24 [INFO] train episode 43186: reward = -74.51, steps = 23 06:57:27 [INFO] train episode 43187: reward = -106.61, steps = 29 06:57:29 [INFO] train episode 43188: reward = -80.62, steps = 21 06:57:31 [INFO] train episode 43189: reward = -67.81, steps = 31 06:57:33 [INFO] train episode 43190: reward = -102.35, steps = 19 06:57:35 [INFO] train episode 43191: reward = -115.57, steps = 20 06:57:37 [INFO] train episode 43192: reward = -55.96, steps = 20 06:57:39 [INFO] train episode 43193: reward = -73.35, steps = 21 06:57:41 [INFO] train episode 43194: reward = -73.29, steps = 22 06:57:44 [INFO] train episode 43195: reward = -131.03, steps = 33 06:57:45 [INFO] train episode 43196: reward = -88.22, steps = 21 06:57:47 [INFO] train episode 43197: reward = -65.73, steps = 19 06:57:49 [INFO] train episode 43198: reward = -76.98, steps = 24 06:57:51 [INFO] train episode 43199: reward = -76.23, steps = 21 06:57:54 [INFO] train episode 43200: reward = -76.20, steps = 22 06:57:56 [INFO] train episode 43201: reward = -62.21, steps = 24 06:57:58 [INFO] train episode 43202: reward = -84.11, steps = 19 06:58:00 [INFO] train episode 43203: reward = -103.81, steps = 24 06:58:02 [INFO] train episode 43204: reward = -104.47, steps = 27 06:58:04 [INFO] train episode 43205: reward = -74.06, steps = 23 06:58:07 [INFO] train episode 43206: reward = -75.13, steps = 24 06:58:08 [INFO] train episode 43207: reward = -79.67, steps = 20 06:58:11 [INFO] train episode 43208: reward = -69.62, steps = 25 06:58:13 [INFO] train episode 43209: reward = -85.77, steps = 27 06:58:15 [INFO] train episode 43210: reward = -63.97, steps = 20 06:58:17 [INFO] train episode 43211: reward = -96.10, steps = 30 06:58:19 [INFO] train episode 43212: reward = -57.21, steps = 24 06:58:22 [INFO] train episode 43213: reward = -93.52, steps = 30 06:58:24 [INFO] train episode 43214: reward = -87.75, steps = 23 06:58:28 [INFO] train episode 43215: reward = -99.46, steps = 40 06:58:29 [INFO] train episode 43216: reward = -60.51, steps = 21 06:58:32 [INFO] train episode 43217: reward = -71.45, steps = 24 06:58:34 [INFO] train episode 43218: reward = -80.59, steps = 25 06:58:36 [INFO] train episode 43219: reward = -71.65, steps = 23 06:58:38 [INFO] train episode 43220: reward = -75.60, steps = 21 06:58:39 [INFO] train episode 43221: reward = -82.19, steps = 20 06:58:43 [INFO] train episode 43222: reward = -51.92, steps = 36 06:58:45 [INFO] train episode 43223: reward = -91.13, steps = 22 06:58:47 [INFO] train episode 43224: reward = -140.84, steps = 26 06:58:49 [INFO] train episode 43225: reward = -79.15, steps = 24 06:58:51 [INFO] train episode 43226: reward = -115.15, steps = 27 06:58:53 [INFO] train episode 43227: reward = -71.44, steps = 19 06:58:54 [INFO] train episode 43228: reward = -71.23, steps = 18 06:58:57 [INFO] train episode 43229: reward = -84.41, steps = 22 06:58:59 [INFO] train episode 43230: reward = -97.55, steps = 24 06:59:01 [INFO] train episode 43231: reward = -91.00, steps = 24 06:59:03 [INFO] train episode 43232: reward = -78.35, steps = 23 06:59:05 [INFO] train episode 43233: reward = -85.58, steps = 21 06:59:06 [INFO] train episode 43234: reward = -56.18, steps = 22 06:59:09 [INFO] train episode 43235: reward = -89.90, steps = 24 06:59:11 [INFO] train episode 43236: reward = -58.95, steps = 25 06:59:13 [INFO] train episode 43237: reward = -81.24, steps = 20 06:59:16 [INFO] train episode 43238: reward = -111.03, steps = 35 06:59:18 [INFO] train episode 43239: reward = -73.91, steps = 28 06:59:20 [INFO] train episode 43240: reward = -76.80, steps = 19 06:59:21 [INFO] train episode 43241: reward = -63.89, steps = 19 06:59:23 [INFO] train episode 43242: reward = -78.47, steps = 18 06:59:25 [INFO] train episode 43243: reward = -49.16, steps = 23 06:59:27 [INFO] train episode 43244: reward = -60.60, steps = 21 06:59:29 [INFO] train episode 43245: reward = -90.61, steps = 22 06:59:31 [INFO] train episode 43246: reward = -71.41, steps = 26 06:59:34 [INFO] train episode 43247: reward = -145.20, steps = 34 06:59:36 [INFO] train episode 43248: reward = -80.69, steps = 21 06:59:38 [INFO] train episode 43249: reward = -70.30, steps = 19 06:59:40 [INFO] train episode 43250: reward = -87.27, steps = 24 06:59:42 [INFO] train episode 43251: reward = -109.10, steps = 29 06:59:44 [INFO] train episode 43252: reward = -80.77, steps = 19 06:59:46 [INFO] train episode 43253: reward = -81.31, steps = 22 06:59:48 [INFO] train episode 43254: reward = -65.20, steps = 23 06:59:50 [INFO] train episode 43255: reward = -65.29, steps = 20 06:59:52 [INFO] train episode 43256: reward = -75.62, steps = 27 06:59:54 [INFO] train episode 43257: reward = -84.86, steps = 21 06:59:56 [INFO] train episode 43258: reward = -30.30, steps = 21 06:59:57 [INFO] train episode 43259: reward = -96.66, steps = 19 06:59:59 [INFO] train episode 43260: reward = -53.01, steps = 19 07:00:01 [INFO] train episode 43261: reward = -95.38, steps = 21 07:00:03 [INFO] train episode 43262: reward = -70.13, steps = 26 07:00:05 [INFO] train episode 43263: reward = -65.27, steps = 22 07:00:07 [INFO] train episode 43264: reward = -101.25, steps = 20 07:00:09 [INFO] train episode 43265: reward = -80.42, steps = 22 07:00:11 [INFO] train episode 43266: reward = -44.88, steps = 23 07:00:13 [INFO] train episode 43267: reward = -79.33, steps = 22 07:00:15 [INFO] train episode 43268: reward = -98.75, steps = 20 07:00:16 [INFO] train episode 43269: reward = -66.42, steps = 20 07:00:19 [INFO] train episode 43270: reward = -85.51, steps = 35 07:00:22 [INFO] train episode 43271: reward = -85.47, steps = 28 07:00:23 [INFO] train episode 43272: reward = -56.45, steps = 18 07:00:25 [INFO] train episode 43273: reward = -55.81, steps = 20 07:00:27 [INFO] train episode 43274: reward = -107.22, steps = 29 07:00:30 [INFO] train episode 43275: reward = -126.57, steps = 33 07:00:32 [INFO] train episode 43276: reward = -42.11, steps = 20 07:00:34 [INFO] train episode 43277: reward = -55.48, steps = 19 07:00:37 [INFO] train episode 43278: reward = -75.76, steps = 31 07:00:39 [INFO] train episode 43279: reward = -101.31, steps = 29 07:00:40 [INFO] train episode 43280: reward = -55.32, steps = 14 07:00:42 [INFO] train episode 43281: reward = -74.21, steps = 19 07:00:45 [INFO] train episode 43282: reward = -111.84, steps = 28 07:00:47 [INFO] train episode 43283: reward = -60.21, steps = 20 07:00:49 [INFO] train episode 43284: reward = -71.31, steps = 22 07:00:52 [INFO] train episode 43285: reward = -80.68, steps = 28 07:00:54 [INFO] train episode 43286: reward = -85.72, steps = 22 07:00:55 [INFO] train episode 43287: reward = -91.61, steps = 19 07:00:58 [INFO] train episode 43288: reward = -77.32, steps = 29 07:00:59 [INFO] train episode 43289: reward = -39.75, steps = 20 07:01:01 [INFO] train episode 43290: reward = -73.95, steps = 24 07:01:04 [INFO] train episode 43291: reward = -51.41, steps = 26 07:01:05 [INFO] train episode 43292: reward = -76.22, steps = 18 07:01:08 [INFO] train episode 43293: reward = -100.08, steps = 31 07:01:10 [INFO] train episode 43294: reward = -46.13, steps = 21 07:01:12 [INFO] train episode 43295: reward = -70.08, steps = 26 07:01:14 [INFO] train episode 43296: reward = -99.63, steps = 19 07:01:16 [INFO] train episode 43297: reward = -45.68, steps = 23 07:01:19 [INFO] train episode 43298: reward = -69.22, steps = 28 07:01:21 [INFO] train episode 43299: reward = -69.93, steps = 25 07:01:23 [INFO] train episode 43300: reward = -89.16, steps = 25 07:01:25 [INFO] train episode 43301: reward = -54.11, steps = 24 07:01:27 [INFO] train episode 43302: reward = -65.82, steps = 25 07:01:29 [INFO] train episode 43303: reward = -115.55, steps = 19 07:01:31 [INFO] train episode 43304: reward = -118.13, steps = 22 07:01:32 [INFO] train episode 43305: reward = -107.17, steps = 19 07:01:34 [INFO] train episode 43306: reward = -87.78, steps = 22 07:01:36 [INFO] train episode 43307: reward = -86.39, steps = 24 07:01:38 [INFO] train episode 43308: reward = -45.74, steps = 21 07:01:40 [INFO] train episode 43309: reward = -85.03, steps = 18 07:01:42 [INFO] train episode 43310: reward = -56.02, steps = 20 07:01:44 [INFO] train episode 43311: reward = -90.70, steps = 28 07:01:46 [INFO] train episode 43312: reward = -88.39, steps = 20 07:01:47 [INFO] train episode 43313: reward = -73.54, steps = 20 07:01:50 [INFO] train episode 43314: reward = -70.75, steps = 22 07:01:51 [INFO] train episode 43315: reward = -117.18, steps = 22 07:01:53 [INFO] train episode 43316: reward = -95.33, steps = 22 07:01:55 [INFO] train episode 43317: reward = -97.01, steps = 19 07:01:57 [INFO] train episode 43318: reward = -95.29, steps = 29 07:01:59 [INFO] train episode 43319: reward = -61.23, steps = 19 07:02:01 [INFO] train episode 43320: reward = -65.88, steps = 26 07:02:03 [INFO] train episode 43321: reward = -108.57, steps = 20 07:02:05 [INFO] train episode 43322: reward = -103.32, steps = 23 07:02:07 [INFO] train episode 43323: reward = -66.94, steps = 20 07:02:09 [INFO] train episode 43324: reward = -101.49, steps = 22 07:02:11 [INFO] train episode 43325: reward = -64.51, steps = 23 07:02:13 [INFO] train episode 43326: reward = -64.95, steps = 20 07:02:14 [INFO] train episode 43327: reward = -37.52, steps = 21 07:02:16 [INFO] train episode 43328: reward = -78.27, steps = 22 07:02:18 [INFO] train episode 43329: reward = -88.38, steps = 18 07:02:20 [INFO] train episode 43330: reward = -51.04, steps = 20 07:02:21 [INFO] train episode 43331: reward = -67.59, steps = 18 07:02:24 [INFO] train episode 43332: reward = -105.26, steps = 24 07:02:25 [INFO] train episode 43333: reward = -57.46, steps = 20 07:02:27 [INFO] train episode 43334: reward = -81.68, steps = 24 07:02:29 [INFO] train episode 43335: reward = -51.27, steps = 20 07:02:31 [INFO] train episode 43336: reward = -100.87, steps = 19 07:02:33 [INFO] train episode 43337: reward = -91.29, steps = 26 07:02:35 [INFO] train episode 43338: reward = -59.10, steps = 26 07:02:37 [INFO] train episode 43339: reward = -63.28, steps = 18 07:02:39 [INFO] train episode 43340: reward = -77.60, steps = 23 07:02:41 [INFO] train episode 43341: reward = -61.31, steps = 19 07:02:43 [INFO] train episode 43342: reward = -52.08, steps = 20 07:02:44 [INFO] train episode 43343: reward = -64.09, steps = 20 07:02:46 [INFO] train episode 43344: reward = -97.31, steps = 21 07:02:48 [INFO] train episode 43345: reward = -41.16, steps = 23 07:02:51 [INFO] train episode 43346: reward = -88.02, steps = 27 07:02:53 [INFO] train episode 43347: reward = -38.07, steps = 21 07:02:54 [INFO] train episode 43348: reward = -89.86, steps = 18 07:02:56 [INFO] train episode 43349: reward = -76.16, steps = 21 07:02:58 [INFO] train episode 43350: reward = -56.42, steps = 21 07:03:00 [INFO] train episode 43351: reward = -58.07, steps = 21 07:03:01 [INFO] train episode 43352: reward = -54.11, steps = 20 07:03:03 [INFO] train episode 43353: reward = -89.57, steps = 24 07:03:05 [INFO] train episode 43354: reward = -69.11, steps = 24 07:03:08 [INFO] train episode 43355: reward = -103.40, steps = 27 07:03:10 [INFO] train episode 43356: reward = -66.44, steps = 24 07:03:12 [INFO] train episode 43357: reward = -77.40, steps = 23 07:03:14 [INFO] train episode 43358: reward = -54.76, steps = 21 07:03:16 [INFO] train episode 43359: reward = -70.65, steps = 22 07:03:18 [INFO] train episode 43360: reward = -45.69, steps = 21 07:03:19 [INFO] train episode 43361: reward = -58.34, steps = 19 07:03:22 [INFO] train episode 43362: reward = -83.27, steps = 31 07:03:24 [INFO] train episode 43363: reward = -99.58, steps = 23 07:03:27 [INFO] train episode 43364: reward = -125.54, steps = 37 07:03:30 [INFO] train episode 43365: reward = -37.44, steps = 25 07:03:32 [INFO] train episode 43366: reward = -78.74, steps = 24 07:03:33 [INFO] train episode 43367: reward = -89.65, steps = 18 07:03:36 [INFO] train episode 43368: reward = -59.36, steps = 19 07:03:38 [INFO] train episode 43369: reward = -53.71, steps = 26 07:03:40 [INFO] train episode 43370: reward = -74.48, steps = 23 07:03:42 [INFO] train episode 43371: reward = -58.31, steps = 21 07:03:44 [INFO] train episode 43372: reward = -78.36, steps = 23 07:03:46 [INFO] train episode 43373: reward = -65.47, steps = 20 07:03:48 [INFO] train episode 43374: reward = -79.50, steps = 18 07:03:49 [INFO] train episode 43375: reward = -101.33, steps = 20 07:03:51 [INFO] train episode 43376: reward = -70.43, steps = 23 07:03:54 [INFO] train episode 43377: reward = -83.40, steps = 26 07:03:55 [INFO] train episode 43378: reward = -96.95, steps = 20 07:03:57 [INFO] train episode 43379: reward = -46.44, steps = 19 07:03:59 [INFO] train episode 43380: reward = -79.66, steps = 21 07:04:01 [INFO] train episode 43381: reward = -55.12, steps = 21 07:04:03 [INFO] train episode 43382: reward = -54.76, steps = 24 07:04:05 [INFO] train episode 43383: reward = -58.31, steps = 20 07:04:06 [INFO] train episode 43384: reward = -50.68, steps = 18 07:04:09 [INFO] train episode 43385: reward = -87.51, steps = 27 07:04:11 [INFO] train episode 43386: reward = -50.62, steps = 21 07:04:13 [INFO] train episode 43387: reward = -69.50, steps = 29 07:04:16 [INFO] train episode 43388: reward = -70.80, steps = 27 07:04:18 [INFO] train episode 43389: reward = -76.79, steps = 27 07:04:20 [INFO] train episode 43390: reward = -70.32, steps = 19 07:04:22 [INFO] train episode 43391: reward = -94.06, steps = 34 07:04:24 [INFO] train episode 43392: reward = -107.57, steps = 19 07:04:26 [INFO] train episode 43393: reward = -67.09, steps = 19 07:04:28 [INFO] train episode 43394: reward = -63.97, steps = 24 07:04:30 [INFO] train episode 43395: reward = -104.53, steps = 21 07:04:32 [INFO] train episode 43396: reward = -68.16, steps = 19 07:04:33 [INFO] train episode 43397: reward = -64.44, steps = 21 07:04:35 [INFO] train episode 43398: reward = -70.51, steps = 18 07:04:37 [INFO] train episode 43399: reward = -66.29, steps = 26 07:04:39 [INFO] train episode 43400: reward = -63.99, steps = 26 07:04:41 [INFO] train episode 43401: reward = -70.22, steps = 23 07:04:43 [INFO] train episode 43402: reward = -46.19, steps = 20 07:04:45 [INFO] train episode 43403: reward = -85.51, steps = 20 07:04:47 [INFO] train episode 43404: reward = -40.98, steps = 21 07:04:49 [INFO] train episode 43405: reward = -67.36, steps = 23 07:04:51 [INFO] train episode 43406: reward = -86.90, steps = 30 07:04:53 [INFO] train episode 43407: reward = -42.96, steps = 19 07:04:55 [INFO] train episode 43408: reward = -89.15, steps = 22 07:04:57 [INFO] train episode 43409: reward = -73.21, steps = 22 07:05:00 [INFO] train episode 43410: reward = -123.04, steps = 29 07:05:02 [INFO] train episode 43411: reward = -84.42, steps = 20 07:05:04 [INFO] train episode 43412: reward = -82.63, steps = 23 07:05:06 [INFO] train episode 43413: reward = -100.44, steps = 31 07:05:08 [INFO] train episode 43414: reward = -84.24, steps = 20 07:05:10 [INFO] train episode 43415: reward = -57.72, steps = 27 07:05:13 [INFO] train episode 43416: reward = -71.36, steps = 25 07:05:16 [INFO] train episode 43417: reward = -96.97, steps = 31 07:05:17 [INFO] train episode 43418: reward = -58.57, steps = 20 07:05:19 [INFO] train episode 43419: reward = -72.75, steps = 25 07:05:21 [INFO] train episode 43420: reward = -69.90, steps = 23 07:05:23 [INFO] train episode 43421: reward = -55.85, steps = 21 07:05:26 [INFO] train episode 43422: reward = -102.23, steps = 35 07:05:28 [INFO] train episode 43423: reward = -84.84, steps = 22 07:05:30 [INFO] train episode 43424: reward = -33.99, steps = 20 07:05:32 [INFO] train episode 43425: reward = -48.97, steps = 22 07:05:34 [INFO] train episode 43426: reward = -89.21, steps = 20 07:05:35 [INFO] train episode 43427: reward = -63.39, steps = 21 07:05:37 [INFO] train episode 43428: reward = -84.73, steps = 21 07:05:39 [INFO] train episode 43429: reward = -37.40, steps = 21 07:05:41 [INFO] train episode 43430: reward = -99.01, steps = 20 07:05:43 [INFO] train episode 43431: reward = -58.68, steps = 27 07:05:45 [INFO] train episode 43432: reward = -62.81, steps = 25 07:05:48 [INFO] train episode 43433: reward = -108.45, steps = 28 07:05:50 [INFO] train episode 43434: reward = -77.88, steps = 24 07:05:52 [INFO] train episode 43435: reward = -82.62, steps = 21 07:05:53 [INFO] train episode 43436: reward = -83.88, steps = 20 07:05:55 [INFO] train episode 43437: reward = -68.80, steps = 18 07:05:57 [INFO] train episode 43438: reward = -72.40, steps = 20 07:05:58 [INFO] train episode 43439: reward = -63.59, steps = 20 07:06:00 [INFO] train episode 43440: reward = -53.75, steps = 21 07:06:02 [INFO] train episode 43441: reward = -63.19, steps = 20 07:06:04 [INFO] train episode 43442: reward = -66.12, steps = 19 07:06:06 [INFO] train episode 43443: reward = -68.38, steps = 19 07:06:07 [INFO] train episode 43444: reward = -55.09, steps = 20 07:06:09 [INFO] train episode 43445: reward = -85.03, steps = 20 07:06:11 [INFO] train episode 43446: reward = -110.84, steps = 26 07:06:13 [INFO] train episode 43447: reward = -80.08, steps = 22 07:06:15 [INFO] train episode 43448: reward = -51.13, steps = 21 07:06:17 [INFO] train episode 43449: reward = -61.16, steps = 25 07:06:20 [INFO] train episode 43450: reward = -83.23, steps = 28 07:06:21 [INFO] train episode 43451: reward = -81.14, steps = 19 07:06:23 [INFO] train episode 43452: reward = -61.55, steps = 20 07:06:26 [INFO] train episode 43453: reward = -50.20, steps = 23 07:06:28 [INFO] train episode 43454: reward = -93.07, steps = 25 07:06:30 [INFO] train episode 43455: reward = -51.43, steps = 30 07:06:32 [INFO] train episode 43456: reward = -125.65, steps = 20 07:06:34 [INFO] train episode 43457: reward = -50.49, steps = 22 07:06:37 [INFO] train episode 43458: reward = -44.42, steps = 25 07:06:39 [INFO] train episode 43459: reward = -57.05, steps = 21 07:06:41 [INFO] train episode 43460: reward = -74.55, steps = 32 07:06:44 [INFO] train episode 43461: reward = -111.74, steps = 28 07:06:45 [INFO] train episode 43462: reward = -92.78, steps = 20 07:06:47 [INFO] train episode 43463: reward = -88.29, steps = 24 07:06:50 [INFO] train episode 43464: reward = -65.64, steps = 25 07:06:52 [INFO] train episode 43465: reward = -88.55, steps = 20 07:06:54 [INFO] train episode 43466: reward = -93.91, steps = 20 07:06:55 [INFO] train episode 43467: reward = -77.62, steps = 20 07:06:57 [INFO] train episode 43468: reward = -64.19, steps = 20 07:07:00 [INFO] train episode 43469: reward = -110.73, steps = 37 07:07:02 [INFO] train episode 43470: reward = -66.53, steps = 20 07:07:03 [INFO] train episode 43471: reward = -54.97, steps = 19 07:07:05 [INFO] train episode 43472: reward = -77.77, steps = 21 07:07:07 [INFO] train episode 43473: reward = -58.02, steps = 18 07:07:09 [INFO] train episode 43474: reward = -71.80, steps = 20 07:07:11 [INFO] train episode 43475: reward = -51.88, steps = 23 07:07:13 [INFO] train episode 43476: reward = -70.24, steps = 27 07:07:15 [INFO] train episode 43477: reward = -63.24, steps = 20 07:07:17 [INFO] train episode 43478: reward = -66.56, steps = 26 07:07:19 [INFO] train episode 43479: reward = -65.25, steps = 24 07:07:21 [INFO] train episode 43480: reward = -55.83, steps = 20 07:07:23 [INFO] train episode 43481: reward = -61.05, steps = 19 07:07:25 [INFO] train episode 43482: reward = -59.27, steps = 19 07:07:26 [INFO] train episode 43483: reward = -84.93, steps = 20 07:07:28 [INFO] train episode 43484: reward = -74.80, steps = 19 07:07:30 [INFO] train episode 43485: reward = -77.92, steps = 20 07:07:32 [INFO] train episode 43486: reward = -101.48, steps = 27 07:07:34 [INFO] train episode 43487: reward = -88.53, steps = 24 07:07:36 [INFO] train episode 43488: reward = -80.07, steps = 24 07:07:38 [INFO] train episode 43489: reward = -55.30, steps = 24 07:07:40 [INFO] train episode 43490: reward = -77.12, steps = 20 07:07:42 [INFO] train episode 43491: reward = -85.75, steps = 25 07:07:44 [INFO] train episode 43492: reward = -78.85, steps = 20 07:07:46 [INFO] train episode 43493: reward = -59.60, steps = 19 07:07:48 [INFO] train episode 43494: reward = -102.63, steps = 22 07:07:50 [INFO] train episode 43495: reward = -95.29, steps = 24 07:07:52 [INFO] train episode 43496: reward = -52.70, steps = 23 07:07:54 [INFO] train episode 43497: reward = -85.40, steps = 25 07:07:56 [INFO] train episode 43498: reward = -42.30, steps = 20 07:07:58 [INFO] train episode 43499: reward = -81.69, steps = 28 07:08:01 [INFO] train episode 43500: reward = -70.18, steps = 32 07:08:03 [INFO] train episode 43501: reward = -92.31, steps = 30 07:08:05 [INFO] train episode 43502: reward = -73.07, steps = 21 07:08:07 [INFO] train episode 43503: reward = -87.39, steps = 22 07:08:10 [INFO] train episode 43504: reward = -91.23, steps = 28 07:08:11 [INFO] train episode 43505: reward = -56.31, steps = 18 07:08:14 [INFO] train episode 43506: reward = -83.34, steps = 28 07:08:16 [INFO] train episode 43507: reward = -71.61, steps = 23 07:08:17 [INFO] train episode 43508: reward = -34.70, steps = 20 07:08:19 [INFO] train episode 43509: reward = -98.58, steps = 21 07:08:21 [INFO] train episode 43510: reward = -99.26, steps = 24 07:08:23 [INFO] train episode 43511: reward = -48.28, steps = 27 07:08:26 [INFO] train episode 43512: reward = -59.33, steps = 20 07:08:27 [INFO] train episode 43513: reward = -49.91, steps = 22 07:08:29 [INFO] train episode 43514: reward = -62.61, steps = 20 07:08:31 [INFO] train episode 43515: reward = -56.73, steps = 20 07:08:33 [INFO] train episode 43516: reward = -96.91, steps = 26 07:08:35 [INFO] train episode 43517: reward = -57.48, steps = 24 07:08:37 [INFO] train episode 43518: reward = -90.00, steps = 22 07:08:39 [INFO] train episode 43519: reward = -55.79, steps = 25 07:08:42 [INFO] train episode 43520: reward = -105.55, steps = 24 07:08:43 [INFO] train episode 43521: reward = -49.82, steps = 18 07:08:45 [INFO] train episode 43522: reward = -42.64, steps = 22 07:08:47 [INFO] train episode 43523: reward = -78.84, steps = 19 07:08:49 [INFO] train episode 43524: reward = -58.42, steps = 22 07:08:51 [INFO] train episode 43525: reward = -61.24, steps = 26 07:08:53 [INFO] train episode 43526: reward = -117.65, steps = 27 07:08:55 [INFO] train episode 43527: reward = -106.85, steps = 27 07:08:58 [INFO] train episode 43528: reward = -68.77, steps = 24 07:09:00 [INFO] train episode 43529: reward = -138.24, steps = 20 07:09:01 [INFO] train episode 43530: reward = -80.71, steps = 18 07:09:03 [INFO] train episode 43531: reward = -75.70, steps = 23 07:09:05 [INFO] train episode 43532: reward = -64.43, steps = 25 07:09:08 [INFO] train episode 43533: reward = -112.28, steps = 31 07:09:10 [INFO] train episode 43534: reward = -77.58, steps = 19 07:09:12 [INFO] train episode 43535: reward = -53.99, steps = 23 07:09:14 [INFO] train episode 43536: reward = -56.49, steps = 20 07:09:17 [INFO] train episode 43537: reward = -76.63, steps = 33 07:09:19 [INFO] train episode 43538: reward = -67.23, steps = 19 07:09:21 [INFO] train episode 43539: reward = -62.14, steps = 22 07:09:23 [INFO] train episode 43540: reward = -61.96, steps = 21 07:09:24 [INFO] train episode 43541: reward = -95.38, steps = 20 07:09:27 [INFO] train episode 43542: reward = -79.69, steps = 32 07:09:29 [INFO] train episode 43543: reward = -72.64, steps = 20 07:09:31 [INFO] train episode 43544: reward = -54.50, steps = 27 07:09:34 [INFO] train episode 43545: reward = -85.28, steps = 24 07:09:36 [INFO] train episode 43546: reward = -80.36, steps = 30 07:09:38 [INFO] train episode 43547: reward = -71.23, steps = 20 07:09:40 [INFO] train episode 43548: reward = -80.60, steps = 23 07:09:42 [INFO] train episode 43549: reward = -58.47, steps = 24 07:09:45 [INFO] train episode 43550: reward = -102.89, steps = 29 07:09:47 [INFO] train episode 43551: reward = -72.10, steps = 23 07:09:49 [INFO] train episode 43552: reward = -50.01, steps = 23 07:09:50 [INFO] train episode 43553: reward = -120.28, steps = 19 07:09:52 [INFO] train episode 43554: reward = -66.00, steps = 21 07:09:55 [INFO] train episode 43555: reward = -74.48, steps = 29 07:09:56 [INFO] train episode 43556: reward = -67.55, steps = 20 07:09:58 [INFO] train episode 43557: reward = -55.50, steps = 20 07:10:01 [INFO] train episode 43558: reward = -29.82, steps = 23 07:10:02 [INFO] train episode 43559: reward = -71.88, steps = 19 07:10:04 [INFO] train episode 43560: reward = -59.96, steps = 24 07:10:06 [INFO] train episode 43561: reward = -78.39, steps = 23 07:10:08 [INFO] train episode 43562: reward = -37.89, steps = 23 07:10:10 [INFO] train episode 43563: reward = -62.71, steps = 20 07:10:13 [INFO] train episode 43564: reward = -78.69, steps = 33 07:10:14 [INFO] train episode 43565: reward = -73.98, steps = 17 07:10:17 [INFO] train episode 43566: reward = -73.55, steps = 21 07:10:19 [INFO] train episode 43567: reward = -80.24, steps = 28 07:10:21 [INFO] train episode 43568: reward = -84.56, steps = 19 07:10:22 [INFO] train episode 43569: reward = -43.87, steps = 21 07:10:24 [INFO] train episode 43570: reward = -99.19, steps = 18 07:10:27 [INFO] train episode 43571: reward = -115.00, steps = 30 07:10:28 [INFO] train episode 43572: reward = -83.46, steps = 20 07:10:31 [INFO] train episode 43573: reward = -84.50, steps = 27 07:10:33 [INFO] train episode 43574: reward = -77.16, steps = 25 07:10:35 [INFO] train episode 43575: reward = -50.47, steps = 22 07:10:37 [INFO] train episode 43576: reward = -62.81, steps = 23 07:10:39 [INFO] train episode 43577: reward = -69.56, steps = 20 07:10:41 [INFO] train episode 43578: reward = -69.13, steps = 22 07:10:43 [INFO] train episode 43579: reward = -63.51, steps = 23 07:10:44 [INFO] train episode 43580: reward = -69.13, steps = 18 07:10:46 [INFO] train episode 43581: reward = -47.82, steps = 19 07:10:48 [INFO] train episode 43582: reward = -56.27, steps = 20 07:10:50 [INFO] train episode 43583: reward = -77.36, steps = 22 07:10:52 [INFO] train episode 43584: reward = -52.28, steps = 20 07:10:54 [INFO] train episode 43585: reward = -69.36, steps = 28 07:10:56 [INFO] train episode 43586: reward = -51.80, steps = 20 07:10:57 [INFO] train episode 43587: reward = -64.13, steps = 17 07:11:00 [INFO] train episode 43588: reward = -83.07, steps = 33 07:11:02 [INFO] train episode 43589: reward = -74.97, steps = 26 07:11:04 [INFO] train episode 43590: reward = -49.63, steps = 20 07:11:07 [INFO] train episode 43591: reward = -54.47, steps = 24 07:11:08 [INFO] train episode 43592: reward = -56.14, steps = 22 07:11:10 [INFO] train episode 43593: reward = -73.35, steps = 22 07:11:12 [INFO] train episode 43594: reward = -113.30, steps = 21 07:11:14 [INFO] train episode 43595: reward = -72.09, steps = 27 07:11:16 [INFO] train episode 43596: reward = -53.40, steps = 23 07:11:18 [INFO] train episode 43597: reward = -75.38, steps = 18 07:11:20 [INFO] train episode 43598: reward = -54.52, steps = 22 07:11:23 [INFO] train episode 43599: reward = -97.27, steps = 29 07:11:25 [INFO] train episode 43600: reward = -68.42, steps = 29 07:11:27 [INFO] train episode 43601: reward = -53.39, steps = 19 07:11:29 [INFO] train episode 43602: reward = -70.46, steps = 28 07:11:31 [INFO] train episode 43603: reward = -75.37, steps = 25 07:11:34 [INFO] train episode 43604: reward = -118.85, steps = 27 07:11:36 [INFO] train episode 43605: reward = -61.44, steps = 21 07:11:38 [INFO] train episode 43606: reward = -24.66, steps = 24 07:11:40 [INFO] train episode 43607: reward = -101.77, steps = 23 07:11:42 [INFO] train episode 43608: reward = -47.36, steps = 20 07:11:43 [INFO] train episode 43609: reward = -72.91, steps = 21 07:11:45 [INFO] train episode 43610: reward = -53.39, steps = 20 07:11:47 [INFO] train episode 43611: reward = -47.15, steps = 20 07:11:49 [INFO] train episode 43612: reward = -66.74, steps = 22 07:11:51 [INFO] train episode 43613: reward = -58.18, steps = 20 07:11:53 [INFO] train episode 43614: reward = -66.40, steps = 28 07:11:55 [INFO] train episode 43615: reward = -66.49, steps = 18 07:11:57 [INFO] train episode 43616: reward = -87.44, steps = 25 07:11:59 [INFO] train episode 43617: reward = -33.09, steps = 22 07:12:01 [INFO] train episode 43618: reward = -101.08, steps = 23 07:12:03 [INFO] train episode 43619: reward = -86.48, steps = 22 07:12:05 [INFO] train episode 43620: reward = -61.89, steps = 23 07:12:07 [INFO] train episode 43621: reward = -53.89, steps = 19 07:12:10 [INFO] train episode 43622: reward = -80.91, steps = 26 07:12:12 [INFO] train episode 43623: reward = -121.58, steps = 23 07:12:14 [INFO] train episode 43624: reward = -52.26, steps = 25 07:12:17 [INFO] train episode 43625: reward = -109.16, steps = 33 07:12:19 [INFO] train episode 43626: reward = -62.34, steps = 31 07:12:21 [INFO] train episode 43627: reward = -69.65, steps = 23 07:12:23 [INFO] train episode 43628: reward = -57.68, steps = 21 07:12:25 [INFO] train episode 43629: reward = -76.52, steps = 18 07:12:28 [INFO] train episode 43630: reward = -104.53, steps = 31 07:12:29 [INFO] train episode 43631: reward = -64.18, steps = 21 07:12:31 [INFO] train episode 43632: reward = -57.28, steps = 20 07:12:33 [INFO] train episode 43633: reward = -44.33, steps = 21 07:12:35 [INFO] train episode 43634: reward = -100.05, steps = 26 07:12:37 [INFO] train episode 43635: reward = -66.92, steps = 25 07:12:39 [INFO] train episode 43636: reward = -59.88, steps = 18 07:12:42 [INFO] train episode 43637: reward = -82.61, steps = 27 07:12:44 [INFO] train episode 43638: reward = -44.15, steps = 28 07:12:46 [INFO] train episode 43639: reward = -98.06, steps = 19 07:12:48 [INFO] train episode 43640: reward = -86.89, steps = 22 07:12:50 [INFO] train episode 43641: reward = -64.23, steps = 23 07:12:51 [INFO] train episode 43642: reward = -82.62, steps = 21 07:12:53 [INFO] train episode 43643: reward = -62.88, steps = 20 07:12:56 [INFO] train episode 43644: reward = -65.31, steps = 22 07:12:58 [INFO] train episode 43645: reward = -53.12, steps = 24 07:13:00 [INFO] train episode 43646: reward = -92.74, steps = 26 07:13:02 [INFO] train episode 43647: reward = -103.20, steps = 24 07:13:04 [INFO] train episode 43648: reward = -67.99, steps = 25 07:13:07 [INFO] train episode 43649: reward = -66.41, steps = 30 07:13:08 [INFO] train episode 43650: reward = -56.41, steps = 22 07:13:10 [INFO] train episode 43651: reward = -73.96, steps = 18 07:13:12 [INFO] train episode 43652: reward = -95.53, steps = 22 07:13:15 [INFO] train episode 43653: reward = -76.71, steps = 27 07:13:17 [INFO] train episode 43654: reward = -83.13, steps = 31 07:13:20 [INFO] train episode 43655: reward = -78.70, steps = 32 07:13:22 [INFO] train episode 43656: reward = -64.59, steps = 22 07:13:24 [INFO] train episode 43657: reward = -48.27, steps = 22 07:13:26 [INFO] train episode 43658: reward = -47.22, steps = 22 07:13:28 [INFO] train episode 43659: reward = -36.82, steps = 20 07:13:30 [INFO] train episode 43660: reward = -87.25, steps = 26 07:13:32 [INFO] train episode 43661: reward = -90.62, steps = 25 07:13:34 [INFO] train episode 43662: reward = -67.37, steps = 19 07:13:35 [INFO] train episode 43663: reward = -83.68, steps = 19 07:13:37 [INFO] train episode 43664: reward = -90.69, steps = 20 07:13:39 [INFO] train episode 43665: reward = -74.97, steps = 26 07:13:41 [INFO] train episode 43666: reward = -55.89, steps = 25 07:13:44 [INFO] train episode 43667: reward = -77.56, steps = 26 07:13:46 [INFO] train episode 43668: reward = -46.58, steps = 24 07:13:48 [INFO] train episode 43669: reward = -116.75, steps = 23 07:13:50 [INFO] train episode 43670: reward = -67.69, steps = 28 07:13:53 [INFO] train episode 43671: reward = -120.58, steps = 34 07:13:55 [INFO] train episode 43672: reward = -43.73, steps = 20 07:13:57 [INFO] train episode 43673: reward = -143.13, steps = 21 07:13:59 [INFO] train episode 43674: reward = -72.78, steps = 22 07:14:01 [INFO] train episode 43675: reward = -74.47, steps = 17 07:14:03 [INFO] train episode 43676: reward = -105.12, steps = 29 07:14:05 [INFO] train episode 43677: reward = -87.12, steps = 29 07:14:07 [INFO] train episode 43678: reward = -90.94, steps = 21 07:14:09 [INFO] train episode 43679: reward = -55.88, steps = 21 07:14:11 [INFO] train episode 43680: reward = -64.34, steps = 21 07:14:13 [INFO] train episode 43681: reward = -67.04, steps = 18 07:14:15 [INFO] train episode 43682: reward = -73.23, steps = 19 07:14:16 [INFO] train episode 43683: reward = -65.77, steps = 17 07:14:18 [INFO] train episode 43684: reward = -80.71, steps = 23 07:14:20 [INFO] train episode 43685: reward = -81.06, steps = 21 07:14:22 [INFO] train episode 43686: reward = -62.40, steps = 25 07:14:24 [INFO] train episode 43687: reward = -76.26, steps = 22 07:14:26 [INFO] train episode 43688: reward = -83.74, steps = 25 07:14:28 [INFO] train episode 43689: reward = -84.13, steps = 20 07:14:29 [INFO] train episode 43690: reward = -59.76, steps = 16 07:14:32 [INFO] train episode 43691: reward = -91.39, steps = 32 07:14:35 [INFO] train episode 43692: reward = -65.41, steps = 30 07:14:36 [INFO] train episode 43693: reward = -67.15, steps = 20 07:14:38 [INFO] train episode 43694: reward = -63.99, steps = 22 07:14:41 [INFO] train episode 43695: reward = -76.88, steps = 24 07:14:42 [INFO] train episode 43696: reward = -152.09, steps = 19 07:14:45 [INFO] train episode 43697: reward = -75.89, steps = 32 07:14:48 [INFO] train episode 43698: reward = -71.98, steps = 25 07:14:50 [INFO] train episode 43699: reward = -52.63, steps = 25 07:14:52 [INFO] train episode 43700: reward = -65.04, steps = 23 07:14:53 [INFO] train episode 43701: reward = -72.89, steps = 18 07:14:55 [INFO] train episode 43702: reward = -59.59, steps = 20 07:14:57 [INFO] train episode 43703: reward = -81.32, steps = 19 07:15:00 [INFO] train episode 43704: reward = -94.44, steps = 31 07:15:02 [INFO] train episode 43705: reward = -55.94, steps = 18 07:15:05 [INFO] train episode 43706: reward = -112.35, steps = 33 07:15:07 [INFO] train episode 43707: reward = -75.63, steps = 27 07:15:08 [INFO] train episode 43708: reward = -53.95, steps = 18 07:15:10 [INFO] train episode 43709: reward = -141.76, steps = 22 07:15:12 [INFO] train episode 43710: reward = -55.44, steps = 21 07:15:14 [INFO] train episode 43711: reward = -88.81, steps = 20 07:15:17 [INFO] train episode 43712: reward = -70.57, steps = 31 07:15:19 [INFO] train episode 43713: reward = -40.57, steps = 23 07:15:21 [INFO] train episode 43714: reward = -60.93, steps = 25 07:15:23 [INFO] train episode 43715: reward = -74.49, steps = 23 07:15:25 [INFO] train episode 43716: reward = -92.09, steps = 27 07:15:27 [INFO] train episode 43717: reward = -74.59, steps = 20 07:15:29 [INFO] train episode 43718: reward = -80.66, steps = 19 07:15:31 [INFO] train episode 43719: reward = -48.96, steps = 23 07:15:33 [INFO] train episode 43720: reward = -70.79, steps = 28 07:15:35 [INFO] train episode 43721: reward = -63.97, steps = 21 07:15:37 [INFO] train episode 43722: reward = -60.68, steps = 19 07:15:38 [INFO] train episode 43723: reward = -54.92, steps = 18 07:15:40 [INFO] train episode 43724: reward = -76.29, steps = 18 07:15:42 [INFO] train episode 43725: reward = -52.23, steps = 22 07:15:43 [INFO] train episode 43726: reward = -48.13, steps = 20 07:15:46 [INFO] train episode 43727: reward = -113.08, steps = 27 07:15:47 [INFO] train episode 43728: reward = -67.43, steps = 21 07:15:50 [INFO] train episode 43729: reward = -79.56, steps = 25 07:15:53 [INFO] train episode 43730: reward = -76.47, steps = 37 07:15:55 [INFO] train episode 43731: reward = -57.23, steps = 26 07:15:57 [INFO] train episode 43732: reward = -58.28, steps = 20 07:16:00 [INFO] train episode 43733: reward = -89.15, steps = 29 07:16:01 [INFO] train episode 43734: reward = -45.31, steps = 21 07:16:04 [INFO] train episode 43735: reward = -84.76, steps = 28 07:16:07 [INFO] train episode 43736: reward = -91.29, steps = 29 07:16:09 [INFO] train episode 43737: reward = -114.96, steps = 31 07:16:11 [INFO] train episode 43738: reward = -76.80, steps = 19 07:16:13 [INFO] train episode 43739: reward = -78.73, steps = 20 07:16:14 [INFO] train episode 43740: reward = -61.06, steps = 20 07:16:16 [INFO] train episode 43741: reward = -35.31, steps = 20 07:16:18 [INFO] train episode 43742: reward = -72.37, steps = 22 07:16:20 [INFO] train episode 43743: reward = -89.62, steps = 21 07:16:22 [INFO] train episode 43744: reward = -103.60, steps = 19 07:16:24 [INFO] train episode 43745: reward = -88.55, steps = 25 07:16:26 [INFO] train episode 43746: reward = -78.58, steps = 25 07:16:28 [INFO] train episode 43747: reward = -84.04, steps = 25 07:16:30 [INFO] train episode 43748: reward = -79.09, steps = 23 07:16:32 [INFO] train episode 43749: reward = -70.61, steps = 26 07:16:34 [INFO] train episode 43750: reward = -83.99, steps = 21 07:16:36 [INFO] train episode 43751: reward = -70.94, steps = 20 07:16:39 [INFO] train episode 43752: reward = -56.11, steps = 29 07:16:41 [INFO] train episode 43753: reward = -52.39, steps = 21 07:16:42 [INFO] train episode 43754: reward = -90.14, steps = 20 07:16:44 [INFO] train episode 43755: reward = -53.48, steps = 25 07:16:46 [INFO] train episode 43756: reward = -83.57, steps = 19 07:16:48 [INFO] train episode 43757: reward = -93.69, steps = 21 07:16:50 [INFO] train episode 43758: reward = -81.52, steps = 20 07:16:53 [INFO] train episode 43759: reward = -104.25, steps = 32 07:16:55 [INFO] train episode 43760: reward = -84.67, steps = 20 07:16:56 [INFO] train episode 43761: reward = -63.89, steps = 19 07:16:58 [INFO] train episode 43762: reward = -100.35, steps = 20 07:17:00 [INFO] train episode 43763: reward = -59.58, steps = 20 07:17:02 [INFO] train episode 43764: reward = -73.69, steps = 30 07:17:04 [INFO] train episode 43765: reward = -46.05, steps = 21 07:17:06 [INFO] train episode 43766: reward = -88.99, steps = 23 07:17:08 [INFO] train episode 43767: reward = -78.20, steps = 21 07:17:10 [INFO] train episode 43768: reward = -73.85, steps = 23 07:17:13 [INFO] train episode 43769: reward = -129.85, steps = 33 07:17:15 [INFO] train episode 43770: reward = -87.61, steps = 28 07:17:17 [INFO] train episode 43771: reward = -69.68, steps = 22 07:17:19 [INFO] train episode 43772: reward = -54.48, steps = 25 07:17:21 [INFO] train episode 43773: reward = -60.04, steps = 19 07:17:23 [INFO] train episode 43774: reward = -62.00, steps = 20 07:17:26 [INFO] train episode 43775: reward = -68.97, steps = 29 07:17:28 [INFO] train episode 43776: reward = -52.87, steps = 24 07:17:29 [INFO] train episode 43777: reward = -48.96, steps = 20 07:17:31 [INFO] train episode 43778: reward = -93.70, steps = 19 07:17:33 [INFO] train episode 43779: reward = -63.58, steps = 19 07:17:36 [INFO] train episode 43780: reward = -92.33, steps = 34 07:17:37 [INFO] train episode 43781: reward = -89.31, steps = 20 07:17:40 [INFO] train episode 43782: reward = -90.19, steps = 30 07:17:43 [INFO] train episode 43783: reward = -69.14, steps = 31 07:17:45 [INFO] train episode 43784: reward = -82.82, steps = 25 07:17:47 [INFO] train episode 43785: reward = -50.62, steps = 20 07:17:49 [INFO] train episode 43786: reward = -57.95, steps = 20 07:17:51 [INFO] train episode 43787: reward = -57.61, steps = 22 07:17:54 [INFO] train episode 43788: reward = -66.71, steps = 30 07:17:56 [INFO] train episode 43789: reward = -87.43, steps = 29 07:17:58 [INFO] train episode 43790: reward = -53.30, steps = 20 07:18:00 [INFO] train episode 43791: reward = -55.81, steps = 20 07:18:03 [INFO] train episode 43792: reward = -96.71, steps = 33 07:18:04 [INFO] train episode 43793: reward = -55.05, steps = 21 07:18:06 [INFO] train episode 43794: reward = -43.74, steps = 19 07:18:08 [INFO] train episode 43795: reward = -43.65, steps = 21 07:18:10 [INFO] train episode 43796: reward = -78.08, steps = 22 07:18:11 [INFO] train episode 43797: reward = -46.20, steps = 19 07:18:14 [INFO] train episode 43798: reward = -57.61, steps = 23 07:18:16 [INFO] train episode 43799: reward = -89.27, steps = 21 07:18:18 [INFO] train episode 43800: reward = -65.30, steps = 25 07:18:20 [INFO] train episode 43801: reward = -59.89, steps = 24 07:18:22 [INFO] train episode 43802: reward = -66.26, steps = 23 07:18:24 [INFO] train episode 43803: reward = -80.72, steps = 23 07:18:26 [INFO] train episode 43804: reward = -60.53, steps = 24 07:18:28 [INFO] train episode 43805: reward = -60.63, steps = 22 07:18:30 [INFO] train episode 43806: reward = -75.55, steps = 22 07:18:32 [INFO] train episode 43807: reward = -57.09, steps = 24 07:18:34 [INFO] train episode 43808: reward = -40.22, steps = 21 07:18:36 [INFO] train episode 43809: reward = -60.59, steps = 23 07:18:38 [INFO] train episode 43810: reward = -65.86, steps = 27 07:18:41 [INFO] train episode 43811: reward = -64.50, steps = 27 07:18:43 [INFO] train episode 43812: reward = -69.95, steps = 28 07:18:47 [INFO] train episode 43813: reward = -123.16, steps = 45 07:18:49 [INFO] train episode 43814: reward = -76.00, steps = 22 07:18:52 [INFO] train episode 43815: reward = -60.76, steps = 32 07:18:54 [INFO] train episode 43816: reward = -39.58, steps = 22 07:18:56 [INFO] train episode 43817: reward = -78.24, steps = 25 07:18:58 [INFO] train episode 43818: reward = -68.28, steps = 23 07:19:00 [INFO] train episode 43819: reward = -44.50, steps = 20 07:19:02 [INFO] train episode 43820: reward = -98.95, steps = 22 07:19:04 [INFO] train episode 43821: reward = -81.17, steps = 20 07:19:05 [INFO] train episode 43822: reward = -77.58, steps = 22 07:19:08 [INFO] train episode 43823: reward = -51.31, steps = 26 07:19:09 [INFO] train episode 43824: reward = -69.60, steps = 20 07:19:11 [INFO] train episode 43825: reward = -68.35, steps = 20 07:19:13 [INFO] train episode 43826: reward = -73.16, steps = 24 07:19:15 [INFO] train episode 43827: reward = -41.94, steps = 18 07:19:17 [INFO] train episode 43828: reward = -100.22, steps = 21 07:19:19 [INFO] train episode 43829: reward = -53.97, steps = 20 07:19:21 [INFO] train episode 43830: reward = -67.79, steps = 27 07:19:23 [INFO] train episode 43831: reward = -78.54, steps = 24 07:19:25 [INFO] train episode 43832: reward = -61.07, steps = 22 07:19:27 [INFO] train episode 43833: reward = -90.90, steps = 29 07:19:30 [INFO] train episode 43834: reward = -45.65, steps = 32 07:19:33 [INFO] train episode 43835: reward = -66.61, steps = 26 07:19:35 [INFO] train episode 43836: reward = -111.47, steps = 31 07:19:37 [INFO] train episode 43837: reward = -92.53, steps = 25 07:19:39 [INFO] train episode 43838: reward = -66.54, steps = 21 07:19:42 [INFO] train episode 43839: reward = -96.42, steps = 34 07:19:44 [INFO] train episode 43840: reward = -81.84, steps = 24 07:19:46 [INFO] train episode 43841: reward = -89.50, steps = 29 07:19:49 [INFO] train episode 43842: reward = -66.85, steps = 33 07:19:52 [INFO] train episode 43843: reward = -72.44, steps = 25 07:19:53 [INFO] train episode 43844: reward = -61.20, steps = 20 07:19:56 [INFO] train episode 43845: reward = -86.49, steps = 28 07:19:58 [INFO] train episode 43846: reward = -73.86, steps = 23 07:20:00 [INFO] train episode 43847: reward = -103.80, steps = 24 07:20:02 [INFO] train episode 43848: reward = -71.14, steps = 24 07:20:04 [INFO] train episode 43849: reward = -88.74, steps = 25 07:20:06 [INFO] train episode 43850: reward = -54.55, steps = 19 07:20:08 [INFO] train episode 43851: reward = -54.56, steps = 23 07:20:11 [INFO] train episode 43852: reward = -119.73, steps = 35 07:20:13 [INFO] train episode 43853: reward = -88.45, steps = 24 07:20:15 [INFO] train episode 43854: reward = -51.44, steps = 20 07:20:17 [INFO] train episode 43855: reward = -78.88, steps = 25 07:20:21 [INFO] train episode 43856: reward = -103.40, steps = 39 07:20:24 [INFO] train episode 43857: reward = -72.66, steps = 28 07:20:26 [INFO] train episode 43858: reward = -75.31, steps = 23 07:20:28 [INFO] train episode 43859: reward = -43.21, steps = 20 07:20:30 [INFO] train episode 43860: reward = -73.02, steps = 27 07:20:33 [INFO] train episode 43861: reward = -90.05, steps = 28 07:20:36 [INFO] train episode 43862: reward = -58.21, steps = 28 07:20:38 [INFO] train episode 43863: reward = -61.09, steps = 18 07:20:40 [INFO] train episode 43864: reward = -62.72, steps = 19 07:20:42 [INFO] train episode 43865: reward = -56.95, steps = 19 07:20:44 [INFO] train episode 43866: reward = -71.92, steps = 25 07:20:47 [INFO] train episode 43867: reward = -54.87, steps = 22 07:20:48 [INFO] train episode 43868: reward = -59.23, steps = 20 07:20:50 [INFO] train episode 43869: reward = -50.18, steps = 21 07:20:53 [INFO] train episode 43870: reward = -90.52, steps = 23 07:20:55 [INFO] train episode 43871: reward = -47.62, steps = 19 07:20:58 [INFO] train episode 43872: reward = -103.48, steps = 39 07:21:01 [INFO] train episode 43873: reward = -78.71, steps = 31 07:21:03 [INFO] train episode 43874: reward = -67.13, steps = 26 07:21:05 [INFO] train episode 43875: reward = -76.76, steps = 25 07:21:07 [INFO] train episode 43876: reward = -64.52, steps = 21 07:21:10 [INFO] train episode 43877: reward = -82.27, steps = 34 07:21:13 [INFO] train episode 43878: reward = -133.16, steps = 31 07:21:14 [INFO] train episode 43879: reward = -74.45, steps = 21 07:21:16 [INFO] train episode 43880: reward = -65.54, steps = 22 07:21:18 [INFO] train episode 43881: reward = -56.47, steps = 22 07:21:21 [INFO] train episode 43882: reward = -71.59, steps = 29 07:21:23 [INFO] train episode 43883: reward = -57.85, steps = 22 07:21:25 [INFO] train episode 43884: reward = -73.98, steps = 23 07:21:27 [INFO] train episode 43885: reward = -88.99, steps = 20 07:21:29 [INFO] train episode 43886: reward = -106.14, steps = 30 07:21:32 [INFO] train episode 43887: reward = -79.13, steps = 30 07:21:34 [INFO] train episode 43888: reward = -70.60, steps = 26 07:21:35 [INFO] train episode 43889: reward = -63.42, steps = 18 07:21:38 [INFO] train episode 43890: reward = -63.77, steps = 27 07:21:40 [INFO] train episode 43891: reward = -66.40, steps = 21 07:21:43 [INFO] train episode 43892: reward = -120.92, steps = 36 07:21:45 [INFO] train episode 43893: reward = -71.13, steps = 20 07:21:47 [INFO] train episode 43894: reward = -33.16, steps = 21 07:21:49 [INFO] train episode 43895: reward = -95.49, steps = 25 07:21:51 [INFO] train episode 43896: reward = -50.70, steps = 21 07:21:53 [INFO] train episode 43897: reward = -83.81, steps = 31 07:21:55 [INFO] train episode 43898: reward = -46.04, steps = 22 07:21:58 [INFO] train episode 43899: reward = -52.74, steps = 32 07:22:00 [INFO] train episode 43900: reward = -60.31, steps = 20 07:22:02 [INFO] train episode 43901: reward = -87.53, steps = 24 07:22:04 [INFO] train episode 43902: reward = -42.93, steps = 27 07:22:06 [INFO] train episode 43903: reward = -52.69, steps = 20 07:22:08 [INFO] train episode 43904: reward = -57.02, steps = 23 07:22:11 [INFO] train episode 43905: reward = -78.83, steps = 36 07:22:13 [INFO] train episode 43906: reward = -41.29, steps = 20 07:22:16 [INFO] train episode 43907: reward = -79.46, steps = 34 07:22:18 [INFO] train episode 43908: reward = -47.44, steps = 19 07:22:20 [INFO] train episode 43909: reward = -92.83, steps = 33 07:22:22 [INFO] train episode 43910: reward = -47.50, steps = 22 07:22:25 [INFO] train episode 43911: reward = -74.44, steps = 39 07:22:28 [INFO] train episode 43912: reward = -50.47, steps = 25 07:22:30 [INFO] train episode 43913: reward = -51.04, steps = 26 07:22:32 [INFO] train episode 43914: reward = -55.56, steps = 20 07:22:34 [INFO] train episode 43915: reward = -90.59, steps = 24 07:22:36 [INFO] train episode 43916: reward = -87.56, steps = 19 07:22:38 [INFO] train episode 43917: reward = -93.16, steps = 25 07:22:40 [INFO] train episode 43918: reward = -39.73, steps = 20 07:22:42 [INFO] train episode 43919: reward = -159.39, steps = 30 07:22:44 [INFO] train episode 43920: reward = -84.43, steps = 19 07:22:46 [INFO] train episode 43921: reward = -55.58, steps = 25 07:22:48 [INFO] train episode 43922: reward = -79.53, steps = 24 07:22:50 [INFO] train episode 43923: reward = -49.77, steps = 23 07:22:53 [INFO] train episode 43924: reward = -46.99, steps = 28 07:22:54 [INFO] train episode 43925: reward = -120.30, steps = 19 07:22:56 [INFO] train episode 43926: reward = -80.64, steps = 18 07:22:58 [INFO] train episode 43927: reward = -62.16, steps = 20 07:23:01 [INFO] train episode 43928: reward = -45.68, steps = 28 07:23:02 [INFO] train episode 43929: reward = -112.87, steps = 20 07:23:04 [INFO] train episode 43930: reward = -30.98, steps = 22 07:23:06 [INFO] train episode 43931: reward = -72.25, steps = 23 07:23:08 [INFO] train episode 43932: reward = -77.93, steps = 20 07:23:10 [INFO] train episode 43933: reward = -86.96, steps = 24 07:23:12 [INFO] train episode 43934: reward = -49.33, steps = 27 07:23:14 [INFO] train episode 43935: reward = -102.86, steps = 20 07:23:15 [INFO] train episode 43936: reward = -101.28, steps = 17 07:23:18 [INFO] train episode 43937: reward = -78.88, steps = 25 07:23:21 [INFO] train episode 43938: reward = -82.50, steps = 30 07:23:23 [INFO] train episode 43939: reward = -79.20, steps = 24 07:23:24 [INFO] train episode 43940: reward = -68.63, steps = 19 07:23:26 [INFO] train episode 43941: reward = -107.39, steps = 19 07:23:28 [INFO] train episode 43942: reward = -61.86, steps = 27 07:23:31 [INFO] train episode 43943: reward = -43.86, steps = 21 07:23:33 [INFO] train episode 43944: reward = -43.69, steps = 25 07:23:36 [INFO] train episode 43945: reward = -49.37, steps = 28 07:23:38 [INFO] train episode 43946: reward = -47.86, steps = 19 07:23:40 [INFO] train episode 43947: reward = -66.18, steps = 33 07:23:42 [INFO] train episode 43948: reward = -61.90, steps = 21 07:23:44 [INFO] train episode 43949: reward = -90.72, steps = 26 07:23:46 [INFO] train episode 43950: reward = -67.97, steps = 19 07:23:48 [INFO] train episode 43951: reward = -52.42, steps = 20 07:23:50 [INFO] train episode 43952: reward = -66.36, steps = 20 07:23:52 [INFO] train episode 43953: reward = -47.43, steps = 25 07:23:54 [INFO] train episode 43954: reward = -76.70, steps = 29 07:23:56 [INFO] train episode 43955: reward = -77.15, steps = 22 07:23:58 [INFO] train episode 43956: reward = -60.23, steps = 21 07:24:00 [INFO] train episode 43957: reward = -45.71, steps = 21 07:24:02 [INFO] train episode 43958: reward = -71.86, steps = 27 07:24:04 [INFO] train episode 43959: reward = -64.69, steps = 22 07:24:07 [INFO] train episode 43960: reward = -123.70, steps = 37 07:24:10 [INFO] train episode 43961: reward = -62.09, steps = 31 07:24:12 [INFO] train episode 43962: reward = -97.37, steps = 29 07:24:15 [INFO] train episode 43963: reward = -67.32, steps = 25 07:24:17 [INFO] train episode 43964: reward = -59.60, steps = 27 07:24:19 [INFO] train episode 43965: reward = -77.95, steps = 21 07:24:21 [INFO] train episode 43966: reward = -121.84, steps = 22 07:24:23 [INFO] train episode 43967: reward = -54.55, steps = 21 07:24:25 [INFO] train episode 43968: reward = -74.54, steps = 25 07:24:27 [INFO] train episode 43969: reward = -54.36, steps = 26 07:24:29 [INFO] train episode 43970: reward = -67.72, steps = 22 07:24:31 [INFO] train episode 43971: reward = -60.24, steps = 21 07:24:33 [INFO] train episode 43972: reward = -108.24, steps = 21 07:24:35 [INFO] train episode 43973: reward = -78.96, steps = 28 07:24:37 [INFO] train episode 43974: reward = -73.00, steps = 16 07:24:39 [INFO] train episode 43975: reward = -81.61, steps = 27 07:24:41 [INFO] train episode 43976: reward = -77.38, steps = 22 07:24:43 [INFO] train episode 43977: reward = -61.36, steps = 19 07:24:46 [INFO] train episode 43978: reward = -52.57, steps = 35 07:24:48 [INFO] train episode 43979: reward = -35.47, steps = 27 07:24:51 [INFO] train episode 43980: reward = -83.16, steps = 27 07:24:53 [INFO] train episode 43981: reward = -59.50, steps = 22 07:24:55 [INFO] train episode 43982: reward = -70.90, steps = 19 07:24:56 [INFO] train episode 43983: reward = -56.44, steps = 18 07:24:59 [INFO] train episode 43984: reward = -81.34, steps = 30 07:25:01 [INFO] train episode 43985: reward = -93.59, steps = 24 07:25:03 [INFO] train episode 43986: reward = -61.97, steps = 23 07:25:05 [INFO] train episode 43987: reward = -74.28, steps = 20 07:25:07 [INFO] train episode 43988: reward = -48.84, steps = 27 07:25:09 [INFO] train episode 43989: reward = -49.92, steps = 20 07:25:12 [INFO] train episode 43990: reward = -108.79, steps = 31 07:25:14 [INFO] train episode 43991: reward = -82.83, steps = 21 07:25:16 [INFO] train episode 43992: reward = -78.00, steps = 33 07:25:18 [INFO] train episode 43993: reward = -68.11, steps = 20 07:25:20 [INFO] train episode 43994: reward = -62.38, steps = 19 07:25:22 [INFO] train episode 43995: reward = -44.11, steps = 20 07:25:24 [INFO] train episode 43996: reward = -59.34, steps = 26 07:25:26 [INFO] train episode 43997: reward = -66.64, steps = 21 07:25:28 [INFO] train episode 43998: reward = -68.49, steps = 21 07:25:30 [INFO] train episode 43999: reward = -89.52, steps = 32 07:25:32 [INFO] train episode 44000: reward = -70.49, steps = 19 07:25:35 [INFO] train episode 44001: reward = -97.74, steps = 28 07:25:37 [INFO] train episode 44002: reward = -87.73, steps = 27 07:25:39 [INFO] train episode 44003: reward = -62.98, steps = 27 07:25:41 [INFO] train episode 44004: reward = -61.10, steps = 20 07:25:43 [INFO] train episode 44005: reward = -90.67, steps = 26 07:25:46 [INFO] train episode 44006: reward = -67.22, steps = 25 07:25:49 [INFO] train episode 44007: reward = -72.74, steps = 36 07:25:50 [INFO] train episode 44008: reward = -78.58, steps = 21 07:25:52 [INFO] train episode 44009: reward = -69.32, steps = 21 07:25:55 [INFO] train episode 44010: reward = -78.39, steps = 29 07:25:57 [INFO] train episode 44011: reward = -103.87, steps = 27 07:25:59 [INFO] train episode 44012: reward = -45.33, steps = 19 07:26:01 [INFO] train episode 44013: reward = -48.88, steps = 20 07:26:03 [INFO] train episode 44014: reward = -144.83, steps = 21 07:26:04 [INFO] train episode 44015: reward = -55.90, steps = 20 07:26:07 [INFO] train episode 44016: reward = -41.08, steps = 31 07:26:09 [INFO] train episode 44017: reward = -56.39, steps = 29 07:26:12 [INFO] train episode 44018: reward = -55.73, steps = 28 07:26:15 [INFO] train episode 44019: reward = -67.86, steps = 28 07:26:17 [INFO] train episode 44020: reward = -69.69, steps = 28 07:26:19 [INFO] train episode 44021: reward = -123.48, steps = 23 07:26:21 [INFO] train episode 44022: reward = -48.04, steps = 18 07:26:23 [INFO] train episode 44023: reward = -54.20, steps = 21 07:26:25 [INFO] train episode 44024: reward = -36.21, steps = 23 07:26:29 [INFO] train episode 44025: reward = -104.96, steps = 39 07:26:31 [INFO] train episode 44026: reward = -33.60, steps = 32 07:26:33 [INFO] train episode 44027: reward = -62.93, steps = 23 07:26:35 [INFO] train episode 44028: reward = -64.88, steps = 20 07:26:38 [INFO] train episode 44029: reward = -99.22, steps = 27 07:26:40 [INFO] train episode 44030: reward = -50.55, steps = 30 07:26:42 [INFO] train episode 44031: reward = -90.23, steps = 23 07:26:45 [INFO] train episode 44032: reward = -63.84, steps = 27 07:26:47 [INFO] train episode 44033: reward = -80.39, steps = 20 07:26:49 [INFO] train episode 44034: reward = -108.18, steps = 28 07:26:52 [INFO] train episode 44035: reward = -120.28, steps = 33 07:26:54 [INFO] train episode 44036: reward = -76.38, steps = 23 07:26:56 [INFO] train episode 44037: reward = -58.92, steps = 23 07:26:58 [INFO] train episode 44038: reward = -101.50, steps = 29 07:27:01 [INFO] train episode 44039: reward = -60.74, steps = 24 07:27:05 [INFO] train episode 44040: reward = -117.46, steps = 47 07:27:06 [INFO] train episode 44041: reward = -47.71, steps = 21 07:27:09 [INFO] train episode 44042: reward = -74.30, steps = 28 07:27:11 [INFO] train episode 44043: reward = -92.66, steps = 26 07:27:14 [INFO] train episode 44044: reward = -92.39, steps = 34 07:27:16 [INFO] train episode 44045: reward = -79.10, steps = 21 07:27:18 [INFO] train episode 44046: reward = -45.74, steps = 19 07:27:20 [INFO] train episode 44047: reward = -73.70, steps = 29 07:27:22 [INFO] train episode 44048: reward = -56.01, steps = 23 07:27:24 [INFO] train episode 44049: reward = -39.99, steps = 25 07:27:27 [INFO] train episode 44050: reward = -71.60, steps = 27 07:27:29 [INFO] train episode 44051: reward = -78.97, steps = 29 07:27:31 [INFO] train episode 44052: reward = -50.27, steps = 22 07:27:34 [INFO] train episode 44053: reward = -100.41, steps = 29 07:27:35 [INFO] train episode 44054: reward = -75.35, steps = 19 07:27:37 [INFO] train episode 44055: reward = -115.66, steps = 23 07:27:39 [INFO] train episode 44056: reward = -40.44, steps = 24 07:27:41 [INFO] train episode 44057: reward = -56.89, steps = 23 07:27:43 [INFO] train episode 44058: reward = -49.55, steps = 23 07:27:45 [INFO] train episode 44059: reward = -49.80, steps = 19 07:27:47 [INFO] train episode 44060: reward = -47.37, steps = 21 07:27:49 [INFO] train episode 44061: reward = -52.34, steps = 21 07:27:52 [INFO] train episode 44062: reward = -32.48, steps = 30 07:27:54 [INFO] train episode 44063: reward = -76.98, steps = 25 07:27:56 [INFO] train episode 44064: reward = -48.81, steps = 20 07:27:57 [INFO] train episode 44065: reward = -46.76, steps = 20 07:28:00 [INFO] train episode 44066: reward = -86.61, steps = 25 07:28:02 [INFO] train episode 44067: reward = -55.63, steps = 26 07:28:05 [INFO] train episode 44068: reward = -79.05, steps = 32 07:28:07 [INFO] train episode 44069: reward = -79.44, steps = 23 07:28:09 [INFO] train episode 44070: reward = -67.93, steps = 27 07:28:11 [INFO] train episode 44071: reward = -36.44, steps = 19 07:28:13 [INFO] train episode 44072: reward = -51.91, steps = 28 07:28:15 [INFO] train episode 44073: reward = -47.77, steps = 21 07:28:17 [INFO] train episode 44074: reward = -75.16, steps = 21 07:28:19 [INFO] train episode 44075: reward = -75.76, steps = 21 07:28:21 [INFO] train episode 44076: reward = -80.44, steps = 26 07:28:23 [INFO] train episode 44077: reward = -62.84, steps = 21 07:28:25 [INFO] train episode 44078: reward = -50.32, steps = 20 07:28:26 [INFO] train episode 44079: reward = -51.18, steps = 20 07:28:29 [INFO] train episode 44080: reward = -70.78, steps = 30 07:28:32 [INFO] train episode 44081: reward = -82.01, steps = 39 07:28:34 [INFO] train episode 44082: reward = -68.37, steps = 20 07:28:37 [INFO] train episode 44083: reward = -54.16, steps = 28 07:28:39 [INFO] train episode 44084: reward = -56.40, steps = 22 07:28:41 [INFO] train episode 44085: reward = -84.49, steps = 28 07:28:44 [INFO] train episode 44086: reward = -75.31, steps = 31 07:28:46 [INFO] train episode 44087: reward = -41.50, steps = 20 07:28:47 [INFO] train episode 44088: reward = -98.95, steps = 20 07:28:50 [INFO] train episode 44089: reward = -61.78, steps = 28 07:28:52 [INFO] train episode 44090: reward = -75.40, steps = 20 07:28:54 [INFO] train episode 44091: reward = -58.76, steps = 20 07:28:55 [INFO] train episode 44092: reward = -38.03, steps = 19 07:28:57 [INFO] train episode 44093: reward = -50.24, steps = 19 07:28:59 [INFO] train episode 44094: reward = -90.08, steps = 20 07:29:01 [INFO] train episode 44095: reward = -100.21, steps = 29 07:29:04 [INFO] train episode 44096: reward = -59.29, steps = 30 07:29:06 [INFO] train episode 44097: reward = -70.32, steps = 19 07:29:09 [INFO] train episode 44098: reward = -57.21, steps = 22 07:29:11 [INFO] train episode 44099: reward = -62.09, steps = 23 07:29:13 [INFO] train episode 44100: reward = -81.96, steps = 20 07:29:17 [INFO] train episode 44101: reward = -56.17, steps = 40 07:29:19 [INFO] train episode 44102: reward = -90.03, steps = 28 07:29:21 [INFO] train episode 44103: reward = -37.65, steps = 26 07:29:23 [INFO] train episode 44104: reward = -37.20, steps = 20 07:29:25 [INFO] train episode 44105: reward = -95.60, steps = 20 07:29:28 [INFO] train episode 44106: reward = -51.93, steps = 33 07:29:31 [INFO] train episode 44107: reward = -147.83, steps = 33 07:29:32 [INFO] train episode 44108: reward = -72.95, steps = 19 07:29:34 [INFO] train episode 44109: reward = -76.46, steps = 24 07:29:36 [INFO] train episode 44110: reward = -42.59, steps = 21 07:29:38 [INFO] train episode 44111: reward = -63.66, steps = 22 07:29:40 [INFO] train episode 44112: reward = -103.90, steps = 19 07:29:43 [INFO] train episode 44113: reward = -105.41, steps = 36 07:29:45 [INFO] train episode 44114: reward = -56.10, steps = 20 07:29:48 [INFO] train episode 44115: reward = -73.82, steps = 28 07:29:50 [INFO] train episode 44116: reward = -46.93, steps = 27 07:29:52 [INFO] train episode 44117: reward = -67.38, steps = 21 07:29:55 [INFO] train episode 44118: reward = -66.86, steps = 33 07:29:57 [INFO] train episode 44119: reward = -88.17, steps = 24 07:29:59 [INFO] train episode 44120: reward = -50.60, steps = 21 07:30:01 [INFO] train episode 44121: reward = -53.70, steps = 22 07:30:04 [INFO] train episode 44122: reward = -102.17, steps = 35 07:30:06 [INFO] train episode 44123: reward = -63.16, steps = 23 07:30:08 [INFO] train episode 44124: reward = -74.48, steps = 31 07:30:12 [INFO] train episode 44125: reward = -110.64, steps = 42 07:30:14 [INFO] train episode 44126: reward = -54.16, steps = 25 07:30:16 [INFO] train episode 44127: reward = -53.92, steps = 20 07:30:18 [INFO] train episode 44128: reward = -50.11, steps = 26 07:30:21 [INFO] train episode 44129: reward = -76.16, steps = 31 07:30:24 [INFO] train episode 44130: reward = -104.48, steps = 33 07:30:26 [INFO] train episode 44131: reward = -59.53, steps = 22 07:30:27 [INFO] train episode 44132: reward = -51.93, steps = 22 07:30:30 [INFO] train episode 44133: reward = -67.09, steps = 29 07:30:33 [INFO] train episode 44134: reward = -63.12, steps = 31 07:30:35 [INFO] train episode 44135: reward = -60.26, steps = 26 07:30:38 [INFO] train episode 44136: reward = -66.10, steps = 27 07:30:41 [INFO] train episode 44137: reward = -83.72, steps = 38 07:30:43 [INFO] train episode 44138: reward = -81.69, steps = 30 07:30:46 [INFO] train episode 44139: reward = -46.94, steps = 22 07:30:48 [INFO] train episode 44140: reward = -53.13, steps = 21 07:30:50 [INFO] train episode 44141: reward = -77.71, steps = 27 07:30:52 [INFO] train episode 44142: reward = -39.89, steps = 23 07:30:54 [INFO] train episode 44143: reward = -60.33, steps = 25 07:30:56 [INFO] train episode 44144: reward = -61.11, steps = 21 07:30:58 [INFO] train episode 44145: reward = -55.84, steps = 27 07:31:01 [INFO] train episode 44146: reward = -61.39, steps = 25 07:31:03 [INFO] train episode 44147: reward = -51.81, steps = 24 07:31:04 [INFO] train episode 44148: reward = -90.60, steps = 20 07:31:07 [INFO] train episode 44149: reward = -70.77, steps = 26 07:31:08 [INFO] train episode 44150: reward = -46.58, steps = 22 07:31:11 [INFO] train episode 44151: reward = -89.34, steps = 25 07:31:13 [INFO] train episode 44152: reward = -77.76, steps = 31 07:31:15 [INFO] train episode 44153: reward = -67.15, steps = 23 07:31:18 [INFO] train episode 44154: reward = -74.44, steps = 33 07:31:20 [INFO] train episode 44155: reward = -35.90, steps = 25 07:31:22 [INFO] train episode 44156: reward = -74.26, steps = 23 07:31:24 [INFO] train episode 44157: reward = -61.47, steps = 23 07:31:26 [INFO] train episode 44158: reward = -48.01, steps = 20 07:31:29 [INFO] train episode 44159: reward = -134.17, steps = 35 07:31:31 [INFO] train episode 44160: reward = -34.27, steps = 24 07:31:33 [INFO] train episode 44161: reward = -52.99, steps = 21 07:31:35 [INFO] train episode 44162: reward = -68.46, steps = 24 07:31:37 [INFO] train episode 44163: reward = -92.03, steps = 24 07:31:39 [INFO] train episode 44164: reward = -51.61, steps = 21 07:31:41 [INFO] train episode 44165: reward = -45.91, steps = 20 07:31:43 [INFO] train episode 44166: reward = -59.03, steps = 24 07:31:46 [INFO] train episode 44167: reward = -62.51, steps = 29 07:31:48 [INFO] train episode 44168: reward = -109.03, steps = 23 07:31:51 [INFO] train episode 44169: reward = -44.88, steps = 35 07:31:54 [INFO] train episode 44170: reward = -40.90, steps = 32 07:31:56 [INFO] train episode 44171: reward = -61.14, steps = 27 07:31:58 [INFO] train episode 44172: reward = -67.91, steps = 23 07:32:00 [INFO] train episode 44173: reward = -68.01, steps = 27 07:32:03 [INFO] train episode 44174: reward = -75.05, steps = 30 07:32:07 [INFO] train episode 44175: reward = -83.62, steps = 37 07:32:09 [INFO] train episode 44176: reward = -75.05, steps = 20 07:32:11 [INFO] train episode 44177: reward = -45.19, steps = 26 07:32:13 [INFO] train episode 44178: reward = -50.58, steps = 21 07:32:15 [INFO] train episode 44179: reward = -59.25, steps = 30 07:32:17 [INFO] train episode 44180: reward = -56.64, steps = 24 07:32:19 [INFO] train episode 44181: reward = -45.62, steps = 26 07:32:22 [INFO] train episode 44182: reward = -72.39, steps = 20 07:32:23 [INFO] train episode 44183: reward = -50.70, steps = 20 07:32:26 [INFO] train episode 44184: reward = -85.46, steps = 27 07:32:28 [INFO] train episode 44185: reward = -82.52, steps = 29 07:32:30 [INFO] train episode 44186: reward = -83.16, steps = 21 07:32:33 [INFO] train episode 44187: reward = -56.57, steps = 33 07:32:35 [INFO] train episode 44188: reward = -45.64, steps = 24 07:32:37 [INFO] train episode 44189: reward = -77.38, steps = 18 07:32:39 [INFO] train episode 44190: reward = -79.17, steps = 27 07:32:42 [INFO] train episode 44191: reward = -53.95, steps = 31 07:32:44 [INFO] train episode 44192: reward = -71.73, steps = 21 07:32:46 [INFO] train episode 44193: reward = -38.46, steps = 22 07:32:48 [INFO] train episode 44194: reward = -61.34, steps = 23 07:32:50 [INFO] train episode 44195: reward = -58.78, steps = 31 07:32:53 [INFO] train episode 44196: reward = -35.51, steps = 23 07:32:55 [INFO] train episode 44197: reward = -58.13, steps = 20 07:32:56 [INFO] train episode 44198: reward = -31.08, steps = 20 07:32:58 [INFO] train episode 44199: reward = -63.77, steps = 23 07:33:00 [INFO] train episode 44200: reward = -49.93, steps = 24 07:33:03 [INFO] train episode 44201: reward = -91.24, steps = 30 07:33:04 [INFO] train episode 44202: reward = -66.11, steps = 18 07:33:06 [INFO] train episode 44203: reward = -49.20, steps = 23 07:33:08 [INFO] train episode 44204: reward = -81.70, steps = 17 07:33:11 [INFO] train episode 44205: reward = -90.39, steps = 26 07:33:13 [INFO] train episode 44206: reward = -78.27, steps = 28 07:33:15 [INFO] train episode 44207: reward = -76.85, steps = 20 07:33:16 [INFO] train episode 44208: reward = -67.62, steps = 19 07:33:18 [INFO] train episode 44209: reward = -41.07, steps = 25 07:33:20 [INFO] train episode 44210: reward = -67.10, steps = 19 07:33:23 [INFO] train episode 44211: reward = -101.26, steps = 34 07:33:25 [INFO] train episode 44212: reward = -62.67, steps = 25 07:33:28 [INFO] train episode 44213: reward = -72.24, steps = 27 07:33:29 [INFO] train episode 44214: reward = -49.10, steps = 20 07:33:32 [INFO] train episode 44215: reward = -84.10, steps = 33 07:33:36 [INFO] train episode 44216: reward = -74.25, steps = 40 07:33:38 [INFO] train episode 44217: reward = -114.76, steps = 30 07:33:41 [INFO] train episode 44218: reward = -106.87, steps = 33 07:33:44 [INFO] train episode 44219: reward = -48.93, steps = 29 07:33:46 [INFO] train episode 44220: reward = -87.77, steps = 28 07:33:49 [INFO] train episode 44221: reward = -100.76, steps = 33 07:33:52 [INFO] train episode 44222: reward = -66.99, steps = 29 07:33:54 [INFO] train episode 44223: reward = -87.73, steps = 33 07:33:56 [INFO] train episode 44224: reward = -59.75, steps = 21 07:33:58 [INFO] train episode 44225: reward = -57.68, steps = 18 07:34:00 [INFO] train episode 44226: reward = -77.52, steps = 22 07:34:03 [INFO] train episode 44227: reward = -35.08, steps = 36 07:34:06 [INFO] train episode 44228: reward = -67.69, steps = 34 07:34:08 [INFO] train episode 44229: reward = -56.18, steps = 24 07:34:10 [INFO] train episode 44230: reward = -49.67, steps = 24 07:34:12 [INFO] train episode 44231: reward = -56.07, steps = 24 07:34:15 [INFO] train episode 44232: reward = -108.65, steps = 33 07:34:17 [INFO] train episode 44233: reward = -70.78, steps = 22 07:34:19 [INFO] train episode 44234: reward = -56.05, steps = 21 07:34:21 [INFO] train episode 44235: reward = -51.82, steps = 30 07:34:24 [INFO] train episode 44236: reward = -57.66, steps = 31 07:34:26 [INFO] train episode 44237: reward = -42.24, steps = 27 07:34:28 [INFO] train episode 44238: reward = -39.55, steps = 22 07:34:30 [INFO] train episode 44239: reward = -48.72, steps = 18 07:34:32 [INFO] train episode 44240: reward = -56.47, steps = 18 07:34:33 [INFO] train episode 44241: reward = -87.89, steps = 21 07:34:35 [INFO] train episode 44242: reward = -59.67, steps = 22 07:34:38 [INFO] train episode 44243: reward = -92.44, steps = 25 07:34:40 [INFO] train episode 44244: reward = -65.83, steps = 24 07:34:42 [INFO] train episode 44245: reward = -60.58, steps = 22 07:34:44 [INFO] train episode 44246: reward = -51.36, steps = 24 07:34:46 [INFO] train episode 44247: reward = -95.34, steps = 22 07:34:48 [INFO] train episode 44248: reward = -40.59, steps = 24 07:34:51 [INFO] train episode 44249: reward = -64.85, steps = 30 07:34:53 [INFO] train episode 44250: reward = -60.15, steps = 25 07:34:56 [INFO] train episode 44251: reward = -54.92, steps = 27 07:34:58 [INFO] train episode 44252: reward = -63.60, steps = 22 07:35:00 [INFO] train episode 44253: reward = -62.27, steps = 19 07:35:02 [INFO] train episode 44254: reward = -65.36, steps = 27 07:35:04 [INFO] train episode 44255: reward = -70.22, steps = 22 07:35:06 [INFO] train episode 44256: reward = -62.19, steps = 20 07:35:08 [INFO] train episode 44257: reward = -46.74, steps = 30 07:35:10 [INFO] train episode 44258: reward = -62.44, steps = 20 07:35:12 [INFO] train episode 44259: reward = -81.14, steps = 31 07:35:15 [INFO] train episode 44260: reward = -87.01, steps = 27 07:35:18 [INFO] train episode 44261: reward = -58.50, steps = 33 07:35:20 [INFO] train episode 44262: reward = -87.33, steps = 20 07:35:22 [INFO] train episode 44263: reward = -78.25, steps = 24 07:35:23 [INFO] train episode 44264: reward = -47.44, steps = 20 07:35:26 [INFO] train episode 44265: reward = -54.78, steps = 26 07:35:28 [INFO] train episode 44266: reward = -60.05, steps = 25 07:35:31 [INFO] train episode 44267: reward = -43.47, steps = 29 07:35:32 [INFO] train episode 44268: reward = -38.46, steps = 21 07:35:34 [INFO] train episode 44269: reward = -41.53, steps = 21 07:35:37 [INFO] train episode 44270: reward = -97.44, steps = 34 07:35:40 [INFO] train episode 44271: reward = -74.07, steps = 39 07:35:43 [INFO] train episode 44272: reward = -39.01, steps = 31 07:35:45 [INFO] train episode 44273: reward = -52.69, steps = 22 07:35:47 [INFO] train episode 44274: reward = -72.97, steps = 25 07:35:50 [INFO] train episode 44275: reward = -51.86, steps = 28 07:35:52 [INFO] train episode 44276: reward = -38.17, steps = 24 07:35:53 [INFO] train episode 44277: reward = -42.09, steps = 22 07:35:55 [INFO] train episode 44278: reward = -48.66, steps = 20 07:35:57 [INFO] train episode 44279: reward = -54.17, steps = 25 07:36:00 [INFO] train episode 44280: reward = -63.71, steps = 27 07:36:04 [INFO] train episode 44281: reward = -62.95, steps = 46 07:36:06 [INFO] train episode 44282: reward = -47.65, steps = 28 07:36:09 [INFO] train episode 44283: reward = -101.92, steps = 34 07:36:11 [INFO] train episode 44284: reward = -59.39, steps = 18 07:36:13 [INFO] train episode 44285: reward = -60.59, steps = 24 07:36:16 [INFO] train episode 44286: reward = -52.65, steps = 35 07:36:18 [INFO] train episode 44287: reward = -68.51, steps = 19 07:36:20 [INFO] train episode 44288: reward = -40.14, steps = 26 07:36:22 [INFO] train episode 44289: reward = -54.61, steps = 24 07:36:24 [INFO] train episode 44290: reward = -62.01, steps = 26 07:36:27 [INFO] train episode 44291: reward = -80.93, steps = 31 07:36:29 [INFO] train episode 44292: reward = -51.34, steps = 32 07:36:31 [INFO] train episode 44293: reward = -63.50, steps = 22 07:36:34 [INFO] train episode 44294: reward = -66.46, steps = 22 07:36:35 [INFO] train episode 44295: reward = -94.32, steps = 18 07:36:38 [INFO] train episode 44296: reward = -65.78, steps = 30 07:36:40 [INFO] train episode 44297: reward = -67.06, steps = 27 07:36:42 [INFO] train episode 44298: reward = -56.20, steps = 22 07:36:45 [INFO] train episode 44299: reward = -78.40, steps = 34 07:36:47 [INFO] train episode 44300: reward = -61.05, steps = 21 07:36:49 [INFO] train episode 44301: reward = -56.90, steps = 20 07:36:51 [INFO] train episode 44302: reward = -43.73, steps = 21 07:36:52 [INFO] train episode 44303: reward = -62.94, steps = 20 07:36:54 [INFO] train episode 44304: reward = -73.87, steps = 23 07:36:57 [INFO] train episode 44305: reward = -95.26, steps = 32 07:36:59 [INFO] train episode 44306: reward = -49.70, steps = 29 07:37:02 [INFO] train episode 44307: reward = -62.76, steps = 31 07:37:05 [INFO] train episode 44308: reward = -90.42, steps = 30 07:37:08 [INFO] train episode 44309: reward = -58.53, steps = 29 07:37:11 [INFO] train episode 44310: reward = -103.97, steps = 40 07:37:15 [INFO] train episode 44311: reward = -94.07, steps = 46 07:37:17 [INFO] train episode 44312: reward = -37.71, steps = 22 07:37:19 [INFO] train episode 44313: reward = -36.44, steps = 23 07:37:21 [INFO] train episode 44314: reward = -49.54, steps = 24 07:37:25 [INFO] train episode 44315: reward = -94.34, steps = 49 07:37:27 [INFO] train episode 44316: reward = -55.73, steps = 22 07:37:29 [INFO] train episode 44317: reward = -49.40, steps = 22 07:37:32 [INFO] train episode 44318: reward = -54.50, steps = 34 07:37:34 [INFO] train episode 44319: reward = -83.66, steps = 26 07:37:37 [INFO] train episode 44320: reward = -70.25, steps = 25 07:37:40 [INFO] train episode 44321: reward = -107.75, steps = 42 07:37:44 [INFO] train episode 44322: reward = -109.90, steps = 40 07:37:47 [INFO] train episode 44323: reward = -94.23, steps = 30 07:37:50 [INFO] train episode 44324: reward = -91.53, steps = 36 07:37:52 [INFO] train episode 44325: reward = -45.32, steps = 21 07:37:54 [INFO] train episode 44326: reward = -70.45, steps = 21 07:37:55 [INFO] train episode 44327: reward = -75.33, steps = 19 07:37:57 [INFO] train episode 44328: reward = -54.79, steps = 22 07:38:00 [INFO] train episode 44329: reward = -62.15, steps = 30 07:38:02 [INFO] train episode 44330: reward = -67.85, steps = 29 07:38:05 [INFO] train episode 44331: reward = -97.05, steps = 32 07:38:07 [INFO] train episode 44332: reward = -43.77, steps = 23 07:38:09 [INFO] train episode 44333: reward = -55.94, steps = 20 07:38:11 [INFO] train episode 44334: reward = -63.88, steps = 23 07:38:14 [INFO] train episode 44335: reward = -73.69, steps = 32 07:38:16 [INFO] train episode 44336: reward = -69.01, steps = 26 07:38:18 [INFO] train episode 44337: reward = -63.60, steps = 23 07:38:21 [INFO] train episode 44338: reward = -133.86, steps = 33 07:38:23 [INFO] train episode 44339: reward = -58.03, steps = 26 07:38:26 [INFO] train episode 44340: reward = -73.38, steps = 29 07:38:28 [INFO] train episode 44341: reward = -68.78, steps = 24 07:38:30 [INFO] train episode 44342: reward = -43.54, steps = 20 07:38:31 [INFO] train episode 44343: reward = -80.41, steps = 21 07:38:33 [INFO] train episode 44344: reward = -79.16, steps = 19 07:38:35 [INFO] train episode 44345: reward = -38.34, steps = 21 07:38:37 [INFO] train episode 44346: reward = -40.15, steps = 22 07:38:40 [INFO] train episode 44347: reward = -78.86, steps = 29 07:38:42 [INFO] train episode 44348: reward = -59.79, steps = 20 07:38:44 [INFO] train episode 44349: reward = -81.74, steps = 32 07:38:48 [INFO] train episode 44350: reward = -64.86, steps = 37 07:38:50 [INFO] train episode 44351: reward = -78.52, steps = 29 07:38:53 [INFO] train episode 44352: reward = -87.37, steps = 40 07:38:55 [INFO] train episode 44353: reward = -39.74, steps = 19 07:38:58 [INFO] train episode 44354: reward = -75.21, steps = 29 07:39:00 [INFO] train episode 44355: reward = -77.01, steps = 27 07:39:02 [INFO] train episode 44356: reward = -81.32, steps = 25 07:39:06 [INFO] train episode 44357: reward = -77.88, steps = 41 07:39:09 [INFO] train episode 44358: reward = -95.51, steps = 35 07:39:11 [INFO] train episode 44359: reward = -45.98, steps = 21 07:39:14 [INFO] train episode 44360: reward = -116.61, steps = 35 07:39:15 [INFO] train episode 44361: reward = -50.82, steps = 18 07:39:18 [INFO] train episode 44362: reward = -59.70, steps = 28 07:39:20 [INFO] train episode 44363: reward = -63.53, steps = 21 07:39:23 [INFO] train episode 44364: reward = -105.35, steps = 41 07:39:25 [INFO] train episode 44365: reward = -55.51, steps = 21 07:39:28 [INFO] train episode 44366: reward = -113.56, steps = 26 07:39:31 [INFO] train episode 44367: reward = -100.09, steps = 37 07:39:33 [INFO] train episode 44368: reward = -68.68, steps = 28 07:39:35 [INFO] train episode 44369: reward = -58.05, steps = 25 07:39:37 [INFO] train episode 44370: reward = -56.35, steps = 20 07:39:39 [INFO] train episode 44371: reward = -88.19, steps = 19 07:39:41 [INFO] train episode 44372: reward = -47.94, steps = 25 07:39:43 [INFO] train episode 44373: reward = -82.78, steps = 20 07:39:45 [INFO] train episode 44374: reward = -99.82, steps = 30 07:39:48 [INFO] train episode 44375: reward = -81.46, steps = 31 07:39:50 [INFO] train episode 44376: reward = -72.24, steps = 30 07:39:53 [INFO] train episode 44377: reward = -47.51, steps = 25 07:39:54 [INFO] train episode 44378: reward = -54.88, steps = 22 07:39:57 [INFO] train episode 44379: reward = -109.05, steps = 31 07:40:00 [INFO] train episode 44380: reward = -28.01, steps = 24 07:40:02 [INFO] train episode 44381: reward = -69.23, steps = 24 07:40:04 [INFO] train episode 44382: reward = -55.05, steps = 26 07:40:06 [INFO] train episode 44383: reward = -44.61, steps = 23 07:40:09 [INFO] train episode 44384: reward = -90.95, steps = 34 07:40:11 [INFO] train episode 44385: reward = -43.52, steps = 22 07:40:13 [INFO] train episode 44386: reward = -45.16, steps = 21 07:40:15 [INFO] train episode 44387: reward = -97.26, steps = 25 07:40:18 [INFO] train episode 44388: reward = -51.89, steps = 36 07:40:20 [INFO] train episode 44389: reward = -48.76, steps = 22 07:40:22 [INFO] train episode 44390: reward = -38.54, steps = 21 07:40:24 [INFO] train episode 44391: reward = -72.71, steps = 31 07:40:26 [INFO] train episode 44392: reward = -67.35, steps = 20 07:40:28 [INFO] train episode 44393: reward = -54.92, steps = 19 07:40:30 [INFO] train episode 44394: reward = -53.32, steps = 26 07:40:32 [INFO] train episode 44395: reward = -45.82, steps = 22 07:40:35 [INFO] train episode 44396: reward = -69.29, steps = 21 07:40:37 [INFO] train episode 44397: reward = -85.61, steps = 28 07:40:40 [INFO] train episode 44398: reward = -55.53, steps = 29 07:40:42 [INFO] train episode 44399: reward = -33.90, steps = 20 07:40:43 [INFO] train episode 44400: reward = -39.31, steps = 21 07:40:45 [INFO] train episode 44401: reward = -56.77, steps = 17 07:40:48 [INFO] train episode 44402: reward = -98.00, steps = 32 07:40:50 [INFO] train episode 44403: reward = -71.66, steps = 28 07:40:52 [INFO] train episode 44404: reward = -77.83, steps = 23 07:40:55 [INFO] train episode 44405: reward = -77.74, steps = 27 07:40:59 [INFO] train episode 44406: reward = -90.43, steps = 48 07:41:01 [INFO] train episode 44407: reward = -88.00, steps = 22 07:41:03 [INFO] train episode 44408: reward = -66.23, steps = 20 07:41:05 [INFO] train episode 44409: reward = -77.66, steps = 28 07:41:07 [INFO] train episode 44410: reward = -68.16, steps = 20 07:41:09 [INFO] train episode 44411: reward = -39.52, steps = 21 07:41:11 [INFO] train episode 44412: reward = -99.14, steps = 20 07:41:12 [INFO] train episode 44413: reward = -66.43, steps = 20 07:41:14 [INFO] train episode 44414: reward = -73.89, steps = 24 07:41:17 [INFO] train episode 44415: reward = -80.25, steps = 31 07:41:19 [INFO] train episode 44416: reward = -50.78, steps = 21 07:41:22 [INFO] train episode 44417: reward = -88.08, steps = 33 07:41:24 [INFO] train episode 44418: reward = -62.40, steps = 21 07:41:26 [INFO] train episode 44419: reward = -48.52, steps = 29 07:41:29 [INFO] train episode 44420: reward = -71.84, steps = 32 07:41:32 [INFO] train episode 44421: reward = -81.24, steps = 33 07:41:35 [INFO] train episode 44422: reward = -86.85, steps = 35 07:41:37 [INFO] train episode 44423: reward = -35.76, steps = 21 07:41:40 [INFO] train episode 44424: reward = -93.13, steps = 33 07:41:41 [INFO] train episode 44425: reward = -53.47, steps = 22 07:41:43 [INFO] train episode 44426: reward = -38.79, steps = 20 07:41:45 [INFO] train episode 44427: reward = -55.09, steps = 21 07:41:48 [INFO] train episode 44428: reward = -49.27, steps = 36 07:41:50 [INFO] train episode 44429: reward = -53.81, steps = 20 07:41:52 [INFO] train episode 44430: reward = -77.47, steps = 20 07:41:55 [INFO] train episode 44431: reward = -93.09, steps = 38 07:41:57 [INFO] train episode 44432: reward = -46.56, steps = 23 07:41:59 [INFO] train episode 44433: reward = -43.52, steps = 25 07:42:01 [INFO] train episode 44434: reward = -48.74, steps = 22 07:42:04 [INFO] train episode 44435: reward = -98.20, steps = 28 07:42:06 [INFO] train episode 44436: reward = -48.25, steps = 20 07:42:08 [INFO] train episode 44437: reward = -46.30, steps = 26 07:42:10 [INFO] train episode 44438: reward = -49.65, steps = 23 07:42:12 [INFO] train episode 44439: reward = -84.68, steps = 27 07:42:17 [INFO] train episode 44440: reward = -179.99, steps = 59 07:42:19 [INFO] train episode 44441: reward = -50.30, steps = 19 07:42:21 [INFO] train episode 44442: reward = -60.39, steps = 23 07:42:23 [INFO] train episode 44443: reward = -67.40, steps = 27 07:42:25 [INFO] train episode 44444: reward = -58.69, steps = 25 07:42:27 [INFO] train episode 44445: reward = -38.19, steps = 20 07:42:29 [INFO] train episode 44446: reward = -48.38, steps = 18 07:42:30 [INFO] train episode 44447: reward = -52.71, steps = 20 07:42:32 [INFO] train episode 44448: reward = -57.30, steps = 21 07:42:36 [INFO] train episode 44449: reward = -85.44, steps = 45 07:42:39 [INFO] train episode 44450: reward = -35.93, steps = 28 07:42:41 [INFO] train episode 44451: reward = -50.98, steps = 21 07:42:43 [INFO] train episode 44452: reward = -75.05, steps = 29 07:42:45 [INFO] train episode 44453: reward = -65.31, steps = 22 07:42:47 [INFO] train episode 44454: reward = -54.00, steps = 22 07:42:49 [INFO] train episode 44455: reward = -80.95, steps = 22 07:42:52 [INFO] train episode 44456: reward = -96.90, steps = 35 07:42:54 [INFO] train episode 44457: reward = -46.49, steps = 24 07:42:56 [INFO] train episode 44458: reward = -74.82, steps = 24 07:42:58 [INFO] train episode 44459: reward = -99.80, steps = 23 07:43:01 [INFO] train episode 44460: reward = -59.75, steps = 25 07:43:03 [INFO] train episode 44461: reward = -66.51, steps = 25 07:43:06 [INFO] train episode 44462: reward = -95.58, steps = 29 07:43:09 [INFO] train episode 44463: reward = -63.36, steps = 37 07:43:11 [INFO] train episode 44464: reward = -88.15, steps = 19 07:43:13 [INFO] train episode 44465: reward = -54.21, steps = 26 07:43:16 [INFO] train episode 44466: reward = -55.76, steps = 33 07:43:18 [INFO] train episode 44467: reward = -48.08, steps = 27 07:43:20 [INFO] train episode 44468: reward = -93.72, steps = 28 07:43:23 [INFO] train episode 44469: reward = -66.50, steps = 27 07:43:26 [INFO] train episode 44470: reward = -78.91, steps = 29 07:43:29 [INFO] train episode 44471: reward = -77.28, steps = 27 07:43:31 [INFO] train episode 44472: reward = -41.64, steps = 21 07:43:32 [INFO] train episode 44473: reward = -56.68, steps = 21 07:43:34 [INFO] train episode 44474: reward = -57.47, steps = 20 07:43:36 [INFO] train episode 44475: reward = -46.19, steps = 20 07:43:38 [INFO] train episode 44476: reward = -53.55, steps = 20 07:43:40 [INFO] train episode 44477: reward = -49.98, steps = 24 07:43:41 [INFO] train episode 44478: reward = -48.37, steps = 21 07:43:43 [INFO] train episode 44479: reward = -67.31, steps = 14 07:43:45 [INFO] train episode 44480: reward = -31.42, steps = 30 07:43:48 [INFO] train episode 44481: reward = -50.78, steps = 31 07:43:51 [INFO] train episode 44482: reward = -70.63, steps = 37 07:43:54 [INFO] train episode 44483: reward = -71.50, steps = 36 07:43:56 [INFO] train episode 44484: reward = -49.59, steps = 23 07:44:00 [INFO] train episode 44485: reward = -56.61, steps = 36 07:44:02 [INFO] train episode 44486: reward = -69.34, steps = 28 07:44:04 [INFO] train episode 44487: reward = -61.18, steps = 22 07:44:07 [INFO] train episode 44488: reward = -42.12, steps = 35 07:44:10 [INFO] train episode 44489: reward = -59.47, steps = 35 07:44:12 [INFO] train episode 44490: reward = -49.32, steps = 20 07:44:15 [INFO] train episode 44491: reward = -76.42, steps = 35 07:44:17 [INFO] train episode 44492: reward = -59.21, steps = 22 07:44:20 [INFO] train episode 44493: reward = -36.01, steps = 35 07:44:21 [INFO] train episode 44494: reward = -61.18, steps = 19 07:44:23 [INFO] train episode 44495: reward = -68.99, steps = 23 07:44:27 [INFO] train episode 44496: reward = -57.54, steps = 41 07:44:29 [INFO] train episode 44497: reward = -56.14, steps = 22 07:44:31 [INFO] train episode 44498: reward = -39.15, steps = 21 07:44:33 [INFO] train episode 44499: reward = -91.03, steps = 31 07:44:35 [INFO] train episode 44500: reward = -62.73, steps = 24 07:44:38 [INFO] train episode 44501: reward = -62.40, steps = 23 07:44:40 [INFO] train episode 44502: reward = -41.38, steps = 25 07:44:41 [INFO] train episode 44503: reward = -52.85, steps = 21 07:44:44 [INFO] train episode 44504: reward = -79.20, steps = 25 07:44:48 [INFO] train episode 44505: reward = -100.94, steps = 46 07:44:50 [INFO] train episode 44506: reward = -52.06, steps = 24 07:44:52 [INFO] train episode 44507: reward = -64.06, steps = 26 07:44:54 [INFO] train episode 44508: reward = -69.69, steps = 28 07:44:58 [INFO] train episode 44509: reward = -58.89, steps = 36 07:45:00 [INFO] train episode 44510: reward = -66.33, steps = 28 07:45:02 [INFO] train episode 44511: reward = -69.70, steps = 19 07:45:04 [INFO] train episode 44512: reward = -69.65, steps = 23 07:45:06 [INFO] train episode 44513: reward = -67.75, steps = 27 07:45:08 [INFO] train episode 44514: reward = -58.48, steps = 23 07:45:10 [INFO] train episode 44515: reward = -71.78, steps = 26 07:45:13 [INFO] train episode 44516: reward = -44.97, steps = 28 07:45:15 [INFO] train episode 44517: reward = -66.38, steps = 30 07:45:18 [INFO] train episode 44518: reward = -66.27, steps = 24 07:45:21 [INFO] train episode 44519: reward = -42.66, steps = 32 07:45:24 [INFO] train episode 44520: reward = -46.32, steps = 26 07:45:26 [INFO] train episode 44521: reward = -26.35, steps = 20 07:45:28 [INFO] train episode 44522: reward = -68.83, steps = 30 07:45:30 [INFO] train episode 44523: reward = -49.14, steps = 22 07:45:32 [INFO] train episode 44524: reward = -39.43, steps = 19 07:45:34 [INFO] train episode 44525: reward = -84.21, steps = 21 07:45:35 [INFO] train episode 44526: reward = -47.60, steps = 20 07:45:38 [INFO] train episode 44527: reward = -51.79, steps = 33 07:45:40 [INFO] train episode 44528: reward = -33.62, steps = 27 07:45:43 [INFO] train episode 44529: reward = -65.09, steps = 35 07:45:47 [INFO] train episode 44530: reward = -111.49, steps = 41 07:45:49 [INFO] train episode 44531: reward = -46.03, steps = 24 07:45:53 [INFO] train episode 44532: reward = -83.32, steps = 42 07:45:55 [INFO] train episode 44533: reward = -43.20, steps = 25 07:45:57 [INFO] train episode 44534: reward = -35.67, steps = 27 07:46:00 [INFO] train episode 44535: reward = -108.57, steps = 38 07:46:02 [INFO] train episode 44536: reward = -85.54, steps = 21 07:46:07 [INFO] train episode 44537: reward = -130.97, steps = 47 07:46:08 [INFO] train episode 44538: reward = -29.11, steps = 22 07:46:11 [INFO] train episode 44539: reward = -58.89, steps = 30 07:46:13 [INFO] train episode 44540: reward = -50.69, steps = 26 07:46:17 [INFO] train episode 44541: reward = -69.13, steps = 37 07:46:20 [INFO] train episode 44542: reward = -87.05, steps = 32 07:46:24 [INFO] train episode 44543: reward = -93.17, steps = 47 07:46:26 [INFO] train episode 44544: reward = -58.91, steps = 22 07:46:29 [INFO] train episode 44545: reward = -77.73, steps = 39 07:46:31 [INFO] train episode 44546: reward = -49.38, steps = 23 07:46:33 [INFO] train episode 44547: reward = -72.22, steps = 23 07:46:35 [INFO] train episode 44548: reward = -54.40, steps = 25 07:46:38 [INFO] train episode 44549: reward = -45.86, steps = 21 07:46:40 [INFO] train episode 44550: reward = -68.89, steps = 27 07:46:43 [INFO] train episode 44551: reward = -93.15, steps = 37 07:46:45 [INFO] train episode 44552: reward = -45.63, steps = 21 07:46:47 [INFO] train episode 44553: reward = -75.70, steps = 18 07:46:48 [INFO] train episode 44554: reward = -58.66, steps = 19 07:46:50 [INFO] train episode 44555: reward = -56.73, steps = 23 07:46:53 [INFO] train episode 44556: reward = -37.43, steps = 25 07:46:56 [INFO] train episode 44557: reward = -82.99, steps = 43 07:46:58 [INFO] train episode 44558: reward = -94.05, steps = 20 07:47:01 [INFO] train episode 44559: reward = -88.26, steps = 35 07:47:04 [INFO] train episode 44560: reward = -41.54, steps = 29 07:47:05 [INFO] train episode 44561: reward = -50.63, steps = 20 07:47:07 [INFO] train episode 44562: reward = -45.76, steps = 21 07:47:10 [INFO] train episode 44563: reward = -79.44, steps = 32 07:47:13 [INFO] train episode 44564: reward = -50.02, steps = 31 07:47:15 [INFO] train episode 44565: reward = -48.02, steps = 20 07:47:17 [INFO] train episode 44566: reward = -91.97, steps = 22 07:47:19 [INFO] train episode 44567: reward = -51.85, steps = 25 07:47:21 [INFO] train episode 44568: reward = -53.15, steps = 29 07:47:23 [INFO] train episode 44569: reward = -43.45, steps = 20 07:47:27 [INFO] train episode 44570: reward = -82.87, steps = 37 07:47:29 [INFO] train episode 44571: reward = -67.04, steps = 26 07:47:30 [INFO] train episode 44572: reward = -48.23, steps = 20 07:47:34 [INFO] train episode 44573: reward = -61.49, steps = 44 07:47:38 [INFO] train episode 44574: reward = -114.02, steps = 40 07:47:41 [INFO] train episode 44575: reward = -65.99, steps = 39 07:47:44 [INFO] train episode 44576: reward = -40.94, steps = 27 07:47:45 [INFO] train episode 44577: reward = -44.86, steps = 18 07:47:47 [INFO] train episode 44578: reward = -53.09, steps = 21 07:47:49 [INFO] train episode 44579: reward = -68.99, steps = 22 07:47:53 [INFO] train episode 44580: reward = -89.19, steps = 45 07:47:55 [INFO] train episode 44581: reward = -64.64, steps = 29 07:47:57 [INFO] train episode 44582: reward = -58.01, steps = 20 07:48:00 [INFO] train episode 44583: reward = -45.01, steps = 39 07:48:03 [INFO] train episode 44584: reward = -72.46, steps = 26 07:48:05 [INFO] train episode 44585: reward = -47.66, steps = 32 07:48:07 [INFO] train episode 44586: reward = -54.11, steps = 24 07:48:10 [INFO] train episode 44587: reward = -44.57, steps = 35 07:48:13 [INFO] train episode 44588: reward = -51.53, steps = 24 07:48:15 [INFO] train episode 44589: reward = -47.01, steps = 29 07:48:17 [INFO] train episode 44590: reward = -51.25, steps = 22 07:48:19 [INFO] train episode 44591: reward = -51.50, steps = 28 07:48:21 [INFO] train episode 44592: reward = -41.75, steps = 24 07:48:23 [INFO] train episode 44593: reward = -51.74, steps = 19 07:48:26 [INFO] train episode 44594: reward = -46.66, steps = 37 07:48:28 [INFO] train episode 44595: reward = -41.98, steps = 22 07:48:30 [INFO] train episode 44596: reward = -49.60, steps = 20 07:48:32 [INFO] train episode 44597: reward = -87.34, steps = 26 07:48:34 [INFO] train episode 44598: reward = -58.32, steps = 19 07:48:36 [INFO] train episode 44599: reward = -80.56, steps = 25 07:48:38 [INFO] train episode 44600: reward = -64.03, steps = 22 07:48:41 [INFO] train episode 44601: reward = -56.62, steps = 33 07:48:43 [INFO] train episode 44602: reward = -67.63, steps = 19 07:48:45 [INFO] train episode 44603: reward = -42.38, steps = 20 07:48:47 [INFO] train episode 44604: reward = -103.65, steps = 33 07:48:50 [INFO] train episode 44605: reward = -67.70, steps = 29 07:48:52 [INFO] train episode 44606: reward = -42.96, steps = 20 07:48:55 [INFO] train episode 44607: reward = -51.79, steps = 35 07:48:57 [INFO] train episode 44608: reward = -29.71, steps = 31 07:49:00 [INFO] train episode 44609: reward = -57.52, steps = 25 07:49:02 [INFO] train episode 44610: reward = -46.97, steps = 23 07:49:05 [INFO] train episode 44611: reward = -57.81, steps = 42 07:49:09 [INFO] train episode 44612: reward = -36.26, steps = 38 07:49:11 [INFO] train episode 44613: reward = -60.25, steps = 20 07:49:13 [INFO] train episode 44614: reward = -53.25, steps = 21 07:49:14 [INFO] train episode 44615: reward = -53.68, steps = 21 07:49:18 [INFO] train episode 44616: reward = -94.98, steps = 33 07:49:20 [INFO] train episode 44617: reward = -48.85, steps = 30 07:49:23 [INFO] train episode 44618: reward = -46.20, steps = 31 07:49:26 [INFO] train episode 44619: reward = -54.34, steps = 36 07:49:28 [INFO] train episode 44620: reward = -46.41, steps = 23 07:49:30 [INFO] train episode 44621: reward = -33.72, steps = 27 07:49:33 [INFO] train episode 44622: reward = -51.28, steps = 33 07:49:35 [INFO] train episode 44623: reward = -49.06, steps = 28 07:49:37 [INFO] train episode 44624: reward = -51.35, steps = 20 07:49:39 [INFO] train episode 44625: reward = -56.82, steps = 23 07:49:41 [INFO] train episode 44626: reward = -56.07, steps = 17 07:49:43 [INFO] train episode 44627: reward = -79.61, steps = 32 07:49:46 [INFO] train episode 44628: reward = -62.98, steps = 29 07:49:49 [INFO] train episode 44629: reward = -99.64, steps = 35 07:49:52 [INFO] train episode 44630: reward = -96.53, steps = 40 07:49:56 [INFO] train episode 44631: reward = -87.09, steps = 37 07:49:57 [INFO] train episode 44632: reward = -69.11, steps = 21 07:49:59 [INFO] train episode 44633: reward = -52.31, steps = 21 07:50:02 [INFO] train episode 44634: reward = -57.45, steps = 29 07:50:04 [INFO] train episode 44635: reward = -62.45, steps = 22 07:50:06 [INFO] train episode 44636: reward = -59.57, steps = 27 07:50:09 [INFO] train episode 44637: reward = -71.95, steps = 29 07:50:12 [INFO] train episode 44638: reward = -40.16, steps = 34 07:50:14 [INFO] train episode 44639: reward = -62.69, steps = 33 07:50:16 [INFO] train episode 44640: reward = -68.48, steps = 19 07:50:18 [INFO] train episode 44641: reward = -55.25, steps = 22 07:50:21 [INFO] train episode 44642: reward = -82.46, steps = 28 07:50:23 [INFO] train episode 44643: reward = -73.33, steps = 29 07:50:25 [INFO] train episode 44644: reward = -33.94, steps = 22 07:50:27 [INFO] train episode 44645: reward = -51.29, steps = 26 07:50:29 [INFO] train episode 44646: reward = -54.09, steps = 20 07:50:31 [INFO] train episode 44647: reward = -56.75, steps = 29 07:50:33 [INFO] train episode 44648: reward = -43.55, steps = 20 07:50:35 [INFO] train episode 44649: reward = -38.19, steps = 21 07:50:37 [INFO] train episode 44650: reward = -37.62, steps = 20 07:50:39 [INFO] train episode 44651: reward = -47.13, steps = 22 07:50:41 [INFO] train episode 44652: reward = -52.89, steps = 19 07:50:42 [INFO] train episode 44653: reward = -62.12, steps = 20 07:50:45 [INFO] train episode 44654: reward = -109.20, steps = 34 07:50:48 [INFO] train episode 44655: reward = -61.58, steps = 27 07:50:50 [INFO] train episode 44656: reward = -65.71, steps = 23 07:50:52 [INFO] train episode 44657: reward = -85.75, steps = 24 07:50:54 [INFO] train episode 44658: reward = -56.66, steps = 25 07:50:56 [INFO] train episode 44659: reward = -77.02, steps = 27 07:50:58 [INFO] train episode 44660: reward = -42.92, steps = 24 07:51:00 [INFO] train episode 44661: reward = -50.98, steps = 20 07:51:02 [INFO] train episode 44662: reward = -65.07, steps = 19 07:51:04 [INFO] train episode 44663: reward = -75.65, steps = 30 07:51:07 [INFO] train episode 44664: reward = -59.92, steps = 25 07:51:10 [INFO] train episode 44665: reward = -32.53, steps = 32 07:51:12 [INFO] train episode 44666: reward = -65.36, steps = 33 07:51:14 [INFO] train episode 44667: reward = -76.97, steps = 21 07:51:16 [INFO] train episode 44668: reward = -52.87, steps = 25 07:51:18 [INFO] train episode 44669: reward = -67.55, steps = 16 07:51:20 [INFO] train episode 44670: reward = -82.98, steps = 20 07:51:21 [INFO] train episode 44671: reward = -43.47, steps = 20 07:51:24 [INFO] train episode 44672: reward = -42.48, steps = 27 07:51:26 [INFO] train episode 44673: reward = -44.05, steps = 25 07:51:29 [INFO] train episode 44674: reward = -57.40, steps = 31 07:51:30 [INFO] train episode 44675: reward = -55.96, steps = 22 07:51:32 [INFO] train episode 44676: reward = -61.63, steps = 20 07:51:34 [INFO] train episode 44677: reward = -54.13, steps = 22 07:51:37 [INFO] train episode 44678: reward = -50.55, steps = 31 07:51:39 [INFO] train episode 44679: reward = -65.87, steps = 24 07:51:41 [INFO] train episode 44680: reward = -82.26, steps = 26 07:51:44 [INFO] train episode 44681: reward = -51.81, steps = 32 07:51:46 [INFO] train episode 44682: reward = -73.62, steps = 22 07:51:47 [INFO] train episode 44683: reward = -73.62, steps = 18 07:51:51 [INFO] train episode 44684: reward = -57.37, steps = 38 07:51:52 [INFO] train episode 44685: reward = -58.02, steps = 21 07:51:54 [INFO] train episode 44686: reward = -55.97, steps = 19 07:51:56 [INFO] train episode 44687: reward = -82.01, steps = 21 07:51:59 [INFO] train episode 44688: reward = -68.19, steps = 23 07:52:01 [INFO] train episode 44689: reward = -28.72, steps = 22 07:52:03 [INFO] train episode 44690: reward = -61.77, steps = 22 07:52:05 [INFO] train episode 44691: reward = -59.84, steps = 23 07:52:07 [INFO] train episode 44692: reward = -67.55, steps = 27 07:52:09 [INFO] train episode 44693: reward = -44.89, steps = 23 07:52:11 [INFO] train episode 44694: reward = -46.87, steps = 26 07:52:14 [INFO] train episode 44695: reward = -53.79, steps = 28 07:52:16 [INFO] train episode 44696: reward = -44.74, steps = 20 07:52:19 [INFO] train episode 44697: reward = -45.24, steps = 40 07:52:21 [INFO] train episode 44698: reward = -53.32, steps = 20 07:52:23 [INFO] train episode 44699: reward = -54.91, steps = 22 07:52:25 [INFO] train episode 44700: reward = -63.13, steps = 24 07:52:29 [INFO] train episode 44701: reward = -108.48, steps = 44 07:52:31 [INFO] train episode 44702: reward = -54.68, steps = 26 07:52:32 [INFO] train episode 44703: reward = -83.33, steps = 19 07:52:35 [INFO] train episode 44704: reward = -42.94, steps = 26 07:52:37 [INFO] train episode 44705: reward = -69.87, steps = 29 07:52:39 [INFO] train episode 44706: reward = -57.06, steps = 19 07:52:41 [INFO] train episode 44707: reward = -31.85, steps = 27 07:52:43 [INFO] train episode 44708: reward = -47.75, steps = 21 07:52:46 [INFO] train episode 44709: reward = -56.26, steps = 33 07:52:48 [INFO] train episode 44710: reward = -59.54, steps = 21 07:52:52 [INFO] train episode 44711: reward = -49.72, steps = 46 07:52:54 [INFO] train episode 44712: reward = -71.30, steps = 27 07:52:56 [INFO] train episode 44713: reward = -60.86, steps = 20 07:52:59 [INFO] train episode 44714: reward = -111.10, steps = 33 07:53:01 [INFO] train episode 44715: reward = -53.75, steps = 22 07:53:04 [INFO] train episode 44716: reward = -42.20, steps = 30 07:53:05 [INFO] train episode 44717: reward = -35.18, steps = 20 07:53:07 [INFO] train episode 44718: reward = -45.64, steps = 24 07:53:09 [INFO] train episode 44719: reward = -52.02, steps = 22 07:53:12 [INFO] train episode 44720: reward = -97.19, steps = 36 07:53:14 [INFO] train episode 44721: reward = -61.72, steps = 21 07:53:16 [INFO] train episode 44722: reward = -43.76, steps = 26 07:53:20 [INFO] train episode 44723: reward = -58.20, steps = 45 07:53:22 [INFO] train episode 44724: reward = -52.88, steps = 26 07:53:24 [INFO] train episode 44725: reward = -70.48, steps = 21 07:53:27 [INFO] train episode 44726: reward = -43.79, steps = 31 07:53:30 [INFO] train episode 44727: reward = -44.59, steps = 31 07:53:32 [INFO] train episode 44728: reward = -50.09, steps = 24 07:53:34 [INFO] train episode 44729: reward = -38.38, steps = 22 07:53:35 [INFO] train episode 44730: reward = -48.81, steps = 20 07:53:37 [INFO] train episode 44731: reward = -83.19, steps = 22 07:53:39 [INFO] train episode 44732: reward = -64.17, steps = 20 07:53:42 [INFO] train episode 44733: reward = -70.04, steps = 36 07:53:44 [INFO] train episode 44734: reward = -44.89, steps = 21 07:53:47 [INFO] train episode 44735: reward = -46.95, steps = 25 07:53:48 [INFO] train episode 44736: reward = -68.56, steps = 16 07:53:51 [INFO] train episode 44737: reward = -57.21, steps = 38 07:53:53 [INFO] train episode 44738: reward = -52.75, steps = 23 07:53:55 [INFO] train episode 44739: reward = -44.32, steps = 21 07:53:57 [INFO] train episode 44740: reward = -64.81, steps = 29 07:54:00 [INFO] train episode 44741: reward = -97.74, steps = 31 07:54:02 [INFO] train episode 44742: reward = -42.34, steps = 22 07:54:04 [INFO] train episode 44743: reward = -44.73, steps = 19 07:54:06 [INFO] train episode 44744: reward = -51.55, steps = 21 07:54:08 [INFO] train episode 44745: reward = -77.50, steps = 29 07:54:11 [INFO] train episode 44746: reward = -52.27, steps = 36 07:54:14 [INFO] train episode 44747: reward = -74.20, steps = 34 07:54:17 [INFO] train episode 44748: reward = -68.65, steps = 26 07:54:19 [INFO] train episode 44749: reward = -56.30, steps = 23 07:54:20 [INFO] train episode 44750: reward = -57.81, steps = 21 07:54:22 [INFO] train episode 44751: reward = -37.16, steps = 22 07:54:25 [INFO] train episode 44752: reward = -70.33, steps = 28 07:54:27 [INFO] train episode 44753: reward = -89.44, steps = 31 07:54:29 [INFO] train episode 44754: reward = -63.46, steps = 21 07:54:31 [INFO] train episode 44755: reward = -46.37, steps = 21 07:54:34 [INFO] train episode 44756: reward = -52.70, steps = 29 07:54:36 [INFO] train episode 44757: reward = -56.22, steps = 23 07:54:38 [INFO] train episode 44758: reward = -65.33, steps = 20 07:54:40 [INFO] train episode 44759: reward = -52.92, steps = 24 07:54:42 [INFO] train episode 44760: reward = -68.10, steps = 28 07:54:44 [INFO] train episode 44761: reward = -42.08, steps = 20 07:54:46 [INFO] train episode 44762: reward = -63.58, steps = 27 07:54:49 [INFO] train episode 44763: reward = -49.99, steps = 24 07:54:53 [INFO] train episode 44764: reward = -62.21, steps = 42 07:54:55 [INFO] train episode 44765: reward = -84.98, steps = 23 07:54:57 [INFO] train episode 44766: reward = -49.22, steps = 24 07:54:58 [INFO] train episode 44767: reward = -50.18, steps = 19 07:55:00 [INFO] train episode 44768: reward = -77.02, steps = 22 07:55:02 [INFO] train episode 44769: reward = -63.21, steps = 23 07:55:05 [INFO] train episode 44770: reward = -65.72, steps = 22 07:55:07 [INFO] train episode 44771: reward = -48.64, steps = 22 07:55:09 [INFO] train episode 44772: reward = -52.15, steps = 25 07:55:11 [INFO] train episode 44773: reward = -50.47, steps = 25 07:55:13 [INFO] train episode 44774: reward = -48.64, steps = 21 07:55:15 [INFO] train episode 44775: reward = -60.54, steps = 25 07:55:17 [INFO] train episode 44776: reward = -57.63, steps = 27 07:55:19 [INFO] train episode 44777: reward = -107.70, steps = 20 07:55:21 [INFO] train episode 44778: reward = -98.65, steps = 20 07:55:25 [INFO] train episode 44779: reward = -123.79, steps = 41 07:55:27 [INFO] train episode 44780: reward = -98.97, steps = 24 07:55:29 [INFO] train episode 44781: reward = -46.43, steps = 22 07:55:32 [INFO] train episode 44782: reward = -59.10, steps = 40 07:55:34 [INFO] train episode 44783: reward = -55.79, steps = 24 07:55:36 [INFO] train episode 44784: reward = -42.05, steps = 21 07:55:38 [INFO] train episode 44785: reward = -46.27, steps = 28 07:55:40 [INFO] train episode 44786: reward = -34.29, steps = 22 07:55:42 [INFO] train episode 44787: reward = -29.65, steps = 20 07:55:44 [INFO] train episode 44788: reward = -65.34, steps = 27 07:55:48 [INFO] train episode 44789: reward = -73.70, steps = 39 07:55:51 [INFO] train episode 44790: reward = -109.95, steps = 35 07:55:53 [INFO] train episode 44791: reward = -54.29, steps = 21 07:55:56 [INFO] train episode 44792: reward = -76.62, steps = 37 07:55:59 [INFO] train episode 44793: reward = -60.30, steps = 31 07:56:01 [INFO] train episode 44794: reward = -67.76, steps = 27 07:56:04 [INFO] train episode 44795: reward = -53.78, steps = 36 07:56:06 [INFO] train episode 44796: reward = -54.43, steps = 25 07:56:08 [INFO] train episode 44797: reward = -51.52, steps = 21 07:56:10 [INFO] train episode 44798: reward = -41.92, steps = 25 07:56:12 [INFO] train episode 44799: reward = -52.89, steps = 24 07:56:15 [INFO] train episode 44800: reward = -96.77, steps = 32 07:56:18 [INFO] train episode 44801: reward = -118.14, steps = 30 07:56:20 [INFO] train episode 44802: reward = -81.96, steps = 29 07:56:22 [INFO] train episode 44803: reward = -61.91, steps = 21 07:56:26 [INFO] train episode 44804: reward = -36.22, steps = 40 07:56:28 [INFO] train episode 44805: reward = -66.35, steps = 30 07:56:30 [INFO] train episode 44806: reward = -40.65, steps = 23 07:56:32 [INFO] train episode 44807: reward = -47.91, steps = 20 07:56:34 [INFO] train episode 44808: reward = -41.52, steps = 26 07:56:37 [INFO] train episode 44809: reward = -48.15, steps = 31 07:56:40 [INFO] train episode 44810: reward = -54.81, steps = 30 07:56:44 [INFO] train episode 44811: reward = -38.64, steps = 46 07:56:47 [INFO] train episode 44812: reward = -60.93, steps = 32 07:56:49 [INFO] train episode 44813: reward = -52.36, steps = 24 07:56:50 [INFO] train episode 44814: reward = -71.28, steps = 21 07:56:52 [INFO] train episode 44815: reward = -51.18, steps = 20 07:56:55 [INFO] train episode 44816: reward = -72.79, steps = 33 07:56:58 [INFO] train episode 44817: reward = -47.86, steps = 26 07:56:59 [INFO] train episode 44818: reward = -57.29, steps = 20 07:57:03 [INFO] train episode 44819: reward = -84.22, steps = 38 07:57:05 [INFO] train episode 44820: reward = -36.48, steps = 27 07:57:07 [INFO] train episode 44821: reward = -75.14, steps = 29 07:57:09 [INFO] train episode 44822: reward = -62.25, steps = 20 07:57:11 [INFO] train episode 44823: reward = -48.92, steps = 20 07:57:13 [INFO] train episode 44824: reward = -40.39, steps = 20 07:57:15 [INFO] train episode 44825: reward = -63.94, steps = 20 07:57:16 [INFO] train episode 44826: reward = -36.39, steps = 21 07:57:18 [INFO] train episode 44827: reward = -84.11, steps = 21 07:57:20 [INFO] train episode 44828: reward = -87.78, steps = 25 07:57:22 [INFO] train episode 44829: reward = -42.46, steps = 24 07:57:25 [INFO] train episode 44830: reward = -82.34, steps = 30 07:57:27 [INFO] train episode 44831: reward = -37.71, steps = 22 07:57:30 [INFO] train episode 44832: reward = -75.46, steps = 26 07:57:33 [INFO] train episode 44833: reward = -93.51, steps = 40 07:57:36 [INFO] train episode 44834: reward = -58.56, steps = 35 07:57:38 [INFO] train episode 44835: reward = -84.01, steps = 20 07:57:40 [INFO] train episode 44836: reward = -42.23, steps = 20 07:57:42 [INFO] train episode 44837: reward = -55.69, steps = 25 07:57:45 [INFO] train episode 44838: reward = -61.64, steps = 22 07:57:46 [INFO] train episode 44839: reward = -57.86, steps = 20 07:57:50 [INFO] train episode 44840: reward = -57.07, steps = 38 07:57:52 [INFO] train episode 44841: reward = -101.16, steps = 32 07:57:57 [INFO] train episode 44842: reward = -134.92, steps = 55 07:57:59 [INFO] train episode 44843: reward = -30.83, steps = 20 07:58:02 [INFO] train episode 44844: reward = -82.42, steps = 32 07:58:05 [INFO] train episode 44845: reward = -80.94, steps = 41 07:58:08 [INFO] train episode 44846: reward = -47.06, steps = 29 07:58:09 [INFO] train episode 44847: reward = -44.95, steps = 20 07:58:12 [INFO] train episode 44848: reward = -50.90, steps = 25 07:58:14 [INFO] train episode 44849: reward = -58.34, steps = 26 07:58:17 [INFO] train episode 44850: reward = -52.57, steps = 29 07:58:19 [INFO] train episode 44851: reward = -53.82, steps = 24 07:58:20 [INFO] train episode 44852: reward = -34.38, steps = 21 07:58:24 [INFO] train episode 44853: reward = -106.43, steps = 38 07:58:25 [INFO] train episode 44854: reward = -66.78, steps = 21 07:58:29 [INFO] train episode 44855: reward = -71.51, steps = 39 07:58:33 [INFO] train episode 44856: reward = -78.24, steps = 43 07:58:35 [INFO] train episode 44857: reward = -45.29, steps = 22 07:58:36 [INFO] train episode 44858: reward = -40.91, steps = 20 07:58:39 [INFO] train episode 44859: reward = -45.49, steps = 25 07:58:40 [INFO] train episode 44860: reward = -49.67, steps = 21 07:58:44 [INFO] train episode 44861: reward = -48.04, steps = 38 07:58:46 [INFO] train episode 44862: reward = -40.10, steps = 22 07:58:50 [INFO] train episode 44863: reward = -62.68, steps = 46 07:58:52 [INFO] train episode 44864: reward = -64.92, steps = 22 07:58:53 [INFO] train episode 44865: reward = -36.94, steps = 20 07:58:56 [INFO] train episode 44866: reward = -71.11, steps = 31 07:58:59 [INFO] train episode 44867: reward = -95.00, steps = 38 07:59:03 [INFO] train episode 44868: reward = -34.96, steps = 36 07:59:05 [INFO] train episode 44869: reward = -47.12, steps = 29 07:59:07 [INFO] train episode 44870: reward = -62.37, steps = 18 07:59:08 [INFO] train episode 44871: reward = -53.16, steps = 22 07:59:10 [INFO] train episode 44872: reward = -72.53, steps = 18 07:59:13 [INFO] train episode 44873: reward = -71.48, steps = 31 07:59:16 [INFO] train episode 44874: reward = -68.88, steps = 37 07:59:19 [INFO] train episode 44875: reward = -67.29, steps = 28 07:59:22 [INFO] train episode 44876: reward = -71.36, steps = 30 07:59:24 [INFO] train episode 44877: reward = -49.07, steps = 23 07:59:29 [INFO] train episode 44878: reward = -102.48, steps = 51 07:59:31 [INFO] train episode 44879: reward = -139.66, steps = 30 07:59:33 [INFO] train episode 44880: reward = -54.83, steps = 21 07:59:35 [INFO] train episode 44881: reward = -77.38, steps = 17 07:59:39 [INFO] train episode 44882: reward = -98.01, steps = 46 07:59:40 [INFO] train episode 44883: reward = -54.11, steps = 20 07:59:43 [INFO] train episode 44884: reward = -66.75, steps = 30 07:59:45 [INFO] train episode 44885: reward = -63.99, steps = 21 07:59:47 [INFO] train episode 44886: reward = -83.69, steps = 30 07:59:49 [INFO] train episode 44887: reward = -58.07, steps = 20 07:59:52 [INFO] train episode 44888: reward = -48.79, steps = 27 07:59:55 [INFO] train episode 44889: reward = -96.80, steps = 46 07:59:57 [INFO] train episode 44890: reward = -57.38, steps = 19 07:59:59 [INFO] train episode 44891: reward = -44.86, steps = 22 08:00:02 [INFO] train episode 44892: reward = -84.50, steps = 37 08:00:04 [INFO] train episode 44893: reward = -52.07, steps = 24 08:00:07 [INFO] train episode 44894: reward = -58.73, steps = 28 08:00:09 [INFO] train episode 44895: reward = -48.78, steps = 25 08:00:11 [INFO] train episode 44896: reward = -57.31, steps = 22 08:00:13 [INFO] train episode 44897: reward = -47.00, steps = 25 08:00:15 [INFO] train episode 44898: reward = -55.78, steps = 19 08:00:17 [INFO] train episode 44899: reward = -56.59, steps = 30 08:00:21 [INFO] train episode 44900: reward = -66.35, steps = 42 08:00:23 [INFO] train episode 44901: reward = -40.27, steps = 27 08:00:25 [INFO] train episode 44902: reward = -49.28, steps = 21 08:00:27 [INFO] train episode 44903: reward = -93.00, steps = 21 08:00:29 [INFO] train episode 44904: reward = -58.15, steps = 20 08:00:31 [INFO] train episode 44905: reward = -78.27, steps = 20 08:00:34 [INFO] train episode 44906: reward = -43.28, steps = 30 08:00:37 [INFO] train episode 44907: reward = -67.79, steps = 36 08:00:40 [INFO] train episode 44908: reward = -75.76, steps = 29 08:00:42 [INFO] train episode 44909: reward = -103.94, steps = 22 08:00:43 [INFO] train episode 44910: reward = -43.36, steps = 20 08:00:45 [INFO] train episode 44911: reward = -38.39, steps = 20 08:00:48 [INFO] train episode 44912: reward = -44.15, steps = 31 08:00:50 [INFO] train episode 44913: reward = -63.19, steps = 27 08:00:53 [INFO] train episode 44914: reward = -82.58, steps = 34 08:00:55 [INFO] train episode 44915: reward = -41.96, steps = 22 08:00:59 [INFO] train episode 44916: reward = -92.73, steps = 36 08:01:02 [INFO] train episode 44917: reward = -58.53, steps = 40 08:01:04 [INFO] train episode 44918: reward = -54.19, steps = 24 08:01:07 [INFO] train episode 44919: reward = -72.04, steps = 39 08:01:09 [INFO] train episode 44920: reward = -33.88, steps = 20 08:01:12 [INFO] train episode 44921: reward = -48.29, steps = 25 08:01:14 [INFO] train episode 44922: reward = -71.98, steps = 31 08:01:17 [INFO] train episode 44923: reward = -137.89, steps = 36 08:01:19 [INFO] train episode 44924: reward = -66.36, steps = 18 08:01:22 [INFO] train episode 44925: reward = -51.11, steps = 34 08:01:23 [INFO] train episode 44926: reward = -55.10, steps = 19 08:01:25 [INFO] train episode 44927: reward = -48.36, steps = 20 08:01:27 [INFO] train episode 44928: reward = -98.77, steps = 22 08:01:29 [INFO] train episode 44929: reward = -48.36, steps = 19 08:01:31 [INFO] train episode 44930: reward = -66.54, steps = 24 08:01:33 [INFO] train episode 44931: reward = -49.75, steps = 21 08:01:35 [INFO] train episode 44932: reward = -45.73, steps = 25 08:01:37 [INFO] train episode 44933: reward = -32.72, steps = 24 08:01:40 [INFO] train episode 44934: reward = -43.01, steps = 35 08:01:42 [INFO] train episode 44935: reward = -61.48, steps = 21 08:01:44 [INFO] train episode 44936: reward = -51.43, steps = 18 08:01:45 [INFO] train episode 44937: reward = -76.46, steps = 20 08:01:47 [INFO] train episode 44938: reward = -57.28, steps = 21 08:01:50 [INFO] train episode 44939: reward = -64.08, steps = 27 08:01:53 [INFO] train episode 44940: reward = -63.68, steps = 43 08:01:55 [INFO] train episode 44941: reward = -59.01, steps = 19 08:01:58 [INFO] train episode 44942: reward = -28.09, steps = 34 08:02:01 [INFO] train episode 44943: reward = -50.78, steps = 39 08:02:03 [INFO] train episode 44944: reward = -57.39, steps = 21 08:02:05 [INFO] train episode 44945: reward = -61.52, steps = 23 08:02:07 [INFO] train episode 44946: reward = -44.99, steps = 25 08:02:09 [INFO] train episode 44947: reward = -54.71, steps = 20 08:02:11 [INFO] train episode 44948: reward = -69.95, steps = 20 08:02:12 [INFO] train episode 44949: reward = -52.14, steps = 21 08:02:15 [INFO] train episode 44950: reward = -74.83, steps = 26 08:02:17 [INFO] train episode 44951: reward = -81.92, steps = 24 08:02:19 [INFO] train episode 44952: reward = -32.91, steps = 27 08:02:21 [INFO] train episode 44953: reward = -70.83, steps = 20 08:02:23 [INFO] train episode 44954: reward = -71.73, steps = 25 08:02:25 [INFO] train episode 44955: reward = -43.86, steps = 21 08:02:27 [INFO] train episode 44956: reward = -68.46, steps = 25 08:02:31 [INFO] train episode 44957: reward = -54.80, steps = 33 08:02:33 [INFO] train episode 44958: reward = -73.75, steps = 25 08:02:35 [INFO] train episode 44959: reward = -52.80, steps = 22 08:02:37 [INFO] train episode 44960: reward = -71.12, steps = 29 08:02:39 [INFO] train episode 44961: reward = -62.32, steps = 20 08:02:42 [INFO] train episode 44962: reward = -95.25, steps = 39 08:02:45 [INFO] train episode 44963: reward = -68.07, steps = 30 08:02:47 [INFO] train episode 44964: reward = -57.00, steps = 22 08:02:49 [INFO] train episode 44965: reward = -62.04, steps = 27 08:02:51 [INFO] train episode 44966: reward = -48.48, steps = 23 08:02:54 [INFO] train episode 44967: reward = -104.85, steps = 32 08:02:57 [INFO] train episode 44968: reward = -58.14, steps = 37 08:02:59 [INFO] train episode 44969: reward = -125.83, steps = 18 08:03:02 [INFO] train episode 44970: reward = -37.95, steps = 27 08:03:03 [INFO] train episode 44971: reward = -47.90, steps = 20 08:03:06 [INFO] train episode 44972: reward = -121.45, steps = 36 08:03:08 [INFO] train episode 44973: reward = -47.08, steps = 21 08:03:10 [INFO] train episode 44974: reward = -98.20, steps = 21 08:03:12 [INFO] train episode 44975: reward = -56.67, steps = 23 08:03:14 [INFO] train episode 44976: reward = -54.10, steps = 20 08:03:19 [INFO] train episode 44977: reward = -82.45, steps = 47 08:03:21 [INFO] train episode 44978: reward = -39.25, steps = 23 08:03:24 [INFO] train episode 44979: reward = -49.59, steps = 26 08:03:27 [INFO] train episode 44980: reward = -73.65, steps = 29 08:03:29 [INFO] train episode 44981: reward = -52.90, steps = 19 08:03:31 [INFO] train episode 44982: reward = -70.23, steps = 21 08:03:33 [INFO] train episode 44983: reward = -66.32, steps = 23 08:03:35 [INFO] train episode 44984: reward = -52.31, steps = 22 08:03:38 [INFO] train episode 44985: reward = -109.88, steps = 33 08:03:40 [INFO] train episode 44986: reward = -64.66, steps = 26 08:03:42 [INFO] train episode 44987: reward = -65.15, steps = 23 08:03:45 [INFO] train episode 44988: reward = -42.38, steps = 30 08:03:47 [INFO] train episode 44989: reward = -44.27, steps = 28 08:03:49 [INFO] train episode 44990: reward = -72.72, steps = 28 08:03:52 [INFO] train episode 44991: reward = -46.24, steps = 27 08:03:54 [INFO] train episode 44992: reward = -67.92, steps = 23 08:03:56 [INFO] train episode 44993: reward = -75.40, steps = 21 08:03:59 [INFO] train episode 44994: reward = -124.33, steps = 32 08:04:02 [INFO] train episode 44995: reward = -49.99, steps = 39 08:04:06 [INFO] train episode 44996: reward = -58.32, steps = 42 08:04:09 [INFO] train episode 44997: reward = -60.36, steps = 32 08:04:10 [INFO] train episode 44998: reward = -70.42, steps = 20 08:04:12 [INFO] train episode 44999: reward = -39.14, steps = 20 08:04:14 [INFO] train episode 45000: reward = -46.72, steps = 24 08:04:16 [INFO] train episode 45001: reward = -29.41, steps = 21 08:04:18 [INFO] train episode 45002: reward = -38.15, steps = 22 08:04:20 [INFO] train episode 45003: reward = -57.19, steps = 24 08:04:22 [INFO] train episode 45004: reward = -32.45, steps = 23 08:04:25 [INFO] train episode 45005: reward = -48.88, steps = 31 08:04:27 [INFO] train episode 45006: reward = -43.23, steps = 27 08:04:31 [INFO] train episode 45007: reward = -98.54, steps = 43 08:04:34 [INFO] train episode 45008: reward = -62.58, steps = 39 08:04:37 [INFO] train episode 45009: reward = -61.59, steps = 34 08:04:39 [INFO] train episode 45010: reward = -45.94, steps = 26 08:04:41 [INFO] train episode 45011: reward = -37.88, steps = 21 08:04:43 [INFO] train episode 45012: reward = -58.02, steps = 27 08:04:45 [INFO] train episode 45013: reward = -53.12, steps = 21 08:04:47 [INFO] train episode 45014: reward = -58.65, steps = 21 08:04:50 [INFO] train episode 45015: reward = -73.04, steps = 32 08:04:51 [INFO] train episode 45016: reward = -24.75, steps = 19 08:04:55 [INFO] train episode 45017: reward = -50.12, steps = 36 08:04:57 [INFO] train episode 45018: reward = -70.18, steps = 28 08:04:59 [INFO] train episode 45019: reward = -61.36, steps = 23 08:05:01 [INFO] train episode 45020: reward = -54.90, steps = 22 08:05:04 [INFO] train episode 45021: reward = -63.69, steps = 26 08:05:06 [INFO] train episode 45022: reward = -66.27, steps = 29 08:05:09 [INFO] train episode 45023: reward = -52.12, steps = 32 08:05:11 [INFO] train episode 45024: reward = -66.56, steps = 21 08:05:13 [INFO] train episode 45025: reward = -55.40, steps = 20 08:05:15 [INFO] train episode 45026: reward = -39.04, steps = 22 08:05:17 [INFO] train episode 45027: reward = -54.26, steps = 31 08:05:20 [INFO] train episode 45028: reward = -66.91, steps = 25 08:05:23 [INFO] train episode 45029: reward = -48.72, steps = 42 08:05:25 [INFO] train episode 45030: reward = -62.82, steps = 25 08:05:27 [INFO] train episode 45031: reward = -73.02, steps = 20 08:05:30 [INFO] train episode 45032: reward = -49.16, steps = 28 08:05:32 [INFO] train episode 45033: reward = -68.04, steps = 21 08:05:34 [INFO] train episode 45034: reward = -62.11, steps = 26 08:05:36 [INFO] train episode 45035: reward = -50.73, steps = 22 08:05:38 [INFO] train episode 45036: reward = -66.03, steps = 29 08:05:40 [INFO] train episode 45037: reward = -63.50, steps = 21 08:05:43 [INFO] train episode 45038: reward = -80.41, steps = 27 08:05:44 [INFO] train episode 45039: reward = -39.36, steps = 20 08:05:47 [INFO] train episode 45040: reward = -53.46, steps = 36 08:05:50 [INFO] train episode 45041: reward = -35.55, steps = 27 08:05:52 [INFO] train episode 45042: reward = -62.75, steps = 26 08:05:55 [INFO] train episode 45043: reward = -85.89, steps = 37 08:05:58 [INFO] train episode 45044: reward = -76.89, steps = 34 08:06:00 [INFO] train episode 45045: reward = -46.46, steps = 22 08:06:02 [INFO] train episode 45046: reward = -50.54, steps = 22 08:06:04 [INFO] train episode 45047: reward = -56.32, steps = 27 08:06:07 [INFO] train episode 45048: reward = -45.80, steps = 28 08:06:09 [INFO] train episode 45049: reward = -55.10, steps = 28 08:06:13 [INFO] train episode 45050: reward = -83.87, steps = 44 08:06:17 [INFO] train episode 45051: reward = -62.61, steps = 38 08:06:19 [INFO] train episode 45052: reward = -88.81, steps = 23 08:06:21 [INFO] train episode 45053: reward = -52.02, steps = 22 08:06:23 [INFO] train episode 45054: reward = -93.29, steps = 22 08:06:25 [INFO] train episode 45055: reward = -72.54, steps = 27 08:06:27 [INFO] train episode 45056: reward = -45.43, steps = 19 08:06:30 [INFO] train episode 45057: reward = -61.74, steps = 32 08:06:34 [INFO] train episode 45058: reward = -151.26, steps = 53 08:06:37 [INFO] train episode 45059: reward = -43.63, steps = 29 08:06:41 [INFO] train episode 45060: reward = -46.68, steps = 46 08:06:43 [INFO] train episode 45061: reward = -100.67, steps = 27 08:06:46 [INFO] train episode 45062: reward = -53.39, steps = 23 08:06:48 [INFO] train episode 45063: reward = -51.69, steps = 27 08:06:50 [INFO] train episode 45064: reward = -42.53, steps = 20 08:06:52 [INFO] train episode 45065: reward = -66.73, steps = 32 08:06:54 [INFO] train episode 45066: reward = -86.00, steps = 24 08:06:56 [INFO] train episode 45067: reward = -66.80, steps = 20 08:06:59 [INFO] train episode 45068: reward = -78.00, steps = 37 08:07:02 [INFO] train episode 45069: reward = -43.09, steps = 26 08:07:04 [INFO] train episode 45070: reward = -48.51, steps = 20 08:07:06 [INFO] train episode 45071: reward = -48.20, steps = 25 08:07:07 [INFO] train episode 45072: reward = -74.84, steps = 18 08:07:10 [INFO] train episode 45073: reward = -51.72, steps = 26 08:07:12 [INFO] train episode 45074: reward = -71.38, steps = 28 08:07:15 [INFO] train episode 45075: reward = -57.97, steps = 34 08:07:18 [INFO] train episode 45076: reward = -61.18, steps = 31 08:07:21 [INFO] train episode 45077: reward = -30.11, steps = 31 08:07:22 [INFO] train episode 45078: reward = -35.98, steps = 19 08:07:25 [INFO] train episode 45079: reward = -66.26, steps = 31 08:07:27 [INFO] train episode 45080: reward = -72.10, steps = 25 08:07:30 [INFO] train episode 45081: reward = -43.99, steps = 36 08:07:32 [INFO] train episode 45082: reward = -58.32, steps = 22 08:07:35 [INFO] train episode 45083: reward = -57.58, steps = 30 08:07:37 [INFO] train episode 45084: reward = -54.78, steps = 32 08:07:39 [INFO] train episode 45085: reward = -48.55, steps = 20 08:07:42 [INFO] train episode 45086: reward = -78.15, steps = 35 08:07:44 [INFO] train episode 45087: reward = -45.93, steps = 21 08:07:46 [INFO] train episode 45088: reward = -33.39, steps = 20 08:07:49 [INFO] train episode 45089: reward = -49.83, steps = 30 08:07:51 [INFO] train episode 45090: reward = -81.38, steps = 27 08:07:53 [INFO] train episode 45091: reward = -68.48, steps = 28 08:07:55 [INFO] train episode 45092: reward = -75.63, steps = 22 08:07:57 [INFO] train episode 45093: reward = -46.13, steps = 25 08:08:00 [INFO] train episode 45094: reward = -65.22, steps = 25 08:08:02 [INFO] train episode 45095: reward = -44.33, steps = 30 08:08:04 [INFO] train episode 45096: reward = -42.62, steps = 21 08:08:07 [INFO] train episode 45097: reward = -116.70, steps = 36 08:08:09 [INFO] train episode 45098: reward = -36.87, steps = 21 08:08:12 [INFO] train episode 45099: reward = -64.45, steps = 29 08:08:13 [INFO] train episode 45100: reward = -60.39, steps = 20 08:08:15 [INFO] train episode 45101: reward = -47.27, steps = 25 08:08:18 [INFO] train episode 45102: reward = -52.95, steps = 27 08:08:20 [INFO] train episode 45103: reward = -67.32, steps = 23 08:08:22 [INFO] train episode 45104: reward = -61.70, steps = 24 08:08:24 [INFO] train episode 45105: reward = -62.90, steps = 19 08:08:26 [INFO] train episode 45106: reward = -56.62, steps = 22 08:08:27 [INFO] train episode 45107: reward = -44.98, steps = 22 08:08:30 [INFO] train episode 45108: reward = -64.27, steps = 29 08:08:32 [INFO] train episode 45109: reward = -64.75, steps = 21 08:08:34 [INFO] train episode 45110: reward = -46.35, steps = 21 08:08:36 [INFO] train episode 45111: reward = -54.64, steps = 20 08:08:38 [INFO] train episode 45112: reward = -42.97, steps = 26 08:08:41 [INFO] train episode 45113: reward = -95.34, steps = 32 08:08:43 [INFO] train episode 45114: reward = -44.49, steps = 22 08:08:45 [INFO] train episode 45115: reward = -66.18, steps = 23 08:08:47 [INFO] train episode 45116: reward = -45.34, steps = 23 08:08:49 [INFO] train episode 45117: reward = -59.93, steps = 22 08:08:51 [INFO] train episode 45118: reward = -85.35, steps = 27 08:08:53 [INFO] train episode 45119: reward = -50.71, steps = 21 08:08:56 [INFO] train episode 45120: reward = -61.00, steps = 30 08:08:58 [INFO] train episode 45121: reward = -118.32, steps = 30 08:09:01 [INFO] train episode 45122: reward = -140.65, steps = 36 08:09:03 [INFO] train episode 45123: reward = -44.83, steps = 19 08:09:04 [INFO] train episode 45124: reward = -71.99, steps = 22 08:09:08 [INFO] train episode 45125: reward = -61.95, steps = 26 08:09:10 [INFO] train episode 45126: reward = -46.38, steps = 21 08:09:11 [INFO] train episode 45127: reward = -41.04, steps = 22 08:09:13 [INFO] train episode 45128: reward = -75.21, steps = 18 08:09:15 [INFO] train episode 45129: reward = -44.58, steps = 20 08:09:17 [INFO] train episode 45130: reward = -57.97, steps = 29 08:09:19 [INFO] train episode 45131: reward = -48.34, steps = 24 08:09:22 [INFO] train episode 45132: reward = -46.70, steps = 30 08:09:24 [INFO] train episode 45133: reward = -49.53, steps = 24 08:09:27 [INFO] train episode 45134: reward = -43.41, steps = 30 08:09:29 [INFO] train episode 45135: reward = -55.08, steps = 27 08:09:31 [INFO] train episode 45136: reward = -49.66, steps = 20 08:09:33 [INFO] train episode 45137: reward = -50.23, steps = 20 08:09:35 [INFO] train episode 45138: reward = -40.97, steps = 24 08:09:37 [INFO] train episode 45139: reward = -47.24, steps = 33 08:09:40 [INFO] train episode 45140: reward = -49.58, steps = 22 08:09:42 [INFO] train episode 45141: reward = -58.02, steps = 25 08:09:44 [INFO] train episode 45142: reward = -46.56, steps = 27 08:09:46 [INFO] train episode 45143: reward = -64.18, steps = 20 08:09:49 [INFO] train episode 45144: reward = -23.04, steps = 34 08:09:50 [INFO] train episode 45145: reward = -41.29, steps = 21 08:09:52 [INFO] train episode 45146: reward = -44.56, steps = 21 08:09:54 [INFO] train episode 45147: reward = -60.20, steps = 25 08:10:00 [INFO] train episode 45148: reward = -154.46, steps = 65 08:10:02 [INFO] train episode 45149: reward = -46.13, steps = 20 08:10:04 [INFO] train episode 45150: reward = -106.20, steps = 25 08:10:06 [INFO] train episode 45151: reward = -67.34, steps = 27 08:10:09 [INFO] train episode 45152: reward = -50.13, steps = 32 08:10:10 [INFO] train episode 45153: reward = -58.52, steps = 19 08:10:13 [INFO] train episode 45154: reward = -39.26, steps = 20 08:10:15 [INFO] train episode 45155: reward = -64.07, steps = 22 08:10:17 [INFO] train episode 45156: reward = -38.51, steps = 29 08:10:19 [INFO] train episode 45157: reward = -97.86, steps = 25 08:10:21 [INFO] train episode 45158: reward = -42.82, steps = 22 08:10:23 [INFO] train episode 45159: reward = -55.04, steps = 21 08:10:26 [INFO] train episode 45160: reward = -106.60, steps = 30 08:10:28 [INFO] train episode 45161: reward = -46.92, steps = 28 08:10:30 [INFO] train episode 45162: reward = -43.22, steps = 19 08:10:32 [INFO] train episode 45163: reward = -97.27, steps = 26 08:10:34 [INFO] train episode 45164: reward = -54.91, steps = 27 08:10:36 [INFO] train episode 45165: reward = -50.38, steps = 22 08:10:39 [INFO] train episode 45166: reward = -30.49, steps = 26 08:10:41 [INFO] train episode 45167: reward = -44.38, steps = 24 08:10:43 [INFO] train episode 45168: reward = -53.95, steps = 25 08:10:45 [INFO] train episode 45169: reward = -70.32, steps = 19 08:10:47 [INFO] train episode 45170: reward = -66.93, steps = 29 08:10:50 [INFO] train episode 45171: reward = -46.80, steps = 31 08:10:52 [INFO] train episode 45172: reward = -52.64, steps = 27 08:10:55 [INFO] train episode 45173: reward = -47.34, steps = 26 08:10:56 [INFO] train episode 45174: reward = -35.54, steps = 21 08:10:59 [INFO] train episode 45175: reward = -54.49, steps = 27 08:11:02 [INFO] train episode 45176: reward = -69.70, steps = 33 08:11:04 [INFO] train episode 45177: reward = -41.92, steps = 27 08:11:06 [INFO] train episode 45178: reward = -43.32, steps = 21 08:11:08 [INFO] train episode 45179: reward = -67.22, steps = 26 08:11:10 [INFO] train episode 45180: reward = -63.54, steps = 18 08:11:11 [INFO] train episode 45181: reward = -49.57, steps = 20 08:11:14 [INFO] train episode 45182: reward = -61.57, steps = 26 08:11:17 [INFO] train episode 45183: reward = -54.24, steps = 33 08:11:19 [INFO] train episode 45184: reward = -56.97, steps = 20 08:11:20 [INFO] train episode 45185: reward = -53.50, steps = 18 08:11:22 [INFO] train episode 45186: reward = -58.27, steps = 20 08:11:25 [INFO] train episode 45187: reward = -51.15, steps = 31 08:11:27 [INFO] train episode 45188: reward = -65.97, steps = 27 08:11:30 [INFO] train episode 45189: reward = -54.16, steps = 34 08:11:32 [INFO] train episode 45190: reward = -52.51, steps = 20 08:11:35 [INFO] train episode 45191: reward = -105.24, steps = 32 08:11:36 [INFO] train episode 45192: reward = -41.94, steps = 19 08:11:38 [INFO] train episode 45193: reward = -57.97, steps = 27 08:11:41 [INFO] train episode 45194: reward = -66.54, steps = 29 08:11:43 [INFO] train episode 45195: reward = -37.39, steps = 23 08:11:45 [INFO] train episode 45196: reward = -52.27, steps = 20 08:11:47 [INFO] train episode 45197: reward = -58.38, steps = 22 08:11:49 [INFO] train episode 45198: reward = -49.71, steps = 20 08:11:51 [INFO] train episode 45199: reward = -63.99, steps = 27 08:11:54 [INFO] train episode 45200: reward = -64.24, steps = 41 08:11:57 [INFO] train episode 45201: reward = -46.16, steps = 22 08:11:59 [INFO] train episode 45202: reward = -44.25, steps = 28 08:12:01 [INFO] train episode 45203: reward = -56.05, steps = 21 08:12:03 [INFO] train episode 45204: reward = -61.18, steps = 22 08:12:05 [INFO] train episode 45205: reward = -37.52, steps = 21 08:12:07 [INFO] train episode 45206: reward = -51.95, steps = 21 08:12:09 [INFO] train episode 45207: reward = -37.55, steps = 20 08:12:11 [INFO] train episode 45208: reward = -47.77, steps = 25 08:12:14 [INFO] train episode 45209: reward = -93.09, steps = 37 08:12:16 [INFO] train episode 45210: reward = -35.75, steps = 24 08:12:18 [INFO] train episode 45211: reward = -79.39, steps = 18 08:12:20 [INFO] train episode 45212: reward = -54.43, steps = 29 08:12:22 [INFO] train episode 45213: reward = -76.83, steps = 19 08:12:24 [INFO] train episode 45214: reward = -40.31, steps = 20 08:12:26 [INFO] train episode 45215: reward = -49.26, steps = 28 08:12:28 [INFO] train episode 45216: reward = -55.48, steps = 22 08:12:31 [INFO] train episode 45217: reward = -84.32, steps = 29 08:12:33 [INFO] train episode 45218: reward = -61.63, steps = 23 08:12:35 [INFO] train episode 45219: reward = -81.30, steps = 26 08:12:38 [INFO] train episode 45220: reward = -107.27, steps = 35 08:12:40 [INFO] train episode 45221: reward = -69.26, steps = 19 08:12:43 [INFO] train episode 45222: reward = -44.55, steps = 31 08:12:44 [INFO] train episode 45223: reward = -62.37, steps = 21 08:12:46 [INFO] train episode 45224: reward = -60.51, steps = 20 08:12:50 [INFO] train episode 45225: reward = -95.36, steps = 33 08:12:52 [INFO] train episode 45226: reward = -49.94, steps = 33 08:12:54 [INFO] train episode 45227: reward = -38.80, steps = 22 08:12:56 [INFO] train episode 45228: reward = -60.56, steps = 20 08:12:58 [INFO] train episode 45229: reward = -75.20, steps = 22 08:13:00 [INFO] train episode 45230: reward = -64.83, steps = 24 08:13:02 [INFO] train episode 45231: reward = -33.96, steps = 29 08:13:04 [INFO] train episode 45232: reward = -54.22, steps = 21 08:13:06 [INFO] train episode 45233: reward = -75.28, steps = 20 08:13:08 [INFO] train episode 45234: reward = -40.37, steps = 26 08:13:10 [INFO] train episode 45235: reward = -53.57, steps = 23 08:13:12 [INFO] train episode 45236: reward = -41.46, steps = 20 08:13:14 [INFO] train episode 45237: reward = -55.61, steps = 22 08:13:16 [INFO] train episode 45238: reward = -56.94, steps = 21 08:13:18 [INFO] train episode 45239: reward = -59.64, steps = 21 08:13:19 [INFO] train episode 45240: reward = -28.13, steps = 20 08:13:23 [INFO] train episode 45241: reward = -87.10, steps = 37 08:13:25 [INFO] train episode 45242: reward = -63.22, steps = 24 08:13:26 [INFO] train episode 45243: reward = -62.51, steps = 20 08:13:28 [INFO] train episode 45244: reward = -85.89, steps = 21 08:13:30 [INFO] train episode 45245: reward = -71.92, steps = 20 08:13:32 [INFO] train episode 45246: reward = -64.07, steps = 19 08:13:34 [INFO] train episode 45247: reward = -40.50, steps = 23 08:13:37 [INFO] train episode 45248: reward = -49.88, steps = 30 08:13:39 [INFO] train episode 45249: reward = -43.91, steps = 33 08:13:41 [INFO] train episode 45250: reward = -32.76, steps = 21 08:13:43 [INFO] train episode 45251: reward = -52.79, steps = 25 08:13:46 [INFO] train episode 45252: reward = -78.06, steps = 31 08:13:49 [INFO] train episode 45253: reward = -113.04, steps = 45 08:13:54 [INFO] train episode 45254: reward = -47.49, steps = 48 08:13:56 [INFO] train episode 45255: reward = -51.85, steps = 23 08:13:58 [INFO] train episode 45256: reward = -84.44, steps = 22 08:14:00 [INFO] train episode 45257: reward = -56.90, steps = 32 08:14:03 [INFO] train episode 45258: reward = -41.05, steps = 25 08:14:05 [INFO] train episode 45259: reward = -74.93, steps = 28 08:14:07 [INFO] train episode 45260: reward = -50.42, steps = 20 08:14:09 [INFO] train episode 45261: reward = -81.24, steps = 21 08:14:11 [INFO] train episode 45262: reward = -43.35, steps = 23 08:14:13 [INFO] train episode 45263: reward = -58.51, steps = 26 08:14:15 [INFO] train episode 45264: reward = -71.48, steps = 25 08:14:18 [INFO] train episode 45265: reward = -67.51, steps = 33 08:14:20 [INFO] train episode 45266: reward = -43.03, steps = 22 08:14:22 [INFO] train episode 45267: reward = -69.50, steps = 21 08:14:25 [INFO] train episode 45268: reward = -72.34, steps = 28 08:14:27 [INFO] train episode 45269: reward = -60.90, steps = 29 08:14:30 [INFO] train episode 45270: reward = -71.11, steps = 33 08:14:32 [INFO] train episode 45271: reward = -62.10, steps = 21 08:14:35 [INFO] train episode 45272: reward = -83.63, steps = 45 08:14:38 [INFO] train episode 45273: reward = -60.59, steps = 27 08:14:41 [INFO] train episode 45274: reward = -73.88, steps = 32 08:14:43 [INFO] train episode 45275: reward = -63.58, steps = 21 08:14:45 [INFO] train episode 45276: reward = -65.21, steps = 28 08:14:48 [INFO] train episode 45277: reward = -45.09, steps = 23 08:14:50 [INFO] train episode 45278: reward = -73.95, steps = 24 08:14:52 [INFO] train episode 45279: reward = -40.73, steps = 25 08:14:54 [INFO] train episode 45280: reward = -72.02, steps = 24 08:14:57 [INFO] train episode 45281: reward = -65.20, steps = 34 08:15:00 [INFO] train episode 45282: reward = -63.75, steps = 33 08:15:02 [INFO] train episode 45283: reward = -70.90, steps = 26 08:15:05 [INFO] train episode 45284: reward = -67.56, steps = 26 08:15:06 [INFO] train episode 45285: reward = -44.62, steps = 20 08:15:09 [INFO] train episode 45286: reward = -72.14, steps = 28 08:15:11 [INFO] train episode 45287: reward = -37.21, steps = 32 08:15:14 [INFO] train episode 45288: reward = -57.79, steps = 28 08:15:17 [INFO] train episode 45289: reward = -30.13, steps = 34 08:15:19 [INFO] train episode 45290: reward = -67.88, steps = 23 08:15:21 [INFO] train episode 45291: reward = -49.38, steps = 19 08:15:22 [INFO] train episode 45292: reward = -54.40, steps = 22 08:15:25 [INFO] train episode 45293: reward = -102.79, steps = 28 08:15:27 [INFO] train episode 45294: reward = -56.29, steps = 26 08:15:29 [INFO] train episode 45295: reward = -46.99, steps = 21 08:15:31 [INFO] train episode 45296: reward = -46.72, steps = 19 08:15:33 [INFO] train episode 45297: reward = -59.45, steps = 24 08:15:35 [INFO] train episode 45298: reward = -35.79, steps = 27 08:15:37 [INFO] train episode 45299: reward = -54.83, steps = 21 08:15:39 [INFO] train episode 45300: reward = -66.63, steps = 27 08:15:41 [INFO] train episode 45301: reward = -64.49, steps = 22 08:15:43 [INFO] train episode 45302: reward = -75.26, steps = 25 08:15:46 [INFO] train episode 45303: reward = -45.46, steps = 25 08:15:48 [INFO] train episode 45304: reward = -92.22, steps = 29 08:15:51 [INFO] train episode 45305: reward = -48.58, steps = 32 08:15:53 [INFO] train episode 45306: reward = -47.67, steps = 22 08:15:54 [INFO] train episode 45307: reward = -36.72, steps = 20 08:15:56 [INFO] train episode 45308: reward = -60.99, steps = 24 08:16:00 [INFO] train episode 45309: reward = -61.96, steps = 34 08:16:02 [INFO] train episode 45310: reward = -95.71, steps = 33 08:16:05 [INFO] train episode 45311: reward = -52.73, steps = 31 08:16:07 [INFO] train episode 45312: reward = -59.06, steps = 26 08:16:09 [INFO] train episode 45313: reward = -46.95, steps = 21 08:16:11 [INFO] train episode 45314: reward = -45.40, steps = 22 08:16:13 [INFO] train episode 45315: reward = -77.29, steps = 27 08:16:15 [INFO] train episode 45316: reward = -63.59, steps = 21 08:16:17 [INFO] train episode 45317: reward = -40.36, steps = 20 08:16:20 [INFO] train episode 45318: reward = -32.99, steps = 34 08:16:22 [INFO] train episode 45319: reward = -60.86, steps = 23 08:16:24 [INFO] train episode 45320: reward = -45.62, steps = 22 08:16:26 [INFO] train episode 45321: reward = -73.01, steps = 22 08:16:29 [INFO] train episode 45322: reward = -49.21, steps = 42 08:16:31 [INFO] train episode 45323: reward = -68.56, steps = 12 08:16:33 [INFO] train episode 45324: reward = -62.10, steps = 29 08:16:35 [INFO] train episode 45325: reward = -43.41, steps = 21 08:16:38 [INFO] train episode 45326: reward = -74.04, steps = 32 08:16:39 [INFO] train episode 45327: reward = -47.58, steps = 19 08:16:42 [INFO] train episode 45328: reward = -72.28, steps = 26 08:16:44 [INFO] train episode 45329: reward = -87.64, steps = 31 08:16:47 [INFO] train episode 45330: reward = -71.81, steps = 32 08:16:49 [INFO] train episode 45331: reward = -87.05, steps = 19 08:16:52 [INFO] train episode 45332: reward = -62.87, steps = 34 08:16:54 [INFO] train episode 45333: reward = -66.21, steps = 26 08:16:57 [INFO] train episode 45334: reward = -96.74, steps = 38 08:17:00 [INFO] train episode 45335: reward = -58.85, steps = 30 08:17:02 [INFO] train episode 45336: reward = -39.99, steps = 27 08:17:04 [INFO] train episode 45337: reward = -56.85, steps = 22 08:17:07 [INFO] train episode 45338: reward = -44.27, steps = 29 08:17:09 [INFO] train episode 45339: reward = -61.64, steps = 25 08:17:11 [INFO] train episode 45340: reward = -44.10, steps = 21 08:17:13 [INFO] train episode 45341: reward = -52.62, steps = 21 08:17:15 [INFO] train episode 45342: reward = -89.60, steps = 26 08:17:17 [INFO] train episode 45343: reward = -57.27, steps = 25 08:17:19 [INFO] train episode 45344: reward = -71.86, steps = 21 08:17:22 [INFO] train episode 45345: reward = -54.84, steps = 30 08:17:25 [INFO] train episode 45346: reward = -72.43, steps = 32 08:17:26 [INFO] train episode 45347: reward = -56.52, steps = 22 08:17:29 [INFO] train episode 45348: reward = -85.04, steps = 28 08:17:31 [INFO] train episode 45349: reward = -44.17, steps = 21 08:17:32 [INFO] train episode 45350: reward = -58.52, steps = 19 08:17:34 [INFO] train episode 45351: reward = -56.84, steps = 21 08:17:37 [INFO] train episode 45352: reward = -37.04, steps = 22 08:17:40 [INFO] train episode 45353: reward = -57.33, steps = 31 08:17:41 [INFO] train episode 45354: reward = -49.33, steps = 20 08:17:45 [INFO] train episode 45355: reward = -52.81, steps = 41 08:17:47 [INFO] train episode 45356: reward = -97.98, steps = 24 08:17:49 [INFO] train episode 45357: reward = -34.16, steps = 21 08:17:52 [INFO] train episode 45358: reward = -54.70, steps = 30 08:17:54 [INFO] train episode 45359: reward = -72.78, steps = 26 08:17:56 [INFO] train episode 45360: reward = -49.14, steps = 25 08:17:58 [INFO] train episode 45361: reward = -48.09, steps = 22 08:18:01 [INFO] train episode 45362: reward = -64.66, steps = 34 08:18:02 [INFO] train episode 45363: reward = -79.59, steps = 20 08:18:04 [INFO] train episode 45364: reward = -68.25, steps = 25 08:18:07 [INFO] train episode 45365: reward = -67.00, steps = 21 08:18:09 [INFO] train episode 45366: reward = -45.05, steps = 30 08:18:12 [INFO] train episode 45367: reward = -59.86, steps = 31 08:18:14 [INFO] train episode 45368: reward = -82.03, steps = 21 08:18:16 [INFO] train episode 45369: reward = -46.57, steps = 22 08:18:19 [INFO] train episode 45370: reward = -59.59, steps = 41 08:18:22 [INFO] train episode 45371: reward = -67.64, steps = 25 08:18:23 [INFO] train episode 45372: reward = -61.98, steps = 22 08:18:25 [INFO] train episode 45373: reward = -46.39, steps = 24 08:18:27 [INFO] train episode 45374: reward = -45.01, steps = 23 08:18:29 [INFO] train episode 45375: reward = -96.94, steps = 20 08:18:33 [INFO] train episode 45376: reward = -95.28, steps = 40 08:18:35 [INFO] train episode 45377: reward = -79.92, steps = 28 08:18:37 [INFO] train episode 45378: reward = -45.72, steps = 22 08:18:39 [INFO] train episode 45379: reward = -64.14, steps = 23 08:18:41 [INFO] train episode 45380: reward = -48.06, steps = 23 08:18:44 [INFO] train episode 45381: reward = -77.00, steps = 30 08:18:46 [INFO] train episode 45382: reward = -37.12, steps = 20 08:18:47 [INFO] train episode 45383: reward = -83.56, steps = 18 08:18:49 [INFO] train episode 45384: reward = -78.12, steps = 24 08:18:51 [INFO] train episode 45385: reward = -46.62, steps = 23 08:18:53 [INFO] train episode 45386: reward = -34.19, steps = 22 08:18:55 [INFO] train episode 45387: reward = -42.86, steps = 24 08:18:57 [INFO] train episode 45388: reward = -65.43, steps = 21 08:19:01 [INFO] train episode 45389: reward = -80.41, steps = 45 08:19:03 [INFO] train episode 45390: reward = -55.23, steps = 19 08:19:05 [INFO] train episode 45391: reward = -65.83, steps = 27 08:19:07 [INFO] train episode 45392: reward = -51.99, steps = 19 08:19:10 [INFO] train episode 45393: reward = -50.40, steps = 33 08:19:11 [INFO] train episode 45394: reward = -43.12, steps = 20 08:19:14 [INFO] train episode 45395: reward = -41.96, steps = 25 08:19:17 [INFO] train episode 45396: reward = -87.31, steps = 38 08:19:19 [INFO] train episode 45397: reward = -43.42, steps = 22 08:19:21 [INFO] train episode 45398: reward = -50.49, steps = 23 08:19:23 [INFO] train episode 45399: reward = -70.79, steps = 23 08:19:25 [INFO] train episode 45400: reward = -50.42, steps = 25 08:19:27 [INFO] train episode 45401: reward = -48.84, steps = 19 08:19:28 [INFO] train episode 45402: reward = -68.59, steps = 20 08:19:31 [INFO] train episode 45403: reward = -83.26, steps = 28 08:19:34 [INFO] train episode 45404: reward = -44.89, steps = 41 08:19:37 [INFO] train episode 45405: reward = -53.37, steps = 29 08:19:39 [INFO] train episode 45406: reward = -41.67, steps = 23 08:19:41 [INFO] train episode 45407: reward = -68.09, steps = 25 08:19:44 [INFO] train episode 45408: reward = -68.98, steps = 28 08:19:46 [INFO] train episode 45409: reward = -49.90, steps = 24 08:19:48 [INFO] train episode 45410: reward = -64.89, steps = 24 08:19:49 [INFO] train episode 45411: reward = -44.59, steps = 20 08:19:52 [INFO] train episode 45412: reward = -61.36, steps = 30 08:19:54 [INFO] train episode 45413: reward = -73.19, steps = 25 08:19:58 [INFO] train episode 45414: reward = -125.00, steps = 46 08:20:00 [INFO] train episode 45415: reward = -32.40, steps = 20 08:20:02 [INFO] train episode 45416: reward = -27.48, steps = 22 08:20:04 [INFO] train episode 45417: reward = -47.42, steps = 22 08:20:06 [INFO] train episode 45418: reward = -59.92, steps = 23 08:20:09 [INFO] train episode 45419: reward = -121.74, steps = 41 08:20:12 [INFO] train episode 45420: reward = -48.73, steps = 26 08:20:14 [INFO] train episode 45421: reward = -45.69, steps = 23 08:20:16 [INFO] train episode 45422: reward = -31.24, steps = 27 08:20:20 [INFO] train episode 45423: reward = -76.88, steps = 33 08:20:22 [INFO] train episode 45424: reward = -50.74, steps = 25 08:20:24 [INFO] train episode 45425: reward = -49.77, steps = 20 08:20:27 [INFO] train episode 45426: reward = -40.20, steps = 28 08:20:31 [INFO] train episode 45427: reward = -59.97, steps = 32 08:20:33 [INFO] train episode 45428: reward = -92.40, steps = 21 08:20:35 [INFO] train episode 45429: reward = -63.56, steps = 28 08:20:38 [INFO] train episode 45430: reward = -55.71, steps = 25 08:20:40 [INFO] train episode 45431: reward = -61.50, steps = 25 08:20:42 [INFO] train episode 45432: reward = -53.92, steps = 23 08:20:45 [INFO] train episode 45433: reward = -62.76, steps = 22 08:20:47 [INFO] train episode 45434: reward = -56.23, steps = 22 08:20:50 [INFO] train episode 45435: reward = -62.45, steps = 37 08:20:52 [INFO] train episode 45436: reward = -66.18, steps = 23 08:20:54 [INFO] train episode 45437: reward = -41.20, steps = 22 08:20:56 [INFO] train episode 45438: reward = -62.72, steps = 19 08:20:57 [INFO] train episode 45439: reward = -43.35, steps = 19 08:21:01 [INFO] train episode 45440: reward = -85.62, steps = 43 08:21:03 [INFO] train episode 45441: reward = -59.82, steps = 20 08:21:05 [INFO] train episode 45442: reward = -80.23, steps = 20 08:21:07 [INFO] train episode 45443: reward = -61.14, steps = 27 08:21:09 [INFO] train episode 45444: reward = -58.61, steps = 24 08:21:11 [INFO] train episode 45445: reward = -60.76, steps = 23 08:21:13 [INFO] train episode 45446: reward = -89.05, steps = 20 08:21:15 [INFO] train episode 45447: reward = -43.00, steps = 23 08:21:18 [INFO] train episode 45448: reward = -71.75, steps = 35 08:21:20 [INFO] train episode 45449: reward = -79.76, steps = 21 08:21:22 [INFO] train episode 45450: reward = -60.50, steps = 19 08:21:23 [INFO] train episode 45451: reward = -34.51, steps = 20 08:21:25 [INFO] train episode 45452: reward = -56.98, steps = 20 08:21:27 [INFO] train episode 45453: reward = -41.04, steps = 21 08:21:29 [INFO] train episode 45454: reward = -61.89, steps = 22 08:21:32 [INFO] train episode 45455: reward = -49.51, steps = 33 08:21:35 [INFO] train episode 45456: reward = -80.20, steps = 42 08:21:37 [INFO] train episode 45457: reward = -53.07, steps = 19 08:21:40 [INFO] train episode 45458: reward = -67.86, steps = 33 08:21:42 [INFO] train episode 45459: reward = -30.89, steps = 21 08:21:43 [INFO] train episode 45460: reward = -45.45, steps = 20 08:21:45 [INFO] train episode 45461: reward = -42.46, steps = 21 08:21:49 [INFO] train episode 45462: reward = -52.15, steps = 42 08:21:51 [INFO] train episode 45463: reward = -58.57, steps = 21 08:21:53 [INFO] train episode 45464: reward = -78.89, steps = 25 08:21:55 [INFO] train episode 45465: reward = -45.05, steps = 20 08:21:57 [INFO] train episode 45466: reward = -87.37, steps = 20 08:21:58 [INFO] train episode 45467: reward = -54.41, steps = 23 08:22:01 [INFO] train episode 45468: reward = -48.17, steps = 29 08:22:03 [INFO] train episode 45469: reward = -66.43, steps = 20 08:22:06 [INFO] train episode 45470: reward = -67.89, steps = 33 08:22:09 [INFO] train episode 45471: reward = -69.02, steps = 32 08:22:10 [INFO] train episode 45472: reward = -74.02, steps = 20 08:22:12 [INFO] train episode 45473: reward = -51.91, steps = 26 08:22:14 [INFO] train episode 45474: reward = -50.62, steps = 23 08:22:17 [INFO] train episode 45475: reward = -76.52, steps = 30 08:22:19 [INFO] train episode 45476: reward = -74.67, steps = 24 08:22:21 [INFO] train episode 45477: reward = -53.12, steps = 21 08:22:23 [INFO] train episode 45478: reward = -102.49, steps = 23 08:22:26 [INFO] train episode 45479: reward = -78.20, steps = 28 08:22:28 [INFO] train episode 45480: reward = -52.63, steps = 22 08:22:30 [INFO] train episode 45481: reward = -50.15, steps = 28 08:22:32 [INFO] train episode 45482: reward = -39.87, steps = 23 08:22:34 [INFO] train episode 45483: reward = -44.73, steps = 24 08:22:36 [INFO] train episode 45484: reward = -56.16, steps = 25 08:22:39 [INFO] train episode 45485: reward = -67.69, steps = 30 08:22:42 [INFO] train episode 45486: reward = -60.82, steps = 38 08:22:44 [INFO] train episode 45487: reward = -69.83, steps = 23 08:22:46 [INFO] train episode 45488: reward = -58.91, steps = 19 08:22:48 [INFO] train episode 45489: reward = -45.43, steps = 24 08:22:50 [INFO] train episode 45490: reward = -53.08, steps = 21 08:22:52 [INFO] train episode 45491: reward = -46.08, steps = 25 08:22:56 [INFO] train episode 45492: reward = -96.53, steps = 45 08:22:58 [INFO] train episode 45493: reward = -43.55, steps = 24 08:23:00 [INFO] train episode 45494: reward = -50.25, steps = 20 08:23:02 [INFO] train episode 45495: reward = -45.22, steps = 22 08:23:04 [INFO] train episode 45496: reward = -73.14, steps = 28 08:23:07 [INFO] train episode 45497: reward = -59.36, steps = 30 08:23:11 [INFO] train episode 45498: reward = -93.91, steps = 44 08:23:13 [INFO] train episode 45499: reward = -47.14, steps = 21 08:23:15 [INFO] train episode 45500: reward = -56.12, steps = 24 08:23:17 [INFO] train episode 45501: reward = -80.24, steps = 20 08:23:20 [INFO] train episode 45502: reward = -82.46, steps = 29 08:23:21 [INFO] train episode 45503: reward = -51.48, steps = 20 08:23:24 [INFO] train episode 45504: reward = -56.68, steps = 26 08:23:26 [INFO] train episode 45505: reward = -54.15, steps = 29 08:23:28 [INFO] train episode 45506: reward = -61.07, steps = 19 08:23:31 [INFO] train episode 45507: reward = -49.10, steps = 30 08:23:32 [INFO] train episode 45508: reward = -45.63, steps = 18 08:23:35 [INFO] train episode 45509: reward = -88.02, steps = 34 08:23:37 [INFO] train episode 45510: reward = -57.09, steps = 20 08:23:39 [INFO] train episode 45511: reward = -64.39, steps = 24 08:23:41 [INFO] train episode 45512: reward = -42.54, steps = 20 08:23:44 [INFO] train episode 45513: reward = -42.43, steps = 34 08:23:46 [INFO] train episode 45514: reward = -62.92, steps = 22 08:23:49 [INFO] train episode 45515: reward = -91.32, steps = 30 08:23:50 [INFO] train episode 45516: reward = -55.63, steps = 20 08:23:53 [INFO] train episode 45517: reward = -56.40, steps = 34 08:23:56 [INFO] train episode 45518: reward = -80.15, steps = 30 08:23:58 [INFO] train episode 45519: reward = -49.83, steps = 23 08:24:00 [INFO] train episode 45520: reward = -86.59, steps = 19 08:24:03 [INFO] train episode 45521: reward = -103.95, steps = 40 08:24:05 [INFO] train episode 45522: reward = -38.89, steps = 20 08:24:07 [INFO] train episode 45523: reward = -36.43, steps = 30 08:24:09 [INFO] train episode 45524: reward = -65.86, steps = 19 08:24:11 [INFO] train episode 45525: reward = -58.96, steps = 29 08:24:14 [INFO] train episode 45526: reward = -34.48, steps = 21 08:24:16 [INFO] train episode 45527: reward = -59.55, steps = 22 08:24:18 [INFO] train episode 45528: reward = -66.42, steps = 28 08:24:20 [INFO] train episode 45529: reward = -50.69, steps = 21 08:24:22 [INFO] train episode 45530: reward = -62.80, steps = 28 08:24:24 [INFO] train episode 45531: reward = -66.73, steps = 22 08:24:26 [INFO] train episode 45532: reward = -43.90, steps = 22 08:24:30 [INFO] train episode 45533: reward = -61.44, steps = 39 08:24:33 [INFO] train episode 45534: reward = -77.14, steps = 39 08:24:34 [INFO] train episode 45535: reward = -58.28, steps = 18 08:24:37 [INFO] train episode 45536: reward = -52.37, steps = 28 08:24:39 [INFO] train episode 45537: reward = -52.21, steps = 27 08:24:43 [INFO] train episode 45538: reward = -100.48, steps = 41 08:24:45 [INFO] train episode 45539: reward = -44.32, steps = 23 08:24:48 [INFO] train episode 45540: reward = -60.54, steps = 37 08:24:50 [INFO] train episode 45541: reward = -88.05, steps = 20 08:24:53 [INFO] train episode 45542: reward = -74.64, steps = 37 08:24:56 [INFO] train episode 45543: reward = -96.95, steps = 34 08:24:59 [INFO] train episode 45544: reward = -23.69, steps = 34 08:25:02 [INFO] train episode 45545: reward = -71.03, steps = 31 08:25:04 [INFO] train episode 45546: reward = -64.23, steps = 27 08:25:07 [INFO] train episode 45547: reward = -67.13, steps = 38 08:25:09 [INFO] train episode 45548: reward = -55.51, steps = 20 08:25:11 [INFO] train episode 45549: reward = -60.50, steps = 25 08:25:13 [INFO] train episode 45550: reward = -40.54, steps = 24 08:25:15 [INFO] train episode 45551: reward = -61.39, steps = 21 08:25:18 [INFO] train episode 45552: reward = -65.08, steps = 24 08:25:20 [INFO] train episode 45553: reward = -70.88, steps = 28 08:25:23 [INFO] train episode 45554: reward = -60.29, steps = 31 08:25:25 [INFO] train episode 45555: reward = -49.02, steps = 21 08:25:27 [INFO] train episode 45556: reward = -46.67, steps = 22 08:25:28 [INFO] train episode 45557: reward = -53.74, steps = 20 08:25:30 [INFO] train episode 45558: reward = -40.04, steps = 23 08:25:33 [INFO] train episode 45559: reward = -86.46, steps = 25 08:25:35 [INFO] train episode 45560: reward = -55.60, steps = 26 08:25:37 [INFO] train episode 45561: reward = -44.46, steps = 21 08:25:40 [INFO] train episode 45562: reward = -78.89, steps = 37 08:25:42 [INFO] train episode 45563: reward = -53.81, steps = 22 08:25:44 [INFO] train episode 45564: reward = -41.91, steps = 20 08:25:47 [INFO] train episode 45565: reward = -97.25, steps = 36 08:25:49 [INFO] train episode 45566: reward = -51.06, steps = 19 08:25:50 [INFO] train episode 45567: reward = -51.52, steps = 21 08:25:54 [INFO] train episode 45568: reward = -37.06, steps = 39 08:25:55 [INFO] train episode 45569: reward = -44.85, steps = 19 08:25:57 [INFO] train episode 45570: reward = -75.14, steps = 22 08:25:59 [INFO] train episode 45571: reward = -67.74, steps = 24 08:26:01 [INFO] train episode 45572: reward = -54.98, steps = 20 08:26:04 [INFO] train episode 45573: reward = -49.30, steps = 24 08:26:07 [INFO] train episode 45574: reward = -55.09, steps = 37 08:26:09 [INFO] train episode 45575: reward = -93.80, steps = 26 08:26:13 [INFO] train episode 45576: reward = -91.54, steps = 44 08:26:15 [INFO] train episode 45577: reward = -49.35, steps = 20 08:26:17 [INFO] train episode 45578: reward = -56.22, steps = 24 08:26:19 [INFO] train episode 45579: reward = -52.76, steps = 18 08:26:21 [INFO] train episode 45580: reward = -86.19, steps = 28 08:26:23 [INFO] train episode 45581: reward = -59.46, steps = 21 08:26:27 [INFO] train episode 45582: reward = -63.74, steps = 41 08:26:29 [INFO] train episode 45583: reward = -51.09, steps = 29 08:26:32 [INFO] train episode 45584: reward = -49.94, steps = 30 08:26:34 [INFO] train episode 45585: reward = -45.31, steps = 27 08:26:36 [INFO] train episode 45586: reward = -50.69, steps = 21 08:26:39 [INFO] train episode 45587: reward = -65.81, steps = 27 08:26:41 [INFO] train episode 45588: reward = -67.70, steps = 25 08:26:42 [INFO] train episode 45589: reward = -57.33, steps = 21 08:26:45 [INFO] train episode 45590: reward = -73.18, steps = 32 08:26:47 [INFO] train episode 45591: reward = -74.50, steps = 20 08:26:49 [INFO] train episode 45592: reward = -38.38, steps = 20 08:26:51 [INFO] train episode 45593: reward = -43.09, steps = 25 08:26:53 [INFO] train episode 45594: reward = -53.47, steps = 22 08:26:56 [INFO] train episode 45595: reward = -52.42, steps = 33 08:26:58 [INFO] train episode 45596: reward = -82.58, steps = 27 08:27:00 [INFO] train episode 45597: reward = -72.31, steps = 21 08:27:02 [INFO] train episode 45598: reward = -66.79, steps = 26 08:27:04 [INFO] train episode 45599: reward = -46.95, steps = 20 08:27:05 [INFO] train episode 45600: reward = -100.11, steps = 19 08:27:08 [INFO] train episode 45601: reward = -77.69, steps = 29 08:27:10 [INFO] train episode 45602: reward = -52.59, steps = 21 08:27:13 [INFO] train episode 45603: reward = -65.34, steps = 32 08:27:15 [INFO] train episode 45604: reward = -38.59, steps = 27 08:27:18 [INFO] train episode 45605: reward = -87.66, steps = 35 08:27:20 [INFO] train episode 45606: reward = -68.85, steps = 21 08:27:22 [INFO] train episode 45607: reward = -83.29, steps = 29 08:27:25 [INFO] train episode 45608: reward = -39.36, steps = 20 08:27:26 [INFO] train episode 45609: reward = -66.76, steps = 18 08:27:28 [INFO] train episode 45610: reward = -50.19, steps = 22 08:27:31 [INFO] train episode 45611: reward = -64.91, steps = 32 08:27:32 [INFO] train episode 45612: reward = -59.45, steps = 19 08:27:34 [INFO] train episode 45613: reward = -59.80, steps = 26 08:27:36 [INFO] train episode 45614: reward = -39.70, steps = 22 08:27:39 [INFO] train episode 45615: reward = -45.46, steps = 23 08:27:41 [INFO] train episode 45616: reward = -34.68, steps = 29 08:27:45 [INFO] train episode 45617: reward = -60.44, steps = 43 08:27:47 [INFO] train episode 45618: reward = -51.02, steps = 22 08:27:49 [INFO] train episode 45619: reward = -83.49, steps = 24 08:27:51 [INFO] train episode 45620: reward = -59.35, steps = 24 08:27:54 [INFO] train episode 45621: reward = -71.90, steps = 34 08:27:56 [INFO] train episode 45622: reward = -66.92, steps = 20 08:27:58 [INFO] train episode 45623: reward = -55.43, steps = 27 08:28:00 [INFO] train episode 45624: reward = -56.13, steps = 19 08:28:02 [INFO] train episode 45625: reward = -57.57, steps = 21 08:28:04 [INFO] train episode 45626: reward = -75.87, steps = 25 08:28:06 [INFO] train episode 45627: reward = -39.17, steps = 22 08:28:07 [INFO] train episode 45628: reward = -48.92, steps = 22 08:28:09 [INFO] train episode 45629: reward = -71.51, steps = 20 08:28:11 [INFO] train episode 45630: reward = -31.23, steps = 23 08:28:13 [INFO] train episode 45631: reward = -32.82, steps = 20 08:28:15 [INFO] train episode 45632: reward = -60.45, steps = 24 08:28:17 [INFO] train episode 45633: reward = -40.24, steps = 25 08:28:19 [INFO] train episode 45634: reward = -71.49, steps = 19 08:28:21 [INFO] train episode 45635: reward = -45.59, steps = 25 08:28:23 [INFO] train episode 45636: reward = -60.91, steps = 20 08:28:25 [INFO] train episode 45637: reward = -65.70, steps = 29 08:28:27 [INFO] train episode 45638: reward = -44.41, steps = 22 08:28:30 [INFO] train episode 45639: reward = -71.42, steps = 28 08:28:32 [INFO] train episode 45640: reward = -69.84, steps = 24 08:28:34 [INFO] train episode 45641: reward = -80.50, steps = 31 08:28:36 [INFO] train episode 45642: reward = -79.17, steps = 19 08:28:39 [INFO] train episode 45643: reward = -64.84, steps = 27 08:28:40 [INFO] train episode 45644: reward = -36.83, steps = 20 08:28:42 [INFO] train episode 45645: reward = -40.10, steps = 20 08:28:44 [INFO] train episode 45646: reward = -45.18, steps = 21 08:28:47 [INFO] train episode 45647: reward = -49.28, steps = 26 08:28:48 [INFO] train episode 45648: reward = -31.36, steps = 21 08:28:51 [INFO] train episode 45649: reward = -57.70, steps = 31 08:28:53 [INFO] train episode 45650: reward = -51.24, steps = 20 08:28:55 [INFO] train episode 45651: reward = -41.63, steps = 27 08:28:57 [INFO] train episode 45652: reward = -48.68, steps = 19 08:28:59 [INFO] train episode 45653: reward = -90.54, steps = 22 08:29:01 [INFO] train episode 45654: reward = -74.37, steps = 23 08:29:04 [INFO] train episode 45655: reward = -46.37, steps = 20 08:29:06 [INFO] train episode 45656: reward = -55.04, steps = 21 08:29:08 [INFO] train episode 45657: reward = -45.03, steps = 22 08:29:09 [INFO] train episode 45658: reward = -62.33, steps = 21 08:29:12 [INFO] train episode 45659: reward = -81.22, steps = 27 08:29:14 [INFO] train episode 45660: reward = -65.32, steps = 25 08:29:16 [INFO] train episode 45661: reward = -31.23, steps = 19 08:29:18 [INFO] train episode 45662: reward = -59.63, steps = 22 08:29:20 [INFO] train episode 45663: reward = -49.04, steps = 31 08:29:22 [INFO] train episode 45664: reward = -60.07, steps = 24 08:29:25 [INFO] train episode 45665: reward = -88.51, steps = 29 08:29:28 [INFO] train episode 45666: reward = -76.19, steps = 32 08:29:30 [INFO] train episode 45667: reward = -84.23, steps = 23 08:29:32 [INFO] train episode 45668: reward = -43.38, steps = 21 08:29:34 [INFO] train episode 45669: reward = -64.29, steps = 25 08:29:36 [INFO] train episode 45670: reward = -53.95, steps = 20 08:29:38 [INFO] train episode 45671: reward = -74.14, steps = 24 08:29:39 [INFO] train episode 45672: reward = -50.99, steps = 21 08:29:41 [INFO] train episode 45673: reward = -50.10, steps = 20 08:29:44 [INFO] train episode 45674: reward = -76.09, steps = 29 08:29:47 [INFO] train episode 45675: reward = -69.13, steps = 32 08:29:49 [INFO] train episode 45676: reward = -47.47, steps = 22 08:29:51 [INFO] train episode 45677: reward = -78.66, steps = 33 08:29:54 [INFO] train episode 45678: reward = -49.17, steps = 32 08:29:56 [INFO] train episode 45679: reward = -41.53, steps = 21 08:29:58 [INFO] train episode 45680: reward = -30.02, steps = 24 08:30:00 [INFO] train episode 45681: reward = -40.93, steps = 26 08:30:03 [INFO] train episode 45682: reward = -60.69, steps = 21 08:30:05 [INFO] train episode 45683: reward = -102.49, steps = 27 08:30:07 [INFO] train episode 45684: reward = -56.49, steps = 20 08:30:09 [INFO] train episode 45685: reward = -49.27, steps = 25 08:30:10 [INFO] train episode 45686: reward = -61.63, steps = 18 08:30:12 [INFO] train episode 45687: reward = -48.90, steps = 20 08:30:14 [INFO] train episode 45688: reward = -64.29, steps = 28 08:30:17 [INFO] train episode 45689: reward = -47.43, steps = 28 08:30:19 [INFO] train episode 45690: reward = -74.90, steps = 21 08:30:21 [INFO] train episode 45691: reward = -83.96, steps = 22 08:30:23 [INFO] train episode 45692: reward = -53.67, steps = 20 08:30:24 [INFO] train episode 45693: reward = -48.22, steps = 21 08:30:27 [INFO] train episode 45694: reward = -41.21, steps = 27 08:30:29 [INFO] train episode 45695: reward = -48.44, steps = 23 08:30:30 [INFO] train episode 45696: reward = -43.59, steps = 21 08:30:32 [INFO] train episode 45697: reward = -55.20, steps = 21 08:30:35 [INFO] train episode 45698: reward = -62.52, steps = 23 08:30:37 [INFO] train episode 45699: reward = -61.81, steps = 24 08:30:39 [INFO] train episode 45700: reward = -84.76, steps = 31 08:30:41 [INFO] train episode 45701: reward = -48.81, steps = 19 08:30:43 [INFO] train episode 45702: reward = -67.35, steps = 21 08:30:45 [INFO] train episode 45703: reward = -33.49, steps = 26 08:30:47 [INFO] train episode 45704: reward = -71.74, steps = 27 08:30:49 [INFO] train episode 45705: reward = -50.65, steps = 21 08:30:51 [INFO] train episode 45706: reward = -63.78, steps = 21 08:30:54 [INFO] train episode 45707: reward = -34.24, steps = 33 08:30:56 [INFO] train episode 45708: reward = -66.11, steps = 23 08:30:58 [INFO] train episode 45709: reward = -45.07, steps = 20 08:31:02 [INFO] train episode 45710: reward = -100.48, steps = 42 08:31:04 [INFO] train episode 45711: reward = -82.71, steps = 28 08:31:07 [INFO] train episode 45712: reward = -73.43, steps = 27 08:31:08 [INFO] train episode 45713: reward = -84.16, steps = 21 08:31:11 [INFO] train episode 45714: reward = -83.89, steps = 34 08:31:13 [INFO] train episode 45715: reward = -53.51, steps = 20 08:31:17 [INFO] train episode 45716: reward = -49.52, steps = 45 08:31:19 [INFO] train episode 45717: reward = -56.60, steps = 28 08:31:21 [INFO] train episode 45718: reward = -62.33, steps = 23 08:31:24 [INFO] train episode 45719: reward = -67.42, steps = 27 08:31:25 [INFO] train episode 45720: reward = -52.98, steps = 19 08:31:27 [INFO] train episode 45721: reward = -48.69, steps = 21 08:31:29 [INFO] train episode 45722: reward = -45.40, steps = 24 08:31:31 [INFO] train episode 45723: reward = -53.69, steps = 19 08:31:33 [INFO] train episode 45724: reward = -97.02, steps = 30 08:31:35 [INFO] train episode 45725: reward = -45.73, steps = 24 08:31:38 [INFO] train episode 45726: reward = -47.51, steps = 25 08:31:40 [INFO] train episode 45727: reward = -53.10, steps = 24 08:31:43 [INFO] train episode 45728: reward = -42.73, steps = 34 08:31:46 [INFO] train episode 45729: reward = -92.19, steps = 38 08:31:48 [INFO] train episode 45730: reward = -71.96, steps = 20 08:31:49 [INFO] train episode 45731: reward = -46.57, steps = 20 08:31:54 [INFO] train episode 45732: reward = -109.39, steps = 45 08:31:56 [INFO] train episode 45733: reward = -55.15, steps = 25 08:31:59 [INFO] train episode 45734: reward = -28.04, steps = 30 08:32:01 [INFO] train episode 45735: reward = -45.41, steps = 27 08:32:04 [INFO] train episode 45736: reward = -32.79, steps = 33 08:32:06 [INFO] train episode 45737: reward = -40.65, steps = 22 08:32:09 [INFO] train episode 45738: reward = -66.42, steps = 31 08:32:11 [INFO] train episode 45739: reward = -65.60, steps = 26 08:32:13 [INFO] train episode 45740: reward = -65.41, steps = 26 08:32:16 [INFO] train episode 45741: reward = -67.66, steps = 29 08:32:19 [INFO] train episode 45742: reward = -39.55, steps = 31 08:32:20 [INFO] train episode 45743: reward = -50.06, steps = 21 08:32:22 [INFO] train episode 45744: reward = -52.34, steps = 22 08:32:25 [INFO] train episode 45745: reward = -48.45, steps = 28 08:32:27 [INFO] train episode 45746: reward = -56.74, steps = 21 08:32:29 [INFO] train episode 45747: reward = -45.53, steps = 28 08:32:31 [INFO] train episode 45748: reward = -49.87, steps = 28 08:32:34 [INFO] train episode 45749: reward = -71.72, steps = 25 08:32:36 [INFO] train episode 45750: reward = -53.01, steps = 21 08:32:38 [INFO] train episode 45751: reward = -51.42, steps = 24 08:32:41 [INFO] train episode 45752: reward = -37.58, steps = 30 08:32:42 [INFO] train episode 45753: reward = -52.72, steps = 20 08:32:44 [INFO] train episode 45754: reward = -40.82, steps = 22 08:32:46 [INFO] train episode 45755: reward = -54.72, steps = 21 08:32:48 [INFO] train episode 45756: reward = -48.20, steps = 22 08:32:50 [INFO] train episode 45757: reward = -52.02, steps = 19 08:32:52 [INFO] train episode 45758: reward = -35.14, steps = 23 08:32:54 [INFO] train episode 45759: reward = -79.04, steps = 23 08:32:56 [INFO] train episode 45760: reward = -61.54, steps = 23 08:33:00 [INFO] train episode 45761: reward = -48.85, steps = 46 08:33:02 [INFO] train episode 45762: reward = -65.31, steps = 27 08:33:05 [INFO] train episode 45763: reward = -36.51, steps = 31 08:33:07 [INFO] train episode 45764: reward = -73.15, steps = 21 08:33:09 [INFO] train episode 45765: reward = -52.33, steps = 24 08:33:11 [INFO] train episode 45766: reward = -47.31, steps = 21 08:33:14 [INFO] train episode 45767: reward = -52.68, steps = 31 08:33:16 [INFO] train episode 45768: reward = -55.33, steps = 22 08:33:19 [INFO] train episode 45769: reward = -85.24, steps = 36 08:33:21 [INFO] train episode 45770: reward = -57.72, steps = 22 08:33:23 [INFO] train episode 45771: reward = -93.37, steps = 27 08:33:26 [INFO] train episode 45772: reward = -79.04, steps = 36 08:33:30 [INFO] train episode 45773: reward = -59.11, steps = 40 08:33:33 [INFO] train episode 45774: reward = -58.76, steps = 37 08:33:35 [INFO] train episode 45775: reward = -90.47, steps = 28 08:33:37 [INFO] train episode 45776: reward = -71.37, steps = 26 08:33:39 [INFO] train episode 45777: reward = -81.03, steps = 24 08:33:41 [INFO] train episode 45778: reward = -64.41, steps = 21 08:33:45 [INFO] train episode 45779: reward = -46.25, steps = 36 08:33:47 [INFO] train episode 45780: reward = -70.96, steps = 24 08:33:48 [INFO] train episode 45781: reward = -52.79, steps = 20 08:33:50 [INFO] train episode 45782: reward = -58.49, steps = 22 08:33:52 [INFO] train episode 45783: reward = -81.76, steps = 24 08:33:54 [INFO] train episode 45784: reward = -68.62, steps = 21 08:33:56 [INFO] train episode 45785: reward = -60.58, steps = 24 08:33:58 [INFO] train episode 45786: reward = -72.15, steps = 25 08:34:01 [INFO] train episode 45787: reward = -46.20, steps = 21 08:34:03 [INFO] train episode 45788: reward = -62.12, steps = 28 08:34:05 [INFO] train episode 45789: reward = -58.54, steps = 26 08:34:07 [INFO] train episode 45790: reward = -85.42, steps = 25 08:34:10 [INFO] train episode 45791: reward = -47.65, steps = 32 08:34:12 [INFO] train episode 45792: reward = -54.74, steps = 22 08:34:14 [INFO] train episode 45793: reward = -40.31, steps = 21 08:34:16 [INFO] train episode 45794: reward = -41.56, steps = 22 08:34:18 [INFO] train episode 45795: reward = -48.33, steps = 22 08:34:20 [INFO] train episode 45796: reward = -72.55, steps = 25 08:34:23 [INFO] train episode 45797: reward = -37.94, steps = 33 08:34:24 [INFO] train episode 45798: reward = -42.71, steps = 21 08:34:27 [INFO] train episode 45799: reward = -59.84, steps = 27 08:34:29 [INFO] train episode 45800: reward = -69.68, steps = 23 08:34:31 [INFO] train episode 45801: reward = -45.31, steps = 24 08:34:34 [INFO] train episode 45802: reward = -79.68, steps = 30 08:34:36 [INFO] train episode 45803: reward = -66.93, steps = 30 08:34:39 [INFO] train episode 45804: reward = -42.95, steps = 30 08:34:41 [INFO] train episode 45805: reward = -82.48, steps = 31 08:34:45 [INFO] train episode 45806: reward = -43.82, steps = 37 08:34:48 [INFO] train episode 45807: reward = -42.58, steps = 26 08:34:51 [INFO] train episode 45808: reward = -80.32, steps = 39 08:34:54 [INFO] train episode 45809: reward = -46.68, steps = 30 08:34:56 [INFO] train episode 45810: reward = -53.59, steps = 25 08:34:58 [INFO] train episode 45811: reward = -35.19, steps = 20 08:34:59 [INFO] train episode 45812: reward = -67.81, steps = 19 08:35:02 [INFO] train episode 45813: reward = -65.65, steps = 28 08:35:04 [INFO] train episode 45814: reward = -51.32, steps = 27 08:35:07 [INFO] train episode 45815: reward = -64.80, steps = 30 08:35:10 [INFO] train episode 45816: reward = -40.62, steps = 41 08:35:13 [INFO] train episode 45817: reward = -54.56, steps = 30 08:35:15 [INFO] train episode 45818: reward = -90.09, steps = 21 08:35:19 [INFO] train episode 45819: reward = -130.41, steps = 50 08:35:21 [INFO] train episode 45820: reward = -40.74, steps = 20 08:35:23 [INFO] train episode 45821: reward = -46.67, steps = 23 08:35:25 [INFO] train episode 45822: reward = -44.44, steps = 22 08:35:27 [INFO] train episode 45823: reward = -45.55, steps = 22 08:35:29 [INFO] train episode 45824: reward = -69.66, steps = 24 08:35:32 [INFO] train episode 45825: reward = -68.53, steps = 31 08:35:34 [INFO] train episode 45826: reward = -18.71, steps = 28 08:35:37 [INFO] train episode 45827: reward = -65.39, steps = 31 08:35:38 [INFO] train episode 45828: reward = -73.73, steps = 18 08:35:41 [INFO] train episode 45829: reward = -48.24, steps = 29 08:35:43 [INFO] train episode 45830: reward = -74.87, steps = 22 08:35:46 [INFO] train episode 45831: reward = -102.90, steps = 33 08:35:48 [INFO] train episode 45832: reward = -89.11, steps = 31 08:35:51 [INFO] train episode 45833: reward = -55.83, steps = 26 08:35:53 [INFO] train episode 45834: reward = -72.25, steps = 30 08:35:55 [INFO] train episode 45835: reward = -130.04, steps = 21 08:35:57 [INFO] train episode 45836: reward = -31.84, steps = 20 08:36:00 [INFO] train episode 45837: reward = -70.13, steps = 33 08:36:01 [INFO] train episode 45838: reward = -51.91, steps = 20 08:36:04 [INFO] train episode 45839: reward = -40.90, steps = 34 08:36:07 [INFO] train episode 45840: reward = -81.65, steps = 26 08:36:08 [INFO] train episode 45841: reward = -87.25, steps = 19 08:36:11 [INFO] train episode 45842: reward = -52.41, steps = 25 08:36:12 [INFO] train episode 45843: reward = -36.34, steps = 21 08:36:14 [INFO] train episode 45844: reward = -58.68, steps = 20 08:36:16 [INFO] train episode 45845: reward = -67.68, steps = 21 08:36:19 [INFO] train episode 45846: reward = -46.26, steps = 36 08:36:21 [INFO] train episode 45847: reward = -69.09, steps = 26 08:36:24 [INFO] train episode 45848: reward = -72.83, steps = 35 08:36:27 [INFO] train episode 45849: reward = -37.76, steps = 33 08:36:29 [INFO] train episode 45850: reward = -46.24, steps = 22 08:36:31 [INFO] train episode 45851: reward = -53.68, steps = 27 08:36:34 [INFO] train episode 45852: reward = -45.85, steps = 31 08:36:37 [INFO] train episode 45853: reward = -44.49, steps = 28 08:36:40 [INFO] train episode 45854: reward = -60.78, steps = 42 08:36:42 [INFO] train episode 45855: reward = -68.97, steps = 20 08:36:44 [INFO] train episode 45856: reward = -44.80, steps = 24 08:36:47 [INFO] train episode 45857: reward = -56.26, steps = 26 08:36:49 [INFO] train episode 45858: reward = -93.00, steps = 35 08:36:52 [INFO] train episode 45859: reward = -81.38, steps = 34 08:36:55 [INFO] train episode 45860: reward = -63.92, steps = 26 08:36:57 [INFO] train episode 45861: reward = -111.48, steps = 29 08:36:59 [INFO] train episode 45862: reward = -53.22, steps = 20 08:37:01 [INFO] train episode 45863: reward = -41.14, steps = 25 08:37:04 [INFO] train episode 45864: reward = -65.85, steps = 29 08:37:06 [INFO] train episode 45865: reward = -61.33, steps = 28 08:37:08 [INFO] train episode 45866: reward = -68.18, steps = 22 08:37:11 [INFO] train episode 45867: reward = -51.81, steps = 25 08:37:12 [INFO] train episode 45868: reward = -57.00, steps = 21 08:37:14 [INFO] train episode 45869: reward = -57.76, steps = 20 08:37:17 [INFO] train episode 45870: reward = -47.96, steps = 36 08:37:19 [INFO] train episode 45871: reward = -45.94, steps = 22 08:37:21 [INFO] train episode 45872: reward = -71.55, steps = 20 08:37:24 [INFO] train episode 45873: reward = -103.25, steps = 34 08:37:26 [INFO] train episode 45874: reward = -44.10, steps = 20 08:37:28 [INFO] train episode 45875: reward = -59.57, steps = 25 08:37:30 [INFO] train episode 45876: reward = -61.84, steps = 30 08:37:32 [INFO] train episode 45877: reward = -53.91, steps = 24 08:37:35 [INFO] train episode 45878: reward = -68.13, steps = 22 08:37:38 [INFO] train episode 45879: reward = -35.43, steps = 41 08:37:40 [INFO] train episode 45880: reward = -56.40, steps = 23 08:37:44 [INFO] train episode 45881: reward = -63.67, steps = 37 08:37:46 [INFO] train episode 45882: reward = -36.25, steps = 24 08:37:48 [INFO] train episode 45883: reward = -99.69, steps = 24 08:37:49 [INFO] train episode 45884: reward = -56.57, steps = 19 08:37:51 [INFO] train episode 45885: reward = -54.48, steps = 20 08:37:53 [INFO] train episode 45886: reward = -51.51, steps = 24 08:37:55 [INFO] train episode 45887: reward = -59.04, steps = 18 08:37:57 [INFO] train episode 45888: reward = -54.77, steps = 20 08:37:59 [INFO] train episode 45889: reward = -40.98, steps = 22 08:38:01 [INFO] train episode 45890: reward = -41.86, steps = 30 08:38:04 [INFO] train episode 45891: reward = -62.04, steps = 31 08:38:07 [INFO] train episode 45892: reward = -32.32, steps = 31 08:38:09 [INFO] train episode 45893: reward = -43.75, steps = 23 08:38:10 [INFO] train episode 45894: reward = -64.97, steps = 20 08:38:12 [INFO] train episode 45895: reward = -40.68, steps = 20 08:38:15 [INFO] train episode 45896: reward = -38.79, steps = 30 08:38:18 [INFO] train episode 45897: reward = -27.40, steps = 33 08:38:20 [INFO] train episode 45898: reward = -63.61, steps = 30 08:38:23 [INFO] train episode 45899: reward = -67.90, steps = 29 08:38:25 [INFO] train episode 45900: reward = -53.72, steps = 26 08:38:26 [INFO] train episode 45901: reward = -54.94, steps = 21 08:38:28 [INFO] train episode 45902: reward = -43.85, steps = 21 08:38:31 [INFO] train episode 45903: reward = -57.53, steps = 23 08:38:33 [INFO] train episode 45904: reward = -58.40, steps = 25 08:38:35 [INFO] train episode 45905: reward = -50.24, steps = 21 08:38:37 [INFO] train episode 45906: reward = -56.28, steps = 27 08:38:39 [INFO] train episode 45907: reward = -69.92, steps = 23 08:38:41 [INFO] train episode 45908: reward = -41.63, steps = 25 08:38:43 [INFO] train episode 45909: reward = -71.38, steps = 26 08:38:45 [INFO] train episode 45910: reward = -72.73, steps = 16 08:38:49 [INFO] train episode 45911: reward = -45.81, steps = 40 08:38:50 [INFO] train episode 45912: reward = -56.06, steps = 20 08:38:53 [INFO] train episode 45913: reward = -44.75, steps = 25 08:38:54 [INFO] train episode 45914: reward = -61.07, steps = 20 08:38:56 [INFO] train episode 45915: reward = -57.57, steps = 21 08:38:58 [INFO] train episode 45916: reward = -55.58, steps = 20 08:39:00 [INFO] train episode 45917: reward = -53.76, steps = 25 08:39:02 [INFO] train episode 45918: reward = -54.83, steps = 24 08:39:04 [INFO] train episode 45919: reward = -51.98, steps = 24 08:39:06 [INFO] train episode 45920: reward = -43.65, steps = 24 08:39:08 [INFO] train episode 45921: reward = -37.87, steps = 21 08:39:10 [INFO] train episode 45922: reward = -60.22, steps = 20 08:39:12 [INFO] train episode 45923: reward = -48.16, steps = 29 08:39:15 [INFO] train episode 45924: reward = -79.22, steps = 24 08:39:18 [INFO] train episode 45925: reward = -80.05, steps = 30 08:39:20 [INFO] train episode 45926: reward = -69.20, steps = 33 08:39:23 [INFO] train episode 45927: reward = -87.57, steps = 27 08:39:24 [INFO] train episode 45928: reward = -82.34, steps = 20 08:39:28 [INFO] train episode 45929: reward = -81.50, steps = 44 08:39:30 [INFO] train episode 45930: reward = -71.58, steps = 28 08:39:33 [INFO] train episode 45931: reward = -51.32, steps = 29 08:39:35 [INFO] train episode 45932: reward = -52.85, steps = 24 08:39:39 [INFO] train episode 45933: reward = -102.46, steps = 39 08:39:41 [INFO] train episode 45934: reward = -73.45, steps = 26 08:39:43 [INFO] train episode 45935: reward = -49.82, steps = 20 08:39:44 [INFO] train episode 45936: reward = -53.62, steps = 20 08:39:47 [INFO] train episode 45937: reward = -81.84, steps = 31 08:39:49 [INFO] train episode 45938: reward = -46.30, steps = 26 08:39:51 [INFO] train episode 45939: reward = -41.59, steps = 21 08:39:54 [INFO] train episode 45940: reward = -83.50, steps = 29 08:39:56 [INFO] train episode 45941: reward = -43.41, steps = 22 08:39:59 [INFO] train episode 45942: reward = -81.61, steps = 37 08:40:03 [INFO] train episode 45943: reward = -48.24, steps = 50 08:40:05 [INFO] train episode 45944: reward = -65.28, steps = 25 08:40:07 [INFO] train episode 45945: reward = -60.96, steps = 21 08:40:09 [INFO] train episode 45946: reward = -50.53, steps = 25 08:40:11 [INFO] train episode 45947: reward = -54.02, steps = 20 08:40:13 [INFO] train episode 45948: reward = -72.20, steps = 26 08:40:16 [INFO] train episode 45949: reward = -78.11, steps = 33 08:40:18 [INFO] train episode 45950: reward = -72.77, steps = 20 08:40:20 [INFO] train episode 45951: reward = -68.21, steps = 20 08:40:22 [INFO] train episode 45952: reward = -67.13, steps = 25 08:40:25 [INFO] train episode 45953: reward = -78.81, steps = 23 08:40:27 [INFO] train episode 45954: reward = -46.68, steps = 24 08:40:29 [INFO] train episode 45955: reward = -63.67, steps = 30 08:40:31 [INFO] train episode 45956: reward = -60.34, steps = 20 08:40:33 [INFO] train episode 45957: reward = -60.73, steps = 22 08:40:35 [INFO] train episode 45958: reward = -41.62, steps = 27 08:40:38 [INFO] train episode 45959: reward = -82.84, steps = 22 08:40:41 [INFO] train episode 45960: reward = -66.66, steps = 41 08:40:44 [INFO] train episode 45961: reward = -85.33, steps = 37 08:40:48 [INFO] train episode 45962: reward = -63.17, steps = 39 08:40:49 [INFO] train episode 45963: reward = -33.68, steps = 20 08:40:51 [INFO] train episode 45964: reward = -63.07, steps = 20 08:40:55 [INFO] train episode 45965: reward = -48.43, steps = 45 08:40:58 [INFO] train episode 45966: reward = -61.30, steps = 27 08:41:00 [INFO] train episode 45967: reward = -60.19, steps = 27 08:41:02 [INFO] train episode 45968: reward = -67.84, steps = 28 08:41:04 [INFO] train episode 45969: reward = -36.94, steps = 19 08:41:07 [INFO] train episode 45970: reward = -67.67, steps = 33 08:41:09 [INFO] train episode 45971: reward = -61.07, steps = 26 08:41:11 [INFO] train episode 45972: reward = -26.02, steps = 21 08:41:14 [INFO] train episode 45973: reward = -83.51, steps = 32 08:41:16 [INFO] train episode 45974: reward = -59.30, steps = 22 08:41:18 [INFO] train episode 45975: reward = -56.73, steps = 32 08:41:20 [INFO] train episode 45976: reward = -62.32, steps = 21 08:41:22 [INFO] train episode 45977: reward = -55.51, steps = 23 08:41:25 [INFO] train episode 45978: reward = -66.07, steps = 32 08:41:27 [INFO] train episode 45979: reward = -73.84, steps = 21 08:41:29 [INFO] train episode 45980: reward = -41.64, steps = 24 08:41:32 [INFO] train episode 45981: reward = -95.22, steps = 30 08:41:35 [INFO] train episode 45982: reward = -61.24, steps = 38 08:41:37 [INFO] train episode 45983: reward = -63.41, steps = 31 08:41:40 [INFO] train episode 45984: reward = -41.66, steps = 21 08:41:42 [INFO] train episode 45985: reward = -67.20, steps = 33 08:41:45 [INFO] train episode 45986: reward = -33.40, steps = 28 08:41:49 [INFO] train episode 45987: reward = -81.54, steps = 55 08:41:51 [INFO] train episode 45988: reward = -56.58, steps = 24 08:41:53 [INFO] train episode 45989: reward = -60.88, steps = 23 08:41:56 [INFO] train episode 45990: reward = -60.22, steps = 31 08:41:58 [INFO] train episode 45991: reward = -63.96, steps = 25 08:42:01 [INFO] train episode 45992: reward = -62.23, steps = 32 08:42:03 [INFO] train episode 45993: reward = -54.07, steps = 24 08:42:06 [INFO] train episode 45994: reward = -48.18, steps = 34 08:42:08 [INFO] train episode 45995: reward = -59.89, steps = 23 08:42:11 [INFO] train episode 45996: reward = -66.62, steps = 36 08:42:13 [INFO] train episode 45997: reward = -47.65, steps = 22 08:42:15 [INFO] train episode 45998: reward = -59.02, steps = 21 08:42:17 [INFO] train episode 45999: reward = -38.85, steps = 20 08:42:19 [INFO] train episode 46000: reward = -58.14, steps = 20 08:42:21 [INFO] train episode 46001: reward = -43.68, steps = 24 08:42:23 [INFO] train episode 46002: reward = -64.78, steps = 29 08:42:27 [INFO] train episode 46003: reward = -74.03, steps = 39 08:42:29 [INFO] train episode 46004: reward = -87.51, steps = 28 08:42:31 [INFO] train episode 46005: reward = -59.99, steps = 20 08:42:33 [INFO] train episode 46006: reward = -45.54, steps = 23 08:42:35 [INFO] train episode 46007: reward = -67.29, steps = 25 08:42:39 [INFO] train episode 46008: reward = -91.35, steps = 49 08:42:42 [INFO] train episode 46009: reward = -82.51, steps = 34 08:42:45 [INFO] train episode 46010: reward = -46.61, steps = 24 08:42:47 [INFO] train episode 46011: reward = -47.36, steps = 24 08:42:49 [INFO] train episode 46012: reward = -63.42, steps = 23 08:42:51 [INFO] train episode 46013: reward = -46.36, steps = 23 08:42:53 [INFO] train episode 46014: reward = -40.20, steps = 21 08:42:55 [INFO] train episode 46015: reward = -102.90, steps = 27 08:42:57 [INFO] train episode 46016: reward = -47.85, steps = 27 08:43:00 [INFO] train episode 46017: reward = -33.83, steps = 33 08:43:03 [INFO] train episode 46018: reward = -78.77, steps = 32 08:43:05 [INFO] train episode 46019: reward = -48.41, steps = 19 08:43:07 [INFO] train episode 46020: reward = -41.87, steps = 21 08:43:09 [INFO] train episode 46021: reward = -68.62, steps = 35 08:43:12 [INFO] train episode 46022: reward = -70.63, steps = 35 08:43:16 [INFO] train episode 46023: reward = -88.78, steps = 33 08:43:19 [INFO] train episode 46024: reward = -67.24, steps = 31 08:43:21 [INFO] train episode 46025: reward = -42.65, steps = 23 08:43:23 [INFO] train episode 46026: reward = -71.70, steps = 27 08:43:25 [INFO] train episode 46027: reward = -49.71, steps = 22 08:43:27 [INFO] train episode 46028: reward = -65.04, steps = 22 08:43:29 [INFO] train episode 46029: reward = -59.04, steps = 21 08:43:31 [INFO] train episode 46030: reward = -69.00, steps = 26 08:43:33 [INFO] train episode 46031: reward = -40.64, steps = 24 08:43:36 [INFO] train episode 46032: reward = -58.88, steps = 28 08:43:38 [INFO] train episode 46033: reward = -41.41, steps = 26 08:43:40 [INFO] train episode 46034: reward = -51.05, steps = 19 08:43:41 [INFO] train episode 46035: reward = -49.64, steps = 20 08:43:43 [INFO] train episode 46036: reward = -61.86, steps = 23 08:43:45 [INFO] train episode 46037: reward = -48.35, steps = 24 08:43:48 [INFO] train episode 46038: reward = -54.22, steps = 23 08:43:50 [INFO] train episode 46039: reward = -50.07, steps = 33 08:43:54 [INFO] train episode 46040: reward = -76.39, steps = 39 08:43:56 [INFO] train episode 46041: reward = -47.81, steps = 21 08:43:57 [INFO] train episode 46042: reward = -49.31, steps = 20 08:43:59 [INFO] train episode 46043: reward = -34.66, steps = 19 08:44:01 [INFO] train episode 46044: reward = -41.03, steps = 23 08:44:03 [INFO] train episode 46045: reward = -81.48, steps = 21 08:44:05 [INFO] train episode 46046: reward = -69.71, steps = 26 08:44:08 [INFO] train episode 46047: reward = -69.77, steps = 30 08:44:10 [INFO] train episode 46048: reward = -66.70, steps = 22 08:44:12 [INFO] train episode 46049: reward = -51.84, steps = 26 08:44:14 [INFO] train episode 46050: reward = -50.59, steps = 22 08:44:15 [INFO] train episode 46051: reward = -63.51, steps = 19 08:44:19 [INFO] train episode 46052: reward = -64.48, steps = 37 08:44:22 [INFO] train episode 46053: reward = -56.57, steps = 31 08:44:23 [INFO] train episode 46054: reward = -43.61, steps = 20 08:44:26 [INFO] train episode 46055: reward = -91.27, steps = 36 08:44:29 [INFO] train episode 46056: reward = -71.95, steps = 33 08:44:32 [INFO] train episode 46057: reward = -58.45, steps = 28 08:44:34 [INFO] train episode 46058: reward = -42.24, steps = 29 08:44:36 [INFO] train episode 46059: reward = -63.32, steps = 20 08:44:38 [INFO] train episode 46060: reward = -38.08, steps = 21 08:44:41 [INFO] train episode 46061: reward = -71.77, steps = 30 08:44:44 [INFO] train episode 46062: reward = -58.95, steps = 40 08:44:46 [INFO] train episode 46063: reward = -53.83, steps = 20 08:44:49 [INFO] train episode 46064: reward = -84.62, steps = 45 08:44:52 [INFO] train episode 46065: reward = -54.28, steps = 20 08:44:55 [INFO] train episode 46066: reward = -87.84, steps = 44 08:44:58 [INFO] train episode 46067: reward = -66.52, steps = 38 08:45:00 [INFO] train episode 46068: reward = -72.97, steps = 19 08:45:02 [INFO] train episode 46069: reward = -34.64, steps = 20 08:45:03 [INFO] train episode 46070: reward = -48.53, steps = 20 08:45:06 [INFO] train episode 46071: reward = -58.35, steps = 25 08:45:08 [INFO] train episode 46072: reward = -55.64, steps = 24 08:45:11 [INFO] train episode 46073: reward = -91.50, steps = 30 08:45:12 [INFO] train episode 46074: reward = -41.73, steps = 19 08:45:14 [INFO] train episode 46075: reward = -32.08, steps = 24 08:45:16 [INFO] train episode 46076: reward = -95.86, steps = 24 08:45:19 [INFO] train episode 46077: reward = -59.31, steps = 34 08:45:22 [INFO] train episode 46078: reward = -70.35, steps = 25 08:45:24 [INFO] train episode 46079: reward = -65.62, steps = 28 08:45:27 [INFO] train episode 46080: reward = -83.60, steps = 28 08:45:31 [INFO] train episode 46081: reward = -56.05, steps = 47 08:45:33 [INFO] train episode 46082: reward = -41.75, steps = 27 08:45:35 [INFO] train episode 46083: reward = -53.14, steps = 25 08:45:38 [INFO] train episode 46084: reward = -49.65, steps = 26 08:45:40 [INFO] train episode 46085: reward = -68.38, steps = 30 08:45:43 [INFO] train episode 46086: reward = -61.69, steps = 30 08:45:45 [INFO] train episode 46087: reward = -43.40, steps = 29 08:45:48 [INFO] train episode 46088: reward = -77.15, steps = 29 08:45:50 [INFO] train episode 46089: reward = -81.68, steps = 27 08:45:52 [INFO] train episode 46090: reward = -68.41, steps = 20 08:45:54 [INFO] train episode 46091: reward = -61.24, steps = 20 08:45:56 [INFO] train episode 46092: reward = -73.58, steps = 24 08:45:57 [INFO] train episode 46093: reward = -65.14, steps = 19 08:46:00 [INFO] train episode 46094: reward = -63.56, steps = 28 08:46:02 [INFO] train episode 46095: reward = -39.69, steps = 25 08:46:06 [INFO] train episode 46096: reward = -51.48, steps = 34 08:46:08 [INFO] train episode 46097: reward = -81.88, steps = 25 08:46:11 [INFO] train episode 46098: reward = -90.69, steps = 32 08:46:13 [INFO] train episode 46099: reward = -70.31, steps = 33 08:46:16 [INFO] train episode 46100: reward = -50.94, steps = 27 08:46:18 [INFO] train episode 46101: reward = -54.30, steps = 23 08:46:20 [INFO] train episode 46102: reward = -62.83, steps = 24 08:46:23 [INFO] train episode 46103: reward = -59.82, steps = 33 08:46:25 [INFO] train episode 46104: reward = -48.45, steps = 28 08:46:27 [INFO] train episode 46105: reward = -55.86, steps = 23 08:46:30 [INFO] train episode 46106: reward = -98.50, steps = 30 08:46:31 [INFO] train episode 46107: reward = -40.32, steps = 19 08:46:33 [INFO] train episode 46108: reward = -54.76, steps = 20 08:46:35 [INFO] train episode 46109: reward = -62.91, steps = 19 08:46:38 [INFO] train episode 46110: reward = -53.70, steps = 35 08:46:40 [INFO] train episode 46111: reward = -54.74, steps = 22 08:46:43 [INFO] train episode 46112: reward = -67.44, steps = 29 08:46:45 [INFO] train episode 46113: reward = -44.12, steps = 31 08:46:47 [INFO] train episode 46114: reward = -59.54, steps = 24 08:46:50 [INFO] train episode 46115: reward = -57.47, steps = 25 08:46:51 [INFO] train episode 46116: reward = -52.40, steps = 21 08:46:53 [INFO] train episode 46117: reward = -76.60, steps = 21 08:46:55 [INFO] train episode 46118: reward = -27.44, steps = 22 08:46:58 [INFO] train episode 46119: reward = -61.70, steps = 23 08:47:01 [INFO] train episode 46120: reward = -55.88, steps = 40 08:47:03 [INFO] train episode 46121: reward = -87.51, steps = 25 08:47:05 [INFO] train episode 46122: reward = -44.38, steps = 27 08:47:08 [INFO] train episode 46123: reward = -48.59, steps = 33 08:47:10 [INFO] train episode 46124: reward = -58.55, steps = 23 08:47:12 [INFO] train episode 46125: reward = -38.41, steps = 23 08:47:15 [INFO] train episode 46126: reward = -58.98, steps = 25 08:47:17 [INFO] train episode 46127: reward = -42.76, steps = 26 08:47:19 [INFO] train episode 46128: reward = -53.05, steps = 20 08:47:22 [INFO] train episode 46129: reward = -91.77, steps = 40 08:47:25 [INFO] train episode 46130: reward = -65.73, steps = 34 08:47:27 [INFO] train episode 46131: reward = -49.51, steps = 23 08:47:29 [INFO] train episode 46132: reward = -62.02, steps = 20 08:47:31 [INFO] train episode 46133: reward = -36.17, steps = 21 08:47:33 [INFO] train episode 46134: reward = -70.17, steps = 29 08:47:36 [INFO] train episode 46135: reward = -56.78, steps = 32 08:47:38 [INFO] train episode 46136: reward = -35.39, steps = 24 08:47:41 [INFO] train episode 46137: reward = -52.36, steps = 35 08:47:44 [INFO] train episode 46138: reward = -50.73, steps = 31 08:47:47 [INFO] train episode 46139: reward = -58.14, steps = 33 08:47:48 [INFO] train episode 46140: reward = -73.01, steps = 21 08:47:50 [INFO] train episode 46141: reward = -43.29, steps = 19 08:47:54 [INFO] train episode 46142: reward = -74.83, steps = 41 08:47:55 [INFO] train episode 46143: reward = -34.57, steps = 20 08:47:57 [INFO] train episode 46144: reward = -40.52, steps = 24 08:48:00 [INFO] train episode 46145: reward = -51.94, steps = 26 08:48:02 [INFO] train episode 46146: reward = -53.19, steps = 24 08:48:05 [INFO] train episode 46147: reward = -78.05, steps = 31 08:48:08 [INFO] train episode 46148: reward = -48.82, steps = 37 08:48:10 [INFO] train episode 46149: reward = -68.77, steps = 31 08:48:13 [INFO] train episode 46150: reward = -45.41, steps = 28 08:48:15 [INFO] train episode 46151: reward = -35.11, steps = 25 08:48:17 [INFO] train episode 46152: reward = -50.21, steps = 20 08:48:19 [INFO] train episode 46153: reward = -44.45, steps = 20 08:48:22 [INFO] train episode 46154: reward = -69.09, steps = 42 08:48:24 [INFO] train episode 46155: reward = -58.14, steps = 20 08:48:27 [INFO] train episode 46156: reward = -86.01, steps = 30 08:48:29 [INFO] train episode 46157: reward = -62.94, steps = 30 08:48:32 [INFO] train episode 46158: reward = -61.20, steps = 29 08:48:34 [INFO] train episode 46159: reward = -44.43, steps = 28 08:48:36 [INFO] train episode 46160: reward = -50.82, steps = 23 08:48:39 [INFO] train episode 46161: reward = -73.09, steps = 28 08:48:42 [INFO] train episode 46162: reward = -42.60, steps = 36 08:48:44 [INFO] train episode 46163: reward = -98.99, steps = 23 08:48:47 [INFO] train episode 46164: reward = -42.67, steps = 33 08:48:49 [INFO] train episode 46165: reward = -36.53, steps = 20 08:48:51 [INFO] train episode 46166: reward = -58.57, steps = 33 08:48:53 [INFO] train episode 46167: reward = -69.17, steps = 23 08:48:57 [INFO] train episode 46168: reward = -42.18, steps = 31 08:48:59 [INFO] train episode 46169: reward = -92.52, steps = 21 08:49:00 [INFO] train episode 46170: reward = -47.86, steps = 21 08:49:03 [INFO] train episode 46171: reward = -105.54, steps = 27 08:49:05 [INFO] train episode 46172: reward = -39.69, steps = 20 08:49:07 [INFO] train episode 46173: reward = -63.95, steps = 20 08:49:08 [INFO] train episode 46174: reward = -41.66, steps = 22 08:49:11 [INFO] train episode 46175: reward = -74.12, steps = 35 08:49:14 [INFO] train episode 46176: reward = -57.75, steps = 28 08:49:15 [INFO] train episode 46177: reward = -60.68, steps = 20 08:49:17 [INFO] train episode 46178: reward = -37.18, steps = 19 08:49:19 [INFO] train episode 46179: reward = -45.63, steps = 20 08:49:21 [INFO] train episode 46180: reward = -73.79, steps = 24 08:49:24 [INFO] train episode 46181: reward = -88.84, steps = 32 08:49:26 [INFO] train episode 46182: reward = -41.13, steps = 24 08:49:28 [INFO] train episode 46183: reward = -55.01, steps = 20 08:49:30 [INFO] train episode 46184: reward = -33.95, steps = 21 08:49:31 [INFO] train episode 46185: reward = -60.70, steps = 18 08:49:34 [INFO] train episode 46186: reward = -86.02, steps = 29 08:49:36 [INFO] train episode 46187: reward = -53.87, steps = 19 08:49:38 [INFO] train episode 46188: reward = -54.09, steps = 29 08:49:40 [INFO] train episode 46189: reward = -38.21, steps = 20 08:49:42 [INFO] train episode 46190: reward = -46.92, steps = 25 08:49:44 [INFO] train episode 46191: reward = -64.75, steps = 23 08:49:46 [INFO] train episode 46192: reward = -45.86, steps = 22 08:49:48 [INFO] train episode 46193: reward = -60.30, steps = 22 08:49:50 [INFO] train episode 46194: reward = -60.42, steps = 22 08:49:54 [INFO] train episode 46195: reward = -115.88, steps = 43 08:49:56 [INFO] train episode 46196: reward = -54.31, steps = 34 08:49:58 [INFO] train episode 46197: reward = -50.92, steps = 21 08:50:00 [INFO] train episode 46198: reward = -49.82, steps = 17 08:50:02 [INFO] train episode 46199: reward = -58.87, steps = 27 08:50:04 [INFO] train episode 46200: reward = -41.95, steps = 20 08:50:05 [INFO] train episode 46201: reward = -64.41, steps = 20 08:50:08 [INFO] train episode 46202: reward = -51.73, steps = 21 08:50:09 [INFO] train episode 46203: reward = -37.64, steps = 20 08:50:11 [INFO] train episode 46204: reward = -50.92, steps = 23 08:50:13 [INFO] train episode 46205: reward = -50.74, steps = 25 08:50:15 [INFO] train episode 46206: reward = -54.67, steps = 22 08:50:17 [INFO] train episode 46207: reward = -34.81, steps = 21 08:50:19 [INFO] train episode 46208: reward = -56.06, steps = 21 08:50:21 [INFO] train episode 46209: reward = -38.33, steps = 29 08:50:24 [INFO] train episode 46210: reward = -45.07, steps = 27 08:50:26 [INFO] train episode 46211: reward = -42.77, steps = 21 08:50:28 [INFO] train episode 46212: reward = -49.32, steps = 22 08:50:30 [INFO] train episode 46213: reward = -48.98, steps = 25 08:50:32 [INFO] train episode 46214: reward = -59.65, steps = 23 08:50:34 [INFO] train episode 46215: reward = -38.52, steps = 28 08:50:36 [INFO] train episode 46216: reward = -57.96, steps = 22 08:50:39 [INFO] train episode 46217: reward = -28.69, steps = 24 08:50:42 [INFO] train episode 46218: reward = -63.42, steps = 35 08:50:43 [INFO] train episode 46219: reward = -60.76, steps = 19 08:50:45 [INFO] train episode 46220: reward = -59.94, steps = 22 08:50:48 [INFO] train episode 46221: reward = -42.40, steps = 37 08:50:50 [INFO] train episode 46222: reward = -54.59, steps = 20 08:50:52 [INFO] train episode 46223: reward = -50.31, steps = 22 08:50:54 [INFO] train episode 46224: reward = -90.12, steps = 19 08:50:56 [INFO] train episode 46225: reward = -56.35, steps = 20 08:50:58 [INFO] train episode 46226: reward = -58.63, steps = 23 08:51:01 [INFO] train episode 46227: reward = -68.10, steps = 39 08:51:04 [INFO] train episode 46228: reward = -73.26, steps = 35 08:51:06 [INFO] train episode 46229: reward = -39.31, steps = 22 08:51:09 [INFO] train episode 46230: reward = -40.83, steps = 38 08:51:11 [INFO] train episode 46231: reward = -53.31, steps = 19 08:51:13 [INFO] train episode 46232: reward = -31.16, steps = 27 08:51:15 [INFO] train episode 46233: reward = -43.93, steps = 21 08:51:17 [INFO] train episode 46234: reward = -31.65, steps = 21 08:51:19 [INFO] train episode 46235: reward = -45.81, steps = 26 08:51:21 [INFO] train episode 46236: reward = -66.73, steps = 20 08:51:22 [INFO] train episode 46237: reward = -50.16, steps = 20 08:51:26 [INFO] train episode 46238: reward = -33.37, steps = 36 08:51:27 [INFO] train episode 46239: reward = -53.38, steps = 19 08:51:29 [INFO] train episode 46240: reward = -48.02, steps = 23 08:51:32 [INFO] train episode 46241: reward = -49.33, steps = 27 08:51:34 [INFO] train episode 46242: reward = -41.25, steps = 22 08:51:35 [INFO] train episode 46243: reward = -86.45, steps = 20 08:51:38 [INFO] train episode 46244: reward = -68.21, steps = 34 08:51:40 [INFO] train episode 46245: reward = -82.55, steps = 20 08:51:42 [INFO] train episode 46246: reward = -48.05, steps = 23 08:51:44 [INFO] train episode 46247: reward = -57.70, steps = 19 08:51:47 [INFO] train episode 46248: reward = -74.28, steps = 22 08:51:48 [INFO] train episode 46249: reward = -66.53, steps = 19 08:51:51 [INFO] train episode 46250: reward = -62.13, steps = 30 08:51:53 [INFO] train episode 46251: reward = -87.53, steps = 29 08:51:55 [INFO] train episode 46252: reward = -40.19, steps = 19 08:51:58 [INFO] train episode 46253: reward = -61.03, steps = 37 08:52:00 [INFO] train episode 46254: reward = -39.84, steps = 23 08:52:03 [INFO] train episode 46255: reward = -42.83, steps = 36 08:52:07 [INFO] train episode 46256: reward = -89.71, steps = 43 08:52:09 [INFO] train episode 46257: reward = -80.06, steps = 20 08:52:10 [INFO] train episode 46258: reward = -57.31, steps = 21 08:52:14 [INFO] train episode 46259: reward = -35.56, steps = 41 08:52:17 [INFO] train episode 46260: reward = -54.92, steps = 29 08:52:18 [INFO] train episode 46261: reward = -58.08, steps = 20 08:52:20 [INFO] train episode 46262: reward = -48.26, steps = 25 08:52:23 [INFO] train episode 46263: reward = -50.69, steps = 27 08:52:24 [INFO] train episode 46264: reward = -72.51, steps = 20 08:52:26 [INFO] train episode 46265: reward = -66.69, steps = 22 08:52:30 [INFO] train episode 46266: reward = -97.70, steps = 44 08:52:32 [INFO] train episode 46267: reward = -55.31, steps = 23 08:52:35 [INFO] train episode 46268: reward = -84.57, steps = 32 08:52:38 [INFO] train episode 46269: reward = -66.54, steps = 27 08:52:39 [INFO] train episode 46270: reward = -58.84, steps = 21 08:52:43 [INFO] train episode 46271: reward = -46.62, steps = 38 08:52:45 [INFO] train episode 46272: reward = -50.80, steps = 28 08:52:48 [INFO] train episode 46273: reward = -52.42, steps = 31 08:52:50 [INFO] train episode 46274: reward = -66.95, steps = 20 08:52:52 [INFO] train episode 46275: reward = -66.67, steps = 31 08:52:55 [INFO] train episode 46276: reward = -81.77, steps = 27 08:52:57 [INFO] train episode 46277: reward = -64.59, steps = 27 08:53:00 [INFO] train episode 46278: reward = -77.62, steps = 39 08:53:02 [INFO] train episode 46279: reward = -57.47, steps = 23 08:53:04 [INFO] train episode 46280: reward = -58.28, steps = 21 08:53:06 [INFO] train episode 46281: reward = -48.62, steps = 19 08:53:08 [INFO] train episode 46282: reward = -43.23, steps = 21 08:53:10 [INFO] train episode 46283: reward = -84.49, steps = 28 08:53:13 [INFO] train episode 46284: reward = -71.60, steps = 37 08:53:16 [INFO] train episode 46285: reward = -47.94, steps = 24 08:53:18 [INFO] train episode 46286: reward = -65.68, steps = 32 08:53:21 [INFO] train episode 46287: reward = -33.94, steps = 31 08:53:23 [INFO] train episode 46288: reward = -69.35, steps = 28 08:53:25 [INFO] train episode 46289: reward = -47.62, steps = 20 08:53:27 [INFO] train episode 46290: reward = -39.69, steps = 24 08:53:29 [INFO] train episode 46291: reward = -46.21, steps = 23 08:53:32 [INFO] train episode 46292: reward = -46.45, steps = 30 08:53:35 [INFO] train episode 46293: reward = -53.02, steps = 33 08:53:37 [INFO] train episode 46294: reward = -75.54, steps = 21 08:53:38 [INFO] train episode 46295: reward = -47.22, steps = 20 08:53:41 [INFO] train episode 46296: reward = -72.07, steps = 27 08:53:44 [INFO] train episode 46297: reward = -81.77, steps = 36 08:53:47 [INFO] train episode 46298: reward = -68.85, steps = 37 08:53:50 [INFO] train episode 46299: reward = -69.22, steps = 32 08:53:52 [INFO] train episode 46300: reward = -62.81, steps = 24 08:53:55 [INFO] train episode 46301: reward = -79.92, steps = 41 08:53:59 [INFO] train episode 46302: reward = -69.95, steps = 42 08:54:02 [INFO] train episode 46303: reward = -86.78, steps = 33 08:54:04 [INFO] train episode 46304: reward = -64.04, steps = 22 08:54:06 [INFO] train episode 46305: reward = -60.30, steps = 25 08:54:10 [INFO] train episode 46306: reward = -52.01, steps = 41 08:54:12 [INFO] train episode 46307: reward = -69.76, steps = 31 08:54:15 [INFO] train episode 46308: reward = -55.78, steps = 28 08:54:17 [INFO] train episode 46309: reward = -47.04, steps = 29 08:54:21 [INFO] train episode 46310: reward = -71.54, steps = 37 08:54:23 [INFO] train episode 46311: reward = -43.99, steps = 22 08:54:24 [INFO] train episode 46312: reward = -60.91, steps = 20 08:54:26 [INFO] train episode 46313: reward = -46.59, steps = 21 08:54:29 [INFO] train episode 46314: reward = -69.53, steps = 32 08:54:31 [INFO] train episode 46315: reward = -76.63, steps = 25 08:54:34 [INFO] train episode 46316: reward = -55.35, steps = 31 08:54:37 [INFO] train episode 46317: reward = -62.28, steps = 23 08:54:40 [INFO] train episode 46318: reward = -74.99, steps = 39 08:54:43 [INFO] train episode 46319: reward = -76.53, steps = 32 08:54:45 [INFO] train episode 46320: reward = -45.77, steps = 30 08:54:47 [INFO] train episode 46321: reward = -44.47, steps = 23 08:54:49 [INFO] train episode 46322: reward = -58.26, steps = 22 08:54:52 [INFO] train episode 46323: reward = -76.65, steps = 29 08:54:54 [INFO] train episode 46324: reward = -67.45, steps = 20 08:54:56 [INFO] train episode 46325: reward = -51.67, steps = 22 08:54:59 [INFO] train episode 46326: reward = -52.26, steps = 37 08:55:01 [INFO] train episode 46327: reward = -72.05, steps = 20 08:55:02 [INFO] train episode 46328: reward = -52.07, steps = 21 08:55:05 [INFO] train episode 46329: reward = -68.29, steps = 35 08:55:09 [INFO] train episode 46330: reward = -29.87, steps = 43 08:55:11 [INFO] train episode 46331: reward = -62.57, steps = 21 08:55:14 [INFO] train episode 46332: reward = -83.34, steps = 34 08:55:16 [INFO] train episode 46333: reward = -55.08, steps = 19 08:55:18 [INFO] train episode 46334: reward = -64.80, steps = 24 08:55:20 [INFO] train episode 46335: reward = -65.93, steps = 31 08:55:24 [INFO] train episode 46336: reward = -59.65, steps = 32 08:55:25 [INFO] train episode 46337: reward = -39.93, steps = 19 08:55:28 [INFO] train episode 46338: reward = -43.92, steps = 23 08:55:30 [INFO] train episode 46339: reward = -32.67, steps = 26 08:55:33 [INFO] train episode 46340: reward = -48.43, steps = 43 08:55:35 [INFO] train episode 46341: reward = -67.23, steps = 24 08:55:37 [INFO] train episode 46342: reward = -43.83, steps = 24 08:55:41 [INFO] train episode 46343: reward = -40.47, steps = 39 08:55:43 [INFO] train episode 46344: reward = -49.36, steps = 20 08:55:46 [INFO] train episode 46345: reward = -101.11, steps = 33 08:55:47 [INFO] train episode 46346: reward = -74.29, steps = 20 08:55:49 [INFO] train episode 46347: reward = -48.83, steps = 24 08:55:52 [INFO] train episode 46348: reward = -73.84, steps = 39 08:55:55 [INFO] train episode 46349: reward = -50.17, steps = 19 08:55:56 [INFO] train episode 46350: reward = -57.19, steps = 21 08:55:59 [INFO] train episode 46351: reward = -48.28, steps = 30 08:56:01 [INFO] train episode 46352: reward = -69.96, steps = 21 08:56:03 [INFO] train episode 46353: reward = -41.86, steps = 22 08:56:06 [INFO] train episode 46354: reward = -39.37, steps = 43 08:56:09 [INFO] train episode 46355: reward = -81.75, steps = 31 08:56:11 [INFO] train episode 46356: reward = -90.02, steps = 22 08:56:13 [INFO] train episode 46357: reward = -77.23, steps = 27 08:56:16 [INFO] train episode 46358: reward = -107.23, steps = 36 08:56:18 [INFO] train episode 46359: reward = -53.49, steps = 20 08:56:21 [INFO] train episode 46360: reward = -62.97, steps = 29 08:56:23 [INFO] train episode 46361: reward = -46.64, steps = 25 08:56:25 [INFO] train episode 46362: reward = -60.16, steps = 26 08:56:29 [INFO] train episode 46363: reward = -87.40, steps = 38 08:56:31 [INFO] train episode 46364: reward = -46.81, steps = 29 08:56:33 [INFO] train episode 46365: reward = -68.60, steps = 20 08:56:36 [INFO] train episode 46366: reward = -66.89, steps = 42 08:56:38 [INFO] train episode 46367: reward = -72.00, steps = 19 08:56:41 [INFO] train episode 46368: reward = -82.59, steps = 36 08:56:44 [INFO] train episode 46369: reward = -42.05, steps = 25 08:56:46 [INFO] train episode 46370: reward = -62.08, steps = 21 08:56:48 [INFO] train episode 46371: reward = -60.56, steps = 26 08:56:51 [INFO] train episode 46372: reward = -74.12, steps = 34 08:56:53 [INFO] train episode 46373: reward = -40.14, steps = 28 08:56:55 [INFO] train episode 46374: reward = -71.01, steps = 21 08:56:57 [INFO] train episode 46375: reward = -74.93, steps = 24 08:56:59 [INFO] train episode 46376: reward = -55.25, steps = 25 08:57:02 [INFO] train episode 46377: reward = -78.22, steps = 27 08:57:04 [INFO] train episode 46378: reward = -107.03, steps = 30 08:57:06 [INFO] train episode 46379: reward = -44.12, steps = 21 08:57:08 [INFO] train episode 46380: reward = -35.83, steps = 26 08:57:10 [INFO] train episode 46381: reward = -65.29, steps = 20 08:57:13 [INFO] train episode 46382: reward = -53.14, steps = 27 08:57:14 [INFO] train episode 46383: reward = -47.32, steps = 20 08:57:17 [INFO] train episode 46384: reward = -91.79, steps = 26 08:57:19 [INFO] train episode 46385: reward = -73.39, steps = 22 08:57:21 [INFO] train episode 46386: reward = -42.82, steps = 25 08:57:22 [INFO] train episode 46387: reward = -51.45, steps = 21 08:57:25 [INFO] train episode 46388: reward = -70.75, steps = 30 08:57:28 [INFO] train episode 46389: reward = -78.70, steps = 21 08:57:31 [INFO] train episode 46390: reward = -57.44, steps = 36 08:57:33 [INFO] train episode 46391: reward = -76.45, steps = 19 08:57:35 [INFO] train episode 46392: reward = -69.30, steps = 32 08:57:38 [INFO] train episode 46393: reward = -55.35, steps = 29 08:57:40 [INFO] train episode 46394: reward = -48.65, steps = 25 08:57:42 [INFO] train episode 46395: reward = -64.90, steps = 25 08:57:44 [INFO] train episode 46396: reward = -48.98, steps = 20 08:57:46 [INFO] train episode 46397: reward = -70.36, steps = 20 08:57:48 [INFO] train episode 46398: reward = -49.58, steps = 21 08:57:51 [INFO] train episode 46399: reward = -45.67, steps = 31 08:57:53 [INFO] train episode 46400: reward = -42.16, steps = 31 08:57:55 [INFO] train episode 46401: reward = -48.81, steps = 20 08:57:57 [INFO] train episode 46402: reward = -51.86, steps = 24 08:57:59 [INFO] train episode 46403: reward = -44.26, steps = 20 08:58:02 [INFO] train episode 46404: reward = -58.71, steps = 31 08:58:04 [INFO] train episode 46405: reward = -39.00, steps = 25 08:58:06 [INFO] train episode 46406: reward = -95.47, steps = 27 08:58:08 [INFO] train episode 46407: reward = -67.69, steps = 23 08:58:10 [INFO] train episode 46408: reward = -66.17, steps = 22 08:58:12 [INFO] train episode 46409: reward = -77.60, steps = 22 08:58:15 [INFO] train episode 46410: reward = -37.62, steps = 36 08:58:17 [INFO] train episode 46411: reward = -50.49, steps = 23 08:58:20 [INFO] train episode 46412: reward = -65.70, steps = 36 08:58:23 [INFO] train episode 46413: reward = -68.94, steps = 32 08:58:25 [INFO] train episode 46414: reward = -42.68, steps = 20 08:58:26 [INFO] train episode 46415: reward = -38.32, steps = 20 08:58:29 [INFO] train episode 46416: reward = -81.14, steps = 33 08:58:32 [INFO] train episode 46417: reward = -46.44, steps = 27 08:58:34 [INFO] train episode 46418: reward = -43.64, steps = 20 08:58:36 [INFO] train episode 46419: reward = -46.48, steps = 28 08:58:39 [INFO] train episode 46420: reward = -54.82, steps = 33 08:58:42 [INFO] train episode 46421: reward = -33.33, steps = 44 08:58:44 [INFO] train episode 46422: reward = -63.86, steps = 22 08:58:46 [INFO] train episode 46423: reward = -42.40, steps = 21 08:58:48 [INFO] train episode 46424: reward = -68.31, steps = 21 08:58:51 [INFO] train episode 46425: reward = -37.77, steps = 27 08:58:53 [INFO] train episode 46426: reward = -50.52, steps = 32 08:58:56 [INFO] train episode 46427: reward = -36.67, steps = 29 08:58:58 [INFO] train episode 46428: reward = -61.48, steps = 27 08:59:00 [INFO] train episode 46429: reward = -66.73, steps = 21 08:59:02 [INFO] train episode 46430: reward = -44.33, steps = 21 08:59:05 [INFO] train episode 46431: reward = -53.57, steps = 32 08:59:07 [INFO] train episode 46432: reward = -51.87, steps = 22 08:59:10 [INFO] train episode 46433: reward = -35.50, steps = 43 08:59:12 [INFO] train episode 46434: reward = -30.70, steps = 22 08:59:14 [INFO] train episode 46435: reward = -53.65, steps = 21 08:59:17 [INFO] train episode 46436: reward = -78.70, steps = 33 08:59:19 [INFO] train episode 46437: reward = -50.60, steps = 21 08:59:22 [INFO] train episode 46438: reward = -95.74, steps = 41 08:59:25 [INFO] train episode 46439: reward = -50.60, steps = 32 08:59:27 [INFO] train episode 46440: reward = -35.23, steps = 28 08:59:29 [INFO] train episode 46441: reward = -34.88, steps = 19 08:59:31 [INFO] train episode 46442: reward = -44.60, steps = 24 08:59:33 [INFO] train episode 46443: reward = -37.36, steps = 21 08:59:35 [INFO] train episode 46444: reward = -50.43, steps = 24 08:59:38 [INFO] train episode 46445: reward = -73.85, steps = 30 08:59:40 [INFO] train episode 46446: reward = -69.16, steps = 20 08:59:42 [INFO] train episode 46447: reward = -69.59, steps = 32 08:59:44 [INFO] train episode 46448: reward = -59.19, steps = 21 08:59:46 [INFO] train episode 46449: reward = -94.73, steps = 19 08:59:48 [INFO] train episode 46450: reward = -58.34, steps = 20 08:59:51 [INFO] train episode 46451: reward = -55.52, steps = 38 08:59:53 [INFO] train episode 46452: reward = -73.29, steps = 28 08:59:56 [INFO] train episode 46453: reward = -54.74, steps = 31 08:59:59 [INFO] train episode 46454: reward = -58.87, steps = 38 09:00:01 [INFO] train episode 46455: reward = -34.06, steps = 23 09:00:03 [INFO] train episode 46456: reward = -74.92, steps = 26 09:00:07 [INFO] train episode 46457: reward = -81.32, steps = 40 09:00:09 [INFO] train episode 46458: reward = -55.13, steps = 19 09:00:12 [INFO] train episode 46459: reward = -78.53, steps = 35 09:00:14 [INFO] train episode 46460: reward = -69.81, steps = 30 09:00:17 [INFO] train episode 46461: reward = -66.54, steps = 21 09:00:19 [INFO] train episode 46462: reward = -68.85, steps = 21 09:00:20 [INFO] train episode 46463: reward = -79.55, steps = 20 09:00:23 [INFO] train episode 46464: reward = -59.21, steps = 24 09:00:26 [INFO] train episode 46465: reward = -52.56, steps = 37 09:00:28 [INFO] train episode 46466: reward = -109.60, steps = 32 09:00:30 [INFO] train episode 46467: reward = -71.30, steps = 25 09:00:33 [INFO] train episode 46468: reward = -63.41, steps = 27 09:00:35 [INFO] train episode 46469: reward = -65.97, steps = 28 09:00:37 [INFO] train episode 46470: reward = -56.84, steps = 20 09:00:39 [INFO] train episode 46471: reward = -57.31, steps = 22 09:00:42 [INFO] train episode 46472: reward = -84.92, steps = 27 09:00:43 [INFO] train episode 46473: reward = -58.65, steps = 20 09:00:46 [INFO] train episode 46474: reward = -70.10, steps = 32 09:00:48 [INFO] train episode 46475: reward = -43.97, steps = 27 09:00:50 [INFO] train episode 46476: reward = -48.37, steps = 23 09:00:52 [INFO] train episode 46477: reward = -40.24, steps = 23 09:00:56 [INFO] train episode 46478: reward = -79.44, steps = 37 09:00:59 [INFO] train episode 46479: reward = -66.71, steps = 31 09:01:01 [INFO] train episode 46480: reward = -35.13, steps = 25 09:01:02 [INFO] train episode 46481: reward = -50.31, steps = 20 09:01:04 [INFO] train episode 46482: reward = -55.94, steps = 21 09:01:06 [INFO] train episode 46483: reward = -48.29, steps = 20 09:01:08 [INFO] train episode 46484: reward = -69.98, steps = 20 09:01:12 [INFO] train episode 46485: reward = -33.41, steps = 43 09:01:14 [INFO] train episode 46486: reward = -43.00, steps = 23 09:01:16 [INFO] train episode 46487: reward = -44.88, steps = 31 09:01:18 [INFO] train episode 46488: reward = -90.29, steps = 20 09:01:20 [INFO] train episode 46489: reward = -55.31, steps = 31 09:01:23 [INFO] train episode 46490: reward = -43.24, steps = 33 09:01:25 [INFO] train episode 46491: reward = -50.47, steps = 27 09:01:28 [INFO] train episode 46492: reward = -53.46, steps = 27 09:01:30 [INFO] train episode 46493: reward = -52.04, steps = 21 09:01:32 [INFO] train episode 46494: reward = -79.70, steps = 23 09:01:34 [INFO] train episode 46495: reward = -95.34, steps = 27 09:01:37 [INFO] train episode 46496: reward = -38.10, steps = 32 09:01:38 [INFO] train episode 46497: reward = -51.79, steps = 20 09:01:41 [INFO] train episode 46498: reward = -37.34, steps = 30 09:01:43 [INFO] train episode 46499: reward = -69.10, steps = 20 09:01:46 [INFO] train episode 46500: reward = -41.86, steps = 28 09:01:48 [INFO] train episode 46501: reward = -68.43, steps = 29 09:01:50 [INFO] train episode 46502: reward = -40.57, steps = 27 09:01:52 [INFO] train episode 46503: reward = -83.20, steps = 26 09:01:54 [INFO] train episode 46504: reward = -52.78, steps = 22 09:01:56 [INFO] train episode 46505: reward = -37.22, steps = 24 09:01:59 [INFO] train episode 46506: reward = -67.55, steps = 29 09:02:01 [INFO] train episode 46507: reward = -51.37, steps = 21 09:02:03 [INFO] train episode 46508: reward = -90.21, steps = 26 09:02:05 [INFO] train episode 46509: reward = -49.06, steps = 25 09:02:08 [INFO] train episode 46510: reward = -63.66, steps = 29 09:02:10 [INFO] train episode 46511: reward = -64.92, steps = 21 09:02:13 [INFO] train episode 46512: reward = -97.16, steps = 37 09:02:16 [INFO] train episode 46513: reward = -55.72, steps = 29 09:02:18 [INFO] train episode 46514: reward = -40.76, steps = 27 09:02:22 [INFO] train episode 46515: reward = -134.31, steps = 44 09:02:24 [INFO] train episode 46516: reward = -50.43, steps = 23 09:02:26 [INFO] train episode 46517: reward = -51.87, steps = 24 09:02:29 [INFO] train episode 46518: reward = -75.25, steps = 39 09:02:31 [INFO] train episode 46519: reward = -60.36, steps = 21 09:02:34 [INFO] train episode 46520: reward = -84.51, steps = 32 09:02:38 [INFO] train episode 46521: reward = -57.96, steps = 48 09:02:41 [INFO] train episode 46522: reward = -116.54, steps = 29 09:02:43 [INFO] train episode 46523: reward = -81.15, steps = 25 09:02:45 [INFO] train episode 46524: reward = -70.26, steps = 22 09:02:47 [INFO] train episode 46525: reward = -66.57, steps = 21 09:02:49 [INFO] train episode 46526: reward = -38.88, steps = 23 09:02:51 [INFO] train episode 46527: reward = -81.19, steps = 19 09:02:53 [INFO] train episode 46528: reward = -54.71, steps = 24 09:02:55 [INFO] train episode 46529: reward = -62.50, steps = 25 09:02:58 [INFO] train episode 46530: reward = -93.59, steps = 33 09:03:01 [INFO] train episode 46531: reward = -97.81, steps = 36 09:03:03 [INFO] train episode 46532: reward = -61.57, steps = 29 09:03:07 [INFO] train episode 46533: reward = -58.67, steps = 36 09:03:10 [INFO] train episode 46534: reward = -68.22, steps = 28 09:03:12 [INFO] train episode 46535: reward = -46.64, steps = 32 09:03:16 [INFO] train episode 46536: reward = -89.03, steps = 38 09:03:18 [INFO] train episode 46537: reward = -52.82, steps = 22 09:03:20 [INFO] train episode 46538: reward = -53.93, steps = 21 09:03:22 [INFO] train episode 46539: reward = -100.21, steps = 23 09:03:24 [INFO] train episode 46540: reward = -54.32, steps = 22 09:03:27 [INFO] train episode 46541: reward = -142.83, steps = 44 09:03:30 [INFO] train episode 46542: reward = -57.01, steps = 37 09:03:34 [INFO] train episode 46543: reward = -79.66, steps = 34 09:03:37 [INFO] train episode 46544: reward = -54.16, steps = 45 09:03:39 [INFO] train episode 46545: reward = -54.04, steps = 21 09:03:41 [INFO] train episode 46546: reward = -67.69, steps = 20 09:03:44 [INFO] train episode 46547: reward = -63.52, steps = 33 09:03:46 [INFO] train episode 46548: reward = -44.06, steps = 22 09:03:47 [INFO] train episode 46549: reward = -40.69, steps = 22 09:03:49 [INFO] train episode 46550: reward = -39.73, steps = 19 09:03:52 [INFO] train episode 46551: reward = -60.59, steps = 31 09:03:55 [INFO] train episode 46552: reward = -77.92, steps = 37 09:03:58 [INFO] train episode 46553: reward = -60.46, steps = 33 09:04:01 [INFO] train episode 46554: reward = -65.63, steps = 33 09:04:04 [INFO] train episode 46555: reward = -60.37, steps = 30 09:04:06 [INFO] train episode 46556: reward = -43.72, steps = 27 09:04:09 [INFO] train episode 46557: reward = -81.30, steps = 32 09:04:12 [INFO] train episode 46558: reward = -64.38, steps = 40 09:04:16 [INFO] train episode 46559: reward = -101.17, steps = 42 09:04:19 [INFO] train episode 46560: reward = -56.30, steps = 36 09:04:22 [INFO] train episode 46561: reward = -73.50, steps = 33 09:04:24 [INFO] train episode 46562: reward = -50.54, steps = 22 09:04:28 [INFO] train episode 46563: reward = -43.37, steps = 44 09:04:30 [INFO] train episode 46564: reward = -47.38, steps = 28 09:04:32 [INFO] train episode 46565: reward = -81.00, steps = 22 09:04:34 [INFO] train episode 46566: reward = -49.86, steps = 22 09:04:36 [INFO] train episode 46567: reward = -63.63, steps = 21 09:04:39 [INFO] train episode 46568: reward = -99.94, steps = 40 09:04:41 [INFO] train episode 46569: reward = -47.53, steps = 25 09:04:45 [INFO] train episode 46570: reward = -65.97, steps = 43 09:04:46 [INFO] train episode 46571: reward = -48.19, steps = 20 09:04:49 [INFO] train episode 46572: reward = -47.85, steps = 29 09:04:52 [INFO] train episode 46573: reward = -60.80, steps = 27 09:04:54 [INFO] train episode 46574: reward = -75.58, steps = 26 09:04:56 [INFO] train episode 46575: reward = -69.68, steps = 22 09:04:58 [INFO] train episode 46576: reward = -44.04, steps = 29 09:05:01 [INFO] train episode 46577: reward = -112.31, steps = 34 09:05:04 [INFO] train episode 46578: reward = -38.04, steps = 28 09:05:05 [INFO] train episode 46579: reward = -61.31, steps = 22 09:05:08 [INFO] train episode 46580: reward = -93.89, steps = 25 09:05:10 [INFO] train episode 46581: reward = -51.26, steps = 21 09:05:12 [INFO] train episode 46582: reward = -74.48, steps = 23 09:05:14 [INFO] train episode 46583: reward = -52.13, steps = 23 09:05:16 [INFO] train episode 46584: reward = -88.78, steps = 27 09:05:18 [INFO] train episode 46585: reward = -41.77, steps = 22 09:05:20 [INFO] train episode 46586: reward = -61.53, steps = 26 09:05:22 [INFO] train episode 46587: reward = -32.16, steps = 25 09:05:26 [INFO] train episode 46588: reward = -68.78, steps = 39 09:05:28 [INFO] train episode 46589: reward = -43.35, steps = 30 09:05:31 [INFO] train episode 46590: reward = -52.19, steps = 33 09:05:33 [INFO] train episode 46591: reward = -35.13, steps = 22 09:05:36 [INFO] train episode 46592: reward = -65.82, steps = 32 09:05:37 [INFO] train episode 46593: reward = -62.79, steps = 19 09:05:40 [INFO] train episode 46594: reward = -40.44, steps = 20 09:05:42 [INFO] train episode 46595: reward = -59.34, steps = 24 09:05:45 [INFO] train episode 46596: reward = -97.40, steps = 39 09:05:47 [INFO] train episode 46597: reward = -49.58, steps = 25 09:05:49 [INFO] train episode 46598: reward = -61.16, steps = 23 09:05:50 [INFO] train episode 46599: reward = -64.16, steps = 18 09:05:52 [INFO] train episode 46600: reward = -83.24, steps = 20 09:05:54 [INFO] train episode 46601: reward = -53.36, steps = 20 09:05:57 [INFO] train episode 46602: reward = -54.68, steps = 20 09:05:59 [INFO] train episode 46603: reward = -48.88, steps = 23 09:06:01 [INFO] train episode 46604: reward = -64.49, steps = 27 09:06:03 [INFO] train episode 46605: reward = -81.53, steps = 27 09:06:06 [INFO] train episode 46606: reward = -60.69, steps = 24 09:06:09 [INFO] train episode 46607: reward = -100.74, steps = 41 09:06:12 [INFO] train episode 46608: reward = -57.10, steps = 25 09:06:15 [INFO] train episode 46609: reward = -66.73, steps = 37 09:06:16 [INFO] train episode 46610: reward = -52.58, steps = 20 09:06:18 [INFO] train episode 46611: reward = -31.79, steps = 20 09:06:21 [INFO] train episode 46612: reward = -49.23, steps = 34 09:06:23 [INFO] train episode 46613: reward = -48.24, steps = 22 09:06:25 [INFO] train episode 46614: reward = -55.69, steps = 26 09:06:28 [INFO] train episode 46615: reward = -45.77, steps = 28 09:06:31 [INFO] train episode 46616: reward = -75.08, steps = 41 09:06:33 [INFO] train episode 46617: reward = -55.95, steps = 25 09:06:36 [INFO] train episode 46618: reward = -83.72, steps = 33 09:06:38 [INFO] train episode 46619: reward = -67.00, steps = 26 09:06:40 [INFO] train episode 46620: reward = -60.49, steps = 25 09:06:43 [INFO] train episode 46621: reward = -55.63, steps = 26 09:06:45 [INFO] train episode 46622: reward = -47.78, steps = 26 09:06:48 [INFO] train episode 46623: reward = -55.27, steps = 35 09:06:51 [INFO] train episode 46624: reward = -64.68, steps = 37 09:06:53 [INFO] train episode 46625: reward = -52.75, steps = 22 09:06:57 [INFO] train episode 46626: reward = -53.37, steps = 38 09:06:59 [INFO] train episode 46627: reward = -60.58, steps = 24 09:07:02 [INFO] train episode 46628: reward = -37.41, steps = 37 09:07:04 [INFO] train episode 46629: reward = -58.13, steps = 24 09:07:06 [INFO] train episode 46630: reward = -52.15, steps = 21 09:07:08 [INFO] train episode 46631: reward = -45.38, steps = 22 09:07:10 [INFO] train episode 46632: reward = -52.07, steps = 23 09:07:12 [INFO] train episode 46633: reward = -45.07, steps = 26 09:07:14 [INFO] train episode 46634: reward = -42.27, steps = 22 09:07:16 [INFO] train episode 46635: reward = -64.00, steps = 20 09:07:18 [INFO] train episode 46636: reward = -54.24, steps = 28 09:07:20 [INFO] train episode 46637: reward = -43.86, steps = 20 09:07:22 [INFO] train episode 46638: reward = -56.69, steps = 24 09:07:25 [INFO] train episode 46639: reward = -59.48, steps = 28 09:07:27 [INFO] train episode 46640: reward = -57.71, steps = 23 09:07:28 [INFO] train episode 46641: reward = -56.59, steps = 22 09:07:31 [INFO] train episode 46642: reward = -56.05, steps = 24 09:07:35 [INFO] train episode 46643: reward = -135.11, steps = 51 09:07:37 [INFO] train episode 46644: reward = -49.54, steps = 23 09:07:40 [INFO] train episode 46645: reward = -36.82, steps = 38 09:07:43 [INFO] train episode 46646: reward = -56.97, steps = 32 09:07:45 [INFO] train episode 46647: reward = -61.51, steps = 21 09:07:47 [INFO] train episode 46648: reward = -90.23, steps = 29 09:07:49 [INFO] train episode 46649: reward = -54.20, steps = 21 09:07:52 [INFO] train episode 46650: reward = -72.78, steps = 34 09:07:55 [INFO] train episode 46651: reward = -97.50, steps = 34 09:07:57 [INFO] train episode 46652: reward = -56.14, steps = 28 09:08:01 [INFO] train episode 46653: reward = -95.09, steps = 40 09:08:04 [INFO] train episode 46654: reward = -47.18, steps = 30 09:08:05 [INFO] train episode 46655: reward = -47.01, steps = 19 09:08:08 [INFO] train episode 46656: reward = -87.28, steps = 29 09:08:11 [INFO] train episode 46657: reward = -59.00, steps = 36 09:08:14 [INFO] train episode 46658: reward = -36.38, steps = 33 09:08:16 [INFO] train episode 46659: reward = -73.62, steps = 30 09:08:19 [INFO] train episode 46660: reward = -56.96, steps = 30 09:08:21 [INFO] train episode 46661: reward = -104.66, steps = 20 09:08:23 [INFO] train episode 46662: reward = -54.35, steps = 20 09:08:24 [INFO] train episode 46663: reward = -58.37, steps = 21 09:08:27 [INFO] train episode 46664: reward = -49.79, steps = 31 09:08:30 [INFO] train episode 46665: reward = -39.15, steps = 32 09:08:32 [INFO] train episode 46666: reward = -49.52, steps = 23 09:08:34 [INFO] train episode 46667: reward = -76.78, steps = 25 09:08:38 [INFO] train episode 46668: reward = -80.67, steps = 42 09:08:40 [INFO] train episode 46669: reward = -48.95, steps = 20 09:08:41 [INFO] train episode 46670: reward = -47.18, steps = 22 09:08:43 [INFO] train episode 46671: reward = -56.78, steps = 20 09:08:46 [INFO] train episode 46672: reward = -33.46, steps = 21 09:08:48 [INFO] train episode 46673: reward = -38.57, steps = 22 09:08:51 [INFO] train episode 46674: reward = -62.01, steps = 33 09:08:54 [INFO] train episode 46675: reward = -105.80, steps = 35 09:08:55 [INFO] train episode 46676: reward = -65.28, steps = 19 09:08:57 [INFO] train episode 46677: reward = -61.93, steps = 23 09:08:59 [INFO] train episode 46678: reward = -32.40, steps = 21 09:09:02 [INFO] train episode 46679: reward = -54.50, steps = 35 09:09:06 [INFO] train episode 46680: reward = -87.08, steps = 39 09:09:08 [INFO] train episode 46681: reward = -50.01, steps = 22 09:09:10 [INFO] train episode 46682: reward = -94.80, steps = 24 09:09:12 [INFO] train episode 46683: reward = -45.36, steps = 27 09:09:14 [INFO] train episode 46684: reward = -65.82, steps = 20 09:09:16 [INFO] train episode 46685: reward = -44.86, steps = 28 09:09:18 [INFO] train episode 46686: reward = -36.66, steps = 21 09:09:21 [INFO] train episode 46687: reward = -54.52, steps = 27 09:09:23 [INFO] train episode 46688: reward = -57.86, steps = 32 09:09:26 [INFO] train episode 46689: reward = -57.38, steps = 28 09:09:28 [INFO] train episode 46690: reward = -50.96, steps = 29 09:09:30 [INFO] train episode 46691: reward = -54.55, steps = 22 09:09:32 [INFO] train episode 46692: reward = -59.27, steps = 24 09:09:34 [INFO] train episode 46693: reward = -38.46, steps = 23 09:09:38 [INFO] train episode 46694: reward = -107.44, steps = 46 09:09:42 [INFO] train episode 46695: reward = -75.08, steps = 40 09:09:43 [INFO] train episode 46696: reward = -68.31, steps = 19 09:09:45 [INFO] train episode 46697: reward = -44.31, steps = 24 09:09:47 [INFO] train episode 46698: reward = -40.25, steps = 21 09:09:49 [INFO] train episode 46699: reward = -66.82, steps = 27 09:09:52 [INFO] train episode 46700: reward = -60.65, steps = 21 09:09:54 [INFO] train episode 46701: reward = -73.01, steps = 30 09:09:56 [INFO] train episode 46702: reward = -56.25, steps = 24 09:09:58 [INFO] train episode 46703: reward = -56.59, steps = 22 09:10:00 [INFO] train episode 46704: reward = -54.24, steps = 21 09:10:02 [INFO] train episode 46705: reward = -41.96, steps = 23 09:10:04 [INFO] train episode 46706: reward = -53.27, steps = 25 09:10:07 [INFO] train episode 46707: reward = -87.82, steps = 27 09:10:10 [INFO] train episode 46708: reward = -71.52, steps = 36 09:10:11 [INFO] train episode 46709: reward = -55.30, steps = 19 09:10:13 [INFO] train episode 46710: reward = -67.01, steps = 19 09:10:16 [INFO] train episode 46711: reward = -113.67, steps = 42 09:10:19 [INFO] train episode 46712: reward = -103.51, steps = 34 09:10:22 [INFO] train episode 46713: reward = -33.41, steps = 32 09:10:25 [INFO] train episode 46714: reward = -86.22, steps = 25 09:10:28 [INFO] train episode 46715: reward = -62.48, steps = 34 09:10:31 [INFO] train episode 46716: reward = -71.45, steps = 35 09:10:33 [INFO] train episode 46717: reward = -74.25, steps = 33 09:10:37 [INFO] train episode 46718: reward = -95.77, steps = 40 09:10:41 [INFO] train episode 46719: reward = -66.08, steps = 40 09:10:42 [INFO] train episode 46720: reward = -73.87, steps = 19 09:10:45 [INFO] train episode 46721: reward = -47.72, steps = 27 09:10:48 [INFO] train episode 46722: reward = -84.00, steps = 33 09:10:50 [INFO] train episode 46723: reward = -60.47, steps = 24 09:10:52 [INFO] train episode 46724: reward = -64.80, steps = 22 09:10:55 [INFO] train episode 46725: reward = -37.01, steps = 38 09:10:57 [INFO] train episode 46726: reward = -54.88, steps = 22 09:10:59 [INFO] train episode 46727: reward = -32.68, steps = 24 09:11:02 [INFO] train episode 46728: reward = -37.87, steps = 35 09:11:04 [INFO] train episode 46729: reward = -58.95, steps = 20 09:11:06 [INFO] train episode 46730: reward = -48.81, steps = 20 09:11:09 [INFO] train episode 46731: reward = -74.44, steps = 36 09:11:11 [INFO] train episode 46732: reward = -59.26, steps = 30 09:11:13 [INFO] train episode 46733: reward = -61.62, steps = 22 09:11:17 [INFO] train episode 46734: reward = -67.72, steps = 50 09:11:19 [INFO] train episode 46735: reward = -28.74, steps = 20 09:11:23 [INFO] train episode 46736: reward = -56.84, steps = 41 09:11:25 [INFO] train episode 46737: reward = -86.81, steps = 25 09:11:27 [INFO] train episode 46738: reward = -64.65, steps = 26 09:11:29 [INFO] train episode 46739: reward = -85.25, steps = 21 09:11:31 [INFO] train episode 46740: reward = -44.11, steps = 20 09:11:33 [INFO] train episode 46741: reward = -77.47, steps = 30 09:11:37 [INFO] train episode 46742: reward = -52.27, steps = 28 09:11:39 [INFO] train episode 46743: reward = -52.77, steps = 23 09:11:42 [INFO] train episode 46744: reward = -92.41, steps = 42 09:11:45 [INFO] train episode 46745: reward = -47.73, steps = 31 09:11:48 [INFO] train episode 46746: reward = -75.30, steps = 40 09:11:51 [INFO] train episode 46747: reward = -108.20, steps = 35 09:11:54 [INFO] train episode 46748: reward = -81.25, steps = 35 09:11:56 [INFO] train episode 46749: reward = -72.71, steps = 24 09:12:00 [INFO] train episode 46750: reward = -49.90, steps = 37 09:12:02 [INFO] train episode 46751: reward = -68.86, steps = 28 09:12:06 [INFO] train episode 46752: reward = -43.90, steps = 38 09:12:09 [INFO] train episode 46753: reward = -60.23, steps = 45 09:12:11 [INFO] train episode 46754: reward = -59.24, steps = 19 09:12:14 [INFO] train episode 46755: reward = -62.65, steps = 32 09:12:16 [INFO] train episode 46756: reward = -39.33, steps = 21 09:12:18 [INFO] train episode 46757: reward = -55.60, steps = 27 09:12:20 [INFO] train episode 46758: reward = -70.90, steps = 23 09:12:22 [INFO] train episode 46759: reward = -45.91, steps = 24 09:12:26 [INFO] train episode 46760: reward = -61.42, steps = 43 09:12:29 [INFO] train episode 46761: reward = -56.61, steps = 33 09:12:31 [INFO] train episode 46762: reward = -84.32, steps = 24 09:12:34 [INFO] train episode 46763: reward = -66.99, steps = 34 09:12:36 [INFO] train episode 46764: reward = -50.58, steps = 20 09:12:37 [INFO] train episode 46765: reward = -70.59, steps = 15 09:12:39 [INFO] train episode 46766: reward = -46.73, steps = 22 09:12:42 [INFO] train episode 46767: reward = -54.83, steps = 32 09:12:46 [INFO] train episode 46768: reward = -106.87, steps = 45 09:12:48 [INFO] train episode 46769: reward = -86.16, steps = 23 09:12:50 [INFO] train episode 46770: reward = -44.88, steps = 22 09:12:52 [INFO] train episode 46771: reward = -46.69, steps = 24 09:12:56 [INFO] train episode 46772: reward = -58.54, steps = 46 09:12:58 [INFO] train episode 46773: reward = -45.48, steps = 21 09:13:00 [INFO] train episode 46774: reward = -76.87, steps = 22 09:13:02 [INFO] train episode 46775: reward = -66.72, steps = 30 09:13:05 [INFO] train episode 46776: reward = -68.68, steps = 30 09:13:09 [INFO] train episode 46777: reward = -35.16, steps = 41 09:13:10 [INFO] train episode 46778: reward = -38.61, steps = 20 09:13:13 [INFO] train episode 46779: reward = -46.75, steps = 32 09:13:15 [INFO] train episode 46780: reward = -35.83, steps = 28 09:13:18 [INFO] train episode 46781: reward = -82.41, steps = 34 09:13:22 [INFO] train episode 46782: reward = -55.82, steps = 35 09:13:24 [INFO] train episode 46783: reward = -54.53, steps = 27 09:13:26 [INFO] train episode 46784: reward = -64.44, steps = 28 09:13:29 [INFO] train episode 46785: reward = -62.77, steps = 36 09:13:31 [INFO] train episode 46786: reward = -44.53, steps = 19 09:13:34 [INFO] train episode 46787: reward = -67.65, steps = 34 09:13:38 [INFO] train episode 46788: reward = -60.97, steps = 41 09:13:40 [INFO] train episode 46789: reward = -47.77, steps = 21 09:13:44 [INFO] train episode 46790: reward = -40.06, steps = 51 09:13:47 [INFO] train episode 46791: reward = -65.74, steps = 38 09:13:49 [INFO] train episode 46792: reward = -43.35, steps = 19 09:13:52 [INFO] train episode 46793: reward = -110.17, steps = 42 09:13:55 [INFO] train episode 46794: reward = -103.94, steps = 37 09:13:58 [INFO] train episode 46795: reward = -87.93, steps = 25 09:14:01 [INFO] train episode 46796: reward = -73.58, steps = 38 09:14:03 [INFO] train episode 46797: reward = -48.44, steps = 29 09:14:06 [INFO] train episode 46798: reward = -70.81, steps = 32 09:14:08 [INFO] train episode 46799: reward = -69.89, steps = 19 09:14:11 [INFO] train episode 46800: reward = -78.41, steps = 38 09:14:14 [INFO] train episode 46801: reward = -56.34, steps = 34 09:14:16 [INFO] train episode 46802: reward = -50.39, steps = 24 09:14:18 [INFO] train episode 46803: reward = -59.69, steps = 24 09:14:21 [INFO] train episode 46804: reward = -66.64, steps = 32 09:14:23 [INFO] train episode 46805: reward = -58.13, steps = 23 09:14:25 [INFO] train episode 46806: reward = -46.36, steps = 21 09:14:29 [INFO] train episode 46807: reward = -117.19, steps = 43 09:14:31 [INFO] train episode 46808: reward = -39.60, steps = 26 09:14:34 [INFO] train episode 46809: reward = -46.38, steps = 27 09:14:36 [INFO] train episode 46810: reward = -60.04, steps = 32 09:14:40 [INFO] train episode 46811: reward = -59.07, steps = 38 09:14:42 [INFO] train episode 46812: reward = -75.37, steps = 20 09:14:44 [INFO] train episode 46813: reward = -47.09, steps = 26 09:14:47 [INFO] train episode 46814: reward = -63.00, steps = 29 09:14:49 [INFO] train episode 46815: reward = -54.78, steps = 32 09:14:51 [INFO] train episode 46816: reward = -43.41, steps = 20 09:14:53 [INFO] train episode 46817: reward = -64.57, steps = 21 09:14:56 [INFO] train episode 46818: reward = -102.54, steps = 31 09:14:58 [INFO] train episode 46819: reward = -51.63, steps = 21 09:15:00 [INFO] train episode 46820: reward = -69.15, steps = 30 09:15:02 [INFO] train episode 46821: reward = -61.07, steps = 18 09:15:04 [INFO] train episode 46822: reward = -29.74, steps = 31 09:15:07 [INFO] train episode 46823: reward = -36.77, steps = 31 09:15:10 [INFO] train episode 46824: reward = -39.49, steps = 35 09:15:12 [INFO] train episode 46825: reward = -64.08, steps = 19 09:15:15 [INFO] train episode 46826: reward = -42.73, steps = 35 09:15:18 [INFO] train episode 46827: reward = -70.93, steps = 33 09:15:20 [INFO] train episode 46828: reward = -49.90, steps = 26 09:15:22 [INFO] train episode 46829: reward = -60.26, steps = 24 09:15:24 [INFO] train episode 46830: reward = -63.19, steps = 19 09:15:26 [INFO] train episode 46831: reward = -36.29, steps = 20 09:15:28 [INFO] train episode 46832: reward = -36.13, steps = 23 09:15:30 [INFO] train episode 46833: reward = -67.95, steps = 31 09:15:32 [INFO] train episode 46834: reward = -45.05, steps = 22 09:15:34 [INFO] train episode 46835: reward = -53.87, steps = 19 09:15:36 [INFO] train episode 46836: reward = -72.83, steps = 23 09:15:38 [INFO] train episode 46837: reward = -105.86, steps = 29 09:15:40 [INFO] train episode 46838: reward = -63.05, steps = 24 09:15:44 [INFO] train episode 46839: reward = -68.79, steps = 35 09:15:46 [INFO] train episode 46840: reward = -118.83, steps = 26 09:15:48 [INFO] train episode 46841: reward = -90.94, steps = 26 09:15:51 [INFO] train episode 46842: reward = -65.80, steps = 32 09:15:53 [INFO] train episode 46843: reward = -62.33, steps = 27 09:15:55 [INFO] train episode 46844: reward = -67.79, steps = 30 09:15:59 [INFO] train episode 46845: reward = -67.45, steps = 43 09:16:02 [INFO] train episode 46846: reward = -121.11, steps = 35 09:16:05 [INFO] train episode 46847: reward = -26.66, steps = 36 09:16:08 [INFO] train episode 46848: reward = -56.79, steps = 29 09:16:10 [INFO] train episode 46849: reward = -75.22, steps = 23 09:16:13 [INFO] train episode 46850: reward = -51.57, steps = 27 09:16:15 [INFO] train episode 46851: reward = -54.64, steps = 24 09:16:17 [INFO] train episode 46852: reward = -71.18, steps = 25 09:16:19 [INFO] train episode 46853: reward = -49.40, steps = 22 09:16:20 [INFO] train episode 46854: reward = -42.22, steps = 23 09:16:23 [INFO] train episode 46855: reward = -80.92, steps = 29 09:16:26 [INFO] train episode 46856: reward = -67.28, steps = 37 09:16:29 [INFO] train episode 46857: reward = -37.57, steps = 25 09:16:30 [INFO] train episode 46858: reward = -47.97, steps = 22 09:16:33 [INFO] train episode 46859: reward = -69.08, steps = 31 09:16:36 [INFO] train episode 46860: reward = -30.54, steps = 29 09:16:37 [INFO] train episode 46861: reward = -37.83, steps = 21 09:16:39 [INFO] train episode 46862: reward = -43.14, steps = 23 09:16:43 [INFO] train episode 46863: reward = -61.64, steps = 38 09:16:45 [INFO] train episode 46864: reward = -46.44, steps = 27 09:16:47 [INFO] train episode 46865: reward = -40.01, steps = 20 09:16:50 [INFO] train episode 46866: reward = -46.98, steps = 28 09:16:52 [INFO] train episode 46867: reward = -62.55, steps = 25 09:16:55 [INFO] train episode 46868: reward = -47.60, steps = 45 09:16:58 [INFO] train episode 46869: reward = -62.24, steps = 33 09:17:01 [INFO] train episode 46870: reward = -50.93, steps = 29 09:17:03 [INFO] train episode 46871: reward = -85.25, steps = 21 09:17:05 [INFO] train episode 46872: reward = -41.75, steps = 26 09:17:07 [INFO] train episode 46873: reward = -71.75, steps = 23 09:17:09 [INFO] train episode 46874: reward = -53.61, steps = 22 09:17:11 [INFO] train episode 46875: reward = -37.02, steps = 24 09:17:14 [INFO] train episode 46876: reward = -75.19, steps = 29 09:17:16 [INFO] train episode 46877: reward = -59.87, steps = 27 09:17:21 [INFO] train episode 46878: reward = -41.73, steps = 42 09:17:23 [INFO] train episode 46879: reward = -46.61, steps = 33 09:17:26 [INFO] train episode 46880: reward = -59.98, steps = 28 09:17:28 [INFO] train episode 46881: reward = -55.09, steps = 23 09:17:29 [INFO] train episode 46882: reward = -57.35, steps = 20 09:17:34 [INFO] train episode 46883: reward = -100.49, steps = 56 09:17:38 [INFO] train episode 46884: reward = -81.50, steps = 40 09:17:40 [INFO] train episode 46885: reward = -73.66, steps = 27 09:17:43 [INFO] train episode 46886: reward = -79.24, steps = 37 09:17:45 [INFO] train episode 46887: reward = -59.09, steps = 20 09:17:47 [INFO] train episode 46888: reward = -47.71, steps = 23 09:17:49 [INFO] train episode 46889: reward = -37.10, steps = 23 09:17:51 [INFO] train episode 46890: reward = -53.74, steps = 20 09:17:54 [INFO] train episode 46891: reward = -62.69, steps = 30 09:17:56 [INFO] train episode 46892: reward = -60.18, steps = 27 09:17:58 [INFO] train episode 46893: reward = -61.84, steps = 29 09:18:02 [INFO] train episode 46894: reward = -37.73, steps = 41 09:18:04 [INFO] train episode 46895: reward = -65.40, steps = 20 09:18:07 [INFO] train episode 46896: reward = -62.35, steps = 35 09:18:09 [INFO] train episode 46897: reward = -34.95, steps = 22 09:18:11 [INFO] train episode 46898: reward = -54.51, steps = 21 09:18:13 [INFO] train episode 46899: reward = -48.67, steps = 25 09:18:15 [INFO] train episode 46900: reward = -45.95, steps = 28 09:18:17 [INFO] train episode 46901: reward = -55.91, steps = 25 09:18:21 [INFO] train episode 46902: reward = -124.27, steps = 46 09:18:23 [INFO] train episode 46903: reward = -47.63, steps = 24 09:18:26 [INFO] train episode 46904: reward = -53.41, steps = 25 09:18:29 [INFO] train episode 46905: reward = -72.11, steps = 34 09:18:31 [INFO] train episode 46906: reward = -83.46, steps = 26 09:18:34 [INFO] train episode 46907: reward = -106.30, steps = 43 09:18:37 [INFO] train episode 46908: reward = -45.12, steps = 22 09:18:39 [INFO] train episode 46909: reward = -120.03, steps = 31 09:18:42 [INFO] train episode 46910: reward = -34.74, steps = 29 09:18:44 [INFO] train episode 46911: reward = -29.07, steps = 21 09:18:46 [INFO] train episode 46912: reward = -63.20, steps = 25 09:18:48 [INFO] train episode 46913: reward = -60.10, steps = 20 09:18:52 [INFO] train episode 46914: reward = -64.80, steps = 42 09:18:54 [INFO] train episode 46915: reward = -73.88, steps = 33 09:18:58 [INFO] train episode 46916: reward = -35.69, steps = 37 09:19:01 [INFO] train episode 46917: reward = -73.34, steps = 39 09:19:03 [INFO] train episode 46918: reward = -59.02, steps = 27 09:19:07 [INFO] train episode 46919: reward = -65.49, steps = 41 09:19:09 [INFO] train episode 46920: reward = -35.02, steps = 23 09:19:10 [INFO] train episode 46921: reward = -52.28, steps = 17 09:19:13 [INFO] train episode 46922: reward = -75.82, steps = 34 09:19:16 [INFO] train episode 46923: reward = -44.32, steps = 32 09:19:18 [INFO] train episode 46924: reward = -58.13, steps = 28 09:19:20 [INFO] train episode 46925: reward = -64.63, steps = 25 09:19:24 [INFO] train episode 46926: reward = -69.16, steps = 37 09:19:26 [INFO] train episode 46927: reward = -47.31, steps = 23 09:19:28 [INFO] train episode 46928: reward = -54.30, steps = 19 09:19:29 [INFO] train episode 46929: reward = -68.43, steps = 20 09:19:32 [INFO] train episode 46930: reward = -53.27, steps = 34 09:19:35 [INFO] train episode 46931: reward = -81.75, steps = 29 09:19:37 [INFO] train episode 46932: reward = -69.06, steps = 31 09:19:40 [INFO] train episode 46933: reward = -46.59, steps = 23 09:19:42 [INFO] train episode 46934: reward = -48.49, steps = 23 09:19:46 [INFO] train episode 46935: reward = -77.72, steps = 54 09:19:48 [INFO] train episode 46936: reward = -59.91, steps = 22 09:19:51 [INFO] train episode 46937: reward = -65.96, steps = 40 09:19:54 [INFO] train episode 46938: reward = -68.07, steps = 30 09:19:56 [INFO] train episode 46939: reward = -64.77, steps = 25 09:19:59 [INFO] train episode 46940: reward = -60.48, steps = 37 09:20:02 [INFO] train episode 46941: reward = -44.37, steps = 24 09:20:04 [INFO] train episode 46942: reward = -53.57, steps = 33 09:20:07 [INFO] train episode 46943: reward = -47.52, steps = 33 09:20:11 [INFO] train episode 46944: reward = -49.74, steps = 34 09:20:13 [INFO] train episode 46945: reward = -67.77, steps = 23 09:20:15 [INFO] train episode 46946: reward = -70.68, steps = 20 09:20:18 [INFO] train episode 46947: reward = -36.39, steps = 30 09:20:20 [INFO] train episode 46948: reward = -62.02, steps = 26 09:20:24 [INFO] train episode 46949: reward = -64.99, steps = 37 09:20:26 [INFO] train episode 46950: reward = -46.13, steps = 23 09:20:30 [INFO] train episode 46951: reward = -70.45, steps = 38 09:20:32 [INFO] train episode 46952: reward = -36.59, steps = 25 09:20:35 [INFO] train episode 46953: reward = -68.16, steps = 34 09:20:40 [INFO] train episode 46954: reward = -62.11, steps = 54 09:20:43 [INFO] train episode 46955: reward = -47.20, steps = 30 09:20:45 [INFO] train episode 46956: reward = -54.55, steps = 21 09:20:47 [INFO] train episode 46957: reward = -55.21, steps = 28 09:20:50 [INFO] train episode 46958: reward = -60.65, steps = 25 09:20:51 [INFO] train episode 46959: reward = -47.87, steps = 19 09:20:54 [INFO] train episode 46960: reward = -42.73, steps = 33 09:20:58 [INFO] train episode 46961: reward = -37.82, steps = 42 09:21:00 [INFO] train episode 46962: reward = -79.45, steps = 29 09:21:04 [INFO] train episode 46963: reward = -53.06, steps = 39 09:21:05 [INFO] train episode 46964: reward = -86.24, steps = 18 09:21:08 [INFO] train episode 46965: reward = -47.47, steps = 28 09:21:10 [INFO] train episode 46966: reward = -68.17, steps = 22 09:21:12 [INFO] train episode 46967: reward = -44.59, steps = 25 09:21:13 [INFO] train episode 46968: reward = -73.30, steps = 22 09:21:21 [INFO] train episode 46969: reward = -94.10, steps = 88 09:21:23 [INFO] train episode 46970: reward = -61.61, steps = 22 09:21:26 [INFO] train episode 46971: reward = -33.27, steps = 36 09:21:29 [INFO] train episode 46972: reward = -69.51, steps = 30 09:21:32 [INFO] train episode 46973: reward = -36.99, steps = 34 09:21:35 [INFO] train episode 46974: reward = -40.60, steps = 41 09:21:37 [INFO] train episode 46975: reward = -65.28, steps = 23 09:21:40 [INFO] train episode 46976: reward = -54.60, steps = 28 09:21:44 [INFO] train episode 46977: reward = -82.68, steps = 50 09:21:47 [INFO] train episode 46978: reward = -86.63, steps = 38 09:21:50 [INFO] train episode 46979: reward = -75.48, steps = 35 09:21:53 [INFO] train episode 46980: reward = -84.03, steps = 35 09:21:55 [INFO] train episode 46981: reward = -42.97, steps = 20 09:21:57 [INFO] train episode 46982: reward = -54.45, steps = 21 09:21:59 [INFO] train episode 46983: reward = -59.94, steps = 21 09:22:02 [INFO] train episode 46984: reward = -32.44, steps = 41 09:22:05 [INFO] train episode 46985: reward = -38.34, steps = 32 09:22:07 [INFO] train episode 46986: reward = -46.85, steps = 22 09:22:10 [INFO] train episode 46987: reward = -75.90, steps = 29 09:22:12 [INFO] train episode 46988: reward = -71.14, steps = 28 09:22:15 [INFO] train episode 46989: reward = -70.91, steps = 35 09:22:20 [INFO] train episode 46990: reward = -63.10, steps = 50 09:22:23 [INFO] train episode 46991: reward = -70.42, steps = 42 09:22:27 [INFO] train episode 46992: reward = -74.29, steps = 44 09:22:29 [INFO] train episode 46993: reward = -62.70, steps = 30 09:22:33 [INFO] train episode 46994: reward = -102.56, steps = 39 09:22:35 [INFO] train episode 46995: reward = -60.50, steps = 20 09:22:36 [INFO] train episode 46996: reward = -40.39, steps = 20 09:22:39 [INFO] train episode 46997: reward = -54.88, steps = 26 09:22:43 [INFO] train episode 46998: reward = -65.89, steps = 45 09:22:46 [INFO] train episode 46999: reward = -72.41, steps = 44 09:22:48 [INFO] train episode 47000: reward = -39.82, steps = 20 09:22:51 [INFO] train episode 47001: reward = -37.72, steps = 27 09:22:53 [INFO] train episode 47002: reward = -56.19, steps = 30 09:22:55 [INFO] train episode 47003: reward = -26.17, steps = 25 09:22:58 [INFO] train episode 47004: reward = -42.32, steps = 27 09:23:00 [INFO] train episode 47005: reward = -33.29, steps = 25 09:23:03 [INFO] train episode 47006: reward = -43.53, steps = 34 09:23:06 [INFO] train episode 47007: reward = -40.85, steps = 31 09:23:09 [INFO] train episode 47008: reward = -33.75, steps = 32 09:23:11 [INFO] train episode 47009: reward = -47.04, steps = 27 09:23:14 [INFO] train episode 47010: reward = -72.60, steps = 29 09:23:16 [INFO] train episode 47011: reward = -38.12, steps = 23 09:23:19 [INFO] train episode 47012: reward = -58.73, steps = 35 09:23:21 [INFO] train episode 47013: reward = -31.83, steps = 21 09:23:23 [INFO] train episode 47014: reward = -41.16, steps = 23 09:23:25 [INFO] train episode 47015: reward = -49.24, steps = 20 09:23:26 [INFO] train episode 47016: reward = -35.55, steps = 22 09:23:29 [INFO] train episode 47017: reward = -42.89, steps = 27 09:23:31 [INFO] train episode 47018: reward = -58.21, steps = 31 09:23:35 [INFO] train episode 47019: reward = -93.27, steps = 35 09:23:37 [INFO] train episode 47020: reward = -56.01, steps = 30 09:23:39 [INFO] train episode 47021: reward = -47.01, steps = 21 09:23:41 [INFO] train episode 47022: reward = -39.64, steps = 20 09:23:43 [INFO] train episode 47023: reward = -52.12, steps = 25 09:23:45 [INFO] train episode 47024: reward = -47.82, steps = 22 09:23:47 [INFO] train episode 47025: reward = -69.45, steps = 21 09:23:49 [INFO] train episode 47026: reward = -54.34, steps = 25 09:23:53 [INFO] train episode 47027: reward = -57.73, steps = 49 09:23:55 [INFO] train episode 47028: reward = -67.44, steps = 18 09:23:57 [INFO] train episode 47029: reward = -44.28, steps = 27 09:24:00 [INFO] train episode 47030: reward = -79.27, steps = 35 09:24:04 [INFO] train episode 47031: reward = -72.21, steps = 42 09:24:06 [INFO] train episode 47032: reward = -43.62, steps = 23 09:24:09 [INFO] train episode 47033: reward = -78.12, steps = 41 09:24:12 [INFO] train episode 47034: reward = -45.82, steps = 27 09:24:14 [INFO] train episode 47035: reward = -45.96, steps = 23 09:24:16 [INFO] train episode 47036: reward = -65.54, steps = 22 09:24:18 [INFO] train episode 47037: reward = -90.13, steps = 26 09:24:21 [INFO] train episode 47038: reward = -79.92, steps = 39 09:24:23 [INFO] train episode 47039: reward = -40.93, steps = 19 09:24:26 [INFO] train episode 47040: reward = -55.23, steps = 36 09:24:29 [INFO] train episode 47041: reward = -49.80, steps = 36 09:24:32 [INFO] train episode 47042: reward = -69.62, steps = 31 09:24:34 [INFO] train episode 47043: reward = -43.99, steps = 27 09:24:38 [INFO] train episode 47044: reward = -93.69, steps = 36 09:24:39 [INFO] train episode 47045: reward = -56.05, steps = 21 09:24:42 [INFO] train episode 47046: reward = -49.98, steps = 31 09:24:45 [INFO] train episode 47047: reward = -57.61, steps = 27 09:24:48 [INFO] train episode 47048: reward = -42.44, steps = 36 09:24:50 [INFO] train episode 47049: reward = -81.10, steps = 20 09:24:52 [INFO] train episode 47050: reward = -49.91, steps = 26 09:24:54 [INFO] train episode 47051: reward = -45.47, steps = 26 09:24:56 [INFO] train episode 47052: reward = -60.16, steps = 20 09:24:59 [INFO] train episode 47053: reward = -39.89, steps = 29 09:25:02 [INFO] train episode 47054: reward = -68.71, steps = 40 09:25:04 [INFO] train episode 47055: reward = -63.93, steps = 20 09:25:07 [INFO] train episode 47056: reward = -64.46, steps = 36 09:25:10 [INFO] train episode 47057: reward = -40.54, steps = 37 09:25:13 [INFO] train episode 47058: reward = -45.42, steps = 34 09:25:17 [INFO] train episode 47059: reward = -83.11, steps = 40 09:25:20 [INFO] train episode 47060: reward = -38.46, steps = 37 09:25:22 [INFO] train episode 47061: reward = -60.37, steps = 26 09:25:24 [INFO] train episode 47062: reward = -52.51, steps = 29 09:25:27 [INFO] train episode 47063: reward = -59.88, steps = 32 09:25:30 [INFO] train episode 47064: reward = -80.75, steps = 29 09:25:32 [INFO] train episode 47065: reward = -53.82, steps = 21 09:25:35 [INFO] train episode 47066: reward = -64.29, steps = 31 09:25:36 [INFO] train episode 47067: reward = -39.61, steps = 21 09:25:39 [INFO] train episode 47068: reward = -60.89, steps = 35 09:25:42 [INFO] train episode 47069: reward = -99.29, steps = 26 09:25:45 [INFO] train episode 47070: reward = -79.39, steps = 37 09:25:48 [INFO] train episode 47071: reward = -67.79, steps = 35 09:25:50 [INFO] train episode 47072: reward = -45.64, steps = 21 09:25:52 [INFO] train episode 47073: reward = -49.09, steps = 21 09:25:54 [INFO] train episode 47074: reward = -45.90, steps = 21 09:25:56 [INFO] train episode 47075: reward = -40.11, steps = 21 09:25:59 [INFO] train episode 47076: reward = -60.56, steps = 30 09:26:02 [INFO] train episode 47077: reward = -45.93, steps = 32 09:26:04 [INFO] train episode 47078: reward = -69.18, steps = 24 09:26:06 [INFO] train episode 47079: reward = -45.37, steps = 29 09:26:11 [INFO] train episode 47080: reward = -111.16, steps = 62 09:26:13 [INFO] train episode 47081: reward = -56.26, steps = 25 09:26:15 [INFO] train episode 47082: reward = -70.74, steps = 24 09:26:18 [INFO] train episode 47083: reward = -40.49, steps = 27 09:26:21 [INFO] train episode 47084: reward = -33.67, steps = 30 09:26:23 [INFO] train episode 47085: reward = -58.13, steps = 31 09:26:27 [INFO] train episode 47086: reward = -70.36, steps = 45 09:26:30 [INFO] train episode 47087: reward = -54.80, steps = 30 09:26:32 [INFO] train episode 47088: reward = -58.40, steps = 26 09:26:36 [INFO] train episode 47089: reward = -88.14, steps = 44 09:26:38 [INFO] train episode 47090: reward = -44.83, steps = 23 09:26:42 [INFO] train episode 47091: reward = -46.32, steps = 43 09:26:45 [INFO] train episode 47092: reward = -31.03, steps = 39 09:26:47 [INFO] train episode 47093: reward = -52.83, steps = 21 09:26:50 [INFO] train episode 47094: reward = -94.46, steps = 27 09:26:51 [INFO] train episode 47095: reward = -57.89, steps = 19 09:26:53 [INFO] train episode 47096: reward = -59.22, steps = 20 09:26:55 [INFO] train episode 47097: reward = -42.43, steps = 27 09:26:58 [INFO] train episode 47098: reward = -54.04, steps = 30 09:27:01 [INFO] train episode 47099: reward = -111.44, steps = 42 09:27:03 [INFO] train episode 47100: reward = -50.20, steps = 22 09:27:06 [INFO] train episode 47101: reward = -34.78, steps = 25 09:27:08 [INFO] train episode 47102: reward = -70.61, steps = 22 09:27:10 [INFO] train episode 47103: reward = -53.32, steps = 25 09:27:12 [INFO] train episode 47104: reward = -51.00, steps = 28 09:27:14 [INFO] train episode 47105: reward = -85.36, steps = 29 09:27:18 [INFO] train episode 47106: reward = -60.80, steps = 40 09:27:20 [INFO] train episode 47107: reward = -57.85, steps = 27 09:27:23 [INFO] train episode 47108: reward = -80.87, steps = 30 09:27:25 [INFO] train episode 47109: reward = -57.08, steps = 23 09:27:28 [INFO] train episode 47110: reward = -46.51, steps = 37 09:27:30 [INFO] train episode 47111: reward = -59.00, steps = 19 09:27:34 [INFO] train episode 47112: reward = -99.10, steps = 47 09:27:36 [INFO] train episode 47113: reward = -82.23, steps = 23 09:27:38 [INFO] train episode 47114: reward = -54.20, steps = 23 09:27:40 [INFO] train episode 47115: reward = -55.24, steps = 25 09:27:43 [INFO] train episode 47116: reward = -86.71, steps = 37 09:27:45 [INFO] train episode 47117: reward = -70.90, steps = 23 09:27:48 [INFO] train episode 47118: reward = -97.39, steps = 31 09:27:50 [INFO] train episode 47119: reward = -47.36, steps = 28 09:27:53 [INFO] train episode 47120: reward = -45.51, steps = 22 09:27:55 [INFO] train episode 47121: reward = -80.03, steps = 27 09:27:57 [INFO] train episode 47122: reward = -80.47, steps = 20 09:27:59 [INFO] train episode 47123: reward = -84.72, steps = 21 09:28:01 [INFO] train episode 47124: reward = -41.12, steps = 23 09:28:04 [INFO] train episode 47125: reward = -56.90, steps = 39 09:28:06 [INFO] train episode 47126: reward = -35.04, steps = 30 09:28:11 [INFO] train episode 47127: reward = -45.50, steps = 47 09:28:14 [INFO] train episode 47128: reward = -82.67, steps = 40 09:28:17 [INFO] train episode 47129: reward = -56.83, steps = 34 09:28:21 [INFO] train episode 47130: reward = -48.98, steps = 52 09:28:25 [INFO] train episode 47131: reward = -59.40, steps = 39 09:28:27 [INFO] train episode 47132: reward = -50.13, steps = 27 09:28:29 [INFO] train episode 47133: reward = -32.53, steps = 26 09:28:32 [INFO] train episode 47134: reward = -51.51, steps = 26 09:28:35 [INFO] train episode 47135: reward = -68.70, steps = 40 09:28:37 [INFO] train episode 47136: reward = -50.15, steps = 27 09:28:40 [INFO] train episode 47137: reward = -61.16, steps = 27 09:28:42 [INFO] train episode 47138: reward = -46.57, steps = 22 09:28:45 [INFO] train episode 47139: reward = -61.51, steps = 20 09:28:47 [INFO] train episode 47140: reward = -49.24, steps = 23 09:28:49 [INFO] train episode 47141: reward = -27.15, steps = 29 09:28:51 [INFO] train episode 47142: reward = -50.70, steps = 20 09:28:53 [INFO] train episode 47143: reward = -52.22, steps = 21 09:28:56 [INFO] train episode 47144: reward = -54.79, steps = 32 09:28:58 [INFO] train episode 47145: reward = -39.40, steps = 30 09:29:02 [INFO] train episode 47146: reward = -106.71, steps = 39 09:29:05 [INFO] train episode 47147: reward = -45.45, steps = 31 09:29:07 [INFO] train episode 47148: reward = -59.50, steps = 26 09:29:11 [INFO] train episode 47149: reward = -74.62, steps = 45 09:29:14 [INFO] train episode 47150: reward = -66.27, steps = 25 09:29:16 [INFO] train episode 47151: reward = -46.73, steps = 29 09:29:19 [INFO] train episode 47152: reward = -61.37, steps = 34 09:29:21 [INFO] train episode 47153: reward = -55.78, steps = 22 09:29:23 [INFO] train episode 47154: reward = -46.84, steps = 27 09:29:25 [INFO] train episode 47155: reward = -42.42, steps = 23 09:29:28 [INFO] train episode 47156: reward = -80.65, steps = 34 09:29:31 [INFO] train episode 47157: reward = -79.46, steps = 30 09:29:34 [INFO] train episode 47158: reward = -44.98, steps = 31 09:29:36 [INFO] train episode 47159: reward = -43.39, steps = 24 09:29:37 [INFO] train episode 47160: reward = -72.32, steps = 22 09:29:40 [INFO] train episode 47161: reward = -73.10, steps = 26 09:29:42 [INFO] train episode 47162: reward = -63.00, steps = 31 09:29:46 [INFO] train episode 47163: reward = -27.49, steps = 32 09:29:47 [INFO] train episode 47164: reward = -60.01, steps = 20 09:29:51 [INFO] train episode 47165: reward = -57.36, steps = 42 09:29:54 [INFO] train episode 47166: reward = -40.70, steps = 39 09:29:57 [INFO] train episode 47167: reward = -41.64, steps = 34 09:29:59 [INFO] train episode 47168: reward = -39.42, steps = 20 09:30:01 [INFO] train episode 47169: reward = -55.74, steps = 19 09:30:03 [INFO] train episode 47170: reward = -47.35, steps = 25 09:30:06 [INFO] train episode 47171: reward = -42.43, steps = 33 09:30:09 [INFO] train episode 47172: reward = -41.61, steps = 39 09:30:12 [INFO] train episode 47173: reward = -113.66, steps = 42 09:30:16 [INFO] train episode 47174: reward = -49.05, steps = 37 09:30:18 [INFO] train episode 47175: reward = -61.01, steps = 30 09:30:21 [INFO] train episode 47176: reward = -34.33, steps = 34 09:30:23 [INFO] train episode 47177: reward = -46.71, steps = 22 09:30:25 [INFO] train episode 47178: reward = -72.43, steps = 18 09:30:27 [INFO] train episode 47179: reward = -44.29, steps = 21 09:30:30 [INFO] train episode 47180: reward = -39.82, steps = 36 09:30:33 [INFO] train episode 47181: reward = -64.03, steps = 35 09:30:36 [INFO] train episode 47182: reward = -39.82, steps = 31 09:30:38 [INFO] train episode 47183: reward = -71.40, steps = 24 09:30:40 [INFO] train episode 47184: reward = -23.88, steps = 20 09:30:42 [INFO] train episode 47185: reward = -50.95, steps = 28 09:30:44 [INFO] train episode 47186: reward = -57.78, steps = 24 09:30:47 [INFO] train episode 47187: reward = -56.05, steps = 27 09:30:49 [INFO] train episode 47188: reward = -45.13, steps = 21 09:30:52 [INFO] train episode 47189: reward = -43.28, steps = 41 09:30:55 [INFO] train episode 47190: reward = -66.72, steps = 28 09:30:58 [INFO] train episode 47191: reward = -45.44, steps = 42 09:31:01 [INFO] train episode 47192: reward = -53.65, steps = 38 09:31:04 [INFO] train episode 47193: reward = -60.43, steps = 31 09:31:07 [INFO] train episode 47194: reward = -16.69, steps = 32 09:31:11 [INFO] train episode 47195: reward = -63.90, steps = 44 09:31:13 [INFO] train episode 47196: reward = -35.09, steps = 21 09:31:14 [INFO] train episode 47197: reward = -51.51, steps = 20 09:31:17 [INFO] train episode 47198: reward = -50.88, steps = 26 09:31:20 [INFO] train episode 47199: reward = -71.42, steps = 32 09:31:21 [INFO] train episode 47200: reward = -54.82, steps = 21 09:31:24 [INFO] train episode 47201: reward = -68.95, steps = 25 09:31:27 [INFO] train episode 47202: reward = -51.48, steps = 39 09:31:29 [INFO] train episode 47203: reward = -34.24, steps = 25 09:31:31 [INFO] train episode 47204: reward = -48.05, steps = 25 09:31:33 [INFO] train episode 47205: reward = -46.91, steps = 20 09:31:36 [INFO] train episode 47206: reward = -60.62, steps = 22 09:31:38 [INFO] train episode 47207: reward = -32.30, steps = 23 09:31:40 [INFO] train episode 47208: reward = -72.47, steps = 28 09:31:43 [INFO] train episode 47209: reward = -75.08, steps = 29 09:31:45 [INFO] train episode 47210: reward = -81.15, steps = 33 09:31:48 [INFO] train episode 47211: reward = -55.24, steps = 26 09:31:50 [INFO] train episode 47212: reward = -47.27, steps = 31 09:31:53 [INFO] train episode 47213: reward = -67.74, steps = 32 09:31:56 [INFO] train episode 47214: reward = -48.83, steps = 26 09:31:58 [INFO] train episode 47215: reward = -56.14, steps = 23 09:31:59 [INFO] train episode 47216: reward = -42.16, steps = 22 09:32:02 [INFO] train episode 47217: reward = -54.50, steps = 27 09:32:04 [INFO] train episode 47218: reward = -59.57, steps = 21 09:32:06 [INFO] train episode 47219: reward = -73.90, steps = 23 09:32:09 [INFO] train episode 47220: reward = -70.16, steps = 39 09:32:13 [INFO] train episode 47221: reward = -117.03, steps = 47 09:32:16 [INFO] train episode 47222: reward = -80.92, steps = 39 09:32:18 [INFO] train episode 47223: reward = -50.70, steps = 21 09:32:21 [INFO] train episode 47224: reward = -39.87, steps = 26 09:32:25 [INFO] train episode 47225: reward = -99.14, steps = 53 09:32:29 [INFO] train episode 47226: reward = -105.97, steps = 38 09:32:30 [INFO] train episode 47227: reward = -56.23, steps = 22 09:32:32 [INFO] train episode 47228: reward = -86.03, steps = 19 09:32:35 [INFO] train episode 47229: reward = -40.56, steps = 36 09:32:37 [INFO] train episode 47230: reward = -86.71, steps = 21 09:32:40 [INFO] train episode 47231: reward = -101.79, steps = 33 09:32:42 [INFO] train episode 47232: reward = -41.00, steps = 20 09:32:44 [INFO] train episode 47233: reward = -58.69, steps = 22 09:32:46 [INFO] train episode 47234: reward = -64.47, steps = 23 09:32:48 [INFO] train episode 47235: reward = -72.17, steps = 20 09:32:51 [INFO] train episode 47236: reward = -60.27, steps = 42 09:32:55 [INFO] train episode 47237: reward = -20.11, steps = 35 09:32:59 [INFO] train episode 47238: reward = -83.66, steps = 53 09:33:01 [INFO] train episode 47239: reward = -54.52, steps = 20 09:33:04 [INFO] train episode 47240: reward = -62.90, steps = 37 09:33:07 [INFO] train episode 47241: reward = -60.90, steps = 34 09:33:09 [INFO] train episode 47242: reward = -43.85, steps = 22 09:33:13 [INFO] train episode 47243: reward = -69.41, steps = 38 09:33:14 [INFO] train episode 47244: reward = -55.27, steps = 22 09:33:16 [INFO] train episode 47245: reward = -64.78, steps = 18 09:33:19 [INFO] train episode 47246: reward = -64.62, steps = 39 09:33:21 [INFO] train episode 47247: reward = -54.79, steps = 21 09:33:23 [INFO] train episode 47248: reward = -43.53, steps = 23 09:33:27 [INFO] train episode 47249: reward = -63.69, steps = 37 09:33:29 [INFO] train episode 47250: reward = -51.81, steps = 27 09:33:32 [INFO] train episode 47251: reward = -45.71, steps = 37 09:33:35 [INFO] train episode 47252: reward = -60.61, steps = 30 09:33:37 [INFO] train episode 47253: reward = -36.41, steps = 28 09:33:39 [INFO] train episode 47254: reward = -50.72, steps = 25 09:33:42 [INFO] train episode 47255: reward = -62.73, steps = 29 09:33:45 [INFO] train episode 47256: reward = -72.88, steps = 32 09:33:48 [INFO] train episode 47257: reward = -35.25, steps = 36 09:33:50 [INFO] train episode 47258: reward = -34.39, steps = 27 09:33:52 [INFO] train episode 47259: reward = -44.75, steps = 22 09:33:54 [INFO] train episode 47260: reward = -57.99, steps = 21 09:33:58 [INFO] train episode 47261: reward = -54.28, steps = 48 09:34:00 [INFO] train episode 47262: reward = -44.77, steps = 26 09:34:03 [INFO] train episode 47263: reward = -86.83, steps = 40 09:34:05 [INFO] train episode 47264: reward = -53.44, steps = 20 09:34:07 [INFO] train episode 47265: reward = -37.31, steps = 21 09:34:09 [INFO] train episode 47266: reward = -53.58, steps = 22 09:34:12 [INFO] train episode 47267: reward = -39.44, steps = 39 09:34:15 [INFO] train episode 47268: reward = -62.59, steps = 30 09:34:17 [INFO] train episode 47269: reward = -38.03, steps = 22 09:34:19 [INFO] train episode 47270: reward = -62.31, steps = 22 09:34:21 [INFO] train episode 47271: reward = -53.37, steps = 27 09:34:23 [INFO] train episode 47272: reward = -40.46, steps = 21 09:34:25 [INFO] train episode 47273: reward = -48.40, steps = 22 09:34:29 [INFO] train episode 47274: reward = -43.27, steps = 41 09:34:32 [INFO] train episode 47275: reward = -42.56, steps = 36 09:34:35 [INFO] train episode 47276: reward = -45.89, steps = 31 09:34:37 [INFO] train episode 47277: reward = -36.59, steps = 22 09:34:39 [INFO] train episode 47278: reward = -89.15, steps = 26 09:34:42 [INFO] train episode 47279: reward = -69.70, steps = 31 09:34:44 [INFO] train episode 47280: reward = -64.43, steps = 26 09:34:46 [INFO] train episode 47281: reward = -48.52, steps = 23 09:34:48 [INFO] train episode 47282: reward = -62.65, steps = 21 09:34:50 [INFO] train episode 47283: reward = -46.09, steps = 25 09:34:53 [INFO] train episode 47284: reward = -49.28, steps = 32 09:34:55 [INFO] train episode 47285: reward = -65.36, steps = 19 09:34:57 [INFO] train episode 47286: reward = -40.23, steps = 33 09:35:01 [INFO] train episode 47287: reward = -50.57, steps = 39 09:35:04 [INFO] train episode 47288: reward = -88.85, steps = 36 09:35:06 [INFO] train episode 47289: reward = -87.12, steps = 21 09:35:08 [INFO] train episode 47290: reward = -50.81, steps = 20 09:35:11 [INFO] train episode 47291: reward = -63.79, steps = 36 09:35:12 [INFO] train episode 47292: reward = -57.33, steps = 19 09:35:15 [INFO] train episode 47293: reward = -46.96, steps = 32 09:35:17 [INFO] train episode 47294: reward = -57.98, steps = 21 09:35:19 [INFO] train episode 47295: reward = -54.10, steps = 19 09:35:21 [INFO] train episode 47296: reward = -70.29, steps = 29 09:35:23 [INFO] train episode 47297: reward = -66.21, steps = 25 09:35:27 [INFO] train episode 47298: reward = -84.06, steps = 42 09:35:29 [INFO] train episode 47299: reward = -48.84, steps = 21 09:35:31 [INFO] train episode 47300: reward = -47.16, steps = 29 09:35:35 [INFO] train episode 47301: reward = -16.34, steps = 36 09:35:42 [INFO] train episode 47302: reward = -122.23, steps = 86 09:35:45 [INFO] train episode 47303: reward = -37.99, steps = 37 09:35:49 [INFO] train episode 47304: reward = -46.27, steps = 38 09:35:51 [INFO] train episode 47305: reward = -56.84, steps = 24 09:35:53 [INFO] train episode 47306: reward = -42.08, steps = 23 09:35:54 [INFO] train episode 47307: reward = -47.46, steps = 20 09:35:57 [INFO] train episode 47308: reward = -55.04, steps = 39 09:36:00 [INFO] train episode 47309: reward = -47.83, steps = 25 09:36:01 [INFO] train episode 47310: reward = -59.13, steps = 19 09:36:03 [INFO] train episode 47311: reward = -55.51, steps = 23 09:36:07 [INFO] train episode 47312: reward = -100.57, steps = 37 09:36:10 [INFO] train episode 47313: reward = -121.45, steps = 40 09:36:13 [INFO] train episode 47314: reward = -65.32, steps = 30 09:36:15 [INFO] train episode 47315: reward = -111.93, steps = 27 09:36:18 [INFO] train episode 47316: reward = -94.89, steps = 35 09:36:21 [INFO] train episode 47317: reward = -33.49, steps = 29 09:36:23 [INFO] train episode 47318: reward = -74.37, steps = 27 09:36:25 [INFO] train episode 47319: reward = -65.42, steps = 29 09:36:29 [INFO] train episode 47320: reward = -50.25, steps = 38 09:36:30 [INFO] train episode 47321: reward = -47.56, steps = 22 09:36:33 [INFO] train episode 47322: reward = -40.69, steps = 25 09:36:34 [INFO] train episode 47323: reward = -64.36, steps = 22 09:36:38 [INFO] train episode 47324: reward = -52.85, steps = 37 09:36:40 [INFO] train episode 47325: reward = -40.68, steps = 28 09:36:43 [INFO] train episode 47326: reward = -49.99, steps = 33 09:36:46 [INFO] train episode 47327: reward = -63.85, steps = 36 09:36:48 [INFO] train episode 47328: reward = -59.45, steps = 23 09:36:50 [INFO] train episode 47329: reward = -76.50, steps = 23 09:36:53 [INFO] train episode 47330: reward = -46.84, steps = 25 09:36:54 [INFO] train episode 47331: reward = -88.02, steps = 20 09:36:58 [INFO] train episode 47332: reward = -59.00, steps = 37 09:37:01 [INFO] train episode 47333: reward = -64.99, steps = 36 09:37:03 [INFO] train episode 47334: reward = -59.46, steps = 31 09:37:07 [INFO] train episode 47335: reward = -98.97, steps = 38 09:37:10 [INFO] train episode 47336: reward = -32.74, steps = 38 09:37:12 [INFO] train episode 47337: reward = -62.58, steps = 26 09:37:15 [INFO] train episode 47338: reward = -58.33, steps = 25 09:37:18 [INFO] train episode 47339: reward = -43.41, steps = 39 09:37:21 [INFO] train episode 47340: reward = -51.63, steps = 24 09:37:26 [INFO] train episode 47341: reward = -155.92, steps = 66 09:37:29 [INFO] train episode 47342: reward = -53.43, steps = 30 09:37:31 [INFO] train episode 47343: reward = -54.14, steps = 26 09:37:35 [INFO] train episode 47344: reward = -43.26, steps = 41 09:37:38 [INFO] train episode 47345: reward = -70.11, steps = 37 09:37:40 [INFO] train episode 47346: reward = -54.57, steps = 20 09:37:43 [INFO] train episode 47347: reward = -46.69, steps = 42 09:37:46 [INFO] train episode 47348: reward = -24.48, steps = 36 09:37:48 [INFO] train episode 47349: reward = -74.04, steps = 24 09:37:50 [INFO] train episode 47350: reward = -62.32, steps = 20 09:37:52 [INFO] train episode 47351: reward = -56.72, steps = 27 09:37:56 [INFO] train episode 47352: reward = -85.39, steps = 39 09:37:58 [INFO] train episode 47353: reward = -59.06, steps = 24 09:38:00 [INFO] train episode 47354: reward = -39.18, steps = 28 09:38:03 [INFO] train episode 47355: reward = -69.04, steps = 26 09:38:05 [INFO] train episode 47356: reward = -49.81, steps = 26 09:38:08 [INFO] train episode 47357: reward = -37.72, steps = 36 09:38:10 [INFO] train episode 47358: reward = -45.44, steps = 23 09:38:13 [INFO] train episode 47359: reward = -63.68, steps = 31 09:38:15 [INFO] train episode 47360: reward = -61.72, steps = 22 09:38:16 [INFO] train episode 47361: reward = -75.92, steps = 19 09:38:18 [INFO] train episode 47362: reward = -55.26, steps = 21 09:38:21 [INFO] train episode 47363: reward = -67.25, steps = 31 09:38:23 [INFO] train episode 47364: reward = -40.87, steps = 23 09:38:28 [INFO] train episode 47365: reward = -60.38, steps = 58 09:38:30 [INFO] train episode 47366: reward = -63.97, steps = 22 09:38:33 [INFO] train episode 47367: reward = -50.25, steps = 35 09:38:35 [INFO] train episode 47368: reward = -76.12, steps = 30 09:38:38 [INFO] train episode 47369: reward = -25.36, steps = 34 09:38:40 [INFO] train episode 47370: reward = -33.66, steps = 21 09:38:43 [INFO] train episode 47371: reward = -87.64, steps = 34 09:38:46 [INFO] train episode 47372: reward = -50.84, steps = 29 09:38:48 [INFO] train episode 47373: reward = -56.01, steps = 26 09:38:51 [INFO] train episode 47374: reward = -61.73, steps = 36 09:38:53 [INFO] train episode 47375: reward = -57.46, steps = 21 09:38:56 [INFO] train episode 47376: reward = -150.52, steps = 36 09:39:00 [INFO] train episode 47377: reward = -79.04, steps = 37 09:39:03 [INFO] train episode 47378: reward = -32.79, steps = 34 09:39:06 [INFO] train episode 47379: reward = -71.22, steps = 39 09:39:08 [INFO] train episode 47380: reward = -43.19, steps = 24 09:39:10 [INFO] train episode 47381: reward = -51.01, steps = 27 09:39:12 [INFO] train episode 47382: reward = -70.38, steps = 25 09:39:16 [INFO] train episode 47383: reward = -40.54, steps = 40 09:39:18 [INFO] train episode 47384: reward = -91.07, steps = 28 09:39:20 [INFO] train episode 47385: reward = -44.17, steps = 23 09:39:23 [INFO] train episode 47386: reward = -65.59, steps = 28 09:39:26 [INFO] train episode 47387: reward = -49.85, steps = 38 09:39:28 [INFO] train episode 47388: reward = -104.12, steps = 30 09:39:31 [INFO] train episode 47389: reward = -71.61, steps = 27 09:39:33 [INFO] train episode 47390: reward = -43.69, steps = 28 09:39:36 [INFO] train episode 47391: reward = -40.92, steps = 26 09:39:38 [INFO] train episode 47392: reward = -69.56, steps = 25 09:39:40 [INFO] train episode 47393: reward = -45.47, steps = 30 09:39:43 [INFO] train episode 47394: reward = -58.20, steps = 28 09:39:46 [INFO] train episode 47395: reward = -39.10, steps = 39 09:39:49 [INFO] train episode 47396: reward = -61.26, steps = 29 09:39:51 [INFO] train episode 47397: reward = -36.03, steps = 27 09:39:55 [INFO] train episode 47398: reward = -62.91, steps = 41 09:39:57 [INFO] train episode 47399: reward = -23.75, steps = 27 09:40:00 [INFO] train episode 47400: reward = -58.66, steps = 31 09:40:02 [INFO] train episode 47401: reward = -61.91, steps = 20 09:40:06 [INFO] train episode 47402: reward = -36.06, steps = 42 09:40:08 [INFO] train episode 47403: reward = -49.58, steps = 23 09:40:10 [INFO] train episode 47404: reward = -72.95, steps = 24 09:40:12 [INFO] train episode 47405: reward = -46.57, steps = 25 09:40:15 [INFO] train episode 47406: reward = -49.49, steps = 29 09:40:18 [INFO] train episode 47407: reward = -84.19, steps = 33 09:40:21 [INFO] train episode 47408: reward = -39.92, steps = 36 09:40:23 [INFO] train episode 47409: reward = -49.80, steps = 20 09:40:25 [INFO] train episode 47410: reward = -39.79, steps = 26 09:40:28 [INFO] train episode 47411: reward = -85.45, steps = 36 09:40:30 [INFO] train episode 47412: reward = -40.36, steps = 26 09:40:32 [INFO] train episode 47413: reward = -69.85, steps = 26 09:40:35 [INFO] train episode 47414: reward = -87.68, steps = 29 09:40:37 [INFO] train episode 47415: reward = -79.56, steps = 22 09:40:39 [INFO] train episode 47416: reward = -53.29, steps = 24 09:40:42 [INFO] train episode 47417: reward = -35.04, steps = 28 09:40:45 [INFO] train episode 47418: reward = -37.25, steps = 42 09:40:48 [INFO] train episode 47419: reward = -21.65, steps = 24 09:40:51 [INFO] train episode 47420: reward = -56.97, steps = 30 09:40:53 [INFO] train episode 47421: reward = -90.45, steps = 34 09:40:56 [INFO] train episode 47422: reward = -45.66, steps = 30 09:40:58 [INFO] train episode 47423: reward = -36.69, steps = 24 09:41:01 [INFO] train episode 47424: reward = -37.87, steps = 36 09:41:03 [INFO] train episode 47425: reward = -70.43, steps = 20 09:41:05 [INFO] train episode 47426: reward = -41.54, steps = 22 09:41:07 [INFO] train episode 47427: reward = -36.06, steps = 26 09:41:11 [INFO] train episode 47428: reward = -70.02, steps = 42 09:41:13 [INFO] train episode 47429: reward = -61.01, steps = 20 09:41:15 [INFO] train episode 47430: reward = -65.83, steps = 28 09:41:17 [INFO] train episode 47431: reward = -36.40, steps = 21 09:41:19 [INFO] train episode 47432: reward = -72.65, steps = 23 09:41:21 [INFO] train episode 47433: reward = -54.18, steps = 28 09:41:24 [INFO] train episode 47434: reward = -41.30, steps = 30 09:41:27 [INFO] train episode 47435: reward = -52.83, steps = 41 09:41:29 [INFO] train episode 47436: reward = -61.16, steps = 23 09:41:31 [INFO] train episode 47437: reward = -39.37, steps = 22 09:41:33 [INFO] train episode 47438: reward = -53.91, steps = 20 09:41:35 [INFO] train episode 47439: reward = -60.91, steps = 23 09:41:38 [INFO] train episode 47440: reward = -57.21, steps = 35 09:41:40 [INFO] train episode 47441: reward = -68.44, steps = 22 09:41:42 [INFO] train episode 47442: reward = -42.89, steps = 25 09:41:44 [INFO] train episode 47443: reward = -32.89, steps = 20 09:41:46 [INFO] train episode 47444: reward = -19.28, steps = 22 09:41:50 [INFO] train episode 47445: reward = -55.06, steps = 45 09:41:51 [INFO] train episode 47446: reward = -42.27, steps = 20 09:41:54 [INFO] train episode 47447: reward = -47.35, steps = 26 09:41:56 [INFO] train episode 47448: reward = -93.05, steps = 19 09:41:59 [INFO] train episode 47449: reward = -52.26, steps = 41 09:42:01 [INFO] train episode 47450: reward = -45.33, steps = 20 09:42:05 [INFO] train episode 47451: reward = -113.84, steps = 46 09:42:08 [INFO] train episode 47452: reward = -58.12, steps = 35 09:42:12 [INFO] train episode 47453: reward = -45.35, steps = 41 09:42:13 [INFO] train episode 47454: reward = -44.61, steps = 20 09:42:15 [INFO] train episode 47455: reward = -65.07, steps = 24 09:42:18 [INFO] train episode 47456: reward = -48.43, steps = 28 09:42:21 [INFO] train episode 47457: reward = -65.29, steps = 36 09:42:23 [INFO] train episode 47458: reward = -57.74, steps = 27 09:42:26 [INFO] train episode 47459: reward = -45.22, steps = 26 09:42:29 [INFO] train episode 47460: reward = -62.74, steps = 35 09:42:31 [INFO] train episode 47461: reward = -38.70, steps = 27 09:42:33 [INFO] train episode 47462: reward = -67.57, steps = 24 09:42:36 [INFO] train episode 47463: reward = -36.66, steps = 29 09:42:38 [INFO] train episode 47464: reward = -37.24, steps = 26 09:42:41 [INFO] train episode 47465: reward = -58.47, steps = 37 09:42:44 [INFO] train episode 47466: reward = -58.06, steps = 35 09:42:46 [INFO] train episode 47467: reward = -46.93, steps = 19 09:42:48 [INFO] train episode 47468: reward = -39.95, steps = 21 09:42:50 [INFO] train episode 47469: reward = -37.24, steps = 21 09:42:53 [INFO] train episode 47470: reward = -53.94, steps = 36 09:42:57 [INFO] train episode 47471: reward = -74.56, steps = 33 09:42:58 [INFO] train episode 47472: reward = -50.88, steps = 20 09:43:00 [INFO] train episode 47473: reward = -38.67, steps = 22 09:43:03 [INFO] train episode 47474: reward = -43.00, steps = 32 09:43:05 [INFO] train episode 47475: reward = -52.23, steps = 20 09:43:08 [INFO] train episode 47476: reward = -76.26, steps = 38 09:43:10 [INFO] train episode 47477: reward = -65.93, steps = 20 09:43:15 [INFO] train episode 47478: reward = -70.24, steps = 53 09:43:17 [INFO] train episode 47479: reward = -66.61, steps = 30 09:43:19 [INFO] train episode 47480: reward = -38.89, steps = 22 09:43:22 [INFO] train episode 47481: reward = -56.08, steps = 37 09:43:24 [INFO] train episode 47482: reward = -49.97, steps = 19 09:43:25 [INFO] train episode 47483: reward = -37.53, steps = 21 09:43:27 [INFO] train episode 47484: reward = -47.36, steps = 21 09:43:29 [INFO] train episode 47485: reward = -35.27, steps = 21 09:43:32 [INFO] train episode 47486: reward = -50.80, steps = 32 09:43:34 [INFO] train episode 47487: reward = -54.63, steps = 22 09:43:36 [INFO] train episode 47488: reward = -67.70, steps = 25 09:43:40 [INFO] train episode 47489: reward = -54.49, steps = 40 09:43:42 [INFO] train episode 47490: reward = -56.60, steps = 28 09:43:45 [INFO] train episode 47491: reward = -55.30, steps = 28 09:43:47 [INFO] train episode 47492: reward = -49.99, steps = 23 09:43:50 [INFO] train episode 47493: reward = -28.04, steps = 39 09:43:52 [INFO] train episode 47494: reward = -51.04, steps = 24 09:43:54 [INFO] train episode 47495: reward = -66.09, steps = 29 09:43:58 [INFO] train episode 47496: reward = -51.19, steps = 37 09:44:00 [INFO] train episode 47497: reward = -47.73, steps = 29 09:44:03 [INFO] train episode 47498: reward = -45.69, steps = 28 09:44:05 [INFO] train episode 47499: reward = -51.99, steps = 24 09:44:07 [INFO] train episode 47500: reward = -22.83, steps = 24 09:44:10 [INFO] train episode 47501: reward = -53.54, steps = 31 09:44:13 [INFO] train episode 47502: reward = -53.08, steps = 40 09:44:16 [INFO] train episode 47503: reward = -71.58, steps = 37 09:44:19 [INFO] train episode 47504: reward = -40.23, steps = 31 09:44:21 [INFO] train episode 47505: reward = -79.53, steps = 22 09:44:24 [INFO] train episode 47506: reward = -82.49, steps = 31 09:44:25 [INFO] train episode 47507: reward = -49.29, steps = 21 09:44:28 [INFO] train episode 47508: reward = -50.23, steps = 34 09:44:30 [INFO] train episode 47509: reward = -32.30, steps = 21 09:44:33 [INFO] train episode 47510: reward = -54.31, steps = 28 09:44:35 [INFO] train episode 47511: reward = -75.78, steps = 30 09:44:38 [INFO] train episode 47512: reward = -41.75, steps = 26 09:44:41 [INFO] train episode 47513: reward = -41.72, steps = 34 09:44:43 [INFO] train episode 47514: reward = -61.61, steps = 25 09:44:47 [INFO] train episode 47515: reward = -101.27, steps = 44 09:44:49 [INFO] train episode 47516: reward = -53.53, steps = 19 09:44:52 [INFO] train episode 47517: reward = -86.67, steps = 45 09:44:54 [INFO] train episode 47518: reward = -38.39, steps = 20 09:44:57 [INFO] train episode 47519: reward = -55.70, steps = 30 09:45:03 [INFO] train episode 47520: reward = -117.90, steps = 69 09:45:05 [INFO] train episode 47521: reward = -81.36, steps = 29 09:45:08 [INFO] train episode 47522: reward = -49.27, steps = 31 09:45:10 [INFO] train episode 47523: reward = -65.84, steps = 20 09:45:12 [INFO] train episode 47524: reward = -74.21, steps = 35 09:45:14 [INFO] train episode 47525: reward = -52.97, steps = 20 09:45:17 [INFO] train episode 47526: reward = -65.03, steps = 32 09:45:20 [INFO] train episode 47527: reward = -39.36, steps = 24 09:45:22 [INFO] train episode 47528: reward = -66.97, steps = 23 09:45:25 [INFO] train episode 47529: reward = -61.86, steps = 40 09:45:27 [INFO] train episode 47530: reward = -42.74, steps = 23 09:45:29 [INFO] train episode 47531: reward = -59.50, steps = 22 09:45:32 [INFO] train episode 47532: reward = -54.19, steps = 36 09:45:34 [INFO] train episode 47533: reward = -56.43, steps = 21 09:45:37 [INFO] train episode 47534: reward = -38.96, steps = 26 09:45:40 [INFO] train episode 47535: reward = -59.82, steps = 44 09:45:43 [INFO] train episode 47536: reward = -70.48, steps = 28 09:45:48 [INFO] train episode 47537: reward = -73.74, steps = 47 09:45:50 [INFO] train episode 47538: reward = -70.10, steps = 25 09:45:52 [INFO] train episode 47539: reward = -82.28, steps = 23 09:45:54 [INFO] train episode 47540: reward = -49.17, steps = 26 09:45:57 [INFO] train episode 47541: reward = -58.43, steps = 36 09:46:00 [INFO] train episode 47542: reward = -58.20, steps = 33 09:46:03 [INFO] train episode 47543: reward = -62.50, steps = 37 09:46:06 [INFO] train episode 47544: reward = -97.76, steps = 35 09:46:09 [INFO] train episode 47545: reward = -37.23, steps = 21 09:46:11 [INFO] train episode 47546: reward = -61.67, steps = 25 09:46:13 [INFO] train episode 47547: reward = -38.99, steps = 32 09:46:17 [INFO] train episode 47548: reward = -76.73, steps = 38 09:46:19 [INFO] train episode 47549: reward = -48.23, steps = 23 09:46:22 [INFO] train episode 47550: reward = -60.63, steps = 36 09:46:26 [INFO] train episode 47551: reward = -51.00, steps = 41 09:46:28 [INFO] train episode 47552: reward = -46.69, steps = 25 09:46:31 [INFO] train episode 47553: reward = -74.04, steps = 36 09:46:33 [INFO] train episode 47554: reward = -77.41, steps = 30 09:46:36 [INFO] train episode 47555: reward = -81.29, steps = 35 09:46:38 [INFO] train episode 47556: reward = -48.68, steps = 21 09:46:41 [INFO] train episode 47557: reward = -71.52, steps = 28 09:46:44 [INFO] train episode 47558: reward = -66.98, steps = 32 09:46:46 [INFO] train episode 47559: reward = -64.72, steps = 31 09:46:49 [INFO] train episode 47560: reward = -44.33, steps = 27 09:46:50 [INFO] train episode 47561: reward = -69.03, steps = 18 09:46:52 [INFO] train episode 47562: reward = -53.41, steps = 19 09:46:56 [INFO] train episode 47563: reward = -28.75, steps = 39 09:46:58 [INFO] train episode 47564: reward = -54.07, steps = 28 09:47:01 [INFO] train episode 47565: reward = -37.65, steps = 41 09:47:04 [INFO] train episode 47566: reward = -68.18, steps = 31 09:47:07 [INFO] train episode 47567: reward = -49.33, steps = 35 09:47:09 [INFO] train episode 47568: reward = -46.22, steps = 26 09:47:14 [INFO] train episode 47569: reward = -118.41, steps = 53 09:47:17 [INFO] train episode 47570: reward = -74.93, steps = 39 09:47:19 [INFO] train episode 47571: reward = -43.55, steps = 23 09:47:22 [INFO] train episode 47572: reward = -27.56, steps = 38 09:47:24 [INFO] train episode 47573: reward = -46.28, steps = 16 09:47:26 [INFO] train episode 47574: reward = -45.60, steps = 23 09:47:28 [INFO] train episode 47575: reward = -57.31, steps = 27 09:47:32 [INFO] train episode 47576: reward = -48.53, steps = 41 09:47:34 [INFO] train episode 47577: reward = -53.44, steps = 27 09:47:37 [INFO] train episode 47578: reward = -74.43, steps = 33 09:47:39 [INFO] train episode 47579: reward = -31.68, steps = 29 09:47:42 [INFO] train episode 47580: reward = -78.05, steps = 32 09:47:46 [INFO] train episode 47581: reward = -68.12, steps = 40 09:47:48 [INFO] train episode 47582: reward = -43.01, steps = 21 09:47:50 [INFO] train episode 47583: reward = -43.02, steps = 35 09:47:53 [INFO] train episode 47584: reward = -23.08, steps = 32 09:47:56 [INFO] train episode 47585: reward = -51.44, steps = 30 09:47:57 [INFO] train episode 47586: reward = -48.72, steps = 20 09:48:01 [INFO] train episode 47587: reward = -24.81, steps = 34 09:48:04 [INFO] train episode 47588: reward = -62.75, steps = 34 09:48:06 [INFO] train episode 47589: reward = -49.10, steps = 23 09:48:08 [INFO] train episode 47590: reward = -46.64, steps = 25 09:48:10 [INFO] train episode 47591: reward = -52.06, steps = 29 09:48:12 [INFO] train episode 47592: reward = -49.71, steps = 21 09:48:15 [INFO] train episode 47593: reward = -55.54, steps = 30 09:48:17 [INFO] train episode 47594: reward = -41.14, steps = 27 09:48:20 [INFO] train episode 47595: reward = -47.58, steps = 32 09:48:23 [INFO] train episode 47596: reward = -57.78, steps = 37 09:48:25 [INFO] train episode 47597: reward = -46.17, steps = 22 09:48:28 [INFO] train episode 47598: reward = -62.16, steps = 39 09:48:31 [INFO] train episode 47599: reward = -89.51, steps = 27 09:48:33 [INFO] train episode 47600: reward = -39.91, steps = 28 09:48:37 [INFO] train episode 47601: reward = -66.02, steps = 40 09:48:39 [INFO] train episode 47602: reward = -33.09, steps = 17 09:48:43 [INFO] train episode 47603: reward = -39.37, steps = 47 09:48:45 [INFO] train episode 47604: reward = -52.87, steps = 25 09:48:48 [INFO] train episode 47605: reward = -43.44, steps = 37 09:48:50 [INFO] train episode 47606: reward = -32.89, steps = 23 09:48:53 [INFO] train episode 47607: reward = -55.16, steps = 33 09:48:58 [INFO] train episode 47608: reward = -76.71, steps = 55 09:49:01 [INFO] train episode 47609: reward = -26.21, steps = 37 09:49:04 [INFO] train episode 47610: reward = -58.34, steps = 31 09:49:07 [INFO] train episode 47611: reward = -90.81, steps = 39 09:49:10 [INFO] train episode 47612: reward = -80.21, steps = 37 09:49:14 [INFO] train episode 47613: reward = -83.48, steps = 51 09:49:16 [INFO] train episode 47614: reward = -49.11, steps = 20 09:49:18 [INFO] train episode 47615: reward = -40.60, steps = 20 09:49:21 [INFO] train episode 47616: reward = -78.23, steps = 26 09:49:24 [INFO] train episode 47617: reward = -50.78, steps = 38 09:49:27 [INFO] train episode 47618: reward = -73.62, steps = 33 09:49:28 [INFO] train episode 47619: reward = -46.95, steps = 21 09:49:31 [INFO] train episode 47620: reward = -53.51, steps = 28 09:49:33 [INFO] train episode 47621: reward = -60.03, steps = 22 09:49:35 [INFO] train episode 47622: reward = -63.16, steps = 24 09:49:39 [INFO] train episode 47623: reward = -37.81, steps = 49 09:49:42 [INFO] train episode 47624: reward = -31.22, steps = 33 09:49:45 [INFO] train episode 47625: reward = -49.33, steps = 35 09:49:47 [INFO] train episode 47626: reward = -29.68, steps = 24 09:49:50 [INFO] train episode 47627: reward = -73.45, steps = 26 09:49:51 [INFO] train episode 47628: reward = -50.29, steps = 20 09:49:52 [INFO] train episode 47629: reward = -64.52, steps = 12 09:49:54 [INFO] train episode 47630: reward = -54.33, steps = 23 09:49:57 [INFO] train episode 47631: reward = -53.52, steps = 36 09:50:02 [INFO] train episode 47632: reward = -91.75, steps = 54 09:50:05 [INFO] train episode 47633: reward = -52.94, steps = 34 09:50:07 [INFO] train episode 47634: reward = -47.03, steps = 24 09:50:10 [INFO] train episode 47635: reward = -42.86, steps = 37 09:50:13 [INFO] train episode 47636: reward = -87.65, steps = 36 09:50:16 [INFO] train episode 47637: reward = -69.91, steps = 31 09:50:18 [INFO] train episode 47638: reward = -77.47, steps = 28 09:50:22 [INFO] train episode 47639: reward = -81.30, steps = 47 09:50:25 [INFO] train episode 47640: reward = -43.47, steps = 33 09:50:28 [INFO] train episode 47641: reward = -100.29, steps = 37 09:50:31 [INFO] train episode 47642: reward = -35.96, steps = 27 09:50:33 [INFO] train episode 47643: reward = -37.83, steps = 27 09:50:36 [INFO] train episode 47644: reward = -76.94, steps = 32 09:50:38 [INFO] train episode 47645: reward = -52.07, steps = 19 09:50:42 [INFO] train episode 47646: reward = -52.09, steps = 49 09:50:44 [INFO] train episode 47647: reward = -71.19, steps = 29 09:50:47 [INFO] train episode 47648: reward = -88.48, steps = 30 09:50:49 [INFO] train episode 47649: reward = -73.87, steps = 26 09:50:53 [INFO] train episode 47650: reward = -65.94, steps = 37 09:50:55 [INFO] train episode 47651: reward = -87.58, steps = 24 09:50:57 [INFO] train episode 47652: reward = -62.45, steps = 32 09:51:00 [INFO] train episode 47653: reward = -51.07, steps = 28 09:51:04 [INFO] train episode 47654: reward = -76.92, steps = 45 09:51:05 [INFO] train episode 47655: reward = -63.25, steps = 22 09:51:09 [INFO] train episode 47656: reward = -57.42, steps = 36 09:51:11 [INFO] train episode 47657: reward = -50.06, steps = 21 09:51:14 [INFO] train episode 47658: reward = -48.50, steps = 34 09:51:17 [INFO] train episode 47659: reward = -46.92, steps = 40 09:51:19 [INFO] train episode 47660: reward = -27.45, steps = 28 09:51:21 [INFO] train episode 47661: reward = -38.89, steps = 25 09:51:25 [INFO] train episode 47662: reward = -25.80, steps = 42 09:51:28 [INFO] train episode 47663: reward = -58.95, steps = 21 09:51:30 [INFO] train episode 47664: reward = -64.65, steps = 28 09:51:33 [INFO] train episode 47665: reward = -37.71, steps = 36 09:51:36 [INFO] train episode 47666: reward = -54.07, steps = 35 09:51:38 [INFO] train episode 47667: reward = -57.81, steps = 25 09:51:41 [INFO] train episode 47668: reward = -59.57, steps = 33 09:51:43 [INFO] train episode 47669: reward = -54.94, steps = 24 09:51:45 [INFO] train episode 47670: reward = -50.58, steps = 23 09:51:49 [INFO] train episode 47671: reward = -42.82, steps = 40 09:51:51 [INFO] train episode 47672: reward = -43.41, steps = 21 09:51:54 [INFO] train episode 47673: reward = -52.18, steps = 39 09:51:56 [INFO] train episode 47674: reward = -51.63, steps = 20 09:51:59 [INFO] train episode 47675: reward = -45.07, steps = 37 09:52:02 [INFO] train episode 47676: reward = -46.36, steps = 38 09:52:04 [INFO] train episode 47677: reward = -58.65, steps = 21 09:52:06 [INFO] train episode 47678: reward = -54.24, steps = 28 09:52:10 [INFO] train episode 47679: reward = -39.13, steps = 41 09:52:13 [INFO] train episode 47680: reward = -56.79, steps = 33 09:52:16 [INFO] train episode 47681: reward = -42.68, steps = 33 09:52:18 [INFO] train episode 47682: reward = -74.22, steps = 21 09:52:20 [INFO] train episode 47683: reward = -32.83, steps = 26 09:52:22 [INFO] train episode 47684: reward = -57.96, steps = 31 09:52:25 [INFO] train episode 47685: reward = -77.99, steps = 34 09:52:30 [INFO] train episode 47686: reward = -92.41, steps = 46 09:52:32 [INFO] train episode 47687: reward = -54.03, steps = 34 09:52:34 [INFO] train episode 47688: reward = -54.59, steps = 20 09:52:37 [INFO] train episode 47689: reward = -45.33, steps = 28 09:52:39 [INFO] train episode 47690: reward = -38.11, steps = 23 09:52:41 [INFO] train episode 47691: reward = -50.32, steps = 27 09:52:43 [INFO] train episode 47692: reward = -53.24, steps = 25 09:52:45 [INFO] train episode 47693: reward = -50.84, steps = 20 09:52:47 [INFO] train episode 47694: reward = -43.50, steps = 21 09:52:50 [INFO] train episode 47695: reward = -38.48, steps = 29 09:52:52 [INFO] train episode 47696: reward = -72.32, steps = 25 09:52:53 [INFO] train episode 47697: reward = -50.56, steps = 20 09:52:56 [INFO] train episode 47698: reward = -43.98, steps = 28 09:52:58 [INFO] train episode 47699: reward = -52.72, steps = 23 09:53:01 [INFO] train episode 47700: reward = -48.34, steps = 27 09:53:04 [INFO] train episode 47701: reward = -110.24, steps = 40 09:53:06 [INFO] train episode 47702: reward = -61.90, steps = 24 09:53:08 [INFO] train episode 47703: reward = -91.16, steps = 22 09:53:11 [INFO] train episode 47704: reward = -51.27, steps = 37 09:53:13 [INFO] train episode 47705: reward = -47.76, steps = 21 09:53:16 [INFO] train episode 47706: reward = -40.39, steps = 33 09:53:18 [INFO] train episode 47707: reward = -58.65, steps = 22 09:53:20 [INFO] train episode 47708: reward = -36.50, steps = 30 09:53:22 [INFO] train episode 47709: reward = -63.96, steps = 18 09:53:25 [INFO] train episode 47710: reward = -59.57, steps = 38 09:53:27 [INFO] train episode 47711: reward = -40.91, steps = 20 09:53:29 [INFO] train episode 47712: reward = -32.84, steps = 24 09:53:32 [INFO] train episode 47713: reward = -71.92, steps = 41 09:53:34 [INFO] train episode 47714: reward = -41.98, steps = 24 09:53:37 [INFO] train episode 47715: reward = -54.56, steps = 32 09:53:39 [INFO] train episode 47716: reward = -38.82, steps = 25 09:53:41 [INFO] train episode 47717: reward = -43.30, steps = 23 09:53:44 [INFO] train episode 47718: reward = -55.37, steps = 35 09:53:48 [INFO] train episode 47719: reward = -45.34, steps = 37 09:53:50 [INFO] train episode 47720: reward = -74.61, steps = 25 09:53:51 [INFO] train episode 47721: reward = -46.42, steps = 20 09:53:54 [INFO] train episode 47722: reward = -44.04, steps = 26 09:53:58 [INFO] train episode 47723: reward = -73.31, steps = 52 09:54:01 [INFO] train episode 47724: reward = -48.91, steps = 37 09:54:05 [INFO] train episode 47725: reward = -55.92, steps = 39 09:54:06 [INFO] train episode 47726: reward = -59.43, steps = 21 09:54:11 [INFO] train episode 47727: reward = -56.09, steps = 56 09:54:13 [INFO] train episode 47728: reward = -49.72, steps = 21 09:54:18 [INFO] train episode 47729: reward = -39.15, steps = 49 09:54:22 [INFO] train episode 47730: reward = -103.23, steps = 40 09:54:25 [INFO] train episode 47731: reward = -64.82, steps = 39 09:54:27 [INFO] train episode 47732: reward = -65.44, steps = 31 09:54:31 [INFO] train episode 47733: reward = -40.43, steps = 44 09:54:33 [INFO] train episode 47734: reward = -41.31, steps = 23 09:54:35 [INFO] train episode 47735: reward = -50.24, steps = 22 09:54:38 [INFO] train episode 47736: reward = -68.59, steps = 25 09:54:40 [INFO] train episode 47737: reward = -81.17, steps = 27 09:54:42 [INFO] train episode 47738: reward = -49.44, steps = 26 09:54:44 [INFO] train episode 47739: reward = -63.54, steps = 19 09:54:47 [INFO] train episode 47740: reward = -50.77, steps = 35 09:54:51 [INFO] train episode 47741: reward = -34.51, steps = 40 09:54:53 [INFO] train episode 47742: reward = -53.36, steps = 29 09:54:55 [INFO] train episode 47743: reward = -36.76, steps = 21 09:54:57 [INFO] train episode 47744: reward = -61.48, steps = 23 09:55:00 [INFO] train episode 47745: reward = -52.56, steps = 38 09:55:04 [INFO] train episode 47746: reward = -131.36, steps = 50 09:55:08 [INFO] train episode 47747: reward = -99.31, steps = 38 09:55:11 [INFO] train episode 47748: reward = -48.45, steps = 37 09:55:13 [INFO] train episode 47749: reward = -103.50, steps = 19 09:55:15 [INFO] train episode 47750: reward = -46.19, steps = 21 09:55:18 [INFO] train episode 47751: reward = -90.83, steps = 47 09:55:21 [INFO] train episode 47752: reward = -62.41, steps = 26 09:55:24 [INFO] train episode 47753: reward = -44.70, steps = 31 09:55:26 [INFO] train episode 47754: reward = -93.22, steps = 28 09:55:28 [INFO] train episode 47755: reward = -40.56, steps = 23 09:55:32 [INFO] train episode 47756: reward = -123.80, steps = 48 09:55:33 [INFO] train episode 47757: reward = -52.79, steps = 15 09:55:35 [INFO] train episode 47758: reward = -46.44, steps = 21 09:55:39 [INFO] train episode 47759: reward = -84.97, steps = 42 09:55:41 [INFO] train episode 47760: reward = -50.84, steps = 23 09:55:44 [INFO] train episode 47761: reward = -48.69, steps = 30 09:55:46 [INFO] train episode 47762: reward = -58.98, steps = 21 09:55:50 [INFO] train episode 47763: reward = -69.26, steps = 46 09:55:52 [INFO] train episode 47764: reward = -33.03, steps = 31 09:55:55 [INFO] train episode 47765: reward = -104.48, steps = 29 09:55:57 [INFO] train episode 47766: reward = -43.94, steps = 26 09:56:00 [INFO] train episode 47767: reward = -51.76, steps = 29 09:56:02 [INFO] train episode 47768: reward = -45.93, steps = 27 09:56:04 [INFO] train episode 47769: reward = -51.90, steps = 27 09:56:06 [INFO] train episode 47770: reward = -56.32, steps = 25 09:56:08 [INFO] train episode 47771: reward = -102.85, steps = 20 09:56:10 [INFO] train episode 47772: reward = -86.69, steps = 21 09:56:12 [INFO] train episode 47773: reward = -42.50, steps = 24 09:56:15 [INFO] train episode 47774: reward = -47.79, steps = 26 09:56:18 [INFO] train episode 47775: reward = -56.75, steps = 36 09:56:20 [INFO] train episode 47776: reward = -60.02, steps = 33 09:56:23 [INFO] train episode 47777: reward = -49.55, steps = 31 09:56:26 [INFO] train episode 47778: reward = -42.91, steps = 26 09:56:28 [INFO] train episode 47779: reward = -29.27, steps = 25 09:56:30 [INFO] train episode 47780: reward = -55.91, steps = 21 09:56:32 [INFO] train episode 47781: reward = -42.64, steps = 23 09:56:33 [INFO] train episode 47782: reward = -41.15, steps = 21 09:56:36 [INFO] train episode 47783: reward = -63.03, steps = 33 09:56:38 [INFO] train episode 47784: reward = -44.48, steps = 22 09:56:40 [INFO] train episode 47785: reward = -34.18, steps = 22 09:56:42 [INFO] train episode 47786: reward = -45.67, steps = 19 09:56:44 [INFO] train episode 47787: reward = -46.70, steps = 27 09:56:47 [INFO] train episode 47788: reward = -41.31, steps = 34 09:56:49 [INFO] train episode 47789: reward = -38.37, steps = 23 09:56:51 [INFO] train episode 47790: reward = -50.31, steps = 24 09:56:53 [INFO] train episode 47791: reward = -47.71, steps = 22 09:56:55 [INFO] train episode 47792: reward = -65.44, steps = 26 09:56:59 [INFO] train episode 47793: reward = -39.07, steps = 42 09:57:02 [INFO] train episode 47794: reward = -38.27, steps = 28 09:57:04 [INFO] train episode 47795: reward = -56.29, steps = 27 09:57:06 [INFO] train episode 47796: reward = -52.86, steps = 21 09:57:08 [INFO] train episode 47797: reward = -64.90, steps = 21 09:57:11 [INFO] train episode 47798: reward = -67.67, steps = 35 09:57:14 [INFO] train episode 47799: reward = -57.56, steps = 27 09:57:17 [INFO] train episode 47800: reward = -44.15, steps = 30 09:57:19 [INFO] train episode 47801: reward = -58.32, steps = 32 09:57:22 [INFO] train episode 47802: reward = -30.30, steps = 31 09:57:24 [INFO] train episode 47803: reward = -37.97, steps = 22 09:57:27 [INFO] train episode 47804: reward = -38.32, steps = 34 09:57:29 [INFO] train episode 47805: reward = -36.40, steps = 21 09:57:32 [INFO] train episode 47806: reward = -49.16, steps = 37 09:57:34 [INFO] train episode 47807: reward = -54.09, steps = 24 09:57:37 [INFO] train episode 47808: reward = -65.57, steps = 40 09:57:41 [INFO] train episode 47809: reward = -52.11, steps = 39 09:57:42 [INFO] train episode 47810: reward = -37.39, steps = 20 09:57:45 [INFO] train episode 47811: reward = -38.60, steps = 32 09:57:48 [INFO] train episode 47812: reward = -86.30, steps = 34 09:57:53 [INFO] train episode 47813: reward = -107.33, steps = 53 09:57:55 [INFO] train episode 47814: reward = -49.87, steps = 24 09:57:56 [INFO] train episode 47815: reward = -37.06, steps = 19 09:57:59 [INFO] train episode 47816: reward = -30.38, steps = 26 09:58:01 [INFO] train episode 47817: reward = -40.46, steps = 22 09:58:03 [INFO] train episode 47818: reward = -62.46, steps = 29 09:58:05 [INFO] train episode 47819: reward = -43.05, steps = 22 09:58:09 [INFO] train episode 47820: reward = -37.19, steps = 47 09:58:12 [INFO] train episode 47821: reward = -61.35, steps = 29 09:58:14 [INFO] train episode 47822: reward = -43.89, steps = 20 09:58:17 [INFO] train episode 47823: reward = -30.23, steps = 34 09:58:19 [INFO] train episode 47824: reward = -38.45, steps = 25 09:58:22 [INFO] train episode 47825: reward = -54.66, steps = 31 09:58:25 [INFO] train episode 47826: reward = -65.30, steps = 36 09:58:28 [INFO] train episode 47827: reward = -82.60, steps = 38 09:58:31 [INFO] train episode 47828: reward = -42.24, steps = 37 09:58:34 [INFO] train episode 47829: reward = -59.64, steps = 34 09:58:37 [INFO] train episode 47830: reward = -42.79, steps = 33 09:58:40 [INFO] train episode 47831: reward = -50.65, steps = 34 09:58:43 [INFO] train episode 47832: reward = -60.27, steps = 36 09:58:46 [INFO] train episode 47833: reward = -54.01, steps = 32 09:58:50 [INFO] train episode 47834: reward = -55.05, steps = 47 09:58:54 [INFO] train episode 47835: reward = -37.07, steps = 39 09:58:56 [INFO] train episode 47836: reward = -97.33, steps = 23 09:58:59 [INFO] train episode 47837: reward = -93.20, steps = 36 09:59:01 [INFO] train episode 47838: reward = -31.58, steps = 32 09:59:05 [INFO] train episode 47839: reward = -55.16, steps = 32 09:59:07 [INFO] train episode 47840: reward = -62.89, steps = 28 09:59:09 [INFO] train episode 47841: reward = -53.20, steps = 19 09:59:10 [INFO] train episode 47842: reward = -43.73, steps = 22 09:59:13 [INFO] train episode 47843: reward = -105.15, steps = 32 09:59:15 [INFO] train episode 47844: reward = -44.46, steps = 23 09:59:18 [INFO] train episode 47845: reward = -46.96, steps = 30 09:59:20 [INFO] train episode 47846: reward = -37.15, steps = 22 09:59:22 [INFO] train episode 47847: reward = -43.09, steps = 25 09:59:25 [INFO] train episode 47848: reward = -69.54, steps = 25 09:59:27 [INFO] train episode 47849: reward = -33.66, steps = 26 09:59:29 [INFO] train episode 47850: reward = -78.28, steps = 20 09:59:33 [INFO] train episode 47851: reward = -57.91, steps = 44 09:59:35 [INFO] train episode 47852: reward = -53.49, steps = 20 09:59:38 [INFO] train episode 47853: reward = -37.05, steps = 33 09:59:40 [INFO] train episode 47854: reward = -62.82, steps = 20 09:59:42 [INFO] train episode 47855: reward = -38.11, steps = 20 09:59:46 [INFO] train episode 47856: reward = -63.66, steps = 45 09:59:49 [INFO] train episode 47857: reward = -62.15, steps = 29 09:59:52 [INFO] train episode 47858: reward = -53.13, steps = 29 09:59:57 [INFO] train episode 47859: reward = -108.04, steps = 48 09:59:59 [INFO] train episode 47860: reward = -90.89, steps = 21 10:00:03 [INFO] train episode 47861: reward = -62.54, steps = 34 10:00:08 [INFO] train episode 47862: reward = -66.25, steps = 45 10:00:10 [INFO] train episode 47863: reward = -61.90, steps = 28 10:00:13 [INFO] train episode 47864: reward = -25.74, steps = 25 10:00:17 [INFO] train episode 47865: reward = -50.18, steps = 41 10:00:19 [INFO] train episode 47866: reward = -56.14, steps = 20 10:00:22 [INFO] train episode 47867: reward = -42.47, steps = 33 10:00:24 [INFO] train episode 47868: reward = -30.10, steps = 29 10:00:26 [INFO] train episode 47869: reward = -37.45, steps = 23 10:00:31 [INFO] train episode 47870: reward = -55.65, steps = 48 10:00:32 [INFO] train episode 47871: reward = -44.53, steps = 21 10:00:34 [INFO] train episode 47872: reward = -49.34, steps = 20 10:00:37 [INFO] train episode 47873: reward = -23.27, steps = 33 10:00:41 [INFO] train episode 47874: reward = -19.91, steps = 45 10:00:43 [INFO] train episode 47875: reward = -45.53, steps = 26 10:00:46 [INFO] train episode 47876: reward = -46.24, steps = 29 10:00:48 [INFO] train episode 47877: reward = -49.07, steps = 19 10:00:50 [INFO] train episode 47878: reward = -37.82, steps = 29 10:00:52 [INFO] train episode 47879: reward = -45.99, steps = 21 10:00:55 [INFO] train episode 47880: reward = -56.61, steps = 30 10:00:57 [INFO] train episode 47881: reward = -43.15, steps = 23 10:00:59 [INFO] train episode 47882: reward = -65.58, steps = 22 10:01:01 [INFO] train episode 47883: reward = -57.31, steps = 22 10:01:03 [INFO] train episode 47884: reward = -49.78, steps = 21 10:01:05 [INFO] train episode 47885: reward = -46.18, steps = 30 10:01:09 [INFO] train episode 47886: reward = -46.35, steps = 44 10:01:12 [INFO] train episode 47887: reward = -76.56, steps = 32 10:01:14 [INFO] train episode 47888: reward = -48.00, steps = 23 10:01:18 [INFO] train episode 47889: reward = -69.07, steps = 41 10:01:20 [INFO] train episode 47890: reward = -43.90, steps = 29 10:01:23 [INFO] train episode 47891: reward = -74.72, steps = 35 10:01:25 [INFO] train episode 47892: reward = -60.81, steps = 19 10:01:28 [INFO] train episode 47893: reward = -55.90, steps = 35 10:01:31 [INFO] train episode 47894: reward = -53.67, steps = 42 10:01:34 [INFO] train episode 47895: reward = -44.59, steps = 31 10:01:37 [INFO] train episode 47896: reward = -36.13, steps = 31 10:01:40 [INFO] train episode 47897: reward = -52.86, steps = 38 10:01:42 [INFO] train episode 47898: reward = -55.05, steps = 20 10:01:45 [INFO] train episode 47899: reward = -29.26, steps = 34 10:01:48 [INFO] train episode 47900: reward = -26.01, steps = 36 10:01:50 [INFO] train episode 47901: reward = -36.84, steps = 23 10:01:52 [INFO] train episode 47902: reward = -73.42, steps = 22 10:01:54 [INFO] train episode 47903: reward = -60.67, steps = 25 10:01:56 [INFO] train episode 47904: reward = -33.36, steps = 22 10:01:58 [INFO] train episode 47905: reward = -43.04, steps = 21 10:02:00 [INFO] train episode 47906: reward = -58.84, steps = 18 10:02:02 [INFO] train episode 47907: reward = -65.64, steps = 29 10:02:06 [INFO] train episode 47908: reward = -77.98, steps = 42 10:02:09 [INFO] train episode 47909: reward = -42.99, steps = 26 10:02:11 [INFO] train episode 47910: reward = -35.03, steps = 22 10:02:14 [INFO] train episode 47911: reward = -78.48, steps = 46 10:02:16 [INFO] train episode 47912: reward = -37.66, steps = 20 10:02:20 [INFO] train episode 47913: reward = -58.09, steps = 45 10:02:25 [INFO] train episode 47914: reward = -32.77, steps = 48 10:02:28 [INFO] train episode 47915: reward = -28.61, steps = 37 10:02:31 [INFO] train episode 47916: reward = -121.12, steps = 41 10:02:33 [INFO] train episode 47917: reward = -57.86, steps = 21 10:02:37 [INFO] train episode 47918: reward = -47.98, steps = 41 10:02:39 [INFO] train episode 47919: reward = -57.59, steps = 21 10:02:41 [INFO] train episode 47920: reward = -40.23, steps = 27 10:02:45 [INFO] train episode 47921: reward = -46.33, steps = 48 10:02:47 [INFO] train episode 47922: reward = -30.23, steps = 20 10:02:49 [INFO] train episode 47923: reward = -45.22, steps = 24 10:02:52 [INFO] train episode 47924: reward = -27.90, steps = 32 10:02:54 [INFO] train episode 47925: reward = -65.67, steps = 19 10:02:57 [INFO] train episode 47926: reward = -25.94, steps = 23 10:03:00 [INFO] train episode 47927: reward = -61.28, steps = 36 10:03:03 [INFO] train episode 47928: reward = -31.71, steps = 36 10:03:06 [INFO] train episode 47929: reward = -59.87, steps = 29 10:03:08 [INFO] train episode 47930: reward = -39.84, steps = 27 10:03:11 [INFO] train episode 47931: reward = -19.14, steps = 32 10:03:14 [INFO] train episode 47932: reward = -88.42, steps = 39 10:03:16 [INFO] train episode 47933: reward = -44.94, steps = 24 10:03:20 [INFO] train episode 47934: reward = -28.88, steps = 43 10:03:23 [INFO] train episode 47935: reward = -23.06, steps = 33 10:03:26 [INFO] train episode 47936: reward = -51.24, steps = 33 10:03:30 [INFO] train episode 47937: reward = -70.85, steps = 45 10:03:32 [INFO] train episode 47938: reward = -53.89, steps = 25 10:03:35 [INFO] train episode 47939: reward = -31.93, steps = 26 10:03:38 [INFO] train episode 47940: reward = -75.63, steps = 39 10:03:41 [INFO] train episode 47941: reward = -67.17, steps = 33 10:03:43 [INFO] train episode 47942: reward = -58.61, steps = 24 10:03:46 [INFO] train episode 47943: reward = -58.95, steps = 28 10:03:49 [INFO] train episode 47944: reward = -53.48, steps = 38 10:03:52 [INFO] train episode 47945: reward = -44.83, steps = 40 10:03:54 [INFO] train episode 47946: reward = -41.33, steps = 24 10:03:57 [INFO] train episode 47947: reward = -45.48, steps = 24 10:03:59 [INFO] train episode 47948: reward = -31.12, steps = 25 10:04:01 [INFO] train episode 47949: reward = -50.88, steps = 24 10:04:04 [INFO] train episode 47950: reward = -72.37, steps = 33 10:04:07 [INFO] train episode 47951: reward = -67.62, steps = 32 10:04:10 [INFO] train episode 47952: reward = -67.10, steps = 31 10:04:14 [INFO] train episode 47953: reward = -41.07, steps = 50 10:04:17 [INFO] train episode 47954: reward = -47.68, steps = 27 10:04:19 [INFO] train episode 47955: reward = -72.22, steps = 30 10:04:22 [INFO] train episode 47956: reward = -68.90, steps = 32 10:04:24 [INFO] train episode 47957: reward = -23.64, steps = 24 10:04:27 [INFO] train episode 47958: reward = -45.95, steps = 36 10:04:30 [INFO] train episode 47959: reward = -44.51, steps = 23 10:04:31 [INFO] train episode 47960: reward = -66.99, steps = 22 10:04:34 [INFO] train episode 47961: reward = -51.45, steps = 27 10:04:37 [INFO] train episode 47962: reward = -31.78, steps = 42 10:04:39 [INFO] train episode 47963: reward = -55.87, steps = 20 10:04:42 [INFO] train episode 47964: reward = -81.51, steps = 29 10:04:44 [INFO] train episode 47965: reward = -37.45, steps = 24 10:04:46 [INFO] train episode 47966: reward = -36.49, steps = 24 10:04:48 [INFO] train episode 47967: reward = -48.92, steps = 19 10:04:51 [INFO] train episode 47968: reward = -33.58, steps = 33 10:04:54 [INFO] train episode 47969: reward = -38.07, steps = 37 10:04:56 [INFO] train episode 47970: reward = -39.77, steps = 23 10:04:58 [INFO] train episode 47971: reward = -42.66, steps = 21 10:05:01 [INFO] train episode 47972: reward = -30.38, steps = 34 10:05:04 [INFO] train episode 47973: reward = -81.21, steps = 37 10:05:07 [INFO] train episode 47974: reward = -43.38, steps = 30 10:05:10 [INFO] train episode 47975: reward = -54.75, steps = 37 10:05:12 [INFO] train episode 47976: reward = -52.68, steps = 28 10:05:16 [INFO] train episode 47977: reward = -21.31, steps = 36 10:05:19 [INFO] train episode 47978: reward = -46.15, steps = 30 10:05:21 [INFO] train episode 47979: reward = -47.31, steps = 24 10:05:23 [INFO] train episode 47980: reward = -60.21, steps = 33 10:05:25 [INFO] train episode 47981: reward = -61.05, steps = 21 10:05:27 [INFO] train episode 47982: reward = -54.95, steps = 23 10:05:31 [INFO] train episode 47983: reward = -92.60, steps = 49 10:05:34 [INFO] train episode 47984: reward = -37.05, steps = 22 10:05:37 [INFO] train episode 47985: reward = -12.32, steps = 39 10:05:39 [INFO] train episode 47986: reward = -57.95, steps = 25 10:05:43 [INFO] train episode 47987: reward = -54.30, steps = 38 10:05:45 [INFO] train episode 47988: reward = -75.80, steps = 33 10:05:50 [INFO] train episode 47989: reward = -104.55, steps = 45 10:05:52 [INFO] train episode 47990: reward = -48.72, steps = 22 10:05:54 [INFO] train episode 47991: reward = -52.00, steps = 22 10:05:56 [INFO] train episode 47992: reward = -60.75, steps = 22 10:05:58 [INFO] train episode 47993: reward = -42.84, steps = 16 10:06:00 [INFO] train episode 47994: reward = -37.39, steps = 32 10:06:02 [INFO] train episode 47995: reward = -50.80, steps = 21 10:06:05 [INFO] train episode 47996: reward = -41.30, steps = 29 10:06:08 [INFO] train episode 47997: reward = -43.20, steps = 35 10:06:10 [INFO] train episode 47998: reward = -51.39, steps = 28 10:06:13 [INFO] train episode 47999: reward = -59.80, steps = 28 10:06:15 [INFO] train episode 48000: reward = -28.30, steps = 24 10:06:18 [INFO] train episode 48001: reward = -60.89, steps = 36 10:06:21 [INFO] train episode 48002: reward = -17.57, steps = 35 10:06:24 [INFO] train episode 48003: reward = -82.35, steps = 30 10:06:27 [INFO] train episode 48004: reward = -10.14, steps = 34 10:06:30 [INFO] train episode 48005: reward = -41.12, steps = 34 10:06:32 [INFO] train episode 48006: reward = -63.31, steps = 26 10:06:34 [INFO] train episode 48007: reward = -61.44, steps = 23 10:06:36 [INFO] train episode 48008: reward = -62.73, steps = 23 10:06:41 [INFO] train episode 48009: reward = -69.93, steps = 51 10:06:44 [INFO] train episode 48010: reward = -38.25, steps = 34 10:06:46 [INFO] train episode 48011: reward = -37.93, steps = 25 10:06:49 [INFO] train episode 48012: reward = -45.22, steps = 35 10:06:55 [INFO] train episode 48013: reward = -113.65, steps = 70 10:06:57 [INFO] train episode 48014: reward = -44.27, steps = 23 10:07:01 [INFO] train episode 48015: reward = -36.46, steps = 41 10:07:03 [INFO] train episode 48016: reward = -48.71, steps = 28 10:07:05 [INFO] train episode 48017: reward = -36.09, steps = 26 10:07:09 [INFO] train episode 48018: reward = -82.39, steps = 36 10:07:11 [INFO] train episode 48019: reward = -34.74, steps = 25 10:07:13 [INFO] train episode 48020: reward = -20.93, steps = 21 10:07:16 [INFO] train episode 48021: reward = -49.78, steps = 33 10:07:17 [INFO] train episode 48022: reward = -27.36, steps = 16 10:07:20 [INFO] train episode 48023: reward = -42.73, steps = 37 10:07:23 [INFO] train episode 48024: reward = -56.09, steps = 36 10:07:27 [INFO] train episode 48025: reward = -60.74, steps = 35 10:07:30 [INFO] train episode 48026: reward = -25.23, steps = 38 10:07:33 [INFO] train episode 48027: reward = -70.26, steps = 31 10:07:36 [INFO] train episode 48028: reward = -47.00, steps = 33 10:07:38 [INFO] train episode 48029: reward = -57.53, steps = 30 10:07:40 [INFO] train episode 48030: reward = -50.20, steps = 20 10:07:44 [INFO] train episode 48031: reward = -55.39, steps = 40 10:07:46 [INFO] train episode 48032: reward = -27.52, steps = 32 10:07:50 [INFO] train episode 48033: reward = -34.84, steps = 40 10:07:52 [INFO] train episode 48034: reward = -49.05, steps = 22 10:07:54 [INFO] train episode 48035: reward = -81.30, steps = 22 10:07:57 [INFO] train episode 48036: reward = -52.72, steps = 33 10:07:59 [INFO] train episode 48037: reward = -69.59, steps = 29 10:08:01 [INFO] train episode 48038: reward = -47.92, steps = 20 10:08:05 [INFO] train episode 48039: reward = -62.49, steps = 42 10:08:06 [INFO] train episode 48040: reward = -67.50, steps = 20 10:08:10 [INFO] train episode 48041: reward = -48.34, steps = 37 10:08:13 [INFO] train episode 48042: reward = -60.06, steps = 36 10:08:17 [INFO] train episode 48043: reward = -89.00, steps = 47 10:08:20 [INFO] train episode 48044: reward = -8.89, steps = 35 10:08:23 [INFO] train episode 48045: reward = -53.66, steps = 39 10:08:26 [INFO] train episode 48046: reward = -44.81, steps = 29 10:08:29 [INFO] train episode 48047: reward = -16.64, steps = 34 10:08:32 [INFO] train episode 48048: reward = -56.79, steps = 30 10:08:33 [INFO] train episode 48049: reward = -50.46, steps = 20 10:08:36 [INFO] train episode 48050: reward = -33.89, steps = 24 10:08:38 [INFO] train episode 48051: reward = -42.92, steps = 28 10:08:41 [INFO] train episode 48052: reward = -58.47, steps = 32 10:08:44 [INFO] train episode 48053: reward = -46.86, steps = 22 10:08:46 [INFO] train episode 48054: reward = -49.51, steps = 29 10:08:48 [INFO] train episode 48055: reward = -81.74, steps = 22 10:08:50 [INFO] train episode 48056: reward = -77.61, steps = 24 10:08:53 [INFO] train episode 48057: reward = -36.18, steps = 35 10:08:56 [INFO] train episode 48058: reward = -40.36, steps = 27 10:08:58 [INFO] train episode 48059: reward = -44.71, steps = 28 10:09:00 [INFO] train episode 48060: reward = -48.54, steps = 20 10:09:03 [INFO] train episode 48061: reward = -61.41, steps = 35 10:09:07 [INFO] train episode 48062: reward = -26.38, steps = 39 10:09:11 [INFO] train episode 48063: reward = -96.08, steps = 49 10:09:13 [INFO] train episode 48064: reward = -34.43, steps = 22 10:09:17 [INFO] train episode 48065: reward = -89.05, steps = 48 10:09:21 [INFO] train episode 48066: reward = -63.52, steps = 42 10:09:23 [INFO] train episode 48067: reward = -63.16, steps = 22 10:09:26 [INFO] train episode 48068: reward = -54.50, steps = 33 10:09:28 [INFO] train episode 48069: reward = -45.43, steps = 33 10:09:31 [INFO] train episode 48070: reward = -70.87, steps = 31 10:09:33 [INFO] train episode 48071: reward = -42.46, steps = 25 10:09:36 [INFO] train episode 48072: reward = -99.54, steps = 28 10:09:38 [INFO] train episode 48073: reward = -65.49, steps = 22 10:09:41 [INFO] train episode 48074: reward = -57.95, steps = 38 10:09:44 [INFO] train episode 48075: reward = -81.56, steps = 39 10:09:46 [INFO] train episode 48076: reward = -41.69, steps = 20 10:09:48 [INFO] train episode 48077: reward = -50.34, steps = 27 10:09:51 [INFO] train episode 48078: reward = -51.94, steps = 31 10:09:54 [INFO] train episode 48079: reward = -80.71, steps = 27 10:09:56 [INFO] train episode 48080: reward = -43.80, steps = 30 10:09:59 [INFO] train episode 48081: reward = -51.47, steps = 27 10:10:01 [INFO] train episode 48082: reward = -42.49, steps = 24 10:10:03 [INFO] train episode 48083: reward = -26.94, steps = 22 10:10:06 [INFO] train episode 48084: reward = -41.43, steps = 39 10:10:10 [INFO] train episode 48085: reward = -78.04, steps = 44 10:10:12 [INFO] train episode 48086: reward = -50.03, steps = 23 10:10:15 [INFO] train episode 48087: reward = -50.90, steps = 27 10:10:18 [INFO] train episode 48088: reward = -28.78, steps = 38 10:10:22 [INFO] train episode 48089: reward = -61.39, steps = 47 10:10:24 [INFO] train episode 48090: reward = -48.79, steps = 22 10:10:28 [INFO] train episode 48091: reward = -47.83, steps = 45 10:10:29 [INFO] train episode 48092: reward = -33.31, steps = 20 10:10:31 [INFO] train episode 48093: reward = -64.64, steps = 22 10:10:33 [INFO] train episode 48094: reward = -45.12, steps = 20 10:10:35 [INFO] train episode 48095: reward = -47.20, steps = 25 10:10:38 [INFO] train episode 48096: reward = -51.75, steps = 24 10:10:40 [INFO] train episode 48097: reward = -31.19, steps = 24 10:10:43 [INFO] train episode 48098: reward = -50.18, steps = 29 10:10:44 [INFO] train episode 48099: reward = -52.68, steps = 16 10:10:46 [INFO] train episode 48100: reward = -40.48, steps = 26 10:10:48 [INFO] train episode 48101: reward = -59.08, steps = 19 10:10:50 [INFO] train episode 48102: reward = -54.80, steps = 21 10:10:53 [INFO] train episode 48103: reward = -74.92, steps = 33 10:10:55 [INFO] train episode 48104: reward = -61.13, steps = 27 10:10:58 [INFO] train episode 48105: reward = -46.33, steps = 30 10:11:01 [INFO] train episode 48106: reward = -40.31, steps = 40 10:11:04 [INFO] train episode 48107: reward = -53.90, steps = 30 10:11:06 [INFO] train episode 48108: reward = -39.96, steps = 24 10:11:09 [INFO] train episode 48109: reward = -52.77, steps = 32 10:11:12 [INFO] train episode 48110: reward = -64.89, steps = 34 10:11:15 [INFO] train episode 48111: reward = -41.01, steps = 31 10:11:18 [INFO] train episode 48112: reward = -32.94, steps = 33 10:11:20 [INFO] train episode 48113: reward = -44.50, steps = 33 10:11:23 [INFO] train episode 48114: reward = -64.20, steps = 34 10:11:28 [INFO] train episode 48115: reward = -68.74, steps = 46 10:11:30 [INFO] train episode 48116: reward = -72.71, steps = 27 10:11:32 [INFO] train episode 48117: reward = -51.91, steps = 28 10:11:34 [INFO] train episode 48118: reward = -43.37, steps = 22 10:11:37 [INFO] train episode 48119: reward = -31.00, steps = 29 10:11:39 [INFO] train episode 48120: reward = -46.76, steps = 23 10:11:42 [INFO] train episode 48121: reward = -53.34, steps = 32 10:11:45 [INFO] train episode 48122: reward = -36.21, steps = 25 10:11:48 [INFO] train episode 48123: reward = -62.46, steps = 37 10:11:50 [INFO] train episode 48124: reward = -62.18, steps = 24 10:11:52 [INFO] train episode 48125: reward = -59.75, steps = 24 10:11:54 [INFO] train episode 48126: reward = -34.48, steps = 19 10:11:59 [INFO] train episode 48127: reward = -118.52, steps = 63 10:12:03 [INFO] train episode 48128: reward = -53.68, steps = 41 10:12:04 [INFO] train episode 48129: reward = -41.56, steps = 20 10:12:09 [INFO] train episode 48130: reward = -70.98, steps = 50 10:12:11 [INFO] train episode 48131: reward = -60.07, steps = 33 10:12:14 [INFO] train episode 48132: reward = -82.93, steps = 30 10:12:19 [INFO] train episode 48133: reward = -62.48, steps = 50 10:12:21 [INFO] train episode 48134: reward = -66.28, steps = 24 10:12:24 [INFO] train episode 48135: reward = -39.26, steps = 33 10:12:26 [INFO] train episode 48136: reward = -61.86, steps = 30 10:12:29 [INFO] train episode 48137: reward = -40.34, steps = 35 10:12:32 [INFO] train episode 48138: reward = -48.20, steps = 24 10:12:34 [INFO] train episode 48139: reward = -51.91, steps = 33 10:12:36 [INFO] train episode 48140: reward = -46.35, steps = 19 10:12:38 [INFO] train episode 48141: reward = -47.11, steps = 21 10:12:41 [INFO] train episode 48142: reward = -55.86, steps = 30 10:12:42 [INFO] train episode 48143: reward = -40.55, steps = 21 10:12:45 [INFO] train episode 48144: reward = -25.20, steps = 29 10:12:48 [INFO] train episode 48145: reward = -53.06, steps = 29 10:12:50 [INFO] train episode 48146: reward = -40.09, steps = 27 10:12:55 [INFO] train episode 48147: reward = -65.51, steps = 52 10:12:57 [INFO] train episode 48148: reward = -49.41, steps = 26 10:13:00 [INFO] train episode 48149: reward = -104.28, steps = 41 10:13:03 [INFO] train episode 48150: reward = -70.40, steps = 32 10:13:05 [INFO] train episode 48151: reward = -61.00, steps = 24 10:13:09 [INFO] train episode 48152: reward = -45.09, steps = 40 10:13:12 [INFO] train episode 48153: reward = -42.44, steps = 41 10:13:14 [INFO] train episode 48154: reward = -50.58, steps = 26 10:13:19 [INFO] train episode 48155: reward = -50.93, steps = 54 10:13:21 [INFO] train episode 48156: reward = -40.56, steps = 23 10:13:24 [INFO] train episode 48157: reward = -48.86, steps = 30 10:13:27 [INFO] train episode 48158: reward = -82.29, steps = 34 10:13:29 [INFO] train episode 48159: reward = -44.12, steps = 25 10:13:31 [INFO] train episode 48160: reward = -52.07, steps = 28 10:13:35 [INFO] train episode 48161: reward = -46.72, steps = 37 10:13:38 [INFO] train episode 48162: reward = -41.08, steps = 34 10:13:39 [INFO] train episode 48163: reward = -45.87, steps = 21 10:13:42 [INFO] train episode 48164: reward = -45.84, steps = 31 10:13:44 [INFO] train episode 48165: reward = -53.02, steps = 24 10:13:46 [INFO] train episode 48166: reward = -60.87, steps = 20 10:13:48 [INFO] train episode 48167: reward = -38.09, steps = 28 10:13:51 [INFO] train episode 48168: reward = -54.36, steps = 26 10:13:53 [INFO] train episode 48169: reward = -47.37, steps = 29 10:13:56 [INFO] train episode 48170: reward = -36.68, steps = 29 10:14:00 [INFO] train episode 48171: reward = -34.12, steps = 47 10:14:03 [INFO] train episode 48172: reward = -62.02, steps = 35 10:14:05 [INFO] train episode 48173: reward = -48.44, steps = 31 10:14:09 [INFO] train episode 48174: reward = -23.97, steps = 33 10:14:11 [INFO] train episode 48175: reward = -58.42, steps = 31 10:14:15 [INFO] train episode 48176: reward = -70.70, steps = 40 10:14:17 [INFO] train episode 48177: reward = -32.27, steps = 22 10:14:20 [INFO] train episode 48178: reward = -55.77, steps = 39 10:14:23 [INFO] train episode 48179: reward = -47.12, steps = 30 10:14:25 [INFO] train episode 48180: reward = -49.55, steps = 26 10:14:28 [INFO] train episode 48181: reward = -42.35, steps = 27 10:14:31 [INFO] train episode 48182: reward = -27.92, steps = 32 10:14:34 [INFO] train episode 48183: reward = -58.60, steps = 32 10:14:36 [INFO] train episode 48184: reward = -53.56, steps = 25 10:14:38 [INFO] train episode 48185: reward = -58.82, steps = 22 10:14:41 [INFO] train episode 48186: reward = -21.45, steps = 29 10:14:43 [INFO] train episode 48187: reward = -48.42, steps = 22 10:14:45 [INFO] train episode 48188: reward = -42.76, steps = 26 10:14:48 [INFO] train episode 48189: reward = -55.27, steps = 32 10:14:51 [INFO] train episode 48190: reward = -60.34, steps = 43 10:14:56 [INFO] train episode 48191: reward = -77.82, steps = 53 10:14:59 [INFO] train episode 48192: reward = -72.15, steps = 33 10:15:01 [INFO] train episode 48193: reward = -46.09, steps = 21 10:15:03 [INFO] train episode 48194: reward = -50.87, steps = 31 10:15:07 [INFO] train episode 48195: reward = -53.52, steps = 43 10:15:09 [INFO] train episode 48196: reward = -43.36, steps = 27 10:15:12 [INFO] train episode 48197: reward = -34.45, steps = 26 10:15:14 [INFO] train episode 48198: reward = -41.34, steps = 28 10:15:17 [INFO] train episode 48199: reward = -44.74, steps = 34 10:15:19 [INFO] train episode 48200: reward = -59.24, steps = 24 10:15:21 [INFO] train episode 48201: reward = -31.34, steps = 21 10:15:24 [INFO] train episode 48202: reward = -13.48, steps = 34 10:15:26 [INFO] train episode 48203: reward = -45.09, steps = 22 10:15:29 [INFO] train episode 48204: reward = -44.47, steps = 27 10:15:30 [INFO] train episode 48205: reward = -39.55, steps = 20 10:15:33 [INFO] train episode 48206: reward = -97.12, steps = 33 10:15:36 [INFO] train episode 48207: reward = -68.60, steps = 28 10:15:37 [INFO] train episode 48208: reward = -69.15, steps = 22 10:15:39 [INFO] train episode 48209: reward = -36.45, steps = 21 10:15:41 [INFO] train episode 48210: reward = -55.61, steps = 20 10:15:45 [INFO] train episode 48211: reward = -75.67, steps = 41 10:15:49 [INFO] train episode 48212: reward = -95.25, steps = 54 10:15:51 [INFO] train episode 48213: reward = -46.43, steps = 20 10:15:57 [INFO] train episode 48214: reward = -191.42, steps = 70 10:16:01 [INFO] train episode 48215: reward = -32.57, steps = 38 10:16:04 [INFO] train episode 48216: reward = -41.84, steps = 35 10:16:06 [INFO] train episode 48217: reward = -31.05, steps = 25 10:16:08 [INFO] train episode 48218: reward = -94.90, steps = 25 10:16:10 [INFO] train episode 48219: reward = -49.11, steps = 24 10:16:13 [INFO] train episode 48220: reward = -58.98, steps = 37 10:16:16 [INFO] train episode 48221: reward = -50.14, steps = 27 10:16:18 [INFO] train episode 48222: reward = -47.50, steps = 23 10:16:20 [INFO] train episode 48223: reward = -78.20, steps = 24 10:16:23 [INFO] train episode 48224: reward = -53.96, steps = 37 10:16:25 [INFO] train episode 48225: reward = -28.48, steps = 26 10:16:29 [INFO] train episode 48226: reward = -88.41, steps = 48 10:16:33 [INFO] train episode 48227: reward = -74.42, steps = 40 10:16:37 [INFO] train episode 48228: reward = -107.44, steps = 47 10:16:39 [INFO] train episode 48229: reward = -81.22, steps = 26 10:16:42 [INFO] train episode 48230: reward = -30.99, steps = 33 10:16:45 [INFO] train episode 48231: reward = -50.24, steps = 32 10:16:47 [INFO] train episode 48232: reward = -47.82, steps = 22 10:16:52 [INFO] train episode 48233: reward = -69.08, steps = 56 10:16:55 [INFO] train episode 48234: reward = -32.34, steps = 32 10:16:57 [INFO] train episode 48235: reward = -110.64, steps = 27 10:16:59 [INFO] train episode 48236: reward = -39.40, steps = 25 10:17:01 [INFO] train episode 48237: reward = -37.61, steps = 25 10:17:04 [INFO] train episode 48238: reward = -36.34, steps = 28 10:17:06 [INFO] train episode 48239: reward = -65.35, steps = 20 10:17:08 [INFO] train episode 48240: reward = -66.70, steps = 29 10:17:11 [INFO] train episode 48241: reward = -53.00, steps = 27 10:17:13 [INFO] train episode 48242: reward = -42.53, steps = 24 10:17:15 [INFO] train episode 48243: reward = -49.44, steps = 29 10:17:20 [INFO] train episode 48244: reward = -55.41, steps = 49 10:17:24 [INFO] train episode 48245: reward = -81.27, steps = 47 10:17:26 [INFO] train episode 48246: reward = -52.87, steps = 22 10:17:28 [INFO] train episode 48247: reward = -44.40, steps = 20 10:17:31 [INFO] train episode 48248: reward = -28.61, steps = 30 10:17:34 [INFO] train episode 48249: reward = -82.55, steps = 42 10:17:38 [INFO] train episode 48250: reward = -45.13, steps = 47 10:17:42 [INFO] train episode 48251: reward = -70.80, steps = 40 10:17:44 [INFO] train episode 48252: reward = -62.81, steps = 22 10:17:46 [INFO] train episode 48253: reward = -39.58, steps = 21 10:17:48 [INFO] train episode 48254: reward = -60.55, steps = 31 10:17:52 [INFO] train episode 48255: reward = -54.90, steps = 38 10:17:55 [INFO] train episode 48256: reward = -49.23, steps = 37 10:17:57 [INFO] train episode 48257: reward = -49.39, steps = 25 10:18:00 [INFO] train episode 48258: reward = -36.94, steps = 32 10:18:02 [INFO] train episode 48259: reward = -46.79, steps = 22 10:18:05 [INFO] train episode 48260: reward = -43.61, steps = 37 10:18:07 [INFO] train episode 48261: reward = -59.62, steps = 24 10:18:09 [INFO] train episode 48262: reward = -67.67, steps = 25 10:18:13 [INFO] train episode 48263: reward = -36.30, steps = 42 10:18:15 [INFO] train episode 48264: reward = -30.89, steps = 24 10:18:18 [INFO] train episode 48265: reward = -39.33, steps = 32 10:18:22 [INFO] train episode 48266: reward = -44.65, steps = 44 10:18:24 [INFO] train episode 48267: reward = -55.90, steps = 19 10:18:25 [INFO] train episode 48268: reward = -46.37, steps = 21 10:18:27 [INFO] train episode 48269: reward = -52.63, steps = 20 10:18:29 [INFO] train episode 48270: reward = -43.26, steps = 26 10:18:32 [INFO] train episode 48271: reward = -46.83, steps = 30 10:18:34 [INFO] train episode 48272: reward = -62.38, steps = 23 10:18:37 [INFO] train episode 48273: reward = -50.45, steps = 33 10:18:40 [INFO] train episode 48274: reward = -48.60, steps = 32 10:18:42 [INFO] train episode 48275: reward = -73.19, steps = 22 10:18:46 [INFO] train episode 48276: reward = -66.79, steps = 47 10:18:48 [INFO] train episode 48277: reward = -37.58, steps = 28 10:18:50 [INFO] train episode 48278: reward = -39.20, steps = 21 10:18:53 [INFO] train episode 48279: reward = -31.22, steps = 30 10:18:56 [INFO] train episode 48280: reward = -46.42, steps = 29 10:18:58 [INFO] train episode 48281: reward = -62.11, steps = 29 10:19:01 [INFO] train episode 48282: reward = -60.19, steps = 33 10:19:04 [INFO] train episode 48283: reward = -82.15, steps = 38 10:19:06 [INFO] train episode 48284: reward = -36.97, steps = 19 10:19:08 [INFO] train episode 48285: reward = -56.84, steps = 24 10:19:12 [INFO] train episode 48286: reward = -116.29, steps = 44 10:19:15 [INFO] train episode 48287: reward = -48.45, steps = 32 10:19:19 [INFO] train episode 48288: reward = -99.63, steps = 46 10:19:20 [INFO] train episode 48289: reward = -84.31, steps = 19 10:19:22 [INFO] train episode 48290: reward = -38.15, steps = 22 10:19:24 [INFO] train episode 48291: reward = -64.38, steps = 20 10:19:28 [INFO] train episode 48292: reward = -60.80, steps = 49 10:19:31 [INFO] train episode 48293: reward = -67.57, steps = 30 10:19:33 [INFO] train episode 48294: reward = -66.44, steps = 29 10:19:36 [INFO] train episode 48295: reward = -51.83, steps = 38 10:19:38 [INFO] train episode 48296: reward = -60.14, steps = 22 10:19:41 [INFO] train episode 48297: reward = -40.20, steps = 34 10:19:44 [INFO] train episode 48298: reward = -50.24, steps = 23 10:19:47 [INFO] train episode 48299: reward = -53.53, steps = 36 10:19:50 [INFO] train episode 48300: reward = -61.05, steps = 37 10:19:52 [INFO] train episode 48301: reward = -60.15, steps = 22 10:19:54 [INFO] train episode 48302: reward = -59.45, steps = 29 10:19:56 [INFO] train episode 48303: reward = -51.33, steps = 29 10:19:58 [INFO] train episode 48304: reward = -53.87, steps = 22 10:20:01 [INFO] train episode 48305: reward = -24.86, steps = 24 10:20:02 [INFO] train episode 48306: reward = -55.62, steps = 18 10:20:05 [INFO] train episode 48307: reward = -53.37, steps = 27 10:20:06 [INFO] train episode 48308: reward = -41.52, steps = 20 10:20:12 [INFO] train episode 48309: reward = -68.78, steps = 59 10:20:14 [INFO] train episode 48310: reward = -37.84, steps = 28 10:20:17 [INFO] train episode 48311: reward = -68.69, steps = 29 10:20:19 [INFO] train episode 48312: reward = -28.31, steps = 23 10:20:21 [INFO] train episode 48313: reward = -60.54, steps = 20 10:20:24 [INFO] train episode 48314: reward = -79.11, steps = 32 10:20:26 [INFO] train episode 48315: reward = -68.44, steps = 23 10:20:28 [INFO] train episode 48316: reward = -39.93, steps = 32 10:20:31 [INFO] train episode 48317: reward = -55.90, steps = 28 10:20:34 [INFO] train episode 48318: reward = -54.73, steps = 32 10:20:36 [INFO] train episode 48319: reward = -39.97, steps = 19 10:20:39 [INFO] train episode 48320: reward = -42.32, steps = 38 10:20:42 [INFO] train episode 48321: reward = -61.71, steps = 32 10:20:43 [INFO] train episode 48322: reward = -67.28, steps = 23 10:20:46 [INFO] train episode 48323: reward = -92.49, steps = 22 10:20:49 [INFO] train episode 48324: reward = -33.46, steps = 25 10:20:51 [INFO] train episode 48325: reward = -41.18, steps = 23 10:20:54 [INFO] train episode 48326: reward = -63.24, steps = 30 10:20:56 [INFO] train episode 48327: reward = -57.46, steps = 26 10:21:00 [INFO] train episode 48328: reward = -37.70, steps = 43 10:21:04 [INFO] train episode 48329: reward = -55.71, steps = 41 10:21:07 [INFO] train episode 48330: reward = -37.06, steps = 32 10:21:11 [INFO] train episode 48331: reward = -44.86, steps = 42 10:21:13 [INFO] train episode 48332: reward = -150.16, steps = 24 10:21:15 [INFO] train episode 48333: reward = -49.06, steps = 23 10:21:19 [INFO] train episode 48334: reward = -39.14, steps = 38 10:21:21 [INFO] train episode 48335: reward = -57.21, steps = 26 10:21:24 [INFO] train episode 48336: reward = -45.44, steps = 25 10:21:25 [INFO] train episode 48337: reward = -42.90, steps = 21 10:21:28 [INFO] train episode 48338: reward = -37.28, steps = 26 10:21:31 [INFO] train episode 48339: reward = -44.79, steps = 37 10:21:32 [INFO] train episode 48340: reward = -48.07, steps = 20 10:21:35 [INFO] train episode 48341: reward = -78.07, steps = 28 10:21:38 [INFO] train episode 48342: reward = -23.61, steps = 38 10:21:44 [INFO] train episode 48343: reward = -77.14, steps = 66 10:21:48 [INFO] train episode 48344: reward = -82.92, steps = 44 10:21:50 [INFO] train episode 48345: reward = -68.59, steps = 32 10:21:53 [INFO] train episode 48346: reward = -49.75, steps = 22 10:21:56 [INFO] train episode 48347: reward = -55.57, steps = 34 10:21:57 [INFO] train episode 48348: reward = -38.41, steps = 20 10:22:00 [INFO] train episode 48349: reward = -39.67, steps = 31 10:22:03 [INFO] train episode 48350: reward = -59.12, steps = 31 10:22:04 [INFO] train episode 48351: reward = -50.20, steps = 17 10:22:07 [INFO] train episode 48352: reward = -44.97, steps = 35 10:22:10 [INFO] train episode 48353: reward = -72.18, steps = 27 10:22:12 [INFO] train episode 48354: reward = -49.28, steps = 23 10:22:14 [INFO] train episode 48355: reward = -52.39, steps = 28 10:22:16 [INFO] train episode 48356: reward = -66.79, steps = 19 10:22:18 [INFO] train episode 48357: reward = -52.37, steps = 31 10:22:21 [INFO] train episode 48358: reward = -34.71, steps = 35 10:22:23 [INFO] train episode 48359: reward = -29.10, steps = 22 10:22:26 [INFO] train episode 48360: reward = -65.53, steps = 23 10:22:27 [INFO] train episode 48361: reward = -38.44, steps = 22 10:22:30 [INFO] train episode 48362: reward = -39.09, steps = 33 10:22:33 [INFO] train episode 48363: reward = -81.61, steps = 35 10:22:35 [INFO] train episode 48364: reward = -43.00, steps = 22 10:22:37 [INFO] train episode 48365: reward = -63.14, steps = 21 10:22:40 [INFO] train episode 48366: reward = -26.78, steps = 36 10:22:43 [INFO] train episode 48367: reward = -38.69, steps = 25 10:22:45 [INFO] train episode 48368: reward = -33.10, steps = 23 10:22:47 [INFO] train episode 48369: reward = -71.47, steps = 24 10:22:49 [INFO] train episode 48370: reward = -51.20, steps = 24 10:22:52 [INFO] train episode 48371: reward = -40.53, steps = 36 10:22:54 [INFO] train episode 48372: reward = -42.77, steps = 20 10:22:57 [INFO] train episode 48373: reward = -35.88, steps = 33 10:22:59 [INFO] train episode 48374: reward = -42.83, steps = 27 10:23:01 [INFO] train episode 48375: reward = -42.18, steps = 24 10:23:04 [INFO] train episode 48376: reward = -31.94, steps = 27 10:23:07 [INFO] train episode 48377: reward = -77.88, steps = 38 10:23:10 [INFO] train episode 48378: reward = -37.46, steps = 26 10:23:13 [INFO] train episode 48379: reward = -51.30, steps = 34 10:23:16 [INFO] train episode 48380: reward = -56.70, steps = 36 10:23:18 [INFO] train episode 48381: reward = -48.00, steps = 23 10:23:21 [INFO] train episode 48382: reward = -49.62, steps = 35 10:23:23 [INFO] train episode 48383: reward = -37.40, steps = 26 10:23:25 [INFO] train episode 48384: reward = -30.53, steps = 23 10:23:27 [INFO] train episode 48385: reward = -49.11, steps = 20 10:23:29 [INFO] train episode 48386: reward = -43.51, steps = 25 10:23:31 [INFO] train episode 48387: reward = -55.39, steps = 19 10:23:33 [INFO] train episode 48388: reward = -54.12, steps = 23 10:23:35 [INFO] train episode 48389: reward = -41.99, steps = 21 10:23:37 [INFO] train episode 48390: reward = -47.57, steps = 28 10:23:39 [INFO] train episode 48391: reward = -50.78, steps = 19 10:23:42 [INFO] train episode 48392: reward = -46.41, steps = 35 10:23:44 [INFO] train episode 48393: reward = -46.34, steps = 23 10:23:46 [INFO] train episode 48394: reward = -41.41, steps = 21 10:23:48 [INFO] train episode 48395: reward = -61.78, steps = 18 10:23:50 [INFO] train episode 48396: reward = -55.97, steps = 29 10:23:52 [INFO] train episode 48397: reward = -56.11, steps = 22 10:23:54 [INFO] train episode 48398: reward = -55.41, steps = 25 10:23:58 [INFO] train episode 48399: reward = -36.82, steps = 38 10:24:00 [INFO] train episode 48400: reward = -59.59, steps = 25 10:24:03 [INFO] train episode 48401: reward = -45.24, steps = 33 10:24:05 [INFO] train episode 48402: reward = -39.82, steps = 20 10:24:06 [INFO] train episode 48403: reward = -57.10, steps = 21 10:24:08 [INFO] train episode 48404: reward = -53.96, steps = 22 10:24:10 [INFO] train episode 48405: reward = -65.71, steps = 22 10:24:13 [INFO] train episode 48406: reward = -26.67, steps = 35 10:24:17 [INFO] train episode 48407: reward = -55.35, steps = 39 10:24:19 [INFO] train episode 48408: reward = -58.07, steps = 19 10:24:21 [INFO] train episode 48409: reward = -44.40, steps = 31 10:24:23 [INFO] train episode 48410: reward = -44.28, steps = 21 10:24:26 [INFO] train episode 48411: reward = -62.91, steps = 36 10:24:29 [INFO] train episode 48412: reward = -81.82, steps = 32 10:24:32 [INFO] train episode 48413: reward = -33.36, steps = 30 10:24:35 [INFO] train episode 48414: reward = -56.56, steps = 31 10:24:36 [INFO] train episode 48415: reward = -59.21, steps = 20 10:24:38 [INFO] train episode 48416: reward = -48.09, steps = 20 10:24:40 [INFO] train episode 48417: reward = -43.82, steps = 21 10:24:44 [INFO] train episode 48418: reward = -36.08, steps = 41 10:24:46 [INFO] train episode 48419: reward = -62.64, steps = 25 10:24:48 [INFO] train episode 48420: reward = -49.80, steps = 24 10:24:51 [INFO] train episode 48421: reward = -77.36, steps = 37 10:24:55 [INFO] train episode 48422: reward = -32.93, steps = 37 10:24:57 [INFO] train episode 48423: reward = -49.40, steps = 28 10:24:59 [INFO] train episode 48424: reward = -36.88, steps = 21 10:25:01 [INFO] train episode 48425: reward = -81.29, steps = 26 10:25:03 [INFO] train episode 48426: reward = -37.67, steps = 20 10:25:05 [INFO] train episode 48427: reward = -44.37, steps = 24 10:25:07 [INFO] train episode 48428: reward = -57.94, steps = 20 10:25:10 [INFO] train episode 48429: reward = -79.63, steps = 35 10:25:11 [INFO] train episode 48430: reward = -90.77, steps = 18 10:25:14 [INFO] train episode 48431: reward = -29.82, steps = 29 10:25:18 [INFO] train episode 48432: reward = -61.63, steps = 48 10:25:20 [INFO] train episode 48433: reward = -43.54, steps = 20 10:25:22 [INFO] train episode 48434: reward = -59.88, steps = 19 10:25:24 [INFO] train episode 48435: reward = -50.79, steps = 27 10:25:27 [INFO] train episode 48436: reward = -56.17, steps = 38 10:25:30 [INFO] train episode 48437: reward = -66.82, steps = 33 10:25:34 [INFO] train episode 48438: reward = -39.51, steps = 45 10:25:36 [INFO] train episode 48439: reward = -43.78, steps = 23 10:25:39 [INFO] train episode 48440: reward = -53.71, steps = 28 10:25:42 [INFO] train episode 48441: reward = -35.39, steps = 36 10:25:43 [INFO] train episode 48442: reward = -53.91, steps = 21 10:25:46 [INFO] train episode 48443: reward = -58.78, steps = 31 10:25:50 [INFO] train episode 48444: reward = -78.35, steps = 37 10:25:53 [INFO] train episode 48445: reward = -53.59, steps = 33 10:25:56 [INFO] train episode 48446: reward = -46.02, steps = 38 10:25:58 [INFO] train episode 48447: reward = -35.87, steps = 20 10:26:02 [INFO] train episode 48448: reward = -49.20, steps = 35 10:26:04 [INFO] train episode 48449: reward = -33.97, steps = 30 10:26:06 [INFO] train episode 48450: reward = -52.65, steps = 26 10:26:09 [INFO] train episode 48451: reward = -83.96, steps = 31 10:26:11 [INFO] train episode 48452: reward = -61.24, steps = 19 10:26:13 [INFO] train episode 48453: reward = -49.41, steps = 23 10:26:15 [INFO] train episode 48454: reward = -46.28, steps = 20 10:26:17 [INFO] train episode 48455: reward = -58.57, steps = 28 10:26:21 [INFO] train episode 48456: reward = -34.65, steps = 41 10:26:23 [INFO] train episode 48457: reward = -56.52, steps = 29 10:26:25 [INFO] train episode 48458: reward = -48.76, steps = 20 10:26:27 [INFO] train episode 48459: reward = -25.10, steps = 21 10:26:29 [INFO] train episode 48460: reward = -62.83, steps = 20 10:26:31 [INFO] train episode 48461: reward = -75.44, steps = 23 10:26:33 [INFO] train episode 48462: reward = -73.69, steps = 22 10:26:35 [INFO] train episode 48463: reward = -66.55, steps = 28 10:26:37 [INFO] train episode 48464: reward = -59.45, steps = 18 10:26:40 [INFO] train episode 48465: reward = -47.75, steps = 30 10:26:42 [INFO] train episode 48466: reward = -56.91, steps = 28 10:26:46 [INFO] train episode 48467: reward = -62.25, steps = 42 10:26:49 [INFO] train episode 48468: reward = -79.91, steps = 32 10:26:51 [INFO] train episode 48469: reward = -46.91, steps = 25 10:26:53 [INFO] train episode 48470: reward = -46.95, steps = 24 10:26:55 [INFO] train episode 48471: reward = -23.24, steps = 29 10:27:00 [INFO] train episode 48472: reward = -58.86, steps = 50 10:27:02 [INFO] train episode 48473: reward = -73.44, steps = 25 10:27:05 [INFO] train episode 48474: reward = -72.59, steps = 34 10:27:07 [INFO] train episode 48475: reward = -51.70, steps = 26 10:27:10 [INFO] train episode 48476: reward = -56.88, steps = 30 10:27:13 [INFO] train episode 48477: reward = -62.95, steps = 32 10:27:16 [INFO] train episode 48478: reward = -31.15, steps = 31 10:27:19 [INFO] train episode 48479: reward = -31.16, steps = 37 10:27:21 [INFO] train episode 48480: reward = -54.15, steps = 26 10:27:26 [INFO] train episode 48481: reward = -93.76, steps = 56 10:27:28 [INFO] train episode 48482: reward = -42.44, steps = 26 10:27:30 [INFO] train episode 48483: reward = -38.32, steps = 22 10:27:34 [INFO] train episode 48484: reward = -38.29, steps = 42 10:27:37 [INFO] train episode 48485: reward = -61.07, steps = 30 10:27:40 [INFO] train episode 48486: reward = -27.87, steps = 37 10:27:43 [INFO] train episode 48487: reward = -65.44, steps = 35 10:27:47 [INFO] train episode 48488: reward = -62.81, steps = 43 10:27:49 [INFO] train episode 48489: reward = -63.74, steps = 31 10:27:52 [INFO] train episode 48490: reward = -33.73, steps = 26 10:27:54 [INFO] train episode 48491: reward = -26.47, steps = 33 10:27:57 [INFO] train episode 48492: reward = -38.95, steps = 26 10:27:59 [INFO] train episode 48493: reward = -54.03, steps = 30 10:28:02 [INFO] train episode 48494: reward = -41.33, steps = 28 10:28:04 [INFO] train episode 48495: reward = -51.80, steps = 19 10:28:06 [INFO] train episode 48496: reward = -33.24, steps = 24 10:28:08 [INFO] train episode 48497: reward = -47.68, steps = 24 10:28:10 [INFO] train episode 48498: reward = -57.60, steps = 21 10:28:12 [INFO] train episode 48499: reward = -56.02, steps = 24 10:28:14 [INFO] train episode 48500: reward = -47.98, steps = 30 10:28:17 [INFO] train episode 48501: reward = -41.74, steps = 29 10:28:20 [INFO] train episode 48502: reward = -32.70, steps = 36 10:28:22 [INFO] train episode 48503: reward = -43.45, steps = 24 10:28:24 [INFO] train episode 48504: reward = -42.34, steps = 21 10:28:28 [INFO] train episode 48505: reward = -31.75, steps = 43 10:28:30 [INFO] train episode 48506: reward = -51.47, steps = 23 10:28:31 [INFO] train episode 48507: reward = -30.59, steps = 21 10:28:35 [INFO] train episode 48508: reward = -44.91, steps = 39 10:28:38 [INFO] train episode 48509: reward = -53.05, steps = 31 10:28:41 [INFO] train episode 48510: reward = -49.51, steps = 38 10:28:43 [INFO] train episode 48511: reward = -48.88, steps = 22 10:28:47 [INFO] train episode 48512: reward = -40.53, steps = 44 10:28:49 [INFO] train episode 48513: reward = -50.48, steps = 19 10:28:52 [INFO] train episode 48514: reward = -70.24, steps = 33 10:28:55 [INFO] train episode 48515: reward = -36.50, steps = 35 10:28:58 [INFO] train episode 48516: reward = -46.48, steps = 31 10:29:00 [INFO] train episode 48517: reward = -43.30, steps = 20 10:29:02 [INFO] train episode 48518: reward = -46.06, steps = 27 10:29:05 [INFO] train episode 48519: reward = -92.24, steps = 28 10:29:08 [INFO] train episode 48520: reward = -53.94, steps = 29 10:29:10 [INFO] train episode 48521: reward = -43.57, steps = 23 10:29:12 [INFO] train episode 48522: reward = -58.73, steps = 22 10:29:15 [INFO] train episode 48523: reward = -96.54, steps = 40 10:29:17 [INFO] train episode 48524: reward = -45.11, steps = 22 10:29:20 [INFO] train episode 48525: reward = -67.95, steps = 31 10:29:23 [INFO] train episode 48526: reward = -65.38, steps = 28 10:29:25 [INFO] train episode 48527: reward = -75.37, steps = 30 10:29:28 [INFO] train episode 48528: reward = -30.23, steps = 25 10:29:29 [INFO] train episode 48529: reward = -56.08, steps = 21 10:29:32 [INFO] train episode 48530: reward = -63.81, steps = 26 10:29:34 [INFO] train episode 48531: reward = -38.98, steps = 27 10:29:36 [INFO] train episode 48532: reward = -17.78, steps = 21 10:29:40 [INFO] train episode 48533: reward = -79.02, steps = 43 10:29:44 [INFO] train episode 48534: reward = -48.28, steps = 45 10:29:47 [INFO] train episode 48535: reward = -90.20, steps = 39 10:29:49 [INFO] train episode 48536: reward = -50.76, steps = 21 10:29:51 [INFO] train episode 48537: reward = -65.51, steps = 22 10:29:54 [INFO] train episode 48538: reward = -36.96, steps = 33 10:29:56 [INFO] train episode 48539: reward = -40.32, steps = 21 10:29:59 [INFO] train episode 48540: reward = -44.49, steps = 36 10:30:01 [INFO] train episode 48541: reward = -37.26, steps = 22 10:30:03 [INFO] train episode 48542: reward = -66.66, steps = 24 10:30:05 [INFO] train episode 48543: reward = -40.82, steps = 20 10:30:07 [INFO] train episode 48544: reward = -35.12, steps = 22 10:30:09 [INFO] train episode 48545: reward = -52.18, steps = 29 10:30:12 [INFO] train episode 48546: reward = -49.67, steps = 34 10:30:14 [INFO] train episode 48547: reward = -32.48, steps = 22 10:30:18 [INFO] train episode 48548: reward = -60.63, steps = 39 10:30:20 [INFO] train episode 48549: reward = -51.91, steps = 34 10:30:23 [INFO] train episode 48550: reward = -56.18, steps = 27 10:30:29 [INFO] train episode 48551: reward = -147.62, steps = 67 10:30:32 [INFO] train episode 48552: reward = -40.36, steps = 43 10:30:34 [INFO] train episode 48553: reward = -71.95, steps = 20 10:30:37 [INFO] train episode 48554: reward = -49.40, steps = 31 10:30:41 [INFO] train episode 48555: reward = -103.90, steps = 52 10:30:44 [INFO] train episode 48556: reward = -48.83, steps = 23 10:30:46 [INFO] train episode 48557: reward = -30.79, steps = 23 10:30:47 [INFO] train episode 48558: reward = -66.41, steps = 21 10:30:50 [INFO] train episode 48559: reward = -53.27, steps = 30 10:30:52 [INFO] train episode 48560: reward = -52.57, steps = 29 10:30:54 [INFO] train episode 48561: reward = -37.39, steps = 20 10:30:57 [INFO] train episode 48562: reward = -81.85, steps = 32 10:30:59 [INFO] train episode 48563: reward = -42.64, steps = 22 10:31:02 [INFO] train episode 48564: reward = -48.28, steps = 33 10:31:04 [INFO] train episode 48565: reward = -43.44, steps = 25 10:31:06 [INFO] train episode 48566: reward = -35.99, steps = 24 10:31:08 [INFO] train episode 48567: reward = -51.86, steps = 24 10:31:10 [INFO] train episode 48568: reward = -64.32, steps = 21 10:31:13 [INFO] train episode 48569: reward = -61.50, steps = 30 10:31:15 [INFO] train episode 48570: reward = -29.20, steps = 27 10:31:17 [INFO] train episode 48571: reward = -41.88, steps = 20 10:31:19 [INFO] train episode 48572: reward = -73.29, steps = 26 10:31:22 [INFO] train episode 48573: reward = -63.65, steps = 31 10:31:24 [INFO] train episode 48574: reward = -73.21, steps = 27 10:31:26 [INFO] train episode 48575: reward = -38.32, steps = 20 10:31:29 [INFO] train episode 48576: reward = -58.93, steps = 31 10:31:32 [INFO] train episode 48577: reward = -61.34, steps = 38 10:31:35 [INFO] train episode 48578: reward = -35.95, steps = 30 10:31:38 [INFO] train episode 48579: reward = -35.23, steps = 44 10:31:41 [INFO] train episode 48580: reward = -50.99, steps = 29 10:31:43 [INFO] train episode 48581: reward = -30.86, steps = 21 10:31:47 [INFO] train episode 48582: reward = -38.38, steps = 37 10:31:49 [INFO] train episode 48583: reward = -76.31, steps = 20 10:31:50 [INFO] train episode 48584: reward = -44.54, steps = 21 10:31:53 [INFO] train episode 48585: reward = -16.85, steps = 29 10:31:55 [INFO] train episode 48586: reward = -45.77, steps = 24 10:31:57 [INFO] train episode 48587: reward = -43.41, steps = 25 10:31:59 [INFO] train episode 48588: reward = -70.63, steps = 24 10:32:03 [INFO] train episode 48589: reward = -46.00, steps = 39 10:32:06 [INFO] train episode 48590: reward = -53.82, steps = 39 10:32:08 [INFO] train episode 48591: reward = -65.88, steps = 21 10:32:11 [INFO] train episode 48592: reward = -65.65, steps = 33 10:32:14 [INFO] train episode 48593: reward = -43.32, steps = 42 10:32:16 [INFO] train episode 48594: reward = -37.71, steps = 22 10:32:19 [INFO] train episode 48595: reward = -42.36, steps = 22 10:32:21 [INFO] train episode 48596: reward = -58.81, steps = 24 10:32:24 [INFO] train episode 48597: reward = -34.94, steps = 35 10:32:26 [INFO] train episode 48598: reward = -54.25, steps = 23 10:32:29 [INFO] train episode 48599: reward = -66.74, steps = 42 10:32:31 [INFO] train episode 48600: reward = -41.67, steps = 20 10:32:33 [INFO] train episode 48601: reward = -41.22, steps = 24 10:32:36 [INFO] train episode 48602: reward = -63.85, steps = 27 10:32:38 [INFO] train episode 48603: reward = -76.71, steps = 32 10:32:41 [INFO] train episode 48604: reward = -78.41, steps = 26 10:32:43 [INFO] train episode 48605: reward = -89.56, steps = 22 10:32:45 [INFO] train episode 48606: reward = -49.58, steps = 24 10:32:47 [INFO] train episode 48607: reward = -55.08, steps = 27 10:32:51 [INFO] train episode 48608: reward = -39.27, steps = 39 10:32:54 [INFO] train episode 48609: reward = -48.08, steps = 34 10:32:56 [INFO] train episode 48610: reward = -57.53, steps = 28 10:32:58 [INFO] train episode 48611: reward = -39.74, steps = 21 10:33:00 [INFO] train episode 48612: reward = -48.65, steps = 19 10:33:02 [INFO] train episode 48613: reward = -69.99, steps = 22 10:33:03 [INFO] train episode 48614: reward = -65.31, steps = 19 10:33:06 [INFO] train episode 48615: reward = -31.70, steps = 31 10:33:10 [INFO] train episode 48616: reward = -68.38, steps = 41 10:33:13 [INFO] train episode 48617: reward = -48.20, steps = 32 10:33:16 [INFO] train episode 48618: reward = -45.81, steps = 38 10:33:19 [INFO] train episode 48619: reward = -69.99, steps = 38 10:33:24 [INFO] train episode 48620: reward = -54.64, steps = 55 10:33:27 [INFO] train episode 48621: reward = -42.08, steps = 31 10:33:29 [INFO] train episode 48622: reward = -73.64, steps = 28 10:33:34 [INFO] train episode 48623: reward = -61.65, steps = 60 10:33:37 [INFO] train episode 48624: reward = -42.21, steps = 27 10:33:39 [INFO] train episode 48625: reward = -44.64, steps = 22 10:33:41 [INFO] train episode 48626: reward = -42.95, steps = 32 10:33:45 [INFO] train episode 48627: reward = -38.23, steps = 46 10:33:48 [INFO] train episode 48628: reward = -46.29, steps = 28 10:33:50 [INFO] train episode 48629: reward = -51.26, steps = 27 10:33:54 [INFO] train episode 48630: reward = -37.58, steps = 40 10:33:57 [INFO] train episode 48631: reward = -76.35, steps = 36 10:34:01 [INFO] train episode 48632: reward = -40.79, steps = 50 10:34:03 [INFO] train episode 48633: reward = -68.84, steps = 26 10:34:07 [INFO] train episode 48634: reward = -22.19, steps = 36 10:34:10 [INFO] train episode 48635: reward = -104.02, steps = 40 10:34:13 [INFO] train episode 48636: reward = -41.80, steps = 26 10:34:14 [INFO] train episode 48637: reward = -59.86, steps = 21 10:34:18 [INFO] train episode 48638: reward = -103.05, steps = 38 10:34:21 [INFO] train episode 48639: reward = -25.21, steps = 36 10:34:22 [INFO] train episode 48640: reward = -45.60, steps = 21 10:34:27 [INFO] train episode 48641: reward = -101.62, steps = 51 10:34:29 [INFO] train episode 48642: reward = -39.76, steps = 23 10:34:31 [INFO] train episode 48643: reward = -55.85, steps = 24 10:34:34 [INFO] train episode 48644: reward = -73.12, steps = 29 10:34:36 [INFO] train episode 48645: reward = -20.87, steps = 29 10:34:39 [INFO] train episode 48646: reward = -55.45, steps = 20 10:34:43 [INFO] train episode 48647: reward = -91.95, steps = 42 10:34:45 [INFO] train episode 48648: reward = -30.20, steps = 31 10:34:48 [INFO] train episode 48649: reward = -34.71, steps = 25 10:34:50 [INFO] train episode 48650: reward = -30.02, steps = 33 10:34:52 [INFO] train episode 48651: reward = -31.47, steps = 22 10:34:55 [INFO] train episode 48652: reward = -30.56, steps = 35 10:35:00 [INFO] train episode 48653: reward = -44.17, steps = 51 10:35:02 [INFO] train episode 48654: reward = -63.43, steps = 24 10:35:05 [INFO] train episode 48655: reward = -33.35, steps = 28 10:35:08 [INFO] train episode 48656: reward = -24.65, steps = 40 10:35:10 [INFO] train episode 48657: reward = -43.15, steps = 22 10:35:12 [INFO] train episode 48658: reward = -39.09, steps = 22 10:35:18 [INFO] train episode 48659: reward = -104.46, steps = 68 10:35:21 [INFO] train episode 48660: reward = -36.53, steps = 35 10:35:23 [INFO] train episode 48661: reward = -72.29, steps = 26 10:35:25 [INFO] train episode 48662: reward = -65.07, steps = 22 10:35:27 [INFO] train episode 48663: reward = -74.50, steps = 20 10:35:30 [INFO] train episode 48664: reward = -20.75, steps = 34 10:35:33 [INFO] train episode 48665: reward = -61.82, steps = 33 10:35:35 [INFO] train episode 48666: reward = -42.83, steps = 24 10:35:39 [INFO] train episode 48667: reward = -137.22, steps = 47 10:35:41 [INFO] train episode 48668: reward = -61.98, steps = 31 10:35:44 [INFO] train episode 48669: reward = -31.17, steps = 26 10:35:45 [INFO] train episode 48670: reward = -57.07, steps = 18 10:35:50 [INFO] train episode 48671: reward = -73.32, steps = 48 10:35:51 [INFO] train episode 48672: reward = -50.82, steps = 18 10:35:53 [INFO] train episode 48673: reward = -36.26, steps = 21 10:35:55 [INFO] train episode 48674: reward = -57.50, steps = 26 10:35:57 [INFO] train episode 48675: reward = -43.24, steps = 26 10:35:59 [INFO] train episode 48676: reward = -58.26, steps = 23 10:36:03 [INFO] train episode 48677: reward = -53.76, steps = 38 10:36:05 [INFO] train episode 48678: reward = -58.49, steps = 23 10:36:07 [INFO] train episode 48679: reward = -57.89, steps = 23 10:36:11 [INFO] train episode 48680: reward = -93.78, steps = 50 10:36:14 [INFO] train episode 48681: reward = -41.44, steps = 40 10:36:18 [INFO] train episode 48682: reward = -61.01, steps = 38 10:36:20 [INFO] train episode 48683: reward = -68.57, steps = 21 10:36:23 [INFO] train episode 48684: reward = -80.72, steps = 38 10:36:26 [INFO] train episode 48685: reward = -18.73, steps = 39 10:36:29 [INFO] train episode 48686: reward = -46.26, steps = 27 10:36:31 [INFO] train episode 48687: reward = -50.25, steps = 24 10:36:33 [INFO] train episode 48688: reward = -33.91, steps = 23 10:36:36 [INFO] train episode 48689: reward = -31.78, steps = 37 10:36:39 [INFO] train episode 48690: reward = -42.20, steps = 28 10:36:42 [INFO] train episode 48691: reward = -73.68, steps = 36 10:36:44 [INFO] train episode 48692: reward = -42.24, steps = 25 10:36:46 [INFO] train episode 48693: reward = -38.29, steps = 21 10:36:50 [INFO] train episode 48694: reward = -67.89, steps = 48 10:36:53 [INFO] train episode 48695: reward = -17.14, steps = 38 10:36:57 [INFO] train episode 48696: reward = -33.31, steps = 38 10:36:59 [INFO] train episode 48697: reward = -47.08, steps = 20 10:37:01 [INFO] train episode 48698: reward = -53.64, steps = 32 10:37:05 [INFO] train episode 48699: reward = -52.81, steps = 37 10:37:07 [INFO] train episode 48700: reward = -27.61, steps = 30 10:37:10 [INFO] train episode 48701: reward = -84.75, steps = 36 10:37:13 [INFO] train episode 48702: reward = -38.60, steps = 35 10:37:16 [INFO] train episode 48703: reward = -50.67, steps = 31 10:37:18 [INFO] train episode 48704: reward = -40.42, steps = 24 10:37:22 [INFO] train episode 48705: reward = -69.60, steps = 47 10:37:26 [INFO] train episode 48706: reward = -66.58, steps = 45 10:37:29 [INFO] train episode 48707: reward = -82.44, steps = 26 10:37:32 [INFO] train episode 48708: reward = -30.80, steps = 31 10:37:36 [INFO] train episode 48709: reward = -43.63, steps = 40 10:37:39 [INFO] train episode 48710: reward = -56.75, steps = 38 10:37:40 [INFO] train episode 48711: reward = -38.95, steps = 18 10:37:42 [INFO] train episode 48712: reward = -73.55, steps = 22 10:37:45 [INFO] train episode 48713: reward = -52.73, steps = 32 10:37:47 [INFO] train episode 48714: reward = -47.64, steps = 21 10:37:48 [INFO] train episode 48715: reward = -55.22, steps = 19 10:37:51 [INFO] train episode 48716: reward = -45.10, steps = 27 10:37:54 [INFO] train episode 48717: reward = -66.98, steps = 33 10:37:57 [INFO] train episode 48718: reward = -30.05, steps = 34 10:37:59 [INFO] train episode 48719: reward = -50.23, steps = 21 10:38:00 [INFO] train episode 48720: reward = -33.43, steps = 20 10:38:04 [INFO] train episode 48721: reward = -73.05, steps = 42 10:38:08 [INFO] train episode 48722: reward = -68.23, steps = 43 10:38:10 [INFO] train episode 48723: reward = -59.26, steps = 22 10:38:12 [INFO] train episode 48724: reward = -48.77, steps = 21 10:38:14 [INFO] train episode 48725: reward = -39.83, steps = 32 10:38:18 [INFO] train episode 48726: reward = -61.26, steps = 48 10:38:21 [INFO] train episode 48727: reward = -29.40, steps = 32 10:38:25 [INFO] train episode 48728: reward = -45.70, steps = 42 10:38:28 [INFO] train episode 48729: reward = -26.51, steps = 37 10:38:30 [INFO] train episode 48730: reward = -83.75, steps = 23 10:38:33 [INFO] train episode 48731: reward = -47.50, steps = 31 10:38:35 [INFO] train episode 48732: reward = -56.82, steps = 21 10:38:38 [INFO] train episode 48733: reward = -65.94, steps = 36 10:38:43 [INFO] train episode 48734: reward = -127.07, steps = 53 10:38:45 [INFO] train episode 48735: reward = -33.24, steps = 31 10:38:47 [INFO] train episode 48736: reward = -41.34, steps = 23 10:38:50 [INFO] train episode 48737: reward = -72.09, steps = 31 10:38:53 [INFO] train episode 48738: reward = -53.31, steps = 36 10:38:56 [INFO] train episode 48739: reward = -52.83, steps = 27 10:39:00 [INFO] train episode 48740: reward = -51.93, steps = 47 10:39:02 [INFO] train episode 48741: reward = -57.72, steps = 29 10:39:07 [INFO] train episode 48742: reward = -81.48, steps = 59 10:39:10 [INFO] train episode 48743: reward = -57.00, steps = 29 10:39:12 [INFO] train episode 48744: reward = -69.25, steps = 21 10:39:15 [INFO] train episode 48745: reward = -38.76, steps = 34 10:39:19 [INFO] train episode 48746: reward = -77.29, steps = 49 10:39:22 [INFO] train episode 48747: reward = -42.16, steps = 39 10:39:25 [INFO] train episode 48748: reward = -17.56, steps = 31 10:39:27 [INFO] train episode 48749: reward = -44.96, steps = 20 10:39:30 [INFO] train episode 48750: reward = -76.25, steps = 36 10:39:32 [INFO] train episode 48751: reward = -64.69, steps = 21 10:39:34 [INFO] train episode 48752: reward = -50.40, steps = 32 10:39:38 [INFO] train episode 48753: reward = -26.04, steps = 41 10:39:40 [INFO] train episode 48754: reward = -46.73, steps = 22 10:39:42 [INFO] train episode 48755: reward = -53.39, steps = 25 10:39:45 [INFO] train episode 48756: reward = -45.05, steps = 33 10:39:48 [INFO] train episode 48757: reward = -62.95, steps = 33 10:39:51 [INFO] train episode 48758: reward = -64.49, steps = 33 10:39:54 [INFO] train episode 48759: reward = -29.08, steps = 43 10:39:57 [INFO] train episode 48760: reward = -57.25, steps = 34 10:40:00 [INFO] train episode 48761: reward = -30.66, steps = 30 10:40:02 [INFO] train episode 48762: reward = -84.65, steps = 25 10:40:04 [INFO] train episode 48763: reward = -57.47, steps = 24 10:40:06 [INFO] train episode 48764: reward = -55.77, steps = 21 10:40:09 [INFO] train episode 48765: reward = -37.60, steps = 29 10:40:11 [INFO] train episode 48766: reward = -39.24, steps = 27 10:40:15 [INFO] train episode 48767: reward = -46.94, steps = 40 10:40:17 [INFO] train episode 48768: reward = -47.73, steps = 22 10:40:20 [INFO] train episode 48769: reward = -29.59, steps = 25 10:40:22 [INFO] train episode 48770: reward = -68.09, steps = 29 10:40:25 [INFO] train episode 48771: reward = -52.37, steps = 35 10:40:27 [INFO] train episode 48772: reward = -43.29, steps = 24 10:40:29 [INFO] train episode 48773: reward = -33.95, steps = 22 10:40:32 [INFO] train episode 48774: reward = -56.58, steps = 35 10:40:35 [INFO] train episode 48775: reward = -75.13, steps = 34 10:40:38 [INFO] train episode 48776: reward = -48.37, steps = 30 10:40:41 [INFO] train episode 48777: reward = -58.53, steps = 32 10:40:44 [INFO] train episode 48778: reward = -56.07, steps = 33 10:40:47 [INFO] train episode 48779: reward = -62.60, steps = 34 10:40:52 [INFO] train episode 48780: reward = -80.21, steps = 52 10:40:54 [INFO] train episode 48781: reward = -82.57, steps = 26 10:40:57 [INFO] train episode 48782: reward = -47.99, steps = 34 10:40:59 [INFO] train episode 48783: reward = -58.89, steps = 26 10:41:02 [INFO] train episode 48784: reward = -57.27, steps = 33 10:41:07 [INFO] train episode 48785: reward = -87.89, steps = 57 10:41:09 [INFO] train episode 48786: reward = -26.38, steps = 23 10:41:12 [INFO] train episode 48787: reward = -70.71, steps = 31 10:41:15 [INFO] train episode 48788: reward = -63.03, steps = 37 10:41:18 [INFO] train episode 48789: reward = -51.33, steps = 36 10:41:21 [INFO] train episode 48790: reward = -53.35, steps = 28 10:41:22 [INFO] train episode 48791: reward = -49.80, steps = 20 10:41:24 [INFO] train episode 48792: reward = -68.06, steps = 22 10:41:29 [INFO] train episode 48793: reward = -57.80, steps = 49 10:41:32 [INFO] train episode 48794: reward = -51.76, steps = 36 10:41:35 [INFO] train episode 48795: reward = -52.84, steps = 35 10:41:38 [INFO] train episode 48796: reward = -61.40, steps = 36 10:41:40 [INFO] train episode 48797: reward = -59.43, steps = 23 10:41:42 [INFO] train episode 48798: reward = -62.36, steps = 24 10:41:46 [INFO] train episode 48799: reward = -108.48, steps = 51 10:41:48 [INFO] train episode 48800: reward = -49.03, steps = 19 10:41:51 [INFO] train episode 48801: reward = -65.77, steps = 31 10:41:54 [INFO] train episode 48802: reward = -65.36, steps = 37 10:41:57 [INFO] train episode 48803: reward = -60.68, steps = 33 10:41:59 [INFO] train episode 48804: reward = -63.14, steps = 29 10:42:03 [INFO] train episode 48805: reward = -24.37, steps = 50 10:42:07 [INFO] train episode 48806: reward = -42.99, steps = 36 10:42:09 [INFO] train episode 48807: reward = -50.95, steps = 30 10:42:12 [INFO] train episode 48808: reward = -26.57, steps = 24 10:42:14 [INFO] train episode 48809: reward = -29.04, steps = 26 10:42:17 [INFO] train episode 48810: reward = -87.47, steps = 41 10:42:20 [INFO] train episode 48811: reward = -55.73, steps = 36 10:42:23 [INFO] train episode 48812: reward = -56.41, steps = 26 10:42:25 [INFO] train episode 48813: reward = -50.13, steps = 31 10:42:28 [INFO] train episode 48814: reward = -59.31, steps = 32 10:42:30 [INFO] train episode 48815: reward = -47.43, steps = 21 10:42:32 [INFO] train episode 48816: reward = -47.77, steps = 19 10:42:33 [INFO] train episode 48817: reward = -69.15, steps = 21 10:42:36 [INFO] train episode 48818: reward = -62.07, steps = 35 10:42:39 [INFO] train episode 48819: reward = -56.63, steps = 23 10:42:41 [INFO] train episode 48820: reward = -34.52, steps = 26 10:42:43 [INFO] train episode 48821: reward = -46.93, steps = 21 10:42:45 [INFO] train episode 48822: reward = -25.67, steps = 28 10:42:48 [INFO] train episode 48823: reward = -37.10, steps = 28 10:42:50 [INFO] train episode 48824: reward = -36.45, steps = 20 10:42:52 [INFO] train episode 48825: reward = -50.23, steps = 31 10:42:55 [INFO] train episode 48826: reward = -44.70, steps = 26 10:42:59 [INFO] train episode 48827: reward = -64.42, steps = 44 10:43:02 [INFO] train episode 48828: reward = -49.52, steps = 38 10:43:04 [INFO] train episode 48829: reward = -44.55, steps = 28 10:43:06 [INFO] train episode 48830: reward = -57.08, steps = 24 10:43:11 [INFO] train episode 48831: reward = -48.61, steps = 45 10:43:13 [INFO] train episode 48832: reward = -38.75, steps = 25 10:43:16 [INFO] train episode 48833: reward = -61.67, steps = 26 10:43:18 [INFO] train episode 48834: reward = -60.64, steps = 24 10:43:21 [INFO] train episode 48835: reward = -80.07, steps = 36 10:43:23 [INFO] train episode 48836: reward = -69.24, steps = 21 10:43:25 [INFO] train episode 48837: reward = -76.26, steps = 27 10:43:29 [INFO] train episode 48838: reward = -49.29, steps = 40 10:43:30 [INFO] train episode 48839: reward = -44.24, steps = 20 10:43:34 [INFO] train episode 48840: reward = -55.53, steps = 43 10:43:37 [INFO] train episode 48841: reward = -71.97, steps = 40 10:43:40 [INFO] train episode 48842: reward = -44.27, steps = 35 10:43:43 [INFO] train episode 48843: reward = -35.07, steps = 27 10:43:46 [INFO] train episode 48844: reward = -41.10, steps = 31 10:43:49 [INFO] train episode 48845: reward = -68.44, steps = 35 10:43:51 [INFO] train episode 48846: reward = -38.99, steps = 23 10:43:54 [INFO] train episode 48847: reward = -63.57, steps = 33 10:43:56 [INFO] train episode 48848: reward = -67.95, steps = 28 10:43:59 [INFO] train episode 48849: reward = -43.52, steps = 35 10:44:02 [INFO] train episode 48850: reward = -35.57, steps = 31 10:44:04 [INFO] train episode 48851: reward = -55.04, steps = 28 10:44:07 [INFO] train episode 48852: reward = -54.63, steps = 25 10:44:09 [INFO] train episode 48853: reward = -50.56, steps = 28 10:44:14 [INFO] train episode 48854: reward = -50.85, steps = 54 10:44:16 [INFO] train episode 48855: reward = -36.51, steps = 24 10:44:18 [INFO] train episode 48856: reward = -52.15, steps = 27 10:44:24 [INFO] train episode 48857: reward = -49.98, steps = 62 10:44:25 [INFO] train episode 48858: reward = -37.39, steps = 21 10:44:27 [INFO] train episode 48859: reward = -52.59, steps = 20 10:44:30 [INFO] train episode 48860: reward = -62.69, steps = 32 10:44:33 [INFO] train episode 48861: reward = -23.34, steps = 25 10:44:34 [INFO] train episode 48862: reward = -77.61, steps = 20 10:44:37 [INFO] train episode 48863: reward = -41.00, steps = 26 10:44:38 [INFO] train episode 48864: reward = -30.62, steps = 17 10:44:43 [INFO] train episode 48865: reward = -95.55, steps = 53 10:44:46 [INFO] train episode 48866: reward = -53.59, steps = 38 10:44:48 [INFO] train episode 48867: reward = -49.26, steps = 21 10:44:51 [INFO] train episode 48868: reward = -51.84, steps = 32 10:44:54 [INFO] train episode 48869: reward = -48.69, steps = 32 10:44:57 [INFO] train episode 48870: reward = -47.93, steps = 34 10:44:59 [INFO] train episode 48871: reward = -36.90, steps = 34 10:45:01 [INFO] train episode 48872: reward = -59.59, steps = 20 10:45:05 [INFO] train episode 48873: reward = -40.04, steps = 36 10:45:08 [INFO] train episode 48874: reward = -32.60, steps = 36 10:45:10 [INFO] train episode 48875: reward = -74.81, steps = 30 10:45:13 [INFO] train episode 48876: reward = -56.59, steps = 36 10:45:17 [INFO] train episode 48877: reward = -28.41, steps = 45 10:45:19 [INFO] train episode 48878: reward = -43.39, steps = 21 10:45:22 [INFO] train episode 48879: reward = -33.14, steps = 33 10:45:24 [INFO] train episode 48880: reward = -56.71, steps = 22 10:45:27 [INFO] train episode 48881: reward = -54.96, steps = 32 10:45:30 [INFO] train episode 48882: reward = -28.07, steps = 33 10:45:33 [INFO] train episode 48883: reward = -33.29, steps = 37 10:45:36 [INFO] train episode 48884: reward = -54.34, steps = 38 10:45:38 [INFO] train episode 48885: reward = -60.20, steps = 25 10:45:41 [INFO] train episode 48886: reward = -67.48, steps = 26 10:45:43 [INFO] train episode 48887: reward = -47.59, steps = 26 10:45:46 [INFO] train episode 48888: reward = -47.88, steps = 33 10:45:49 [INFO] train episode 48889: reward = -64.93, steps = 41 10:45:53 [INFO] train episode 48890: reward = -89.26, steps = 42 10:45:56 [INFO] train episode 48891: reward = -43.09, steps = 29 10:46:00 [INFO] train episode 48892: reward = -42.87, steps = 57 10:46:04 [INFO] train episode 48893: reward = -32.26, steps = 37 10:46:07 [INFO] train episode 48894: reward = -84.93, steps = 31 10:46:09 [INFO] train episode 48895: reward = -51.04, steps = 21 10:46:13 [INFO] train episode 48896: reward = -53.25, steps = 43 10:46:15 [INFO] train episode 48897: reward = -41.39, steps = 29 10:46:19 [INFO] train episode 48898: reward = -55.41, steps = 51 10:46:22 [INFO] train episode 48899: reward = -30.87, steps = 35 10:46:25 [INFO] train episode 48900: reward = -36.76, steps = 26 10:46:27 [INFO] train episode 48901: reward = -59.25, steps = 22 10:46:31 [INFO] train episode 48902: reward = -30.73, steps = 52 10:46:34 [INFO] train episode 48903: reward = -58.05, steps = 29 10:46:37 [INFO] train episode 48904: reward = -48.85, steps = 34 10:46:40 [INFO] train episode 48905: reward = -54.44, steps = 32 10:46:42 [INFO] train episode 48906: reward = -89.26, steps = 27 10:46:44 [INFO] train episode 48907: reward = -45.06, steps = 22 10:46:47 [INFO] train episode 48908: reward = -41.55, steps = 33 10:46:51 [INFO] train episode 48909: reward = -55.84, steps = 43 10:46:53 [INFO] train episode 48910: reward = -31.67, steps = 24 10:46:54 [INFO] train episode 48911: reward = -63.75, steps = 20 10:46:56 [INFO] train episode 48912: reward = -73.90, steps = 19 10:46:58 [INFO] train episode 48913: reward = -59.28, steps = 21 10:47:01 [INFO] train episode 48914: reward = -51.30, steps = 29 10:47:03 [INFO] train episode 48915: reward = -45.29, steps = 21 10:47:05 [INFO] train episode 48916: reward = -35.05, steps = 23 10:47:08 [INFO] train episode 48917: reward = -38.54, steps = 37 10:47:10 [INFO] train episode 48918: reward = -50.09, steps = 25 10:47:12 [INFO] train episode 48919: reward = -58.00, steps = 18 10:47:16 [INFO] train episode 48920: reward = -65.29, steps = 50 10:47:18 [INFO] train episode 48921: reward = -34.68, steps = 23 10:47:20 [INFO] train episode 48922: reward = -30.72, steps = 22 10:47:22 [INFO] train episode 48923: reward = -63.29, steps = 19 10:47:24 [INFO] train episode 48924: reward = -68.74, steps = 29 10:47:26 [INFO] train episode 48925: reward = -56.44, steps = 21 10:47:29 [INFO] train episode 48926: reward = -36.00, steps = 37 10:47:32 [INFO] train episode 48927: reward = -37.83, steps = 25 10:47:35 [INFO] train episode 48928: reward = -56.20, steps = 47 10:47:38 [INFO] train episode 48929: reward = -29.66, steps = 29 10:47:40 [INFO] train episode 48930: reward = -62.83, steps = 24 10:47:43 [INFO] train episode 48931: reward = -48.08, steps = 30 10:47:46 [INFO] train episode 48932: reward = -58.85, steps = 32 10:47:49 [INFO] train episode 48933: reward = -34.51, steps = 39 10:47:54 [INFO] train episode 48934: reward = -50.59, steps = 55 10:47:57 [INFO] train episode 48935: reward = -51.05, steps = 39 10:48:00 [INFO] train episode 48936: reward = -39.79, steps = 30 10:48:02 [INFO] train episode 48937: reward = -48.02, steps = 21 10:48:03 [INFO] train episode 48938: reward = -48.30, steps = 21 10:48:06 [INFO] train episode 48939: reward = -40.82, steps = 31 10:48:09 [INFO] train episode 48940: reward = -71.26, steps = 39 10:48:12 [INFO] train episode 48941: reward = -38.84, steps = 26 10:48:15 [INFO] train episode 48942: reward = -38.79, steps = 37 10:48:18 [INFO] train episode 48943: reward = -27.78, steps = 33 10:48:20 [INFO] train episode 48944: reward = -50.46, steps = 21 10:48:22 [INFO] train episode 48945: reward = -66.36, steps = 30 10:48:25 [INFO] train episode 48946: reward = -89.49, steps = 39 10:48:28 [INFO] train episode 48947: reward = -38.76, steps = 30 10:48:30 [INFO] train episode 48948: reward = -45.56, steps = 23 10:48:32 [INFO] train episode 48949: reward = -51.01, steps = 20 10:48:35 [INFO] train episode 48950: reward = -30.63, steps = 34 10:48:38 [INFO] train episode 48951: reward = -48.47, steps = 28 10:48:39 [INFO] train episode 48952: reward = -35.64, steps = 22 10:48:41 [INFO] train episode 48953: reward = -46.10, steps = 21 10:48:44 [INFO] train episode 48954: reward = -68.51, steps = 31 10:48:47 [INFO] train episode 48955: reward = -46.14, steps = 30 10:48:50 [INFO] train episode 48956: reward = -72.85, steps = 37 10:48:53 [INFO] train episode 48957: reward = -59.03, steps = 41 10:48:58 [INFO] train episode 48958: reward = -80.55, steps = 40 10:49:00 [INFO] train episode 48959: reward = -30.04, steps = 31 10:49:03 [INFO] train episode 48960: reward = -52.25, steps = 23 10:49:06 [INFO] train episode 48961: reward = -36.19, steps = 44 10:49:10 [INFO] train episode 48962: reward = -40.89, steps = 42 10:49:12 [INFO] train episode 48963: reward = -48.03, steps = 28 10:49:15 [INFO] train episode 48964: reward = -28.81, steps = 32 10:49:17 [INFO] train episode 48965: reward = -46.19, steps = 22 10:49:20 [INFO] train episode 48966: reward = -19.35, steps = 30 10:49:23 [INFO] train episode 48967: reward = -43.72, steps = 36 10:49:25 [INFO] train episode 48968: reward = -47.14, steps = 20 10:49:28 [INFO] train episode 48969: reward = -92.56, steps = 34 10:49:30 [INFO] train episode 48970: reward = -63.52, steps = 29 10:49:35 [INFO] train episode 48971: reward = -67.98, steps = 52 10:49:38 [INFO] train episode 48972: reward = -45.47, steps = 44 10:49:40 [INFO] train episode 48973: reward = -53.77, steps = 18 10:49:43 [INFO] train episode 48974: reward = -70.12, steps = 40 10:49:46 [INFO] train episode 48975: reward = -42.39, steps = 28 10:49:48 [INFO] train episode 48976: reward = -62.11, steps = 25 10:49:51 [INFO] train episode 48977: reward = -20.41, steps = 33 10:49:54 [INFO] train episode 48978: reward = -50.69, steps = 39 10:49:57 [INFO] train episode 48979: reward = -59.82, steps = 34 10:50:01 [INFO] train episode 48980: reward = -74.29, steps = 41 10:50:03 [INFO] train episode 48981: reward = -63.54, steps = 34 10:50:06 [INFO] train episode 48982: reward = -43.89, steps = 21 10:50:11 [INFO] train episode 48983: reward = -97.06, steps = 62 10:50:13 [INFO] train episode 48984: reward = -38.69, steps = 26 10:50:15 [INFO] train episode 48985: reward = -46.19, steps = 22 10:50:18 [INFO] train episode 48986: reward = -21.82, steps = 37 10:50:21 [INFO] train episode 48987: reward = -58.83, steps = 31 10:50:23 [INFO] train episode 48988: reward = -49.96, steps = 26 10:50:25 [INFO] train episode 48989: reward = -53.70, steps = 25 10:50:29 [INFO] train episode 48990: reward = -63.14, steps = 48 10:50:31 [INFO] train episode 48991: reward = -54.18, steps = 25 10:50:35 [INFO] train episode 48992: reward = -53.42, steps = 48 10:50:39 [INFO] train episode 48993: reward = -55.57, steps = 34 10:50:42 [INFO] train episode 48994: reward = -41.98, steps = 37 10:50:44 [INFO] train episode 48995: reward = -44.52, steps = 26 10:50:47 [INFO] train episode 48996: reward = -45.59, steps = 33 10:50:50 [INFO] train episode 48997: reward = -35.62, steps = 32 10:50:53 [INFO] train episode 48998: reward = -59.28, steps = 38 10:50:56 [INFO] train episode 48999: reward = -33.14, steps = 34 10:50:59 [INFO] train episode 49000: reward = -37.35, steps = 34 10:51:02 [INFO] train episode 49001: reward = -44.70, steps = 32 10:51:04 [INFO] train episode 49002: reward = -55.73, steps = 29 10:51:07 [INFO] train episode 49003: reward = -37.51, steps = 32 10:51:10 [INFO] train episode 49004: reward = -31.92, steps = 31 10:51:13 [INFO] train episode 49005: reward = -16.95, steps = 36 10:51:16 [INFO] train episode 49006: reward = -46.18, steps = 30 10:51:18 [INFO] train episode 49007: reward = -41.84, steps = 29 10:51:21 [INFO] train episode 49008: reward = -57.36, steps = 36 10:51:25 [INFO] train episode 49009: reward = -52.49, steps = 41 10:51:29 [INFO] train episode 49010: reward = -53.33, steps = 51 10:51:32 [INFO] train episode 49011: reward = -74.60, steps = 35 10:51:35 [INFO] train episode 49012: reward = -66.71, steps = 38 10:51:38 [INFO] train episode 49013: reward = -66.00, steps = 36 10:51:42 [INFO] train episode 49014: reward = -52.64, steps = 35 10:51:44 [INFO] train episode 49015: reward = -35.95, steps = 28 10:51:47 [INFO] train episode 49016: reward = -22.68, steps = 29 10:51:50 [INFO] train episode 49017: reward = -43.08, steps = 34 10:51:52 [INFO] train episode 49018: reward = -48.99, steps = 26 10:51:54 [INFO] train episode 49019: reward = -49.98, steps = 21 10:51:59 [INFO] train episode 49020: reward = -61.69, steps = 46 10:52:01 [INFO] train episode 49021: reward = -28.43, steps = 23 10:52:04 [INFO] train episode 49022: reward = -32.05, steps = 38 10:52:05 [INFO] train episode 49023: reward = -50.73, steps = 20 10:52:09 [INFO] train episode 49024: reward = -43.23, steps = 42 10:52:12 [INFO] train episode 49025: reward = -81.09, steps = 31 10:52:14 [INFO] train episode 49026: reward = -34.77, steps = 21 10:52:16 [INFO] train episode 49027: reward = -35.66, steps = 29 10:52:19 [INFO] train episode 49028: reward = -58.66, steps = 33 10:52:21 [INFO] train episode 49029: reward = -43.90, steps = 25 10:52:23 [INFO] train episode 49030: reward = -42.68, steps = 25 10:52:25 [INFO] train episode 49031: reward = -96.14, steps = 23 10:52:28 [INFO] train episode 49032: reward = -40.82, steps = 28 10:52:32 [INFO] train episode 49033: reward = -84.46, steps = 51 10:52:35 [INFO] train episode 49034: reward = -38.69, steps = 26 10:52:37 [INFO] train episode 49035: reward = -32.87, steps = 31 10:52:40 [INFO] train episode 49036: reward = -55.31, steps = 25 10:52:41 [INFO] train episode 49037: reward = -43.81, steps = 23 10:52:45 [INFO] train episode 49038: reward = -29.18, steps = 40 10:52:47 [INFO] train episode 49039: reward = -38.32, steps = 25 10:52:51 [INFO] train episode 49040: reward = -22.31, steps = 37 10:52:53 [INFO] train episode 49041: reward = -47.33, steps = 25 10:52:56 [INFO] train episode 49042: reward = -70.48, steps = 32 10:53:00 [INFO] train episode 49043: reward = -73.75, steps = 48 10:53:02 [INFO] train episode 49044: reward = -41.25, steps = 20 10:53:04 [INFO] train episode 49045: reward = -40.13, steps = 34 10:53:08 [INFO] train episode 49046: reward = -80.33, steps = 38 10:53:10 [INFO] train episode 49047: reward = -50.31, steps = 21 10:53:12 [INFO] train episode 49048: reward = -56.60, steps = 25 10:53:14 [INFO] train episode 49049: reward = -65.58, steps = 26 10:53:16 [INFO] train episode 49050: reward = -73.00, steps = 17 10:53:18 [INFO] train episode 49051: reward = -49.60, steps = 29 10:53:21 [INFO] train episode 49052: reward = -44.21, steps = 32 10:53:24 [INFO] train episode 49053: reward = -47.52, steps = 41 10:53:27 [INFO] train episode 49054: reward = -62.37, steps = 35 10:53:29 [INFO] train episode 49055: reward = -48.99, steps = 22 10:53:32 [INFO] train episode 49056: reward = -79.66, steps = 29 10:53:34 [INFO] train episode 49057: reward = -46.20, steps = 19 10:53:36 [INFO] train episode 49058: reward = -55.52, steps = 24 10:53:39 [INFO] train episode 49059: reward = -35.75, steps = 33 10:53:41 [INFO] train episode 49060: reward = -57.58, steps = 27 10:53:43 [INFO] train episode 49061: reward = -41.34, steps = 26 10:53:47 [INFO] train episode 49062: reward = -31.30, steps = 35 10:53:49 [INFO] train episode 49063: reward = -51.14, steps = 35 10:53:51 [INFO] train episode 49064: reward = -42.22, steps = 23 10:53:54 [INFO] train episode 49065: reward = -65.33, steps = 27 10:53:55 [INFO] train episode 49066: reward = -49.07, steps = 20 10:53:58 [INFO] train episode 49067: reward = -51.64, steps = 33 10:54:00 [INFO] train episode 49068: reward = -64.67, steps = 21 10:54:02 [INFO] train episode 49069: reward = -69.92, steps = 20 10:54:05 [INFO] train episode 49070: reward = -30.80, steps = 30 10:54:08 [INFO] train episode 49071: reward = -46.49, steps = 41 10:54:13 [INFO] train episode 49072: reward = -64.90, steps = 59 10:54:18 [INFO] train episode 49073: reward = -77.69, steps = 52 10:54:20 [INFO] train episode 49074: reward = -30.34, steps = 25 10:54:23 [INFO] train episode 49075: reward = -31.92, steps = 35 10:54:25 [INFO] train episode 49076: reward = -74.24, steps = 28 10:54:27 [INFO] train episode 49077: reward = -44.86, steps = 26 10:54:31 [INFO] train episode 49078: reward = -39.48, steps = 38 10:54:32 [INFO] train episode 49079: reward = -69.04, steps = 20 10:54:36 [INFO] train episode 49080: reward = -59.38, steps = 38 10:54:39 [INFO] train episode 49081: reward = -23.91, steps = 29 10:54:41 [INFO] train episode 49082: reward = -52.65, steps = 20 10:54:45 [INFO] train episode 49083: reward = -62.60, steps = 41 10:54:47 [INFO] train episode 49084: reward = -32.70, steps = 30 10:54:50 [INFO] train episode 49085: reward = -40.47, steps = 31 10:54:52 [INFO] train episode 49086: reward = -56.57, steps = 23 10:54:54 [INFO] train episode 49087: reward = -46.11, steps = 24 10:54:58 [INFO] train episode 49088: reward = -67.21, steps = 39 10:55:00 [INFO] train episode 49089: reward = -94.04, steps = 28 10:55:04 [INFO] train episode 49090: reward = -81.42, steps = 44 10:55:06 [INFO] train episode 49091: reward = -62.70, steps = 26 10:55:09 [INFO] train episode 49092: reward = -51.45, steps = 37 10:55:12 [INFO] train episode 49093: reward = -33.55, steps = 31 10:55:15 [INFO] train episode 49094: reward = -50.46, steps = 31 10:55:17 [INFO] train episode 49095: reward = -32.34, steps = 24 10:55:19 [INFO] train episode 49096: reward = -43.70, steps = 23 10:55:22 [INFO] train episode 49097: reward = -58.24, steps = 36 10:55:25 [INFO] train episode 49098: reward = -60.11, steps = 36 10:55:28 [INFO] train episode 49099: reward = -45.43, steps = 34 10:55:30 [INFO] train episode 49100: reward = -66.51, steps = 19 10:55:33 [INFO] train episode 49101: reward = -65.63, steps = 37 10:55:34 [INFO] train episode 49102: reward = -37.31, steps = 19 10:55:36 [INFO] train episode 49103: reward = -49.45, steps = 25 10:55:39 [INFO] train episode 49104: reward = -44.26, steps = 24 10:55:41 [INFO] train episode 49105: reward = -48.45, steps = 25 10:55:43 [INFO] train episode 49106: reward = -51.33, steps = 26 10:55:46 [INFO] train episode 49107: reward = -26.03, steps = 31 10:55:48 [INFO] train episode 49108: reward = -40.51, steps = 29 10:55:52 [INFO] train episode 49109: reward = -29.23, steps = 49 10:55:56 [INFO] train episode 49110: reward = -42.30, steps = 33 10:55:59 [INFO] train episode 49111: reward = -55.36, steps = 33 10:56:01 [INFO] train episode 49112: reward = -53.48, steps = 23 10:56:03 [INFO] train episode 49113: reward = -45.86, steps = 25 10:56:05 [INFO] train episode 49114: reward = -42.01, steps = 24 10:56:09 [INFO] train episode 49115: reward = -45.62, steps = 46 10:56:11 [INFO] train episode 49116: reward = -18.81, steps = 25 10:56:13 [INFO] train episode 49117: reward = -30.15, steps = 22 10:56:16 [INFO] train episode 49118: reward = -28.08, steps = 30 10:56:17 [INFO] train episode 49119: reward = -52.96, steps = 19 10:56:20 [INFO] train episode 49120: reward = -55.66, steps = 27 10:56:22 [INFO] train episode 49121: reward = -30.57, steps = 31 10:56:25 [INFO] train episode 49122: reward = -48.07, steps = 35 10:56:28 [INFO] train episode 49123: reward = -30.00, steps = 27 10:56:31 [INFO] train episode 49124: reward = -14.03, steps = 42 10:56:35 [INFO] train episode 49125: reward = -43.53, steps = 38 10:56:36 [INFO] train episode 49126: reward = -36.18, steps = 19 10:56:38 [INFO] train episode 49127: reward = -53.16, steps = 20 10:56:42 [INFO] train episode 49128: reward = -59.68, steps = 45 10:56:46 [INFO] train episode 49129: reward = -56.05, steps = 37 10:56:48 [INFO] train episode 49130: reward = -60.73, steps = 29 10:56:50 [INFO] train episode 49131: reward = -57.42, steps = 20 10:56:52 [INFO] train episode 49132: reward = -71.30, steps = 21 10:56:54 [INFO] train episode 49133: reward = -69.05, steps = 33 10:56:58 [INFO] train episode 49134: reward = -81.97, steps = 36 10:57:01 [INFO] train episode 49135: reward = -67.99, steps = 27 10:57:02 [INFO] train episode 49136: reward = -68.56, steps = 20 10:57:05 [INFO] train episode 49137: reward = -45.38, steps = 37 10:57:08 [INFO] train episode 49138: reward = -43.20, steps = 25 10:57:11 [INFO] train episode 49139: reward = -52.44, steps = 36 10:57:15 [INFO] train episode 49140: reward = -43.06, steps = 46 10:57:17 [INFO] train episode 49141: reward = -46.58, steps = 28 10:57:20 [INFO] train episode 49142: reward = -49.17, steps = 26 10:57:23 [INFO] train episode 49143: reward = -29.83, steps = 35 10:57:27 [INFO] train episode 49144: reward = -103.79, steps = 49 10:57:29 [INFO] train episode 49145: reward = -39.64, steps = 23 10:57:33 [INFO] train episode 49146: reward = -53.52, steps = 36 10:57:36 [INFO] train episode 49147: reward = -53.24, steps = 40 10:57:39 [INFO] train episode 49148: reward = -30.60, steps = 33 10:57:41 [INFO] train episode 49149: reward = -48.78, steps = 20 10:57:44 [INFO] train episode 49150: reward = -28.60, steps = 38 10:57:47 [INFO] train episode 49151: reward = -64.02, steps = 37 10:57:52 [INFO] train episode 49152: reward = -33.24, steps = 55 10:57:55 [INFO] train episode 49153: reward = -45.90, steps = 34 10:57:59 [INFO] train episode 49154: reward = -41.65, steps = 42 10:58:01 [INFO] train episode 49155: reward = -39.32, steps = 25 10:58:04 [INFO] train episode 49156: reward = -47.47, steps = 28 10:58:06 [INFO] train episode 49157: reward = -58.90, steps = 32 10:58:09 [INFO] train episode 49158: reward = -43.58, steps = 30 10:58:12 [INFO] train episode 49159: reward = -44.09, steps = 38 10:58:14 [INFO] train episode 49160: reward = -61.48, steps = 21 10:58:19 [INFO] train episode 49161: reward = -88.30, steps = 52 10:58:24 [INFO] train episode 49162: reward = -105.32, steps = 59 10:58:26 [INFO] train episode 49163: reward = -52.85, steps = 25 10:58:28 [INFO] train episode 49164: reward = -35.45, steps = 30 10:58:31 [INFO] train episode 49165: reward = -64.53, steps = 36 10:58:33 [INFO] train episode 49166: reward = -50.18, steps = 23 10:58:36 [INFO] train episode 49167: reward = -22.88, steps = 24 10:58:39 [INFO] train episode 49168: reward = -66.89, steps = 42 10:58:41 [INFO] train episode 49169: reward = -50.70, steps = 23 10:58:45 [INFO] train episode 49170: reward = -56.97, steps = 41 10:58:48 [INFO] train episode 49171: reward = -58.29, steps = 41 10:58:51 [INFO] train episode 49172: reward = -19.05, steps = 31 10:58:53 [INFO] train episode 49173: reward = -42.93, steps = 22 10:58:57 [INFO] train episode 49174: reward = -32.19, steps = 47 10:58:59 [INFO] train episode 49175: reward = -64.97, steps = 23 10:59:01 [INFO] train episode 49176: reward = -43.61, steps = 20 10:59:04 [INFO] train episode 49177: reward = -18.67, steps = 33 10:59:08 [INFO] train episode 49178: reward = -42.09, steps = 40 10:59:09 [INFO] train episode 49179: reward = -41.71, steps = 21 10:59:11 [INFO] train episode 49180: reward = -56.21, steps = 21 10:59:15 [INFO] train episode 49181: reward = -30.94, steps = 46 10:59:17 [INFO] train episode 49182: reward = -27.78, steps = 27 10:59:20 [INFO] train episode 49183: reward = -35.50, steps = 27 10:59:23 [INFO] train episode 49184: reward = -53.24, steps = 32 10:59:26 [INFO] train episode 49185: reward = -35.15, steps = 43 10:59:29 [INFO] train episode 49186: reward = -43.54, steps = 25 10:59:32 [INFO] train episode 49187: reward = -40.30, steps = 40 10:59:35 [INFO] train episode 49188: reward = -21.74, steps = 34 10:59:36 [INFO] train episode 49189: reward = -46.80, steps = 15 10:59:38 [INFO] train episode 49190: reward = -60.80, steps = 22 10:59:44 [INFO] train episode 49191: reward = -63.66, steps = 63 10:59:46 [INFO] train episode 49192: reward = -53.80, steps = 22 10:59:48 [INFO] train episode 49193: reward = -77.53, steps = 30 10:59:51 [INFO] train episode 49194: reward = -60.41, steps = 34 10:59:54 [INFO] train episode 49195: reward = -24.75, steps = 37 10:59:57 [INFO] train episode 49196: reward = -44.53, steps = 31 10:59:59 [INFO] train episode 49197: reward = -30.98, steps = 25 11:00:02 [INFO] train episode 49198: reward = -27.69, steps = 30 11:00:04 [INFO] train episode 49199: reward = -65.75, steps = 21 11:00:07 [INFO] train episode 49200: reward = -17.85, steps = 34 11:00:08 [INFO] train episode 49201: reward = -78.73, steps = 21 11:00:12 [INFO] train episode 49202: reward = -63.28, steps = 42 11:00:15 [INFO] train episode 49203: reward = -53.88, steps = 37 11:00:18 [INFO] train episode 49204: reward = -54.13, steps = 25 11:00:19 [INFO] train episode 49205: reward = -32.85, steps = 22 11:00:23 [INFO] train episode 49206: reward = -45.73, steps = 33 11:00:26 [INFO] train episode 49207: reward = -75.97, steps = 35 11:00:28 [INFO] train episode 49208: reward = -40.82, steps = 24 11:00:32 [INFO] train episode 49209: reward = -36.17, steps = 41 11:00:34 [INFO] train episode 49210: reward = -32.35, steps = 26 11:00:37 [INFO] train episode 49211: reward = -24.67, steps = 37 11:00:42 [INFO] train episode 49212: reward = -99.36, steps = 56 11:00:44 [INFO] train episode 49213: reward = -47.46, steps = 21 11:00:46 [INFO] train episode 49214: reward = -69.76, steps = 24 11:00:50 [INFO] train episode 49215: reward = -36.17, steps = 43 11:00:53 [INFO] train episode 49216: reward = -58.98, steps = 32 11:00:54 [INFO] train episode 49217: reward = -46.82, steps = 19 11:00:59 [INFO] train episode 49218: reward = -58.47, steps = 47 11:01:00 [INFO] train episode 49219: reward = -39.53, steps = 19 11:01:04 [INFO] train episode 49220: reward = -67.35, steps = 43 11:01:06 [INFO] train episode 49221: reward = -38.35, steps = 27 11:01:08 [INFO] train episode 49222: reward = -64.57, steps = 25 11:01:12 [INFO] train episode 49223: reward = -55.93, steps = 38 11:01:15 [INFO] train episode 49224: reward = -60.33, steps = 37 11:01:18 [INFO] train episode 49225: reward = -48.33, steps = 40 11:01:23 [INFO] train episode 49226: reward = -46.23, steps = 54 11:01:26 [INFO] train episode 49227: reward = -33.65, steps = 38 11:01:29 [INFO] train episode 49228: reward = -35.59, steps = 32 11:01:31 [INFO] train episode 49229: reward = -61.83, steps = 20 11:01:33 [INFO] train episode 49230: reward = -32.17, steps = 21 11:01:37 [INFO] train episode 49231: reward = -62.73, steps = 55 11:01:40 [INFO] train episode 49232: reward = -30.20, steps = 31 11:01:43 [INFO] train episode 49233: reward = -55.53, steps = 34 11:01:45 [INFO] train episode 49234: reward = -49.39, steps = 22 11:01:47 [INFO] train episode 49235: reward = -55.96, steps = 20 11:01:50 [INFO] train episode 49236: reward = -44.40, steps = 32 11:01:51 [INFO] train episode 49237: reward = -45.56, steps = 21 11:01:54 [INFO] train episode 49238: reward = -59.14, steps = 35 11:01:58 [INFO] train episode 49239: reward = -77.72, steps = 48 11:02:01 [INFO] train episode 49240: reward = -61.69, steps = 29 11:02:03 [INFO] train episode 49241: reward = -44.12, steps = 22 11:02:06 [INFO] train episode 49242: reward = -42.45, steps = 32 11:02:09 [INFO] train episode 49243: reward = -15.17, steps = 42 11:02:12 [INFO] train episode 49244: reward = -59.12, steps = 32 11:02:16 [INFO] train episode 49245: reward = -49.96, steps = 46 11:02:19 [INFO] train episode 49246: reward = -38.24, steps = 29 11:02:21 [INFO] train episode 49247: reward = -39.90, steps = 29 11:02:24 [INFO] train episode 49248: reward = -36.10, steps = 27 11:02:25 [INFO] train episode 49249: reward = -30.74, steps = 20 11:02:28 [INFO] train episode 49250: reward = -33.27, steps = 28 11:02:31 [INFO] train episode 49251: reward = -27.94, steps = 40 11:02:34 [INFO] train episode 49252: reward = -88.92, steps = 28 11:02:38 [INFO] train episode 49253: reward = -44.54, steps = 39 11:02:40 [INFO] train episode 49254: reward = -52.35, steps = 23 11:02:42 [INFO] train episode 49255: reward = -28.75, steps = 34 11:02:44 [INFO] train episode 49256: reward = -47.40, steps = 20 11:02:46 [INFO] train episode 49257: reward = -55.50, steps = 20 11:02:48 [INFO] train episode 49258: reward = -75.27, steps = 19 11:02:50 [INFO] train episode 49259: reward = -78.58, steps = 28 11:02:54 [INFO] train episode 49260: reward = -77.88, steps = 42 11:02:58 [INFO] train episode 49261: reward = -53.68, steps = 52 11:03:01 [INFO] train episode 49262: reward = -46.04, steps = 33 11:03:04 [INFO] train episode 49263: reward = -89.18, steps = 32 11:03:08 [INFO] train episode 49264: reward = -46.53, steps = 44 11:03:10 [INFO] train episode 49265: reward = -44.37, steps = 29 11:03:15 [INFO] train episode 49266: reward = -32.35, steps = 53 11:03:19 [INFO] train episode 49267: reward = -73.88, steps = 47 11:03:22 [INFO] train episode 49268: reward = -39.16, steps = 21 11:03:23 [INFO] train episode 49269: reward = -56.59, steps = 23 11:03:27 [INFO] train episode 49270: reward = -87.27, steps = 39 11:03:30 [INFO] train episode 49271: reward = -45.91, steps = 39 11:03:33 [INFO] train episode 49272: reward = -35.76, steps = 36 11:03:36 [INFO] train episode 49273: reward = -44.63, steps = 27 11:03:39 [INFO] train episode 49274: reward = -48.98, steps = 40 11:03:44 [INFO] train episode 49275: reward = -42.63, steps = 51 11:03:47 [INFO] train episode 49276: reward = -43.79, steps = 38 11:03:50 [INFO] train episode 49277: reward = -33.14, steps = 40 11:03:53 [INFO] train episode 49278: reward = -33.30, steps = 27 11:03:55 [INFO] train episode 49279: reward = -63.99, steps = 24 11:03:58 [INFO] train episode 49280: reward = -30.14, steps = 34 11:04:00 [INFO] train episode 49281: reward = -56.95, steps = 23 11:04:05 [INFO] train episode 49282: reward = -42.90, steps = 56 11:04:07 [INFO] train episode 49283: reward = -31.39, steps = 29 11:04:10 [INFO] train episode 49284: reward = -51.59, steps = 25 11:04:14 [INFO] train episode 49285: reward = -70.15, steps = 49 11:04:18 [INFO] train episode 49286: reward = -18.72, steps = 45 11:04:19 [INFO] train episode 49287: reward = -47.24, steps = 21 11:04:22 [INFO] train episode 49288: reward = -39.62, steps = 32 11:04:24 [INFO] train episode 49289: reward = -37.11, steps = 22 11:04:29 [INFO] train episode 49290: reward = -78.40, steps = 53 11:04:33 [INFO] train episode 49291: reward = -65.35, steps = 45 11:04:36 [INFO] train episode 49292: reward = -31.07, steps = 34 11:04:37 [INFO] train episode 49293: reward = -43.48, steps = 21 11:04:39 [INFO] train episode 49294: reward = -47.11, steps = 20 11:04:42 [INFO] train episode 49295: reward = -56.10, steps = 27 11:04:43 [INFO] train episode 49296: reward = -45.78, steps = 20 11:04:46 [INFO] train episode 49297: reward = -42.26, steps = 33 11:04:49 [INFO] train episode 49298: reward = -58.72, steps = 36 11:04:51 [INFO] train episode 49299: reward = -34.70, steps = 21 11:04:54 [INFO] train episode 49300: reward = -75.21, steps = 37 11:04:57 [INFO] train episode 49301: reward = -34.93, steps = 30 11:05:00 [INFO] train episode 49302: reward = -52.16, steps = 36 11:05:03 [INFO] train episode 49303: reward = -26.67, steps = 33 11:05:06 [INFO] train episode 49304: reward = -55.38, steps = 33 11:05:09 [INFO] train episode 49305: reward = -46.56, steps = 40 11:05:12 [INFO] train episode 49306: reward = -81.84, steps = 29 11:05:14 [INFO] train episode 49307: reward = -37.11, steps = 21 11:05:16 [INFO] train episode 49308: reward = -40.37, steps = 24 11:05:19 [INFO] train episode 49309: reward = -49.64, steps = 33 11:05:21 [INFO] train episode 49310: reward = -47.81, steps = 29 11:05:25 [INFO] train episode 49311: reward = -29.59, steps = 38 11:05:30 [INFO] train episode 49312: reward = -127.28, steps = 65 11:05:34 [INFO] train episode 49313: reward = -55.08, steps = 40 11:05:36 [INFO] train episode 49314: reward = -46.25, steps = 30 11:05:39 [INFO] train episode 49315: reward = -58.44, steps = 30 11:05:45 [INFO] train episode 49316: reward = -135.85, steps = 70 11:05:47 [INFO] train episode 49317: reward = -37.66, steps = 26 11:05:49 [INFO] train episode 49318: reward = -54.90, steps = 25 11:05:53 [INFO] train episode 49319: reward = -34.86, steps = 38 11:05:54 [INFO] train episode 49320: reward = -55.82, steps = 21 11:05:57 [INFO] train episode 49321: reward = -21.90, steps = 34 11:06:01 [INFO] train episode 49322: reward = -38.13, steps = 36 11:06:04 [INFO] train episode 49323: reward = -48.87, steps = 37 11:06:07 [INFO] train episode 49324: reward = -47.98, steps = 24 11:06:10 [INFO] train episode 49325: reward = -68.33, steps = 35 11:06:12 [INFO] train episode 49326: reward = -17.57, steps = 33 11:06:16 [INFO] train episode 49327: reward = -28.31, steps = 42 11:06:19 [INFO] train episode 49328: reward = -50.66, steps = 31 11:06:22 [INFO] train episode 49329: reward = -24.15, steps = 38 11:06:24 [INFO] train episode 49330: reward = -54.16, steps = 22 11:06:27 [INFO] train episode 49331: reward = -52.41, steps = 31 11:06:29 [INFO] train episode 49332: reward = -42.46, steps = 29 11:06:32 [INFO] train episode 49333: reward = -63.82, steps = 31 11:06:35 [INFO] train episode 49334: reward = -59.55, steps = 35 11:06:38 [INFO] train episode 49335: reward = -19.57, steps = 32 11:06:40 [INFO] train episode 49336: reward = -39.32, steps = 29 11:06:43 [INFO] train episode 49337: reward = -38.44, steps = 27 11:06:46 [INFO] train episode 49338: reward = -89.06, steps = 34 11:06:48 [INFO] train episode 49339: reward = -50.51, steps = 30 11:06:51 [INFO] train episode 49340: reward = -45.44, steps = 27 11:06:52 [INFO] train episode 49341: reward = -52.80, steps = 17 11:06:56 [INFO] train episode 49342: reward = -53.10, steps = 40 11:06:58 [INFO] train episode 49343: reward = -62.01, steps = 27 11:07:00 [INFO] train episode 49344: reward = -48.01, steps = 28 11:07:04 [INFO] train episode 49345: reward = -77.07, steps = 36 11:07:07 [INFO] train episode 49346: reward = -13.70, steps = 39 11:07:09 [INFO] train episode 49347: reward = -50.03, steps = 21 11:07:11 [INFO] train episode 49348: reward = -43.61, steps = 26 11:07:13 [INFO] train episode 49349: reward = -51.09, steps = 25 11:07:17 [INFO] train episode 49350: reward = -19.17, steps = 38 11:07:20 [INFO] train episode 49351: reward = -36.47, steps = 34 11:07:22 [INFO] train episode 49352: reward = -27.31, steps = 26 11:07:24 [INFO] train episode 49353: reward = -37.36, steps = 23 11:07:26 [INFO] train episode 49354: reward = -47.57, steps = 28 11:07:31 [INFO] train episode 49355: reward = -48.88, steps = 50 11:07:33 [INFO] train episode 49356: reward = -52.12, steps = 24 11:07:38 [INFO] train episode 49357: reward = -72.89, steps = 61 11:07:41 [INFO] train episode 49358: reward = -45.73, steps = 36 11:07:44 [INFO] train episode 49359: reward = -59.82, steps = 33 11:07:47 [INFO] train episode 49360: reward = -37.77, steps = 31 11:07:51 [INFO] train episode 49361: reward = -53.16, steps = 48 11:07:55 [INFO] train episode 49362: reward = -58.73, steps = 49 11:07:57 [INFO] train episode 49363: reward = -83.38, steps = 20 11:08:00 [INFO] train episode 49364: reward = -44.33, steps = 41 11:08:03 [INFO] train episode 49365: reward = -45.18, steps = 36 11:08:06 [INFO] train episode 49366: reward = -38.73, steps = 24 11:08:08 [INFO] train episode 49367: reward = -41.88, steps = 27 11:08:10 [INFO] train episode 49368: reward = -49.66, steps = 23 11:08:13 [INFO] train episode 49369: reward = -43.52, steps = 30 11:08:16 [INFO] train episode 49370: reward = -81.28, steps = 36 11:08:18 [INFO] train episode 49371: reward = -47.49, steps = 24 11:08:20 [INFO] train episode 49372: reward = -33.77, steps = 30 11:08:26 [INFO] train episode 49373: reward = -116.23, steps = 61 11:08:28 [INFO] train episode 49374: reward = -56.14, steps = 24 11:08:29 [INFO] train episode 49375: reward = -58.71, steps = 17 11:08:32 [INFO] train episode 49376: reward = -41.52, steps = 24 11:08:34 [INFO] train episode 49377: reward = -41.60, steps = 28 11:08:36 [INFO] train episode 49378: reward = -37.40, steps = 25 11:08:39 [INFO] train episode 49379: reward = -39.58, steps = 27 11:08:41 [INFO] train episode 49380: reward = -55.30, steps = 26 11:08:46 [INFO] train episode 49381: reward = -62.78, steps = 54 11:08:49 [INFO] train episode 49382: reward = -41.91, steps = 34 11:08:51 [INFO] train episode 49383: reward = -41.12, steps = 26 11:08:55 [INFO] train episode 49384: reward = -58.87, steps = 49 11:08:59 [INFO] train episode 49385: reward = -19.14, steps = 33 11:09:04 [INFO] train episode 49386: reward = -100.84, steps = 65 11:09:07 [INFO] train episode 49387: reward = -29.35, steps = 32 11:09:11 [INFO] train episode 49388: reward = -46.51, steps = 38 11:09:13 [INFO] train episode 49389: reward = -64.82, steps = 24 11:09:16 [INFO] train episode 49390: reward = -31.25, steps = 33 11:09:18 [INFO] train episode 49391: reward = -59.16, steps = 28 11:09:20 [INFO] train episode 49392: reward = -49.10, steps = 22 11:09:22 [INFO] train episode 49393: reward = -60.20, steps = 23 11:09:24 [INFO] train episode 49394: reward = -52.75, steps = 24 11:09:28 [INFO] train episode 49395: reward = -58.71, steps = 40 11:09:29 [INFO] train episode 49396: reward = -72.85, steps = 20 11:09:32 [INFO] train episode 49397: reward = -32.49, steps = 24 11:09:34 [INFO] train episode 49398: reward = -49.48, steps = 34 11:09:37 [INFO] train episode 49399: reward = -38.41, steps = 30 11:09:40 [INFO] train episode 49400: reward = -41.17, steps = 37 11:09:43 [INFO] train episode 49401: reward = -55.32, steps = 26 11:09:44 [INFO] train episode 49402: reward = -49.70, steps = 22 11:09:49 [INFO] train episode 49403: reward = -40.65, steps = 52 11:09:51 [INFO] train episode 49404: reward = -59.45, steps = 26 11:09:54 [INFO] train episode 49405: reward = -48.11, steps = 36 11:09:56 [INFO] train episode 49406: reward = -62.32, steps = 20 11:09:59 [INFO] train episode 49407: reward = -42.06, steps = 38 11:10:03 [INFO] train episode 49408: reward = -78.77, steps = 43 11:10:05 [INFO] train episode 49409: reward = -48.94, steps = 19 11:10:08 [INFO] train episode 49410: reward = -26.18, steps = 36 11:10:11 [INFO] train episode 49411: reward = -32.39, steps = 38 11:10:14 [INFO] train episode 49412: reward = -48.30, steps = 30 11:10:16 [INFO] train episode 49413: reward = -65.35, steps = 18 11:10:17 [INFO] train episode 49414: reward = -59.47, steps = 19 11:10:21 [INFO] train episode 49415: reward = -84.17, steps = 40 11:10:23 [INFO] train episode 49416: reward = -58.45, steps = 31 11:10:26 [INFO] train episode 49417: reward = -25.88, steps = 28 11:10:28 [INFO] train episode 49418: reward = -32.38, steps = 30 11:10:32 [INFO] train episode 49419: reward = -54.89, steps = 37 11:10:35 [INFO] train episode 49420: reward = -58.46, steps = 44 11:10:38 [INFO] train episode 49421: reward = -46.50, steps = 24 11:10:39 [INFO] train episode 49422: reward = -55.39, steps = 18 11:10:41 [INFO] train episode 49423: reward = -70.02, steps = 24 11:10:45 [INFO] train episode 49424: reward = -48.60, steps = 42 11:10:47 [INFO] train episode 49425: reward = -41.54, steps = 20 11:10:49 [INFO] train episode 49426: reward = -58.95, steps = 26 11:10:52 [INFO] train episode 49427: reward = -79.48, steps = 34 11:10:58 [INFO] train episode 49428: reward = -76.55, steps = 64 11:11:02 [INFO] train episode 49429: reward = -60.22, steps = 39 11:11:03 [INFO] train episode 49430: reward = -51.62, steps = 18 11:11:05 [INFO] train episode 49431: reward = -65.02, steps = 20 11:11:09 [INFO] train episode 49432: reward = -78.36, steps = 45 11:11:11 [INFO] train episode 49433: reward = -81.81, steps = 25 11:11:15 [INFO] train episode 49434: reward = -46.73, steps = 46 11:11:17 [INFO] train episode 49435: reward = -40.09, steps = 25 11:11:22 [INFO] train episode 49436: reward = -15.94, steps = 52 11:11:23 [INFO] train episode 49437: reward = -64.43, steps = 19 11:11:27 [INFO] train episode 49438: reward = -7.61, steps = 50 11:11:30 [INFO] train episode 49439: reward = -44.32, steps = 29 11:11:31 [INFO] train episode 49440: reward = -50.32, steps = 18 11:11:35 [INFO] train episode 49441: reward = -29.54, steps = 34 11:11:37 [INFO] train episode 49442: reward = -60.13, steps = 31 11:11:41 [INFO] train episode 49443: reward = -55.24, steps = 41 11:11:44 [INFO] train episode 49444: reward = -54.36, steps = 34 11:11:49 [INFO] train episode 49445: reward = -32.93, steps = 57 11:11:53 [INFO] train episode 49446: reward = -61.15, steps = 43 11:11:55 [INFO] train episode 49447: reward = -46.96, steps = 27 11:11:58 [INFO] train episode 49448: reward = -36.88, steps = 34 11:12:00 [INFO] train episode 49449: reward = -45.01, steps = 23 11:12:02 [INFO] train episode 49450: reward = -88.06, steps = 23 11:12:06 [INFO] train episode 49451: reward = -38.86, steps = 35 11:12:07 [INFO] train episode 49452: reward = -48.95, steps = 20 11:12:11 [INFO] train episode 49453: reward = -30.60, steps = 40 11:12:14 [INFO] train episode 49454: reward = -60.09, steps = 40 11:12:18 [INFO] train episode 49455: reward = -22.81, steps = 45 11:12:20 [INFO] train episode 49456: reward = -38.17, steps = 24 11:12:23 [INFO] train episode 49457: reward = -32.16, steps = 39 11:12:25 [INFO] train episode 49458: reward = -56.66, steps = 22 11:12:27 [INFO] train episode 49459: reward = -43.41, steps = 23 11:12:30 [INFO] train episode 49460: reward = -40.38, steps = 37 11:12:33 [INFO] train episode 49461: reward = -51.39, steps = 36 11:12:36 [INFO] train episode 49462: reward = -72.08, steps = 26 11:12:39 [INFO] train episode 49463: reward = -57.53, steps = 32 11:12:43 [INFO] train episode 49464: reward = -49.06, steps = 45 11:12:46 [INFO] train episode 49465: reward = -36.47, steps = 39 11:12:50 [INFO] train episode 49466: reward = -19.63, steps = 49 11:12:54 [INFO] train episode 49467: reward = -55.42, steps = 43 11:12:57 [INFO] train episode 49468: reward = -44.71, steps = 35 11:13:00 [INFO] train episode 49469: reward = -61.36, steps = 30 11:13:02 [INFO] train episode 49470: reward = -74.17, steps = 24 11:13:05 [INFO] train episode 49471: reward = -30.27, steps = 31 11:13:06 [INFO] train episode 49472: reward = -58.18, steps = 21 11:13:09 [INFO] train episode 49473: reward = -39.07, steps = 25 11:13:13 [INFO] train episode 49474: reward = -22.94, steps = 48 11:13:16 [INFO] train episode 49475: reward = -51.73, steps = 40 11:13:20 [INFO] train episode 49476: reward = -53.55, steps = 44 11:13:24 [INFO] train episode 49477: reward = -39.93, steps = 46 11:13:27 [INFO] train episode 49478: reward = -53.64, steps = 23 11:13:28 [INFO] train episode 49479: reward = -58.55, steps = 21 11:13:31 [INFO] train episode 49480: reward = -40.07, steps = 30 11:13:32 [INFO] train episode 49481: reward = -38.78, steps = 19 11:13:36 [INFO] train episode 49482: reward = -51.99, steps = 40 11:13:39 [INFO] train episode 49483: reward = -57.25, steps = 32 11:13:41 [INFO] train episode 49484: reward = -40.23, steps = 28 11:13:44 [INFO] train episode 49485: reward = -39.83, steps = 35 11:13:48 [INFO] train episode 49486: reward = -42.01, steps = 43 11:13:51 [INFO] train episode 49487: reward = -50.31, steps = 40 11:13:55 [INFO] train episode 49488: reward = -33.35, steps = 37 11:13:58 [INFO] train episode 49489: reward = -40.90, steps = 34 11:14:01 [INFO] train episode 49490: reward = -47.51, steps = 37 11:14:03 [INFO] train episode 49491: reward = -64.02, steps = 18 11:14:05 [INFO] train episode 49492: reward = -42.85, steps = 25 11:14:06 [INFO] train episode 49493: reward = -36.37, steps = 20 11:14:10 [INFO] train episode 49494: reward = -79.32, steps = 44 11:14:12 [INFO] train episode 49495: reward = -52.41, steps = 25 11:14:16 [INFO] train episode 49496: reward = -67.62, steps = 38 11:14:17 [INFO] train episode 49497: reward = -52.49, steps = 19 11:14:20 [INFO] train episode 49498: reward = -45.38, steps = 34 11:14:22 [INFO] train episode 49499: reward = -64.81, steps = 26 11:14:26 [INFO] train episode 49500: reward = -101.94, steps = 45 11:14:31 [INFO] train episode 49501: reward = -29.66, steps = 47 11:14:33 [INFO] train episode 49502: reward = -27.79, steps = 33 11:14:37 [INFO] train episode 49503: reward = -19.38, steps = 39 11:14:41 [INFO] train episode 49504: reward = -41.92, steps = 43 11:14:45 [INFO] train episode 49505: reward = -48.78, steps = 34 11:14:47 [INFO] train episode 49506: reward = -46.31, steps = 32 11:14:51 [INFO] train episode 49507: reward = -31.28, steps = 42 11:14:53 [INFO] train episode 49508: reward = -66.38, steps = 24 11:14:55 [INFO] train episode 49509: reward = -45.15, steps = 28 11:14:58 [INFO] train episode 49510: reward = -65.86, steps = 35 11:15:03 [INFO] train episode 49511: reward = -37.62, steps = 49 11:15:05 [INFO] train episode 49512: reward = -53.99, steps = 29 11:15:07 [INFO] train episode 49513: reward = -51.67, steps = 19 11:15:11 [INFO] train episode 49514: reward = -47.33, steps = 48 11:15:15 [INFO] train episode 49515: reward = -60.43, steps = 50 11:15:18 [INFO] train episode 49516: reward = -42.78, steps = 26 11:15:20 [INFO] train episode 49517: reward = -37.29, steps = 31 11:15:23 [INFO] train episode 49518: reward = -55.96, steps = 29 11:15:26 [INFO] train episode 49519: reward = -50.41, steps = 38 11:15:28 [INFO] train episode 49520: reward = -62.09, steps = 28 11:15:32 [INFO] train episode 49521: reward = -10.96, steps = 39 11:15:34 [INFO] train episode 49522: reward = -66.25, steps = 23 11:15:37 [INFO] train episode 49523: reward = -48.68, steps = 31 11:15:40 [INFO] train episode 49524: reward = -65.18, steps = 45 11:15:44 [INFO] train episode 49525: reward = -49.29, steps = 39 11:15:46 [INFO] train episode 49526: reward = -49.72, steps = 29 11:15:49 [INFO] train episode 49527: reward = -25.74, steps = 34 11:15:52 [INFO] train episode 49528: reward = -104.19, steps = 36 11:15:54 [INFO] train episode 49529: reward = -42.91, steps = 21 11:15:56 [INFO] train episode 49530: reward = -48.94, steps = 27 11:15:59 [INFO] train episode 49531: reward = -41.73, steps = 25 11:16:03 [INFO] train episode 49532: reward = -16.05, steps = 48 11:16:06 [INFO] train episode 49533: reward = -67.56, steps = 38 11:16:09 [INFO] train episode 49534: reward = -54.77, steps = 35 11:16:13 [INFO] train episode 49535: reward = -51.53, steps = 40 11:16:16 [INFO] train episode 49536: reward = -53.86, steps = 38 11:16:18 [INFO] train episode 49537: reward = -69.66, steps = 20 11:16:21 [INFO] train episode 49538: reward = -49.20, steps = 37 11:16:25 [INFO] train episode 49539: reward = -21.84, steps = 51 11:16:28 [INFO] train episode 49540: reward = -46.48, steps = 31 11:16:31 [INFO] train episode 49541: reward = -51.62, steps = 40 11:16:33 [INFO] train episode 49542: reward = -46.23, steps = 21 11:16:35 [INFO] train episode 49543: reward = -63.18, steps = 22 11:16:37 [INFO] train episode 49544: reward = -58.74, steps = 19 11:16:40 [INFO] train episode 49545: reward = -53.85, steps = 28 11:16:43 [INFO] train episode 49546: reward = -53.84, steps = 44 11:16:45 [INFO] train episode 49547: reward = -35.83, steps = 23 11:16:47 [INFO] train episode 49548: reward = -64.82, steps = 25 11:16:51 [INFO] train episode 49549: reward = -49.84, steps = 32 11:16:54 [INFO] train episode 49550: reward = -32.27, steps = 42 11:16:57 [INFO] train episode 49551: reward = -53.74, steps = 33 11:16:59 [INFO] train episode 49552: reward = -28.83, steps = 27 11:17:03 [INFO] train episode 49553: reward = -64.91, steps = 46 11:17:05 [INFO] train episode 49554: reward = -39.87, steps = 26 11:17:09 [INFO] train episode 49555: reward = -34.86, steps = 44 11:17:12 [INFO] train episode 49556: reward = -26.38, steps = 24 11:17:13 [INFO] train episode 49557: reward = -51.98, steps = 21 11:17:17 [INFO] train episode 49558: reward = -56.14, steps = 45 11:17:21 [INFO] train episode 49559: reward = -33.78, steps = 45 11:17:24 [INFO] train episode 49560: reward = -39.09, steps = 34 11:17:26 [INFO] train episode 49561: reward = -64.35, steps = 23 11:17:29 [INFO] train episode 49562: reward = -52.37, steps = 40 11:17:32 [INFO] train episode 49563: reward = -49.77, steps = 26 11:17:34 [INFO] train episode 49564: reward = -43.99, steps = 24 11:17:37 [INFO] train episode 49565: reward = -42.74, steps = 35 11:17:41 [INFO] train episode 49566: reward = -49.79, steps = 42 11:17:43 [INFO] train episode 49567: reward = -38.88, steps = 21 11:17:46 [INFO] train episode 49568: reward = -64.53, steps = 37 11:17:48 [INFO] train episode 49569: reward = -67.15, steps = 17 11:17:50 [INFO] train episode 49570: reward = -43.66, steps = 24 11:17:53 [INFO] train episode 49571: reward = -58.33, steps = 40 11:17:56 [INFO] train episode 49572: reward = -89.25, steps = 28 11:17:59 [INFO] train episode 49573: reward = -51.05, steps = 38 11:18:01 [INFO] train episode 49574: reward = -59.63, steps = 24 11:18:04 [INFO] train episode 49575: reward = -39.52, steps = 30 11:18:08 [INFO] train episode 49576: reward = -53.79, steps = 46 11:18:10 [INFO] train episode 49577: reward = -47.73, steps = 30 11:18:13 [INFO] train episode 49578: reward = -17.06, steps = 30 11:18:15 [INFO] train episode 49579: reward = -27.01, steps = 27 11:18:18 [INFO] train episode 49580: reward = -50.35, steps = 30 11:18:22 [INFO] train episode 49581: reward = -62.64, steps = 42 11:18:25 [INFO] train episode 49582: reward = -26.70, steps = 37 11:18:27 [INFO] train episode 49583: reward = -37.82, steps = 28 11:18:30 [INFO] train episode 49584: reward = -49.36, steps = 26 11:18:31 [INFO] train episode 49585: reward = -42.10, steps = 19 11:18:34 [INFO] train episode 49586: reward = -33.97, steps = 30 11:18:36 [INFO] train episode 49587: reward = -31.96, steps = 30 11:18:38 [INFO] train episode 49588: reward = -50.49, steps = 20 11:18:40 [INFO] train episode 49589: reward = -35.64, steps = 24 11:18:43 [INFO] train episode 49590: reward = -43.48, steps = 31 11:18:47 [INFO] train episode 49591: reward = -59.45, steps = 46 11:18:50 [INFO] train episode 49592: reward = -45.23, steps = 31 11:18:52 [INFO] train episode 49593: reward = -63.37, steps = 29 11:18:54 [INFO] train episode 49594: reward = -25.94, steps = 22 11:18:57 [INFO] train episode 49595: reward = -54.34, steps = 35 11:18:59 [INFO] train episode 49596: reward = -58.04, steps = 21 11:19:03 [INFO] train episode 49597: reward = -117.63, steps = 44 11:19:06 [INFO] train episode 49598: reward = -53.14, steps = 29 11:19:08 [INFO] train episode 49599: reward = -33.31, steps = 27 11:19:10 [INFO] train episode 49600: reward = -38.16, steps = 24 11:19:12 [INFO] train episode 49601: reward = -29.14, steps = 21 11:19:15 [INFO] train episode 49602: reward = -35.86, steps = 39 11:19:18 [INFO] train episode 49603: reward = -44.88, steps = 27 11:19:19 [INFO] train episode 49604: reward = -51.37, steps = 21 11:19:21 [INFO] train episode 49605: reward = -58.02, steps = 23 11:19:23 [INFO] train episode 49606: reward = -43.86, steps = 21 11:19:26 [INFO] train episode 49607: reward = -58.28, steps = 30 11:19:28 [INFO] train episode 49608: reward = -64.13, steps = 26 11:19:29 [INFO] train episode 49609: reward = -40.14, steps = 18 11:19:32 [INFO] train episode 49610: reward = -42.17, steps = 25 11:19:35 [INFO] train episode 49611: reward = -47.37, steps = 38 11:19:37 [INFO] train episode 49612: reward = -34.76, steps = 26 11:19:39 [INFO] train episode 49613: reward = -57.69, steps = 17 11:19:41 [INFO] train episode 49614: reward = -43.62, steps = 24 11:19:43 [INFO] train episode 49615: reward = -64.30, steps = 25 11:19:45 [INFO] train episode 49616: reward = -41.50, steps = 27 11:19:49 [INFO] train episode 49617: reward = -16.78, steps = 35 11:19:52 [INFO] train episode 49618: reward = -38.31, steps = 36 11:19:54 [INFO] train episode 49619: reward = -31.31, steps = 24 11:19:58 [INFO] train episode 49620: reward = -84.87, steps = 45 11:19:59 [INFO] train episode 49621: reward = -66.52, steps = 20 11:20:02 [INFO] train episode 49622: reward = -96.39, steps = 33 11:20:05 [INFO] train episode 49623: reward = -17.86, steps = 36 11:20:07 [INFO] train episode 49624: reward = -77.14, steps = 19 11:20:09 [INFO] train episode 49625: reward = -49.81, steps = 24 11:20:12 [INFO] train episode 49626: reward = -52.87, steps = 28 11:20:15 [INFO] train episode 49627: reward = -66.18, steps = 35 11:20:19 [INFO] train episode 49628: reward = -31.18, steps = 51 11:20:23 [INFO] train episode 49629: reward = -36.25, steps = 34 11:20:27 [INFO] train episode 49630: reward = -21.12, steps = 48 11:20:31 [INFO] train episode 49631: reward = -44.24, steps = 29 11:20:38 [INFO] train episode 49632: reward = -22.97, steps = 37 11:20:42 [INFO] train episode 49633: reward = -67.17, steps = 21 11:20:48 [INFO] train episode 49634: reward = -50.04, steps = 37 11:20:53 [INFO] train episode 49635: reward = -44.79, steps = 31 11:20:59 [INFO] train episode 49636: reward = -35.79, steps = 40 11:21:04 [INFO] train episode 49637: reward = -87.17, steps = 31 11:21:10 [INFO] train episode 49638: reward = -40.88, steps = 34 11:21:15 [INFO] train episode 49639: reward = -36.59, steps = 28 11:21:19 [INFO] train episode 49640: reward = -44.61, steps = 22 11:21:24 [INFO] train episode 49641: reward = -46.38, steps = 31 11:21:30 [INFO] train episode 49642: reward = -73.68, steps = 44 11:21:39 [INFO] train episode 49643: reward = -53.81, steps = 58 11:21:42 [INFO] train episode 49644: reward = -70.82, steps = 35 11:21:45 [INFO] train episode 49645: reward = -49.10, steps = 43 11:21:49 [INFO] train episode 49646: reward = -55.27, steps = 37 11:21:51 [INFO] train episode 49647: reward = -56.61, steps = 19 11:21:57 [INFO] train episode 49648: reward = -110.68, steps = 41 11:22:00 [INFO] train episode 49649: reward = -32.86, steps = 25 11:22:03 [INFO] train episode 49650: reward = -66.56, steps = 29 11:22:05 [INFO] train episode 49651: reward = -55.69, steps = 20 11:22:07 [INFO] train episode 49652: reward = -30.65, steps = 30 11:22:11 [INFO] train episode 49653: reward = -43.57, steps = 38 11:22:14 [INFO] train episode 49654: reward = -37.93, steps = 29 11:22:18 [INFO] train episode 49655: reward = -60.06, steps = 36 11:22:21 [INFO] train episode 49656: reward = -33.85, steps = 32 11:22:23 [INFO] train episode 49657: reward = -39.93, steps = 23 11:22:27 [INFO] train episode 49658: reward = -36.45, steps = 35 11:22:29 [INFO] train episode 49659: reward = -46.26, steps = 20 11:22:32 [INFO] train episode 49660: reward = -46.33, steps = 32 11:22:36 [INFO] train episode 49661: reward = -19.26, steps = 31 11:22:38 [INFO] train episode 49662: reward = -53.98, steps = 29 11:22:44 [INFO] train episode 49663: reward = -56.07, steps = 63 11:22:47 [INFO] train episode 49664: reward = -14.42, steps = 31 11:22:49 [INFO] train episode 49665: reward = -34.85, steps = 29 11:22:54 [INFO] train episode 49666: reward = -30.52, steps = 40 11:22:57 [INFO] train episode 49667: reward = -45.23, steps = 25 11:22:59 [INFO] train episode 49668: reward = -48.23, steps = 23 11:23:02 [INFO] train episode 49669: reward = -73.28, steps = 22 11:23:05 [INFO] train episode 49670: reward = -55.93, steps = 38 11:23:09 [INFO] train episode 49671: reward = -52.40, steps = 40 11:23:12 [INFO] train episode 49672: reward = -43.94, steps = 32 11:23:15 [INFO] train episode 49673: reward = -39.68, steps = 35 11:23:18 [INFO] train episode 49674: reward = -44.12, steps = 25 11:23:22 [INFO] train episode 49675: reward = -103.82, steps = 51 11:23:27 [INFO] train episode 49676: reward = -55.26, steps = 50 11:23:30 [INFO] train episode 49677: reward = -33.27, steps = 38 11:23:33 [INFO] train episode 49678: reward = -39.72, steps = 29 11:23:36 [INFO] train episode 49679: reward = -48.82, steps = 40 11:23:39 [INFO] train episode 49680: reward = -69.40, steps = 32 11:23:42 [INFO] train episode 49681: reward = -50.40, steps = 34 11:23:46 [INFO] train episode 49682: reward = -35.42, steps = 40 11:23:49 [INFO] train episode 49683: reward = -45.32, steps = 38 11:23:53 [INFO] train episode 49684: reward = -26.15, steps = 48 11:23:55 [INFO] train episode 49685: reward = -27.86, steps = 22 11:23:57 [INFO] train episode 49686: reward = -47.32, steps = 23 11:24:00 [INFO] train episode 49687: reward = -52.42, steps = 19 11:24:02 [INFO] train episode 49688: reward = -35.99, steps = 22 11:24:05 [INFO] train episode 49689: reward = -41.04, steps = 37 11:24:09 [INFO] train episode 49690: reward = -51.41, steps = 37 11:24:12 [INFO] train episode 49691: reward = -48.36, steps = 38 11:24:15 [INFO] train episode 49692: reward = -53.10, steps = 38 11:24:18 [INFO] train episode 49693: reward = -53.21, steps = 32 11:24:20 [INFO] train episode 49694: reward = -46.19, steps = 20 11:24:23 [INFO] train episode 49695: reward = -31.63, steps = 37 11:24:27 [INFO] train episode 49696: reward = -39.52, steps = 41 11:24:29 [INFO] train episode 49697: reward = -55.28, steps = 27 11:24:33 [INFO] train episode 49698: reward = -73.02, steps = 40 11:24:37 [INFO] train episode 49699: reward = -77.12, steps = 51 11:24:41 [INFO] train episode 49700: reward = -29.84, steps = 42 11:24:44 [INFO] train episode 49701: reward = -55.82, steps = 33 11:24:47 [INFO] train episode 49702: reward = -36.72, steps = 33 11:24:51 [INFO] train episode 49703: reward = -25.33, steps = 41 11:24:53 [INFO] train episode 49704: reward = -43.05, steps = 18 11:24:56 [INFO] train episode 49705: reward = -10.76, steps = 40 11:24:59 [INFO] train episode 49706: reward = -31.54, steps = 30 11:25:02 [INFO] train episode 49707: reward = -85.15, steps = 41 11:25:05 [INFO] train episode 49708: reward = -43.28, steps = 27 11:25:08 [INFO] train episode 49709: reward = -62.40, steps = 36 11:25:11 [INFO] train episode 49710: reward = -38.53, steps = 36 11:25:15 [INFO] train episode 49711: reward = -56.69, steps = 40 11:25:18 [INFO] train episode 49712: reward = -14.76, steps = 34 11:25:20 [INFO] train episode 49713: reward = -42.13, steps = 20 11:25:23 [INFO] train episode 49714: reward = -51.92, steps = 36 11:25:27 [INFO] train episode 49715: reward = -70.65, steps = 49 11:25:29 [INFO] train episode 49716: reward = -56.49, steps = 19 11:25:31 [INFO] train episode 49717: reward = -40.11, steps = 28 11:25:36 [INFO] train episode 49718: reward = -53.30, steps = 51 11:25:39 [INFO] train episode 49719: reward = -61.22, steps = 28 11:25:42 [INFO] train episode 49720: reward = -41.82, steps = 41 11:25:45 [INFO] train episode 49721: reward = -105.84, steps = 39 11:25:49 [INFO] train episode 49722: reward = -38.20, steps = 38 11:25:52 [INFO] train episode 49723: reward = -45.09, steps = 33 11:25:55 [INFO] train episode 49724: reward = -37.55, steps = 37 11:25:59 [INFO] train episode 49725: reward = -36.04, steps = 43 11:26:02 [INFO] train episode 49726: reward = -77.01, steps = 41 11:26:06 [INFO] train episode 49727: reward = -54.28, steps = 40 11:26:08 [INFO] train episode 49728: reward = -37.12, steps = 28 11:26:11 [INFO] train episode 49729: reward = -66.35, steps = 20 11:26:14 [INFO] train episode 49730: reward = -52.81, steps = 34 11:26:16 [INFO] train episode 49731: reward = -52.08, steps = 22 11:26:18 [INFO] train episode 49732: reward = -26.38, steps = 30 11:26:20 [INFO] train episode 49733: reward = -36.50, steps = 25 11:26:22 [INFO] train episode 49734: reward = -54.50, steps = 19 11:26:25 [INFO] train episode 49735: reward = -98.79, steps = 33 11:26:29 [INFO] train episode 49736: reward = -27.77, steps = 35 11:26:32 [INFO] train episode 49737: reward = -22.74, steps = 45 11:26:35 [INFO] train episode 49738: reward = -108.78, steps = 32 11:26:38 [INFO] train episode 49739: reward = -20.76, steps = 28 11:26:41 [INFO] train episode 49740: reward = -71.03, steps = 36 11:26:45 [INFO] train episode 49741: reward = -50.84, steps = 39 11:26:49 [INFO] train episode 49742: reward = -43.85, steps = 54 11:26:52 [INFO] train episode 49743: reward = -47.43, steps = 31 11:26:56 [INFO] train episode 49744: reward = -50.76, steps = 39 11:27:01 [INFO] train episode 49745: reward = -54.34, steps = 52 11:27:03 [INFO] train episode 49746: reward = -49.65, steps = 23 11:27:06 [INFO] train episode 49747: reward = -50.84, steps = 28 11:27:08 [INFO] train episode 49748: reward = -42.98, steps = 24 11:27:12 [INFO] train episode 49749: reward = -41.45, steps = 56 11:27:16 [INFO] train episode 49750: reward = -49.02, steps = 35 11:27:19 [INFO] train episode 49751: reward = -39.82, steps = 30 11:27:21 [INFO] train episode 49752: reward = -53.59, steps = 34 11:27:25 [INFO] train episode 49753: reward = -34.36, steps = 42 11:27:28 [INFO] train episode 49754: reward = -34.59, steps = 35 11:27:31 [INFO] train episode 49755: reward = -43.69, steps = 30 11:27:36 [INFO] train episode 49756: reward = -42.33, steps = 53 11:27:38 [INFO] train episode 49757: reward = -56.55, steps = 27 11:27:45 [INFO] train episode 49758: reward = -119.30, steps = 83 11:27:47 [INFO] train episode 49759: reward = -68.59, steps = 20 11:27:52 [INFO] train episode 49760: reward = -24.32, steps = 50 11:27:54 [INFO] train episode 49761: reward = -37.50, steps = 27 11:27:56 [INFO] train episode 49762: reward = -77.56, steps = 21 11:27:59 [INFO] train episode 49763: reward = -70.56, steps = 28 11:28:01 [INFO] train episode 49764: reward = -73.37, steps = 24 11:28:05 [INFO] train episode 49765: reward = -53.57, steps = 38 11:28:07 [INFO] train episode 49766: reward = -40.29, steps = 21 11:28:10 [INFO] train episode 49767: reward = -30.45, steps = 34 11:28:15 [INFO] train episode 49768: reward = -68.98, steps = 64 11:28:18 [INFO] train episode 49769: reward = -39.45, steps = 32 11:28:21 [INFO] train episode 49770: reward = -33.02, steps = 28 11:28:25 [INFO] train episode 49771: reward = -75.94, steps = 44 11:28:27 [INFO] train episode 49772: reward = -65.92, steps = 30 11:28:32 [INFO] train episode 49773: reward = -48.16, steps = 48 11:28:35 [INFO] train episode 49774: reward = -47.87, steps = 36 11:28:38 [INFO] train episode 49775: reward = -72.77, steps = 32 11:28:42 [INFO] train episode 49776: reward = -51.23, steps = 44 11:28:45 [INFO] train episode 49777: reward = -59.66, steps = 37 11:28:49 [INFO] train episode 49778: reward = -40.22, steps = 37 11:28:51 [INFO] train episode 49779: reward = -53.46, steps = 30 11:28:53 [INFO] train episode 49780: reward = -43.17, steps = 20 11:28:56 [INFO] train episode 49781: reward = -33.73, steps = 32 11:28:59 [INFO] train episode 49782: reward = -27.45, steps = 38 11:29:03 [INFO] train episode 49783: reward = -42.25, steps = 38 11:29:06 [INFO] train episode 49784: reward = -43.61, steps = 25 11:29:09 [INFO] train episode 49785: reward = -26.83, steps = 39 11:29:13 [INFO] train episode 49786: reward = -47.38, steps = 41 11:29:15 [INFO] train episode 49787: reward = -58.92, steps = 23 11:29:18 [INFO] train episode 49788: reward = -26.71, steps = 37 11:29:21 [INFO] train episode 49789: reward = -47.46, steps = 37 11:29:26 [INFO] train episode 49790: reward = -24.02, steps = 56 11:29:30 [INFO] train episode 49791: reward = -64.50, steps = 37 11:29:33 [INFO] train episode 49792: reward = -15.93, steps = 36 11:29:36 [INFO] train episode 49793: reward = -36.66, steps = 37 11:29:40 [INFO] train episode 49794: reward = -57.71, steps = 44 11:29:43 [INFO] train episode 49795: reward = -38.74, steps = 33 11:29:47 [INFO] train episode 49796: reward = -38.35, steps = 45 11:29:51 [INFO] train episode 49797: reward = -64.66, steps = 40 11:29:54 [INFO] train episode 49798: reward = -41.75, steps = 29 11:29:56 [INFO] train episode 49799: reward = -75.14, steps = 25 11:29:59 [INFO] train episode 49800: reward = -33.39, steps = 36 11:30:02 [INFO] train episode 49801: reward = -66.36, steps = 25 11:30:04 [INFO] train episode 49802: reward = -60.33, steps = 20 11:30:07 [INFO] train episode 49803: reward = -67.91, steps = 40 11:30:10 [INFO] train episode 49804: reward = -40.75, steps = 35 11:30:12 [INFO] train episode 49805: reward = -25.53, steps = 23 11:30:17 [INFO] train episode 49806: reward = -56.83, steps = 49 11:30:20 [INFO] train episode 49807: reward = -52.47, steps = 38 11:30:24 [INFO] train episode 49808: reward = -45.67, steps = 46 11:30:27 [INFO] train episode 49809: reward = -72.18, steps = 28 11:30:29 [INFO] train episode 49810: reward = -36.52, steps = 25 11:30:32 [INFO] train episode 49811: reward = -48.42, steps = 27 11:30:35 [INFO] train episode 49812: reward = -52.60, steps = 33 11:30:37 [INFO] train episode 49813: reward = -35.78, steps = 24 11:30:41 [INFO] train episode 49814: reward = -44.89, steps = 46 11:30:44 [INFO] train episode 49815: reward = -34.60, steps = 34 11:30:46 [INFO] train episode 49816: reward = -56.54, steps = 20 11:30:49 [INFO] train episode 49817: reward = -71.56, steps = 29 11:30:51 [INFO] train episode 49818: reward = -47.28, steps = 21 11:30:54 [INFO] train episode 49819: reward = -44.84, steps = 34 11:30:56 [INFO] train episode 49820: reward = -39.98, steps = 27 11:30:58 [INFO] train episode 49821: reward = -55.23, steps = 23 11:31:00 [INFO] train episode 49822: reward = -35.77, steps = 20 11:31:04 [INFO] train episode 49823: reward = -54.59, steps = 39 11:31:06 [INFO] train episode 49824: reward = -35.39, steps = 23 11:31:08 [INFO] train episode 49825: reward = -47.38, steps = 27 11:31:10 [INFO] train episode 49826: reward = -63.73, steps = 21 11:31:13 [INFO] train episode 49827: reward = -47.49, steps = 29 11:31:15 [INFO] train episode 49828: reward = -53.73, steps = 21 11:31:17 [INFO] train episode 49829: reward = -35.86, steps = 29 11:31:19 [INFO] train episode 49830: reward = -50.05, steps = 22 11:31:22 [INFO] train episode 49831: reward = -47.37, steps = 24 11:31:26 [INFO] train episode 49832: reward = -40.59, steps = 40 11:31:29 [INFO] train episode 49833: reward = -56.71, steps = 33 11:31:32 [INFO] train episode 49834: reward = -63.21, steps = 28 11:31:34 [INFO] train episode 49835: reward = -54.99, steps = 23 11:31:37 [INFO] train episode 49836: reward = -31.09, steps = 37 11:31:39 [INFO] train episode 49837: reward = -44.07, steps = 27 11:31:42 [INFO] train episode 49838: reward = -38.02, steps = 21 11:31:45 [INFO] train episode 49839: reward = -28.89, steps = 38 11:31:48 [INFO] train episode 49840: reward = -54.29, steps = 35 11:31:51 [INFO] train episode 49841: reward = -45.99, steps = 38 11:31:56 [INFO] train episode 49842: reward = -45.40, steps = 52 11:31:58 [INFO] train episode 49843: reward = -45.36, steps = 21 11:32:02 [INFO] train episode 49844: reward = -106.39, steps = 43 11:32:04 [INFO] train episode 49845: reward = -31.49, steps = 28 11:32:06 [INFO] train episode 49846: reward = -42.45, steps = 20 11:32:09 [INFO] train episode 49847: reward = -47.03, steps = 37 11:32:14 [INFO] train episode 49848: reward = -59.25, steps = 48 11:32:17 [INFO] train episode 49849: reward = -56.61, steps = 32 11:32:21 [INFO] train episode 49850: reward = -70.62, steps = 44 11:32:26 [INFO] train episode 49851: reward = -88.06, steps = 62 11:32:30 [INFO] train episode 49852: reward = -35.04, steps = 43 11:32:34 [INFO] train episode 49853: reward = -21.78, steps = 43 11:32:37 [INFO] train episode 49854: reward = -34.46, steps = 33 11:32:40 [INFO] train episode 49855: reward = -27.15, steps = 31 11:32:44 [INFO] train episode 49856: reward = -39.36, steps = 44 11:32:47 [INFO] train episode 49857: reward = -53.03, steps = 36 11:32:50 [INFO] train episode 49858: reward = -40.87, steps = 29 11:32:53 [INFO] train episode 49859: reward = -48.87, steps = 27 11:32:55 [INFO] train episode 49860: reward = -62.94, steps = 19 11:32:59 [INFO] train episode 49861: reward = -28.61, steps = 44 11:33:01 [INFO] train episode 49862: reward = -45.90, steps = 22 11:33:04 [INFO] train episode 49863: reward = -47.06, steps = 38 11:33:08 [INFO] train episode 49864: reward = -73.80, steps = 40 11:33:11 [INFO] train episode 49865: reward = -71.55, steps = 39 11:33:14 [INFO] train episode 49866: reward = -49.80, steps = 34 11:33:18 [INFO] train episode 49867: reward = -4.16, steps = 42 11:33:23 [INFO] train episode 49868: reward = -71.10, steps = 48 11:33:25 [INFO] train episode 49869: reward = -50.58, steps = 24 11:33:27 [INFO] train episode 49870: reward = -38.49, steps = 29 11:33:30 [INFO] train episode 49871: reward = -53.00, steps = 30 11:33:34 [INFO] train episode 49872: reward = -63.74, steps = 40 11:33:37 [INFO] train episode 49873: reward = -37.61, steps = 36 11:33:40 [INFO] train episode 49874: reward = -21.02, steps = 31 11:33:44 [INFO] train episode 49875: reward = -27.06, steps = 45 11:33:47 [INFO] train episode 49876: reward = -47.14, steps = 32 11:33:50 [INFO] train episode 49877: reward = -57.56, steps = 42 11:33:53 [INFO] train episode 49878: reward = -50.60, steps = 32 11:33:57 [INFO] train episode 49879: reward = -56.31, steps = 37 11:33:59 [INFO] train episode 49880: reward = -53.94, steps = 22 11:34:01 [INFO] train episode 49881: reward = -39.45, steps = 30 11:34:04 [INFO] train episode 49882: reward = -39.84, steps = 27 11:34:07 [INFO] train episode 49883: reward = -32.14, steps = 33 11:34:09 [INFO] train episode 49884: reward = -87.53, steps = 32 11:34:11 [INFO] train episode 49885: reward = -55.80, steps = 20 11:34:14 [INFO] train episode 49886: reward = -30.79, steps = 28 11:34:17 [INFO] train episode 49887: reward = -56.71, steps = 37 11:34:20 [INFO] train episode 49888: reward = -45.64, steps = 33 11:34:22 [INFO] train episode 49889: reward = -50.21, steps = 19 11:34:24 [INFO] train episode 49890: reward = -37.60, steps = 23 11:34:27 [INFO] train episode 49891: reward = -93.05, steps = 35 11:34:30 [INFO] train episode 49892: reward = -43.54, steps = 26 11:34:32 [INFO] train episode 49893: reward = -32.75, steps = 24 11:34:35 [INFO] train episode 49894: reward = -54.21, steps = 42 11:34:39 [INFO] train episode 49895: reward = -40.72, steps = 41 11:34:41 [INFO] train episode 49896: reward = -57.20, steps = 21 11:34:44 [INFO] train episode 49897: reward = -43.93, steps = 31 11:34:47 [INFO] train episode 49898: reward = -32.38, steps = 34 11:34:51 [INFO] train episode 49899: reward = -73.31, steps = 41 11:34:55 [INFO] train episode 49900: reward = -80.35, steps = 49 11:34:59 [INFO] train episode 49901: reward = -43.98, steps = 51 11:35:02 [INFO] train episode 49902: reward = -73.35, steps = 29 11:35:05 [INFO] train episode 49903: reward = -50.98, steps = 34 11:35:07 [INFO] train episode 49904: reward = -58.65, steps = 19 11:35:09 [INFO] train episode 49905: reward = -62.03, steps = 23 11:35:12 [INFO] train episode 49906: reward = -63.17, steps = 39 11:35:15 [INFO] train episode 49907: reward = -55.68, steps = 31 11:35:18 [INFO] train episode 49908: reward = -61.22, steps = 28 11:35:20 [INFO] train episode 49909: reward = -44.33, steps = 23 11:35:22 [INFO] train episode 49910: reward = -56.02, steps = 31 11:35:25 [INFO] train episode 49911: reward = -40.56, steps = 30 11:35:28 [INFO] train episode 49912: reward = -52.13, steps = 35 11:35:32 [INFO] train episode 49913: reward = -56.65, steps = 46 11:35:37 [INFO] train episode 49914: reward = -52.73, steps = 52 11:35:41 [INFO] train episode 49915: reward = -62.34, steps = 48 11:35:45 [INFO] train episode 49916: reward = -48.67, steps = 41 11:35:49 [INFO] train episode 49917: reward = -59.88, steps = 35 11:35:51 [INFO] train episode 49918: reward = -61.98, steps = 24 11:35:54 [INFO] train episode 49919: reward = -47.02, steps = 36 11:35:58 [INFO] train episode 49920: reward = -24.70, steps = 44 11:36:02 [INFO] train episode 49921: reward = -41.32, steps = 40 11:36:04 [INFO] train episode 49922: reward = -47.24, steps = 25 11:36:08 [INFO] train episode 49923: reward = -27.22, steps = 36 11:36:10 [INFO] train episode 49924: reward = -51.99, steps = 28 11:36:12 [INFO] train episode 49925: reward = -84.68, steps = 22 11:36:15 [INFO] train episode 49926: reward = -65.86, steps = 33 11:36:18 [INFO] train episode 49927: reward = -74.31, steps = 37 11:36:21 [INFO] train episode 49928: reward = -49.81, steps = 32 11:36:23 [INFO] train episode 49929: reward = -60.19, steps = 20 11:36:25 [INFO] train episode 49930: reward = -43.44, steps = 20 11:36:29 [INFO] train episode 49931: reward = -62.19, steps = 42 11:36:31 [INFO] train episode 49932: reward = -42.75, steps = 25 11:36:33 [INFO] train episode 49933: reward = -33.59, steps = 25 11:36:36 [INFO] train episode 49934: reward = -43.57, steps = 35 11:36:40 [INFO] train episode 49935: reward = -39.52, steps = 39 11:36:42 [INFO] train episode 49936: reward = -26.98, steps = 27 11:36:46 [INFO] train episode 49937: reward = -26.41, steps = 39 11:36:48 [INFO] train episode 49938: reward = -49.40, steps = 21 11:36:51 [INFO] train episode 49939: reward = -31.90, steps = 33 11:36:53 [INFO] train episode 49940: reward = -40.03, steps = 26 11:36:56 [INFO] train episode 49941: reward = -48.68, steps = 31 11:37:00 [INFO] train episode 49942: reward = -37.16, steps = 41 11:37:01 [INFO] train episode 49943: reward = -45.69, steps = 18 11:37:05 [INFO] train episode 49944: reward = -49.57, steps = 38 11:37:07 [INFO] train episode 49945: reward = -44.53, steps = 30 11:37:10 [INFO] train episode 49946: reward = -41.56, steps = 30 11:37:15 [INFO] train episode 49947: reward = -93.00, steps = 57 11:37:17 [INFO] train episode 49948: reward = -52.46, steps = 23 11:37:19 [INFO] train episode 49949: reward = -65.48, steps = 22 11:37:21 [INFO] train episode 49950: reward = -52.90, steps = 18 11:37:23 [INFO] train episode 49951: reward = -27.23, steps = 25 11:37:25 [INFO] train episode 49952: reward = -44.25, steps = 23 11:37:28 [INFO] train episode 49953: reward = -50.25, steps = 25 11:37:30 [INFO] train episode 49954: reward = -57.01, steps = 21 11:37:33 [INFO] train episode 49955: reward = -60.99, steps = 38 11:37:37 [INFO] train episode 49956: reward = -39.46, steps = 48 11:37:41 [INFO] train episode 49957: reward = -26.36, steps = 44 11:37:43 [INFO] train episode 49958: reward = -58.74, steps = 19 11:37:45 [INFO] train episode 49959: reward = -49.80, steps = 20 11:37:48 [INFO] train episode 49960: reward = -57.04, steps = 37 11:37:52 [INFO] train episode 49961: reward = -30.87, steps = 50 11:37:55 [INFO] train episode 49962: reward = -49.31, steps = 33 11:37:58 [INFO] train episode 49963: reward = -42.49, steps = 24 11:38:05 [INFO] train episode 49964: reward = -65.61, steps = 60 11:38:09 [INFO] train episode 49965: reward = -13.47, steps = 38 11:38:12 [INFO] train episode 49966: reward = -63.10, steps = 36 11:38:15 [INFO] train episode 49967: reward = -49.61, steps = 31 11:38:18 [INFO] train episode 49968: reward = -7.93, steps = 37 11:38:22 [INFO] train episode 49969: reward = -44.39, steps = 42 11:38:24 [INFO] train episode 49970: reward = -52.96, steps = 21 11:38:28 [INFO] train episode 49971: reward = -73.56, steps = 38 11:38:31 [INFO] train episode 49972: reward = -9.50, steps = 34 11:38:33 [INFO] train episode 49973: reward = -54.22, steps = 30 11:38:36 [INFO] train episode 49974: reward = -60.25, steps = 24 11:38:40 [INFO] train episode 49975: reward = -41.65, steps = 45 11:38:42 [INFO] train episode 49976: reward = -113.16, steps = 21 11:38:44 [INFO] train episode 49977: reward = -36.87, steps = 28 11:38:47 [INFO] train episode 49978: reward = -38.75, steps = 24 11:38:52 [INFO] train episode 49979: reward = -72.59, steps = 58 11:38:56 [INFO] train episode 49980: reward = -27.87, steps = 38 11:39:00 [INFO] train episode 49981: reward = -23.08, steps = 45 11:39:02 [INFO] train episode 49982: reward = -43.85, steps = 20 11:39:06 [INFO] train episode 49983: reward = -65.39, steps = 47 11:39:08 [INFO] train episode 49984: reward = -38.18, steps = 25 11:39:13 [INFO] train episode 49985: reward = -16.74, steps = 48 11:39:16 [INFO] train episode 49986: reward = -67.93, steps = 29 11:39:18 [INFO] train episode 49987: reward = -28.30, steps = 26 11:39:19 [INFO] train episode 49988: reward = -45.31, steps = 18 11:39:23 [INFO] train episode 49989: reward = -29.84, steps = 37 11:39:26 [INFO] train episode 49990: reward = -41.21, steps = 36 11:39:28 [INFO] train episode 49991: reward = -34.25, steps = 21 11:39:31 [INFO] train episode 49992: reward = -42.75, steps = 33 11:39:33 [INFO] train episode 49993: reward = -52.41, steps = 25 11:39:37 [INFO] train episode 49994: reward = -54.59, steps = 40 11:39:39 [INFO] train episode 49995: reward = -34.67, steps = 22 11:39:42 [INFO] train episode 49996: reward = -58.91, steps = 37 11:39:45 [INFO] train episode 49997: reward = -52.84, steps = 24 11:39:48 [INFO] train episode 49998: reward = -10.85, steps = 39 11:39:50 [INFO] train episode 49999: reward = -66.21, steps = 20 11:39:53 [INFO] train episode 50000: reward = -45.86, steps = 43 11:39:57 [INFO] train episode 50001: reward = -14.21, steps = 43 11:40:00 [INFO] train episode 50002: reward = -34.81, steps = 25 11:40:04 [INFO] train episode 50003: reward = -25.63, steps = 43 11:40:06 [INFO] train episode 50004: reward = -29.83, steps = 29 11:40:10 [INFO] train episode 50005: reward = -32.12, steps = 40 11:40:13 [INFO] train episode 50006: reward = -41.04, steps = 34 11:40:15 [INFO] train episode 50007: reward = -31.03, steps = 22 11:40:18 [INFO] train episode 50008: reward = -20.57, steps = 39 11:40:21 [INFO] train episode 50009: reward = -51.77, steps = 29 11:40:23 [INFO] train episode 50010: reward = -49.90, steps = 19 11:40:25 [INFO] train episode 50011: reward = -35.68, steps = 23 11:40:27 [INFO] train episode 50012: reward = -42.63, steps = 25 11:40:31 [INFO] train episode 50013: reward = -51.77, steps = 42 11:40:33 [INFO] train episode 50014: reward = -50.87, steps = 19 11:40:35 [INFO] train episode 50015: reward = -77.28, steps = 25 11:40:38 [INFO] train episode 50016: reward = -25.55, steps = 37 11:40:40 [INFO] train episode 50017: reward = -47.87, steps = 21 11:40:45 [INFO] train episode 50018: reward = -48.30, steps = 50 11:40:47 [INFO] train episode 50019: reward = -59.37, steps = 27 11:40:51 [INFO] train episode 50020: reward = -37.50, steps = 41 11:40:53 [INFO] train episode 50021: reward = -66.35, steps = 24 11:40:57 [INFO] train episode 50022: reward = -31.38, steps = 41 11:40:59 [INFO] train episode 50023: reward = -54.69, steps = 20 11:41:01 [INFO] train episode 50024: reward = -33.43, steps = 23 11:41:06 [INFO] train episode 50025: reward = -53.72, steps = 57 11:41:09 [INFO] train episode 50026: reward = -42.89, steps = 38 11:41:11 [INFO] train episode 50027: reward = -67.26, steps = 20 11:41:15 [INFO] train episode 50028: reward = -44.43, steps = 40 11:41:18 [INFO] train episode 50029: reward = -45.75, steps = 35 11:41:20 [INFO] train episode 50030: reward = -58.39, steps = 19 11:41:23 [INFO] train episode 50031: reward = -36.66, steps = 35 11:41:27 [INFO] train episode 50032: reward = -37.12, steps = 41 11:41:31 [INFO] train episode 50033: reward = -24.37, steps = 48 11:41:34 [INFO] train episode 50034: reward = -37.62, steps = 35 11:41:38 [INFO] train episode 50035: reward = -42.82, steps = 45 11:41:41 [INFO] train episode 50036: reward = -51.65, steps = 39 11:41:44 [INFO] train episode 50037: reward = -59.14, steps = 24 11:41:46 [INFO] train episode 50038: reward = -79.44, steps = 28 11:41:51 [INFO] train episode 50039: reward = -42.26, steps = 43 11:41:54 [INFO] train episode 50040: reward = -19.26, steps = 38 11:41:57 [INFO] train episode 50041: reward = -32.45, steps = 33 11:42:00 [INFO] train episode 50042: reward = -31.77, steps = 29 11:42:03 [INFO] train episode 50043: reward = -36.53, steps = 41 11:42:07 [INFO] train episode 50044: reward = -42.62, steps = 41 11:42:10 [INFO] train episode 50045: reward = -56.37, steps = 24 11:42:13 [INFO] train episode 50046: reward = -38.99, steps = 37 11:42:16 [INFO] train episode 50047: reward = -60.35, steps = 37 11:42:20 [INFO] train episode 50048: reward = -26.24, steps = 41 11:42:23 [INFO] train episode 50049: reward = -26.62, steps = 30 11:42:26 [INFO] train episode 50050: reward = -9.66, steps = 37 11:42:29 [INFO] train episode 50051: reward = -74.87, steps = 27 11:42:32 [INFO] train episode 50052: reward = -24.38, steps = 41 11:42:36 [INFO] train episode 50053: reward = -45.12, steps = 38 11:42:38 [INFO] train episode 50054: reward = -41.39, steps = 27 11:42:42 [INFO] train episode 50055: reward = -58.85, steps = 40 11:42:44 [INFO] train episode 50056: reward = -41.39, steps = 29 11:42:49 [INFO] train episode 50057: reward = -15.60, steps = 47 11:42:51 [INFO] train episode 50058: reward = -50.39, steps = 18 11:42:53 [INFO] train episode 50059: reward = -48.44, steps = 24 11:42:57 [INFO] train episode 50060: reward = -51.50, steps = 45 11:43:00 [INFO] train episode 50061: reward = -27.75, steps = 33 11:43:04 [INFO] train episode 50062: reward = -15.24, steps = 31 11:43:07 [INFO] train episode 50063: reward = -55.76, steps = 34 11:43:09 [INFO] train episode 50064: reward = -76.24, steps = 20 11:43:11 [INFO] train episode 50065: reward = -49.66, steps = 22 11:43:14 [INFO] train episode 50066: reward = -25.46, steps = 36 11:43:17 [INFO] train episode 50067: reward = -0.63, steps = 37 11:43:20 [INFO] train episode 50068: reward = -54.78, steps = 28 11:43:22 [INFO] train episode 50069: reward = -39.86, steps = 26 11:43:26 [INFO] train episode 50070: reward = -28.12, steps = 42 11:43:30 [INFO] train episode 50071: reward = -56.51, steps = 42 11:43:37 [INFO] train episode 50072: reward = -110.45, steps = 81 11:43:39 [INFO] train episode 50073: reward = -51.14, steps = 18 11:43:41 [INFO] train episode 50074: reward = -56.15, steps = 23 11:43:45 [INFO] train episode 50075: reward = -36.36, steps = 43 11:43:48 [INFO] train episode 50076: reward = -30.15, steps = 43 11:43:51 [INFO] train episode 50077: reward = -68.64, steps = 25 11:43:53 [INFO] train episode 50078: reward = -53.48, steps = 22 11:43:55 [INFO] train episode 50079: reward = -43.03, steps = 23 11:43:57 [INFO] train episode 50080: reward = -41.77, steps = 22 11:44:00 [INFO] train episode 50081: reward = -46.00, steps = 35 11:44:04 [INFO] train episode 50082: reward = -52.59, steps = 41 11:44:08 [INFO] train episode 50083: reward = -55.59, steps = 48 11:44:10 [INFO] train episode 50084: reward = -45.19, steps = 22 11:44:13 [INFO] train episode 50085: reward = -59.07, steps = 33 11:44:16 [INFO] train episode 50086: reward = -50.70, steps = 31 11:44:20 [INFO] train episode 50087: reward = -57.77, steps = 48 11:44:23 [INFO] train episode 50088: reward = -37.63, steps = 36 11:44:25 [INFO] train episode 50089: reward = -56.20, steps = 21 11:44:28 [INFO] train episode 50090: reward = -44.80, steps = 33 11:44:32 [INFO] train episode 50091: reward = -32.78, steps = 45 11:44:34 [INFO] train episode 50092: reward = -62.08, steps = 24 11:44:37 [INFO] train episode 50093: reward = -49.84, steps = 30 11:44:39 [INFO] train episode 50094: reward = -19.54, steps = 29 11:44:42 [INFO] train episode 50095: reward = -39.62, steps = 30 11:44:44 [INFO] train episode 50096: reward = -41.52, steps = 20 11:44:49 [INFO] train episode 50097: reward = -33.99, steps = 41 11:44:52 [INFO] train episode 50098: reward = -31.66, steps = 39 11:44:55 [INFO] train episode 50099: reward = -38.52, steps = 38 11:45:00 [INFO] train episode 50100: reward = -35.17, steps = 42 11:45:02 [INFO] train episode 50101: reward = -14.63, steps = 32 11:45:06 [INFO] train episode 50102: reward = -34.42, steps = 46 11:45:10 [INFO] train episode 50103: reward = -24.71, steps = 38 11:45:12 [INFO] train episode 50104: reward = -58.77, steps = 23 11:45:15 [INFO] train episode 50105: reward = -29.36, steps = 38 11:45:18 [INFO] train episode 50106: reward = -80.65, steps = 32 11:45:21 [INFO] train episode 50107: reward = -27.89, steps = 31 11:45:24 [INFO] train episode 50108: reward = -17.84, steps = 37 11:45:28 [INFO] train episode 50109: reward = -62.41, steps = 42 11:45:31 [INFO] train episode 50110: reward = -43.31, steps = 32 11:45:34 [INFO] train episode 50111: reward = -55.77, steps = 28 11:45:38 [INFO] train episode 50112: reward = -31.36, steps = 45 11:45:41 [INFO] train episode 50113: reward = -56.88, steps = 38 11:45:47 [INFO] train episode 50114: reward = -29.89, steps = 67 11:45:50 [INFO] train episode 50115: reward = -42.16, steps = 33 11:45:54 [INFO] train episode 50116: reward = -69.57, steps = 43 11:45:57 [INFO] train episode 50117: reward = -35.15, steps = 35 11:45:59 [INFO] train episode 50118: reward = -44.01, steps = 31 11:46:03 [INFO] train episode 50119: reward = -37.36, steps = 37 11:46:05 [INFO] train episode 50120: reward = -50.16, steps = 23 11:46:08 [INFO] train episode 50121: reward = -26.50, steps = 37 11:46:11 [INFO] train episode 50122: reward = -50.80, steps = 36 11:46:14 [INFO] train episode 50123: reward = -40.62, steps = 28 11:46:16 [INFO] train episode 50124: reward = -39.58, steps = 29 11:46:20 [INFO] train episode 50125: reward = -39.37, steps = 42 11:46:26 [INFO] train episode 50126: reward = -63.48, steps = 58 11:46:29 [INFO] train episode 50127: reward = -25.85, steps = 39 11:46:31 [INFO] train episode 50128: reward = -43.20, steps = 28 11:46:35 [INFO] train episode 50129: reward = -48.63, steps = 44 11:46:38 [INFO] train episode 50130: reward = -41.75, steps = 28 11:46:41 [INFO] train episode 50131: reward = -25.90, steps = 37 11:46:44 [INFO] train episode 50132: reward = -33.67, steps = 35 11:46:47 [INFO] train episode 50133: reward = -38.97, steps = 29 11:46:50 [INFO] train episode 50134: reward = -25.98, steps = 37 11:46:54 [INFO] train episode 50135: reward = -15.50, steps = 35 11:46:57 [INFO] train episode 50136: reward = -33.67, steps = 32 11:47:00 [INFO] train episode 50137: reward = -37.74, steps = 32 11:47:03 [INFO] train episode 50138: reward = -49.80, steps = 31 11:47:06 [INFO] train episode 50139: reward = -42.12, steps = 45 11:47:09 [INFO] train episode 50140: reward = -29.12, steps = 29 11:47:12 [INFO] train episode 50141: reward = -35.92, steps = 30 11:47:14 [INFO] train episode 50142: reward = -44.31, steps = 21 11:47:17 [INFO] train episode 50143: reward = -23.78, steps = 36 11:47:19 [INFO] train episode 50144: reward = -40.13, steps = 25 11:47:22 [INFO] train episode 50145: reward = -39.63, steps = 33 11:47:24 [INFO] train episode 50146: reward = -54.60, steps = 22 11:47:27 [INFO] train episode 50147: reward = -46.74, steps = 31 11:47:29 [INFO] train episode 50148: reward = -56.34, steps = 20 11:47:32 [INFO] train episode 50149: reward = -34.79, steps = 32 11:47:38 [INFO] train episode 50150: reward = -94.61, steps = 63 11:47:41 [INFO] train episode 50151: reward = -28.42, steps = 43 11:47:43 [INFO] train episode 50152: reward = -64.53, steps = 20 11:47:46 [INFO] train episode 50153: reward = -82.59, steps = 23 11:47:49 [INFO] train episode 50154: reward = -52.91, steps = 35 11:47:52 [INFO] train episode 50155: reward = -24.20, steps = 29 11:47:54 [INFO] train episode 50156: reward = -45.97, steps = 22 11:47:57 [INFO] train episode 50157: reward = -48.93, steps = 35 11:48:00 [INFO] train episode 50158: reward = -25.02, steps = 32 11:48:04 [INFO] train episode 50159: reward = -17.37, steps = 42 11:48:07 [INFO] train episode 50160: reward = -33.74, steps = 28 11:48:11 [INFO] train episode 50161: reward = -25.76, steps = 50 11:48:15 [INFO] train episode 50162: reward = -48.26, steps = 47 11:48:17 [INFO] train episode 50163: reward = -26.54, steps = 22 11:48:21 [INFO] train episode 50164: reward = -46.94, steps = 42 11:48:25 [INFO] train episode 50165: reward = -42.74, steps = 42 11:48:28 [INFO] train episode 50166: reward = -36.91, steps = 31 11:48:31 [INFO] train episode 50167: reward = -27.95, steps = 35 11:48:34 [INFO] train episode 50168: reward = -23.58, steps = 37 11:48:38 [INFO] train episode 50169: reward = -60.06, steps = 40 11:48:41 [INFO] train episode 50170: reward = -26.51, steps = 34 11:48:44 [INFO] train episode 50171: reward = -21.13, steps = 30 11:48:47 [INFO] train episode 50172: reward = -23.05, steps = 36 11:48:49 [INFO] train episode 50173: reward = -30.17, steps = 28 11:48:52 [INFO] train episode 50174: reward = -62.81, steps = 27 11:48:54 [INFO] train episode 50175: reward = -59.08, steps = 23 11:48:58 [INFO] train episode 50176: reward = -51.11, steps = 39 11:49:01 [INFO] train episode 50177: reward = -49.43, steps = 31 11:49:03 [INFO] train episode 50178: reward = -47.57, steps = 25 11:49:07 [INFO] train episode 50179: reward = -26.20, steps = 50 11:49:10 [INFO] train episode 50180: reward = -44.27, steps = 26 11:49:13 [INFO] train episode 50181: reward = -45.22, steps = 28 11:49:17 [INFO] train episode 50182: reward = -34.77, steps = 47 11:49:20 [INFO] train episode 50183: reward = -26.44, steps = 40 11:49:24 [INFO] train episode 50184: reward = -46.25, steps = 37 11:49:26 [INFO] train episode 50185: reward = -38.62, steps = 27 11:49:29 [INFO] train episode 50186: reward = -34.18, steps = 30 11:49:32 [INFO] train episode 50187: reward = -40.92, steps = 38 11:49:36 [INFO] train episode 50188: reward = -37.54, steps = 40 11:49:40 [INFO] train episode 50189: reward = -42.11, steps = 44 11:49:43 [INFO] train episode 50190: reward = -44.22, steps = 33 11:49:46 [INFO] train episode 50191: reward = -39.65, steps = 32 11:49:49 [INFO] train episode 50192: reward = -15.57, steps = 39 11:49:53 [INFO] train episode 50193: reward = -24.93, steps = 38 11:49:57 [INFO] train episode 50194: reward = -22.40, steps = 56 11:50:01 [INFO] train episode 50195: reward = -33.00, steps = 35 11:50:03 [INFO] train episode 50196: reward = -32.86, steps = 23 11:50:07 [INFO] train episode 50197: reward = -16.03, steps = 37 11:50:10 [INFO] train episode 50198: reward = -66.61, steps = 37 11:50:14 [INFO] train episode 50199: reward = -16.80, steps = 42 11:50:17 [INFO] train episode 50200: reward = -25.54, steps = 37 11:50:21 [INFO] train episode 50201: reward = -89.62, steps = 41 11:50:25 [INFO] train episode 50202: reward = -17.08, steps = 45 11:50:29 [INFO] train episode 50203: reward = -41.66, steps = 45 11:50:32 [INFO] train episode 50204: reward = -51.41, steps = 31 11:50:35 [INFO] train episode 50205: reward = -28.31, steps = 38 11:50:38 [INFO] train episode 50206: reward = -39.92, steps = 31 11:50:41 [INFO] train episode 50207: reward = -38.16, steps = 31 11:50:45 [INFO] train episode 50208: reward = -18.95, steps = 37 11:50:50 [INFO] train episode 50209: reward = -34.70, steps = 56 11:50:53 [INFO] train episode 50210: reward = -11.89, steps = 36 11:50:56 [INFO] train episode 50211: reward = -35.70, steps = 33 11:51:00 [INFO] train episode 50212: reward = -20.78, steps = 39 11:51:02 [INFO] train episode 50213: reward = -36.65, steps = 29 11:51:05 [INFO] train episode 50214: reward = -36.16, steps = 30 11:51:09 [INFO] train episode 50215: reward = -31.01, steps = 37 11:51:12 [INFO] train episode 50216: reward = -17.25, steps = 39 11:51:15 [INFO] train episode 50217: reward = -65.72, steps = 38 11:51:17 [INFO] train episode 50218: reward = -52.84, steps = 22 11:51:22 [INFO] train episode 50219: reward = -25.33, steps = 47 11:51:25 [INFO] train episode 50220: reward = -65.18, steps = 39 11:51:28 [INFO] train episode 50221: reward = -30.22, steps = 28 11:51:32 [INFO] train episode 50222: reward = -38.16, steps = 43 11:51:34 [INFO] train episode 50223: reward = -37.73, steps = 27 11:51:38 [INFO] train episode 50224: reward = -29.07, steps = 42 11:51:42 [INFO] train episode 50225: reward = -21.09, steps = 38 11:51:45 [INFO] train episode 50226: reward = -61.42, steps = 35 11:51:48 [INFO] train episode 50227: reward = -45.01, steps = 36 11:51:50 [INFO] train episode 50228: reward = -38.19, steps = 22 11:51:52 [INFO] train episode 50229: reward = -47.60, steps = 27 11:51:55 [INFO] train episode 50230: reward = -48.97, steps = 32 11:51:58 [INFO] train episode 50231: reward = -40.81, steps = 25 11:52:01 [INFO] train episode 50232: reward = -37.42, steps = 36 11:52:04 [INFO] train episode 50233: reward = -31.88, steps = 36 11:52:07 [INFO] train episode 50234: reward = -15.65, steps = 36 11:52:09 [INFO] train episode 50235: reward = -41.59, steps = 21 11:52:11 [INFO] train episode 50236: reward = -48.46, steps = 24 11:52:15 [INFO] train episode 50237: reward = -73.35, steps = 40 11:52:19 [INFO] train episode 50238: reward = -23.06, steps = 49 11:52:22 [INFO] train episode 50239: reward = -23.88, steps = 33 11:52:24 [INFO] train episode 50240: reward = -54.72, steps = 25 11:52:26 [INFO] train episode 50241: reward = -40.28, steps = 21 11:52:30 [INFO] train episode 50242: reward = -63.28, steps = 37 11:52:33 [INFO] train episode 50243: reward = -34.46, steps = 40 11:52:36 [INFO] train episode 50244: reward = -30.91, steps = 35 11:52:39 [INFO] train episode 50245: reward = -53.67, steps = 35 11:52:43 [INFO] train episode 50246: reward = -47.45, steps = 36 11:52:46 [INFO] train episode 50247: reward = -41.66, steps = 30 11:52:48 [INFO] train episode 50248: reward = -26.72, steps = 31 11:52:50 [INFO] train episode 50249: reward = -58.25, steps = 22 11:52:53 [INFO] train episode 50250: reward = -65.95, steps = 27 11:52:54 [INFO] train episode 50251: reward = -37.95, steps = 19 11:52:57 [INFO] train episode 50252: reward = -44.80, steps = 31 11:53:01 [INFO] train episode 50253: reward = -28.62, steps = 34 11:53:04 [INFO] train episode 50254: reward = -44.67, steps = 34 11:53:06 [INFO] train episode 50255: reward = -51.64, steps = 26 11:53:09 [INFO] train episode 50256: reward = -38.11, steps = 33 11:53:12 [INFO] train episode 50257: reward = -26.93, steps = 34 11:53:14 [INFO] train episode 50258: reward = -41.55, steps = 22 11:53:17 [INFO] train episode 50259: reward = -42.76, steps = 29 11:53:20 [INFO] train episode 50260: reward = -47.13, steps = 31 11:53:23 [INFO] train episode 50261: reward = -25.43, steps = 32 11:53:26 [INFO] train episode 50262: reward = -42.95, steps = 36 11:53:29 [INFO] train episode 50263: reward = -23.36, steps = 41 11:53:33 [INFO] train episode 50264: reward = -48.05, steps = 40 11:53:36 [INFO] train episode 50265: reward = -50.36, steps = 29 11:53:39 [INFO] train episode 50266: reward = -45.31, steps = 40 11:53:42 [INFO] train episode 50267: reward = -28.34, steps = 29 11:53:46 [INFO] train episode 50268: reward = -29.56, steps = 46 11:53:50 [INFO] train episode 50269: reward = -18.74, steps = 35 11:53:54 [INFO] train episode 50270: reward = -27.61, steps = 41 11:53:57 [INFO] train episode 50271: reward = -37.74, steps = 40 11:54:00 [INFO] train episode 50272: reward = -33.84, steps = 38 11:54:05 [INFO] train episode 50273: reward = -17.95, steps = 56 11:54:07 [INFO] train episode 50274: reward = -62.06, steps = 20 11:54:12 [INFO] train episode 50275: reward = -37.32, steps = 51 11:54:15 [INFO] train episode 50276: reward = -51.71, steps = 34 11:54:18 [INFO] train episode 50277: reward = -18.33, steps = 41 11:54:22 [INFO] train episode 50278: reward = -58.73, steps = 44 11:54:26 [INFO] train episode 50279: reward = -37.43, steps = 34 11:54:29 [INFO] train episode 50280: reward = -48.00, steps = 33 11:54:31 [INFO] train episode 50281: reward = -49.70, steps = 24 11:54:33 [INFO] train episode 50282: reward = -23.02, steps = 26 11:54:37 [INFO] train episode 50283: reward = -32.32, steps = 45 11:54:41 [INFO] train episode 50284: reward = -31.01, steps = 40 11:54:43 [INFO] train episode 50285: reward = -34.35, steps = 24 11:54:46 [INFO] train episode 50286: reward = -39.78, steps = 37 11:54:50 [INFO] train episode 50287: reward = -27.59, steps = 43 11:54:53 [INFO] train episode 50288: reward = -34.49, steps = 40 11:54:58 [INFO] train episode 50289: reward = -35.74, steps = 44 11:55:01 [INFO] train episode 50290: reward = -41.08, steps = 38 11:55:05 [INFO] train episode 50291: reward = -47.48, steps = 39 11:55:07 [INFO] train episode 50292: reward = -24.37, steps = 27 11:55:09 [INFO] train episode 50293: reward = -54.58, steps = 19 11:55:12 [INFO] train episode 50294: reward = -25.01, steps = 37 11:55:15 [INFO] train episode 50295: reward = -81.98, steps = 26 11:55:18 [INFO] train episode 50296: reward = -54.94, steps = 44 11:55:22 [INFO] train episode 50297: reward = -39.71, steps = 39 11:55:25 [INFO] train episode 50298: reward = -23.85, steps = 38 11:55:29 [INFO] train episode 50299: reward = -41.43, steps = 46 11:55:31 [INFO] train episode 50300: reward = -64.51, steps = 21 11:55:34 [INFO] train episode 50301: reward = -62.50, steps = 29 11:55:37 [INFO] train episode 50302: reward = -31.42, steps = 32 11:55:40 [INFO] train episode 50303: reward = -33.76, steps = 38 11:55:43 [INFO] train episode 50304: reward = -44.16, steps = 28 11:55:47 [INFO] train episode 50305: reward = -27.02, steps = 43 11:55:50 [INFO] train episode 50306: reward = 0.04, steps = 41 11:55:53 [INFO] train episode 50307: reward = -22.72, steps = 37 11:55:57 [INFO] train episode 50308: reward = -13.50, steps = 40 11:56:01 [INFO] train episode 50309: reward = -35.31, steps = 40 11:56:05 [INFO] train episode 50310: reward = -56.18, steps = 48 11:56:08 [INFO] train episode 50311: reward = -40.23, steps = 35 11:56:11 [INFO] train episode 50312: reward = -33.92, steps = 35 11:56:15 [INFO] train episode 50313: reward = -7.59, steps = 41 11:56:18 [INFO] train episode 50314: reward = -37.86, steps = 30 11:56:19 [INFO] train episode 50315: reward = -40.89, steps = 21 11:56:23 [INFO] train episode 50316: reward = -42.41, steps = 45 11:56:26 [INFO] train episode 50317: reward = -21.74, steps = 25 11:56:27 [INFO] train episode 50318: reward = -14.32, steps = 23 11:56:31 [INFO] train episode 50319: reward = -31.11, steps = 44 11:56:35 [INFO] train episode 50320: reward = -47.59, steps = 35 11:56:37 [INFO] train episode 50321: reward = -51.41, steps = 25 11:56:41 [INFO] train episode 50322: reward = -10.54, steps = 43 11:56:46 [INFO] train episode 50323: reward = -30.11, steps = 53 11:56:48 [INFO] train episode 50324: reward = -32.06, steps = 29 11:56:51 [INFO] train episode 50325: reward = -50.27, steps = 25 11:56:52 [INFO] train episode 50326: reward = -54.48, steps = 16 11:56:56 [INFO] train episode 50327: reward = -24.68, steps = 45 11:57:00 [INFO] train episode 50328: reward = -30.89, steps = 38 11:57:03 [INFO] train episode 50329: reward = -17.91, steps = 36 11:57:07 [INFO] train episode 50330: reward = -46.13, steps = 37 11:57:11 [INFO] train episode 50331: reward = -46.98, steps = 46 11:57:13 [INFO] train episode 50332: reward = -23.28, steps = 32 11:57:16 [INFO] train episode 50333: reward = -17.68, steps = 33 11:57:19 [INFO] train episode 50334: reward = -26.90, steps = 36 11:57:23 [INFO] train episode 50335: reward = -19.06, steps = 37 11:57:25 [INFO] train episode 50336: reward = -54.82, steps = 24 11:57:27 [INFO] train episode 50337: reward = -38.16, steps = 25 11:57:30 [INFO] train episode 50338: reward = -46.83, steps = 27 11:57:32 [INFO] train episode 50339: reward = -22.27, steps = 26 11:57:36 [INFO] train episode 50340: reward = -30.49, steps = 47 11:57:40 [INFO] train episode 50341: reward = -16.35, steps = 46 11:57:43 [INFO] train episode 50342: reward = -46.15, steps = 34 11:57:46 [INFO] train episode 50343: reward = -46.39, steps = 32 11:57:48 [INFO] train episode 50344: reward = -55.35, steps = 22 11:57:51 [INFO] train episode 50345: reward = -42.08, steps = 29 11:57:54 [INFO] train episode 50346: reward = -45.70, steps = 41 11:57:58 [INFO] train episode 50347: reward = -29.20, steps = 39 11:58:01 [INFO] train episode 50348: reward = -33.13, steps = 36 11:58:05 [INFO] train episode 50349: reward = -14.94, steps = 43 11:58:07 [INFO] train episode 50350: reward = -64.59, steps = 22 11:58:11 [INFO] train episode 50351: reward = -15.88, steps = 40 11:58:15 [INFO] train episode 50352: reward = -14.75, steps = 44 11:58:17 [INFO] train episode 50353: reward = -31.62, steps = 25 11:58:20 [INFO] train episode 50354: reward = -18.83, steps = 31 11:58:23 [INFO] train episode 50355: reward = -58.41, steps = 32 11:58:25 [INFO] train episode 50356: reward = -69.61, steps = 29 11:58:28 [INFO] train episode 50357: reward = -34.77, steps = 35 11:58:31 [INFO] train episode 50358: reward = -44.91, steps = 20 11:58:36 [INFO] train episode 50359: reward = -147.06, steps = 66 11:58:38 [INFO] train episode 50360: reward = -40.24, steps = 23 11:58:42 [INFO] train episode 50361: reward = -37.46, steps = 44 11:58:46 [INFO] train episode 50362: reward = -44.27, steps = 37 11:58:49 [INFO] train episode 50363: reward = -75.48, steps = 35 11:58:51 [INFO] train episode 50364: reward = -35.60, steps = 26 11:58:53 [INFO] train episode 50365: reward = -67.95, steps = 19 11:58:55 [INFO] train episode 50366: reward = -47.06, steps = 23 11:58:58 [INFO] train episode 50367: reward = -19.02, steps = 36 11:59:01 [INFO] train episode 50368: reward = -26.19, steps = 38 11:59:04 [INFO] train episode 50369: reward = -21.60, steps = 23 11:59:08 [INFO] train episode 50370: reward = -46.48, steps = 52 11:59:11 [INFO] train episode 50371: reward = -16.97, steps = 34 11:59:14 [INFO] train episode 50372: reward = -32.39, steps = 26 11:59:18 [INFO] train episode 50373: reward = -64.76, steps = 39 11:59:21 [INFO] train episode 50374: reward = -52.55, steps = 24 11:59:23 [INFO] train episode 50375: reward = -36.36, steps = 25 11:59:27 [INFO] train episode 50376: reward = -37.58, steps = 40 11:59:31 [INFO] train episode 50377: reward = -26.82, steps = 50 11:59:33 [INFO] train episode 50378: reward = -33.46, steps = 22 11:59:36 [INFO] train episode 50379: reward = -46.67, steps = 27 11:59:39 [INFO] train episode 50380: reward = -40.90, steps = 24 11:59:43 [INFO] train episode 50381: reward = -53.01, steps = 42 11:59:46 [INFO] train episode 50382: reward = -28.94, steps = 39 11:59:49 [INFO] train episode 50383: reward = -35.09, steps = 39 11:59:51 [INFO] train episode 50384: reward = -36.58, steps = 24 11:59:54 [INFO] train episode 50385: reward = -41.00, steps = 25 11:59:57 [INFO] train episode 50386: reward = -52.06, steps = 31 12:00:01 [INFO] train episode 50387: reward = -20.03, steps = 52 12:00:04 [INFO] train episode 50388: reward = -54.58, steps = 36 12:00:06 [INFO] train episode 50389: reward = -30.34, steps = 22 12:00:08 [INFO] train episode 50390: reward = -55.12, steps = 20 12:00:13 [INFO] train episode 50391: reward = -42.34, steps = 50 12:00:18 [INFO] train episode 50392: reward = -59.71, steps = 55 12:00:21 [INFO] train episode 50393: reward = -24.58, steps = 44 12:00:24 [INFO] train episode 50394: reward = -43.92, steps = 33 12:00:28 [INFO] train episode 50395: reward = -19.74, steps = 43 12:00:32 [INFO] train episode 50396: reward = -17.04, steps = 41 12:00:35 [INFO] train episode 50397: reward = -33.44, steps = 37 12:00:39 [INFO] train episode 50398: reward = -50.73, steps = 40 12:00:42 [INFO] train episode 50399: reward = -40.95, steps = 33 12:00:44 [INFO] train episode 50400: reward = -35.46, steps = 24 12:00:47 [INFO] train episode 50401: reward = -34.54, steps = 33 12:00:50 [INFO] train episode 50402: reward = -41.42, steps = 40 12:00:56 [INFO] train episode 50403: reward = -31.89, steps = 65 12:01:01 [INFO] train episode 50404: reward = -37.51, steps = 53 12:01:05 [INFO] train episode 50405: reward = -41.19, steps = 41 12:01:07 [INFO] train episode 50406: reward = -60.84, steps = 24 12:01:10 [INFO] train episode 50407: reward = -29.27, steps = 36 12:01:14 [INFO] train episode 50408: reward = -44.83, steps = 48 12:01:18 [INFO] train episode 50409: reward = -47.02, steps = 39 12:01:21 [INFO] train episode 50410: reward = -27.49, steps = 36 12:01:25 [INFO] train episode 50411: reward = -31.27, steps = 43 12:01:29 [INFO] train episode 50412: reward = -18.31, steps = 43 12:01:33 [INFO] train episode 50413: reward = -49.30, steps = 41 12:01:36 [INFO] train episode 50414: reward = -83.51, steps = 34 12:01:39 [INFO] train episode 50415: reward = -38.80, steps = 40 12:01:43 [INFO] train episode 50416: reward = -18.70, steps = 40 12:01:45 [INFO] train episode 50417: reward = -73.31, steps = 30 12:01:48 [INFO] train episode 50418: reward = -28.06, steps = 32 12:01:52 [INFO] train episode 50419: reward = -8.70, steps = 39 12:01:56 [INFO] train episode 50420: reward = -37.51, steps = 53 12:02:01 [INFO] train episode 50421: reward = -31.58, steps = 51 12:02:04 [INFO] train episode 50422: reward = -35.09, steps = 37 12:02:07 [INFO] train episode 50423: reward = -7.86, steps = 35 12:02:11 [INFO] train episode 50424: reward = -39.34, steps = 35 12:02:13 [INFO] train episode 50425: reward = -51.28, steps = 30 12:02:16 [INFO] train episode 50426: reward = -36.39, steps = 34 12:02:18 [INFO] train episode 50427: reward = -55.13, steps = 18 12:02:22 [INFO] train episode 50428: reward = -95.53, steps = 50 12:02:27 [INFO] train episode 50429: reward = -28.75, steps = 48 12:02:29 [INFO] train episode 50430: reward = -38.50, steps = 24 12:02:30 [INFO] train episode 50431: reward = -49.66, steps = 20 12:02:34 [INFO] train episode 50432: reward = -37.64, steps = 30 12:02:37 [INFO] train episode 50433: reward = -90.14, steps = 38 12:02:42 [INFO] train episode 50434: reward = -44.86, steps = 51 12:02:46 [INFO] train episode 50435: reward = -50.01, steps = 50 12:02:49 [INFO] train episode 50436: reward = -30.66, steps = 25 12:02:51 [INFO] train episode 50437: reward = -54.25, steps = 32 12:02:55 [INFO] train episode 50438: reward = -57.87, steps = 37 12:02:57 [INFO] train episode 50439: reward = -35.02, steps = 22 12:03:00 [INFO] train episode 50440: reward = -34.75, steps = 32 12:03:02 [INFO] train episode 50441: reward = -42.55, steps = 21 12:03:04 [INFO] train episode 50442: reward = -37.10, steps = 21 12:03:06 [INFO] train episode 50443: reward = -55.26, steps = 18 12:03:09 [INFO] train episode 50444: reward = -27.45, steps = 37 12:03:14 [INFO] train episode 50445: reward = -41.73, steps = 50 12:03:16 [INFO] train episode 50446: reward = -44.94, steps = 24 12:03:19 [INFO] train episode 50447: reward = -47.47, steps = 40 12:03:21 [INFO] train episode 50448: reward = -37.37, steps = 19 12:03:24 [INFO] train episode 50449: reward = -48.49, steps = 37 12:03:28 [INFO] train episode 50450: reward = -52.31, steps = 37 12:03:29 [INFO] train episode 50451: reward = -64.27, steps = 17 12:03:31 [INFO] train episode 50452: reward = -47.35, steps = 21 12:03:33 [INFO] train episode 50453: reward = -44.60, steps = 24 12:03:36 [INFO] train episode 50454: reward = -29.21, steps = 30 12:03:39 [INFO] train episode 50455: reward = -30.54, steps = 42 12:03:43 [INFO] train episode 50456: reward = -28.74, steps = 39 12:03:45 [INFO] train episode 50457: reward = -39.72, steps = 22 12:03:48 [INFO] train episode 50458: reward = -24.12, steps = 35 12:03:51 [INFO] train episode 50459: reward = -23.02, steps = 26 12:03:55 [INFO] train episode 50460: reward = -29.14, steps = 49 12:03:58 [INFO] train episode 50461: reward = -55.66, steps = 39 12:04:02 [INFO] train episode 50462: reward = -42.14, steps = 32 12:04:05 [INFO] train episode 50463: reward = -36.55, steps = 40 12:04:07 [INFO] train episode 50464: reward = -60.26, steps = 22 12:04:09 [INFO] train episode 50465: reward = -52.66, steps = 22 12:04:15 [INFO] train episode 50466: reward = -66.11, steps = 63 12:04:18 [INFO] train episode 50467: reward = -25.27, steps = 37 12:04:20 [INFO] train episode 50468: reward = -77.63, steps = 19 12:04:22 [INFO] train episode 50469: reward = -31.19, steps = 22 12:04:25 [INFO] train episode 50470: reward = -64.56, steps = 30 12:04:27 [INFO] train episode 50471: reward = -48.07, steps = 31 12:04:30 [INFO] train episode 50472: reward = -30.28, steps = 25 12:04:32 [INFO] train episode 50473: reward = -33.20, steps = 30 12:04:35 [INFO] train episode 50474: reward = -29.66, steps = 24 12:04:37 [INFO] train episode 50475: reward = -34.71, steps = 28 12:04:41 [INFO] train episode 50476: reward = -5.59, steps = 39 12:04:43 [INFO] train episode 50477: reward = -47.86, steps = 24 12:04:46 [INFO] train episode 50478: reward = -26.63, steps = 37 12:04:51 [INFO] train episode 50479: reward = -27.02, steps = 48 12:04:54 [INFO] train episode 50480: reward = -40.71, steps = 35 12:04:58 [INFO] train episode 50481: reward = -39.24, steps = 47 12:05:02 [INFO] train episode 50482: reward = -45.76, steps = 44 12:05:06 [INFO] train episode 50483: reward = -34.23, steps = 45 12:05:09 [INFO] train episode 50484: reward = -55.05, steps = 34 12:05:12 [INFO] train episode 50485: reward = -39.41, steps = 29 12:05:13 [INFO] train episode 50486: reward = -32.66, steps = 20 12:05:17 [INFO] train episode 50487: reward = -18.24, steps = 41 12:05:19 [INFO] train episode 50488: reward = -95.83, steps = 20 12:05:22 [INFO] train episode 50489: reward = -25.34, steps = 35 12:05:25 [INFO] train episode 50490: reward = -44.17, steps = 33 12:05:29 [INFO] train episode 50491: reward = -39.14, steps = 42 12:05:32 [INFO] train episode 50492: reward = -49.79, steps = 24 12:05:35 [INFO] train episode 50493: reward = -25.61, steps = 39 12:05:38 [INFO] train episode 50494: reward = -13.55, steps = 40 12:05:42 [INFO] train episode 50495: reward = -41.37, steps = 36 12:05:45 [INFO] train episode 50496: reward = -53.79, steps = 28 12:05:47 [INFO] train episode 50497: reward = -54.37, steps = 28 12:05:50 [INFO] train episode 50498: reward = -25.68, steps = 28 12:05:52 [INFO] train episode 50499: reward = -40.81, steps = 23 12:05:55 [INFO] train episode 50500: reward = -40.90, steps = 40 12:05:57 [INFO] train episode 50501: reward = -47.56, steps = 21 12:06:00 [INFO] train episode 50502: reward = -34.28, steps = 29 12:06:03 [INFO] train episode 50503: reward = -27.00, steps = 39 12:06:07 [INFO] train episode 50504: reward = -14.37, steps = 36 12:06:08 [INFO] train episode 50505: reward = -30.11, steps = 21 12:06:13 [INFO] train episode 50506: reward = -11.61, steps = 43 12:06:16 [INFO] train episode 50507: reward = -87.06, steps = 40 12:06:20 [INFO] train episode 50508: reward = -53.10, steps = 43 12:06:23 [INFO] train episode 50509: reward = -46.47, steps = 37 12:06:27 [INFO] train episode 50510: reward = -53.28, steps = 46 12:06:30 [INFO] train episode 50511: reward = -43.66, steps = 28 12:06:32 [INFO] train episode 50512: reward = -41.83, steps = 27 12:06:34 [INFO] train episode 50513: reward = -45.45, steps = 17 12:06:36 [INFO] train episode 50514: reward = -40.22, steps = 20 12:06:38 [INFO] train episode 50515: reward = -71.57, steps = 29 12:06:41 [INFO] train episode 50516: reward = -47.79, steps = 29 12:06:45 [INFO] train episode 50517: reward = -48.33, steps = 48 12:06:48 [INFO] train episode 50518: reward = -32.59, steps = 34 12:06:51 [INFO] train episode 50519: reward = -56.29, steps = 30 12:06:54 [INFO] train episode 50520: reward = -32.04, steps = 33 12:06:56 [INFO] train episode 50521: reward = -40.81, steps = 28 12:07:00 [INFO] train episode 50522: reward = -71.26, steps = 39 12:07:04 [INFO] train episode 50523: reward = -16.63, steps = 45 12:07:07 [INFO] train episode 50524: reward = -32.81, steps = 33 12:07:11 [INFO] train episode 50525: reward = -26.17, steps = 42 12:07:14 [INFO] train episode 50526: reward = -67.18, steps = 40 12:07:18 [INFO] train episode 50527: reward = -42.72, steps = 47 12:07:23 [INFO] train episode 50528: reward = -119.29, steps = 51 12:07:26 [INFO] train episode 50529: reward = -56.45, steps = 32 12:07:29 [INFO] train episode 50530: reward = -26.56, steps = 32 12:07:31 [INFO] train episode 50531: reward = -41.89, steps = 28 12:07:34 [INFO] train episode 50532: reward = -28.97, steps = 35 12:07:38 [INFO] train episode 50533: reward = -26.62, steps = 39 12:07:41 [INFO] train episode 50534: reward = -45.67, steps = 35 12:07:43 [INFO] train episode 50535: reward = -27.79, steps = 22 12:07:46 [INFO] train episode 50536: reward = -5.62, steps = 35 12:07:49 [INFO] train episode 50537: reward = -19.17, steps = 33 12:07:54 [INFO] train episode 50538: reward = -34.14, steps = 47 12:07:55 [INFO] train episode 50539: reward = -40.05, steps = 21 12:07:58 [INFO] train episode 50540: reward = -44.06, steps = 25 12:08:01 [INFO] train episode 50541: reward = -24.58, steps = 38 12:08:04 [INFO] train episode 50542: reward = -12.15, steps = 37 12:08:08 [INFO] train episode 50543: reward = -39.17, steps = 40 12:08:12 [INFO] train episode 50544: reward = -24.56, steps = 45 12:08:14 [INFO] train episode 50545: reward = -42.85, steps = 26 12:08:17 [INFO] train episode 50546: reward = -37.48, steps = 29 12:08:20 [INFO] train episode 50547: reward = -18.20, steps = 43 12:08:24 [INFO] train episode 50548: reward = -25.11, steps = 37 12:08:28 [INFO] train episode 50549: reward = -33.62, steps = 39 12:08:32 [INFO] train episode 50550: reward = -16.82, steps = 43 12:08:36 [INFO] train episode 50551: reward = -35.12, steps = 51 12:08:39 [INFO] train episode 50552: reward = -37.13, steps = 30 12:08:44 [INFO] train episode 50553: reward = -26.93, steps = 50 12:08:46 [INFO] train episode 50554: reward = -34.68, steps = 29 12:08:49 [INFO] train episode 50555: reward = -43.65, steps = 37 12:08:51 [INFO] train episode 50556: reward = -34.31, steps = 25 12:08:55 [INFO] train episode 50557: reward = -15.54, steps = 41 12:08:59 [INFO] train episode 50558: reward = -16.61, steps = 42 12:09:03 [INFO] train episode 50559: reward = -60.34, steps = 42 12:09:06 [INFO] train episode 50560: reward = -28.55, steps = 33 12:09:09 [INFO] train episode 50561: reward = -58.34, steps = 32 12:09:11 [INFO] train episode 50562: reward = -51.46, steps = 25 12:09:14 [INFO] train episode 50563: reward = -58.08, steps = 31 12:09:17 [INFO] train episode 50564: reward = -17.13, steps = 36 12:09:21 [INFO] train episode 50565: reward = -35.71, steps = 38 12:09:25 [INFO] train episode 50566: reward = -40.18, steps = 46 12:09:28 [INFO] train episode 50567: reward = -7.64, steps = 42 12:09:31 [INFO] train episode 50568: reward = -13.45, steps = 32 12:09:34 [INFO] train episode 50569: reward = -57.00, steps = 33 12:09:37 [INFO] train episode 50570: reward = -44.30, steps = 26 12:09:40 [INFO] train episode 50571: reward = -32.28, steps = 36 12:09:42 [INFO] train episode 50572: reward = -30.51, steps = 29 12:09:45 [INFO] train episode 50573: reward = -19.89, steps = 36 12:09:49 [INFO] train episode 50574: reward = -42.88, steps = 40 12:09:51 [INFO] train episode 50575: reward = -57.86, steps = 19 12:09:53 [INFO] train episode 50576: reward = -51.41, steps = 24 12:09:56 [INFO] train episode 50577: reward = -47.42, steps = 29 12:09:59 [INFO] train episode 50578: reward = -33.89, steps = 35 12:10:01 [INFO] train episode 50579: reward = -24.90, steps = 28 12:10:05 [INFO] train episode 50580: reward = -33.75, steps = 35 12:10:07 [INFO] train episode 50581: reward = -41.82, steps = 30 12:10:09 [INFO] train episode 50582: reward = -38.65, steps = 19 12:10:12 [INFO] train episode 50583: reward = -42.94, steps = 37 12:10:16 [INFO] train episode 50584: reward = -7.05, steps = 42 12:10:21 [INFO] train episode 50585: reward = -43.00, steps = 53 12:10:23 [INFO] train episode 50586: reward = -36.13, steps = 31 12:10:25 [INFO] train episode 50587: reward = -45.81, steps = 20 12:10:29 [INFO] train episode 50588: reward = -59.18, steps = 37 12:10:32 [INFO] train episode 50589: reward = -34.39, steps = 41 12:10:36 [INFO] train episode 50590: reward = -21.36, steps = 38 12:10:40 [INFO] train episode 50591: reward = -22.89, steps = 41 12:10:42 [INFO] train episode 50592: reward = -28.65, steps = 34 12:10:47 [INFO] train episode 50593: reward = -40.16, steps = 48 12:10:49 [INFO] train episode 50594: reward = -46.21, steps = 24 12:10:52 [INFO] train episode 50595: reward = -49.51, steps = 35 12:10:56 [INFO] train episode 50596: reward = -34.29, steps = 40 12:10:59 [INFO] train episode 50597: reward = -45.83, steps = 36 12:11:02 [INFO] train episode 50598: reward = -41.95, steps = 33 12:11:05 [INFO] train episode 50599: reward = -0.66, steps = 40 12:11:08 [INFO] train episode 50600: reward = -15.48, steps = 28 12:11:12 [INFO] train episode 50601: reward = -2.57, steps = 44 12:11:16 [INFO] train episode 50602: reward = -9.45, steps = 45 12:11:18 [INFO] train episode 50603: reward = -41.57, steps = 26 12:11:20 [INFO] train episode 50604: reward = -60.58, steps = 22 12:11:25 [INFO] train episode 50605: reward = -46.35, steps = 42 12:11:28 [INFO] train episode 50606: reward = -34.92, steps = 37 12:11:31 [INFO] train episode 50607: reward = -33.65, steps = 26 12:11:34 [INFO] train episode 50608: reward = -43.52, steps = 43 12:11:37 [INFO] train episode 50609: reward = -56.82, steps = 34 12:11:40 [INFO] train episode 50610: reward = -85.82, steps = 31 12:11:44 [INFO] train episode 50611: reward = -65.20, steps = 43 12:11:46 [INFO] train episode 50612: reward = -42.52, steps = 22 12:11:49 [INFO] train episode 50613: reward = -34.05, steps = 28 12:11:50 [INFO] train episode 50614: reward = -63.62, steps = 18 12:11:52 [INFO] train episode 50615: reward = -66.50, steps = 20 12:11:56 [INFO] train episode 50616: reward = -66.41, steps = 46 12:11:59 [INFO] train episode 50617: reward = -49.70, steps = 32 12:12:02 [INFO] train episode 50618: reward = -30.71, steps = 37 12:12:05 [INFO] train episode 50619: reward = -36.36, steps = 31 12:12:07 [INFO] train episode 50620: reward = -48.76, steps = 19 12:12:10 [INFO] train episode 50621: reward = -31.34, steps = 35 12:12:12 [INFO] train episode 50622: reward = -43.56, steps = 22 12:12:15 [INFO] train episode 50623: reward = -68.84, steps = 36 12:12:18 [INFO] train episode 50624: reward = -33.82, steps = 27 12:12:21 [INFO] train episode 50625: reward = -20.63, steps = 39 12:12:24 [INFO] train episode 50626: reward = -57.04, steps = 36 12:12:29 [INFO] train episode 50627: reward = -59.61, steps = 51 12:12:32 [INFO] train episode 50628: reward = -40.06, steps = 32 12:12:35 [INFO] train episode 50629: reward = -32.60, steps = 39 12:12:38 [INFO] train episode 50630: reward = -27.27, steps = 29 12:12:41 [INFO] train episode 50631: reward = -35.51, steps = 37 12:12:44 [INFO] train episode 50632: reward = -40.10, steps = 36 12:12:47 [INFO] train episode 50633: reward = -24.89, steps = 29 12:12:49 [INFO] train episode 50634: reward = -64.04, steps = 25 12:12:52 [INFO] train episode 50635: reward = -14.81, steps = 32 12:12:56 [INFO] train episode 50636: reward = -60.51, steps = 42 12:13:02 [INFO] train episode 50637: reward = -82.20, steps = 71 12:13:06 [INFO] train episode 50638: reward = -44.91, steps = 36 12:13:09 [INFO] train episode 50639: reward = -29.57, steps = 36 12:13:13 [INFO] train episode 50640: reward = -45.13, steps = 45 12:13:15 [INFO] train episode 50641: reward = -52.61, steps = 20 12:13:17 [INFO] train episode 50642: reward = -25.13, steps = 26 12:13:20 [INFO] train episode 50643: reward = -50.66, steps = 37 12:13:24 [INFO] train episode 50644: reward = -20.94, steps = 41 12:13:27 [INFO] train episode 50645: reward = -30.26, steps = 29 12:13:30 [INFO] train episode 50646: reward = -44.81, steps = 37 12:13:34 [INFO] train episode 50647: reward = -39.44, steps = 44 12:13:38 [INFO] train episode 50648: reward = -62.58, steps = 38 12:13:40 [INFO] train episode 50649: reward = -30.90, steps = 26 12:13:43 [INFO] train episode 50650: reward = -41.24, steps = 39 12:13:45 [INFO] train episode 50651: reward = -34.69, steps = 25 12:13:48 [INFO] train episode 50652: reward = -49.08, steps = 25 12:13:51 [INFO] train episode 50653: reward = -65.75, steps = 38 12:13:54 [INFO] train episode 50654: reward = -29.69, steps = 32 12:13:57 [INFO] train episode 50655: reward = -33.40, steps = 29 12:14:00 [INFO] train episode 50656: reward = -6.02, steps = 38 12:14:03 [INFO] train episode 50657: reward = -47.95, steps = 34 12:14:06 [INFO] train episode 50658: reward = -23.14, steps = 30 12:14:07 [INFO] train episode 50659: reward = -26.12, steps = 21 12:14:12 [INFO] train episode 50660: reward = -16.93, steps = 46 12:14:15 [INFO] train episode 50661: reward = -56.76, steps = 39 12:14:17 [INFO] train episode 50662: reward = -42.04, steps = 26 12:14:22 [INFO] train episode 50663: reward = -44.64, steps = 41 12:14:25 [INFO] train episode 50664: reward = -87.06, steps = 35 12:14:27 [INFO] train episode 50665: reward = -57.19, steps = 20 12:14:29 [INFO] train episode 50666: reward = -52.08, steps = 18 12:14:31 [INFO] train episode 50667: reward = -35.75, steps = 26 12:14:34 [INFO] train episode 50668: reward = -16.86, steps = 34 12:14:37 [INFO] train episode 50669: reward = -46.25, steps = 34 12:14:39 [INFO] train episode 50670: reward = -32.70, steps = 26 12:14:41 [INFO] train episode 50671: reward = -53.07, steps = 20 12:14:45 [INFO] train episode 50672: reward = -27.63, steps = 35 12:14:48 [INFO] train episode 50673: reward = -31.51, steps = 38 12:14:50 [INFO] train episode 50674: reward = -44.62, steps = 23 12:14:53 [INFO] train episode 50675: reward = -34.14, steps = 34 12:14:54 [INFO] train episode 50676: reward = -41.45, steps = 11 12:14:58 [INFO] train episode 50677: reward = -25.31, steps = 42 12:15:02 [INFO] train episode 50678: reward = -47.88, steps = 39 12:15:04 [INFO] train episode 50679: reward = -37.67, steps = 26 12:15:07 [INFO] train episode 50680: reward = -25.14, steps = 36 12:15:09 [INFO] train episode 50681: reward = -28.30, steps = 21 12:15:12 [INFO] train episode 50682: reward = -28.14, steps = 41 12:15:16 [INFO] train episode 50683: reward = -61.16, steps = 35 12:15:18 [INFO] train episode 50684: reward = -51.53, steps = 20 12:15:21 [INFO] train episode 50685: reward = -46.08, steps = 33 12:15:23 [INFO] train episode 50686: reward = -34.88, steps = 32 12:15:26 [INFO] train episode 50687: reward = -34.50, steps = 28 12:15:29 [INFO] train episode 50688: reward = -31.49, steps = 39 12:15:31 [INFO] train episode 50689: reward = -42.51, steps = 23 12:15:35 [INFO] train episode 50690: reward = -32.53, steps = 35 12:15:38 [INFO] train episode 50691: reward = -60.51, steps = 40 12:15:41 [INFO] train episode 50692: reward = -59.31, steps = 30 12:15:45 [INFO] train episode 50693: reward = -34.35, steps = 44 12:15:47 [INFO] train episode 50694: reward = -38.69, steps = 23 12:15:50 [INFO] train episode 50695: reward = -28.19, steps = 40 12:15:57 [INFO] train episode 50696: reward = -44.57, steps = 77 12:15:59 [INFO] train episode 50697: reward = -49.43, steps = 27 12:16:03 [INFO] train episode 50698: reward = -37.50, steps = 43 12:16:05 [INFO] train episode 50699: reward = -49.02, steps = 21 12:16:09 [INFO] train episode 50700: reward = -53.59, steps = 43 12:16:13 [INFO] train episode 50701: reward = -73.50, steps = 47 12:16:17 [INFO] train episode 50702: reward = -8.04, steps = 42 12:16:20 [INFO] train episode 50703: reward = -31.53, steps = 34 12:16:24 [INFO] train episode 50704: reward = -22.35, steps = 37 12:16:27 [INFO] train episode 50705: reward = -33.53, steps = 41 12:16:30 [INFO] train episode 50706: reward = -10.27, steps = 31 12:16:32 [INFO] train episode 50707: reward = -32.64, steps = 27 12:16:35 [INFO] train episode 50708: reward = -26.01, steps = 36 12:16:38 [INFO] train episode 50709: reward = -44.57, steps = 23 12:16:41 [INFO] train episode 50710: reward = -32.21, steps = 41 12:16:43 [INFO] train episode 50711: reward = -27.57, steps = 22 12:16:46 [INFO] train episode 50712: reward = -35.70, steps = 30 12:16:50 [INFO] train episode 50713: reward = -59.21, steps = 45 12:16:53 [INFO] train episode 50714: reward = -39.01, steps = 28 12:16:58 [INFO] train episode 50715: reward = -45.97, steps = 57 12:17:01 [INFO] train episode 50716: reward = -36.14, steps = 39 12:17:03 [INFO] train episode 50717: reward = -56.00, steps = 24 12:17:06 [INFO] train episode 50718: reward = -60.03, steps = 29 12:17:08 [INFO] train episode 50719: reward = -22.35, steps = 26 12:17:10 [INFO] train episode 50720: reward = -59.27, steps = 19 12:17:13 [INFO] train episode 50721: reward = -34.56, steps = 33 12:17:16 [INFO] train episode 50722: reward = -50.51, steps = 25 12:17:18 [INFO] train episode 50723: reward = -39.60, steps = 23 12:17:21 [INFO] train episode 50724: reward = -36.65, steps = 25 12:17:22 [INFO] train episode 50725: reward = -32.03, steps = 21 12:17:26 [INFO] train episode 50726: reward = -77.86, steps = 40 12:17:28 [INFO] train episode 50727: reward = -61.47, steps = 23 12:17:32 [INFO] train episode 50728: reward = -17.67, steps = 36 12:17:35 [INFO] train episode 50729: reward = -23.44, steps = 37 12:17:38 [INFO] train episode 50730: reward = -46.10, steps = 33 12:17:41 [INFO] train episode 50731: reward = -18.57, steps = 34 12:17:43 [INFO] train episode 50732: reward = -35.16, steps = 23 12:17:49 [INFO] train episode 50733: reward = -48.23, steps = 73 12:17:51 [INFO] train episode 50734: reward = -56.28, steps = 19 12:17:55 [INFO] train episode 50735: reward = -37.75, steps = 43 12:17:58 [INFO] train episode 50736: reward = -34.10, steps = 37 12:18:02 [INFO] train episode 50737: reward = -32.96, steps = 41 12:18:05 [INFO] train episode 50738: reward = -21.11, steps = 38 12:18:08 [INFO] train episode 50739: reward = -48.27, steps = 33 12:18:11 [INFO] train episode 50740: reward = -56.23, steps = 37 12:18:13 [INFO] train episode 50741: reward = -57.51, steps = 19 12:18:16 [INFO] train episode 50742: reward = -34.23, steps = 34 12:18:21 [INFO] train episode 50743: reward = -92.15, steps = 56 12:18:23 [INFO] train episode 50744: reward = -49.89, steps = 20 12:18:27 [INFO] train episode 50745: reward = -23.96, steps = 43 12:18:28 [INFO] train episode 50746: reward = -65.44, steps = 19 12:18:31 [INFO] train episode 50747: reward = -39.83, steps = 34 12:18:34 [INFO] train episode 50748: reward = -44.66, steps = 30 12:18:36 [INFO] train episode 50749: reward = -54.85, steps = 20 12:18:38 [INFO] train episode 50750: reward = -32.75, steps = 22 12:18:41 [INFO] train episode 50751: reward = -31.83, steps = 35 12:18:45 [INFO] train episode 50752: reward = -35.49, steps = 45 12:18:49 [INFO] train episode 50753: reward = -18.45, steps = 40 12:18:52 [INFO] train episode 50754: reward = -40.49, steps = 36 12:18:56 [INFO] train episode 50755: reward = -32.44, steps = 41 12:19:00 [INFO] train episode 50756: reward = -61.84, steps = 41 12:19:02 [INFO] train episode 50757: reward = -38.73, steps = 28 12:19:05 [INFO] train episode 50758: reward = -22.65, steps = 35 12:19:08 [INFO] train episode 50759: reward = -42.96, steps = 33 12:19:10 [INFO] train episode 50760: reward = -55.99, steps = 20 12:19:13 [INFO] train episode 50761: reward = -54.33, steps = 31 12:19:16 [INFO] train episode 50762: reward = -61.02, steps = 40 12:19:19 [INFO] train episode 50763: reward = -25.50, steps = 33 12:19:23 [INFO] train episode 50764: reward = -61.94, steps = 41 12:19:28 [INFO] train episode 50765: reward = -34.46, steps = 55 12:19:31 [INFO] train episode 50766: reward = -23.53, steps = 32 12:19:33 [INFO] train episode 50767: reward = -47.63, steps = 24 12:19:36 [INFO] train episode 50768: reward = -35.20, steps = 36 12:19:38 [INFO] train episode 50769: reward = -49.50, steps = 27 12:19:42 [INFO] train episode 50770: reward = -59.90, steps = 39 12:19:44 [INFO] train episode 50771: reward = -57.10, steps = 24 12:19:46 [INFO] train episode 50772: reward = -40.84, steps = 25 12:19:48 [INFO] train episode 50773: reward = -49.10, steps = 20 12:19:51 [INFO] train episode 50774: reward = -51.06, steps = 35 12:19:54 [INFO] train episode 50775: reward = -34.58, steps = 28 12:19:57 [INFO] train episode 50776: reward = -35.22, steps = 36 12:20:00 [INFO] train episode 50777: reward = -26.03, steps = 35 12:20:04 [INFO] train episode 50778: reward = -19.87, steps = 36 12:20:06 [INFO] train episode 50779: reward = -57.66, steps = 31 12:20:09 [INFO] train episode 50780: reward = -36.50, steps = 34 12:20:11 [INFO] train episode 50781: reward = -40.21, steps = 20 12:20:15 [INFO] train episode 50782: reward = -57.88, steps = 30 12:20:17 [INFO] train episode 50783: reward = -44.11, steps = 27 12:20:20 [INFO] train episode 50784: reward = -52.22, steps = 32 12:20:22 [INFO] train episode 50785: reward = -23.78, steps = 30 12:20:30 [INFO] train episode 50786: reward = -84.52, steps = 87 12:20:32 [INFO] train episode 50787: reward = -41.13, steps = 21 12:20:36 [INFO] train episode 50788: reward = -41.17, steps = 37 12:20:41 [INFO] train episode 50789: reward = -45.04, steps = 45 12:20:45 [INFO] train episode 50790: reward = -13.99, steps = 41 12:20:47 [INFO] train episode 50791: reward = -68.55, steps = 19 12:20:51 [INFO] train episode 50792: reward = -21.13, steps = 41 12:20:55 [INFO] train episode 50793: reward = -25.45, steps = 38 12:20:58 [INFO] train episode 50794: reward = -42.37, steps = 36 12:21:00 [INFO] train episode 50795: reward = -44.60, steps = 24 12:21:05 [INFO] train episode 50796: reward = -47.75, steps = 49 12:21:07 [INFO] train episode 50797: reward = -40.11, steps = 20 12:21:13 [INFO] train episode 50798: reward = -120.18, steps = 79 12:21:17 [INFO] train episode 50799: reward = -54.56, steps = 38 12:21:20 [INFO] train episode 50800: reward = -18.78, steps = 41 12:21:24 [INFO] train episode 50801: reward = -19.44, steps = 32 12:21:25 [INFO] train episode 50802: reward = -43.61, steps = 19 12:21:29 [INFO] train episode 50803: reward = -8.06, steps = 39 12:21:32 [INFO] train episode 50804: reward = -29.81, steps = 35 12:21:34 [INFO] train episode 50805: reward = -57.76, steps = 27 12:21:37 [INFO] train episode 50806: reward = -58.04, steps = 37 12:21:40 [INFO] train episode 50807: reward = -46.91, steps = 22 12:21:43 [INFO] train episode 50808: reward = -44.85, steps = 35 12:21:45 [INFO] train episode 50809: reward = -26.93, steps = 29 12:21:49 [INFO] train episode 50810: reward = -27.13, steps = 41 12:21:52 [INFO] train episode 50811: reward = -14.38, steps = 42 12:21:55 [INFO] train episode 50812: reward = -59.54, steps = 26 12:21:58 [INFO] train episode 50813: reward = -28.29, steps = 32 12:22:02 [INFO] train episode 50814: reward = -86.22, steps = 43 12:22:04 [INFO] train episode 50815: reward = -33.86, steps = 21 12:22:06 [INFO] train episode 50816: reward = -41.84, steps = 31 12:22:10 [INFO] train episode 50817: reward = -40.61, steps = 37 12:22:12 [INFO] train episode 50818: reward = -38.29, steps = 27 12:22:14 [INFO] train episode 50819: reward = -29.76, steps = 22 12:22:18 [INFO] train episode 50820: reward = -45.27, steps = 41 12:22:22 [INFO] train episode 50821: reward = -28.95, steps = 47 12:22:24 [INFO] train episode 50822: reward = -46.18, steps = 23 12:22:26 [INFO] train episode 50823: reward = -43.54, steps = 22 12:22:29 [INFO] train episode 50824: reward = -27.42, steps = 38 12:22:31 [INFO] train episode 50825: reward = -19.73, steps = 22 12:22:33 [INFO] train episode 50826: reward = -47.00, steps = 20 12:22:36 [INFO] train episode 50827: reward = -28.83, steps = 37 12:22:39 [INFO] train episode 50828: reward = -50.43, steps = 29 12:22:41 [INFO] train episode 50829: reward = -39.31, steps = 23 12:22:44 [INFO] train episode 50830: reward = -74.15, steps = 33 12:22:47 [INFO] train episode 50831: reward = -39.68, steps = 23 12:22:50 [INFO] train episode 50832: reward = -19.36, steps = 39 12:22:53 [INFO] train episode 50833: reward = -62.00, steps = 33 12:22:55 [INFO] train episode 50834: reward = -27.88, steps = 30 12:22:59 [INFO] train episode 50835: reward = -36.76, steps = 41 12:23:03 [INFO] train episode 50836: reward = -23.85, steps = 38 12:23:08 [INFO] train episode 50837: reward = -23.28, steps = 60 12:23:10 [INFO] train episode 50838: reward = -41.31, steps = 27 12:23:14 [INFO] train episode 50839: reward = -37.28, steps = 32 12:23:17 [INFO] train episode 50840: reward = -55.48, steps = 30 12:23:19 [INFO] train episode 50841: reward = -45.13, steps = 31 12:23:22 [INFO] train episode 50842: reward = -36.62, steps = 34 12:23:32 [INFO] train episode 50843: reward = -70.15, steps = 118 12:23:35 [INFO] train episode 50844: reward = -33.75, steps = 23 12:23:38 [INFO] train episode 50845: reward = -13.22, steps = 41 12:23:42 [INFO] train episode 50846: reward = -45.06, steps = 47 12:23:45 [INFO] train episode 50847: reward = -20.44, steps = 28 12:23:47 [INFO] train episode 50848: reward = -45.03, steps = 29 12:23:51 [INFO] train episode 50849: reward = -50.04, steps = 45 12:23:53 [INFO] train episode 50850: reward = -27.89, steps = 21 12:23:55 [INFO] train episode 50851: reward = -45.55, steps = 20 12:23:59 [INFO] train episode 50852: reward = -44.88, steps = 51 12:24:01 [INFO] train episode 50853: reward = -28.12, steps = 23 12:24:04 [INFO] train episode 50854: reward = -37.38, steps = 24 12:24:07 [INFO] train episode 50855: reward = -42.11, steps = 31 12:24:10 [INFO] train episode 50856: reward = -45.55, steps = 39 12:24:13 [INFO] train episode 50857: reward = -17.81, steps = 31 12:24:16 [INFO] train episode 50858: reward = -49.57, steps = 39 12:24:18 [INFO] train episode 50859: reward = -31.88, steps = 22 12:24:20 [INFO] train episode 50860: reward = -40.23, steps = 23 12:24:24 [INFO] train episode 50861: reward = -55.63, steps = 46 12:24:28 [INFO] train episode 50862: reward = -26.51, steps = 36 12:24:31 [INFO] train episode 50863: reward = -26.94, steps = 38 12:24:34 [INFO] train episode 50864: reward = -33.91, steps = 31 12:24:39 [INFO] train episode 50865: reward = -19.33, steps = 49 12:24:42 [INFO] train episode 50866: reward = -27.92, steps = 40 12:24:46 [INFO] train episode 50867: reward = -58.49, steps = 44 12:24:49 [INFO] train episode 50868: reward = -32.74, steps = 32 12:24:51 [INFO] train episode 50869: reward = -52.03, steps = 20 12:24:53 [INFO] train episode 50870: reward = -46.60, steps = 26 12:24:55 [INFO] train episode 50871: reward = -55.70, steps = 22 12:24:58 [INFO] train episode 50872: reward = -20.93, steps = 27 12:25:01 [INFO] train episode 50873: reward = -49.04, steps = 45 12:25:03 [INFO] train episode 50874: reward = -46.55, steps = 22 12:25:06 [INFO] train episode 50875: reward = -46.70, steps = 28 12:25:09 [INFO] train episode 50876: reward = -30.14, steps = 33 12:25:11 [INFO] train episode 50877: reward = -29.82, steps = 26 12:25:16 [INFO] train episode 50878: reward = -59.31, steps = 48 12:25:19 [INFO] train episode 50879: reward = -44.31, steps = 39 12:25:21 [INFO] train episode 50880: reward = -44.93, steps = 29 12:25:25 [INFO] train episode 50881: reward = -35.70, steps = 41 12:25:29 [INFO] train episode 50882: reward = -16.99, steps = 43 12:25:33 [INFO] train episode 50883: reward = -9.30, steps = 41 12:25:35 [INFO] train episode 50884: reward = -38.25, steps = 27 12:25:37 [INFO] train episode 50885: reward = -57.87, steps = 23 12:25:40 [INFO] train episode 50886: reward = -33.85, steps = 33 12:25:43 [INFO] train episode 50887: reward = -52.68, steps = 35 12:25:46 [INFO] train episode 50888: reward = -27.35, steps = 33 12:25:49 [INFO] train episode 50889: reward = -16.99, steps = 29 12:25:52 [INFO] train episode 50890: reward = -40.09, steps = 35 12:25:55 [INFO] train episode 50891: reward = -24.21, steps = 42 12:25:59 [INFO] train episode 50892: reward = -36.37, steps = 45 12:26:02 [INFO] train episode 50893: reward = -86.42, steps = 31 12:26:06 [INFO] train episode 50894: reward = -32.15, steps = 39 12:26:10 [INFO] train episode 50895: reward = -29.36, steps = 37 12:26:12 [INFO] train episode 50896: reward = -24.25, steps = 27 12:26:14 [INFO] train episode 50897: reward = -64.33, steps = 20 12:26:16 [INFO] train episode 50898: reward = -37.76, steps = 27 12:26:19 [INFO] train episode 50899: reward = -36.45, steps = 30 12:26:21 [INFO] train episode 50900: reward = -45.01, steps = 19 12:26:23 [INFO] train episode 50901: reward = -34.73, steps = 30 12:26:26 [INFO] train episode 50902: reward = -51.85, steps = 35 12:26:31 [INFO] train episode 50903: reward = -31.61, steps = 51 12:26:33 [INFO] train episode 50904: reward = -38.35, steps = 20 12:26:35 [INFO] train episode 50905: reward = -38.28, steps = 27 12:26:39 [INFO] train episode 50906: reward = -28.99, steps = 37 12:26:41 [INFO] train episode 50907: reward = -31.94, steps = 27 12:26:44 [INFO] train episode 50908: reward = -25.90, steps = 31 12:26:46 [INFO] train episode 50909: reward = -26.06, steps = 30 12:26:49 [INFO] train episode 50910: reward = -41.45, steps = 25 12:26:52 [INFO] train episode 50911: reward = -10.86, steps = 37 12:26:56 [INFO] train episode 50912: reward = -59.82, steps = 51 12:27:00 [INFO] train episode 50913: reward = -19.32, steps = 36 12:27:02 [INFO] train episode 50914: reward = -24.80, steps = 23 12:27:04 [INFO] train episode 50915: reward = -44.86, steps = 30 12:27:08 [INFO] train episode 50916: reward = -20.14, steps = 34 12:27:10 [INFO] train episode 50917: reward = -20.28, steps = 28 12:27:13 [INFO] train episode 50918: reward = -51.08, steps = 29 12:27:15 [INFO] train episode 50919: reward = -53.63, steps = 23 12:27:17 [INFO] train episode 50920: reward = -29.64, steps = 31 12:27:21 [INFO] train episode 50921: reward = -73.44, steps = 37 12:27:24 [INFO] train episode 50922: reward = -35.97, steps = 31 12:27:26 [INFO] train episode 50923: reward = -29.43, steps = 32 12:27:29 [INFO] train episode 50924: reward = -38.17, steps = 24 12:27:31 [INFO] train episode 50925: reward = -38.54, steps = 23 12:27:32 [INFO] train episode 50926: reward = -24.52, steps = 20 12:27:36 [INFO] train episode 50927: reward = -14.73, steps = 39 12:27:38 [INFO] train episode 50928: reward = -56.64, steps = 23 12:27:42 [INFO] train episode 50929: reward = -37.19, steps = 40 12:27:45 [INFO] train episode 50930: reward = -16.64, steps = 38 12:27:48 [INFO] train episode 50931: reward = -46.89, steps = 37 12:27:51 [INFO] train episode 50932: reward = -74.24, steps = 39 12:27:55 [INFO] train episode 50933: reward = -30.03, steps = 34 12:27:57 [INFO] train episode 50934: reward = -37.98, steps = 20 12:27:59 [INFO] train episode 50935: reward = -63.33, steps = 26 12:28:02 [INFO] train episode 50936: reward = -26.14, steps = 30 12:28:05 [INFO] train episode 50937: reward = -46.89, steps = 30 12:28:07 [INFO] train episode 50938: reward = -55.58, steps = 29 12:28:10 [INFO] train episode 50939: reward = -32.26, steps = 29 12:28:15 [INFO] train episode 50940: reward = 2.38, steps = 53 12:28:19 [INFO] train episode 50941: reward = -54.02, steps = 46 12:28:21 [INFO] train episode 50942: reward = -79.91, steps = 24 12:28:25 [INFO] train episode 50943: reward = -17.84, steps = 42 12:28:30 [INFO] train episode 50944: reward = -33.21, steps = 61 12:28:34 [INFO] train episode 50945: reward = -32.38, steps = 40 12:28:37 [INFO] train episode 50946: reward = -17.39, steps = 33 12:28:40 [INFO] train episode 50947: reward = -54.57, steps = 33 12:28:44 [INFO] train episode 50948: reward = -24.23, steps = 45 12:28:46 [INFO] train episode 50949: reward = -23.45, steps = 25 12:28:50 [INFO] train episode 50950: reward = -21.37, steps = 39 12:28:53 [INFO] train episode 50951: reward = -76.84, steps = 37 12:28:55 [INFO] train episode 50952: reward = -61.57, steps = 26 12:28:59 [INFO] train episode 50953: reward = -35.03, steps = 35 12:29:02 [INFO] train episode 50954: reward = -30.39, steps = 34 12:29:07 [INFO] train episode 50955: reward = -84.62, steps = 42 12:29:11 [INFO] train episode 50956: reward = -44.01, steps = 46 12:29:13 [INFO] train episode 50957: reward = -57.48, steps = 23 12:29:15 [INFO] train episode 50958: reward = -52.07, steps = 22 12:29:18 [INFO] train episode 50959: reward = -21.46, steps = 29 12:29:21 [INFO] train episode 50960: reward = -44.03, steps = 35 12:29:24 [INFO] train episode 50961: reward = -37.36, steps = 30 12:29:27 [INFO] train episode 50962: reward = -36.45, steps = 40 12:29:31 [INFO] train episode 50963: reward = -38.74, steps = 37 12:29:35 [INFO] train episode 50964: reward = -39.20, steps = 42 12:29:38 [INFO] train episode 50965: reward = -60.63, steps = 37 12:29:45 [INFO] train episode 50966: reward = -106.38, steps = 83 12:29:48 [INFO] train episode 50967: reward = -38.42, steps = 32 12:29:54 [INFO] train episode 50968: reward = -65.69, steps = 62 12:29:57 [INFO] train episode 50969: reward = -43.30, steps = 43 12:29:59 [INFO] train episode 50970: reward = -41.60, steps = 21 12:30:03 [INFO] train episode 50971: reward = -52.13, steps = 38 12:30:08 [INFO] train episode 50972: reward = -68.01, steps = 51 12:30:10 [INFO] train episode 50973: reward = -25.53, steps = 31 12:30:14 [INFO] train episode 50974: reward = -41.69, steps = 49 12:30:18 [INFO] train episode 50975: reward = -68.08, steps = 40 12:30:21 [INFO] train episode 50976: reward = -27.92, steps = 31 12:30:24 [INFO] train episode 50977: reward = -33.79, steps = 27 12:30:26 [INFO] train episode 50978: reward = -19.27, steps = 32 12:30:29 [INFO] train episode 50979: reward = -24.38, steps = 26 12:30:31 [INFO] train episode 50980: reward = -31.10, steps = 30 12:30:34 [INFO] train episode 50981: reward = -37.11, steps = 29 12:30:37 [INFO] train episode 50982: reward = -41.35, steps = 38 12:30:42 [INFO] train episode 50983: reward = -20.75, steps = 43 12:30:44 [INFO] train episode 50984: reward = -45.75, steps = 27 12:30:46 [INFO] train episode 50985: reward = -44.83, steps = 22 12:30:48 [INFO] train episode 50986: reward = -34.63, steps = 20 12:30:51 [INFO] train episode 50987: reward = -79.99, steps = 30 12:30:55 [INFO] train episode 50988: reward = -35.80, steps = 41 12:30:58 [INFO] train episode 50989: reward = -30.52, steps = 42 12:31:01 [INFO] train episode 50990: reward = -56.34, steps = 34 12:31:03 [INFO] train episode 50991: reward = -35.39, steps = 21 12:31:05 [INFO] train episode 50992: reward = -52.25, steps = 20 12:31:07 [INFO] train episode 50993: reward = -25.40, steps = 28 12:31:10 [INFO] train episode 50994: reward = -23.92, steps = 33 12:31:14 [INFO] train episode 50995: reward = -73.15, steps = 35 12:31:16 [INFO] train episode 50996: reward = -41.86, steps = 26 12:31:19 [INFO] train episode 50997: reward = -56.70, steps = 30 12:31:22 [INFO] train episode 50998: reward = -13.98, steps = 43 12:31:25 [INFO] train episode 50999: reward = -54.15, steps = 24 12:31:27 [INFO] train episode 51000: reward = -50.62, steps = 23 12:31:30 [INFO] train episode 51001: reward = -50.61, steps = 36 12:31:33 [INFO] train episode 51002: reward = -47.53, steps = 28 12:31:35 [INFO] train episode 51003: reward = -24.77, steps = 27 12:31:38 [INFO] train episode 51004: reward = -27.73, steps = 31 12:31:41 [INFO] train episode 51005: reward = -27.33, steps = 33 12:31:44 [INFO] train episode 51006: reward = -40.26, steps = 31 12:31:46 [INFO] train episode 51007: reward = -26.74, steps = 25 12:31:51 [INFO] train episode 51008: reward = -40.44, steps = 61 12:31:55 [INFO] train episode 51009: reward = -39.65, steps = 43 12:31:59 [INFO] train episode 51010: reward = -34.47, steps = 41 12:32:02 [INFO] train episode 51011: reward = -25.05, steps = 41 12:32:05 [INFO] train episode 51012: reward = -32.27, steps = 21 12:32:07 [INFO] train episode 51013: reward = -26.64, steps = 27 12:32:09 [INFO] train episode 51014: reward = -52.69, steps = 20 12:32:11 [INFO] train episode 51015: reward = -47.26, steps = 27 12:32:15 [INFO] train episode 51016: reward = -31.28, steps = 35 12:32:23 [INFO] train episode 51017: reward = -35.74, steps = 93 12:32:26 [INFO] train episode 51018: reward = -30.92, steps = 30 12:32:30 [INFO] train episode 51019: reward = -56.07, steps = 54 12:32:34 [INFO] train episode 51020: reward = -44.51, steps = 40 12:32:37 [INFO] train episode 51021: reward = -32.29, steps = 30 12:32:40 [INFO] train episode 51022: reward = -45.90, steps = 33 12:32:43 [INFO] train episode 51023: reward = -6.09, steps = 34 12:32:45 [INFO] train episode 51024: reward = -53.11, steps = 23 12:32:47 [INFO] train episode 51025: reward = -71.26, steps = 25 12:32:50 [INFO] train episode 51026: reward = -45.29, steps = 21 12:32:53 [INFO] train episode 51027: reward = -6.39, steps = 40 12:32:55 [INFO] train episode 51028: reward = -42.53, steps = 20 12:32:58 [INFO] train episode 51029: reward = -11.79, steps = 35 12:33:00 [INFO] train episode 51030: reward = -39.52, steps = 28 12:33:02 [INFO] train episode 51031: reward = -40.55, steps = 19 12:33:07 [INFO] train episode 51032: reward = -42.71, steps = 51 12:33:10 [INFO] train episode 51033: reward = -20.05, steps = 36 12:33:13 [INFO] train episode 51034: reward = -43.77, steps = 32 12:33:17 [INFO] train episode 51035: reward = -35.67, steps = 47 12:33:19 [INFO] train episode 51036: reward = -47.90, steps = 24 12:33:23 [INFO] train episode 51037: reward = -56.70, steps = 45 12:33:26 [INFO] train episode 51038: reward = -16.92, steps = 34 12:33:29 [INFO] train episode 51039: reward = -35.70, steps = 28 12:33:32 [INFO] train episode 51040: reward = -52.49, steps = 39 12:33:35 [INFO] train episode 51041: reward = -41.22, steps = 33 12:33:39 [INFO] train episode 51042: reward = -40.52, steps = 43 12:33:42 [INFO] train episode 51043: reward = -26.93, steps = 36 12:33:47 [INFO] train episode 51044: reward = -12.35, steps = 52 12:33:50 [INFO] train episode 51045: reward = -22.78, steps = 32 12:33:54 [INFO] train episode 51046: reward = -34.62, steps = 47 12:33:57 [INFO] train episode 51047: reward = -36.46, steps = 34 12:34:00 [INFO] train episode 51048: reward = -22.23, steps = 35 12:34:04 [INFO] train episode 51049: reward = -35.44, steps = 39 12:34:08 [INFO] train episode 51050: reward = -20.18, steps = 48 12:34:09 [INFO] train episode 51051: reward = -40.72, steps = 19 12:34:14 [INFO] train episode 51052: reward = -21.28, steps = 46 12:34:16 [INFO] train episode 51053: reward = -26.46, steps = 29 12:34:19 [INFO] train episode 51054: reward = -37.02, steps = 25 12:34:21 [INFO] train episode 51055: reward = -46.34, steps = 23 12:34:23 [INFO] train episode 51056: reward = -18.21, steps = 30 12:34:28 [INFO] train episode 51057: reward = -36.44, steps = 56 12:34:32 [INFO] train episode 51058: reward = -20.32, steps = 38 12:34:35 [INFO] train episode 51059: reward = -56.97, steps = 42 12:34:39 [INFO] train episode 51060: reward = -42.06, steps = 35 12:34:42 [INFO] train episode 51061: reward = -35.48, steps = 43 12:34:47 [INFO] train episode 51062: reward = -37.54, steps = 45 12:34:50 [INFO] train episode 51063: reward = -51.40, steps = 37 12:34:52 [INFO] train episode 51064: reward = -58.63, steps = 28 12:34:54 [INFO] train episode 51065: reward = -30.33, steps = 20 12:34:57 [INFO] train episode 51066: reward = -40.44, steps = 30 12:34:59 [INFO] train episode 51067: reward = -49.84, steps = 21 12:35:03 [INFO] train episode 51068: reward = -26.63, steps = 36 12:35:06 [INFO] train episode 51069: reward = -32.56, steps = 38 12:35:10 [INFO] train episode 51070: reward = -27.04, steps = 44 12:35:15 [INFO] train episode 51071: reward = -39.64, steps = 51 12:35:19 [INFO] train episode 51072: reward = -27.63, steps = 42 12:35:21 [INFO] train episode 51073: reward = -43.21, steps = 21 12:35:23 [INFO] train episode 51074: reward = -8.23, steps = 32 12:35:26 [INFO] train episode 51075: reward = -32.62, steps = 31 12:35:29 [INFO] train episode 51076: reward = -45.59, steps = 31 12:35:31 [INFO] train episode 51077: reward = -35.92, steps = 21 12:35:33 [INFO] train episode 51078: reward = -42.71, steps = 21 12:35:36 [INFO] train episode 51079: reward = -24.61, steps = 31 12:35:39 [INFO] train episode 51080: reward = -38.61, steps = 32 12:35:41 [INFO] train episode 51081: reward = -30.76, steps = 31 12:35:46 [INFO] train episode 51082: reward = -55.15, steps = 55 12:35:49 [INFO] train episode 51083: reward = -36.07, steps = 31 12:35:51 [INFO] train episode 51084: reward = -35.84, steps = 22 12:35:54 [INFO] train episode 51085: reward = -32.75, steps = 31 12:35:58 [INFO] train episode 51086: reward = -45.00, steps = 49 12:36:00 [INFO] train episode 51087: reward = -50.66, steps = 25 12:36:03 [INFO] train episode 51088: reward = -32.61, steps = 34 12:36:06 [INFO] train episode 51089: reward = -40.24, steps = 29 12:36:08 [INFO] train episode 51090: reward = -56.55, steps = 25 12:36:10 [INFO] train episode 51091: reward = -41.27, steps = 21 12:36:13 [INFO] train episode 51092: reward = -47.88, steps = 31 12:36:22 [INFO] train episode 51093: reward = -110.96, steps = 111 12:36:26 [INFO] train episode 51094: reward = -56.60, steps = 37 12:36:28 [INFO] train episode 51095: reward = -40.44, steps = 21 12:36:30 [INFO] train episode 51096: reward = -33.55, steps = 28 12:36:34 [INFO] train episode 51097: reward = -51.58, steps = 46 12:36:37 [INFO] train episode 51098: reward = -22.87, steps = 33 12:36:41 [INFO] train episode 51099: reward = -24.69, steps = 38 12:36:43 [INFO] train episode 51100: reward = -29.44, steps = 23 12:36:47 [INFO] train episode 51101: reward = -56.45, steps = 39 12:36:50 [INFO] train episode 51102: reward = -40.92, steps = 33 12:36:52 [INFO] train episode 51103: reward = -53.68, steps = 27 12:36:54 [INFO] train episode 51104: reward = -68.14, steps = 20 12:36:57 [INFO] train episode 51105: reward = -41.96, steps = 38 12:37:00 [INFO] train episode 51106: reward = -42.37, steps = 33 12:37:03 [INFO] train episode 51107: reward = -28.59, steps = 27 12:37:07 [INFO] train episode 51108: reward = -32.18, steps = 49 12:37:09 [INFO] train episode 51109: reward = -32.81, steps = 27 12:37:11 [INFO] train episode 51110: reward = -40.61, steps = 24 12:37:15 [INFO] train episode 51111: reward = -18.94, steps = 31 12:37:18 [INFO] train episode 51112: reward = -48.93, steps = 43 12:37:22 [INFO] train episode 51113: reward = -49.18, steps = 38 12:37:24 [INFO] train episode 51114: reward = -13.20, steps = 29 12:37:27 [INFO] train episode 51115: reward = -51.92, steps = 29 12:37:29 [INFO] train episode 51116: reward = -36.86, steps = 25 12:37:32 [INFO] train episode 51117: reward = -54.40, steps = 26 12:37:34 [INFO] train episode 51118: reward = -39.29, steps = 31 12:37:36 [INFO] train episode 51119: reward = -29.24, steps = 24 12:37:39 [INFO] train episode 51120: reward = -34.30, steps = 30 12:37:42 [INFO] train episode 51121: reward = -44.72, steps = 36 12:37:45 [INFO] train episode 51122: reward = -28.93, steps = 28 12:37:47 [INFO] train episode 51123: reward = -63.85, steps = 27 12:37:50 [INFO] train episode 51124: reward = -37.84, steps = 27 12:37:53 [INFO] train episode 51125: reward = -37.14, steps = 34 12:37:54 [INFO] train episode 51126: reward = -41.83, steps = 21 12:37:58 [INFO] train episode 51127: reward = -57.60, steps = 29 12:38:02 [INFO] train episode 51128: reward = -19.28, steps = 40 12:38:05 [INFO] train episode 51129: reward = -63.32, steps = 38 12:38:09 [INFO] train episode 51130: reward = -21.76, steps = 46 12:38:12 [INFO] train episode 51131: reward = -39.73, steps = 31 12:38:17 [INFO] train episode 51132: reward = -29.91, steps = 60 12:38:20 [INFO] train episode 51133: reward = -53.43, steps = 38 12:38:25 [INFO] train episode 51134: reward = -43.17, steps = 49 12:38:27 [INFO] train episode 51135: reward = -40.12, steps = 24 12:38:29 [INFO] train episode 51136: reward = -46.50, steps = 25 12:38:32 [INFO] train episode 51137: reward = -38.10, steps = 32 12:38:35 [INFO] train episode 51138: reward = -24.10, steps = 32 12:38:38 [INFO] train episode 51139: reward = -18.57, steps = 31 12:38:42 [INFO] train episode 51140: reward = -35.43, steps = 42 12:38:45 [INFO] train episode 51141: reward = -34.22, steps = 42 12:38:48 [INFO] train episode 51142: reward = -27.76, steps = 24 12:38:49 [INFO] train episode 51143: reward = -45.57, steps = 20 12:38:54 [INFO] train episode 51144: reward = -34.59, steps = 51 12:38:56 [INFO] train episode 51145: reward = -50.03, steps = 21 12:38:58 [INFO] train episode 51146: reward = -15.62, steps = 25 12:39:00 [INFO] train episode 51147: reward = -33.88, steps = 23 12:39:02 [INFO] train episode 51148: reward = -48.33, steps = 23 12:39:05 [INFO] train episode 51149: reward = -33.16, steps = 29 12:39:08 [INFO] train episode 51150: reward = -31.28, steps = 36 12:39:11 [INFO] train episode 51151: reward = -39.97, steps = 37 12:39:14 [INFO] train episode 51152: reward = -39.89, steps = 29 12:39:17 [INFO] train episode 51153: reward = -33.50, steps = 29 12:39:19 [INFO] train episode 51154: reward = -32.17, steps = 28 12:39:21 [INFO] train episode 51155: reward = -41.86, steps = 20 12:39:24 [INFO] train episode 51156: reward = -37.29, steps = 30 12:39:27 [INFO] train episode 51157: reward = -24.77, steps = 35 12:39:30 [INFO] train episode 51158: reward = -14.85, steps = 37 12:39:33 [INFO] train episode 51159: reward = -68.66, steps = 33 12:39:36 [INFO] train episode 51160: reward = -21.38, steps = 39 12:39:39 [INFO] train episode 51161: reward = -57.04, steps = 26 12:39:43 [INFO] train episode 51162: reward = -14.05, steps = 45 12:39:46 [INFO] train episode 51163: reward = -21.57, steps = 35 12:39:48 [INFO] train episode 51164: reward = -45.63, steps = 20 12:39:51 [INFO] train episode 51165: reward = -21.39, steps = 35 12:39:54 [INFO] train episode 51166: reward = -35.55, steps = 40 12:39:57 [INFO] train episode 51167: reward = -31.90, steps = 26 12:39:59 [INFO] train episode 51168: reward = -37.99, steps = 22 12:40:01 [INFO] train episode 51169: reward = -14.16, steps = 29 12:40:04 [INFO] train episode 51170: reward = -51.49, steps = 34 12:40:08 [INFO] train episode 51171: reward = -25.86, steps = 38 12:40:10 [INFO] train episode 51172: reward = -57.42, steps = 22 12:40:13 [INFO] train episode 51173: reward = -28.93, steps = 41 12:40:17 [INFO] train episode 51174: reward = -30.70, steps = 41 12:40:20 [INFO] train episode 51175: reward = -23.24, steps = 33 12:40:23 [INFO] train episode 51176: reward = -11.97, steps = 36 12:40:26 [INFO] train episode 51177: reward = -8.49, steps = 38 12:40:33 [INFO] train episode 51178: reward = -58.48, steps = 69 12:40:35 [INFO] train episode 51179: reward = -44.97, steps = 29 12:40:39 [INFO] train episode 51180: reward = -73.92, steps = 40 12:40:42 [INFO] train episode 51181: reward = -20.97, steps = 32 12:40:44 [INFO] train episode 51182: reward = -37.40, steps = 29 12:40:47 [INFO] train episode 51183: reward = -28.10, steps = 32 12:40:50 [INFO] train episode 51184: reward = -16.17, steps = 34 12:40:54 [INFO] train episode 51185: reward = -44.21, steps = 32 12:40:57 [INFO] train episode 51186: reward = -48.24, steps = 38 12:41:01 [INFO] train episode 51187: reward = -39.79, steps = 50 12:41:04 [INFO] train episode 51188: reward = -26.59, steps = 25 12:41:08 [INFO] train episode 51189: reward = -7.30, steps = 47 12:41:11 [INFO] train episode 51190: reward = -25.24, steps = 28 12:41:13 [INFO] train episode 51191: reward = -10.56, steps = 32 12:41:17 [INFO] train episode 51192: reward = -14.87, steps = 44 12:41:20 [INFO] train episode 51193: reward = -28.25, steps = 33 12:41:22 [INFO] train episode 51194: reward = -33.86, steps = 24 12:41:24 [INFO] train episode 51195: reward = -34.13, steps = 20 12:41:27 [INFO] train episode 51196: reward = -55.72, steps = 32 12:41:30 [INFO] train episode 51197: reward = -28.96, steps = 32 12:41:32 [INFO] train episode 51198: reward = -36.08, steps = 26 12:41:36 [INFO] train episode 51199: reward = -12.37, steps = 38 12:41:38 [INFO] train episode 51200: reward = -43.40, steps = 21 12:41:42 [INFO] train episode 51201: reward = -52.84, steps = 47 12:41:44 [INFO] train episode 51202: reward = -68.06, steps = 25 12:41:48 [INFO] train episode 51203: reward = -31.33, steps = 41 12:41:50 [INFO] train episode 51204: reward = -26.63, steps = 33 12:41:53 [INFO] train episode 51205: reward = -20.76, steps = 20 12:41:54 [INFO] train episode 51206: reward = -31.77, steps = 21 12:41:56 [INFO] train episode 51207: reward = -35.29, steps = 20 12:41:59 [INFO] train episode 51208: reward = -25.54, steps = 29 12:42:01 [INFO] train episode 51209: reward = -35.69, steps = 29 12:42:04 [INFO] train episode 51210: reward = -35.38, steps = 34 12:42:06 [INFO] train episode 51211: reward = -49.69, steps = 21 12:42:10 [INFO] train episode 51212: reward = -59.10, steps = 39 12:42:13 [INFO] train episode 51213: reward = -22.38, steps = 33 12:42:16 [INFO] train episode 51214: reward = -33.87, steps = 35 12:42:19 [INFO] train episode 51215: reward = -27.04, steps = 27 12:42:22 [INFO] train episode 51216: reward = -66.70, steps = 45 12:42:25 [INFO] train episode 51217: reward = -30.03, steps = 21 12:42:28 [INFO] train episode 51218: reward = -23.11, steps = 38 12:42:30 [INFO] train episode 51219: reward = -32.89, steps = 25 12:42:33 [INFO] train episode 51220: reward = -25.40, steps = 30 12:42:35 [INFO] train episode 51221: reward = -34.68, steps = 26 12:42:39 [INFO] train episode 51222: reward = -36.28, steps = 37 12:42:42 [INFO] train episode 51223: reward = -32.46, steps = 39 12:42:46 [INFO] train episode 51224: reward = -35.81, steps = 37 12:42:48 [INFO] train episode 51225: reward = -23.91, steps = 26 12:42:50 [INFO] train episode 51226: reward = -40.68, steps = 21 12:42:53 [INFO] train episode 51227: reward = -24.01, steps = 33 12:42:56 [INFO] train episode 51228: reward = -17.36, steps = 34 12:42:59 [INFO] train episode 51229: reward = -39.67, steps = 24 12:43:02 [INFO] train episode 51230: reward = -8.95, steps = 35 12:43:05 [INFO] train episode 51231: reward = -22.81, steps = 33 12:43:07 [INFO] train episode 51232: reward = -23.65, steps = 26 12:43:09 [INFO] train episode 51233: reward = -51.53, steps = 20 12:43:11 [INFO] train episode 51234: reward = -38.27, steps = 22 12:43:15 [INFO] train episode 51235: reward = -23.77, steps = 42 12:43:18 [INFO] train episode 51236: reward = -34.81, steps = 33 12:43:20 [INFO] train episode 51237: reward = -47.52, steps = 23 12:43:23 [INFO] train episode 51238: reward = -35.71, steps = 26 12:43:25 [INFO] train episode 51239: reward = -39.40, steps = 28 12:43:28 [INFO] train episode 51240: reward = -48.25, steps = 29 12:43:30 [INFO] train episode 51241: reward = -60.68, steps = 27 12:43:33 [INFO] train episode 51242: reward = -41.72, steps = 25 12:43:35 [INFO] train episode 51243: reward = -44.41, steps = 25 12:43:37 [INFO] train episode 51244: reward = -38.78, steps = 24 12:43:40 [INFO] train episode 51245: reward = -52.12, steps = 34 12:43:42 [INFO] train episode 51246: reward = -34.90, steps = 25 12:43:45 [INFO] train episode 51247: reward = -41.15, steps = 35 12:43:48 [INFO] train episode 51248: reward = -52.60, steps = 22 12:43:51 [INFO] train episode 51249: reward = -51.16, steps = 27 12:43:55 [INFO] train episode 51250: reward = -76.12, steps = 48 12:43:57 [INFO] train episode 51251: reward = -23.63, steps = 21 12:44:01 [INFO] train episode 51252: reward = -34.72, steps = 51 12:44:06 [INFO] train episode 51253: reward = -33.92, steps = 45 12:44:08 [INFO] train episode 51254: reward = -40.97, steps = 32 12:44:13 [INFO] train episode 51255: reward = -59.70, steps = 50 12:44:17 [INFO] train episode 51256: reward = -68.94, steps = 43 12:44:20 [INFO] train episode 51257: reward = -47.96, steps = 36 12:44:23 [INFO] train episode 51258: reward = -33.03, steps = 37 12:44:26 [INFO] train episode 51259: reward = -30.99, steps = 35 12:44:28 [INFO] train episode 51260: reward = -46.34, steps = 21 12:44:31 [INFO] train episode 51261: reward = -36.61, steps = 32 12:44:34 [INFO] train episode 51262: reward = -22.59, steps = 39 12:44:39 [INFO] train episode 51263: reward = -47.27, steps = 50 12:44:42 [INFO] train episode 51264: reward = -37.29, steps = 27 12:44:46 [INFO] train episode 51265: reward = -34.65, steps = 52 12:44:49 [INFO] train episode 51266: reward = -20.85, steps = 35 12:44:52 [INFO] train episode 51267: reward = -40.94, steps = 32 12:44:55 [INFO] train episode 51268: reward = -31.80, steps = 35 12:44:57 [INFO] train episode 51269: reward = -50.85, steps = 24 12:45:01 [INFO] train episode 51270: reward = -105.18, steps = 43 12:45:05 [INFO] train episode 51271: reward = -24.73, steps = 42 12:45:08 [INFO] train episode 51272: reward = -51.74, steps = 37 12:45:11 [INFO] train episode 51273: reward = -65.16, steps = 30 12:45:13 [INFO] train episode 51274: reward = -32.55, steps = 28 12:45:16 [INFO] train episode 51275: reward = -47.18, steps = 24 12:45:18 [INFO] train episode 51276: reward = -16.83, steps = 32 12:45:22 [INFO] train episode 51277: reward = -24.16, steps = 42 12:45:25 [INFO] train episode 51278: reward = -37.77, steps = 30 12:45:28 [INFO] train episode 51279: reward = -39.70, steps = 32 12:45:32 [INFO] train episode 51280: reward = -23.61, steps = 47 12:45:34 [INFO] train episode 51281: reward = -54.99, steps = 21 12:45:36 [INFO] train episode 51282: reward = -27.49, steps = 29 12:45:40 [INFO] train episode 51283: reward = -29.96, steps = 41 12:45:42 [INFO] train episode 51284: reward = -36.34, steps = 26 12:45:46 [INFO] train episode 51285: reward = -41.00, steps = 44 12:45:48 [INFO] train episode 51286: reward = -32.42, steps = 22 12:45:50 [INFO] train episode 51287: reward = -44.29, steps = 20 12:45:52 [INFO] train episode 51288: reward = -56.29, steps = 23 12:45:55 [INFO] train episode 51289: reward = -19.18, steps = 35 12:45:58 [INFO] train episode 51290: reward = -39.69, steps = 24 12:46:01 [INFO] train episode 51291: reward = -13.96, steps = 43 12:46:04 [INFO] train episode 51292: reward = -41.26, steps = 29 12:46:06 [INFO] train episode 51293: reward = -45.28, steps = 30 12:46:08 [INFO] train episode 51294: reward = -46.18, steps = 20 12:46:11 [INFO] train episode 51295: reward = -21.78, steps = 39 12:46:18 [INFO] train episode 51296: reward = -74.54, steps = 67 12:46:20 [INFO] train episode 51297: reward = -35.08, steps = 23 12:46:23 [INFO] train episode 51298: reward = -59.88, steps = 33 12:46:27 [INFO] train episode 51299: reward = -3.10, steps = 51 12:46:31 [INFO] train episode 51300: reward = -24.20, steps = 37 12:46:33 [INFO] train episode 51301: reward = -22.37, steps = 28 12:46:37 [INFO] train episode 51302: reward = -23.52, steps = 39 12:46:40 [INFO] train episode 51303: reward = -36.88, steps = 37 12:46:42 [INFO] train episode 51304: reward = -46.33, steps = 20 12:46:45 [INFO] train episode 51305: reward = -49.98, steps = 31 12:46:48 [INFO] train episode 51306: reward = -14.44, steps = 34 12:46:50 [INFO] train episode 51307: reward = -41.53, steps = 21 12:46:53 [INFO] train episode 51308: reward = -37.03, steps = 27 12:46:55 [INFO] train episode 51309: reward = -15.33, steps = 30 12:46:57 [INFO] train episode 51310: reward = -31.22, steps = 23 12:47:01 [INFO] train episode 51311: reward = -22.89, steps = 38 12:47:04 [INFO] train episode 51312: reward = -39.83, steps = 36 12:47:07 [INFO] train episode 51313: reward = -37.74, steps = 35 12:47:10 [INFO] train episode 51314: reward = -40.77, steps = 35 12:47:14 [INFO] train episode 51315: reward = -26.76, steps = 44 12:47:16 [INFO] train episode 51316: reward = -60.35, steps = 20 12:47:18 [INFO] train episode 51317: reward = -32.69, steps = 31 12:47:23 [INFO] train episode 51318: reward = -24.60, steps = 46 12:47:26 [INFO] train episode 51319: reward = -18.61, steps = 36 12:47:29 [INFO] train episode 51320: reward = -15.10, steps = 35 12:47:32 [INFO] train episode 51321: reward = -79.20, steps = 40 12:47:35 [INFO] train episode 51322: reward = -24.59, steps = 36 12:47:38 [INFO] train episode 51323: reward = -22.94, steps = 22 12:47:41 [INFO] train episode 51324: reward = -34.40, steps = 34 12:47:44 [INFO] train episode 51325: reward = -40.73, steps = 37 12:47:47 [INFO] train episode 51326: reward = -13.17, steps = 37 12:47:54 [INFO] train episode 51327: reward = -13.51, steps = 72 12:47:56 [INFO] train episode 51328: reward = -26.42, steps = 23 12:47:57 [INFO] train episode 51329: reward = -48.60, steps = 20 12:47:59 [INFO] train episode 51330: reward = -22.42, steps = 20 12:48:02 [INFO] train episode 51331: reward = -33.48, steps = 27 12:48:04 [INFO] train episode 51332: reward = -48.20, steps = 32 12:48:07 [INFO] train episode 51333: reward = -16.71, steps = 27 12:48:10 [INFO] train episode 51334: reward = -36.63, steps = 28 12:48:13 [INFO] train episode 51335: reward = -42.71, steps = 35 12:48:15 [INFO] train episode 51336: reward = -11.66, steps = 34 12:48:19 [INFO] train episode 51337: reward = -29.66, steps = 46 12:48:23 [INFO] train episode 51338: reward = -24.09, steps = 37 12:48:26 [INFO] train episode 51339: reward = -22.98, steps = 33 12:48:29 [INFO] train episode 51340: reward = -49.75, steps = 39 12:48:31 [INFO] train episode 51341: reward = -56.07, steps = 25 12:48:34 [INFO] train episode 51342: reward = -33.14, steps = 26 12:48:36 [INFO] train episode 51343: reward = -36.03, steps = 26 12:48:39 [INFO] train episode 51344: reward = -55.69, steps = 30 12:48:42 [INFO] train episode 51345: reward = -26.23, steps = 30 12:48:44 [INFO] train episode 51346: reward = -35.43, steps = 23 12:48:47 [INFO] train episode 51347: reward = -55.33, steps = 32 12:48:49 [INFO] train episode 51348: reward = -45.66, steps = 29 12:48:52 [INFO] train episode 51349: reward = -21.70, steps = 34 12:48:55 [INFO] train episode 51350: reward = -9.40, steps = 33 12:48:58 [INFO] train episode 51351: reward = -17.48, steps = 32 12:49:01 [INFO] train episode 51352: reward = -17.20, steps = 32 12:49:03 [INFO] train episode 51353: reward = -52.91, steps = 23 12:49:06 [INFO] train episode 51354: reward = -45.82, steps = 30 12:49:08 [INFO] train episode 51355: reward = -38.56, steps = 27 12:49:12 [INFO] train episode 51356: reward = -32.78, steps = 40 12:49:15 [INFO] train episode 51357: reward = -38.93, steps = 34 12:49:21 [INFO] train episode 51358: reward = -86.28, steps = 69 12:49:24 [INFO] train episode 51359: reward = -33.47, steps = 30 12:49:27 [INFO] train episode 51360: reward = -41.31, steps = 37 12:49:29 [INFO] train episode 51361: reward = -45.71, steps = 19 12:49:32 [INFO] train episode 51362: reward = -23.71, steps = 28 12:49:35 [INFO] train episode 51363: reward = -17.99, steps = 44 12:49:40 [INFO] train episode 51364: reward = -22.87, steps = 42 12:49:43 [INFO] train episode 51365: reward = -46.77, steps = 37 12:49:46 [INFO] train episode 51366: reward = -36.56, steps = 39 12:49:49 [INFO] train episode 51367: reward = -16.39, steps = 27 12:49:53 [INFO] train episode 51368: reward = -27.34, steps = 43 12:49:55 [INFO] train episode 51369: reward = -37.32, steps = 30 12:49:57 [INFO] train episode 51370: reward = -38.57, steps = 20 12:49:59 [INFO] train episode 51371: reward = -43.16, steps = 25 12:50:04 [INFO] train episode 51372: reward = -25.79, steps = 41 12:50:09 [INFO] train episode 51373: reward = -64.26, steps = 59 12:50:13 [INFO] train episode 51374: reward = -25.33, steps = 47 12:50:16 [INFO] train episode 51375: reward = -29.69, steps = 36 12:50:20 [INFO] train episode 51376: reward = -26.04, steps = 43 12:50:22 [INFO] train episode 51377: reward = -54.89, steps = 25 12:50:26 [INFO] train episode 51378: reward = -6.77, steps = 44 12:50:28 [INFO] train episode 51379: reward = -36.17, steps = 26 12:50:30 [INFO] train episode 51380: reward = -47.39, steps = 22 12:50:33 [INFO] train episode 51381: reward = -34.21, steps = 29 12:50:36 [INFO] train episode 51382: reward = -38.93, steps = 32 12:50:39 [INFO] train episode 51383: reward = -27.21, steps = 38 12:50:42 [INFO] train episode 51384: reward = -32.88, steps = 30 12:50:45 [INFO] train episode 51385: reward = -41.61, steps = 30 12:50:48 [INFO] train episode 51386: reward = -17.63, steps = 37 12:50:52 [INFO] train episode 51387: reward = -32.90, steps = 44 12:50:55 [INFO] train episode 51388: reward = -23.53, steps = 26 12:50:58 [INFO] train episode 51389: reward = -19.35, steps = 38 12:51:01 [INFO] train episode 51390: reward = -31.34, steps = 39 12:51:04 [INFO] train episode 51391: reward = -0.31, steps = 36 12:51:08 [INFO] train episode 51392: reward = -40.66, steps = 37 12:51:10 [INFO] train episode 51393: reward = -20.21, steps = 21 12:51:12 [INFO] train episode 51394: reward = -55.42, steps = 22 12:51:14 [INFO] train episode 51395: reward = -51.52, steps = 26 12:51:17 [INFO] train episode 51396: reward = -56.34, steps = 27 12:51:19 [INFO] train episode 51397: reward = -46.87, steps = 31 12:51:22 [INFO] train episode 51398: reward = -45.83, steps = 26 12:51:25 [INFO] train episode 51399: reward = -44.93, steps = 36 12:51:28 [INFO] train episode 51400: reward = -40.10, steps = 31 12:51:31 [INFO] train episode 51401: reward = -19.90, steps = 35 12:51:34 [INFO] train episode 51402: reward = -35.68, steps = 38 12:51:37 [INFO] train episode 51403: reward = -39.73, steps = 29 12:51:39 [INFO] train episode 51404: reward = -42.39, steps = 25 12:51:42 [INFO] train episode 51405: reward = -26.05, steps = 35 12:51:44 [INFO] train episode 51406: reward = -44.71, steps = 21 12:51:46 [INFO] train episode 51407: reward = -49.56, steps = 24 12:51:49 [INFO] train episode 51408: reward = -48.93, steps = 37 12:51:52 [INFO] train episode 51409: reward = -23.81, steps = 33 12:51:55 [INFO] train episode 51410: reward = -33.56, steps = 34 12:51:58 [INFO] train episode 51411: reward = -34.03, steps = 24 12:52:02 [INFO] train episode 51412: reward = -82.04, steps = 52 12:52:05 [INFO] train episode 51413: reward = -43.05, steps = 27 12:52:08 [INFO] train episode 51414: reward = -41.69, steps = 36 12:52:11 [INFO] train episode 51415: reward = -1.21, steps = 37 12:52:14 [INFO] train episode 51416: reward = -35.88, steps = 29 12:52:16 [INFO] train episode 51417: reward = -56.68, steps = 28 12:52:21 [INFO] train episode 51418: reward = -49.00, steps = 48 12:52:24 [INFO] train episode 51419: reward = -47.60, steps = 35 12:52:27 [INFO] train episode 51420: reward = -13.35, steps = 33 12:52:29 [INFO] train episode 51421: reward = -40.42, steps = 27 12:52:33 [INFO] train episode 51422: reward = -20.70, steps = 37 12:52:38 [INFO] train episode 51423: reward = -38.76, steps = 43 12:52:42 [INFO] train episode 51424: reward = -32.75, steps = 48 12:52:44 [INFO] train episode 51425: reward = -32.45, steps = 21 12:52:47 [INFO] train episode 51426: reward = -26.79, steps = 33 12:52:49 [INFO] train episode 51427: reward = -32.79, steps = 23 12:52:52 [INFO] train episode 51428: reward = -31.76, steps = 35 12:52:54 [INFO] train episode 51429: reward = -53.15, steps = 21 12:52:56 [INFO] train episode 51430: reward = -30.92, steps = 29 12:52:59 [INFO] train episode 51431: reward = -15.61, steps = 31 12:53:02 [INFO] train episode 51432: reward = -63.84, steps = 33 12:53:04 [INFO] train episode 51433: reward = -35.25, steps = 21 12:53:07 [INFO] train episode 51434: reward = -46.96, steps = 25 12:53:09 [INFO] train episode 51435: reward = -30.59, steps = 29 12:53:11 [INFO] train episode 51436: reward = -39.79, steps = 20 12:53:14 [INFO] train episode 51437: reward = -28.38, steps = 37 12:53:18 [INFO] train episode 51438: reward = -17.34, steps = 44 12:53:21 [INFO] train episode 51439: reward = -35.77, steps = 31 12:53:23 [INFO] train episode 51440: reward = -42.70, steps = 22 12:53:25 [INFO] train episode 51441: reward = -43.36, steps = 24 12:53:27 [INFO] train episode 51442: reward = -48.59, steps = 22 12:53:32 [INFO] train episode 51443: reward = -25.12, steps = 52 12:53:36 [INFO] train episode 51444: reward = -31.18, steps = 50 12:53:39 [INFO] train episode 51445: reward = -32.98, steps = 26 12:53:43 [INFO] train episode 51446: reward = -17.70, steps = 48 12:53:45 [INFO] train episode 51447: reward = -38.04, steps = 27 12:53:48 [INFO] train episode 51448: reward = -31.16, steps = 32 12:53:52 [INFO] train episode 51449: reward = -39.40, steps = 50 12:53:56 [INFO] train episode 51450: reward = -19.64, steps = 31 12:53:58 [INFO] train episode 51451: reward = -70.87, steps = 24 12:54:01 [INFO] train episode 51452: reward = -21.51, steps = 42 12:54:03 [INFO] train episode 51453: reward = -34.81, steps = 20 12:54:07 [INFO] train episode 51454: reward = -22.56, steps = 38 12:54:08 [INFO] train episode 51455: reward = -42.75, steps = 20 12:54:12 [INFO] train episode 51456: reward = -13.24, steps = 41 12:54:15 [INFO] train episode 51457: reward = -28.55, steps = 27 12:54:17 [INFO] train episode 51458: reward = -50.64, steps = 31 12:54:20 [INFO] train episode 51459: reward = -34.22, steps = 28 12:54:23 [INFO] train episode 51460: reward = -33.31, steps = 41 12:54:25 [INFO] train episode 51461: reward = -31.82, steps = 21 12:54:29 [INFO] train episode 51462: reward = -15.75, steps = 38 12:54:31 [INFO] train episode 51463: reward = -39.19, steps = 25 12:54:35 [INFO] train episode 51464: reward = 0.30, steps = 40 12:54:38 [INFO] train episode 51465: reward = -17.20, steps = 35 12:54:41 [INFO] train episode 51466: reward = -7.98, steps = 33 12:54:45 [INFO] train episode 51467: reward = -19.15, steps = 41 12:54:49 [INFO] train episode 51468: reward = -44.05, steps = 43 12:54:52 [INFO] train episode 51469: reward = -12.87, steps = 38 12:54:54 [INFO] train episode 51470: reward = -47.33, steps = 21 12:54:57 [INFO] train episode 51471: reward = -40.91, steps = 36 12:55:00 [INFO] train episode 51472: reward = -60.87, steps = 31 12:55:04 [INFO] train episode 51473: reward = -27.26, steps = 41 12:55:08 [INFO] train episode 51474: reward = -63.10, steps = 48 12:55:11 [INFO] train episode 51475: reward = -29.40, steps = 33 12:55:13 [INFO] train episode 51476: reward = -65.48, steps = 22 12:55:16 [INFO] train episode 51477: reward = -29.66, steps = 31 12:55:22 [INFO] train episode 51478: reward = -78.77, steps = 69 12:55:24 [INFO] train episode 51479: reward = -26.75, steps = 31 12:55:28 [INFO] train episode 51480: reward = -25.26, steps = 44 12:55:30 [INFO] train episode 51481: reward = -46.36, steps = 20 12:55:34 [INFO] train episode 51482: reward = -53.91, steps = 32 12:55:38 [INFO] train episode 51483: reward = -22.31, steps = 47 12:55:42 [INFO] train episode 51484: reward = -78.48, steps = 49 12:55:44 [INFO] train episode 51485: reward = -42.69, steps = 23 12:55:48 [INFO] train episode 51486: reward = -13.28, steps = 42 12:55:52 [INFO] train episode 51487: reward = -56.96, steps = 38 12:55:55 [INFO] train episode 51488: reward = -19.08, steps = 37 12:55:58 [INFO] train episode 51489: reward = -24.30, steps = 34 12:56:01 [INFO] train episode 51490: reward = -17.73, steps = 33 12:56:03 [INFO] train episode 51491: reward = -44.05, steps = 31 12:56:06 [INFO] train episode 51492: reward = -30.91, steps = 26 12:56:09 [INFO] train episode 51493: reward = -15.52, steps = 33 12:56:11 [INFO] train episode 51494: reward = -30.71, steps = 28 12:56:14 [INFO] train episode 51495: reward = -43.96, steps = 32 12:56:17 [INFO] train episode 51496: reward = -31.97, steps = 32 12:56:21 [INFO] train episode 51497: reward = -34.00, steps = 45 12:56:23 [INFO] train episode 51498: reward = -55.54, steps = 24 12:56:26 [INFO] train episode 51499: reward = -18.25, steps = 34 12:56:29 [INFO] train episode 51500: reward = -44.15, steps = 32 12:56:32 [INFO] train episode 51501: reward = -18.40, steps = 35 12:56:35 [INFO] train episode 51502: reward = -31.54, steps = 36 12:56:38 [INFO] train episode 51503: reward = -22.92, steps = 28 12:56:42 [INFO] train episode 51504: reward = -45.09, steps = 36 12:56:44 [INFO] train episode 51505: reward = -19.82, steps = 32 12:56:48 [INFO] train episode 51506: reward = -20.97, steps = 43 12:56:50 [INFO] train episode 51507: reward = -29.81, steps = 23 12:56:53 [INFO] train episode 51508: reward = -18.27, steps = 34 12:56:56 [INFO] train episode 51509: reward = -27.58, steps = 33 12:56:59 [INFO] train episode 51510: reward = -47.80, steps = 25 12:57:02 [INFO] train episode 51511: reward = -47.36, steps = 39 12:57:05 [INFO] train episode 51512: reward = -29.29, steps = 38 12:57:09 [INFO] train episode 51513: reward = -18.17, steps = 40 12:57:12 [INFO] train episode 51514: reward = -27.77, steps = 26 12:57:15 [INFO] train episode 51515: reward = -17.33, steps = 36 12:57:17 [INFO] train episode 51516: reward = -75.48, steps = 24 12:57:20 [INFO] train episode 51517: reward = -36.21, steps = 36 12:57:24 [INFO] train episode 51518: reward = -55.15, steps = 46 12:57:28 [INFO] train episode 51519: reward = -21.70, steps = 42 12:57:31 [INFO] train episode 51520: reward = -47.75, steps = 33 12:57:34 [INFO] train episode 51521: reward = -30.67, steps = 33 12:57:37 [INFO] train episode 51522: reward = -16.05, steps = 38 12:57:41 [INFO] train episode 51523: reward = -43.16, steps = 48 12:57:44 [INFO] train episode 51524: reward = -47.38, steps = 32 12:57:46 [INFO] train episode 51525: reward = -49.20, steps = 24 12:57:49 [INFO] train episode 51526: reward = -41.07, steps = 32 12:57:53 [INFO] train episode 51527: reward = -22.18, steps = 45 12:57:55 [INFO] train episode 51528: reward = -40.94, steps = 20 12:57:57 [INFO] train episode 51529: reward = -20.73, steps = 25 12:57:59 [INFO] train episode 51530: reward = -29.53, steps = 20 12:58:02 [INFO] train episode 51531: reward = -31.17, steps = 32 12:58:05 [INFO] train episode 51532: reward = -12.59, steps = 28 12:58:07 [INFO] train episode 51533: reward = -34.81, steps = 22 12:58:09 [INFO] train episode 51534: reward = -34.39, steps = 22 12:58:11 [INFO] train episode 51535: reward = -30.84, steps = 23 12:58:13 [INFO] train episode 51536: reward = -30.68, steps = 30 12:58:17 [INFO] train episode 51537: reward = -14.13, steps = 36 12:58:19 [INFO] train episode 51538: reward = -8.60, steps = 32 12:58:22 [INFO] train episode 51539: reward = -47.15, steps = 28 12:58:25 [INFO] train episode 51540: reward = -32.95, steps = 37 12:58:27 [INFO] train episode 51541: reward = -35.98, steps = 22 12:58:31 [INFO] train episode 51542: reward = -41.10, steps = 31 12:58:35 [INFO] train episode 51543: reward = -45.79, steps = 39 12:58:38 [INFO] train episode 51544: reward = -50.38, steps = 35 12:58:42 [INFO] train episode 51545: reward = -47.06, steps = 48 12:58:45 [INFO] train episode 51546: reward = -24.56, steps = 34 12:58:47 [INFO] train episode 51547: reward = -25.98, steps = 25 12:58:51 [INFO] train episode 51548: reward = -57.27, steps = 35 12:58:54 [INFO] train episode 51549: reward = -25.11, steps = 37 12:58:57 [INFO] train episode 51550: reward = -23.89, steps = 30 12:58:59 [INFO] train episode 51551: reward = -43.27, steps = 26 12:59:02 [INFO] train episode 51552: reward = -21.71, steps = 35 12:59:07 [INFO] train episode 51553: reward = -34.44, steps = 47 12:59:09 [INFO] train episode 51554: reward = -21.81, steps = 35 12:59:13 [INFO] train episode 51555: reward = -90.44, steps = 42 12:59:16 [INFO] train episode 51556: reward = -11.79, steps = 34 12:59:20 [INFO] train episode 51557: reward = 4.60, steps = 46 12:59:23 [INFO] train episode 51558: reward = -18.54, steps = 34 12:59:26 [INFO] train episode 51559: reward = -34.51, steps = 36 12:59:30 [INFO] train episode 51560: reward = -54.72, steps = 45 12:59:32 [INFO] train episode 51561: reward = -55.32, steps = 24 12:59:35 [INFO] train episode 51562: reward = -24.40, steps = 24 12:59:39 [INFO] train episode 51563: reward = -14.25, steps = 41 12:59:42 [INFO] train episode 51564: reward = -38.19, steps = 36 12:59:44 [INFO] train episode 51565: reward = -40.18, steps = 21 12:59:47 [INFO] train episode 51566: reward = -31.96, steps = 43 12:59:51 [INFO] train episode 51567: reward = 2.83, steps = 47 12:59:55 [INFO] train episode 51568: reward = -27.99, steps = 42 12:59:58 [INFO] train episode 51569: reward = -33.12, steps = 27 13:00:00 [INFO] train episode 51570: reward = -29.96, steps = 26 13:00:03 [INFO] train episode 51571: reward = -16.47, steps = 38 13:00:05 [INFO] train episode 51572: reward = -57.24, steps = 19 13:00:08 [INFO] train episode 51573: reward = -59.18, steps = 40 13:00:12 [INFO] train episode 51574: reward = -23.45, steps = 36 13:00:15 [INFO] train episode 51575: reward = -41.01, steps = 31 13:00:17 [INFO] train episode 51576: reward = -38.33, steps = 21 13:00:19 [INFO] train episode 51577: reward = -28.82, steps = 24 13:00:23 [INFO] train episode 51578: reward = -30.18, steps = 45 13:00:27 [INFO] train episode 51579: reward = -28.31, steps = 46 13:00:30 [INFO] train episode 51580: reward = -19.44, steps = 34 13:00:32 [INFO] train episode 51581: reward = -24.82, steps = 25 13:00:35 [INFO] train episode 51582: reward = -32.79, steps = 33 13:00:38 [INFO] train episode 51583: reward = -21.50, steps = 31 13:00:40 [INFO] train episode 51584: reward = -29.01, steps = 22 13:00:44 [INFO] train episode 51585: reward = -9.48, steps = 44 13:00:47 [INFO] train episode 51586: reward = -10.75, steps = 31 13:00:48 [INFO] train episode 51587: reward = -37.88, steps = 19 13:00:51 [INFO] train episode 51588: reward = -48.30, steps = 24 13:00:53 [INFO] train episode 51589: reward = -34.13, steps = 25 13:00:55 [INFO] train episode 51590: reward = -42.88, steps = 21 13:00:58 [INFO] train episode 51591: reward = -56.11, steps = 37 13:01:01 [INFO] train episode 51592: reward = -33.34, steps = 27 13:01:05 [INFO] train episode 51593: reward = -14.69, steps = 47 13:01:07 [INFO] train episode 51594: reward = -20.30, steps = 32 13:01:10 [INFO] train episode 51595: reward = -41.83, steps = 31 13:01:12 [INFO] train episode 51596: reward = -36.38, steps = 22 13:01:15 [INFO] train episode 51597: reward = -32.69, steps = 24 13:01:17 [INFO] train episode 51598: reward = -39.45, steps = 31 13:01:20 [INFO] train episode 51599: reward = -47.40, steps = 30 13:01:22 [INFO] train episode 51600: reward = -30.83, steps = 29 13:01:26 [INFO] train episode 51601: reward = -25.87, steps = 32 13:01:28 [INFO] train episode 51602: reward = -44.25, steps = 21 13:01:30 [INFO] train episode 51603: reward = -60.33, steps = 29 13:01:34 [INFO] train episode 51604: reward = -15.49, steps = 40 13:01:36 [INFO] train episode 51605: reward = -29.28, steps = 26 13:01:39 [INFO] train episode 51606: reward = -28.32, steps = 32 13:01:41 [INFO] train episode 51607: reward = -47.79, steps = 25 13:01:44 [INFO] train episode 51608: reward = -57.42, steps = 24 13:01:46 [INFO] train episode 51609: reward = -39.82, steps = 28 13:01:49 [INFO] train episode 51610: reward = -28.44, steps = 24 13:01:52 [INFO] train episode 51611: reward = -21.80, steps = 35 13:01:54 [INFO] train episode 51612: reward = -69.07, steps = 33 13:01:58 [INFO] train episode 51613: reward = -11.69, steps = 41 13:02:02 [INFO] train episode 51614: reward = -37.97, steps = 45 13:02:05 [INFO] train episode 51615: reward = -29.83, steps = 29 13:02:12 [INFO] train episode 51616: reward = -67.50, steps = 81 13:02:14 [INFO] train episode 51617: reward = -25.98, steps = 29 13:02:17 [INFO] train episode 51618: reward = -11.84, steps = 31 13:02:19 [INFO] train episode 51619: reward = -28.61, steps = 28 13:02:26 [INFO] train episode 51620: reward = -38.70, steps = 75 13:02:29 [INFO] train episode 51621: reward = -14.37, steps = 33 13:02:32 [INFO] train episode 51622: reward = -34.28, steps = 32 13:02:36 [INFO] train episode 51623: reward = -1.17, steps = 41 13:02:39 [INFO] train episode 51624: reward = -16.23, steps = 35 13:02:42 [INFO] train episode 51625: reward = -30.46, steps = 30 13:02:44 [INFO] train episode 51626: reward = -71.36, steps = 27 13:02:47 [INFO] train episode 51627: reward = -20.56, steps = 27 13:02:50 [INFO] train episode 51628: reward = -14.46, steps = 37 13:02:53 [INFO] train episode 51629: reward = -39.63, steps = 33 13:02:55 [INFO] train episode 51630: reward = -32.56, steps = 22 13:02:59 [INFO] train episode 51631: reward = -7.28, steps = 40 13:03:01 [INFO] train episode 51632: reward = -31.77, steps = 26 13:03:05 [INFO] train episode 51633: reward = -21.46, steps = 45 13:03:08 [INFO] train episode 51634: reward = -18.95, steps = 39 13:03:11 [INFO] train episode 51635: reward = -15.27, steps = 32 13:03:15 [INFO] train episode 51636: reward = -28.67, steps = 45 13:03:17 [INFO] train episode 51637: reward = -46.48, steps = 20 13:03:19 [INFO] train episode 51638: reward = -36.26, steps = 21 13:03:22 [INFO] train episode 51639: reward = -27.03, steps = 31 13:03:26 [INFO] train episode 51640: reward = -19.29, steps = 41 13:03:28 [INFO] train episode 51641: reward = -18.40, steps = 31 13:03:31 [INFO] train episode 51642: reward = -23.67, steps = 25 13:03:34 [INFO] train episode 51643: reward = -20.68, steps = 38 13:03:36 [INFO] train episode 51644: reward = -46.47, steps = 21 13:03:38 [INFO] train episode 51645: reward = -38.06, steps = 20 13:03:41 [INFO] train episode 51646: reward = -16.86, steps = 41 13:03:45 [INFO] train episode 51647: reward = -52.16, steps = 41 13:03:48 [INFO] train episode 51648: reward = -48.43, steps = 41 13:03:52 [INFO] train episode 51649: reward = -25.46, steps = 43 13:03:55 [INFO] train episode 51650: reward = -37.51, steps = 28 13:03:58 [INFO] train episode 51651: reward = -32.10, steps = 31 13:04:00 [INFO] train episode 51652: reward = -18.38, steps = 26 13:04:03 [INFO] train episode 51653: reward = -16.15, steps = 34 13:04:05 [INFO] train episode 51654: reward = -41.90, steps = 21 13:04:06 [INFO] train episode 51655: reward = -79.47, steps = 20 13:04:09 [INFO] train episode 51656: reward = -47.28, steps = 26 13:04:11 [INFO] train episode 51657: reward = -42.07, steps = 28 13:04:13 [INFO] train episode 51658: reward = -63.19, steps = 20 13:04:16 [INFO] train episode 51659: reward = -39.77, steps = 22 13:04:21 [INFO] train episode 51660: reward = -33.11, steps = 57 13:04:24 [INFO] train episode 51661: reward = -31.10, steps = 27 13:04:26 [INFO] train episode 51662: reward = -18.66, steps = 22 13:04:28 [INFO] train episode 51663: reward = -44.32, steps = 21 13:04:32 [INFO] train episode 51664: reward = -84.48, steps = 42 13:04:35 [INFO] train episode 51665: reward = -36.95, steps = 40 13:04:39 [INFO] train episode 51666: reward = -15.11, steps = 41 13:04:41 [INFO] train episode 51667: reward = -29.96, steps = 27 13:04:45 [INFO] train episode 51668: reward = -5.45, steps = 39 13:04:46 [INFO] train episode 51669: reward = -43.96, steps = 19 13:04:50 [INFO] train episode 51670: reward = -27.02, steps = 33 13:04:52 [INFO] train episode 51671: reward = -30.30, steps = 27 13:04:54 [INFO] train episode 51672: reward = -45.10, steps = 23 13:04:58 [INFO] train episode 51673: reward = -0.94, steps = 41 13:05:01 [INFO] train episode 51674: reward = -14.68, steps = 34 13:05:03 [INFO] train episode 51675: reward = -13.15, steps = 28 13:05:06 [INFO] train episode 51676: reward = -32.88, steps = 32 13:05:09 [INFO] train episode 51677: reward = -11.64, steps = 37 13:05:11 [INFO] train episode 51678: reward = -55.29, steps = 22 13:05:14 [INFO] train episode 51679: reward = -23.08, steps = 28 13:05:16 [INFO] train episode 51680: reward = -41.85, steps = 24 13:05:19 [INFO] train episode 51681: reward = -15.49, steps = 37 13:05:21 [INFO] train episode 51682: reward = -50.08, steps = 20 13:05:24 [INFO] train episode 51683: reward = -23.11, steps = 36 13:05:28 [INFO] train episode 51684: reward = -37.88, steps = 37 13:05:31 [INFO] train episode 51685: reward = -17.92, steps = 40 13:05:35 [INFO] train episode 51686: reward = -22.75, steps = 45 13:05:38 [INFO] train episode 51687: reward = -60.67, steps = 30 13:05:40 [INFO] train episode 51688: reward = -33.22, steps = 21 13:05:42 [INFO] train episode 51689: reward = -29.00, steps = 22 13:05:44 [INFO] train episode 51690: reward = -31.61, steps = 31 13:05:46 [INFO] train episode 51691: reward = -26.17, steps = 24 13:05:49 [INFO] train episode 51692: reward = -14.98, steps = 34 13:05:53 [INFO] train episode 51693: reward = -37.26, steps = 39 13:05:56 [INFO] train episode 51694: reward = -24.16, steps = 31 13:05:58 [INFO] train episode 51695: reward = -35.18, steps = 26 13:06:02 [INFO] train episode 51696: reward = -38.03, steps = 41 13:06:05 [INFO] train episode 51697: reward = -36.97, steps = 36 13:06:09 [INFO] train episode 51698: reward = -30.42, steps = 38 13:06:11 [INFO] train episode 51699: reward = -48.04, steps = 27 13:06:13 [INFO] train episode 51700: reward = -34.26, steps = 29 13:06:16 [INFO] train episode 51701: reward = -62.42, steps = 33 13:06:18 [INFO] train episode 51702: reward = -36.11, steps = 20 13:06:21 [INFO] train episode 51703: reward = -20.44, steps = 37 13:06:25 [INFO] train episode 51704: reward = -19.59, steps = 35 13:06:27 [INFO] train episode 51705: reward = -18.97, steps = 30 13:06:31 [INFO] train episode 51706: reward = -20.39, steps = 38 13:06:33 [INFO] train episode 51707: reward = -32.63, steps = 24 13:06:34 [INFO] train episode 51708: reward = -34.03, steps = 17 13:06:38 [INFO] train episode 51709: reward = -11.45, steps = 39 13:06:41 [INFO] train episode 51710: reward = -14.14, steps = 27 13:06:45 [INFO] train episode 51711: reward = 4.63, steps = 47 13:06:49 [INFO] train episode 51712: reward = -31.12, steps = 52 13:06:51 [INFO] train episode 51713: reward = -53.27, steps = 20 13:06:55 [INFO] train episode 51714: reward = 6.06, steps = 47 13:06:58 [INFO] train episode 51715: reward = -38.59, steps = 25 13:06:59 [INFO] train episode 51716: reward = -37.83, steps = 20 13:07:03 [INFO] train episode 51717: reward = -43.78, steps = 43 13:07:05 [INFO] train episode 51718: reward = -30.88, steps = 23 13:07:07 [INFO] train episode 51719: reward = -46.98, steps = 21 13:07:09 [INFO] train episode 51720: reward = -34.24, steps = 26 13:07:12 [INFO] train episode 51721: reward = -31.14, steps = 33 13:07:15 [INFO] train episode 51722: reward = -51.40, steps = 26 13:07:18 [INFO] train episode 51723: reward = -63.57, steps = 30 13:07:22 [INFO] train episode 51724: reward = -39.27, steps = 47 13:07:24 [INFO] train episode 51725: reward = -33.67, steps = 21 13:07:27 [INFO] train episode 51726: reward = -7.44, steps = 34 13:07:31 [INFO] train episode 51727: reward = -36.14, steps = 36 13:07:33 [INFO] train episode 51728: reward = -37.37, steps = 30 13:07:36 [INFO] train episode 51729: reward = -5.32, steps = 36 13:07:41 [INFO] train episode 51730: reward = -14.58, steps = 59 13:07:43 [INFO] train episode 51731: reward = -44.97, steps = 20 13:07:46 [INFO] train episode 51732: reward = -22.48, steps = 27 13:07:49 [INFO] train episode 51733: reward = -17.50, steps = 38 13:07:51 [INFO] train episode 51734: reward = -45.99, steps = 19 13:07:54 [INFO] train episode 51735: reward = -28.68, steps = 33 13:07:56 [INFO] train episode 51736: reward = -29.78, steps = 25 13:07:58 [INFO] train episode 51737: reward = -31.35, steps = 26 13:08:00 [INFO] train episode 51738: reward = -47.08, steps = 25 13:08:02 [INFO] train episode 51739: reward = -36.09, steps = 20 13:08:04 [INFO] train episode 51740: reward = -27.01, steps = 18 13:08:07 [INFO] train episode 51741: reward = -8.13, steps = 30 13:08:09 [INFO] train episode 51742: reward = -31.16, steps = 31 13:08:13 [INFO] train episode 51743: reward = -36.95, steps = 36 13:08:15 [INFO] train episode 51744: reward = -11.95, steps = 34 13:08:17 [INFO] train episode 51745: reward = -50.50, steps = 21 13:08:20 [INFO] train episode 51746: reward = -41.49, steps = 26 13:08:23 [INFO] train episode 51747: reward = -32.37, steps = 30 13:08:27 [INFO] train episode 51748: reward = 1.77, steps = 50 13:08:29 [INFO] train episode 51749: reward = -28.59, steps = 20 13:08:31 [INFO] train episode 51750: reward = -32.24, steps = 25 13:08:33 [INFO] train episode 51751: reward = -37.18, steps = 22 13:08:36 [INFO] train episode 51752: reward = -7.79, steps = 31 13:08:39 [INFO] train episode 51753: reward = -18.01, steps = 32 13:08:42 [INFO] train episode 51754: reward = -16.84, steps = 44 13:08:44 [INFO] train episode 51755: reward = -36.15, steps = 19 13:08:47 [INFO] train episode 51756: reward = -32.17, steps = 32 13:08:49 [INFO] train episode 51757: reward = -29.01, steps = 23 13:08:51 [INFO] train episode 51758: reward = -31.37, steps = 22 13:08:54 [INFO] train episode 51759: reward = -17.86, steps = 30 13:08:57 [INFO] train episode 51760: reward = -4.61, steps = 36 13:09:01 [INFO] train episode 51761: reward = -39.65, steps = 41 13:09:05 [INFO] train episode 51762: reward = -89.17, steps = 50 13:09:09 [INFO] train episode 51763: reward = -37.42, steps = 44 13:09:11 [INFO] train episode 51764: reward = -40.22, steps = 23 13:09:14 [INFO] train episode 51765: reward = -78.58, steps = 25 13:09:17 [INFO] train episode 51766: reward = -16.32, steps = 39 13:09:19 [INFO] train episode 51767: reward = -31.11, steps = 21 13:09:25 [INFO] train episode 51768: reward = -56.33, steps = 60 13:09:26 [INFO] train episode 51769: reward = -45.51, steps = 21 13:09:29 [INFO] train episode 51770: reward = -11.78, steps = 36 13:09:35 [INFO] train episode 51771: reward = -39.46, steps = 59 13:09:38 [INFO] train episode 51772: reward = -45.06, steps = 36 13:09:41 [INFO] train episode 51773: reward = -10.64, steps = 35 13:09:45 [INFO] train episode 51774: reward = 5.17, steps = 41 13:09:48 [INFO] train episode 51775: reward = -18.40, steps = 37 13:09:50 [INFO] train episode 51776: reward = -48.74, steps = 19 13:09:52 [INFO] train episode 51777: reward = -32.08, steps = 23 13:09:54 [INFO] train episode 51778: reward = -58.16, steps = 31 13:09:59 [INFO] train episode 51779: reward = -16.31, steps = 43 13:10:02 [INFO] train episode 51780: reward = -37.94, steps = 36 13:10:03 [INFO] train episode 51781: reward = -40.42, steps = 20 13:10:06 [INFO] train episode 51782: reward = -26.97, steps = 31 13:10:08 [INFO] train episode 51783: reward = -17.31, steps = 21 13:10:10 [INFO] train episode 51784: reward = -19.07, steps = 29 13:10:15 [INFO] train episode 51785: reward = -16.45, steps = 46 13:10:18 [INFO] train episode 51786: reward = -35.06, steps = 29 13:10:21 [INFO] train episode 51787: reward = -22.66, steps = 33 13:10:24 [INFO] train episode 51788: reward = -21.72, steps = 40 13:10:28 [INFO] train episode 51789: reward = -20.67, steps = 42 13:10:31 [INFO] train episode 51790: reward = -13.26, steps = 36 13:10:35 [INFO] train episode 51791: reward = -21.23, steps = 48 13:10:39 [INFO] train episode 51792: reward = -18.19, steps = 35 13:10:41 [INFO] train episode 51793: reward = -13.40, steps = 33 13:10:44 [INFO] train episode 51794: reward = -21.58, steps = 24 13:10:47 [INFO] train episode 51795: reward = -31.64, steps = 35 13:10:50 [INFO] train episode 51796: reward = -24.52, steps = 34 13:10:53 [INFO] train episode 51797: reward = -30.20, steps = 40 13:10:55 [INFO] train episode 51798: reward = -24.70, steps = 22 13:10:57 [INFO] train episode 51799: reward = -35.87, steps = 21 13:10:59 [INFO] train episode 51800: reward = -33.96, steps = 26 13:11:03 [INFO] train episode 51801: reward = -41.83, steps = 36 13:11:05 [INFO] train episode 51802: reward = -25.84, steps = 27 13:11:07 [INFO] train episode 51803: reward = -55.53, steps = 22 13:11:11 [INFO] train episode 51804: reward = -20.05, steps = 43 13:11:13 [INFO] train episode 51805: reward = -44.73, steps = 25 13:11:15 [INFO] train episode 51806: reward = -26.34, steps = 21 13:11:17 [INFO] train episode 51807: reward = -31.12, steps = 24 13:11:19 [INFO] train episode 51808: reward = -35.14, steps = 21 13:11:22 [INFO] train episode 51809: reward = -25.64, steps = 35 13:11:25 [INFO] train episode 51810: reward = -13.88, steps = 28 13:11:27 [INFO] train episode 51811: reward = -16.90, steps = 23 13:11:29 [INFO] train episode 51812: reward = -30.04, steps = 21 13:11:33 [INFO] train episode 51813: reward = -27.24, steps = 55 13:11:37 [INFO] train episode 51814: reward = -16.37, steps = 37 13:11:40 [INFO] train episode 51815: reward = -43.44, steps = 38 13:11:42 [INFO] train episode 51816: reward = -41.87, steps = 20 13:11:46 [INFO] train episode 51817: reward = -0.51, steps = 44 13:11:49 [INFO] train episode 51818: reward = -17.51, steps = 35 13:11:52 [INFO] train episode 51819: reward = -26.63, steps = 30 13:11:55 [INFO] train episode 51820: reward = -47.24, steps = 33 13:11:58 [INFO] train episode 51821: reward = -21.63, steps = 35 13:12:00 [INFO] train episode 51822: reward = -25.65, steps = 25 13:12:05 [INFO] train episode 51823: reward = -29.95, steps = 56 13:12:08 [INFO] train episode 51824: reward = -49.35, steps = 38 13:12:11 [INFO] train episode 51825: reward = -14.03, steps = 34 13:12:13 [INFO] train episode 51826: reward = -30.70, steps = 21 13:12:15 [INFO] train episode 51827: reward = -36.07, steps = 26 13:12:17 [INFO] train episode 51828: reward = -31.12, steps = 25 13:12:21 [INFO] train episode 51829: reward = -2.06, steps = 39 13:12:23 [INFO] train episode 51830: reward = -29.61, steps = 25 13:12:25 [INFO] train episode 51831: reward = -26.91, steps = 24 13:12:28 [INFO] train episode 51832: reward = -40.93, steps = 30 13:12:31 [INFO] train episode 51833: reward = -6.61, steps = 34 13:12:36 [INFO] train episode 51834: reward = -24.18, steps = 53 13:12:39 [INFO] train episode 51835: reward = -38.79, steps = 35 13:12:41 [INFO] train episode 51836: reward = -37.31, steps = 25 13:12:44 [INFO] train episode 51837: reward = -25.17, steps = 31 13:12:47 [INFO] train episode 51838: reward = -32.08, steps = 32 13:12:50 [INFO] train episode 51839: reward = -7.20, steps = 40 13:12:53 [INFO] train episode 51840: reward = -31.74, steps = 27 13:12:57 [INFO] train episode 51841: reward = -41.08, steps = 40 13:13:01 [INFO] train episode 51842: reward = -17.62, steps = 45 13:13:03 [INFO] train episode 51843: reward = -26.85, steps = 22 13:13:04 [INFO] train episode 51844: reward = -36.08, steps = 20 13:13:08 [INFO] train episode 51845: reward = -21.86, steps = 38 13:13:10 [INFO] train episode 51846: reward = -31.29, steps = 20 13:13:15 [INFO] train episode 51847: reward = -15.22, steps = 54 13:13:17 [INFO] train episode 51848: reward = -34.37, steps = 21 13:13:21 [INFO] train episode 51849: reward = -20.43, steps = 41 13:13:26 [INFO] train episode 51850: reward = -17.85, steps = 59 13:13:30 [INFO] train episode 51851: reward = 5.74, steps = 40 13:13:33 [INFO] train episode 51852: reward = -22.12, steps = 40 13:13:37 [INFO] train episode 51853: reward = -20.70, steps = 42 13:13:39 [INFO] train episode 51854: reward = -19.72, steps = 26 13:13:42 [INFO] train episode 51855: reward = -38.92, steps = 35 13:13:46 [INFO] train episode 51856: reward = -1.48, steps = 36 13:13:49 [INFO] train episode 51857: reward = -19.74, steps = 32 13:13:52 [INFO] train episode 51858: reward = -51.27, steps = 39 13:13:54 [INFO] train episode 51859: reward = -24.59, steps = 23 13:13:57 [INFO] train episode 51860: reward = -11.37, steps = 36 13:14:01 [INFO] train episode 51861: reward = -21.45, steps = 38 13:14:03 [INFO] train episode 51862: reward = -30.54, steps = 21 13:14:06 [INFO] train episode 51863: reward = -30.52, steps = 31 13:14:09 [INFO] train episode 51864: reward = -22.04, steps = 37 13:14:11 [INFO] train episode 51865: reward = -47.96, steps = 20 13:14:13 [INFO] train episode 51866: reward = -23.11, steps = 26 13:14:16 [INFO] train episode 51867: reward = -30.33, steps = 38 13:14:19 [INFO] train episode 51868: reward = -25.94, steps = 29 13:14:22 [INFO] train episode 51869: reward = -17.70, steps = 37 13:14:26 [INFO] train episode 51870: reward = -15.26, steps = 42 13:14:29 [INFO] train episode 51871: reward = -0.96, steps = 37 13:14:31 [INFO] train episode 51872: reward = -38.63, steps = 25 13:14:34 [INFO] train episode 51873: reward = -2.35, steps = 35 13:14:38 [INFO] train episode 51874: reward = -18.31, steps = 41 13:14:41 [INFO] train episode 51875: reward = -47.85, steps = 24 13:14:45 [INFO] train episode 51876: reward = -14.10, steps = 49 13:14:47 [INFO] train episode 51877: reward = -38.33, steps = 26 13:14:49 [INFO] train episode 51878: reward = -28.26, steps = 21 13:14:51 [INFO] train episode 51879: reward = -33.22, steps = 24 13:14:54 [INFO] train episode 51880: reward = -52.65, steps = 25 13:14:55 [INFO] train episode 51881: reward = -28.32, steps = 21 13:14:58 [INFO] train episode 51882: reward = -10.87, steps = 30 13:15:01 [INFO] train episode 51883: reward = -22.88, steps = 30 13:15:03 [INFO] train episode 51884: reward = -4.05, steps = 31 13:15:05 [INFO] train episode 51885: reward = -33.79, steps = 20 13:15:09 [INFO] train episode 51886: reward = -30.62, steps = 35 13:15:11 [INFO] train episode 51887: reward = -14.19, steps = 33 13:15:13 [INFO] train episode 51888: reward = -66.37, steps = 21 13:15:17 [INFO] train episode 51889: reward = -21.22, steps = 42 13:15:21 [INFO] train episode 51890: reward = -28.32, steps = 44 13:15:22 [INFO] train episode 51891: reward = -30.52, steps = 20 13:15:25 [INFO] train episode 51892: reward = -37.21, steps = 28 13:15:28 [INFO] train episode 51893: reward = -4.96, steps = 37 13:15:31 [INFO] train episode 51894: reward = -7.39, steps = 37 13:15:34 [INFO] train episode 51895: reward = -30.11, steps = 24 13:15:38 [INFO] train episode 51896: reward = -16.99, steps = 55 13:15:43 [INFO] train episode 51897: reward = -67.46, steps = 53 13:15:46 [INFO] train episode 51898: reward = -25.84, steps = 32 13:15:48 [INFO] train episode 51899: reward = -31.48, steps = 20 13:15:52 [INFO] train episode 51900: reward = -5.93, steps = 47 13:15:54 [INFO] train episode 51901: reward = -28.48, steps = 24 13:15:58 [INFO] train episode 51902: reward = -0.15, steps = 39 13:16:01 [INFO] train episode 51903: reward = -12.40, steps = 36 13:16:05 [INFO] train episode 51904: reward = -17.69, steps = 33 13:16:08 [INFO] train episode 51905: reward = -39.28, steps = 36 13:16:11 [INFO] train episode 51906: reward = -6.88, steps = 36 13:16:13 [INFO] train episode 51907: reward = -33.71, steps = 21 13:16:17 [INFO] train episode 51908: reward = 5.31, steps = 40 13:16:20 [INFO] train episode 51909: reward = -6.75, steps = 39 13:16:22 [INFO] train episode 51910: reward = -10.95, steps = 29 13:16:25 [INFO] train episode 51911: reward = -10.09, steps = 31 13:16:28 [INFO] train episode 51912: reward = -29.66, steps = 37 13:16:31 [INFO] train episode 51913: reward = -30.77, steps = 26 13:16:34 [INFO] train episode 51914: reward = -23.71, steps = 32 13:16:36 [INFO] train episode 51915: reward = -49.54, steps = 28 13:16:40 [INFO] train episode 51916: reward = -8.80, steps = 46 13:16:44 [INFO] train episode 51917: reward = -55.58, steps = 48 13:16:47 [INFO] train episode 51918: reward = -40.31, steps = 24 13:16:50 [INFO] train episode 51919: reward = -23.37, steps = 32 13:16:53 [INFO] train episode 51920: reward = -28.38, steps = 34 13:16:56 [INFO] train episode 51921: reward = 1.09, steps = 35 13:16:59 [INFO] train episode 51922: reward = -35.98, steps = 38 13:17:03 [INFO] train episode 51923: reward = -17.93, steps = 45 13:17:06 [INFO] train episode 51924: reward = -17.30, steps = 31 13:17:11 [INFO] train episode 51925: reward = -15.56, steps = 55 13:17:15 [INFO] train episode 51926: reward = -24.17, steps = 50 13:17:18 [INFO] train episode 51927: reward = -15.21, steps = 38 13:17:22 [INFO] train episode 51928: reward = -8.65, steps = 34 13:17:25 [INFO] train episode 51929: reward = -13.57, steps = 40 13:17:27 [INFO] train episode 51930: reward = -28.32, steps = 24 13:17:31 [INFO] train episode 51931: reward = -67.04, steps = 48 13:17:34 [INFO] train episode 51932: reward = -10.84, steps = 35 13:17:38 [INFO] train episode 51933: reward = -28.17, steps = 37 13:17:42 [INFO] train episode 51934: reward = -10.86, steps = 42 13:17:44 [INFO] train episode 51935: reward = -58.25, steps = 32 13:17:46 [INFO] train episode 51936: reward = -54.43, steps = 22 13:17:49 [INFO] train episode 51937: reward = -56.34, steps = 33 13:17:53 [INFO] train episode 51938: reward = -17.48, steps = 42 13:17:55 [INFO] train episode 51939: reward = -28.82, steps = 22 13:17:57 [INFO] train episode 51940: reward = -23.68, steps = 24 13:18:00 [INFO] train episode 51941: reward = -32.11, steps = 31 13:18:03 [INFO] train episode 51942: reward = -27.68, steps = 36 13:18:07 [INFO] train episode 51943: reward = -10.67, steps = 43 13:18:11 [INFO] train episode 51944: reward = -21.17, steps = 46 13:18:14 [INFO] train episode 51945: reward = -16.73, steps = 36 13:18:18 [INFO] train episode 51946: reward = -13.55, steps = 48 13:18:21 [INFO] train episode 51947: reward = -1.48, steps = 30 13:18:24 [INFO] train episode 51948: reward = -5.98, steps = 34 13:18:27 [INFO] train episode 51949: reward = -19.32, steps = 31 13:18:30 [INFO] train episode 51950: reward = -28.33, steps = 29 13:18:33 [INFO] train episode 51951: reward = -36.26, steps = 40 13:18:36 [INFO] train episode 51952: reward = -12.21, steps = 37 13:18:41 [INFO] train episode 51953: reward = -4.50, steps = 48 13:18:44 [INFO] train episode 51954: reward = -29.28, steps = 38 13:18:50 [INFO] train episode 51955: reward = -54.64, steps = 70 13:18:54 [INFO] train episode 51956: reward = -42.04, steps = 39 13:18:56 [INFO] train episode 51957: reward = -18.09, steps = 28 13:19:01 [INFO] train episode 51958: reward = -54.74, steps = 48 13:19:05 [INFO] train episode 51959: reward = -39.55, steps = 40 13:19:08 [INFO] train episode 51960: reward = -16.04, steps = 32 13:19:12 [INFO] train episode 51961: reward = -0.83, steps = 51 13:19:14 [INFO] train episode 51962: reward = -26.54, steps = 24 13:19:17 [INFO] train episode 51963: reward = -30.00, steps = 29 13:19:20 [INFO] train episode 51964: reward = -22.69, steps = 37 13:19:22 [INFO] train episode 51965: reward = -35.25, steps = 21 13:19:26 [INFO] train episode 51966: reward = -31.46, steps = 42 13:19:30 [INFO] train episode 51967: reward = 2.82, steps = 40 13:19:33 [INFO] train episode 51968: reward = -18.56, steps = 36 13:19:35 [INFO] train episode 51969: reward = -29.84, steps = 28 13:19:38 [INFO] train episode 51970: reward = -15.70, steps = 28 13:19:41 [INFO] train episode 51971: reward = -33.80, steps = 46 13:19:44 [INFO] train episode 51972: reward = -44.90, steps = 26 13:19:48 [INFO] train episode 51973: reward = -8.94, steps = 47 13:19:51 [INFO] train episode 51974: reward = -24.24, steps = 38 13:19:54 [INFO] train episode 51975: reward = -32.60, steps = 29 13:19:56 [INFO] train episode 51976: reward = -15.42, steps = 30 13:19:59 [INFO] train episode 51977: reward = -22.96, steps = 32 13:20:03 [INFO] train episode 51978: reward = -12.66, steps = 40 13:20:06 [INFO] train episode 51979: reward = -25.72, steps = 34 13:20:10 [INFO] train episode 51980: reward = -6.00, steps = 45 13:20:14 [INFO] train episode 51981: reward = -23.65, steps = 46 13:20:17 [INFO] train episode 51982: reward = -25.45, steps = 36 13:20:21 [INFO] train episode 51983: reward = -25.47, steps = 37 13:20:24 [INFO] train episode 51984: reward = -18.62, steps = 38 13:20:28 [INFO] train episode 51985: reward = -18.57, steps = 49 13:20:30 [INFO] train episode 51986: reward = -37.93, steps = 23 13:20:33 [INFO] train episode 51987: reward = -25.94, steps = 35 13:20:38 [INFO] train episode 51988: reward = -25.25, steps = 41 13:20:40 [INFO] train episode 51989: reward = -32.51, steps = 20 13:20:44 [INFO] train episode 51990: reward = -19.58, steps = 43 13:20:48 [INFO] train episode 51991: reward = -14.55, steps = 37 13:20:51 [INFO] train episode 51992: reward = -18.73, steps = 37 13:20:55 [INFO] train episode 51993: reward = -24.36, steps = 40 13:20:59 [INFO] train episode 51994: reward = -1.84, steps = 42 13:21:02 [INFO] train episode 51995: reward = -13.71, steps = 33 13:21:05 [INFO] train episode 51996: reward = -4.67, steps = 35 13:21:09 [INFO] train episode 51997: reward = -4.43, steps = 38 13:21:11 [INFO] train episode 51998: reward = -8.62, steps = 22 13:21:15 [INFO] train episode 51999: reward = -5.39, steps = 42 13:21:18 [INFO] train episode 52000: reward = -8.92, steps = 40 13:21:21 [INFO] train episode 52001: reward = -37.40, steps = 30 13:21:23 [INFO] train episode 52002: reward = -34.81, steps = 34 13:21:26 [INFO] train episode 52003: reward = -39.95, steps = 29 13:21:30 [INFO] train episode 52004: reward = 8.00, steps = 38 13:21:32 [INFO] train episode 52005: reward = -19.74, steps = 32 13:21:35 [INFO] train episode 52006: reward = -56.73, steps = 26 13:21:37 [INFO] train episode 52007: reward = -32.47, steps = 28 13:21:41 [INFO] train episode 52008: reward = -18.90, steps = 42 13:21:45 [INFO] train episode 52009: reward = -33.66, steps = 50 13:21:48 [INFO] train episode 52010: reward = -26.47, steps = 35 13:21:52 [INFO] train episode 52011: reward = -25.03, steps = 38 13:21:55 [INFO] train episode 52012: reward = -10.64, steps = 31 13:21:59 [INFO] train episode 52013: reward = -24.08, steps = 41 13:22:01 [INFO] train episode 52014: reward = -40.81, steps = 21 13:22:04 [INFO] train episode 52015: reward = -26.76, steps = 36 13:22:06 [INFO] train episode 52016: reward = -26.63, steps = 25 13:22:10 [INFO] train episode 52017: reward = -25.85, steps = 46 13:22:13 [INFO] train episode 52018: reward = -20.71, steps = 28 13:22:16 [INFO] train episode 52019: reward = -17.85, steps = 37 13:22:19 [INFO] train episode 52020: reward = -21.05, steps = 31 13:22:21 [INFO] train episode 52021: reward = -31.93, steps = 21 13:22:23 [INFO] train episode 52022: reward = -33.33, steps = 24 13:22:25 [INFO] train episode 52023: reward = -22.44, steps = 24 13:22:27 [INFO] train episode 52024: reward = -40.65, steps = 27 13:22:29 [INFO] train episode 52025: reward = -34.35, steps = 23 13:22:34 [INFO] train episode 52026: reward = -19.19, steps = 52 13:22:36 [INFO] train episode 52027: reward = -30.10, steps = 19 13:22:40 [INFO] train episode 52028: reward = -25.53, steps = 45 13:22:43 [INFO] train episode 52029: reward = -4.03, steps = 34 13:22:46 [INFO] train episode 52030: reward = -31.13, steps = 38 13:22:50 [INFO] train episode 52031: reward = -19.98, steps = 41 13:22:52 [INFO] train episode 52032: reward = -21.80, steps = 25 13:22:57 [INFO] train episode 52033: reward = -25.72, steps = 55 13:23:01 [INFO] train episode 52034: reward = -15.96, steps = 37 13:23:05 [INFO] train episode 52035: reward = -36.51, steps = 41 13:23:07 [INFO] train episode 52036: reward = -20.18, steps = 27 13:23:10 [INFO] train episode 52037: reward = -44.03, steps = 40 13:23:15 [INFO] train episode 52038: reward = -8.19, steps = 52 13:23:19 [INFO] train episode 52039: reward = -5.27, steps = 47 13:23:21 [INFO] train episode 52040: reward = -25.73, steps = 25 13:23:25 [INFO] train episode 52041: reward = -6.92, steps = 36 13:23:28 [INFO] train episode 52042: reward = 3.73, steps = 45 13:23:31 [INFO] train episode 52043: reward = -24.20, steps = 34 13:23:35 [INFO] train episode 52044: reward = -15.55, steps = 43 13:23:38 [INFO] train episode 52045: reward = -20.78, steps = 34 13:23:40 [INFO] train episode 52046: reward = -34.67, steps = 25 13:23:44 [INFO] train episode 52047: reward = 0.03, steps = 43 13:23:47 [INFO] train episode 52048: reward = -45.40, steps = 32 13:23:49 [INFO] train episode 52049: reward = -11.76, steps = 30 13:23:52 [INFO] train episode 52050: reward = -55.90, steps = 25 13:23:54 [INFO] train episode 52051: reward = -58.63, steps = 22 13:23:57 [INFO] train episode 52052: reward = -18.36, steps = 40 13:24:00 [INFO] train episode 52053: reward = -21.67, steps = 31 13:24:04 [INFO] train episode 52054: reward = -9.45, steps = 44 13:24:06 [INFO] train episode 52055: reward = -56.78, steps = 19 13:24:09 [INFO] train episode 52056: reward = -15.65, steps = 36 13:24:12 [INFO] train episode 52057: reward = -12.33, steps = 32 13:24:15 [INFO] train episode 52058: reward = -10.88, steps = 38 13:24:19 [INFO] train episode 52059: reward = -27.76, steps = 40 13:24:23 [INFO] train episode 52060: reward = -7.54, steps = 49 13:24:26 [INFO] train episode 52061: reward = -5.81, steps = 37 13:24:30 [INFO] train episode 52062: reward = -16.40, steps = 41 13:24:33 [INFO] train episode 52063: reward = -13.32, steps = 33 13:24:38 [INFO] train episode 52064: reward = -61.72, steps = 55 13:24:40 [INFO] train episode 52065: reward = -23.12, steps = 30 13:24:44 [INFO] train episode 52066: reward = -1.90, steps = 34 13:24:47 [INFO] train episode 52067: reward = -14.16, steps = 34 13:24:51 [INFO] train episode 52068: reward = -24.49, steps = 40 13:24:53 [INFO] train episode 52069: reward = -35.35, steps = 22 13:24:56 [INFO] train episode 52070: reward = -18.53, steps = 36 13:25:00 [INFO] train episode 52071: reward = -14.20, steps = 35 13:25:02 [INFO] train episode 52072: reward = -53.52, steps = 29 13:25:07 [INFO] train episode 52073: reward = -25.45, steps = 48 13:25:09 [INFO] train episode 52074: reward = -19.78, steps = 30 13:25:14 [INFO] train episode 52075: reward = -23.46, steps = 60 13:25:18 [INFO] train episode 52076: reward = -21.51, steps = 39 13:25:21 [INFO] train episode 52077: reward = -10.71, steps = 34 13:25:23 [INFO] train episode 52078: reward = -9.22, steps = 26 13:25:27 [INFO] train episode 52079: reward = -21.24, steps = 41 13:25:30 [INFO] train episode 52080: reward = -33.86, steps = 34 13:25:34 [INFO] train episode 52081: reward = -24.54, steps = 40 13:25:37 [INFO] train episode 52082: reward = -35.54, steps = 42 13:25:40 [INFO] train episode 52083: reward = -49.44, steps = 37 13:25:44 [INFO] train episode 52084: reward = -4.83, steps = 36 13:25:46 [INFO] train episode 52085: reward = -10.61, steps = 33 13:25:52 [INFO] train episode 52086: reward = -34.75, steps = 60 13:25:54 [INFO] train episode 52087: reward = -29.25, steps = 20 13:25:56 [INFO] train episode 52088: reward = -25.33, steps = 24 13:25:58 [INFO] train episode 52089: reward = -32.71, steps = 23 13:26:00 [INFO] train episode 52090: reward = -4.58, steps = 29 13:26:04 [INFO] train episode 52091: reward = -19.75, steps = 36 13:26:06 [INFO] train episode 52092: reward = -0.62, steps = 30 13:26:09 [INFO] train episode 52093: reward = -35.25, steps = 26 13:26:12 [INFO] train episode 52094: reward = -4.51, steps = 40 13:26:14 [INFO] train episode 52095: reward = -45.63, steps = 21 13:26:17 [INFO] train episode 52096: reward = -7.17, steps = 33 13:26:20 [INFO] train episode 52097: reward = -42.44, steps = 30 13:26:22 [INFO] train episode 52098: reward = -12.06, steps = 30 13:26:25 [INFO] train episode 52099: reward = -10.16, steps = 33 13:26:28 [INFO] train episode 52100: reward = -19.17, steps = 32 13:26:31 [INFO] train episode 52101: reward = -4.29, steps = 32 13:26:33 [INFO] train episode 52102: reward = -25.44, steps = 22 13:26:36 [INFO] train episode 52103: reward = -16.01, steps = 32 13:26:39 [INFO] train episode 52104: reward = -13.25, steps = 30 13:26:41 [INFO] train episode 52105: reward = -17.74, steps = 31 13:26:44 [INFO] train episode 52106: reward = -14.32, steps = 26 13:26:47 [INFO] train episode 52107: reward = -5.89, steps = 35 13:26:49 [INFO] train episode 52108: reward = -47.29, steps = 24 13:26:53 [INFO] train episode 52109: reward = -3.37, steps = 37 13:26:56 [INFO] train episode 52110: reward = -32.50, steps = 33 13:26:59 [INFO] train episode 52111: reward = -36.10, steps = 35 13:27:01 [INFO] train episode 52112: reward = -46.39, steps = 23 13:27:04 [INFO] train episode 52113: reward = -7.91, steps = 42 13:27:08 [INFO] train episode 52114: reward = -19.68, steps = 37 13:27:11 [INFO] train episode 52115: reward = -23.51, steps = 40 13:27:14 [INFO] train episode 52116: reward = -20.35, steps = 35 13:27:16 [INFO] train episode 52117: reward = -49.35, steps = 20 13:27:21 [INFO] train episode 52118: reward = -10.19, steps = 53 13:27:24 [INFO] train episode 52119: reward = -23.22, steps = 30 13:27:27 [INFO] train episode 52120: reward = -21.64, steps = 32 13:27:30 [INFO] train episode 52121: reward = -15.35, steps = 35 13:27:32 [INFO] train episode 52122: reward = -35.28, steps = 24 13:27:34 [INFO] train episode 52123: reward = -20.40, steps = 30 13:27:37 [INFO] train episode 52124: reward = -45.26, steps = 27 13:27:41 [INFO] train episode 52125: reward = -2.04, steps = 48 13:27:44 [INFO] train episode 52126: reward = -6.77, steps = 36 13:27:48 [INFO] train episode 52127: reward = -50.89, steps = 31 13:27:51 [INFO] train episode 52128: reward = -19.92, steps = 43 13:27:54 [INFO] train episode 52129: reward = -4.95, steps = 32 13:27:58 [INFO] train episode 52130: reward = -8.71, steps = 41 13:28:02 [INFO] train episode 52131: reward = -10.18, steps = 44 13:28:06 [INFO] train episode 52132: reward = -0.49, steps = 42 13:28:09 [INFO] train episode 52133: reward = -12.67, steps = 42 13:28:12 [INFO] train episode 52134: reward = -21.82, steps = 28 13:28:15 [INFO] train episode 52135: reward = -11.56, steps = 31 13:28:18 [INFO] train episode 52136: reward = -6.52, steps = 36 13:28:20 [INFO] train episode 52137: reward = -53.32, steps = 19 13:28:22 [INFO] train episode 52138: reward = -45.44, steps = 22 13:28:24 [INFO] train episode 52139: reward = -23.13, steps = 30 13:28:26 [INFO] train episode 52140: reward = -38.36, steps = 20 13:28:32 [INFO] train episode 52141: reward = -81.47, steps = 72 13:28:37 [INFO] train episode 52142: reward = -17.99, steps = 43 13:28:39 [INFO] train episode 52143: reward = -26.01, steps = 27 13:28:42 [INFO] train episode 52144: reward = -25.01, steps = 37 13:28:47 [INFO] train episode 52145: reward = -2.85, steps = 48 13:28:50 [INFO] train episode 52146: reward = -36.05, steps = 31 13:28:52 [INFO] train episode 52147: reward = -11.07, steps = 31 13:28:56 [INFO] train episode 52148: reward = -26.35, steps = 40 13:28:58 [INFO] train episode 52149: reward = -31.93, steps = 25 13:29:00 [INFO] train episode 52150: reward = -18.38, steps = 24 13:29:03 [INFO] train episode 52151: reward = -28.20, steps = 19 13:29:06 [INFO] train episode 52152: reward = -32.90, steps = 34 13:29:09 [INFO] train episode 52153: reward = -11.46, steps = 40 13:29:11 [INFO] train episode 52154: reward = -59.46, steps = 17 13:29:14 [INFO] train episode 52155: reward = -4.46, steps = 40 13:29:17 [INFO] train episode 52156: reward = -35.98, steps = 32 13:29:21 [INFO] train episode 52157: reward = -5.20, steps = 36 13:29:24 [INFO] train episode 52158: reward = -11.90, steps = 34 13:29:27 [INFO] train episode 52159: reward = -1.22, steps = 39 13:29:31 [INFO] train episode 52160: reward = -26.44, steps = 48 13:29:33 [INFO] train episode 52161: reward = -27.84, steps = 23 13:29:36 [INFO] train episode 52162: reward = -59.58, steps = 30 13:29:40 [INFO] train episode 52163: reward = -15.80, steps = 37 13:29:44 [INFO] train episode 52164: reward = -8.88, steps = 49 13:29:46 [INFO] train episode 52165: reward = -30.40, steps = 29 13:29:49 [INFO] train episode 52166: reward = -6.24, steps = 29 13:29:52 [INFO] train episode 52167: reward = -15.48, steps = 31 13:29:55 [INFO] train episode 52168: reward = -15.53, steps = 36 13:29:59 [INFO] train episode 52169: reward = -29.48, steps = 42 13:30:01 [INFO] train episode 52170: reward = -21.03, steps = 22 13:30:04 [INFO] train episode 52171: reward = -14.16, steps = 39 13:30:07 [INFO] train episode 52172: reward = -25.76, steps = 33 13:30:10 [INFO] train episode 52173: reward = -33.89, steps = 32 13:30:14 [INFO] train episode 52174: reward = -28.04, steps = 45 13:30:16 [INFO] train episode 52175: reward = -33.65, steps = 23 13:30:19 [INFO] train episode 52176: reward = -14.83, steps = 32 13:30:22 [INFO] train episode 52177: reward = -21.41, steps = 34 13:30:27 [INFO] train episode 52178: reward = -12.40, steps = 52 13:30:29 [INFO] train episode 52179: reward = -38.49, steps = 30 13:30:32 [INFO] train episode 52180: reward = -7.34, steps = 38 13:30:36 [INFO] train episode 52181: reward = -3.07, steps = 40 13:30:38 [INFO] train episode 52182: reward = -44.89, steps = 24 13:30:42 [INFO] train episode 52183: reward = -14.38, steps = 36 13:30:46 [INFO] train episode 52184: reward = -38.07, steps = 38 13:30:49 [INFO] train episode 52185: reward = -13.73, steps = 40 13:30:51 [INFO] train episode 52186: reward = -37.63, steps = 19 13:30:54 [INFO] train episode 52187: reward = -0.06, steps = 29 13:30:57 [INFO] train episode 52188: reward = -16.69, steps = 36 13:31:03 [INFO] train episode 52189: reward = -52.91, steps = 66 13:31:06 [INFO] train episode 52190: reward = -6.59, steps = 38 13:31:09 [INFO] train episode 52191: reward = -16.42, steps = 33 13:31:12 [INFO] train episode 52192: reward = -13.95, steps = 33 13:31:15 [INFO] train episode 52193: reward = -44.37, steps = 30 13:31:17 [INFO] train episode 52194: reward = -34.87, steps = 22 13:31:19 [INFO] train episode 52195: reward = -20.78, steps = 20 13:31:22 [INFO] train episode 52196: reward = -44.02, steps = 34 13:31:25 [INFO] train episode 52197: reward = 1.23, steps = 44 13:31:27 [INFO] train episode 52198: reward = -38.79, steps = 20 13:31:29 [INFO] train episode 52199: reward = -27.21, steps = 25 13:31:33 [INFO] train episode 52200: reward = -3.81, steps = 34 13:31:35 [INFO] train episode 52201: reward = -32.08, steps = 27 13:31:39 [INFO] train episode 52202: reward = -23.19, steps = 40 13:31:41 [INFO] train episode 52203: reward = -20.88, steps = 22 13:31:44 [INFO] train episode 52204: reward = 0.07, steps = 38 13:31:47 [INFO] train episode 52205: reward = -25.95, steps = 35 13:31:50 [INFO] train episode 52206: reward = -22.10, steps = 35 13:31:54 [INFO] train episode 52207: reward = -16.77, steps = 36 13:31:57 [INFO] train episode 52208: reward = 2.02, steps = 40 13:32:00 [INFO] train episode 52209: reward = -27.21, steps = 40 13:32:03 [INFO] train episode 52210: reward = -37.22, steps = 21 13:32:05 [INFO] train episode 52211: reward = -40.28, steps = 29 13:32:07 [INFO] train episode 52212: reward = -29.16, steps = 23 13:32:10 [INFO] train episode 52213: reward = -17.38, steps = 31 13:32:13 [INFO] train episode 52214: reward = -16.61, steps = 36 13:32:16 [INFO] train episode 52215: reward = -13.89, steps = 31 13:32:19 [INFO] train episode 52216: reward = -47.99, steps = 35 13:32:21 [INFO] train episode 52217: reward = -34.22, steps = 27 13:32:24 [INFO] train episode 52218: reward = -20.15, steps = 28 13:32:26 [INFO] train episode 52219: reward = -23.00, steps = 23 13:32:29 [INFO] train episode 52220: reward = -7.35, steps = 32 13:32:31 [INFO] train episode 52221: reward = -19.08, steps = 26 13:32:34 [INFO] train episode 52222: reward = -24.24, steps = 32 13:32:38 [INFO] train episode 52223: reward = -35.90, steps = 36 13:32:41 [INFO] train episode 52224: reward = -15.43, steps = 39 13:32:44 [INFO] train episode 52225: reward = -47.48, steps = 29 13:32:46 [INFO] train episode 52226: reward = -34.00, steps = 20 13:32:49 [INFO] train episode 52227: reward = -8.28, steps = 40 13:32:52 [INFO] train episode 52228: reward = -40.15, steps = 23 13:32:54 [INFO] train episode 52229: reward = -5.86, steps = 33 13:32:58 [INFO] train episode 52230: reward = -13.96, steps = 42 13:33:00 [INFO] train episode 52231: reward = -20.45, steps = 25 13:33:03 [INFO] train episode 52232: reward = -38.17, steps = 34 13:33:07 [INFO] train episode 52233: reward = -20.57, steps = 42 13:33:10 [INFO] train episode 52234: reward = -19.41, steps = 27 13:33:13 [INFO] train episode 52235: reward = -19.46, steps = 33 13:33:15 [INFO] train episode 52236: reward = -11.61, steps = 30 13:33:17 [INFO] train episode 52237: reward = -33.89, steps = 22 13:33:19 [INFO] train episode 52238: reward = -24.50, steps = 23 13:33:23 [INFO] train episode 52239: reward = -10.55, steps = 43 13:33:25 [INFO] train episode 52240: reward = -17.38, steps = 23 13:33:29 [INFO] train episode 52241: reward = -14.28, steps = 37 13:33:32 [INFO] train episode 52242: reward = -64.75, steps = 36 13:33:34 [INFO] train episode 52243: reward = -18.61, steps = 26 13:33:37 [INFO] train episode 52244: reward = -14.43, steps = 31 13:33:40 [INFO] train episode 52245: reward = -13.93, steps = 33 13:33:43 [INFO] train episode 52246: reward = -44.01, steps = 23 13:33:47 [INFO] train episode 52247: reward = -7.15, steps = 47 13:33:51 [INFO] train episode 52248: reward = 3.96, steps = 41 13:33:54 [INFO] train episode 52249: reward = -16.41, steps = 45 13:33:58 [INFO] train episode 52250: reward = 3.22, steps = 40 13:34:00 [INFO] train episode 52251: reward = -44.10, steps = 21 13:34:03 [INFO] train episode 52252: reward = -25.23, steps = 28 13:34:05 [INFO] train episode 52253: reward = -27.87, steps = 22 13:34:09 [INFO] train episode 52254: reward = -36.07, steps = 47 13:34:11 [INFO] train episode 52255: reward = -8.14, steps = 30 13:34:15 [INFO] train episode 52256: reward = -9.85, steps = 37 13:34:17 [INFO] train episode 52257: reward = -33.47, steps = 25 13:34:20 [INFO] train episode 52258: reward = -9.03, steps = 28 13:34:22 [INFO] train episode 52259: reward = -17.44, steps = 32 13:34:25 [INFO] train episode 52260: reward = -14.97, steps = 35 13:34:29 [INFO] train episode 52261: reward = -20.59, steps = 38 13:34:31 [INFO] train episode 52262: reward = -32.43, steps = 19 13:34:33 [INFO] train episode 52263: reward = -21.81, steps = 20 13:34:35 [INFO] train episode 52264: reward = -43.37, steps = 27 13:34:39 [INFO] train episode 52265: reward = 1.09, steps = 47 13:34:43 [INFO] train episode 52266: reward = -2.92, steps = 47 13:34:46 [INFO] train episode 52267: reward = -10.48, steps = 34 13:34:49 [INFO] train episode 52268: reward = -24.19, steps = 24 13:34:53 [INFO] train episode 52269: reward = -25.66, steps = 49 13:34:55 [INFO] train episode 52270: reward = -19.39, steps = 26 13:34:58 [INFO] train episode 52271: reward = -14.00, steps = 29 13:35:00 [INFO] train episode 52272: reward = -42.15, steps = 21 13:35:03 [INFO] train episode 52273: reward = -29.91, steps = 34 13:35:06 [INFO] train episode 52274: reward = -25.44, steps = 31 13:35:07 [INFO] train episode 52275: reward = -31.98, steps = 22 13:35:11 [INFO] train episode 52276: reward = 0.58, steps = 46 13:35:13 [INFO] train episode 52277: reward = -32.36, steps = 17 13:35:16 [INFO] train episode 52278: reward = -9.16, steps = 33 13:35:21 [INFO] train episode 52279: reward = 4.10, steps = 50 13:35:24 [INFO] train episode 52280: reward = 0.40, steps = 44 13:35:28 [INFO] train episode 52281: reward = -0.42, steps = 46 13:35:31 [INFO] train episode 52282: reward = -9.62, steps = 38 13:35:34 [INFO] train episode 52283: reward = -34.35, steps = 25 13:35:39 [INFO] train episode 52284: reward = 10.06, steps = 57 13:35:42 [INFO] train episode 52285: reward = -12.01, steps = 32 13:35:44 [INFO] train episode 52286: reward = -29.54, steps = 31 13:35:47 [INFO] train episode 52287: reward = -13.36, steps = 33 13:35:51 [INFO] train episode 52288: reward = -25.01, steps = 35 13:35:53 [INFO] train episode 52289: reward = -28.21, steps = 26 13:35:57 [INFO] train episode 52290: reward = -6.11, steps = 46 13:36:00 [INFO] train episode 52291: reward = -3.77, steps = 36 13:36:03 [INFO] train episode 52292: reward = -5.19, steps = 35 13:36:05 [INFO] train episode 52293: reward = -40.12, steps = 20 13:36:08 [INFO] train episode 52294: reward = -47.13, steps = 33 13:36:10 [INFO] train episode 52295: reward = -39.05, steps = 19 13:36:12 [INFO] train episode 52296: reward = -40.85, steps = 22 13:36:15 [INFO] train episode 52297: reward = 1.12, steps = 33 13:36:18 [INFO] train episode 52298: reward = -10.43, steps = 39 13:36:20 [INFO] train episode 52299: reward = -20.56, steps = 22 13:36:23 [INFO] train episode 52300: reward = -5.30, steps = 30 13:36:26 [INFO] train episode 52301: reward = -36.94, steps = 30 13:36:29 [INFO] train episode 52302: reward = -16.66, steps = 34 13:36:32 [INFO] train episode 52303: reward = -8.95, steps = 41 13:36:37 [INFO] train episode 52304: reward = -1.08, steps = 44 13:36:40 [INFO] train episode 52305: reward = -29.35, steps = 27 13:36:41 [INFO] train episode 52306: reward = -46.48, steps = 20 13:36:44 [INFO] train episode 52307: reward = -28.16, steps = 31 13:36:47 [INFO] train episode 52308: reward = -8.06, steps = 33 13:36:50 [INFO] train episode 52309: reward = -42.61, steps = 35 13:36:52 [INFO] train episode 52310: reward = -25.19, steps = 22 13:36:55 [INFO] train episode 52311: reward = -6.03, steps = 38 13:36:59 [INFO] train episode 52312: reward = -10.22, steps = 35 13:37:03 [INFO] train episode 52313: reward = -25.18, steps = 56 13:37:07 [INFO] train episode 52314: reward = -27.43, steps = 40 13:37:09 [INFO] train episode 52315: reward = -21.10, steps = 27 13:37:13 [INFO] train episode 52316: reward = -55.69, steps = 34 13:37:14 [INFO] train episode 52317: reward = -25.69, steps = 20 13:37:17 [INFO] train episode 52318: reward = -43.39, steps = 33 13:37:20 [INFO] train episode 52319: reward = -33.80, steps = 32 13:37:23 [INFO] train episode 52320: reward = -10.00, steps = 39 13:37:26 [INFO] train episode 52321: reward = -24.96, steps = 36 13:37:30 [INFO] train episode 52322: reward = -2.51, steps = 38 13:37:32 [INFO] train episode 52323: reward = -19.70, steps = 24 13:37:36 [INFO] train episode 52324: reward = -15.19, steps = 38 13:37:40 [INFO] train episode 52325: reward = -21.01, steps = 46 13:37:44 [INFO] train episode 52326: reward = -14.86, steps = 47 13:37:48 [INFO] train episode 52327: reward = -11.89, steps = 45 13:37:51 [INFO] train episode 52328: reward = -5.87, steps = 33 13:37:54 [INFO] train episode 52329: reward = -10.41, steps = 40 13:37:57 [INFO] train episode 52330: reward = -15.41, steps = 31 13:38:00 [INFO] train episode 52331: reward = -25.05, steps = 38 13:38:02 [INFO] train episode 52332: reward = -29.61, steps = 20 13:38:05 [INFO] train episode 52333: reward = -19.10, steps = 28 13:38:07 [INFO] train episode 52334: reward = -46.20, steps = 22 13:38:09 [INFO] train episode 52335: reward = -18.01, steps = 31 13:38:13 [INFO] train episode 52336: reward = -48.88, steps = 44 13:38:15 [INFO] train episode 52337: reward = -23.50, steps = 19 13:38:18 [INFO] train episode 52338: reward = -27.67, steps = 29 13:38:19 [INFO] train episode 52339: reward = -19.33, steps = 20 13:38:22 [INFO] train episode 52340: reward = -22.91, steps = 32 13:38:26 [INFO] train episode 52341: reward = -23.71, steps = 49 13:38:28 [INFO] train episode 52342: reward = -33.27, steps = 24 13:38:31 [INFO] train episode 52343: reward = -18.78, steps = 27 13:38:34 [INFO] train episode 52344: reward = -13.60, steps = 28 13:38:37 [INFO] train episode 52345: reward = -5.13, steps = 39 13:38:39 [INFO] train episode 52346: reward = -23.51, steps = 26 13:38:43 [INFO] train episode 52347: reward = -13.83, steps = 41 13:38:45 [INFO] train episode 52348: reward = -14.18, steps = 22 13:38:48 [INFO] train episode 52349: reward = -22.36, steps = 33 13:38:50 [INFO] train episode 52350: reward = -31.94, steps = 22 13:38:53 [INFO] train episode 52351: reward = -13.67, steps = 36 13:38:56 [INFO] train episode 52352: reward = -23.04, steps = 33 13:39:00 [INFO] train episode 52353: reward = -23.82, steps = 43 13:39:03 [INFO] train episode 52354: reward = 0.65, steps = 40 13:39:05 [INFO] train episode 52355: reward = -27.84, steps = 20 13:39:07 [INFO] train episode 52356: reward = -38.92, steps = 23 13:39:10 [INFO] train episode 52357: reward = -34.77, steps = 35 13:39:14 [INFO] train episode 52358: reward = -11.06, steps = 46 13:39:16 [INFO] train episode 52359: reward = -22.82, steps = 25 13:39:19 [INFO] train episode 52360: reward = -16.25, steps = 30 13:39:22 [INFO] train episode 52361: reward = -16.53, steps = 30 13:39:25 [INFO] train episode 52362: reward = -32.74, steps = 31 13:39:27 [INFO] train episode 52363: reward = -15.30, steps = 29 13:39:31 [INFO] train episode 52364: reward = -6.49, steps = 34 13:39:34 [INFO] train episode 52365: reward = -7.19, steps = 35 13:39:38 [INFO] train episode 52366: reward = -6.76, steps = 44 13:39:41 [INFO] train episode 52367: reward = 1.22, steps = 37 13:39:43 [INFO] train episode 52368: reward = -33.35, steps = 20 13:39:45 [INFO] train episode 52369: reward = -23.72, steps = 22 13:39:48 [INFO] train episode 52370: reward = -12.54, steps = 29 13:39:50 [INFO] train episode 52371: reward = -16.97, steps = 27 13:39:53 [INFO] train episode 52372: reward = -6.64, steps = 33 13:39:56 [INFO] train episode 52373: reward = -24.69, steps = 27 13:39:57 [INFO] train episode 52374: reward = -36.05, steps = 20 13:40:00 [INFO] train episode 52375: reward = -18.59, steps = 29 13:40:02 [INFO] train episode 52376: reward = -7.42, steps = 25 13:40:05 [INFO] train episode 52377: reward = -40.31, steps = 30 13:40:08 [INFO] train episode 52378: reward = -15.23, steps = 35 13:40:11 [INFO] train episode 52379: reward = -18.59, steps = 35 13:40:14 [INFO] train episode 52380: reward = -25.57, steps = 30 13:40:17 [INFO] train episode 52381: reward = -15.82, steps = 31 13:40:19 [INFO] train episode 52382: reward = -16.03, steps = 22 13:40:22 [INFO] train episode 52383: reward = -7.21, steps = 37 13:40:25 [INFO] train episode 52384: reward = -16.04, steps = 42 13:40:28 [INFO] train episode 52385: reward = -6.64, steps = 30 13:40:31 [INFO] train episode 52386: reward = -5.79, steps = 36 13:40:38 [INFO] train episode 52387: reward = -28.25, steps = 73 13:40:41 [INFO] train episode 52388: reward = -22.26, steps = 39 13:40:44 [INFO] train episode 52389: reward = -10.55, steps = 31 13:40:48 [INFO] train episode 52390: reward = -3.62, steps = 48 13:40:52 [INFO] train episode 52391: reward = -3.34, steps = 41 13:40:55 [INFO] train episode 52392: reward = -27.14, steps = 36 13:40:57 [INFO] train episode 52393: reward = -17.13, steps = 23 13:41:00 [INFO] train episode 52394: reward = -17.45, steps = 34 13:41:03 [INFO] train episode 52395: reward = -10.64, steps = 33 13:41:06 [INFO] train episode 52396: reward = -20.31, steps = 34 13:41:08 [INFO] train episode 52397: reward = -33.32, steps = 20 13:41:11 [INFO] train episode 52398: reward = -23.35, steps = 43 13:41:14 [INFO] train episode 52399: reward = 5.34, steps = 37 13:41:17 [INFO] train episode 52400: reward = -11.64, steps = 30 13:41:21 [INFO] train episode 52401: reward = -15.85, steps = 37 13:41:22 [INFO] train episode 52402: reward = -35.15, steps = 20 13:41:26 [INFO] train episode 52403: reward = -20.13, steps = 40 13:41:28 [INFO] train episode 52404: reward = -30.00, steps = 28 13:41:30 [INFO] train episode 52405: reward = -49.25, steps = 22 13:41:34 [INFO] train episode 52406: reward = -14.27, steps = 42 13:41:37 [INFO] train episode 52407: reward = 2.78, steps = 36 13:41:39 [INFO] train episode 52408: reward = -42.38, steps = 19 13:41:41 [INFO] train episode 52409: reward = -36.28, steps = 24 13:41:43 [INFO] train episode 52410: reward = -17.32, steps = 24 13:41:47 [INFO] train episode 52411: reward = -1.29, steps = 51 13:41:52 [INFO] train episode 52412: reward = 3.00, steps = 50 13:41:54 [INFO] train episode 52413: reward = -32.43, steps = 28 13:41:58 [INFO] train episode 52414: reward = 3.77, steps = 42 13:42:01 [INFO] train episode 52415: reward = -49.16, steps = 39 13:42:05 [INFO] train episode 52416: reward = -13.54, steps = 34 13:42:08 [INFO] train episode 52417: reward = -15.15, steps = 37 13:42:11 [INFO] train episode 52418: reward = -10.17, steps = 36 13:42:14 [INFO] train episode 52419: reward = -30.06, steps = 31 13:42:16 [INFO] train episode 52420: reward = -31.81, steps = 21 13:42:20 [INFO] train episode 52421: reward = 2.29, steps = 45 13:42:22 [INFO] train episode 52422: reward = -23.21, steps = 28 13:42:25 [INFO] train episode 52423: reward = -21.57, steps = 26 13:42:28 [INFO] train episode 52424: reward = -18.32, steps = 25 13:42:29 [INFO] train episode 52425: reward = -21.74, steps = 22 13:42:33 [INFO] train episode 52426: reward = -15.83, steps = 42 13:42:35 [INFO] train episode 52427: reward = -37.09, steps = 24 13:42:38 [INFO] train episode 52428: reward = -20.97, steps = 19 13:42:41 [INFO] train episode 52429: reward = -16.42, steps = 37 13:42:44 [INFO] train episode 52430: reward = -22.15, steps = 41 13:42:47 [INFO] train episode 52431: reward = -23.54, steps = 32 13:42:51 [INFO] train episode 52432: reward = 5.08, steps = 45 13:42:56 [INFO] train episode 52433: reward = -14.43, steps = 46 13:42:58 [INFO] train episode 52434: reward = -27.01, steps = 24 13:43:02 [INFO] train episode 52435: reward = -7.19, steps = 42 13:43:04 [INFO] train episode 52436: reward = -31.75, steps = 23 13:43:07 [INFO] train episode 52437: reward = -16.27, steps = 38 13:43:10 [INFO] train episode 52438: reward = -19.15, steps = 31 13:43:14 [INFO] train episode 52439: reward = -23.00, steps = 42 13:43:16 [INFO] train episode 52440: reward = -26.40, steps = 30 13:43:20 [INFO] train episode 52441: reward = -14.99, steps = 44 13:43:22 [INFO] train episode 52442: reward = -21.51, steps = 23 13:43:25 [INFO] train episode 52443: reward = -52.69, steps = 27 13:43:29 [INFO] train episode 52444: reward = -11.35, steps = 44 13:43:32 [INFO] train episode 52445: reward = -8.95, steps = 36 13:43:34 [INFO] train episode 52446: reward = -27.87, steps = 23 13:43:40 [INFO] train episode 52447: reward = 7.42, steps = 64 13:43:42 [INFO] train episode 52448: reward = -40.89, steps = 19 13:43:45 [INFO] train episode 52449: reward = 6.51, steps = 37 13:43:48 [INFO] train episode 52450: reward = -30.88, steps = 30 13:43:50 [INFO] train episode 52451: reward = -12.18, steps = 27 13:43:54 [INFO] train episode 52452: reward = -4.94, steps = 45 13:43:57 [INFO] train episode 52453: reward = -23.34, steps = 40 13:44:01 [INFO] train episode 52454: reward = -24.73, steps = 34 13:44:04 [INFO] train episode 52455: reward = -2.41, steps = 38 13:44:07 [INFO] train episode 52456: reward = -9.53, steps = 37 13:44:10 [INFO] train episode 52457: reward = -35.23, steps = 34 13:44:13 [INFO] train episode 52458: reward = -15.42, steps = 37 13:44:17 [INFO] train episode 52459: reward = -15.45, steps = 36 13:44:20 [INFO] train episode 52460: reward = -36.03, steps = 41 13:44:23 [INFO] train episode 52461: reward = -19.31, steps = 33 13:44:25 [INFO] train episode 52462: reward = -17.53, steps = 30 13:44:27 [INFO] train episode 52463: reward = -28.15, steps = 22 13:44:29 [INFO] train episode 52464: reward = -33.47, steps = 22 13:44:34 [INFO] train episode 52465: reward = -4.61, steps = 45 13:44:37 [INFO] train episode 52466: reward = -22.71, steps = 44 13:44:40 [INFO] train episode 52467: reward = -19.65, steps = 27 13:44:42 [INFO] train episode 52468: reward = -10.74, steps = 27 13:44:45 [INFO] train episode 52469: reward = -18.36, steps = 33 13:44:48 [INFO] train episode 52470: reward = -33.77, steps = 30 13:44:50 [INFO] train episode 52471: reward = -22.33, steps = 22 13:44:52 [INFO] train episode 52472: reward = -15.88, steps = 27 13:44:55 [INFO] train episode 52473: reward = -14.86, steps = 31 13:44:58 [INFO] train episode 52474: reward = -10.56, steps = 34 13:45:02 [INFO] train episode 52475: reward = 17.08, steps = 46 13:45:05 [INFO] train episode 52476: reward = -17.05, steps = 33 13:45:08 [INFO] train episode 52477: reward = -12.82, steps = 31 13:45:11 [INFO] train episode 52478: reward = -12.62, steps = 40 13:45:14 [INFO] train episode 52479: reward = -15.35, steps = 30 13:45:17 [INFO] train episode 52480: reward = -13.45, steps = 42 13:45:21 [INFO] train episode 52481: reward = -12.59, steps = 32 13:45:26 [INFO] train episode 52482: reward = -7.85, steps = 49 13:45:30 [INFO] train episode 52483: reward = 7.56, steps = 50 13:45:32 [INFO] train episode 52484: reward = -27.27, steps = 22 13:45:34 [INFO] train episode 52485: reward = -8.80, steps = 30 13:45:38 [INFO] train episode 52486: reward = -1.96, steps = 33 13:45:43 [INFO] train episode 52487: reward = -14.60, steps = 48 13:45:45 [INFO] train episode 52488: reward = -23.66, steps = 24 13:45:48 [INFO] train episode 52489: reward = -31.04, steps = 35 13:45:51 [INFO] train episode 52490: reward = 4.21, steps = 36 13:45:56 [INFO] train episode 52491: reward = -5.51, steps = 51 13:45:58 [INFO] train episode 52492: reward = -31.27, steps = 23 13:46:00 [INFO] train episode 52493: reward = -21.46, steps = 25 13:46:03 [INFO] train episode 52494: reward = -7.65, steps = 29 13:46:05 [INFO] train episode 52495: reward = -33.28, steps = 23 13:46:08 [INFO] train episode 52496: reward = -1.56, steps = 38 13:46:13 [INFO] train episode 52497: reward = -28.17, steps = 43 13:46:15 [INFO] train episode 52498: reward = -29.70, steps = 23 13:46:16 [INFO] train episode 52499: reward = -34.82, steps = 21 13:46:19 [INFO] train episode 52500: reward = -25.05, steps = 27 13:46:22 [INFO] train episode 52501: reward = -24.85, steps = 36 13:46:24 [INFO] train episode 52502: reward = -15.42, steps = 26 13:46:27 [INFO] train episode 52503: reward = -47.40, steps = 30 13:46:29 [INFO] train episode 52504: reward = -50.51, steps = 17 13:46:32 [INFO] train episode 52505: reward = -11.54, steps = 35 13:46:35 [INFO] train episode 52506: reward = -19.62, steps = 39 13:46:38 [INFO] train episode 52507: reward = -33.51, steps = 32 13:46:42 [INFO] train episode 52508: reward = -6.10, steps = 47 13:46:46 [INFO] train episode 52509: reward = -9.08, steps = 37 13:46:50 [INFO] train episode 52510: reward = -16.95, steps = 47 13:46:53 [INFO] train episode 52511: reward = -22.71, steps = 29 13:46:57 [INFO] train episode 52512: reward = 4.54, steps = 47 13:47:00 [INFO] train episode 52513: reward = -12.85, steps = 38 13:47:03 [INFO] train episode 52514: reward = -6.38, steps = 28 13:47:08 [INFO] train episode 52515: reward = 2.78, steps = 58 13:47:11 [INFO] train episode 52516: reward = -6.93, steps = 39 13:47:16 [INFO] train episode 52517: reward = -2.44, steps = 53 13:47:18 [INFO] train episode 52518: reward = -30.16, steps = 21 13:47:20 [INFO] train episode 52519: reward = -19.04, steps = 26 13:47:23 [INFO] train episode 52520: reward = -21.38, steps = 32 13:47:26 [INFO] train episode 52521: reward = -29.50, steps = 37 13:47:30 [INFO] train episode 52522: reward = -25.49, steps = 37 13:47:32 [INFO] train episode 52523: reward = -15.11, steps = 22 13:47:35 [INFO] train episode 52524: reward = -21.11, steps = 31 13:47:37 [INFO] train episode 52525: reward = -27.74, steps = 27 13:47:40 [INFO] train episode 52526: reward = -18.49, steps = 40 13:47:44 [INFO] train episode 52527: reward = -39.50, steps = 45 13:47:47 [INFO] train episode 52528: reward = -28.68, steps = 30 13:47:49 [INFO] train episode 52529: reward = -42.56, steps = 23 13:47:52 [INFO] train episode 52530: reward = -28.16, steps = 31 13:47:54 [INFO] train episode 52531: reward = -16.18, steps = 28 13:47:57 [INFO] train episode 52532: reward = -15.18, steps = 27 13:48:00 [INFO] train episode 52533: reward = -13.17, steps = 37 13:48:03 [INFO] train episode 52534: reward = -1.31, steps = 35 13:48:05 [INFO] train episode 52535: reward = -45.76, steps = 21 13:48:08 [INFO] train episode 52536: reward = -27.63, steps = 32 13:48:10 [INFO] train episode 52537: reward = -13.30, steps = 24 13:48:12 [INFO] train episode 52538: reward = -24.95, steps = 26 13:48:16 [INFO] train episode 52539: reward = -13.86, steps = 38 13:48:20 [INFO] train episode 52540: reward = -39.23, steps = 36 13:48:23 [INFO] train episode 52541: reward = -6.79, steps = 38 13:48:27 [INFO] train episode 52542: reward = -19.29, steps = 37 13:48:29 [INFO] train episode 52543: reward = -33.96, steps = 26 13:48:33 [INFO] train episode 52544: reward = -9.42, steps = 45 13:48:36 [INFO] train episode 52545: reward = -16.05, steps = 34 13:48:38 [INFO] train episode 52546: reward = -28.44, steps = 25 13:48:41 [INFO] train episode 52547: reward = -10.84, steps = 28 13:48:44 [INFO] train episode 52548: reward = -15.40, steps = 29 13:48:46 [INFO] train episode 52549: reward = -22.05, steps = 21 13:48:48 [INFO] train episode 52550: reward = -26.27, steps = 22 13:48:52 [INFO] train episode 52551: reward = -4.39, steps = 45 13:48:54 [INFO] train episode 52552: reward = -10.20, steps = 33 13:48:58 [INFO] train episode 52553: reward = -12.32, steps = 36 13:49:01 [INFO] train episode 52554: reward = -14.38, steps = 30 13:49:03 [INFO] train episode 52555: reward = -33.23, steps = 22 13:49:06 [INFO] train episode 52556: reward = -4.45, steps = 44 13:49:10 [INFO] train episode 52557: reward = 6.12, steps = 48 13:49:13 [INFO] train episode 52558: reward = -35.20, steps = 25 13:49:17 [INFO] train episode 52559: reward = 3.63, steps = 40 13:49:19 [INFO] train episode 52560: reward = -10.88, steps = 33 13:49:22 [INFO] train episode 52561: reward = -16.39, steps = 32 13:49:25 [INFO] train episode 52562: reward = -18.22, steps = 29 13:49:28 [INFO] train episode 52563: reward = -20.66, steps = 33 13:49:31 [INFO] train episode 52564: reward = -13.48, steps = 32 13:49:33 [INFO] train episode 52565: reward = -32.02, steps = 24 13:49:35 [INFO] train episode 52566: reward = -19.39, steps = 27 13:49:39 [INFO] train episode 52567: reward = -12.24, steps = 40 13:49:42 [INFO] train episode 52568: reward = 13.14, steps = 44 13:49:45 [INFO] train episode 52569: reward = -17.80, steps = 26 13:49:49 [INFO] train episode 52570: reward = -58.97, steps = 46 13:49:52 [INFO] train episode 52571: reward = -13.49, steps = 38 13:49:55 [INFO] train episode 52572: reward = -35.52, steps = 28 13:49:58 [INFO] train episode 52573: reward = -16.74, steps = 39 13:50:01 [INFO] train episode 52574: reward = -16.65, steps = 28 13:50:03 [INFO] train episode 52575: reward = -37.83, steps = 26 13:50:08 [INFO] train episode 52576: reward = -16.78, steps = 48 13:50:11 [INFO] train episode 52577: reward = 5.63, steps = 40 13:50:15 [INFO] train episode 52578: reward = -7.52, steps = 41 13:50:17 [INFO] train episode 52579: reward = -43.04, steps = 20 13:50:19 [INFO] train episode 52580: reward = -27.63, steps = 20 13:50:21 [INFO] train episode 52581: reward = -41.90, steps = 23 13:50:23 [INFO] train episode 52582: reward = -15.37, steps = 30 13:50:27 [INFO] train episode 52583: reward = -9.81, steps = 38 13:50:29 [INFO] train episode 52584: reward = -24.75, steps = 19 13:50:32 [INFO] train episode 52585: reward = -3.62, steps = 35 13:50:34 [INFO] train episode 52586: reward = -34.62, steps = 21 13:50:37 [INFO] train episode 52587: reward = -26.44, steps = 32 13:50:39 [INFO] train episode 52588: reward = -33.24, steps = 21 13:50:41 [INFO] train episode 52589: reward = -4.25, steps = 29 13:50:44 [INFO] train episode 52590: reward = -8.23, steps = 36 13:50:47 [INFO] train episode 52591: reward = -36.40, steps = 29 13:50:50 [INFO] train episode 52592: reward = -24.49, steps = 33 13:50:53 [INFO] train episode 52593: reward = -15.64, steps = 29 13:50:55 [INFO] train episode 52594: reward = -20.85, steps = 21 13:50:58 [INFO] train episode 52595: reward = 3.68, steps = 42 13:51:04 [INFO] train episode 52596: reward = -1.02, steps = 62 13:51:07 [INFO] train episode 52597: reward = -19.71, steps = 28 13:51:08 [INFO] train episode 52598: reward = -29.43, steps = 20 13:51:11 [INFO] train episode 52599: reward = -8.35, steps = 36 13:51:14 [INFO] train episode 52600: reward = -29.72, steps = 30 13:51:18 [INFO] train episode 52601: reward = -23.92, steps = 33 13:51:21 [INFO] train episode 52602: reward = -0.79, steps = 44 13:51:26 [INFO] train episode 52603: reward = 6.19, steps = 55 13:51:29 [INFO] train episode 52604: reward = -8.55, steps = 34 13:51:33 [INFO] train episode 52605: reward = -11.92, steps = 39 13:51:37 [INFO] train episode 52606: reward = 1.35, steps = 48 13:51:40 [INFO] train episode 52607: reward = -15.50, steps = 29 13:51:42 [INFO] train episode 52608: reward = -28.95, steps = 26 13:51:45 [INFO] train episode 52609: reward = -8.52, steps = 38 13:51:47 [INFO] train episode 52610: reward = -28.68, steps = 20 13:51:49 [INFO] train episode 52611: reward = -29.95, steps = 21 13:51:52 [INFO] train episode 52612: reward = -25.65, steps = 34 13:51:55 [INFO] train episode 52613: reward = -17.73, steps = 38 13:51:59 [INFO] train episode 52614: reward = -7.70, steps = 41 13:52:03 [INFO] train episode 52615: reward = 10.75, steps = 52 13:52:06 [INFO] train episode 52616: reward = -11.67, steps = 31 13:52:11 [INFO] train episode 52617: reward = -1.37, steps = 52 13:52:14 [INFO] train episode 52618: reward = -20.14, steps = 37 13:52:17 [INFO] train episode 52619: reward = -5.06, steps = 38 13:52:21 [INFO] train episode 52620: reward = -3.23, steps = 42 13:52:24 [INFO] train episode 52621: reward = -29.57, steps = 31 13:52:26 [INFO] train episode 52622: reward = -12.77, steps = 29 13:52:29 [INFO] train episode 52623: reward = -23.26, steps = 24 13:52:30 [INFO] train episode 52624: reward = -40.27, steps = 20 13:52:34 [INFO] train episode 52625: reward = -21.71, steps = 36 13:52:36 [INFO] train episode 52626: reward = -6.85, steps = 24 13:52:39 [INFO] train episode 52627: reward = -6.57, steps = 40 13:52:41 [INFO] train episode 52628: reward = -38.97, steps = 18 13:52:44 [INFO] train episode 52629: reward = -45.15, steps = 31 13:52:47 [INFO] train episode 52630: reward = -2.67, steps = 38 13:52:51 [INFO] train episode 52631: reward = -42.63, steps = 41 13:52:53 [INFO] train episode 52632: reward = -26.02, steps = 26 13:52:55 [INFO] train episode 52633: reward = -38.56, steps = 20 13:52:59 [INFO] train episode 52634: reward = -7.79, steps = 45 13:53:03 [INFO] train episode 52635: reward = -76.60, steps = 51 13:53:06 [INFO] train episode 52636: reward = -28.96, steps = 27 13:53:09 [INFO] train episode 52637: reward = -12.91, steps = 38 13:53:12 [INFO] train episode 52638: reward = -15.27, steps = 35 13:53:14 [INFO] train episode 52639: reward = -36.12, steps = 20 13:53:18 [INFO] train episode 52640: reward = -9.62, steps = 40 13:53:21 [INFO] train episode 52641: reward = -27.69, steps = 41 13:53:24 [INFO] train episode 52642: reward = -2.89, steps = 41 13:53:28 [INFO] train episode 52643: reward = -12.31, steps = 40 13:53:32 [INFO] train episode 52644: reward = -23.43, steps = 37 13:53:34 [INFO] train episode 52645: reward = -16.33, steps = 27 13:53:38 [INFO] train episode 52646: reward = -3.82, steps = 44 13:53:41 [INFO] train episode 52647: reward = -12.07, steps = 42 13:53:44 [INFO] train episode 52648: reward = -12.01, steps = 29 13:53:47 [INFO] train episode 52649: reward = -3.50, steps = 34 13:53:50 [INFO] train episode 52650: reward = 0.90, steps = 35 13:53:53 [INFO] train episode 52651: reward = -24.97, steps = 32 13:53:57 [INFO] train episode 52652: reward = -6.44, steps = 52 13:53:59 [INFO] train episode 52653: reward = -33.67, steps = 22 13:54:02 [INFO] train episode 52654: reward = -10.07, steps = 36 13:54:06 [INFO] train episode 52655: reward = 1.58, steps = 36 13:54:07 [INFO] train episode 52656: reward = -32.64, steps = 19 13:54:09 [INFO] train episode 52657: reward = -24.97, steps = 21 13:54:13 [INFO] train episode 52658: reward = -10.60, steps = 40 13:54:17 [INFO] train episode 52659: reward = 11.56, steps = 41 13:54:20 [INFO] train episode 52660: reward = -9.48, steps = 32 13:54:24 [INFO] train episode 52661: reward = -13.52, steps = 41 13:54:25 [INFO] train episode 52662: reward = -50.32, steps = 21 13:54:28 [INFO] train episode 52663: reward = -16.84, steps = 31 13:54:31 [INFO] train episode 52664: reward = -11.93, steps = 36 13:54:36 [INFO] train episode 52665: reward = -20.46, steps = 48 13:54:41 [INFO] train episode 52666: reward = -8.38, steps = 62 13:54:45 [INFO] train episode 52667: reward = 4.76, steps = 45 13:54:49 [INFO] train episode 52668: reward = -2.99, steps = 39 13:54:52 [INFO] train episode 52669: reward = -15.31, steps = 36 13:54:55 [INFO] train episode 52670: reward = -21.08, steps = 38 13:54:57 [INFO] train episode 52671: reward = -27.37, steps = 21 13:54:59 [INFO] train episode 52672: reward = -18.23, steps = 24 13:55:02 [INFO] train episode 52673: reward = -39.52, steps = 26 13:55:05 [INFO] train episode 52674: reward = -4.87, steps = 40 13:55:10 [INFO] train episode 52675: reward = 4.77, steps = 48 13:55:13 [INFO] train episode 52676: reward = 1.58, steps = 37 13:55:17 [INFO] train episode 52677: reward = -36.11, steps = 50 13:55:19 [INFO] train episode 52678: reward = -26.11, steps = 22 13:55:24 [INFO] train episode 52679: reward = -11.01, steps = 60 13:55:27 [INFO] train episode 52680: reward = -22.54, steps = 28 13:55:30 [INFO] train episode 52681: reward = -30.47, steps = 39 13:55:34 [INFO] train episode 52682: reward = 2.54, steps = 40 13:55:36 [INFO] train episode 52683: reward = -10.27, steps = 34 13:55:39 [INFO] train episode 52684: reward = -19.75, steps = 30 13:55:42 [INFO] train episode 52685: reward = -12.38, steps = 36 13:55:45 [INFO] train episode 52686: reward = -22.03, steps = 28 13:55:48 [INFO] train episode 52687: reward = -22.61, steps = 32 13:55:52 [INFO] train episode 52688: reward = -3.16, steps = 50 13:55:55 [INFO] train episode 52689: reward = -21.29, steps = 34 13:55:58 [INFO] train episode 52690: reward = -12.45, steps = 35 13:56:02 [INFO] train episode 52691: reward = -37.74, steps = 39 13:56:05 [INFO] train episode 52692: reward = 9.91, steps = 42 13:56:09 [INFO] train episode 52693: reward = -11.89, steps = 40 13:56:11 [INFO] train episode 52694: reward = -23.00, steps = 25 13:56:15 [INFO] train episode 52695: reward = 0.21, steps = 43 13:56:18 [INFO] train episode 52696: reward = -12.11, steps = 28 13:56:21 [INFO] train episode 52697: reward = -9.49, steps = 41 13:56:24 [INFO] train episode 52698: reward = 4.54, steps = 37 13:56:28 [INFO] train episode 52699: reward = 2.03, steps = 39 13:56:30 [INFO] train episode 52700: reward = -25.68, steps = 20 13:56:32 [INFO] train episode 52701: reward = -31.20, steps = 26 13:56:34 [INFO] train episode 52702: reward = -13.75, steps = 25 13:56:38 [INFO] train episode 52703: reward = -19.35, steps = 46 13:56:41 [INFO] train episode 52704: reward = -7.65, steps = 30 13:56:43 [INFO] train episode 52705: reward = -19.05, steps = 26 13:56:46 [INFO] train episode 52706: reward = -29.15, steps = 23 13:56:50 [INFO] train episode 52707: reward = -20.08, steps = 44 13:56:51 [INFO] train episode 52708: reward = -28.20, steps = 22 13:56:55 [INFO] train episode 52709: reward = 10.08, steps = 44 13:56:58 [INFO] train episode 52710: reward = -7.27, steps = 32 13:57:00 [INFO] train episode 52711: reward = -21.15, steps = 26 13:57:04 [INFO] train episode 52712: reward = -6.04, steps = 40 13:57:08 [INFO] train episode 52713: reward = -4.97, steps = 34 13:57:11 [INFO] train episode 52714: reward = -23.24, steps = 39 13:57:13 [INFO] train episode 52715: reward = -26.81, steps = 23 13:57:17 [INFO] train episode 52716: reward = 16.03, steps = 43 13:57:19 [INFO] train episode 52717: reward = -43.14, steps = 19 13:57:21 [INFO] train episode 52718: reward = -8.02, steps = 29 13:57:25 [INFO] train episode 52719: reward = -3.49, steps = 41 13:57:28 [INFO] train episode 52720: reward = -11.14, steps = 36 13:57:31 [INFO] train episode 52721: reward = -29.57, steps = 28 13:57:34 [INFO] train episode 52722: reward = 7.26, steps = 38 13:57:36 [INFO] train episode 52723: reward = -36.12, steps = 22 13:57:38 [INFO] train episode 52724: reward = -7.78, steps = 26 13:57:42 [INFO] train episode 52725: reward = 5.27, steps = 38 13:57:45 [INFO] train episode 52726: reward = -3.26, steps = 40 13:57:48 [INFO] train episode 52727: reward = -11.85, steps = 39 13:57:54 [INFO] train episode 52728: reward = -0.47, steps = 58 13:57:56 [INFO] train episode 52729: reward = -20.92, steps = 31 13:58:01 [INFO] train episode 52730: reward = 15.00, steps = 54 13:58:03 [INFO] train episode 52731: reward = -25.48, steps = 25 13:58:08 [INFO] train episode 52732: reward = 3.31, steps = 50 13:58:12 [INFO] train episode 52733: reward = 5.67, steps = 41 13:58:14 [INFO] train episode 52734: reward = -30.51, steps = 25 13:58:16 [INFO] train episode 52735: reward = -31.96, steps = 26 13:58:18 [INFO] train episode 52736: reward = -32.83, steps = 22 13:58:22 [INFO] train episode 52737: reward = -9.34, steps = 44 13:58:25 [INFO] train episode 52738: reward = -24.21, steps = 32 13:58:28 [INFO] train episode 52739: reward = -27.17, steps = 41 13:58:31 [INFO] train episode 52740: reward = -17.95, steps = 30 13:58:34 [INFO] train episode 52741: reward = -34.60, steps = 33 13:58:36 [INFO] train episode 52742: reward = -20.95, steps = 29 13:58:40 [INFO] train episode 52743: reward = -12.73, steps = 40 13:58:44 [INFO] train episode 52744: reward = 1.79, steps = 43 13:58:47 [INFO] train episode 52745: reward = -7.56, steps = 27 13:58:49 [INFO] train episode 52746: reward = -21.29, steps = 24 13:58:53 [INFO] train episode 52747: reward = -9.21, steps = 47 13:58:57 [INFO] train episode 52748: reward = -5.52, steps = 43 13:58:59 [INFO] train episode 52749: reward = -26.00, steps = 22 13:59:02 [INFO] train episode 52750: reward = -24.06, steps = 31 13:59:06 [INFO] train episode 52751: reward = 10.58, steps = 50 13:59:09 [INFO] train episode 52752: reward = 1.83, steps = 38 13:59:12 [INFO] train episode 52753: reward = -32.57, steps = 36 13:59:14 [INFO] train episode 52754: reward = -29.27, steps = 21 13:59:17 [INFO] train episode 52755: reward = 4.24, steps = 38 13:59:21 [INFO] train episode 52756: reward = 1.89, steps = 45 13:59:24 [INFO] train episode 52757: reward = -1.15, steps = 29 13:59:28 [INFO] train episode 52758: reward = -19.97, steps = 39 13:59:31 [INFO] train episode 52759: reward = -9.25, steps = 33 13:59:33 [INFO] train episode 52760: reward = -17.69, steps = 26 13:59:37 [INFO] train episode 52761: reward = 1.41, steps = 47 13:59:40 [INFO] train episode 52762: reward = -9.22, steps = 34 13:59:43 [INFO] train episode 52763: reward = -15.29, steps = 33 13:59:45 [INFO] train episode 52764: reward = -34.98, steps = 21 13:59:47 [INFO] train episode 52765: reward = -27.23, steps = 25 13:59:50 [INFO] train episode 52766: reward = -21.83, steps = 36 13:59:52 [INFO] train episode 52767: reward = -37.81, steps = 21 13:59:56 [INFO] train episode 52768: reward = 12.08, steps = 47 13:59:59 [INFO] train episode 52769: reward = -18.97, steps = 29 14:00:02 [INFO] train episode 52770: reward = -15.59, steps = 30 14:00:06 [INFO] train episode 52771: reward = -20.57, steps = 47 14:00:10 [INFO] train episode 52772: reward = 3.94, steps = 38 14:00:14 [INFO] train episode 52773: reward = 12.66, steps = 48 14:00:15 [INFO] train episode 52774: reward = -17.12, steps = 19 14:00:19 [INFO] train episode 52775: reward = -7.48, steps = 43 14:00:22 [INFO] train episode 52776: reward = -17.78, steps = 25 14:00:24 [INFO] train episode 52777: reward = -15.06, steps = 27 14:00:28 [INFO] train episode 52778: reward = 1.40, steps = 45 14:00:31 [INFO] train episode 52779: reward = -19.67, steps = 41 14:00:35 [INFO] train episode 52780: reward = -32.10, steps = 34 14:00:38 [INFO] train episode 52781: reward = 6.65, steps = 40 14:00:41 [INFO] train episode 52782: reward = 1.86, steps = 37 14:00:45 [INFO] train episode 52783: reward = -3.61, steps = 48 14:00:48 [INFO] train episode 52784: reward = -15.69, steps = 33 14:00:52 [INFO] train episode 52785: reward = -10.04, steps = 33 14:00:54 [INFO] train episode 52786: reward = -37.24, steps = 28 14:00:56 [INFO] train episode 52787: reward = -10.27, steps = 26 14:01:00 [INFO] train episode 52788: reward = -9.44, steps = 45 14:01:04 [INFO] train episode 52789: reward = -9.37, steps = 45 14:01:07 [INFO] train episode 52790: reward = 6.06, steps = 37 14:01:09 [INFO] train episode 52791: reward = -27.56, steps = 22 14:01:12 [INFO] train episode 52792: reward = -18.05, steps = 26 14:01:14 [INFO] train episode 52793: reward = -26.52, steps = 26 14:01:17 [INFO] train episode 52794: reward = -1.79, steps = 33 14:01:20 [INFO] train episode 52795: reward = -7.17, steps = 38 14:01:24 [INFO] train episode 52796: reward = -12.07, steps = 38 14:01:28 [INFO] train episode 52797: reward = -32.18, steps = 51 14:01:31 [INFO] train episode 52798: reward = -10.32, steps = 38 14:01:35 [INFO] train episode 52799: reward = -3.66, steps = 44 14:01:39 [INFO] train episode 52800: reward = -7.82, steps = 48 14:01:43 [INFO] train episode 52801: reward = 6.09, steps = 42 14:01:45 [INFO] train episode 52802: reward = -17.29, steps = 23 14:01:47 [INFO] train episode 52803: reward = -19.33, steps = 21 14:01:49 [INFO] train episode 52804: reward = -9.13, steps = 30 14:01:52 [INFO] train episode 52805: reward = -6.52, steps = 34 14:01:56 [INFO] train episode 52806: reward = 1.52, steps = 40 14:02:00 [INFO] train episode 52807: reward = -11.03, steps = 48 14:02:02 [INFO] train episode 52808: reward = -35.80, steps = 20 14:02:05 [INFO] train episode 52809: reward = -6.50, steps = 37 14:02:08 [INFO] train episode 52810: reward = 4.35, steps = 35 14:02:12 [INFO] train episode 52811: reward = -12.56, steps = 40 14:02:15 [INFO] train episode 52812: reward = -6.55, steps = 40 14:02:19 [INFO] train episode 52813: reward = 2.20, steps = 45 14:02:22 [INFO] train episode 52814: reward = -4.36, steps = 30 14:02:26 [INFO] train episode 52815: reward = -28.24, steps = 44 14:02:28 [INFO] train episode 52816: reward = -44.95, steps = 19 14:02:30 [INFO] train episode 52817: reward = -18.31, steps = 27 14:02:32 [INFO] train episode 52818: reward = -23.40, steps = 25 14:02:34 [INFO] train episode 52819: reward = -34.17, steps = 21 14:02:36 [INFO] train episode 52820: reward = -27.47, steps = 23 14:02:38 [INFO] train episode 52821: reward = -30.61, steps = 20 14:02:42 [INFO] train episode 52822: reward = -11.96, steps = 45 14:02:47 [INFO] train episode 52823: reward = -2.93, steps = 57 14:02:51 [INFO] train episode 52824: reward = 0.56, steps = 44 14:02:55 [INFO] train episode 52825: reward = 2.33, steps = 35 14:02:59 [INFO] train episode 52826: reward = 2.51, steps = 50 14:03:03 [INFO] train episode 52827: reward = -28.11, steps = 37 14:03:06 [INFO] train episode 52828: reward = -23.80, steps = 36 14:03:09 [INFO] train episode 52829: reward = -22.03, steps = 40 14:03:12 [INFO] train episode 52830: reward = -18.36, steps = 27 14:03:13 [INFO] train episode 52831: reward = -25.38, steps = 22 14:03:18 [INFO] train episode 52832: reward = -3.98, steps = 44 14:03:20 [INFO] train episode 52833: reward = -36.54, steps = 29 14:03:23 [INFO] train episode 52834: reward = -13.35, steps = 29 14:03:25 [INFO] train episode 52835: reward = -42.58, steps = 19 14:03:27 [INFO] train episode 52836: reward = -21.65, steps = 29 14:03:30 [INFO] train episode 52837: reward = -8.55, steps = 29 14:03:33 [INFO] train episode 52838: reward = 0.95, steps = 30 14:03:36 [INFO] train episode 52839: reward = 0.48, steps = 34 14:03:38 [INFO] train episode 52840: reward = -18.54, steps = 32 14:03:41 [INFO] train episode 52841: reward = -31.54, steps = 37 14:03:44 [INFO] train episode 52842: reward = -16.34, steps = 32 14:03:48 [INFO] train episode 52843: reward = 2.96, steps = 36 14:03:50 [INFO] train episode 52844: reward = -27.76, steps = 20 14:03:53 [INFO] train episode 52845: reward = 6.64, steps = 39 14:03:56 [INFO] train episode 52846: reward = -33.29, steps = 36 14:03:59 [INFO] train episode 52847: reward = -8.17, steps = 31 14:04:02 [INFO] train episode 52848: reward = -4.42, steps = 37 14:04:07 [INFO] train episode 52849: reward = 7.81, steps = 59 14:04:11 [INFO] train episode 52850: reward = -8.29, steps = 39 14:04:14 [INFO] train episode 52851: reward = -4.92, steps = 42 14:04:17 [INFO] train episode 52852: reward = -23.15, steps = 22 14:04:18 [INFO] train episode 52853: reward = -37.14, steps = 22 14:04:23 [INFO] train episode 52854: reward = -1.37, steps = 48 14:04:26 [INFO] train episode 52855: reward = -23.22, steps = 31 14:04:30 [INFO] train episode 52856: reward = 3.86, steps = 50 14:04:32 [INFO] train episode 52857: reward = -41.31, steps = 24 14:04:35 [INFO] train episode 52858: reward = -0.96, steps = 37 14:04:39 [INFO] train episode 52859: reward = -24.83, steps = 34 14:04:41 [INFO] train episode 52860: reward = -24.45, steps = 30 14:04:45 [INFO] train episode 52861: reward = 3.70, steps = 47 14:04:47 [INFO] train episode 52862: reward = -22.60, steps = 22 14:04:50 [INFO] train episode 52863: reward = -0.82, steps = 34 14:04:52 [INFO] train episode 52864: reward = -30.27, steps = 21 14:04:55 [INFO] train episode 52865: reward = -1.80, steps = 36 14:04:58 [INFO] train episode 52866: reward = -22.62, steps = 33 14:05:02 [INFO] train episode 52867: reward = -18.11, steps = 41 14:05:04 [INFO] train episode 52868: reward = -33.87, steps = 22 14:05:07 [INFO] train episode 52869: reward = -18.50, steps = 35 14:05:10 [INFO] train episode 52870: reward = -12.65, steps = 37 14:05:14 [INFO] train episode 52871: reward = 4.55, steps = 37 14:05:18 [INFO] train episode 52872: reward = 0.57, steps = 48 14:05:19 [INFO] train episode 52873: reward = -28.71, steps = 21 14:05:24 [INFO] train episode 52874: reward = -13.39, steps = 48 14:05:27 [INFO] train episode 52875: reward = -28.44, steps = 34 14:05:29 [INFO] train episode 52876: reward = -26.12, steps = 28 14:05:32 [INFO] train episode 52877: reward = 0.65, steps = 35 14:05:36 [INFO] train episode 52878: reward = -11.08, steps = 41 14:05:40 [INFO] train episode 52879: reward = -10.67, steps = 48 14:05:43 [INFO] train episode 52880: reward = -8.86, steps = 34 14:05:46 [INFO] train episode 52881: reward = -18.65, steps = 33 14:05:49 [INFO] train episode 52882: reward = -8.91, steps = 31 14:05:52 [INFO] train episode 52883: reward = -2.62, steps = 35 14:05:55 [INFO] train episode 52884: reward = -15.53, steps = 26 14:05:59 [INFO] train episode 52885: reward = -2.17, steps = 42 14:06:02 [INFO] train episode 52886: reward = -1.06, steps = 43 14:06:06 [INFO] train episode 52887: reward = -29.87, steps = 45 14:06:08 [INFO] train episode 52888: reward = -12.77, steps = 23 14:06:10 [INFO] train episode 52889: reward = -33.96, steps = 25 14:06:14 [INFO] train episode 52890: reward = -4.13, steps = 33 14:06:18 [INFO] train episode 52891: reward = -7.18, steps = 52 14:06:20 [INFO] train episode 52892: reward = -13.72, steps = 25 14:06:22 [INFO] train episode 52893: reward = -26.54, steps = 23 14:06:25 [INFO] train episode 52894: reward = -6.62, steps = 35 14:06:29 [INFO] train episode 52895: reward = -5.84, steps = 41 14:06:33 [INFO] train episode 52896: reward = 0.37, steps = 45 14:06:37 [INFO] train episode 52897: reward = -4.63, steps = 40 14:06:40 [INFO] train episode 52898: reward = 11.72, steps = 39 14:06:43 [INFO] train episode 52899: reward = -6.08, steps = 37 14:06:48 [INFO] train episode 52900: reward = -31.68, steps = 50 14:06:50 [INFO] train episode 52901: reward = -25.53, steps = 20 14:06:53 [INFO] train episode 52902: reward = -3.15, steps = 41 14:06:56 [INFO] train episode 52903: reward = -17.08, steps = 30 14:06:59 [INFO] train episode 52904: reward = -45.15, steps = 34 14:07:01 [INFO] train episode 52905: reward = -26.65, steps = 21 14:07:03 [INFO] train episode 52906: reward = -14.69, steps = 29 14:07:06 [INFO] train episode 52907: reward = -0.72, steps = 28 14:07:09 [INFO] train episode 52908: reward = -1.08, steps = 36 14:07:12 [INFO] train episode 52909: reward = -2.92, steps = 35 14:07:15 [INFO] train episode 52910: reward = -21.67, steps = 33 14:07:18 [INFO] train episode 52911: reward = -13.36, steps = 33 14:07:22 [INFO] train episode 52912: reward = -16.93, steps = 43 14:07:24 [INFO] train episode 52913: reward = -32.70, steps = 26 14:07:28 [INFO] train episode 52914: reward = -1.85, steps = 43 14:07:31 [INFO] train episode 52915: reward = -23.88, steps = 33 14:07:32 [INFO] train episode 52916: reward = -39.75, steps = 19 14:07:36 [INFO] train episode 52917: reward = -10.40, steps = 43 14:07:40 [INFO] train episode 52918: reward = -17.14, steps = 39 14:07:43 [INFO] train episode 52919: reward = -20.35, steps = 45 14:07:46 [INFO] train episode 52920: reward = -47.21, steps = 36 14:07:50 [INFO] train episode 52921: reward = -4.57, steps = 40 14:07:54 [INFO] train episode 52922: reward = -15.68, steps = 40 14:07:58 [INFO] train episode 52923: reward = -25.47, steps = 46 14:07:59 [INFO] train episode 52924: reward = -26.03, steps = 20 14:08:02 [INFO] train episode 52925: reward = -13.18, steps = 27 14:08:05 [INFO] train episode 52926: reward = -22.25, steps = 34 14:08:08 [INFO] train episode 52927: reward = -24.01, steps = 31 14:08:10 [INFO] train episode 52928: reward = -22.61, steps = 24 14:08:12 [INFO] train episode 52929: reward = -21.70, steps = 21 14:08:15 [INFO] train episode 52930: reward = -12.86, steps = 34 14:08:18 [INFO] train episode 52931: reward = -36.20, steps = 38 14:08:22 [INFO] train episode 52932: reward = 11.23, steps = 46 14:08:26 [INFO] train episode 52933: reward = -7.95, steps = 35 14:08:29 [INFO] train episode 52934: reward = 0.27, steps = 33 14:08:31 [INFO] train episode 52935: reward = -11.81, steps = 27 14:08:35 [INFO] train episode 52936: reward = -19.89, steps = 47 14:08:40 [INFO] train episode 52937: reward = -19.51, steps = 53 14:08:43 [INFO] train episode 52938: reward = -0.20, steps = 33 14:08:47 [INFO] train episode 52939: reward = 2.41, steps = 47 14:08:49 [INFO] train episode 52940: reward = -22.11, steps = 24 14:08:52 [INFO] train episode 52941: reward = 0.64, steps = 28 14:08:55 [INFO] train episode 52942: reward = 2.59, steps = 37 14:09:00 [INFO] train episode 52943: reward = -16.79, steps = 54 14:09:03 [INFO] train episode 52944: reward = -28.05, steps = 26 14:09:06 [INFO] train episode 52945: reward = -10.29, steps = 40 14:09:10 [INFO] train episode 52946: reward = -7.53, steps = 48 14:09:14 [INFO] train episode 52947: reward = 0.42, steps = 45 14:09:16 [INFO] train episode 52948: reward = -27.87, steps = 22 14:09:20 [INFO] train episode 52949: reward = -2.45, steps = 39 14:09:23 [INFO] train episode 52950: reward = -23.68, steps = 38 14:09:25 [INFO] train episode 52951: reward = -30.81, steps = 20 14:09:27 [INFO] train episode 52952: reward = -25.54, steps = 22 14:09:29 [INFO] train episode 52953: reward = -13.37, steps = 23 14:09:31 [INFO] train episode 52954: reward = -32.03, steps = 22 14:09:34 [INFO] train episode 52955: reward = -1.45, steps = 34 14:09:37 [INFO] train episode 52956: reward = -0.76, steps = 40 14:09:41 [INFO] train episode 52957: reward = -8.75, steps = 42 14:09:46 [INFO] train episode 52958: reward = 4.04, steps = 53 14:09:48 [INFO] train episode 52959: reward = -8.25, steps = 29 14:09:51 [INFO] train episode 52960: reward = -21.16, steps = 35 14:09:53 [INFO] train episode 52961: reward = -25.53, steps = 22 14:09:56 [INFO] train episode 52962: reward = -10.23, steps = 33 14:09:59 [INFO] train episode 52963: reward = -30.33, steps = 36 14:10:02 [INFO] train episode 52964: reward = -20.31, steps = 22 14:10:05 [INFO] train episode 52965: reward = -34.70, steps = 38 14:10:09 [INFO] train episode 52966: reward = -3.78, steps = 44 14:10:10 [INFO] train episode 52967: reward = -23.89, steps = 20 14:10:14 [INFO] train episode 52968: reward = -3.41, steps = 42 14:10:16 [INFO] train episode 52969: reward = -23.57, steps = 28 14:10:19 [INFO] train episode 52970: reward = -26.10, steps = 31 14:10:23 [INFO] train episode 52971: reward = -9.52, steps = 36 14:10:24 [INFO] train episode 52972: reward = -33.84, steps = 20 14:10:27 [INFO] train episode 52973: reward = -6.93, steps = 31 14:10:30 [INFO] train episode 52974: reward = -9.48, steps = 31 14:10:33 [INFO] train episode 52975: reward = 1.23, steps = 39 14:10:38 [INFO] train episode 52976: reward = 1.58, steps = 46 14:10:41 [INFO] train episode 52977: reward = -0.69, steps = 35 14:10:45 [INFO] train episode 52978: reward = 6.86, steps = 47 14:10:48 [INFO] train episode 52979: reward = -0.67, steps = 42 14:10:52 [INFO] train episode 52980: reward = -24.73, steps = 41 14:10:54 [INFO] train episode 52981: reward = -12.25, steps = 23 14:10:56 [INFO] train episode 52982: reward = -28.49, steps = 25 14:10:59 [INFO] train episode 52983: reward = -2.58, steps = 35 14:11:02 [INFO] train episode 52984: reward = -30.19, steps = 26 14:11:04 [INFO] train episode 52985: reward = -28.10, steps = 28 14:11:09 [INFO] train episode 52986: reward = -0.69, steps = 49 14:11:12 [INFO] train episode 52987: reward = 3.79, steps = 43 14:11:15 [INFO] train episode 52988: reward = -5.82, steps = 32 14:11:19 [INFO] train episode 52989: reward = -5.88, steps = 44 14:11:22 [INFO] train episode 52990: reward = -16.94, steps = 25 14:11:25 [INFO] train episode 52991: reward = -12.56, steps = 41 14:11:28 [INFO] train episode 52992: reward = -7.66, steps = 33 14:11:30 [INFO] train episode 52993: reward = -24.19, steps = 23 14:11:32 [INFO] train episode 52994: reward = -26.68, steps = 21 14:11:34 [INFO] train episode 52995: reward = -23.49, steps = 30 14:11:39 [INFO] train episode 52996: reward = -5.42, steps = 35 14:11:41 [INFO] train episode 52997: reward = 1.78, steps = 31 14:11:44 [INFO] train episode 52998: reward = -11.33, steps = 36 14:11:47 [INFO] train episode 52999: reward = -6.58, steps = 32 14:11:50 [INFO] train episode 53000: reward = -16.68, steps = 30 14:11:53 [INFO] train episode 53001: reward = -9.49, steps = 36 14:11:56 [INFO] train episode 53002: reward = 3.75, steps = 33 14:12:00 [INFO] train episode 53003: reward = -14.92, steps = 45 14:12:03 [INFO] train episode 53004: reward = -17.04, steps = 31 14:12:05 [INFO] train episode 53005: reward = -10.57, steps = 30 14:12:08 [INFO] train episode 53006: reward = -15.99, steps = 29 14:12:11 [INFO] train episode 53007: reward = -13.13, steps = 29 14:12:15 [INFO] train episode 53008: reward = -8.57, steps = 46 14:12:17 [INFO] train episode 53009: reward = -18.06, steps = 31 14:12:19 [INFO] train episode 53010: reward = -41.63, steps = 22 14:12:22 [INFO] train episode 53011: reward = -27.60, steps = 30 14:12:25 [INFO] train episode 53012: reward = -11.31, steps = 37 14:12:30 [INFO] train episode 53013: reward = -6.45, steps = 57 14:12:33 [INFO] train episode 53014: reward = 2.69, steps = 37 14:12:36 [INFO] train episode 53015: reward = -28.30, steps = 31 14:12:40 [INFO] train episode 53016: reward = -18.33, steps = 38 14:12:42 [INFO] train episode 53017: reward = -10.48, steps = 34 14:12:47 [INFO] train episode 53018: reward = 5.36, steps = 41 14:12:49 [INFO] train episode 53019: reward = -34.88, steps = 24 14:12:52 [INFO] train episode 53020: reward = -12.57, steps = 38 14:12:55 [INFO] train episode 53021: reward = 9.10, steps = 35 14:12:57 [INFO] train episode 53022: reward = -35.97, steps = 26 14:13:04 [INFO] train episode 53023: reward = -49.38, steps = 75 14:13:07 [INFO] train episode 53024: reward = -15.01, steps = 33 14:13:09 [INFO] train episode 53025: reward = -12.82, steps = 28 14:13:12 [INFO] train episode 53026: reward = -17.61, steps = 25 14:13:14 [INFO] train episode 53027: reward = -12.98, steps = 29 14:13:17 [INFO] train episode 53028: reward = -12.16, steps = 26 14:13:19 [INFO] train episode 53029: reward = -31.63, steps = 25 14:13:22 [INFO] train episode 53030: reward = -8.46, steps = 34 14:13:24 [INFO] train episode 53031: reward = -24.46, steps = 20 14:13:26 [INFO] train episode 53032: reward = -26.19, steps = 27 14:13:30 [INFO] train episode 53033: reward = -7.03, steps = 47 14:13:34 [INFO] train episode 53034: reward = 16.05, steps = 51 14:13:38 [INFO] train episode 53035: reward = -8.23, steps = 38 14:13:41 [INFO] train episode 53036: reward = -20.99, steps = 33 14:13:44 [INFO] train episode 53037: reward = -10.88, steps = 36 14:13:47 [INFO] train episode 53038: reward = -5.40, steps = 35 14:13:50 [INFO] train episode 53039: reward = -25.46, steps = 26 14:13:53 [INFO] train episode 53040: reward = -9.69, steps = 40 14:13:56 [INFO] train episode 53041: reward = -43.14, steps = 35 14:13:58 [INFO] train episode 53042: reward = -23.65, steps = 22 14:14:01 [INFO] train episode 53043: reward = -25.77, steps = 35 14:14:03 [INFO] train episode 53044: reward = -41.10, steps = 20 14:14:07 [INFO] train episode 53045: reward = -5.31, steps = 48 14:14:09 [INFO] train episode 53046: reward = -20.05, steps = 24 14:14:13 [INFO] train episode 53047: reward = -16.35, steps = 38 14:14:17 [INFO] train episode 53048: reward = 2.06, steps = 43 14:14:21 [INFO] train episode 53049: reward = -32.00, steps = 46 14:14:23 [INFO] train episode 53050: reward = -19.84, steps = 28 14:14:26 [INFO] train episode 53051: reward = -26.44, steps = 31 14:14:32 [INFO] train episode 53052: reward = 6.08, steps = 60 14:14:34 [INFO] train episode 53053: reward = -37.97, steps = 21 14:14:37 [INFO] train episode 53054: reward = -18.76, steps = 34 14:14:40 [INFO] train episode 53055: reward = -13.85, steps = 28 14:14:44 [INFO] train episode 53056: reward = -3.62, steps = 48 14:14:46 [INFO] train episode 53057: reward = -34.46, steps = 27 14:14:49 [INFO] train episode 53058: reward = -40.24, steps = 27 14:14:51 [INFO] train episode 53059: reward = -27.42, steps = 24 14:14:54 [INFO] train episode 53060: reward = -16.05, steps = 31 14:14:57 [INFO] train episode 53061: reward = -29.21, steps = 31 14:14:59 [INFO] train episode 53062: reward = -27.56, steps = 25 14:15:02 [INFO] train episode 53063: reward = -5.93, steps = 32 14:15:03 [INFO] train episode 53064: reward = -24.72, steps = 18 14:15:06 [INFO] train episode 53065: reward = -21.77, steps = 27 14:15:10 [INFO] train episode 53066: reward = 1.79, steps = 51 14:15:15 [INFO] train episode 53067: reward = 0.59, steps = 54 14:15:17 [INFO] train episode 53068: reward = -14.21, steps = 27 14:15:21 [INFO] train episode 53069: reward = -8.16, steps = 38 14:15:24 [INFO] train episode 53070: reward = -29.20, steps = 44 14:15:28 [INFO] train episode 53071: reward = -1.79, steps = 35 14:15:34 [INFO] train episode 53072: reward = -26.48, steps = 75 14:15:37 [INFO] train episode 53073: reward = -15.13, steps = 32 14:15:40 [INFO] train episode 53074: reward = -17.69, steps = 39 14:15:44 [INFO] train episode 53075: reward = -31.28, steps = 44 14:15:47 [INFO] train episode 53076: reward = -19.83, steps = 27 14:15:49 [INFO] train episode 53077: reward = -23.42, steps = 31 14:15:52 [INFO] train episode 53078: reward = -1.07, steps = 36 14:15:55 [INFO] train episode 53079: reward = -4.51, steps = 32 14:15:59 [INFO] train episode 53080: reward = 18.18, steps = 38 14:16:01 [INFO] train episode 53081: reward = -21.35, steps = 25 14:16:05 [INFO] train episode 53082: reward = -5.56, steps = 44 14:16:07 [INFO] train episode 53083: reward = -16.64, steps = 25 14:16:11 [INFO] train episode 53084: reward = -5.39, steps = 46 14:16:15 [INFO] train episode 53085: reward = 2.60, steps = 42 14:16:19 [INFO] train episode 53086: reward = 3.38, steps = 42 14:16:23 [INFO] train episode 53087: reward = -6.83, steps = 54 14:16:27 [INFO] train episode 53088: reward = 13.15, steps = 45 14:16:30 [INFO] train episode 53089: reward = -6.87, steps = 35 14:16:34 [INFO] train episode 53090: reward = -22.68, steps = 37 14:16:36 [INFO] train episode 53091: reward = -23.85, steps = 26 14:16:40 [INFO] train episode 53092: reward = 9.58, steps = 41 14:16:43 [INFO] train episode 53093: reward = -38.64, steps = 43 14:16:47 [INFO] train episode 53094: reward = 3.24, steps = 43 14:16:50 [INFO] train episode 53095: reward = -16.26, steps = 36 14:16:53 [INFO] train episode 53096: reward = -17.76, steps = 27 14:16:55 [INFO] train episode 53097: reward = -28.91, steps = 20 14:16:58 [INFO] train episode 53098: reward = 13.44, steps = 37 14:17:01 [INFO] train episode 53099: reward = -22.77, steps = 35 14:17:03 [INFO] train episode 53100: reward = -22.92, steps = 22 14:17:13 [INFO] train episode 53101: reward = -49.60, steps = 117 14:17:17 [INFO] train episode 53102: reward = -6.83, steps = 39 14:17:21 [INFO] train episode 53103: reward = -10.00, steps = 49 14:17:23 [INFO] train episode 53104: reward = -16.33, steps = 28 14:17:28 [INFO] train episode 53105: reward = -1.42, steps = 43 14:17:32 [INFO] train episode 53106: reward = 8.02, steps = 46 14:17:35 [INFO] train episode 53107: reward = 0.34, steps = 33 14:17:37 [INFO] train episode 53108: reward = -35.37, steps = 23 14:17:40 [INFO] train episode 53109: reward = -6.01, steps = 35 14:17:43 [INFO] train episode 53110: reward = -14.41, steps = 31 14:17:45 [INFO] train episode 53111: reward = -22.86, steps = 31 14:17:48 [INFO] train episode 53112: reward = -3.60, steps = 34 14:17:52 [INFO] train episode 53113: reward = 7.41, steps = 32 14:17:55 [INFO] train episode 53114: reward = 3.45, steps = 44 14:17:57 [INFO] train episode 53115: reward = -37.84, steps = 20 14:18:00 [INFO] train episode 53116: reward = -4.31, steps = 38 14:18:04 [INFO] train episode 53117: reward = 11.55, steps = 44 14:18:07 [INFO] train episode 53118: reward = -33.29, steps = 26 14:18:10 [INFO] train episode 53119: reward = -7.74, steps = 36 14:18:13 [INFO] train episode 53120: reward = -28.61, steps = 39 14:18:17 [INFO] train episode 53121: reward = -17.08, steps = 43 14:18:20 [INFO] train episode 53122: reward = -15.82, steps = 32 14:18:24 [INFO] train episode 53123: reward = -17.09, steps = 46 14:18:28 [INFO] train episode 53124: reward = 8.10, steps = 42 14:18:31 [INFO] train episode 53125: reward = 2.79, steps = 36 14:18:34 [INFO] train episode 53126: reward = -3.32, steps = 35 14:18:38 [INFO] train episode 53127: reward = 10.87, steps = 42 14:18:43 [INFO] train episode 53128: reward = 6.28, steps = 54 14:18:46 [INFO] train episode 53129: reward = 6.35, steps = 42 14:18:50 [INFO] train episode 53130: reward = -5.68, steps = 39 14:18:52 [INFO] train episode 53131: reward = -21.11, steps = 31 14:18:55 [INFO] train episode 53132: reward = -8.31, steps = 32 14:18:58 [INFO] train episode 53133: reward = -12.51, steps = 31 14:19:02 [INFO] train episode 53134: reward = -47.54, steps = 42 14:19:04 [INFO] train episode 53135: reward = -52.60, steps = 21 14:19:06 [INFO] train episode 53136: reward = -20.28, steps = 34 14:19:09 [INFO] train episode 53137: reward = -13.75, steps = 29 14:19:13 [INFO] train episode 53138: reward = -7.73, steps = 40 14:19:15 [INFO] train episode 53139: reward = -40.85, steps = 27 14:19:17 [INFO] train episode 53140: reward = -36.97, steps = 21 14:19:20 [INFO] train episode 53141: reward = -5.14, steps = 37 14:19:22 [INFO] train episode 53142: reward = -34.89, steps = 20 14:19:24 [INFO] train episode 53143: reward = -32.29, steps = 23 14:19:28 [INFO] train episode 53144: reward = 3.34, steps = 40 14:19:34 [INFO] train episode 53145: reward = -10.95, steps = 68 14:19:36 [INFO] train episode 53146: reward = -7.96, steps = 33 14:19:39 [INFO] train episode 53147: reward = -5.17, steps = 33 14:19:43 [INFO] train episode 53148: reward = 4.15, steps = 41 14:19:46 [INFO] train episode 53149: reward = -22.93, steps = 31 14:19:49 [INFO] train episode 53150: reward = -37.43, steps = 35 14:19:52 [INFO] train episode 53151: reward = -3.33, steps = 39 14:19:56 [INFO] train episode 53152: reward = -9.59, steps = 39 14:19:59 [INFO] train episode 53153: reward = -17.12, steps = 35 14:20:01 [INFO] train episode 53154: reward = -38.53, steps = 22 14:20:03 [INFO] train episode 53155: reward = -34.95, steps = 20 14:20:05 [INFO] train episode 53156: reward = -12.59, steps = 26 14:20:07 [INFO] train episode 53157: reward = -20.92, steps = 25 14:20:10 [INFO] train episode 53158: reward = -16.92, steps = 38 14:20:13 [INFO] train episode 53159: reward = -15.93, steps = 33 14:20:16 [INFO] train episode 53160: reward = -28.24, steps = 21 14:20:20 [INFO] train episode 53161: reward = -17.48, steps = 53 14:20:24 [INFO] train episode 53162: reward = -16.91, steps = 37 14:20:27 [INFO] train episode 53163: reward = 0.71, steps = 39 14:20:30 [INFO] train episode 53164: reward = -3.09, steps = 32 14:20:35 [INFO] train episode 53165: reward = 21.69, steps = 50 14:20:37 [INFO] train episode 53166: reward = -30.68, steps = 20 14:20:39 [INFO] train episode 53167: reward = -17.25, steps = 26 14:20:44 [INFO] train episode 53168: reward = 12.40, steps = 54 14:20:46 [INFO] train episode 53169: reward = -30.21, steps = 27 14:20:50 [INFO] train episode 53170: reward = -22.96, steps = 38 14:20:53 [INFO] train episode 53171: reward = -18.89, steps = 37 14:20:56 [INFO] train episode 53172: reward = -9.41, steps = 41 14:20:59 [INFO] train episode 53173: reward = -23.62, steps = 33 14:21:05 [INFO] train episode 53174: reward = -49.00, steps = 51 14:21:09 [INFO] train episode 53175: reward = 5.56, steps = 41 14:21:11 [INFO] train episode 53176: reward = -12.82, steps = 25 14:21:14 [INFO] train episode 53177: reward = -18.58, steps = 26 14:21:17 [INFO] train episode 53178: reward = -21.86, steps = 34 14:21:21 [INFO] train episode 53179: reward = -13.76, steps = 38 14:21:23 [INFO] train episode 53180: reward = -30.42, steps = 22 14:21:27 [INFO] train episode 53181: reward = -43.39, steps = 35 14:21:30 [INFO] train episode 53182: reward = -10.71, steps = 35 14:21:31 [INFO] train episode 53183: reward = -29.11, steps = 19 14:21:33 [INFO] train episode 53184: reward = -20.65, steps = 21 14:21:35 [INFO] train episode 53185: reward = -20.80, steps = 20 14:21:37 [INFO] train episode 53186: reward = -24.23, steps = 30 14:21:40 [INFO] train episode 53187: reward = -32.65, steps = 29 14:21:43 [INFO] train episode 53188: reward = -10.20, steps = 35 14:21:47 [INFO] train episode 53189: reward = -9.44, steps = 36 14:21:49 [INFO] train episode 53190: reward = -25.77, steps = 32 14:21:51 [INFO] train episode 53191: reward = -34.17, steps = 23 14:21:54 [INFO] train episode 53192: reward = -34.77, steps = 32 14:21:58 [INFO] train episode 53193: reward = -6.37, steps = 39 14:22:02 [INFO] train episode 53194: reward = -5.88, steps = 43 14:22:05 [INFO] train episode 53195: reward = -7.58, steps = 38 14:22:08 [INFO] train episode 53196: reward = -10.73, steps = 36 14:22:13 [INFO] train episode 53197: reward = -18.35, steps = 56 14:22:17 [INFO] train episode 53198: reward = -3.42, steps = 43 14:22:20 [INFO] train episode 53199: reward = -5.65, steps = 42 14:22:23 [INFO] train episode 53200: reward = -9.69, steps = 30 14:22:26 [INFO] train episode 53201: reward = -27.88, steps = 37 14:22:31 [INFO] train episode 53202: reward = -1.82, steps = 50 14:22:34 [INFO] train episode 53203: reward = -10.31, steps = 38 14:22:37 [INFO] train episode 53204: reward = 4.45, steps = 36 14:22:41 [INFO] train episode 53205: reward = -8.02, steps = 37 14:22:48 [INFO] train episode 53206: reward = -45.04, steps = 82 14:22:51 [INFO] train episode 53207: reward = 2.11, steps = 41 14:22:55 [INFO] train episode 53208: reward = 11.35, steps = 43 14:22:58 [INFO] train episode 53209: reward = -13.45, steps = 35 14:23:02 [INFO] train episode 53210: reward = -0.96, steps = 41 14:23:05 [INFO] train episode 53211: reward = -20.65, steps = 35 14:23:08 [INFO] train episode 53212: reward = -10.14, steps = 33 14:23:12 [INFO] train episode 53213: reward = 10.65, steps = 45 14:23:15 [INFO] train episode 53214: reward = -6.97, steps = 35 14:23:23 [INFO] train episode 53215: reward = -58.23, steps = 83 14:23:25 [INFO] train episode 53216: reward = -26.64, steps = 26 14:23:28 [INFO] train episode 53217: reward = -12.26, steps = 34 14:23:30 [INFO] train episode 53218: reward = -17.68, steps = 23 14:23:35 [INFO] train episode 53219: reward = -9.19, steps = 46 14:23:37 [INFO] train episode 53220: reward = -20.70, steps = 28 14:23:39 [INFO] train episode 53221: reward = -14.52, steps = 23 14:23:43 [INFO] train episode 53222: reward = -11.69, steps = 41 14:23:46 [INFO] train episode 53223: reward = -0.44, steps = 35 14:23:50 [INFO] train episode 53224: reward = 1.59, steps = 40 14:23:53 [INFO] train episode 53225: reward = -18.24, steps = 39 14:23:56 [INFO] train episode 53226: reward = -16.61, steps = 39 14:23:59 [INFO] train episode 53227: reward = -1.32, steps = 36 14:24:03 [INFO] train episode 53228: reward = -2.09, steps = 44 14:24:07 [INFO] train episode 53229: reward = -2.81, steps = 40 14:24:11 [INFO] train episode 53230: reward = -5.23, steps = 45 14:24:13 [INFO] train episode 53231: reward = -29.96, steps = 21 14:24:16 [INFO] train episode 53232: reward = -12.17, steps = 41 14:24:19 [INFO] train episode 53233: reward = -19.70, steps = 30 14:24:22 [INFO] train episode 53234: reward = -3.31, steps = 38 14:24:26 [INFO] train episode 53235: reward = 1.84, steps = 45 14:24:30 [INFO] train episode 53236: reward = -16.79, steps = 49 14:24:34 [INFO] train episode 53237: reward = 4.40, steps = 42 14:24:38 [INFO] train episode 53238: reward = 3.63, steps = 36 14:24:40 [INFO] train episode 53239: reward = 2.54, steps = 33 14:24:42 [INFO] train episode 53240: reward = -37.99, steps = 20 14:24:45 [INFO] train episode 53241: reward = -16.54, steps = 34 14:24:47 [INFO] train episode 53242: reward = -22.42, steps = 22 14:24:50 [INFO] train episode 53243: reward = -3.12, steps = 36 14:24:54 [INFO] train episode 53244: reward = -11.62, steps = 41 14:24:59 [INFO] train episode 53245: reward = -7.24, steps = 48 14:25:01 [INFO] train episode 53246: reward = -13.08, steps = 33 14:25:06 [INFO] train episode 53247: reward = -3.00, steps = 48 14:25:09 [INFO] train episode 53248: reward = -6.25, steps = 38 14:25:12 [INFO] train episode 53249: reward = -23.22, steps = 27 14:25:14 [INFO] train episode 53250: reward = -28.46, steps = 24 14:25:18 [INFO] train episode 53251: reward = 20.01, steps = 38 14:25:20 [INFO] train episode 53252: reward = -14.31, steps = 28 14:25:23 [INFO] train episode 53253: reward = -4.39, steps = 30 14:25:27 [INFO] train episode 53254: reward = 11.09, steps = 53 14:25:30 [INFO] train episode 53255: reward = -5.48, steps = 31 14:25:33 [INFO] train episode 53256: reward = -7.17, steps = 34 14:25:37 [INFO] train episode 53257: reward = 4.32, steps = 42 14:25:40 [INFO] train episode 53258: reward = -6.93, steps = 35 14:25:43 [INFO] train episode 53259: reward = 4.21, steps = 36 14:25:45 [INFO] train episode 53260: reward = -31.20, steps = 24 14:25:48 [INFO] train episode 53261: reward = -5.27, steps = 35 14:25:52 [INFO] train episode 53262: reward = -0.73, steps = 39 14:25:55 [INFO] train episode 53263: reward = -0.05, steps = 34 14:25:57 [INFO] train episode 53264: reward = -19.55, steps = 31 14:26:01 [INFO] train episode 53265: reward = 1.18, steps = 39 14:26:05 [INFO] train episode 53266: reward = -13.37, steps = 40 14:26:07 [INFO] train episode 53267: reward = -16.53, steps = 32 14:26:10 [INFO] train episode 53268: reward = -21.88, steps = 30 14:26:13 [INFO] train episode 53269: reward = 3.99, steps = 39 14:26:16 [INFO] train episode 53270: reward = -27.41, steps = 21 14:26:20 [INFO] train episode 53271: reward = -4.63, steps = 35 14:26:23 [INFO] train episode 53272: reward = -6.73, steps = 40 14:26:26 [INFO] train episode 53273: reward = -3.73, steps = 33 14:26:28 [INFO] train episode 53274: reward = -28.26, steps = 23 14:26:31 [INFO] train episode 53275: reward = -6.89, steps = 41 14:26:34 [INFO] train episode 53276: reward = -32.52, steps = 25 14:26:38 [INFO] train episode 53277: reward = 0.81, steps = 43 14:26:42 [INFO] train episode 53278: reward = 4.31, steps = 44 14:26:44 [INFO] train episode 53279: reward = -24.97, steps = 28 14:26:47 [INFO] train episode 53280: reward = -23.91, steps = 36 14:26:50 [INFO] train episode 53281: reward = -26.16, steps = 27 14:26:53 [INFO] train episode 53282: reward = -9.19, steps = 32 14:26:56 [INFO] train episode 53283: reward = -0.11, steps = 38 14:26:59 [INFO] train episode 53284: reward = -12.53, steps = 34 14:27:02 [INFO] train episode 53285: reward = -2.16, steps = 41 14:27:06 [INFO] train episode 53286: reward = -5.35, steps = 41 14:27:09 [INFO] train episode 53287: reward = -1.36, steps = 31 14:27:12 [INFO] train episode 53288: reward = 2.96, steps = 37 14:27:16 [INFO] train episode 53289: reward = -5.40, steps = 39 14:27:17 [INFO] train episode 53290: reward = -25.15, steps = 22 14:27:22 [INFO] train episode 53291: reward = 1.83, steps = 47 14:27:25 [INFO] train episode 53292: reward = 2.37, steps = 37 14:27:27 [INFO] train episode 53293: reward = -16.17, steps = 26 14:27:30 [INFO] train episode 53294: reward = -14.12, steps = 31 14:27:34 [INFO] train episode 53295: reward = -8.22, steps = 34 14:27:37 [INFO] train episode 53296: reward = -12.60, steps = 33 14:27:40 [INFO] train episode 53297: reward = -2.69, steps = 35 14:27:43 [INFO] train episode 53298: reward = -13.53, steps = 37 14:27:46 [INFO] train episode 53299: reward = -3.51, steps = 32 14:27:50 [INFO] train episode 53300: reward = -1.67, steps = 41 14:27:51 [INFO] train episode 53301: reward = -25.41, steps = 20 14:27:54 [INFO] train episode 53302: reward = -21.87, steps = 27 14:27:57 [INFO] train episode 53303: reward = -16.15, steps = 29 14:28:00 [INFO] train episode 53304: reward = -12.54, steps = 32 14:28:02 [INFO] train episode 53305: reward = -22.03, steps = 28 14:28:05 [INFO] train episode 53306: reward = -24.92, steps = 32 14:28:08 [INFO] train episode 53307: reward = -4.65, steps = 39 14:28:12 [INFO] train episode 53308: reward = -5.54, steps = 32 14:28:15 [INFO] train episode 53309: reward = 14.41, steps = 38 14:28:18 [INFO] train episode 53310: reward = -12.02, steps = 40 14:28:23 [INFO] train episode 53311: reward = 15.16, steps = 51 14:28:28 [INFO] train episode 53312: reward = 4.74, steps = 61 14:28:32 [INFO] train episode 53313: reward = -19.48, steps = 39 14:28:36 [INFO] train episode 53314: reward = 1.29, steps = 53 14:28:40 [INFO] train episode 53315: reward = 6.27, steps = 43 14:28:45 [INFO] train episode 53316: reward = -3.43, steps = 45 14:28:49 [INFO] train episode 53317: reward = -29.35, steps = 44 14:28:52 [INFO] train episode 53318: reward = -7.30, steps = 35 14:28:55 [INFO] train episode 53319: reward = -5.63, steps = 38 14:28:57 [INFO] train episode 53320: reward = -18.17, steps = 20 14:29:01 [INFO] train episode 53321: reward = -10.16, steps = 37 14:29:04 [INFO] train episode 53322: reward = -0.88, steps = 34 14:29:07 [INFO] train episode 53323: reward = -13.65, steps = 34 14:29:11 [INFO] train episode 53324: reward = -9.98, steps = 38 14:29:14 [INFO] train episode 53325: reward = -23.45, steps = 43 14:29:19 [INFO] train episode 53326: reward = -1.82, steps = 37 14:29:22 [INFO] train episode 53327: reward = -18.57, steps = 39 14:29:25 [INFO] train episode 53328: reward = -0.58, steps = 34 14:29:28 [INFO] train episode 53329: reward = -15.20, steps = 33 14:29:32 [INFO] train episode 53330: reward = -7.73, steps = 40 14:29:34 [INFO] train episode 53331: reward = -23.49, steps = 27 14:29:37 [INFO] train episode 53332: reward = -17.02, steps = 31 14:29:42 [INFO] train episode 53333: reward = -50.23, steps = 57 14:29:44 [INFO] train episode 53334: reward = -28.93, steps = 22 14:29:48 [INFO] train episode 53335: reward = -0.85, steps = 47 14:29:52 [INFO] train episode 53336: reward = 1.95, steps = 41 14:29:54 [INFO] train episode 53337: reward = -22.01, steps = 21 14:29:56 [INFO] train episode 53338: reward = -34.95, steps = 25 14:30:00 [INFO] train episode 53339: reward = -24.30, steps = 44 14:30:03 [INFO] train episode 53340: reward = -5.85, steps = 36 14:30:06 [INFO] train episode 53341: reward = -9.16, steps = 37 14:30:09 [INFO] train episode 53342: reward = -25.90, steps = 25 14:30:12 [INFO] train episode 53343: reward = -4.68, steps = 35 14:30:16 [INFO] train episode 53344: reward = -1.31, steps = 47 14:30:19 [INFO] train episode 53345: reward = -13.62, steps = 38 14:30:22 [INFO] train episode 53346: reward = -3.91, steps = 36 14:30:25 [INFO] train episode 53347: reward = -12.71, steps = 29 14:30:29 [INFO] train episode 53348: reward = -40.00, steps = 37 14:30:31 [INFO] train episode 53349: reward = -6.37, steps = 27 14:30:34 [INFO] train episode 53350: reward = -16.22, steps = 31 14:30:36 [INFO] train episode 53351: reward = -18.06, steps = 26 14:30:38 [INFO] train episode 53352: reward = -35.42, steps = 19 14:30:41 [INFO] train episode 53353: reward = -1.97, steps = 33 14:30:44 [INFO] train episode 53354: reward = 4.77, steps = 33 14:30:46 [INFO] train episode 53355: reward = -31.57, steps = 21 14:30:49 [INFO] train episode 53356: reward = -0.72, steps = 36 14:30:52 [INFO] train episode 53357: reward = -17.73, steps = 31 14:30:54 [INFO] train episode 53358: reward = -22.48, steps = 30 14:30:58 [INFO] train episode 53359: reward = -3.48, steps = 41 14:31:02 [INFO] train episode 53360: reward = 4.36, steps = 40 14:31:04 [INFO] train episode 53361: reward = -6.03, steps = 31 14:31:08 [INFO] train episode 53362: reward = -7.30, steps = 41 14:31:11 [INFO] train episode 53363: reward = -3.59, steps = 37 14:31:14 [INFO] train episode 53364: reward = -10.10, steps = 25 14:31:16 [INFO] train episode 53365: reward = -26.63, steps = 30 14:31:19 [INFO] train episode 53366: reward = -19.24, steps = 28 14:31:22 [INFO] train episode 53367: reward = 5.08, steps = 39 14:31:26 [INFO] train episode 53368: reward = 12.47, steps = 47 14:31:28 [INFO] train episode 53369: reward = -36.23, steps = 19 14:31:32 [INFO] train episode 53370: reward = -3.56, steps = 38 14:31:35 [INFO] train episode 53371: reward = -0.97, steps = 37 14:31:38 [INFO] train episode 53372: reward = -0.25, steps = 37 14:31:41 [INFO] train episode 53373: reward = -12.45, steps = 37 14:31:44 [INFO] train episode 53374: reward = -7.15, steps = 32 14:31:47 [INFO] train episode 53375: reward = -13.28, steps = 30 14:31:51 [INFO] train episode 53376: reward = -15.73, steps = 42 14:31:53 [INFO] train episode 53377: reward = -41.16, steps = 24 14:31:57 [INFO] train episode 53378: reward = 0.48, steps = 40 14:31:59 [INFO] train episode 53379: reward = -11.71, steps = 27 14:32:00 [INFO] train episode 53380: reward = -60.98, steps = 18 14:32:03 [INFO] train episode 53381: reward = -17.10, steps = 21 14:32:05 [INFO] train episode 53382: reward = -42.50, steps = 23 14:32:09 [INFO] train episode 53383: reward = 4.12, steps = 47 14:32:12 [INFO] train episode 53384: reward = -31.15, steps = 36 14:32:17 [INFO] train episode 53385: reward = -10.53, steps = 52 14:32:21 [INFO] train episode 53386: reward = 2.21, steps = 34 14:32:24 [INFO] train episode 53387: reward = 9.03, steps = 40 14:32:27 [INFO] train episode 53388: reward = 0.61, steps = 34 14:32:30 [INFO] train episode 53389: reward = -6.89, steps = 40 14:32:34 [INFO] train episode 53390: reward = -5.34, steps = 42 14:32:39 [INFO] train episode 53391: reward = -7.39, steps = 52 14:32:43 [INFO] train episode 53392: reward = 9.13, steps = 47 14:32:47 [INFO] train episode 53393: reward = -7.64, steps = 40 14:32:49 [INFO] train episode 53394: reward = -38.55, steps = 20 14:32:53 [INFO] train episode 53395: reward = -16.86, steps = 48 14:32:57 [INFO] train episode 53396: reward = -8.92, steps = 37 14:32:59 [INFO] train episode 53397: reward = -2.23, steps = 33 14:33:03 [INFO] train episode 53398: reward = 0.85, steps = 38 14:33:05 [INFO] train episode 53399: reward = -26.02, steps = 23 14:33:09 [INFO] train episode 53400: reward = -12.80, steps = 39 14:33:11 [INFO] train episode 53401: reward = -20.36, steps = 24 14:33:14 [INFO] train episode 53402: reward = -24.55, steps = 37 14:33:16 [INFO] train episode 53403: reward = -25.23, steps = 26 14:33:19 [INFO] train episode 53404: reward = -6.02, steps = 28 14:33:21 [INFO] train episode 53405: reward = -5.92, steps = 30 14:33:25 [INFO] train episode 53406: reward = -7.48, steps = 39 14:33:29 [INFO] train episode 53407: reward = -34.46, steps = 40 14:33:32 [INFO] train episode 53408: reward = -12.30, steps = 35 14:33:35 [INFO] train episode 53409: reward = -4.36, steps = 42 14:33:38 [INFO] train episode 53410: reward = -28.06, steps = 27 14:33:40 [INFO] train episode 53411: reward = -28.11, steps = 22 14:33:44 [INFO] train episode 53412: reward = 2.75, steps = 44 14:33:48 [INFO] train episode 53413: reward = -41.67, steps = 45 14:33:50 [INFO] train episode 53414: reward = -24.13, steps = 25 14:33:53 [INFO] train episode 53415: reward = -10.58, steps = 36 14:33:56 [INFO] train episode 53416: reward = -14.86, steps = 32 14:33:59 [INFO] train episode 53417: reward = -31.09, steps = 28 14:34:02 [INFO] train episode 53418: reward = -3.42, steps = 40 14:34:06 [INFO] train episode 53419: reward = 2.28, steps = 44 14:34:09 [INFO] train episode 53420: reward = -21.15, steps = 28 14:34:12 [INFO] train episode 53421: reward = -13.92, steps = 37 14:34:14 [INFO] train episode 53422: reward = -40.35, steps = 18 14:34:17 [INFO] train episode 53423: reward = -19.73, steps = 37 14:34:19 [INFO] train episode 53424: reward = -20.75, steps = 25 14:34:23 [INFO] train episode 53425: reward = -2.80, steps = 41 14:34:25 [INFO] train episode 53426: reward = -25.76, steps = 26 14:34:27 [INFO] train episode 53427: reward = -32.73, steps = 22 14:34:29 [INFO] train episode 53428: reward = -27.27, steps = 24 14:34:31 [INFO] train episode 53429: reward = -26.48, steps = 20 14:34:33 [INFO] train episode 53430: reward = -28.36, steps = 21 14:34:37 [INFO] train episode 53431: reward = -8.76, steps = 37 14:34:40 [INFO] train episode 53432: reward = -26.76, steps = 39 14:34:44 [INFO] train episode 53433: reward = 0.15, steps = 42 14:34:47 [INFO] train episode 53434: reward = 0.84, steps = 30 14:34:50 [INFO] train episode 53435: reward = -25.01, steps = 40 14:34:54 [INFO] train episode 53436: reward = -2.69, steps = 40 14:34:58 [INFO] train episode 53437: reward = -9.40, steps = 42 14:35:01 [INFO] train episode 53438: reward = -5.26, steps = 39 14:35:04 [INFO] train episode 53439: reward = -5.24, steps = 35 14:35:06 [INFO] train episode 53440: reward = -31.26, steps = 21 14:35:09 [INFO] train episode 53441: reward = -16.18, steps = 30 14:35:15 [INFO] train episode 53442: reward = -15.16, steps = 58 14:35:18 [INFO] train episode 53443: reward = -19.26, steps = 31 14:35:21 [INFO] train episode 53444: reward = 4.89, steps = 35 14:35:24 [INFO] train episode 53445: reward = -8.44, steps = 39 14:35:29 [INFO] train episode 53446: reward = -10.62, steps = 58 14:35:32 [INFO] train episode 53447: reward = 6.25, steps = 34 14:35:36 [INFO] train episode 53448: reward = -5.72, steps = 42 14:35:39 [INFO] train episode 53449: reward = -1.83, steps = 30 14:35:43 [INFO] train episode 53450: reward = -28.14, steps = 46 14:35:45 [INFO] train episode 53451: reward = -19.10, steps = 26 14:35:49 [INFO] train episode 53452: reward = -6.48, steps = 41 14:35:52 [INFO] train episode 53453: reward = -8.96, steps = 39 14:35:56 [INFO] train episode 53454: reward = -4.95, steps = 36 14:35:58 [INFO] train episode 53455: reward = 0.84, steps = 31 14:36:00 [INFO] train episode 53456: reward = -27.03, steps = 21 14:36:03 [INFO] train episode 53457: reward = -31.23, steps = 28 14:36:06 [INFO] train episode 53458: reward = 1.31, steps = 37 14:36:11 [INFO] train episode 53459: reward = 16.40, steps = 50 14:36:14 [INFO] train episode 53460: reward = 2.65, steps = 43 14:36:18 [INFO] train episode 53461: reward = -19.86, steps = 38 14:36:20 [INFO] train episode 53462: reward = -23.66, steps = 23 14:36:24 [INFO] train episode 53463: reward = -8.45, steps = 46 14:36:28 [INFO] train episode 53464: reward = -9.78, steps = 43 14:36:31 [INFO] train episode 53465: reward = -18.53, steps = 30 14:36:33 [INFO] train episode 53466: reward = -34.04, steps = 23 14:36:36 [INFO] train episode 53467: reward = -9.72, steps = 34 14:36:39 [INFO] train episode 53468: reward = 4.70, steps = 42 14:36:43 [INFO] train episode 53469: reward = 2.75, steps = 39 14:36:46 [INFO] train episode 53470: reward = -3.67, steps = 33 14:36:51 [INFO] train episode 53471: reward = 19.88, steps = 50 14:36:55 [INFO] train episode 53472: reward = 6.29, steps = 48 14:36:57 [INFO] train episode 53473: reward = -21.92, steps = 25 14:37:00 [INFO] train episode 53474: reward = -12.70, steps = 33 14:37:04 [INFO] train episode 53475: reward = -16.47, steps = 43 14:37:08 [INFO] train episode 53476: reward = 6.92, steps = 50 14:37:12 [INFO] train episode 53477: reward = 6.01, steps = 45 14:37:15 [INFO] train episode 53478: reward = -11.71, steps = 34 14:37:18 [INFO] train episode 53479: reward = -31.00, steps = 23 14:37:20 [INFO] train episode 53480: reward = -19.02, steps = 27 14:37:24 [INFO] train episode 53481: reward = -43.03, steps = 47 14:37:28 [INFO] train episode 53482: reward = 7.34, steps = 40 14:37:31 [INFO] train episode 53483: reward = -1.31, steps = 36 14:37:35 [INFO] train episode 53484: reward = 12.79, steps = 42 14:37:38 [INFO] train episode 53485: reward = -7.12, steps = 40 14:37:40 [INFO] train episode 53486: reward = -27.59, steps = 24 14:37:42 [INFO] train episode 53487: reward = -22.65, steps = 20 14:37:45 [INFO] train episode 53488: reward = -9.99, steps = 32 14:37:47 [INFO] train episode 53489: reward = -18.40, steps = 23 14:37:50 [INFO] train episode 53490: reward = -12.80, steps = 28 14:37:52 [INFO] train episode 53491: reward = -13.49, steps = 26 14:37:55 [INFO] train episode 53492: reward = -10.58, steps = 33 14:37:59 [INFO] train episode 53493: reward = -5.04, steps = 50 14:38:02 [INFO] train episode 53494: reward = -2.20, steps = 41 14:38:06 [INFO] train episode 53495: reward = -5.59, steps = 39 14:38:08 [INFO] train episode 53496: reward = -17.13, steps = 26 14:38:12 [INFO] train episode 53497: reward = -0.99, steps = 31 14:38:15 [INFO] train episode 53498: reward = -34.58, steps = 30 14:38:18 [INFO] train episode 53499: reward = -13.88, steps = 39 14:38:20 [INFO] train episode 53500: reward = -54.97, steps = 19 14:38:23 [INFO] train episode 53501: reward = -21.90, steps = 31 14:38:25 [INFO] train episode 53502: reward = -39.06, steps = 20 14:38:27 [INFO] train episode 53503: reward = -11.64, steps = 31 14:38:30 [INFO] train episode 53504: reward = -13.25, steps = 32 14:38:34 [INFO] train episode 53505: reward = 11.72, steps = 48 14:38:36 [INFO] train episode 53506: reward = -21.51, steps = 20 14:38:40 [INFO] train episode 53507: reward = -1.61, steps = 36 14:38:43 [INFO] train episode 53508: reward = -14.66, steps = 36 14:38:47 [INFO] train episode 53509: reward = -2.87, steps = 41 14:38:50 [INFO] train episode 53510: reward = -1.27, steps = 36 14:38:53 [INFO] train episode 53511: reward = -4.95, steps = 34 14:38:57 [INFO] train episode 53512: reward = 2.47, steps = 46 14:39:00 [INFO] train episode 53513: reward = -3.66, steps = 37 14:39:04 [INFO] train episode 53514: reward = -5.68, steps = 40 14:39:07 [INFO] train episode 53515: reward = 15.74, steps = 42 14:39:10 [INFO] train episode 53516: reward = -23.14, steps = 27 14:39:12 [INFO] train episode 53517: reward = -42.37, steps = 20 14:39:15 [INFO] train episode 53518: reward = -12.15, steps = 38 14:39:18 [INFO] train episode 53519: reward = -14.84, steps = 35 14:39:21 [INFO] train episode 53520: reward = 7.91, steps = 37 14:39:26 [INFO] train episode 53521: reward = -19.95, steps = 49 14:39:28 [INFO] train episode 53522: reward = -18.30, steps = 24 14:39:31 [INFO] train episode 53523: reward = -5.36, steps = 31 14:39:34 [INFO] train episode 53524: reward = -2.02, steps = 34 14:39:37 [INFO] train episode 53525: reward = -9.67, steps = 44 14:39:41 [INFO] train episode 53526: reward = -40.68, steps = 37 14:39:44 [INFO] train episode 53527: reward = 14.96, steps = 37 14:39:48 [INFO] train episode 53528: reward = 0.47, steps = 50 14:39:51 [INFO] train episode 53529: reward = -7.81, steps = 32 14:39:54 [INFO] train episode 53530: reward = -3.23, steps = 34 14:39:57 [INFO] train episode 53531: reward = -9.57, steps = 38 14:39:59 [INFO] train episode 53532: reward = -37.41, steps = 21 14:40:03 [INFO] train episode 53533: reward = -6.56, steps = 37 14:40:09 [INFO] train episode 53534: reward = 13.44, steps = 71 14:40:11 [INFO] train episode 53535: reward = -29.51, steps = 22 14:40:13 [INFO] train episode 53536: reward = -32.55, steps = 19 14:40:15 [INFO] train episode 53537: reward = -38.72, steps = 22 14:40:18 [INFO] train episode 53538: reward = -12.89, steps = 41 14:40:22 [INFO] train episode 53539: reward = -12.75, steps = 41 14:40:25 [INFO] train episode 53540: reward = -14.35, steps = 42 14:40:28 [INFO] train episode 53541: reward = -20.31, steps = 34 14:40:31 [INFO] train episode 53542: reward = -8.19, steps = 28 14:40:34 [INFO] train episode 53543: reward = -7.15, steps = 32 14:40:37 [INFO] train episode 53544: reward = -12.97, steps = 34 14:40:41 [INFO] train episode 53545: reward = -8.29, steps = 47 14:40:44 [INFO] train episode 53546: reward = -22.23, steps = 25 14:40:46 [INFO] train episode 53547: reward = 0.57, steps = 33 14:40:50 [INFO] train episode 53548: reward = 2.77, steps = 37 14:40:52 [INFO] train episode 53549: reward = -34.96, steps = 29 14:40:56 [INFO] train episode 53550: reward = 6.46, steps = 40 14:40:59 [INFO] train episode 53551: reward = -7.45, steps = 38 14:41:03 [INFO] train episode 53552: reward = -2.91, steps = 44 14:41:08 [INFO] train episode 53553: reward = 0.85, steps = 41 14:41:10 [INFO] train episode 53554: reward = -8.10, steps = 32 14:41:14 [INFO] train episode 53555: reward = 7.43, steps = 36 14:41:17 [INFO] train episode 53556: reward = -13.80, steps = 34 14:41:20 [INFO] train episode 53557: reward = -3.02, steps = 43 14:41:24 [INFO] train episode 53558: reward = 8.95, steps = 42 14:41:27 [INFO] train episode 53559: reward = -27.13, steps = 34 14:41:30 [INFO] train episode 53560: reward = -3.80, steps = 38 14:41:33 [INFO] train episode 53561: reward = -13.84, steps = 34 14:41:37 [INFO] train episode 53562: reward = -14.54, steps = 41 14:41:41 [INFO] train episode 53563: reward = -10.93, steps = 42 14:41:44 [INFO] train episode 53564: reward = -22.68, steps = 34 14:41:46 [INFO] train episode 53565: reward = -27.18, steps = 25 14:41:50 [INFO] train episode 53566: reward = -1.09, steps = 47 14:41:53 [INFO] train episode 53567: reward = -9.38, steps = 35 14:41:57 [INFO] train episode 53568: reward = 15.54, steps = 47 14:41:59 [INFO] train episode 53569: reward = -26.98, steps = 22 14:42:01 [INFO] train episode 53570: reward = -15.72, steps = 21 14:42:04 [INFO] train episode 53571: reward = 0.02, steps = 37 14:42:07 [INFO] train episode 53572: reward = -24.61, steps = 36 14:42:11 [INFO] train episode 53573: reward = 0.60, steps = 37 14:42:16 [INFO] train episode 53574: reward = 6.56, steps = 53 14:42:18 [INFO] train episode 53575: reward = -17.95, steps = 30 14:42:21 [INFO] train episode 53576: reward = -12.56, steps = 37 14:42:25 [INFO] train episode 53577: reward = -15.52, steps = 36 14:42:28 [INFO] train episode 53578: reward = -9.33, steps = 35 14:42:31 [INFO] train episode 53579: reward = -3.06, steps = 39 14:42:35 [INFO] train episode 53580: reward = -15.13, steps = 40 14:42:37 [INFO] train episode 53581: reward = -30.78, steps = 22 14:42:40 [INFO] train episode 53582: reward = -6.26, steps = 37 14:42:44 [INFO] train episode 53583: reward = -7.28, steps = 40 14:42:49 [INFO] train episode 53584: reward = -9.10, steps = 51 14:42:51 [INFO] train episode 53585: reward = -18.39, steps = 24 14:42:54 [INFO] train episode 53586: reward = -17.42, steps = 33 14:42:57 [INFO] train episode 53587: reward = 5.60, steps = 36 14:42:59 [INFO] train episode 53588: reward = -31.93, steps = 25 14:43:03 [INFO] train episode 53589: reward = -10.11, steps = 35 14:43:06 [INFO] train episode 53590: reward = -3.08, steps = 43 14:43:10 [INFO] train episode 53591: reward = 3.76, steps = 43 14:43:12 [INFO] train episode 53592: reward = -21.57, steps = 22 14:43:15 [INFO] train episode 53593: reward = -9.63, steps = 31 14:43:18 [INFO] train episode 53594: reward = -58.18, steps = 29 14:43:21 [INFO] train episode 53595: reward = -13.06, steps = 34 14:43:24 [INFO] train episode 53596: reward = -10.36, steps = 35 14:43:26 [INFO] train episode 53597: reward = -27.83, steps = 24 14:43:28 [INFO] train episode 53598: reward = -11.92, steps = 30 14:43:32 [INFO] train episode 53599: reward = -0.05, steps = 35 14:43:34 [INFO] train episode 53600: reward = -6.69, steps = 28 14:43:36 [INFO] train episode 53601: reward = -21.10, steps = 21 14:43:39 [INFO] train episode 53602: reward = -10.65, steps = 37 14:43:42 [INFO] train episode 53603: reward = -10.60, steps = 35 14:43:45 [INFO] train episode 53604: reward = -33.32, steps = 30 14:43:47 [INFO] train episode 53605: reward = -20.44, steps = 25 14:43:50 [INFO] train episode 53606: reward = -6.86, steps = 33 14:43:54 [INFO] train episode 53607: reward = -28.54, steps = 44 14:43:58 [INFO] train episode 53608: reward = -1.32, steps = 43 14:44:03 [INFO] train episode 53609: reward = 8.50, steps = 48 14:44:06 [INFO] train episode 53610: reward = -17.18, steps = 26 14:44:08 [INFO] train episode 53611: reward = -29.75, steps = 21 14:44:11 [INFO] train episode 53612: reward = -15.12, steps = 34 14:44:14 [INFO] train episode 53613: reward = -0.54, steps = 38 14:44:17 [INFO] train episode 53614: reward = -30.65, steps = 29 14:44:20 [INFO] train episode 53615: reward = -7.68, steps = 34 14:44:23 [INFO] train episode 53616: reward = -27.89, steps = 28 14:44:26 [INFO] train episode 53617: reward = -8.81, steps = 44 14:44:30 [INFO] train episode 53618: reward = 0.56, steps = 39 14:44:33 [INFO] train episode 53619: reward = -4.13, steps = 43 14:44:36 [INFO] train episode 53620: reward = -24.05, steps = 31 14:44:40 [INFO] train episode 53621: reward = -0.54, steps = 38 14:44:43 [INFO] train episode 53622: reward = -13.77, steps = 34 14:44:46 [INFO] train episode 53623: reward = -2.08, steps = 39 14:44:49 [INFO] train episode 53624: reward = -12.69, steps = 32 14:44:52 [INFO] train episode 53625: reward = -7.28, steps = 34 14:44:55 [INFO] train episode 53626: reward = -1.39, steps = 34 14:44:59 [INFO] train episode 53627: reward = 8.53, steps = 39 14:45:01 [INFO] train episode 53628: reward = -16.89, steps = 30 14:45:04 [INFO] train episode 53629: reward = -25.85, steps = 28 14:45:08 [INFO] train episode 53630: reward = 5.91, steps = 50 14:45:12 [INFO] train episode 53631: reward = -7.05, steps = 43 14:45:17 [INFO] train episode 53632: reward = 5.12, steps = 52 14:45:21 [INFO] train episode 53633: reward = -9.62, steps = 52 14:45:24 [INFO] train episode 53634: reward = -15.87, steps = 30 14:45:26 [INFO] train episode 53635: reward = -29.70, steps = 20 14:45:30 [INFO] train episode 53636: reward = 11.63, steps = 43 14:45:33 [INFO] train episode 53637: reward = -9.90, steps = 34 14:45:36 [INFO] train episode 53638: reward = 2.19, steps = 45 14:45:40 [INFO] train episode 53639: reward = 0.87, steps = 37 14:45:43 [INFO] train episode 53640: reward = -10.66, steps = 29 14:45:45 [INFO] train episode 53641: reward = -17.91, steps = 29 14:45:48 [INFO] train episode 53642: reward = -0.84, steps = 37 14:45:52 [INFO] train episode 53643: reward = 2.14, steps = 42 14:45:54 [INFO] train episode 53644: reward = -22.79, steps = 26 14:45:56 [INFO] train episode 53645: reward = -11.28, steps = 23 14:46:01 [INFO] train episode 53646: reward = -13.87, steps = 51 14:46:05 [INFO] train episode 53647: reward = -49.78, steps = 45 14:46:08 [INFO] train episode 53648: reward = -2.90, steps = 39 14:46:11 [INFO] train episode 53649: reward = -12.26, steps = 36 14:46:15 [INFO] train episode 53650: reward = 5.29, steps = 35 14:46:17 [INFO] train episode 53651: reward = -1.93, steps = 31 14:46:20 [INFO] train episode 53652: reward = -26.82, steps = 23 14:46:23 [INFO] train episode 53653: reward = 7.12, steps = 38 14:46:27 [INFO] train episode 53654: reward = 5.55, steps = 45 14:46:29 [INFO] train episode 53655: reward = -22.72, steps = 23 14:46:32 [INFO] train episode 53656: reward = -9.30, steps = 36 14:46:35 [INFO] train episode 53657: reward = -14.35, steps = 35 14:46:38 [INFO] train episode 53658: reward = -9.89, steps = 34 14:46:42 [INFO] train episode 53659: reward = 9.64, steps = 40 14:46:45 [INFO] train episode 53660: reward = 1.79, steps = 34 14:46:48 [INFO] train episode 53661: reward = -5.22, steps = 37 14:46:52 [INFO] train episode 53662: reward = -0.76, steps = 42 14:46:55 [INFO] train episode 53663: reward = -25.57, steps = 30 14:46:59 [INFO] train episode 53664: reward = -5.24, steps = 37 14:47:03 [INFO] train episode 53665: reward = -2.82, steps = 47 14:47:06 [INFO] train episode 53666: reward = -9.71, steps = 31 14:47:09 [INFO] train episode 53667: reward = -9.55, steps = 40 14:47:13 [INFO] train episode 53668: reward = 6.07, steps = 43 14:47:16 [INFO] train episode 53669: reward = 9.12, steps = 36 14:47:20 [INFO] train episode 53670: reward = 4.28, steps = 38 14:47:23 [INFO] train episode 53671: reward = 7.44, steps = 42 14:47:26 [INFO] train episode 53672: reward = -15.82, steps = 29 14:47:29 [INFO] train episode 53673: reward = -3.67, steps = 34 14:47:33 [INFO] train episode 53674: reward = 17.96, steps = 45 14:47:35 [INFO] train episode 53675: reward = -9.72, steps = 29 14:47:39 [INFO] train episode 53676: reward = -0.79, steps = 46 14:47:42 [INFO] train episode 53677: reward = -11.29, steps = 31 14:47:45 [INFO] train episode 53678: reward = -7.94, steps = 31 14:47:48 [INFO] train episode 53679: reward = -1.80, steps = 43 14:47:52 [INFO] train episode 53680: reward = -38.55, steps = 39 14:47:55 [INFO] train episode 53681: reward = -12.12, steps = 32 14:47:57 [INFO] train episode 53682: reward = -18.05, steps = 27 14:48:01 [INFO] train episode 53683: reward = -5.16, steps = 38 14:48:03 [INFO] train episode 53684: reward = -13.51, steps = 31 14:48:06 [INFO] train episode 53685: reward = -11.25, steps = 29 14:48:09 [INFO] train episode 53686: reward = -15.23, steps = 32 14:48:12 [INFO] train episode 53687: reward = -2.80, steps = 37 14:48:14 [INFO] train episode 53688: reward = -26.86, steps = 22 14:48:18 [INFO] train episode 53689: reward = 2.20, steps = 40 14:48:22 [INFO] train episode 53690: reward = -32.29, steps = 46 14:48:25 [INFO] train episode 53691: reward = 4.73, steps = 39 14:48:28 [INFO] train episode 53692: reward = -9.04, steps = 36 14:48:31 [INFO] train episode 53693: reward = -34.91, steps = 33 14:48:33 [INFO] train episode 53694: reward = -24.93, steps = 23 14:48:37 [INFO] train episode 53695: reward = -9.79, steps = 40 14:48:40 [INFO] train episode 53696: reward = -10.91, steps = 35 14:48:42 [INFO] train episode 53697: reward = -42.63, steps = 21 14:48:46 [INFO] train episode 53698: reward = -10.31, steps = 41 14:48:49 [INFO] train episode 53699: reward = 7.16, steps = 41 14:48:52 [INFO] train episode 53700: reward = -14.09, steps = 34 14:48:56 [INFO] train episode 53701: reward = 3.61, steps = 38 14:49:00 [INFO] train episode 53702: reward = -5.96, steps = 48 14:49:04 [INFO] train episode 53703: reward = 1.69, steps = 40 14:49:09 [INFO] train episode 53704: reward = -23.80, steps = 66 14:49:12 [INFO] train episode 53705: reward = -3.60, steps = 35 14:49:16 [INFO] train episode 53706: reward = -2.93, steps = 45 14:49:19 [INFO] train episode 53707: reward = -17.93, steps = 28 14:49:21 [INFO] train episode 53708: reward = -22.15, steps = 25 14:49:24 [INFO] train episode 53709: reward = 2.22, steps = 32 14:49:27 [INFO] train episode 53710: reward = -4.13, steps = 37 14:49:32 [INFO] train episode 53711: reward = -14.53, steps = 53 14:49:35 [INFO] train episode 53712: reward = 7.57, steps = 37 14:49:37 [INFO] train episode 53713: reward = -15.77, steps = 25 14:49:42 [INFO] train episode 53714: reward = -7.18, steps = 56 14:49:45 [INFO] train episode 53715: reward = -4.42, steps = 35 14:49:47 [INFO] train episode 53716: reward = -26.03, steps = 20 14:49:51 [INFO] train episode 53717: reward = 0.01, steps = 40 14:49:55 [INFO] train episode 53718: reward = 5.06, steps = 38 14:49:58 [INFO] train episode 53719: reward = 7.74, steps = 41 14:50:00 [INFO] train episode 53720: reward = -20.94, steps = 27 14:50:03 [INFO] train episode 53721: reward = -24.43, steps = 25 14:50:07 [INFO] train episode 53722: reward = -7.76, steps = 40 14:50:11 [INFO] train episode 53723: reward = -11.10, steps = 48 14:50:14 [INFO] train episode 53724: reward = 9.89, steps = 38 14:50:16 [INFO] train episode 53725: reward = -16.85, steps = 26 14:50:20 [INFO] train episode 53726: reward = 5.30, steps = 44 14:50:23 [INFO] train episode 53727: reward = -39.00, steps = 36 14:50:26 [INFO] train episode 53728: reward = -7.52, steps = 34 14:50:29 [INFO] train episode 53729: reward = -12.60, steps = 25 14:50:32 [INFO] train episode 53730: reward = -4.86, steps = 39 14:50:36 [INFO] train episode 53731: reward = -2.57, steps = 37 14:50:39 [INFO] train episode 53732: reward = 8.94, steps = 37 14:50:41 [INFO] train episode 53733: reward = -38.52, steps = 19 14:50:43 [INFO] train episode 53734: reward = 5.51, steps = 32 14:50:46 [INFO] train episode 53735: reward = -26.11, steps = 26 14:50:49 [INFO] train episode 53736: reward = -10.76, steps = 34 14:50:52 [INFO] train episode 53737: reward = -12.61, steps = 36 14:50:55 [INFO] train episode 53738: reward = -10.08, steps = 30 14:50:58 [INFO] train episode 53739: reward = -5.40, steps = 35 14:51:00 [INFO] train episode 53740: reward = -5.01, steps = 30 14:51:03 [INFO] train episode 53741: reward = -2.50, steps = 32 14:51:07 [INFO] train episode 53742: reward = -20.70, steps = 36 14:51:10 [INFO] train episode 53743: reward = 1.83, steps = 44 14:51:14 [INFO] train episode 53744: reward = -3.11, steps = 44 14:51:19 [INFO] train episode 53745: reward = -3.63, steps = 55 14:51:22 [INFO] train episode 53746: reward = 0.35, steps = 36 14:51:25 [INFO] train episode 53747: reward = -35.44, steps = 30 14:51:28 [INFO] train episode 53748: reward = -4.67, steps = 36 14:51:30 [INFO] train episode 53749: reward = -16.33, steps = 24 14:51:33 [INFO] train episode 53750: reward = 0.16, steps = 36 14:51:36 [INFO] train episode 53751: reward = -15.39, steps = 31 14:51:39 [INFO] train episode 53752: reward = -26.13, steps = 29 14:51:42 [INFO] train episode 53753: reward = -14.98, steps = 33 14:51:46 [INFO] train episode 53754: reward = -8.89, steps = 48 14:51:49 [INFO] train episode 53755: reward = -20.20, steps = 34 14:51:51 [INFO] train episode 53756: reward = -23.46, steps = 22 14:51:54 [INFO] train episode 53757: reward = 2.89, steps = 42 14:51:58 [INFO] train episode 53758: reward = 12.80, steps = 43 14:52:02 [INFO] train episode 53759: reward = -15.95, steps = 36 14:52:06 [INFO] train episode 53760: reward = 0.31, steps = 49 14:52:08 [INFO] train episode 53761: reward = -30.58, steps = 21 14:52:13 [INFO] train episode 53762: reward = -21.08, steps = 53 14:52:15 [INFO] train episode 53763: reward = -20.02, steps = 23 14:52:19 [INFO] train episode 53764: reward = 1.50, steps = 46 14:52:22 [INFO] train episode 53765: reward = -0.25, steps = 41 14:52:26 [INFO] train episode 53766: reward = -4.71, steps = 40 14:52:30 [INFO] train episode 53767: reward = 4.71, steps = 48 14:52:32 [INFO] train episode 53768: reward = -29.26, steps = 20 14:52:35 [INFO] train episode 53769: reward = -13.62, steps = 33 14:52:37 [INFO] train episode 53770: reward = -3.90, steps = 31 14:52:40 [INFO] train episode 53771: reward = -39.94, steps = 28 14:52:43 [INFO] train episode 53772: reward = 4.46, steps = 39 14:52:46 [INFO] train episode 53773: reward = -29.96, steps = 23 14:52:49 [INFO] train episode 53774: reward = -7.61, steps = 33 14:52:53 [INFO] train episode 53775: reward = -9.40, steps = 45 14:52:56 [INFO] train episode 53776: reward = 1.53, steps = 33 14:52:59 [INFO] train episode 53777: reward = -9.54, steps = 33 14:53:03 [INFO] train episode 53778: reward = 12.91, steps = 38 14:53:06 [INFO] train episode 53779: reward = 9.79, steps = 43 14:53:09 [INFO] train episode 53780: reward = -28.01, steps = 25 14:53:11 [INFO] train episode 53781: reward = -29.24, steps = 30 14:53:15 [INFO] train episode 53782: reward = 12.16, steps = 46 14:53:20 [INFO] train episode 53783: reward = 14.63, steps = 54 14:53:23 [INFO] train episode 53784: reward = -11.19, steps = 26 14:53:25 [INFO] train episode 53785: reward = -2.52, steps = 33 14:53:27 [INFO] train episode 53786: reward = -16.51, steps = 23 14:53:31 [INFO] train episode 53787: reward = 3.55, steps = 39 14:53:35 [INFO] train episode 53788: reward = -21.15, steps = 41 14:53:38 [INFO] train episode 53789: reward = 11.97, steps = 44 14:53:41 [INFO] train episode 53790: reward = -6.81, steps = 32 14:53:44 [INFO] train episode 53791: reward = -14.27, steps = 33 14:53:47 [INFO] train episode 53792: reward = -0.11, steps = 39 14:53:51 [INFO] train episode 53793: reward = -15.21, steps = 32 14:53:54 [INFO] train episode 53794: reward = -6.23, steps = 36 14:53:56 [INFO] train episode 53795: reward = -37.38, steps = 30 14:53:58 [INFO] train episode 53796: reward = -24.28, steps = 24 14:54:00 [INFO] train episode 53797: reward = -42.04, steps = 20 14:54:04 [INFO] train episode 53798: reward = 6.18, steps = 39 14:54:08 [INFO] train episode 53799: reward = -9.58, steps = 49 14:54:11 [INFO] train episode 53800: reward = -71.32, steps = 31 14:54:14 [INFO] train episode 53801: reward = -0.38, steps = 41 14:54:18 [INFO] train episode 53802: reward = 7.24, steps = 40 14:54:21 [INFO] train episode 53803: reward = -28.32, steps = 38 14:54:23 [INFO] train episode 53804: reward = -32.97, steps = 18 14:54:26 [INFO] train episode 53805: reward = -21.37, steps = 30 14:54:29 [INFO] train episode 53806: reward = -11.52, steps = 35 14:54:31 [INFO] train episode 53807: reward = -9.70, steps = 25 14:54:34 [INFO] train episode 53808: reward = -7.84, steps = 30 14:54:37 [INFO] train episode 53809: reward = -33.71, steps = 41 14:54:40 [INFO] train episode 53810: reward = -44.22, steps = 22 14:54:43 [INFO] train episode 53811: reward = 6.34, steps = 44 14:54:46 [INFO] train episode 53812: reward = -12.18, steps = 30 14:54:50 [INFO] train episode 53813: reward = 14.27, steps = 45 14:54:52 [INFO] train episode 53814: reward = -19.95, steps = 25 14:54:55 [INFO] train episode 53815: reward = -2.80, steps = 30 14:54:57 [INFO] train episode 53816: reward = -29.42, steps = 28 14:55:03 [INFO] train episode 53817: reward = -2.43, steps = 61 14:55:06 [INFO] train episode 53818: reward = -6.58, steps = 37 14:55:09 [INFO] train episode 53819: reward = -22.31, steps = 36 14:55:11 [INFO] train episode 53820: reward = -41.40, steps = 21 14:55:14 [INFO] train episode 53821: reward = -5.87, steps = 28 14:55:17 [INFO] train episode 53822: reward = 0.26, steps = 41 14:55:20 [INFO] train episode 53823: reward = -9.91, steps = 32 14:55:23 [INFO] train episode 53824: reward = 3.68, steps = 42 14:55:27 [INFO] train episode 53825: reward = -10.71, steps = 41 14:55:31 [INFO] train episode 53826: reward = -5.56, steps = 37 14:55:32 [INFO] train episode 53827: reward = -32.35, steps = 22 14:55:36 [INFO] train episode 53828: reward = -5.53, steps = 39 14:55:38 [INFO] train episode 53829: reward = -17.71, steps = 27 14:55:43 [INFO] train episode 53830: reward = 6.74, steps = 40 14:55:46 [INFO] train episode 53831: reward = -27.80, steps = 38 14:55:48 [INFO] train episode 53832: reward = -34.33, steps = 21 14:55:52 [INFO] train episode 53833: reward = -1.56, steps = 51 14:55:55 [INFO] train episode 53834: reward = -23.77, steps = 25 14:55:58 [INFO] train episode 53835: reward = 4.88, steps = 40 14:56:02 [INFO] train episode 53836: reward = -21.53, steps = 38 14:56:04 [INFO] train episode 53837: reward = -19.71, steps = 31 14:56:08 [INFO] train episode 53838: reward = 0.06, steps = 44 14:56:12 [INFO] train episode 53839: reward = 13.70, steps = 41 14:56:15 [INFO] train episode 53840: reward = 7.67, steps = 39 14:56:18 [INFO] train episode 53841: reward = -9.66, steps = 35 14:56:23 [INFO] train episode 53842: reward = 3.94, steps = 55 14:56:26 [INFO] train episode 53843: reward = 1.95, steps = 39 14:56:28 [INFO] train episode 53844: reward = -34.99, steps = 21 14:56:31 [INFO] train episode 53845: reward = 11.36, steps = 31 14:56:35 [INFO] train episode 53846: reward = -9.58, steps = 37 14:56:39 [INFO] train episode 53847: reward = -0.27, steps = 50 14:56:43 [INFO] train episode 53848: reward = 11.83, steps = 50 14:56:47 [INFO] train episode 53849: reward = -10.16, steps = 33 14:56:49 [INFO] train episode 53850: reward = -0.06, steps = 31 14:56:52 [INFO] train episode 53851: reward = -7.51, steps = 30 14:56:55 [INFO] train episode 53852: reward = -8.80, steps = 32 14:56:57 [INFO] train episode 53853: reward = 3.83, steps = 32 14:57:00 [INFO] train episode 53854: reward = 5.28, steps = 33 14:57:04 [INFO] train episode 53855: reward = -1.42, steps = 40 14:57:07 [INFO] train episode 53856: reward = -7.99, steps = 34 14:57:09 [INFO] train episode 53857: reward = -19.59, steps = 18 14:57:11 [INFO] train episode 53858: reward = -32.52, steps = 20 14:57:13 [INFO] train episode 53859: reward = -29.03, steps = 27 14:57:16 [INFO] train episode 53860: reward = -50.96, steps = 39 14:57:20 [INFO] train episode 53861: reward = 11.47, steps = 42 14:57:24 [INFO] train episode 53862: reward = 1.22, steps = 44 14:57:26 [INFO] train episode 53863: reward = -8.84, steps = 26 14:57:29 [INFO] train episode 53864: reward = -22.55, steps = 34 14:57:32 [INFO] train episode 53865: reward = -6.48, steps = 32 14:57:35 [INFO] train episode 53866: reward = -6.94, steps = 34 14:57:37 [INFO] train episode 53867: reward = -30.40, steps = 21 14:57:40 [INFO] train episode 53868: reward = -11.36, steps = 32 14:57:43 [INFO] train episode 53869: reward = 3.32, steps = 31 14:57:47 [INFO] train episode 53870: reward = 23.69, steps = 54 14:57:50 [INFO] train episode 53871: reward = -6.80, steps = 36 14:57:53 [INFO] train episode 53872: reward = -24.96, steps = 22 14:57:56 [INFO] train episode 53873: reward = -10.32, steps = 42 14:58:00 [INFO] train episode 53874: reward = 6.01, steps = 43 14:58:03 [INFO] train episode 53875: reward = -8.06, steps = 38 14:58:06 [INFO] train episode 53876: reward = -24.39, steps = 26 14:58:10 [INFO] train episode 53877: reward = 14.06, steps = 40 14:58:12 [INFO] train episode 53878: reward = -29.85, steps = 32 14:58:14 [INFO] train episode 53879: reward = -19.70, steps = 21 14:58:16 [INFO] train episode 53880: reward = -33.94, steps = 24 14:58:20 [INFO] train episode 53881: reward = -10.19, steps = 41 14:58:22 [INFO] train episode 53882: reward = -1.89, steps = 27 14:58:26 [INFO] train episode 53883: reward = -3.56, steps = 42 14:58:28 [INFO] train episode 53884: reward = -24.91, steps = 26 14:58:32 [INFO] train episode 53885: reward = -2.68, steps = 44 14:58:37 [INFO] train episode 53886: reward = 1.26, steps = 44 14:58:41 [INFO] train episode 53887: reward = 1.35, steps = 39 14:58:42 [INFO] train episode 53888: reward = -36.03, steps = 20 14:58:47 [INFO] train episode 53889: reward = 12.29, steps = 53 14:58:48 [INFO] train episode 53890: reward = -56.25, steps = 17 14:58:53 [INFO] train episode 53891: reward = 11.02, steps = 50 14:58:55 [INFO] train episode 53892: reward = -22.73, steps = 21 14:58:57 [INFO] train episode 53893: reward = -34.22, steps = 24 14:59:01 [INFO] train episode 53894: reward = 7.38, steps = 36 14:59:03 [INFO] train episode 53895: reward = -5.00, steps = 31 14:59:07 [INFO] train episode 53896: reward = 7.92, steps = 49 14:59:10 [INFO] train episode 53897: reward = -17.18, steps = 34 14:59:13 [INFO] train episode 53898: reward = -6.91, steps = 33 14:59:17 [INFO] train episode 53899: reward = -9.80, steps = 31 14:59:19 [INFO] train episode 53900: reward = -23.54, steps = 22 14:59:22 [INFO] train episode 53901: reward = -7.85, steps = 39 14:59:24 [INFO] train episode 53902: reward = -6.20, steps = 28 14:59:29 [INFO] train episode 53903: reward = 11.15, steps = 49 14:59:34 [INFO] train episode 53904: reward = 8.25, steps = 54 14:59:37 [INFO] train episode 53905: reward = 2.18, steps = 45 14:59:41 [INFO] train episode 53906: reward = 1.72, steps = 36 14:59:44 [INFO] train episode 53907: reward = -12.65, steps = 35 14:59:45 [INFO] train episode 53908: reward = -21.88, steps = 19 14:59:49 [INFO] train episode 53909: reward = 6.08, steps = 38 14:59:53 [INFO] train episode 53910: reward = 15.31, steps = 46 14:59:55 [INFO] train episode 53911: reward = -12.00, steps = 21 14:59:58 [INFO] train episode 53912: reward = -0.89, steps = 39 15:00:00 [INFO] train episode 53913: reward = -36.50, steps = 23 15:00:04 [INFO] train episode 53914: reward = 5.50, steps = 38 15:00:06 [INFO] train episode 53915: reward = -7.74, steps = 30 15:00:10 [INFO] train episode 53916: reward = 9.93, steps = 38 15:00:13 [INFO] train episode 53917: reward = -15.75, steps = 34 15:00:16 [INFO] train episode 53918: reward = -11.23, steps = 34 15:00:19 [INFO] train episode 53919: reward = -5.27, steps = 35 15:00:22 [INFO] train episode 53920: reward = -16.47, steps = 30 15:00:24 [INFO] train episode 53921: reward = -11.04, steps = 30 15:00:26 [INFO] train episode 53922: reward = -37.92, steps = 22 15:00:30 [INFO] train episode 53923: reward = -30.48, steps = 41 15:00:33 [INFO] train episode 53924: reward = -2.27, steps = 38 15:00:37 [INFO] train episode 53925: reward = -0.37, steps = 40 15:00:40 [INFO] train episode 53926: reward = 4.61, steps = 39 15:00:43 [INFO] train episode 53927: reward = -9.84, steps = 35 15:00:46 [INFO] train episode 53928: reward = -19.29, steps = 33 15:00:49 [INFO] train episode 53929: reward = -24.05, steps = 33 15:00:52 [INFO] train episode 53930: reward = -7.68, steps = 31 15:00:56 [INFO] train episode 53931: reward = -28.92, steps = 47 15:01:00 [INFO] train episode 53932: reward = -3.77, steps = 39 15:01:02 [INFO] train episode 53933: reward = -36.55, steps = 24 15:01:04 [INFO] train episode 53934: reward = -21.61, steps = 21 15:01:06 [INFO] train episode 53935: reward = -16.05, steps = 29 15:01:09 [INFO] train episode 53936: reward = -10.14, steps = 31 15:01:12 [INFO] train episode 53937: reward = -3.05, steps = 31 15:01:16 [INFO] train episode 53938: reward = 13.86, steps = 53 15:01:19 [INFO] train episode 53939: reward = -8.73, steps = 33 15:01:22 [INFO] train episode 53940: reward = 7.35, steps = 36 15:01:26 [INFO] train episode 53941: reward = 0.71, steps = 35 15:01:32 [INFO] train episode 53942: reward = -8.97, steps = 57 15:01:35 [INFO] train episode 53943: reward = 1.80, steps = 41 15:01:38 [INFO] train episode 53944: reward = -1.52, steps = 39 15:01:42 [INFO] train episode 53945: reward = -9.90, steps = 41 15:01:45 [INFO] train episode 53946: reward = -26.87, steps = 36 15:01:48 [INFO] train episode 53947: reward = -17.44, steps = 27 15:01:50 [INFO] train episode 53948: reward = -12.25, steps = 27 15:01:54 [INFO] train episode 53949: reward = -3.62, steps = 47 15:01:58 [INFO] train episode 53950: reward = 1.73, steps = 37 15:02:00 [INFO] train episode 53951: reward = -29.63, steps = 24 15:02:03 [INFO] train episode 53952: reward = 0.44, steps = 36 15:02:07 [INFO] train episode 53953: reward = 5.93, steps = 42 15:02:11 [INFO] train episode 53954: reward = -3.51, steps = 53 15:02:13 [INFO] train episode 53955: reward = -22.75, steps = 20 15:02:16 [INFO] train episode 53956: reward = -25.70, steps = 26 15:02:20 [INFO] train episode 53957: reward = 12.45, steps = 45 15:02:22 [INFO] train episode 53958: reward = -42.20, steps = 22 15:02:24 [INFO] train episode 53959: reward = -0.67, steps = 32 15:02:29 [INFO] train episode 53960: reward = 7.94, steps = 46 15:02:32 [INFO] train episode 53961: reward = -0.41, steps = 35 15:02:34 [INFO] train episode 53962: reward = -9.69, steps = 24 15:02:37 [INFO] train episode 53963: reward = -5.17, steps = 38 15:02:40 [INFO] train episode 53964: reward = -11.61, steps = 28 15:02:42 [INFO] train episode 53965: reward = -32.96, steps = 21 15:02:45 [INFO] train episode 53966: reward = -6.87, steps = 34 15:02:49 [INFO] train episode 53967: reward = -0.77, steps = 47 15:02:52 [INFO] train episode 53968: reward = -5.99, steps = 34 15:02:55 [INFO] train episode 53969: reward = 7.62, steps = 33 15:02:59 [INFO] train episode 53970: reward = 11.11, steps = 52 15:03:04 [INFO] train episode 53971: reward = 2.52, steps = 45 15:03:08 [INFO] train episode 53972: reward = -40.91, steps = 56 15:03:13 [INFO] train episode 53973: reward = -6.65, steps = 48 15:03:14 [INFO] train episode 53974: reward = -22.69, steps = 20 15:03:18 [INFO] train episode 53975: reward = 0.53, steps = 37 15:03:21 [INFO] train episode 53976: reward = -5.05, steps = 38 15:03:23 [INFO] train episode 53977: reward = -26.94, steps = 23 15:03:25 [INFO] train episode 53978: reward = -18.36, steps = 24 15:03:30 [INFO] train episode 53979: reward = -12.87, steps = 48 15:03:33 [INFO] train episode 53980: reward = -8.53, steps = 38 15:03:35 [INFO] train episode 53981: reward = -25.12, steps = 20 15:03:39 [INFO] train episode 53982: reward = 2.58, steps = 46 15:03:42 [INFO] train episode 53983: reward = 14.43, steps = 36 15:03:44 [INFO] train episode 53984: reward = -18.24, steps = 27 15:03:47 [INFO] train episode 53985: reward = -20.05, steps = 35 15:03:50 [INFO] train episode 53986: reward = -23.14, steps = 25 15:03:53 [INFO] train episode 53987: reward = 6.24, steps = 36 15:03:57 [INFO] train episode 53988: reward = 8.68, steps = 41 15:03:59 [INFO] train episode 53989: reward = -5.17, steps = 33 15:04:04 [INFO] train episode 53990: reward = -19.37, steps = 49 15:04:06 [INFO] train episode 53991: reward = -44.45, steps = 19 15:04:08 [INFO] train episode 53992: reward = -7.53, steps = 30 15:04:11 [INFO] train episode 53993: reward = -23.91, steps = 24 15:04:14 [INFO] train episode 53994: reward = -30.59, steps = 35 15:04:17 [INFO] train episode 53995: reward = 10.91, steps = 43 15:04:21 [INFO] train episode 53996: reward = 4.55, steps = 34 15:04:24 [INFO] train episode 53997: reward = -6.82, steps = 31 15:04:28 [INFO] train episode 53998: reward = 3.38, steps = 38 15:04:32 [INFO] train episode 53999: reward = -5.06, steps = 45 15:04:34 [INFO] train episode 54000: reward = -16.90, steps = 32 15:04:38 [INFO] train episode 54001: reward = 2.90, steps = 38 15:04:41 [INFO] train episode 54002: reward = -9.97, steps = 32 15:04:44 [INFO] train episode 54003: reward = -0.97, steps = 36 15:04:47 [INFO] train episode 54004: reward = 15.04, steps = 40 15:04:51 [INFO] train episode 54005: reward = -4.54, steps = 43 15:04:56 [INFO] train episode 54006: reward = 18.61, steps = 50 15:04:59 [INFO] train episode 54007: reward = 2.55, steps = 37 15:05:02 [INFO] train episode 54008: reward = -1.15, steps = 38 15:05:05 [INFO] train episode 54009: reward = -22.40, steps = 31 15:05:07 [INFO] train episode 54010: reward = -15.03, steps = 22 15:05:10 [INFO] train episode 54011: reward = -6.72, steps = 29 15:05:12 [INFO] train episode 54012: reward = -35.07, steps = 20 15:05:16 [INFO] train episode 54013: reward = 16.79, steps = 45 15:05:19 [INFO] train episode 54014: reward = -9.74, steps = 35 15:05:22 [INFO] train episode 54015: reward = 0.31, steps = 35 15:05:26 [INFO] train episode 54016: reward = -3.41, steps = 45 15:05:29 [INFO] train episode 54017: reward = 8.04, steps = 39 15:05:32 [INFO] train episode 54018: reward = -14.65, steps = 28 15:05:36 [INFO] train episode 54019: reward = -30.12, steps = 44 15:05:39 [INFO] train episode 54020: reward = -11.28, steps = 34 15:05:42 [INFO] train episode 54021: reward = 1.77, steps = 40 15:05:45 [INFO] train episode 54022: reward = -10.45, steps = 32 15:05:49 [INFO] train episode 54023: reward = -14.92, steps = 43 15:05:53 [INFO] train episode 54024: reward = -12.62, steps = 45 15:05:55 [INFO] train episode 54025: reward = -9.95, steps = 31 15:05:59 [INFO] train episode 54026: reward = 1.79, steps = 43 15:06:02 [INFO] train episode 54027: reward = 2.70, steps = 35 15:06:06 [INFO] train episode 54028: reward = -8.75, steps = 37 15:06:08 [INFO] train episode 54029: reward = -6.37, steps = 32 15:06:12 [INFO] train episode 54030: reward = -3.18, steps = 47 15:06:17 [INFO] train episode 54031: reward = 10.37, steps = 43 15:06:20 [INFO] train episode 54032: reward = 7.16, steps = 36 15:06:23 [INFO] train episode 54033: reward = -2.86, steps = 36 15:06:26 [INFO] train episode 54034: reward = 0.06, steps = 41 15:06:30 [INFO] train episode 54035: reward = -4.63, steps = 38 15:06:33 [INFO] train episode 54036: reward = -20.86, steps = 37 15:06:36 [INFO] train episode 54037: reward = -49.48, steps = 33 15:06:40 [INFO] train episode 54038: reward = 7.76, steps = 45 15:06:43 [INFO] train episode 54039: reward = -2.39, steps = 38 15:06:46 [INFO] train episode 54040: reward = -6.68, steps = 34 15:06:50 [INFO] train episode 54041: reward = -5.50, steps = 43 15:06:54 [INFO] train episode 54042: reward = -13.98, steps = 38 15:06:57 [INFO] train episode 54043: reward = 9.67, steps = 43 15:06:59 [INFO] train episode 54044: reward = -25.78, steps = 20 15:07:03 [INFO] train episode 54045: reward = -3.70, steps = 42 15:07:06 [INFO] train episode 54046: reward = -6.30, steps = 32 15:07:09 [INFO] train episode 54047: reward = 1.01, steps = 38 15:07:11 [INFO] train episode 54048: reward = -10.83, steps = 23 15:07:15 [INFO] train episode 54049: reward = -6.58, steps = 38 15:07:18 [INFO] train episode 54050: reward = -1.96, steps = 34 15:07:22 [INFO] train episode 54051: reward = 7.56, steps = 39 15:07:25 [INFO] train episode 54052: reward = -15.06, steps = 33 15:07:28 [INFO] train episode 54053: reward = 0.31, steps = 36 15:07:33 [INFO] train episode 54054: reward = 2.27, steps = 53 15:07:36 [INFO] train episode 54055: reward = -2.68, steps = 33 15:07:39 [INFO] train episode 54056: reward = -5.04, steps = 34 15:07:42 [INFO] train episode 54057: reward = 4.26, steps = 34 15:07:45 [INFO] train episode 54058: reward = -4.16, steps = 40 15:07:49 [INFO] train episode 54059: reward = 4.08, steps = 37 15:07:52 [INFO] train episode 54060: reward = -19.01, steps = 41 15:07:55 [INFO] train episode 54061: reward = -15.09, steps = 33 15:07:58 [INFO] train episode 54062: reward = -5.40, steps = 34 15:08:01 [INFO] train episode 54063: reward = -12.17, steps = 35 15:08:05 [INFO] train episode 54064: reward = 1.96, steps = 39 15:08:09 [INFO] train episode 54065: reward = -0.61, steps = 52 15:08:12 [INFO] train episode 54066: reward = -9.24, steps = 33 15:08:16 [INFO] train episode 54067: reward = -5.29, steps = 38 15:08:19 [INFO] train episode 54068: reward = -7.73, steps = 34 15:08:22 [INFO] train episode 54069: reward = -8.87, steps = 36 15:08:26 [INFO] train episode 54070: reward = -49.10, steps = 50 15:08:29 [INFO] train episode 54071: reward = -23.87, steps = 26 15:08:31 [INFO] train episode 54072: reward = -15.19, steps = 28 15:08:33 [INFO] train episode 54073: reward = -38.75, steps = 21 15:08:36 [INFO] train episode 54074: reward = -7.34, steps = 34 15:08:40 [INFO] train episode 54075: reward = 9.17, steps = 43 15:08:43 [INFO] train episode 54076: reward = -10.84, steps = 35 15:08:46 [INFO] train episode 54077: reward = -6.13, steps = 36 15:08:48 [INFO] train episode 54078: reward = -8.79, steps = 27 15:08:51 [INFO] train episode 54079: reward = -9.30, steps = 29 15:08:55 [INFO] train episode 54080: reward = 4.16, steps = 42 15:08:57 [INFO] train episode 54081: reward = -25.04, steps = 25 15:08:59 [INFO] train episode 54082: reward = -18.40, steps = 26 15:09:03 [INFO] train episode 54083: reward = 2.47, steps = 34 15:09:05 [INFO] train episode 54084: reward = -9.24, steps = 31 15:09:08 [INFO] train episode 54085: reward = -10.41, steps = 26 15:09:11 [INFO] train episode 54086: reward = -1.94, steps = 38 15:09:14 [INFO] train episode 54087: reward = -10.98, steps = 29 15:09:17 [INFO] train episode 54088: reward = 0.18, steps = 35 15:09:20 [INFO] train episode 54089: reward = -1.32, steps = 39 15:09:24 [INFO] train episode 54090: reward = 9.48, steps = 42 15:09:27 [INFO] train episode 54091: reward = 10.82, steps = 38 15:09:30 [INFO] train episode 54092: reward = -10.41, steps = 37 15:09:34 [INFO] train episode 54093: reward = -16.44, steps = 32 15:09:37 [INFO] train episode 54094: reward = -4.33, steps = 37 15:09:41 [INFO] train episode 54095: reward = 14.27, steps = 46 15:09:43 [INFO] train episode 54096: reward = -12.29, steps = 31 15:09:47 [INFO] train episode 54097: reward = 12.31, steps = 45 15:09:50 [INFO] train episode 54098: reward = -7.98, steps = 32 15:09:53 [INFO] train episode 54099: reward = -9.79, steps = 24 15:09:56 [INFO] train episode 54100: reward = -5.04, steps = 35 15:09:59 [INFO] train episode 54101: reward = 10.43, steps = 37 15:10:02 [INFO] train episode 54102: reward = 1.58, steps = 40 15:10:07 [INFO] train episode 54103: reward = 14.31, steps = 48 15:10:10 [INFO] train episode 54104: reward = -4.11, steps = 41 15:10:13 [INFO] train episode 54105: reward = -23.38, steps = 37 15:10:16 [INFO] train episode 54106: reward = -16.11, steps = 26 15:10:20 [INFO] train episode 54107: reward = 4.75, steps = 38 15:10:23 [INFO] train episode 54108: reward = -7.63, steps = 40 15:10:26 [INFO] train episode 54109: reward = -18.85, steps = 30 15:10:29 [INFO] train episode 54110: reward = 4.89, steps = 32 15:10:32 [INFO] train episode 54111: reward = 15.48, steps = 38 15:10:36 [INFO] train episode 54112: reward = -0.13, steps = 41 15:10:42 [INFO] train episode 54113: reward = -57.46, steps = 69 15:10:45 [INFO] train episode 54114: reward = -12.33, steps = 34 15:10:47 [INFO] train episode 54115: reward = -22.72, steps = 21 15:10:49 [INFO] train episode 54116: reward = -33.61, steps = 24 15:10:53 [INFO] train episode 54117: reward = -12.83, steps = 39 15:10:56 [INFO] train episode 54118: reward = -6.44, steps = 40 15:11:00 [INFO] train episode 54119: reward = 2.35, steps = 43 15:11:03 [INFO] train episode 54120: reward = -17.99, steps = 34 15:11:05 [INFO] train episode 54121: reward = -19.69, steps = 20 15:11:09 [INFO] train episode 54122: reward = 9.12, steps = 49 15:11:13 [INFO] train episode 54123: reward = 6.01, steps = 37 15:11:15 [INFO] train episode 54124: reward = -17.02, steps = 29 15:11:20 [INFO] train episode 54125: reward = -24.66, steps = 58 15:11:24 [INFO] train episode 54126: reward = 11.37, steps = 51 15:11:28 [INFO] train episode 54127: reward = -18.94, steps = 33 15:11:31 [INFO] train episode 54128: reward = -0.88, steps = 33 15:11:34 [INFO] train episode 54129: reward = -5.10, steps = 42 15:11:38 [INFO] train episode 54130: reward = -1.83, steps = 40 15:11:41 [INFO] train episode 54131: reward = -4.09, steps = 35 15:11:44 [INFO] train episode 54132: reward = -2.20, steps = 33 15:11:46 [INFO] train episode 54133: reward = -35.87, steps = 24 15:11:49 [INFO] train episode 54134: reward = -2.63, steps = 30 15:11:52 [INFO] train episode 54135: reward = -9.61, steps = 45 15:11:55 [INFO] train episode 54136: reward = 3.15, steps = 35 15:12:00 [INFO] train episode 54137: reward = 20.23, steps = 48 15:12:04 [INFO] train episode 54138: reward = 3.52, steps = 42 15:12:07 [INFO] train episode 54139: reward = 9.85, steps = 45 15:12:11 [INFO] train episode 54140: reward = 1.44, steps = 37 15:12:14 [INFO] train episode 54141: reward = -6.20, steps = 35 15:12:16 [INFO] train episode 54142: reward = -21.41, steps = 20 15:12:20 [INFO] train episode 54143: reward = -30.35, steps = 53 15:12:24 [INFO] train episode 54144: reward = 1.91, steps = 38 15:12:27 [INFO] train episode 54145: reward = 8.76, steps = 37 15:12:30 [INFO] train episode 54146: reward = -1.59, steps = 37 15:12:34 [INFO] train episode 54147: reward = 9.97, steps = 37 15:12:36 [INFO] train episode 54148: reward = -9.70, steps = 31 15:12:39 [INFO] train episode 54149: reward = -22.17, steps = 34 15:12:42 [INFO] train episode 54150: reward = 0.99, steps = 35 15:12:46 [INFO] train episode 54151: reward = 4.66, steps = 41 15:12:50 [INFO] train episode 54152: reward = -0.15, steps = 41 15:12:54 [INFO] train episode 54153: reward = 5.31, steps = 51 15:12:57 [INFO] train episode 54154: reward = -6.74, steps = 30 15:13:00 [INFO] train episode 54155: reward = 2.81, steps = 35 15:13:03 [INFO] train episode 54156: reward = -9.74, steps = 29 15:13:06 [INFO] train episode 54157: reward = 3.76, steps = 36 15:13:11 [INFO] train episode 54158: reward = -6.56, steps = 45 15:13:14 [INFO] train episode 54159: reward = 0.42, steps = 36 15:13:17 [INFO] train episode 54160: reward = 0.28, steps = 31 15:13:20 [INFO] train episode 54161: reward = -8.65, steps = 32 15:13:23 [INFO] train episode 54162: reward = -7.16, steps = 36 15:13:27 [INFO] train episode 54163: reward = -4.61, steps = 48 15:13:30 [INFO] train episode 54164: reward = 11.83, steps = 40 15:13:34 [INFO] train episode 54165: reward = 11.12, steps = 44 15:13:39 [INFO] train episode 54166: reward = -19.50, steps = 49 15:13:42 [INFO] train episode 54167: reward = -5.31, steps = 33 15:13:45 [INFO] train episode 54168: reward = 7.42, steps = 39 15:13:48 [INFO] train episode 54169: reward = -8.79, steps = 37 15:13:52 [INFO] train episode 54170: reward = -7.97, steps = 42 15:13:55 [INFO] train episode 54171: reward = 7.45, steps = 35 15:13:58 [INFO] train episode 54172: reward = -10.36, steps = 30 15:14:00 [INFO] train episode 54173: reward = 2.40, steps = 32 15:14:04 [INFO] train episode 54174: reward = 7.28, steps = 41 15:14:07 [INFO] train episode 54175: reward = -3.74, steps = 34 15:14:12 [INFO] train episode 54176: reward = 4.91, steps = 44 15:14:15 [INFO] train episode 54177: reward = 12.08, steps = 45 15:14:19 [INFO] train episode 54178: reward = 2.72, steps = 39 15:14:23 [INFO] train episode 54179: reward = 12.67, steps = 46 15:14:26 [INFO] train episode 54180: reward = -7.53, steps = 33 15:14:29 [INFO] train episode 54181: reward = -4.46, steps = 32 15:14:33 [INFO] train episode 54182: reward = 4.53, steps = 48 15:14:36 [INFO] train episode 54183: reward = 2.04, steps = 31 15:14:39 [INFO] train episode 54184: reward = -8.27, steps = 39 15:14:43 [INFO] train episode 54185: reward = -23.94, steps = 45 15:14:48 [INFO] train episode 54186: reward = 13.31, steps = 59 15:14:52 [INFO] train episode 54187: reward = 23.30, steps = 44 15:14:54 [INFO] train episode 54188: reward = -30.05, steps = 21 15:14:56 [INFO] train episode 54189: reward = -22.42, steps = 20 15:14:59 [INFO] train episode 54190: reward = -7.73, steps = 31 15:15:02 [INFO] train episode 54191: reward = -5.71, steps = 32 15:15:05 [INFO] train episode 54192: reward = -1.88, steps = 42 15:15:08 [INFO] train episode 54193: reward = 2.17, steps = 36 15:15:13 [INFO] train episode 54194: reward = -40.05, steps = 54 15:15:16 [INFO] train episode 54195: reward = -0.67, steps = 31 15:15:19 [INFO] train episode 54196: reward = -4.35, steps = 37 15:15:23 [INFO] train episode 54197: reward = 1.82, steps = 38 15:15:25 [INFO] train episode 54198: reward = -35.34, steps = 30 15:15:28 [INFO] train episode 54199: reward = 1.29, steps = 36 15:15:35 [INFO] train episode 54200: reward = -1.19, steps = 68 15:15:37 [INFO] train episode 54201: reward = 2.54, steps = 33 15:15:40 [INFO] train episode 54202: reward = -13.93, steps = 32 15:15:42 [INFO] train episode 54203: reward = -10.98, steps = 26 15:15:46 [INFO] train episode 54204: reward = 10.17, steps = 35 15:15:48 [INFO] train episode 54205: reward = -31.69, steps = 31 15:15:52 [INFO] train episode 54206: reward = 7.27, steps = 38 15:15:54 [INFO] train episode 54207: reward = -13.26, steps = 30 15:15:56 [INFO] train episode 54208: reward = -44.62, steps = 20 15:15:59 [INFO] train episode 54209: reward = -7.25, steps = 32 15:16:03 [INFO] train episode 54210: reward = -0.43, steps = 40 15:16:07 [INFO] train episode 54211: reward = -5.74, steps = 40 15:16:10 [INFO] train episode 54212: reward = 3.58, steps = 36 15:16:13 [INFO] train episode 54213: reward = -5.97, steps = 31 15:16:16 [INFO] train episode 54214: reward = -4.22, steps = 40 15:16:21 [INFO] train episode 54215: reward = -6.49, steps = 49 15:16:25 [INFO] train episode 54216: reward = -2.85, steps = 56 15:16:29 [INFO] train episode 54217: reward = -0.56, steps = 37 15:16:32 [INFO] train episode 54218: reward = -2.87, steps = 37 15:16:35 [INFO] train episode 54219: reward = -7.41, steps = 34 15:16:37 [INFO] train episode 54220: reward = -20.47, steps = 24 15:16:44 [INFO] train episode 54221: reward = -21.64, steps = 75 15:16:47 [INFO] train episode 54222: reward = -10.95, steps = 34 15:16:50 [INFO] train episode 54223: reward = -2.07, steps = 34 15:16:54 [INFO] train episode 54224: reward = 0.38, steps = 47 15:16:58 [INFO] train episode 54225: reward = -5.37, steps = 41 15:17:01 [INFO] train episode 54226: reward = -6.16, steps = 32 15:17:05 [INFO] train episode 54227: reward = 1.68, steps = 48 15:17:11 [INFO] train episode 54228: reward = -70.58, steps = 72 15:17:13 [INFO] train episode 54229: reward = -29.24, steps = 19 15:17:17 [INFO] train episode 54230: reward = 2.26, steps = 46 15:17:23 [INFO] train episode 54231: reward = -26.95, steps = 71 15:17:25 [INFO] train episode 54232: reward = -12.99, steps = 24 15:17:29 [INFO] train episode 54233: reward = -11.21, steps = 42 15:17:33 [INFO] train episode 54234: reward = 2.74, steps = 48 15:17:36 [INFO] train episode 54235: reward = 15.27, steps = 37 15:17:40 [INFO] train episode 54236: reward = -5.67, steps = 45 15:17:44 [INFO] train episode 54237: reward = 6.90, steps = 38 15:17:46 [INFO] train episode 54238: reward = -48.87, steps = 31 15:17:49 [INFO] train episode 54239: reward = -10.94, steps = 35 15:17:54 [INFO] train episode 54240: reward = -10.08, steps = 52 15:17:57 [INFO] train episode 54241: reward = -1.27, steps = 38 15:18:00 [INFO] train episode 54242: reward = 6.25, steps = 35 15:18:04 [INFO] train episode 54243: reward = -6.17, steps = 39 15:18:07 [INFO] train episode 54244: reward = -17.03, steps = 39 15:18:12 [INFO] train episode 54245: reward = 6.81, steps = 50 15:18:15 [INFO] train episode 54246: reward = 0.04, steps = 34 15:18:19 [INFO] train episode 54247: reward = 5.60, steps = 45 15:18:22 [INFO] train episode 54248: reward = -1.97, steps = 39 15:18:26 [INFO] train episode 54249: reward = 0.06, steps = 42 15:18:30 [INFO] train episode 54250: reward = 5.14, steps = 43 15:18:33 [INFO] train episode 54251: reward = -12.71, steps = 35 15:18:36 [INFO] train episode 54252: reward = 5.93, steps = 37 15:18:39 [INFO] train episode 54253: reward = 1.48, steps = 37 15:18:42 [INFO] train episode 54254: reward = -2.06, steps = 29 15:18:46 [INFO] train episode 54255: reward = -11.23, steps = 43 15:18:50 [INFO] train episode 54256: reward = 8.14, steps = 49 15:18:53 [INFO] train episode 54257: reward = -3.19, steps = 37 15:18:57 [INFO] train episode 54258: reward = -11.21, steps = 44 15:19:02 [INFO] train episode 54259: reward = -5.23, steps = 38 15:19:05 [INFO] train episode 54260: reward = -2.18, steps = 39 15:19:07 [INFO] train episode 54261: reward = -23.40, steps = 21 15:19:10 [INFO] train episode 54262: reward = -11.47, steps = 35 15:19:13 [INFO] train episode 54263: reward = 1.86, steps = 37 15:19:16 [INFO] train episode 54264: reward = 1.56, steps = 37 15:19:20 [INFO] train episode 54265: reward = -24.79, steps = 41 15:19:24 [INFO] train episode 54266: reward = 3.43, steps = 46 15:19:27 [INFO] train episode 54267: reward = 0.21, steps = 33 15:19:30 [INFO] train episode 54268: reward = -7.98, steps = 32 15:19:34 [INFO] train episode 54269: reward = 2.75, steps = 40 15:19:37 [INFO] train episode 54270: reward = -13.31, steps = 32 15:19:39 [INFO] train episode 54271: reward = -11.94, steps = 32 15:19:41 [INFO] train episode 54272: reward = -21.77, steps = 24 15:19:45 [INFO] train episode 54273: reward = 8.71, steps = 43 15:19:49 [INFO] train episode 54274: reward = 2.88, steps = 44 15:19:53 [INFO] train episode 54275: reward = 1.92, steps = 37 15:19:56 [INFO] train episode 54276: reward = 2.20, steps = 41 15:19:58 [INFO] train episode 54277: reward = -52.75, steps = 25 15:20:02 [INFO] train episode 54278: reward = -4.36, steps = 37 15:20:05 [INFO] train episode 54279: reward = 4.17, steps = 37 15:20:09 [INFO] train episode 54280: reward = -7.84, steps = 48 15:20:12 [INFO] train episode 54281: reward = -47.87, steps = 33 15:20:15 [INFO] train episode 54282: reward = -22.32, steps = 38 15:20:19 [INFO] train episode 54283: reward = 1.01, steps = 39 15:20:22 [INFO] train episode 54284: reward = 0.24, steps = 35 15:20:24 [INFO] train episode 54285: reward = -38.67, steps = 21 15:20:28 [INFO] train episode 54286: reward = -6.82, steps = 40 15:20:32 [INFO] train episode 54287: reward = -0.64, steps = 35 15:20:36 [INFO] train episode 54288: reward = 14.00, steps = 46 15:20:40 [INFO] train episode 54289: reward = 4.26, steps = 39 15:20:44 [INFO] train episode 54290: reward = 6.13, steps = 34 15:20:47 [INFO] train episode 54291: reward = 5.81, steps = 37 15:20:51 [INFO] train episode 54292: reward = -4.48, steps = 42 15:20:54 [INFO] train episode 54293: reward = -9.62, steps = 41 15:20:59 [INFO] train episode 54294: reward = 1.55, steps = 46 15:21:01 [INFO] train episode 54295: reward = -16.03, steps = 27 15:21:04 [INFO] train episode 54296: reward = -12.91, steps = 33 15:21:08 [INFO] train episode 54297: reward = 8.84, steps = 43 15:21:13 [INFO] train episode 54298: reward = -45.20, steps = 54 15:21:16 [INFO] train episode 54299: reward = 2.22, steps = 33 15:21:18 [INFO] train episode 54300: reward = -21.67, steps = 29 15:21:23 [INFO] train episode 54301: reward = 6.96, steps = 52 15:21:26 [INFO] train episode 54302: reward = 6.53, steps = 32 15:21:30 [INFO] train episode 54303: reward = 3.44, steps = 41 15:21:33 [INFO] train episode 54304: reward = -19.56, steps = 36 15:21:36 [INFO] train episode 54305: reward = 4.17, steps = 36 15:21:41 [INFO] train episode 54306: reward = -8.38, steps = 58 15:21:45 [INFO] train episode 54307: reward = 1.16, steps = 46 15:21:49 [INFO] train episode 54308: reward = 5.80, steps = 40 15:21:50 [INFO] train episode 54309: reward = -31.50, steps = 21 15:21:54 [INFO] train episode 54310: reward = 3.35, steps = 38 15:21:57 [INFO] train episode 54311: reward = 5.43, steps = 38 15:22:01 [INFO] train episode 54312: reward = 8.69, steps = 35 15:22:05 [INFO] train episode 54313: reward = 3.59, steps = 42 15:22:11 [INFO] train episode 54314: reward = 9.43, steps = 74 15:22:15 [INFO] train episode 54315: reward = 6.34, steps = 42 15:22:19 [INFO] train episode 54316: reward = 1.38, steps = 42 15:22:22 [INFO] train episode 54317: reward = -9.97, steps = 41 15:22:27 [INFO] train episode 54318: reward = 11.10, steps = 55 15:22:31 [INFO] train episode 54319: reward = -6.37, steps = 42 15:22:34 [INFO] train episode 54320: reward = 13.08, steps = 36 15:22:38 [INFO] train episode 54321: reward = -0.39, steps = 41 15:22:43 [INFO] train episode 54322: reward = 20.70, steps = 58 15:22:47 [INFO] train episode 54323: reward = -5.40, steps = 45 15:22:50 [INFO] train episode 54324: reward = -12.50, steps = 42 15:22:54 [INFO] train episode 54325: reward = -15.57, steps = 33 15:22:56 [INFO] train episode 54326: reward = -18.78, steps = 28 15:23:00 [INFO] train episode 54327: reward = 2.88, steps = 43 15:23:03 [INFO] train episode 54328: reward = -22.14, steps = 40 15:23:07 [INFO] train episode 54329: reward = 3.70, steps = 39 15:23:10 [INFO] train episode 54330: reward = -9.60, steps = 37 15:23:14 [INFO] train episode 54331: reward = 8.58, steps = 38 15:23:17 [INFO] train episode 54332: reward = 3.53, steps = 41 15:23:21 [INFO] train episode 54333: reward = 1.01, steps = 40 15:23:23 [INFO] train episode 54334: reward = -15.72, steps = 27 15:23:27 [INFO] train episode 54335: reward = 12.48, steps = 41 15:23:31 [INFO] train episode 54336: reward = 7.75, steps = 44 15:23:34 [INFO] train episode 54337: reward = 0.19, steps = 37 15:23:36 [INFO] train episode 54338: reward = -13.25, steps = 23 15:23:40 [INFO] train episode 54339: reward = -1.39, steps = 48 15:23:43 [INFO] train episode 54340: reward = -3.01, steps = 33 15:23:47 [INFO] train episode 54341: reward = -25.75, steps = 39 15:23:48 [INFO] train episode 54342: reward = -24.14, steps = 20 15:23:51 [INFO] train episode 54343: reward = -4.34, steps = 32 15:23:53 [INFO] train episode 54344: reward = -30.84, steps = 22 15:23:57 [INFO] train episode 54345: reward = 10.82, steps = 39 15:23:59 [INFO] train episode 54346: reward = -23.99, steps = 21 15:24:02 [INFO] train episode 54347: reward = -13.61, steps = 32 15:24:05 [INFO] train episode 54348: reward = 9.25, steps = 42 15:24:08 [INFO] train episode 54349: reward = -6.47, steps = 31 15:24:12 [INFO] train episode 54350: reward = 5.30, steps = 43 15:24:15 [INFO] train episode 54351: reward = -12.71, steps = 39 15:24:18 [INFO] train episode 54352: reward = -19.15, steps = 33 15:24:22 [INFO] train episode 54353: reward = -1.19, steps = 42 15:24:25 [INFO] train episode 54354: reward = -14.82, steps = 31 15:24:27 [INFO] train episode 54355: reward = 0.50, steps = 30 15:24:32 [INFO] train episode 54356: reward = 7.33, steps = 47 15:24:35 [INFO] train episode 54357: reward = 5.01, steps = 46 15:24:38 [INFO] train episode 54358: reward = -11.91, steps = 32 15:24:42 [INFO] train episode 54359: reward = 1.38, steps = 38 15:24:45 [INFO] train episode 54360: reward = -2.83, steps = 32 15:24:49 [INFO] train episode 54361: reward = -5.79, steps = 42 15:24:52 [INFO] train episode 54362: reward = -6.96, steps = 38 15:24:56 [INFO] train episode 54363: reward = -9.60, steps = 35 15:25:00 [INFO] train episode 54364: reward = 12.64, steps = 46 15:25:03 [INFO] train episode 54365: reward = -17.04, steps = 36 15:25:07 [INFO] train episode 54366: reward = -15.68, steps = 49 15:25:10 [INFO] train episode 54367: reward = -6.09, steps = 35 15:25:14 [INFO] train episode 54368: reward = -1.64, steps = 37 15:25:16 [INFO] train episode 54369: reward = -9.35, steps = 24 15:25:20 [INFO] train episode 54370: reward = -1.17, steps = 43 15:25:23 [INFO] train episode 54371: reward = -2.18, steps = 36 15:25:26 [INFO] train episode 54372: reward = -28.86, steps = 33 15:25:33 [INFO] train episode 54373: reward = 8.81, steps = 83 15:25:37 [INFO] train episode 54374: reward = 6.24, steps = 37 15:25:40 [INFO] train episode 54375: reward = -3.24, steps = 38 15:25:43 [INFO] train episode 54376: reward = -7.56, steps = 31 15:25:45 [INFO] train episode 54377: reward = -0.66, steps = 30 15:25:49 [INFO] train episode 54378: reward = -2.77, steps = 40 15:25:53 [INFO] train episode 54379: reward = 0.55, steps = 48 15:25:55 [INFO] train episode 54380: reward = -16.70, steps = 21 15:25:58 [INFO] train episode 54381: reward = -4.61, steps = 31 15:26:01 [INFO] train episode 54382: reward = -7.86, steps = 34 15:26:04 [INFO] train episode 54383: reward = 11.24, steps = 42 15:26:08 [INFO] train episode 54384: reward = 19.39, steps = 43 15:26:12 [INFO] train episode 54385: reward = 13.11, steps = 45 15:26:16 [INFO] train episode 54386: reward = 0.36, steps = 41 15:26:20 [INFO] train episode 54387: reward = 4.05, steps = 43 15:26:23 [INFO] train episode 54388: reward = 11.87, steps = 39 15:26:27 [INFO] train episode 54389: reward = -10.61, steps = 45 15:26:30 [INFO] train episode 54390: reward = -6.82, steps = 31 15:26:33 [INFO] train episode 54391: reward = -2.31, steps = 37 15:26:37 [INFO] train episode 54392: reward = 5.66, steps = 43 15:26:40 [INFO] train episode 54393: reward = -2.31, steps = 34 15:26:44 [INFO] train episode 54394: reward = -23.82, steps = 42 15:26:47 [INFO] train episode 54395: reward = -5.26, steps = 32 15:26:50 [INFO] train episode 54396: reward = -2.69, steps = 39 15:26:53 [INFO] train episode 54397: reward = -9.20, steps = 29 15:26:56 [INFO] train episode 54398: reward = -24.78, steps = 29 15:26:59 [INFO] train episode 54399: reward = 3.32, steps = 37 15:27:01 [INFO] train episode 54400: reward = -43.97, steps = 20 15:27:03 [INFO] train episode 54401: reward = -24.68, steps = 21 15:27:05 [INFO] train episode 54402: reward = -31.67, steps = 28 15:27:09 [INFO] train episode 54403: reward = 7.41, steps = 42 15:27:12 [INFO] train episode 54404: reward = 2.63, steps = 36 15:27:16 [INFO] train episode 54405: reward = 5.26, steps = 41 15:27:20 [INFO] train episode 54406: reward = -1.81, steps = 45 15:27:22 [INFO] train episode 54407: reward = -9.68, steps = 31 15:27:26 [INFO] train episode 54408: reward = -3.03, steps = 36 15:27:30 [INFO] train episode 54409: reward = -11.66, steps = 44 15:27:33 [INFO] train episode 54410: reward = -6.24, steps = 40 15:27:36 [INFO] train episode 54411: reward = -6.79, steps = 33 15:27:39 [INFO] train episode 54412: reward = 11.70, steps = 37 15:27:42 [INFO] train episode 54413: reward = -32.84, steps = 30 15:27:45 [INFO] train episode 54414: reward = -25.27, steps = 33 15:27:47 [INFO] train episode 54415: reward = -17.51, steps = 20 15:27:51 [INFO] train episode 54416: reward = 10.12, steps = 36 15:27:54 [INFO] train episode 54417: reward = 3.98, steps = 38 15:27:57 [INFO] train episode 54418: reward = -7.42, steps = 30 15:28:00 [INFO] train episode 54419: reward = 1.11, steps = 36 15:28:04 [INFO] train episode 54420: reward = -1.94, steps = 37 15:28:07 [INFO] train episode 54421: reward = 12.14, steps = 41 15:28:11 [INFO] train episode 54422: reward = 1.35, steps = 39 15:28:14 [INFO] train episode 54423: reward = 3.81, steps = 34 15:28:17 [INFO] train episode 54424: reward = 1.73, steps = 44 15:28:22 [INFO] train episode 54425: reward = -20.00, steps = 44 15:28:25 [INFO] train episode 54426: reward = 4.62, steps = 33 15:28:28 [INFO] train episode 54427: reward = 3.98, steps = 42 15:28:32 [INFO] train episode 54428: reward = 5.98, steps = 43 15:28:36 [INFO] train episode 54429: reward = -8.51, steps = 43 15:28:39 [INFO] train episode 54430: reward = -3.70, steps = 33 15:28:42 [INFO] train episode 54431: reward = -22.37, steps = 31 15:28:46 [INFO] train episode 54432: reward = 14.31, steps = 42 15:28:49 [INFO] train episode 54433: reward = -17.26, steps = 35 15:28:52 [INFO] train episode 54434: reward = -13.24, steps = 29 15:28:55 [INFO] train episode 54435: reward = 2.82, steps = 45 15:29:00 [INFO] train episode 54436: reward = 8.68, steps = 50 15:29:02 [INFO] train episode 54437: reward = -24.01, steps = 24 15:29:08 [INFO] train episode 54438: reward = 13.11, steps = 53 15:29:11 [INFO] train episode 54439: reward = -0.71, steps = 38 15:29:16 [INFO] train episode 54440: reward = -10.93, steps = 54 15:29:19 [INFO] train episode 54441: reward = 11.94, steps = 39 15:29:21 [INFO] train episode 54442: reward = -32.36, steps = 20 15:29:23 [INFO] train episode 54443: reward = -29.41, steps = 26 15:29:27 [INFO] train episode 54444: reward = 5.30, steps = 38 15:29:30 [INFO] train episode 54445: reward = 8.13, steps = 36 15:29:34 [INFO] train episode 54446: reward = -9.24, steps = 39 15:29:37 [INFO] train episode 54447: reward = 7.91, steps = 36 15:29:40 [INFO] train episode 54448: reward = -3.00, steps = 37 15:29:44 [INFO] train episode 54449: reward = -1.60, steps = 39 15:29:47 [INFO] train episode 54450: reward = -19.85, steps = 41 15:29:50 [INFO] train episode 54451: reward = -24.61, steps = 32 15:29:55 [INFO] train episode 54452: reward = 11.93, steps = 57 15:29:58 [INFO] train episode 54453: reward = -20.39, steps = 26 15:30:01 [INFO] train episode 54454: reward = -7.59, steps = 44 15:30:05 [INFO] train episode 54455: reward = -12.12, steps = 36 15:30:08 [INFO] train episode 54456: reward = 3.29, steps = 42 15:30:11 [INFO] train episode 54457: reward = -5.92, steps = 35 15:30:15 [INFO] train episode 54458: reward = 8.88, steps = 38 15:30:19 [INFO] train episode 54459: reward = 1.10, steps = 48 15:30:23 [INFO] train episode 54460: reward = 23.38, steps = 46 15:30:26 [INFO] train episode 54461: reward = 3.51, steps = 37 15:30:28 [INFO] train episode 54462: reward = -33.75, steps = 20 15:30:31 [INFO] train episode 54463: reward = -17.99, steps = 33 15:30:34 [INFO] train episode 54464: reward = 14.20, steps = 37 15:30:38 [INFO] train episode 54465: reward = -7.02, steps = 40 15:30:42 [INFO] train episode 54466: reward = -1.70, steps = 46 15:30:45 [INFO] train episode 54467: reward = -10.41, steps = 33 15:30:51 [INFO] train episode 54468: reward = -28.27, steps = 52 15:30:54 [INFO] train episode 54469: reward = -0.27, steps = 40 15:30:56 [INFO] train episode 54470: reward = -27.76, steps = 20 15:31:00 [INFO] train episode 54471: reward = 9.47, steps = 43 15:31:02 [INFO] train episode 54472: reward = -19.71, steps = 22 15:31:05 [INFO] train episode 54473: reward = 7.30, steps = 40 15:31:08 [INFO] train episode 54474: reward = -6.16, steps = 32 15:31:13 [INFO] train episode 54475: reward = 3.02, steps = 58 15:31:17 [INFO] train episode 54476: reward = -6.97, steps = 44 15:31:21 [INFO] train episode 54477: reward = -13.62, steps = 39 15:31:24 [INFO] train episode 54478: reward = -3.02, steps = 38 15:31:28 [INFO] train episode 54479: reward = 3.78, steps = 45 15:31:32 [INFO] train episode 54480: reward = 5.97, steps = 44 15:31:35 [INFO] train episode 54481: reward = -10.17, steps = 30 15:31:39 [INFO] train episode 54482: reward = 8.57, steps = 51 15:31:42 [INFO] train episode 54483: reward = -6.01, steps = 31 15:31:46 [INFO] train episode 54484: reward = -4.67, steps = 46 15:31:49 [INFO] train episode 54485: reward = 3.70, steps = 30 15:31:53 [INFO] train episode 54486: reward = -2.78, steps = 39 15:31:56 [INFO] train episode 54487: reward = 6.52, steps = 39 15:31:59 [INFO] train episode 54488: reward = 6.93, steps = 37 15:32:03 [INFO] train episode 54489: reward = 11.44, steps = 47 15:32:05 [INFO] train episode 54490: reward = -58.50, steps = 21 15:32:09 [INFO] train episode 54491: reward = -2.41, steps = 43 15:32:12 [INFO] train episode 54492: reward = 8.01, steps = 37 15:32:14 [INFO] train episode 54493: reward = -24.52, steps = 21 15:32:18 [INFO] train episode 54494: reward = 7.45, steps = 44 15:32:23 [INFO] train episode 54495: reward = 9.20, steps = 47 15:32:26 [INFO] train episode 54496: reward = 7.70, steps = 37 15:32:29 [INFO] train episode 54497: reward = -14.02, steps = 32 15:32:32 [INFO] train episode 54498: reward = -18.39, steps = 35 15:32:35 [INFO] train episode 54499: reward = 7.74, steps = 33 15:32:38 [INFO] train episode 54500: reward = -5.04, steps = 34 15:32:43 [INFO] train episode 54501: reward = 7.15, steps = 54 15:32:46 [INFO] train episode 54502: reward = -23.50, steps = 28 15:32:48 [INFO] train episode 54503: reward = -16.28, steps = 22 15:32:51 [INFO] train episode 54504: reward = 4.40, steps = 36 15:32:54 [INFO] train episode 54505: reward = 11.35, steps = 43 15:32:57 [INFO] train episode 54506: reward = -3.36, steps = 29 15:33:01 [INFO] train episode 54507: reward = 6.19, steps = 38 15:33:05 [INFO] train episode 54508: reward = 20.00, steps = 46 15:33:08 [INFO] train episode 54509: reward = 7.96, steps = 39 15:33:12 [INFO] train episode 54510: reward = -5.55, steps = 37 15:33:15 [INFO] train episode 54511: reward = 2.00, steps = 37 15:33:18 [INFO] train episode 54512: reward = -8.23, steps = 35 15:33:25 [INFO] train episode 54513: reward = -13.48, steps = 84 15:33:29 [INFO] train episode 54514: reward = -58.27, steps = 37 15:33:32 [INFO] train episode 54515: reward = 6.89, steps = 35 15:33:36 [INFO] train episode 54516: reward = 2.42, steps = 47 15:33:39 [INFO] train episode 54517: reward = -15.07, steps = 36 15:33:41 [INFO] train episode 54518: reward = -12.94, steps = 23 15:33:45 [INFO] train episode 54519: reward = -4.74, steps = 39 15:33:49 [INFO] train episode 54520: reward = -2.83, steps = 40 15:33:53 [INFO] train episode 54521: reward = -1.53, steps = 43 15:33:56 [INFO] train episode 54522: reward = 3.80, steps = 37 15:34:01 [INFO] train episode 54523: reward = -30.41, steps = 47 15:34:03 [INFO] train episode 54524: reward = -21.95, steps = 24 15:34:07 [INFO] train episode 54525: reward = -8.35, steps = 48 15:34:11 [INFO] train episode 54526: reward = -16.24, steps = 41 15:34:13 [INFO] train episode 54527: reward = -8.95, steps = 30 15:34:17 [INFO] train episode 54528: reward = 4.17, steps = 39 15:34:21 [INFO] train episode 54529: reward = -47.28, steps = 41 15:34:24 [INFO] train episode 54530: reward = -26.54, steps = 39 15:34:27 [INFO] train episode 54531: reward = -2.59, steps = 34 15:34:29 [INFO] train episode 54532: reward = -36.22, steps = 21 15:34:33 [INFO] train episode 54533: reward = -18.16, steps = 46 15:34:39 [INFO] train episode 54534: reward = -1.60, steps = 63 15:34:42 [INFO] train episode 54535: reward = -0.77, steps = 35 15:34:45 [INFO] train episode 54536: reward = -14.85, steps = 40 15:34:50 [INFO] train episode 54537: reward = -3.74, steps = 46 15:34:54 [INFO] train episode 54538: reward = 8.35, steps = 45 15:34:56 [INFO] train episode 54539: reward = -9.95, steps = 31 15:34:59 [INFO] train episode 54540: reward = 7.57, steps = 36 15:35:03 [INFO] train episode 54541: reward = 19.71, steps = 44 15:35:07 [INFO] train episode 54542: reward = -0.12, steps = 42 15:35:10 [INFO] train episode 54543: reward = -25.04, steps = 34 15:35:14 [INFO] train episode 54544: reward = -4.42, steps = 48 15:35:17 [INFO] train episode 54545: reward = -14.17, steps = 35 15:35:21 [INFO] train episode 54546: reward = 3.48, steps = 37 15:35:24 [INFO] train episode 54547: reward = -33.22, steps = 29 15:35:27 [INFO] train episode 54548: reward = -20.27, steps = 40 15:35:30 [INFO] train episode 54549: reward = 1.49, steps = 37 15:35:33 [INFO] train episode 54550: reward = -17.82, steps = 26 15:35:34 [INFO] train episode 54551: reward = -33.86, steps = 19 15:35:37 [INFO] train episode 54552: reward = 3.46, steps = 32 15:35:43 [INFO] train episode 54553: reward = -10.60, steps = 65 15:35:46 [INFO] train episode 54554: reward = 0.06, steps = 37 15:35:49 [INFO] train episode 54555: reward = 0.46, steps = 36 15:35:52 [INFO] train episode 54556: reward = -7.92, steps = 26 15:35:54 [INFO] train episode 54557: reward = -19.80, steps = 26 15:35:57 [INFO] train episode 54558: reward = 5.02, steps = 35 15:36:01 [INFO] train episode 54559: reward = -11.09, steps = 44 15:36:04 [INFO] train episode 54560: reward = -1.63, steps = 31 15:36:07 [INFO] train episode 54561: reward = -8.00, steps = 40 15:36:11 [INFO] train episode 54562: reward = 4.86, steps = 42 15:36:14 [INFO] train episode 54563: reward = 2.33, steps = 32 15:36:18 [INFO] train episode 54564: reward = -8.56, steps = 42 15:36:21 [INFO] train episode 54565: reward = 9.92, steps = 41 15:36:25 [INFO] train episode 54566: reward = -4.94, steps = 41 15:36:30 [INFO] train episode 54567: reward = -25.15, steps = 54 15:36:33 [INFO] train episode 54568: reward = 3.30, steps = 34 15:36:35 [INFO] train episode 54569: reward = -10.74, steps = 27 15:36:39 [INFO] train episode 54570: reward = -17.59, steps = 43 15:36:44 [INFO] train episode 54571: reward = -8.21, steps = 45 15:36:47 [INFO] train episode 54572: reward = -14.98, steps = 36 15:36:51 [INFO] train episode 54573: reward = -6.07, steps = 46 15:36:55 [INFO] train episode 54574: reward = 7.11, steps = 43 15:36:58 [INFO] train episode 54575: reward = -13.74, steps = 32 15:37:01 [INFO] train episode 54576: reward = -8.14, steps = 35 15:37:04 [INFO] train episode 54577: reward = -28.10, steps = 33 15:37:07 [INFO] train episode 54578: reward = -17.17, steps = 26 15:37:10 [INFO] train episode 54579: reward = -22.64, steps = 37 15:37:12 [INFO] train episode 54580: reward = -14.13, steps = 23 15:37:15 [INFO] train episode 54581: reward = 0.70, steps = 37 15:37:18 [INFO] train episode 54582: reward = 0.08, steps = 33 15:37:22 [INFO] train episode 54583: reward = 13.50, steps = 42 15:37:25 [INFO] train episode 54584: reward = -8.43, steps = 34 15:37:28 [INFO] train episode 54585: reward = 4.08, steps = 33 15:37:30 [INFO] train episode 54586: reward = -4.30, steps = 29 15:37:34 [INFO] train episode 54587: reward = -3.55, steps = 44 15:37:37 [INFO] train episode 54588: reward = -12.22, steps = 29 15:37:41 [INFO] train episode 54589: reward = -2.12, steps = 48 15:37:45 [INFO] train episode 54590: reward = -8.97, steps = 39 15:37:49 [INFO] train episode 54591: reward = -56.31, steps = 55 15:37:53 [INFO] train episode 54592: reward = 4.69, steps = 40 15:38:00 [INFO] train episode 54593: reward = 11.21, steps = 80 15:38:04 [INFO] train episode 54594: reward = -12.46, steps = 46 15:38:07 [INFO] train episode 54595: reward = -12.45, steps = 34 15:38:11 [INFO] train episode 54596: reward = -5.63, steps = 38 15:38:13 [INFO] train episode 54597: reward = -5.07, steps = 30 15:38:16 [INFO] train episode 54598: reward = 4.65, steps = 34 15:38:19 [INFO] train episode 54599: reward = -9.73, steps = 33 15:38:22 [INFO] train episode 54600: reward = 10.28, steps = 37 15:38:26 [INFO] train episode 54601: reward = 1.55, steps = 33 15:38:29 [INFO] train episode 54602: reward = -18.42, steps = 35 15:38:33 [INFO] train episode 54603: reward = 8.36, steps = 50 15:38:37 [INFO] train episode 54604: reward = 20.72, steps = 40 15:38:40 [INFO] train episode 54605: reward = -10.29, steps = 35 15:38:43 [INFO] train episode 54606: reward = 0.39, steps = 36 15:38:47 [INFO] train episode 54607: reward = -3.94, steps = 38 15:38:49 [INFO] train episode 54608: reward = -13.55, steps = 32 15:38:52 [INFO] train episode 54609: reward = -2.23, steps = 33 15:38:56 [INFO] train episode 54610: reward = 5.42, steps = 43 15:39:00 [INFO] train episode 54611: reward = -2.62, steps = 38 15:39:04 [INFO] train episode 54612: reward = 2.26, steps = 49 15:39:07 [INFO] train episode 54613: reward = 5.04, steps = 33 15:39:10 [INFO] train episode 54614: reward = -2.05, steps = 33 15:39:14 [INFO] train episode 54615: reward = -11.84, steps = 41 15:39:18 [INFO] train episode 54616: reward = -6.16, steps = 50 15:39:22 [INFO] train episode 54617: reward = -1.42, steps = 44 15:39:26 [INFO] train episode 54618: reward = 5.01, steps = 44 15:39:29 [INFO] train episode 54619: reward = -4.28, steps = 40 15:39:37 [INFO] train episode 54620: reward = -73.58, steps = 94 15:39:42 [INFO] train episode 54621: reward = -0.12, steps = 39 15:39:45 [INFO] train episode 54622: reward = 0.84, steps = 41 15:39:49 [INFO] train episode 54623: reward = 1.80, steps = 38 15:39:53 [INFO] train episode 54624: reward = 0.49, steps = 44 15:39:57 [INFO] train episode 54625: reward = 13.75, steps = 46 15:40:03 [INFO] train episode 54626: reward = 5.33, steps = 63 15:40:06 [INFO] train episode 54627: reward = -16.11, steps = 37 15:40:09 [INFO] train episode 54628: reward = 11.15, steps = 38 15:40:14 [INFO] train episode 54629: reward = 0.79, steps = 46 15:40:17 [INFO] train episode 54630: reward = 7.10, steps = 32 15:40:19 [INFO] train episode 54631: reward = -17.40, steps = 27 15:40:23 [INFO] train episode 54632: reward = -12.08, steps = 37 15:40:26 [INFO] train episode 54633: reward = 1.91, steps = 34 15:40:29 [INFO] train episode 54634: reward = -9.45, steps = 34 15:40:33 [INFO] train episode 54635: reward = -14.03, steps = 43 15:40:37 [INFO] train episode 54636: reward = -3.71, steps = 46 15:40:41 [INFO] train episode 54637: reward = 0.08, steps = 37 15:40:45 [INFO] train episode 54638: reward = -7.06, steps = 45 15:40:50 [INFO] train episode 54639: reward = -4.94, steps = 53 15:40:55 [INFO] train episode 54640: reward = 8.70, steps = 56 15:40:59 [INFO] train episode 54641: reward = 3.98, steps = 53 15:41:07 [INFO] train episode 54642: reward = 4.13, steps = 85 15:41:11 [INFO] train episode 54643: reward = -9.62, steps = 43 15:41:14 [INFO] train episode 54644: reward = -0.25, steps = 34 15:41:20 [INFO] train episode 54645: reward = -20.54, steps = 76 15:41:24 [INFO] train episode 54646: reward = 2.16, steps = 41 15:41:27 [INFO] train episode 54647: reward = -16.81, steps = 33 15:41:31 [INFO] train episode 54648: reward = 9.66, steps = 45 15:41:34 [INFO] train episode 54649: reward = -11.07, steps = 39 15:41:37 [INFO] train episode 54650: reward = -7.32, steps = 29 15:41:40 [INFO] train episode 54651: reward = -5.20, steps = 35 15:41:45 [INFO] train episode 54652: reward = -4.73, steps = 45 15:41:47 [INFO] train episode 54653: reward = -39.22, steps = 33 15:41:51 [INFO] train episode 54654: reward = 5.35, steps = 37 15:41:54 [INFO] train episode 54655: reward = 13.98, steps = 44 15:41:59 [INFO] train episode 54656: reward = 14.60, steps = 49 15:42:02 [INFO] train episode 54657: reward = 1.37, steps = 34 15:42:06 [INFO] train episode 54658: reward = 1.71, steps = 44 15:42:08 [INFO] train episode 54659: reward = -25.93, steps = 28 15:42:12 [INFO] train episode 54660: reward = 11.94, steps = 51 15:42:16 [INFO] train episode 54661: reward = 0.92, steps = 38 15:42:19 [INFO] train episode 54662: reward = -17.03, steps = 33 15:42:23 [INFO] train episode 54663: reward = 11.81, steps = 46 15:42:28 [INFO] train episode 54664: reward = 20.12, steps = 58 15:42:32 [INFO] train episode 54665: reward = 2.86, steps = 48 15:42:36 [INFO] train episode 54666: reward = -7.51, steps = 39 15:42:40 [INFO] train episode 54667: reward = -0.08, steps = 42 15:42:44 [INFO] train episode 54668: reward = 12.07, steps = 40 15:42:48 [INFO] train episode 54669: reward = -4.22, steps = 38 15:42:51 [INFO] train episode 54670: reward = 9.11, steps = 37 15:42:54 [INFO] train episode 54671: reward = -0.92, steps = 35 15:42:58 [INFO] train episode 54672: reward = 3.67, steps = 44 15:43:02 [INFO] train episode 54673: reward = 16.38, steps = 43 15:43:06 [INFO] train episode 54674: reward = 1.85, steps = 34 15:43:09 [INFO] train episode 54675: reward = 2.78, steps = 41 15:43:12 [INFO] train episode 54676: reward = 1.80, steps = 34 15:43:15 [INFO] train episode 54677: reward = 3.53, steps = 35 15:43:18 [INFO] train episode 54678: reward = -3.33, steps = 32 15:43:22 [INFO] train episode 54679: reward = 16.26, steps = 47 15:43:25 [INFO] train episode 54680: reward = -9.69, steps = 31 15:43:28 [INFO] train episode 54681: reward = -15.34, steps = 32 15:43:31 [INFO] train episode 54682: reward = -7.28, steps = 37 15:43:35 [INFO] train episode 54683: reward = 14.66, steps = 49 15:43:39 [INFO] train episode 54684: reward = 3.30, steps = 36 15:43:40 [INFO] train episode 54685: reward = -33.99, steps = 20 15:43:43 [INFO] train episode 54686: reward = 1.74, steps = 34 15:43:47 [INFO] train episode 54687: reward = 3.56, steps = 40 15:43:50 [INFO] train episode 54688: reward = 6.59, steps = 39 15:43:54 [INFO] train episode 54689: reward = -5.99, steps = 35 15:43:57 [INFO] train episode 54690: reward = -2.06, steps = 43 15:44:01 [INFO] train episode 54691: reward = 2.56, steps = 39 15:44:02 [INFO] train episode 54692: reward = -18.04, steps = 20 15:44:06 [INFO] train episode 54693: reward = 0.44, steps = 43 15:44:12 [INFO] train episode 54694: reward = 8.92, steps = 58 15:44:15 [INFO] train episode 54695: reward = 1.31, steps = 37 15:44:17 [INFO] train episode 54696: reward = -44.18, steps = 22 15:44:21 [INFO] train episode 54697: reward = -6.74, steps = 49 15:44:24 [INFO] train episode 54698: reward = -9.11, steps = 30 15:44:28 [INFO] train episode 54699: reward = 5.50, steps = 45 15:44:31 [INFO] train episode 54700: reward = -6.63, steps = 33 15:44:33 [INFO] train episode 54701: reward = -25.28, steps = 22 15:44:37 [INFO] train episode 54702: reward = 1.13, steps = 48 15:44:41 [INFO] train episode 54703: reward = 8.55, steps = 40 15:44:44 [INFO] train episode 54704: reward = -16.55, steps = 32 15:44:47 [INFO] train episode 54705: reward = 3.10, steps = 39 15:44:52 [INFO] train episode 54706: reward = 5.96, steps = 49 15:44:55 [INFO] train episode 54707: reward = 0.30, steps = 38 15:44:58 [INFO] train episode 54708: reward = -6.02, steps = 30 15:45:01 [INFO] train episode 54709: reward = 5.25, steps = 39 15:45:04 [INFO] train episode 54710: reward = 1.94, steps = 34 15:45:07 [INFO] train episode 54711: reward = -1.88, steps = 35 15:45:11 [INFO] train episode 54712: reward = 6.14, steps = 38 15:45:13 [INFO] train episode 54713: reward = -5.30, steps = 33 15:45:17 [INFO] train episode 54714: reward = -0.47, steps = 34 15:45:18 [INFO] train episode 54715: reward = -51.71, steps = 19 15:45:21 [INFO] train episode 54716: reward = 5.45, steps = 35 15:45:25 [INFO] train episode 54717: reward = 6.55, steps = 37 15:45:28 [INFO] train episode 54718: reward = 3.51, steps = 38 15:45:32 [INFO] train episode 54719: reward = 10.94, steps = 41 15:45:36 [INFO] train episode 54720: reward = 15.35, steps = 40 15:45:39 [INFO] train episode 54721: reward = 9.76, steps = 35 15:45:43 [INFO] train episode 54722: reward = 10.82, steps = 38 15:45:45 [INFO] train episode 54723: reward = -34.13, steps = 22 15:45:49 [INFO] train episode 54724: reward = 7.15, steps = 40 15:45:52 [INFO] train episode 54725: reward = 6.32, steps = 38 15:45:55 [INFO] train episode 54726: reward = -13.62, steps = 30 15:45:58 [INFO] train episode 54727: reward = 0.19, steps = 36 15:46:01 [INFO] train episode 54728: reward = -9.00, steps = 32 15:46:04 [INFO] train episode 54729: reward = -3.09, steps = 28 15:46:09 [INFO] train episode 54730: reward = 6.18, steps = 58 15:46:12 [INFO] train episode 54731: reward = -10.96, steps = 32 15:46:15 [INFO] train episode 54732: reward = -3.94, steps = 35 15:46:18 [INFO] train episode 54733: reward = -6.07, steps = 34 15:46:21 [INFO] train episode 54734: reward = 10.20, steps = 36 15:46:25 [INFO] train episode 54735: reward = -0.75, steps = 38 15:46:27 [INFO] train episode 54736: reward = -18.98, steps = 25 15:46:30 [INFO] train episode 54737: reward = -6.14, steps = 40 15:46:34 [INFO] train episode 54738: reward = -2.93, steps = 44 15:46:38 [INFO] train episode 54739: reward = 1.68, steps = 41 15:46:41 [INFO] train episode 54740: reward = 0.20, steps = 36 15:46:43 [INFO] train episode 54741: reward = -9.50, steps = 23 15:46:47 [INFO] train episode 54742: reward = 0.45, steps = 38 15:46:49 [INFO] train episode 54743: reward = -13.65, steps = 24 15:46:52 [INFO] train episode 54744: reward = -2.73, steps = 32 15:46:54 [INFO] train episode 54745: reward = -32.82, steps = 20 15:46:57 [INFO] train episode 54746: reward = 12.32, steps = 38 15:47:01 [INFO] train episode 54747: reward = -9.07, steps = 38 15:47:04 [INFO] train episode 54748: reward = 13.54, steps = 46 15:47:08 [INFO] train episode 54749: reward = 8.70, steps = 36 15:47:11 [INFO] train episode 54750: reward = -4.10, steps = 35 15:47:14 [INFO] train episode 54751: reward = 14.52, steps = 40 15:47:17 [INFO] train episode 54752: reward = 3.96, steps = 33 15:47:19 [INFO] train episode 54753: reward = -37.09, steps = 22 15:47:23 [INFO] train episode 54754: reward = -20.89, steps = 43 15:47:27 [INFO] train episode 54755: reward = 2.22, steps = 49 15:47:30 [INFO] train episode 54756: reward = -0.82, steps = 35 15:47:33 [INFO] train episode 54757: reward = -1.28, steps = 31 15:47:35 [INFO] train episode 54758: reward = -14.55, steps = 23 15:47:39 [INFO] train episode 54759: reward = 6.35, steps = 43 15:47:42 [INFO] train episode 54760: reward = 6.79, steps = 37 15:47:46 [INFO] train episode 54761: reward = 13.58, steps = 37 15:47:48 [INFO] train episode 54762: reward = -22.63, steps = 30 15:47:52 [INFO] train episode 54763: reward = -30.42, steps = 37 15:47:56 [INFO] train episode 54764: reward = 6.75, steps = 47 15:47:59 [INFO] train episode 54765: reward = -8.44, steps = 37 15:48:03 [INFO] train episode 54766: reward = -10.97, steps = 39 15:48:05 [INFO] train episode 54767: reward = -6.75, steps = 31 15:48:08 [INFO] train episode 54768: reward = 11.98, steps = 36 15:48:12 [INFO] train episode 54769: reward = 8.50, steps = 43 15:48:16 [INFO] train episode 54770: reward = 5.20, steps = 43 15:48:20 [INFO] train episode 54771: reward = -0.52, steps = 41 15:48:24 [INFO] train episode 54772: reward = -3.94, steps = 46 15:48:27 [INFO] train episode 54773: reward = 6.70, steps = 35 15:48:29 [INFO] train episode 54774: reward = -37.80, steps = 21 15:48:32 [INFO] train episode 54775: reward = -8.06, steps = 32 15:48:37 [INFO] train episode 54776: reward = 5.51, steps = 46 15:48:40 [INFO] train episode 54777: reward = 10.89, steps = 43 15:48:44 [INFO] train episode 54778: reward = 24.68, steps = 45 15:48:47 [INFO] train episode 54779: reward = 1.59, steps = 30 15:48:51 [INFO] train episode 54780: reward = -15.45, steps = 42 15:48:55 [INFO] train episode 54781: reward = 12.26, steps = 42 15:48:59 [INFO] train episode 54782: reward = 6.61, steps = 48 15:49:03 [INFO] train episode 54783: reward = -19.07, steps = 44 15:49:06 [INFO] train episode 54784: reward = 10.94, steps = 41 15:49:09 [INFO] train episode 54785: reward = 2.10, steps = 30 15:49:12 [INFO] train episode 54786: reward = -0.32, steps = 33 15:49:17 [INFO] train episode 54787: reward = -11.02, steps = 55 15:49:22 [INFO] train episode 54788: reward = 19.91, steps = 58 15:49:26 [INFO] train episode 54789: reward = -5.12, steps = 51 15:49:28 [INFO] train episode 54790: reward = -15.05, steps = 23 15:49:31 [INFO] train episode 54791: reward = -13.36, steps = 34 15:49:36 [INFO] train episode 54792: reward = 16.56, steps = 47 15:49:38 [INFO] train episode 54793: reward = -6.70, steps = 31 15:49:42 [INFO] train episode 54794: reward = 3.02, steps = 42 15:49:46 [INFO] train episode 54795: reward = -11.67, steps = 37 15:49:49 [INFO] train episode 54796: reward = -0.53, steps = 38 15:49:51 [INFO] train episode 54797: reward = -21.29, steps = 23 15:49:54 [INFO] train episode 54798: reward = -11.93, steps = 32 15:49:57 [INFO] train episode 54799: reward = 4.43, steps = 35 15:50:01 [INFO] train episode 54800: reward = 5.70, steps = 45 15:50:05 [INFO] train episode 54801: reward = 12.07, steps = 41 15:50:08 [INFO] train episode 54802: reward = 12.17, steps = 38 15:50:12 [INFO] train episode 54803: reward = 9.49, steps = 40 15:50:16 [INFO] train episode 54804: reward = -1.71, steps = 52 15:50:21 [INFO] train episode 54805: reward = 6.61, steps = 58 15:50:26 [INFO] train episode 54806: reward = -9.18, steps = 49 15:50:28 [INFO] train episode 54807: reward = -20.81, steps = 23 15:50:31 [INFO] train episode 54808: reward = 5.47, steps = 39 15:50:36 [INFO] train episode 54809: reward = 7.28, steps = 50 15:50:40 [INFO] train episode 54810: reward = 1.13, steps = 45 15:50:44 [INFO] train episode 54811: reward = -8.36, steps = 49 15:50:47 [INFO] train episode 54812: reward = -5.62, steps = 37 15:50:51 [INFO] train episode 54813: reward = 0.69, steps = 42 15:50:54 [INFO] train episode 54814: reward = -19.27, steps = 37 15:50:57 [INFO] train episode 54815: reward = 2.68, steps = 38 15:51:01 [INFO] train episode 54816: reward = 3.24, steps = 35 15:51:06 [INFO] train episode 54817: reward = 11.52, steps = 60 15:51:10 [INFO] train episode 54818: reward = -17.96, steps = 40 15:51:15 [INFO] train episode 54819: reward = 17.00, steps = 57 15:51:19 [INFO] train episode 54820: reward = -0.14, steps = 44 15:51:21 [INFO] train episode 54821: reward = -8.54, steps = 30 15:51:25 [INFO] train episode 54822: reward = 0.93, steps = 38 15:51:28 [INFO] train episode 54823: reward = 1.26, steps = 30 15:51:31 [INFO] train episode 54824: reward = 7.10, steps = 39 15:51:35 [INFO] train episode 54825: reward = 8.45, steps = 39 15:51:38 [INFO] train episode 54826: reward = -8.50, steps = 39 15:51:45 [INFO] train episode 54827: reward = -69.96, steps = 84 15:51:49 [INFO] train episode 54828: reward = -2.46, steps = 42 15:51:53 [INFO] train episode 54829: reward = 8.10, steps = 43 15:51:56 [INFO] train episode 54830: reward = -10.49, steps = 38 15:51:59 [INFO] train episode 54831: reward = 9.08, steps = 34 15:52:03 [INFO] train episode 54832: reward = -2.49, steps = 43 15:52:08 [INFO] train episode 54833: reward = 14.08, steps = 48 15:52:10 [INFO] train episode 54834: reward = -9.07, steps = 28 15:52:14 [INFO] train episode 54835: reward = 3.11, steps = 42 15:52:17 [INFO] train episode 54836: reward = 7.36, steps = 45 15:52:21 [INFO] train episode 54837: reward = 6.55, steps = 40 15:52:25 [INFO] train episode 54838: reward = 10.36, steps = 40 15:52:30 [INFO] train episode 54839: reward = 20.19, steps = 58 15:52:33 [INFO] train episode 54840: reward = -13.48, steps = 32 15:52:36 [INFO] train episode 54841: reward = -3.08, steps = 41 15:52:42 [INFO] train episode 54842: reward = 3.51, steps = 68 15:52:46 [INFO] train episode 54843: reward = 10.14, steps = 44 15:52:48 [INFO] train episode 54844: reward = -12.87, steps = 22 15:52:52 [INFO] train episode 54845: reward = -5.74, steps = 51 15:52:57 [INFO] train episode 54846: reward = 1.13, steps = 44 15:53:01 [INFO] train episode 54847: reward = -8.41, steps = 45 15:53:03 [INFO] train episode 54848: reward = -19.94, steps = 29 15:53:07 [INFO] train episode 54849: reward = 1.78, steps = 44 15:53:11 [INFO] train episode 54850: reward = 3.47, steps = 45 15:53:15 [INFO] train episode 54851: reward = 5.16, steps = 45 15:53:19 [INFO] train episode 54852: reward = 9.07, steps = 43 15:53:25 [INFO] train episode 54853: reward = 14.96, steps = 70 15:53:28 [INFO] train episode 54854: reward = -24.47, steps = 35 15:53:32 [INFO] train episode 54855: reward = 0.98, steps = 50 15:53:36 [INFO] train episode 54856: reward = -16.51, steps = 47 15:53:40 [INFO] train episode 54857: reward = 6.65, steps = 45 15:53:43 [INFO] train episode 54858: reward = 3.85, steps = 30 15:53:46 [INFO] train episode 54859: reward = -11.53, steps = 34 15:53:50 [INFO] train episode 54860: reward = 9.39, steps = 41 15:53:53 [INFO] train episode 54861: reward = 0.23, steps = 39 15:53:57 [INFO] train episode 54862: reward = 15.98, steps = 42 15:54:00 [INFO] train episode 54863: reward = 10.96, steps = 36 15:54:03 [INFO] train episode 54864: reward = -4.07, steps = 35 15:54:07 [INFO] train episode 54865: reward = 12.18, steps = 40 15:54:10 [INFO] train episode 54866: reward = -9.45, steps = 38 15:54:14 [INFO] train episode 54867: reward = 20.68, steps = 43 15:54:18 [INFO] train episode 54868: reward = 18.12, steps = 47 15:54:23 [INFO] train episode 54869: reward = 7.29, steps = 51 15:54:27 [INFO] train episode 54870: reward = -12.18, steps = 44 15:54:31 [INFO] train episode 54871: reward = 0.51, steps = 37 15:54:34 [INFO] train episode 54872: reward = 6.64, steps = 39 15:54:39 [INFO] train episode 54873: reward = 12.63, steps = 52 15:54:42 [INFO] train episode 54874: reward = -1.63, steps = 37 15:54:44 [INFO] train episode 54875: reward = -17.17, steps = 27 15:54:48 [INFO] train episode 54876: reward = -18.48, steps = 32 15:54:51 [INFO] train episode 54877: reward = 5.82, steps = 36 15:54:55 [INFO] train episode 54878: reward = 15.79, steps = 47 15:54:57 [INFO] train episode 54879: reward = -6.77, steps = 28 15:55:01 [INFO] train episode 54880: reward = 4.25, steps = 45 15:55:05 [INFO] train episode 54881: reward = -12.88, steps = 36 15:55:10 [INFO] train episode 54882: reward = -13.33, steps = 65 15:55:13 [INFO] train episode 54883: reward = -23.96, steps = 27 15:55:16 [INFO] train episode 54884: reward = -9.14, steps = 35 15:55:19 [INFO] train episode 54885: reward = 2.94, steps = 38 15:55:23 [INFO] train episode 54886: reward = -10.45, steps = 43 15:55:26 [INFO] train episode 54887: reward = 2.09, steps = 38 15:55:28 [INFO] train episode 54888: reward = -21.43, steps = 20 15:55:31 [INFO] train episode 54889: reward = -18.56, steps = 31 15:55:33 [INFO] train episode 54890: reward = -3.82, steps = 33 15:55:35 [INFO] train episode 54891: reward = -34.65, steps = 18 15:55:38 [INFO] train episode 54892: reward = 10.17, steps = 34 15:55:44 [INFO] train episode 54893: reward = 30.98, steps = 62 15:55:47 [INFO] train episode 54894: reward = 6.95, steps = 44 15:55:52 [INFO] train episode 54895: reward = 8.71, steps = 47 15:55:55 [INFO] train episode 54896: reward = -4.31, steps = 37 15:55:58 [INFO] train episode 54897: reward = -7.90, steps = 32 15:56:01 [INFO] train episode 54898: reward = -1.84, steps = 32 15:56:04 [INFO] train episode 54899: reward = 4.29, steps = 35 15:56:07 [INFO] train episode 54900: reward = 7.22, steps = 33 15:56:10 [INFO] train episode 54901: reward = -8.48, steps = 34 15:56:14 [INFO] train episode 54902: reward = 6.22, steps = 44 15:56:18 [INFO] train episode 54903: reward = 5.09, steps = 47 15:56:19 [INFO] train episode 54904: reward = -35.15, steps = 18 15:56:24 [INFO] train episode 54905: reward = 12.49, steps = 45 15:56:27 [INFO] train episode 54906: reward = 3.15, steps = 36 15:56:29 [INFO] train episode 54907: reward = -2.60, steps = 27 15:56:33 [INFO] train episode 54908: reward = 1.07, steps = 49 15:56:37 [INFO] train episode 54909: reward = -4.21, steps = 39 15:56:42 [INFO] train episode 54910: reward = 14.59, steps = 50 15:56:44 [INFO] train episode 54911: reward = -14.43, steps = 26 15:56:48 [INFO] train episode 54912: reward = 11.92, steps = 45 15:56:50 [INFO] train episode 54913: reward = -4.89, steps = 25 15:56:52 [INFO] train episode 54914: reward = -15.86, steps = 23 15:56:56 [INFO] train episode 54915: reward = 0.65, steps = 42 15:56:59 [INFO] train episode 54916: reward = -3.92, steps = 34 15:57:03 [INFO] train episode 54917: reward = -0.97, steps = 42 15:57:06 [INFO] train episode 54918: reward = -11.29, steps = 42 15:57:10 [INFO] train episode 54919: reward = 7.16, steps = 36 15:57:12 [INFO] train episode 54920: reward = -13.52, steps = 29 15:57:16 [INFO] train episode 54921: reward = -18.14, steps = 41 15:57:19 [INFO] train episode 54922: reward = -11.44, steps = 22 15:57:22 [INFO] train episode 54923: reward = -0.67, steps = 38 15:57:25 [INFO] train episode 54924: reward = 14.12, steps = 39 15:57:30 [INFO] train episode 54925: reward = 27.06, steps = 52 15:57:33 [INFO] train episode 54926: reward = -11.55, steps = 31 15:57:36 [INFO] train episode 54927: reward = -17.25, steps = 33 15:57:38 [INFO] train episode 54928: reward = -7.01, steps = 26 15:57:41 [INFO] train episode 54929: reward = 4.20, steps = 37 15:57:45 [INFO] train episode 54930: reward = -13.40, steps = 41 15:57:49 [INFO] train episode 54931: reward = -38.10, steps = 43 15:57:52 [INFO] train episode 54932: reward = 10.58, steps = 44 15:57:57 [INFO] train episode 54933: reward = 6.34, steps = 50 15:58:00 [INFO] train episode 54934: reward = 1.55, steps = 42 15:58:04 [INFO] train episode 54935: reward = -1.64, steps = 38 15:58:08 [INFO] train episode 54936: reward = -14.07, steps = 45 15:58:11 [INFO] train episode 54937: reward = -26.38, steps = 31 15:58:14 [INFO] train episode 54938: reward = -20.08, steps = 30 15:58:17 [INFO] train episode 54939: reward = -8.97, steps = 36 15:58:19 [INFO] train episode 54940: reward = -30.36, steps = 20 15:58:20 [INFO] train episode 54941: reward = -34.29, steps = 19 15:58:22 [INFO] train episode 54942: reward = -26.20, steps = 22 15:58:26 [INFO] train episode 54943: reward = 4.16, steps = 39 15:58:29 [INFO] train episode 54944: reward = 3.77, steps = 36 15:58:32 [INFO] train episode 54945: reward = -7.18, steps = 40 15:58:36 [INFO] train episode 54946: reward = -17.04, steps = 42 15:58:40 [INFO] train episode 54947: reward = -2.89, steps = 40 15:58:43 [INFO] train episode 54948: reward = -2.81, steps = 31 15:58:47 [INFO] train episode 54949: reward = -3.66, steps = 47 15:58:50 [INFO] train episode 54950: reward = 2.63, steps = 36 15:58:52 [INFO] train episode 54951: reward = -14.48, steps = 23 15:58:55 [INFO] train episode 54952: reward = -9.33, steps = 34 15:58:59 [INFO] train episode 54953: reward = -3.45, steps = 42 15:59:03 [INFO] train episode 54954: reward = 10.02, steps = 50 15:59:06 [INFO] train episode 54955: reward = -2.93, steps = 27 15:59:09 [INFO] train episode 54956: reward = 2.29, steps = 43 15:59:12 [INFO] train episode 54957: reward = -4.46, steps = 32 15:59:16 [INFO] train episode 54958: reward = 1.82, steps = 37 15:59:19 [INFO] train episode 54959: reward = -12.22, steps = 34 15:59:22 [INFO] train episode 54960: reward = 8.43, steps = 32 15:59:27 [INFO] train episode 54961: reward = 23.30, steps = 44 15:59:30 [INFO] train episode 54962: reward = 14.49, steps = 36 15:59:33 [INFO] train episode 54963: reward = 0.98, steps = 34 15:59:36 [INFO] train episode 54964: reward = -3.91, steps = 32 15:59:40 [INFO] train episode 54965: reward = 2.43, steps = 37 15:59:42 [INFO] train episode 54966: reward = -26.13, steps = 30 15:59:45 [INFO] train episode 54967: reward = -23.75, steps = 31 15:59:48 [INFO] train episode 54968: reward = -3.66, steps = 32 15:59:52 [INFO] train episode 54969: reward = 14.73, steps = 47 15:59:56 [INFO] train episode 54970: reward = 15.96, steps = 51 16:00:00 [INFO] train episode 54971: reward = -13.53, steps = 39 16:00:02 [INFO] train episode 54972: reward = -4.73, steps = 29 16:00:05 [INFO] train episode 54973: reward = 12.75, steps = 37 16:00:09 [INFO] train episode 54974: reward = 5.98, steps = 40 16:00:12 [INFO] train episode 54975: reward = -4.70, steps = 35 16:00:16 [INFO] train episode 54976: reward = 7.22, steps = 36 16:00:20 [INFO] train episode 54977: reward = 2.91, steps = 38 16:00:23 [INFO] train episode 54978: reward = 17.66, steps = 39 16:00:26 [INFO] train episode 54979: reward = 5.81, steps = 37 16:00:30 [INFO] train episode 54980: reward = -5.59, steps = 41 16:00:32 [INFO] train episode 54981: reward = -24.75, steps = 20 16:00:36 [INFO] train episode 54982: reward = 3.58, steps = 42 16:00:39 [INFO] train episode 54983: reward = -0.47, steps = 39 16:00:43 [INFO] train episode 54984: reward = 6.02, steps = 45 16:00:48 [INFO] train episode 54985: reward = 4.67, steps = 46 16:00:50 [INFO] train episode 54986: reward = -3.12, steps = 31 16:00:53 [INFO] train episode 54987: reward = -13.18, steps = 34 16:00:58 [INFO] train episode 54988: reward = 9.50, steps = 49 16:01:02 [INFO] train episode 54989: reward = 10.65, steps = 45 16:01:05 [INFO] train episode 54990: reward = -0.22, steps = 37 16:01:08 [INFO] train episode 54991: reward = -0.65, steps = 37 16:01:14 [INFO] train episode 54992: reward = 10.14, steps = 64 16:01:17 [INFO] train episode 54993: reward = 8.10, steps = 38 16:01:21 [INFO] train episode 54994: reward = -60.19, steps = 41 16:01:25 [INFO] train episode 54995: reward = 7.34, steps = 50 16:01:28 [INFO] train episode 54996: reward = -11.85, steps = 32 16:01:33 [INFO] train episode 54997: reward = 18.10, steps = 56 16:01:37 [INFO] train episode 54998: reward = -20.51, steps = 49 16:01:42 [INFO] train episode 54999: reward = 0.09, steps = 50 16:01:45 [INFO] train episode 55000: reward = -22.50, steps = 42 16:01:48 [INFO] train episode 55001: reward = -11.79, steps = 32 16:01:51 [INFO] train episode 55002: reward = -11.58, steps = 26 16:01:55 [INFO] train episode 55003: reward = -2.05, steps = 47 16:01:59 [INFO] train episode 55004: reward = 15.20, steps = 46 16:02:03 [INFO] train episode 55005: reward = 9.36, steps = 48 16:02:06 [INFO] train episode 55006: reward = 1.97, steps = 39 16:02:09 [INFO] train episode 55007: reward = -7.82, steps = 24 16:02:11 [INFO] train episode 55008: reward = -0.65, steps = 31 16:02:15 [INFO] train episode 55009: reward = 0.95, steps = 44 16:02:19 [INFO] train episode 55010: reward = 0.59, steps = 40 16:02:22 [INFO] train episode 55011: reward = -4.91, steps = 41 16:02:26 [INFO] train episode 55012: reward = 12.26, steps = 43 16:02:30 [INFO] train episode 55013: reward = 6.59, steps = 44 16:02:33 [INFO] train episode 55014: reward = -11.15, steps = 35 16:02:38 [INFO] train episode 55015: reward = 10.24, steps = 47 16:02:41 [INFO] train episode 55016: reward = 10.09, steps = 37 16:02:44 [INFO] train episode 55017: reward = -1.85, steps = 32 16:02:48 [INFO] train episode 55018: reward = 6.12, steps = 47 16:02:51 [INFO] train episode 55019: reward = 4.48, steps = 35 16:02:55 [INFO] train episode 55020: reward = -7.22, steps = 39 16:02:58 [INFO] train episode 55021: reward = -10.27, steps = 36 16:03:00 [INFO] train episode 55022: reward = -17.13, steps = 23 16:03:03 [INFO] train episode 55023: reward = -0.42, steps = 36 16:03:06 [INFO] train episode 55024: reward = -6.89, steps = 33 16:03:09 [INFO] train episode 55025: reward = 0.34, steps = 35 16:03:14 [INFO] train episode 55026: reward = -13.11, steps = 42 16:03:18 [INFO] train episode 55027: reward = 4.64, steps = 41 16:03:21 [INFO] train episode 55028: reward = 10.71, steps = 39 16:03:24 [INFO] train episode 55029: reward = -16.78, steps = 28 16:03:27 [INFO] train episode 55030: reward = -41.18, steps = 40 16:03:31 [INFO] train episode 55031: reward = 1.41, steps = 43 16:03:35 [INFO] train episode 55032: reward = 6.01, steps = 40 16:03:38 [INFO] train episode 55033: reward = 1.90, steps = 46 16:03:43 [INFO] train episode 55034: reward = -2.73, steps = 49 16:03:47 [INFO] train episode 55035: reward = 14.29, steps = 45 16:03:51 [INFO] train episode 55036: reward = -0.71, steps = 45 16:03:54 [INFO] train episode 55037: reward = 3.73, steps = 40 16:03:57 [INFO] train episode 55038: reward = -10.92, steps = 35 16:04:01 [INFO] train episode 55039: reward = 18.47, steps = 41 16:04:04 [INFO] train episode 55040: reward = -2.46, steps = 27 16:04:07 [INFO] train episode 55041: reward = -31.40, steps = 43 16:04:11 [INFO] train episode 55042: reward = 2.11, steps = 46 16:04:14 [INFO] train episode 55043: reward = -18.78, steps = 32 16:04:17 [INFO] train episode 55044: reward = 0.76, steps = 40 16:04:20 [INFO] train episode 55045: reward = -30.40, steps = 21 16:04:22 [INFO] train episode 55046: reward = -8.53, steps = 31 16:04:26 [INFO] train episode 55047: reward = 2.38, steps = 37 16:04:29 [INFO] train episode 55048: reward = 1.97, steps = 40 16:04:32 [INFO] train episode 55049: reward = -0.48, steps = 37 16:04:37 [INFO] train episode 55050: reward = 0.96, steps = 40 16:04:40 [INFO] train episode 55051: reward = 8.53, steps = 37 16:04:44 [INFO] train episode 55052: reward = -9.86, steps = 43 16:04:47 [INFO] train episode 55053: reward = 4.14, steps = 40 16:04:51 [INFO] train episode 55054: reward = 14.61, steps = 41 16:04:55 [INFO] train episode 55055: reward = -9.72, steps = 42 16:04:58 [INFO] train episode 55056: reward = -6.23, steps = 36 16:05:01 [INFO] train episode 55057: reward = -15.89, steps = 36 16:05:03 [INFO] train episode 55058: reward = -1.66, steps = 29 16:05:08 [INFO] train episode 55059: reward = 8.13, steps = 49 16:05:12 [INFO] train episode 55060: reward = 7.51, steps = 48 16:05:15 [INFO] train episode 55061: reward = -11.87, steps = 28 16:05:17 [INFO] train episode 55062: reward = -27.11, steps = 31 16:05:20 [INFO] train episode 55063: reward = -32.52, steps = 31 16:05:23 [INFO] train episode 55064: reward = -26.50, steps = 29 16:05:27 [INFO] train episode 55065: reward = -2.86, steps = 42 16:05:30 [INFO] train episode 55066: reward = -20.24, steps = 45 16:05:33 [INFO] train episode 55067: reward = -17.53, steps = 31 16:05:37 [INFO] train episode 55068: reward = 3.83, steps = 39 16:05:38 [INFO] train episode 55069: reward = -18.21, steps = 21 16:05:42 [INFO] train episode 55070: reward = -8.56, steps = 33 16:05:45 [INFO] train episode 55071: reward = -2.65, steps = 39 16:05:50 [INFO] train episode 55072: reward = 17.62, steps = 57 16:05:53 [INFO] train episode 55073: reward = 8.81, steps = 35 16:05:56 [INFO] train episode 55074: reward = 3.79, steps = 32 16:05:59 [INFO] train episode 55075: reward = 3.40, steps = 39 16:06:01 [INFO] train episode 55076: reward = -33.05, steps = 21 16:06:05 [INFO] train episode 55077: reward = -4.29, steps = 42 16:06:07 [INFO] train episode 55078: reward = -33.54, steps = 18 16:06:11 [INFO] train episode 55079: reward = 4.32, steps = 43 16:06:14 [INFO] train episode 55080: reward = -12.69, steps = 31 16:06:18 [INFO] train episode 55081: reward = 9.44, steps = 49 16:06:21 [INFO] train episode 55082: reward = 10.61, steps = 34 16:06:25 [INFO] train episode 55083: reward = -18.24, steps = 40 16:06:27 [INFO] train episode 55084: reward = -21.53, steps = 20 16:06:31 [INFO] train episode 55085: reward = 21.34, steps = 53 16:06:36 [INFO] train episode 55086: reward = 3.39, steps = 54 16:06:39 [INFO] train episode 55087: reward = -7.58, steps = 33 16:06:42 [INFO] train episode 55088: reward = 4.00, steps = 34 16:06:44 [INFO] train episode 55089: reward = -11.31, steps = 24 16:06:48 [INFO] train episode 55090: reward = -0.82, steps = 34 16:06:51 [INFO] train episode 55091: reward = -10.36, steps = 36 16:06:54 [INFO] train episode 55092: reward = 9.86, steps = 36 16:06:56 [INFO] train episode 55093: reward = -19.38, steps = 30 16:06:59 [INFO] train episode 55094: reward = -20.64, steps = 27 16:07:03 [INFO] train episode 55095: reward = 13.17, steps = 44 16:07:06 [INFO] train episode 55096: reward = -25.70, steps = 31 16:07:08 [INFO] train episode 55097: reward = -14.81, steps = 31 16:07:12 [INFO] train episode 55098: reward = 26.42, steps = 42 16:07:15 [INFO] train episode 55099: reward = -10.41, steps = 39 16:07:23 [INFO] train episode 55100: reward = 20.56, steps = 88 16:07:25 [INFO] train episode 55101: reward = -15.53, steps = 21 16:07:29 [INFO] train episode 55102: reward = 10.76, steps = 42 16:07:32 [INFO] train episode 55103: reward = 6.06, steps = 41 16:07:36 [INFO] train episode 55104: reward = 19.76, steps = 39 16:07:39 [INFO] train episode 55105: reward = -3.12, steps = 39 16:07:42 [INFO] train episode 55106: reward = -1.51, steps = 35 16:07:48 [INFO] train episode 55107: reward = -6.07, steps = 61 16:07:52 [INFO] train episode 55108: reward = 18.60, steps = 48 16:07:55 [INFO] train episode 55109: reward = -13.13, steps = 32 16:07:58 [INFO] train episode 55110: reward = 11.02, steps = 34 16:08:01 [INFO] train episode 55111: reward = 12.48, steps = 39 16:08:05 [INFO] train episode 55112: reward = 10.78, steps = 43 16:08:09 [INFO] train episode 55113: reward = 17.48, steps = 49 16:08:13 [INFO] train episode 55114: reward = -22.40, steps = 46 16:08:17 [INFO] train episode 55115: reward = 2.96, steps = 36 16:08:19 [INFO] train episode 55116: reward = -15.70, steps = 25 16:08:21 [INFO] train episode 55117: reward = -12.89, steps = 29 16:08:24 [INFO] train episode 55118: reward = -18.85, steps = 29 16:08:28 [INFO] train episode 55119: reward = 19.04, steps = 47 16:08:31 [INFO] train episode 55120: reward = 2.96, steps = 30 16:08:34 [INFO] train episode 55121: reward = -1.19, steps = 41 16:08:37 [INFO] train episode 55122: reward = -2.84, steps = 32 16:08:41 [INFO] train episode 55123: reward = 8.41, steps = 36 16:08:44 [INFO] train episode 55124: reward = 4.14, steps = 37 16:08:47 [INFO] train episode 55125: reward = -5.81, steps = 36 16:08:50 [INFO] train episode 55126: reward = 5.55, steps = 37 16:08:54 [INFO] train episode 55127: reward = 6.11, steps = 46 16:08:59 [INFO] train episode 55128: reward = 8.16, steps = 49 16:09:02 [INFO] train episode 55129: reward = 0.88, steps = 31 16:09:04 [INFO] train episode 55130: reward = -21.51, steps = 21 16:09:08 [INFO] train episode 55131: reward = -6.53, steps = 36 16:09:11 [INFO] train episode 55132: reward = 3.15, steps = 44 16:09:14 [INFO] train episode 55133: reward = -23.00, steps = 24 16:09:18 [INFO] train episode 55134: reward = 11.73, steps = 46 16:09:22 [INFO] train episode 55135: reward = 3.05, steps = 43 16:09:24 [INFO] train episode 55136: reward = -2.50, steps = 30 16:09:27 [INFO] train episode 55137: reward = -0.72, steps = 34 16:09:31 [INFO] train episode 55138: reward = 7.44, steps = 35 16:09:33 [INFO] train episode 55139: reward = -3.50, steps = 32 16:09:37 [INFO] train episode 55140: reward = -1.84, steps = 38 16:09:41 [INFO] train episode 55141: reward = 6.14, steps = 45 16:09:45 [INFO] train episode 55142: reward = 6.50, steps = 54 16:09:50 [INFO] train episode 55143: reward = 9.24, steps = 47 16:09:53 [INFO] train episode 55144: reward = -48.01, steps = 34 16:09:56 [INFO] train episode 55145: reward = -24.41, steps = 39 16:09:59 [INFO] train episode 55146: reward = -0.67, steps = 30 16:10:04 [INFO] train episode 55147: reward = 18.67, steps = 59 16:10:08 [INFO] train episode 55148: reward = -5.00, steps = 44 16:10:12 [INFO] train episode 55149: reward = 22.33, steps = 46 16:10:15 [INFO] train episode 55150: reward = 0.29, steps = 33 16:10:19 [INFO] train episode 55151: reward = 11.45, steps = 42 16:10:23 [INFO] train episode 55152: reward = 22.68, steps = 48 16:10:27 [INFO] train episode 55153: reward = 9.58, steps = 45 16:10:30 [INFO] train episode 55154: reward = 16.62, steps = 41 16:10:34 [INFO] train episode 55155: reward = -28.69, steps = 37 16:10:38 [INFO] train episode 55156: reward = 9.20, steps = 41 16:10:42 [INFO] train episode 55157: reward = 17.46, steps = 46 16:10:45 [INFO] train episode 55158: reward = -15.55, steps = 35 16:10:52 [INFO] train episode 55159: reward = 3.56, steps = 84 16:10:56 [INFO] train episode 55160: reward = 6.97, steps = 40 16:11:00 [INFO] train episode 55161: reward = 5.39, steps = 43 16:11:02 [INFO] train episode 55162: reward = -18.74, steps = 26 16:11:06 [INFO] train episode 55163: reward = 25.88, steps = 44 16:11:09 [INFO] train episode 55164: reward = 8.09, steps = 36 16:11:13 [INFO] train episode 55165: reward = 2.45, steps = 49 16:11:16 [INFO] train episode 55166: reward = -1.51, steps = 34 16:11:19 [INFO] train episode 55167: reward = -6.36, steps = 32 16:11:25 [INFO] train episode 55168: reward = 10.59, steps = 59 16:11:28 [INFO] train episode 55169: reward = 8.68, steps = 38 16:11:31 [INFO] train episode 55170: reward = 1.16, steps = 31 16:11:34 [INFO] train episode 55171: reward = -9.75, steps = 40 16:11:37 [INFO] train episode 55172: reward = -15.17, steps = 35 16:11:40 [INFO] train episode 55173: reward = 6.21, steps = 35 16:11:43 [INFO] train episode 55174: reward = -15.79, steps = 34 16:11:47 [INFO] train episode 55175: reward = -16.60, steps = 43 16:11:51 [INFO] train episode 55176: reward = -8.14, steps = 45 16:11:55 [INFO] train episode 55177: reward = -7.38, steps = 46 16:11:58 [INFO] train episode 55178: reward = -5.14, steps = 29 16:12:01 [INFO] train episode 55179: reward = -7.63, steps = 32 16:12:04 [INFO] train episode 55180: reward = -10.73, steps = 36 16:12:07 [INFO] train episode 55181: reward = -25.00, steps = 29 16:12:11 [INFO] train episode 55182: reward = 16.24, steps = 45 16:12:15 [INFO] train episode 55183: reward = -0.21, steps = 39 16:12:18 [INFO] train episode 55184: reward = 7.17, steps = 41 16:12:21 [INFO] train episode 55185: reward = -1.15, steps = 40 16:12:26 [INFO] train episode 55186: reward = 6.76, steps = 53 16:12:29 [INFO] train episode 55187: reward = -5.52, steps = 31 16:12:31 [INFO] train episode 55188: reward = -20.24, steps = 28 16:12:34 [INFO] train episode 55189: reward = -9.85, steps = 28 16:12:36 [INFO] train episode 55190: reward = -13.52, steps = 28 16:12:40 [INFO] train episode 55191: reward = -0.70, steps = 40 16:12:44 [INFO] train episode 55192: reward = -11.06, steps = 45 16:12:48 [INFO] train episode 55193: reward = -20.71, steps = 40 16:12:50 [INFO] train episode 55194: reward = -18.22, steps = 34 16:12:53 [INFO] train episode 55195: reward = -4.50, steps = 33 16:12:56 [INFO] train episode 55196: reward = -22.16, steps = 32 16:12:59 [INFO] train episode 55197: reward = 1.64, steps = 31 16:13:04 [INFO] train episode 55198: reward = 1.88, steps = 51 16:13:06 [INFO] train episode 55199: reward = -0.35, steps = 31 16:13:10 [INFO] train episode 55200: reward = -9.58, steps = 44 16:13:14 [INFO] train episode 55201: reward = -17.68, steps = 38 16:13:17 [INFO] train episode 55202: reward = 8.80, steps = 36 16:13:20 [INFO] train episode 55203: reward = -0.55, steps = 35 16:13:23 [INFO] train episode 55204: reward = 12.03, steps = 31 16:13:26 [INFO] train episode 55205: reward = -2.86, steps = 41 16:13:31 [INFO] train episode 55206: reward = -5.23, steps = 50 16:13:33 [INFO] train episode 55207: reward = -19.24, steps = 25 16:13:37 [INFO] train episode 55208: reward = 12.81, steps = 44 16:13:39 [INFO] train episode 55209: reward = -12.77, steps = 31 16:13:43 [INFO] train episode 55210: reward = -1.99, steps = 35 16:13:47 [INFO] train episode 55211: reward = 2.97, steps = 58 16:13:51 [INFO] train episode 55212: reward = 9.47, steps = 38 16:13:54 [INFO] train episode 55213: reward = -4.45, steps = 37 16:13:58 [INFO] train episode 55214: reward = 21.50, steps = 44 16:14:02 [INFO] train episode 55215: reward = 0.40, steps = 40 16:14:05 [INFO] train episode 55216: reward = 5.84, steps = 39 16:14:09 [INFO] train episode 55217: reward = -27.44, steps = 50 16:14:12 [INFO] train episode 55218: reward = -1.36, steps = 33 16:14:16 [INFO] train episode 55219: reward = -32.39, steps = 48 16:14:20 [INFO] train episode 55220: reward = -1.84, steps = 34 16:14:26 [INFO] train episode 55221: reward = 18.41, steps = 67 16:14:29 [INFO] train episode 55222: reward = 15.06, steps = 36 16:14:33 [INFO] train episode 55223: reward = 4.39, steps = 45 16:14:37 [INFO] train episode 55224: reward = 2.04, steps = 43 16:14:41 [INFO] train episode 55225: reward = -2.54, steps = 44 16:14:45 [INFO] train episode 55226: reward = -0.22, steps = 43 16:14:48 [INFO] train episode 55227: reward = -5.97, steps = 42 16:14:52 [INFO] train episode 55228: reward = -0.63, steps = 46 16:14:56 [INFO] train episode 55229: reward = -0.35, steps = 37 16:14:59 [INFO] train episode 55230: reward = -12.46, steps = 30 16:15:01 [INFO] train episode 55231: reward = -20.44, steps = 24 16:15:03 [INFO] train episode 55232: reward = -20.82, steps = 20 16:15:05 [INFO] train episode 55233: reward = -7.04, steps = 21 16:15:08 [INFO] train episode 55234: reward = -4.70, steps = 29 16:15:11 [INFO] train episode 55235: reward = -4.40, steps = 40 16:15:14 [INFO] train episode 55236: reward = -2.70, steps = 34 16:15:18 [INFO] train episode 55237: reward = -4.81, steps = 40 16:15:20 [INFO] train episode 55238: reward = -25.89, steps = 23 16:15:22 [INFO] train episode 55239: reward = -25.80, steps = 23 16:15:26 [INFO] train episode 55240: reward = 6.50, steps = 44 16:15:29 [INFO] train episode 55241: reward = 8.92, steps = 37 16:15:32 [INFO] train episode 55242: reward = -7.75, steps = 29 16:15:35 [INFO] train episode 55243: reward = -28.34, steps = 34 16:15:37 [INFO] train episode 55244: reward = -23.44, steps = 24 16:15:39 [INFO] train episode 55245: reward = -12.40, steps = 25 16:15:41 [INFO] train episode 55246: reward = -15.01, steps = 27 16:15:46 [INFO] train episode 55247: reward = 13.51, steps = 50 16:15:48 [INFO] train episode 55248: reward = -1.57, steps = 29 16:15:52 [INFO] train episode 55249: reward = 9.65, steps = 45 16:15:55 [INFO] train episode 55250: reward = -1.25, steps = 30 16:15:59 [INFO] train episode 55251: reward = 7.28, steps = 50 16:16:02 [INFO] train episode 55252: reward = -14.67, steps = 29 16:16:05 [INFO] train episode 55253: reward = -6.69, steps = 33 16:16:08 [INFO] train episode 55254: reward = -0.94, steps = 40 16:16:11 [INFO] train episode 55255: reward = -10.37, steps = 31 16:16:13 [INFO] train episode 55256: reward = -13.70, steps = 29 16:16:17 [INFO] train episode 55257: reward = 6.30, steps = 39 16:16:19 [INFO] train episode 55258: reward = -13.66, steps = 23 16:16:22 [INFO] train episode 55259: reward = -5.64, steps = 32 16:16:25 [INFO] train episode 55260: reward = -8.78, steps = 37 16:16:29 [INFO] train episode 55261: reward = 8.61, steps = 41 16:16:31 [INFO] train episode 55262: reward = -14.12, steps = 21 16:16:36 [INFO] train episode 55263: reward = 20.73, steps = 53 16:16:39 [INFO] train episode 55264: reward = -4.65, steps = 33 16:16:41 [INFO] train episode 55265: reward = -5.34, steps = 32 16:16:44 [INFO] train episode 55266: reward = -9.69, steps = 32 16:16:47 [INFO] train episode 55267: reward = -21.77, steps = 30 16:16:51 [INFO] train episode 55268: reward = 18.54, steps = 45 16:16:53 [INFO] train episode 55269: reward = -21.31, steps = 21 16:16:56 [INFO] train episode 55270: reward = -21.10, steps = 38 16:16:59 [INFO] train episode 55271: reward = -16.96, steps = 31 16:17:04 [INFO] train episode 55272: reward = 4.30, steps = 52 16:17:07 [INFO] train episode 55273: reward = -15.31, steps = 37 16:17:10 [INFO] train episode 55274: reward = -9.68, steps = 34 16:17:12 [INFO] train episode 55275: reward = -24.44, steps = 23 16:17:17 [INFO] train episode 55276: reward = -5.27, steps = 51 16:17:20 [INFO] train episode 55277: reward = 9.52, steps = 40 16:17:23 [INFO] train episode 55278: reward = 2.84, steps = 35 16:17:25 [INFO] train episode 55279: reward = -19.92, steps = 22 16:17:29 [INFO] train episode 55280: reward = 2.93, steps = 41 16:17:32 [INFO] train episode 55281: reward = 7.88, steps = 43 16:17:36 [INFO] train episode 55282: reward = -6.65, steps = 34 16:17:39 [INFO] train episode 55283: reward = 7.79, steps = 40 16:17:43 [INFO] train episode 55284: reward = 5.39, steps = 50 16:17:47 [INFO] train episode 55285: reward = -0.37, steps = 43 16:17:49 [INFO] train episode 55286: reward = -19.15, steps = 29 16:17:53 [INFO] train episode 55287: reward = -10.40, steps = 27 16:17:56 [INFO] train episode 55288: reward = -9.98, steps = 33 16:17:58 [INFO] train episode 55289: reward = -15.58, steps = 26 16:18:01 [INFO] train episode 55290: reward = 0.52, steps = 30 16:18:04 [INFO] train episode 55291: reward = -14.17, steps = 40 16:18:07 [INFO] train episode 55292: reward = -5.16, steps = 31 16:18:10 [INFO] train episode 55293: reward = -11.07, steps = 26 16:18:12 [INFO] train episode 55294: reward = -30.36, steps = 28 16:18:14 [INFO] train episode 55295: reward = -38.62, steps = 21 16:18:17 [INFO] train episode 55296: reward = -1.67, steps = 39 16:18:21 [INFO] train episode 55297: reward = -5.05, steps = 38 16:18:23 [INFO] train episode 55298: reward = 6.40, steps = 33 16:18:28 [INFO] train episode 55299: reward = -3.88, steps = 44 16:18:31 [INFO] train episode 55300: reward = 0.34, steps = 38 16:18:34 [INFO] train episode 55301: reward = -9.32, steps = 37 16:18:38 [INFO] train episode 55302: reward = 3.94, steps = 41 16:18:40 [INFO] train episode 55303: reward = -11.26, steps = 25 16:18:43 [INFO] train episode 55304: reward = -20.24, steps = 35 16:18:47 [INFO] train episode 55305: reward = -5.13, steps = 39 16:18:51 [INFO] train episode 55306: reward = 15.25, steps = 51 16:18:53 [INFO] train episode 55307: reward = -20.41, steps = 25 16:18:56 [INFO] train episode 55308: reward = -5.43, steps = 35 16:19:01 [INFO] train episode 55309: reward = -0.54, steps = 53 16:19:05 [INFO] train episode 55310: reward = -1.85, steps = 39 16:19:07 [INFO] train episode 55311: reward = -31.02, steps = 27 16:19:11 [INFO] train episode 55312: reward = 1.32, steps = 41 16:19:15 [INFO] train episode 55313: reward = 22.19, steps = 49 16:19:18 [INFO] train episode 55314: reward = 2.33, steps = 36 16:19:22 [INFO] train episode 55315: reward = -3.10, steps = 41 16:19:25 [INFO] train episode 55316: reward = 0.14, steps = 38 16:19:31 [INFO] train episode 55317: reward = 18.13, steps = 61 16:19:35 [INFO] train episode 55318: reward = 2.18, steps = 46 16:19:37 [INFO] train episode 55319: reward = -4.05, steps = 29 16:19:41 [INFO] train episode 55320: reward = 5.77, steps = 42 16:19:43 [INFO] train episode 55321: reward = -10.69, steps = 23 16:19:49 [INFO] train episode 55322: reward = -17.66, steps = 65 16:19:52 [INFO] train episode 55323: reward = -18.50, steps = 33 16:19:54 [INFO] train episode 55324: reward = -5.12, steps = 30 16:19:57 [INFO] train episode 55325: reward = -7.78, steps = 29 16:20:00 [INFO] train episode 55326: reward = -9.06, steps = 32 16:20:02 [INFO] train episode 55327: reward = -20.51, steps = 27 16:20:04 [INFO] train episode 55328: reward = -39.87, steps = 19 16:20:06 [INFO] train episode 55329: reward = -22.64, steps = 23 16:20:09 [INFO] train episode 55330: reward = -15.19, steps = 33 16:20:11 [INFO] train episode 55331: reward = -16.40, steps = 21 16:20:13 [INFO] train episode 55332: reward = -21.45, steps = 32 16:20:17 [INFO] train episode 55333: reward = -9.14, steps = 39 16:20:22 [INFO] train episode 55334: reward = -41.71, steps = 54 16:20:25 [INFO] train episode 55335: reward = -5.70, steps = 38 16:20:28 [INFO] train episode 55336: reward = -9.62, steps = 36 16:20:31 [INFO] train episode 55337: reward = -5.62, steps = 33 16:20:35 [INFO] train episode 55338: reward = 7.63, steps = 45 16:20:40 [INFO] train episode 55339: reward = 5.80, steps = 50 16:20:43 [INFO] train episode 55340: reward = 2.24, steps = 38 16:20:47 [INFO] train episode 55341: reward = -30.37, steps = 36 16:20:49 [INFO] train episode 55342: reward = -3.24, steps = 29 16:20:53 [INFO] train episode 55343: reward = -15.44, steps = 42 16:20:57 [INFO] train episode 55344: reward = -27.50, steps = 42 16:20:59 [INFO] train episode 55345: reward = -16.53, steps = 21 16:21:02 [INFO] train episode 55346: reward = -13.01, steps = 34 16:21:04 [INFO] train episode 55347: reward = -4.15, steps = 29 16:21:06 [INFO] train episode 55348: reward = -19.30, steps = 21 16:21:10 [INFO] train episode 55349: reward = 0.46, steps = 42 16:21:14 [INFO] train episode 55350: reward = -21.99, steps = 35 16:21:17 [INFO] train episode 55351: reward = -3.85, steps = 33 16:21:21 [INFO] train episode 55352: reward = 12.15, steps = 44 16:21:24 [INFO] train episode 55353: reward = -19.88, steps = 25 16:21:27 [INFO] train episode 55354: reward = 4.00, steps = 34 16:21:31 [INFO] train episode 55355: reward = 1.30, steps = 42 16:21:34 [INFO] train episode 55356: reward = 0.98, steps = 34 16:21:39 [INFO] train episode 55357: reward = 6.86, steps = 45 16:21:42 [INFO] train episode 55358: reward = -27.92, steps = 35 16:21:45 [INFO] train episode 55359: reward = -5.24, steps = 32 16:21:48 [INFO] train episode 55360: reward = 9.50, steps = 44 16:21:51 [INFO] train episode 55361: reward = -5.36, steps = 34 16:21:54 [INFO] train episode 55362: reward = 0.28, steps = 30 16:21:56 [INFO] train episode 55363: reward = -29.32, steps = 20 16:22:00 [INFO] train episode 55364: reward = 4.03, steps = 40 16:22:03 [INFO] train episode 55365: reward = -5.95, steps = 35 16:22:07 [INFO] train episode 55366: reward = -4.95, steps = 55 16:22:09 [INFO] train episode 55367: reward = -6.25, steps = 24 16:22:14 [INFO] train episode 55368: reward = -2.81, steps = 55 16:22:18 [INFO] train episode 55369: reward = 12.91, steps = 36 16:22:21 [INFO] train episode 55370: reward = 3.93, steps = 35 16:22:24 [INFO] train episode 55371: reward = 1.60, steps = 34 16:22:27 [INFO] train episode 55372: reward = -21.44, steps = 36 16:22:32 [INFO] train episode 55373: reward = 1.04, steps = 57 16:22:34 [INFO] train episode 55374: reward = -15.81, steps = 27 16:22:39 [INFO] train episode 55375: reward = 11.57, steps = 54 16:22:43 [INFO] train episode 55376: reward = -8.25, steps = 38 16:22:47 [INFO] train episode 55377: reward = -7.41, steps = 54 16:22:52 [INFO] train episode 55378: reward = 16.54, steps = 47 16:22:55 [INFO] train episode 55379: reward = -11.19, steps = 38 16:22:57 [INFO] train episode 55380: reward = -7.21, steps = 29 16:23:02 [INFO] train episode 55381: reward = 2.04, steps = 49 16:23:05 [INFO] train episode 55382: reward = 18.50, steps = 39 16:23:07 [INFO] train episode 55383: reward = -16.23, steps = 22 16:23:11 [INFO] train episode 55384: reward = -27.18, steps = 44 16:23:14 [INFO] train episode 55385: reward = -5.02, steps = 38 16:23:17 [INFO] train episode 55386: reward = -0.31, steps = 36 16:23:21 [INFO] train episode 55387: reward = 2.06, steps = 40 16:23:24 [INFO] train episode 55388: reward = -11.09, steps = 34 16:23:27 [INFO] train episode 55389: reward = -12.21, steps = 30 16:23:30 [INFO] train episode 55390: reward = 12.87, steps = 37 16:23:33 [INFO] train episode 55391: reward = -8.17, steps = 31 16:23:35 [INFO] train episode 55392: reward = -14.39, steps = 33 16:23:39 [INFO] train episode 55393: reward = -1.04, steps = 32 16:23:42 [INFO] train episode 55394: reward = 7.36, steps = 40 16:23:47 [INFO] train episode 55395: reward = 7.26, steps = 44 16:23:50 [INFO] train episode 55396: reward = -15.96, steps = 35 16:23:53 [INFO] train episode 55397: reward = 1.58, steps = 34 16:23:55 [INFO] train episode 55398: reward = -26.13, steps = 23 16:23:59 [INFO] train episode 55399: reward = 1.07, steps = 44 16:24:02 [INFO] train episode 55400: reward = 13.72, steps = 39 16:24:05 [INFO] train episode 55401: reward = 14.40, steps = 38 16:24:09 [INFO] train episode 55402: reward = -5.92, steps = 39 16:24:13 [INFO] train episode 55403: reward = 3.94, steps = 40 16:24:17 [INFO] train episode 55404: reward = 16.69, steps = 44 16:24:18 [INFO] train episode 55405: reward = -16.89, steps = 20 16:24:21 [INFO] train episode 55406: reward = 1.57, steps = 33 16:24:25 [INFO] train episode 55407: reward = -8.22, steps = 41 16:24:30 [INFO] train episode 55408: reward = -13.67, steps = 54 16:24:33 [INFO] train episode 55409: reward = -11.00, steps = 36 16:24:35 [INFO] train episode 55410: reward = -20.67, steps = 31 16:24:39 [INFO] train episode 55411: reward = 2.67, steps = 35 16:24:41 [INFO] train episode 55412: reward = -2.07, steps = 32 16:24:44 [INFO] train episode 55413: reward = -20.58, steps = 23 16:24:48 [INFO] train episode 55414: reward = -0.63, steps = 46 16:24:51 [INFO] train episode 55415: reward = 18.23, steps = 40 16:24:54 [INFO] train episode 55416: reward = -14.70, steps = 37 16:24:58 [INFO] train episode 55417: reward = -8.53, steps = 37 16:25:01 [INFO] train episode 55418: reward = 3.87, steps = 31 16:25:03 [INFO] train episode 55419: reward = -14.22, steps = 30 16:25:06 [INFO] train episode 55420: reward = -30.68, steps = 32 16:25:08 [INFO] train episode 55421: reward = -15.64, steps = 24 16:25:11 [INFO] train episode 55422: reward = 0.69, steps = 35 16:25:14 [INFO] train episode 55423: reward = -5.33, steps = 34 16:25:18 [INFO] train episode 55424: reward = -12.68, steps = 36 16:25:21 [INFO] train episode 55425: reward = -8.52, steps = 41 16:25:24 [INFO] train episode 55426: reward = -6.65, steps = 34 16:25:27 [INFO] train episode 55427: reward = -14.40, steps = 33 16:25:31 [INFO] train episode 55428: reward = 12.15, steps = 39 16:25:35 [INFO] train episode 55429: reward = 9.68, steps = 42 16:25:38 [INFO] train episode 55430: reward = 6.98, steps = 37 16:25:42 [INFO] train episode 55431: reward = 1.34, steps = 51 16:25:45 [INFO] train episode 55432: reward = -10.48, steps = 35 16:25:49 [INFO] train episode 55433: reward = -42.12, steps = 38 16:25:51 [INFO] train episode 55434: reward = -18.45, steps = 27 16:25:55 [INFO] train episode 55435: reward = 16.67, steps = 40 16:25:58 [INFO] train episode 55436: reward = 13.16, steps = 43 16:26:01 [INFO] train episode 55437: reward = 9.60, steps = 39 16:26:05 [INFO] train episode 55438: reward = -7.60, steps = 38 16:26:08 [INFO] train episode 55439: reward = -20.32, steps = 28 16:26:11 [INFO] train episode 55440: reward = 1.13, steps = 37 16:26:13 [INFO] train episode 55441: reward = -2.14, steps = 30 16:26:16 [INFO] train episode 55442: reward = 5.72, steps = 32 16:26:19 [INFO] train episode 55443: reward = -11.71, steps = 34 16:26:21 [INFO] train episode 55444: reward = -24.20, steps = 22 16:26:25 [INFO] train episode 55445: reward = -3.26, steps = 43 16:26:28 [INFO] train episode 55446: reward = -13.12, steps = 28 16:26:30 [INFO] train episode 55447: reward = -18.46, steps = 26 16:26:34 [INFO] train episode 55448: reward = -32.43, steps = 51 16:26:38 [INFO] train episode 55449: reward = -3.77, steps = 35 16:26:42 [INFO] train episode 55450: reward = -15.58, steps = 35 16:26:45 [INFO] train episode 55451: reward = 8.82, steps = 40 16:26:49 [INFO] train episode 55452: reward = 8.38, steps = 40 16:26:54 [INFO] train episode 55453: reward = 10.18, steps = 58 16:26:56 [INFO] train episode 55454: reward = -20.31, steps = 20 16:27:01 [INFO] train episode 55455: reward = 15.30, steps = 59 16:27:03 [INFO] train episode 55456: reward = -14.09, steps = 32 16:27:07 [INFO] train episode 55457: reward = 5.58, steps = 40 16:27:11 [INFO] train episode 55458: reward = -14.23, steps = 39 16:27:13 [INFO] train episode 55459: reward = -58.11, steps = 23 16:27:16 [INFO] train episode 55460: reward = 15.03, steps = 40 16:27:20 [INFO] train episode 55461: reward = 20.33, steps = 43 16:27:23 [INFO] train episode 55462: reward = 10.49, steps = 39 16:27:25 [INFO] train episode 55463: reward = -27.72, steps = 27 16:27:29 [INFO] train episode 55464: reward = -7.46, steps = 36 16:27:32 [INFO] train episode 55465: reward = 1.68, steps = 37 16:27:34 [INFO] train episode 55466: reward = -13.74, steps = 28 16:27:37 [INFO] train episode 55467: reward = -11.50, steps = 36 16:27:40 [INFO] train episode 55468: reward = -4.42, steps = 35 16:27:44 [INFO] train episode 55469: reward = 10.27, steps = 42 16:27:46 [INFO] train episode 55470: reward = -24.29, steps = 21 16:27:49 [INFO] train episode 55471: reward = -19.54, steps = 38 16:27:53 [INFO] train episode 55472: reward = 7.00, steps = 42 16:27:59 [INFO] train episode 55473: reward = 7.79, steps = 60 16:28:03 [INFO] train episode 55474: reward = -5.23, steps = 45 16:28:04 [INFO] train episode 55475: reward = -66.82, steps = 19 16:28:07 [INFO] train episode 55476: reward = -0.53, steps = 30 16:28:09 [INFO] train episode 55477: reward = -18.38, steps = 29 16:28:13 [INFO] train episode 55478: reward = -9.55, steps = 44 16:28:17 [INFO] train episode 55479: reward = 5.44, steps = 41 16:28:20 [INFO] train episode 55480: reward = -9.03, steps = 38 16:28:22 [INFO] train episode 55481: reward = -12.55, steps = 24 16:28:25 [INFO] train episode 55482: reward = -7.86, steps = 32 16:28:29 [INFO] train episode 55483: reward = -8.15, steps = 40 16:28:32 [INFO] train episode 55484: reward = 5.83, steps = 37 16:28:35 [INFO] train episode 55485: reward = 0.19, steps = 34 16:28:40 [INFO] train episode 55486: reward = -8.58, steps = 53 16:28:43 [INFO] train episode 55487: reward = 2.61, steps = 42 16:28:47 [INFO] train episode 55488: reward = -21.68, steps = 39 16:28:50 [INFO] train episode 55489: reward = -4.53, steps = 32 16:28:53 [INFO] train episode 55490: reward = -6.35, steps = 37 16:28:56 [INFO] train episode 55491: reward = -10.88, steps = 32 16:28:59 [INFO] train episode 55492: reward = -9.09, steps = 37 16:29:03 [INFO] train episode 55493: reward = 8.97, steps = 40 16:29:06 [INFO] train episode 55494: reward = -1.79, steps = 32 16:29:09 [INFO] train episode 55495: reward = -12.24, steps = 27 16:29:12 [INFO] train episode 55496: reward = 5.11, steps = 36 16:29:15 [INFO] train episode 55497: reward = -24.41, steps = 37 16:29:18 [INFO] train episode 55498: reward = -10.38, steps = 28 16:29:21 [INFO] train episode 55499: reward = 2.64, steps = 34 16:29:25 [INFO] train episode 55500: reward = 4.71, steps = 46 16:29:28 [INFO] train episode 55501: reward = -21.86, steps = 32 16:29:32 [INFO] train episode 55502: reward = -14.34, steps = 48 16:29:37 [INFO] train episode 55503: reward = 20.28, steps = 43 16:29:41 [INFO] train episode 55504: reward = 23.86, steps = 51 16:29:44 [INFO] train episode 55505: reward = 9.77, steps = 34 16:29:47 [INFO] train episode 55506: reward = -10.56, steps = 28 16:29:49 [INFO] train episode 55507: reward = -7.94, steps = 28 16:29:51 [INFO] train episode 55508: reward = -26.95, steps = 20 16:29:54 [INFO] train episode 55509: reward = -13.00, steps = 34 16:29:58 [INFO] train episode 55510: reward = -15.26, steps = 46 16:30:01 [INFO] train episode 55511: reward = 1.27, steps = 33 16:30:06 [INFO] train episode 55512: reward = 19.99, steps = 52 16:30:09 [INFO] train episode 55513: reward = -19.79, steps = 37 16:30:12 [INFO] train episode 55514: reward = -10.30, steps = 27 16:30:14 [INFO] train episode 55515: reward = -4.59, steps = 27 16:30:17 [INFO] train episode 55516: reward = 12.70, steps = 40 16:30:20 [INFO] train episode 55517: reward = -22.27, steps = 34 16:30:23 [INFO] train episode 55518: reward = -16.53, steps = 32 16:30:27 [INFO] train episode 55519: reward = -4.41, steps = 38 16:30:29 [INFO] train episode 55520: reward = -7.02, steps = 31 16:30:33 [INFO] train episode 55521: reward = 2.09, steps = 45 16:30:36 [INFO] train episode 55522: reward = -19.48, steps = 29 16:30:38 [INFO] train episode 55523: reward = -17.89, steps = 28 16:30:40 [INFO] train episode 55524: reward = -30.17, steps = 19 16:30:42 [INFO] train episode 55525: reward = -37.40, steps = 19 16:30:45 [INFO] train episode 55526: reward = 2.95, steps = 34 16:30:48 [INFO] train episode 55527: reward = -3.27, steps = 31 16:30:52 [INFO] train episode 55528: reward = 9.41, steps = 49 16:30:56 [INFO] train episode 55529: reward = 11.72, steps = 42 16:31:00 [INFO] train episode 55530: reward = -16.83, steps = 41 16:31:04 [INFO] train episode 55531: reward = 16.85, steps = 52 16:31:08 [INFO] train episode 55532: reward = 8.21, steps = 52 16:31:11 [INFO] train episode 55533: reward = -10.30, steps = 31 16:31:15 [INFO] train episode 55534: reward = 13.63, steps = 42 16:31:17 [INFO] train episode 55535: reward = -21.91, steps = 21 16:31:19 [INFO] train episode 55536: reward = -20.42, steps = 21 16:31:23 [INFO] train episode 55537: reward = 8.72, steps = 48 16:31:25 [INFO] train episode 55538: reward = -14.23, steps = 27 16:31:28 [INFO] train episode 55539: reward = -12.45, steps = 28 16:31:31 [INFO] train episode 55540: reward = 2.98, steps = 38 16:31:35 [INFO] train episode 55541: reward = 16.79, steps = 50 16:31:38 [INFO] train episode 55542: reward = -9.90, steps = 30 16:31:40 [INFO] train episode 55543: reward = -21.91, steps = 26 16:31:43 [INFO] train episode 55544: reward = -11.96, steps = 32 16:31:46 [INFO] train episode 55545: reward = -13.97, steps = 28 16:31:48 [INFO] train episode 55546: reward = -21.65, steps = 20 16:31:51 [INFO] train episode 55547: reward = 11.49, steps = 44 16:31:54 [INFO] train episode 55548: reward = -19.92, steps = 35 16:31:57 [INFO] train episode 55549: reward = 2.00, steps = 33 16:32:01 [INFO] train episode 55550: reward = -4.65, steps = 38 16:32:03 [INFO] train episode 55551: reward = -0.68, steps = 29 16:32:08 [INFO] train episode 55552: reward = 6.42, steps = 49 16:32:11 [INFO] train episode 55553: reward = 11.37, steps = 36 16:32:14 [INFO] train episode 55554: reward = 15.24, steps = 45 16:32:18 [INFO] train episode 55555: reward = -6.34, steps = 34 16:32:21 [INFO] train episode 55556: reward = 1.47, steps = 33 16:32:24 [INFO] train episode 55557: reward = 16.72, steps = 39 16:32:27 [INFO] train episode 55558: reward = -8.35, steps = 31 16:32:30 [INFO] train episode 55559: reward = -8.36, steps = 27 16:32:32 [INFO] train episode 55560: reward = -0.97, steps = 30 16:32:36 [INFO] train episode 55561: reward = -13.47, steps = 36 16:32:40 [INFO] train episode 55562: reward = -23.62, steps = 39 16:32:44 [INFO] train episode 55563: reward = 0.40, steps = 48 16:32:47 [INFO] train episode 55564: reward = 4.65, steps = 31 16:32:49 [INFO] train episode 55565: reward = -29.97, steps = 33 16:32:53 [INFO] train episode 55566: reward = 16.65, steps = 41 16:32:57 [INFO] train episode 55567: reward = 1.78, steps = 39 16:33:01 [INFO] train episode 55568: reward = -3.72, steps = 51 16:33:04 [INFO] train episode 55569: reward = -18.17, steps = 31 16:33:08 [INFO] train episode 55570: reward = 12.08, steps = 44 16:33:10 [INFO] train episode 55571: reward = -38.87, steps = 18 16:33:13 [INFO] train episode 55572: reward = 12.86, steps = 41 16:33:17 [INFO] train episode 55573: reward = 10.32, steps = 38 16:33:20 [INFO] train episode 55574: reward = -21.66, steps = 35 16:33:23 [INFO] train episode 55575: reward = 10.29, steps = 39 16:33:27 [INFO] train episode 55576: reward = -4.29, steps = 40 16:33:30 [INFO] train episode 55577: reward = 15.94, steps = 42 16:33:34 [INFO] train episode 55578: reward = 17.53, steps = 41 16:33:38 [INFO] train episode 55579: reward = 10.44, steps = 42 16:33:40 [INFO] train episode 55580: reward = -11.28, steps = 22 16:33:43 [INFO] train episode 55581: reward = -4.56, steps = 31 16:33:47 [INFO] train episode 55582: reward = 13.81, steps = 47 16:33:51 [INFO] train episode 55583: reward = -1.49, steps = 52 16:33:54 [INFO] train episode 55584: reward = -10.23, steps = 36 16:33:59 [INFO] train episode 55585: reward = 21.59, steps = 53 16:34:02 [INFO] train episode 55586: reward = 7.50, steps = 36 16:34:06 [INFO] train episode 55587: reward = -1.90, steps = 49 16:34:09 [INFO] train episode 55588: reward = -3.83, steps = 35 16:34:13 [INFO] train episode 55589: reward = 2.68, steps = 39 16:34:15 [INFO] train episode 55590: reward = -4.47, steps = 26 16:34:19 [INFO] train episode 55591: reward = 3.47, steps = 41 16:34:21 [INFO] train episode 55592: reward = -3.55, steps = 28 16:34:24 [INFO] train episode 55593: reward = 3.75, steps = 33 16:34:29 [INFO] train episode 55594: reward = 9.59, steps = 58 16:34:33 [INFO] train episode 55595: reward = 2.88, steps = 42 16:34:36 [INFO] train episode 55596: reward = -20.30, steps = 32 16:34:39 [INFO] train episode 55597: reward = -0.38, steps = 43 16:34:43 [INFO] train episode 55598: reward = -2.43, steps = 42 16:34:47 [INFO] train episode 55599: reward = -0.40, steps = 39 16:34:50 [INFO] train episode 55600: reward = -4.61, steps = 38 16:34:54 [INFO] train episode 55601: reward = -14.08, steps = 43 16:34:56 [INFO] train episode 55602: reward = -2.18, steps = 33 16:34:59 [INFO] train episode 55603: reward = -2.06, steps = 30 16:35:03 [INFO] train episode 55604: reward = 11.90, steps = 44 16:35:06 [INFO] train episode 55605: reward = 4.59, steps = 38 16:35:09 [INFO] train episode 55606: reward = -11.06, steps = 33 16:35:12 [INFO] train episode 55607: reward = -6.42, steps = 34 16:35:14 [INFO] train episode 55608: reward = -27.13, steps = 26 16:35:19 [INFO] train episode 55609: reward = -15.40, steps = 50 16:35:24 [INFO] train episode 55610: reward = -0.26, steps = 45 16:35:26 [INFO] train episode 55611: reward = -20.78, steps = 21 16:35:29 [INFO] train episode 55612: reward = 17.98, steps = 43 16:35:31 [INFO] train episode 55613: reward = -26.21, steps = 22 16:35:34 [INFO] train episode 55614: reward = -1.63, steps = 31 16:35:38 [INFO] train episode 55615: reward = -31.08, steps = 37 16:35:41 [INFO] train episode 55616: reward = 12.33, steps = 40 16:35:45 [INFO] train episode 55617: reward = 3.91, steps = 49 16:35:48 [INFO] train episode 55618: reward = 3.27, steps = 34 16:35:51 [INFO] train episode 55619: reward = -5.48, steps = 26 16:35:53 [INFO] train episode 55620: reward = -19.88, steps = 28 16:35:56 [INFO] train episode 55621: reward = -4.10, steps = 35 16:35:59 [INFO] train episode 55622: reward = -25.18, steps = 28 16:36:02 [INFO] train episode 55623: reward = 9.21, steps = 38 16:36:06 [INFO] train episode 55624: reward = -13.18, steps = 41 16:36:07 [INFO] train episode 55625: reward = -16.40, steps = 20 16:36:10 [INFO] train episode 55626: reward = -20.02, steps = 28 16:36:13 [INFO] train episode 55627: reward = 2.98, steps = 35 16:36:15 [INFO] train episode 55628: reward = -7.22, steps = 25 16:36:19 [INFO] train episode 55629: reward = 20.34, steps = 51 16:36:24 [INFO] train episode 55630: reward = -50.08, steps = 50 16:36:27 [INFO] train episode 55631: reward = -3.74, steps = 31 16:36:30 [INFO] train episode 55632: reward = -6.15, steps = 36 16:36:33 [INFO] train episode 55633: reward = 5.23, steps = 35 16:36:36 [INFO] train episode 55634: reward = 6.98, steps = 31 16:36:40 [INFO] train episode 55635: reward = 8.55, steps = 43 16:36:43 [INFO] train episode 55636: reward = 1.45, steps = 37 16:36:47 [INFO] train episode 55637: reward = -5.71, steps = 42 16:36:50 [INFO] train episode 55638: reward = 10.03, steps = 35 16:36:53 [INFO] train episode 55639: reward = 3.57, steps = 35 16:36:57 [INFO] train episode 55640: reward = 18.79, steps = 42 16:37:00 [INFO] train episode 55641: reward = -8.13, steps = 34 16:37:02 [INFO] train episode 55642: reward = -2.97, steps = 30 16:37:05 [INFO] train episode 55643: reward = -6.45, steps = 34 16:37:10 [INFO] train episode 55644: reward = 17.68, steps = 50 16:37:13 [INFO] train episode 55645: reward = -0.62, steps = 37 16:37:15 [INFO] train episode 55646: reward = -14.11, steps = 26 16:37:19 [INFO] train episode 55647: reward = 13.93, steps = 42 16:37:23 [INFO] train episode 55648: reward = -3.41, steps = 50 16:37:28 [INFO] train episode 55649: reward = -12.22, steps = 48 16:37:30 [INFO] train episode 55650: reward = -18.83, steps = 27 16:37:32 [INFO] train episode 55651: reward = -13.42, steps = 21 16:37:33 [INFO] train episode 55652: reward = -30.71, steps = 20 16:37:36 [INFO] train episode 55653: reward = 0.61, steps = 33 16:37:40 [INFO] train episode 55654: reward = 5.18, steps = 39 16:37:44 [INFO] train episode 55655: reward = 16.76, steps = 42 16:37:46 [INFO] train episode 55656: reward = -10.95, steps = 31 16:37:49 [INFO] train episode 55657: reward = -3.55, steps = 30 16:37:52 [INFO] train episode 55658: reward = -10.46, steps = 31 16:37:55 [INFO] train episode 55659: reward = 14.17, steps = 38 16:37:58 [INFO] train episode 55660: reward = 0.94, steps = 33 16:38:01 [INFO] train episode 55661: reward = -14.51, steps = 29 16:38:04 [INFO] train episode 55662: reward = -30.51, steps = 42 16:38:07 [INFO] train episode 55663: reward = -10.68, steps = 28 16:38:09 [INFO] train episode 55664: reward = -25.38, steps = 28 16:38:11 [INFO] train episode 55665: reward = -26.89, steps = 22 16:38:15 [INFO] train episode 55666: reward = 4.52, steps = 41 16:38:18 [INFO] train episode 55667: reward = -11.66, steps = 26 16:38:21 [INFO] train episode 55668: reward = 1.87, steps = 32 16:38:24 [INFO] train episode 55669: reward = 6.15, steps = 31 16:38:27 [INFO] train episode 55670: reward = 19.45, steps = 42 16:38:31 [INFO] train episode 55671: reward = 9.92, steps = 38 16:38:36 [INFO] train episode 55672: reward = -7.47, steps = 56 16:38:40 [INFO] train episode 55673: reward = -19.54, steps = 44 16:38:44 [INFO] train episode 55674: reward = 7.06, steps = 52 16:38:47 [INFO] train episode 55675: reward = -4.12, steps = 32 16:38:49 [INFO] train episode 55676: reward = -22.98, steps = 20 16:38:53 [INFO] train episode 55677: reward = -1.05, steps = 46 16:38:55 [INFO] train episode 55678: reward = -2.30, steps = 26 16:38:58 [INFO] train episode 55679: reward = -24.85, steps = 27 16:39:00 [INFO] train episode 55680: reward = -31.22, steps = 30 16:39:04 [INFO] train episode 55681: reward = -2.36, steps = 45 16:39:07 [INFO] train episode 55682: reward = -29.47, steps = 25 16:39:09 [INFO] train episode 55683: reward = 1.06, steps = 31 16:39:13 [INFO] train episode 55684: reward = 20.40, steps = 41 16:39:16 [INFO] train episode 55685: reward = 18.39, steps = 40 16:39:21 [INFO] train episode 55686: reward = 10.01, steps = 46 16:39:24 [INFO] train episode 55687: reward = 9.45, steps = 42 16:39:28 [INFO] train episode 55688: reward = -25.03, steps = 40 16:39:30 [INFO] train episode 55689: reward = -1.68, steps = 33 16:39:34 [INFO] train episode 55690: reward = 22.21, steps = 38 16:39:38 [INFO] train episode 55691: reward = 18.86, steps = 48 16:39:42 [INFO] train episode 55692: reward = 11.15, steps = 49 16:39:45 [INFO] train episode 55693: reward = -8.72, steps = 26 16:39:48 [INFO] train episode 55694: reward = -1.28, steps = 38 16:39:52 [INFO] train episode 55695: reward = -6.67, steps = 48 16:39:56 [INFO] train episode 55696: reward = -11.52, steps = 42 16:39:59 [INFO] train episode 55697: reward = -10.02, steps = 30 16:40:03 [INFO] train episode 55698: reward = 21.85, steps = 50 16:40:06 [INFO] train episode 55699: reward = 0.10, steps = 38 16:40:09 [INFO] train episode 55700: reward = 4.23, steps = 34 16:40:13 [INFO] train episode 55701: reward = 8.01, steps = 37 16:40:16 [INFO] train episode 55702: reward = -21.55, steps = 37 16:40:18 [INFO] train episode 55703: reward = -4.89, steps = 30 16:40:21 [INFO] train episode 55704: reward = -9.32, steps = 34 16:40:25 [INFO] train episode 55705: reward = 7.44, steps = 37 16:40:27 [INFO] train episode 55706: reward = -21.05, steps = 23 16:40:31 [INFO] train episode 55707: reward = 8.63, steps = 45 16:40:34 [INFO] train episode 55708: reward = 7.63, steps = 40 16:40:36 [INFO] train episode 55709: reward = -15.89, steps = 23 16:40:38 [INFO] train episode 55710: reward = -14.67, steps = 22 16:40:42 [INFO] train episode 55711: reward = -7.22, steps = 31 16:40:45 [INFO] train episode 55712: reward = -0.52, steps = 35 16:40:48 [INFO] train episode 55713: reward = -13.58, steps = 44 16:40:54 [INFO] train episode 55714: reward = 6.89, steps = 62 16:40:55 [INFO] train episode 55715: reward = -29.15, steps = 19 16:40:59 [INFO] train episode 55716: reward = -2.67, steps = 37 16:41:03 [INFO] train episode 55717: reward = 18.39, steps = 48 16:41:07 [INFO] train episode 55718: reward = -2.98, steps = 51 16:41:09 [INFO] train episode 55719: reward = -15.17, steps = 25 16:41:15 [INFO] train episode 55720: reward = 7.62, steps = 50 16:41:19 [INFO] train episode 55721: reward = 9.80, steps = 49 16:41:21 [INFO] train episode 55722: reward = -10.26, steps = 28 16:41:25 [INFO] train episode 55723: reward = -6.33, steps = 39 16:41:27 [INFO] train episode 55724: reward = 2.03, steps = 28 16:41:30 [INFO] train episode 55725: reward = -7.44, steps = 27 16:41:37 [INFO] train episode 55726: reward = 0.75, steps = 81 16:41:39 [INFO] train episode 55727: reward = -16.22, steps = 22 16:41:42 [INFO] train episode 55728: reward = 2.24, steps = 42 16:41:45 [INFO] train episode 55729: reward = 0.38, steps = 32 16:41:47 [INFO] train episode 55730: reward = -29.86, steps = 20 16:41:50 [INFO] train episode 55731: reward = 16.53, steps = 37 16:41:52 [INFO] train episode 55732: reward = -11.59, steps = 23 16:41:55 [INFO] train episode 55733: reward = -15.96, steps = 37 16:41:58 [INFO] train episode 55734: reward = -1.72, steps = 35 16:42:01 [INFO] train episode 55735: reward = -10.01, steps = 30 16:42:04 [INFO] train episode 55736: reward = -10.40, steps = 28 16:42:07 [INFO] train episode 55737: reward = 4.61, steps = 42 16:42:11 [INFO] train episode 55738: reward = -1.11, steps = 36 16:42:13 [INFO] train episode 55739: reward = -6.72, steps = 28 16:42:17 [INFO] train episode 55740: reward = 3.76, steps = 40 16:42:20 [INFO] train episode 55741: reward = -8.47, steps = 34 16:42:23 [INFO] train episode 55742: reward = -8.47, steps = 33 16:42:26 [INFO] train episode 55743: reward = 11.79, steps = 39 16:42:30 [INFO] train episode 55744: reward = 5.11, steps = 46 16:42:34 [INFO] train episode 55745: reward = 3.73, steps = 45 16:42:37 [INFO] train episode 55746: reward = -3.79, steps = 30 16:42:41 [INFO] train episode 55747: reward = 17.00, steps = 50 16:42:44 [INFO] train episode 55748: reward = -5.04, steps = 29 16:42:48 [INFO] train episode 55749: reward = 20.59, steps = 41 16:42:51 [INFO] train episode 55750: reward = 0.50, steps = 30 16:42:54 [INFO] train episode 55751: reward = 19.84, steps = 39 16:42:56 [INFO] train episode 55752: reward = -17.56, steps = 22 16:43:00 [INFO] train episode 55753: reward = -20.71, steps = 47 16:43:03 [INFO] train episode 55754: reward = -13.36, steps = 34 16:43:05 [INFO] train episode 55755: reward = -16.67, steps = 23 16:43:09 [INFO] train episode 55756: reward = 7.73, steps = 43 16:43:12 [INFO] train episode 55757: reward = -12.17, steps = 29 16:43:14 [INFO] train episode 55758: reward = -51.98, steps = 33 16:43:19 [INFO] train episode 55759: reward = -5.17, steps = 50 16:43:22 [INFO] train episode 55760: reward = -15.68, steps = 33 16:43:24 [INFO] train episode 55761: reward = -24.37, steps = 21 16:43:29 [INFO] train episode 55762: reward = 24.33, steps = 65 16:43:34 [INFO] train episode 55763: reward = -1.61, steps = 60 16:43:37 [INFO] train episode 55764: reward = -13.26, steps = 27 16:43:40 [INFO] train episode 55765: reward = -11.85, steps = 26 16:43:42 [INFO] train episode 55766: reward = -13.21, steps = 27 16:43:45 [INFO] train episode 55767: reward = -1.71, steps = 39 16:43:47 [INFO] train episode 55768: reward = -30.70, steps = 22 16:43:50 [INFO] train episode 55769: reward = 8.10, steps = 36 16:43:52 [INFO] train episode 55770: reward = -11.65, steps = 22 16:43:57 [INFO] train episode 55771: reward = 12.26, steps = 47 16:44:01 [INFO] train episode 55772: reward = 6.17, steps = 48 16:44:02 [INFO] train episode 55773: reward = -18.02, steps = 20 16:44:05 [INFO] train episode 55774: reward = -2.59, steps = 29 16:44:08 [INFO] train episode 55775: reward = -28.91, steps = 27 16:44:12 [INFO] train episode 55776: reward = 4.00, steps = 36 16:44:15 [INFO] train episode 55777: reward = -19.05, steps = 34 16:44:16 [INFO] train episode 55778: reward = -16.99, steps = 21 16:44:20 [INFO] train episode 55779: reward = 20.70, steps = 38 16:44:24 [INFO] train episode 55780: reward = -4.35, steps = 50 16:44:29 [INFO] train episode 55781: reward = -5.11, steps = 45 16:44:31 [INFO] train episode 55782: reward = -18.76, steps = 24 16:44:34 [INFO] train episode 55783: reward = 10.86, steps = 39 16:44:38 [INFO] train episode 55784: reward = 14.09, steps = 38 16:44:42 [INFO] train episode 55785: reward = 17.12, steps = 50 16:44:46 [INFO] train episode 55786: reward = -12.55, steps = 46 16:44:49 [INFO] train episode 55787: reward = 11.31, steps = 36 16:44:52 [INFO] train episode 55788: reward = -4.61, steps = 31 16:44:55 [INFO] train episode 55789: reward = 2.20, steps = 36 16:45:01 [INFO] train episode 55790: reward = -35.74, steps = 60 16:45:04 [INFO] train episode 55791: reward = 7.33, steps = 38 16:45:07 [INFO] train episode 55792: reward = 16.81, steps = 39 16:45:09 [INFO] train episode 55793: reward = -11.99, steps = 26 16:45:13 [INFO] train episode 55794: reward = 8.76, steps = 44 16:45:20 [INFO] train episode 55795: reward = -10.30, steps = 71 16:45:22 [INFO] train episode 55796: reward = -14.57, steps = 31 16:45:26 [INFO] train episode 55797: reward = -2.00, steps = 42 16:45:29 [INFO] train episode 55798: reward = -26.83, steps = 33 16:45:32 [INFO] train episode 55799: reward = 13.03, steps = 39 16:45:37 [INFO] train episode 55800: reward = 25.50, steps = 46 16:45:40 [INFO] train episode 55801: reward = -50.44, steps = 39 16:45:43 [INFO] train episode 55802: reward = -6.23, steps = 38 16:45:47 [INFO] train episode 55803: reward = -29.51, steps = 41 16:45:52 [INFO] train episode 55804: reward = -18.90, steps = 53 16:45:55 [INFO] train episode 55805: reward = 18.84, steps = 37 16:45:57 [INFO] train episode 55806: reward = -6.91, steps = 29 16:46:00 [INFO] train episode 55807: reward = -3.50, steps = 33 16:46:05 [INFO] train episode 55808: reward = 21.69, steps = 54 16:46:07 [INFO] train episode 55809: reward = -61.42, steps = 25 16:46:10 [INFO] train episode 55810: reward = 2.05, steps = 35 16:46:14 [INFO] train episode 55811: reward = 24.95, steps = 47 16:46:18 [INFO] train episode 55812: reward = -28.55, steps = 38 16:46:23 [INFO] train episode 55813: reward = 23.21, steps = 54 16:46:24 [INFO] train episode 55814: reward = -59.78, steps = 19 16:46:28 [INFO] train episode 55815: reward = -29.39, steps = 37 16:46:30 [INFO] train episode 55816: reward = -3.41, steps = 31 16:46:33 [INFO] train episode 55817: reward = 2.71, steps = 35 16:46:37 [INFO] train episode 55818: reward = -7.41, steps = 43 16:46:41 [INFO] train episode 55819: reward = 21.39, steps = 43 16:46:44 [INFO] train episode 55820: reward = -21.89, steps = 29 16:46:47 [INFO] train episode 55821: reward = 19.28, steps = 37 16:46:51 [INFO] train episode 55822: reward = -4.57, steps = 45 16:46:55 [INFO] train episode 55823: reward = 11.64, steps = 45 16:46:58 [INFO] train episode 55824: reward = 8.66, steps = 39 16:47:02 [INFO] train episode 55825: reward = -1.00, steps = 38 16:47:05 [INFO] train episode 55826: reward = -6.29, steps = 32 16:47:09 [INFO] train episode 55827: reward = 1.56, steps = 44 16:47:13 [INFO] train episode 55828: reward = 18.94, steps = 44 16:47:16 [INFO] train episode 55829: reward = -10.43, steps = 31 16:47:19 [INFO] train episode 55830: reward = 9.01, steps = 35 16:47:22 [INFO] train episode 55831: reward = -6.02, steps = 39 16:47:26 [INFO] train episode 55832: reward = 6.29, steps = 39 16:47:29 [INFO] train episode 55833: reward = 5.10, steps = 36 16:47:32 [INFO] train episode 55834: reward = -8.30, steps = 31 16:47:37 [INFO] train episode 55835: reward = -24.58, steps = 60 16:47:40 [INFO] train episode 55836: reward = 10.37, steps = 35 16:47:44 [INFO] train episode 55837: reward = 15.09, steps = 41 16:47:46 [INFO] train episode 55838: reward = -27.78, steps = 21 16:47:49 [INFO] train episode 55839: reward = 1.67, steps = 35 16:47:51 [INFO] train episode 55840: reward = -28.06, steps = 24 16:47:55 [INFO] train episode 55841: reward = 6.95, steps = 47 16:48:00 [INFO] train episode 55842: reward = 13.68, steps = 57 16:48:03 [INFO] train episode 55843: reward = 1.07, steps = 36 16:48:07 [INFO] train episode 55844: reward = 5.16, steps = 40 16:48:11 [INFO] train episode 55845: reward = -2.43, steps = 48 16:48:15 [INFO] train episode 55846: reward = 1.22, steps = 42 16:48:18 [INFO] train episode 55847: reward = -21.84, steps = 38 16:48:22 [INFO] train episode 55848: reward = 0.18, steps = 41 16:48:25 [INFO] train episode 55849: reward = 1.48, steps = 43 16:48:27 [INFO] train episode 55850: reward = -36.92, steps = 23 16:48:32 [INFO] train episode 55851: reward = 20.66, steps = 48 16:48:37 [INFO] train episode 55852: reward = 0.08, steps = 64 16:48:39 [INFO] train episode 55853: reward = -11.77, steps = 20 16:48:43 [INFO] train episode 55854: reward = 2.17, steps = 43 16:48:45 [INFO] train episode 55855: reward = -16.14, steps = 22 16:48:49 [INFO] train episode 55856: reward = 9.04, steps = 42 16:48:52 [INFO] train episode 55857: reward = 18.64, steps = 37 16:48:55 [INFO] train episode 55858: reward = 16.96, steps = 39 16:48:58 [INFO] train episode 55859: reward = 1.05, steps = 35 16:49:03 [INFO] train episode 55860: reward = -8.99, steps = 50 16:49:07 [INFO] train episode 55861: reward = 10.91, steps = 51 16:49:11 [INFO] train episode 55862: reward = 3.47, steps = 43 16:49:13 [INFO] train episode 55863: reward = -6.82, steps = 29 16:49:16 [INFO] train episode 55864: reward = -12.94, steps = 29 16:49:20 [INFO] train episode 55865: reward = 10.47, steps = 47 16:49:24 [INFO] train episode 55866: reward = -3.32, steps = 37 16:49:26 [INFO] train episode 55867: reward = -18.95, steps = 28 16:49:29 [INFO] train episode 55868: reward = 5.72, steps = 38 16:49:32 [INFO] train episode 55869: reward = -0.02, steps = 32 16:49:36 [INFO] train episode 55870: reward = 13.59, steps = 41 16:49:38 [INFO] train episode 55871: reward = -17.71, steps = 22 16:49:42 [INFO] train episode 55872: reward = 13.92, steps = 47 16:49:45 [INFO] train episode 55873: reward = -3.00, steps = 34 16:49:47 [INFO] train episode 55874: reward = -25.55, steps = 29 16:49:51 [INFO] train episode 55875: reward = 15.22, steps = 40 16:49:56 [INFO] train episode 55876: reward = -1.29, steps = 46 16:49:59 [INFO] train episode 55877: reward = 11.90, steps = 35 16:50:02 [INFO] train episode 55878: reward = 15.95, steps = 38 16:50:05 [INFO] train episode 55879: reward = 3.44, steps = 37 16:50:09 [INFO] train episode 55880: reward = 12.45, steps = 45 16:50:14 [INFO] train episode 55881: reward = 11.41, steps = 51 16:50:17 [INFO] train episode 55882: reward = 1.38, steps = 31 16:50:20 [INFO] train episode 55883: reward = -18.82, steps = 35 16:50:23 [INFO] train episode 55884: reward = 10.19, steps = 36 16:50:26 [INFO] train episode 55885: reward = -1.51, steps = 32 16:50:29 [INFO] train episode 55886: reward = -0.74, steps = 36 16:50:35 [INFO] train episode 55887: reward = -26.95, steps = 70 16:50:39 [INFO] train episode 55888: reward = 17.07, steps = 40 16:50:42 [INFO] train episode 55889: reward = -0.87, steps = 30 16:50:45 [INFO] train episode 55890: reward = 3.09, steps = 38 16:50:48 [INFO] train episode 55891: reward = 0.53, steps = 33 16:50:52 [INFO] train episode 55892: reward = -7.46, steps = 49 16:50:55 [INFO] train episode 55893: reward = 5.69, steps = 33 16:50:59 [INFO] train episode 55894: reward = 15.56, steps = 48 16:51:02 [INFO] train episode 55895: reward = -32.81, steps = 30 16:51:05 [INFO] train episode 55896: reward = 13.48, steps = 36 16:51:08 [INFO] train episode 55897: reward = -34.51, steps = 31 16:51:10 [INFO] train episode 55898: reward = -21.77, steps = 21 16:51:13 [INFO] train episode 55899: reward = -1.64, steps = 30 16:51:15 [INFO] train episode 55900: reward = 15.06, steps = 34 16:51:19 [INFO] train episode 55901: reward = 8.12, steps = 40 16:51:22 [INFO] train episode 55902: reward = -10.70, steps = 35 16:51:25 [INFO] train episode 55903: reward = 4.50, steps = 42 16:51:29 [INFO] train episode 55904: reward = -6.74, steps = 32 16:51:32 [INFO] train episode 55905: reward = 7.69, steps = 37 16:51:34 [INFO] train episode 55906: reward = -14.67, steps = 31 16:51:37 [INFO] train episode 55907: reward = -0.29, steps = 33 16:51:41 [INFO] train episode 55908: reward = 12.19, steps = 49 16:51:45 [INFO] train episode 55909: reward = 6.24, steps = 34 16:51:49 [INFO] train episode 55910: reward = 24.21, steps = 48 16:51:51 [INFO] train episode 55911: reward = -14.78, steps = 27 16:51:54 [INFO] train episode 55912: reward = 9.20, steps = 32 16:51:57 [INFO] train episode 55913: reward = -6.36, steps = 32 16:52:00 [INFO] train episode 55914: reward = -0.09, steps = 31 16:52:03 [INFO] train episode 55915: reward = -9.82, steps = 34 16:52:05 [INFO] train episode 55916: reward = -13.69, steps = 30 16:52:08 [INFO] train episode 55917: reward = -6.65, steps = 31 16:52:12 [INFO] train episode 55918: reward = 19.35, steps = 52 16:52:16 [INFO] train episode 55919: reward = -16.82, steps = 39 16:52:22 [INFO] train episode 55920: reward = -3.79, steps = 67 16:52:25 [INFO] train episode 55921: reward = 2.98, steps = 42 16:52:29 [INFO] train episode 55922: reward = 13.42, steps = 40 16:52:33 [INFO] train episode 55923: reward = 4.48, steps = 42 16:52:38 [INFO] train episode 55924: reward = 20.61, steps = 55 16:52:42 [INFO] train episode 55925: reward = 19.11, steps = 49 16:52:44 [INFO] train episode 55926: reward = -20.72, steps = 20 16:52:46 [INFO] train episode 55927: reward = -16.82, steps = 22 16:52:50 [INFO] train episode 55928: reward = -8.14, steps = 36 16:52:54 [INFO] train episode 55929: reward = 14.99, steps = 44 16:52:58 [INFO] train episode 55930: reward = -39.91, steps = 49 16:53:03 [INFO] train episode 55931: reward = -7.75, steps = 54 16:53:08 [INFO] train episode 55932: reward = 15.35, steps = 52 16:53:11 [INFO] train episode 55933: reward = 26.74, steps = 43 16:53:15 [INFO] train episode 55934: reward = 14.23, steps = 41 16:53:18 [INFO] train episode 55935: reward = -31.48, steps = 35 16:53:20 [INFO] train episode 55936: reward = -25.29, steps = 29 16:53:24 [INFO] train episode 55937: reward = 3.90, steps = 32 16:53:27 [INFO] train episode 55938: reward = 12.28, steps = 36 16:53:30 [INFO] train episode 55939: reward = -2.39, steps = 37 16:53:32 [INFO] train episode 55940: reward = -2.97, steps = 29 16:53:36 [INFO] train episode 55941: reward = -5.40, steps = 39 16:53:39 [INFO] train episode 55942: reward = -3.65, steps = 37 16:53:43 [INFO] train episode 55943: reward = -11.09, steps = 44 16:53:45 [INFO] train episode 55944: reward = -22.83, steps = 18 16:53:49 [INFO] train episode 55945: reward = 19.28, steps = 48 16:53:51 [INFO] train episode 55946: reward = -14.13, steps = 22 16:53:53 [INFO] train episode 55947: reward = -15.43, steps = 22 16:53:56 [INFO] train episode 55948: reward = -0.77, steps = 37 16:54:01 [INFO] train episode 55949: reward = 12.82, steps = 53 16:54:03 [INFO] train episode 55950: reward = 8.21, steps = 30 16:54:07 [INFO] train episode 55951: reward = 16.03, steps = 40 16:54:09 [INFO] train episode 55952: reward = -22.45, steps = 21 16:54:11 [INFO] train episode 55953: reward = -23.47, steps = 21 16:54:14 [INFO] train episode 55954: reward = -0.89, steps = 38 16:54:18 [INFO] train episode 55955: reward = 4.34, steps = 45 16:54:22 [INFO] train episode 55956: reward = -0.02, steps = 42 16:54:24 [INFO] train episode 55957: reward = -3.46, steps = 27 16:54:28 [INFO] train episode 55958: reward = -10.19, steps = 38 16:54:31 [INFO] train episode 55959: reward = 2.52, steps = 35 16:54:38 [INFO] train episode 55960: reward = 20.53, steps = 77 16:54:41 [INFO] train episode 55961: reward = -12.32, steps = 40 16:54:45 [INFO] train episode 55962: reward = -29.23, steps = 33 16:54:48 [INFO] train episode 55963: reward = 19.89, steps = 43 16:54:52 [INFO] train episode 55964: reward = 5.90, steps = 35 16:54:55 [INFO] train episode 55965: reward = 9.99, steps = 41 16:54:57 [INFO] train episode 55966: reward = -10.52, steps = 27 16:55:01 [INFO] train episode 55967: reward = 19.29, steps = 37 16:55:05 [INFO] train episode 55968: reward = 2.00, steps = 44 16:55:07 [INFO] train episode 55969: reward = -13.72, steps = 23 16:55:10 [INFO] train episode 55970: reward = 3.47, steps = 34 16:55:11 [INFO] train episode 55971: reward = -16.48, steps = 19 16:55:14 [INFO] train episode 55972: reward = 6.82, steps = 33 16:55:17 [INFO] train episode 55973: reward = -12.71, steps = 27 16:55:21 [INFO] train episode 55974: reward = 19.15, steps = 44 16:55:23 [INFO] train episode 55975: reward = -15.55, steps = 22 16:55:26 [INFO] train episode 55976: reward = 9.51, steps = 42 16:55:30 [INFO] train episode 55977: reward = 7.90, steps = 39 16:55:33 [INFO] train episode 55978: reward = 16.48, steps = 34 16:55:36 [INFO] train episode 55979: reward = 13.01, steps = 40 16:55:40 [INFO] train episode 55980: reward = -2.81, steps = 38 16:55:44 [INFO] train episode 55981: reward = 12.49, steps = 40 16:55:47 [INFO] train episode 55982: reward = -18.81, steps = 40 16:55:51 [INFO] train episode 55983: reward = -7.12, steps = 32 16:55:55 [INFO] train episode 55984: reward = 16.97, steps = 46 16:55:58 [INFO] train episode 55985: reward = 5.73, steps = 34 16:56:01 [INFO] train episode 55986: reward = 9.77, steps = 39 16:56:06 [INFO] train episode 55987: reward = 21.71, steps = 50 16:56:10 [INFO] train episode 55988: reward = 16.13, steps = 53 16:56:12 [INFO] train episode 55989: reward = -33.68, steps = 24 16:56:16 [INFO] train episode 55990: reward = 16.81, steps = 44 16:56:19 [INFO] train episode 55991: reward = 7.70, steps = 40 16:56:24 [INFO] train episode 55992: reward = 16.18, steps = 43 16:56:26 [INFO] train episode 55993: reward = -4.44, steps = 32 16:56:30 [INFO] train episode 55994: reward = 10.41, steps = 41 16:56:35 [INFO] train episode 55995: reward = 15.29, steps = 58 16:56:37 [INFO] train episode 55996: reward = -9.69, steps = 20 16:56:41 [INFO] train episode 55997: reward = 8.66, steps = 44 16:56:44 [INFO] train episode 55998: reward = 3.86, steps = 37 16:56:46 [INFO] train episode 55999: reward = -16.98, steps = 20 16:56:50 [INFO] train episode 56000: reward = -6.51, steps = 41 16:56:53 [INFO] train episode 56001: reward = 7.19, steps = 39 16:56:56 [INFO] train episode 56002: reward = 12.60, steps = 36 16:56:59 [INFO] train episode 56003: reward = 11.34, steps = 37 16:57:02 [INFO] train episode 56004: reward = -2.31, steps = 33 16:57:04 [INFO] train episode 56005: reward = -15.67, steps = 20 16:57:07 [INFO] train episode 56006: reward = 11.08, steps = 39 16:57:12 [INFO] train episode 56007: reward = 16.94, steps = 52 16:57:15 [INFO] train episode 56008: reward = 6.74, steps = 37 16:57:17 [INFO] train episode 56009: reward = -29.85, steps = 21 16:57:19 [INFO] train episode 56010: reward = -21.91, steps = 21 16:57:22 [INFO] train episode 56011: reward = -5.74, steps = 28 16:57:25 [INFO] train episode 56012: reward = 5.70, steps = 43 16:57:28 [INFO] train episode 56013: reward = 7.32, steps = 32 16:57:31 [INFO] train episode 56014: reward = -1.47, steps = 32 16:57:34 [INFO] train episode 56015: reward = -5.42, steps = 32 16:57:36 [INFO] train episode 56016: reward = -22.95, steps = 23 16:57:38 [INFO] train episode 56017: reward = -15.70, steps = 20 16:57:41 [INFO] train episode 56018: reward = 6.94, steps = 33 16:57:44 [INFO] train episode 56019: reward = -7.10, steps = 31 16:57:46 [INFO] train episode 56020: reward = -10.77, steps = 27 16:57:49 [INFO] train episode 56021: reward = 2.51, steps = 32 16:57:52 [INFO] train episode 56022: reward = -8.97, steps = 41 16:57:55 [INFO] train episode 56023: reward = 4.37, steps = 32 16:57:59 [INFO] train episode 56024: reward = 1.09, steps = 39 16:58:03 [INFO] train episode 56025: reward = 2.22, steps = 42 16:58:06 [INFO] train episode 56026: reward = 10.96, steps = 41 16:58:09 [INFO] train episode 56027: reward = 4.47, steps = 34 16:58:14 [INFO] train episode 56028: reward = 16.06, steps = 56 16:58:17 [INFO] train episode 56029: reward = -9.64, steps = 28 16:58:20 [INFO] train episode 56030: reward = 15.46, steps = 46 16:58:24 [INFO] train episode 56031: reward = 12.32, steps = 42 16:58:27 [INFO] train episode 56032: reward = 4.33, steps = 35 16:58:30 [INFO] train episode 56033: reward = 9.99, steps = 32 16:58:33 [INFO] train episode 56034: reward = -8.01, steps = 30 16:58:36 [INFO] train episode 56035: reward = 8.43, steps = 30 16:58:40 [INFO] train episode 56036: reward = 17.03, steps = 45 16:58:44 [INFO] train episode 56037: reward = 19.94, steps = 43 16:58:47 [INFO] train episode 56038: reward = 7.49, steps = 34 16:58:50 [INFO] train episode 56039: reward = -3.86, steps = 28 16:58:54 [INFO] train episode 56040: reward = 6.66, steps = 43 16:58:56 [INFO] train episode 56041: reward = -11.81, steps = 33 16:59:00 [INFO] train episode 56042: reward = -16.39, steps = 38 16:59:03 [INFO] train episode 56043: reward = -28.57, steps = 40 16:59:07 [INFO] train episode 56044: reward = 9.50, steps = 37 16:59:11 [INFO] train episode 56045: reward = 14.46, steps = 52 16:59:14 [INFO] train episode 56046: reward = -14.51, steps = 27 16:59:17 [INFO] train episode 56047: reward = -12.72, steps = 39 16:59:20 [INFO] train episode 56048: reward = 12.11, steps = 32 16:59:24 [INFO] train episode 56049: reward = 18.96, steps = 46 16:59:28 [INFO] train episode 56050: reward = 26.79, steps = 44 16:59:30 [INFO] train episode 56051: reward = -9.78, steps = 25 16:59:34 [INFO] train episode 56052: reward = 13.54, steps = 39 16:59:36 [INFO] train episode 56053: reward = -27.95, steps = 20 16:59:39 [INFO] train episode 56054: reward = 4.73, steps = 32 16:59:42 [INFO] train episode 56055: reward = -0.70, steps = 35 16:59:45 [INFO] train episode 56056: reward = 3.32, steps = 36 16:59:48 [INFO] train episode 56057: reward = 2.99, steps = 34 16:59:51 [INFO] train episode 56058: reward = 4.10, steps = 36 16:59:54 [INFO] train episode 56059: reward = -17.77, steps = 27 16:59:56 [INFO] train episode 56060: reward = -8.26, steps = 28 16:59:58 [INFO] train episode 56061: reward = -18.06, steps = 24 17:00:02 [INFO] train episode 56062: reward = 17.10, steps = 38 17:00:05 [INFO] train episode 56063: reward = 22.57, steps = 46 17:00:09 [INFO] train episode 56064: reward = 2.32, steps = 40 17:00:12 [INFO] train episode 56065: reward = 6.47, steps = 34 17:00:17 [INFO] train episode 56066: reward = 11.20, steps = 57 17:00:20 [INFO] train episode 56067: reward = 10.29, steps = 38 17:00:22 [INFO] train episode 56068: reward = -14.05, steps = 20 17:00:25 [INFO] train episode 56069: reward = 13.17, steps = 37 17:00:29 [INFO] train episode 56070: reward = 7.64, steps = 44 17:00:33 [INFO] train episode 56071: reward = 18.73, steps = 43 17:00:37 [INFO] train episode 56072: reward = 14.00, steps = 39 17:00:41 [INFO] train episode 56073: reward = 4.03, steps = 49 17:00:44 [INFO] train episode 56074: reward = -0.79, steps = 31 17:00:47 [INFO] train episode 56075: reward = 6.03, steps = 38 17:00:50 [INFO] train episode 56076: reward = -0.41, steps = 33 17:00:53 [INFO] train episode 56077: reward = -20.40, steps = 32 17:00:57 [INFO] train episode 56078: reward = 3.52, steps = 44 17:01:01 [INFO] train episode 56079: reward = 24.60, steps = 46 17:01:03 [INFO] train episode 56080: reward = -9.46, steps = 29 17:01:07 [INFO] train episode 56081: reward = 23.49, steps = 40 17:01:10 [INFO] train episode 56082: reward = -2.41, steps = 33 17:01:11 [INFO] train episode 56083: reward = -27.39, steps = 21 17:01:15 [INFO] train episode 56084: reward = 11.80, steps = 41 17:01:18 [INFO] train episode 56085: reward = 4.05, steps = 33 17:01:22 [INFO] train episode 56086: reward = 23.26, steps = 41 17:01:25 [INFO] train episode 56087: reward = 5.07, steps = 34 17:01:28 [INFO] train episode 56088: reward = 5.95, steps = 37 17:01:31 [INFO] train episode 56089: reward = 9.11, steps = 36 17:01:35 [INFO] train episode 56090: reward = 18.09, steps = 39 17:01:39 [INFO] train episode 56091: reward = 7.50, steps = 46 17:01:43 [INFO] train episode 56092: reward = -5.74, steps = 39 17:01:47 [INFO] train episode 56093: reward = 16.86, steps = 42 17:01:49 [INFO] train episode 56094: reward = -16.46, steps = 23 17:01:51 [INFO] train episode 56095: reward = -27.01, steps = 26 17:01:54 [INFO] train episode 56096: reward = 5.63, steps = 36 17:01:58 [INFO] train episode 56097: reward = 13.39, steps = 40 17:02:02 [INFO] train episode 56098: reward = 8.83, steps = 41 17:02:04 [INFO] train episode 56099: reward = 12.92, steps = 34 17:02:07 [INFO] train episode 56100: reward = 8.45, steps = 33 17:02:11 [INFO] train episode 56101: reward = -10.85, steps = 46 17:02:13 [INFO] train episode 56102: reward = -6.89, steps = 24 17:02:17 [INFO] train episode 56103: reward = 18.61, steps = 36 17:02:19 [INFO] train episode 56104: reward = -20.80, steps = 26 17:02:22 [INFO] train episode 56105: reward = 14.13, steps = 34 17:02:25 [INFO] train episode 56106: reward = 3.70, steps = 36 17:02:28 [INFO] train episode 56107: reward = 9.61, steps = 35 17:02:34 [INFO] train episode 56108: reward = 12.52, steps = 61 17:02:38 [INFO] train episode 56109: reward = -6.54, steps = 39 17:02:41 [INFO] train episode 56110: reward = -1.13, steps = 33 17:02:44 [INFO] train episode 56111: reward = 11.97, steps = 41 17:02:47 [INFO] train episode 56112: reward = 13.88, steps = 38 17:02:52 [INFO] train episode 56113: reward = 12.38, steps = 46 17:02:55 [INFO] train episode 56114: reward = 6.32, steps = 41 17:02:59 [INFO] train episode 56115: reward = 1.93, steps = 36 17:03:02 [INFO] train episode 56116: reward = 9.58, steps = 42 17:03:06 [INFO] train episode 56117: reward = 4.45, steps = 43 17:03:08 [INFO] train episode 56118: reward = -8.76, steps = 22 17:03:11 [INFO] train episode 56119: reward = -4.76, steps = 31 17:03:13 [INFO] train episode 56120: reward = -6.92, steps = 21 17:03:16 [INFO] train episode 56121: reward = 18.44, steps = 36 17:03:18 [INFO] train episode 56122: reward = 4.72, steps = 30 17:03:21 [INFO] train episode 56123: reward = -2.58, steps = 27 17:03:23 [INFO] train episode 56124: reward = -19.56, steps = 24 17:03:26 [INFO] train episode 56125: reward = -5.82, steps = 35 17:03:29 [INFO] train episode 56126: reward = 7.86, steps = 36 17:03:32 [INFO] train episode 56127: reward = -11.03, steps = 27 17:03:35 [INFO] train episode 56128: reward = 7.92, steps = 38 17:03:38 [INFO] train episode 56129: reward = 19.02, steps = 36 17:03:41 [INFO] train episode 56130: reward = -6.24, steps = 28 17:03:44 [INFO] train episode 56131: reward = 5.97, steps = 34 17:03:47 [INFO] train episode 56132: reward = -3.20, steps = 31 17:03:49 [INFO] train episode 56133: reward = 8.44, steps = 31 17:03:54 [INFO] train episode 56134: reward = 1.32, steps = 53 17:03:57 [INFO] train episode 56135: reward = 6.65, steps = 37 17:04:00 [INFO] train episode 56136: reward = -8.53, steps = 24 17:04:04 [INFO] train episode 56137: reward = 4.30, steps = 48 17:04:06 [INFO] train episode 56138: reward = -23.10, steps = 30 17:04:10 [INFO] train episode 56139: reward = 7.08, steps = 36 17:04:13 [INFO] train episode 56140: reward = -2.50, steps = 33 17:04:15 [INFO] train episode 56141: reward = -26.31, steps = 22 17:04:17 [INFO] train episode 56142: reward = 0.59, steps = 30 17:04:20 [INFO] train episode 56143: reward = 4.65, steps = 32 17:04:23 [INFO] train episode 56144: reward = 13.33, steps = 36 17:04:26 [INFO] train episode 56145: reward = 12.68, steps = 33 17:04:31 [INFO] train episode 56146: reward = 17.70, steps = 36 17:04:34 [INFO] train episode 56147: reward = 9.89, steps = 34 17:04:37 [INFO] train episode 56148: reward = -2.21, steps = 34 17:04:40 [INFO] train episode 56149: reward = 15.95, steps = 38 17:04:42 [INFO] train episode 56150: reward = -16.29, steps = 22 17:04:45 [INFO] train episode 56151: reward = 3.80, steps = 36 17:04:49 [INFO] train episode 56152: reward = 9.06, steps = 39 17:04:52 [INFO] train episode 56153: reward = 16.50, steps = 38 17:04:55 [INFO] train episode 56154: reward = 6.57, steps = 36 17:04:58 [INFO] train episode 56155: reward = 8.32, steps = 34 17:05:02 [INFO] train episode 56156: reward = 15.14, steps = 42 17:05:04 [INFO] train episode 56157: reward = -33.65, steps = 20 17:05:07 [INFO] train episode 56158: reward = 14.96, steps = 34 17:05:10 [INFO] train episode 56159: reward = 19.28, steps = 37 17:05:13 [INFO] train episode 56160: reward = -5.08, steps = 32 17:05:17 [INFO] train episode 56161: reward = 12.59, steps = 45 17:05:20 [INFO] train episode 56162: reward = 17.47, steps = 36 17:05:23 [INFO] train episode 56163: reward = 12.07, steps = 40 17:05:27 [INFO] train episode 56164: reward = 15.77, steps = 38 17:05:30 [INFO] train episode 56165: reward = 15.76, steps = 37 17:05:33 [INFO] train episode 56166: reward = -5.72, steps = 26 17:05:34 [INFO] train episode 56167: reward = -24.91, steps = 21 17:05:37 [INFO] train episode 56168: reward = 2.41, steps = 30 17:05:40 [INFO] train episode 56169: reward = 17.73, steps = 35 17:05:42 [INFO] train episode 56170: reward = -14.49, steps = 21 17:05:46 [INFO] train episode 56171: reward = 14.17, steps = 43 17:05:48 [INFO] train episode 56172: reward = -22.18, steps = 28 17:05:51 [INFO] train episode 56173: reward = 17.30, steps = 36 17:05:54 [INFO] train episode 56174: reward = 10.37, steps = 34 17:05:57 [INFO] train episode 56175: reward = 9.49, steps = 31 17:06:00 [INFO] train episode 56176: reward = -3.17, steps = 38 17:06:05 [INFO] train episode 56177: reward = 22.10, steps = 44 17:06:08 [INFO] train episode 56178: reward = 16.48, steps = 38 17:06:12 [INFO] train episode 56179: reward = 25.23, steps = 54 17:06:15 [INFO] train episode 56180: reward = 4.06, steps = 26 17:06:17 [INFO] train episode 56181: reward = -9.20, steps = 23 17:06:20 [INFO] train episode 56182: reward = 5.75, steps = 35 17:06:23 [INFO] train episode 56183: reward = 9.54, steps = 33 17:06:26 [INFO] train episode 56184: reward = -10.99, steps = 36 17:06:29 [INFO] train episode 56185: reward = -0.79, steps = 34 17:06:31 [INFO] train episode 56186: reward = -21.28, steps = 22 17:06:34 [INFO] train episode 56187: reward = -6.27, steps = 33 17:06:37 [INFO] train episode 56188: reward = 12.36, steps = 34 17:06:40 [INFO] train episode 56189: reward = 1.28, steps = 31 17:06:43 [INFO] train episode 56190: reward = 0.64, steps = 37 17:06:46 [INFO] train episode 56191: reward = -4.92, steps = 36 17:06:50 [INFO] train episode 56192: reward = 23.87, steps = 50 17:06:53 [INFO] train episode 56193: reward = -24.17, steps = 29 17:06:57 [INFO] train episode 56194: reward = -12.16, steps = 43 17:06:59 [INFO] train episode 56195: reward = -14.55, steps = 21 17:07:01 [INFO] train episode 56196: reward = -0.57, steps = 31 17:07:05 [INFO] train episode 56197: reward = 6.89, steps = 46 17:07:09 [INFO] train episode 56198: reward = 6.64, steps = 33 17:07:11 [INFO] train episode 56199: reward = 2.62, steps = 31 17:07:14 [INFO] train episode 56200: reward = -2.77, steps = 28 17:07:17 [INFO] train episode 56201: reward = 6.52, steps = 42 17:07:19 [INFO] train episode 56202: reward = -27.84, steps = 20 17:07:22 [INFO] train episode 56203: reward = 10.26, steps = 37 17:07:27 [INFO] train episode 56204: reward = 23.52, steps = 43 17:07:32 [INFO] train episode 56205: reward = 16.28, steps = 62 17:07:36 [INFO] train episode 56206: reward = 9.90, steps = 39 17:07:39 [INFO] train episode 56207: reward = 4.59, steps = 42 17:07:44 [INFO] train episode 56208: reward = 2.67, steps = 46 17:07:48 [INFO] train episode 56209: reward = 15.80, steps = 55 17:07:52 [INFO] train episode 56210: reward = 16.95, steps = 42 17:07:55 [INFO] train episode 56211: reward = 13.20, steps = 37 17:07:58 [INFO] train episode 56212: reward = 0.84, steps = 32 17:08:01 [INFO] train episode 56213: reward = -13.53, steps = 27 17:08:04 [INFO] train episode 56214: reward = 16.83, steps = 37 17:08:07 [INFO] train episode 56215: reward = 15.96, steps = 35 17:08:10 [INFO] train episode 56216: reward = 8.69, steps = 38 17:08:13 [INFO] train episode 56217: reward = 1.65, steps = 36 17:08:16 [INFO] train episode 56218: reward = -7.71, steps = 30 17:08:18 [INFO] train episode 56219: reward = -18.80, steps = 22 17:08:21 [INFO] train episode 56220: reward = -1.30, steps = 37 17:08:25 [INFO] train episode 56221: reward = 11.44, steps = 39 17:08:28 [INFO] train episode 56222: reward = 17.89, steps = 43 17:08:32 [INFO] train episode 56223: reward = 9.45, steps = 33 17:08:34 [INFO] train episode 56224: reward = -9.21, steps = 28 17:08:37 [INFO] train episode 56225: reward = 2.62, steps = 39 17:08:41 [INFO] train episode 56226: reward = 10.31, steps = 43 17:08:45 [INFO] train episode 56227: reward = 16.93, steps = 39 17:08:49 [INFO] train episode 56228: reward = 29.94, steps = 53 17:08:54 [INFO] train episode 56229: reward = 15.03, steps = 52 17:08:57 [INFO] train episode 56230: reward = 17.69, steps = 41 17:09:02 [INFO] train episode 56231: reward = 3.88, steps = 50 17:09:06 [INFO] train episode 56232: reward = 18.47, steps = 43 17:09:09 [INFO] train episode 56233: reward = 17.98, steps = 38 17:09:13 [INFO] train episode 56234: reward = 25.81, steps = 44 17:09:17 [INFO] train episode 56235: reward = 29.50, steps = 49 17:09:21 [INFO] train episode 56236: reward = 20.15, steps = 37 17:09:24 [INFO] train episode 56237: reward = 21.73, steps = 42 17:09:28 [INFO] train episode 56238: reward = 15.46, steps = 39 17:09:31 [INFO] train episode 56239: reward = 12.82, steps = 40 17:09:36 [INFO] train episode 56240: reward = 18.48, steps = 49 17:09:39 [INFO] train episode 56241: reward = 11.53, steps = 43 17:09:43 [INFO] train episode 56242: reward = 22.79, steps = 39 17:09:46 [INFO] train episode 56243: reward = 9.96, steps = 40 17:09:49 [INFO] train episode 56244: reward = 6.75, steps = 34 17:09:53 [INFO] train episode 56245: reward = 13.90, steps = 38 17:09:56 [INFO] train episode 56246: reward = 15.25, steps = 37 17:09:59 [INFO] train episode 56247: reward = 11.30, steps = 37 17:10:01 [INFO] train episode 56248: reward = -33.45, steps = 21 17:10:05 [INFO] train episode 56249: reward = 3.00, steps = 51 17:10:09 [INFO] train episode 56250: reward = 24.50, steps = 39 17:10:12 [INFO] train episode 56251: reward = 21.30, steps = 38 17:10:16 [INFO] train episode 56252: reward = 5.69, steps = 40 17:10:18 [INFO] train episode 56253: reward = -14.65, steps = 25 17:10:23 [INFO] train episode 56254: reward = 34.05, steps = 48 17:10:26 [INFO] train episode 56255: reward = -5.58, steps = 35 17:10:29 [INFO] train episode 56256: reward = -2.89, steps = 38 17:10:32 [INFO] train episode 56257: reward = -10.11, steps = 33 17:10:34 [INFO] train episode 56258: reward = -25.24, steps = 25 17:10:38 [INFO] train episode 56259: reward = 15.26, steps = 39 17:10:42 [INFO] train episode 56260: reward = 12.80, steps = 38 17:10:44 [INFO] train episode 56261: reward = -5.81, steps = 24 17:10:48 [INFO] train episode 56262: reward = 27.50, steps = 46 17:10:50 [INFO] train episode 56263: reward = -4.79, steps = 24 17:10:52 [INFO] train episode 56264: reward = -14.54, steps = 25 17:10:55 [INFO] train episode 56265: reward = 1.37, steps = 34 17:10:58 [INFO] train episode 56266: reward = 6.02, steps = 35 17:11:02 [INFO] train episode 56267: reward = 19.31, steps = 39 17:11:07 [INFO] train episode 56268: reward = 0.21, steps = 59 17:11:13 [INFO] train episode 56269: reward = -20.02, steps = 66 17:11:16 [INFO] train episode 56270: reward = 10.93, steps = 39 17:11:19 [INFO] train episode 56271: reward = 20.82, steps = 39 17:11:23 [INFO] train episode 56272: reward = 13.26, steps = 39 17:11:26 [INFO] train episode 56273: reward = 4.77, steps = 39 17:11:30 [INFO] train episode 56274: reward = -6.28, steps = 38 17:11:33 [INFO] train episode 56275: reward = 11.48, steps = 41 17:11:36 [INFO] train episode 56276: reward = -10.33, steps = 33 17:11:38 [INFO] train episode 56277: reward = -0.65, steps = 25 17:11:41 [INFO] train episode 56278: reward = 23.60, steps = 35 17:11:45 [INFO] train episode 56279: reward = 19.43, steps = 40 17:11:48 [INFO] train episode 56280: reward = 15.61, steps = 37 17:11:53 [INFO] train episode 56281: reward = 36.29, steps = 54 17:11:56 [INFO] train episode 56282: reward = 14.41, steps = 33 17:12:00 [INFO] train episode 56283: reward = -0.20, steps = 45 17:12:02 [INFO] train episode 56284: reward = -5.90, steps = 21 17:12:05 [INFO] train episode 56285: reward = -2.38, steps = 35 17:12:07 [INFO] train episode 56286: reward = -12.42, steps = 22 17:12:10 [INFO] train episode 56287: reward = 20.88, steps = 34 17:12:13 [INFO] train episode 56288: reward = 18.99, steps = 40 17:12:17 [INFO] train episode 56289: reward = 23.60, steps = 43 17:12:19 [INFO] train episode 56290: reward = -14.64, steps = 25 17:12:23 [INFO] train episode 56291: reward = 7.44, steps = 38 17:12:27 [INFO] train episode 56292: reward = 19.56, steps = 52 17:12:31 [INFO] train episode 56293: reward = 20.23, steps = 43 17:12:35 [INFO] train episode 56294: reward = 9.79, steps = 49 17:12:38 [INFO] train episode 56295: reward = -21.28, steps = 26 17:12:41 [INFO] train episode 56296: reward = 2.40, steps = 34 17:12:44 [INFO] train episode 56297: reward = 10.94, steps = 33 17:12:46 [INFO] train episode 56298: reward = 10.93, steps = 32 17:12:50 [INFO] train episode 56299: reward = -22.09, steps = 34 17:12:51 [INFO] train episode 56300: reward = -36.33, steps = 19 17:12:54 [INFO] train episode 56301: reward = -10.43, steps = 26 17:12:55 [INFO] train episode 56302: reward = -22.39, steps = 21 17:12:59 [INFO] train episode 56303: reward = 29.64, steps = 46 17:13:02 [INFO] train episode 56304: reward = 7.47, steps = 33 17:13:06 [INFO] train episode 56305: reward = 10.61, steps = 35 17:13:09 [INFO] train episode 56306: reward = 11.53, steps = 36 17:13:12 [INFO] train episode 56307: reward = 0.77, steps = 35 17:13:16 [INFO] train episode 56308: reward = 25.27, steps = 45 17:13:19 [INFO] train episode 56309: reward = -1.17, steps = 34 17:13:24 [INFO] train episode 56310: reward = 20.37, steps = 46 17:13:27 [INFO] train episode 56311: reward = 20.95, steps = 39 17:13:30 [INFO] train episode 56312: reward = -11.42, steps = 28 17:13:33 [INFO] train episode 56313: reward = 20.83, steps = 35 17:13:35 [INFO] train episode 56314: reward = 5.41, steps = 29 17:13:38 [INFO] train episode 56315: reward = 2.30, steps = 32 17:13:43 [INFO] train episode 56316: reward = 13.60, steps = 57 17:13:45 [INFO] train episode 56317: reward = -16.97, steps = 23 17:13:49 [INFO] train episode 56318: reward = 23.02, steps = 43 17:13:52 [INFO] train episode 56319: reward = 19.70, steps = 38 17:13:55 [INFO] train episode 56320: reward = -8.10, steps = 28 17:13:58 [INFO] train episode 56321: reward = -0.75, steps = 33 17:14:01 [INFO] train episode 56322: reward = 14.17, steps = 34 17:14:04 [INFO] train episode 56323: reward = -11.71, steps = 36 17:14:07 [INFO] train episode 56324: reward = 19.10, steps = 39 17:14:10 [INFO] train episode 56325: reward = -16.32, steps = 26 17:14:14 [INFO] train episode 56326: reward = 14.81, steps = 46 17:14:16 [INFO] train episode 56327: reward = 6.46, steps = 30 17:14:19 [INFO] train episode 56328: reward = 6.86, steps = 31 17:14:23 [INFO] train episode 56329: reward = -14.29, steps = 50 17:14:28 [INFO] train episode 56330: reward = 37.67, steps = 50 17:14:31 [INFO] train episode 56331: reward = 10.96, steps = 37 17:14:35 [INFO] train episode 56332: reward = 12.13, steps = 48 17:14:39 [INFO] train episode 56333: reward = 18.07, steps = 33 17:14:42 [INFO] train episode 56334: reward = 24.45, steps = 39 17:14:46 [INFO] train episode 56335: reward = 5.39, steps = 45 17:14:49 [INFO] train episode 56336: reward = -21.11, steps = 27 17:14:52 [INFO] train episode 56337: reward = -2.03, steps = 38 17:14:55 [INFO] train episode 56338: reward = -0.52, steps = 34 17:15:00 [INFO] train episode 56339: reward = 27.00, steps = 50 17:15:02 [INFO] train episode 56340: reward = 5.27, steps = 31 17:15:05 [INFO] train episode 56341: reward = 17.93, steps = 33 17:15:08 [INFO] train episode 56342: reward = 7.93, steps = 30 17:15:11 [INFO] train episode 56343: reward = 0.15, steps = 37 17:15:14 [INFO] train episode 56344: reward = 10.04, steps = 37 17:15:18 [INFO] train episode 56345: reward = 12.67, steps = 46 17:15:21 [INFO] train episode 56346: reward = 4.67, steps = 38 17:15:25 [INFO] train episode 56347: reward = -26.56, steps = 39 17:15:28 [INFO] train episode 56348: reward = 0.16, steps = 36 17:15:32 [INFO] train episode 56349: reward = 23.90, steps = 42 17:15:37 [INFO] train episode 56350: reward = -32.82, steps = 54 17:15:41 [INFO] train episode 56351: reward = 16.85, steps = 46 17:15:43 [INFO] train episode 56352: reward = -4.48, steps = 30 17:15:45 [INFO] train episode 56353: reward = -35.04, steps = 21 17:15:47 [INFO] train episode 56354: reward = -17.28, steps = 23 17:15:50 [INFO] train episode 56355: reward = -9.17, steps = 35 17:15:54 [INFO] train episode 56356: reward = 14.39, steps = 41 17:15:57 [INFO] train episode 56357: reward = 6.06, steps = 34 17:15:59 [INFO] train episode 56358: reward = -12.85, steps = 23 17:16:01 [INFO] train episode 56359: reward = -10.25, steps = 24 17:16:05 [INFO] train episode 56360: reward = 20.46, steps = 42 17:16:08 [INFO] train episode 56361: reward = 7.51, steps = 37 17:16:12 [INFO] train episode 56362: reward = 0.48, steps = 30 17:16:15 [INFO] train episode 56363: reward = 4.85, steps = 36 17:16:18 [INFO] train episode 56364: reward = 21.04, steps = 42 17:16:21 [INFO] train episode 56365: reward = -6.17, steps = 27 17:16:24 [INFO] train episode 56366: reward = 19.85, steps = 36 17:16:27 [INFO] train episode 56367: reward = 4.82, steps = 38 17:16:31 [INFO] train episode 56368: reward = 8.72, steps = 40 17:16:33 [INFO] train episode 56369: reward = -23.46, steps = 20 17:16:37 [INFO] train episode 56370: reward = 23.37, steps = 41 17:16:40 [INFO] train episode 56371: reward = -13.05, steps = 36 17:16:42 [INFO] train episode 56372: reward = -8.44, steps = 22 17:16:45 [INFO] train episode 56373: reward = 3.91, steps = 35 17:16:48 [INFO] train episode 56374: reward = 5.76, steps = 40 17:16:51 [INFO] train episode 56375: reward = 16.77, steps = 33 17:16:55 [INFO] train episode 56376: reward = 8.02, steps = 40 17:16:58 [INFO] train episode 56377: reward = 9.69, steps = 37 17:17:00 [INFO] train episode 56378: reward = -13.49, steps = 23 17:17:03 [INFO] train episode 56379: reward = 8.72, steps = 34 17:17:06 [INFO] train episode 56380: reward = 20.82, steps = 40 17:17:10 [INFO] train episode 56381: reward = 12.38, steps = 39 17:17:14 [INFO] train episode 56382: reward = 18.72, steps = 41 17:17:17 [INFO] train episode 56383: reward = 11.66, steps = 42 17:17:21 [INFO] train episode 56384: reward = 20.15, steps = 40 17:17:24 [INFO] train episode 56385: reward = 14.32, steps = 37 17:17:26 [INFO] train episode 56386: reward = -26.59, steps = 22 17:17:31 [INFO] train episode 56387: reward = 14.47, steps = 50 17:17:34 [INFO] train episode 56388: reward = 3.97, steps = 39 17:17:36 [INFO] train episode 56389: reward = -16.52, steps = 21 17:17:39 [INFO] train episode 56390: reward = 8.42, steps = 33 17:17:42 [INFO] train episode 56391: reward = 18.75, steps = 37 17:17:46 [INFO] train episode 56392: reward = -25.88, steps = 46 17:17:50 [INFO] train episode 56393: reward = 5.89, steps = 39 17:17:52 [INFO] train episode 56394: reward = -27.53, steps = 26 17:17:56 [INFO] train episode 56395: reward = 12.18, steps = 39 17:17:58 [INFO] train episode 56396: reward = -11.46, steps = 23 17:18:01 [INFO] train episode 56397: reward = 29.12, steps = 36 17:18:03 [INFO] train episode 56398: reward = -7.14, steps = 28 17:18:06 [INFO] train episode 56399: reward = 13.65, steps = 35 17:18:10 [INFO] train episode 56400: reward = 22.96, steps = 41 17:18:13 [INFO] train episode 56401: reward = 13.86, steps = 33 17:18:17 [INFO] train episode 56402: reward = 10.36, steps = 45 17:18:19 [INFO] train episode 56403: reward = -10.40, steps = 25 17:18:22 [INFO] train episode 56404: reward = 7.42, steps = 35 17:18:26 [INFO] train episode 56405: reward = 18.81, steps = 45 17:18:30 [INFO] train episode 56406: reward = 13.22, steps = 46 17:18:35 [INFO] train episode 56407: reward = 20.37, steps = 56 17:18:38 [INFO] train episode 56408: reward = 21.70, steps = 38 17:18:43 [INFO] train episode 56409: reward = 4.45, steps = 50 17:18:46 [INFO] train episode 56410: reward = 0.61, steps = 31 17:18:49 [INFO] train episode 56411: reward = 11.17, steps = 34 17:18:53 [INFO] train episode 56412: reward = 34.11, steps = 51 17:18:56 [INFO] train episode 56413: reward = 16.88, steps = 35 17:18:59 [INFO] train episode 56414: reward = -29.83, steps = 25 17:19:01 [INFO] train episode 56415: reward = -22.26, steps = 19 17:19:06 [INFO] train episode 56416: reward = 21.74, steps = 47 17:19:09 [INFO] train episode 56417: reward = 12.65, steps = 45 17:19:11 [INFO] train episode 56418: reward = -18.07, steps = 22 17:19:13 [INFO] train episode 56419: reward = -8.86, steps = 23 17:19:17 [INFO] train episode 56420: reward = 17.04, steps = 42 17:19:19 [INFO] train episode 56421: reward = -20.49, steps = 19 17:19:23 [INFO] train episode 56422: reward = 11.54, steps = 41 17:19:26 [INFO] train episode 56423: reward = 19.04, steps = 35 17:19:33 [INFO] train episode 56424: reward = -12.22, steps = 78 17:19:36 [INFO] train episode 56425: reward = -19.18, steps = 36 17:19:38 [INFO] train episode 56426: reward = -4.01, steps = 26 17:19:40 [INFO] train episode 56427: reward = -9.42, steps = 23 17:19:44 [INFO] train episode 56428: reward = 4.65, steps = 41 17:19:47 [INFO] train episode 56429: reward = 1.38, steps = 36 17:19:50 [INFO] train episode 56430: reward = 21.24, steps = 36 17:19:54 [INFO] train episode 56431: reward = 27.57, steps = 39 17:19:56 [INFO] train episode 56432: reward = -27.69, steps = 25 17:19:59 [INFO] train episode 56433: reward = 11.56, steps = 39 17:20:02 [INFO] train episode 56434: reward = 18.45, steps = 37 17:20:07 [INFO] train episode 56435: reward = 39.98, steps = 52 17:20:11 [INFO] train episode 56436: reward = 10.01, steps = 38 17:20:14 [INFO] train episode 56437: reward = 31.24, steps = 43 17:20:19 [INFO] train episode 56438: reward = 17.07, steps = 50 17:20:21 [INFO] train episode 56439: reward = -18.71, steps = 23 17:20:25 [INFO] train episode 56440: reward = 28.60, steps = 50 17:20:28 [INFO] train episode 56441: reward = 14.14, steps = 30 17:20:31 [INFO] train episode 56442: reward = 11.36, steps = 40 17:20:35 [INFO] train episode 56443: reward = 5.25, steps = 46 17:20:40 [INFO] train episode 56444: reward = 20.37, steps = 41 17:20:44 [INFO] train episode 56445: reward = 17.39, steps = 39 17:20:48 [INFO] train episode 56446: reward = 19.96, steps = 42 17:20:51 [INFO] train episode 56447: reward = 16.74, steps = 33 17:20:53 [INFO] train episode 56448: reward = -17.81, steps = 22 17:20:58 [INFO] train episode 56449: reward = 13.89, steps = 40 17:21:00 [INFO] train episode 56450: reward = -12.42, steps = 26 17:21:03 [INFO] train episode 56451: reward = -29.18, steps = 24 17:21:07 [INFO] train episode 56452: reward = 16.39, steps = 42 17:21:09 [INFO] train episode 56453: reward = -3.40, steps = 30 17:21:12 [INFO] train episode 56454: reward = -4.15, steps = 30 17:21:15 [INFO] train episode 56455: reward = -10.60, steps = 27 17:21:17 [INFO] train episode 56456: reward = -3.83, steps = 30 17:21:21 [INFO] train episode 56457: reward = 4.03, steps = 42 17:21:23 [INFO] train episode 56458: reward = -14.11, steps = 22 17:21:25 [INFO] train episode 56459: reward = -19.47, steps = 20 17:21:28 [INFO] train episode 56460: reward = 12.73, steps = 33 17:21:31 [INFO] train episode 56461: reward = 12.16, steps = 39 17:21:33 [INFO] train episode 56462: reward = -5.23, steps = 22 17:21:35 [INFO] train episode 56463: reward = -9.46, steps = 22 17:21:37 [INFO] train episode 56464: reward = -7.24, steps = 22 17:21:41 [INFO] train episode 56465: reward = 11.43, steps = 46 17:21:45 [INFO] train episode 56466: reward = 7.26, steps = 35 17:21:47 [INFO] train episode 56467: reward = -8.05, steps = 30 17:21:51 [INFO] train episode 56468: reward = 15.86, steps = 44 17:21:55 [INFO] train episode 56469: reward = 31.22, steps = 38 17:21:57 [INFO] train episode 56470: reward = 4.00, steps = 33 17:22:00 [INFO] train episode 56471: reward = 3.84, steps = 28 17:22:04 [INFO] train episode 56472: reward = 11.11, steps = 36 17:22:06 [INFO] train episode 56473: reward = -6.07, steps = 23 17:22:09 [INFO] train episode 56474: reward = 8.89, steps = 30 17:22:13 [INFO] train episode 56475: reward = 29.57, steps = 44 17:22:16 [INFO] train episode 56476: reward = 2.36, steps = 34 17:22:19 [INFO] train episode 56477: reward = 16.67, steps = 37 17:22:22 [INFO] train episode 56478: reward = -4.74, steps = 28 17:22:25 [INFO] train episode 56479: reward = 4.63, steps = 39 17:22:27 [INFO] train episode 56480: reward = -3.40, steps = 26 17:22:30 [INFO] train episode 56481: reward = 0.49, steps = 34 17:22:36 [INFO] train episode 56482: reward = -5.73, steps = 55 17:22:37 [INFO] train episode 56483: reward = -40.20, steps = 20 17:22:41 [INFO] train episode 56484: reward = 17.58, steps = 36 17:22:44 [INFO] train episode 56485: reward = 21.70, steps = 40 17:22:48 [INFO] train episode 56486: reward = 25.49, steps = 40 17:22:52 [INFO] train episode 56487: reward = 22.49, steps = 42 17:22:56 [INFO] train episode 56488: reward = 1.66, steps = 45 17:22:59 [INFO] train episode 56489: reward = 3.12, steps = 37 17:23:02 [INFO] train episode 56490: reward = 14.71, steps = 36 17:23:05 [INFO] train episode 56491: reward = 11.33, steps = 31 17:23:08 [INFO] train episode 56492: reward = 10.31, steps = 36 17:23:11 [INFO] train episode 56493: reward = 13.30, steps = 38 17:23:14 [INFO] train episode 56494: reward = 12.01, steps = 34 17:23:16 [INFO] train episode 56495: reward = -13.09, steps = 23 17:23:20 [INFO] train episode 56496: reward = -16.86, steps = 41 17:23:23 [INFO] train episode 56497: reward = 7.91, steps = 33 17:23:26 [INFO] train episode 56498: reward = -11.53, steps = 37 17:23:29 [INFO] train episode 56499: reward = 5.13, steps = 27 17:23:32 [INFO] train episode 56500: reward = 20.07, steps = 41 17:23:36 [INFO] train episode 56501: reward = 12.14, steps = 40 17:23:39 [INFO] train episode 56502: reward = 16.69, steps = 35 17:23:43 [INFO] train episode 56503: reward = 19.46, steps = 42 17:23:46 [INFO] train episode 56504: reward = 22.38, steps = 40 17:23:50 [INFO] train episode 56505: reward = -12.24, steps = 40 17:23:53 [INFO] train episode 56506: reward = 22.54, steps = 38 17:23:57 [INFO] train episode 56507: reward = 7.23, steps = 37 17:24:00 [INFO] train episode 56508: reward = 1.26, steps = 35 17:24:02 [INFO] train episode 56509: reward = -11.97, steps = 30 17:24:06 [INFO] train episode 56510: reward = 5.19, steps = 41 17:24:09 [INFO] train episode 56511: reward = 5.26, steps = 36 17:24:13 [INFO] train episode 56512: reward = 16.33, steps = 36 17:24:17 [INFO] train episode 56513: reward = 7.51, steps = 51 17:24:19 [INFO] train episode 56514: reward = -5.32, steps = 25 17:24:23 [INFO] train episode 56515: reward = -5.80, steps = 39 17:24:27 [INFO] train episode 56516: reward = -2.02, steps = 44 17:24:31 [INFO] train episode 56517: reward = 10.42, steps = 43 17:24:33 [INFO] train episode 56518: reward = -7.58, steps = 28 17:24:37 [INFO] train episode 56519: reward = 10.82, steps = 38 17:24:41 [INFO] train episode 56520: reward = -40.38, steps = 54 17:24:45 [INFO] train episode 56521: reward = -1.52, steps = 37 17:24:48 [INFO] train episode 56522: reward = 8.22, steps = 37 17:24:52 [INFO] train episode 56523: reward = 16.62, steps = 40 17:24:54 [INFO] train episode 56524: reward = -11.97, steps = 21 17:24:57 [INFO] train episode 56525: reward = -8.45, steps = 31 17:25:01 [INFO] train episode 56526: reward = 11.57, steps = 37 17:25:05 [INFO] train episode 56527: reward = 13.77, steps = 39 17:25:09 [INFO] train episode 56528: reward = 31.68, steps = 47 17:25:10 [INFO] train episode 56529: reward = -27.88, steps = 19 17:25:14 [INFO] train episode 56530: reward = 17.73, steps = 41 17:25:17 [INFO] train episode 56531: reward = -13.72, steps = 31 17:25:20 [INFO] train episode 56532: reward = 5.64, steps = 36 17:25:24 [INFO] train episode 56533: reward = -11.03, steps = 43 17:25:28 [INFO] train episode 56534: reward = 28.55, steps = 42 17:25:30 [INFO] train episode 56535: reward = -3.91, steps = 26 17:25:34 [INFO] train episode 56536: reward = 14.37, steps = 37 17:25:38 [INFO] train episode 56537: reward = 22.62, steps = 41 17:25:40 [INFO] train episode 56538: reward = -2.57, steps = 26 17:25:43 [INFO] train episode 56539: reward = -7.02, steps = 33 17:25:45 [INFO] train episode 56540: reward = -13.78, steps = 22 17:25:49 [INFO] train episode 56541: reward = 3.43, steps = 53 17:25:54 [INFO] train episode 56542: reward = 3.42, steps = 45 17:25:58 [INFO] train episode 56543: reward = 10.89, steps = 44 17:26:01 [INFO] train episode 56544: reward = 10.32, steps = 39 17:26:04 [INFO] train episode 56545: reward = -0.75, steps = 37 17:26:08 [INFO] train episode 56546: reward = 19.31, steps = 39 17:26:11 [INFO] train episode 56547: reward = -3.03, steps = 33 17:26:13 [INFO] train episode 56548: reward = -12.22, steps = 21 17:26:16 [INFO] train episode 56549: reward = 13.08, steps = 36 17:26:20 [INFO] train episode 56550: reward = 30.96, steps = 39 17:26:22 [INFO] train episode 56551: reward = -26.92, steps = 23 17:26:25 [INFO] train episode 56552: reward = -15.79, steps = 32 17:26:29 [INFO] train episode 56553: reward = 10.42, steps = 39 17:26:32 [INFO] train episode 56554: reward = 3.41, steps = 37 17:26:35 [INFO] train episode 56555: reward = 5.21, steps = 38 17:26:38 [INFO] train episode 56556: reward = 3.44, steps = 31 17:26:43 [INFO] train episode 56557: reward = 19.39, steps = 45 17:26:45 [INFO] train episode 56558: reward = -21.58, steps = 23 17:26:49 [INFO] train episode 56559: reward = 30.06, steps = 43 17:26:54 [INFO] train episode 56560: reward = 11.69, steps = 62 17:26:57 [INFO] train episode 56561: reward = 10.03, steps = 32 17:27:01 [INFO] train episode 56562: reward = 18.98, steps = 42 17:27:04 [INFO] train episode 56563: reward = 4.07, steps = 30 17:27:08 [INFO] train episode 56564: reward = 30.55, steps = 44 17:27:11 [INFO] train episode 56565: reward = -3.21, steps = 27 17:27:14 [INFO] train episode 56566: reward = -6.44, steps = 35 17:27:18 [INFO] train episode 56567: reward = 18.69, steps = 45 17:27:22 [INFO] train episode 56568: reward = 28.96, steps = 42 17:27:25 [INFO] train episode 56569: reward = -6.62, steps = 27 17:27:26 [INFO] train episode 56570: reward = -12.49, steps = 21 17:27:31 [INFO] train episode 56571: reward = -7.52, steps = 52 17:27:35 [INFO] train episode 56572: reward = 21.20, steps = 36 17:27:39 [INFO] train episode 56573: reward = 18.74, steps = 42 17:27:44 [INFO] train episode 56574: reward = 10.14, steps = 61 17:27:48 [INFO] train episode 56575: reward = 20.09, steps = 38 17:27:52 [INFO] train episode 56576: reward = 14.54, steps = 42 17:27:55 [INFO] train episode 56577: reward = 8.79, steps = 33 17:27:58 [INFO] train episode 56578: reward = 7.97, steps = 34 17:28:04 [INFO] train episode 56579: reward = -24.58, steps = 52 17:28:07 [INFO] train episode 56580: reward = -1.61, steps = 29 17:28:10 [INFO] train episode 56581: reward = 3.69, steps = 36 17:28:14 [INFO] train episode 56582: reward = 16.37, steps = 44 17:28:17 [INFO] train episode 56583: reward = 19.06, steps = 37 17:28:20 [INFO] train episode 56584: reward = -12.00, steps = 31 17:28:23 [INFO] train episode 56585: reward = -14.05, steps = 35 17:28:27 [INFO] train episode 56586: reward = 12.54, steps = 36 17:28:31 [INFO] train episode 56587: reward = 5.91, steps = 37 17:28:34 [INFO] train episode 56588: reward = 2.14, steps = 37 17:28:37 [INFO] train episode 56589: reward = 18.44, steps = 34 17:28:40 [INFO] train episode 56590: reward = 6.97, steps = 31 17:28:44 [INFO] train episode 56591: reward = -1.55, steps = 36 17:28:47 [INFO] train episode 56592: reward = -23.58, steps = 36 17:28:52 [INFO] train episode 56593: reward = 27.92, steps = 47 17:28:55 [INFO] train episode 56594: reward = 25.85, steps = 36 17:28:59 [INFO] train episode 56595: reward = 19.72, steps = 43 17:29:01 [INFO] train episode 56596: reward = -18.61, steps = 22 17:29:07 [INFO] train episode 56597: reward = 14.13, steps = 57 17:29:13 [INFO] train episode 56598: reward = 32.15, steps = 53 17:29:16 [INFO] train episode 56599: reward = 21.40, steps = 40 17:29:21 [INFO] train episode 56600: reward = 28.99, steps = 44 17:29:24 [INFO] train episode 56601: reward = -1.97, steps = 31 17:29:27 [INFO] train episode 56602: reward = 15.95, steps = 36 17:29:31 [INFO] train episode 56603: reward = 17.18, steps = 45 17:29:34 [INFO] train episode 56604: reward = -11.22, steps = 28 17:29:36 [INFO] train episode 56605: reward = -3.85, steps = 26 17:29:39 [INFO] train episode 56606: reward = -11.25, steps = 23 17:29:42 [INFO] train episode 56607: reward = 26.67, steps = 38 17:29:49 [INFO] train episode 56608: reward = 15.89, steps = 67 17:29:52 [INFO] train episode 56609: reward = 11.99, steps = 37 17:29:56 [INFO] train episode 56610: reward = 16.51, steps = 44 17:29:59 [INFO] train episode 56611: reward = 13.27, steps = 34 17:30:01 [INFO] train episode 56612: reward = -29.26, steps = 20 17:30:06 [INFO] train episode 56613: reward = 22.07, steps = 50 17:30:08 [INFO] train episode 56614: reward = -50.76, steps = 18 17:30:10 [INFO] train episode 56615: reward = -9.96, steps = 24 17:30:14 [INFO] train episode 56616: reward = 21.03, steps = 38 17:30:19 [INFO] train episode 56617: reward = 39.78, steps = 55 17:30:22 [INFO] train episode 56618: reward = 6.95, steps = 34 17:30:25 [INFO] train episode 56619: reward = 13.62, steps = 41 17:30:28 [INFO] train episode 56620: reward = -8.51, steps = 23 17:30:32 [INFO] train episode 56621: reward = 16.11, steps = 40 17:30:35 [INFO] train episode 56622: reward = 16.80, steps = 33 17:30:38 [INFO] train episode 56623: reward = -8.03, steps = 31 17:30:41 [INFO] train episode 56624: reward = -6.12, steps = 39 17:30:46 [INFO] train episode 56625: reward = 21.74, steps = 48 17:30:50 [INFO] train episode 56626: reward = -14.00, steps = 47 17:30:54 [INFO] train episode 56627: reward = 12.91, steps = 38 17:30:57 [INFO] train episode 56628: reward = 18.18, steps = 39 17:31:01 [INFO] train episode 56629: reward = -14.03, steps = 39 17:31:06 [INFO] train episode 56630: reward = 28.92, steps = 51 17:31:10 [INFO] train episode 56631: reward = -7.45, steps = 32 17:31:13 [INFO] train episode 56632: reward = 14.83, steps = 42 17:31:17 [INFO] train episode 56633: reward = 21.94, steps = 43 17:31:21 [INFO] train episode 56634: reward = 27.54, steps = 40 17:31:25 [INFO] train episode 56635: reward = 10.21, steps = 34 17:31:28 [INFO] train episode 56636: reward = 16.57, steps = 43 17:31:32 [INFO] train episode 56637: reward = 33.39, steps = 39 17:31:36 [INFO] train episode 56638: reward = 21.87, steps = 41 17:31:40 [INFO] train episode 56639: reward = 6.34, steps = 41 17:31:43 [INFO] train episode 56640: reward = 19.44, steps = 39 17:31:48 [INFO] train episode 56641: reward = 26.82, steps = 49 17:31:52 [INFO] train episode 56642: reward = 28.65, steps = 47 17:31:56 [INFO] train episode 56643: reward = 24.73, steps = 42 17:31:59 [INFO] train episode 56644: reward = 5.63, steps = 28 17:32:03 [INFO] train episode 56645: reward = 23.50, steps = 45 17:32:06 [INFO] train episode 56646: reward = -1.29, steps = 33 17:32:10 [INFO] train episode 56647: reward = 26.75, steps = 43 17:32:15 [INFO] train episode 56648: reward = 21.38, steps = 47 17:32:18 [INFO] train episode 56649: reward = 5.40, steps = 41 17:32:25 [INFO] train episode 56650: reward = -13.08, steps = 68 17:32:28 [INFO] train episode 56651: reward = -6.72, steps = 33 17:32:32 [INFO] train episode 56652: reward = 12.92, steps = 47 17:32:35 [INFO] train episode 56653: reward = 0.58, steps = 31 17:32:40 [INFO] train episode 56654: reward = 24.20, steps = 43 17:32:42 [INFO] train episode 56655: reward = -3.07, steps = 28 17:32:47 [INFO] train episode 56656: reward = 19.80, steps = 40 17:32:51 [INFO] train episode 56657: reward = 18.96, steps = 43 17:32:53 [INFO] train episode 56658: reward = -17.70, steps = 21 17:32:54 [INFO] train episode 56659: reward = -19.16, steps = 21 17:32:59 [INFO] train episode 56660: reward = 10.61, steps = 44 17:33:01 [INFO] train episode 56661: reward = -6.80, steps = 27 17:33:04 [INFO] train episode 56662: reward = -32.99, steps = 21 17:33:08 [INFO] train episode 56663: reward = 16.63, steps = 42 17:33:11 [INFO] train episode 56664: reward = 17.79, steps = 38 17:33:15 [INFO] train episode 56665: reward = 9.03, steps = 40 17:33:20 [INFO] train episode 56666: reward = 24.31, steps = 51 17:33:24 [INFO] train episode 56667: reward = 8.70, steps = 47 17:33:28 [INFO] train episode 56668: reward = 30.02, steps = 45 17:33:30 [INFO] train episode 56669: reward = -13.54, steps = 20 17:33:33 [INFO] train episode 56670: reward = 8.43, steps = 31 17:33:37 [INFO] train episode 56671: reward = -3.88, steps = 34 17:33:41 [INFO] train episode 56672: reward = 15.04, steps = 46 17:33:44 [INFO] train episode 56673: reward = 19.37, steps = 34 17:33:47 [INFO] train episode 56674: reward = -11.86, steps = 28 17:33:50 [INFO] train episode 56675: reward = 9.83, steps = 32 17:33:54 [INFO] train episode 56676: reward = 12.98, steps = 42 17:33:58 [INFO] train episode 56677: reward = 24.11, steps = 38 17:34:01 [INFO] train episode 56678: reward = 14.72, steps = 35 17:34:03 [INFO] train episode 56679: reward = -9.72, steps = 26 17:34:08 [INFO] train episode 56680: reward = 28.03, steps = 48 17:34:12 [INFO] train episode 56681: reward = 0.99, steps = 43 17:34:16 [INFO] train episode 56682: reward = 9.63, steps = 38 17:34:20 [INFO] train episode 56683: reward = 6.15, steps = 47 17:34:24 [INFO] train episode 56684: reward = 9.63, steps = 42 17:34:29 [INFO] train episode 56685: reward = 34.18, steps = 49 17:34:32 [INFO] train episode 56686: reward = 8.95, steps = 32 17:34:34 [INFO] train episode 56687: reward = -28.97, steps = 21 17:34:38 [INFO] train episode 56688: reward = 19.46, steps = 37 17:34:41 [INFO] train episode 56689: reward = 27.67, steps = 38 17:34:45 [INFO] train episode 56690: reward = 13.60, steps = 40 17:34:49 [INFO] train episode 56691: reward = 24.88, steps = 44 17:34:53 [INFO] train episode 56692: reward = 16.11, steps = 33 17:34:56 [INFO] train episode 56693: reward = 11.69, steps = 40 17:34:59 [INFO] train episode 56694: reward = -3.82, steps = 31 17:35:04 [INFO] train episode 56695: reward = 19.16, steps = 45 17:35:08 [INFO] train episode 56696: reward = 0.19, steps = 39 17:35:11 [INFO] train episode 56697: reward = 17.71, steps = 35 17:35:15 [INFO] train episode 56698: reward = 30.39, steps = 47 17:35:19 [INFO] train episode 56699: reward = 39.42, steps = 45 17:35:24 [INFO] train episode 56700: reward = 14.67, steps = 47 17:35:28 [INFO] train episode 56701: reward = 19.79, steps = 46 17:35:31 [INFO] train episode 56702: reward = -1.11, steps = 31 17:35:35 [INFO] train episode 56703: reward = 4.98, steps = 36 17:35:38 [INFO] train episode 56704: reward = 17.04, steps = 42 17:35:44 [INFO] train episode 56705: reward = 19.89, steps = 55 17:35:48 [INFO] train episode 56706: reward = 16.36, steps = 40 17:35:51 [INFO] train episode 56707: reward = -5.18, steps = 38 17:35:55 [INFO] train episode 56708: reward = 24.30, steps = 42 17:35:58 [INFO] train episode 56709: reward = 9.12, steps = 30 17:36:03 [INFO] train episode 56710: reward = 24.46, steps = 56 17:36:07 [INFO] train episode 56711: reward = 17.57, steps = 36 17:36:09 [INFO] train episode 56712: reward = 1.41, steps = 29 17:36:13 [INFO] train episode 56713: reward = 35.66, steps = 41 17:36:16 [INFO] train episode 56714: reward = -19.12, steps = 21 17:36:18 [INFO] train episode 56715: reward = 5.98, steps = 28 17:36:21 [INFO] train episode 56716: reward = 20.78, steps = 34 17:36:23 [INFO] train episode 56717: reward = 0.30, steps = 21 17:36:27 [INFO] train episode 56718: reward = 24.24, steps = 35 17:36:30 [INFO] train episode 56719: reward = 24.27, steps = 38 17:36:35 [INFO] train episode 56720: reward = 21.40, steps = 46 17:36:38 [INFO] train episode 56721: reward = 24.44, steps = 35 17:36:42 [INFO] train episode 56722: reward = 18.79, steps = 38 17:36:46 [INFO] train episode 56723: reward = 29.26, steps = 49 17:36:50 [INFO] train episode 56724: reward = 15.31, steps = 34 17:36:53 [INFO] train episode 56725: reward = 15.12, steps = 35 17:36:56 [INFO] train episode 56726: reward = 17.50, steps = 33 17:37:01 [INFO] train episode 56727: reward = 29.08, steps = 47 17:37:04 [INFO] train episode 56728: reward = 21.80, steps = 37 17:37:11 [INFO] train episode 56729: reward = 33.42, steps = 69 17:37:14 [INFO] train episode 56730: reward = -5.57, steps = 33 17:37:18 [INFO] train episode 56731: reward = 21.95, steps = 41 17:37:23 [INFO] train episode 56732: reward = -7.78, steps = 45 17:37:27 [INFO] train episode 56733: reward = 22.84, steps = 39 17:37:30 [INFO] train episode 56734: reward = 27.40, steps = 34 17:37:34 [INFO] train episode 56735: reward = 34.62, steps = 43 17:37:39 [INFO] train episode 56736: reward = 5.35, steps = 51 17:37:42 [INFO] train episode 56737: reward = 12.56, steps = 34 17:37:46 [INFO] train episode 56738: reward = 27.44, steps = 38 17:37:52 [INFO] train episode 56739: reward = 42.56, steps = 57 17:37:56 [INFO] train episode 56740: reward = 28.56, steps = 52 17:38:01 [INFO] train episode 56741: reward = 31.04, steps = 41 17:38:05 [INFO] train episode 56742: reward = 36.07, steps = 51 17:38:09 [INFO] train episode 56743: reward = 39.39, steps = 40 17:38:12 [INFO] train episode 56744: reward = 16.46, steps = 32 17:38:15 [INFO] train episode 56745: reward = 10.14, steps = 33 17:38:20 [INFO] train episode 56746: reward = 24.70, steps = 43 17:38:22 [INFO] train episode 56747: reward = -3.16, steps = 24 17:38:25 [INFO] train episode 56748: reward = 15.46, steps = 35 17:38:29 [INFO] train episode 56749: reward = 24.53, steps = 37 17:38:34 [INFO] train episode 56750: reward = 39.16, steps = 56 17:38:39 [INFO] train episode 56751: reward = 13.82, steps = 46 17:38:43 [INFO] train episode 56752: reward = 28.64, steps = 41 17:38:46 [INFO] train episode 56753: reward = -2.10, steps = 31 17:38:50 [INFO] train episode 56754: reward = 32.60, steps = 50 17:38:55 [INFO] train episode 56755: reward = 21.14, steps = 43 17:38:58 [INFO] train episode 56756: reward = 15.95, steps = 36 17:39:02 [INFO] train episode 56757: reward = 23.26, steps = 35 17:39:04 [INFO] train episode 56758: reward = 4.56, steps = 29 17:39:07 [INFO] train episode 56759: reward = -0.18, steps = 29 17:39:11 [INFO] train episode 56760: reward = 11.80, steps = 33 17:39:14 [INFO] train episode 56761: reward = 10.87, steps = 33 17:39:16 [INFO] train episode 56762: reward = -8.25, steps = 28 17:39:20 [INFO] train episode 56763: reward = 24.95, steps = 38 17:39:24 [INFO] train episode 56764: reward = 19.35, steps = 40 17:39:28 [INFO] train episode 56765: reward = 21.00, steps = 36 17:39:32 [INFO] train episode 56766: reward = 28.31, steps = 46 17:39:35 [INFO] train episode 56767: reward = 14.75, steps = 37 17:39:39 [INFO] train episode 56768: reward = 18.71, steps = 38 17:39:47 [INFO] train episode 56769: reward = -6.35, steps = 87 17:39:51 [INFO] train episode 56770: reward = 11.39, steps = 40 17:39:55 [INFO] train episode 56771: reward = 9.61, steps = 42 17:39:58 [INFO] train episode 56772: reward = -0.26, steps = 29 17:40:00 [INFO] train episode 56773: reward = -11.52, steps = 28 17:40:05 [INFO] train episode 56774: reward = 35.32, steps = 45 17:40:07 [INFO] train episode 56775: reward = 5.21, steps = 26 17:40:11 [INFO] train episode 56776: reward = 15.27, steps = 39 17:40:15 [INFO] train episode 56777: reward = 20.45, steps = 42 17:40:19 [INFO] train episode 56778: reward = 18.24, steps = 41 17:40:23 [INFO] train episode 56779: reward = 20.95, steps = 41 17:40:26 [INFO] train episode 56780: reward = -9.70, steps = 30 17:40:29 [INFO] train episode 56781: reward = 8.58, steps = 33 17:40:33 [INFO] train episode 56782: reward = 16.24, steps = 37 17:40:38 [INFO] train episode 56783: reward = 38.06, steps = 45 17:40:41 [INFO] train episode 56784: reward = 15.03, steps = 32 17:40:49 [INFO] train episode 56785: reward = -8.40, steps = 86 17:40:56 [INFO] train episode 56786: reward = 36.77, steps = 72 17:40:59 [INFO] train episode 56787: reward = -17.07, steps = 22 17:41:02 [INFO] train episode 56788: reward = 9.55, steps = 36 17:41:06 [INFO] train episode 56789: reward = 17.10, steps = 45 17:41:11 [INFO] train episode 56790: reward = 17.33, steps = 49 17:41:13 [INFO] train episode 56791: reward = 0.39, steps = 27 17:41:18 [INFO] train episode 56792: reward = 16.76, steps = 42 17:41:23 [INFO] train episode 56793: reward = 18.01, steps = 52 17:41:26 [INFO] train episode 56794: reward = 14.84, steps = 32 17:41:30 [INFO] train episode 56795: reward = 28.43, steps = 48 17:41:35 [INFO] train episode 56796: reward = 15.97, steps = 45 17:41:38 [INFO] train episode 56797: reward = 21.76, steps = 38 17:41:42 [INFO] train episode 56798: reward = 13.15, steps = 36 17:41:45 [INFO] train episode 56799: reward = 7.24, steps = 36 17:41:49 [INFO] train episode 56800: reward = 4.10, steps = 42 17:41:53 [INFO] train episode 56801: reward = 22.80, steps = 38 17:41:56 [INFO] train episode 56802: reward = 16.68, steps = 33 17:41:59 [INFO] train episode 56803: reward = 8.87, steps = 31 17:42:03 [INFO] train episode 56804: reward = 22.89, steps = 38 17:42:07 [INFO] train episode 56805: reward = 40.75, steps = 46 17:42:11 [INFO] train episode 56806: reward = -6.23, steps = 34 17:42:14 [INFO] train episode 56807: reward = 14.92, steps = 32 17:42:17 [INFO] train episode 56808: reward = 9.15, steps = 35 17:42:25 [INFO] train episode 56809: reward = 42.29, steps = 80 17:42:29 [INFO] train episode 56810: reward = 21.62, steps = 42 17:42:33 [INFO] train episode 56811: reward = 32.81, steps = 41 17:42:35 [INFO] train episode 56812: reward = -20.93, steps = 22 17:42:40 [INFO] train episode 56813: reward = 33.49, steps = 49 17:42:44 [INFO] train episode 56814: reward = 20.92, steps = 37 17:42:46 [INFO] train episode 56815: reward = -11.34, steps = 22 17:42:50 [INFO] train episode 56816: reward = 22.24, steps = 40 17:42:54 [INFO] train episode 56817: reward = 7.37, steps = 37 17:42:56 [INFO] train episode 56818: reward = -2.83, steps = 26 17:43:01 [INFO] train episode 56819: reward = 22.94, steps = 50 17:43:07 [INFO] train episode 56820: reward = 43.63, steps = 52 17:43:10 [INFO] train episode 56821: reward = 27.65, steps = 42 17:43:14 [INFO] train episode 56822: reward = 28.54, steps = 37 17:43:18 [INFO] train episode 56823: reward = 15.45, steps = 40 17:43:23 [INFO] train episode 56824: reward = -1.74, steps = 54 17:43:27 [INFO] train episode 56825: reward = 6.07, steps = 34 17:43:29 [INFO] train episode 56826: reward = -8.59, steps = 23 17:43:33 [INFO] train episode 56827: reward = 17.00, steps = 47 17:43:37 [INFO] train episode 56828: reward = 24.60, steps = 37 17:43:41 [INFO] train episode 56829: reward = 7.77, steps = 40 17:43:43 [INFO] train episode 56830: reward = 1.61, steps = 25 17:43:47 [INFO] train episode 56831: reward = -4.22, steps = 28 17:43:54 [INFO] train episode 56832: reward = 66.96, steps = 74 17:43:58 [INFO] train episode 56833: reward = 16.32, steps = 38 17:44:01 [INFO] train episode 56834: reward = 8.36, steps = 34 17:44:05 [INFO] train episode 56835: reward = 20.99, steps = 42 17:44:07 [INFO] train episode 56836: reward = -13.90, steps = 25 17:44:14 [INFO] train episode 56837: reward = -11.96, steps = 66 17:44:17 [INFO] train episode 56838: reward = 16.65, steps = 32 17:44:20 [INFO] train episode 56839: reward = 9.97, steps = 33 17:44:23 [INFO] train episode 56840: reward = 21.80, steps = 39 17:44:27 [INFO] train episode 56841: reward = 23.37, steps = 39 17:44:32 [INFO] train episode 56842: reward = 22.39, steps = 45 17:44:34 [INFO] train episode 56843: reward = -4.52, steps = 24 17:44:37 [INFO] train episode 56844: reward = 7.79, steps = 33 17:44:41 [INFO] train episode 56845: reward = 24.87, steps = 37 17:44:43 [INFO] train episode 56846: reward = -5.14, steps = 23 17:44:46 [INFO] train episode 56847: reward = 2.33, steps = 32 17:44:50 [INFO] train episode 56848: reward = 11.44, steps = 32 17:44:53 [INFO] train episode 56849: reward = 33.04, steps = 37 17:44:56 [INFO] train episode 56850: reward = 5.00, steps = 31 17:45:02 [INFO] train episode 56851: reward = 43.75, steps = 59 17:45:07 [INFO] train episode 56852: reward = 19.14, steps = 49 17:45:11 [INFO] train episode 56853: reward = 36.04, steps = 43 17:45:13 [INFO] train episode 56854: reward = -19.39, steps = 24 17:45:16 [INFO] train episode 56855: reward = -1.69, steps = 33 17:45:19 [INFO] train episode 56856: reward = -12.82, steps = 27 17:45:22 [INFO] train episode 56857: reward = 1.32, steps = 32 17:45:26 [INFO] train episode 56858: reward = 31.37, steps = 44 17:45:31 [INFO] train episode 56859: reward = 44.60, steps = 58 17:45:36 [INFO] train episode 56860: reward = 30.75, steps = 48 17:45:39 [INFO] train episode 56861: reward = -1.24, steps = 30 17:45:41 [INFO] train episode 56862: reward = -8.78, steps = 24 17:45:48 [INFO] train episode 56863: reward = 48.01, steps = 72 17:45:51 [INFO] train episode 56864: reward = 5.01, steps = 37 17:45:58 [INFO] train episode 56865: reward = 19.82, steps = 68 17:46:02 [INFO] train episode 56866: reward = 15.81, steps = 42 17:46:05 [INFO] train episode 56867: reward = 20.83, steps = 33 17:46:09 [INFO] train episode 56868: reward = 21.15, steps = 39 17:46:13 [INFO] train episode 56869: reward = 23.02, steps = 40 17:46:17 [INFO] train episode 56870: reward = 26.46, steps = 41 17:46:21 [INFO] train episode 56871: reward = 42.02, steps = 44 17:46:24 [INFO] train episode 56872: reward = 22.30, steps = 35 17:46:28 [INFO] train episode 56873: reward = 12.16, steps = 40 17:46:32 [INFO] train episode 56874: reward = 26.49, steps = 39 17:46:35 [INFO] train episode 56875: reward = 8.20, steps = 30 17:46:39 [INFO] train episode 56876: reward = 25.33, steps = 40 17:46:41 [INFO] train episode 56877: reward = -9.53, steps = 27 17:46:45 [INFO] train episode 56878: reward = 22.17, steps = 36 17:46:50 [INFO] train episode 56879: reward = 32.62, steps = 54 17:46:54 [INFO] train episode 56880: reward = 5.96, steps = 37 17:46:59 [INFO] train episode 56881: reward = -3.39, steps = 52 17:47:03 [INFO] train episode 56882: reward = -3.15, steps = 33 17:47:06 [INFO] train episode 56883: reward = 15.46, steps = 35 17:47:08 [INFO] train episode 56884: reward = -5.12, steps = 26 17:47:14 [INFO] train episode 56885: reward = 43.53, steps = 58 17:47:16 [INFO] train episode 56886: reward = -17.92, steps = 24 17:47:20 [INFO] train episode 56887: reward = 17.94, steps = 35 17:47:22 [INFO] train episode 56888: reward = -3.60, steps = 27 17:47:25 [INFO] train episode 56889: reward = 21.54, steps = 34 17:47:28 [INFO] train episode 56890: reward = -15.90, steps = 28 17:47:32 [INFO] train episode 56891: reward = 25.09, steps = 38 17:47:35 [INFO] train episode 56892: reward = 7.35, steps = 32 17:47:37 [INFO] train episode 56893: reward = 2.27, steps = 25 17:47:43 [INFO] train episode 56894: reward = -11.35, steps = 68 17:47:47 [INFO] train episode 56895: reward = 22.78, steps = 37 17:47:50 [INFO] train episode 56896: reward = -0.60, steps = 27 17:47:53 [INFO] train episode 56897: reward = 25.72, steps = 40 17:47:57 [INFO] train episode 56898: reward = 25.33, steps = 40 17:48:02 [INFO] train episode 56899: reward = 51.83, steps = 49 17:48:07 [INFO] train episode 56900: reward = 37.08, steps = 46 17:48:09 [INFO] train episode 56901: reward = 6.84, steps = 30 17:48:11 [INFO] train episode 56902: reward = -16.65, steps = 21 17:48:13 [INFO] train episode 56903: reward = -24.61, steps = 21 17:48:17 [INFO] train episode 56904: reward = 17.54, steps = 37 17:48:22 [INFO] train episode 56905: reward = 18.72, steps = 46 17:48:25 [INFO] train episode 56906: reward = 21.55, steps = 40 17:48:30 [INFO] train episode 56907: reward = 28.77, steps = 46 17:48:33 [INFO] train episode 56908: reward = 21.55, steps = 39 17:48:37 [INFO] train episode 56909: reward = 5.34, steps = 33 17:48:41 [INFO] train episode 56910: reward = 33.47, steps = 39 17:48:44 [INFO] train episode 56911: reward = 8.15, steps = 39 17:48:48 [INFO] train episode 56912: reward = 23.12, steps = 35 17:48:54 [INFO] train episode 56913: reward = 38.75, steps = 64 17:48:59 [INFO] train episode 56914: reward = 35.31, steps = 49 17:49:04 [INFO] train episode 56915: reward = 41.90, steps = 64 17:49:09 [INFO] train episode 56916: reward = 37.83, steps = 51 17:49:13 [INFO] train episode 56917: reward = 34.11, steps = 42 17:49:17 [INFO] train episode 56918: reward = 3.82, steps = 40 17:49:21 [INFO] train episode 56919: reward = 14.46, steps = 37 17:49:24 [INFO] train episode 56920: reward = 23.76, steps = 36 17:49:28 [INFO] train episode 56921: reward = 26.58, steps = 40 17:49:31 [INFO] train episode 56922: reward = 13.28, steps = 35 17:49:35 [INFO] train episode 56923: reward = 29.54, steps = 40 17:49:39 [INFO] train episode 56924: reward = 20.54, steps = 48 17:49:42 [INFO] train episode 56925: reward = 1.74, steps = 28 17:49:46 [INFO] train episode 56926: reward = 27.36, steps = 45 17:49:51 [INFO] train episode 56927: reward = 22.97, steps = 43 17:49:55 [INFO] train episode 56928: reward = 25.42, steps = 46 17:49:59 [INFO] train episode 56929: reward = 31.16, steps = 41 17:50:01 [INFO] train episode 56930: reward = -12.78, steps = 27 17:50:07 [INFO] train episode 56931: reward = 18.63, steps = 46 17:50:10 [INFO] train episode 56932: reward = 17.06, steps = 33 17:50:14 [INFO] train episode 56933: reward = 30.07, steps = 40 17:50:18 [INFO] train episode 56934: reward = 46.23, steps = 47 17:50:21 [INFO] train episode 56935: reward = -1.35, steps = 29 17:50:25 [INFO] train episode 56936: reward = 20.46, steps = 38 17:50:28 [INFO] train episode 56937: reward = 17.21, steps = 38 17:50:32 [INFO] train episode 56938: reward = 20.73, steps = 35 17:50:34 [INFO] train episode 56939: reward = 14.23, steps = 31 17:50:37 [INFO] train episode 56940: reward = 1.64, steps = 28 17:50:43 [INFO] train episode 56941: reward = 27.38, steps = 54 17:50:46 [INFO] train episode 56942: reward = 1.12, steps = 32 17:50:49 [INFO] train episode 56943: reward = 7.40, steps = 34 17:50:53 [INFO] train episode 56944: reward = 30.34, steps = 46 17:50:59 [INFO] train episode 56945: reward = 40.35, steps = 56 17:51:03 [INFO] train episode 56946: reward = 15.28, steps = 41 17:51:07 [INFO] train episode 56947: reward = 23.49, steps = 39 17:51:11 [INFO] train episode 56948: reward = 39.87, steps = 40 17:51:16 [INFO] train episode 56949: reward = 29.81, steps = 59 17:51:22 [INFO] train episode 56950: reward = 41.33, steps = 52 17:51:26 [INFO] train episode 56951: reward = 35.48, steps = 46 17:51:30 [INFO] train episode 56952: reward = 24.93, steps = 39 17:51:32 [INFO] train episode 56953: reward = -3.19, steps = 25 17:51:37 [INFO] train episode 56954: reward = 32.14, steps = 50 17:51:41 [INFO] train episode 56955: reward = 2.14, steps = 41 17:51:44 [INFO] train episode 56956: reward = 20.84, steps = 33 17:51:48 [INFO] train episode 56957: reward = 48.80, steps = 48 17:51:53 [INFO] train episode 56958: reward = 31.59, steps = 50 17:51:57 [INFO] train episode 56959: reward = 13.06, steps = 36 17:52:01 [INFO] train episode 56960: reward = 31.41, steps = 43 17:52:03 [INFO] train episode 56961: reward = -8.52, steps = 23 17:52:06 [INFO] train episode 56962: reward = 6.23, steps = 33 17:52:10 [INFO] train episode 56963: reward = 23.31, steps = 44 17:52:14 [INFO] train episode 56964: reward = -1.63, steps = 33 17:52:17 [INFO] train episode 56965: reward = 8.50, steps = 29 17:52:21 [INFO] train episode 56966: reward = 40.02, steps = 48 17:52:24 [INFO] train episode 56967: reward = 12.89, steps = 34 17:52:30 [INFO] train episode 56968: reward = 6.28, steps = 61 17:52:35 [INFO] train episode 56969: reward = 37.73, steps = 51 17:52:39 [INFO] train episode 56970: reward = 34.97, steps = 43 17:52:43 [INFO] train episode 56971: reward = 22.88, steps = 34 17:52:45 [INFO] train episode 56972: reward = -4.11, steps = 21 17:52:49 [INFO] train episode 56973: reward = 28.94, steps = 42 17:52:53 [INFO] train episode 56974: reward = 34.47, steps = 45 17:52:57 [INFO] train episode 56975: reward = 27.57, steps = 37 17:53:01 [INFO] train episode 56976: reward = 13.18, steps = 44 17:53:05 [INFO] train episode 56977: reward = 29.54, steps = 42 17:53:09 [INFO] train episode 56978: reward = 25.18, steps = 38 17:53:12 [INFO] train episode 56979: reward = -3.27, steps = 29 17:53:16 [INFO] train episode 56980: reward = 24.13, steps = 43 17:53:20 [INFO] train episode 56981: reward = 4.22, steps = 34 17:53:23 [INFO] train episode 56982: reward = 18.03, steps = 34 17:53:27 [INFO] train episode 56983: reward = 10.62, steps = 43 17:53:33 [INFO] train episode 56984: reward = 54.95, steps = 64 17:53:37 [INFO] train episode 56985: reward = 19.75, steps = 33 17:53:41 [INFO] train episode 56986: reward = 34.26, steps = 48 17:53:46 [INFO] train episode 56987: reward = 29.93, steps = 44 17:53:50 [INFO] train episode 56988: reward = 31.59, steps = 50 17:53:55 [INFO] train episode 56989: reward = 25.44, steps = 49 17:53:59 [INFO] train episode 56990: reward = 22.85, steps = 36 17:54:02 [INFO] train episode 56991: reward = 28.38, steps = 39 17:54:06 [INFO] train episode 56992: reward = 33.69, steps = 42 17:54:11 [INFO] train episode 56993: reward = 34.81, steps = 47 17:54:11 [INFO] ==== test ==== 17:54:16 [INFO] test episode 0: reward = 57.85, steps = 53 17:54:20 [INFO] test episode 1: reward = 57.74, steps = 46 17:54:25 [INFO] test episode 2: reward = 60.24, steps = 49 17:54:29 [INFO] test episode 3: reward = 47.78, steps = 43 17:54:34 [INFO] test episode 4: reward = 58.69, steps = 51 17:54:39 [INFO] test episode 5: reward = 54.30, steps = 52 17:54:43 [INFO] test episode 6: reward = 43.65, steps = 41 17:54:47 [INFO] test episode 7: reward = 46.35, steps = 44 17:54:52 [INFO] test episode 8: reward = 47.63, steps = 43 17:54:56 [INFO] test episode 9: reward = 60.35, steps = 50 17:55:00 [INFO] test episode 10: reward = 43.50, steps = 41 17:55:04 [INFO] test episode 11: reward = 53.07, steps = 48 17:55:10 [INFO] test episode 12: reward = 53.01, steps = 50 17:55:14 [INFO] test episode 13: reward = 57.56, steps = 46 17:55:18 [INFO] test episode 14: reward = 54.57, steps = 48 17:55:22 [INFO] test episode 15: reward = 56.61, steps = 45 17:55:27 [INFO] test episode 16: reward = 45.43, steps = 45 17:55:31 [INFO] test episode 17: reward = 54.87, steps = 49 17:55:36 [INFO] test episode 18: reward = 52.37, steps = 46 17:55:40 [INFO] test episode 19: reward = 48.89, steps = 45 17:55:45 [INFO] test episode 20: reward = 50.95, steps = 46 17:55:48 [INFO] test episode 21: reward = 41.83, steps = 38 17:55:53 [INFO] test episode 22: reward = 51.55, steps = 50 17:55:56 [INFO] test episode 23: reward = 18.65, steps = 26 17:56:00 [INFO] test episode 24: reward = 55.92, steps = 44 17:56:04 [INFO] test episode 25: reward = 42.88, steps = 41 17:56:08 [INFO] test episode 26: reward = 51.21, steps = 48 17:56:12 [INFO] test episode 27: reward = 44.29, steps = 40 17:56:15 [INFO] test episode 28: reward = 39.05, steps = 40 17:56:17 [INFO] test episode 29: reward = -3.19, steps = 18 17:56:22 [INFO] test episode 30: reward = 55.52, steps = 46 17:56:25 [INFO] test episode 31: reward = 37.64, steps = 38 17:56:29 [INFO] test episode 32: reward = 40.08, steps = 40 17:56:32 [INFO] test episode 33: reward = 40.58, steps = 39 17:56:36 [INFO] test episode 34: reward = 41.21, steps = 39 17:56:40 [INFO] test episode 35: reward = 37.37, steps = 38 17:56:44 [INFO] test episode 36: reward = 49.82, steps = 44 17:56:50 [INFO] test episode 37: reward = 60.86, steps = 59 17:56:55 [INFO] test episode 38: reward = 58.02, steps = 49 17:56:59 [INFO] test episode 39: reward = 47.28, steps = 43 17:57:03 [INFO] test episode 40: reward = 49.87, steps = 41 17:57:07 [INFO] test episode 41: reward = 55.73, steps = 43 17:57:10 [INFO] test episode 42: reward = 32.34, steps = 33 17:57:15 [INFO] test episode 43: reward = 49.71, steps = 45 17:57:18 [INFO] test episode 44: reward = 25.72, steps = 32 17:57:22 [INFO] test episode 45: reward = 54.97, steps = 45 17:57:25 [INFO] test episode 46: reward = 37.30, steps = 36 17:57:30 [INFO] test episode 47: reward = 48.77, steps = 46 17:57:35 [INFO] test episode 48: reward = 53.36, steps = 49 17:57:38 [INFO] test episode 49: reward = 48.62, steps = 43 17:57:42 [INFO] test episode 50: reward = 47.21, steps = 42 17:57:47 [INFO] test episode 51: reward = 61.10, steps = 53 17:57:52 [INFO] test episode 52: reward = 50.92, steps = 45 17:57:56 [INFO] test episode 53: reward = 42.70, steps = 42 17:57:59 [INFO] test episode 54: reward = 43.51, steps = 40 17:58:04 [INFO] test episode 55: reward = 57.91, steps = 50 17:58:10 [INFO] test episode 56: reward = 59.94, steps = 61 17:58:12 [INFO] test episode 57: reward = 9.68, steps = 25 17:58:17 [INFO] test episode 58: reward = 56.46, steps = 54 17:58:23 [INFO] test episode 59: reward = 60.39, steps = 57 17:58:27 [INFO] test episode 60: reward = 54.96, steps = 47 17:58:32 [INFO] test episode 61: reward = 50.84, steps = 50 17:58:35 [INFO] test episode 62: reward = 24.57, steps = 33 17:58:40 [INFO] test episode 63: reward = 55.59, steps = 49 17:58:45 [INFO] test episode 64: reward = 58.67, steps = 49 17:58:48 [INFO] test episode 65: reward = 43.93, steps = 38 17:58:51 [INFO] test episode 66: reward = 15.79, steps = 27 17:58:56 [INFO] test episode 67: reward = 63.04, steps = 60 17:59:00 [INFO] test episode 68: reward = 39.82, steps = 36 17:59:04 [INFO] test episode 69: reward = 52.81, steps = 45 17:59:09 [INFO] test episode 70: reward = 54.88, steps = 51 17:59:13 [INFO] test episode 71: reward = 42.42, steps = 38 17:59:16 [INFO] test episode 72: reward = 40.72, steps = 39 17:59:20 [INFO] test episode 73: reward = 39.36, steps = 38 17:59:24 [INFO] test episode 74: reward = 51.69, steps = 46 17:59:28 [INFO] test episode 75: reward = 48.78, steps = 41 17:59:32 [INFO] test episode 76: reward = 54.46, steps = 46 17:59:37 [INFO] test episode 77: reward = 51.22, steps = 45 17:59:41 [INFO] test episode 78: reward = 48.71, steps = 44 17:59:45 [INFO] test episode 79: reward = 51.07, steps = 45 17:59:50 [INFO] test episode 80: reward = 44.58, steps = 43 17:59:55 [INFO] test episode 81: reward = 53.71, steps = 49 17:59:59 [INFO] test episode 82: reward = 53.55, steps = 42 18:00:04 [INFO] test episode 83: reward = 60.92, steps = 53 18:00:08 [INFO] test episode 84: reward = 49.82, steps = 47 18:00:12 [INFO] test episode 85: reward = 45.92, steps = 39 18:00:16 [INFO] test episode 86: reward = 42.13, steps = 39 18:00:19 [INFO] test episode 87: reward = 37.70, steps = 37 18:00:23 [INFO] test episode 88: reward = 50.20, steps = 47 18:00:29 [INFO] test episode 89: reward = 53.45, steps = 56 18:00:34 [INFO] test episode 90: reward = 55.59, steps = 52 18:00:37 [INFO] test episode 91: reward = 44.08, steps = 37 18:00:41 [INFO] test episode 92: reward = 35.20, steps = 42 18:00:44 [INFO] test episode 93: reward = 24.29, steps = 29 18:00:49 [INFO] test episode 94: reward = 54.76, steps = 49 18:00:53 [INFO] test episode 95: reward = 47.90, steps = 42 18:00:57 [INFO] test episode 96: reward = 51.84, steps = 47 18:01:01 [INFO] test episode 97: reward = 50.97, steps = 46 18:01:06 [INFO] test episode 98: reward = 50.18, steps = 40 18:01:10 [INFO] test episode 99: reward = 54.06, steps = 47 18:01:10 [INFO] average episode reward = 47.66 ± 11.13
