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))
00:00:49 [INFO] ==== expert ==== 00:00:58 [INFO] expert episode 0: reward = 3636.76, steps = 1000 00:01:08 [INFO] expert episode 1: reward = 3584.22, steps = 1000 00:01:18 [INFO] expert episode 2: reward = 3582.76, steps = 1000 00:01:28 [INFO] expert episode 3: reward = 3641.40, steps = 1000 00:01:37 [INFO] expert episode 4: reward = 3581.67, steps = 1000 00:01:37 [INFO] average expert episode reward = 3605.36 ± 27.58 00:01:37 [INFO] ==== train ==== 00:01:38 [INFO] train episode 0: reward = -63.72, steps = 19 00:01:38 [INFO] train episode 1: reward = -79.26, steps = 18 00:01:38 [INFO] train episode 2: reward = -101.20, steps = 19 00:01:38 [INFO] train episode 3: reward = -121.00, steps = 21 00:01:38 [INFO] train episode 4: reward = -121.34, steps = 23 00:01:38 [INFO] train episode 5: reward = -105.25, steps = 20 00:01:38 [INFO] train episode 6: reward = -104.22, steps = 24 00:01:39 [INFO] train episode 7: reward = -110.07, steps = 18 00:01:39 [INFO] train episode 8: reward = -79.59, steps = 18 00:01:39 [INFO] train episode 9: reward = -86.04, steps = 18 00:01:39 [INFO] train episode 10: reward = -100.15, steps = 19 00:01:39 [INFO] train episode 11: reward = -92.21, steps = 19 00:01:39 [INFO] train episode 12: reward = -81.53, steps = 19 00:01:39 [INFO] train episode 13: reward = -55.47, steps = 17 00:01:39 [INFO] train episode 14: reward = -84.40, steps = 19 00:01:40 [INFO] train episode 15: reward = -75.52, steps = 22 00:01:40 [INFO] train episode 16: reward = -111.63, steps = 13 00:01:40 [INFO] train episode 17: reward = -88.16, steps = 18 00:01:40 [INFO] train episode 18: reward = -70.55, steps = 18 00:01:40 [INFO] train episode 19: reward = -74.66, steps = 19 00:01:40 [INFO] train episode 20: reward = -78.41, steps = 19 00:01:40 [INFO] train episode 21: reward = -128.64, steps = 20 00:01:41 [INFO] train episode 22: reward = -106.75, steps = 25 00:01:41 [INFO] train episode 23: reward = -78.14, steps = 13 00:01:41 [INFO] train episode 24: reward = -127.27, steps = 20 00:01:41 [INFO] train episode 25: reward = -122.89, steps = 20 00:01:41 [INFO] train episode 26: reward = -89.53, steps = 20 00:01:41 [INFO] train episode 27: reward = -67.32, steps = 20 00:01:41 [INFO] train episode 28: reward = -86.83, steps = 20 00:01:42 [INFO] train episode 29: reward = -118.94, steps = 27 00:01:42 [INFO] train episode 30: reward = -91.88, steps = 21 00:01:42 [INFO] train episode 31: reward = -100.63, steps = 21 00:01:42 [INFO] train episode 32: reward = -140.94, steps = 23 00:01:42 [INFO] train episode 33: reward = -79.66, steps = 17 00:01:42 [INFO] train episode 34: reward = -124.77, steps = 25 00:01:43 [INFO] train episode 35: reward = -94.10, steps = 19 00:01:43 [INFO] train episode 36: reward = -105.95, steps = 20 00:01:43 [INFO] train episode 37: reward = -56.11, steps = 17 00:01:43 [INFO] train episode 38: reward = -91.23, steps = 22 00:01:43 [INFO] train episode 39: reward = -85.03, steps = 20 00:01:43 [INFO] train episode 40: reward = -95.77, steps = 18 00:01:44 [INFO] train episode 41: reward = -164.06, steps = 38 00:01:44 [INFO] train episode 42: reward = -115.70, steps = 19 00:01:44 [INFO] train episode 43: reward = -95.29, steps = 20 00:01:44 [INFO] train episode 44: reward = -104.02, steps = 19 00:01:44 [INFO] train episode 45: reward = -68.41, steps = 20 00:01:44 [INFO] train episode 46: reward = -91.57, steps = 19 00:01:44 [INFO] train episode 47: reward = -85.19, steps = 18 00:01:45 [INFO] train episode 48: reward = -115.72, steps = 22 00:01:45 [INFO] train episode 49: reward = -79.27, steps = 19 00:01:45 [INFO] train episode 50: reward = -81.30, steps = 20 00:01:45 [INFO] train episode 51: reward = -133.22, steps = 18 00:01:45 [INFO] train episode 52: reward = -93.86, steps = 22 00:01:45 [INFO] train episode 53: reward = -96.73, steps = 21 00:01:45 [INFO] train episode 54: reward = -66.55, steps = 16 00:01:46 [INFO] train episode 55: reward = -87.76, steps = 19 00:01:46 [INFO] train episode 56: reward = -67.54, steps = 18 00:01:46 [INFO] train episode 57: reward = -91.42, steps = 21 00:01:46 [INFO] train episode 58: reward = -84.03, steps = 20 00:01:46 [INFO] train episode 59: reward = -65.17, steps = 18 00:01:46 [INFO] train episode 60: reward = -75.14, steps = 19 00:01:46 [INFO] train episode 61: reward = -99.50, steps = 20 00:01:47 [INFO] train episode 62: reward = -74.90, steps = 19 00:01:47 [INFO] train episode 63: reward = -113.58, steps = 18 00:01:47 [INFO] train episode 64: reward = -80.82, steps = 18 00:01:47 [INFO] train episode 65: reward = -83.79, steps = 17 00:01:47 [INFO] train episode 66: reward = -94.67, steps = 19 00:01:47 [INFO] train episode 67: reward = -84.05, steps = 19 00:01:47 [INFO] train episode 68: reward = -78.79, steps = 18 00:01:48 [INFO] train episode 69: reward = -107.73, steps = 17 00:01:48 [INFO] train episode 70: reward = -100.23, steps = 18 00:01:48 [INFO] train episode 71: reward = -94.50, steps = 19 00:01:48 [INFO] train episode 72: reward = -88.38, steps = 21 00:01:48 [INFO] train episode 73: reward = -87.46, steps = 18 00:01:48 [INFO] train episode 74: reward = -105.03, steps = 20 00:01:48 [INFO] train episode 75: reward = -101.33, steps = 21 00:01:49 [INFO] train episode 76: reward = -73.44, steps = 18 00:01:49 [INFO] train episode 77: reward = -89.39, steps = 20 00:01:49 [INFO] train episode 78: reward = -102.22, steps = 20 00:01:49 [INFO] train episode 79: reward = -72.76, steps = 19 00:01:49 [INFO] train episode 80: reward = -62.02, steps = 17 00:01:49 [INFO] train episode 81: reward = -67.44, steps = 21 00:01:49 [INFO] train episode 82: reward = -68.69, steps = 18 00:01:50 [INFO] train episode 83: reward = -95.63, steps = 21 00:01:50 [INFO] train episode 84: reward = -96.32, steps = 19 00:01:50 [INFO] train episode 85: reward = -63.78, steps = 18 00:01:50 [INFO] train episode 86: reward = -76.43, steps = 19 00:01:50 [INFO] train episode 87: reward = -87.74, steps = 19 00:01:50 [INFO] train episode 88: reward = -98.14, steps = 18 00:01:50 [INFO] train episode 89: reward = -90.91, steps = 18 00:01:51 [INFO] train episode 90: reward = -110.48, steps = 19 00:01:51 [INFO] train episode 91: reward = -92.45, steps = 21 00:01:51 [INFO] train episode 92: reward = -80.29, steps = 18 00:01:51 [INFO] train episode 93: reward = -100.84, steps = 25 00:01:51 [INFO] train episode 94: reward = -85.42, steps = 19 00:01:51 [INFO] train episode 95: reward = -81.76, steps = 20 00:01:51 [INFO] train episode 96: reward = -67.25, steps = 19 00:01:52 [INFO] train episode 97: reward = -99.35, steps = 19 00:01:52 [INFO] train episode 98: reward = -91.27, steps = 19 00:01:52 [INFO] train episode 99: reward = -71.53, steps = 19 00:01:52 [INFO] train episode 100: reward = -112.72, steps = 17 00:01:52 [INFO] train episode 101: reward = -114.19, steps = 22 00:01:53 [INFO] train episode 102: reward = -76.24, steps = 21 00:01:53 [INFO] train episode 103: reward = -74.61, steps = 18 00:01:53 [INFO] train episode 104: reward = -55.32, steps = 15 00:01:53 [INFO] train episode 105: reward = -98.36, steps = 18 00:01:53 [INFO] train episode 106: reward = -102.10, steps = 19 00:01:53 [INFO] train episode 107: reward = -65.78, steps = 17 00:01:53 [INFO] train episode 108: reward = -68.27, steps = 18 00:01:53 [INFO] train episode 109: reward = -65.36, steps = 18 00:01:54 [INFO] train episode 110: reward = -108.98, steps = 19 00:01:54 [INFO] train episode 111: reward = -121.80, steps = 22 00:01:54 [INFO] train episode 112: reward = -96.55, steps = 21 00:01:54 [INFO] train episode 113: reward = -74.04, steps = 20 00:01:54 [INFO] train episode 114: reward = -81.71, steps = 19 00:01:54 [INFO] train episode 115: reward = -93.27, steps = 18 00:01:54 [INFO] train episode 116: reward = -104.09, steps = 19 00:01:55 [INFO] train episode 117: reward = -60.36, steps = 21 00:01:55 [INFO] train episode 118: reward = -75.47, steps = 20 00:01:55 [INFO] train episode 119: reward = -87.60, steps = 19 00:01:55 [INFO] train episode 120: reward = -65.44, steps = 19 00:01:55 [INFO] train episode 121: reward = -80.27, steps = 19 00:01:55 [INFO] train episode 122: reward = -98.13, steps = 23 00:01:55 [INFO] train episode 123: reward = -116.50, steps = 31 00:01:56 [INFO] train episode 124: reward = -115.24, steps = 24 00:01:56 [INFO] train episode 125: reward = -97.93, steps = 20 00:01:56 [INFO] train episode 126: reward = -108.48, steps = 19 00:01:56 [INFO] train episode 127: reward = -90.57, steps = 19 00:01:56 [INFO] train episode 128: reward = -71.02, steps = 18 00:01:56 [INFO] train episode 129: reward = -88.75, steps = 19 00:01:56 [INFO] train episode 130: reward = -72.32, steps = 20 00:01:57 [INFO] train episode 131: reward = -107.86, steps = 23 00:01:57 [INFO] train episode 132: reward = -92.95, steps = 18 00:01:57 [INFO] train episode 133: reward = -62.91, steps = 18 00:01:57 [INFO] train episode 134: reward = -99.12, steps = 19 00:01:57 [INFO] train episode 135: reward = -72.98, steps = 18 00:01:57 [INFO] train episode 136: reward = -137.55, steps = 35 00:01:58 [INFO] train episode 137: reward = -86.44, steps = 20 00:01:58 [INFO] train episode 138: reward = -106.31, steps = 19 00:01:58 [INFO] train episode 139: reward = -76.52, steps = 18 00:01:58 [INFO] train episode 140: reward = -86.80, steps = 18 00:01:58 [INFO] train episode 141: reward = -81.92, steps = 20 00:01:58 [INFO] train episode 142: reward = -115.66, steps = 18 00:01:58 [INFO] train episode 143: reward = -79.19, steps = 18 00:01:58 [INFO] train episode 144: reward = -104.18, steps = 19 00:01:59 [INFO] train episode 145: reward = -51.30, steps = 19 00:01:59 [INFO] train episode 146: reward = -90.47, steps = 18 00:01:59 [INFO] train episode 147: reward = -120.87, steps = 25 00:01:59 [INFO] train episode 148: reward = -114.48, steps = 25 00:01:59 [INFO] train episode 149: reward = -63.68, steps = 17 00:01:59 [INFO] train episode 150: reward = -67.05, steps = 19 00:02:00 [INFO] train episode 151: reward = -79.55, steps = 21 00:02:00 [INFO] train episode 152: reward = -90.74, steps = 19 00:02:00 [INFO] train episode 153: reward = -83.85, steps = 20 00:02:00 [INFO] train episode 154: reward = -77.32, steps = 20 00:02:00 [INFO] train episode 155: reward = -83.28, steps = 19 00:02:00 [INFO] train episode 156: reward = -74.99, steps = 18 00:02:00 [INFO] train episode 157: reward = -89.08, steps = 20 00:02:01 [INFO] train episode 158: reward = -71.74, steps = 19 00:02:01 [INFO] train episode 159: reward = -88.26, steps = 21 00:02:01 [INFO] train episode 160: reward = -71.80, steps = 19 00:02:01 [INFO] train episode 161: reward = -76.66, steps = 20 00:02:01 [INFO] train episode 162: reward = -95.48, steps = 18 00:02:01 [INFO] train episode 163: reward = -95.68, steps = 20 00:02:01 [INFO] train episode 164: reward = -88.70, steps = 19 00:02:02 [INFO] train episode 165: reward = -91.93, steps = 18 00:02:02 [INFO] train episode 166: reward = -108.61, steps = 18 00:02:02 [INFO] train episode 167: reward = -102.56, steps = 19 00:02:02 [INFO] train episode 168: reward = -107.23, steps = 24 00:02:02 [INFO] train episode 169: reward = -101.88, steps = 25 00:02:02 [INFO] train episode 170: reward = -69.59, steps = 19 00:02:02 [INFO] train episode 171: reward = -94.55, steps = 20 00:02:03 [INFO] train episode 172: reward = -91.49, steps = 18 00:02:03 [INFO] train episode 173: reward = -68.64, steps = 18 00:02:03 [INFO] train episode 174: reward = -85.67, steps = 21 00:02:03 [INFO] train episode 175: reward = -68.59, steps = 20 00:02:03 [INFO] train episode 176: reward = -69.06, steps = 18 00:02:03 [INFO] train episode 177: reward = -97.02, steps = 19 00:02:03 [INFO] train episode 178: reward = -92.53, steps = 20 00:02:04 [INFO] train episode 179: reward = -87.18, steps = 19 00:02:04 [INFO] train episode 180: reward = -80.32, steps = 20 00:02:04 [INFO] train episode 181: reward = -73.56, steps = 18 00:02:04 [INFO] train episode 182: reward = -90.86, steps = 19 00:02:04 [INFO] train episode 183: reward = -76.78, steps = 20 00:02:04 [INFO] train episode 184: reward = -94.44, steps = 18 00:02:04 [INFO] train episode 185: reward = -68.18, steps = 20 00:02:05 [INFO] train episode 186: reward = -62.51, steps = 18 00:02:05 [INFO] train episode 187: reward = -102.78, steps = 24 00:02:05 [INFO] train episode 188: reward = -92.92, steps = 19 00:02:05 [INFO] train episode 189: reward = -59.77, steps = 19 00:02:05 [INFO] train episode 190: reward = -59.09, steps = 19 00:02:05 [INFO] train episode 191: reward = -97.27, steps = 18 00:02:05 [INFO] train episode 192: reward = -91.19, steps = 18 00:02:06 [INFO] train episode 193: reward = -72.68, steps = 19 00:02:06 [INFO] train episode 194: reward = -77.62, steps = 19 00:02:06 [INFO] train episode 195: reward = -104.17, steps = 26 00:02:06 [INFO] train episode 196: reward = -79.28, steps = 17 00:02:06 [INFO] train episode 197: reward = -101.34, steps = 19 00:02:06 [INFO] train episode 198: reward = -104.44, steps = 19 00:02:07 [INFO] train episode 199: reward = -71.19, steps = 18 00:02:07 [INFO] train episode 200: reward = -94.46, steps = 24 00:02:07 [INFO] train episode 201: reward = -69.68, steps = 20 00:02:07 [INFO] train episode 202: reward = -85.45, steps = 19 00:02:07 [INFO] train episode 203: reward = -107.02, steps = 20 00:02:07 [INFO] train episode 204: reward = -82.22, steps = 18 00:02:07 [INFO] train episode 205: reward = -75.52, steps = 20 00:02:08 [INFO] train episode 206: reward = -87.08, steps = 23 00:02:08 [INFO] train episode 207: reward = -79.33, steps = 16 00:02:08 [INFO] train episode 208: reward = -57.69, steps = 14 00:02:08 [INFO] train episode 209: reward = -85.29, steps = 19 00:02:08 [INFO] train episode 210: reward = -109.29, steps = 20 00:02:08 [INFO] train episode 211: reward = -71.29, steps = 19 00:02:08 [INFO] train episode 212: reward = -82.15, steps = 19 00:02:09 [INFO] train episode 213: reward = -85.33, steps = 19 00:02:09 [INFO] train episode 214: reward = -103.59, steps = 20 00:02:09 [INFO] train episode 215: reward = -74.83, steps = 19 00:02:09 [INFO] train episode 216: reward = -79.59, steps = 21 00:02:09 [INFO] train episode 217: reward = -121.60, steps = 19 00:02:09 [INFO] train episode 218: reward = -102.23, steps = 19 00:02:09 [INFO] train episode 219: reward = -94.18, steps = 19 00:02:10 [INFO] train episode 220: reward = -89.82, steps = 21 00:02:10 [INFO] train episode 221: reward = -125.16, steps = 24 00:02:10 [INFO] train episode 222: reward = -116.36, steps = 19 00:02:10 [INFO] train episode 223: reward = -100.24, steps = 15 00:02:10 [INFO] train episode 224: reward = -88.16, steps = 19 00:02:10 [INFO] train episode 225: reward = -67.30, steps = 20 00:02:10 [INFO] train episode 226: reward = -68.78, steps = 19 00:02:11 [INFO] train episode 227: reward = -67.04, steps = 19 00:02:11 [INFO] train episode 228: reward = -97.36, steps = 18 00:02:11 [INFO] train episode 229: reward = -89.86, steps = 18 00:02:11 [INFO] train episode 230: reward = -74.31, steps = 19 00:02:11 [INFO] train episode 231: reward = -78.24, steps = 20 00:02:11 [INFO] train episode 232: reward = -71.65, steps = 21 00:02:11 [INFO] train episode 233: reward = -94.61, steps = 19 00:02:12 [INFO] train episode 234: reward = -93.52, steps = 21 00:02:12 [INFO] train episode 235: reward = -95.88, steps = 20 00:02:12 [INFO] train episode 236: reward = -83.87, steps = 19 00:02:12 [INFO] train episode 237: reward = -82.61, steps = 20 00:02:12 [INFO] train episode 238: reward = -79.11, steps = 19 00:02:12 [INFO] train episode 239: reward = -132.11, steps = 29 00:02:12 [INFO] train episode 240: reward = -93.49, steps = 21 00:02:13 [INFO] train episode 241: reward = -98.48, steps = 20 00:02:13 [INFO] train episode 242: reward = -84.43, steps = 18 00:02:13 [INFO] train episode 243: reward = -76.14, steps = 19 00:02:13 [INFO] train episode 244: reward = -100.69, steps = 18 00:02:13 [INFO] train episode 245: reward = -108.71, steps = 27 00:02:13 [INFO] train episode 246: reward = -97.35, steps = 22 00:02:13 [INFO] train episode 247: reward = -118.45, steps = 18 00:02:14 [INFO] train episode 248: reward = -75.68, steps = 19 00:02:14 [INFO] train episode 249: reward = -104.66, steps = 20 00:02:14 [INFO] train episode 250: reward = -118.61, steps = 18 00:02:14 [INFO] train episode 251: reward = -92.43, steps = 17 00:02:14 [INFO] train episode 252: reward = -58.81, steps = 20 00:02:14 [INFO] train episode 253: reward = -81.58, steps = 18 00:02:14 [INFO] train episode 254: reward = -68.40, steps = 22 00:02:15 [INFO] train episode 255: reward = -122.72, steps = 18 00:02:15 [INFO] train episode 256: reward = -74.77, steps = 19 00:02:15 [INFO] train episode 257: reward = -95.61, steps = 21 00:02:15 [INFO] train episode 258: reward = -68.99, steps = 19 00:02:15 [INFO] train episode 259: reward = -95.21, steps = 19 00:02:15 [INFO] train episode 260: reward = -101.05, steps = 20 00:02:15 [INFO] train episode 261: reward = -71.32, steps = 20 00:02:16 [INFO] train episode 262: reward = -84.82, steps = 20 00:02:16 [INFO] train episode 263: reward = -72.77, steps = 18 00:02:16 [INFO] train episode 264: reward = -84.49, steps = 19 00:02:16 [INFO] train episode 265: reward = -101.34, steps = 19 00:02:16 [INFO] train episode 266: reward = -83.55, steps = 18 00:02:16 [INFO] train episode 267: reward = -79.61, steps = 18 00:02:16 [INFO] train episode 268: reward = -72.87, steps = 19 00:02:17 [INFO] train episode 269: reward = -66.43, steps = 19 00:02:17 [INFO] train episode 270: reward = -90.92, steps = 19 00:02:17 [INFO] train episode 271: reward = -106.38, steps = 20 00:02:17 [INFO] train episode 272: reward = -100.96, steps = 19 00:02:17 [INFO] train episode 273: reward = -104.60, steps = 18 00:02:17 [INFO] train episode 274: reward = -81.14, steps = 19 00:02:17 [INFO] train episode 275: reward = -99.40, steps = 19 00:02:18 [INFO] train episode 276: reward = -86.95, steps = 20 00:02:18 [INFO] train episode 277: reward = -71.35, steps = 20 00:02:18 [INFO] train episode 278: reward = -98.09, steps = 14 00:02:18 [INFO] train episode 279: reward = -118.92, steps = 24 00:02:18 [INFO] train episode 280: reward = -84.66, steps = 24 00:02:18 [INFO] train episode 281: reward = -92.10, steps = 18 00:02:18 [INFO] train episode 282: reward = -68.69, steps = 19 00:02:19 [INFO] train episode 283: reward = -107.23, steps = 28 00:02:19 [INFO] train episode 284: reward = -83.80, steps = 18 00:02:19 [INFO] train episode 285: reward = -101.59, steps = 19 00:02:19 [INFO] train episode 286: reward = -110.23, steps = 19 00:02:19 [INFO] train episode 287: reward = -84.10, steps = 18 00:02:19 [INFO] train episode 288: reward = -95.31, steps = 20 00:02:20 [INFO] train episode 289: reward = -89.92, steps = 20 00:02:20 [INFO] train episode 290: reward = -102.70, steps = 19 00:02:20 [INFO] train episode 291: reward = -87.66, steps = 19 00:02:20 [INFO] train episode 292: reward = -85.52, steps = 19 00:02:20 [INFO] train episode 293: reward = -145.41, steps = 23 00:02:20 [INFO] train episode 294: reward = -88.11, steps = 20 00:02:21 [INFO] train episode 295: reward = -96.29, steps = 24 00:02:21 [INFO] train episode 296: reward = -99.49, steps = 19 00:02:21 [INFO] train episode 297: reward = -83.90, steps = 19 00:02:21 [INFO] train episode 298: reward = -69.19, steps = 18 00:02:21 [INFO] train episode 299: reward = -73.95, steps = 19 00:02:21 [INFO] train episode 300: reward = -114.53, steps = 22 00:02:22 [INFO] train episode 301: reward = -93.72, steps = 22 00:02:22 [INFO] train episode 302: reward = -68.95, steps = 19 00:02:22 [INFO] train episode 303: reward = -97.68, steps = 18 00:02:22 [INFO] train episode 304: reward = -80.17, steps = 18 00:02:22 [INFO] train episode 305: reward = -95.32, steps = 19 00:02:22 [INFO] train episode 306: reward = -72.93, steps = 19 00:02:22 [INFO] train episode 307: reward = -68.63, steps = 18 00:02:22 [INFO] train episode 308: reward = -90.66, steps = 20 00:02:23 [INFO] train episode 309: reward = -69.68, steps = 19 00:02:23 [INFO] train episode 310: reward = -84.93, steps = 20 00:02:23 [INFO] train episode 311: reward = -113.95, steps = 19 00:02:23 [INFO] train episode 312: reward = -77.39, steps = 19 00:02:23 [INFO] train episode 313: reward = -66.09, steps = 18 00:02:23 [INFO] train episode 314: reward = -80.06, steps = 19 00:02:23 [INFO] train episode 315: reward = -80.00, steps = 19 00:02:24 [INFO] train episode 316: reward = -66.53, steps = 18 00:02:24 [INFO] train episode 317: reward = -81.58, steps = 18 00:02:24 [INFO] train episode 318: reward = -135.00, steps = 28 00:02:24 [INFO] train episode 319: reward = -99.00, steps = 19 00:02:24 [INFO] train episode 320: reward = -91.45, steps = 20 00:02:24 [INFO] train episode 321: reward = -98.88, steps = 18 00:02:24 [INFO] train episode 322: reward = -87.81, steps = 21 00:02:25 [INFO] train episode 323: reward = -98.90, steps = 19 00:02:25 [INFO] train episode 324: reward = -74.62, steps = 19 00:02:25 [INFO] train episode 325: reward = -73.98, steps = 20 00:02:25 [INFO] train episode 326: reward = -82.31, steps = 20 00:02:25 [INFO] train episode 327: reward = -78.89, steps = 18 00:02:25 [INFO] train episode 328: reward = -76.93, steps = 19 00:02:25 [INFO] train episode 329: reward = -88.72, steps = 21 00:02:26 [INFO] train episode 330: reward = -82.51, steps = 19 00:02:26 [INFO] train episode 331: reward = -81.78, steps = 19 00:02:26 [INFO] train episode 332: reward = -63.23, steps = 20 00:02:26 [INFO] train episode 333: reward = -83.29, steps = 20 00:02:26 [INFO] train episode 334: reward = -121.66, steps = 19 00:02:26 [INFO] train episode 335: reward = -70.82, steps = 19 00:02:26 [INFO] train episode 336: reward = -87.60, steps = 18 00:02:27 [INFO] train episode 337: reward = -75.80, steps = 20 00:02:27 [INFO] train episode 338: reward = -77.91, steps = 19 00:02:27 [INFO] train episode 339: reward = -85.26, steps = 17 00:02:27 [INFO] train episode 340: reward = -90.55, steps = 18 00:02:27 [INFO] train episode 341: reward = -68.81, steps = 20 00:02:27 [INFO] train episode 342: reward = -89.16, steps = 20 00:02:27 [INFO] train episode 343: reward = -87.82, steps = 19 00:02:28 [INFO] train episode 344: reward = -81.47, steps = 17 00:02:28 [INFO] train episode 345: reward = -73.42, steps = 20 00:02:28 [INFO] train episode 346: reward = -67.23, steps = 20 00:02:28 [INFO] train episode 347: reward = -107.59, steps = 23 00:02:28 [INFO] train episode 348: reward = -65.44, steps = 18 00:02:28 [INFO] train episode 349: reward = -89.56, steps = 19 00:02:28 [INFO] train episode 350: reward = -104.99, steps = 27 00:02:29 [INFO] train episode 351: reward = -73.80, steps = 19 00:02:29 [INFO] train episode 352: reward = -72.22, steps = 21 00:02:29 [INFO] train episode 353: reward = -95.00, steps = 20 00:02:29 [INFO] train episode 354: reward = -73.50, steps = 19 00:02:29 [INFO] train episode 355: reward = -90.15, steps = 18 00:02:29 [INFO] train episode 356: reward = -88.00, steps = 22 00:02:29 [INFO] train episode 357: reward = -88.69, steps = 23 00:02:30 [INFO] train episode 358: reward = -80.03, steps = 20 00:02:30 [INFO] train episode 359: reward = -72.71, steps = 19 00:02:30 [INFO] train episode 360: reward = -79.44, steps = 18 00:02:30 [INFO] train episode 361: reward = -83.62, steps = 18 00:02:30 [INFO] train episode 362: reward = -75.27, steps = 20 00:02:30 [INFO] train episode 363: reward = -81.17, steps = 19 00:02:30 [INFO] train episode 364: reward = -97.04, steps = 20 00:02:31 [INFO] train episode 365: reward = -109.19, steps = 18 00:02:31 [INFO] train episode 366: reward = -107.02, steps = 20 00:02:31 [INFO] train episode 367: reward = -79.94, steps = 20 00:02:31 [INFO] train episode 368: reward = -90.88, steps = 18 00:02:31 [INFO] train episode 369: reward = -65.40, steps = 19 00:02:31 [INFO] train episode 370: reward = -103.56, steps = 19 00:02:31 [INFO] train episode 371: reward = -83.35, steps = 19 00:02:32 [INFO] train episode 372: reward = -84.95, steps = 19 00:02:32 [INFO] train episode 373: reward = -81.42, steps = 18 00:02:32 [INFO] train episode 374: reward = -87.09, steps = 17 00:02:32 [INFO] train episode 375: reward = -81.66, steps = 23 00:02:32 [INFO] train episode 376: reward = -106.91, steps = 19 00:02:32 [INFO] train episode 377: reward = -117.74, steps = 19 00:02:32 [INFO] train episode 378: reward = -112.21, steps = 19 00:02:33 [INFO] train episode 379: reward = -78.14, steps = 18 00:02:33 [INFO] train episode 380: reward = -78.29, steps = 20 00:02:33 [INFO] train episode 381: reward = -95.02, steps = 20 00:02:33 [INFO] train episode 382: reward = -65.45, steps = 19 00:02:33 [INFO] train episode 383: reward = -64.49, steps = 20 00:02:33 [INFO] train episode 384: reward = -82.38, steps = 20 00:02:33 [INFO] train episode 385: reward = -82.72, steps = 20 00:02:34 [INFO] train episode 386: reward = -126.76, steps = 19 00:02:34 [INFO] train episode 387: reward = -73.83, steps = 18 00:02:34 [INFO] train episode 388: reward = -62.43, steps = 20 00:02:34 [INFO] train episode 389: reward = -86.17, steps = 19 00:02:34 [INFO] train episode 390: reward = -91.79, steps = 19 00:02:35 [INFO] train episode 391: reward = -126.29, steps = 23 00:02:35 [INFO] train episode 392: reward = -89.60, steps = 25 00:02:35 [INFO] train episode 393: reward = -95.39, steps = 19 00:02:35 [INFO] train episode 394: reward = -78.33, steps = 19 00:02:35 [INFO] train episode 395: reward = -98.86, steps = 19 00:02:35 [INFO] train episode 396: reward = -58.89, steps = 20 00:02:36 [INFO] train episode 397: reward = -111.34, steps = 29 00:02:36 [INFO] train episode 398: reward = -88.26, steps = 20 00:02:36 [INFO] train episode 399: reward = -81.94, steps = 18 00:02:36 [INFO] train episode 400: reward = -83.91, steps = 20 00:02:36 [INFO] train episode 401: reward = -94.56, steps = 20 00:02:36 [INFO] train episode 402: reward = -86.64, steps = 23 00:02:36 [INFO] train episode 403: reward = -85.86, steps = 26 00:02:37 [INFO] train episode 404: reward = -69.18, steps = 19 00:02:37 [INFO] train episode 405: reward = -84.11, steps = 20 00:02:37 [INFO] train episode 406: reward = -69.81, steps = 24 00:02:37 [INFO] train episode 407: reward = -81.02, steps = 19 00:02:37 [INFO] train episode 408: reward = -132.51, steps = 27 00:02:37 [INFO] train episode 409: reward = -70.15, steps = 21 00:02:37 [INFO] train episode 410: reward = -79.36, steps = 18 00:02:38 [INFO] train episode 411: reward = -94.19, steps = 23 00:02:38 [INFO] train episode 412: reward = -59.94, steps = 18 00:02:38 [INFO] train episode 413: reward = -66.08, steps = 19 00:02:38 [INFO] train episode 414: reward = -89.18, steps = 19 00:02:38 [INFO] train episode 415: reward = -99.71, steps = 18 00:02:38 [INFO] train episode 416: reward = -83.45, steps = 19 00:02:38 [INFO] train episode 417: reward = -81.04, steps = 18 00:02:39 [INFO] train episode 418: reward = -71.37, steps = 21 00:02:39 [INFO] train episode 419: reward = -96.53, steps = 20 00:02:39 [INFO] train episode 420: reward = -72.07, steps = 19 00:02:39 [INFO] train episode 421: reward = -103.68, steps = 20 00:02:39 [INFO] train episode 422: reward = -76.01, steps = 18 00:02:39 [INFO] train episode 423: reward = -109.06, steps = 28 00:02:40 [INFO] train episode 424: reward = -91.69, steps = 19 00:02:40 [INFO] train episode 425: reward = -96.56, steps = 20 00:02:40 [INFO] train episode 426: reward = -63.67, steps = 19 00:02:40 [INFO] train episode 427: reward = -93.00, steps = 20 00:02:40 [INFO] train episode 428: reward = -98.19, steps = 22 00:02:40 [INFO] train episode 429: reward = -87.65, steps = 19 00:02:40 [INFO] train episode 430: reward = -83.71, steps = 20 00:02:41 [INFO] train episode 431: reward = -113.58, steps = 22 00:02:41 [INFO] train episode 432: reward = -83.07, steps = 24 00:02:41 [INFO] train episode 433: reward = -78.36, steps = 19 00:02:41 [INFO] train episode 434: reward = -78.33, steps = 20 00:02:41 [INFO] train episode 435: reward = -108.74, steps = 19 00:02:41 [INFO] train episode 436: reward = -80.92, steps = 20 00:02:41 [INFO] train episode 437: reward = -90.37, steps = 17 00:02:42 [INFO] train episode 438: reward = -80.80, steps = 17 00:02:42 [INFO] train episode 439: reward = -84.49, steps = 20 00:02:42 [INFO] train episode 440: reward = -80.96, steps = 24 00:02:42 [INFO] train episode 441: reward = -66.54, steps = 22 00:02:42 [INFO] train episode 442: reward = -63.17, steps = 18 00:02:42 [INFO] train episode 443: reward = -90.54, steps = 22 00:02:42 [INFO] train episode 444: reward = -71.64, steps = 16 00:02:43 [INFO] train episode 445: reward = -96.30, steps = 20 00:02:43 [INFO] train episode 446: reward = -108.29, steps = 20 00:02:43 [INFO] train episode 447: reward = -99.40, steps = 19 00:02:43 [INFO] train episode 448: reward = -95.01, steps = 20 00:02:43 [INFO] train episode 449: reward = -81.41, steps = 20 00:02:43 [INFO] train episode 450: reward = -72.56, steps = 20 00:02:43 [INFO] train episode 451: reward = -114.87, steps = 21 00:02:44 [INFO] train episode 452: reward = -75.76, steps = 20 00:02:44 [INFO] train episode 453: reward = -84.48, steps = 21 00:02:44 [INFO] train episode 454: reward = -68.78, steps = 18 00:02:44 [INFO] train episode 455: reward = -90.05, steps = 22 00:02:44 [INFO] train episode 456: reward = -48.07, steps = 19 00:02:44 [INFO] train episode 457: reward = -70.61, steps = 19 00:02:44 [INFO] train episode 458: reward = -85.84, steps = 19 00:02:45 [INFO] train episode 459: reward = -64.90, steps = 19 00:02:45 [INFO] train episode 460: reward = -97.38, steps = 20 00:02:45 [INFO] train episode 461: reward = -93.98, steps = 18 00:02:45 [INFO] train episode 462: reward = -81.00, steps = 19 00:02:45 [INFO] train episode 463: reward = -77.34, steps = 19 00:02:45 [INFO] train episode 464: reward = -91.45, steps = 21 00:02:45 [INFO] train episode 465: reward = -92.84, steps = 22 00:02:46 [INFO] train episode 466: reward = -99.27, steps = 20 00:02:46 [INFO] train episode 467: reward = -85.73, steps = 22 00:02:46 [INFO] train episode 468: reward = -106.49, steps = 19 00:02:46 [INFO] train episode 469: reward = -91.37, steps = 21 00:02:46 [INFO] train episode 470: reward = -133.00, steps = 25 00:02:46 [INFO] train episode 471: reward = -70.98, steps = 19 00:02:47 [INFO] train episode 472: reward = -95.64, steps = 21 00:02:47 [INFO] train episode 473: reward = -68.61, steps = 19 00:02:47 [INFO] train episode 474: reward = -76.81, steps = 19 00:02:47 [INFO] train episode 475: reward = -68.17, steps = 19 00:02:47 [INFO] train episode 476: reward = -77.78, steps = 19 00:02:47 [INFO] train episode 477: reward = -88.22, steps = 18 00:02:47 [INFO] train episode 478: reward = -77.17, steps = 19 00:02:48 [INFO] train episode 479: reward = -89.16, steps = 19 00:02:48 [INFO] train episode 480: reward = -94.59, steps = 18 00:02:48 [INFO] train episode 481: reward = -118.34, steps = 21 00:02:48 [INFO] train episode 482: reward = -68.34, steps = 19 00:02:48 [INFO] train episode 483: reward = -73.69, steps = 19 00:02:48 [INFO] train episode 484: reward = -69.84, steps = 18 00:02:49 [INFO] train episode 485: reward = -69.72, steps = 19 00:02:49 [INFO] train episode 486: reward = -96.21, steps = 20 00:02:49 [INFO] train episode 487: reward = -77.51, steps = 19 00:02:49 [INFO] train episode 488: reward = -93.45, steps = 26 00:02:49 [INFO] train episode 489: reward = -66.70, steps = 20 00:02:49 [INFO] train episode 490: reward = -78.05, steps = 20 00:02:50 [INFO] train episode 491: reward = -102.47, steps = 20 00:02:50 [INFO] train episode 492: reward = -74.67, steps = 19 00:02:50 [INFO] train episode 493: reward = -98.99, steps = 20 00:02:50 [INFO] train episode 494: reward = -122.12, steps = 22 00:02:50 [INFO] train episode 495: reward = -106.54, steps = 21 00:02:50 [INFO] train episode 496: reward = -87.65, steps = 19 00:02:50 [INFO] train episode 497: reward = -87.64, steps = 18 00:02:51 [INFO] train episode 498: reward = -91.28, steps = 20 00:02:51 [INFO] train episode 499: reward = -78.95, steps = 18 00:02:51 [INFO] train episode 500: reward = -69.61, steps = 21 00:02:51 [INFO] train episode 501: reward = -90.35, steps = 18 00:02:51 [INFO] train episode 502: reward = -83.10, steps = 18 00:02:51 [INFO] train episode 503: reward = -73.28, steps = 19 00:02:51 [INFO] train episode 504: reward = -92.62, steps = 19 00:02:52 [INFO] train episode 505: reward = -110.33, steps = 21 00:02:52 [INFO] train episode 506: reward = -106.37, steps = 23 00:02:52 [INFO] train episode 507: reward = -68.65, steps = 19 00:02:52 [INFO] train episode 508: reward = -73.84, steps = 18 00:02:52 [INFO] train episode 509: reward = -94.13, steps = 16 00:02:52 [INFO] train episode 510: reward = -115.74, steps = 20 00:02:52 [INFO] train episode 511: reward = -117.01, steps = 26 00:02:53 [INFO] train episode 512: reward = -95.08, steps = 19 00:02:53 [INFO] train episode 513: reward = -73.15, steps = 19 00:02:53 [INFO] train episode 514: reward = -84.90, steps = 19 00:02:53 [INFO] train episode 515: reward = -100.65, steps = 21 00:02:53 [INFO] train episode 516: reward = -100.94, steps = 18 00:02:53 [INFO] train episode 517: reward = -60.62, steps = 19 00:02:53 [INFO] train episode 518: reward = -100.36, steps = 18 00:02:54 [INFO] train episode 519: reward = -76.81, steps = 20 00:02:54 [INFO] train episode 520: reward = -97.41, steps = 18 00:02:54 [INFO] train episode 521: reward = -112.22, steps = 21 00:02:54 [INFO] train episode 522: reward = -69.95, steps = 19 00:02:54 [INFO] train episode 523: reward = -58.63, steps = 20 00:02:54 [INFO] train episode 524: reward = -99.24, steps = 20 00:02:54 [INFO] train episode 525: reward = -82.06, steps = 20 00:02:55 [INFO] train episode 526: reward = -119.16, steps = 29 00:02:55 [INFO] train episode 527: reward = -93.04, steps = 18 00:02:55 [INFO] train episode 528: reward = -77.84, steps = 20 00:02:55 [INFO] train episode 529: reward = -86.02, steps = 19 00:02:55 [INFO] train episode 530: reward = -130.92, steps = 23 00:02:55 [INFO] train episode 531: reward = -91.26, steps = 18 00:02:56 [INFO] train episode 532: reward = -142.22, steps = 27 00:02:56 [INFO] train episode 533: reward = -61.67, steps = 19 00:02:56 [INFO] train episode 534: reward = -88.48, steps = 19 00:02:56 [INFO] train episode 535: reward = -64.32, steps = 19 00:02:56 [INFO] train episode 536: reward = -74.48, steps = 18 00:02:56 [INFO] train episode 537: reward = -95.96, steps = 18 00:02:56 [INFO] train episode 538: reward = -80.39, steps = 19 00:02:57 [INFO] train episode 539: reward = -72.11, steps = 21 00:02:57 [INFO] train episode 540: reward = -80.65, steps = 19 00:02:57 [INFO] train episode 541: reward = -93.59, steps = 21 00:02:57 [INFO] train episode 542: reward = -119.47, steps = 24 00:02:57 [INFO] train episode 543: reward = -91.61, steps = 24 00:02:57 [INFO] train episode 544: reward = -74.12, steps = 19 00:02:57 [INFO] train episode 545: reward = -85.23, steps = 20 00:02:58 [INFO] train episode 546: reward = -75.40, steps = 18 00:02:58 [INFO] train episode 547: reward = -70.19, steps = 21 00:02:58 [INFO] train episode 548: reward = -75.99, steps = 19 00:02:58 [INFO] train episode 549: reward = -105.40, steps = 23 00:02:58 [INFO] train episode 550: reward = -99.32, steps = 19 00:02:58 [INFO] train episode 551: reward = -71.33, steps = 18 00:02:58 [INFO] train episode 552: reward = -84.71, steps = 19 00:02:59 [INFO] train episode 553: reward = -76.11, steps = 16 00:02:59 [INFO] train episode 554: reward = -75.19, steps = 19 00:02:59 [INFO] train episode 555: reward = -101.87, steps = 21 00:02:59 [INFO] train episode 556: reward = -93.11, steps = 20 00:02:59 [INFO] train episode 557: reward = -80.24, steps = 19 00:02:59 [INFO] train episode 558: reward = -88.99, steps = 20 00:02:59 [INFO] train episode 559: reward = -60.78, steps = 21 00:03:00 [INFO] train episode 560: reward = -85.35, steps = 18 00:03:00 [INFO] train episode 561: reward = -82.32, steps = 20 00:03:00 [INFO] train episode 562: reward = -88.72, steps = 19 00:03:00 [INFO] train episode 563: reward = -95.39, steps = 19 00:03:00 [INFO] train episode 564: reward = -95.97, steps = 20 00:03:00 [INFO] train episode 565: reward = -118.47, steps = 22 00:03:00 [INFO] train episode 566: reward = -61.90, steps = 16 00:03:01 [INFO] train episode 567: reward = -97.17, steps = 21 00:03:01 [INFO] train episode 568: reward = -87.54, steps = 19 00:03:01 [INFO] train episode 569: reward = -125.56, steps = 25 00:03:01 [INFO] train episode 570: reward = -75.89, steps = 19 00:03:01 [INFO] train episode 571: reward = -93.40, steps = 19 00:03:01 [INFO] train episode 572: reward = -100.12, steps = 21 00:03:01 [INFO] train episode 573: reward = -107.38, steps = 20 00:03:02 [INFO] train episode 574: reward = -62.99, steps = 19 00:03:02 [INFO] train episode 575: reward = -84.44, steps = 19 00:03:02 [INFO] train episode 576: reward = -75.82, steps = 19 00:03:02 [INFO] train episode 577: reward = -82.86, steps = 15 00:03:02 [INFO] train episode 578: reward = -90.50, steps = 19 00:03:02 [INFO] train episode 579: reward = -98.35, steps = 20 00:03:02 [INFO] train episode 580: reward = -74.99, steps = 17 00:03:03 [INFO] train episode 581: reward = -60.62, steps = 20 00:03:03 [INFO] train episode 582: reward = -109.98, steps = 19 00:03:03 [INFO] train episode 583: reward = -63.84, steps = 19 00:03:03 [INFO] train episode 584: reward = -105.22, steps = 20 00:03:03 [INFO] train episode 585: reward = -110.56, steps = 20 00:03:04 [INFO] train episode 586: reward = -79.56, steps = 21 00:03:04 [INFO] train episode 587: reward = -89.44, steps = 19 00:03:04 [INFO] train episode 588: reward = -88.22, steps = 20 00:03:04 [INFO] train episode 589: reward = -71.36, steps = 18 00:03:04 [INFO] train episode 590: reward = -75.84, steps = 19 00:03:04 [INFO] train episode 591: reward = -71.51, steps = 19 00:03:04 [INFO] train episode 592: reward = -103.49, steps = 18 00:03:05 [INFO] train episode 593: reward = -126.30, steps = 26 00:03:05 [INFO] train episode 594: reward = -74.79, steps = 18 00:03:05 [INFO] train episode 595: reward = -83.29, steps = 18 00:03:05 [INFO] train episode 596: reward = -98.34, steps = 18 00:03:05 [INFO] train episode 597: reward = -98.56, steps = 19 00:03:05 [INFO] train episode 598: reward = -77.25, steps = 20 00:03:05 [INFO] train episode 599: reward = -127.20, steps = 20 00:03:06 [INFO] train episode 600: reward = -125.75, steps = 24 00:03:06 [INFO] train episode 601: reward = -101.99, steps = 30 00:03:06 [INFO] train episode 602: reward = -91.13, steps = 22 00:03:06 [INFO] train episode 603: reward = -149.34, steps = 30 00:03:06 [INFO] train episode 604: reward = -92.26, steps = 20 00:03:06 [INFO] train episode 605: reward = -92.76, steps = 20 00:03:07 [INFO] train episode 606: reward = -87.38, steps = 19 00:03:07 [INFO] train episode 607: reward = -78.30, steps = 19 00:03:07 [INFO] train episode 608: reward = -97.55, steps = 20 00:03:07 [INFO] train episode 609: reward = -88.81, steps = 19 00:03:07 [INFO] train episode 610: reward = -136.49, steps = 39 00:03:07 [INFO] train episode 611: reward = -90.41, steps = 20 00:03:08 [INFO] train episode 612: reward = -100.18, steps = 19 00:03:08 [INFO] train episode 613: reward = -86.32, steps = 20 00:03:08 [INFO] train episode 614: reward = -80.94, steps = 18 00:03:08 [INFO] train episode 615: reward = -82.54, steps = 21 00:03:08 [INFO] train episode 616: reward = -76.21, steps = 19 00:03:08 [INFO] train episode 617: reward = -69.95, steps = 19 00:03:08 [INFO] train episode 618: reward = -120.25, steps = 20 00:03:09 [INFO] train episode 619: reward = -88.61, steps = 20 00:03:09 [INFO] train episode 620: reward = -84.07, steps = 18 00:03:09 [INFO] train episode 621: reward = -72.22, steps = 19 00:03:09 [INFO] train episode 622: reward = -115.44, steps = 19 00:03:09 [INFO] train episode 623: reward = -118.62, steps = 22 00:03:09 [INFO] train episode 624: reward = -92.63, steps = 27 00:03:09 [INFO] train episode 625: reward = -87.20, steps = 19 00:03:10 [INFO] train episode 626: reward = -74.63, steps = 18 00:03:10 [INFO] train episode 627: reward = -69.37, steps = 20 00:03:10 [INFO] train episode 628: reward = -91.05, steps = 25 00:03:10 [INFO] train episode 629: reward = -77.93, steps = 19 00:03:10 [INFO] train episode 630: reward = -78.10, steps = 18 00:03:10 [INFO] train episode 631: reward = -76.15, steps = 19 00:03:11 [INFO] train episode 632: reward = -78.70, steps = 20 00:03:11 [INFO] train episode 633: reward = -86.61, steps = 20 00:03:11 [INFO] train episode 634: reward = -67.92, steps = 17 00:03:11 [INFO] train episode 635: reward = -108.56, steps = 19 00:03:11 [INFO] train episode 636: reward = -76.09, steps = 19 00:03:11 [INFO] train episode 637: reward = -69.21, steps = 20 00:03:11 [INFO] train episode 638: reward = -88.71, steps = 19 00:03:11 [INFO] train episode 639: reward = -69.09, steps = 19 00:03:12 [INFO] train episode 640: reward = -113.35, steps = 24 00:03:12 [INFO] train episode 641: reward = -46.02, steps = 19 00:03:12 [INFO] train episode 642: reward = -66.71, steps = 20 00:03:12 [INFO] train episode 643: reward = -66.90, steps = 20 00:03:12 [INFO] train episode 644: reward = -79.33, steps = 18 00:03:12 [INFO] train episode 645: reward = -109.06, steps = 20 00:03:13 [INFO] train episode 646: reward = -89.97, steps = 20 00:03:13 [INFO] train episode 647: reward = -127.89, steps = 22 00:03:13 [INFO] train episode 648: reward = -107.76, steps = 21 00:03:13 [INFO] train episode 649: reward = -86.59, steps = 19 00:03:13 [INFO] train episode 650: reward = -103.59, steps = 19 00:03:13 [INFO] train episode 651: reward = -80.49, steps = 20 00:03:13 [INFO] train episode 652: reward = -71.86, steps = 19 00:03:14 [INFO] train episode 653: reward = -91.79, steps = 19 00:03:14 [INFO] train episode 654: reward = -77.54, steps = 20 00:03:14 [INFO] train episode 655: reward = -111.46, steps = 29 00:03:14 [INFO] train episode 656: reward = -76.01, steps = 24 00:03:14 [INFO] train episode 657: reward = -102.62, steps = 24 00:03:14 [INFO] train episode 658: reward = -93.03, steps = 23 00:03:15 [INFO] train episode 659: reward = -103.69, steps = 20 00:03:15 [INFO] train episode 660: reward = -93.65, steps = 22 00:03:15 [INFO] train episode 661: reward = -86.49, steps = 20 00:03:15 [INFO] train episode 662: reward = -114.84, steps = 21 00:03:15 [INFO] train episode 663: reward = -70.61, steps = 17 00:03:15 [INFO] train episode 664: reward = -94.04, steps = 15 00:03:15 [INFO] train episode 665: reward = -92.16, steps = 20 00:03:16 [INFO] train episode 666: reward = -88.37, steps = 21 00:03:16 [INFO] train episode 667: reward = -67.86, steps = 20 00:03:16 [INFO] train episode 668: reward = -74.56, steps = 20 00:03:16 [INFO] train episode 669: reward = -86.12, steps = 18 00:03:16 [INFO] train episode 670: reward = -82.71, steps = 18 00:03:16 [INFO] train episode 671: reward = -109.01, steps = 19 00:03:17 [INFO] train episode 672: reward = -127.96, steps = 31 00:03:17 [INFO] train episode 673: reward = -75.98, steps = 19 00:03:17 [INFO] train episode 674: reward = -66.70, steps = 19 00:03:17 [INFO] train episode 675: reward = -80.34, steps = 22 00:03:17 [INFO] train episode 676: reward = -87.11, steps = 19 00:03:17 [INFO] train episode 677: reward = -51.91, steps = 20 00:03:18 [INFO] train episode 678: reward = -81.74, steps = 20 00:03:18 [INFO] train episode 679: reward = -66.19, steps = 18 00:03:18 [INFO] train episode 680: reward = -71.60, steps = 19 00:03:18 [INFO] train episode 681: reward = -67.28, steps = 19 00:03:18 [INFO] train episode 682: reward = -77.30, steps = 20 00:03:18 [INFO] train episode 683: reward = -108.71, steps = 18 00:03:18 [INFO] train episode 684: reward = -82.95, steps = 18 00:03:19 [INFO] train episode 685: reward = -81.64, steps = 19 00:03:19 [INFO] train episode 686: reward = -69.06, steps = 20 00:03:19 [INFO] train episode 687: reward = -150.14, steps = 39 00:03:19 [INFO] train episode 688: reward = -119.85, steps = 23 00:03:19 [INFO] train episode 689: reward = -70.62, steps = 19 00:03:19 [INFO] train episode 690: reward = -75.02, steps = 18 00:03:20 [INFO] train episode 691: reward = -83.56, steps = 22 00:03:20 [INFO] train episode 692: reward = -132.74, steps = 28 00:03:20 [INFO] train episode 693: reward = -60.21, steps = 20 00:03:20 [INFO] train episode 694: reward = -104.67, steps = 21 00:03:20 [INFO] train episode 695: reward = -96.80, steps = 19 00:03:20 [INFO] train episode 696: reward = -101.79, steps = 20 00:03:20 [INFO] train episode 697: reward = -99.94, steps = 20 00:03:21 [INFO] train episode 698: reward = -99.38, steps = 24 00:03:21 [INFO] train episode 699: reward = -82.30, steps = 20 00:03:21 [INFO] train episode 700: reward = -82.09, steps = 20 00:03:21 [INFO] train episode 701: reward = -107.11, steps = 19 00:03:21 [INFO] train episode 702: reward = -109.53, steps = 21 00:03:21 [INFO] train episode 703: reward = -106.52, steps = 23 00:03:21 [INFO] train episode 704: reward = -83.78, steps = 19 00:03:22 [INFO] train episode 705: reward = -54.46, steps = 17 00:03:22 [INFO] train episode 706: reward = -81.31, steps = 20 00:03:22 [INFO] train episode 707: reward = -79.30, steps = 19 00:03:22 [INFO] train episode 708: reward = -88.90, steps = 20 00:03:22 [INFO] train episode 709: reward = -72.87, steps = 18 00:03:22 [INFO] train episode 710: reward = -152.65, steps = 32 00:03:23 [INFO] train episode 711: reward = -100.82, steps = 21 00:03:23 [INFO] train episode 712: reward = -86.37, steps = 19 00:03:23 [INFO] train episode 713: reward = -90.12, steps = 19 00:03:23 [INFO] train episode 714: reward = -82.59, steps = 19 00:03:23 [INFO] train episode 715: reward = -104.00, steps = 28 00:03:23 [INFO] train episode 716: reward = -75.94, steps = 17 00:03:23 [INFO] train episode 717: reward = -79.39, steps = 19 00:03:24 [INFO] train episode 718: reward = -107.04, steps = 25 00:03:24 [INFO] train episode 719: reward = -79.32, steps = 19 00:03:24 [INFO] train episode 720: reward = -93.20, steps = 19 00:03:24 [INFO] train episode 721: reward = -70.45, steps = 18 00:03:24 [INFO] train episode 722: reward = -90.07, steps = 19 00:03:24 [INFO] train episode 723: reward = -66.55, steps = 24 00:03:24 [INFO] train episode 724: reward = -65.62, steps = 18 00:03:25 [INFO] train episode 725: reward = -108.98, steps = 26 00:03:25 [INFO] train episode 726: reward = -108.79, steps = 31 00:03:25 [INFO] train episode 727: reward = -94.13, steps = 20 00:03:25 [INFO] train episode 728: reward = -112.96, steps = 26 00:03:25 [INFO] train episode 729: reward = -67.40, steps = 19 00:03:25 [INFO] train episode 730: reward = -102.33, steps = 17 00:03:26 [INFO] train episode 731: reward = -79.83, steps = 19 00:03:26 [INFO] train episode 732: reward = -75.20, steps = 19 00:03:26 [INFO] train episode 733: reward = -120.77, steps = 30 00:03:26 [INFO] train episode 734: reward = -83.71, steps = 20 00:03:26 [INFO] train episode 735: reward = -94.07, steps = 19 00:03:26 [INFO] train episode 736: reward = -82.76, steps = 20 00:03:27 [INFO] train episode 737: reward = -82.52, steps = 21 00:03:27 [INFO] train episode 738: reward = -68.56, steps = 17 00:03:27 [INFO] train episode 739: reward = -103.22, steps = 27 00:03:27 [INFO] train episode 740: reward = -86.99, steps = 22 00:03:27 [INFO] train episode 741: reward = -104.68, steps = 12 00:03:27 [INFO] train episode 742: reward = -67.29, steps = 20 00:03:27 [INFO] train episode 743: reward = -86.07, steps = 20 00:03:28 [INFO] train episode 744: reward = -99.12, steps = 20 00:03:28 [INFO] train episode 745: reward = -90.82, steps = 19 00:03:28 [INFO] train episode 746: reward = -73.08, steps = 19 00:03:28 [INFO] train episode 747: reward = -112.72, steps = 19 00:03:28 [INFO] train episode 748: reward = -98.95, steps = 27 00:03:28 [INFO] train episode 749: reward = -101.42, steps = 18 00:03:28 [INFO] train episode 750: reward = -77.02, steps = 19 00:03:29 [INFO] train episode 751: reward = -84.22, steps = 21 00:03:29 [INFO] train episode 752: reward = -82.36, steps = 19 00:03:29 [INFO] train episode 753: reward = -96.94, steps = 21 00:03:29 [INFO] train episode 754: reward = -100.88, steps = 22 00:03:29 [INFO] train episode 755: reward = -88.32, steps = 20 00:03:29 [INFO] train episode 756: reward = -78.73, steps = 19 00:03:29 [INFO] train episode 757: reward = -98.29, steps = 21 00:03:30 [INFO] train episode 758: reward = -80.31, steps = 18 00:03:30 [INFO] train episode 759: reward = -63.81, steps = 19 00:03:30 [INFO] train episode 760: reward = -84.87, steps = 19 00:03:30 [INFO] train episode 761: reward = -71.29, steps = 19 00:03:30 [INFO] train episode 762: reward = -76.65, steps = 20 00:03:30 [INFO] train episode 763: reward = -98.58, steps = 19 00:03:30 [INFO] train episode 764: reward = -76.79, steps = 19 00:03:31 [INFO] train episode 765: reward = -83.42, steps = 19 00:03:31 [INFO] train episode 766: reward = -102.01, steps = 19 00:03:31 [INFO] train episode 767: reward = -84.56, steps = 19 00:03:31 [INFO] train episode 768: reward = -107.58, steps = 20 00:03:31 [INFO] train episode 769: reward = -84.03, steps = 21 00:03:32 [INFO] train episode 770: reward = -123.68, steps = 24 00:03:32 [INFO] train episode 771: reward = -103.73, steps = 24 00:03:32 [INFO] train episode 772: reward = -92.34, steps = 18 00:03:32 [INFO] train episode 773: reward = -65.46, steps = 23 00:03:32 [INFO] train episode 774: reward = -75.05, steps = 19 00:03:32 [INFO] train episode 775: reward = -122.18, steps = 22 00:03:33 [INFO] train episode 776: reward = -86.30, steps = 19 00:03:33 [INFO] train episode 777: reward = -82.84, steps = 23 00:03:33 [INFO] train episode 778: reward = -93.75, steps = 24 00:03:33 [INFO] train episode 779: reward = -85.11, steps = 19 00:03:33 [INFO] train episode 780: reward = -107.78, steps = 23 00:03:33 [INFO] train episode 781: reward = -66.18, steps = 17 00:03:34 [INFO] train episode 782: reward = -112.19, steps = 19 00:03:34 [INFO] train episode 783: reward = -81.28, steps = 20 00:03:34 [INFO] train episode 784: reward = -85.55, steps = 19 00:03:34 [INFO] train episode 785: reward = -74.76, steps = 20 00:03:34 [INFO] train episode 786: reward = -83.64, steps = 18 00:03:35 [INFO] train episode 787: reward = -86.40, steps = 19 00:03:35 [INFO] train episode 788: reward = -95.37, steps = 19 00:03:35 [INFO] train episode 789: reward = -97.78, steps = 22 00:03:35 [INFO] train episode 790: reward = -83.89, steps = 21 00:03:35 [INFO] train episode 791: reward = -78.96, steps = 22 00:03:35 [INFO] train episode 792: reward = -88.03, steps = 20 00:03:36 [INFO] train episode 793: reward = -74.80, steps = 20 00:03:36 [INFO] train episode 794: reward = -91.63, steps = 22 00:03:36 [INFO] train episode 795: reward = -72.25, steps = 20 00:03:36 [INFO] train episode 796: reward = -73.77, steps = 18 00:03:36 [INFO] train episode 797: reward = -89.79, steps = 19 00:03:36 [INFO] train episode 798: reward = -92.60, steps = 19 00:03:37 [INFO] train episode 799: reward = -63.43, steps = 18 00:03:37 [INFO] train episode 800: reward = -97.48, steps = 20 00:03:37 [INFO] train episode 801: reward = -96.92, steps = 20 00:03:37 [INFO] train episode 802: reward = -67.66, steps = 21 00:03:37 [INFO] train episode 803: reward = -74.97, steps = 18 00:03:37 [INFO] train episode 804: reward = -54.51, steps = 16 00:03:37 [INFO] train episode 805: reward = -83.59, steps = 19 00:03:37 [INFO] train episode 806: reward = -92.14, steps = 19 00:03:38 [INFO] train episode 807: reward = -98.03, steps = 27 00:03:38 [INFO] train episode 808: reward = -68.47, steps = 19 00:03:38 [INFO] train episode 809: reward = -85.70, steps = 19 00:03:38 [INFO] train episode 810: reward = -87.82, steps = 19 00:03:38 [INFO] train episode 811: reward = -79.40, steps = 19 00:03:38 [INFO] train episode 812: reward = -93.73, steps = 19 00:03:38 [INFO] train episode 813: reward = -91.63, steps = 19 00:03:39 [INFO] train episode 814: reward = -75.43, steps = 20 00:03:39 [INFO] train episode 815: reward = -126.57, steps = 32 00:03:39 [INFO] train episode 816: reward = -91.08, steps = 21 00:03:39 [INFO] train episode 817: reward = -108.81, steps = 24 00:03:39 [INFO] train episode 818: reward = -78.41, steps = 20 00:03:39 [INFO] train episode 819: reward = -119.95, steps = 21 00:03:40 [INFO] train episode 820: reward = -109.75, steps = 20 00:03:40 [INFO] train episode 821: reward = -97.26, steps = 17 00:03:40 [INFO] train episode 822: reward = -74.67, steps = 20 00:03:40 [INFO] train episode 823: reward = -65.92, steps = 20 00:03:40 [INFO] train episode 824: reward = -88.44, steps = 21 00:03:40 [INFO] train episode 825: reward = -106.88, steps = 20 00:03:40 [INFO] train episode 826: reward = -86.58, steps = 28 00:03:41 [INFO] train episode 827: reward = -63.17, steps = 18 00:03:41 [INFO] train episode 828: reward = -90.56, steps = 20 00:03:41 [INFO] train episode 829: reward = -79.95, steps = 20 00:03:41 [INFO] train episode 830: reward = -90.01, steps = 17 00:03:41 [INFO] train episode 831: reward = -76.53, steps = 18 00:03:41 [INFO] train episode 832: reward = -84.88, steps = 20 00:03:41 [INFO] train episode 833: reward = -86.00, steps = 21 00:03:42 [INFO] train episode 834: reward = -113.69, steps = 19 00:03:42 [INFO] train episode 835: reward = -90.38, steps = 18 00:03:42 [INFO] train episode 836: reward = -57.18, steps = 20 00:03:42 [INFO] train episode 837: reward = -104.34, steps = 19 00:03:42 [INFO] train episode 838: reward = -99.40, steps = 19 00:03:42 [INFO] train episode 839: reward = -100.39, steps = 21 00:03:42 [INFO] train episode 840: reward = -87.56, steps = 19 00:03:43 [INFO] train episode 841: reward = -112.62, steps = 34 00:03:43 [INFO] train episode 842: reward = -62.74, steps = 19 00:03:43 [INFO] train episode 843: reward = -72.67, steps = 19 00:03:43 [INFO] train episode 844: reward = -94.27, steps = 20 00:03:43 [INFO] train episode 845: reward = -80.59, steps = 19 00:03:43 [INFO] train episode 846: reward = -91.75, steps = 22 00:03:44 [INFO] train episode 847: reward = -97.67, steps = 31 00:03:44 [INFO] train episode 848: reward = -87.55, steps = 19 00:03:44 [INFO] train episode 849: reward = -74.02, steps = 19 00:03:44 [INFO] train episode 850: reward = -64.56, steps = 20 00:03:44 [INFO] train episode 851: reward = -60.55, steps = 19 00:03:44 [INFO] train episode 852: reward = -101.87, steps = 24 00:03:44 [INFO] train episode 853: reward = -102.67, steps = 20 00:03:45 [INFO] train episode 854: reward = -96.54, steps = 22 00:03:45 [INFO] train episode 855: reward = -85.66, steps = 20 00:03:45 [INFO] train episode 856: reward = -96.38, steps = 19 00:03:45 [INFO] train episode 857: reward = -92.07, steps = 23 00:03:45 [INFO] train episode 858: reward = -110.31, steps = 21 00:03:45 [INFO] train episode 859: reward = -78.68, steps = 19 00:03:45 [INFO] train episode 860: reward = -80.49, steps = 19 00:03:46 [INFO] train episode 861: reward = -96.03, steps = 29 00:03:46 [INFO] train episode 862: reward = -102.06, steps = 20 00:03:46 [INFO] train episode 863: reward = -90.34, steps = 21 00:03:46 [INFO] train episode 864: reward = -86.14, steps = 20 00:03:47 [INFO] train episode 865: reward = -134.96, steps = 33 00:03:47 [INFO] train episode 866: reward = -56.30, steps = 21 00:03:47 [INFO] train episode 867: reward = -74.15, steps = 21 00:03:47 [INFO] train episode 868: reward = -97.76, steps = 23 00:03:47 [INFO] train episode 869: reward = -77.65, steps = 20 00:03:47 [INFO] train episode 870: reward = -80.61, steps = 20 00:03:47 [INFO] train episode 871: reward = -99.06, steps = 17 00:03:48 [INFO] train episode 872: reward = -87.22, steps = 24 00:03:48 [INFO] train episode 873: reward = -85.08, steps = 18 00:03:48 [INFO] train episode 874: reward = -73.92, steps = 20 00:03:48 [INFO] train episode 875: reward = -63.12, steps = 18 00:03:48 [INFO] train episode 876: reward = -87.61, steps = 20 00:03:48 [INFO] train episode 877: reward = -94.91, steps = 24 00:03:48 [INFO] train episode 878: reward = -77.20, steps = 20 00:03:49 [INFO] train episode 879: reward = -112.23, steps = 30 00:03:49 [INFO] train episode 880: reward = -76.07, steps = 19 00:03:49 [INFO] train episode 881: reward = -129.83, steps = 32 00:03:49 [INFO] train episode 882: reward = -73.24, steps = 21 00:03:49 [INFO] train episode 883: reward = -53.66, steps = 20 00:03:49 [INFO] train episode 884: reward = -87.96, steps = 24 00:03:50 [INFO] train episode 885: reward = -166.06, steps = 30 00:03:50 [INFO] train episode 886: reward = -88.05, steps = 19 00:03:50 [INFO] train episode 887: reward = -94.27, steps = 15 00:03:50 [INFO] train episode 888: reward = -78.27, steps = 20 00:03:50 [INFO] train episode 889: reward = -61.12, steps = 20 00:03:50 [INFO] train episode 890: reward = -80.67, steps = 19 00:03:50 [INFO] train episode 891: reward = -66.70, steps = 19 00:03:51 [INFO] train episode 892: reward = -115.87, steps = 26 00:03:51 [INFO] train episode 893: reward = -79.96, steps = 18 00:03:51 [INFO] train episode 894: reward = -79.77, steps = 18 00:03:51 [INFO] train episode 895: reward = -114.08, steps = 18 00:03:51 [INFO] train episode 896: reward = -84.11, steps = 19 00:03:51 [INFO] train episode 897: reward = -102.24, steps = 20 00:03:51 [INFO] train episode 898: reward = -76.23, steps = 23 00:03:52 [INFO] train episode 899: reward = -86.14, steps = 20 00:03:52 [INFO] train episode 900: reward = -83.53, steps = 19 00:03:52 [INFO] train episode 901: reward = -71.15, steps = 19 00:03:52 [INFO] train episode 902: reward = -85.16, steps = 19 00:03:52 [INFO] train episode 903: reward = -77.37, steps = 19 00:03:52 [INFO] train episode 904: reward = -115.70, steps = 19 00:03:52 [INFO] train episode 905: reward = -89.47, steps = 21 00:03:53 [INFO] train episode 906: reward = -99.24, steps = 21 00:03:53 [INFO] train episode 907: reward = -101.71, steps = 20 00:03:53 [INFO] train episode 908: reward = -79.17, steps = 19 00:03:53 [INFO] train episode 909: reward = -97.31, steps = 20 00:03:53 [INFO] train episode 910: reward = -83.50, steps = 18 00:03:53 [INFO] train episode 911: reward = -85.62, steps = 19 00:03:53 [INFO] train episode 912: reward = -63.25, steps = 19 00:03:54 [INFO] train episode 913: reward = -86.14, steps = 22 00:03:54 [INFO] train episode 914: reward = -73.54, steps = 20 00:03:54 [INFO] train episode 915: reward = -55.67, steps = 19 00:03:54 [INFO] train episode 916: reward = -76.51, steps = 19 00:03:54 [INFO] train episode 917: reward = -110.33, steps = 27 00:03:54 [INFO] train episode 918: reward = -122.25, steps = 24 00:03:54 [INFO] train episode 919: reward = -101.48, steps = 20 00:03:55 [INFO] train episode 920: reward = -67.03, steps = 19 00:03:55 [INFO] train episode 921: reward = -125.01, steps = 37 00:03:55 [INFO] train episode 922: reward = -94.14, steps = 18 00:03:55 [INFO] train episode 923: reward = -66.96, steps = 23 00:03:55 [INFO] train episode 924: reward = -95.19, steps = 19 00:03:55 [INFO] train episode 925: reward = -118.88, steps = 34 00:03:56 [INFO] train episode 926: reward = -122.43, steps = 32 00:03:56 [INFO] train episode 927: reward = -111.64, steps = 24 00:03:56 [INFO] train episode 928: reward = -76.87, steps = 19 00:03:56 [INFO] train episode 929: reward = -100.74, steps = 25 00:03:56 [INFO] train episode 930: reward = -107.86, steps = 20 00:03:56 [INFO] train episode 931: reward = -108.32, steps = 17 00:03:57 [INFO] train episode 932: reward = -166.38, steps = 33 00:03:57 [INFO] train episode 933: reward = -82.02, steps = 23 00:03:57 [INFO] train episode 934: reward = -73.41, steps = 19 00:03:57 [INFO] train episode 935: reward = -92.27, steps = 19 00:03:57 [INFO] train episode 936: reward = -68.27, steps = 21 00:03:57 [INFO] train episode 937: reward = -113.90, steps = 27 00:03:58 [INFO] train episode 938: reward = -97.50, steps = 19 00:03:58 [INFO] train episode 939: reward = -78.54, steps = 14 00:03:58 [INFO] train episode 940: reward = -95.47, steps = 20 00:03:58 [INFO] train episode 941: reward = -54.64, steps = 19 00:03:58 [INFO] train episode 942: reward = -71.40, steps = 19 00:03:58 [INFO] train episode 943: reward = -99.98, steps = 20 00:03:58 [INFO] train episode 944: reward = -83.55, steps = 22 00:03:59 [INFO] train episode 945: reward = -127.56, steps = 27 00:03:59 [INFO] train episode 946: reward = -75.50, steps = 19 00:03:59 [INFO] train episode 947: reward = -80.49, steps = 19 00:03:59 [INFO] train episode 948: reward = -58.75, steps = 19 00:03:59 [INFO] train episode 949: reward = -75.35, steps = 19 00:03:59 [INFO] train episode 950: reward = -63.11, steps = 19 00:04:00 [INFO] train episode 951: reward = -94.46, steps = 21 00:04:00 [INFO] train episode 952: reward = -57.32, steps = 19 00:04:00 [INFO] train episode 953: reward = -71.98, steps = 19 00:04:00 [INFO] train episode 954: reward = -123.19, steps = 29 00:04:00 [INFO] train episode 955: reward = -66.31, steps = 21 00:04:00 [INFO] train episode 956: reward = -53.99, steps = 19 00:04:01 [INFO] train episode 957: reward = -113.91, steps = 23 00:04:01 [INFO] train episode 958: reward = -69.66, steps = 19 00:04:01 [INFO] train episode 959: reward = -80.09, steps = 19 00:04:01 [INFO] train episode 960: reward = -86.54, steps = 19 00:04:01 [INFO] train episode 961: reward = -63.67, steps = 20 00:04:01 [INFO] train episode 962: reward = -122.75, steps = 25 00:04:01 [INFO] train episode 963: reward = -99.83, steps = 23 00:04:02 [INFO] train episode 964: reward = -102.07, steps = 18 00:04:02 [INFO] train episode 965: reward = -93.44, steps = 22 00:04:02 [INFO] train episode 966: reward = -87.34, steps = 19 00:04:02 [INFO] train episode 967: reward = -85.33, steps = 20 00:04:02 [INFO] train episode 968: reward = -80.02, steps = 19 00:04:02 [INFO] train episode 969: reward = -84.26, steps = 20 00:04:02 [INFO] train episode 970: reward = -55.84, steps = 20 00:04:03 [INFO] train episode 971: reward = -83.64, steps = 18 00:04:03 [INFO] train episode 972: reward = -94.74, steps = 25 00:04:03 [INFO] train episode 973: reward = -103.52, steps = 22 00:04:03 [INFO] train episode 974: reward = -98.75, steps = 23 00:04:03 [INFO] train episode 975: reward = -87.65, steps = 18 00:04:03 [INFO] train episode 976: reward = -69.26, steps = 19 00:04:04 [INFO] train episode 977: reward = -118.81, steps = 34 00:04:04 [INFO] train episode 978: reward = -81.79, steps = 21 00:04:04 [INFO] train episode 979: reward = -84.90, steps = 20 00:04:04 [INFO] train episode 980: reward = -94.75, steps = 19 00:04:04 [INFO] train episode 981: reward = -79.69, steps = 19 00:04:04 [INFO] train episode 982: reward = -77.08, steps = 15 00:04:04 [INFO] train episode 983: reward = -112.40, steps = 25 00:04:05 [INFO] train episode 984: reward = -107.15, steps = 26 00:04:05 [INFO] train episode 985: reward = -81.81, steps = 21 00:04:05 [INFO] train episode 986: reward = -134.20, steps = 32 00:04:05 [INFO] train episode 987: reward = -93.35, steps = 19 00:04:05 [INFO] train episode 988: reward = -96.06, steps = 20 00:04:05 [INFO] train episode 989: reward = -96.92, steps = 24 00:04:06 [INFO] train episode 990: reward = -81.81, steps = 22 00:04:06 [INFO] train episode 991: reward = -66.63, steps = 19 00:04:06 [INFO] train episode 992: reward = -92.01, steps = 23 00:04:06 [INFO] train episode 993: reward = -91.23, steps = 20 00:04:06 [INFO] train episode 994: reward = -119.76, steps = 25 00:04:06 [INFO] train episode 995: reward = -72.56, steps = 19 00:04:06 [INFO] train episode 996: reward = -94.91, steps = 21 00:04:07 [INFO] train episode 997: reward = -126.43, steps = 22 00:04:07 [INFO] train episode 998: reward = -92.50, steps = 19 00:04:07 [INFO] train episode 999: reward = -75.64, steps = 20 00:04:07 [INFO] train episode 1000: reward = -87.56, steps = 24 00:04:07 [INFO] train episode 1001: reward = -91.45, steps = 21 00:04:07 [INFO] train episode 1002: reward = -67.96, steps = 22 00:04:07 [INFO] train episode 1003: reward = -77.02, steps = 17 00:04:08 [INFO] train episode 1004: reward = -68.83, steps = 19 00:04:08 [INFO] train episode 1005: reward = -80.74, steps = 19 00:04:08 [INFO] train episode 1006: reward = -76.57, steps = 17 00:04:08 [INFO] train episode 1007: reward = -107.08, steps = 19 00:04:08 [INFO] train episode 1008: reward = -96.85, steps = 20 00:04:08 [INFO] train episode 1009: reward = -69.88, steps = 18 00:04:09 [INFO] train episode 1010: reward = -101.53, steps = 23 00:04:09 [INFO] train episode 1011: reward = -70.20, steps = 19 00:04:09 [INFO] train episode 1012: reward = -112.14, steps = 23 00:04:09 [INFO] train episode 1013: reward = -72.08, steps = 19 00:04:09 [INFO] train episode 1014: reward = -206.22, steps = 35 00:04:09 [INFO] train episode 1015: reward = -83.41, steps = 24 00:04:10 [INFO] train episode 1016: reward = -74.28, steps = 19 00:04:10 [INFO] train episode 1017: reward = -94.90, steps = 19 00:04:10 [INFO] train episode 1018: reward = -91.39, steps = 18 00:04:10 [INFO] train episode 1019: reward = -72.24, steps = 20 00:04:10 [INFO] train episode 1020: reward = -77.22, steps = 20 00:04:10 [INFO] train episode 1021: reward = -88.13, steps = 19 00:04:10 [INFO] train episode 1022: reward = -91.03, steps = 20 00:04:11 [INFO] train episode 1023: reward = -58.69, steps = 18 00:04:11 [INFO] train episode 1024: reward = -84.02, steps = 23 00:04:11 [INFO] train episode 1025: reward = -82.71, steps = 21 00:04:11 [INFO] train episode 1026: reward = -108.42, steps = 24 00:04:11 [INFO] train episode 1027: reward = -78.38, steps = 21 00:04:11 [INFO] train episode 1028: reward = -88.05, steps = 19 00:04:11 [INFO] train episode 1029: reward = -83.91, steps = 23 00:04:12 [INFO] train episode 1030: reward = -87.37, steps = 20 00:04:12 [INFO] train episode 1031: reward = -93.90, steps = 19 00:04:12 [INFO] train episode 1032: reward = -85.57, steps = 19 00:04:12 [INFO] train episode 1033: reward = -70.42, steps = 19 00:04:12 [INFO] train episode 1034: reward = -57.55, steps = 17 00:04:12 [INFO] train episode 1035: reward = -99.67, steps = 21 00:04:12 [INFO] train episode 1036: reward = -104.16, steps = 18 00:04:13 [INFO] train episode 1037: reward = -90.37, steps = 21 00:04:13 [INFO] train episode 1038: reward = -101.56, steps = 19 00:04:13 [INFO] train episode 1039: reward = -72.10, steps = 20 00:04:13 [INFO] train episode 1040: reward = -108.40, steps = 25 00:04:13 [INFO] train episode 1041: reward = -102.58, steps = 25 00:04:13 [INFO] train episode 1042: reward = -89.35, steps = 19 00:04:14 [INFO] train episode 1043: reward = -83.81, steps = 20 00:04:14 [INFO] train episode 1044: reward = -97.72, steps = 22 00:04:14 [INFO] train episode 1045: reward = -97.34, steps = 25 00:04:14 [INFO] train episode 1046: reward = -75.77, steps = 22 00:04:14 [INFO] train episode 1047: reward = -116.29, steps = 28 00:04:15 [INFO] train episode 1048: reward = -77.08, steps = 19 00:04:15 [INFO] train episode 1049: reward = -73.91, steps = 20 00:04:15 [INFO] train episode 1050: reward = -79.33, steps = 19 00:04:15 [INFO] train episode 1051: reward = -62.47, steps = 21 00:04:15 [INFO] train episode 1052: reward = -70.85, steps = 20 00:04:15 [INFO] train episode 1053: reward = -87.83, steps = 23 00:04:15 [INFO] train episode 1054: reward = -141.12, steps = 21 00:04:16 [INFO] train episode 1055: reward = -169.09, steps = 33 00:04:16 [INFO] train episode 1056: reward = -59.44, steps = 18 00:04:16 [INFO] train episode 1057: reward = -73.41, steps = 19 00:04:16 [INFO] train episode 1058: reward = -98.40, steps = 24 00:04:16 [INFO] train episode 1059: reward = -80.31, steps = 20 00:04:16 [INFO] train episode 1060: reward = -60.05, steps = 20 00:04:17 [INFO] train episode 1061: reward = -57.05, steps = 20 00:04:17 [INFO] train episode 1062: reward = -80.46, steps = 22 00:04:17 [INFO] train episode 1063: reward = -97.94, steps = 21 00:04:17 [INFO] train episode 1064: reward = -75.06, steps = 21 00:04:17 [INFO] train episode 1065: reward = -87.01, steps = 21 00:04:17 [INFO] train episode 1066: reward = -105.85, steps = 22 00:04:17 [INFO] train episode 1067: reward = -99.03, steps = 13 00:04:18 [INFO] train episode 1068: reward = -104.41, steps = 19 00:04:18 [INFO] train episode 1069: reward = -117.74, steps = 30 00:04:18 [INFO] train episode 1070: reward = -81.48, steps = 21 00:04:18 [INFO] train episode 1071: reward = -92.25, steps = 18 00:04:18 [INFO] train episode 1072: reward = -64.16, steps = 19 00:04:18 [INFO] train episode 1073: reward = -79.84, steps = 21 00:04:19 [INFO] train episode 1074: reward = -83.46, steps = 20 00:04:19 [INFO] train episode 1075: reward = -73.97, steps = 20 00:04:19 [INFO] train episode 1076: reward = -90.27, steps = 18 00:04:19 [INFO] train episode 1077: reward = -100.44, steps = 22 00:04:19 [INFO] train episode 1078: reward = -90.01, steps = 24 00:04:19 [INFO] train episode 1079: reward = -124.30, steps = 21 00:04:19 [INFO] train episode 1080: reward = -83.17, steps = 19 00:04:20 [INFO] train episode 1081: reward = -73.82, steps = 17 00:04:20 [INFO] train episode 1082: reward = -73.81, steps = 19 00:04:20 [INFO] train episode 1083: reward = -127.49, steps = 31 00:04:20 [INFO] train episode 1084: reward = -113.88, steps = 26 00:04:20 [INFO] train episode 1085: reward = -79.24, steps = 22 00:04:20 [INFO] train episode 1086: reward = -70.60, steps = 20 00:04:21 [INFO] train episode 1087: reward = -78.08, steps = 19 00:04:21 [INFO] train episode 1088: reward = -142.17, steps = 28 00:04:21 [INFO] train episode 1089: reward = -69.82, steps = 19 00:04:21 [INFO] train episode 1090: reward = -74.40, steps = 18 00:04:21 [INFO] train episode 1091: reward = -98.26, steps = 20 00:04:21 [INFO] train episode 1092: reward = -87.24, steps = 20 00:04:21 [INFO] train episode 1093: reward = -74.10, steps = 18 00:04:22 [INFO] train episode 1094: reward = -77.70, steps = 20 00:04:22 [INFO] train episode 1095: reward = -70.52, steps = 19 00:04:22 [INFO] train episode 1096: reward = -73.66, steps = 21 00:04:22 [INFO] train episode 1097: reward = -93.25, steps = 20 00:04:22 [INFO] train episode 1098: reward = -71.31, steps = 18 00:04:22 [INFO] train episode 1099: reward = -105.01, steps = 19 00:04:22 [INFO] train episode 1100: reward = -76.22, steps = 13 00:04:23 [INFO] train episode 1101: reward = -76.39, steps = 19 00:04:23 [INFO] train episode 1102: reward = -80.65, steps = 19 00:04:23 [INFO] train episode 1103: reward = -83.04, steps = 21 00:04:23 [INFO] train episode 1104: reward = -122.23, steps = 22 00:04:23 [INFO] train episode 1105: reward = -94.62, steps = 26 00:04:23 [INFO] train episode 1106: reward = -59.52, steps = 19 00:04:23 [INFO] train episode 1107: reward = -62.90, steps = 20 00:04:24 [INFO] train episode 1108: reward = -79.99, steps = 21 00:04:24 [INFO] train episode 1109: reward = -127.11, steps = 23 00:04:24 [INFO] train episode 1110: reward = -68.12, steps = 19 00:04:24 [INFO] train episode 1111: reward = -95.97, steps = 17 00:04:24 [INFO] train episode 1112: reward = -97.21, steps = 29 00:04:24 [INFO] train episode 1113: reward = -109.93, steps = 23 00:04:25 [INFO] train episode 1114: reward = -86.58, steps = 19 00:04:25 [INFO] train episode 1115: reward = -67.21, steps = 18 00:04:25 [INFO] train episode 1116: reward = -71.50, steps = 18 00:04:25 [INFO] train episode 1117: reward = -89.72, steps = 20 00:04:25 [INFO] train episode 1118: reward = -78.93, steps = 21 00:04:25 [INFO] train episode 1119: reward = -74.65, steps = 19 00:04:25 [INFO] train episode 1120: reward = -90.87, steps = 19 00:04:26 [INFO] train episode 1121: reward = -95.07, steps = 26 00:04:26 [INFO] train episode 1122: reward = -81.18, steps = 22 00:04:26 [INFO] train episode 1123: reward = -79.49, steps = 20 00:04:26 [INFO] train episode 1124: reward = -79.62, steps = 20 00:04:26 [INFO] train episode 1125: reward = -91.98, steps = 19 00:04:26 [INFO] train episode 1126: reward = -83.89, steps = 21 00:04:26 [INFO] train episode 1127: reward = -75.49, steps = 20 00:04:27 [INFO] train episode 1128: reward = -78.52, steps = 22 00:04:27 [INFO] train episode 1129: reward = -70.38, steps = 19 00:04:27 [INFO] train episode 1130: reward = -100.07, steps = 29 00:04:27 [INFO] train episode 1131: reward = -62.04, steps = 21 00:04:27 [INFO] train episode 1132: reward = -64.25, steps = 20 00:04:27 [INFO] train episode 1133: reward = -100.75, steps = 25 00:04:28 [INFO] train episode 1134: reward = -100.60, steps = 20 00:04:28 [INFO] train episode 1135: reward = -69.04, steps = 23 00:04:28 [INFO] train episode 1136: reward = -102.07, steps = 31 00:04:28 [INFO] train episode 1137: reward = -66.80, steps = 19 00:04:28 [INFO] train episode 1138: reward = -68.56, steps = 18 00:04:29 [INFO] train episode 1139: reward = -74.60, steps = 23 00:04:29 [INFO] train episode 1140: reward = -92.78, steps = 23 00:04:29 [INFO] train episode 1141: reward = -71.82, steps = 20 00:04:29 [INFO] train episode 1142: reward = -96.12, steps = 23 00:04:29 [INFO] train episode 1143: reward = -120.54, steps = 26 00:04:29 [INFO] train episode 1144: reward = -87.06, steps = 20 00:04:30 [INFO] train episode 1145: reward = -90.86, steps = 18 00:04:30 [INFO] train episode 1146: reward = -101.83, steps = 30 00:04:30 [INFO] train episode 1147: reward = -98.59, steps = 24 00:04:30 [INFO] train episode 1148: reward = -62.15, steps = 19 00:04:30 [INFO] train episode 1149: reward = -92.23, steps = 21 00:04:30 [INFO] train episode 1150: reward = -79.41, steps = 23 00:04:30 [INFO] train episode 1151: reward = -79.73, steps = 19 00:04:31 [INFO] train episode 1152: reward = -80.54, steps = 19 00:04:31 [INFO] train episode 1153: reward = -61.44, steps = 19 00:04:31 [INFO] train episode 1154: reward = -100.14, steps = 21 00:04:31 [INFO] train episode 1155: reward = -124.61, steps = 23 00:04:31 [INFO] train episode 1156: reward = -71.56, steps = 23 00:04:31 [INFO] train episode 1157: reward = -93.74, steps = 21 00:04:32 [INFO] train episode 1158: reward = -93.33, steps = 24 00:04:32 [INFO] train episode 1159: reward = -86.16, steps = 19 00:04:32 [INFO] train episode 1160: reward = -95.23, steps = 21 00:04:32 [INFO] train episode 1161: reward = -88.73, steps = 20 00:04:32 [INFO] train episode 1162: reward = -68.52, steps = 20 00:04:32 [INFO] train episode 1163: reward = -124.45, steps = 28 00:04:32 [INFO] train episode 1164: reward = -89.81, steps = 22 00:04:33 [INFO] train episode 1165: reward = -86.31, steps = 19 00:04:33 [INFO] train episode 1166: reward = -81.36, steps = 24 00:04:33 [INFO] train episode 1167: reward = -102.34, steps = 22 00:04:33 [INFO] train episode 1168: reward = -117.65, steps = 29 00:04:33 [INFO] train episode 1169: reward = -98.32, steps = 24 00:04:33 [INFO] train episode 1170: reward = -78.55, steps = 19 00:04:34 [INFO] train episode 1171: reward = -89.98, steps = 22 00:04:34 [INFO] train episode 1172: reward = -79.55, steps = 23 00:04:34 [INFO] train episode 1173: reward = -79.04, steps = 20 00:04:34 [INFO] train episode 1174: reward = -83.95, steps = 25 00:04:34 [INFO] train episode 1175: reward = -79.61, steps = 19 00:04:34 [INFO] train episode 1176: reward = -90.09, steps = 20 00:04:34 [INFO] train episode 1177: reward = -94.23, steps = 20 00:04:35 [INFO] train episode 1178: reward = -97.29, steps = 23 00:04:35 [INFO] train episode 1179: reward = -149.60, steps = 45 00:04:35 [INFO] train episode 1180: reward = -91.04, steps = 20 00:04:35 [INFO] train episode 1181: reward = -71.03, steps = 20 00:04:35 [INFO] train episode 1182: reward = -113.63, steps = 25 00:04:36 [INFO] train episode 1183: reward = -91.53, steps = 20 00:04:36 [INFO] train episode 1184: reward = -80.65, steps = 22 00:04:36 [INFO] train episode 1185: reward = -59.59, steps = 21 00:04:36 [INFO] train episode 1186: reward = -91.22, steps = 21 00:04:36 [INFO] train episode 1187: reward = -63.72, steps = 21 00:04:37 [INFO] train episode 1188: reward = -77.25, steps = 22 00:04:37 [INFO] train episode 1189: reward = -126.90, steps = 20 00:04:37 [INFO] train episode 1190: reward = -85.71, steps = 21 00:04:37 [INFO] train episode 1191: reward = -105.55, steps = 20 00:04:37 [INFO] train episode 1192: reward = -78.99, steps = 20 00:04:38 [INFO] train episode 1193: reward = -101.72, steps = 30 00:04:38 [INFO] train episode 1194: reward = -80.82, steps = 18 00:04:38 [INFO] train episode 1195: reward = -95.16, steps = 21 00:04:38 [INFO] train episode 1196: reward = -103.65, steps = 29 00:04:38 [INFO] train episode 1197: reward = -94.22, steps = 26 00:04:38 [INFO] train episode 1198: reward = -129.91, steps = 22 00:04:38 [INFO] train episode 1199: reward = -93.12, steps = 19 00:04:39 [INFO] train episode 1200: reward = -139.94, steps = 30 00:04:39 [INFO] train episode 1201: reward = -94.29, steps = 19 00:04:39 [INFO] train episode 1202: reward = -73.97, steps = 19 00:04:39 [INFO] train episode 1203: reward = -93.25, steps = 19 00:04:39 [INFO] train episode 1204: reward = -99.26, steps = 28 00:04:39 [INFO] train episode 1205: reward = -94.57, steps = 26 00:04:40 [INFO] train episode 1206: reward = -54.36, steps = 22 00:04:40 [INFO] train episode 1207: reward = -93.83, steps = 21 00:04:40 [INFO] train episode 1208: reward = -70.88, steps = 22 00:04:40 [INFO] train episode 1209: reward = -102.70, steps = 25 00:04:40 [INFO] train episode 1210: reward = -85.98, steps = 21 00:04:40 [INFO] train episode 1211: reward = -87.14, steps = 30 00:04:41 [INFO] train episode 1212: reward = -74.69, steps = 20 00:04:41 [INFO] train episode 1213: reward = -84.87, steps = 19 00:04:41 [INFO] train episode 1214: reward = -83.19, steps = 25 00:04:41 [INFO] train episode 1215: reward = -102.22, steps = 27 00:04:41 [INFO] train episode 1216: reward = -74.11, steps = 20 00:04:41 [INFO] train episode 1217: reward = -73.75, steps = 19 00:04:42 [INFO] train episode 1218: reward = -101.93, steps = 20 00:04:42 [INFO] train episode 1219: reward = -77.81, steps = 22 00:04:42 [INFO] train episode 1220: reward = -68.91, steps = 19 00:04:42 [INFO] train episode 1221: reward = -101.99, steps = 23 00:04:42 [INFO] train episode 1222: reward = -86.48, steps = 22 00:04:43 [INFO] train episode 1223: reward = -89.54, steps = 22 00:04:43 [INFO] train episode 1224: reward = -103.48, steps = 21 00:04:43 [INFO] train episode 1225: reward = -83.28, steps = 20 00:04:43 [INFO] train episode 1226: reward = -85.00, steps = 22 00:04:43 [INFO] train episode 1227: reward = -59.15, steps = 20 00:04:43 [INFO] train episode 1228: reward = -69.09, steps = 18 00:04:43 [INFO] train episode 1229: reward = -53.22, steps = 21 00:04:44 [INFO] train episode 1230: reward = -106.05, steps = 22 00:04:44 [INFO] train episode 1231: reward = -78.63, steps = 21 00:04:44 [INFO] train episode 1232: reward = -95.12, steps = 21 00:04:44 [INFO] train episode 1233: reward = -76.52, steps = 20 00:04:44 [INFO] train episode 1234: reward = -58.72, steps = 22 00:04:44 [INFO] train episode 1235: reward = -102.47, steps = 21 00:04:45 [INFO] train episode 1236: reward = -70.45, steps = 21 00:04:45 [INFO] train episode 1237: reward = -83.99, steps = 20 00:04:45 [INFO] train episode 1238: reward = -120.58, steps = 24 00:04:45 [INFO] train episode 1239: reward = -68.64, steps = 19 00:04:45 [INFO] train episode 1240: reward = -86.96, steps = 22 00:04:45 [INFO] train episode 1241: reward = -77.42, steps = 20 00:04:45 [INFO] train episode 1242: reward = -59.20, steps = 20 00:04:46 [INFO] train episode 1243: reward = -109.86, steps = 25 00:04:46 [INFO] train episode 1244: reward = -104.64, steps = 30 00:04:46 [INFO] train episode 1245: reward = -98.11, steps = 32 00:04:46 [INFO] train episode 1246: reward = -77.97, steps = 22 00:04:46 [INFO] train episode 1247: reward = -92.66, steps = 23 00:04:46 [INFO] train episode 1248: reward = -90.80, steps = 20 00:04:47 [INFO] train episode 1249: reward = -90.33, steps = 16 00:04:47 [INFO] train episode 1250: reward = -117.32, steps = 23 00:04:47 [INFO] train episode 1251: reward = -97.10, steps = 26 00:04:47 [INFO] train episode 1252: reward = -92.65, steps = 19 00:04:47 [INFO] train episode 1253: reward = -77.61, steps = 26 00:04:47 [INFO] train episode 1254: reward = -77.70, steps = 20 00:04:47 [INFO] train episode 1255: reward = -94.74, steps = 21 00:04:48 [INFO] train episode 1256: reward = -87.94, steps = 21 00:04:48 [INFO] train episode 1257: reward = -85.54, steps = 22 00:04:48 [INFO] train episode 1258: reward = -69.77, steps = 24 00:04:48 [INFO] train episode 1259: reward = -90.81, steps = 21 00:04:48 [INFO] train episode 1260: reward = -90.24, steps = 20 00:04:48 [INFO] train episode 1261: reward = -93.46, steps = 20 00:04:49 [INFO] train episode 1262: reward = -101.22, steps = 22 00:04:49 [INFO] train episode 1263: reward = -76.63, steps = 20 00:04:49 [INFO] train episode 1264: reward = -112.25, steps = 23 00:04:49 [INFO] train episode 1265: reward = -111.50, steps = 20 00:04:49 [INFO] train episode 1266: reward = -69.66, steps = 19 00:04:49 [INFO] train episode 1267: reward = -114.82, steps = 29 00:04:49 [INFO] train episode 1268: reward = -131.05, steps = 33 00:04:50 [INFO] train episode 1269: reward = -83.88, steps = 19 00:04:50 [INFO] train episode 1270: reward = -91.12, steps = 20 00:04:50 [INFO] train episode 1271: reward = -172.14, steps = 35 00:04:50 [INFO] train episode 1272: reward = -96.72, steps = 23 00:04:50 [INFO] train episode 1273: reward = -96.96, steps = 21 00:04:50 [INFO] train episode 1274: reward = -63.02, steps = 19 00:04:51 [INFO] train episode 1275: reward = -83.45, steps = 21 00:04:51 [INFO] train episode 1276: reward = -76.00, steps = 19 00:04:51 [INFO] train episode 1277: reward = -77.57, steps = 23 00:04:51 [INFO] train episode 1278: reward = -73.78, steps = 20 00:04:51 [INFO] train episode 1279: reward = -80.69, steps = 19 00:04:51 [INFO] train episode 1280: reward = -74.17, steps = 20 00:04:51 [INFO] train episode 1281: reward = -66.42, steps = 19 00:04:52 [INFO] train episode 1282: reward = -72.61, steps = 20 00:04:52 [INFO] train episode 1283: reward = -82.72, steps = 19 00:04:52 [INFO] train episode 1284: reward = -66.47, steps = 21 00:04:52 [INFO] train episode 1285: reward = -70.85, steps = 17 00:04:52 [INFO] train episode 1286: reward = -111.63, steps = 21 00:04:52 [INFO] train episode 1287: reward = -79.02, steps = 29 00:04:53 [INFO] train episode 1288: reward = -94.04, steps = 21 00:04:53 [INFO] train episode 1289: reward = -125.39, steps = 27 00:04:53 [INFO] train episode 1290: reward = -102.72, steps = 24 00:04:53 [INFO] train episode 1291: reward = -78.34, steps = 19 00:04:53 [INFO] train episode 1292: reward = -82.59, steps = 20 00:04:54 [INFO] train episode 1293: reward = -87.73, steps = 16 00:04:54 [INFO] train episode 1294: reward = -77.92, steps = 18 00:04:54 [INFO] train episode 1295: reward = -76.88, steps = 20 00:04:54 [INFO] train episode 1296: reward = -96.49, steps = 22 00:04:54 [INFO] train episode 1297: reward = -105.12, steps = 23 00:04:54 [INFO] train episode 1298: reward = -91.41, steps = 19 00:04:54 [INFO] train episode 1299: reward = -82.11, steps = 24 00:04:55 [INFO] train episode 1300: reward = -109.62, steps = 27 00:04:55 [INFO] train episode 1301: reward = -95.14, steps = 23 00:04:55 [INFO] train episode 1302: reward = -105.35, steps = 19 00:04:55 [INFO] train episode 1303: reward = -83.60, steps = 19 00:04:55 [INFO] train episode 1304: reward = -116.37, steps = 26 00:04:56 [INFO] train episode 1305: reward = -75.50, steps = 20 00:04:56 [INFO] train episode 1306: reward = -146.30, steps = 31 00:04:56 [INFO] train episode 1307: reward = -91.98, steps = 23 00:04:56 [INFO] train episode 1308: reward = -109.04, steps = 20 00:04:56 [INFO] train episode 1309: reward = -81.70, steps = 25 00:04:57 [INFO] train episode 1310: reward = -75.87, steps = 20 00:04:57 [INFO] train episode 1311: reward = -86.61, steps = 22 00:04:57 [INFO] train episode 1312: reward = -84.55, steps = 20 00:04:57 [INFO] train episode 1313: reward = -80.14, steps = 19 00:04:57 [INFO] train episode 1314: reward = -81.99, steps = 23 00:04:58 [INFO] train episode 1315: reward = -77.76, steps = 27 00:04:58 [INFO] train episode 1316: reward = -137.58, steps = 36 00:04:58 [INFO] train episode 1317: reward = -123.82, steps = 31 00:04:58 [INFO] train episode 1318: reward = -92.05, steps = 20 00:04:58 [INFO] train episode 1319: reward = -76.46, steps = 19 00:04:58 [INFO] train episode 1320: reward = -87.62, steps = 24 00:04:59 [INFO] train episode 1321: reward = -97.09, steps = 24 00:04:59 [INFO] train episode 1322: reward = -90.27, steps = 23 00:04:59 [INFO] train episode 1323: reward = -83.65, steps = 18 00:04:59 [INFO] train episode 1324: reward = -116.66, steps = 20 00:04:59 [INFO] train episode 1325: reward = -162.03, steps = 37 00:04:59 [INFO] train episode 1326: reward = -94.26, steps = 24 00:05:00 [INFO] train episode 1327: reward = -88.63, steps = 21 00:05:00 [INFO] train episode 1328: reward = -90.28, steps = 26 00:05:00 [INFO] train episode 1329: reward = -96.24, steps = 20 00:05:00 [INFO] train episode 1330: reward = -86.97, steps = 27 00:05:00 [INFO] train episode 1331: reward = -128.01, steps = 33 00:05:00 [INFO] train episode 1332: reward = -72.61, steps = 20 00:05:01 [INFO] train episode 1333: reward = -152.02, steps = 36 00:05:01 [INFO] train episode 1334: reward = -78.34, steps = 23 00:05:01 [INFO] train episode 1335: reward = -77.58, steps = 20 00:05:01 [INFO] train episode 1336: reward = -66.92, steps = 20 00:05:01 [INFO] train episode 1337: reward = -73.29, steps = 20 00:05:02 [INFO] train episode 1338: reward = -109.45, steps = 43 00:05:02 [INFO] train episode 1339: reward = -101.05, steps = 22 00:05:02 [INFO] train episode 1340: reward = -83.92, steps = 20 00:05:02 [INFO] train episode 1341: reward = -79.30, steps = 19 00:05:02 [INFO] train episode 1342: reward = -115.58, steps = 26 00:05:02 [INFO] train episode 1343: reward = -123.08, steps = 20 00:05:03 [INFO] train episode 1344: reward = -85.92, steps = 28 00:05:03 [INFO] train episode 1345: reward = -97.95, steps = 26 00:05:03 [INFO] train episode 1346: reward = -93.33, steps = 19 00:05:03 [INFO] train episode 1347: reward = -72.37, steps = 18 00:05:03 [INFO] train episode 1348: reward = -51.41, steps = 18 00:05:03 [INFO] train episode 1349: reward = -92.54, steps = 22 00:05:04 [INFO] train episode 1350: reward = -84.30, steps = 21 00:05:04 [INFO] train episode 1351: reward = -80.32, steps = 22 00:05:04 [INFO] train episode 1352: reward = -75.89, steps = 18 00:05:04 [INFO] train episode 1353: reward = -90.17, steps = 24 00:05:04 [INFO] train episode 1354: reward = -128.00, steps = 22 00:05:04 [INFO] train episode 1355: reward = -122.36, steps = 26 00:05:05 [INFO] train episode 1356: reward = -110.34, steps = 22 00:05:05 [INFO] train episode 1357: reward = -83.57, steps = 24 00:05:05 [INFO] train episode 1358: reward = -122.51, steps = 30 00:05:05 [INFO] train episode 1359: reward = -76.40, steps = 19 00:05:05 [INFO] train episode 1360: reward = -96.62, steps = 21 00:05:06 [INFO] train episode 1361: reward = -86.85, steps = 19 00:05:06 [INFO] train episode 1362: reward = -90.02, steps = 20 00:05:06 [INFO] train episode 1363: reward = -81.16, steps = 22 00:05:06 [INFO] train episode 1364: reward = -131.07, steps = 35 00:05:06 [INFO] train episode 1365: reward = -66.65, steps = 20 00:05:06 [INFO] train episode 1366: reward = -77.89, steps = 22 00:05:07 [INFO] train episode 1367: reward = -110.65, steps = 28 00:05:07 [INFO] train episode 1368: reward = -97.13, steps = 24 00:05:07 [INFO] train episode 1369: reward = -71.20, steps = 20 00:05:07 [INFO] train episode 1370: reward = -110.02, steps = 32 00:05:07 [INFO] train episode 1371: reward = -93.67, steps = 30 00:05:08 [INFO] train episode 1372: reward = -92.52, steps = 22 00:05:08 [INFO] train episode 1373: reward = -125.62, steps = 28 00:05:08 [INFO] train episode 1374: reward = -52.98, steps = 20 00:05:08 [INFO] train episode 1375: reward = -88.65, steps = 22 00:05:08 [INFO] train episode 1376: reward = -114.21, steps = 22 00:05:08 [INFO] train episode 1377: reward = -64.67, steps = 19 00:05:08 [INFO] train episode 1378: reward = -78.45, steps = 19 00:05:09 [INFO] train episode 1379: reward = -60.91, steps = 20 00:05:09 [INFO] train episode 1380: reward = -115.13, steps = 26 00:05:09 [INFO] train episode 1381: reward = -85.78, steps = 20 00:05:09 [INFO] train episode 1382: reward = -108.99, steps = 23 00:05:09 [INFO] train episode 1383: reward = -70.92, steps = 19 00:05:09 [INFO] train episode 1384: reward = -61.04, steps = 17 00:05:10 [INFO] train episode 1385: reward = -69.80, steps = 20 00:05:10 [INFO] train episode 1386: reward = -122.06, steps = 39 00:05:10 [INFO] train episode 1387: reward = -90.70, steps = 21 00:05:10 [INFO] train episode 1388: reward = -79.94, steps = 24 00:05:10 [INFO] train episode 1389: reward = -107.63, steps = 29 00:05:11 [INFO] train episode 1390: reward = -82.72, steps = 21 00:05:11 [INFO] train episode 1391: reward = -78.00, steps = 19 00:05:11 [INFO] train episode 1392: reward = -61.71, steps = 20 00:05:11 [INFO] train episode 1393: reward = -94.85, steps = 21 00:05:11 [INFO] train episode 1394: reward = -75.01, steps = 29 00:05:11 [INFO] train episode 1395: reward = -78.30, steps = 18 00:05:12 [INFO] train episode 1396: reward = -94.40, steps = 20 00:05:12 [INFO] train episode 1397: reward = -107.36, steps = 25 00:05:12 [INFO] train episode 1398: reward = -101.34, steps = 28 00:05:12 [INFO] train episode 1399: reward = -79.57, steps = 19 00:05:12 [INFO] train episode 1400: reward = -71.63, steps = 21 00:05:12 [INFO] train episode 1401: reward = -83.62, steps = 24 00:05:13 [INFO] train episode 1402: reward = -95.18, steps = 24 00:05:13 [INFO] train episode 1403: reward = -65.17, steps = 23 00:05:13 [INFO] train episode 1404: reward = -109.05, steps = 19 00:05:13 [INFO] train episode 1405: reward = -85.85, steps = 21 00:05:13 [INFO] train episode 1406: reward = -79.99, steps = 21 00:05:13 [INFO] train episode 1407: reward = -73.30, steps = 20 00:05:13 [INFO] train episode 1408: reward = -110.76, steps = 28 00:05:14 [INFO] train episode 1409: reward = -101.93, steps = 23 00:05:14 [INFO] train episode 1410: reward = -77.98, steps = 19 00:05:14 [INFO] train episode 1411: reward = -94.44, steps = 24 00:05:14 [INFO] train episode 1412: reward = -66.28, steps = 22 00:05:14 [INFO] train episode 1413: reward = -89.43, steps = 20 00:05:14 [INFO] train episode 1414: reward = -75.50, steps = 23 00:05:15 [INFO] train episode 1415: reward = -216.19, steps = 35 00:05:15 [INFO] train episode 1416: reward = -108.71, steps = 26 00:05:15 [INFO] train episode 1417: reward = -75.69, steps = 21 00:05:15 [INFO] train episode 1418: reward = -101.31, steps = 29 00:05:15 [INFO] train episode 1419: reward = -85.88, steps = 21 00:05:15 [INFO] train episode 1420: reward = -81.70, steps = 22 00:05:16 [INFO] train episode 1421: reward = -111.21, steps = 26 00:05:16 [INFO] train episode 1422: reward = -105.37, steps = 26 00:05:16 [INFO] train episode 1423: reward = -76.17, steps = 26 00:05:16 [INFO] train episode 1424: reward = -95.45, steps = 24 00:05:16 [INFO] train episode 1425: reward = -153.64, steps = 36 00:05:17 [INFO] train episode 1426: reward = -116.79, steps = 31 00:05:17 [INFO] train episode 1427: reward = -95.92, steps = 22 00:05:17 [INFO] train episode 1428: reward = -98.19, steps = 19 00:05:17 [INFO] train episode 1429: reward = -84.99, steps = 21 00:05:17 [INFO] train episode 1430: reward = -109.37, steps = 20 00:05:17 [INFO] train episode 1431: reward = -86.73, steps = 22 00:05:18 [INFO] train episode 1432: reward = -102.91, steps = 23 00:05:18 [INFO] train episode 1433: reward = -73.89, steps = 20 00:05:18 [INFO] train episode 1434: reward = -181.11, steps = 54 00:05:18 [INFO] train episode 1435: reward = -81.37, steps = 20 00:05:18 [INFO] train episode 1436: reward = -81.59, steps = 19 00:05:18 [INFO] train episode 1437: reward = -82.14, steps = 25 00:05:19 [INFO] train episode 1438: reward = -83.28, steps = 19 00:05:19 [INFO] train episode 1439: reward = -96.64, steps = 22 00:05:19 [INFO] train episode 1440: reward = -66.51, steps = 21 00:05:19 [INFO] train episode 1441: reward = -106.89, steps = 28 00:05:19 [INFO] train episode 1442: reward = -72.78, steps = 21 00:05:20 [INFO] train episode 1443: reward = -99.58, steps = 26 00:05:20 [INFO] train episode 1444: reward = -69.26, steps = 19 00:05:20 [INFO] train episode 1445: reward = -162.48, steps = 54 00:05:20 [INFO] train episode 1446: reward = -59.91, steps = 20 00:05:20 [INFO] train episode 1447: reward = -87.33, steps = 20 00:05:20 [INFO] train episode 1448: reward = -77.32, steps = 18 00:05:21 [INFO] train episode 1449: reward = -91.22, steps = 27 00:05:21 [INFO] train episode 1450: reward = -69.36, steps = 19 00:05:21 [INFO] train episode 1451: reward = -132.32, steps = 19 00:05:21 [INFO] train episode 1452: reward = -94.45, steps = 20 00:05:21 [INFO] train episode 1453: reward = -97.89, steps = 23 00:05:21 [INFO] train episode 1454: reward = -63.32, steps = 25 00:05:21 [INFO] train episode 1455: reward = -89.74, steps = 20 00:05:22 [INFO] train episode 1456: reward = -123.26, steps = 30 00:05:22 [INFO] train episode 1457: reward = -133.58, steps = 33 00:05:22 [INFO] train episode 1458: reward = -103.84, steps = 24 00:05:22 [INFO] train episode 1459: reward = -55.96, steps = 17 00:05:22 [INFO] train episode 1460: reward = -113.99, steps = 34 00:05:23 [INFO] train episode 1461: reward = -54.26, steps = 20 00:05:23 [INFO] train episode 1462: reward = -126.68, steps = 26 00:05:23 [INFO] train episode 1463: reward = -77.03, steps = 19 00:05:23 [INFO] train episode 1464: reward = -184.28, steps = 38 00:05:23 [INFO] train episode 1465: reward = -67.10, steps = 20 00:05:24 [INFO] train episode 1466: reward = -124.66, steps = 32 00:05:24 [INFO] train episode 1467: reward = -189.35, steps = 49 00:05:24 [INFO] train episode 1468: reward = -87.48, steps = 21 00:05:24 [INFO] train episode 1469: reward = -67.50, steps = 20 00:05:25 [INFO] train episode 1470: reward = -320.89, steps = 68 00:05:25 [INFO] train episode 1471: reward = -97.59, steps = 29 00:05:25 [INFO] train episode 1472: reward = -95.10, steps = 23 00:05:25 [INFO] train episode 1473: reward = -79.77, steps = 21 00:05:25 [INFO] train episode 1474: reward = -66.61, steps = 20 00:05:26 [INFO] train episode 1475: reward = -127.57, steps = 35 00:05:26 [INFO] train episode 1476: reward = -104.06, steps = 21 00:05:26 [INFO] train episode 1477: reward = -85.95, steps = 23 00:05:26 [INFO] train episode 1478: reward = -76.58, steps = 19 00:05:26 [INFO] train episode 1479: reward = -121.14, steps = 35 00:05:27 [INFO] train episode 1480: reward = -87.59, steps = 24 00:05:27 [INFO] train episode 1481: reward = -105.57, steps = 33 00:05:27 [INFO] train episode 1482: reward = -65.67, steps = 21 00:05:27 [INFO] train episode 1483: reward = -81.93, steps = 23 00:05:27 [INFO] train episode 1484: reward = -75.95, steps = 28 00:05:27 [INFO] train episode 1485: reward = -86.68, steps = 24 00:05:28 [INFO] train episode 1486: reward = -91.28, steps = 19 00:05:28 [INFO] train episode 1487: reward = -82.88, steps = 18 00:05:28 [INFO] train episode 1488: reward = -105.62, steps = 39 00:05:28 [INFO] train episode 1489: reward = -95.79, steps = 31 00:05:28 [INFO] train episode 1490: reward = -88.02, steps = 21 00:05:29 [INFO] train episode 1491: reward = -121.93, steps = 43 00:05:29 [INFO] train episode 1492: reward = -110.41, steps = 23 00:05:29 [INFO] train episode 1493: reward = -86.82, steps = 21 00:05:29 [INFO] train episode 1494: reward = -116.59, steps = 26 00:05:29 [INFO] train episode 1495: reward = -65.53, steps = 20 00:05:29 [INFO] train episode 1496: reward = -75.01, steps = 20 00:05:30 [INFO] train episode 1497: reward = -70.02, steps = 21 00:05:30 [INFO] train episode 1498: reward = -83.36, steps = 21 00:05:30 [INFO] train episode 1499: reward = -91.27, steps = 23 00:05:30 [INFO] train episode 1500: reward = -155.68, steps = 45 00:05:30 [INFO] train episode 1501: reward = -89.24, steps = 30 00:05:31 [INFO] train episode 1502: reward = -51.55, steps = 20 00:05:31 [INFO] train episode 1503: reward = -108.67, steps = 30 00:05:31 [INFO] train episode 1504: reward = -115.68, steps = 40 00:05:31 [INFO] train episode 1505: reward = -82.63, steps = 20 00:05:31 [INFO] train episode 1506: reward = -69.57, steps = 19 00:05:31 [INFO] train episode 1507: reward = -92.80, steps = 20 00:05:32 [INFO] train episode 1508: reward = -75.23, steps = 30 00:05:32 [INFO] train episode 1509: reward = -61.04, steps = 20 00:05:32 [INFO] train episode 1510: reward = -101.37, steps = 35 00:05:32 [INFO] train episode 1511: reward = -99.94, steps = 20 00:05:32 [INFO] train episode 1512: reward = -70.34, steps = 21 00:05:33 [INFO] train episode 1513: reward = -101.76, steps = 25 00:05:33 [INFO] train episode 1514: reward = -82.98, steps = 21 00:05:33 [INFO] train episode 1515: reward = -63.50, steps = 20 00:05:33 [INFO] train episode 1516: reward = -81.78, steps = 27 00:05:33 [INFO] train episode 1517: reward = -87.96, steps = 22 00:05:33 [INFO] train episode 1518: reward = -92.11, steps = 26 00:05:34 [INFO] train episode 1519: reward = -59.03, steps = 27 00:05:34 [INFO] train episode 1520: reward = -68.29, steps = 20 00:05:34 [INFO] train episode 1521: reward = -67.13, steps = 20 00:05:34 [INFO] train episode 1522: reward = -95.73, steps = 24 00:05:34 [INFO] train episode 1523: reward = -87.16, steps = 24 00:05:34 [INFO] train episode 1524: reward = -101.07, steps = 30 00:05:35 [INFO] train episode 1525: reward = -145.40, steps = 40 00:05:35 [INFO] train episode 1526: reward = -68.32, steps = 19 00:05:35 [INFO] train episode 1527: reward = -76.42, steps = 22 00:05:35 [INFO] train episode 1528: reward = -81.60, steps = 29 00:05:35 [INFO] train episode 1529: reward = -81.16, steps = 21 00:05:36 [INFO] train episode 1530: reward = -129.10, steps = 36 00:05:36 [INFO] train episode 1531: reward = -93.20, steps = 25 00:05:36 [INFO] train episode 1532: reward = -99.84, steps = 26 00:05:36 [INFO] train episode 1533: reward = -90.43, steps = 24 00:05:36 [INFO] train episode 1534: reward = -102.61, steps = 45 00:05:37 [INFO] train episode 1535: reward = -98.64, steps = 26 00:05:37 [INFO] train episode 1536: reward = -72.59, steps = 22 00:05:37 [INFO] train episode 1537: reward = -89.17, steps = 22 00:05:37 [INFO] train episode 1538: reward = -127.58, steps = 28 00:05:37 [INFO] train episode 1539: reward = -123.26, steps = 24 00:05:37 [INFO] train episode 1540: reward = -113.26, steps = 25 00:05:38 [INFO] train episode 1541: reward = -80.30, steps = 20 00:05:38 [INFO] train episode 1542: reward = -85.12, steps = 22 00:05:38 [INFO] train episode 1543: reward = -67.81, steps = 23 00:05:38 [INFO] train episode 1544: reward = -100.71, steps = 26 00:05:38 [INFO] train episode 1545: reward = -60.77, steps = 22 00:05:39 [INFO] train episode 1546: reward = -80.27, steps = 24 00:05:39 [INFO] train episode 1547: reward = -89.04, steps = 20 00:05:39 [INFO] train episode 1548: reward = -136.18, steps = 37 00:05:39 [INFO] train episode 1549: reward = -80.34, steps = 20 00:05:39 [INFO] train episode 1550: reward = -80.08, steps = 20 00:05:39 [INFO] train episode 1551: reward = -97.06, steps = 21 00:05:40 [INFO] train episode 1552: reward = -134.11, steps = 38 00:05:40 [INFO] train episode 1553: reward = -131.51, steps = 30 00:05:40 [INFO] train episode 1554: reward = -82.44, steps = 22 00:05:40 [INFO] train episode 1555: reward = -87.98, steps = 21 00:05:40 [INFO] train episode 1556: reward = -73.84, steps = 20 00:05:40 [INFO] train episode 1557: reward = -58.50, steps = 21 00:05:41 [INFO] train episode 1558: reward = -63.87, steps = 22 00:05:41 [INFO] train episode 1559: reward = -94.59, steps = 26 00:05:41 [INFO] train episode 1560: reward = -61.71, steps = 19 00:05:41 [INFO] train episode 1561: reward = -95.99, steps = 19 00:05:41 [INFO] train episode 1562: reward = -87.72, steps = 22 00:05:41 [INFO] train episode 1563: reward = -91.48, steps = 36 00:05:42 [INFO] train episode 1564: reward = -70.46, steps = 22 00:05:42 [INFO] train episode 1565: reward = -90.35, steps = 23 00:05:42 [INFO] train episode 1566: reward = -202.57, steps = 53 00:05:42 [INFO] train episode 1567: reward = -90.19, steps = 29 00:05:43 [INFO] train episode 1568: reward = -67.04, steps = 20 00:05:43 [INFO] train episode 1569: reward = -86.79, steps = 20 00:05:43 [INFO] train episode 1570: reward = -74.07, steps = 21 00:05:43 [INFO] train episode 1571: reward = -74.99, steps = 20 00:05:43 [INFO] train episode 1572: reward = -82.14, steps = 24 00:05:43 [INFO] train episode 1573: reward = -115.74, steps = 29 00:05:44 [INFO] train episode 1574: reward = -109.94, steps = 29 00:05:44 [INFO] train episode 1575: reward = -84.04, steps = 20 00:05:44 [INFO] train episode 1576: reward = -69.70, steps = 21 00:05:44 [INFO] train episode 1577: reward = -80.34, steps = 21 00:05:44 [INFO] train episode 1578: reward = -109.48, steps = 34 00:05:44 [INFO] train episode 1579: reward = -103.13, steps = 26 00:05:45 [INFO] train episode 1580: reward = -75.20, steps = 25 00:05:45 [INFO] train episode 1581: reward = -149.47, steps = 36 00:05:45 [INFO] train episode 1582: reward = -69.02, steps = 23 00:05:45 [INFO] train episode 1583: reward = -96.99, steps = 24 00:05:45 [INFO] train episode 1584: reward = -56.27, steps = 21 00:05:46 [INFO] train episode 1585: reward = -114.11, steps = 36 00:05:46 [INFO] train episode 1586: reward = -69.56, steps = 20 00:05:46 [INFO] train episode 1587: reward = -84.64, steps = 24 00:05:46 [INFO] train episode 1588: reward = -118.50, steps = 29 00:05:46 [INFO] train episode 1589: reward = -97.00, steps = 29 00:05:46 [INFO] train episode 1590: reward = -107.67, steps = 25 00:05:47 [INFO] train episode 1591: reward = -100.87, steps = 29 00:05:47 [INFO] train episode 1592: reward = -119.77, steps = 25 00:05:47 [INFO] train episode 1593: reward = -63.82, steps = 19 00:05:47 [INFO] train episode 1594: reward = -97.76, steps = 25 00:05:47 [INFO] train episode 1595: reward = -83.16, steps = 29 00:05:47 [INFO] train episode 1596: reward = -111.06, steps = 34 00:05:48 [INFO] train episode 1597: reward = -73.56, steps = 20 00:05:48 [INFO] train episode 1598: reward = -91.61, steps = 28 00:05:48 [INFO] train episode 1599: reward = -89.39, steps = 20 00:05:48 [INFO] train episode 1600: reward = -96.65, steps = 23 00:05:48 [INFO] train episode 1601: reward = -102.75, steps = 27 00:05:49 [INFO] train episode 1602: reward = -84.38, steps = 20 00:05:49 [INFO] train episode 1603: reward = -146.90, steps = 34 00:05:49 [INFO] train episode 1604: reward = -95.06, steps = 29 00:05:49 [INFO] train episode 1605: reward = -87.79, steps = 21 00:05:49 [INFO] train episode 1606: reward = -87.30, steps = 28 00:05:49 [INFO] train episode 1607: reward = -85.99, steps = 21 00:05:50 [INFO] train episode 1608: reward = -122.60, steps = 31 00:05:50 [INFO] train episode 1609: reward = -79.52, steps = 26 00:05:50 [INFO] train episode 1610: reward = -93.94, steps = 30 00:05:50 [INFO] train episode 1611: reward = -126.99, steps = 45 00:05:51 [INFO] train episode 1612: reward = -62.33, steps = 21 00:05:51 [INFO] train episode 1613: reward = -81.43, steps = 22 00:05:51 [INFO] train episode 1614: reward = -91.35, steps = 29 00:05:51 [INFO] train episode 1615: reward = -118.33, steps = 34 00:05:51 [INFO] train episode 1616: reward = -105.82, steps = 25 00:05:51 [INFO] train episode 1617: reward = -92.66, steps = 21 00:05:52 [INFO] train episode 1618: reward = -68.33, steps = 21 00:05:52 [INFO] train episode 1619: reward = -109.52, steps = 26 00:05:52 [INFO] train episode 1620: reward = -107.84, steps = 22 00:05:52 [INFO] train episode 1621: reward = -71.76, steps = 29 00:05:53 [INFO] train episode 1622: reward = -82.14, steps = 26 00:05:53 [INFO] train episode 1623: reward = -105.83, steps = 30 00:05:53 [INFO] train episode 1624: reward = -98.15, steps = 30 00:05:53 [INFO] train episode 1625: reward = -271.81, steps = 66 00:05:54 [INFO] train episode 1626: reward = -71.68, steps = 22 00:05:54 [INFO] train episode 1627: reward = -116.61, steps = 33 00:05:54 [INFO] train episode 1628: reward = -84.16, steps = 23 00:05:54 [INFO] train episode 1629: reward = -61.65, steps = 21 00:05:54 [INFO] train episode 1630: reward = -83.74, steps = 20 00:05:54 [INFO] train episode 1631: reward = -197.52, steps = 41 00:05:55 [INFO] train episode 1632: reward = -54.28, steps = 21 00:05:55 [INFO] train episode 1633: reward = -113.54, steps = 28 00:05:55 [INFO] train episode 1634: reward = -146.09, steps = 25 00:05:55 [INFO] train episode 1635: reward = -140.62, steps = 32 00:05:55 [INFO] train episode 1636: reward = -78.13, steps = 21 00:05:55 [INFO] train episode 1637: reward = -79.70, steps = 23 00:05:56 [INFO] train episode 1638: reward = -131.15, steps = 25 00:05:56 [INFO] train episode 1639: reward = -54.29, steps = 21 00:05:56 [INFO] train episode 1640: reward = -79.96, steps = 22 00:05:56 [INFO] train episode 1641: reward = -62.10, steps = 21 00:05:56 [INFO] train episode 1642: reward = -178.14, steps = 41 00:05:57 [INFO] train episode 1643: reward = -136.49, steps = 39 00:05:57 [INFO] train episode 1644: reward = -67.00, steps = 22 00:05:57 [INFO] train episode 1645: reward = -47.79, steps = 18 00:05:57 [INFO] train episode 1646: reward = -105.86, steps = 27 00:05:57 [INFO] train episode 1647: reward = -99.85, steps = 29 00:05:58 [INFO] train episode 1648: reward = -187.13, steps = 45 00:05:58 [INFO] train episode 1649: reward = -60.48, steps = 21 00:05:58 [INFO] train episode 1650: reward = -85.66, steps = 23 00:05:58 [INFO] train episode 1651: reward = -72.91, steps = 30 00:05:58 [INFO] train episode 1652: reward = -126.28, steps = 38 00:05:58 [INFO] train episode 1653: reward = -123.41, steps = 32 00:05:59 [INFO] train episode 1654: reward = -67.33, steps = 21 00:05:59 [INFO] train episode 1655: reward = -85.55, steps = 20 00:05:59 [INFO] train episode 1656: reward = -67.64, steps = 21 00:05:59 [INFO] train episode 1657: reward = -76.68, steps = 28 00:05:59 [INFO] train episode 1658: reward = -67.63, steps = 22 00:05:59 [INFO] train episode 1659: reward = -80.39, steps = 21 00:06:00 [INFO] train episode 1660: reward = -124.03, steps = 20 00:06:00 [INFO] train episode 1661: reward = -110.49, steps = 35 00:06:00 [INFO] train episode 1662: reward = -84.43, steps = 22 00:06:00 [INFO] train episode 1663: reward = -125.02, steps = 27 00:06:00 [INFO] train episode 1664: reward = -96.43, steps = 26 00:06:01 [INFO] train episode 1665: reward = -124.56, steps = 25 00:06:01 [INFO] train episode 1666: reward = -113.83, steps = 50 00:06:01 [INFO] train episode 1667: reward = -198.48, steps = 39 00:06:01 [INFO] train episode 1668: reward = -113.54, steps = 25 00:06:01 [INFO] train episode 1669: reward = -85.18, steps = 19 00:06:02 [INFO] train episode 1670: reward = -86.18, steps = 24 00:06:02 [INFO] train episode 1671: reward = -93.59, steps = 29 00:06:02 [INFO] train episode 1672: reward = -58.48, steps = 21 00:06:02 [INFO] train episode 1673: reward = -123.03, steps = 28 00:06:02 [INFO] train episode 1674: reward = -82.23, steps = 23 00:06:02 [INFO] train episode 1675: reward = -73.42, steps = 25 00:06:03 [INFO] train episode 1676: reward = -74.28, steps = 23 00:06:03 [INFO] train episode 1677: reward = -142.15, steps = 36 00:06:03 [INFO] train episode 1678: reward = -153.05, steps = 49 00:06:03 [INFO] train episode 1679: reward = -108.97, steps = 31 00:06:04 [INFO] train episode 1680: reward = -112.87, steps = 37 00:06:04 [INFO] train episode 1681: reward = -94.59, steps = 32 00:06:04 [INFO] train episode 1682: reward = -49.54, steps = 22 00:06:04 [INFO] train episode 1683: reward = -76.14, steps = 20 00:06:04 [INFO] train episode 1684: reward = -82.24, steps = 24 00:06:04 [INFO] train episode 1685: reward = -89.06, steps = 26 00:06:05 [INFO] train episode 1686: reward = -105.60, steps = 25 00:06:05 [INFO] train episode 1687: reward = -74.45, steps = 22 00:06:05 [INFO] train episode 1688: reward = -101.06, steps = 21 00:06:05 [INFO] train episode 1689: reward = -76.37, steps = 18 00:06:05 [INFO] train episode 1690: reward = -115.93, steps = 24 00:06:06 [INFO] train episode 1691: reward = -48.77, steps = 22 00:06:06 [INFO] train episode 1692: reward = -79.12, steps = 24 00:06:06 [INFO] train episode 1693: reward = -86.24, steps = 21 00:06:06 [INFO] train episode 1694: reward = -59.46, steps = 21 00:06:06 [INFO] train episode 1695: reward = -68.13, steps = 25 00:06:07 [INFO] train episode 1696: reward = -380.77, steps = 99 00:06:07 [INFO] train episode 1697: reward = -58.43, steps = 16 00:06:07 [INFO] train episode 1698: reward = -80.15, steps = 24 00:06:07 [INFO] train episode 1699: reward = -85.01, steps = 30 00:06:07 [INFO] train episode 1700: reward = -84.82, steps = 25 00:06:08 [INFO] train episode 1701: reward = -179.78, steps = 53 00:06:08 [INFO] train episode 1702: reward = -67.72, steps = 21 00:06:08 [INFO] train episode 1703: reward = -100.34, steps = 21 00:06:08 [INFO] train episode 1704: reward = -92.75, steps = 28 00:06:08 [INFO] train episode 1705: reward = -61.35, steps = 19 00:06:09 [INFO] train episode 1706: reward = -100.22, steps = 37 00:06:09 [INFO] train episode 1707: reward = -79.14, steps = 22 00:06:09 [INFO] train episode 1708: reward = -67.68, steps = 21 00:06:09 [INFO] train episode 1709: reward = -84.45, steps = 22 00:06:09 [INFO] train episode 1710: reward = -88.31, steps = 25 00:06:10 [INFO] train episode 1711: reward = -97.37, steps = 30 00:06:10 [INFO] train episode 1712: reward = -116.46, steps = 20 00:06:10 [INFO] train episode 1713: reward = -142.86, steps = 38 00:06:10 [INFO] train episode 1714: reward = -89.49, steps = 32 00:06:10 [INFO] train episode 1715: reward = -129.63, steps = 35 00:06:10 [INFO] train episode 1716: reward = -63.22, steps = 21 00:06:11 [INFO] train episode 1717: reward = -45.49, steps = 20 00:06:11 [INFO] train episode 1718: reward = -109.19, steps = 41 00:06:11 [INFO] train episode 1719: reward = -68.93, steps = 19 00:06:11 [INFO] train episode 1720: reward = -78.34, steps = 18 00:06:11 [INFO] train episode 1721: reward = -104.42, steps = 38 00:06:12 [INFO] train episode 1722: reward = -51.36, steps = 20 00:06:12 [INFO] train episode 1723: reward = -86.17, steps = 21 00:06:12 [INFO] train episode 1724: reward = -111.19, steps = 34 00:06:12 [INFO] train episode 1725: reward = -109.10, steps = 33 00:06:12 [INFO] train episode 1726: reward = -71.02, steps = 20 00:06:13 [INFO] train episode 1727: reward = -153.80, steps = 38 00:06:13 [INFO] train episode 1728: reward = -75.59, steps = 21 00:06:13 [INFO] train episode 1729: reward = -78.49, steps = 22 00:06:13 [INFO] train episode 1730: reward = -97.32, steps = 20 00:06:13 [INFO] train episode 1731: reward = -51.57, steps = 20 00:06:13 [INFO] train episode 1732: reward = -59.22, steps = 19 00:06:13 [INFO] train episode 1733: reward = -66.68, steps = 20 00:06:14 [INFO] train episode 1734: reward = -124.65, steps = 33 00:06:14 [INFO] train episode 1735: reward = -87.10, steps = 22 00:06:14 [INFO] train episode 1736: reward = -92.07, steps = 32 00:06:14 [INFO] train episode 1737: reward = -101.36, steps = 22 00:06:14 [INFO] train episode 1738: reward = -150.21, steps = 37 00:06:15 [INFO] train episode 1739: reward = -68.38, steps = 25 00:06:15 [INFO] train episode 1740: reward = -65.09, steps = 22 00:06:15 [INFO] train episode 1741: reward = -76.71, steps = 24 00:06:15 [INFO] train episode 1742: reward = -138.29, steps = 39 00:06:15 [INFO] train episode 1743: reward = -116.76, steps = 34 00:06:16 [INFO] train episode 1744: reward = -84.24, steps = 23 00:06:16 [INFO] train episode 1745: reward = -115.14, steps = 35 00:06:16 [INFO] train episode 1746: reward = -63.56, steps = 22 00:06:16 [INFO] train episode 1747: reward = -70.25, steps = 22 00:06:16 [INFO] train episode 1748: reward = -77.48, steps = 22 00:06:16 [INFO] train episode 1749: reward = -74.86, steps = 20 00:06:17 [INFO] train episode 1750: reward = -148.13, steps = 36 00:06:17 [INFO] train episode 1751: reward = -89.77, steps = 24 00:06:17 [INFO] train episode 1752: reward = -85.00, steps = 21 00:06:17 [INFO] train episode 1753: reward = -85.21, steps = 22 00:06:17 [INFO] train episode 1754: reward = -104.55, steps = 34 00:06:18 [INFO] train episode 1755: reward = -96.35, steps = 30 00:06:18 [INFO] train episode 1756: reward = -110.99, steps = 30 00:06:18 [INFO] train episode 1757: reward = -66.36, steps = 23 00:06:18 [INFO] train episode 1758: reward = -53.90, steps = 23 00:06:18 [INFO] train episode 1759: reward = -64.68, steps = 21 00:06:19 [INFO] train episode 1760: reward = -135.35, steps = 33 00:06:19 [INFO] train episode 1761: reward = -88.96, steps = 30 00:06:19 [INFO] train episode 1762: reward = -114.51, steps = 46 00:06:20 [INFO] train episode 1763: reward = -218.47, steps = 60 00:06:20 [INFO] train episode 1764: reward = -82.13, steps = 23 00:06:20 [INFO] train episode 1765: reward = -83.41, steps = 21 00:06:20 [INFO] train episode 1766: reward = -86.65, steps = 23 00:06:20 [INFO] train episode 1767: reward = -82.85, steps = 28 00:06:20 [INFO] train episode 1768: reward = -91.73, steps = 26 00:06:21 [INFO] train episode 1769: reward = -120.25, steps = 39 00:06:21 [INFO] train episode 1770: reward = -74.46, steps = 20 00:06:21 [INFO] train episode 1771: reward = -63.13, steps = 29 00:06:21 [INFO] train episode 1772: reward = -131.43, steps = 49 00:06:22 [INFO] train episode 1773: reward = -124.24, steps = 37 00:06:22 [INFO] train episode 1774: reward = -87.73, steps = 19 00:06:22 [INFO] train episode 1775: reward = -60.08, steps = 18 00:06:22 [INFO] train episode 1776: reward = -63.56, steps = 19 00:06:22 [INFO] train episode 1777: reward = -81.91, steps = 20 00:06:22 [INFO] train episode 1778: reward = -84.60, steps = 28 00:06:23 [INFO] train episode 1779: reward = -135.45, steps = 40 00:06:23 [INFO] train episode 1780: reward = -95.42, steps = 38 00:06:23 [INFO] train episode 1781: reward = -147.96, steps = 50 00:06:23 [INFO] train episode 1782: reward = -85.44, steps = 25 00:06:24 [INFO] train episode 1783: reward = -137.16, steps = 46 00:06:24 [INFO] train episode 1784: reward = -115.84, steps = 31 00:06:24 [INFO] train episode 1785: reward = -74.88, steps = 24 00:06:24 [INFO] train episode 1786: reward = -82.61, steps = 33 00:06:25 [INFO] train episode 1787: reward = -119.00, steps = 42 00:06:25 [INFO] train episode 1788: reward = -78.41, steps = 21 00:06:25 [INFO] train episode 1789: reward = -150.48, steps = 50 00:06:25 [INFO] train episode 1790: reward = -70.49, steps = 22 00:06:25 [INFO] train episode 1791: reward = -95.52, steps = 26 00:06:26 [INFO] train episode 1792: reward = -84.45, steps = 41 00:06:26 [INFO] train episode 1793: reward = -85.30, steps = 26 00:06:26 [INFO] train episode 1794: reward = -86.46, steps = 28 00:06:26 [INFO] train episode 1795: reward = -91.50, steps = 21 00:06:26 [INFO] train episode 1796: reward = -138.27, steps = 40 00:06:27 [INFO] train episode 1797: reward = -77.26, steps = 20 00:06:27 [INFO] train episode 1798: reward = -122.06, steps = 42 00:06:27 [INFO] train episode 1799: reward = -71.67, steps = 26 00:06:27 [INFO] train episode 1800: reward = -66.29, steps = 22 00:06:27 [INFO] train episode 1801: reward = -118.01, steps = 33 00:06:28 [INFO] train episode 1802: reward = -134.94, steps = 57 00:06:28 [INFO] train episode 1803: reward = -137.63, steps = 34 00:06:28 [INFO] train episode 1804: reward = -156.48, steps = 37 00:06:28 [INFO] train episode 1805: reward = -83.02, steps = 21 00:06:29 [INFO] train episode 1806: reward = -88.79, steps = 27 00:06:29 [INFO] train episode 1807: reward = -132.94, steps = 38 00:06:29 [INFO] train episode 1808: reward = -90.85, steps = 34 00:06:29 [INFO] train episode 1809: reward = -55.65, steps = 20 00:06:30 [INFO] train episode 1810: reward = -138.02, steps = 28 00:06:30 [INFO] train episode 1811: reward = -63.26, steps = 19 00:06:30 [INFO] train episode 1812: reward = -127.26, steps = 49 00:06:30 [INFO] train episode 1813: reward = -176.14, steps = 46 00:06:30 [INFO] train episode 1814: reward = -88.07, steps = 33 00:06:31 [INFO] train episode 1815: reward = -111.71, steps = 25 00:06:31 [INFO] train episode 1816: reward = -152.45, steps = 51 00:06:31 [INFO] train episode 1817: reward = -77.86, steps = 29 00:06:31 [INFO] train episode 1818: reward = -60.95, steps = 21 00:06:31 [INFO] train episode 1819: reward = -73.23, steps = 21 00:06:32 [INFO] train episode 1820: reward = -84.35, steps = 21 00:06:32 [INFO] train episode 1821: reward = -136.43, steps = 46 00:06:32 [INFO] train episode 1822: reward = -104.26, steps = 34 00:06:33 [INFO] train episode 1823: reward = -63.04, steps = 24 00:06:33 [INFO] train episode 1824: reward = -155.05, steps = 38 00:06:33 [INFO] train episode 1825: reward = -68.90, steps = 20 00:06:33 [INFO] train episode 1826: reward = -101.21, steps = 39 00:06:34 [INFO] train episode 1827: reward = -171.19, steps = 44 00:06:34 [INFO] train episode 1828: reward = -73.82, steps = 27 00:06:34 [INFO] train episode 1829: reward = -185.22, steps = 62 00:06:34 [INFO] train episode 1830: reward = -74.92, steps = 20 00:06:34 [INFO] train episode 1831: reward = -132.58, steps = 38 00:06:35 [INFO] train episode 1832: reward = -116.52, steps = 35 00:06:35 [INFO] train episode 1833: reward = -89.19, steps = 33 00:06:35 [INFO] train episode 1834: reward = -85.61, steps = 31 00:06:35 [INFO] train episode 1835: reward = -111.95, steps = 28 00:06:36 [INFO] train episode 1836: reward = -103.46, steps = 48 00:06:36 [INFO] train episode 1837: reward = -201.59, steps = 55 00:06:36 [INFO] train episode 1838: reward = -133.19, steps = 41 00:06:36 [INFO] train episode 1839: reward = -97.09, steps = 24 00:06:37 [INFO] train episode 1840: reward = -122.57, steps = 39 00:06:37 [INFO] train episode 1841: reward = -114.90, steps = 42 00:06:37 [INFO] train episode 1842: reward = -87.76, steps = 26 00:06:37 [INFO] train episode 1843: reward = -109.42, steps = 30 00:06:38 [INFO] train episode 1844: reward = -101.32, steps = 25 00:06:38 [INFO] train episode 1845: reward = -87.50, steps = 27 00:06:38 [INFO] train episode 1846: reward = -71.36, steps = 19 00:06:38 [INFO] train episode 1847: reward = -166.38, steps = 37 00:06:38 [INFO] train episode 1848: reward = -101.18, steps = 25 00:06:39 [INFO] train episode 1849: reward = -145.22, steps = 42 00:06:39 [INFO] train episode 1850: reward = -95.57, steps = 26 00:06:39 [INFO] train episode 1851: reward = -103.25, steps = 36 00:06:39 [INFO] train episode 1852: reward = -81.35, steps = 20 00:06:39 [INFO] train episode 1853: reward = -88.68, steps = 28 00:06:40 [INFO] train episode 1854: reward = -135.12, steps = 45 00:06:40 [INFO] train episode 1855: reward = -178.70, steps = 55 00:06:40 [INFO] train episode 1856: reward = -179.92, steps = 53 00:06:40 [INFO] train episode 1857: reward = -110.59, steps = 23 00:06:41 [INFO] train episode 1858: reward = -140.95, steps = 41 00:06:41 [INFO] train episode 1859: reward = -92.09, steps = 24 00:06:41 [INFO] train episode 1860: reward = -75.18, steps = 25 00:06:42 [INFO] train episode 1861: reward = -212.33, steps = 81 00:06:42 [INFO] train episode 1862: reward = -109.38, steps = 24 00:06:42 [INFO] train episode 1863: reward = -120.55, steps = 45 00:06:42 [INFO] train episode 1864: reward = -119.91, steps = 36 00:06:43 [INFO] train episode 1865: reward = -201.38, steps = 70 00:06:43 [INFO] train episode 1866: reward = -157.50, steps = 49 00:06:43 [INFO] train episode 1867: reward = -85.29, steps = 30 00:06:43 [INFO] train episode 1868: reward = -72.15, steps = 21 00:06:44 [INFO] train episode 1869: reward = -120.24, steps = 38 00:06:44 [INFO] train episode 1870: reward = -95.75, steps = 28 00:06:44 [INFO] train episode 1871: reward = -78.08, steps = 28 00:06:44 [INFO] train episode 1872: reward = -107.01, steps = 28 00:06:44 [INFO] train episode 1873: reward = -74.20, steps = 40 00:06:45 [INFO] train episode 1874: reward = -79.81, steps = 24 00:06:45 [INFO] train episode 1875: reward = -74.98, steps = 30 00:06:45 [INFO] train episode 1876: reward = -97.44, steps = 23 00:06:46 [INFO] train episode 1877: reward = -174.95, steps = 52 00:06:46 [INFO] train episode 1878: reward = -228.89, steps = 65 00:06:46 [INFO] train episode 1879: reward = -124.48, steps = 30 00:06:47 [INFO] train episode 1880: reward = -143.59, steps = 57 00:06:47 [INFO] train episode 1881: reward = -112.36, steps = 35 00:06:47 [INFO] train episode 1882: reward = -92.58, steps = 37 00:06:47 [INFO] train episode 1883: reward = -121.65, steps = 38 00:06:47 [INFO] train episode 1884: reward = -89.22, steps = 22 00:06:48 [INFO] train episode 1885: reward = -117.23, steps = 32 00:06:48 [INFO] train episode 1886: reward = -171.39, steps = 45 00:06:48 [INFO] train episode 1887: reward = -63.81, steps = 18 00:06:48 [INFO] train episode 1888: reward = -182.95, steps = 50 00:06:49 [INFO] train episode 1889: reward = -115.62, steps = 26 00:06:49 [INFO] train episode 1890: reward = -131.11, steps = 42 00:06:49 [INFO] train episode 1891: reward = -71.49, steps = 25 00:06:49 [INFO] train episode 1892: reward = -205.55, steps = 43 00:06:49 [INFO] train episode 1893: reward = -66.19, steps = 29 00:06:50 [INFO] train episode 1894: reward = -261.80, steps = 86 00:06:50 [INFO] train episode 1895: reward = -96.61, steps = 23 00:06:50 [INFO] train episode 1896: reward = -153.20, steps = 44 00:06:51 [INFO] train episode 1897: reward = -89.09, steps = 24 00:06:51 [INFO] train episode 1898: reward = -99.15, steps = 29 00:06:51 [INFO] train episode 1899: reward = -107.11, steps = 34 00:06:51 [INFO] train episode 1900: reward = -74.76, steps = 26 00:06:51 [INFO] train episode 1901: reward = -106.18, steps = 32 00:06:52 [INFO] train episode 1902: reward = -87.69, steps = 43 00:06:52 [INFO] train episode 1903: reward = -109.73, steps = 32 00:06:52 [INFO] train episode 1904: reward = -166.79, steps = 37 00:06:52 [INFO] train episode 1905: reward = -99.36, steps = 38 00:06:53 [INFO] train episode 1906: reward = -117.04, steps = 45 00:06:53 [INFO] train episode 1907: reward = -145.29, steps = 56 00:06:53 [INFO] train episode 1908: reward = -190.62, steps = 51 00:06:54 [INFO] train episode 1909: reward = -174.78, steps = 61 00:06:54 [INFO] train episode 1910: reward = -143.01, steps = 45 00:06:54 [INFO] train episode 1911: reward = -190.10, steps = 52 00:06:55 [INFO] train episode 1912: reward = -97.15, steps = 20 00:06:55 [INFO] train episode 1913: reward = -154.67, steps = 40 00:06:55 [INFO] train episode 1914: reward = -68.94, steps = 21 00:06:55 [INFO] train episode 1915: reward = -163.86, steps = 55 00:06:55 [INFO] train episode 1916: reward = -57.29, steps = 25 00:06:56 [INFO] train episode 1917: reward = -123.77, steps = 35 00:06:56 [INFO] train episode 1918: reward = -64.50, steps = 31 00:06:56 [INFO] train episode 1919: reward = -213.68, steps = 50 00:06:56 [INFO] train episode 1920: reward = -66.23, steps = 22 00:06:57 [INFO] train episode 1921: reward = -100.13, steps = 31 00:06:57 [INFO] train episode 1922: reward = -86.29, steps = 23 00:06:57 [INFO] train episode 1923: reward = -164.89, steps = 37 00:06:57 [INFO] train episode 1924: reward = -125.06, steps = 40 00:06:57 [INFO] train episode 1925: reward = -103.16, steps = 26 00:06:58 [INFO] train episode 1926: reward = -280.97, steps = 58 00:06:58 [INFO] train episode 1927: reward = -79.12, steps = 19 00:06:58 [INFO] train episode 1928: reward = -113.81, steps = 29 00:06:59 [INFO] train episode 1929: reward = -115.86, steps = 40 00:06:59 [INFO] train episode 1930: reward = -103.51, steps = 25 00:06:59 [INFO] train episode 1931: reward = -109.34, steps = 39 00:06:59 [INFO] train episode 1932: reward = -102.14, steps = 20 00:07:00 [INFO] train episode 1933: reward = -129.19, steps = 56 00:07:00 [INFO] train episode 1934: reward = -206.19, steps = 66 00:07:00 [INFO] train episode 1935: reward = -182.61, steps = 55 00:07:00 [INFO] train episode 1936: reward = -72.73, steps = 27 00:07:01 [INFO] train episode 1937: reward = -144.42, steps = 50 00:07:01 [INFO] train episode 1938: reward = -138.60, steps = 39 00:07:01 [INFO] train episode 1939: reward = -118.18, steps = 23 00:07:01 [INFO] train episode 1940: reward = -106.35, steps = 41 00:07:02 [INFO] train episode 1941: reward = -121.07, steps = 60 00:07:02 [INFO] train episode 1942: reward = -79.36, steps = 42 00:07:03 [INFO] train episode 1943: reward = -234.81, steps = 87 00:07:03 [INFO] train episode 1944: reward = -91.46, steps = 28 00:07:03 [INFO] train episode 1945: reward = -109.33, steps = 33 00:07:03 [INFO] train episode 1946: reward = -146.34, steps = 34 00:07:04 [INFO] train episode 1947: reward = -171.13, steps = 40 00:07:04 [INFO] train episode 1948: reward = -101.69, steps = 46 00:07:04 [INFO] train episode 1949: reward = -82.61, steps = 39 00:07:04 [INFO] train episode 1950: reward = -85.89, steps = 31 00:07:05 [INFO] train episode 1951: reward = -154.75, steps = 37 00:07:05 [INFO] train episode 1952: reward = -89.69, steps = 27 00:07:05 [INFO] train episode 1953: reward = -154.57, steps = 38 00:07:06 [INFO] train episode 1954: reward = -227.33, steps = 68 00:07:06 [INFO] train episode 1955: reward = -114.04, steps = 38 00:07:06 [INFO] train episode 1956: reward = -96.34, steps = 31 00:07:06 [INFO] train episode 1957: reward = -118.44, steps = 35 00:07:07 [INFO] train episode 1958: reward = -104.02, steps = 29 00:07:07 [INFO] train episode 1959: reward = -70.31, steps = 25 00:07:07 [INFO] train episode 1960: reward = -89.50, steps = 29 00:07:07 [INFO] train episode 1961: reward = -68.74, steps = 40 00:07:07 [INFO] train episode 1962: reward = -92.35, steps = 28 00:07:08 [INFO] train episode 1963: reward = -129.38, steps = 42 00:07:08 [INFO] train episode 1964: reward = -106.27, steps = 36 00:07:08 [INFO] train episode 1965: reward = -65.45, steps = 19 00:07:08 [INFO] train episode 1966: reward = -194.49, steps = 62 00:07:09 [INFO] train episode 1967: reward = -127.20, steps = 37 00:07:09 [INFO] train episode 1968: reward = -146.83, steps = 56 00:07:09 [INFO] train episode 1969: reward = -88.43, steps = 21 00:07:09 [INFO] train episode 1970: reward = -92.71, steps = 19 00:07:09 [INFO] train episode 1971: reward = -56.53, steps = 20 00:07:10 [INFO] train episode 1972: reward = -107.99, steps = 38 00:07:10 [INFO] train episode 1973: reward = -88.47, steps = 34 00:07:10 [INFO] train episode 1974: reward = -131.51, steps = 53 00:07:10 [INFO] train episode 1975: reward = -98.50, steps = 29 00:07:11 [INFO] train episode 1976: reward = -133.90, steps = 51 00:07:11 [INFO] train episode 1977: reward = -99.31, steps = 40 00:07:11 [INFO] train episode 1978: reward = -91.01, steps = 23 00:07:11 [INFO] train episode 1979: reward = -62.04, steps = 22 00:07:12 [INFO] train episode 1980: reward = -203.26, steps = 46 00:07:12 [INFO] train episode 1981: reward = -86.63, steps = 27 00:07:12 [INFO] train episode 1982: reward = -103.37, steps = 41 00:07:13 [INFO] train episode 1983: reward = -100.78, steps = 32 00:07:13 [INFO] train episode 1984: reward = -55.27, steps = 20 00:07:13 [INFO] train episode 1985: reward = -125.06, steps = 49 00:07:13 [INFO] train episode 1986: reward = -112.95, steps = 37 00:07:13 [INFO] train episode 1987: reward = -91.04, steps = 32 00:07:14 [INFO] train episode 1988: reward = -214.82, steps = 65 00:07:14 [INFO] train episode 1989: reward = -105.13, steps = 22 00:07:14 [INFO] train episode 1990: reward = -128.15, steps = 37 00:07:15 [INFO] train episode 1991: reward = -153.47, steps = 60 00:07:15 [INFO] train episode 1992: reward = -234.27, steps = 64 00:07:15 [INFO] train episode 1993: reward = -85.91, steps = 33 00:07:16 [INFO] train episode 1994: reward = -135.97, steps = 41 00:07:16 [INFO] train episode 1995: reward = -102.30, steps = 28 00:07:16 [INFO] train episode 1996: reward = -89.18, steps = 34 00:07:16 [INFO] train episode 1997: reward = -90.59, steps = 20 00:07:17 [INFO] train episode 1998: reward = -261.73, steps = 77 00:07:17 [INFO] train episode 1999: reward = -108.20, steps = 31 00:07:17 [INFO] train episode 2000: reward = -60.21, steps = 20 00:07:18 [INFO] train episode 2001: reward = -107.12, steps = 49 00:07:18 [INFO] train episode 2002: reward = -210.10, steps = 59 00:07:18 [INFO] train episode 2003: reward = -99.10, steps = 32 00:07:18 [INFO] train episode 2004: reward = -217.96, steps = 48 00:07:19 [INFO] train episode 2005: reward = -284.25, steps = 82 00:07:19 [INFO] train episode 2006: reward = -124.90, steps = 37 00:07:19 [INFO] train episode 2007: reward = -133.31, steps = 41 00:07:20 [INFO] train episode 2008: reward = -70.22, steps = 35 00:07:20 [INFO] train episode 2009: reward = -355.33, steps = 109 00:07:21 [INFO] train episode 2010: reward = -205.68, steps = 64 00:07:21 [INFO] train episode 2011: reward = -119.89, steps = 41 00:07:21 [INFO] train episode 2012: reward = -137.81, steps = 37 00:07:21 [INFO] train episode 2013: reward = -92.48, steps = 41 00:07:22 [INFO] train episode 2014: reward = -81.22, steps = 22 00:07:22 [INFO] train episode 2015: reward = -145.93, steps = 53 00:07:22 [INFO] train episode 2016: reward = -149.85, steps = 48 00:07:22 [INFO] train episode 2017: reward = -106.88, steps = 31 00:07:23 [INFO] train episode 2018: reward = -75.13, steps = 40 00:07:23 [INFO] train episode 2019: reward = -56.37, steps = 20 00:07:23 [INFO] train episode 2020: reward = -71.64, steps = 18 00:07:23 [INFO] train episode 2021: reward = -130.85, steps = 46 00:07:24 [INFO] train episode 2022: reward = -80.00, steps = 38 00:07:24 [INFO] train episode 2023: reward = -74.44, steps = 27 00:07:24 [INFO] train episode 2024: reward = -90.06, steps = 30 00:07:24 [INFO] train episode 2025: reward = -114.06, steps = 47 00:07:24 [INFO] train episode 2026: reward = -71.48, steps = 27 00:07:25 [INFO] train episode 2027: reward = -165.23, steps = 42 00:07:25 [INFO] train episode 2028: reward = -125.87, steps = 50 00:07:26 [INFO] train episode 2029: reward = -119.19, steps = 51 00:07:26 [INFO] train episode 2030: reward = -104.63, steps = 43 00:07:26 [INFO] train episode 2031: reward = -85.30, steps = 23 00:07:26 [INFO] train episode 2032: reward = -99.14, steps = 24 00:07:26 [INFO] train episode 2033: reward = -82.34, steps = 19 00:07:27 [INFO] train episode 2034: reward = -88.29, steps = 41 00:07:27 [INFO] train episode 2035: reward = -128.76, steps = 39 00:07:27 [INFO] train episode 2036: reward = -147.84, steps = 57 00:07:28 [INFO] train episode 2037: reward = -114.46, steps = 40 00:07:28 [INFO] train episode 2038: reward = -136.46, steps = 41 00:07:28 [INFO] train episode 2039: reward = -152.71, steps = 58 00:07:28 [INFO] train episode 2040: reward = -79.02, steps = 39 00:07:29 [INFO] train episode 2041: reward = -115.06, steps = 49 00:07:29 [INFO] train episode 2042: reward = -115.79, steps = 44 00:07:29 [INFO] train episode 2043: reward = -93.52, steps = 28 00:07:30 [INFO] train episode 2044: reward = -96.68, steps = 46 00:07:30 [INFO] train episode 2045: reward = -88.36, steps = 26 00:07:30 [INFO] train episode 2046: reward = -86.36, steps = 24 00:07:30 [INFO] train episode 2047: reward = -143.43, steps = 38 00:07:30 [INFO] train episode 2048: reward = -102.51, steps = 51 00:07:31 [INFO] train episode 2049: reward = -148.34, steps = 42 00:07:31 [INFO] train episode 2050: reward = -149.87, steps = 48 00:07:31 [INFO] train episode 2051: reward = -110.13, steps = 36 00:07:32 [INFO] train episode 2052: reward = -142.99, steps = 44 00:07:32 [INFO] train episode 2053: reward = -213.74, steps = 56 00:07:32 [INFO] train episode 2054: reward = -127.44, steps = 38 00:07:33 [INFO] train episode 2055: reward = -142.64, steps = 56 00:07:33 [INFO] train episode 2056: reward = -109.40, steps = 39 00:07:33 [INFO] train episode 2057: reward = -166.35, steps = 55 00:07:34 [INFO] train episode 2058: reward = -236.58, steps = 76 00:07:34 [INFO] train episode 2059: reward = -111.75, steps = 38 00:07:34 [INFO] train episode 2060: reward = -76.58, steps = 37 00:07:34 [INFO] train episode 2061: reward = -54.55, steps = 21 00:07:35 [INFO] train episode 2062: reward = -126.33, steps = 49 00:07:35 [INFO] train episode 2063: reward = -161.87, steps = 49 00:07:35 [INFO] train episode 2064: reward = -179.42, steps = 63 00:07:36 [INFO] train episode 2065: reward = -223.06, steps = 65 00:07:36 [INFO] train episode 2066: reward = -213.57, steps = 78 00:07:36 [INFO] train episode 2067: reward = -81.12, steps = 35 00:07:37 [INFO] train episode 2068: reward = -142.72, steps = 46 00:07:37 [INFO] train episode 2069: reward = -175.16, steps = 53 00:07:37 [INFO] train episode 2070: reward = -129.67, steps = 41 00:07:38 [INFO] train episode 2071: reward = -93.50, steps = 38 00:07:38 [INFO] train episode 2072: reward = -140.43, steps = 45 00:07:38 [INFO] train episode 2073: reward = -124.70, steps = 46 00:07:39 [INFO] train episode 2074: reward = -87.68, steps = 39 00:07:39 [INFO] train episode 2075: reward = -93.78, steps = 24 00:07:39 [INFO] train episode 2076: reward = -143.56, steps = 48 00:07:39 [INFO] train episode 2077: reward = -56.37, steps = 24 00:07:40 [INFO] train episode 2078: reward = -124.42, steps = 40 00:07:40 [INFO] train episode 2079: reward = -110.21, steps = 41 00:07:40 [INFO] train episode 2080: reward = -157.19, steps = 65 00:07:40 [INFO] train episode 2081: reward = -109.01, steps = 32 00:07:41 [INFO] train episode 2082: reward = -65.07, steps = 23 00:07:41 [INFO] train episode 2083: reward = -178.90, steps = 59 00:07:41 [INFO] train episode 2084: reward = -140.82, steps = 57 00:07:42 [INFO] train episode 2085: reward = -228.83, steps = 58 00:07:42 [INFO] train episode 2086: reward = -58.72, steps = 20 00:07:42 [INFO] train episode 2087: reward = -68.67, steps = 21 00:07:42 [INFO] train episode 2088: reward = -192.93, steps = 54 00:07:43 [INFO] train episode 2089: reward = -127.16, steps = 42 00:07:43 [INFO] train episode 2090: reward = -186.11, steps = 58 00:07:44 [INFO] train episode 2091: reward = -275.98, steps = 85 00:07:44 [INFO] train episode 2092: reward = -155.46, steps = 54 00:07:44 [INFO] train episode 2093: reward = -77.51, steps = 24 00:07:45 [INFO] train episode 2094: reward = -234.66, steps = 74 00:07:45 [INFO] train episode 2095: reward = -142.38, steps = 57 00:07:45 [INFO] train episode 2096: reward = -115.05, steps = 46 00:07:45 [INFO] train episode 2097: reward = -83.92, steps = 21 00:07:46 [INFO] train episode 2098: reward = -155.41, steps = 41 00:07:46 [INFO] train episode 2099: reward = -86.45, steps = 34 00:07:46 [INFO] train episode 2100: reward = -179.69, steps = 57 00:07:47 [INFO] train episode 2101: reward = -230.23, steps = 84 00:07:47 [INFO] train episode 2102: reward = -116.99, steps = 40 00:07:47 [INFO] train episode 2103: reward = -135.39, steps = 38 00:07:48 [INFO] train episode 2104: reward = -161.94, steps = 57 00:07:48 [INFO] train episode 2105: reward = -317.43, steps = 98 00:07:49 [INFO] train episode 2106: reward = -97.31, steps = 41 00:07:49 [INFO] train episode 2107: reward = -153.56, steps = 58 00:07:49 [INFO] train episode 2108: reward = -98.77, steps = 25 00:07:50 [INFO] train episode 2109: reward = -194.14, steps = 77 00:07:50 [INFO] train episode 2110: reward = -99.77, steps = 36 00:07:50 [INFO] train episode 2111: reward = -90.02, steps = 34 00:07:50 [INFO] train episode 2112: reward = -201.36, steps = 58 00:07:51 [INFO] train episode 2113: reward = -109.17, steps = 44 00:07:51 [INFO] train episode 2114: reward = -133.04, steps = 43 00:07:51 [INFO] train episode 2115: reward = -78.09, steps = 33 00:07:52 [INFO] train episode 2116: reward = -187.30, steps = 65 00:07:52 [INFO] train episode 2117: reward = -105.54, steps = 38 00:07:52 [INFO] train episode 2118: reward = -59.83, steps = 20 00:07:53 [INFO] train episode 2119: reward = -90.35, steps = 43 00:07:53 [INFO] train episode 2120: reward = -99.70, steps = 38 00:07:53 [INFO] train episode 2121: reward = -102.05, steps = 27 00:07:53 [INFO] train episode 2122: reward = -252.36, steps = 65 00:07:54 [INFO] train episode 2123: reward = -195.61, steps = 71 00:07:54 [INFO] train episode 2124: reward = -149.16, steps = 39 00:07:55 [INFO] train episode 2125: reward = -134.31, steps = 49 00:07:55 [INFO] train episode 2126: reward = -123.05, steps = 49 00:07:55 [INFO] train episode 2127: reward = -134.46, steps = 42 00:07:55 [INFO] train episode 2128: reward = -112.64, steps = 41 00:07:56 [INFO] train episode 2129: reward = -100.33, steps = 30 00:07:56 [INFO] train episode 2130: reward = -127.56, steps = 47 00:07:56 [INFO] train episode 2131: reward = -215.66, steps = 65 00:07:57 [INFO] train episode 2132: reward = -158.22, steps = 63 00:07:57 [INFO] train episode 2133: reward = -111.96, steps = 47 00:07:57 [INFO] train episode 2134: reward = -199.73, steps = 45 00:07:58 [INFO] train episode 2135: reward = -222.21, steps = 70 00:07:58 [INFO] train episode 2136: reward = -79.14, steps = 28 00:07:58 [INFO] train episode 2137: reward = -98.55, steps = 38 00:07:59 [INFO] train episode 2138: reward = -250.14, steps = 66 00:07:59 [INFO] train episode 2139: reward = -137.85, steps = 40 00:07:59 [INFO] train episode 2140: reward = -117.30, steps = 46 00:07:59 [INFO] train episode 2141: reward = -122.87, steps = 42 00:08:00 [INFO] train episode 2142: reward = -205.43, steps = 58 00:08:00 [INFO] train episode 2143: reward = -73.99, steps = 29 00:08:00 [INFO] train episode 2144: reward = -171.85, steps = 43 00:08:01 [INFO] train episode 2145: reward = -178.57, steps = 56 00:08:01 [INFO] train episode 2146: reward = -226.67, steps = 84 00:08:01 [INFO] train episode 2147: reward = -119.89, steps = 41 00:08:02 [INFO] train episode 2148: reward = -117.63, steps = 24 00:08:02 [INFO] train episode 2149: reward = -117.75, steps = 46 00:08:02 [INFO] train episode 2150: reward = -149.83, steps = 45 00:08:02 [INFO] train episode 2151: reward = -81.74, steps = 25 00:08:03 [INFO] train episode 2152: reward = -128.59, steps = 55 00:08:03 [INFO] train episode 2153: reward = -201.07, steps = 54 00:08:04 [INFO] train episode 2154: reward = -199.88, steps = 81 00:08:04 [INFO] train episode 2155: reward = -215.08, steps = 63 00:08:05 [INFO] train episode 2156: reward = -120.89, steps = 52 00:08:05 [INFO] train episode 2157: reward = -133.73, steps = 39 00:08:05 [INFO] train episode 2158: reward = -88.97, steps = 35 00:08:05 [INFO] train episode 2159: reward = -95.76, steps = 41 00:08:06 [INFO] train episode 2160: reward = -137.03, steps = 41 00:08:06 [INFO] train episode 2161: reward = -88.21, steps = 46 00:08:06 [INFO] train episode 2162: reward = -86.76, steps = 20 00:08:06 [INFO] train episode 2163: reward = -148.03, steps = 51 00:08:07 [INFO] train episode 2164: reward = -154.56, steps = 34 00:08:07 [INFO] train episode 2165: reward = -100.19, steps = 26 00:08:07 [INFO] train episode 2166: reward = -328.19, steps = 80 00:08:08 [INFO] train episode 2167: reward = -130.63, steps = 50 00:08:08 [INFO] train episode 2168: reward = -261.08, steps = 69 00:08:08 [INFO] train episode 2169: reward = -110.64, steps = 41 00:08:09 [INFO] train episode 2170: reward = -222.09, steps = 69 00:08:09 [INFO] train episode 2171: reward = -107.75, steps = 35 00:08:09 [INFO] train episode 2172: reward = -158.18, steps = 43 00:08:10 [INFO] train episode 2173: reward = -80.25, steps = 34 00:08:10 [INFO] train episode 2174: reward = -186.65, steps = 56 00:08:10 [INFO] train episode 2175: reward = -207.45, steps = 58 00:08:11 [INFO] train episode 2176: reward = -130.70, steps = 61 00:08:11 [INFO] train episode 2177: reward = -82.38, steps = 33 00:08:11 [INFO] train episode 2178: reward = -107.13, steps = 46 00:08:12 [INFO] train episode 2179: reward = -185.71, steps = 63 00:08:12 [INFO] train episode 2180: reward = -185.11, steps = 64 00:08:12 [INFO] train episode 2181: reward = -164.27, steps = 53 00:08:13 [INFO] train episode 2182: reward = -143.63, steps = 55 00:08:13 [INFO] train episode 2183: reward = -85.78, steps = 41 00:08:13 [INFO] train episode 2184: reward = -118.35, steps = 48 00:08:14 [INFO] train episode 2185: reward = -157.13, steps = 51 00:08:14 [INFO] train episode 2186: reward = -89.89, steps = 32 00:08:14 [INFO] train episode 2187: reward = -190.25, steps = 57 00:08:14 [INFO] train episode 2188: reward = -130.36, steps = 44 00:08:15 [INFO] train episode 2189: reward = -157.72, steps = 56 00:08:15 [INFO] train episode 2190: reward = -240.13, steps = 70 00:08:16 [INFO] train episode 2191: reward = -163.65, steps = 46 00:08:16 [INFO] train episode 2192: reward = -254.11, steps = 71 00:08:17 [INFO] train episode 2193: reward = -199.97, steps = 90 00:08:17 [INFO] train episode 2194: reward = -125.00, steps = 45 00:08:17 [INFO] train episode 2195: reward = -113.22, steps = 50 00:08:18 [INFO] train episode 2196: reward = -267.15, steps = 80 00:08:18 [INFO] train episode 2197: reward = -249.63, steps = 60 00:08:19 [INFO] train episode 2198: reward = -159.17, steps = 52 00:08:19 [INFO] train episode 2199: reward = -147.37, steps = 71 00:08:19 [INFO] train episode 2200: reward = -82.00, steps = 42 00:08:20 [INFO] train episode 2201: reward = -130.33, steps = 42 00:08:20 [INFO] train episode 2202: reward = -183.04, steps = 60 00:08:20 [INFO] train episode 2203: reward = -94.39, steps = 42 00:08:21 [INFO] train episode 2204: reward = -196.44, steps = 61 00:08:21 [INFO] train episode 2205: reward = -182.58, steps = 65 00:08:21 [INFO] train episode 2206: reward = -162.10, steps = 56 00:08:22 [INFO] train episode 2207: reward = -168.29, steps = 38 00:08:22 [INFO] train episode 2208: reward = -159.68, steps = 59 00:08:22 [INFO] train episode 2209: reward = -93.91, steps = 39 00:08:23 [INFO] train episode 2210: reward = -115.03, steps = 47 00:08:23 [INFO] train episode 2211: reward = -232.05, steps = 63 00:08:24 [INFO] train episode 2212: reward = -252.88, steps = 79 00:08:24 [INFO] train episode 2213: reward = -114.25, steps = 54 00:08:24 [INFO] train episode 2214: reward = -129.71, steps = 40 00:08:24 [INFO] train episode 2215: reward = -72.81, steps = 29 00:08:25 [INFO] train episode 2216: reward = -253.26, steps = 73 00:08:25 [INFO] train episode 2217: reward = -67.51, steps = 26 00:08:25 [INFO] train episode 2218: reward = -133.34, steps = 40 00:08:26 [INFO] train episode 2219: reward = -291.97, steps = 84 00:08:26 [INFO] train episode 2220: reward = -162.24, steps = 45 00:08:26 [INFO] train episode 2221: reward = -146.86, steps = 41 00:08:27 [INFO] train episode 2222: reward = -170.30, steps = 60 00:08:27 [INFO] train episode 2223: reward = -91.77, steps = 39 00:08:27 [INFO] train episode 2224: reward = -124.50, steps = 54 00:08:28 [INFO] train episode 2225: reward = -171.63, steps = 60 00:08:28 [INFO] train episode 2226: reward = -103.71, steps = 30 00:08:28 [INFO] train episode 2227: reward = -196.26, steps = 73 00:08:28 [INFO] train episode 2228: reward = -80.43, steps = 27 00:08:29 [INFO] train episode 2229: reward = -90.45, steps = 41 00:08:29 [INFO] train episode 2230: reward = -81.89, steps = 27 00:08:29 [INFO] train episode 2231: reward = -127.91, steps = 53 00:08:29 [INFO] train episode 2232: reward = -107.93, steps = 39 00:08:30 [INFO] train episode 2233: reward = -92.50, steps = 38 00:08:30 [INFO] train episode 2234: reward = -132.76, steps = 46 00:08:30 [INFO] train episode 2235: reward = -102.13, steps = 32 00:08:31 [INFO] train episode 2236: reward = -216.67, steps = 76 00:08:31 [INFO] train episode 2237: reward = -125.56, steps = 41 00:08:32 [INFO] train episode 2238: reward = -232.42, steps = 64 00:08:32 [INFO] train episode 2239: reward = -193.27, steps = 49 00:08:32 [INFO] train episode 2240: reward = -95.45, steps = 24 00:08:33 [INFO] train episode 2241: reward = -260.43, steps = 82 00:08:33 [INFO] train episode 2242: reward = -151.68, steps = 62 00:08:33 [INFO] train episode 2243: reward = -247.36, steps = 66 00:08:34 [INFO] train episode 2244: reward = -260.14, steps = 62 00:08:34 [INFO] train episode 2245: reward = -257.38, steps = 100 00:08:35 [INFO] train episode 2246: reward = -192.18, steps = 57 00:08:35 [INFO] train episode 2247: reward = -69.52, steps = 24 00:08:35 [INFO] train episode 2248: reward = -119.89, steps = 35 00:08:36 [INFO] train episode 2249: reward = -127.94, steps = 55 00:08:36 [INFO] train episode 2250: reward = -204.05, steps = 58 00:08:36 [INFO] train episode 2251: reward = -62.07, steps = 42 00:08:37 [INFO] train episode 2252: reward = -178.54, steps = 57 00:08:37 [INFO] train episode 2253: reward = -170.28, steps = 78 00:08:38 [INFO] train episode 2254: reward = -306.94, steps = 88 00:08:38 [INFO] train episode 2255: reward = -137.48, steps = 49 00:08:38 [INFO] train episode 2256: reward = -88.75, steps = 45 00:08:39 [INFO] train episode 2257: reward = -215.24, steps = 70 00:08:39 [INFO] train episode 2258: reward = -230.85, steps = 50 00:08:39 [INFO] train episode 2259: reward = -194.21, steps = 61 00:08:40 [INFO] train episode 2260: reward = -141.66, steps = 57 00:08:40 [INFO] train episode 2261: reward = -154.17, steps = 45 00:08:40 [INFO] train episode 2262: reward = -93.39, steps = 42 00:08:41 [INFO] train episode 2263: reward = -65.54, steps = 18 00:08:41 [INFO] train episode 2264: reward = -109.27, steps = 54 00:08:41 [INFO] train episode 2265: reward = -212.81, steps = 90 00:08:42 [INFO] train episode 2266: reward = -89.24, steps = 36 00:08:42 [INFO] train episode 2267: reward = -113.39, steps = 17 00:08:42 [INFO] train episode 2268: reward = -211.37, steps = 96 00:08:43 [INFO] train episode 2269: reward = -96.16, steps = 42 00:08:43 [INFO] train episode 2270: reward = -220.95, steps = 71 00:08:43 [INFO] train episode 2271: reward = -140.86, steps = 43 00:08:44 [INFO] train episode 2272: reward = -191.15, steps = 46 00:08:44 [INFO] train episode 2273: reward = -193.80, steps = 74 00:08:45 [INFO] train episode 2274: reward = -86.52, steps = 40 00:08:45 [INFO] train episode 2275: reward = -186.42, steps = 59 00:08:45 [INFO] train episode 2276: reward = -152.12, steps = 57 00:08:46 [INFO] train episode 2277: reward = -122.31, steps = 57 00:08:46 [INFO] train episode 2278: reward = -153.76, steps = 46 00:08:46 [INFO] train episode 2279: reward = -103.78, steps = 49 00:08:47 [INFO] train episode 2280: reward = -105.13, steps = 41 00:08:47 [INFO] train episode 2281: reward = -215.31, steps = 59 00:08:47 [INFO] train episode 2282: reward = -114.41, steps = 44 00:08:48 [INFO] train episode 2283: reward = -169.06, steps = 54 00:08:48 [INFO] train episode 2284: reward = -107.62, steps = 55 00:08:48 [INFO] train episode 2285: reward = -179.95, steps = 55 00:08:49 [INFO] train episode 2286: reward = -136.97, steps = 52 00:08:49 [INFO] train episode 2287: reward = -141.23, steps = 56 00:08:49 [INFO] train episode 2288: reward = -146.91, steps = 44 00:08:50 [INFO] train episode 2289: reward = -157.53, steps = 63 00:08:50 [INFO] train episode 2290: reward = -136.49, steps = 53 00:08:50 [INFO] train episode 2291: reward = -207.64, steps = 79 00:08:51 [INFO] train episode 2292: reward = -69.58, steps = 16 00:08:51 [INFO] train episode 2293: reward = -104.54, steps = 52 00:08:51 [INFO] train episode 2294: reward = -134.39, steps = 46 00:08:51 [INFO] train episode 2295: reward = -97.06, steps = 41 00:08:52 [INFO] train episode 2296: reward = -216.71, steps = 61 00:08:52 [INFO] train episode 2297: reward = -163.89, steps = 42 00:08:52 [INFO] train episode 2298: reward = -60.96, steps = 21 00:08:53 [INFO] train episode 2299: reward = -155.99, steps = 67 00:08:53 [INFO] train episode 2300: reward = -155.01, steps = 54 00:08:53 [INFO] train episode 2301: reward = -124.65, steps = 49 00:08:54 [INFO] train episode 2302: reward = -129.69, steps = 50 00:08:54 [INFO] train episode 2303: reward = -224.66, steps = 86 00:08:55 [INFO] train episode 2304: reward = -104.84, steps = 44 00:08:55 [INFO] train episode 2305: reward = -216.92, steps = 68 00:08:55 [INFO] train episode 2306: reward = -102.46, steps = 34 00:08:55 [INFO] train episode 2307: reward = -46.99, steps = 23 00:08:56 [INFO] train episode 2308: reward = -77.46, steps = 38 00:08:56 [INFO] train episode 2309: reward = -216.26, steps = 81 00:08:57 [INFO] train episode 2310: reward = -229.38, steps = 61 00:08:57 [INFO] train episode 2311: reward = -268.76, steps = 86 00:08:58 [INFO] train episode 2312: reward = -93.49, steps = 53 00:08:58 [INFO] train episode 2313: reward = -78.91, steps = 21 00:08:58 [INFO] train episode 2314: reward = -199.98, steps = 82 00:08:59 [INFO] train episode 2315: reward = -116.68, steps = 43 00:08:59 [INFO] train episode 2316: reward = -340.01, steps = 120 00:09:00 [INFO] train episode 2317: reward = -130.54, steps = 44 00:09:00 [INFO] train episode 2318: reward = -320.65, steps = 85 00:09:00 [INFO] train episode 2319: reward = -130.46, steps = 48 00:09:01 [INFO] train episode 2320: reward = -363.86, steps = 100 00:09:01 [INFO] train episode 2321: reward = -139.02, steps = 46 00:09:02 [INFO] train episode 2322: reward = -148.13, steps = 47 00:09:02 [INFO] train episode 2323: reward = -358.32, steps = 91 00:09:02 [INFO] train episode 2324: reward = -98.91, steps = 45 00:09:03 [INFO] train episode 2325: reward = -78.32, steps = 37 00:09:03 [INFO] train episode 2326: reward = -230.44, steps = 63 00:09:03 [INFO] train episode 2327: reward = -114.37, steps = 32 00:09:04 [INFO] train episode 2328: reward = -69.04, steps = 39 00:09:04 [INFO] train episode 2329: reward = -238.40, steps = 60 00:09:04 [INFO] train episode 2330: reward = -92.61, steps = 41 00:09:05 [INFO] train episode 2331: reward = -118.40, steps = 65 00:09:06 [INFO] train episode 2332: reward = -264.29, steps = 105 00:09:06 [INFO] train episode 2333: reward = -108.19, steps = 47 00:09:06 [INFO] train episode 2334: reward = -87.34, steps = 24 00:09:06 [INFO] train episode 2335: reward = -106.43, steps = 22 00:09:07 [INFO] train episode 2336: reward = -189.74, steps = 86 00:09:07 [INFO] train episode 2337: reward = -97.24, steps = 37 00:09:07 [INFO] train episode 2338: reward = -145.10, steps = 47 00:09:07 [INFO] train episode 2339: reward = -69.96, steps = 17 00:09:08 [INFO] train episode 2340: reward = -287.44, steps = 99 00:09:08 [INFO] train episode 2341: reward = -146.00, steps = 48 00:09:08 [INFO] train episode 2342: reward = -96.94, steps = 24 00:09:09 [INFO] train episode 2343: reward = -91.07, steps = 38 00:09:09 [INFO] train episode 2344: reward = -84.52, steps = 38 00:09:09 [INFO] train episode 2345: reward = -125.62, steps = 60 00:09:10 [INFO] train episode 2346: reward = -105.52, steps = 53 00:09:10 [INFO] train episode 2347: reward = -125.98, steps = 47 00:09:10 [INFO] train episode 2348: reward = -89.34, steps = 36 00:09:11 [INFO] train episode 2349: reward = -136.89, steps = 51 00:09:11 [INFO] train episode 2350: reward = -212.29, steps = 66 00:09:11 [INFO] train episode 2351: reward = -143.94, steps = 38 00:09:12 [INFO] train episode 2352: reward = -158.43, steps = 54 00:09:12 [INFO] train episode 2353: reward = -107.30, steps = 41 00:09:12 [INFO] train episode 2354: reward = -181.87, steps = 55 00:09:13 [INFO] train episode 2355: reward = -138.47, steps = 68 00:09:13 [INFO] train episode 2356: reward = -154.79, steps = 49 00:09:13 [INFO] train episode 2357: reward = -177.83, steps = 54 00:09:14 [INFO] train episode 2358: reward = -150.21, steps = 53 00:09:14 [INFO] train episode 2359: reward = -85.34, steps = 28 00:09:14 [INFO] train episode 2360: reward = -172.74, steps = 55 00:09:15 [INFO] train episode 2361: reward = -183.69, steps = 55 00:09:15 [INFO] train episode 2362: reward = -185.16, steps = 57 00:09:15 [INFO] train episode 2363: reward = -128.64, steps = 56 00:09:16 [INFO] train episode 2364: reward = -136.02, steps = 59 00:09:16 [INFO] train episode 2365: reward = -118.24, steps = 58 00:09:16 [INFO] train episode 2366: reward = -125.17, steps = 51 00:09:17 [INFO] train episode 2367: reward = -82.75, steps = 27 00:09:17 [INFO] train episode 2368: reward = -114.03, steps = 36 00:09:17 [INFO] train episode 2369: reward = -131.00, steps = 62 00:09:17 [INFO] train episode 2370: reward = -154.68, steps = 42 00:09:18 [INFO] train episode 2371: reward = -165.69, steps = 70 00:09:18 [INFO] train episode 2372: reward = -188.35, steps = 56 00:09:18 [INFO] train episode 2373: reward = -62.99, steps = 18 00:09:19 [INFO] train episode 2374: reward = -195.07, steps = 56 00:09:19 [INFO] train episode 2375: reward = -140.51, steps = 48 00:09:19 [INFO] train episode 2376: reward = -155.49, steps = 64 00:09:20 [INFO] train episode 2377: reward = -211.36, steps = 60 00:09:20 [INFO] train episode 2378: reward = -203.01, steps = 77 00:09:21 [INFO] train episode 2379: reward = -260.39, steps = 76 00:09:21 [INFO] train episode 2380: reward = -174.68, steps = 81 00:09:22 [INFO] train episode 2381: reward = -205.43, steps = 70 00:09:22 [INFO] train episode 2382: reward = -197.34, steps = 75 00:09:23 [INFO] train episode 2383: reward = -103.19, steps = 18 00:09:23 [INFO] train episode 2384: reward = -145.44, steps = 59 00:09:23 [INFO] train episode 2385: reward = -155.54, steps = 61 00:09:24 [INFO] train episode 2386: reward = -124.17, steps = 46 00:09:24 [INFO] train episode 2387: reward = -173.07, steps = 64 00:09:25 [INFO] train episode 2388: reward = -138.05, steps = 64 00:09:25 [INFO] train episode 2389: reward = -287.79, steps = 90 00:09:25 [INFO] train episode 2390: reward = -151.04, steps = 48 00:09:26 [INFO] train episode 2391: reward = -196.83, steps = 71 00:09:26 [INFO] train episode 2392: reward = -133.63, steps = 49 00:09:27 [INFO] train episode 2393: reward = -215.32, steps = 54 00:09:27 [INFO] train episode 2394: reward = -87.25, steps = 28 00:09:27 [INFO] train episode 2395: reward = -216.93, steps = 63 00:09:27 [INFO] train episode 2396: reward = -131.94, steps = 45 00:09:28 [INFO] train episode 2397: reward = -79.19, steps = 41 00:09:28 [INFO] train episode 2398: reward = -126.86, steps = 43 00:09:28 [INFO] train episode 2399: reward = -107.72, steps = 43 00:09:29 [INFO] train episode 2400: reward = -139.98, steps = 59 00:09:29 [INFO] train episode 2401: reward = -160.78, steps = 54 00:09:29 [INFO] train episode 2402: reward = -205.81, steps = 62 00:09:30 [INFO] train episode 2403: reward = -147.15, steps = 50 00:09:30 [INFO] train episode 2404: reward = -132.69, steps = 45 00:09:30 [INFO] train episode 2405: reward = -183.34, steps = 84 00:09:31 [INFO] train episode 2406: reward = -230.43, steps = 79 00:09:31 [INFO] train episode 2407: reward = -170.43, steps = 68 00:09:32 [INFO] train episode 2408: reward = -202.07, steps = 85 00:09:32 [INFO] train episode 2409: reward = -150.37, steps = 47 00:09:33 [INFO] train episode 2410: reward = -159.90, steps = 61 00:09:33 [INFO] train episode 2411: reward = -84.42, steps = 35 00:09:33 [INFO] train episode 2412: reward = -125.06, steps = 50 00:09:34 [INFO] train episode 2413: reward = -83.60, steps = 46 00:09:34 [INFO] train episode 2414: reward = -67.75, steps = 18 00:09:34 [INFO] train episode 2415: reward = -145.00, steps = 61 00:09:34 [INFO] train episode 2416: reward = -51.88, steps = 15 00:09:35 [INFO] train episode 2417: reward = -125.88, steps = 71 00:09:35 [INFO] train episode 2418: reward = -157.52, steps = 45 00:09:36 [INFO] train episode 2419: reward = -196.78, steps = 66 00:09:36 [INFO] train episode 2420: reward = -253.93, steps = 74 00:09:37 [INFO] train episode 2421: reward = -142.58, steps = 71 00:09:37 [INFO] train episode 2422: reward = -103.57, steps = 45 00:09:37 [INFO] train episode 2423: reward = -71.12, steps = 18 00:09:37 [INFO] train episode 2424: reward = -112.51, steps = 47 00:09:38 [INFO] train episode 2425: reward = -142.99, steps = 44 00:09:38 [INFO] train episode 2426: reward = -266.91, steps = 90 00:09:39 [INFO] train episode 2427: reward = -197.26, steps = 66 00:09:39 [INFO] train episode 2428: reward = -132.69, steps = 47 00:09:39 [INFO] train episode 2429: reward = -154.47, steps = 73 00:09:40 [INFO] train episode 2430: reward = -130.43, steps = 62 00:09:40 [INFO] train episode 2431: reward = -112.40, steps = 49 00:09:40 [INFO] train episode 2432: reward = -166.04, steps = 48 00:09:41 [INFO] train episode 2433: reward = -143.11, steps = 42 00:09:42 [INFO] train episode 2434: reward = -392.24, steps = 148 00:09:42 [INFO] train episode 2435: reward = -244.25, steps = 96 00:09:43 [INFO] train episode 2436: reward = -107.15, steps = 64 00:09:43 [INFO] train episode 2437: reward = -115.21, steps = 46 00:09:43 [INFO] train episode 2438: reward = -163.71, steps = 50 00:09:44 [INFO] train episode 2439: reward = -187.26, steps = 64 00:09:44 [INFO] train episode 2440: reward = -137.23, steps = 63 00:09:44 [INFO] train episode 2441: reward = -143.11, steps = 42 00:09:45 [INFO] train episode 2442: reward = -165.66, steps = 59 00:09:45 [INFO] train episode 2443: reward = -195.75, steps = 67 00:09:45 [INFO] train episode 2444: reward = -119.95, steps = 45 00:09:46 [INFO] train episode 2445: reward = -157.10, steps = 53 00:09:46 [INFO] train episode 2446: reward = -93.53, steps = 43 00:09:46 [INFO] train episode 2447: reward = -199.06, steps = 72 00:09:47 [INFO] train episode 2448: reward = -104.00, steps = 48 00:09:47 [INFO] train episode 2449: reward = -179.52, steps = 49 00:09:47 [INFO] train episode 2450: reward = -157.86, steps = 56 00:09:48 [INFO] train episode 2451: reward = -126.00, steps = 56 00:09:48 [INFO] train episode 2452: reward = -261.68, steps = 64 00:09:49 [INFO] train episode 2453: reward = -148.71, steps = 53 00:09:49 [INFO] train episode 2454: reward = -136.45, steps = 64 00:09:50 [INFO] train episode 2455: reward = -85.81, steps = 43 00:09:50 [INFO] train episode 2456: reward = -151.94, steps = 60 00:09:50 [INFO] train episode 2457: reward = -214.07, steps = 82 00:09:51 [INFO] train episode 2458: reward = -81.70, steps = 36 00:09:51 [INFO] train episode 2459: reward = -63.99, steps = 19 00:09:51 [INFO] train episode 2460: reward = -130.59, steps = 46 00:09:51 [INFO] train episode 2461: reward = -105.08, steps = 34 00:09:52 [INFO] train episode 2462: reward = -73.00, steps = 23 00:09:52 [INFO] train episode 2463: reward = -132.68, steps = 59 00:09:52 [INFO] train episode 2464: reward = -87.12, steps = 33 00:09:53 [INFO] train episode 2465: reward = -316.29, steps = 120 00:09:53 [INFO] train episode 2466: reward = -87.01, steps = 42 00:09:53 [INFO] train episode 2467: reward = -108.61, steps = 32 00:09:54 [INFO] train episode 2468: reward = -63.41, steps = 36 00:09:54 [INFO] train episode 2469: reward = -117.93, steps = 67 00:09:54 [INFO] train episode 2470: reward = -248.91, steps = 65 00:09:55 [INFO] train episode 2471: reward = -93.38, steps = 38 00:09:55 [INFO] train episode 2472: reward = -143.49, steps = 48 00:09:55 [INFO] train episode 2473: reward = -136.48, steps = 64 00:09:56 [INFO] train episode 2474: reward = -119.28, steps = 49 00:09:56 [INFO] train episode 2475: reward = -171.59, steps = 57 00:09:56 [INFO] train episode 2476: reward = -113.86, steps = 39 00:09:57 [INFO] train episode 2477: reward = -126.46, steps = 57 00:09:57 [INFO] train episode 2478: reward = -145.35, steps = 47 00:09:58 [INFO] train episode 2479: reward = -157.63, steps = 89 00:09:58 [INFO] train episode 2480: reward = -118.66, steps = 44 00:09:58 [INFO] train episode 2481: reward = -165.82, steps = 91 00:09:59 [INFO] train episode 2482: reward = -64.70, steps = 44 00:09:59 [INFO] train episode 2483: reward = -175.83, steps = 59 00:09:59 [INFO] train episode 2484: reward = -104.78, steps = 38 00:10:00 [INFO] train episode 2485: reward = -290.99, steps = 97 00:10:01 [INFO] train episode 2486: reward = -239.46, steps = 82 00:10:01 [INFO] train episode 2487: reward = -130.40, steps = 43 00:10:01 [INFO] train episode 2488: reward = -151.57, steps = 49 00:10:02 [INFO] train episode 2489: reward = -80.96, steps = 53 00:10:02 [INFO] train episode 2490: reward = -173.60, steps = 67 00:10:02 [INFO] train episode 2491: reward = -95.02, steps = 46 00:10:03 [INFO] train episode 2492: reward = -101.00, steps = 48 00:10:03 [INFO] train episode 2493: reward = -81.70, steps = 48 00:10:03 [INFO] train episode 2494: reward = -81.04, steps = 38 00:10:04 [INFO] train episode 2495: reward = -182.75, steps = 57 00:10:04 [INFO] train episode 2496: reward = -116.27, steps = 68 00:10:04 [INFO] train episode 2497: reward = -141.64, steps = 45 00:10:05 [INFO] train episode 2498: reward = -113.47, steps = 51 00:10:05 [INFO] train episode 2499: reward = -228.63, steps = 81 00:10:06 [INFO] train episode 2500: reward = -304.90, steps = 121 00:10:06 [INFO] train episode 2501: reward = -172.54, steps = 65 00:10:07 [INFO] train episode 2502: reward = -115.94, steps = 61 00:10:07 [INFO] train episode 2503: reward = -86.93, steps = 50 00:10:07 [INFO] train episode 2504: reward = -118.51, steps = 65 00:10:08 [INFO] train episode 2505: reward = -166.15, steps = 54 00:10:08 [INFO] train episode 2506: reward = -69.25, steps = 36 00:10:08 [INFO] train episode 2507: reward = -111.21, steps = 57 00:10:09 [INFO] train episode 2508: reward = -196.22, steps = 80 00:10:09 [INFO] train episode 2509: reward = -86.95, steps = 43 00:10:10 [INFO] train episode 2510: reward = -104.47, steps = 55 00:10:10 [INFO] train episode 2511: reward = -216.47, steps = 73 00:10:11 [INFO] train episode 2512: reward = -179.77, steps = 84 00:10:11 [INFO] train episode 2513: reward = -164.60, steps = 73 00:10:11 [INFO] train episode 2514: reward = -118.54, steps = 46 00:10:12 [INFO] train episode 2515: reward = -93.05, steps = 47 00:10:12 [INFO] train episode 2516: reward = -217.82, steps = 76 00:10:12 [INFO] train episode 2517: reward = -158.39, steps = 55 00:10:13 [INFO] train episode 2518: reward = -217.56, steps = 61 00:10:13 [INFO] train episode 2519: reward = -135.54, steps = 78 00:10:14 [INFO] train episode 2520: reward = -215.34, steps = 86 00:10:14 [INFO] train episode 2521: reward = -279.39, steps = 111 00:10:15 [INFO] train episode 2522: reward = -94.96, steps = 54 00:10:16 [INFO] train episode 2523: reward = -161.04, steps = 73 00:10:16 [INFO] train episode 2524: reward = -101.97, steps = 39 00:10:16 [INFO] train episode 2525: reward = -144.55, steps = 67 00:10:17 [INFO] train episode 2526: reward = -180.71, steps = 62 00:10:17 [INFO] train episode 2527: reward = -77.02, steps = 45 00:10:17 [INFO] train episode 2528: reward = -59.98, steps = 36 00:10:17 [INFO] train episode 2529: reward = -57.00, steps = 32 00:10:18 [INFO] train episode 2530: reward = -101.11, steps = 45 00:10:18 [INFO] train episode 2531: reward = -141.88, steps = 71 00:10:18 [INFO] train episode 2532: reward = -91.01, steps = 41 00:10:19 [INFO] train episode 2533: reward = -109.01, steps = 35 00:10:19 [INFO] train episode 2534: reward = -104.78, steps = 40 00:10:19 [INFO] train episode 2535: reward = -130.71, steps = 53 00:10:20 [INFO] train episode 2536: reward = -164.35, steps = 64 00:10:20 [INFO] train episode 2537: reward = -113.35, steps = 43 00:10:20 [INFO] train episode 2538: reward = -106.54, steps = 58 00:10:21 [INFO] train episode 2539: reward = -110.30, steps = 42 00:10:21 [INFO] train episode 2540: reward = -176.28, steps = 90 00:10:21 [INFO] train episode 2541: reward = -87.62, steps = 44 00:10:22 [INFO] train episode 2542: reward = -200.27, steps = 72 00:10:22 [INFO] train episode 2543: reward = -187.57, steps = 67 00:10:23 [INFO] train episode 2544: reward = -109.85, steps = 37 00:10:23 [INFO] train episode 2545: reward = -155.14, steps = 55 00:10:23 [INFO] train episode 2546: reward = -122.96, steps = 46 00:10:24 [INFO] train episode 2547: reward = -125.03, steps = 54 00:10:24 [INFO] train episode 2548: reward = -141.21, steps = 60 00:10:24 [INFO] train episode 2549: reward = -69.39, steps = 46 00:10:24 [INFO] train episode 2550: reward = -68.87, steps = 35 00:10:25 [INFO] train episode 2551: reward = -160.24, steps = 58 00:10:25 [INFO] train episode 2552: reward = -212.28, steps = 66 00:10:26 [INFO] train episode 2553: reward = -104.77, steps = 52 00:10:26 [INFO] train episode 2554: reward = -121.47, steps = 44 00:10:26 [INFO] train episode 2555: reward = -81.32, steps = 41 00:10:26 [INFO] train episode 2556: reward = -138.06, steps = 67 00:10:27 [INFO] train episode 2557: reward = -268.28, steps = 120 00:10:28 [INFO] train episode 2558: reward = -158.90, steps = 85 00:10:28 [INFO] train episode 2559: reward = -62.43, steps = 28 00:10:29 [INFO] train episode 2560: reward = -257.22, steps = 101 00:10:29 [INFO] train episode 2561: reward = -120.75, steps = 57 00:10:29 [INFO] train episode 2562: reward = -82.42, steps = 34 00:10:30 [INFO] train episode 2563: reward = -61.24, steps = 36 00:10:30 [INFO] train episode 2564: reward = -77.36, steps = 45 00:10:31 [INFO] train episode 2565: reward = -268.08, steps = 108 00:10:31 [INFO] train episode 2566: reward = -80.45, steps = 36 00:10:31 [INFO] train episode 2567: reward = -179.18, steps = 54 00:10:32 [INFO] train episode 2568: reward = -104.62, steps = 56 00:10:32 [INFO] train episode 2569: reward = -177.43, steps = 75 00:10:32 [INFO] train episode 2570: reward = -111.38, steps = 44 00:10:33 [INFO] train episode 2571: reward = -78.35, steps = 32 00:10:33 [INFO] train episode 2572: reward = -143.60, steps = 48 00:10:33 [INFO] train episode 2573: reward = -128.15, steps = 42 00:10:34 [INFO] train episode 2574: reward = -166.13, steps = 58 00:10:34 [INFO] train episode 2575: reward = -239.41, steps = 111 00:10:35 [INFO] train episode 2576: reward = -171.99, steps = 100 00:10:35 [INFO] train episode 2577: reward = -108.02, steps = 47 00:10:35 [INFO] train episode 2578: reward = -135.31, steps = 48 00:10:36 [INFO] train episode 2579: reward = -183.12, steps = 61 00:10:36 [INFO] train episode 2580: reward = -83.95, steps = 44 00:10:36 [INFO] train episode 2581: reward = -64.52, steps = 39 00:10:37 [INFO] train episode 2582: reward = -437.33, steps = 179 00:10:38 [INFO] train episode 2583: reward = -147.16, steps = 50 00:10:38 [INFO] train episode 2584: reward = -152.25, steps = 64 00:10:39 [INFO] train episode 2585: reward = -134.17, steps = 60 00:10:39 [INFO] train episode 2586: reward = -318.35, steps = 156 00:10:40 [INFO] train episode 2587: reward = -121.41, steps = 40 00:10:40 [INFO] train episode 2588: reward = -129.69, steps = 65 00:10:41 [INFO] train episode 2589: reward = -207.51, steps = 66 00:10:41 [INFO] train episode 2590: reward = -73.31, steps = 39 00:10:41 [INFO] train episode 2591: reward = -142.01, steps = 66 00:10:42 [INFO] train episode 2592: reward = -76.55, steps = 57 00:10:42 [INFO] train episode 2593: reward = -284.04, steps = 110 00:10:43 [INFO] train episode 2594: reward = -125.80, steps = 54 00:10:43 [INFO] train episode 2595: reward = -206.43, steps = 88 00:10:44 [INFO] train episode 2596: reward = -137.72, steps = 43 00:10:44 [INFO] train episode 2597: reward = -151.83, steps = 57 00:10:44 [INFO] train episode 2598: reward = -64.82, steps = 42 00:10:45 [INFO] train episode 2599: reward = -147.00, steps = 87 00:10:45 [INFO] train episode 2600: reward = -110.35, steps = 68 00:10:46 [INFO] train episode 2601: reward = -116.75, steps = 82 00:10:46 [INFO] train episode 2602: reward = -196.30, steps = 107 00:10:47 [INFO] train episode 2603: reward = -218.27, steps = 97 00:10:47 [INFO] train episode 2604: reward = -83.34, steps = 36 00:10:48 [INFO] train episode 2605: reward = -86.93, steps = 60 00:10:48 [INFO] train episode 2606: reward = -122.42, steps = 38 00:10:48 [INFO] train episode 2607: reward = -140.51, steps = 42 00:10:49 [INFO] train episode 2608: reward = -77.80, steps = 56 00:10:49 [INFO] train episode 2609: reward = -131.92, steps = 54 00:10:50 [INFO] train episode 2610: reward = -338.99, steps = 137 00:10:50 [INFO] train episode 2611: reward = -170.49, steps = 71 00:10:51 [INFO] train episode 2612: reward = -98.24, steps = 51 00:10:51 [INFO] train episode 2613: reward = -90.24, steps = 40 00:10:51 [INFO] train episode 2614: reward = -110.37, steps = 57 00:10:52 [INFO] train episode 2615: reward = -171.47, steps = 61 00:10:52 [INFO] train episode 2616: reward = -93.85, steps = 35 00:10:52 [INFO] train episode 2617: reward = -113.94, steps = 40 00:10:52 [INFO] train episode 2618: reward = -123.66, steps = 58 00:10:53 [INFO] train episode 2619: reward = -69.72, steps = 21 00:10:53 [INFO] train episode 2620: reward = -112.62, steps = 61 00:10:53 [INFO] train episode 2621: reward = -124.47, steps = 43 00:10:54 [INFO] train episode 2622: reward = -161.57, steps = 73 00:10:54 [INFO] train episode 2623: reward = -85.40, steps = 40 00:10:55 [INFO] train episode 2624: reward = -110.02, steps = 64 00:10:55 [INFO] train episode 2625: reward = -102.89, steps = 43 00:10:55 [INFO] train episode 2626: reward = -176.47, steps = 55 00:10:56 [INFO] train episode 2627: reward = -145.02, steps = 49 00:10:56 [INFO] train episode 2628: reward = -163.77, steps = 66 00:10:56 [INFO] train episode 2629: reward = -88.77, steps = 33 00:10:57 [INFO] train episode 2630: reward = -166.18, steps = 98 00:10:57 [INFO] train episode 2631: reward = -109.86, steps = 68 00:10:58 [INFO] train episode 2632: reward = -111.58, steps = 56 00:10:58 [INFO] train episode 2633: reward = -173.74, steps = 73 00:10:59 [INFO] train episode 2634: reward = -175.96, steps = 52 00:10:59 [INFO] train episode 2635: reward = -121.37, steps = 50 00:10:59 [INFO] train episode 2636: reward = -144.56, steps = 60 00:11:00 [INFO] train episode 2637: reward = -189.57, steps = 85 00:11:00 [INFO] train episode 2638: reward = -82.01, steps = 32 00:11:01 [INFO] train episode 2639: reward = -206.25, steps = 108 00:11:01 [INFO] train episode 2640: reward = -143.57, steps = 62 00:11:02 [INFO] train episode 2641: reward = -242.66, steps = 89 00:11:02 [INFO] train episode 2642: reward = -145.33, steps = 73 00:11:02 [INFO] train episode 2643: reward = -104.48, steps = 40 00:11:03 [INFO] train episode 2644: reward = -142.04, steps = 55 00:11:03 [INFO] train episode 2645: reward = -176.94, steps = 80 00:11:04 [INFO] train episode 2646: reward = -125.17, steps = 50 00:11:04 [INFO] train episode 2647: reward = -147.36, steps = 86 00:11:05 [INFO] train episode 2648: reward = -72.35, steps = 41 00:11:05 [INFO] train episode 2649: reward = -157.97, steps = 67 00:11:05 [INFO] train episode 2650: reward = -114.25, steps = 67 00:11:06 [INFO] train episode 2651: reward = -145.75, steps = 83 00:11:06 [INFO] train episode 2652: reward = -66.52, steps = 28 00:11:07 [INFO] train episode 2653: reward = -123.07, steps = 56 00:11:07 [INFO] train episode 2654: reward = -72.15, steps = 53 00:11:08 [INFO] train episode 2655: reward = -336.60, steps = 149 00:11:09 [INFO] train episode 2656: reward = -238.71, steps = 107 00:11:09 [INFO] train episode 2657: reward = -121.57, steps = 53 00:11:09 [INFO] train episode 2658: reward = -102.75, steps = 57 00:11:10 [INFO] train episode 2659: reward = -102.37, steps = 60 00:11:10 [INFO] train episode 2660: reward = -193.72, steps = 88 00:11:11 [INFO] train episode 2661: reward = -103.24, steps = 39 00:11:11 [INFO] train episode 2662: reward = -81.14, steps = 51 00:11:11 [INFO] train episode 2663: reward = -104.73, steps = 55 00:11:12 [INFO] train episode 2664: reward = -188.56, steps = 82 00:11:12 [INFO] train episode 2665: reward = -61.19, steps = 35 00:11:13 [INFO] train episode 2666: reward = -165.02, steps = 72 00:11:13 [INFO] train episode 2667: reward = -119.09, steps = 48 00:11:14 [INFO] train episode 2668: reward = -196.02, steps = 104 00:11:14 [INFO] train episode 2669: reward = -121.27, steps = 47 00:11:14 [INFO] train episode 2670: reward = -182.20, steps = 62 00:11:15 [INFO] train episode 2671: reward = -81.47, steps = 32 00:11:15 [INFO] train episode 2672: reward = -174.32, steps = 108 00:11:16 [INFO] train episode 2673: reward = -73.38, steps = 54 00:11:16 [INFO] train episode 2674: reward = -100.20, steps = 40 00:11:16 [INFO] train episode 2675: reward = -156.18, steps = 66 00:11:17 [INFO] train episode 2676: reward = -123.89, steps = 53 00:11:17 [INFO] train episode 2677: reward = -84.16, steps = 59 00:11:17 [INFO] train episode 2678: reward = -96.52, steps = 52 00:11:18 [INFO] train episode 2679: reward = -195.69, steps = 101 00:11:18 [INFO] train episode 2680: reward = -97.92, steps = 46 00:11:19 [INFO] train episode 2681: reward = -144.66, steps = 68 00:11:19 [INFO] train episode 2682: reward = -118.46, steps = 47 00:11:20 [INFO] train episode 2683: reward = -139.16, steps = 66 00:11:20 [INFO] train episode 2684: reward = -136.82, steps = 74 00:11:20 [INFO] train episode 2685: reward = -117.62, steps = 44 00:11:21 [INFO] train episode 2686: reward = -141.50, steps = 50 00:11:21 [INFO] train episode 2687: reward = -167.37, steps = 61 00:11:22 [INFO] train episode 2688: reward = -68.87, steps = 59 00:11:22 [INFO] train episode 2689: reward = -199.05, steps = 63 00:11:22 [INFO] train episode 2690: reward = -133.95, steps = 59 00:11:23 [INFO] train episode 2691: reward = -148.17, steps = 78 00:11:23 [INFO] train episode 2692: reward = -108.15, steps = 48 00:11:23 [INFO] train episode 2693: reward = -81.83, steps = 39 00:11:24 [INFO] train episode 2694: reward = -87.97, steps = 36 00:11:24 [INFO] train episode 2695: reward = -138.29, steps = 65 00:11:24 [INFO] train episode 2696: reward = -85.49, steps = 22 00:11:25 [INFO] train episode 2697: reward = -93.09, steps = 58 00:11:25 [INFO] train episode 2698: reward = -142.34, steps = 51 00:11:25 [INFO] train episode 2699: reward = -146.83, steps = 51 00:11:26 [INFO] train episode 2700: reward = -133.71, steps = 50 00:11:26 [INFO] train episode 2701: reward = -149.04, steps = 83 00:11:27 [INFO] train episode 2702: reward = -138.44, steps = 57 00:11:27 [INFO] train episode 2703: reward = -63.58, steps = 22 00:11:27 [INFO] train episode 2704: reward = -117.37, steps = 30 00:11:28 [INFO] train episode 2705: reward = -252.41, steps = 90 00:11:28 [INFO] train episode 2706: reward = -110.97, steps = 70 00:11:28 [INFO] train episode 2707: reward = -120.51, steps = 45 00:11:29 [INFO] train episode 2708: reward = -84.27, steps = 44 00:11:29 [INFO] train episode 2709: reward = -67.57, steps = 39 00:11:29 [INFO] train episode 2710: reward = -92.91, steps = 49 00:11:30 [INFO] train episode 2711: reward = -193.70, steps = 65 00:11:30 [INFO] train episode 2712: reward = -217.49, steps = 69 00:11:30 [INFO] train episode 2713: reward = -126.30, steps = 53 00:11:31 [INFO] train episode 2714: reward = -151.25, steps = 62 00:11:31 [INFO] train episode 2715: reward = -92.04, steps = 33 00:11:31 [INFO] train episode 2716: reward = -153.77, steps = 62 00:11:32 [INFO] train episode 2717: reward = -122.22, steps = 61 00:11:32 [INFO] train episode 2718: reward = -113.38, steps = 48 00:11:32 [INFO] train episode 2719: reward = -113.19, steps = 69 00:11:33 [INFO] train episode 2720: reward = -145.39, steps = 52 00:11:33 [INFO] train episode 2721: reward = -151.84, steps = 57 00:11:34 [INFO] train episode 2722: reward = -73.08, steps = 57 00:11:34 [INFO] train episode 2723: reward = -88.14, steps = 45 00:11:34 [INFO] train episode 2724: reward = -112.41, steps = 51 00:11:35 [INFO] train episode 2725: reward = -129.15, steps = 48 00:11:35 [INFO] train episode 2726: reward = -152.23, steps = 58 00:11:35 [INFO] train episode 2727: reward = -124.31, steps = 45 00:11:36 [INFO] train episode 2728: reward = -63.20, steps = 37 00:11:36 [INFO] train episode 2729: reward = -88.34, steps = 44 00:11:36 [INFO] train episode 2730: reward = -132.03, steps = 55 00:11:37 [INFO] train episode 2731: reward = -115.79, steps = 60 00:11:37 [INFO] train episode 2732: reward = -159.79, steps = 81 00:11:38 [INFO] train episode 2733: reward = -130.01, steps = 88 00:11:38 [INFO] train episode 2734: reward = -122.89, steps = 69 00:11:39 [INFO] train episode 2735: reward = -118.88, steps = 46 00:11:39 [INFO] train episode 2736: reward = -43.23, steps = 19 00:11:39 [INFO] train episode 2737: reward = -168.54, steps = 82 00:11:40 [INFO] train episode 2738: reward = -117.27, steps = 47 00:11:40 [INFO] train episode 2739: reward = -145.24, steps = 63 00:11:40 [INFO] train episode 2740: reward = -142.06, steps = 59 00:11:41 [INFO] train episode 2741: reward = -146.59, steps = 58 00:11:41 [INFO] train episode 2742: reward = -116.88, steps = 48 00:11:41 [INFO] train episode 2743: reward = -109.99, steps = 52 00:11:42 [INFO] train episode 2744: reward = -98.92, steps = 59 00:11:42 [INFO] train episode 2745: reward = -205.00, steps = 88 00:11:43 [INFO] train episode 2746: reward = -130.44, steps = 52 00:11:43 [INFO] train episode 2747: reward = -159.06, steps = 63 00:11:43 [INFO] train episode 2748: reward = -126.22, steps = 48 00:11:44 [INFO] train episode 2749: reward = -79.02, steps = 44 00:11:44 [INFO] train episode 2750: reward = -142.81, steps = 80 00:11:45 [INFO] train episode 2751: reward = -133.15, steps = 63 00:11:45 [INFO] train episode 2752: reward = -133.89, steps = 57 00:11:45 [INFO] train episode 2753: reward = -132.09, steps = 51 00:11:45 [INFO] train episode 2754: reward = -116.39, steps = 42 00:11:46 [INFO] train episode 2755: reward = -85.71, steps = 56 00:11:46 [INFO] train episode 2756: reward = -174.07, steps = 69 00:11:46 [INFO] train episode 2757: reward = -76.42, steps = 29 00:11:47 [INFO] train episode 2758: reward = -216.96, steps = 105 00:11:48 [INFO] train episode 2759: reward = -176.76, steps = 104 00:11:48 [INFO] train episode 2760: reward = -51.16, steps = 50 00:11:49 [INFO] train episode 2761: reward = -65.49, steps = 56 00:11:49 [INFO] train episode 2762: reward = -146.79, steps = 60 00:11:50 [INFO] train episode 2763: reward = -116.23, steps = 71 00:11:50 [INFO] train episode 2764: reward = -159.37, steps = 92 00:11:51 [INFO] train episode 2765: reward = -132.11, steps = 65 00:11:51 [INFO] train episode 2766: reward = -80.12, steps = 20 00:11:51 [INFO] train episode 2767: reward = -81.45, steps = 57 00:11:52 [INFO] train episode 2768: reward = -139.18, steps = 92 00:11:52 [INFO] train episode 2769: reward = -90.13, steps = 40 00:11:52 [INFO] train episode 2770: reward = -161.31, steps = 57 00:11:53 [INFO] train episode 2771: reward = -84.74, steps = 45 00:11:53 [INFO] train episode 2772: reward = -147.77, steps = 57 00:11:53 [INFO] train episode 2773: reward = -91.71, steps = 54 00:11:54 [INFO] train episode 2774: reward = -82.77, steps = 47 00:11:54 [INFO] train episode 2775: reward = -137.85, steps = 85 00:11:54 [INFO] train episode 2776: reward = -64.67, steps = 19 00:11:55 [INFO] train episode 2777: reward = -122.06, steps = 62 00:11:56 [INFO] train episode 2778: reward = -125.44, steps = 119 00:11:56 [INFO] train episode 2779: reward = -171.75, steps = 47 00:11:56 [INFO] train episode 2780: reward = -146.04, steps = 47 00:11:57 [INFO] train episode 2781: reward = -149.78, steps = 62 00:11:57 [INFO] train episode 2782: reward = -96.93, steps = 43 00:11:57 [INFO] train episode 2783: reward = -101.21, steps = 39 00:11:57 [INFO] train episode 2784: reward = -130.44, steps = 53 00:11:58 [INFO] train episode 2785: reward = -160.94, steps = 53 00:11:58 [INFO] train episode 2786: reward = -98.43, steps = 59 00:11:59 [INFO] train episode 2787: reward = -164.25, steps = 64 00:11:59 [INFO] train episode 2788: reward = -72.78, steps = 39 00:11:59 [INFO] train episode 2789: reward = -134.19, steps = 67 00:12:00 [INFO] train episode 2790: reward = -141.98, steps = 55 00:12:00 [INFO] train episode 2791: reward = -151.51, steps = 88 00:12:00 [INFO] train episode 2792: reward = -77.18, steps = 41 00:12:01 [INFO] train episode 2793: reward = -95.53, steps = 46 00:12:01 [INFO] train episode 2794: reward = -90.79, steps = 54 00:12:02 [INFO] train episode 2795: reward = -135.71, steps = 51 00:12:02 [INFO] train episode 2796: reward = -128.58, steps = 83 00:12:03 [INFO] train episode 2797: reward = -119.05, steps = 66 00:12:03 [INFO] train episode 2798: reward = -125.00, steps = 84 00:12:03 [INFO] train episode 2799: reward = -97.01, steps = 42 00:12:04 [INFO] train episode 2800: reward = -118.61, steps = 40 00:12:04 [INFO] train episode 2801: reward = -105.93, steps = 72 00:12:04 [INFO] train episode 2802: reward = -90.53, steps = 54 00:12:05 [INFO] train episode 2803: reward = -146.07, steps = 83 00:12:05 [INFO] train episode 2804: reward = -128.37, steps = 59 00:12:06 [INFO] train episode 2805: reward = -149.93, steps = 75 00:12:06 [INFO] train episode 2806: reward = -152.03, steps = 78 00:12:07 [INFO] train episode 2807: reward = -73.10, steps = 58 00:12:07 [INFO] train episode 2808: reward = -113.95, steps = 48 00:12:08 [INFO] train episode 2809: reward = -148.17, steps = 65 00:12:08 [INFO] train episode 2810: reward = -141.08, steps = 52 00:12:09 [INFO] train episode 2811: reward = -241.06, steps = 116 00:12:09 [INFO] train episode 2812: reward = -86.80, steps = 43 00:12:09 [INFO] train episode 2813: reward = -124.52, steps = 54 00:12:10 [INFO] train episode 2814: reward = -113.77, steps = 54 00:12:10 [INFO] train episode 2815: reward = -127.65, steps = 47 00:12:10 [INFO] train episode 2816: reward = -97.25, steps = 45 00:12:10 [INFO] train episode 2817: reward = -96.23, steps = 41 00:12:11 [INFO] train episode 2818: reward = -168.76, steps = 75 00:12:11 [INFO] train episode 2819: reward = -122.32, steps = 80 00:12:12 [INFO] train episode 2820: reward = -168.47, steps = 59 00:12:13 [INFO] train episode 2821: reward = -218.23, steps = 126 00:12:13 [INFO] train episode 2822: reward = -135.53, steps = 47 00:12:13 [INFO] train episode 2823: reward = -120.68, steps = 68 00:12:14 [INFO] train episode 2824: reward = -154.53, steps = 68 00:12:14 [INFO] train episode 2825: reward = -139.20, steps = 72 00:12:15 [INFO] train episode 2826: reward = -88.37, steps = 41 00:12:15 [INFO] train episode 2827: reward = -74.16, steps = 57 00:12:15 [INFO] train episode 2828: reward = -140.83, steps = 50 00:12:16 [INFO] train episode 2829: reward = -122.52, steps = 63 00:12:16 [INFO] train episode 2830: reward = -83.64, steps = 28 00:12:16 [INFO] train episode 2831: reward = -89.41, steps = 60 00:12:17 [INFO] train episode 2832: reward = -142.87, steps = 56 00:12:17 [INFO] train episode 2833: reward = -105.47, steps = 73 00:12:18 [INFO] train episode 2834: reward = -155.80, steps = 56 00:12:18 [INFO] train episode 2835: reward = -125.47, steps = 76 00:12:19 [INFO] train episode 2836: reward = -148.61, steps = 87 00:12:19 [INFO] train episode 2837: reward = -67.41, steps = 41 00:12:19 [INFO] train episode 2838: reward = -121.30, steps = 46 00:12:20 [INFO] train episode 2839: reward = -136.86, steps = 64 00:12:20 [INFO] train episode 2840: reward = -88.76, steps = 53 00:12:20 [INFO] train episode 2841: reward = -103.24, steps = 55 00:12:21 [INFO] train episode 2842: reward = -90.74, steps = 58 00:12:21 [INFO] train episode 2843: reward = -102.99, steps = 54 00:12:22 [INFO] train episode 2844: reward = -188.22, steps = 86 00:12:22 [INFO] train episode 2845: reward = -81.36, steps = 64 00:12:22 [INFO] train episode 2846: reward = -98.32, steps = 45 00:12:23 [INFO] train episode 2847: reward = -161.52, steps = 75 00:12:23 [INFO] train episode 2848: reward = -124.69, steps = 38 00:12:23 [INFO] train episode 2849: reward = -178.26, steps = 69 00:12:24 [INFO] train episode 2850: reward = -114.62, steps = 51 00:12:24 [INFO] train episode 2851: reward = -117.10, steps = 56 00:12:25 [INFO] train episode 2852: reward = -133.86, steps = 71 00:12:25 [INFO] train episode 2853: reward = -126.96, steps = 76 00:12:25 [INFO] train episode 2854: reward = -72.08, steps = 58 00:12:26 [INFO] train episode 2855: reward = -131.46, steps = 56 00:12:26 [INFO] train episode 2856: reward = -65.41, steps = 42 00:12:26 [INFO] train episode 2857: reward = -146.13, steps = 60 00:12:27 [INFO] train episode 2858: reward = -191.98, steps = 102 00:12:28 [INFO] train episode 2859: reward = -58.15, steps = 25 00:12:28 [INFO] train episode 2860: reward = -152.49, steps = 59 00:12:28 [INFO] train episode 2861: reward = -80.73, steps = 75 00:12:29 [INFO] train episode 2862: reward = -89.87, steps = 65 00:12:29 [INFO] train episode 2863: reward = -58.84, steps = 46 00:12:29 [INFO] train episode 2864: reward = -103.37, steps = 45 00:12:30 [INFO] train episode 2865: reward = -74.33, steps = 52 00:12:30 [INFO] train episode 2866: reward = -92.94, steps = 61 00:12:30 [INFO] train episode 2867: reward = -118.65, steps = 52 00:12:31 [INFO] train episode 2868: reward = -152.66, steps = 71 00:12:31 [INFO] train episode 2869: reward = -90.07, steps = 46 00:12:31 [INFO] train episode 2870: reward = -90.35, steps = 44 00:12:32 [INFO] train episode 2871: reward = -133.83, steps = 77 00:12:32 [INFO] train episode 2872: reward = -103.13, steps = 65 00:12:33 [INFO] train episode 2873: reward = -145.63, steps = 52 00:12:33 [INFO] train episode 2874: reward = -132.04, steps = 69 00:12:33 [INFO] train episode 2875: reward = -125.27, steps = 52 00:12:34 [INFO] train episode 2876: reward = -136.70, steps = 67 00:12:34 [INFO] train episode 2877: reward = -74.84, steps = 51 00:12:35 [INFO] train episode 2878: reward = -98.73, steps = 50 00:12:35 [INFO] train episode 2879: reward = -101.56, steps = 67 00:12:35 [INFO] train episode 2880: reward = -89.00, steps = 34 00:12:35 [INFO] train episode 2881: reward = -72.04, steps = 34 00:12:36 [INFO] train episode 2882: reward = -108.52, steps = 47 00:12:36 [INFO] train episode 2883: reward = -101.18, steps = 65 00:12:37 [INFO] train episode 2884: reward = -186.58, steps = 84 00:12:37 [INFO] train episode 2885: reward = -139.30, steps = 50 00:12:37 [INFO] train episode 2886: reward = -87.98, steps = 32 00:12:38 [INFO] train episode 2887: reward = -68.93, steps = 55 00:12:38 [INFO] train episode 2888: reward = -90.60, steps = 35 00:12:38 [INFO] train episode 2889: reward = -129.85, steps = 65 00:12:39 [INFO] train episode 2890: reward = -125.91, steps = 75 00:12:39 [INFO] train episode 2891: reward = -151.70, steps = 80 00:12:40 [INFO] train episode 2892: reward = -136.86, steps = 74 00:12:41 [INFO] train episode 2893: reward = -164.82, steps = 92 00:12:41 [INFO] train episode 2894: reward = -83.58, steps = 65 00:12:41 [INFO] train episode 2895: reward = -90.33, steps = 58 00:12:42 [INFO] train episode 2896: reward = -175.21, steps = 98 00:12:42 [INFO] train episode 2897: reward = -64.62, steps = 29 00:12:43 [INFO] train episode 2898: reward = -79.66, steps = 52 00:12:43 [INFO] train episode 2899: reward = -96.42, steps = 57 00:12:43 [INFO] train episode 2900: reward = -112.13, steps = 45 00:12:44 [INFO] train episode 2901: reward = -135.66, steps = 60 00:12:44 [INFO] train episode 2902: reward = -111.50, steps = 62 00:12:45 [INFO] train episode 2903: reward = -223.74, steps = 111 00:12:45 [INFO] train episode 2904: reward = -173.50, steps = 71 00:12:46 [INFO] train episode 2905: reward = -141.29, steps = 63 00:12:46 [INFO] train episode 2906: reward = -154.52, steps = 64 00:12:47 [INFO] train episode 2907: reward = -91.09, steps = 72 00:12:47 [INFO] train episode 2908: reward = -106.69, steps = 67 00:12:47 [INFO] train episode 2909: reward = -70.01, steps = 53 00:12:48 [INFO] train episode 2910: reward = -101.38, steps = 56 00:12:48 [INFO] train episode 2911: reward = -168.06, steps = 55 00:12:48 [INFO] train episode 2912: reward = -66.78, steps = 41 00:12:49 [INFO] train episode 2913: reward = -124.90, steps = 46 00:12:49 [INFO] train episode 2914: reward = -183.78, steps = 80 00:12:50 [INFO] train episode 2915: reward = -99.54, steps = 76 00:12:50 [INFO] train episode 2916: reward = -119.04, steps = 50 00:12:50 [INFO] train episode 2917: reward = -161.34, steps = 61 00:12:51 [INFO] train episode 2918: reward = -102.41, steps = 41 00:12:51 [INFO] train episode 2919: reward = -75.84, steps = 58 00:12:51 [INFO] train episode 2920: reward = -141.37, steps = 60 00:12:52 [INFO] train episode 2921: reward = -140.34, steps = 57 00:12:52 [INFO] train episode 2922: reward = -114.62, steps = 36 00:12:52 [INFO] train episode 2923: reward = -128.63, steps = 57 00:12:53 [INFO] train episode 2924: reward = -140.04, steps = 61 00:12:53 [INFO] train episode 2925: reward = -106.00, steps = 53 00:12:53 [INFO] train episode 2926: reward = -125.73, steps = 50 00:12:54 [INFO] train episode 2927: reward = -140.50, steps = 55 00:12:54 [INFO] train episode 2928: reward = -102.58, steps = 42 00:12:55 [INFO] train episode 2929: reward = -112.85, steps = 52 00:12:55 [INFO] train episode 2930: reward = -129.53, steps = 64 00:12:55 [INFO] train episode 2931: reward = -87.28, steps = 53 00:12:56 [INFO] train episode 2932: reward = -94.88, steps = 72 00:12:56 [INFO] train episode 2933: reward = -85.69, steps = 45 00:12:57 [INFO] train episode 2934: reward = -89.20, steps = 80 00:12:57 [INFO] train episode 2935: reward = -41.49, steps = 49 00:12:57 [INFO] train episode 2936: reward = -135.05, steps = 68 00:12:58 [INFO] train episode 2937: reward = -142.89, steps = 74 00:12:58 [INFO] train episode 2938: reward = -98.88, steps = 45 00:12:59 [INFO] train episode 2939: reward = -155.32, steps = 134 00:12:59 [INFO] train episode 2940: reward = -107.52, steps = 62 00:13:00 [INFO] train episode 2941: reward = -55.73, steps = 29 00:13:00 [INFO] train episode 2942: reward = -81.52, steps = 55 00:13:00 [INFO] train episode 2943: reward = -89.39, steps = 60 00:13:01 [INFO] train episode 2944: reward = -134.61, steps = 70 00:13:01 [INFO] train episode 2945: reward = -103.99, steps = 45 00:13:02 [INFO] train episode 2946: reward = -106.73, steps = 60 00:13:02 [INFO] train episode 2947: reward = -114.60, steps = 48 00:13:02 [INFO] train episode 2948: reward = -146.39, steps = 63 00:13:03 [INFO] train episode 2949: reward = -100.64, steps = 52 00:13:03 [INFO] train episode 2950: reward = -130.58, steps = 95 00:13:04 [INFO] train episode 2951: reward = -111.46, steps = 71 00:13:04 [INFO] train episode 2952: reward = -76.13, steps = 60 00:13:05 [INFO] train episode 2953: reward = -111.48, steps = 42 00:13:05 [INFO] train episode 2954: reward = -76.18, steps = 72 00:13:05 [INFO] train episode 2955: reward = -92.53, steps = 49 00:13:06 [INFO] train episode 2956: reward = -100.48, steps = 62 00:13:06 [INFO] train episode 2957: reward = -149.08, steps = 75 00:13:07 [INFO] train episode 2958: reward = -114.00, steps = 54 00:13:07 [INFO] train episode 2959: reward = -95.14, steps = 42 00:13:08 [INFO] train episode 2960: reward = -138.63, steps = 74 00:13:08 [INFO] train episode 2961: reward = -97.95, steps = 62 00:13:08 [INFO] train episode 2962: reward = -121.18, steps = 49 00:13:09 [INFO] train episode 2963: reward = -127.93, steps = 50 00:13:09 [INFO] train episode 2964: reward = -97.88, steps = 49 00:13:09 [INFO] train episode 2965: reward = -130.46, steps = 74 00:13:10 [INFO] train episode 2966: reward = -129.43, steps = 75 00:13:10 [INFO] train episode 2967: reward = -92.89, steps = 44 00:13:11 [INFO] train episode 2968: reward = -83.90, steps = 54 00:13:11 [INFO] train episode 2969: reward = -93.44, steps = 42 00:13:11 [INFO] train episode 2970: reward = -120.26, steps = 78 00:13:12 [INFO] train episode 2971: reward = -164.63, steps = 98 00:13:12 [INFO] train episode 2972: reward = -81.16, steps = 59 00:13:13 [INFO] train episode 2973: reward = -150.37, steps = 83 00:13:13 [INFO] train episode 2974: reward = -58.06, steps = 67 00:13:14 [INFO] train episode 2975: reward = -121.62, steps = 64 00:13:14 [INFO] train episode 2976: reward = -177.50, steps = 94 00:13:15 [INFO] train episode 2977: reward = -155.25, steps = 64 00:13:15 [INFO] train episode 2978: reward = -52.50, steps = 52 00:13:16 [INFO] train episode 2979: reward = -194.87, steps = 82 00:13:16 [INFO] train episode 2980: reward = -73.66, steps = 64 00:13:16 [INFO] train episode 2981: reward = -88.42, steps = 61 00:13:17 [INFO] train episode 2982: reward = -147.31, steps = 60 00:13:17 [INFO] train episode 2983: reward = -107.94, steps = 89 00:13:18 [INFO] train episode 2984: reward = -100.25, steps = 50 00:13:18 [INFO] train episode 2985: reward = -122.52, steps = 54 00:13:18 [INFO] train episode 2986: reward = -91.75, steps = 65 00:13:19 [INFO] train episode 2987: reward = -183.57, steps = 119 00:13:20 [INFO] train episode 2988: reward = -81.20, steps = 58 00:13:20 [INFO] train episode 2989: reward = -74.21, steps = 55 00:13:20 [INFO] train episode 2990: reward = -87.74, steps = 54 00:13:21 [INFO] train episode 2991: reward = -75.60, steps = 45 00:13:21 [INFO] train episode 2992: reward = -163.34, steps = 83 00:13:22 [INFO] train episode 2993: reward = -64.67, steps = 37 00:13:22 [INFO] train episode 2994: reward = -156.90, steps = 88 00:13:23 [INFO] train episode 2995: reward = -122.10, steps = 55 00:13:23 [INFO] train episode 2996: reward = -105.62, steps = 73 00:13:24 [INFO] train episode 2997: reward = -121.43, steps = 104 00:13:24 [INFO] train episode 2998: reward = -113.27, steps = 65 00:13:24 [INFO] train episode 2999: reward = -47.18, steps = 43 00:13:25 [INFO] train episode 3000: reward = -100.25, steps = 50 00:13:25 [INFO] train episode 3001: reward = -102.05, steps = 40 00:13:25 [INFO] train episode 3002: reward = -104.18, steps = 51 00:13:26 [INFO] train episode 3003: reward = -115.01, steps = 52 00:13:26 [INFO] train episode 3004: reward = -81.40, steps = 36 00:13:26 [INFO] train episode 3005: reward = -116.82, steps = 43 00:13:27 [INFO] train episode 3006: reward = -98.42, steps = 54 00:13:27 [INFO] train episode 3007: reward = -97.08, steps = 53 00:13:27 [INFO] train episode 3008: reward = -75.09, steps = 39 00:13:28 [INFO] train episode 3009: reward = -108.84, steps = 53 00:13:28 [INFO] train episode 3010: reward = -120.58, steps = 58 00:13:28 [INFO] train episode 3011: reward = -102.57, steps = 43 00:13:29 [INFO] train episode 3012: reward = -123.30, steps = 58 00:13:29 [INFO] train episode 3013: reward = -102.41, steps = 54 00:13:29 [INFO] train episode 3014: reward = -80.28, steps = 41 00:13:30 [INFO] train episode 3015: reward = -111.83, steps = 52 00:13:30 [INFO] train episode 3016: reward = -107.14, steps = 88 00:13:30 [INFO] train episode 3017: reward = -107.52, steps = 61 00:13:31 [INFO] train episode 3018: reward = -115.17, steps = 46 00:13:31 [INFO] train episode 3019: reward = -131.28, steps = 73 00:13:32 [INFO] train episode 3020: reward = -80.12, steps = 66 00:13:32 [INFO] train episode 3021: reward = -164.36, steps = 79 00:13:33 [INFO] train episode 3022: reward = -94.92, steps = 56 00:13:33 [INFO] train episode 3023: reward = -144.26, steps = 73 00:13:33 [INFO] train episode 3024: reward = -98.89, steps = 37 00:13:34 [INFO] train episode 3025: reward = -111.70, steps = 85 00:13:34 [INFO] train episode 3026: reward = -95.32, steps = 47 00:13:35 [INFO] train episode 3027: reward = -62.43, steps = 18 00:13:35 [INFO] train episode 3028: reward = -106.72, steps = 70 00:13:35 [INFO] train episode 3029: reward = -44.32, steps = 35 00:13:36 [INFO] train episode 3030: reward = -85.98, steps = 53 00:13:36 [INFO] train episode 3031: reward = -117.10, steps = 53 00:13:36 [INFO] train episode 3032: reward = -128.92, steps = 62 00:13:37 [INFO] train episode 3033: reward = -119.05, steps = 47 00:13:37 [INFO] train episode 3034: reward = -92.70, steps = 49 00:13:37 [INFO] train episode 3035: reward = -100.72, steps = 51 00:13:38 [INFO] train episode 3036: reward = -132.29, steps = 86 00:13:38 [INFO] train episode 3037: reward = -99.23, steps = 50 00:13:39 [INFO] train episode 3038: reward = -88.50, steps = 46 00:13:39 [INFO] train episode 3039: reward = -129.40, steps = 47 00:13:39 [INFO] train episode 3040: reward = -123.60, steps = 62 00:13:40 [INFO] train episode 3041: reward = -59.75, steps = 51 00:13:40 [INFO] train episode 3042: reward = -86.92, steps = 63 00:13:40 [INFO] train episode 3043: reward = -67.86, steps = 27 00:13:41 [INFO] train episode 3044: reward = -61.91, steps = 53 00:13:41 [INFO] train episode 3045: reward = -128.04, steps = 97 00:13:41 [INFO] train episode 3046: reward = -73.27, steps = 43 00:13:42 [INFO] train episode 3047: reward = -126.49, steps = 77 00:13:42 [INFO] train episode 3048: reward = -80.08, steps = 39 00:13:43 [INFO] train episode 3049: reward = -82.10, steps = 40 00:13:43 [INFO] train episode 3050: reward = -123.67, steps = 44 00:13:43 [INFO] train episode 3051: reward = -78.29, steps = 54 00:13:43 [INFO] train episode 3052: reward = -53.19, steps = 43 00:13:44 [INFO] train episode 3053: reward = -56.77, steps = 48 00:13:44 [INFO] train episode 3054: reward = -134.13, steps = 69 00:13:45 [INFO] train episode 3055: reward = -105.69, steps = 48 00:13:45 [INFO] train episode 3056: reward = -77.92, steps = 46 00:13:45 [INFO] train episode 3057: reward = -95.32, steps = 69 00:13:46 [INFO] train episode 3058: reward = -79.61, steps = 38 00:13:46 [INFO] train episode 3059: reward = -56.29, steps = 44 00:13:46 [INFO] train episode 3060: reward = -112.41, steps = 48 00:13:47 [INFO] train episode 3061: reward = -80.55, steps = 56 00:13:47 [INFO] train episode 3062: reward = -88.97, steps = 52 00:13:47 [INFO] train episode 3063: reward = -105.25, steps = 53 00:13:48 [INFO] train episode 3064: reward = -117.88, steps = 57 00:13:48 [INFO] train episode 3065: reward = -38.86, steps = 49 00:13:49 [INFO] train episode 3066: reward = -97.90, steps = 61 00:13:49 [INFO] train episode 3067: reward = -66.49, steps = 46 00:13:49 [INFO] train episode 3068: reward = -89.88, steps = 45 00:13:49 [INFO] train episode 3069: reward = -54.41, steps = 45 00:13:50 [INFO] train episode 3070: reward = -74.26, steps = 41 00:13:50 [INFO] train episode 3071: reward = -84.46, steps = 54 00:13:51 [INFO] train episode 3072: reward = -150.82, steps = 86 00:13:51 [INFO] train episode 3073: reward = -79.78, steps = 38 00:13:51 [INFO] train episode 3074: reward = -84.48, steps = 55 00:13:52 [INFO] train episode 3075: reward = -111.80, steps = 100 00:13:52 [INFO] train episode 3076: reward = -133.85, steps = 56 00:13:53 [INFO] train episode 3077: reward = -118.80, steps = 74 00:13:53 [INFO] train episode 3078: reward = -106.46, steps = 47 00:13:53 [INFO] train episode 3079: reward = -126.88, steps = 51 00:13:54 [INFO] train episode 3080: reward = -95.27, steps = 47 00:13:54 [INFO] train episode 3081: reward = -49.49, steps = 39 00:13:54 [INFO] train episode 3082: reward = -101.25, steps = 43 00:13:55 [INFO] train episode 3083: reward = -105.24, steps = 40 00:13:55 [INFO] train episode 3084: reward = -85.16, steps = 43 00:13:55 [INFO] train episode 3085: reward = -108.21, steps = 99 00:13:56 [INFO] train episode 3086: reward = -63.33, steps = 61 00:13:56 [INFO] train episode 3087: reward = -82.90, steps = 55 00:13:57 [INFO] train episode 3088: reward = -56.56, steps = 63 00:13:57 [INFO] train episode 3089: reward = -76.24, steps = 52 00:13:57 [INFO] train episode 3090: reward = -78.89, steps = 63 00:13:58 [INFO] train episode 3091: reward = -94.72, steps = 46 00:13:58 [INFO] train episode 3092: reward = -159.83, steps = 86 00:13:59 [INFO] train episode 3093: reward = -60.26, steps = 51 00:13:59 [INFO] train episode 3094: reward = -88.20, steps = 40 00:13:59 [INFO] train episode 3095: reward = -41.89, steps = 53 00:14:00 [INFO] train episode 3096: reward = -125.38, steps = 76 00:14:00 [INFO] train episode 3097: reward = -93.07, steps = 47 00:14:00 [INFO] train episode 3098: reward = -59.52, steps = 55 00:14:01 [INFO] train episode 3099: reward = -131.88, steps = 68 00:14:01 [INFO] train episode 3100: reward = -88.82, steps = 49 00:14:02 [INFO] train episode 3101: reward = -94.33, steps = 81 00:14:02 [INFO] train episode 3102: reward = -79.84, steps = 69 00:14:03 [INFO] train episode 3103: reward = -100.70, steps = 65 00:14:03 [INFO] train episode 3104: reward = -68.04, steps = 58 00:14:03 [INFO] train episode 3105: reward = -66.16, steps = 48 00:14:04 [INFO] train episode 3106: reward = -92.21, steps = 60 00:14:04 [INFO] train episode 3107: reward = -60.60, steps = 38 00:14:04 [INFO] train episode 3108: reward = -110.02, steps = 46 00:14:05 [INFO] train episode 3109: reward = -103.73, steps = 54 00:14:05 [INFO] train episode 3110: reward = -59.52, steps = 30 00:14:05 [INFO] train episode 3111: reward = -53.22, steps = 40 00:14:06 [INFO] train episode 3112: reward = -61.44, steps = 44 00:14:06 [INFO] train episode 3113: reward = -50.92, steps = 46 00:14:06 [INFO] train episode 3114: reward = -103.73, steps = 48 00:14:07 [INFO] train episode 3115: reward = -50.77, steps = 59 00:14:07 [INFO] train episode 3116: reward = -91.96, steps = 58 00:14:07 [INFO] train episode 3117: reward = -73.29, steps = 54 00:14:08 [INFO] train episode 3118: reward = -110.81, steps = 64 00:14:08 [INFO] train episode 3119: reward = -90.10, steps = 41 00:14:08 [INFO] train episode 3120: reward = -61.85, steps = 55 00:14:09 [INFO] train episode 3121: reward = -90.80, steps = 42 00:14:09 [INFO] train episode 3122: reward = -90.40, steps = 82 00:14:10 [INFO] train episode 3123: reward = -71.16, steps = 49 00:14:10 [INFO] train episode 3124: reward = -89.51, steps = 57 00:14:10 [INFO] train episode 3125: reward = -98.28, steps = 57 00:14:11 [INFO] train episode 3126: reward = -105.91, steps = 52 00:14:11 [INFO] train episode 3127: reward = -47.23, steps = 43 00:14:11 [INFO] train episode 3128: reward = -66.47, steps = 38 00:14:11 [INFO] train episode 3129: reward = -63.79, steps = 35 00:14:12 [INFO] train episode 3130: reward = -99.70, steps = 46 00:14:12 [INFO] train episode 3131: reward = -92.34, steps = 53 00:14:12 [INFO] train episode 3132: reward = -60.96, steps = 32 00:14:13 [INFO] train episode 3133: reward = -69.65, steps = 52 00:14:13 [INFO] train episode 3134: reward = -96.66, steps = 47 00:14:13 [INFO] train episode 3135: reward = -81.44, steps = 60 00:14:14 [INFO] train episode 3136: reward = -73.56, steps = 49 00:14:14 [INFO] train episode 3137: reward = -70.71, steps = 40 00:14:15 [INFO] train episode 3138: reward = -107.85, steps = 60 00:14:15 [INFO] train episode 3139: reward = -47.57, steps = 39 00:14:15 [INFO] train episode 3140: reward = -100.23, steps = 74 00:14:16 [INFO] train episode 3141: reward = -55.16, steps = 39 00:14:16 [INFO] train episode 3142: reward = -76.10, steps = 54 00:14:16 [INFO] train episode 3143: reward = -111.87, steps = 39 00:14:17 [INFO] train episode 3144: reward = -83.64, steps = 63 00:14:17 [INFO] train episode 3145: reward = -118.48, steps = 56 00:14:17 [INFO] train episode 3146: reward = -125.96, steps = 55 00:14:18 [INFO] train episode 3147: reward = -72.70, steps = 65 00:14:18 [INFO] train episode 3148: reward = -80.41, steps = 44 00:14:18 [INFO] train episode 3149: reward = -101.10, steps = 50 00:14:19 [INFO] train episode 3150: reward = -117.11, steps = 66 00:14:19 [INFO] train episode 3151: reward = -80.12, steps = 57 00:14:20 [INFO] train episode 3152: reward = -67.92, steps = 51 00:14:20 [INFO] train episode 3153: reward = -114.59, steps = 48 00:14:20 [INFO] train episode 3154: reward = -167.22, steps = 65 00:14:21 [INFO] train episode 3155: reward = -146.04, steps = 62 00:14:21 [INFO] train episode 3156: reward = -82.88, steps = 52 00:14:21 [INFO] train episode 3157: reward = -52.72, steps = 48 00:14:22 [INFO] train episode 3158: reward = -79.96, steps = 62 00:14:22 [INFO] train episode 3159: reward = -70.66, steps = 42 00:14:22 [INFO] train episode 3160: reward = -111.67, steps = 52 00:14:23 [INFO] train episode 3161: reward = -99.10, steps = 61 00:14:23 [INFO] train episode 3162: reward = -71.91, steps = 18 00:14:23 [INFO] train episode 3163: reward = -54.16, steps = 47 00:14:24 [INFO] train episode 3164: reward = -71.10, steps = 51 00:14:24 [INFO] train episode 3165: reward = -97.24, steps = 58 00:14:24 [INFO] train episode 3166: reward = -72.46, steps = 46 00:14:25 [INFO] train episode 3167: reward = -93.06, steps = 63 00:14:25 [INFO] train episode 3168: reward = -50.53, steps = 17 00:14:25 [INFO] train episode 3169: reward = -120.18, steps = 71 00:14:26 [INFO] train episode 3170: reward = -77.55, steps = 39 00:14:26 [INFO] train episode 3171: reward = -56.11, steps = 50 00:14:26 [INFO] train episode 3172: reward = -76.64, steps = 64 00:14:27 [INFO] train episode 3173: reward = -102.53, steps = 44 00:14:27 [INFO] train episode 3174: reward = -72.25, steps = 14 00:14:27 [INFO] train episode 3175: reward = -67.70, steps = 39 00:14:28 [INFO] train episode 3176: reward = -141.71, steps = 78 00:14:28 [INFO] train episode 3177: reward = -91.79, steps = 67 00:14:29 [INFO] train episode 3178: reward = -73.03, steps = 55 00:14:29 [INFO] train episode 3179: reward = -112.05, steps = 46 00:14:29 [INFO] train episode 3180: reward = -106.85, steps = 56 00:14:30 [INFO] train episode 3181: reward = -35.74, steps = 37 00:14:30 [INFO] train episode 3182: reward = -33.38, steps = 36 00:14:30 [INFO] train episode 3183: reward = -45.90, steps = 33 00:14:30 [INFO] train episode 3184: reward = -139.39, steps = 74 00:14:31 [INFO] train episode 3185: reward = -101.66, steps = 80 00:14:31 [INFO] train episode 3186: reward = -91.71, steps = 47 00:14:32 [INFO] train episode 3187: reward = -93.14, steps = 70 00:14:32 [INFO] train episode 3188: reward = -107.93, steps = 85 00:14:33 [INFO] train episode 3189: reward = -66.15, steps = 59 00:14:33 [INFO] train episode 3190: reward = -61.17, steps = 34 00:14:33 [INFO] train episode 3191: reward = -90.01, steps = 39 00:14:34 [INFO] train episode 3192: reward = -81.06, steps = 67 00:14:34 [INFO] train episode 3193: reward = -94.29, steps = 61 00:14:34 [INFO] train episode 3194: reward = -99.16, steps = 62 00:14:35 [INFO] train episode 3195: reward = -57.81, steps = 50 00:14:35 [INFO] train episode 3196: reward = -82.28, steps = 37 00:14:36 [INFO] train episode 3197: reward = -108.31, steps = 70 00:14:36 [INFO] train episode 3198: reward = -106.08, steps = 56 00:14:36 [INFO] train episode 3199: reward = -81.02, steps = 45 00:14:37 [INFO] train episode 3200: reward = -98.45, steps = 46 00:14:37 [INFO] train episode 3201: reward = -89.89, steps = 56 00:14:37 [INFO] train episode 3202: reward = -59.23, steps = 79 00:14:38 [INFO] train episode 3203: reward = -67.85, steps = 46 00:14:38 [INFO] train episode 3204: reward = -100.65, steps = 52 00:14:38 [INFO] train episode 3205: reward = -108.95, steps = 56 00:14:39 [INFO] train episode 3206: reward = -64.07, steps = 49 00:14:39 [INFO] train episode 3207: reward = -62.56, steps = 47 00:14:39 [INFO] train episode 3208: reward = -122.38, steps = 63 00:14:40 [INFO] train episode 3209: reward = -129.74, steps = 84 00:14:40 [INFO] train episode 3210: reward = -87.72, steps = 51 00:14:41 [INFO] train episode 3211: reward = -65.49, steps = 47 00:14:41 [INFO] train episode 3212: reward = -50.75, steps = 43 00:14:41 [INFO] train episode 3213: reward = -57.23, steps = 47 00:14:42 [INFO] train episode 3214: reward = -115.86, steps = 42 00:14:42 [INFO] train episode 3215: reward = -65.09, steps = 54 00:14:42 [INFO] train episode 3216: reward = -52.60, steps = 45 00:14:43 [INFO] train episode 3217: reward = -65.66, steps = 54 00:14:43 [INFO] train episode 3218: reward = -119.16, steps = 84 00:14:44 [INFO] train episode 3219: reward = -88.28, steps = 80 00:14:44 [INFO] train episode 3220: reward = -55.22, steps = 43 00:14:45 [INFO] train episode 3221: reward = -96.34, steps = 85 00:14:45 [INFO] train episode 3222: reward = -116.48, steps = 72 00:14:45 [INFO] train episode 3223: reward = -98.10, steps = 62 00:14:46 [INFO] train episode 3224: reward = -89.70, steps = 60 00:14:46 [INFO] train episode 3225: reward = -113.94, steps = 75 00:14:47 [INFO] train episode 3226: reward = -72.29, steps = 59 00:14:47 [INFO] train episode 3227: reward = -63.48, steps = 55 00:14:47 [INFO] train episode 3228: reward = -66.50, steps = 40 00:14:48 [INFO] train episode 3229: reward = -96.15, steps = 63 00:14:48 [INFO] train episode 3230: reward = -100.36, steps = 53 00:14:48 [INFO] train episode 3231: reward = -38.54, steps = 41 00:14:49 [INFO] train episode 3232: reward = -83.41, steps = 43 00:14:49 [INFO] train episode 3233: reward = -102.43, steps = 43 00:14:49 [INFO] train episode 3234: reward = -48.78, steps = 63 00:14:50 [INFO] train episode 3235: reward = -67.76, steps = 26 00:14:50 [INFO] train episode 3236: reward = -106.44, steps = 54 00:14:50 [INFO] train episode 3237: reward = -83.25, steps = 51 00:14:51 [INFO] train episode 3238: reward = -41.77, steps = 51 00:14:51 [INFO] train episode 3239: reward = -62.08, steps = 47 00:14:51 [INFO] train episode 3240: reward = -37.28, steps = 35 00:14:51 [INFO] train episode 3241: reward = -82.78, steps = 44 00:14:52 [INFO] train episode 3242: reward = -84.04, steps = 47 00:14:53 [INFO] train episode 3243: reward = -228.89, steps = 159 00:14:53 [INFO] train episode 3244: reward = -100.74, steps = 82 00:14:54 [INFO] train episode 3245: reward = -59.19, steps = 58 00:14:54 [INFO] train episode 3246: reward = -84.56, steps = 62 00:14:55 [INFO] train episode 3247: reward = -65.04, steps = 44 00:14:55 [INFO] train episode 3248: reward = -82.07, steps = 59 00:14:55 [INFO] train episode 3249: reward = -91.34, steps = 37 00:14:55 [INFO] train episode 3250: reward = -59.86, steps = 33 00:14:56 [INFO] train episode 3251: reward = -77.06, steps = 39 00:14:56 [INFO] train episode 3252: reward = -51.34, steps = 49 00:14:56 [INFO] train episode 3253: reward = -52.96, steps = 39 00:14:57 [INFO] train episode 3254: reward = -53.68, steps = 45 00:14:57 [INFO] train episode 3255: reward = -55.61, steps = 44 00:14:57 [INFO] train episode 3256: reward = -67.06, steps = 61 00:14:58 [INFO] train episode 3257: reward = -109.67, steps = 53 00:14:58 [INFO] train episode 3258: reward = -73.41, steps = 25 00:14:58 [INFO] train episode 3259: reward = -67.24, steps = 22 00:14:58 [INFO] train episode 3260: reward = -68.52, steps = 51 00:14:59 [INFO] train episode 3261: reward = -60.00, steps = 55 00:14:59 [INFO] train episode 3262: reward = -56.64, steps = 46 00:14:59 [INFO] train episode 3263: reward = -49.54, steps = 45 00:15:00 [INFO] train episode 3264: reward = -73.38, steps = 75 00:15:00 [INFO] train episode 3265: reward = -70.44, steps = 56 00:15:00 [INFO] train episode 3266: reward = -109.47, steps = 47 00:15:01 [INFO] train episode 3267: reward = -51.23, steps = 33 00:15:01 [INFO] train episode 3268: reward = -97.62, steps = 58 00:15:01 [INFO] train episode 3269: reward = -87.03, steps = 58 00:15:02 [INFO] train episode 3270: reward = -90.96, steps = 47 00:15:02 [INFO] train episode 3271: reward = -75.98, steps = 65 00:15:02 [INFO] train episode 3272: reward = -140.12, steps = 55 00:15:03 [INFO] train episode 3273: reward = -63.81, steps = 68 00:15:03 [INFO] train episode 3274: reward = -113.68, steps = 75 00:15:04 [INFO] train episode 3275: reward = -33.27, steps = 35 00:15:04 [INFO] train episode 3276: reward = -129.77, steps = 91 00:15:05 [INFO] train episode 3277: reward = -58.42, steps = 73 00:15:05 [INFO] train episode 3278: reward = -36.06, steps = 39 00:15:05 [INFO] train episode 3279: reward = -107.17, steps = 56 00:15:06 [INFO] train episode 3280: reward = -38.05, steps = 44 00:15:06 [INFO] train episode 3281: reward = -88.32, steps = 54 00:15:06 [INFO] train episode 3282: reward = -27.34, steps = 36 00:15:07 [INFO] train episode 3283: reward = -102.18, steps = 111 00:15:08 [INFO] train episode 3284: reward = -101.60, steps = 65 00:15:08 [INFO] train episode 3285: reward = -113.03, steps = 47 00:15:08 [INFO] train episode 3286: reward = -45.11, steps = 35 00:15:09 [INFO] train episode 3287: reward = -76.67, steps = 47 00:15:09 [INFO] train episode 3288: reward = -74.60, steps = 52 00:15:09 [INFO] train episode 3289: reward = -89.83, steps = 71 00:15:10 [INFO] train episode 3290: reward = -86.92, steps = 44 00:15:10 [INFO] train episode 3291: reward = -76.71, steps = 56 00:15:11 [INFO] train episode 3292: reward = -120.60, steps = 80 00:15:11 [INFO] train episode 3293: reward = -75.97, steps = 60 00:15:11 [INFO] train episode 3294: reward = -65.80, steps = 39 00:15:12 [INFO] train episode 3295: reward = -50.15, steps = 53 00:15:12 [INFO] train episode 3296: reward = -137.25, steps = 65 00:15:12 [INFO] train episode 3297: reward = -50.25, steps = 18 00:15:12 [INFO] train episode 3298: reward = -59.16, steps = 49 00:15:13 [INFO] train episode 3299: reward = -79.16, steps = 53 00:15:13 [INFO] train episode 3300: reward = -83.55, steps = 75 00:15:14 [INFO] train episode 3301: reward = -122.77, steps = 57 00:15:14 [INFO] train episode 3302: reward = -59.80, steps = 73 00:15:15 [INFO] train episode 3303: reward = -93.64, steps = 61 00:15:15 [INFO] train episode 3304: reward = -40.17, steps = 42 00:15:15 [INFO] train episode 3305: reward = -172.25, steps = 85 00:15:16 [INFO] train episode 3306: reward = -89.36, steps = 47 00:15:16 [INFO] train episode 3307: reward = -42.98, steps = 40 00:15:16 [INFO] train episode 3308: reward = -80.96, steps = 41 00:15:17 [INFO] train episode 3309: reward = -47.26, steps = 47 00:15:17 [INFO] train episode 3310: reward = -107.41, steps = 58 00:15:17 [INFO] train episode 3311: reward = -31.07, steps = 41 00:15:18 [INFO] train episode 3312: reward = -98.65, steps = 43 00:15:18 [INFO] train episode 3313: reward = -61.86, steps = 20 00:15:18 [INFO] train episode 3314: reward = -76.32, steps = 56 00:15:18 [INFO] train episode 3315: reward = -96.75, steps = 42 00:15:19 [INFO] train episode 3316: reward = -75.94, steps = 55 00:15:19 [INFO] train episode 3317: reward = -72.77, steps = 42 00:15:19 [INFO] train episode 3318: reward = -87.82, steps = 40 00:15:20 [INFO] train episode 3319: reward = -74.08, steps = 59 00:15:20 [INFO] train episode 3320: reward = -111.79, steps = 68 00:15:20 [INFO] train episode 3321: reward = -90.82, steps = 41 00:15:21 [INFO] train episode 3322: reward = -75.72, steps = 50 00:15:21 [INFO] train episode 3323: reward = -57.91, steps = 59 00:15:22 [INFO] train episode 3324: reward = -83.89, steps = 56 00:15:22 [INFO] train episode 3325: reward = -48.40, steps = 37 00:15:22 [INFO] train episode 3326: reward = -96.23, steps = 65 00:15:23 [INFO] train episode 3327: reward = -102.05, steps = 64 00:15:23 [INFO] train episode 3328: reward = -93.37, steps = 45 00:15:23 [INFO] train episode 3329: reward = -76.91, steps = 55 00:15:24 [INFO] train episode 3330: reward = -94.67, steps = 62 00:15:24 [INFO] train episode 3331: reward = -68.61, steps = 53 00:15:25 [INFO] train episode 3332: reward = -85.93, steps = 46 00:15:25 [INFO] train episode 3333: reward = -119.60, steps = 64 00:15:25 [INFO] train episode 3334: reward = -115.27, steps = 37 00:15:26 [INFO] train episode 3335: reward = -96.09, steps = 44 00:15:26 [INFO] train episode 3336: reward = -50.15, steps = 36 00:15:26 [INFO] train episode 3337: reward = -97.95, steps = 66 00:15:26 [INFO] train episode 3338: reward = -42.71, steps = 21 00:15:27 [INFO] train episode 3339: reward = -51.06, steps = 45 00:15:27 [INFO] train episode 3340: reward = -68.88, steps = 52 00:15:27 [INFO] train episode 3341: reward = -75.64, steps = 65 00:15:28 [INFO] train episode 3342: reward = -51.37, steps = 37 00:15:28 [INFO] train episode 3343: reward = -54.30, steps = 53 00:15:28 [INFO] train episode 3344: reward = -36.09, steps = 44 00:15:29 [INFO] train episode 3345: reward = -99.00, steps = 47 00:15:29 [INFO] train episode 3346: reward = -54.16, steps = 48 00:15:29 [INFO] train episode 3347: reward = -39.78, steps = 54 00:15:30 [INFO] train episode 3348: reward = -90.00, steps = 62 00:15:30 [INFO] train episode 3349: reward = -67.74, steps = 45 00:15:30 [INFO] train episode 3350: reward = -66.59, steps = 50 00:15:31 [INFO] train episode 3351: reward = -58.60, steps = 40 00:15:31 [INFO] train episode 3352: reward = -56.90, steps = 44 00:15:31 [INFO] train episode 3353: reward = -54.54, steps = 61 00:15:32 [INFO] train episode 3354: reward = -93.52, steps = 75 00:15:32 [INFO] train episode 3355: reward = -60.83, steps = 35 00:15:32 [INFO] train episode 3356: reward = -46.85, steps = 42 00:15:33 [INFO] train episode 3357: reward = -51.55, steps = 55 00:15:33 [INFO] train episode 3358: reward = -117.75, steps = 65 00:15:34 [INFO] train episode 3359: reward = -97.12, steps = 71 00:15:34 [INFO] train episode 3360: reward = -87.70, steps = 58 00:15:34 [INFO] train episode 3361: reward = -49.47, steps = 40 00:15:35 [INFO] train episode 3362: reward = -114.45, steps = 54 00:15:35 [INFO] train episode 3363: reward = -58.83, steps = 51 00:15:35 [INFO] train episode 3364: reward = -40.50, steps = 47 00:15:36 [INFO] train episode 3365: reward = -53.46, steps = 33 00:15:36 [INFO] train episode 3366: reward = -163.45, steps = 79 00:15:37 [INFO] train episode 3367: reward = -99.31, steps = 57 00:15:37 [INFO] train episode 3368: reward = -84.96, steps = 46 00:15:37 [INFO] train episode 3369: reward = -62.59, steps = 55 00:15:37 [INFO] train episode 3370: reward = -51.59, steps = 35 00:15:38 [INFO] train episode 3371: reward = -64.23, steps = 59 00:15:38 [INFO] train episode 3372: reward = -66.33, steps = 47 00:15:38 [INFO] train episode 3373: reward = -64.86, steps = 47 00:15:39 [INFO] train episode 3374: reward = -20.64, steps = 38 00:15:39 [INFO] train episode 3375: reward = -69.29, steps = 76 00:15:39 [INFO] train episode 3376: reward = -44.32, steps = 38 00:15:40 [INFO] train episode 3377: reward = -52.32, steps = 49 00:15:40 [INFO] train episode 3378: reward = -79.10, steps = 44 00:15:41 [INFO] train episode 3379: reward = -82.91, steps = 80 00:15:41 [INFO] train episode 3380: reward = -110.64, steps = 65 00:15:41 [INFO] train episode 3381: reward = -58.77, steps = 67 00:15:42 [INFO] train episode 3382: reward = -59.95, steps = 35 00:15:42 [INFO] train episode 3383: reward = -56.11, steps = 42 00:15:42 [INFO] train episode 3384: reward = -54.01, steps = 19 00:15:42 [INFO] train episode 3385: reward = -53.31, steps = 60 00:15:43 [INFO] train episode 3386: reward = -62.99, steps = 39 00:15:43 [INFO] train episode 3387: reward = -72.27, steps = 41 00:15:44 [INFO] train episode 3388: reward = -113.49, steps = 91 00:15:44 [INFO] train episode 3389: reward = -119.71, steps = 64 00:15:44 [INFO] train episode 3390: reward = -62.81, steps = 45 00:15:45 [INFO] train episode 3391: reward = -38.53, steps = 41 00:15:45 [INFO] train episode 3392: reward = -53.80, steps = 41 00:15:45 [INFO] train episode 3393: reward = -112.11, steps = 61 00:15:46 [INFO] train episode 3394: reward = -50.15, steps = 53 00:15:46 [INFO] train episode 3395: reward = -119.02, steps = 60 00:15:46 [INFO] train episode 3396: reward = -45.73, steps = 36 00:15:47 [INFO] train episode 3397: reward = -101.34, steps = 54 00:15:47 [INFO] train episode 3398: reward = -26.10, steps = 33 00:15:47 [INFO] train episode 3399: reward = -54.24, steps = 55 00:15:48 [INFO] train episode 3400: reward = -67.20, steps = 55 00:15:48 [INFO] train episode 3401: reward = -53.91, steps = 48 00:15:48 [INFO] train episode 3402: reward = -55.46, steps = 39 00:15:49 [INFO] train episode 3403: reward = -41.21, steps = 46 00:15:49 [INFO] train episode 3404: reward = -51.63, steps = 43 00:15:49 [INFO] train episode 3405: reward = -57.27, steps = 62 00:15:50 [INFO] train episode 3406: reward = -46.16, steps = 53 00:15:50 [INFO] train episode 3407: reward = -72.70, steps = 68 00:15:51 [INFO] train episode 3408: reward = -123.69, steps = 56 00:15:51 [INFO] train episode 3409: reward = -118.56, steps = 65 00:15:51 [INFO] train episode 3410: reward = -70.98, steps = 40 00:15:52 [INFO] train episode 3411: reward = -60.98, steps = 52 00:15:52 [INFO] train episode 3412: reward = -82.47, steps = 55 00:15:52 [INFO] train episode 3413: reward = -77.56, steps = 40 00:15:52 [INFO] train episode 3414: reward = -57.28, steps = 40 00:15:53 [INFO] train episode 3415: reward = -49.01, steps = 29 00:15:53 [INFO] train episode 3416: reward = -83.59, steps = 51 00:15:53 [INFO] train episode 3417: reward = -41.95, steps = 37 00:15:54 [INFO] train episode 3418: reward = -79.66, steps = 71 00:15:54 [INFO] train episode 3419: reward = -69.34, steps = 49 00:15:54 [INFO] train episode 3420: reward = -57.09, steps = 24 00:15:54 [INFO] train episode 3421: reward = -50.04, steps = 44 00:15:55 [INFO] train episode 3422: reward = -94.92, steps = 53 00:15:55 [INFO] train episode 3423: reward = -27.34, steps = 46 00:15:56 [INFO] train episode 3424: reward = -67.79, steps = 58 00:15:56 [INFO] train episode 3425: reward = -98.70, steps = 67 00:15:56 [INFO] train episode 3426: reward = -70.64, steps = 64 00:15:57 [INFO] train episode 3427: reward = -54.83, steps = 46 00:15:57 [INFO] train episode 3428: reward = -49.94, steps = 42 00:15:57 [INFO] train episode 3429: reward = -74.98, steps = 54 00:15:58 [INFO] train episode 3430: reward = -44.19, steps = 43 00:15:58 [INFO] train episode 3431: reward = -109.55, steps = 54 00:15:58 [INFO] train episode 3432: reward = -62.01, steps = 47 00:15:59 [INFO] train episode 3433: reward = -60.32, steps = 65 00:15:59 [INFO] train episode 3434: reward = -64.36, steps = 63 00:15:59 [INFO] train episode 3435: reward = -70.26, steps = 43 00:16:00 [INFO] train episode 3436: reward = -35.12, steps = 53 00:16:00 [INFO] train episode 3437: reward = -122.98, steps = 55 00:16:00 [INFO] train episode 3438: reward = -29.81, steps = 41 00:16:01 [INFO] train episode 3439: reward = -55.70, steps = 40 00:16:01 [INFO] train episode 3440: reward = -64.83, steps = 45 00:16:02 [INFO] train episode 3441: reward = -58.55, steps = 48 00:16:02 [INFO] train episode 3442: reward = -64.52, steps = 47 00:16:02 [INFO] train episode 3443: reward = -117.28, steps = 66 00:16:03 [INFO] train episode 3444: reward = -60.89, steps = 58 00:16:03 [INFO] train episode 3445: reward = -53.31, steps = 52 00:16:03 [INFO] train episode 3446: reward = -54.92, steps = 43 00:16:04 [INFO] train episode 3447: reward = -28.25, steps = 34 00:16:04 [INFO] train episode 3448: reward = -62.67, steps = 56 00:16:04 [INFO] train episode 3449: reward = -88.76, steps = 61 00:16:05 [INFO] train episode 3450: reward = -85.29, steps = 60 00:16:05 [INFO] train episode 3451: reward = -46.15, steps = 49 00:16:05 [INFO] train episode 3452: reward = -91.26, steps = 63 00:16:06 [INFO] train episode 3453: reward = -60.08, steps = 39 00:16:06 [INFO] train episode 3454: reward = -94.20, steps = 59 00:16:06 [INFO] train episode 3455: reward = -73.79, steps = 30 00:16:07 [INFO] train episode 3456: reward = -94.26, steps = 63 00:16:07 [INFO] train episode 3457: reward = -66.23, steps = 60 00:16:07 [INFO] train episode 3458: reward = -62.47, steps = 49 00:16:08 [INFO] train episode 3459: reward = -66.49, steps = 50 00:16:08 [INFO] train episode 3460: reward = -28.43, steps = 33 00:16:08 [INFO] train episode 3461: reward = -120.02, steps = 73 00:16:09 [INFO] train episode 3462: reward = -57.31, steps = 44 00:16:09 [INFO] train episode 3463: reward = -77.27, steps = 63 00:16:10 [INFO] train episode 3464: reward = -50.19, steps = 51 00:16:10 [INFO] train episode 3465: reward = -101.42, steps = 68 00:16:10 [INFO] train episode 3466: reward = -85.48, steps = 46 00:16:11 [INFO] train episode 3467: reward = -110.74, steps = 48 00:16:11 [INFO] train episode 3468: reward = -28.86, steps = 47 00:16:11 [INFO] train episode 3469: reward = -87.65, steps = 53 00:16:12 [INFO] train episode 3470: reward = -53.72, steps = 36 00:16:12 [INFO] train episode 3471: reward = -54.79, steps = 53 00:16:12 [INFO] train episode 3472: reward = -38.76, steps = 38 00:16:12 [INFO] train episode 3473: reward = -42.54, steps = 45 00:16:13 [INFO] train episode 3474: reward = -57.28, steps = 89 00:16:13 [INFO] train episode 3475: reward = -23.47, steps = 44 00:16:14 [INFO] train episode 3476: reward = -47.36, steps = 51 00:16:14 [INFO] train episode 3477: reward = -46.77, steps = 34 00:16:14 [INFO] train episode 3478: reward = -85.99, steps = 35 00:16:14 [INFO] train episode 3479: reward = -24.68, steps = 38 00:16:15 [INFO] train episode 3480: reward = -59.78, steps = 32 00:16:15 [INFO] train episode 3481: reward = -85.24, steps = 68 00:16:15 [INFO] train episode 3482: reward = -54.60, steps = 24 00:16:16 [INFO] train episode 3483: reward = -79.38, steps = 46 00:16:16 [INFO] train episode 3484: reward = -88.63, steps = 55 00:16:16 [INFO] train episode 3485: reward = -103.84, steps = 68 00:16:17 [INFO] train episode 3486: reward = -88.57, steps = 54 00:16:17 [INFO] train episode 3487: reward = -47.13, steps = 59 00:16:18 [INFO] train episode 3488: reward = -57.59, steps = 48 00:16:18 [INFO] train episode 3489: reward = -56.21, steps = 35 00:16:18 [INFO] train episode 3490: reward = -88.74, steps = 42 00:16:18 [INFO] train episode 3491: reward = -58.25, steps = 37 00:16:19 [INFO] train episode 3492: reward = -52.74, steps = 35 00:16:19 [INFO] train episode 3493: reward = -41.32, steps = 42 00:16:19 [INFO] train episode 3494: reward = -137.00, steps = 91 00:16:20 [INFO] train episode 3495: reward = -82.66, steps = 58 00:16:20 [INFO] train episode 3496: reward = -81.74, steps = 62 00:16:21 [INFO] train episode 3497: reward = -103.10, steps = 69 00:16:21 [INFO] train episode 3498: reward = -67.45, steps = 43 00:16:21 [INFO] train episode 3499: reward = -66.38, steps = 18 00:16:21 [INFO] train episode 3500: reward = -45.17, steps = 21 00:16:22 [INFO] train episode 3501: reward = -58.24, steps = 44 00:16:22 [INFO] train episode 3502: reward = -42.83, steps = 42 00:16:22 [INFO] train episode 3503: reward = -97.91, steps = 50 00:16:22 [INFO] train episode 3504: reward = -43.34, steps = 20 00:16:23 [INFO] train episode 3505: reward = -56.73, steps = 54 00:16:23 [INFO] train episode 3506: reward = -64.14, steps = 47 00:16:23 [INFO] train episode 3507: reward = -28.16, steps = 40 00:16:24 [INFO] train episode 3508: reward = -110.48, steps = 73 00:16:24 [INFO] train episode 3509: reward = -77.52, steps = 77 00:16:25 [INFO] train episode 3510: reward = -63.82, steps = 63 00:16:25 [INFO] train episode 3511: reward = -61.21, steps = 55 00:16:25 [INFO] train episode 3512: reward = -61.40, steps = 39 00:16:26 [INFO] train episode 3513: reward = -36.51, steps = 50 00:16:26 [INFO] train episode 3514: reward = -45.54, steps = 41 00:16:26 [INFO] train episode 3515: reward = -49.29, steps = 61 00:16:26 [INFO] train episode 3516: reward = -33.31, steps = 27 00:16:27 [INFO] train episode 3517: reward = -32.18, steps = 43 00:16:27 [INFO] train episode 3518: reward = -116.37, steps = 67 00:16:27 [INFO] train episode 3519: reward = -22.19, steps = 33 00:16:28 [INFO] train episode 3520: reward = -98.77, steps = 59 00:16:28 [INFO] train episode 3521: reward = -97.77, steps = 47 00:16:29 [INFO] train episode 3522: reward = -110.94, steps = 68 00:16:29 [INFO] train episode 3523: reward = -47.92, steps = 36 00:16:29 [INFO] train episode 3524: reward = -50.52, steps = 38 00:16:30 [INFO] train episode 3525: reward = -74.47, steps = 47 00:16:30 [INFO] train episode 3526: reward = -78.47, steps = 47 00:16:30 [INFO] train episode 3527: reward = -25.50, steps = 44 00:16:30 [INFO] train episode 3528: reward = -67.83, steps = 50 00:16:31 [INFO] train episode 3529: reward = -69.46, steps = 57 00:16:31 [INFO] train episode 3530: reward = -34.56, steps = 46 00:16:31 [INFO] train episode 3531: reward = -58.42, steps = 56 00:16:32 [INFO] train episode 3532: reward = -52.07, steps = 40 00:16:32 [INFO] train episode 3533: reward = -40.02, steps = 40 00:16:32 [INFO] train episode 3534: reward = -50.61, steps = 49 00:16:33 [INFO] train episode 3535: reward = -64.78, steps = 35 00:16:33 [INFO] train episode 3536: reward = -24.76, steps = 41 00:16:33 [INFO] train episode 3537: reward = -58.40, steps = 63 00:16:33 [INFO] train episode 3538: reward = -57.58, steps = 37 00:16:34 [INFO] train episode 3539: reward = -41.42, steps = 45 00:16:34 [INFO] train episode 3540: reward = -51.04, steps = 43 00:16:34 [INFO] train episode 3541: reward = -60.82, steps = 49 00:16:35 [INFO] train episode 3542: reward = -31.97, steps = 32 00:16:35 [INFO] train episode 3543: reward = -62.41, steps = 61 00:16:35 [INFO] train episode 3544: reward = -68.38, steps = 43 00:16:36 [INFO] train episode 3545: reward = -51.82, steps = 44 00:16:36 [INFO] train episode 3546: reward = -65.59, steps = 66 00:16:36 [INFO] train episode 3547: reward = -39.21, steps = 45 00:16:37 [INFO] train episode 3548: reward = -57.77, steps = 43 00:16:37 [INFO] train episode 3549: reward = -27.61, steps = 21 00:16:37 [INFO] train episode 3550: reward = -26.25, steps = 30 00:16:37 [INFO] train episode 3551: reward = -45.03, steps = 51 00:16:38 [INFO] train episode 3552: reward = -48.08, steps = 44 00:16:38 [INFO] train episode 3553: reward = -37.99, steps = 37 00:16:38 [INFO] train episode 3554: reward = -52.82, steps = 44 00:16:38 [INFO] train episode 3555: reward = -39.95, steps = 28 00:16:39 [INFO] train episode 3556: reward = -46.70, steps = 28 00:16:39 [INFO] train episode 3557: reward = -81.15, steps = 60 00:16:39 [INFO] train episode 3558: reward = -38.59, steps = 28 00:16:39 [INFO] train episode 3559: reward = -52.62, steps = 31 00:16:40 [INFO] train episode 3560: reward = -78.02, steps = 58 00:16:40 [INFO] train episode 3561: reward = -46.12, steps = 56 00:16:41 [INFO] train episode 3562: reward = -64.41, steps = 58 00:16:41 [INFO] train episode 3563: reward = -39.18, steps = 45 00:16:41 [INFO] train episode 3564: reward = -29.50, steps = 36 00:16:41 [INFO] train episode 3565: reward = -40.08, steps = 25 00:16:41 [INFO] train episode 3566: reward = -41.37, steps = 31 00:16:42 [INFO] train episode 3567: reward = -42.04, steps = 43 00:16:42 [INFO] train episode 3568: reward = -34.03, steps = 33 00:16:42 [INFO] train episode 3569: reward = -44.17, steps = 31 00:16:43 [INFO] train episode 3570: reward = -40.20, steps = 27 00:16:43 [INFO] train episode 3571: reward = -48.18, steps = 44 00:16:43 [INFO] train episode 3572: reward = -64.09, steps = 39 00:16:44 [INFO] train episode 3573: reward = -56.28, steps = 57 00:16:44 [INFO] train episode 3574: reward = -42.01, steps = 39 00:16:44 [INFO] train episode 3575: reward = -29.98, steps = 61 00:16:44 [INFO] train episode 3576: reward = -38.21, steps = 19 00:16:45 [INFO] train episode 3577: reward = -56.14, steps = 83 00:16:45 [INFO] train episode 3578: reward = -59.16, steps = 37 00:16:45 [INFO] train episode 3579: reward = -37.35, steps = 36 00:16:46 [INFO] train episode 3580: reward = -70.17, steps = 69 00:16:46 [INFO] train episode 3581: reward = -40.07, steps = 44 00:16:46 [INFO] train episode 3582: reward = -43.45, steps = 30 00:16:47 [INFO] train episode 3583: reward = -33.32, steps = 38 00:16:47 [INFO] train episode 3584: reward = -46.44, steps = 48 00:16:47 [INFO] train episode 3585: reward = -51.06, steps = 24 00:16:47 [INFO] train episode 3586: reward = -41.61, steps = 30 00:16:48 [INFO] train episode 3587: reward = -49.84, steps = 42 00:16:48 [INFO] train episode 3588: reward = -27.76, steps = 46 00:16:48 [INFO] train episode 3589: reward = -58.43, steps = 34 00:16:48 [INFO] train episode 3590: reward = -39.81, steps = 46 00:16:49 [INFO] train episode 3591: reward = -57.44, steps = 26 00:16:49 [INFO] train episode 3592: reward = -28.58, steps = 48 00:16:49 [INFO] train episode 3593: reward = -70.75, steps = 40 00:16:49 [INFO] train episode 3594: reward = -51.51, steps = 46 00:16:50 [INFO] train episode 3595: reward = -42.35, steps = 35 00:16:50 [INFO] train episode 3596: reward = -46.92, steps = 38 00:16:50 [INFO] train episode 3597: reward = -31.60, steps = 39 00:16:50 [INFO] train episode 3598: reward = -52.27, steps = 35 00:16:51 [INFO] train episode 3599: reward = -69.92, steps = 49 00:16:51 [INFO] train episode 3600: reward = -43.42, steps = 40 00:16:51 [INFO] train episode 3601: reward = -61.54, steps = 38 00:16:52 [INFO] train episode 3602: reward = -67.25, steps = 52 00:16:52 [INFO] train episode 3603: reward = -35.99, steps = 35 00:16:52 [INFO] train episode 3604: reward = -38.13, steps = 38 00:16:52 [INFO] train episode 3605: reward = -90.08, steps = 54 00:16:53 [INFO] train episode 3606: reward = -73.82, steps = 56 00:16:53 [INFO] train episode 3607: reward = -41.64, steps = 32 00:16:53 [INFO] train episode 3608: reward = -40.70, steps = 33 00:16:54 [INFO] train episode 3609: reward = -24.77, steps = 44 00:16:54 [INFO] train episode 3610: reward = -26.81, steps = 43 00:16:54 [INFO] train episode 3611: reward = -70.60, steps = 59 00:16:54 [INFO] train episode 3612: reward = -59.23, steps = 45 00:16:55 [INFO] train episode 3613: reward = -40.19, steps = 29 00:16:55 [INFO] train episode 3614: reward = -31.08, steps = 39 00:16:55 [INFO] train episode 3615: reward = -68.05, steps = 48 00:16:56 [INFO] train episode 3616: reward = -45.12, steps = 37 00:16:56 [INFO] train episode 3617: reward = -60.51, steps = 55 00:16:56 [INFO] train episode 3618: reward = -64.70, steps = 31 00:16:56 [INFO] train episode 3619: reward = -50.36, steps = 23 00:16:57 [INFO] train episode 3620: reward = -65.30, steps = 47 00:16:57 [INFO] train episode 3621: reward = -47.87, steps = 24 00:16:57 [INFO] train episode 3622: reward = -46.15, steps = 35 00:16:57 [INFO] train episode 3623: reward = -39.97, steps = 25 00:16:57 [INFO] train episode 3624: reward = -54.77, steps = 23 00:16:58 [INFO] train episode 3625: reward = -59.90, steps = 42 00:16:58 [INFO] train episode 3626: reward = -33.97, steps = 32 00:16:58 [INFO] train episode 3627: reward = -61.31, steps = 38 00:16:58 [INFO] train episode 3628: reward = -46.28, steps = 36 00:16:59 [INFO] train episode 3629: reward = -83.44, steps = 52 00:16:59 [INFO] train episode 3630: reward = -42.74, steps = 41 00:16:59 [INFO] train episode 3631: reward = -32.91, steps = 39 00:17:00 [INFO] train episode 3632: reward = -42.93, steps = 30 00:17:00 [INFO] train episode 3633: reward = -95.44, steps = 58 00:17:00 [INFO] train episode 3634: reward = -42.12, steps = 50 00:17:00 [INFO] train episode 3635: reward = -35.68, steps = 34 00:17:01 [INFO] train episode 3636: reward = -38.59, steps = 37 00:17:01 [INFO] train episode 3637: reward = -65.91, steps = 39 00:17:01 [INFO] train episode 3638: reward = -82.29, steps = 40 00:17:02 [INFO] train episode 3639: reward = -38.54, steps = 36 00:17:02 [INFO] train episode 3640: reward = -41.67, steps = 43 00:17:02 [INFO] train episode 3641: reward = -43.68, steps = 40 00:17:02 [INFO] train episode 3642: reward = -45.20, steps = 28 00:17:03 [INFO] train episode 3643: reward = -69.18, steps = 55 00:17:03 [INFO] train episode 3644: reward = -38.72, steps = 45 00:17:03 [INFO] train episode 3645: reward = -44.42, steps = 27 00:17:04 [INFO] train episode 3646: reward = -52.76, steps = 45 00:17:04 [INFO] train episode 3647: reward = -49.82, steps = 66 00:17:05 [INFO] train episode 3648: reward = -60.85, steps = 78 00:17:05 [INFO] train episode 3649: reward = -59.92, steps = 40 00:17:05 [INFO] train episode 3650: reward = -70.08, steps = 46 00:17:05 [INFO] train episode 3651: reward = -42.88, steps = 34 00:17:06 [INFO] train episode 3652: reward = -35.21, steps = 40 00:17:06 [INFO] train episode 3653: reward = -50.41, steps = 46 00:17:06 [INFO] train episode 3654: reward = -30.57, steps = 38 00:17:07 [INFO] train episode 3655: reward = -50.92, steps = 52 00:17:07 [INFO] train episode 3656: reward = -39.45, steps = 32 00:17:07 [INFO] train episode 3657: reward = -47.13, steps = 26 00:17:07 [INFO] train episode 3658: reward = -67.35, steps = 47 00:17:08 [INFO] train episode 3659: reward = -35.44, steps = 48 00:17:08 [INFO] train episode 3660: reward = -153.62, steps = 131 00:17:09 [INFO] train episode 3661: reward = -61.44, steps = 44 00:17:09 [INFO] train episode 3662: reward = -60.68, steps = 46 00:17:09 [INFO] train episode 3663: reward = -56.39, steps = 21 00:17:09 [INFO] train episode 3664: reward = -63.03, steps = 36 00:17:10 [INFO] train episode 3665: reward = -56.65, steps = 54 00:17:10 [INFO] train episode 3666: reward = -30.14, steps = 33 00:17:10 [INFO] train episode 3667: reward = -38.98, steps = 44 00:17:11 [INFO] train episode 3668: reward = -37.08, steps = 31 00:17:11 [INFO] train episode 3669: reward = -28.77, steps = 36 00:17:11 [INFO] train episode 3670: reward = -41.46, steps = 36 00:17:11 [INFO] train episode 3671: reward = -76.31, steps = 47 00:17:12 [INFO] train episode 3672: reward = -34.58, steps = 35 00:17:12 [INFO] train episode 3673: reward = -16.92, steps = 45 00:17:12 [INFO] train episode 3674: reward = -55.30, steps = 48 00:17:13 [INFO] train episode 3675: reward = -82.64, steps = 72 00:17:13 [INFO] train episode 3676: reward = -39.93, steps = 34 00:17:13 [INFO] train episode 3677: reward = -36.93, steps = 36 00:17:13 [INFO] train episode 3678: reward = -62.71, steps = 58 00:17:14 [INFO] train episode 3679: reward = -53.16, steps = 38 00:17:14 [INFO] train episode 3680: reward = -60.87, steps = 36 00:17:14 [INFO] train episode 3681: reward = -44.91, steps = 49 00:17:15 [INFO] train episode 3682: reward = -86.48, steps = 37 00:17:15 [INFO] train episode 3683: reward = -45.56, steps = 45 00:17:15 [INFO] train episode 3684: reward = -49.85, steps = 43 00:17:15 [INFO] train episode 3685: reward = -66.65, steps = 44 00:17:16 [INFO] train episode 3686: reward = -39.73, steps = 27 00:17:16 [INFO] train episode 3687: reward = -80.62, steps = 43 00:17:16 [INFO] train episode 3688: reward = -57.75, steps = 44 00:17:16 [INFO] train episode 3689: reward = -42.49, steps = 35 00:17:17 [INFO] train episode 3690: reward = -45.06, steps = 43 00:17:17 [INFO] train episode 3691: reward = -47.26, steps = 45 00:17:17 [INFO] train episode 3692: reward = -59.74, steps = 50 00:17:18 [INFO] train episode 3693: reward = -68.10, steps = 35 00:17:18 [INFO] train episode 3694: reward = -64.86, steps = 46 00:17:18 [INFO] train episode 3695: reward = -55.51, steps = 36 00:17:18 [INFO] train episode 3696: reward = -45.23, steps = 50 00:17:19 [INFO] train episode 3697: reward = -51.25, steps = 39 00:17:19 [INFO] train episode 3698: reward = -14.01, steps = 47 00:17:19 [INFO] train episode 3699: reward = -48.21, steps = 28 00:17:20 [INFO] train episode 3700: reward = -52.51, steps = 56 00:17:20 [INFO] train episode 3701: reward = -37.64, steps = 34 00:17:20 [INFO] train episode 3702: reward = -47.50, steps = 37 00:17:20 [INFO] train episode 3703: reward = -59.04, steps = 46 00:17:21 [INFO] train episode 3704: reward = -55.42, steps = 35 00:17:21 [INFO] train episode 3705: reward = -76.40, steps = 49 00:17:21 [INFO] train episode 3706: reward = -52.47, steps = 47 00:17:22 [INFO] train episode 3707: reward = -51.26, steps = 55 00:17:22 [INFO] train episode 3708: reward = -54.64, steps = 58 00:17:22 [INFO] train episode 3709: reward = -44.73, steps = 22 00:17:23 [INFO] train episode 3710: reward = -47.35, steps = 44 00:17:23 [INFO] train episode 3711: reward = -55.96, steps = 52 00:17:23 [INFO] train episode 3712: reward = -60.76, steps = 44 00:17:24 [INFO] train episode 3713: reward = -49.32, steps = 39 00:17:24 [INFO] train episode 3714: reward = -41.08, steps = 45 00:17:24 [INFO] train episode 3715: reward = -59.87, steps = 41 00:17:24 [INFO] train episode 3716: reward = -42.74, steps = 19 00:17:25 [INFO] train episode 3717: reward = -60.96, steps = 53 00:17:25 [INFO] train episode 3718: reward = -38.26, steps = 34 00:17:25 [INFO] train episode 3719: reward = -47.86, steps = 40 00:17:25 [INFO] train episode 3720: reward = -47.48, steps = 36 00:17:26 [INFO] train episode 3721: reward = -27.15, steps = 40 00:17:26 [INFO] train episode 3722: reward = -37.21, steps = 30 00:17:26 [INFO] train episode 3723: reward = -31.49, steps = 24 00:17:26 [INFO] train episode 3724: reward = -35.43, steps = 38 00:17:26 [INFO] train episode 3725: reward = -42.57, steps = 26 00:17:27 [INFO] train episode 3726: reward = -41.28, steps = 36 00:17:27 [INFO] train episode 3727: reward = -41.87, steps = 37 00:17:27 [INFO] train episode 3728: reward = -40.38, steps = 22 00:17:27 [INFO] train episode 3729: reward = -42.76, steps = 21 00:17:28 [INFO] train episode 3730: reward = -36.86, steps = 44 00:17:28 [INFO] train episode 3731: reward = -28.67, steps = 40 00:17:28 [INFO] train episode 3732: reward = -46.40, steps = 38 00:17:28 [INFO] train episode 3733: reward = -40.96, steps = 34 00:17:29 [INFO] train episode 3734: reward = -38.26, steps = 37 00:17:29 [INFO] train episode 3735: reward = -41.05, steps = 41 00:17:29 [INFO] train episode 3736: reward = -67.35, steps = 38 00:17:29 [INFO] train episode 3737: reward = -54.53, steps = 25 00:17:30 [INFO] train episode 3738: reward = -45.87, steps = 25 00:17:30 [INFO] train episode 3739: reward = -46.91, steps = 34 00:17:30 [INFO] train episode 3740: reward = -36.54, steps = 34 00:17:30 [INFO] train episode 3741: reward = -28.75, steps = 29 00:17:30 [INFO] train episode 3742: reward = -46.31, steps = 31 00:17:31 [INFO] train episode 3743: reward = -52.98, steps = 35 00:17:31 [INFO] train episode 3744: reward = -57.01, steps = 38 00:17:31 [INFO] train episode 3745: reward = -53.94, steps = 28 00:17:31 [INFO] train episode 3746: reward = -46.18, steps = 22 00:17:32 [INFO] train episode 3747: reward = -27.00, steps = 34 00:17:32 [INFO] train episode 3748: reward = -41.42, steps = 39 00:17:32 [INFO] train episode 3749: reward = -67.41, steps = 19 00:17:32 [INFO] train episode 3750: reward = -64.61, steps = 50 00:17:33 [INFO] train episode 3751: reward = -48.36, steps = 51 00:17:33 [INFO] train episode 3752: reward = -38.17, steps = 38 00:17:33 [INFO] train episode 3753: reward = -56.99, steps = 20 00:17:33 [INFO] train episode 3754: reward = -34.60, steps = 35 00:17:33 [INFO] train episode 3755: reward = -46.89, steps = 38 00:17:34 [INFO] train episode 3756: reward = -47.80, steps = 39 00:17:34 [INFO] train episode 3757: reward = -44.18, steps = 41 00:17:34 [INFO] train episode 3758: reward = -39.91, steps = 35 00:17:34 [INFO] train episode 3759: reward = -46.77, steps = 34 00:17:35 [INFO] train episode 3760: reward = -38.44, steps = 29 00:17:35 [INFO] train episode 3761: reward = -36.93, steps = 26 00:17:35 [INFO] train episode 3762: reward = -39.68, steps = 38 00:17:35 [INFO] train episode 3763: reward = -43.04, steps = 21 00:17:35 [INFO] train episode 3764: reward = -63.46, steps = 24 00:17:36 [INFO] train episode 3765: reward = -70.92, steps = 27 00:17:36 [INFO] train episode 3766: reward = -24.58, steps = 48 00:17:36 [INFO] train episode 3767: reward = -45.26, steps = 26 00:17:37 [INFO] train episode 3768: reward = -34.29, steps = 39 00:17:37 [INFO] train episode 3769: reward = -43.09, steps = 32 00:17:37 [INFO] train episode 3770: reward = -35.98, steps = 48 00:17:37 [INFO] train episode 3771: reward = -59.00, steps = 29 00:17:38 [INFO] train episode 3772: reward = -53.47, steps = 41 00:17:38 [INFO] train episode 3773: reward = -23.59, steps = 34 00:17:38 [INFO] train episode 3774: reward = -35.96, steps = 34 00:17:38 [INFO] train episode 3775: reward = -35.39, steps = 33 00:17:38 [INFO] train episode 3776: reward = -34.77, steps = 35 00:17:39 [INFO] train episode 3777: reward = -37.12, steps = 41 00:17:39 [INFO] train episode 3778: reward = -115.01, steps = 68 00:17:39 [INFO] train episode 3779: reward = -34.15, steps = 31 00:17:40 [INFO] train episode 3780: reward = -42.53, steps = 36 00:17:40 [INFO] train episode 3781: reward = -42.98, steps = 20 00:17:40 [INFO] train episode 3782: reward = -38.57, steps = 43 00:17:40 [INFO] train episode 3783: reward = -44.29, steps = 40 00:17:41 [INFO] train episode 3784: reward = -56.40, steps = 18 00:17:41 [INFO] train episode 3785: reward = -47.59, steps = 24 00:17:41 [INFO] train episode 3786: reward = -31.84, steps = 31 00:17:41 [INFO] train episode 3787: reward = -40.04, steps = 29 00:17:41 [INFO] train episode 3788: reward = -47.86, steps = 55 00:17:42 [INFO] train episode 3789: reward = -43.84, steps = 33 00:17:42 [INFO] train episode 3790: reward = -40.80, steps = 36 00:17:42 [INFO] train episode 3791: reward = -43.81, steps = 44 00:17:42 [INFO] train episode 3792: reward = -58.29, steps = 36 00:17:43 [INFO] train episode 3793: reward = -28.06, steps = 33 00:17:43 [INFO] train episode 3794: reward = -46.34, steps = 35 00:17:43 [INFO] train episode 3795: reward = -38.61, steps = 36 00:17:44 [INFO] train episode 3796: reward = -33.59, steps = 47 00:17:44 [INFO] train episode 3797: reward = -41.01, steps = 31 00:17:44 [INFO] train episode 3798: reward = -28.66, steps = 23 00:17:44 [INFO] train episode 3799: reward = -34.54, steps = 52 00:17:45 [INFO] train episode 3800: reward = -62.05, steps = 50 00:17:45 [INFO] train episode 3801: reward = -52.68, steps = 29 00:17:45 [INFO] train episode 3802: reward = -65.96, steps = 55 00:17:46 [INFO] train episode 3803: reward = -72.41, steps = 67 00:17:46 [INFO] train episode 3804: reward = -46.63, steps = 51 00:17:46 [INFO] train episode 3805: reward = -31.82, steps = 27 00:17:46 [INFO] train episode 3806: reward = -38.91, steps = 36 00:17:47 [INFO] train episode 3807: reward = -56.68, steps = 29 00:17:47 [INFO] train episode 3808: reward = -21.94, steps = 29 00:17:47 [INFO] train episode 3809: reward = -43.79, steps = 23 00:17:47 [INFO] train episode 3810: reward = -34.53, steps = 21 00:17:47 [INFO] train episode 3811: reward = -70.83, steps = 32 00:17:48 [INFO] train episode 3812: reward = -38.70, steps = 34 00:17:48 [INFO] train episode 3813: reward = -22.43, steps = 24 00:17:48 [INFO] train episode 3814: reward = -77.30, steps = 69 00:17:48 [INFO] train episode 3815: reward = -32.26, steps = 29 00:17:49 [INFO] train episode 3816: reward = -40.00, steps = 35 00:17:49 [INFO] train episode 3817: reward = -47.78, steps = 44 00:17:49 [INFO] train episode 3818: reward = -27.47, steps = 30 00:17:50 [INFO] train episode 3819: reward = -40.62, steps = 43 00:17:50 [INFO] train episode 3820: reward = -55.18, steps = 50 00:17:50 [INFO] train episode 3821: reward = -36.14, steps = 38 00:17:50 [INFO] train episode 3822: reward = -48.26, steps = 20 00:17:51 [INFO] train episode 3823: reward = -61.01, steps = 29 00:17:51 [INFO] train episode 3824: reward = -44.84, steps = 38 00:17:51 [INFO] train episode 3825: reward = -42.82, steps = 25 00:17:51 [INFO] train episode 3826: reward = -38.01, steps = 28 00:17:51 [INFO] train episode 3827: reward = -37.58, steps = 31 00:17:52 [INFO] train episode 3828: reward = -44.51, steps = 23 00:17:52 [INFO] train episode 3829: reward = -68.79, steps = 49 00:17:52 [INFO] train episode 3830: reward = -35.36, steps = 30 00:17:52 [INFO] train episode 3831: reward = -61.85, steps = 54 00:17:53 [INFO] train episode 3832: reward = -21.36, steps = 42 00:17:53 [INFO] train episode 3833: reward = -43.31, steps = 31 00:17:53 [INFO] train episode 3834: reward = -68.04, steps = 54 00:17:54 [INFO] train episode 3835: reward = -42.65, steps = 41 00:17:54 [INFO] train episode 3836: reward = -46.24, steps = 37 00:17:54 [INFO] train episode 3837: reward = -48.46, steps = 45 00:17:54 [INFO] train episode 3838: reward = -39.46, steps = 20 00:17:54 [INFO] train episode 3839: reward = -57.29, steps = 28 00:17:55 [INFO] train episode 3840: reward = -40.40, steps = 29 00:17:55 [INFO] train episode 3841: reward = -52.18, steps = 37 00:17:55 [INFO] train episode 3842: reward = -35.74, steps = 24 00:17:55 [INFO] train episode 3843: reward = -71.36, steps = 16 00:17:55 [INFO] train episode 3844: reward = -80.07, steps = 40 00:17:56 [INFO] train episode 3845: reward = -52.55, steps = 53 00:17:56 [INFO] train episode 3846: reward = -34.81, steps = 35 00:17:56 [INFO] train episode 3847: reward = -33.08, steps = 42 00:17:57 [INFO] train episode 3848: reward = -46.27, steps = 37 00:17:57 [INFO] train episode 3849: reward = -32.72, steps = 38 00:17:57 [INFO] train episode 3850: reward = -57.31, steps = 34 00:17:57 [INFO] train episode 3851: reward = -39.91, steps = 23 00:17:58 [INFO] train episode 3852: reward = -63.28, steps = 35 00:17:58 [INFO] train episode 3853: reward = -25.15, steps = 37 00:17:58 [INFO] train episode 3854: reward = -19.68, steps = 35 00:17:58 [INFO] train episode 3855: reward = -44.02, steps = 24 00:17:58 [INFO] train episode 3856: reward = -46.18, steps = 25 00:17:58 [INFO] train episode 3857: reward = -51.76, steps = 22 00:17:59 [INFO] train episode 3858: reward = -65.51, steps = 37 00:17:59 [INFO] train episode 3859: reward = -46.58, steps = 53 00:17:59 [INFO] train episode 3860: reward = -72.68, steps = 40 00:18:00 [INFO] train episode 3861: reward = -50.86, steps = 32 00:18:00 [INFO] train episode 3862: reward = -44.05, steps = 37 00:18:00 [INFO] train episode 3863: reward = -31.76, steps = 33 00:18:00 [INFO] train episode 3864: reward = -57.40, steps = 31 00:18:01 [INFO] train episode 3865: reward = -61.75, steps = 45 00:18:01 [INFO] train episode 3866: reward = -44.10, steps = 20 00:18:01 [INFO] train episode 3867: reward = -63.34, steps = 35 00:18:01 [INFO] train episode 3868: reward = -58.74, steps = 48 00:18:01 [INFO] train episode 3869: reward = -47.12, steps = 33 00:18:02 [INFO] train episode 3870: reward = -35.36, steps = 41 00:18:02 [INFO] train episode 3871: reward = -29.37, steps = 32 00:18:02 [INFO] train episode 3872: reward = -47.00, steps = 38 00:18:02 [INFO] train episode 3873: reward = -51.95, steps = 28 00:18:03 [INFO] train episode 3874: reward = -38.98, steps = 30 00:18:03 [INFO] train episode 3875: reward = -47.62, steps = 32 00:18:03 [INFO] train episode 3876: reward = -33.13, steps = 25 00:18:04 [INFO] train episode 3877: reward = -102.03, steps = 46 00:18:04 [INFO] train episode 3878: reward = -60.30, steps = 30 00:18:04 [INFO] train episode 3879: reward = -87.61, steps = 42 00:18:04 [INFO] train episode 3880: reward = -49.02, steps = 35 00:18:05 [INFO] train episode 3881: reward = -52.88, steps = 30 00:18:05 [INFO] train episode 3882: reward = -40.15, steps = 22 00:18:05 [INFO] train episode 3883: reward = -32.19, steps = 25 00:18:05 [INFO] train episode 3884: reward = -42.27, steps = 28 00:18:05 [INFO] train episode 3885: reward = -45.19, steps = 29 00:18:06 [INFO] train episode 3886: reward = -25.34, steps = 42 00:18:06 [INFO] train episode 3887: reward = -59.14, steps = 37 00:18:06 [INFO] train episode 3888: reward = -54.84, steps = 27 00:18:06 [INFO] train episode 3889: reward = -38.71, steps = 35 00:18:06 [INFO] train episode 3890: reward = -63.24, steps = 41 00:18:07 [INFO] train episode 3891: reward = -30.70, steps = 31 00:18:07 [INFO] train episode 3892: reward = -45.04, steps = 43 00:18:07 [INFO] train episode 3893: reward = -56.76, steps = 27 00:18:07 [INFO] train episode 3894: reward = -54.86, steps = 25 00:18:08 [INFO] train episode 3895: reward = -34.87, steps = 27 00:18:08 [INFO] train episode 3896: reward = -64.55, steps = 33 00:18:08 [INFO] train episode 3897: reward = -24.45, steps = 28 00:18:08 [INFO] train episode 3898: reward = -70.00, steps = 43 00:18:08 [INFO] train episode 3899: reward = -36.11, steps = 29 00:18:09 [INFO] train episode 3900: reward = -42.66, steps = 43 00:18:09 [INFO] train episode 3901: reward = -28.46, steps = 38 00:18:09 [INFO] train episode 3902: reward = -43.78, steps = 36 00:18:09 [INFO] train episode 3903: reward = -40.35, steps = 27 00:18:10 [INFO] train episode 3904: reward = -53.60, steps = 36 00:18:10 [INFO] train episode 3905: reward = -42.32, steps = 23 00:18:10 [INFO] train episode 3906: reward = -44.26, steps = 30 00:18:10 [INFO] train episode 3907: reward = -42.90, steps = 39 00:18:11 [INFO] train episode 3908: reward = -27.79, steps = 33 00:18:11 [INFO] train episode 3909: reward = -30.46, steps = 28 00:18:11 [INFO] train episode 3910: reward = -43.62, steps = 36 00:18:11 [INFO] train episode 3911: reward = -34.67, steps = 25 00:18:11 [INFO] train episode 3912: reward = -58.83, steps = 31 00:18:12 [INFO] train episode 3913: reward = -47.57, steps = 39 00:18:12 [INFO] train episode 3914: reward = -43.24, steps = 36 00:18:12 [INFO] train episode 3915: reward = -37.33, steps = 27 00:18:12 [INFO] train episode 3916: reward = -67.53, steps = 31 00:18:12 [INFO] train episode 3917: reward = -43.88, steps = 37 00:18:13 [INFO] train episode 3918: reward = -46.41, steps = 35 00:18:13 [INFO] train episode 3919: reward = -41.77, steps = 27 00:18:13 [INFO] train episode 3920: reward = -41.81, steps = 20 00:18:13 [INFO] train episode 3921: reward = -34.66, steps = 37 00:18:14 [INFO] train episode 3922: reward = -45.18, steps = 40 00:18:14 [INFO] train episode 3923: reward = -35.51, steps = 39 00:18:14 [INFO] train episode 3924: reward = -50.15, steps = 25 00:18:14 [INFO] train episode 3925: reward = -33.30, steps = 43 00:18:14 [INFO] train episode 3926: reward = -46.14, steps = 21 00:18:15 [INFO] train episode 3927: reward = -37.39, steps = 37 00:18:15 [INFO] train episode 3928: reward = -49.00, steps = 39 00:18:15 [INFO] train episode 3929: reward = -43.30, steps = 27 00:18:15 [INFO] train episode 3930: reward = -49.86, steps = 29 00:18:16 [INFO] train episode 3931: reward = -83.53, steps = 73 00:18:16 [INFO] train episode 3932: reward = -43.41, steps = 23 00:18:16 [INFO] train episode 3933: reward = -44.53, steps = 30 00:18:17 [INFO] train episode 3934: reward = -33.87, steps = 31 00:18:17 [INFO] train episode 3935: reward = -29.97, steps = 43 00:18:17 [INFO] train episode 3936: reward = -47.20, steps = 36 00:18:17 [INFO] train episode 3937: reward = -41.98, steps = 30 00:18:18 [INFO] train episode 3938: reward = -58.07, steps = 58 00:18:18 [INFO] train episode 3939: reward = -46.38, steps = 24 00:18:18 [INFO] train episode 3940: reward = -61.74, steps = 35 00:18:18 [INFO] train episode 3941: reward = -41.88, steps = 45 00:18:19 [INFO] train episode 3942: reward = -31.34, steps = 32 00:18:19 [INFO] train episode 3943: reward = -42.46, steps = 35 00:18:19 [INFO] train episode 3944: reward = -29.66, steps = 22 00:18:19 [INFO] train episode 3945: reward = -76.38, steps = 36 00:18:20 [INFO] train episode 3946: reward = -39.47, steps = 63 00:18:20 [INFO] train episode 3947: reward = -55.87, steps = 22 00:18:20 [INFO] train episode 3948: reward = -25.17, steps = 49 00:18:20 [INFO] train episode 3949: reward = -51.10, steps = 23 00:18:20 [INFO] train episode 3950: reward = -67.27, steps = 21 00:18:21 [INFO] train episode 3951: reward = -39.52, steps = 21 00:18:21 [INFO] train episode 3952: reward = -46.24, steps = 51 00:18:21 [INFO] train episode 3953: reward = -29.89, steps = 38 00:18:21 [INFO] train episode 3954: reward = -33.35, steps = 25 00:18:22 [INFO] train episode 3955: reward = -34.78, steps = 39 00:18:22 [INFO] train episode 3956: reward = -65.91, steps = 28 00:18:22 [INFO] train episode 3957: reward = -31.32, steps = 32 00:18:22 [INFO] train episode 3958: reward = -17.68, steps = 37 00:18:22 [INFO] train episode 3959: reward = -58.88, steps = 21 00:18:23 [INFO] train episode 3960: reward = -65.94, steps = 38 00:18:23 [INFO] train episode 3961: reward = -53.36, steps = 18 00:18:23 [INFO] train episode 3962: reward = -55.23, steps = 53 00:18:23 [INFO] train episode 3963: reward = -36.39, steps = 25 00:18:24 [INFO] train episode 3964: reward = -67.88, steps = 35 00:18:24 [INFO] train episode 3965: reward = -52.12, steps = 26 00:18:24 [INFO] train episode 3966: reward = -39.48, steps = 27 00:18:24 [INFO] train episode 3967: reward = -42.38, steps = 23 00:18:24 [INFO] train episode 3968: reward = -56.80, steps = 22 00:18:25 [INFO] train episode 3969: reward = -73.86, steps = 33 00:18:25 [INFO] train episode 3970: reward = -49.10, steps = 44 00:18:25 [INFO] train episode 3971: reward = -39.91, steps = 34 00:18:25 [INFO] train episode 3972: reward = -31.91, steps = 22 00:18:25 [INFO] train episode 3973: reward = -48.60, steps = 32 00:18:26 [INFO] train episode 3974: reward = -33.03, steps = 31 00:18:26 [INFO] train episode 3975: reward = -127.08, steps = 71 00:18:26 [INFO] train episode 3976: reward = -21.70, steps = 32 00:18:27 [INFO] train episode 3977: reward = -46.07, steps = 33 00:18:27 [INFO] train episode 3978: reward = -43.95, steps = 26 00:18:27 [INFO] train episode 3979: reward = -58.53, steps = 44 00:18:27 [INFO] train episode 3980: reward = -44.30, steps = 22 00:18:27 [INFO] train episode 3981: reward = -56.97, steps = 31 00:18:28 [INFO] train episode 3982: reward = -30.93, steps = 34 00:18:28 [INFO] train episode 3983: reward = -37.34, steps = 25 00:18:28 [INFO] train episode 3984: reward = -42.65, steps = 45 00:18:28 [INFO] train episode 3985: reward = -40.18, steps = 21 00:18:28 [INFO] train episode 3986: reward = -44.48, steps = 23 00:18:29 [INFO] train episode 3987: reward = -36.24, steps = 28 00:18:29 [INFO] train episode 3988: reward = -58.65, steps = 35 00:18:29 [INFO] train episode 3989: reward = -50.72, steps = 24 00:18:29 [INFO] train episode 3990: reward = -38.09, steps = 28 00:18:29 [INFO] train episode 3991: reward = -63.04, steps = 41 00:18:30 [INFO] train episode 3992: reward = -25.76, steps = 24 00:18:30 [INFO] train episode 3993: reward = -39.43, steps = 32 00:18:30 [INFO] train episode 3994: reward = -58.00, steps = 37 00:18:31 [INFO] train episode 3995: reward = -39.05, steps = 37 00:18:31 [INFO] train episode 3996: reward = -30.40, steps = 33 00:18:31 [INFO] train episode 3997: reward = -41.66, steps = 46 00:18:31 [INFO] train episode 3998: reward = -33.66, steps = 39 00:18:32 [INFO] train episode 3999: reward = -42.20, steps = 30 00:18:32 [INFO] train episode 4000: reward = -27.39, steps = 40 00:18:32 [INFO] train episode 4001: reward = -55.64, steps = 20 00:18:32 [INFO] train episode 4002: reward = -31.42, steps = 49 00:18:33 [INFO] train episode 4003: reward = -51.34, steps = 42 00:18:33 [INFO] train episode 4004: reward = -53.41, steps = 21 00:18:33 [INFO] train episode 4005: reward = -30.60, steps = 36 00:18:33 [INFO] train episode 4006: reward = -63.66, steps = 20 00:18:34 [INFO] train episode 4007: reward = -30.12, steps = 32 00:18:34 [INFO] train episode 4008: reward = -53.06, steps = 20 00:18:34 [INFO] train episode 4009: reward = -50.62, steps = 20 00:18:34 [INFO] train episode 4010: reward = -44.82, steps = 20 00:18:34 [INFO] train episode 4011: reward = -46.63, steps = 37 00:18:34 [INFO] train episode 4012: reward = -39.15, steps = 21 00:18:35 [INFO] train episode 4013: reward = -35.63, steps = 20 00:18:35 [INFO] train episode 4014: reward = -38.28, steps = 22 00:18:35 [INFO] train episode 4015: reward = -54.79, steps = 42 00:18:35 [INFO] train episode 4016: reward = -39.17, steps = 22 00:18:35 [INFO] train episode 4017: reward = -38.41, steps = 24 00:18:35 [INFO] train episode 4018: reward = -39.73, steps = 29 00:18:36 [INFO] train episode 4019: reward = -59.96, steps = 33 00:18:36 [INFO] train episode 4020: reward = -44.26, steps = 21 00:18:36 [INFO] train episode 4021: reward = -50.04, steps = 22 00:18:36 [INFO] train episode 4022: reward = -58.71, steps = 22 00:18:36 [INFO] train episode 4023: reward = -70.17, steps = 41 00:18:37 [INFO] train episode 4024: reward = -54.49, steps = 33 00:18:37 [INFO] train episode 4025: reward = -52.33, steps = 28 00:18:37 [INFO] train episode 4026: reward = -49.24, steps = 32 00:18:37 [INFO] train episode 4027: reward = -50.23, steps = 34 00:18:37 [INFO] train episode 4028: reward = -45.74, steps = 32 00:18:38 [INFO] train episode 4029: reward = -38.74, steps = 35 00:18:38 [INFO] train episode 4030: reward = -55.02, steps = 20 00:18:38 [INFO] train episode 4031: reward = -60.44, steps = 38 00:18:38 [INFO] train episode 4032: reward = -45.68, steps = 36 00:18:39 [INFO] train episode 4033: reward = -49.80, steps = 30 00:18:39 [INFO] train episode 4034: reward = -68.58, steps = 34 00:18:39 [INFO] train episode 4035: reward = -44.21, steps = 21 00:18:39 [INFO] train episode 4036: reward = -30.44, steps = 27 00:18:39 [INFO] train episode 4037: reward = -61.67, steps = 27 00:18:40 [INFO] train episode 4038: reward = -43.78, steps = 40 00:18:40 [INFO] train episode 4039: reward = -42.69, steps = 26 00:18:40 [INFO] train episode 4040: reward = -29.41, steps = 30 00:18:40 [INFO] train episode 4041: reward = -39.57, steps = 25 00:18:40 [INFO] train episode 4042: reward = -71.79, steps = 22 00:18:41 [INFO] train episode 4043: reward = -39.94, steps = 27 00:18:41 [INFO] train episode 4044: reward = -38.56, steps = 34 00:18:41 [INFO] train episode 4045: reward = -33.40, steps = 21 00:18:41 [INFO] train episode 4046: reward = -49.41, steps = 29 00:18:41 [INFO] train episode 4047: reward = -43.33, steps = 35 00:18:42 [INFO] train episode 4048: reward = -37.27, steps = 32 00:18:42 [INFO] train episode 4049: reward = -49.90, steps = 38 00:18:42 [INFO] train episode 4050: reward = -33.30, steps = 51 00:18:42 [INFO] train episode 4051: reward = -60.69, steps = 22 00:18:42 [INFO] train episode 4052: reward = -55.53, steps = 32 00:18:43 [INFO] train episode 4053: reward = -50.51, steps = 23 00:18:43 [INFO] train episode 4054: reward = -60.36, steps = 30 00:18:43 [INFO] train episode 4055: reward = -33.83, steps = 42 00:18:44 [INFO] train episode 4056: reward = -77.30, steps = 47 00:18:44 [INFO] train episode 4057: reward = -67.87, steps = 35 00:18:44 [INFO] train episode 4058: reward = -33.12, steps = 31 00:18:44 [INFO] train episode 4059: reward = -96.49, steps = 54 00:18:45 [INFO] train episode 4060: reward = -80.29, steps = 47 00:18:45 [INFO] train episode 4061: reward = -46.06, steps = 25 00:18:45 [INFO] train episode 4062: reward = -36.71, steps = 43 00:18:45 [INFO] train episode 4063: reward = -40.01, steps = 26 00:18:46 [INFO] train episode 4064: reward = -29.67, steps = 28 00:18:46 [INFO] train episode 4065: reward = -56.36, steps = 23 00:18:46 [INFO] train episode 4066: reward = -61.63, steps = 37 00:18:46 [INFO] train episode 4067: reward = -34.67, steps = 19 00:18:46 [INFO] train episode 4068: reward = -49.16, steps = 30 00:18:47 [INFO] train episode 4069: reward = -49.05, steps = 31 00:18:47 [INFO] train episode 4070: reward = -47.22, steps = 40 00:18:47 [INFO] train episode 4071: reward = -58.81, steps = 34 00:18:47 [INFO] train episode 4072: reward = -42.68, steps = 31 00:18:47 [INFO] train episode 4073: reward = -37.83, steps = 27 00:18:48 [INFO] train episode 4074: reward = -66.66, steps = 35 00:18:48 [INFO] train episode 4075: reward = -65.68, steps = 31 00:18:48 [INFO] train episode 4076: reward = -57.14, steps = 24 00:18:48 [INFO] train episode 4077: reward = -51.51, steps = 24 00:18:48 [INFO] train episode 4078: reward = -51.52, steps = 29 00:18:49 [INFO] train episode 4079: reward = -29.81, steps = 35 00:18:49 [INFO] train episode 4080: reward = -43.13, steps = 36 00:18:49 [INFO] train episode 4081: reward = -58.60, steps = 28 00:18:49 [INFO] train episode 4082: reward = -58.22, steps = 39 00:18:50 [INFO] train episode 4083: reward = -33.07, steps = 37 00:18:50 [INFO] train episode 4084: reward = -53.28, steps = 30 00:18:50 [INFO] train episode 4085: reward = -36.50, steps = 23 00:18:50 [INFO] train episode 4086: reward = -42.78, steps = 22 00:18:50 [INFO] train episode 4087: reward = -66.98, steps = 22 00:18:51 [INFO] train episode 4088: reward = -44.18, steps = 44 00:18:51 [INFO] train episode 4089: reward = -37.54, steps = 22 00:18:51 [INFO] train episode 4090: reward = -51.68, steps = 28 00:18:51 [INFO] train episode 4091: reward = -27.64, steps = 20 00:18:51 [INFO] train episode 4092: reward = -48.03, steps = 29 00:18:51 [INFO] train episode 4093: reward = -39.99, steps = 22 00:18:52 [INFO] train episode 4094: reward = -25.33, steps = 44 00:18:52 [INFO] train episode 4095: reward = -34.72, steps = 25 00:18:52 [INFO] train episode 4096: reward = -41.79, steps = 37 00:18:52 [INFO] train episode 4097: reward = -38.59, steps = 25 00:18:53 [INFO] train episode 4098: reward = -36.95, steps = 48 00:18:53 [INFO] train episode 4099: reward = -34.01, steps = 23 00:18:53 [INFO] train episode 4100: reward = -45.89, steps = 37 00:18:53 [INFO] train episode 4101: reward = -34.21, steps = 39 00:18:53 [INFO] train episode 4102: reward = -46.08, steps = 27 00:18:54 [INFO] train episode 4103: reward = -45.32, steps = 26 00:18:54 [INFO] train episode 4104: reward = -38.96, steps = 42 00:18:54 [INFO] train episode 4105: reward = -39.04, steps = 20 00:18:54 [INFO] train episode 4106: reward = -29.45, steps = 21 00:18:54 [INFO] train episode 4107: reward = -50.71, steps = 22 00:18:55 [INFO] train episode 4108: reward = -72.66, steps = 47 00:18:55 [INFO] train episode 4109: reward = -45.77, steps = 35 00:18:55 [INFO] train episode 4110: reward = -37.98, steps = 32 00:18:55 [INFO] train episode 4111: reward = -40.65, steps = 28 00:18:56 [INFO] train episode 4112: reward = -43.76, steps = 35 00:18:56 [INFO] train episode 4113: reward = -50.39, steps = 32 00:18:56 [INFO] train episode 4114: reward = -35.39, steps = 25 00:18:56 [INFO] train episode 4115: reward = -47.50, steps = 24 00:18:56 [INFO] train episode 4116: reward = -71.74, steps = 28 00:18:57 [INFO] train episode 4117: reward = -37.02, steps = 36 00:18:57 [INFO] train episode 4118: reward = -51.86, steps = 39 00:18:57 [INFO] train episode 4119: reward = -53.90, steps = 35 00:18:58 [INFO] train episode 4120: reward = -26.26, steps = 44 00:18:58 [INFO] train episode 4121: reward = -40.31, steps = 31 00:18:58 [INFO] train episode 4122: reward = -63.01, steps = 31 00:18:58 [INFO] train episode 4123: reward = -44.15, steps = 42 00:18:59 [INFO] train episode 4124: reward = -88.79, steps = 52 00:18:59 [INFO] train episode 4125: reward = -26.26, steps = 26 00:18:59 [INFO] train episode 4126: reward = -74.09, steps = 42 00:18:59 [INFO] train episode 4127: reward = -75.36, steps = 53 00:19:00 [INFO] train episode 4128: reward = -34.17, steps = 21 00:19:00 [INFO] train episode 4129: reward = -25.48, steps = 33 00:19:00 [INFO] train episode 4130: reward = -33.39, steps = 26 00:19:00 [INFO] train episode 4131: reward = -31.59, steps = 28 00:19:00 [INFO] train episode 4132: reward = -49.72, steps = 23 00:19:01 [INFO] train episode 4133: reward = -45.61, steps = 26 00:19:01 [INFO] train episode 4134: reward = -65.42, steps = 27 00:19:01 [INFO] train episode 4135: reward = -81.04, steps = 40 00:19:01 [INFO] train episode 4136: reward = -46.87, steps = 39 00:19:02 [INFO] train episode 4137: reward = -55.52, steps = 39 00:19:02 [INFO] train episode 4138: reward = -34.79, steps = 32 00:19:02 [INFO] train episode 4139: reward = -43.35, steps = 31 00:19:02 [INFO] train episode 4140: reward = -47.44, steps = 28 00:19:02 [INFO] train episode 4141: reward = -100.70, steps = 40 00:19:03 [INFO] train episode 4142: reward = -58.91, steps = 48 00:19:03 [INFO] train episode 4143: reward = -46.80, steps = 21 00:19:03 [INFO] train episode 4144: reward = -55.09, steps = 49 00:19:03 [INFO] train episode 4145: reward = -49.31, steps = 21 00:19:04 [INFO] train episode 4146: reward = -46.91, steps = 22 00:19:04 [INFO] train episode 4147: reward = -32.22, steps = 25 00:19:04 [INFO] train episode 4148: reward = -55.18, steps = 34 00:19:04 [INFO] train episode 4149: reward = -54.01, steps = 39 00:19:05 [INFO] train episode 4150: reward = -42.36, steps = 30 00:19:05 [INFO] train episode 4151: reward = -49.75, steps = 22 00:19:05 [INFO] train episode 4152: reward = -40.25, steps = 29 00:19:05 [INFO] train episode 4153: reward = -36.37, steps = 23 00:19:05 [INFO] train episode 4154: reward = -35.38, steps = 29 00:19:06 [INFO] train episode 4155: reward = -78.62, steps = 42 00:19:06 [INFO] train episode 4156: reward = -53.30, steps = 20 00:19:06 [INFO] train episode 4157: reward = -60.09, steps = 53 00:19:06 [INFO] train episode 4158: reward = -40.47, steps = 38 00:19:06 [INFO] train episode 4159: reward = -38.54, steps = 19 00:19:07 [INFO] train episode 4160: reward = -40.14, steps = 35 00:19:07 [INFO] train episode 4161: reward = -29.24, steps = 34 00:19:07 [INFO] train episode 4162: reward = -62.78, steps = 38 00:19:07 [INFO] train episode 4163: reward = -36.00, steps = 22 00:19:08 [INFO] train episode 4164: reward = -45.09, steps = 28 00:19:08 [INFO] train episode 4165: reward = -35.36, steps = 31 00:19:08 [INFO] train episode 4166: reward = -33.36, steps = 33 00:19:08 [INFO] train episode 4167: reward = -49.24, steps = 39 00:19:08 [INFO] train episode 4168: reward = -51.66, steps = 43 00:19:09 [INFO] train episode 4169: reward = -41.45, steps = 19 00:19:09 [INFO] train episode 4170: reward = -42.14, steps = 31 00:19:09 [INFO] train episode 4171: reward = -62.92, steps = 37 00:19:09 [INFO] train episode 4172: reward = -61.21, steps = 44 00:19:10 [INFO] train episode 4173: reward = -34.69, steps = 20 00:19:10 [INFO] train episode 4174: reward = -39.84, steps = 25 00:19:10 [INFO] train episode 4175: reward = -47.20, steps = 37 00:19:10 [INFO] train episode 4176: reward = -29.81, steps = 27 00:19:10 [INFO] train episode 4177: reward = -45.33, steps = 25 00:19:11 [INFO] train episode 4178: reward = -60.37, steps = 29 00:19:11 [INFO] train episode 4179: reward = -42.04, steps = 30 00:19:11 [INFO] train episode 4180: reward = -49.50, steps = 21 00:19:11 [INFO] train episode 4181: reward = -51.02, steps = 23 00:19:11 [INFO] train episode 4182: reward = -30.55, steps = 30 00:19:12 [INFO] train episode 4183: reward = -42.68, steps = 23 00:19:12 [INFO] train episode 4184: reward = -77.79, steps = 35 00:19:12 [INFO] train episode 4185: reward = -55.88, steps = 32 00:19:12 [INFO] train episode 4186: reward = -25.12, steps = 34 00:19:13 [INFO] train episode 4187: reward = -44.61, steps = 33 00:19:13 [INFO] train episode 4188: reward = -34.88, steps = 26 00:19:13 [INFO] train episode 4189: reward = -45.29, steps = 30 00:19:13 [INFO] train episode 4190: reward = -38.51, steps = 30 00:19:13 [INFO] train episode 4191: reward = -40.49, steps = 22 00:19:14 [INFO] train episode 4192: reward = -43.14, steps = 25 00:19:14 [INFO] train episode 4193: reward = -32.56, steps = 20 00:19:14 [INFO] train episode 4194: reward = -32.94, steps = 41 00:19:14 [INFO] train episode 4195: reward = -42.46, steps = 40 00:19:14 [INFO] train episode 4196: reward = -46.40, steps = 26 00:19:15 [INFO] train episode 4197: reward = -59.43, steps = 30 00:19:15 [INFO] train episode 4198: reward = -54.40, steps = 21 00:19:15 [INFO] train episode 4199: reward = -58.90, steps = 28 00:19:15 [INFO] train episode 4200: reward = -59.59, steps = 31 00:19:15 [INFO] train episode 4201: reward = -24.31, steps = 33 00:19:16 [INFO] train episode 4202: reward = -41.02, steps = 25 00:19:16 [INFO] train episode 4203: reward = -47.92, steps = 41 00:19:16 [INFO] train episode 4204: reward = -34.65, steps = 24 00:19:16 [INFO] train episode 4205: reward = -37.61, steps = 22 00:19:16 [INFO] train episode 4206: reward = -35.49, steps = 20 00:19:17 [INFO] train episode 4207: reward = -45.69, steps = 26 00:19:17 [INFO] train episode 4208: reward = -39.29, steps = 27 00:19:17 [INFO] train episode 4209: reward = -37.15, steps = 27 00:19:17 [INFO] train episode 4210: reward = -50.67, steps = 26 00:19:17 [INFO] train episode 4211: reward = -51.99, steps = 28 00:19:17 [INFO] train episode 4212: reward = -44.68, steps = 24 00:19:18 [INFO] train episode 4213: reward = -42.42, steps = 36 00:19:18 [INFO] train episode 4214: reward = -40.28, steps = 25 00:19:18 [INFO] train episode 4215: reward = -57.05, steps = 30 00:19:18 [INFO] train episode 4216: reward = -56.82, steps = 23 00:19:18 [INFO] train episode 4217: reward = -37.71, steps = 26 00:19:19 [INFO] train episode 4218: reward = -35.26, steps = 30 00:19:19 [INFO] train episode 4219: reward = -39.75, steps = 31 00:19:19 [INFO] train episode 4220: reward = -61.98, steps = 31 00:19:19 [INFO] train episode 4221: reward = -44.44, steps = 22 00:19:19 [INFO] train episode 4222: reward = -35.78, steps = 33 00:19:20 [INFO] train episode 4223: reward = -68.35, steps = 44 00:19:20 [INFO] train episode 4224: reward = -50.15, steps = 22 00:19:20 [INFO] train episode 4225: reward = -42.24, steps = 27 00:19:20 [INFO] train episode 4226: reward = -40.71, steps = 21 00:19:20 [INFO] train episode 4227: reward = -49.31, steps = 25 00:19:20 [INFO] train episode 4228: reward = -43.19, steps = 22 00:19:21 [INFO] train episode 4229: reward = -35.37, steps = 29 00:19:21 [INFO] train episode 4230: reward = -40.23, steps = 21 00:19:21 [INFO] train episode 4231: reward = -43.51, steps = 41 00:19:21 [INFO] train episode 4232: reward = -40.60, steps = 34 00:19:21 [INFO] train episode 4233: reward = -47.28, steps = 28 00:19:22 [INFO] train episode 4234: reward = -47.63, steps = 21 00:19:22 [INFO] train episode 4235: reward = -59.90, steps = 30 00:19:22 [INFO] train episode 4236: reward = -74.64, steps = 46 00:19:22 [INFO] train episode 4237: reward = -45.93, steps = 26 00:19:23 [INFO] train episode 4238: reward = -44.78, steps = 36 00:19:23 [INFO] train episode 4239: reward = -54.86, steps = 22 00:19:23 [INFO] train episode 4240: reward = -52.06, steps = 28 00:19:23 [INFO] train episode 4241: reward = -31.07, steps = 36 00:19:23 [INFO] train episode 4242: reward = -71.96, steps = 28 00:19:24 [INFO] train episode 4243: reward = -45.66, steps = 19 00:19:24 [INFO] train episode 4244: reward = -43.91, steps = 40 00:19:24 [INFO] train episode 4245: reward = -64.37, steps = 51 00:19:25 [INFO] train episode 4246: reward = -48.12, steps = 24 00:19:25 [INFO] train episode 4247: reward = -42.19, steps = 30 00:19:25 [INFO] train episode 4248: reward = -66.22, steps = 27 00:19:25 [INFO] train episode 4249: reward = -44.06, steps = 31 00:19:25 [INFO] train episode 4250: reward = -52.61, steps = 42 00:19:26 [INFO] train episode 4251: reward = -57.70, steps = 22 00:19:26 [INFO] train episode 4252: reward = -71.35, steps = 21 00:19:26 [INFO] train episode 4253: reward = -34.18, steps = 20 00:19:26 [INFO] train episode 4254: reward = -49.78, steps = 32 00:19:26 [INFO] train episode 4255: reward = -48.20, steps = 33 00:19:27 [INFO] train episode 4256: reward = -62.01, steps = 43 00:19:27 [INFO] train episode 4257: reward = -24.48, steps = 29 00:19:27 [INFO] train episode 4258: reward = -49.55, steps = 25 00:19:27 [INFO] train episode 4259: reward = -47.44, steps = 50 00:19:28 [INFO] train episode 4260: reward = -45.53, steps = 39 00:19:28 [INFO] train episode 4261: reward = -42.98, steps = 30 00:19:28 [INFO] train episode 4262: reward = -82.61, steps = 58 00:19:28 [INFO] train episode 4263: reward = -53.62, steps = 21 00:19:29 [INFO] train episode 4264: reward = -47.14, steps = 22 00:19:29 [INFO] train episode 4265: reward = -40.03, steps = 26 00:19:29 [INFO] train episode 4266: reward = -66.69, steps = 43 00:19:29 [INFO] train episode 4267: reward = -42.75, steps = 21 00:19:29 [INFO] train episode 4268: reward = -42.32, steps = 20 00:19:30 [INFO] train episode 4269: reward = -40.01, steps = 27 00:19:30 [INFO] train episode 4270: reward = -46.16, steps = 25 00:19:30 [INFO] train episode 4271: reward = -64.93, steps = 19 00:19:30 [INFO] train episode 4272: reward = -52.62, steps = 25 00:19:30 [INFO] train episode 4273: reward = -43.42, steps = 19 00:19:30 [INFO] train episode 4274: reward = -42.61, steps = 31 00:19:31 [INFO] train episode 4275: reward = -45.28, steps = 22 00:19:31 [INFO] train episode 4276: reward = -40.17, steps = 21 00:19:31 [INFO] train episode 4277: reward = -35.74, steps = 24 00:19:31 [INFO] train episode 4278: reward = -49.01, steps = 23 00:19:31 [INFO] train episode 4279: reward = -42.50, steps = 22 00:19:31 [INFO] train episode 4280: reward = -57.30, steps = 19 00:19:32 [INFO] train episode 4281: reward = -50.38, steps = 39 00:19:32 [INFO] train episode 4282: reward = -50.66, steps = 45 00:19:32 [INFO] train episode 4283: reward = -38.83, steps = 42 00:19:32 [INFO] train episode 4284: reward = -51.87, steps = 29 00:19:33 [INFO] train episode 4285: reward = -57.55, steps = 31 00:19:33 [INFO] train episode 4286: reward = -62.45, steps = 18 00:19:33 [INFO] train episode 4287: reward = -51.08, steps = 22 00:19:33 [INFO] train episode 4288: reward = -30.32, steps = 27 00:19:33 [INFO] train episode 4289: reward = -44.66, steps = 36 00:19:33 [INFO] train episode 4290: reward = -32.65, steps = 24 00:19:34 [INFO] train episode 4291: reward = -36.09, steps = 24 00:19:34 [INFO] train episode 4292: reward = -52.26, steps = 42 00:19:34 [INFO] train episode 4293: reward = -51.90, steps = 25 00:19:34 [INFO] train episode 4294: reward = -33.88, steps = 19 00:19:34 [INFO] train episode 4295: reward = -32.32, steps = 38 00:19:35 [INFO] train episode 4296: reward = -36.95, steps = 39 00:19:35 [INFO] train episode 4297: reward = -34.64, steps = 35 00:19:35 [INFO] train episode 4298: reward = -42.40, steps = 21 00:19:35 [INFO] train episode 4299: reward = -46.96, steps = 23 00:19:35 [INFO] train episode 4300: reward = -51.30, steps = 24 00:19:36 [INFO] train episode 4301: reward = -55.93, steps = 38 00:19:36 [INFO] train episode 4302: reward = -41.71, steps = 26 00:19:36 [INFO] train episode 4303: reward = -42.08, steps = 30 00:19:36 [INFO] train episode 4304: reward = -41.55, steps = 34 00:19:36 [INFO] train episode 4305: reward = -25.15, steps = 22 00:19:37 [INFO] train episode 4306: reward = -39.23, steps = 20 00:19:37 [INFO] train episode 4307: reward = -48.20, steps = 21 00:19:37 [INFO] train episode 4308: reward = -54.80, steps = 25 00:19:37 [INFO] train episode 4309: reward = -53.55, steps = 22 00:19:37 [INFO] train episode 4310: reward = -41.82, steps = 45 00:19:38 [INFO] train episode 4311: reward = -54.22, steps = 27 00:19:38 [INFO] train episode 4312: reward = -37.79, steps = 22 00:19:38 [INFO] train episode 4313: reward = -62.76, steps = 30 00:19:38 [INFO] train episode 4314: reward = -39.36, steps = 28 00:19:39 [INFO] train episode 4315: reward = -56.57, steps = 25 00:19:39 [INFO] train episode 4316: reward = -39.68, steps = 19 00:19:39 [INFO] train episode 4317: reward = -31.57, steps = 19 00:19:39 [INFO] train episode 4318: reward = -48.43, steps = 19 00:19:39 [INFO] train episode 4319: reward = -36.96, steps = 20 00:19:39 [INFO] train episode 4320: reward = -26.87, steps = 26 00:19:40 [INFO] train episode 4321: reward = -30.81, steps = 26 00:19:40 [INFO] train episode 4322: reward = -32.95, steps = 20 00:19:40 [INFO] train episode 4323: reward = -35.33, steps = 21 00:19:40 [INFO] train episode 4324: reward = -50.43, steps = 21 00:19:40 [INFO] train episode 4325: reward = -74.88, steps = 48 00:19:40 [INFO] train episode 4326: reward = -42.17, steps = 21 00:19:41 [INFO] train episode 4327: reward = -22.60, steps = 25 00:19:41 [INFO] train episode 4328: reward = -54.39, steps = 46 00:19:41 [INFO] train episode 4329: reward = -27.90, steps = 31 00:19:41 [INFO] train episode 4330: reward = -38.73, steps = 32 00:19:42 [INFO] train episode 4331: reward = -39.06, steps = 30 00:19:42 [INFO] train episode 4332: reward = -43.79, steps = 20 00:19:42 [INFO] train episode 4333: reward = -60.56, steps = 17 00:19:42 [INFO] train episode 4334: reward = -22.71, steps = 33 00:19:42 [INFO] train episode 4335: reward = -48.47, steps = 33 00:19:43 [INFO] train episode 4336: reward = -63.57, steps = 50 00:19:43 [INFO] train episode 4337: reward = -57.33, steps = 43 00:19:43 [INFO] train episode 4338: reward = -35.70, steps = 23 00:19:43 [INFO] train episode 4339: reward = -33.93, steps = 20 00:19:43 [INFO] train episode 4340: reward = -44.40, steps = 22 00:19:44 [INFO] train episode 4341: reward = -51.62, steps = 19 00:19:44 [INFO] train episode 4342: reward = -50.45, steps = 31 00:19:44 [INFO] train episode 4343: reward = -48.64, steps = 30 00:19:44 [INFO] train episode 4344: reward = -32.76, steps = 23 00:19:44 [INFO] train episode 4345: reward = -53.40, steps = 21 00:19:45 [INFO] train episode 4346: reward = -16.10, steps = 44 00:19:45 [INFO] train episode 4347: reward = -46.38, steps = 49 00:19:45 [INFO] train episode 4348: reward = -24.04, steps = 19 00:19:45 [INFO] train episode 4349: reward = -29.77, steps = 24 00:19:45 [INFO] train episode 4350: reward = -47.90, steps = 23 00:19:46 [INFO] train episode 4351: reward = -38.52, steps = 32 00:19:46 [INFO] train episode 4352: reward = -38.40, steps = 29 00:19:46 [INFO] train episode 4353: reward = -48.02, steps = 34 00:19:46 [INFO] train episode 4354: reward = -55.81, steps = 26 00:19:46 [INFO] train episode 4355: reward = -52.92, steps = 25 00:19:46 [INFO] train episode 4356: reward = -36.31, steps = 21 00:19:47 [INFO] train episode 4357: reward = -34.01, steps = 33 00:19:47 [INFO] train episode 4358: reward = -39.05, steps = 20 00:19:47 [INFO] train episode 4359: reward = -56.64, steps = 25 00:19:47 [INFO] train episode 4360: reward = -45.95, steps = 26 00:19:47 [INFO] train episode 4361: reward = -40.17, steps = 23 00:19:48 [INFO] train episode 4362: reward = -49.55, steps = 32 00:19:48 [INFO] train episode 4363: reward = -24.68, steps = 31 00:19:48 [INFO] train episode 4364: reward = -40.99, steps = 21 00:19:48 [INFO] train episode 4365: reward = -26.46, steps = 31 00:19:48 [INFO] train episode 4366: reward = -46.56, steps = 23 00:19:48 [INFO] train episode 4367: reward = -44.73, steps = 21 00:19:49 [INFO] train episode 4368: reward = -59.21, steps = 31 00:19:49 [INFO] train episode 4369: reward = -31.63, steps = 33 00:19:49 [INFO] train episode 4370: reward = -39.66, steps = 27 00:19:49 [INFO] train episode 4371: reward = -45.86, steps = 20 00:19:49 [INFO] train episode 4372: reward = -51.65, steps = 19 00:19:50 [INFO] train episode 4373: reward = -37.75, steps = 30 00:19:50 [INFO] train episode 4374: reward = -32.77, steps = 27 00:19:50 [INFO] train episode 4375: reward = -37.76, steps = 21 00:19:50 [INFO] train episode 4376: reward = -62.52, steps = 36 00:19:50 [INFO] train episode 4377: reward = -31.88, steps = 21 00:19:50 [INFO] train episode 4378: reward = -47.95, steps = 25 00:19:51 [INFO] train episode 4379: reward = -47.56, steps = 27 00:19:51 [INFO] train episode 4380: reward = -46.06, steps = 31 00:19:51 [INFO] train episode 4381: reward = -49.00, steps = 35 00:19:51 [INFO] train episode 4382: reward = -41.81, steps = 20 00:19:51 [INFO] train episode 4383: reward = -32.43, steps = 14 00:19:51 [INFO] train episode 4384: reward = -30.44, steps = 20 00:19:52 [INFO] train episode 4385: reward = -36.77, steps = 27 00:19:52 [INFO] train episode 4386: reward = -40.82, steps = 29 00:19:52 [INFO] train episode 4387: reward = -59.39, steps = 27 00:19:52 [INFO] train episode 4388: reward = -49.60, steps = 31 00:19:53 [INFO] train episode 4389: reward = -33.04, steps = 22 00:19:53 [INFO] train episode 4390: reward = -43.24, steps = 26 00:19:53 [INFO] train episode 4391: reward = -51.96, steps = 19 00:19:53 [INFO] train episode 4392: reward = -85.07, steps = 27 00:19:53 [INFO] train episode 4393: reward = -38.34, steps = 27 00:19:53 [INFO] train episode 4394: reward = -55.25, steps = 20 00:19:54 [INFO] train episode 4395: reward = -48.60, steps = 27 00:19:54 [INFO] train episode 4396: reward = -59.21, steps = 26 00:19:54 [INFO] train episode 4397: reward = -60.71, steps = 21 00:19:54 [INFO] train episode 4398: reward = -51.77, steps = 29 00:19:54 [INFO] train episode 4399: reward = -45.48, steps = 20 00:19:55 [INFO] train episode 4400: reward = -24.55, steps = 36 00:19:55 [INFO] train episode 4401: reward = -46.60, steps = 32 00:19:55 [INFO] train episode 4402: reward = -46.08, steps = 18 00:19:55 [INFO] train episode 4403: reward = -43.48, steps = 20 00:19:55 [INFO] train episode 4404: reward = -28.72, steps = 22 00:19:55 [INFO] train episode 4405: reward = -35.23, steps = 23 00:19:56 [INFO] train episode 4406: reward = -39.77, steps = 28 00:19:56 [INFO] train episode 4407: reward = -27.18, steps = 24 00:19:56 [INFO] train episode 4408: reward = -51.77, steps = 35 00:19:56 [INFO] train episode 4409: reward = -55.96, steps = 40 00:19:57 [INFO] train episode 4410: reward = -37.17, steps = 40 00:19:57 [INFO] train episode 4411: reward = -55.15, steps = 19 00:19:57 [INFO] train episode 4412: reward = -37.15, steps = 20 00:19:57 [INFO] train episode 4413: reward = -43.34, steps = 21 00:19:57 [INFO] train episode 4414: reward = -33.03, steps = 28 00:19:57 [INFO] train episode 4415: reward = -55.03, steps = 27 00:19:58 [INFO] train episode 4416: reward = -27.37, steps = 36 00:19:58 [INFO] train episode 4417: reward = -30.43, steps = 21 00:19:58 [INFO] train episode 4418: reward = -56.18, steps = 23 00:19:58 [INFO] train episode 4419: reward = -57.30, steps = 23 00:19:58 [INFO] train episode 4420: reward = -35.18, steps = 23 00:19:59 [INFO] train episode 4421: reward = -56.74, steps = 27 00:19:59 [INFO] train episode 4422: reward = -44.27, steps = 32 00:19:59 [INFO] train episode 4423: reward = -42.87, steps = 21 00:19:59 [INFO] train episode 4424: reward = -54.26, steps = 37 00:19:59 [INFO] train episode 4425: reward = -25.18, steps = 30 00:20:00 [INFO] train episode 4426: reward = -36.96, steps = 34 00:20:00 [INFO] train episode 4427: reward = -36.15, steps = 23 00:20:00 [INFO] train episode 4428: reward = -21.27, steps = 25 00:20:00 [INFO] train episode 4429: reward = -47.46, steps = 20 00:20:01 [INFO] train episode 4430: reward = -51.50, steps = 30 00:20:01 [INFO] train episode 4431: reward = -56.76, steps = 24 00:20:01 [INFO] train episode 4432: reward = -40.76, steps = 19 00:20:01 [INFO] train episode 4433: reward = -54.71, steps = 25 00:20:01 [INFO] train episode 4434: reward = -41.21, steps = 20 00:20:01 [INFO] train episode 4435: reward = -35.63, steps = 24 00:20:02 [INFO] train episode 4436: reward = -34.68, steps = 32 00:20:02 [INFO] train episode 4437: reward = -50.94, steps = 21 00:20:02 [INFO] train episode 4438: reward = -48.60, steps = 26 00:20:02 [INFO] train episode 4439: reward = -50.08, steps = 21 00:20:02 [INFO] train episode 4440: reward = -32.52, steps = 21 00:20:03 [INFO] train episode 4441: reward = -33.83, steps = 41 00:20:03 [INFO] train episode 4442: reward = -60.34, steps = 34 00:20:03 [INFO] train episode 4443: reward = -44.41, steps = 35 00:20:03 [INFO] train episode 4444: reward = -35.63, steps = 22 00:20:03 [INFO] train episode 4445: reward = -64.97, steps = 33 00:20:04 [INFO] train episode 4446: reward = -33.05, steps = 24 00:20:04 [INFO] train episode 4447: reward = -34.49, steps = 24 00:20:04 [INFO] train episode 4448: reward = -43.17, steps = 19 00:20:04 [INFO] train episode 4449: reward = -47.44, steps = 38 00:20:04 [INFO] train episode 4450: reward = -55.26, steps = 38 00:20:05 [INFO] train episode 4451: reward = -34.22, steps = 34 00:20:05 [INFO] train episode 4452: reward = -43.67, steps = 26 00:20:05 [INFO] train episode 4453: reward = -41.00, steps = 26 00:20:05 [INFO] train episode 4454: reward = -42.18, steps = 26 00:20:05 [INFO] train episode 4455: reward = -33.70, steps = 23 00:20:05 [INFO] train episode 4456: reward = -50.11, steps = 27 00:20:06 [INFO] train episode 4457: reward = -58.32, steps = 32 00:20:06 [INFO] train episode 4458: reward = -39.84, steps = 20 00:20:06 [INFO] train episode 4459: reward = -42.46, steps = 30 00:20:06 [INFO] train episode 4460: reward = -44.69, steps = 22 00:20:07 [INFO] train episode 4461: reward = -51.86, steps = 24 00:20:07 [INFO] train episode 4462: reward = -46.52, steps = 24 00:20:07 [INFO] train episode 4463: reward = -59.66, steps = 27 00:20:07 [INFO] train episode 4464: reward = -50.28, steps = 20 00:20:07 [INFO] train episode 4465: reward = -37.10, steps = 21 00:20:07 [INFO] train episode 4466: reward = -28.89, steps = 28 00:20:08 [INFO] train episode 4467: reward = -68.41, steps = 40 00:20:08 [INFO] train episode 4468: reward = -60.01, steps = 29 00:20:08 [INFO] train episode 4469: reward = -48.47, steps = 24 00:20:08 [INFO] train episode 4470: reward = -45.45, steps = 21 00:20:08 [INFO] train episode 4471: reward = -45.85, steps = 20 00:20:09 [INFO] train episode 4472: reward = -54.12, steps = 29 00:20:09 [INFO] train episode 4473: reward = -35.62, steps = 20 00:20:09 [INFO] train episode 4474: reward = -45.81, steps = 26 00:20:09 [INFO] train episode 4475: reward = -39.40, steps = 21 00:20:09 [INFO] train episode 4476: reward = -56.11, steps = 24 00:20:09 [INFO] train episode 4477: reward = -34.14, steps = 29 00:20:10 [INFO] train episode 4478: reward = -50.26, steps = 35 00:20:10 [INFO] train episode 4479: reward = -37.94, steps = 28 00:20:10 [INFO] train episode 4480: reward = -38.87, steps = 28 00:20:10 [INFO] train episode 4481: reward = -35.83, steps = 20 00:20:10 [INFO] train episode 4482: reward = -39.20, steps = 24 00:20:11 [INFO] train episode 4483: reward = -45.46, steps = 23 00:20:11 [INFO] train episode 4484: reward = -41.42, steps = 21 00:20:11 [INFO] train episode 4485: reward = -42.08, steps = 31 00:20:11 [INFO] train episode 4486: reward = -45.33, steps = 24 00:20:11 [INFO] train episode 4487: reward = -44.70, steps = 26 00:20:11 [INFO] train episode 4488: reward = -52.32, steps = 40 00:20:12 [INFO] train episode 4489: reward = -45.90, steps = 31 00:20:12 [INFO] train episode 4490: reward = -27.53, steps = 25 00:20:12 [INFO] train episode 4491: reward = -52.09, steps = 30 00:20:12 [INFO] train episode 4492: reward = -55.66, steps = 21 00:20:12 [INFO] train episode 4493: reward = -63.30, steps = 37 00:20:13 [INFO] train episode 4494: reward = -37.84, steps = 21 00:20:13 [INFO] train episode 4495: reward = -44.41, steps = 42 00:20:13 [INFO] train episode 4496: reward = -35.60, steps = 32 00:20:13 [INFO] train episode 4497: reward = -21.30, steps = 34 00:20:14 [INFO] train episode 4498: reward = -51.97, steps = 22 00:20:14 [INFO] train episode 4499: reward = -43.93, steps = 35 00:20:14 [INFO] train episode 4500: reward = -31.65, steps = 22 00:20:14 [INFO] train episode 4501: reward = -50.39, steps = 23 00:20:14 [INFO] train episode 4502: reward = -44.56, steps = 20 00:20:14 [INFO] train episode 4503: reward = -35.55, steps = 26 00:20:15 [INFO] train episode 4504: reward = -30.01, steps = 19 00:20:15 [INFO] train episode 4505: reward = -40.08, steps = 30 00:20:15 [INFO] train episode 4506: reward = -41.05, steps = 19 00:20:15 [INFO] train episode 4507: reward = -48.27, steps = 20 00:20:15 [INFO] train episode 4508: reward = -39.14, steps = 23 00:20:15 [INFO] train episode 4509: reward = -28.63, steps = 19 00:20:16 [INFO] train episode 4510: reward = -47.54, steps = 22 00:20:16 [INFO] train episode 4511: reward = -37.20, steps = 26 00:20:16 [INFO] train episode 4512: reward = -48.96, steps = 30 00:20:16 [INFO] train episode 4513: reward = -52.30, steps = 23 00:20:16 [INFO] train episode 4514: reward = -37.69, steps = 20 00:20:16 [INFO] train episode 4515: reward = -35.48, steps = 24 00:20:17 [INFO] train episode 4516: reward = -41.64, steps = 19 00:20:17 [INFO] train episode 4517: reward = -73.30, steps = 49 00:20:17 [INFO] train episode 4518: reward = -67.98, steps = 24 00:20:17 [INFO] train episode 4519: reward = -32.12, steps = 20 00:20:17 [INFO] train episode 4520: reward = -36.66, steps = 21 00:20:18 [INFO] train episode 4521: reward = -50.30, steps = 20 00:20:18 [INFO] train episode 4522: reward = -30.65, steps = 40 00:20:18 [INFO] train episode 4523: reward = -30.47, steps = 35 00:20:18 [INFO] train episode 4524: reward = -41.51, steps = 16 00:20:18 [INFO] train episode 4525: reward = -30.36, steps = 24 00:20:19 [INFO] train episode 4526: reward = -37.04, steps = 41 00:20:19 [INFO] train episode 4527: reward = -36.69, steps = 37 00:20:19 [INFO] train episode 4528: reward = -53.16, steps = 24 00:20:19 [INFO] train episode 4529: reward = -52.96, steps = 27 00:20:19 [INFO] train episode 4530: reward = -49.43, steps = 41 00:20:20 [INFO] train episode 4531: reward = -36.14, steps = 21 00:20:20 [INFO] train episode 4532: reward = -33.78, steps = 22 00:20:20 [INFO] train episode 4533: reward = -46.81, steps = 26 00:20:20 [INFO] train episode 4534: reward = -47.84, steps = 24 00:20:21 [INFO] train episode 4535: reward = -53.56, steps = 19 00:20:21 [INFO] train episode 4536: reward = -57.31, steps = 31 00:20:21 [INFO] train episode 4537: reward = -54.13, steps = 38 00:20:21 [INFO] train episode 4538: reward = -58.48, steps = 35 00:20:21 [INFO] train episode 4539: reward = -34.27, steps = 36 00:20:22 [INFO] train episode 4540: reward = -50.47, steps = 33 00:20:22 [INFO] train episode 4541: reward = -45.67, steps = 21 00:20:22 [INFO] train episode 4542: reward = -45.33, steps = 26 00:20:22 [INFO] train episode 4543: reward = -74.99, steps = 18 00:20:22 [INFO] train episode 4544: reward = -44.86, steps = 25 00:20:22 [INFO] train episode 4545: reward = -39.74, steps = 21 00:20:23 [INFO] train episode 4546: reward = -51.43, steps = 33 00:20:23 [INFO] train episode 4547: reward = -55.50, steps = 34 00:20:23 [INFO] train episode 4548: reward = -27.50, steps = 23 00:20:23 [INFO] train episode 4549: reward = -46.47, steps = 26 00:20:23 [INFO] train episode 4550: reward = -37.89, steps = 23 00:20:24 [INFO] train episode 4551: reward = -46.71, steps = 31 00:20:24 [INFO] train episode 4552: reward = -29.15, steps = 19 00:20:24 [INFO] train episode 4553: reward = -44.07, steps = 35 00:20:24 [INFO] train episode 4554: reward = -43.79, steps = 21 00:20:24 [INFO] train episode 4555: reward = -50.53, steps = 21 00:20:24 [INFO] train episode 4556: reward = -60.15, steps = 23 00:20:25 [INFO] train episode 4557: reward = -51.91, steps = 26 00:20:25 [INFO] train episode 4558: reward = -39.23, steps = 36 00:20:25 [INFO] train episode 4559: reward = -41.80, steps = 25 00:20:25 [INFO] train episode 4560: reward = -49.98, steps = 28 00:20:25 [INFO] train episode 4561: reward = -25.13, steps = 28 00:20:26 [INFO] train episode 4562: reward = -48.09, steps = 20 00:20:26 [INFO] train episode 4563: reward = -45.64, steps = 28 00:20:26 [INFO] train episode 4564: reward = -38.11, steps = 22 00:20:26 [INFO] train episode 4565: reward = -57.94, steps = 28 00:20:26 [INFO] train episode 4566: reward = -39.32, steps = 27 00:20:27 [INFO] train episode 4567: reward = -47.51, steps = 37 00:20:27 [INFO] train episode 4568: reward = -37.08, steps = 39 00:20:27 [INFO] train episode 4569: reward = -35.30, steps = 23 00:20:27 [INFO] train episode 4570: reward = -47.28, steps = 30 00:20:27 [INFO] train episode 4571: reward = -38.69, steps = 21 00:20:28 [INFO] train episode 4572: reward = -45.52, steps = 21 00:20:28 [INFO] train episode 4573: reward = -61.92, steps = 43 00:20:28 [INFO] train episode 4574: reward = -45.33, steps = 30 00:20:28 [INFO] train episode 4575: reward = -55.81, steps = 28 00:20:28 [INFO] train episode 4576: reward = -32.44, steps = 26 00:20:29 [INFO] train episode 4577: reward = -36.97, steps = 20 00:20:29 [INFO] train episode 4578: reward = -30.94, steps = 28 00:20:29 [INFO] train episode 4579: reward = -38.97, steps = 36 00:20:29 [INFO] train episode 4580: reward = -43.02, steps = 30 00:20:29 [INFO] train episode 4581: reward = -49.43, steps = 18 00:20:29 [INFO] train episode 4582: reward = -50.44, steps = 20 00:20:30 [INFO] train episode 4583: reward = -37.08, steps = 35 00:20:30 [INFO] train episode 4584: reward = -44.14, steps = 21 00:20:30 [INFO] train episode 4585: reward = -52.98, steps = 26 00:20:30 [INFO] train episode 4586: reward = -50.64, steps = 25 00:20:30 [INFO] train episode 4587: reward = -42.24, steps = 27 00:20:30 [INFO] train episode 4588: reward = -38.38, steps = 20 00:20:31 [INFO] train episode 4589: reward = -54.78, steps = 26 00:20:31 [INFO] train episode 4590: reward = -43.67, steps = 21 00:20:31 [INFO] train episode 4591: reward = -37.84, steps = 24 00:20:31 [INFO] train episode 4592: reward = -43.84, steps = 21 00:20:31 [INFO] train episode 4593: reward = -61.11, steps = 43 00:20:32 [INFO] train episode 4594: reward = -40.54, steps = 21 00:20:32 [INFO] train episode 4595: reward = -31.61, steps = 22 00:20:32 [INFO] train episode 4596: reward = -40.80, steps = 21 00:20:32 [INFO] train episode 4597: reward = -47.03, steps = 21 00:20:32 [INFO] train episode 4598: reward = -36.27, steps = 34 00:20:33 [INFO] train episode 4599: reward = -43.07, steps = 22 00:20:33 [INFO] train episode 4600: reward = -38.65, steps = 42 00:20:33 [INFO] train episode 4601: reward = -36.11, steps = 21 00:20:33 [INFO] train episode 4602: reward = -45.80, steps = 25 00:20:34 [INFO] train episode 4603: reward = -46.54, steps = 23 00:20:34 [INFO] train episode 4604: reward = -52.43, steps = 31 00:20:35 [INFO] train episode 4605: reward = -50.01, steps = 22 00:20:35 [INFO] train episode 4606: reward = -66.81, steps = 32 00:20:35 [INFO] train episode 4607: reward = -49.54, steps = 21 00:20:36 [INFO] train episode 4608: reward = -43.68, steps = 38 00:20:36 [INFO] train episode 4609: reward = -40.37, steps = 20 00:20:36 [INFO] train episode 4610: reward = -40.42, steps = 19 00:20:36 [INFO] train episode 4611: reward = -40.20, steps = 35 00:20:36 [INFO] train episode 4612: reward = -52.57, steps = 18 00:20:37 [INFO] train episode 4613: reward = -32.30, steps = 42 00:20:37 [INFO] train episode 4614: reward = -43.18, steps = 20 00:20:37 [INFO] train episode 4615: reward = -47.89, steps = 24 00:20:37 [INFO] train episode 4616: reward = -56.40, steps = 27 00:20:38 [INFO] train episode 4617: reward = -41.96, steps = 28 00:20:38 [INFO] train episode 4618: reward = -67.46, steps = 33 00:20:38 [INFO] train episode 4619: reward = -33.66, steps = 23 00:20:38 [INFO] train episode 4620: reward = -54.55, steps = 30 00:20:39 [INFO] train episode 4621: reward = -44.82, steps = 25 00:20:39 [INFO] train episode 4622: reward = -40.99, steps = 21 00:20:39 [INFO] train episode 4623: reward = -38.54, steps = 22 00:20:39 [INFO] train episode 4624: reward = -59.76, steps = 40 00:20:40 [INFO] train episode 4625: reward = -53.77, steps = 27 00:20:40 [INFO] train episode 4626: reward = -38.16, steps = 35 00:20:40 [INFO] train episode 4627: reward = -34.83, steps = 31 00:20:40 [INFO] train episode 4628: reward = -46.85, steps = 26 00:20:40 [INFO] train episode 4629: reward = -36.09, steps = 20 00:20:41 [INFO] train episode 4630: reward = -53.83, steps = 38 00:20:41 [INFO] train episode 4631: reward = -34.08, steps = 24 00:20:41 [INFO] train episode 4632: reward = -44.02, steps = 29 00:20:42 [INFO] train episode 4633: reward = -34.15, steps = 41 00:20:42 [INFO] train episode 4634: reward = -35.75, steps = 19 00:20:42 [INFO] train episode 4635: reward = -49.26, steps = 21 00:20:42 [INFO] train episode 4636: reward = -52.71, steps = 20 00:20:42 [INFO] train episode 4637: reward = -32.19, steps = 21 00:20:43 [INFO] train episode 4638: reward = -40.43, steps = 27 00:20:43 [INFO] train episode 4639: reward = -48.30, steps = 37 00:20:43 [INFO] train episode 4640: reward = -36.76, steps = 21 00:20:43 [INFO] train episode 4641: reward = -62.97, steps = 30 00:20:43 [INFO] train episode 4642: reward = -25.79, steps = 20 00:20:44 [INFO] train episode 4643: reward = -42.03, steps = 21 00:20:44 [INFO] train episode 4644: reward = -44.96, steps = 28 00:20:44 [INFO] train episode 4645: reward = -32.26, steps = 47 00:20:45 [INFO] train episode 4646: reward = -53.57, steps = 47 00:20:45 [INFO] train episode 4647: reward = -31.98, steps = 23 00:20:45 [INFO] train episode 4648: reward = -46.14, steps = 19 00:20:45 [INFO] train episode 4649: reward = -37.65, steps = 20 00:20:45 [INFO] train episode 4650: reward = -42.50, steps = 22 00:20:46 [INFO] train episode 4651: reward = -44.79, steps = 27 00:20:46 [INFO] train episode 4652: reward = -42.71, steps = 25 00:20:46 [INFO] train episode 4653: reward = -45.43, steps = 28 00:20:46 [INFO] train episode 4654: reward = -19.55, steps = 36 00:20:47 [INFO] train episode 4655: reward = -42.55, steps = 26 00:20:47 [INFO] train episode 4656: reward = -33.12, steps = 25 00:20:47 [INFO] train episode 4657: reward = -39.41, steps = 38 00:20:47 [INFO] train episode 4658: reward = -35.45, steps = 22 00:20:48 [INFO] train episode 4659: reward = -39.55, steps = 54 00:20:48 [INFO] train episode 4660: reward = -33.84, steps = 28 00:20:48 [INFO] train episode 4661: reward = -66.89, steps = 33 00:20:49 [INFO] train episode 4662: reward = -37.02, steps = 20 00:20:49 [INFO] train episode 4663: reward = -46.43, steps = 23 00:20:49 [INFO] train episode 4664: reward = -41.15, steps = 28 00:20:49 [INFO] train episode 4665: reward = -78.86, steps = 40 00:20:49 [INFO] train episode 4666: reward = -37.92, steps = 24 00:20:50 [INFO] train episode 4667: reward = -32.60, steps = 20 00:20:50 [INFO] train episode 4668: reward = -47.06, steps = 28 00:20:50 [INFO] train episode 4669: reward = -34.01, steps = 31 00:20:50 [INFO] train episode 4670: reward = -44.97, steps = 19 00:20:50 [INFO] train episode 4671: reward = -26.43, steps = 23 00:20:51 [INFO] train episode 4672: reward = -41.35, steps = 28 00:20:51 [INFO] train episode 4673: reward = -56.71, steps = 50 00:20:52 [INFO] train episode 4674: reward = -24.51, steps = 31 00:20:52 [INFO] train episode 4675: reward = -36.85, steps = 38 00:20:52 [INFO] train episode 4676: reward = -47.28, steps = 28 00:20:52 [INFO] train episode 4677: reward = -33.49, steps = 24 00:20:53 [INFO] train episode 4678: reward = -42.05, steps = 39 00:20:53 [INFO] train episode 4679: reward = -38.09, steps = 30 00:20:53 [INFO] train episode 4680: reward = -35.31, steps = 20 00:20:53 [INFO] train episode 4681: reward = -58.18, steps = 31 00:20:54 [INFO] train episode 4682: reward = -30.51, steps = 29 00:20:54 [INFO] train episode 4683: reward = -60.44, steps = 42 00:20:54 [INFO] train episode 4684: reward = -37.66, steps = 22 00:20:54 [INFO] train episode 4685: reward = -34.93, steps = 24 00:20:54 [INFO] train episode 4686: reward = -60.30, steps = 37 00:20:55 [INFO] train episode 4687: reward = -57.26, steps = 38 00:20:55 [INFO] train episode 4688: reward = -31.82, steps = 40 00:20:55 [INFO] train episode 4689: reward = -40.19, steps = 24 00:20:55 [INFO] train episode 4690: reward = -46.51, steps = 27 00:20:56 [INFO] train episode 4691: reward = -50.52, steps = 21 00:20:56 [INFO] train episode 4692: reward = -45.88, steps = 34 00:20:56 [INFO] train episode 4693: reward = -36.95, steps = 21 00:20:56 [INFO] train episode 4694: reward = -39.38, steps = 42 00:20:57 [INFO] train episode 4695: reward = -50.12, steps = 24 00:20:57 [INFO] train episode 4696: reward = -57.41, steps = 42 00:20:57 [INFO] train episode 4697: reward = -43.33, steps = 20 00:20:58 [INFO] train episode 4698: reward = -41.75, steps = 33 00:20:58 [INFO] train episode 4699: reward = -49.30, steps = 39 00:20:58 [INFO] train episode 4700: reward = -34.47, steps = 26 00:20:58 [INFO] train episode 4701: reward = -44.33, steps = 27 00:20:58 [INFO] train episode 4702: reward = -36.15, steps = 27 00:20:59 [INFO] train episode 4703: reward = -39.92, steps = 29 00:20:59 [INFO] train episode 4704: reward = -27.88, steps = 20 00:20:59 [INFO] train episode 4705: reward = -46.77, steps = 20 00:20:59 [INFO] train episode 4706: reward = -54.00, steps = 28 00:20:59 [INFO] train episode 4707: reward = -59.57, steps = 38 00:20:59 [INFO] train episode 4708: reward = -32.10, steps = 21 00:21:00 [INFO] train episode 4709: reward = -43.81, steps = 36 00:21:00 [INFO] train episode 4710: reward = -51.62, steps = 23 00:21:00 [INFO] train episode 4711: reward = -35.84, steps = 29 00:21:00 [INFO] train episode 4712: reward = -44.05, steps = 22 00:21:00 [INFO] train episode 4713: reward = -42.41, steps = 21 00:21:01 [INFO] train episode 4714: reward = -27.45, steps = 38 00:21:01 [INFO] train episode 4715: reward = -44.85, steps = 29 00:21:01 [INFO] train episode 4716: reward = -81.06, steps = 35 00:21:01 [INFO] train episode 4717: reward = -39.72, steps = 24 00:21:01 [INFO] train episode 4718: reward = -39.86, steps = 27 00:21:02 [INFO] train episode 4719: reward = -40.68, steps = 19 00:21:02 [INFO] train episode 4720: reward = -58.28, steps = 32 00:21:02 [INFO] train episode 4721: reward = -39.84, steps = 23 00:21:02 [INFO] train episode 4722: reward = -35.88, steps = 36 00:21:02 [INFO] train episode 4723: reward = -28.82, steps = 21 00:21:03 [INFO] train episode 4724: reward = -28.81, steps = 31 00:21:03 [INFO] train episode 4725: reward = -46.14, steps = 31 00:21:03 [INFO] train episode 4726: reward = -32.48, steps = 34 00:21:03 [INFO] train episode 4727: reward = -58.37, steps = 24 00:21:04 [INFO] train episode 4728: reward = -62.58, steps = 34 00:21:04 [INFO] train episode 4729: reward = -36.75, steps = 24 00:21:04 [INFO] train episode 4730: reward = -41.89, steps = 23 00:21:04 [INFO] train episode 4731: reward = -41.61, steps = 20 00:21:04 [INFO] train episode 4732: reward = -40.81, steps = 21 00:21:05 [INFO] train episode 4733: reward = -58.99, steps = 36 00:21:05 [INFO] train episode 4734: reward = -35.14, steps = 27 00:21:05 [INFO] train episode 4735: reward = -38.45, steps = 20 00:21:05 [INFO] train episode 4736: reward = -38.99, steps = 38 00:21:05 [INFO] train episode 4737: reward = -52.55, steps = 24 00:21:06 [INFO] train episode 4738: reward = -46.21, steps = 21 00:21:06 [INFO] train episode 4739: reward = -50.10, steps = 29 00:21:06 [INFO] train episode 4740: reward = -38.98, steps = 20 00:21:06 [INFO] train episode 4741: reward = -32.24, steps = 25 00:21:06 [INFO] train episode 4742: reward = -49.31, steps = 20 00:21:07 [INFO] train episode 4743: reward = -33.42, steps = 22 00:21:07 [INFO] train episode 4744: reward = -38.61, steps = 20 00:21:07 [INFO] train episode 4745: reward = -79.36, steps = 24 00:21:07 [INFO] train episode 4746: reward = -48.51, steps = 28 00:21:07 [INFO] train episode 4747: reward = -47.89, steps = 32 00:21:08 [INFO] train episode 4748: reward = -43.99, steps = 35 00:21:08 [INFO] train episode 4749: reward = -39.90, steps = 28 00:21:08 [INFO] train episode 4750: reward = -51.43, steps = 20 00:21:08 [INFO] train episode 4751: reward = -50.11, steps = 33 00:21:08 [INFO] train episode 4752: reward = -44.44, steps = 43 00:21:09 [INFO] train episode 4753: reward = -44.12, steps = 27 00:21:09 [INFO] train episode 4754: reward = -35.94, steps = 22 00:21:09 [INFO] train episode 4755: reward = -50.88, steps = 20 00:21:09 [INFO] train episode 4756: reward = -25.50, steps = 22 00:21:09 [INFO] train episode 4757: reward = -38.36, steps = 21 00:21:09 [INFO] train episode 4758: reward = -37.67, steps = 36 00:21:10 [INFO] train episode 4759: reward = -42.77, steps = 39 00:21:10 [INFO] train episode 4760: reward = -44.66, steps = 34 00:21:10 [INFO] train episode 4761: reward = -30.72, steps = 21 00:21:10 [INFO] train episode 4762: reward = -44.11, steps = 29 00:21:10 [INFO] train episode 4763: reward = -48.02, steps = 25 00:21:11 [INFO] train episode 4764: reward = -47.22, steps = 26 00:21:11 [INFO] train episode 4765: reward = -49.14, steps = 26 00:21:11 [INFO] train episode 4766: reward = -37.84, steps = 20 00:21:11 [INFO] train episode 4767: reward = -67.26, steps = 32 00:21:11 [INFO] train episode 4768: reward = -20.86, steps = 39 00:21:12 [INFO] train episode 4769: reward = -37.54, steps = 32 00:21:12 [INFO] train episode 4770: reward = -69.41, steps = 27 00:21:12 [INFO] train episode 4771: reward = -37.99, steps = 20 00:21:12 [INFO] train episode 4772: reward = -42.39, steps = 21 00:21:12 [INFO] train episode 4773: reward = -37.67, steps = 21 00:21:12 [INFO] train episode 4774: reward = -37.59, steps = 27 00:21:13 [INFO] train episode 4775: reward = -28.66, steps = 20 00:21:13 [INFO] train episode 4776: reward = -39.88, steps = 20 00:21:13 [INFO] train episode 4777: reward = -50.13, steps = 21 00:21:13 [INFO] train episode 4778: reward = -30.58, steps = 30 00:21:13 [INFO] train episode 4779: reward = -40.46, steps = 20 00:21:13 [INFO] train episode 4780: reward = -42.07, steps = 23 00:21:14 [INFO] train episode 4781: reward = -39.92, steps = 22 00:21:14 [INFO] train episode 4782: reward = -29.52, steps = 36 00:21:14 [INFO] train episode 4783: reward = -62.77, steps = 14 00:21:14 [INFO] train episode 4784: reward = -44.85, steps = 27 00:21:14 [INFO] train episode 4785: reward = -57.95, steps = 35 00:21:15 [INFO] train episode 4786: reward = -53.51, steps = 37 00:21:15 [INFO] train episode 4787: reward = -50.73, steps = 19 00:21:15 [INFO] train episode 4788: reward = -44.89, steps = 19 00:21:15 [INFO] train episode 4789: reward = -53.59, steps = 21 00:21:15 [INFO] train episode 4790: reward = -39.32, steps = 32 00:21:16 [INFO] train episode 4791: reward = -62.17, steps = 41 00:21:16 [INFO] train episode 4792: reward = -57.73, steps = 18 00:21:16 [INFO] train episode 4793: reward = -43.51, steps = 30 00:21:16 [INFO] train episode 4794: reward = -45.44, steps = 34 00:21:16 [INFO] train episode 4795: reward = -49.01, steps = 24 00:21:16 [INFO] train episode 4796: reward = -36.80, steps = 30 00:21:17 [INFO] train episode 4797: reward = -37.64, steps = 39 00:21:17 [INFO] train episode 4798: reward = -44.61, steps = 20 00:21:17 [INFO] train episode 4799: reward = -42.43, steps = 21 00:21:17 [INFO] train episode 4800: reward = -35.57, steps = 20 00:21:17 [INFO] train episode 4801: reward = -38.50, steps = 29 00:21:18 [INFO] train episode 4802: reward = -32.04, steps = 19 00:21:18 [INFO] train episode 4803: reward = -42.21, steps = 31 00:21:18 [INFO] train episode 4804: reward = -49.37, steps = 54 00:21:18 [INFO] train episode 4805: reward = -40.46, steps = 24 00:21:18 [INFO] train episode 4806: reward = -34.18, steps = 33 00:21:19 [INFO] train episode 4807: reward = -54.50, steps = 26 00:21:19 [INFO] train episode 4808: reward = -52.75, steps = 41 00:21:19 [INFO] train episode 4809: reward = -27.96, steps = 24 00:21:19 [INFO] train episode 4810: reward = -42.59, steps = 20 00:21:19 [INFO] train episode 4811: reward = -45.61, steps = 31 00:21:20 [INFO] train episode 4812: reward = -50.41, steps = 25 00:21:20 [INFO] train episode 4813: reward = -39.32, steps = 25 00:21:20 [INFO] train episode 4814: reward = -37.88, steps = 24 00:21:20 [INFO] train episode 4815: reward = -25.06, steps = 29 00:21:21 [INFO] train episode 4816: reward = -41.22, steps = 23 00:21:21 [INFO] train episode 4817: reward = -25.16, steps = 19 00:21:21 [INFO] train episode 4818: reward = -25.54, steps = 23 00:21:21 [INFO] train episode 4819: reward = -39.00, steps = 23 00:21:21 [INFO] train episode 4820: reward = -35.98, steps = 30 00:21:22 [INFO] train episode 4821: reward = -41.02, steps = 40 00:21:22 [INFO] train episode 4822: reward = -24.17, steps = 20 00:21:22 [INFO] train episode 4823: reward = -50.69, steps = 22 00:21:22 [INFO] train episode 4824: reward = -46.66, steps = 20 00:21:22 [INFO] train episode 4825: reward = -22.32, steps = 33 00:21:22 [INFO] train episode 4826: reward = -34.71, steps = 32 00:21:23 [INFO] train episode 4827: reward = -33.95, steps = 26 00:21:23 [INFO] train episode 4828: reward = -39.52, steps = 36 00:21:23 [INFO] train episode 4829: reward = -39.67, steps = 29 00:21:23 [INFO] train episode 4830: reward = -62.94, steps = 41 00:21:23 [INFO] train episode 4831: reward = -37.97, steps = 28 00:21:24 [INFO] train episode 4832: reward = -45.28, steps = 37 00:21:24 [INFO] train episode 4833: reward = -38.79, steps = 27 00:21:24 [INFO] train episode 4834: reward = -35.29, steps = 21 00:21:24 [INFO] train episode 4835: reward = -57.69, steps = 29 00:21:24 [INFO] train episode 4836: reward = -41.45, steps = 19 00:21:25 [INFO] train episode 4837: reward = -31.07, steps = 22 00:21:25 [INFO] train episode 4838: reward = -47.94, steps = 28 00:21:25 [INFO] train episode 4839: reward = -60.11, steps = 26 00:21:25 [INFO] train episode 4840: reward = -34.42, steps = 41 00:21:25 [INFO] train episode 4841: reward = -58.18, steps = 17 00:21:26 [INFO] train episode 4842: reward = -36.51, steps = 29 00:21:26 [INFO] train episode 4843: reward = -41.96, steps = 36 00:21:26 [INFO] train episode 4844: reward = -54.43, steps = 20 00:21:26 [INFO] train episode 4845: reward = -31.75, steps = 23 00:21:26 [INFO] train episode 4846: reward = -39.25, steps = 36 00:21:27 [INFO] train episode 4847: reward = -25.72, steps = 35 00:21:27 [INFO] train episode 4848: reward = -33.93, steps = 27 00:21:27 [INFO] train episode 4849: reward = -41.05, steps = 20 00:21:27 [INFO] train episode 4850: reward = -30.08, steps = 25 00:21:27 [INFO] train episode 4851: reward = -55.29, steps = 22 00:21:27 [INFO] train episode 4852: reward = -34.58, steps = 20 00:21:28 [INFO] train episode 4853: reward = -35.17, steps = 30 00:21:28 [INFO] train episode 4854: reward = -36.21, steps = 20 00:21:28 [INFO] train episode 4855: reward = -56.59, steps = 39 00:21:28 [INFO] train episode 4856: reward = -35.43, steps = 21 00:21:28 [INFO] train episode 4857: reward = -51.49, steps = 28 00:21:29 [INFO] train episode 4858: reward = -45.66, steps = 39 00:21:29 [INFO] train episode 4859: reward = -38.67, steps = 29 00:21:29 [INFO] train episode 4860: reward = -51.19, steps = 25 00:21:29 [INFO] train episode 4861: reward = -34.73, steps = 21 00:21:29 [INFO] train episode 4862: reward = -31.26, steps = 20 00:21:29 [INFO] train episode 4863: reward = -35.19, steps = 22 00:21:30 [INFO] train episode 4864: reward = -54.40, steps = 20 00:21:30 [INFO] train episode 4865: reward = -31.36, steps = 35 00:21:30 [INFO] train episode 4866: reward = -27.87, steps = 27 00:21:30 [INFO] train episode 4867: reward = -37.65, steps = 24 00:21:30 [INFO] train episode 4868: reward = -35.22, steps = 29 00:21:31 [INFO] train episode 4869: reward = -59.10, steps = 20 00:21:31 [INFO] train episode 4870: reward = -24.96, steps = 33 00:21:31 [INFO] train episode 4871: reward = -36.68, steps = 24 00:21:31 [INFO] train episode 4872: reward = -58.28, steps = 22 00:21:31 [INFO] train episode 4873: reward = -42.56, steps = 21 00:21:31 [INFO] train episode 4874: reward = -41.27, steps = 17 00:21:32 [INFO] train episode 4875: reward = -46.04, steps = 29 00:21:32 [INFO] train episode 4876: reward = -33.31, steps = 26 00:21:32 [INFO] train episode 4877: reward = -48.85, steps = 23 00:21:32 [INFO] train episode 4878: reward = -41.73, steps = 34 00:21:32 [INFO] train episode 4879: reward = -37.65, steps = 34 00:21:33 [INFO] train episode 4880: reward = -49.99, steps = 35 00:21:33 [INFO] train episode 4881: reward = -38.91, steps = 22 00:21:33 [INFO] train episode 4882: reward = -49.36, steps = 21 00:21:33 [INFO] train episode 4883: reward = -46.31, steps = 28 00:21:33 [INFO] train episode 4884: reward = -36.70, steps = 28 00:21:33 [INFO] train episode 4885: reward = -29.18, steps = 19 00:21:34 [INFO] train episode 4886: reward = -26.67, steps = 26 00:21:34 [INFO] train episode 4887: reward = -44.04, steps = 20 00:21:34 [INFO] train episode 4888: reward = -56.96, steps = 46 00:21:35 [INFO] train episode 4889: reward = -57.07, steps = 33 00:21:35 [INFO] train episode 4890: reward = -27.12, steps = 20 00:21:35 [INFO] train episode 4891: reward = -45.95, steps = 29 00:21:35 [INFO] train episode 4892: reward = -43.59, steps = 29 00:21:35 [INFO] train episode 4893: reward = -34.38, steps = 27 00:21:36 [INFO] train episode 4894: reward = -44.58, steps = 38 00:21:36 [INFO] train episode 4895: reward = -53.71, steps = 36 00:21:36 [INFO] train episode 4896: reward = -46.03, steps = 34 00:21:36 [INFO] train episode 4897: reward = -55.22, steps = 33 00:21:36 [INFO] train episode 4898: reward = -40.15, steps = 25 00:21:37 [INFO] train episode 4899: reward = -39.98, steps = 32 00:21:37 [INFO] train episode 4900: reward = -51.30, steps = 37 00:21:37 [INFO] train episode 4901: reward = -35.61, steps = 21 00:21:37 [INFO] train episode 4902: reward = -41.43, steps = 23 00:21:37 [INFO] train episode 4903: reward = -33.12, steps = 32 00:21:38 [INFO] train episode 4904: reward = -33.13, steps = 22 00:21:38 [INFO] train episode 4905: reward = -35.07, steps = 19 00:21:38 [INFO] train episode 4906: reward = -44.36, steps = 32 00:21:38 [INFO] train episode 4907: reward = -48.80, steps = 28 00:21:38 [INFO] train episode 4908: reward = -48.32, steps = 34 00:21:38 [INFO] train episode 4909: reward = -42.98, steps = 18 00:21:39 [INFO] train episode 4910: reward = -43.05, steps = 28 00:21:39 [INFO] train episode 4911: reward = -44.41, steps = 39 00:21:39 [INFO] train episode 4912: reward = -36.74, steps = 20 00:21:39 [INFO] train episode 4913: reward = -46.60, steps = 22 00:21:39 [INFO] train episode 4914: reward = -40.17, steps = 19 00:21:40 [INFO] train episode 4915: reward = -39.19, steps = 29 00:21:40 [INFO] train episode 4916: reward = -29.42, steps = 20 00:21:40 [INFO] train episode 4917: reward = -51.65, steps = 26 00:21:40 [INFO] train episode 4918: reward = -41.10, steps = 34 00:21:40 [INFO] train episode 4919: reward = -55.04, steps = 36 00:21:41 [INFO] train episode 4920: reward = -42.91, steps = 21 00:21:41 [INFO] train episode 4921: reward = -63.15, steps = 32 00:21:41 [INFO] train episode 4922: reward = -36.64, steps = 29 00:21:41 [INFO] train episode 4923: reward = -33.64, steps = 27 00:21:41 [INFO] train episode 4924: reward = -42.45, steps = 20 00:21:42 [INFO] train episode 4925: reward = -39.87, steps = 31 00:21:42 [INFO] train episode 4926: reward = -45.76, steps = 37 00:21:42 [INFO] train episode 4927: reward = -37.32, steps = 30 00:21:42 [INFO] train episode 4928: reward = -44.10, steps = 27 00:21:42 [INFO] train episode 4929: reward = -53.98, steps = 21 00:21:42 [INFO] train episode 4930: reward = -35.27, steps = 21 00:21:43 [INFO] train episode 4931: reward = -33.63, steps = 22 00:21:43 [INFO] train episode 4932: reward = -22.34, steps = 33 00:21:43 [INFO] train episode 4933: reward = -34.89, steps = 20 00:21:43 [INFO] train episode 4934: reward = -43.44, steps = 23 00:21:43 [INFO] train episode 4935: reward = -48.14, steps = 23 00:21:43 [INFO] train episode 4936: reward = -48.20, steps = 21 00:21:44 [INFO] train episode 4937: reward = -37.67, steps = 34 00:21:44 [INFO] train episode 4938: reward = -29.68, steps = 30 00:21:44 [INFO] train episode 4939: reward = -64.15, steps = 35 00:21:44 [INFO] train episode 4940: reward = -34.55, steps = 27 00:21:44 [INFO] train episode 4941: reward = -39.05, steps = 27 00:21:45 [INFO] train episode 4942: reward = -56.18, steps = 39 00:21:45 [INFO] train episode 4943: reward = -38.21, steps = 22 00:21:45 [INFO] train episode 4944: reward = -39.01, steps = 42 00:21:45 [INFO] train episode 4945: reward = -44.90, steps = 25 00:21:46 [INFO] train episode 4946: reward = -44.99, steps = 32 00:21:46 [INFO] train episode 4947: reward = -40.74, steps = 19 00:21:46 [INFO] train episode 4948: reward = -47.39, steps = 24 00:21:46 [INFO] train episode 4949: reward = -51.81, steps = 38 00:21:46 [INFO] train episode 4950: reward = -44.90, steps = 32 00:21:46 [INFO] train episode 4951: reward = -43.57, steps = 20 00:21:47 [INFO] train episode 4952: reward = -40.43, steps = 21 00:21:47 [INFO] train episode 4953: reward = -37.77, steps = 32 00:21:47 [INFO] train episode 4954: reward = -44.41, steps = 31 00:21:47 [INFO] train episode 4955: reward = -28.40, steps = 20 00:21:48 [INFO] train episode 4956: reward = -50.42, steps = 34 00:21:48 [INFO] train episode 4957: reward = -41.17, steps = 21 00:21:48 [INFO] train episode 4958: reward = -38.15, steps = 25 00:21:48 [INFO] train episode 4959: reward = -46.68, steps = 38 00:21:48 [INFO] train episode 4960: reward = -38.39, steps = 21 00:21:49 [INFO] train episode 4961: reward = -53.46, steps = 35 00:21:49 [INFO] train episode 4962: reward = -29.64, steps = 52 00:21:49 [INFO] train episode 4963: reward = -60.12, steps = 41 00:21:50 [INFO] train episode 4964: reward = -43.97, steps = 30 00:21:50 [INFO] train episode 4965: reward = -36.18, steps = 27 00:21:50 [INFO] train episode 4966: reward = -41.70, steps = 28 00:21:50 [INFO] train episode 4967: reward = -37.43, steps = 17 00:21:50 [INFO] train episode 4968: reward = -34.03, steps = 20 00:21:50 [INFO] train episode 4969: reward = -27.02, steps = 31 00:21:51 [INFO] train episode 4970: reward = -54.80, steps = 44 00:21:51 [INFO] train episode 4971: reward = -73.84, steps = 43 00:21:51 [INFO] train episode 4972: reward = -32.43, steps = 21 00:21:51 [INFO] train episode 4973: reward = -36.34, steps = 30 00:21:51 [INFO] train episode 4974: reward = -46.56, steps = 19 00:21:52 [INFO] train episode 4975: reward = -49.94, steps = 41 00:21:52 [INFO] train episode 4976: reward = -42.17, steps = 32 00:21:52 [INFO] train episode 4977: reward = -58.24, steps = 39 00:21:52 [INFO] train episode 4978: reward = -42.81, steps = 25 00:21:53 [INFO] train episode 4979: reward = -44.49, steps = 24 00:21:53 [INFO] train episode 4980: reward = -35.94, steps = 28 00:21:53 [INFO] train episode 4981: reward = -38.29, steps = 20 00:21:53 [INFO] train episode 4982: reward = -37.08, steps = 30 00:21:53 [INFO] train episode 4983: reward = -46.57, steps = 29 00:21:54 [INFO] train episode 4984: reward = -24.81, steps = 32 00:21:54 [INFO] train episode 4985: reward = -35.22, steps = 21 00:21:54 [INFO] train episode 4986: reward = -30.26, steps = 31 00:21:54 [INFO] train episode 4987: reward = -45.04, steps = 36 00:21:54 [INFO] train episode 4988: reward = -58.04, steps = 40 00:21:55 [INFO] train episode 4989: reward = -56.29, steps = 21 00:21:55 [INFO] train episode 4990: reward = -28.31, steps = 30 00:21:55 [INFO] train episode 4991: reward = -33.56, steps = 27 00:21:55 [INFO] train episode 4992: reward = -39.85, steps = 34 00:21:55 [INFO] train episode 4993: reward = -40.06, steps = 24 00:21:56 [INFO] train episode 4994: reward = -36.55, steps = 21 00:21:56 [INFO] train episode 4995: reward = -49.87, steps = 25 00:21:56 [INFO] train episode 4996: reward = -39.17, steps = 19 00:21:56 [INFO] train episode 4997: reward = -39.94, steps = 32 00:21:56 [INFO] train episode 4998: reward = -34.75, steps = 20 00:21:56 [INFO] train episode 4999: reward = -58.97, steps = 19 00:21:57 [INFO] train episode 5000: reward = -58.44, steps = 44 00:21:57 [INFO] train episode 5001: reward = -39.68, steps = 21 00:21:57 [INFO] train episode 5002: reward = -28.54, steps = 34 00:21:57 [INFO] train episode 5003: reward = -30.89, steps = 20 00:21:57 [INFO] train episode 5004: reward = -41.09, steps = 20 00:21:58 [INFO] train episode 5005: reward = -53.85, steps = 32 00:21:58 [INFO] train episode 5006: reward = -40.74, steps = 26 00:21:58 [INFO] train episode 5007: reward = -27.89, steps = 29 00:21:58 [INFO] train episode 5008: reward = -37.05, steps = 27 00:21:58 [INFO] train episode 5009: reward = -33.08, steps = 31 00:21:58 [INFO] train episode 5010: reward = -32.65, steps = 21 00:21:59 [INFO] train episode 5011: reward = -33.51, steps = 33 00:21:59 [INFO] train episode 5012: reward = -44.93, steps = 29 00:21:59 [INFO] train episode 5013: reward = -44.12, steps = 24 00:21:59 [INFO] train episode 5014: reward = -39.06, steps = 23 00:22:00 [INFO] train episode 5015: reward = -35.36, steps = 35 00:22:00 [INFO] train episode 5016: reward = -53.68, steps = 37 00:22:00 [INFO] train episode 5017: reward = -36.37, steps = 27 00:22:00 [INFO] train episode 5018: reward = -53.86, steps = 28 00:22:00 [INFO] train episode 5019: reward = -37.01, steps = 22 00:22:00 [INFO] train episode 5020: reward = -58.16, steps = 26 00:22:01 [INFO] train episode 5021: reward = -46.04, steps = 41 00:22:01 [INFO] train episode 5022: reward = -45.60, steps = 32 00:22:01 [INFO] train episode 5023: reward = -56.42, steps = 36 00:22:02 [INFO] train episode 5024: reward = -46.46, steps = 39 00:22:02 [INFO] train episode 5025: reward = -44.94, steps = 45 00:22:02 [INFO] train episode 5026: reward = -22.89, steps = 31 00:22:02 [INFO] train episode 5027: reward = -51.70, steps = 30 00:22:03 [INFO] train episode 5028: reward = -38.65, steps = 25 00:22:03 [INFO] train episode 5029: reward = -53.61, steps = 20 00:22:03 [INFO] train episode 5030: reward = -38.87, steps = 23 00:22:03 [INFO] train episode 5031: reward = -50.53, steps = 20 00:22:03 [INFO] train episode 5032: reward = -40.42, steps = 21 00:22:03 [INFO] train episode 5033: reward = -61.31, steps = 28 00:22:04 [INFO] train episode 5034: reward = -44.43, steps = 31 00:22:04 [INFO] train episode 5035: reward = -47.17, steps = 39 00:22:04 [INFO] train episode 5036: reward = -65.31, steps = 45 00:22:04 [INFO] train episode 5037: reward = -61.02, steps = 36 00:22:05 [INFO] train episode 5038: reward = -25.96, steps = 26 00:22:05 [INFO] train episode 5039: reward = -30.97, steps = 20 00:22:05 [INFO] train episode 5040: reward = -44.54, steps = 23 00:22:05 [INFO] train episode 5041: reward = -32.41, steps = 21 00:22:05 [INFO] train episode 5042: reward = -68.19, steps = 33 00:22:05 [INFO] train episode 5043: reward = -47.97, steps = 22 00:22:06 [INFO] train episode 5044: reward = -64.89, steps = 45 00:22:06 [INFO] train episode 5045: reward = -33.80, steps = 35 00:22:06 [INFO] train episode 5046: reward = -29.17, steps = 27 00:22:06 [INFO] train episode 5047: reward = -45.41, steps = 20 00:22:07 [INFO] train episode 5048: reward = -42.67, steps = 34 00:22:07 [INFO] train episode 5049: reward = -39.34, steps = 26 00:22:07 [INFO] train episode 5050: reward = -38.21, steps = 20 00:22:07 [INFO] train episode 5051: reward = -38.38, steps = 32 00:22:07 [INFO] train episode 5052: reward = -47.00, steps = 33 00:22:08 [INFO] train episode 5053: reward = -25.83, steps = 37 00:22:08 [INFO] train episode 5054: reward = -40.67, steps = 29 00:22:08 [INFO] train episode 5055: reward = -20.38, steps = 26 00:22:08 [INFO] train episode 5056: reward = -61.03, steps = 51 00:22:08 [INFO] train episode 5057: reward = -44.60, steps = 31 00:22:09 [INFO] train episode 5058: reward = -43.02, steps = 33 00:22:09 [INFO] train episode 5059: reward = -44.40, steps = 28 00:22:09 [INFO] train episode 5060: reward = -29.68, steps = 33 00:22:09 [INFO] train episode 5061: reward = -40.31, steps = 19 00:22:09 [INFO] train episode 5062: reward = -45.18, steps = 41 00:22:10 [INFO] train episode 5063: reward = -37.92, steps = 24 00:22:10 [INFO] train episode 5064: reward = -42.94, steps = 38 00:22:10 [INFO] train episode 5065: reward = -45.09, steps = 21 00:22:10 [INFO] train episode 5066: reward = -45.85, steps = 24 00:22:10 [INFO] train episode 5067: reward = -44.52, steps = 34 00:22:11 [INFO] train episode 5068: reward = -33.60, steps = 36 00:22:11 [INFO] train episode 5069: reward = -39.04, steps = 28 00:22:11 [INFO] train episode 5070: reward = -28.17, steps = 30 00:22:11 [INFO] train episode 5071: reward = -42.07, steps = 35 00:22:12 [INFO] train episode 5072: reward = -32.24, steps = 24 00:22:12 [INFO] train episode 5073: reward = -49.51, steps = 26 00:22:12 [INFO] train episode 5074: reward = -37.91, steps = 30 00:22:12 [INFO] train episode 5075: reward = -39.62, steps = 20 00:22:12 [INFO] train episode 5076: reward = -40.13, steps = 36 00:22:12 [INFO] train episode 5077: reward = -37.94, steps = 35 00:22:13 [INFO] train episode 5078: reward = -45.58, steps = 36 00:22:13 [INFO] train episode 5079: reward = -43.01, steps = 20 00:22:13 [INFO] train episode 5080: reward = -60.41, steps = 36 00:22:13 [INFO] train episode 5081: reward = -56.12, steps = 32 00:22:14 [INFO] train episode 5082: reward = -35.27, steps = 37 00:22:14 [INFO] train episode 5083: reward = -35.92, steps = 24 00:22:14 [INFO] train episode 5084: reward = -50.70, steps = 35 00:22:14 [INFO] train episode 5085: reward = -41.22, steps = 26 00:22:14 [INFO] train episode 5086: reward = -31.44, steps = 35 00:22:15 [INFO] train episode 5087: reward = -34.19, steps = 20 00:22:15 [INFO] train episode 5088: reward = -34.16, steps = 21 00:22:15 [INFO] train episode 5089: reward = -31.98, steps = 27 00:22:15 [INFO] train episode 5090: reward = -38.25, steps = 24 00:22:15 [INFO] train episode 5091: reward = -57.82, steps = 29 00:22:16 [INFO] train episode 5092: reward = -32.40, steps = 22 00:22:16 [INFO] train episode 5093: reward = -75.52, steps = 47 00:22:16 [INFO] train episode 5094: reward = -26.17, steps = 34 00:22:16 [INFO] train episode 5095: reward = -42.86, steps = 26 00:22:17 [INFO] train episode 5096: reward = -48.50, steps = 32 00:22:17 [INFO] train episode 5097: reward = -34.85, steps = 21 00:22:17 [INFO] train episode 5098: reward = -39.21, steps = 36 00:22:17 [INFO] train episode 5099: reward = -33.75, steps = 21 00:22:17 [INFO] train episode 5100: reward = -39.15, steps = 29 00:22:17 [INFO] train episode 5101: reward = -32.15, steps = 26 00:22:18 [INFO] train episode 5102: reward = -71.68, steps = 35 00:22:18 [INFO] train episode 5103: reward = -59.41, steps = 31 00:22:18 [INFO] train episode 5104: reward = -43.08, steps = 21 00:22:18 [INFO] train episode 5105: reward = -62.05, steps = 41 00:22:19 [INFO] train episode 5106: reward = -65.36, steps = 38 00:22:19 [INFO] train episode 5107: reward = -39.47, steps = 40 00:22:19 [INFO] train episode 5108: reward = -29.64, steps = 25 00:22:19 [INFO] train episode 5109: reward = -37.10, steps = 21 00:22:20 [INFO] train episode 5110: reward = -36.09, steps = 44 00:22:20 [INFO] train episode 5111: reward = -46.40, steps = 29 00:22:20 [INFO] train episode 5112: reward = -42.83, steps = 27 00:22:20 [INFO] train episode 5113: reward = -53.13, steps = 24 00:22:20 [INFO] train episode 5114: reward = -44.34, steps = 21 00:22:20 [INFO] train episode 5115: reward = -42.42, steps = 19 00:22:21 [INFO] train episode 5116: reward = -39.87, steps = 35 00:22:21 [INFO] train episode 5117: reward = -36.04, steps = 28 00:22:21 [INFO] train episode 5118: reward = -37.79, steps = 33 00:22:21 [INFO] train episode 5119: reward = -19.98, steps = 21 00:22:21 [INFO] train episode 5120: reward = -50.00, steps = 34 00:22:22 [INFO] train episode 5121: reward = -35.93, steps = 22 00:22:22 [INFO] train episode 5122: reward = -33.02, steps = 21 00:22:22 [INFO] train episode 5123: reward = -43.46, steps = 30 00:22:22 [INFO] train episode 5124: reward = -34.65, steps = 20 00:22:22 [INFO] train episode 5125: reward = -38.30, steps = 27 00:22:22 [INFO] train episode 5126: reward = -35.82, steps = 22 00:22:23 [INFO] train episode 5127: reward = -32.36, steps = 25 00:22:23 [INFO] train episode 5128: reward = -61.38, steps = 46 00:22:23 [INFO] train episode 5129: reward = -36.43, steps = 21 00:22:23 [INFO] train episode 5130: reward = -35.08, steps = 25 00:22:23 [INFO] train episode 5131: reward = -51.22, steps = 24 00:22:23 [INFO] train episode 5132: reward = -33.82, steps = 22 00:22:24 [INFO] train episode 5133: reward = -35.70, steps = 22 00:22:24 [INFO] train episode 5134: reward = -28.14, steps = 31 00:22:24 [INFO] train episode 5135: reward = -39.42, steps = 34 00:22:24 [INFO] train episode 5136: reward = -33.44, steps = 24 00:22:24 [INFO] train episode 5137: reward = -64.60, steps = 17 00:22:25 [INFO] train episode 5138: reward = -39.27, steps = 31 00:22:25 [INFO] train episode 5139: reward = -29.56, steps = 24 00:22:25 [INFO] train episode 5140: reward = -32.14, steps = 22 00:22:25 [INFO] train episode 5141: reward = -28.72, steps = 41 00:22:25 [INFO] train episode 5142: reward = -35.47, steps = 22 00:22:26 [INFO] train episode 5143: reward = -39.83, steps = 37 00:22:26 [INFO] train episode 5144: reward = -30.76, steps = 22 00:22:26 [INFO] train episode 5145: reward = -38.29, steps = 20 00:22:26 [INFO] train episode 5146: reward = -57.46, steps = 17 00:22:26 [INFO] train episode 5147: reward = -29.36, steps = 37 00:22:27 [INFO] train episode 5148: reward = -28.49, steps = 31 00:22:27 [INFO] train episode 5149: reward = -36.83, steps = 21 00:22:27 [INFO] train episode 5150: reward = -35.14, steps = 21 00:22:27 [INFO] train episode 5151: reward = -67.83, steps = 34 00:22:27 [INFO] train episode 5152: reward = -46.28, steps = 28 00:22:28 [INFO] train episode 5153: reward = -43.28, steps = 47 00:22:28 [INFO] train episode 5154: reward = -47.29, steps = 41 00:22:28 [INFO] train episode 5155: reward = -41.26, steps = 43 00:22:29 [INFO] train episode 5156: reward = -41.33, steps = 20 00:22:29 [INFO] train episode 5157: reward = -42.53, steps = 37 00:22:29 [INFO] train episode 5158: reward = -34.98, steps = 34 00:22:29 [INFO] train episode 5159: reward = -42.77, steps = 28 00:22:30 [INFO] train episode 5160: reward = -31.52, steps = 39 00:22:30 [INFO] train episode 5161: reward = -33.72, steps = 36 00:22:30 [INFO] train episode 5162: reward = -42.60, steps = 26 00:22:30 [INFO] train episode 5163: reward = -64.68, steps = 45 00:22:31 [INFO] train episode 5164: reward = -26.26, steps = 43 00:22:31 [INFO] train episode 5165: reward = -37.29, steps = 25 00:22:31 [INFO] train episode 5166: reward = -54.36, steps = 31 00:22:31 [INFO] train episode 5167: reward = -43.25, steps = 25 00:22:32 [INFO] train episode 5168: reward = -68.45, steps = 51 00:22:32 [INFO] train episode 5169: reward = -43.65, steps = 36 00:22:32 [INFO] train episode 5170: reward = -30.37, steps = 25 00:22:32 [INFO] train episode 5171: reward = -41.11, steps = 26 00:22:32 [INFO] train episode 5172: reward = -35.26, steps = 21 00:22:33 [INFO] train episode 5173: reward = -39.50, steps = 33 00:22:33 [INFO] train episode 5174: reward = -38.54, steps = 25 00:22:33 [INFO] train episode 5175: reward = -39.23, steps = 31 00:22:33 [INFO] train episode 5176: reward = -21.50, steps = 30 00:22:33 [INFO] train episode 5177: reward = -38.88, steps = 25 00:22:34 [INFO] train episode 5178: reward = -46.35, steps = 34 00:22:34 [INFO] train episode 5179: reward = -53.64, steps = 30 00:22:34 [INFO] train episode 5180: reward = -36.00, steps = 24 00:22:34 [INFO] train episode 5181: reward = -30.03, steps = 26 00:22:34 [INFO] train episode 5182: reward = -29.55, steps = 25 00:22:34 [INFO] train episode 5183: reward = -50.69, steps = 24 00:22:35 [INFO] train episode 5184: reward = -40.95, steps = 35 00:22:35 [INFO] train episode 5185: reward = -34.17, steps = 37 00:22:35 [INFO] train episode 5186: reward = -36.77, steps = 21 00:22:35 [INFO] train episode 5187: reward = -30.30, steps = 20 00:22:35 [INFO] train episode 5188: reward = -39.82, steps = 21 00:22:36 [INFO] train episode 5189: reward = -47.44, steps = 18 00:22:36 [INFO] train episode 5190: reward = -35.06, steps = 25 00:22:36 [INFO] train episode 5191: reward = -51.83, steps = 35 00:22:36 [INFO] train episode 5192: reward = -38.73, steps = 35 00:22:36 [INFO] train episode 5193: reward = -58.47, steps = 28 00:22:37 [INFO] train episode 5194: reward = -60.17, steps = 34 00:22:37 [INFO] train episode 5195: reward = -57.10, steps = 34 00:22:37 [INFO] train episode 5196: reward = -49.84, steps = 19 00:22:37 [INFO] train episode 5197: reward = -45.31, steps = 18 00:22:37 [INFO] train episode 5198: reward = -44.81, steps = 32 00:22:38 [INFO] train episode 5199: reward = -36.80, steps = 29 00:22:38 [INFO] train episode 5200: reward = -34.96, steps = 33 00:22:38 [INFO] train episode 5201: reward = -36.13, steps = 32 00:22:38 [INFO] train episode 5202: reward = -38.98, steps = 34 00:22:38 [INFO] train episode 5203: reward = -23.31, steps = 25 00:22:39 [INFO] train episode 5204: reward = -18.37, steps = 35 00:22:39 [INFO] train episode 5205: reward = -32.69, steps = 21 00:22:39 [INFO] train episode 5206: reward = -35.00, steps = 37 00:22:39 [INFO] train episode 5207: reward = -30.82, steps = 25 00:22:39 [INFO] train episode 5208: reward = -35.05, steps = 29 00:22:40 [INFO] train episode 5209: reward = -35.24, steps = 43 00:22:40 [INFO] train episode 5210: reward = -39.59, steps = 22 00:22:40 [INFO] train episode 5211: reward = -40.61, steps = 24 00:22:40 [INFO] train episode 5212: reward = -47.68, steps = 44 00:22:40 [INFO] train episode 5213: reward = -36.72, steps = 23 00:22:41 [INFO] train episode 5214: reward = -32.95, steps = 20 00:22:41 [INFO] train episode 5215: reward = -49.18, steps = 20 00:22:41 [INFO] train episode 5216: reward = -34.81, steps = 20 00:22:41 [INFO] train episode 5217: reward = -34.68, steps = 31 00:22:41 [INFO] train episode 5218: reward = -50.48, steps = 25 00:22:41 [INFO] train episode 5219: reward = -30.18, steps = 19 00:22:42 [INFO] train episode 5220: reward = -41.61, steps = 35 00:22:42 [INFO] train episode 5221: reward = -30.76, steps = 24 00:22:42 [INFO] train episode 5222: reward = -37.99, steps = 22 00:22:42 [INFO] train episode 5223: reward = -26.70, steps = 27 00:22:43 [INFO] train episode 5224: reward = -57.89, steps = 33 00:22:43 [INFO] train episode 5225: reward = -32.10, steps = 27 00:22:43 [INFO] train episode 5226: reward = -29.39, steps = 23 00:22:43 [INFO] train episode 5227: reward = -37.17, steps = 46 00:22:43 [INFO] train episode 5228: reward = -48.25, steps = 20 00:22:44 [INFO] train episode 5229: reward = -30.44, steps = 23 00:22:44 [INFO] train episode 5230: reward = -54.28, steps = 31 00:22:44 [INFO] train episode 5231: reward = -32.86, steps = 30 00:22:44 [INFO] train episode 5232: reward = -31.21, steps = 24 00:22:44 [INFO] train episode 5233: reward = -48.54, steps = 43 00:22:45 [INFO] train episode 5234: reward = -30.04, steps = 42 00:22:45 [INFO] train episode 5235: reward = -41.21, steps = 29 00:22:45 [INFO] train episode 5236: reward = -42.12, steps = 22 00:22:45 [INFO] train episode 5237: reward = -33.71, steps = 47 00:22:46 [INFO] train episode 5238: reward = -30.12, steps = 26 00:22:46 [INFO] train episode 5239: reward = -37.89, steps = 21 00:22:46 [INFO] train episode 5240: reward = -44.20, steps = 30 00:22:46 [INFO] train episode 5241: reward = -39.48, steps = 33 00:22:46 [INFO] train episode 5242: reward = -53.09, steps = 31 00:22:47 [INFO] train episode 5243: reward = -47.35, steps = 36 00:22:47 [INFO] train episode 5244: reward = -33.76, steps = 40 00:22:47 [INFO] train episode 5245: reward = -32.36, steps = 20 00:22:47 [INFO] train episode 5246: reward = -42.21, steps = 21 00:22:47 [INFO] train episode 5247: reward = -28.20, steps = 32 00:22:48 [INFO] train episode 5248: reward = -37.77, steps = 37 00:22:48 [INFO] train episode 5249: reward = -31.19, steps = 24 00:22:48 [INFO] train episode 5250: reward = -38.81, steps = 21 00:22:48 [INFO] train episode 5251: reward = -28.27, steps = 31 00:22:48 [INFO] train episode 5252: reward = -38.16, steps = 22 00:22:49 [INFO] train episode 5253: reward = -56.86, steps = 35 00:22:49 [INFO] train episode 5254: reward = -28.24, steps = 35 00:22:49 [INFO] train episode 5255: reward = -48.29, steps = 30 00:22:49 [INFO] train episode 5256: reward = -48.86, steps = 33 00:22:49 [INFO] train episode 5257: reward = -29.14, steps = 28 00:22:50 [INFO] train episode 5258: reward = -47.31, steps = 17 00:22:50 [INFO] train episode 5259: reward = -38.82, steps = 28 00:22:50 [INFO] train episode 5260: reward = -34.60, steps = 21 00:22:50 [INFO] train episode 5261: reward = -44.59, steps = 23 00:22:50 [INFO] train episode 5262: reward = -11.63, steps = 47 00:22:51 [INFO] train episode 5263: reward = -20.19, steps = 32 00:22:51 [INFO] train episode 5264: reward = -17.18, steps = 67 00:22:51 [INFO] train episode 5265: reward = -31.67, steps = 33 00:22:52 [INFO] train episode 5266: reward = -39.32, steps = 39 00:22:52 [INFO] train episode 5267: reward = -34.46, steps = 33 00:22:52 [INFO] train episode 5268: reward = -13.75, steps = 29 00:22:52 [INFO] train episode 5269: reward = -30.46, steps = 34 00:22:53 [INFO] train episode 5270: reward = -67.66, steps = 52 00:22:53 [INFO] train episode 5271: reward = -29.31, steps = 21 00:22:53 [INFO] train episode 5272: reward = -31.11, steps = 30 00:22:53 [INFO] train episode 5273: reward = -42.52, steps = 25 00:22:53 [INFO] train episode 5274: reward = -41.10, steps = 33 00:22:54 [INFO] train episode 5275: reward = -22.84, steps = 37 00:22:54 [INFO] train episode 5276: reward = -32.40, steps = 34 00:22:54 [INFO] train episode 5277: reward = -27.44, steps = 21 00:22:54 [INFO] train episode 5278: reward = -34.92, steps = 36 00:22:54 [INFO] train episode 5279: reward = -33.48, steps = 26 00:22:55 [INFO] train episode 5280: reward = -35.64, steps = 27 00:22:55 [INFO] train episode 5281: reward = -38.01, steps = 35 00:22:55 [INFO] train episode 5282: reward = -27.40, steps = 27 00:22:56 [INFO] train episode 5283: reward = -36.81, steps = 23 00:22:56 [INFO] train episode 5284: reward = -45.23, steps = 24 00:22:56 [INFO] train episode 5285: reward = -41.21, steps = 22 00:22:56 [INFO] train episode 5286: reward = -48.98, steps = 24 00:22:57 [INFO] train episode 5287: reward = -46.52, steps = 39 00:22:57 [INFO] train episode 5288: reward = -45.53, steps = 19 00:22:57 [INFO] train episode 5289: reward = -25.34, steps = 34 00:22:57 [INFO] train episode 5290: reward = -30.16, steps = 33 00:22:57 [INFO] train episode 5291: reward = -29.49, steps = 34 00:22:58 [INFO] train episode 5292: reward = -33.71, steps = 25 00:22:58 [INFO] train episode 5293: reward = -55.33, steps = 72 00:22:58 [INFO] train episode 5294: reward = -38.97, steps = 32 00:22:59 [INFO] train episode 5295: reward = -46.51, steps = 36 00:22:59 [INFO] train episode 5296: reward = -34.22, steps = 39 00:22:59 [INFO] train episode 5297: reward = -52.92, steps = 33 00:22:59 [INFO] train episode 5298: reward = -33.22, steps = 31 00:22:59 [INFO] train episode 5299: reward = -69.48, steps = 42 00:23:00 [INFO] train episode 5300: reward = -40.18, steps = 35 00:23:00 [INFO] train episode 5301: reward = -50.25, steps = 31 00:23:00 [INFO] train episode 5302: reward = -34.27, steps = 26 00:23:00 [INFO] train episode 5303: reward = -27.54, steps = 32 00:23:01 [INFO] train episode 5304: reward = -20.35, steps = 35 00:23:01 [INFO] train episode 5305: reward = -43.14, steps = 27 00:23:01 [INFO] train episode 5306: reward = -57.76, steps = 33 00:23:01 [INFO] train episode 5307: reward = -33.34, steps = 35 00:23:02 [INFO] train episode 5308: reward = -38.76, steps = 20 00:23:02 [INFO] train episode 5309: reward = -47.39, steps = 38 00:23:02 [INFO] train episode 5310: reward = -42.42, steps = 29 00:23:02 [INFO] train episode 5311: reward = -32.97, steps = 19 00:23:02 [INFO] train episode 5312: reward = -47.13, steps = 39 00:23:03 [INFO] train episode 5313: reward = -40.70, steps = 29 00:23:03 [INFO] train episode 5314: reward = -41.76, steps = 35 00:23:03 [INFO] train episode 5315: reward = -28.98, steps = 27 00:23:03 [INFO] train episode 5316: reward = -37.67, steps = 37 00:23:03 [INFO] train episode 5317: reward = -25.38, steps = 24 00:23:04 [INFO] train episode 5318: reward = -64.83, steps = 37 00:23:04 [INFO] train episode 5319: reward = -35.26, steps = 25 00:23:04 [INFO] train episode 5320: reward = -43.45, steps = 26 00:23:04 [INFO] train episode 5321: reward = -26.82, steps = 40 00:23:05 [INFO] train episode 5322: reward = -54.00, steps = 33 00:23:05 [INFO] train episode 5323: reward = -22.13, steps = 40 00:23:05 [INFO] train episode 5324: reward = -28.86, steps = 20 00:23:05 [INFO] train episode 5325: reward = -30.06, steps = 40 00:23:06 [INFO] train episode 5326: reward = -50.21, steps = 45 00:23:06 [INFO] train episode 5327: reward = -17.60, steps = 38 00:23:06 [INFO] train episode 5328: reward = -44.25, steps = 27 00:23:06 [INFO] train episode 5329: reward = -53.00, steps = 36 00:23:07 [INFO] train episode 5330: reward = -51.39, steps = 32 00:23:07 [INFO] train episode 5331: reward = -42.28, steps = 21 00:23:07 [INFO] train episode 5332: reward = -28.08, steps = 26 00:23:07 [INFO] train episode 5333: reward = -40.49, steps = 24 00:23:07 [INFO] train episode 5334: reward = -16.88, steps = 34 00:23:08 [INFO] train episode 5335: reward = -36.30, steps = 21 00:23:08 [INFO] train episode 5336: reward = -51.20, steps = 26 00:23:08 [INFO] train episode 5337: reward = -34.09, steps = 29 00:23:08 [INFO] train episode 5338: reward = -22.90, steps = 36 00:23:08 [INFO] train episode 5339: reward = -51.15, steps = 46 00:23:09 [INFO] train episode 5340: reward = -35.61, steps = 22 00:23:09 [INFO] train episode 5341: reward = -41.85, steps = 41 00:23:09 [INFO] train episode 5342: reward = -41.21, steps = 34 00:23:09 [INFO] train episode 5343: reward = -36.27, steps = 37 00:23:10 [INFO] train episode 5344: reward = -18.49, steps = 35 00:23:10 [INFO] train episode 5345: reward = -43.60, steps = 29 00:23:10 [INFO] train episode 5346: reward = -24.75, steps = 21 00:23:11 [INFO] train episode 5347: reward = -42.21, steps = 50 00:23:11 [INFO] train episode 5348: reward = -29.67, steps = 39 00:23:11 [INFO] train episode 5349: reward = -40.28, steps = 20 00:23:11 [INFO] train episode 5350: reward = -29.48, steps = 35 00:23:11 [INFO] train episode 5351: reward = -18.75, steps = 36 00:23:12 [INFO] train episode 5352: reward = -33.79, steps = 31 00:23:12 [INFO] train episode 5353: reward = -56.95, steps = 35 00:23:12 [INFO] train episode 5354: reward = -40.70, steps = 22 00:23:12 [INFO] train episode 5355: reward = -28.35, steps = 54 00:23:13 [INFO] train episode 5356: reward = -44.43, steps = 20 00:23:13 [INFO] train episode 5357: reward = -30.73, steps = 20 00:23:13 [INFO] train episode 5358: reward = -34.94, steps = 22 00:23:13 [INFO] train episode 5359: reward = -55.56, steps = 45 00:23:13 [INFO] train episode 5360: reward = -45.22, steps = 34 00:23:14 [INFO] train episode 5361: reward = -28.58, steps = 30 00:23:14 [INFO] train episode 5362: reward = -38.24, steps = 28 00:23:14 [INFO] train episode 5363: reward = -23.34, steps = 31 00:23:14 [INFO] train episode 5364: reward = -30.81, steps = 38 00:23:15 [INFO] train episode 5365: reward = -40.19, steps = 37 00:23:15 [INFO] train episode 5366: reward = -33.08, steps = 24 00:23:15 [INFO] train episode 5367: reward = -21.81, steps = 41 00:23:15 [INFO] train episode 5368: reward = -39.10, steps = 35 00:23:15 [INFO] train episode 5369: reward = -22.06, steps = 31 00:23:16 [INFO] train episode 5370: reward = -52.28, steps = 26 00:23:16 [INFO] train episode 5371: reward = -17.02, steps = 45 00:23:16 [INFO] train episode 5372: reward = -39.86, steps = 25 00:23:16 [INFO] train episode 5373: reward = -26.33, steps = 35 00:23:17 [INFO] train episode 5374: reward = -31.24, steps = 32 00:23:17 [INFO] train episode 5375: reward = -36.01, steps = 37 00:23:17 [INFO] train episode 5376: reward = -53.45, steps = 32 00:23:17 [INFO] train episode 5377: reward = -44.86, steps = 28 00:23:17 [INFO] train episode 5378: reward = -37.90, steps = 27 00:23:18 [INFO] train episode 5379: reward = -40.17, steps = 28 00:23:18 [INFO] train episode 5380: reward = -25.71, steps = 34 00:23:18 [INFO] train episode 5381: reward = -9.70, steps = 36 00:23:18 [INFO] train episode 5382: reward = -23.32, steps = 28 00:23:19 [INFO] train episode 5383: reward = -44.93, steps = 39 00:23:19 [INFO] train episode 5384: reward = -33.40, steps = 32 00:23:19 [INFO] train episode 5385: reward = -23.84, steps = 40 00:23:19 [INFO] train episode 5386: reward = -46.20, steps = 36 00:23:19 [INFO] train episode 5387: reward = -45.30, steps = 21 00:23:20 [INFO] train episode 5388: reward = -27.34, steps = 21 00:23:20 [INFO] train episode 5389: reward = -30.25, steps = 28 00:23:20 [INFO] train episode 5390: reward = -42.24, steps = 28 00:23:20 [INFO] train episode 5391: reward = -32.84, steps = 20 00:23:20 [INFO] train episode 5392: reward = -37.35, steps = 30 00:23:21 [INFO] train episode 5393: reward = -25.20, steps = 37 00:23:21 [INFO] train episode 5394: reward = -35.80, steps = 34 00:23:21 [INFO] train episode 5395: reward = -24.05, steps = 40 00:23:21 [INFO] train episode 5396: reward = -34.43, steps = 24 00:23:21 [INFO] train episode 5397: reward = -29.46, steps = 34 00:23:22 [INFO] train episode 5398: reward = -39.58, steps = 24 00:23:22 [INFO] train episode 5399: reward = -23.53, steps = 34 00:23:22 [INFO] train episode 5400: reward = -43.03, steps = 34 00:23:22 [INFO] train episode 5401: reward = -34.20, steps = 22 00:23:22 [INFO] train episode 5402: reward = -44.08, steps = 32 00:23:23 [INFO] train episode 5403: reward = -30.83, steps = 21 00:23:23 [INFO] train episode 5404: reward = -30.60, steps = 32 00:23:23 [INFO] train episode 5405: reward = -36.05, steps = 21 00:23:23 [INFO] train episode 5406: reward = -49.24, steps = 29 00:23:23 [INFO] train episode 5407: reward = -39.05, steps = 22 00:23:23 [INFO] train episode 5408: reward = -38.67, steps = 23 00:23:24 [INFO] train episode 5409: reward = -36.02, steps = 32 00:23:24 [INFO] train episode 5410: reward = -31.47, steps = 41 00:23:24 [INFO] train episode 5411: reward = -36.98, steps = 31 00:23:25 [INFO] train episode 5412: reward = -48.89, steps = 20 00:23:25 [INFO] train episode 5413: reward = -27.02, steps = 40 00:23:25 [INFO] train episode 5414: reward = -25.77, steps = 22 00:23:25 [INFO] train episode 5415: reward = -30.34, steps = 40 00:23:26 [INFO] train episode 5416: reward = -35.46, steps = 41 00:23:26 [INFO] train episode 5417: reward = -25.36, steps = 31 00:23:26 [INFO] train episode 5418: reward = -25.32, steps = 34 00:23:26 [INFO] train episode 5419: reward = -27.79, steps = 32 00:23:26 [INFO] train episode 5420: reward = -42.97, steps = 42 00:23:27 [INFO] train episode 5421: reward = -36.84, steps = 23 00:23:27 [INFO] train episode 5422: reward = -35.74, steps = 27 00:23:27 [INFO] train episode 5423: reward = -33.27, steps = 20 00:23:27 [INFO] train episode 5424: reward = -35.49, steps = 17 00:23:27 [INFO] train episode 5425: reward = -35.46, steps = 27 00:23:27 [INFO] train episode 5426: reward = -36.20, steps = 23 00:23:28 [INFO] train episode 5427: reward = -35.90, steps = 33 00:23:28 [INFO] train episode 5428: reward = -23.05, steps = 31 00:23:28 [INFO] train episode 5429: reward = -38.77, steps = 30 00:23:28 [INFO] train episode 5430: reward = -35.84, steps = 35 00:23:28 [INFO] train episode 5431: reward = -41.07, steps = 25 00:23:29 [INFO] train episode 5432: reward = -32.15, steps = 18 00:23:29 [INFO] train episode 5433: reward = -32.78, steps = 49 00:23:29 [INFO] train episode 5434: reward = -31.16, steps = 21 00:23:29 [INFO] train episode 5435: reward = -32.67, steps = 21 00:23:29 [INFO] train episode 5436: reward = -34.69, steps = 27 00:23:30 [INFO] train episode 5437: reward = -41.78, steps = 32 00:23:30 [INFO] train episode 5438: reward = -26.79, steps = 30 00:23:30 [INFO] train episode 5439: reward = -36.00, steps = 25 00:23:30 [INFO] train episode 5440: reward = -42.86, steps = 43 00:23:31 [INFO] train episode 5441: reward = -34.00, steps = 24 00:23:31 [INFO] train episode 5442: reward = -35.83, steps = 23 00:23:31 [INFO] train episode 5443: reward = -14.43, steps = 49 00:23:31 [INFO] train episode 5444: reward = -37.48, steps = 27 00:23:31 [INFO] train episode 5445: reward = -21.08, steps = 41 00:23:32 [INFO] train episode 5446: reward = -39.95, steps = 38 00:23:32 [INFO] train episode 5447: reward = -28.08, steps = 33 00:23:32 [INFO] train episode 5448: reward = -48.30, steps = 34 00:23:32 [INFO] train episode 5449: reward = -28.93, steps = 26 00:23:33 [INFO] train episode 5450: reward = -28.10, steps = 29 00:23:33 [INFO] train episode 5451: reward = -44.25, steps = 38 00:23:33 [INFO] train episode 5452: reward = -30.44, steps = 38 00:23:33 [INFO] train episode 5453: reward = -39.75, steps = 25 00:23:33 [INFO] train episode 5454: reward = -37.40, steps = 21 00:23:34 [INFO] train episode 5455: reward = -42.17, steps = 39 00:23:34 [INFO] train episode 5456: reward = -50.86, steps = 26 00:23:34 [INFO] train episode 5457: reward = -21.13, steps = 25 00:23:34 [INFO] train episode 5458: reward = -29.05, steps = 38 00:23:34 [INFO] train episode 5459: reward = -34.13, steps = 19 00:23:34 [INFO] train episode 5460: reward = -27.69, steps = 27 00:23:35 [INFO] train episode 5461: reward = -50.19, steps = 18 00:23:35 [INFO] train episode 5462: reward = -23.23, steps = 35 00:23:35 [INFO] train episode 5463: reward = -34.38, steps = 36 00:23:35 [INFO] train episode 5464: reward = -20.77, steps = 34 00:23:36 [INFO] train episode 5465: reward = -26.05, steps = 40 00:23:36 [INFO] train episode 5466: reward = -31.70, steps = 21 00:23:36 [INFO] train episode 5467: reward = -27.98, steps = 40 00:23:36 [INFO] train episode 5468: reward = -32.80, steps = 40 00:23:36 [INFO] train episode 5469: reward = -32.80, steps = 21 00:23:37 [INFO] train episode 5470: reward = -45.02, steps = 29 00:23:37 [INFO] train episode 5471: reward = -24.26, steps = 30 00:23:37 [INFO] train episode 5472: reward = -28.02, steps = 30 00:23:37 [INFO] train episode 5473: reward = -47.35, steps = 38 00:23:38 [INFO] train episode 5474: reward = -40.02, steps = 23 00:23:38 [INFO] train episode 5475: reward = -42.02, steps = 19 00:23:38 [INFO] train episode 5476: reward = -38.51, steps = 30 00:23:38 [INFO] train episode 5477: reward = -26.75, steps = 31 00:23:39 [INFO] train episode 5478: reward = -25.76, steps = 35 00:23:39 [INFO] train episode 5479: reward = -40.57, steps = 29 00:23:39 [INFO] train episode 5480: reward = -31.02, steps = 26 00:23:39 [INFO] train episode 5481: reward = -45.28, steps = 33 00:23:39 [INFO] train episode 5482: reward = -31.52, steps = 21 00:23:40 [INFO] train episode 5483: reward = -29.49, steps = 30 00:23:40 [INFO] train episode 5484: reward = -37.79, steps = 20 00:23:40 [INFO] train episode 5485: reward = -42.04, steps = 42 00:23:40 [INFO] train episode 5486: reward = -29.75, steps = 30 00:23:40 [INFO] train episode 5487: reward = -37.94, steps = 19 00:23:41 [INFO] train episode 5488: reward = -43.97, steps = 24 00:23:41 [INFO] train episode 5489: reward = -35.82, steps = 38 00:23:41 [INFO] train episode 5490: reward = -27.44, steps = 20 00:23:41 [INFO] train episode 5491: reward = -40.38, steps = 34 00:23:41 [INFO] train episode 5492: reward = -35.12, steps = 25 00:23:42 [INFO] train episode 5493: reward = -32.10, steps = 21 00:23:42 [INFO] train episode 5494: reward = -30.24, steps = 23 00:23:42 [INFO] train episode 5495: reward = -33.47, steps = 24 00:23:42 [INFO] train episode 5496: reward = -41.53, steps = 25 00:23:42 [INFO] train episode 5497: reward = -18.21, steps = 47 00:23:43 [INFO] train episode 5498: reward = -35.34, steps = 24 00:23:43 [INFO] train episode 5499: reward = -37.36, steps = 28 00:23:43 [INFO] train episode 5500: reward = -30.27, steps = 28 00:23:43 [INFO] train episode 5501: reward = -28.44, steps = 21 00:23:43 [INFO] train episode 5502: reward = -41.79, steps = 32 00:23:44 [INFO] train episode 5503: reward = -36.40, steps = 38 00:23:44 [INFO] train episode 5504: reward = -29.10, steps = 26 00:23:44 [INFO] train episode 5505: reward = -24.69, steps = 32 00:23:44 [INFO] train episode 5506: reward = -46.26, steps = 22 00:23:44 [INFO] train episode 5507: reward = -37.24, steps = 24 00:23:44 [INFO] train episode 5508: reward = -32.32, steps = 22 00:23:45 [INFO] train episode 5509: reward = -49.88, steps = 32 00:23:45 [INFO] train episode 5510: reward = -30.20, steps = 34 00:23:45 [INFO] train episode 5511: reward = -30.48, steps = 29 00:23:45 [INFO] train episode 5512: reward = -35.17, steps = 23 00:23:45 [INFO] train episode 5513: reward = -42.85, steps = 28 00:23:46 [INFO] train episode 5514: reward = -45.96, steps = 31 00:23:46 [INFO] train episode 5515: reward = -45.39, steps = 34 00:23:46 [INFO] train episode 5516: reward = -29.16, steps = 31 00:23:46 [INFO] train episode 5517: reward = -42.52, steps = 31 00:23:47 [INFO] train episode 5518: reward = -35.58, steps = 35 00:23:47 [INFO] train episode 5519: reward = -24.95, steps = 36 00:23:47 [INFO] train episode 5520: reward = -27.60, steps = 39 00:23:47 [INFO] train episode 5521: reward = -36.48, steps = 33 00:23:47 [INFO] train episode 5522: reward = -41.01, steps = 35 00:23:48 [INFO] train episode 5523: reward = -26.15, steps = 41 00:23:48 [INFO] train episode 5524: reward = -36.04, steps = 36 00:23:48 [INFO] train episode 5525: reward = -33.91, steps = 36 00:23:49 [INFO] train episode 5526: reward = -28.37, steps = 40 00:23:49 [INFO] train episode 5527: reward = -36.60, steps = 25 00:23:49 [INFO] train episode 5528: reward = -65.51, steps = 43 00:23:49 [INFO] train episode 5529: reward = -31.25, steps = 33 00:23:49 [INFO] train episode 5530: reward = -23.38, steps = 25 00:23:50 [INFO] train episode 5531: reward = -37.22, steps = 27 00:23:50 [INFO] train episode 5532: reward = -39.66, steps = 29 00:23:50 [INFO] train episode 5533: reward = -37.56, steps = 33 00:23:50 [INFO] train episode 5534: reward = -40.73, steps = 32 00:23:50 [INFO] train episode 5535: reward = -56.20, steps = 31 00:23:51 [INFO] train episode 5536: reward = -56.41, steps = 43 00:23:51 [INFO] train episode 5537: reward = -28.52, steps = 20 00:23:51 [INFO] train episode 5538: reward = -30.94, steps = 22 00:23:51 [INFO] train episode 5539: reward = -37.18, steps = 34 00:23:52 [INFO] train episode 5540: reward = -34.67, steps = 22 00:23:52 [INFO] train episode 5541: reward = -28.86, steps = 21 00:23:52 [INFO] train episode 5542: reward = -65.21, steps = 32 00:23:52 [INFO] train episode 5543: reward = -47.91, steps = 37 00:23:53 [INFO] train episode 5544: reward = -27.98, steps = 42 00:23:53 [INFO] train episode 5545: reward = -19.76, steps = 33 00:23:53 [INFO] train episode 5546: reward = -48.85, steps = 40 00:23:53 [INFO] train episode 5547: reward = -29.64, steps = 21 00:23:53 [INFO] train episode 5548: reward = -52.17, steps = 18 00:23:54 [INFO] train episode 5549: reward = -41.37, steps = 41 00:23:54 [INFO] train episode 5550: reward = -36.35, steps = 35 00:23:54 [INFO] train episode 5551: reward = -52.18, steps = 34 00:23:54 [INFO] train episode 5552: reward = -39.72, steps = 18 00:23:54 [INFO] train episode 5553: reward = -49.78, steps = 28 00:23:55 [INFO] train episode 5554: reward = -28.50, steps = 35 00:23:55 [INFO] train episode 5555: reward = -43.50, steps = 24 00:23:55 [INFO] train episode 5556: reward = -30.11, steps = 21 00:23:55 [INFO] train episode 5557: reward = -32.43, steps = 29 00:23:55 [INFO] train episode 5558: reward = -33.53, steps = 23 00:23:55 [INFO] train episode 5559: reward = -26.17, steps = 22 00:23:56 [INFO] train episode 5560: reward = -37.27, steps = 27 00:23:56 [INFO] train episode 5561: reward = -56.38, steps = 34 00:23:56 [INFO] train episode 5562: reward = -35.13, steps = 42 00:23:56 [INFO] train episode 5563: reward = -31.37, steps = 33 00:23:57 [INFO] train episode 5564: reward = -41.11, steps = 26 00:23:57 [INFO] train episode 5565: reward = -41.99, steps = 31 00:23:57 [INFO] train episode 5566: reward = -30.93, steps = 35 00:23:57 [INFO] train episode 5567: reward = -31.81, steps = 28 00:23:57 [INFO] train episode 5568: reward = -20.58, steps = 27 00:23:57 [INFO] train episode 5569: reward = -45.71, steps = 21 00:23:58 [INFO] train episode 5570: reward = -54.08, steps = 27 00:23:58 [INFO] train episode 5571: reward = -23.87, steps = 36 00:23:58 [INFO] train episode 5572: reward = -51.54, steps = 27 00:23:58 [INFO] train episode 5573: reward = -38.80, steps = 23 00:23:58 [INFO] train episode 5574: reward = -31.84, steps = 26 00:23:59 [INFO] train episode 5575: reward = -55.54, steps = 42 00:23:59 [INFO] train episode 5576: reward = -50.61, steps = 43 00:23:59 [INFO] train episode 5577: reward = -47.03, steps = 33 00:23:59 [INFO] train episode 5578: reward = -32.00, steps = 20 00:24:00 [INFO] train episode 5579: reward = -41.26, steps = 37 00:24:00 [INFO] train episode 5580: reward = -46.70, steps = 31 00:24:00 [INFO] train episode 5581: reward = -34.25, steps = 48 00:24:00 [INFO] train episode 5582: reward = -35.60, steps = 24 00:24:01 [INFO] train episode 5583: reward = -48.15, steps = 17 00:24:01 [INFO] train episode 5584: reward = -31.22, steps = 22 00:24:01 [INFO] train episode 5585: reward = -39.46, steps = 35 00:24:01 [INFO] train episode 5586: reward = -38.98, steps = 32 00:24:01 [INFO] train episode 5587: reward = -35.67, steps = 25 00:24:01 [INFO] train episode 5588: reward = -54.36, steps = 35 00:24:02 [INFO] train episode 5589: reward = -32.23, steps = 29 00:24:02 [INFO] train episode 5590: reward = -46.85, steps = 33 00:24:02 [INFO] train episode 5591: reward = -34.96, steps = 32 00:24:02 [INFO] train episode 5592: reward = -43.22, steps = 35 00:24:03 [INFO] train episode 5593: reward = -35.83, steps = 32 00:24:03 [INFO] train episode 5594: reward = -31.28, steps = 22 00:24:03 [INFO] train episode 5595: reward = -36.41, steps = 24 00:24:03 [INFO] train episode 5596: reward = -33.45, steps = 31 00:24:03 [INFO] train episode 5597: reward = -26.23, steps = 35 00:24:04 [INFO] train episode 5598: reward = -45.01, steps = 37 00:24:04 [INFO] train episode 5599: reward = -14.78, steps = 33 00:24:04 [INFO] train episode 5600: reward = -36.62, steps = 25 00:24:04 [INFO] train episode 5601: reward = -48.82, steps = 23 00:24:04 [INFO] train episode 5602: reward = -28.85, steps = 26 00:24:05 [INFO] train episode 5603: reward = -44.50, steps = 33 00:24:05 [INFO] train episode 5604: reward = -38.10, steps = 34 00:24:05 [INFO] train episode 5605: reward = -26.11, steps = 29 00:24:05 [INFO] train episode 5606: reward = -24.15, steps = 25 00:24:06 [INFO] train episode 5607: reward = -52.32, steps = 28 00:24:06 [INFO] train episode 5608: reward = -54.00, steps = 33 00:24:06 [INFO] train episode 5609: reward = -39.01, steps = 30 00:24:06 [INFO] train episode 5610: reward = -35.91, steps = 20 00:24:07 [INFO] train episode 5611: reward = -33.68, steps = 36 00:24:07 [INFO] train episode 5612: reward = -32.39, steps = 28 00:24:07 [INFO] train episode 5613: reward = -40.98, steps = 23 00:24:07 [INFO] train episode 5614: reward = -35.05, steps = 41 00:24:07 [INFO] train episode 5615: reward = -53.34, steps = 26 00:24:08 [INFO] train episode 5616: reward = -32.28, steps = 29 00:24:08 [INFO] train episode 5617: reward = -27.98, steps = 27 00:24:08 [INFO] train episode 5618: reward = -43.45, steps = 27 00:24:08 [INFO] train episode 5619: reward = -30.54, steps = 21 00:24:08 [INFO] train episode 5620: reward = -30.99, steps = 31 00:24:09 [INFO] train episode 5621: reward = -43.83, steps = 30 00:24:09 [INFO] train episode 5622: reward = -27.23, steps = 28 00:24:09 [INFO] train episode 5623: reward = -38.83, steps = 33 00:24:09 [INFO] train episode 5624: reward = -25.26, steps = 28 00:24:09 [INFO] train episode 5625: reward = -30.71, steps = 27 00:24:10 [INFO] train episode 5626: reward = -37.47, steps = 30 00:24:10 [INFO] train episode 5627: reward = -49.57, steps = 42 00:24:10 [INFO] train episode 5628: reward = -43.96, steps = 36 00:24:10 [INFO] train episode 5629: reward = -33.36, steps = 31 00:24:10 [INFO] train episode 5630: reward = -50.07, steps = 29 00:24:11 [INFO] train episode 5631: reward = -37.40, steps = 32 00:24:11 [INFO] train episode 5632: reward = -34.15, steps = 23 00:24:11 [INFO] train episode 5633: reward = -22.92, steps = 45 00:24:11 [INFO] train episode 5634: reward = -50.11, steps = 35 00:24:12 [INFO] train episode 5635: reward = -34.96, steps = 24 00:24:12 [INFO] train episode 5636: reward = -41.24, steps = 32 00:24:12 [INFO] train episode 5637: reward = -54.00, steps = 37 00:24:12 [INFO] train episode 5638: reward = -28.93, steps = 25 00:24:12 [INFO] train episode 5639: reward = -31.30, steps = 34 00:24:13 [INFO] train episode 5640: reward = -33.85, steps = 35 00:24:13 [INFO] train episode 5641: reward = -29.36, steps = 24 00:24:13 [INFO] train episode 5642: reward = -16.72, steps = 35 00:24:13 [INFO] train episode 5643: reward = -26.81, steps = 35 00:24:13 [INFO] train episode 5644: reward = -31.84, steps = 22 00:24:14 [INFO] train episode 5645: reward = -36.01, steps = 29 00:24:14 [INFO] train episode 5646: reward = -22.53, steps = 34 00:24:14 [INFO] train episode 5647: reward = -25.31, steps = 26 00:24:14 [INFO] train episode 5648: reward = -32.73, steps = 20 00:24:15 [INFO] train episode 5649: reward = -39.46, steps = 45 00:24:15 [INFO] train episode 5650: reward = -18.96, steps = 24 00:24:15 [INFO] train episode 5651: reward = -36.58, steps = 40 00:24:15 [INFO] train episode 5652: reward = -36.76, steps = 33 00:24:15 [INFO] train episode 5653: reward = -55.95, steps = 35 00:24:16 [INFO] train episode 5654: reward = -36.37, steps = 35 00:24:16 [INFO] train episode 5655: reward = -22.00, steps = 32 00:24:16 [INFO] train episode 5656: reward = -29.48, steps = 23 00:24:16 [INFO] train episode 5657: reward = -37.50, steps = 22 00:24:16 [INFO] train episode 5658: reward = -12.55, steps = 36 00:24:17 [INFO] train episode 5659: reward = -47.68, steps = 19 00:24:17 [INFO] train episode 5660: reward = -64.05, steps = 37 00:24:17 [INFO] train episode 5661: reward = -44.06, steps = 28 00:24:17 [INFO] train episode 5662: reward = -24.38, steps = 36 00:24:17 [INFO] train episode 5663: reward = -31.14, steps = 35 00:24:18 [INFO] train episode 5664: reward = -46.61, steps = 19 00:24:18 [INFO] train episode 5665: reward = -20.45, steps = 38 00:24:18 [INFO] train episode 5666: reward = -26.85, steps = 41 00:24:18 [INFO] train episode 5667: reward = -22.78, steps = 30 00:24:19 [INFO] train episode 5668: reward = -66.06, steps = 32 00:24:19 [INFO] train episode 5669: reward = -30.72, steps = 27 00:24:19 [INFO] train episode 5670: reward = -33.66, steps = 46 00:24:19 [INFO] train episode 5671: reward = -24.74, steps = 33 00:24:20 [INFO] train episode 5672: reward = -28.87, steps = 29 00:24:20 [INFO] train episode 5673: reward = -27.13, steps = 31 00:24:20 [INFO] train episode 5674: reward = -38.86, steps = 35 00:24:20 [INFO] train episode 5675: reward = -27.80, steps = 27 00:24:21 [INFO] train episode 5676: reward = -50.09, steps = 32 00:24:21 [INFO] train episode 5677: reward = -26.26, steps = 36 00:24:21 [INFO] train episode 5678: reward = -27.55, steps = 33 00:24:21 [INFO] train episode 5679: reward = -43.51, steps = 30 00:24:21 [INFO] train episode 5680: reward = -38.18, steps = 32 00:24:22 [INFO] train episode 5681: reward = -48.23, steps = 29 00:24:22 [INFO] train episode 5682: reward = -36.40, steps = 26 00:24:22 [INFO] train episode 5683: reward = -51.68, steps = 17 00:24:22 [INFO] train episode 5684: reward = -49.09, steps = 35 00:24:22 [INFO] train episode 5685: reward = -45.11, steps = 29 00:24:23 [INFO] train episode 5686: reward = -31.74, steps = 35 00:24:23 [INFO] train episode 5687: reward = -25.52, steps = 47 00:24:23 [INFO] train episode 5688: reward = -57.71, steps = 32 00:24:23 [INFO] train episode 5689: reward = -19.07, steps = 46 00:24:24 [INFO] train episode 5690: reward = -26.70, steps = 24 00:24:24 [INFO] train episode 5691: reward = -38.86, steps = 41 00:24:24 [INFO] train episode 5692: reward = -32.08, steps = 34 00:24:24 [INFO] train episode 5693: reward = -28.18, steps = 28 00:24:25 [INFO] train episode 5694: reward = -32.98, steps = 28 00:24:25 [INFO] train episode 5695: reward = -32.98, steps = 37 00:24:25 [INFO] train episode 5696: reward = -26.44, steps = 21 00:24:25 [INFO] train episode 5697: reward = -37.50, steps = 21 00:24:25 [INFO] train episode 5698: reward = -27.41, steps = 22 00:24:25 [INFO] train episode 5699: reward = -49.30, steps = 26 00:24:26 [INFO] train episode 5700: reward = -37.66, steps = 28 00:24:26 [INFO] train episode 5701: reward = -34.50, steps = 38 00:24:26 [INFO] train episode 5702: reward = -43.57, steps = 48 00:24:26 [INFO] train episode 5703: reward = -39.34, steps = 32 00:24:27 [INFO] train episode 5704: reward = -25.01, steps = 32 00:24:27 [INFO] train episode 5705: reward = -32.28, steps = 32 00:24:27 [INFO] train episode 5706: reward = -30.36, steps = 37 00:24:27 [INFO] train episode 5707: reward = -25.36, steps = 26 00:24:28 [INFO] train episode 5708: reward = -10.37, steps = 36 00:24:28 [INFO] train episode 5709: reward = -15.83, steps = 39 00:24:28 [INFO] train episode 5710: reward = -37.87, steps = 23 00:24:28 [INFO] train episode 5711: reward = -72.05, steps = 26 00:24:28 [INFO] train episode 5712: reward = -43.99, steps = 48 00:24:29 [INFO] train episode 5713: reward = -30.14, steps = 29 00:24:29 [INFO] train episode 5714: reward = -39.46, steps = 27 00:24:29 [INFO] train episode 5715: reward = -48.12, steps = 28 00:24:29 [INFO] train episode 5716: reward = -24.07, steps = 31 00:24:29 [INFO] train episode 5717: reward = -47.74, steps = 35 00:24:30 [INFO] train episode 5718: reward = -32.58, steps = 33 00:24:30 [INFO] train episode 5719: reward = -32.21, steps = 28 00:24:30 [INFO] train episode 5720: reward = -25.57, steps = 24 00:24:30 [INFO] train episode 5721: reward = -35.81, steps = 20 00:24:30 [INFO] train episode 5722: reward = -39.33, steps = 21 00:24:31 [INFO] train episode 5723: reward = -39.50, steps = 32 00:24:31 [INFO] train episode 5724: reward = -20.86, steps = 34 00:24:31 [INFO] train episode 5725: reward = -30.55, steps = 20 00:24:31 [INFO] train episode 5726: reward = -52.94, steps = 35 00:24:31 [INFO] train episode 5727: reward = -32.20, steps = 35 00:24:32 [INFO] train episode 5728: reward = -23.40, steps = 36 00:24:32 [INFO] train episode 5729: reward = -36.04, steps = 25 00:24:32 [INFO] train episode 5730: reward = -30.75, steps = 24 00:24:33 [INFO] train episode 5731: reward = -29.42, steps = 39 00:24:33 [INFO] train episode 5732: reward = -45.22, steps = 23 00:24:33 [INFO] train episode 5733: reward = -25.94, steps = 24 00:24:33 [INFO] train episode 5734: reward = -46.50, steps = 33 00:24:33 [INFO] train episode 5735: reward = -32.58, steps = 21 00:24:33 [INFO] train episode 5736: reward = -27.05, steps = 19 00:24:34 [INFO] train episode 5737: reward = -32.55, steps = 35 00:24:34 [INFO] train episode 5738: reward = -42.44, steps = 23 00:24:34 [INFO] train episode 5739: reward = -36.10, steps = 33 00:24:34 [INFO] train episode 5740: reward = -31.22, steps = 53 00:24:35 [INFO] train episode 5741: reward = -29.00, steps = 29 00:24:35 [INFO] train episode 5742: reward = -45.36, steps = 26 00:24:35 [INFO] train episode 5743: reward = -50.40, steps = 41 00:24:35 [INFO] train episode 5744: reward = -39.22, steps = 29 00:24:36 [INFO] train episode 5745: reward = -51.81, steps = 37 00:24:36 [INFO] train episode 5746: reward = -30.91, steps = 43 00:24:36 [INFO] train episode 5747: reward = -51.75, steps = 40 00:24:36 [INFO] train episode 5748: reward = -24.15, steps = 28 00:24:37 [INFO] train episode 5749: reward = -27.40, steps = 45 00:24:37 [INFO] train episode 5750: reward = -41.92, steps = 22 00:24:37 [INFO] train episode 5751: reward = -44.99, steps = 58 00:24:37 [INFO] train episode 5752: reward = -32.94, steps = 35 00:24:38 [INFO] train episode 5753: reward = -28.13, steps = 42 00:24:38 [INFO] train episode 5754: reward = -33.49, steps = 24 00:24:38 [INFO] train episode 5755: reward = -52.05, steps = 27 00:24:38 [INFO] train episode 5756: reward = -24.08, steps = 34 00:24:38 [INFO] train episode 5757: reward = -46.57, steps = 27 00:24:39 [INFO] train episode 5758: reward = -47.98, steps = 30 00:24:39 [INFO] train episode 5759: reward = -50.64, steps = 82 00:24:39 [INFO] train episode 5760: reward = -24.45, steps = 21 00:24:39 [INFO] train episode 5761: reward = -60.15, steps = 27 00:24:40 [INFO] train episode 5762: reward = -59.07, steps = 41 00:24:40 [INFO] train episode 5763: reward = -41.43, steps = 36 00:24:40 [INFO] train episode 5764: reward = -36.11, steps = 35 00:24:40 [INFO] train episode 5765: reward = -26.32, steps = 29 00:24:41 [INFO] train episode 5766: reward = -30.81, steps = 30 00:24:41 [INFO] train episode 5767: reward = -39.86, steps = 34 00:24:41 [INFO] train episode 5768: reward = -38.23, steps = 38 00:24:41 [INFO] train episode 5769: reward = -56.08, steps = 38 00:24:42 [INFO] train episode 5770: reward = -27.19, steps = 37 00:24:42 [INFO] train episode 5771: reward = -40.12, steps = 31 00:24:42 [INFO] train episode 5772: reward = -28.95, steps = 21 00:24:42 [INFO] train episode 5773: reward = -26.21, steps = 35 00:24:42 [INFO] train episode 5774: reward = -46.17, steps = 42 00:24:43 [INFO] train episode 5775: reward = -27.46, steps = 34 00:24:43 [INFO] train episode 5776: reward = -47.56, steps = 40 00:24:43 [INFO] train episode 5777: reward = -36.92, steps = 40 00:24:43 [INFO] train episode 5778: reward = -36.15, steps = 35 00:24:44 [INFO] train episode 5779: reward = -38.89, steps = 22 00:24:44 [INFO] train episode 5780: reward = -40.72, steps = 50 00:24:44 [INFO] train episode 5781: reward = -45.98, steps = 37 00:24:44 [INFO] train episode 5782: reward = -29.75, steps = 48 00:24:45 [INFO] train episode 5783: reward = -41.76, steps = 23 00:24:45 [INFO] train episode 5784: reward = -43.38, steps = 38 00:24:45 [INFO] train episode 5785: reward = -40.90, steps = 47 00:24:45 [INFO] train episode 5786: reward = -53.20, steps = 28 00:24:46 [INFO] train episode 5787: reward = -41.42, steps = 38 00:24:46 [INFO] train episode 5788: reward = -54.31, steps = 37 00:24:46 [INFO] train episode 5789: reward = -30.81, steps = 31 00:24:46 [INFO] train episode 5790: reward = -33.04, steps = 22 00:24:47 [INFO] train episode 5791: reward = -31.66, steps = 36 00:24:47 [INFO] train episode 5792: reward = -28.43, steps = 32 00:24:47 [INFO] train episode 5793: reward = -51.15, steps = 50 00:24:47 [INFO] train episode 5794: reward = -26.59, steps = 22 00:24:48 [INFO] train episode 5795: reward = -35.59, steps = 34 00:24:48 [INFO] train episode 5796: reward = -33.04, steps = 39 00:24:48 [INFO] train episode 5797: reward = -21.68, steps = 37 00:24:48 [INFO] train episode 5798: reward = -33.95, steps = 22 00:24:48 [INFO] train episode 5799: reward = -40.28, steps = 20 00:24:49 [INFO] train episode 5800: reward = -35.85, steps = 24 00:24:49 [INFO] train episode 5801: reward = -38.73, steps = 24 00:24:49 [INFO] train episode 5802: reward = -30.97, steps = 32 00:24:49 [INFO] train episode 5803: reward = -50.23, steps = 42 00:24:50 [INFO] train episode 5804: reward = -44.93, steps = 31 00:24:50 [INFO] train episode 5805: reward = -64.70, steps = 38 00:24:50 [INFO] train episode 5806: reward = -27.02, steps = 24 00:24:50 [INFO] train episode 5807: reward = -27.07, steps = 28 00:24:50 [INFO] train episode 5808: reward = -38.23, steps = 31 00:24:51 [INFO] train episode 5809: reward = -51.00, steps = 50 00:24:51 [INFO] train episode 5810: reward = -25.54, steps = 41 00:24:51 [INFO] train episode 5811: reward = -36.39, steps = 47 00:24:51 [INFO] train episode 5812: reward = -39.40, steps = 22 00:24:52 [INFO] train episode 5813: reward = -30.99, steps = 21 00:24:52 [INFO] train episode 5814: reward = -29.45, steps = 34 00:24:52 [INFO] train episode 5815: reward = -38.27, steps = 27 00:24:52 [INFO] train episode 5816: reward = -41.92, steps = 26 00:24:52 [INFO] train episode 5817: reward = -41.04, steps = 40 00:24:53 [INFO] train episode 5818: reward = -17.74, steps = 43 00:24:53 [INFO] train episode 5819: reward = -66.59, steps = 44 00:24:53 [INFO] train episode 5820: reward = -57.88, steps = 40 00:24:53 [INFO] train episode 5821: reward = -45.25, steps = 21 00:24:54 [INFO] train episode 5822: reward = -38.11, steps = 32 00:24:54 [INFO] train episode 5823: reward = -48.72, steps = 38 00:24:54 [INFO] train episode 5824: reward = -53.86, steps = 29 00:24:54 [INFO] train episode 5825: reward = -29.18, steps = 43 00:24:55 [INFO] train episode 5826: reward = -26.53, steps = 34 00:24:55 [INFO] train episode 5827: reward = -44.64, steps = 34 00:24:55 [INFO] train episode 5828: reward = -48.95, steps = 24 00:24:55 [INFO] train episode 5829: reward = -39.31, steps = 35 00:24:56 [INFO] train episode 5830: reward = -37.84, steps = 26 00:24:56 [INFO] train episode 5831: reward = -43.85, steps = 37 00:24:56 [INFO] train episode 5832: reward = -32.50, steps = 27 00:24:56 [INFO] train episode 5833: reward = -31.50, steps = 29 00:24:56 [INFO] train episode 5834: reward = -23.84, steps = 39 00:24:57 [INFO] train episode 5835: reward = -40.01, steps = 35 00:24:57 [INFO] train episode 5836: reward = -45.49, steps = 39 00:24:57 [INFO] train episode 5837: reward = -25.91, steps = 49 00:24:57 [INFO] train episode 5838: reward = -32.36, steps = 28 00:24:58 [INFO] train episode 5839: reward = -31.47, steps = 35 00:24:58 [INFO] train episode 5840: reward = -36.04, steps = 35 00:24:58 [INFO] train episode 5841: reward = -32.17, steps = 33 00:24:58 [INFO] train episode 5842: reward = -30.70, steps = 32 00:24:59 [INFO] train episode 5843: reward = -29.21, steps = 34 00:24:59 [INFO] train episode 5844: reward = -21.98, steps = 25 00:24:59 [INFO] train episode 5845: reward = -31.81, steps = 29 00:24:59 [INFO] train episode 5846: reward = -24.06, steps = 44 00:25:00 [INFO] train episode 5847: reward = -35.73, steps = 21 00:25:00 [INFO] train episode 5848: reward = -25.26, steps = 38 00:25:00 [INFO] train episode 5849: reward = -49.43, steps = 30 00:25:00 [INFO] train episode 5850: reward = -40.87, steps = 28 00:25:01 [INFO] train episode 5851: reward = -35.22, steps = 29 00:25:01 [INFO] train episode 5852: reward = -37.71, steps = 33 00:25:01 [INFO] train episode 5853: reward = -40.78, steps = 30 00:25:01 [INFO] train episode 5854: reward = -36.58, steps = 22 00:25:01 [INFO] train episode 5855: reward = -34.45, steps = 26 00:25:01 [INFO] train episode 5856: reward = -50.58, steps = 24 00:25:02 [INFO] train episode 5857: reward = -38.42, steps = 35 00:25:02 [INFO] train episode 5858: reward = -60.47, steps = 38 00:25:02 [INFO] train episode 5859: reward = -32.49, steps = 32 00:25:02 [INFO] train episode 5860: reward = -39.77, steps = 21 00:25:02 [INFO] train episode 5861: reward = -21.57, steps = 33 00:25:03 [INFO] train episode 5862: reward = -29.34, steps = 34 00:25:03 [INFO] train episode 5863: reward = -26.70, steps = 22 00:25:03 [INFO] train episode 5864: reward = -14.53, steps = 29 00:25:03 [INFO] train episode 5865: reward = -34.98, steps = 23 00:25:04 [INFO] train episode 5866: reward = -50.81, steps = 35 00:25:04 [INFO] train episode 5867: reward = -75.90, steps = 62 00:25:04 [INFO] train episode 5868: reward = -39.21, steps = 28 00:25:04 [INFO] train episode 5869: reward = -38.89, steps = 33 00:25:05 [INFO] train episode 5870: reward = -21.30, steps = 31 00:25:05 [INFO] train episode 5871: reward = -36.02, steps = 34 00:25:05 [INFO] train episode 5872: reward = -31.15, steps = 41 00:25:05 [INFO] train episode 5873: reward = -41.46, steps = 28 00:25:06 [INFO] train episode 5874: reward = -38.49, steps = 31 00:25:06 [INFO] train episode 5875: reward = -26.05, steps = 42 00:25:06 [INFO] train episode 5876: reward = -30.56, steps = 30 00:25:06 [INFO] train episode 5877: reward = -31.04, steps = 36 00:25:07 [INFO] train episode 5878: reward = -49.47, steps = 34 00:25:07 [INFO] train episode 5879: reward = -64.67, steps = 34 00:25:07 [INFO] train episode 5880: reward = -38.99, steps = 23 00:25:07 [INFO] train episode 5881: reward = -11.39, steps = 46 00:25:08 [INFO] train episode 5882: reward = -36.38, steps = 43 00:25:08 [INFO] train episode 5883: reward = -43.04, steps = 34 00:25:08 [INFO] train episode 5884: reward = -30.23, steps = 48 00:25:08 [INFO] train episode 5885: reward = -51.71, steps = 19 00:25:09 [INFO] train episode 5886: reward = -24.72, steps = 32 00:25:09 [INFO] train episode 5887: reward = -29.52, steps = 22 00:25:09 [INFO] train episode 5888: reward = -37.72, steps = 39 00:25:09 [INFO] train episode 5889: reward = -32.57, steps = 27 00:25:09 [INFO] train episode 5890: reward = -60.22, steps = 38 00:25:10 [INFO] train episode 5891: reward = -38.87, steps = 20 00:25:10 [INFO] train episode 5892: reward = -49.59, steps = 44 00:25:10 [INFO] train episode 5893: reward = -33.81, steps = 30 00:25:10 [INFO] train episode 5894: reward = -25.72, steps = 31 00:25:11 [INFO] train episode 5895: reward = -32.26, steps = 30 00:25:11 [INFO] train episode 5896: reward = -29.32, steps = 23 00:25:11 [INFO] train episode 5897: reward = -57.12, steps = 19 00:25:11 [INFO] train episode 5898: reward = -30.44, steps = 27 00:25:11 [INFO] train episode 5899: reward = -35.15, steps = 24 00:25:11 [INFO] train episode 5900: reward = -39.46, steps = 43 00:25:12 [INFO] train episode 5901: reward = -29.00, steps = 31 00:25:12 [INFO] train episode 5902: reward = -49.08, steps = 29 00:25:12 [INFO] train episode 5903: reward = -32.99, steps = 32 00:25:12 [INFO] train episode 5904: reward = -30.80, steps = 24 00:25:12 [INFO] train episode 5905: reward = -30.18, steps = 29 00:25:13 [INFO] train episode 5906: reward = -30.50, steps = 22 00:25:13 [INFO] train episode 5907: reward = -41.04, steps = 39 00:25:13 [INFO] train episode 5908: reward = -47.15, steps = 30 00:25:14 [INFO] train episode 5909: reward = -33.87, steps = 26 00:25:14 [INFO] train episode 5910: reward = -47.34, steps = 33 00:25:14 [INFO] train episode 5911: reward = -38.74, steps = 39 00:25:14 [INFO] train episode 5912: reward = -34.27, steps = 28 00:25:14 [INFO] train episode 5913: reward = -39.28, steps = 41 00:25:15 [INFO] train episode 5914: reward = -61.64, steps = 26 00:25:15 [INFO] train episode 5915: reward = -34.30, steps = 21 00:25:15 [INFO] train episode 5916: reward = -30.46, steps = 22 00:25:15 [INFO] train episode 5917: reward = -57.53, steps = 28 00:25:15 [INFO] train episode 5918: reward = -38.18, steps = 21 00:25:16 [INFO] train episode 5919: reward = -50.65, steps = 32 00:25:16 [INFO] train episode 5920: reward = -35.57, steps = 39 00:25:16 [INFO] train episode 5921: reward = -47.25, steps = 26 00:25:16 [INFO] train episode 5922: reward = -36.48, steps = 30 00:25:16 [INFO] train episode 5923: reward = -32.69, steps = 35 00:25:17 [INFO] train episode 5924: reward = -26.45, steps = 28 00:25:17 [INFO] train episode 5925: reward = -56.23, steps = 45 00:25:17 [INFO] train episode 5926: reward = -21.82, steps = 40 00:25:17 [INFO] train episode 5927: reward = -62.99, steps = 34 00:25:18 [INFO] train episode 5928: reward = -40.59, steps = 36 00:25:18 [INFO] train episode 5929: reward = -46.22, steps = 35 00:25:18 [INFO] train episode 5930: reward = -50.62, steps = 54 00:25:18 [INFO] train episode 5931: reward = -39.39, steps = 31 00:25:19 [INFO] train episode 5932: reward = -30.20, steps = 33 00:25:19 [INFO] train episode 5933: reward = -55.36, steps = 30 00:25:19 [INFO] train episode 5934: reward = -39.64, steps = 32 00:25:19 [INFO] train episode 5935: reward = -33.07, steps = 41 00:25:20 [INFO] train episode 5936: reward = -50.32, steps = 29 00:25:20 [INFO] train episode 5937: reward = -42.71, steps = 29 00:25:20 [INFO] train episode 5938: reward = -32.08, steps = 28 00:25:20 [INFO] train episode 5939: reward = -29.37, steps = 38 00:25:20 [INFO] train episode 5940: reward = -28.63, steps = 22 00:25:21 [INFO] train episode 5941: reward = -34.06, steps = 32 00:25:21 [INFO] train episode 5942: reward = -54.47, steps = 21 00:25:21 [INFO] train episode 5943: reward = -31.61, steps = 24 00:25:21 [INFO] train episode 5944: reward = -42.88, steps = 21 00:25:21 [INFO] train episode 5945: reward = -50.65, steps = 34 00:25:21 [INFO] train episode 5946: reward = -30.94, steps = 35 00:25:22 [INFO] train episode 5947: reward = -46.90, steps = 34 00:25:22 [INFO] train episode 5948: reward = -23.10, steps = 35 00:25:22 [INFO] train episode 5949: reward = -20.59, steps = 36 00:25:22 [INFO] train episode 5950: reward = -78.39, steps = 38 00:25:23 [INFO] train episode 5951: reward = -48.95, steps = 36 00:25:23 [INFO] train episode 5952: reward = -36.29, steps = 27 00:25:23 [INFO] train episode 5953: reward = -50.76, steps = 27 00:25:23 [INFO] train episode 5954: reward = -31.71, steps = 22 00:25:23 [INFO] train episode 5955: reward = -21.21, steps = 32 00:25:24 [INFO] train episode 5956: reward = -41.32, steps = 36 00:25:24 [INFO] train episode 5957: reward = -48.83, steps = 28 00:25:24 [INFO] train episode 5958: reward = -27.43, steps = 31 00:25:24 [INFO] train episode 5959: reward = -61.79, steps = 53 00:25:25 [INFO] train episode 5960: reward = -40.56, steps = 32 00:25:25 [INFO] train episode 5961: reward = -79.15, steps = 41 00:25:25 [INFO] train episode 5962: reward = -23.01, steps = 31 00:25:25 [INFO] train episode 5963: reward = -55.20, steps = 47 00:25:26 [INFO] train episode 5964: reward = -34.75, steps = 30 00:25:26 [INFO] train episode 5965: reward = -46.48, steps = 17 00:25:26 [INFO] train episode 5966: reward = -41.80, steps = 30 00:25:26 [INFO] train episode 5967: reward = -31.18, steps = 33 00:25:27 [INFO] train episode 5968: reward = -56.52, steps = 64 00:25:27 [INFO] train episode 5969: reward = -31.56, steps = 27 00:25:27 [INFO] train episode 5970: reward = -40.63, steps = 31 00:25:27 [INFO] train episode 5971: reward = -40.61, steps = 17 00:25:28 [INFO] train episode 5972: reward = -39.05, steps = 42 00:25:28 [INFO] train episode 5973: reward = -32.25, steps = 23 00:25:28 [INFO] train episode 5974: reward = -42.64, steps = 20 00:25:28 [INFO] train episode 5975: reward = -33.26, steps = 32 00:25:28 [INFO] train episode 5976: reward = -55.54, steps = 26 00:25:29 [INFO] train episode 5977: reward = -40.98, steps = 50 00:25:29 [INFO] train episode 5978: reward = -34.97, steps = 36 00:25:29 [INFO] train episode 5979: reward = -49.33, steps = 43 00:25:29 [INFO] train episode 5980: reward = -40.22, steps = 33 00:25:30 [INFO] train episode 5981: reward = -43.31, steps = 21 00:25:30 [INFO] train episode 5982: reward = -4.79, steps = 45 00:25:30 [INFO] train episode 5983: reward = -40.66, steps = 20 00:25:30 [INFO] train episode 5984: reward = -30.75, steps = 26 00:25:31 [INFO] train episode 5985: reward = -40.67, steps = 38 00:25:31 [INFO] train episode 5986: reward = -35.25, steps = 31 00:25:31 [INFO] train episode 5987: reward = -57.46, steps = 36 00:25:31 [INFO] train episode 5988: reward = -36.41, steps = 20 00:25:31 [INFO] train episode 5989: reward = -51.42, steps = 42 00:25:32 [INFO] train episode 5990: reward = -53.05, steps = 42 00:25:32 [INFO] train episode 5991: reward = -16.65, steps = 30 00:25:32 [INFO] train episode 5992: reward = -41.59, steps = 26 00:25:32 [INFO] train episode 5993: reward = -49.51, steps = 22 00:25:32 [INFO] train episode 5994: reward = -35.84, steps = 33 00:25:33 [INFO] train episode 5995: reward = -16.17, steps = 43 00:25:33 [INFO] train episode 5996: reward = -34.83, steps = 29 00:25:33 [INFO] train episode 5997: reward = -26.87, steps = 23 00:25:33 [INFO] train episode 5998: reward = -36.18, steps = 21 00:25:33 [INFO] train episode 5999: reward = -48.57, steps = 42 00:25:34 [INFO] train episode 6000: reward = -38.63, steps = 49 00:25:34 [INFO] train episode 6001: reward = -48.52, steps = 34 00:25:34 [INFO] train episode 6002: reward = -39.26, steps = 33 00:25:34 [INFO] train episode 6003: reward = -39.13, steps = 34 00:25:35 [INFO] train episode 6004: reward = -40.94, steps = 21 00:25:35 [INFO] train episode 6005: reward = -36.43, steps = 27 00:25:35 [INFO] train episode 6006: reward = -59.92, steps = 33 00:25:35 [INFO] train episode 6007: reward = -38.09, steps = 33 00:25:35 [INFO] train episode 6008: reward = -24.30, steps = 17 00:25:36 [INFO] train episode 6009: reward = -41.55, steps = 32 00:25:36 [INFO] train episode 6010: reward = -57.67, steps = 41 00:25:36 [INFO] train episode 6011: reward = -62.28, steps = 35 00:25:36 [INFO] train episode 6012: reward = -47.79, steps = 45 00:25:37 [INFO] train episode 6013: reward = -40.19, steps = 34 00:25:37 [INFO] train episode 6014: reward = -34.52, steps = 28 00:25:37 [INFO] train episode 6015: reward = -53.01, steps = 42 00:25:37 [INFO] train episode 6016: reward = -37.65, steps = 31 00:25:38 [INFO] train episode 6017: reward = -46.85, steps = 41 00:25:38 [INFO] train episode 6018: reward = -22.35, steps = 34 00:25:38 [INFO] train episode 6019: reward = -41.23, steps = 33 00:25:38 [INFO] train episode 6020: reward = -23.80, steps = 33 00:25:38 [INFO] train episode 6021: reward = -30.87, steps = 35 00:25:39 [INFO] train episode 6022: reward = -40.77, steps = 36 00:25:39 [INFO] train episode 6023: reward = -61.29, steps = 36 00:25:39 [INFO] train episode 6024: reward = -39.24, steps = 36 00:25:39 [INFO] train episode 6025: reward = -40.17, steps = 35 00:25:40 [INFO] train episode 6026: reward = -47.38, steps = 32 00:25:40 [INFO] train episode 6027: reward = -43.09, steps = 29 00:25:40 [INFO] train episode 6028: reward = -22.76, steps = 37 00:25:41 [INFO] train episode 6029: reward = -56.08, steps = 24 00:25:41 [INFO] train episode 6030: reward = -30.38, steps = 23 00:25:41 [INFO] train episode 6031: reward = -40.17, steps = 29 00:25:41 [INFO] train episode 6032: reward = -33.62, steps = 35 00:25:41 [INFO] train episode 6033: reward = -25.32, steps = 39 00:25:42 [INFO] train episode 6034: reward = -49.06, steps = 21 00:25:42 [INFO] train episode 6035: reward = -39.28, steps = 29 00:25:42 [INFO] train episode 6036: reward = -23.60, steps = 46 00:25:42 [INFO] train episode 6037: reward = -35.87, steps = 36 00:25:43 [INFO] train episode 6038: reward = -38.40, steps = 26 00:25:43 [INFO] train episode 6039: reward = -34.31, steps = 36 00:25:43 [INFO] train episode 6040: reward = -29.80, steps = 45 00:25:43 [INFO] train episode 6041: reward = -47.56, steps = 26 00:25:43 [INFO] train episode 6042: reward = -35.89, steps = 27 00:25:44 [INFO] train episode 6043: reward = -34.18, steps = 28 00:25:44 [INFO] train episode 6044: reward = -74.42, steps = 45 00:25:44 [INFO] train episode 6045: reward = -31.62, steps = 20 00:25:44 [INFO] train episode 6046: reward = -41.04, steps = 40 00:25:45 [INFO] train episode 6047: reward = -45.62, steps = 24 00:25:45 [INFO] train episode 6048: reward = -24.23, steps = 38 00:25:45 [INFO] train episode 6049: reward = -38.79, steps = 35 00:25:45 [INFO] train episode 6050: reward = -49.01, steps = 29 00:25:46 [INFO] train episode 6051: reward = -37.69, steps = 31 00:25:46 [INFO] train episode 6052: reward = -22.42, steps = 42 00:25:46 [INFO] train episode 6053: reward = -35.85, steps = 26 00:25:46 [INFO] train episode 6054: reward = -44.46, steps = 21 00:25:46 [INFO] train episode 6055: reward = -49.18, steps = 26 00:25:47 [INFO] train episode 6056: reward = -53.50, steps = 36 00:25:47 [INFO] train episode 6057: reward = -19.69, steps = 31 00:25:47 [INFO] train episode 6058: reward = -42.28, steps = 24 00:25:47 [INFO] train episode 6059: reward = -40.53, steps = 24 00:25:47 [INFO] train episode 6060: reward = -29.54, steps = 25 00:25:47 [INFO] train episode 6061: reward = -43.77, steps = 36 00:25:48 [INFO] train episode 6062: reward = -57.80, steps = 36 00:25:48 [INFO] train episode 6063: reward = -16.23, steps = 23 00:25:48 [INFO] train episode 6064: reward = -42.73, steps = 45 00:25:48 [INFO] train episode 6065: reward = -31.66, steps = 25 00:25:49 [INFO] train episode 6066: reward = -41.23, steps = 65 00:25:49 [INFO] train episode 6067: reward = -42.06, steps = 27 00:25:49 [INFO] train episode 6068: reward = -43.55, steps = 40 00:25:49 [INFO] train episode 6069: reward = -35.48, steps = 21 00:25:49 [INFO] train episode 6070: reward = -28.46, steps = 21 00:25:50 [INFO] train episode 6071: reward = -51.39, steps = 30 00:25:50 [INFO] train episode 6072: reward = -38.67, steps = 34 00:25:50 [INFO] train episode 6073: reward = -48.55, steps = 41 00:25:50 [INFO] train episode 6074: reward = -36.07, steps = 35 00:25:51 [INFO] train episode 6075: reward = -40.24, steps = 31 00:25:51 [INFO] train episode 6076: reward = -50.50, steps = 35 00:25:51 [INFO] train episode 6077: reward = -38.45, steps = 28 00:25:51 [INFO] train episode 6078: reward = -41.66, steps = 31 00:25:51 [INFO] train episode 6079: reward = -39.93, steps = 25 00:25:52 [INFO] train episode 6080: reward = -64.85, steps = 49 00:25:52 [INFO] train episode 6081: reward = -34.19, steps = 38 00:25:52 [INFO] train episode 6082: reward = -50.76, steps = 32 00:25:52 [INFO] train episode 6083: reward = -30.20, steps = 22 00:25:53 [INFO] train episode 6084: reward = -52.21, steps = 36 00:25:53 [INFO] train episode 6085: reward = -49.75, steps = 29 00:25:53 [INFO] train episode 6086: reward = -81.22, steps = 42 00:25:53 [INFO] train episode 6087: reward = -32.44, steps = 26 00:25:54 [INFO] train episode 6088: reward = -35.57, steps = 45 00:25:54 [INFO] train episode 6089: reward = -32.52, steps = 32 00:25:54 [INFO] train episode 6090: reward = -29.58, steps = 44 00:25:55 [INFO] train episode 6091: reward = -39.20, steps = 37 00:25:55 [INFO] train episode 6092: reward = -44.82, steps = 28 00:25:55 [INFO] train episode 6093: reward = -33.79, steps = 22 00:25:55 [INFO] train episode 6094: reward = -41.71, steps = 27 00:25:55 [INFO] train episode 6095: reward = -39.16, steps = 30 00:25:56 [INFO] train episode 6096: reward = -33.38, steps = 45 00:25:56 [INFO] train episode 6097: reward = -43.03, steps = 24 00:25:56 [INFO] train episode 6098: reward = -40.64, steps = 35 00:25:56 [INFO] train episode 6099: reward = -21.92, steps = 38 00:25:56 [INFO] train episode 6100: reward = -39.45, steps = 26 00:25:57 [INFO] train episode 6101: reward = -44.16, steps = 32 00:25:57 [INFO] train episode 6102: reward = -47.59, steps = 22 00:25:57 [INFO] train episode 6103: reward = -36.95, steps = 19 00:25:57 [INFO] train episode 6104: reward = -51.65, steps = 35 00:25:57 [INFO] train episode 6105: reward = -31.96, steps = 18 00:25:58 [INFO] train episode 6106: reward = -55.28, steps = 42 00:25:58 [INFO] train episode 6107: reward = -54.86, steps = 31 00:25:58 [INFO] train episode 6108: reward = -44.36, steps = 28 00:25:58 [INFO] train episode 6109: reward = -32.45, steps = 28 00:25:58 [INFO] train episode 6110: reward = -29.03, steps = 27 00:25:59 [INFO] train episode 6111: reward = -36.77, steps = 27 00:25:59 [INFO] train episode 6112: reward = -51.64, steps = 38 00:25:59 [INFO] train episode 6113: reward = -55.69, steps = 33 00:25:59 [INFO] train episode 6114: reward = -33.20, steps = 27 00:26:00 [INFO] train episode 6115: reward = -42.25, steps = 40 00:26:00 [INFO] train episode 6116: reward = -38.30, steps = 39 00:26:00 [INFO] train episode 6117: reward = -36.68, steps = 44 00:26:00 [INFO] train episode 6118: reward = -43.53, steps = 31 00:26:00 [INFO] train episode 6119: reward = -38.18, steps = 24 00:26:01 [INFO] train episode 6120: reward = -31.73, steps = 24 00:26:01 [INFO] train episode 6121: reward = -59.11, steps = 40 00:26:01 [INFO] train episode 6122: reward = -28.02, steps = 26 00:26:01 [INFO] train episode 6123: reward = -58.19, steps = 23 00:26:01 [INFO] train episode 6124: reward = -43.08, steps = 31 00:26:02 [INFO] train episode 6125: reward = -48.62, steps = 36 00:26:02 [INFO] train episode 6126: reward = -28.53, steps = 39 00:26:02 [INFO] train episode 6127: reward = -47.11, steps = 31 00:26:02 [INFO] train episode 6128: reward = -56.10, steps = 37 00:26:03 [INFO] train episode 6129: reward = -42.65, steps = 48 00:26:03 [INFO] train episode 6130: reward = -47.81, steps = 32 00:26:03 [INFO] train episode 6131: reward = -48.86, steps = 42 00:26:03 [INFO] train episode 6132: reward = -42.54, steps = 23 00:26:04 [INFO] train episode 6133: reward = -32.91, steps = 29 00:26:04 [INFO] train episode 6134: reward = -37.14, steps = 29 00:26:04 [INFO] train episode 6135: reward = -47.54, steps = 29 00:26:04 [INFO] train episode 6136: reward = -31.90, steps = 25 00:26:04 [INFO] train episode 6137: reward = -65.70, steps = 45 00:26:05 [INFO] train episode 6138: reward = -28.63, steps = 21 00:26:05 [INFO] train episode 6139: reward = -38.07, steps = 30 00:26:05 [INFO] train episode 6140: reward = -32.08, steps = 27 00:26:05 [INFO] train episode 6141: reward = -56.86, steps = 36 00:26:05 [INFO] train episode 6142: reward = -34.97, steps = 34 00:26:06 [INFO] train episode 6143: reward = -47.31, steps = 30 00:26:06 [INFO] train episode 6144: reward = -31.15, steps = 22 00:26:06 [INFO] train episode 6145: reward = -72.42, steps = 29 00:26:06 [INFO] train episode 6146: reward = -42.14, steps = 23 00:26:06 [INFO] train episode 6147: reward = -32.67, steps = 38 00:26:07 [INFO] train episode 6148: reward = -62.34, steps = 36 00:26:07 [INFO] train episode 6149: reward = -44.45, steps = 26 00:26:07 [INFO] train episode 6150: reward = -31.30, steps = 37 00:26:08 [INFO] train episode 6151: reward = -28.99, steps = 25 00:26:08 [INFO] train episode 6152: reward = -55.57, steps = 48 00:26:08 [INFO] train episode 6153: reward = -65.59, steps = 40 00:26:08 [INFO] train episode 6154: reward = -25.54, steps = 27 00:26:09 [INFO] train episode 6155: reward = -35.12, steps = 36 00:26:09 [INFO] train episode 6156: reward = -42.98, steps = 45 00:26:09 [INFO] train episode 6157: reward = -64.01, steps = 40 00:26:09 [INFO] train episode 6158: reward = -21.20, steps = 38 00:26:10 [INFO] train episode 6159: reward = -44.72, steps = 37 00:26:10 [INFO] train episode 6160: reward = -29.39, steps = 35 00:26:10 [INFO] train episode 6161: reward = -33.21, steps = 24 00:26:10 [INFO] train episode 6162: reward = -24.35, steps = 38 00:26:10 [INFO] train episode 6163: reward = -42.43, steps = 30 00:26:11 [INFO] train episode 6164: reward = -54.73, steps = 33 00:26:11 [INFO] train episode 6165: reward = -29.81, steps = 37 00:26:11 [INFO] train episode 6166: reward = -38.32, steps = 30 00:26:11 [INFO] train episode 6167: reward = -33.82, steps = 34 00:26:12 [INFO] train episode 6168: reward = -49.09, steps = 26 00:26:12 [INFO] train episode 6169: reward = -81.22, steps = 45 00:26:12 [INFO] train episode 6170: reward = -45.62, steps = 32 00:26:12 [INFO] train episode 6171: reward = -46.51, steps = 24 00:26:13 [INFO] train episode 6172: reward = -66.68, steps = 42 00:26:13 [INFO] train episode 6173: reward = -34.91, steps = 23 00:26:13 [INFO] train episode 6174: reward = -48.26, steps = 23 00:26:13 [INFO] train episode 6175: reward = -45.69, steps = 23 00:26:13 [INFO] train episode 6176: reward = -61.15, steps = 34 00:26:13 [INFO] train episode 6177: reward = -43.68, steps = 38 00:26:14 [INFO] train episode 6178: reward = -59.76, steps = 38 00:26:14 [INFO] train episode 6179: reward = -42.33, steps = 25 00:26:14 [INFO] train episode 6180: reward = -38.73, steps = 22 00:26:14 [INFO] train episode 6181: reward = -32.34, steps = 41 00:26:15 [INFO] train episode 6182: reward = -31.61, steps = 30 00:26:15 [INFO] train episode 6183: reward = -33.37, steps = 25 00:26:15 [INFO] train episode 6184: reward = -41.56, steps = 21 00:26:15 [INFO] train episode 6185: reward = -49.18, steps = 51 00:26:16 [INFO] train episode 6186: reward = -28.73, steps = 22 00:26:16 [INFO] train episode 6187: reward = -34.57, steps = 31 00:26:16 [INFO] train episode 6188: reward = -34.20, steps = 31 00:26:16 [INFO] train episode 6189: reward = -34.57, steps = 21 00:26:17 [INFO] train episode 6190: reward = -45.08, steps = 37 00:26:17 [INFO] train episode 6191: reward = -46.34, steps = 27 00:26:17 [INFO] train episode 6192: reward = -44.52, steps = 36 00:26:17 [INFO] train episode 6193: reward = -58.19, steps = 29 00:26:18 [INFO] train episode 6194: reward = -45.64, steps = 33 00:26:18 [INFO] train episode 6195: reward = -38.56, steps = 33 00:26:18 [INFO] train episode 6196: reward = -40.64, steps = 19 00:26:18 [INFO] train episode 6197: reward = -43.24, steps = 34 00:26:18 [INFO] train episode 6198: reward = -28.65, steps = 30 00:26:19 [INFO] train episode 6199: reward = -58.42, steps = 31 00:26:19 [INFO] train episode 6200: reward = -20.30, steps = 31 00:26:19 [INFO] train episode 6201: reward = -48.89, steps = 50 00:26:19 [INFO] train episode 6202: reward = -30.28, steps = 25 00:26:20 [INFO] train episode 6203: reward = -52.40, steps = 39 00:26:20 [INFO] train episode 6204: reward = -24.05, steps = 27 00:26:20 [INFO] train episode 6205: reward = -21.89, steps = 36 00:26:20 [INFO] train episode 6206: reward = -40.69, steps = 24 00:26:20 [INFO] train episode 6207: reward = -31.73, steps = 32 00:26:21 [INFO] train episode 6208: reward = -35.40, steps = 29 00:26:21 [INFO] train episode 6209: reward = -14.46, steps = 34 00:26:21 [INFO] train episode 6210: reward = -69.62, steps = 38 00:26:21 [INFO] train episode 6211: reward = -35.68, steps = 27 00:26:22 [INFO] train episode 6212: reward = -60.89, steps = 38 00:26:22 [INFO] train episode 6213: reward = -64.50, steps = 40 00:26:22 [INFO] train episode 6214: reward = -46.66, steps = 31 00:26:22 [INFO] train episode 6215: reward = -49.35, steps = 26 00:26:23 [INFO] train episode 6216: reward = -34.27, steps = 22 00:26:23 [INFO] train episode 6217: reward = -80.75, steps = 66 00:26:23 [INFO] train episode 6218: reward = -43.97, steps = 46 00:26:24 [INFO] train episode 6219: reward = -48.66, steps = 36 00:26:24 [INFO] train episode 6220: reward = -32.65, steps = 19 00:26:24 [INFO] train episode 6221: reward = -47.26, steps = 21 00:26:24 [INFO] train episode 6222: reward = -40.96, steps = 24 00:26:24 [INFO] train episode 6223: reward = -53.99, steps = 39 00:26:25 [INFO] train episode 6224: reward = -13.82, steps = 44 00:26:25 [INFO] train episode 6225: reward = -23.50, steps = 43 00:26:25 [INFO] train episode 6226: reward = -37.50, steps = 39 00:26:25 [INFO] train episode 6227: reward = -23.13, steps = 43 00:26:26 [INFO] train episode 6228: reward = -52.31, steps = 27 00:26:26 [INFO] train episode 6229: reward = -55.03, steps = 39 00:26:26 [INFO] train episode 6230: reward = -39.86, steps = 34 00:26:26 [INFO] train episode 6231: reward = -50.83, steps = 24 00:26:27 [INFO] train episode 6232: reward = -42.31, steps = 37 00:26:27 [INFO] train episode 6233: reward = -56.44, steps = 28 00:26:27 [INFO] train episode 6234: reward = -52.86, steps = 36 00:26:27 [INFO] train episode 6235: reward = -49.79, steps = 44 00:26:27 [INFO] train episode 6236: reward = -32.80, steps = 23 00:26:28 [INFO] train episode 6237: reward = -65.73, steps = 45 00:26:28 [INFO] train episode 6238: reward = -21.40, steps = 38 00:26:28 [INFO] train episode 6239: reward = -34.86, steps = 25 00:26:28 [INFO] train episode 6240: reward = -32.34, steps = 31 00:26:29 [INFO] train episode 6241: reward = -56.17, steps = 34 00:26:29 [INFO] train episode 6242: reward = -34.82, steps = 56 00:26:29 [INFO] train episode 6243: reward = -36.90, steps = 40 00:26:29 [INFO] train episode 6244: reward = -30.81, steps = 24 00:26:30 [INFO] train episode 6245: reward = -53.33, steps = 29 00:26:30 [INFO] train episode 6246: reward = -25.85, steps = 22 00:26:30 [INFO] train episode 6247: reward = -19.09, steps = 22 00:26:30 [INFO] train episode 6248: reward = -56.73, steps = 32 00:26:30 [INFO] train episode 6249: reward = -48.67, steps = 37 00:26:31 [INFO] train episode 6250: reward = -73.56, steps = 36 00:26:31 [INFO] train episode 6251: reward = -31.40, steps = 25 00:26:31 [INFO] train episode 6252: reward = -32.58, steps = 49 00:26:31 [INFO] train episode 6253: reward = -36.96, steps = 25 00:26:32 [INFO] train episode 6254: reward = -46.66, steps = 41 00:26:32 [INFO] train episode 6255: reward = -45.41, steps = 21 00:26:32 [INFO] train episode 6256: reward = -48.93, steps = 41 00:26:32 [INFO] train episode 6257: reward = -41.39, steps = 31 00:26:32 [INFO] train episode 6258: reward = -32.09, steps = 21 00:26:33 [INFO] train episode 6259: reward = -35.90, steps = 32 00:26:33 [INFO] train episode 6260: reward = -44.27, steps = 28 00:26:33 [INFO] train episode 6261: reward = -37.99, steps = 30 00:26:33 [INFO] train episode 6262: reward = -60.99, steps = 40 00:26:34 [INFO] train episode 6263: reward = -35.24, steps = 45 00:26:34 [INFO] train episode 6264: reward = -61.38, steps = 31 00:26:34 [INFO] train episode 6265: reward = -24.49, steps = 41 00:26:34 [INFO] train episode 6266: reward = -61.63, steps = 51 00:26:35 [INFO] train episode 6267: reward = -43.58, steps = 22 00:26:35 [INFO] train episode 6268: reward = -21.22, steps = 45 00:26:35 [INFO] train episode 6269: reward = -55.73, steps = 40 00:26:36 [INFO] train episode 6270: reward = -25.88, steps = 22 00:26:36 [INFO] train episode 6271: reward = -42.89, steps = 45 00:26:36 [INFO] train episode 6272: reward = -48.03, steps = 36 00:26:36 [INFO] train episode 6273: reward = -39.83, steps = 35 00:26:37 [INFO] train episode 6274: reward = -35.40, steps = 38 00:26:37 [INFO] train episode 6275: reward = -33.11, steps = 24 00:26:37 [INFO] train episode 6276: reward = -51.56, steps = 32 00:26:37 [INFO] train episode 6277: reward = -64.59, steps = 44 00:26:38 [INFO] train episode 6278: reward = -37.48, steps = 39 00:26:38 [INFO] train episode 6279: reward = -30.88, steps = 32 00:26:38 [INFO] train episode 6280: reward = -57.00, steps = 31 00:26:38 [INFO] train episode 6281: reward = -26.30, steps = 23 00:26:38 [INFO] train episode 6282: reward = -27.10, steps = 24 00:26:39 [INFO] train episode 6283: reward = -58.14, steps = 45 00:26:39 [INFO] train episode 6284: reward = -41.43, steps = 32 00:26:39 [INFO] train episode 6285: reward = -38.51, steps = 33 00:26:39 [INFO] train episode 6286: reward = -35.45, steps = 32 00:26:39 [INFO] train episode 6287: reward = -26.60, steps = 21 00:26:40 [INFO] train episode 6288: reward = -39.94, steps = 35 00:26:40 [INFO] train episode 6289: reward = -27.21, steps = 29 00:26:40 [INFO] train episode 6290: reward = -66.80, steps = 29 00:26:40 [INFO] train episode 6291: reward = -42.78, steps = 28 00:26:41 [INFO] train episode 6292: reward = -64.03, steps = 42 00:26:41 [INFO] train episode 6293: reward = -32.97, steps = 27 00:26:41 [INFO] train episode 6294: reward = -34.27, steps = 38 00:26:41 [INFO] train episode 6295: reward = -67.99, steps = 40 00:26:42 [INFO] train episode 6296: reward = -49.12, steps = 37 00:26:42 [INFO] train episode 6297: reward = -35.71, steps = 21 00:26:42 [INFO] train episode 6298: reward = -42.51, steps = 22 00:26:42 [INFO] train episode 6299: reward = -37.49, steps = 37 00:26:42 [INFO] train episode 6300: reward = -24.97, steps = 31 00:26:43 [INFO] train episode 6301: reward = -28.55, steps = 25 00:26:43 [INFO] train episode 6302: reward = -31.32, steps = 31 00:26:43 [INFO] train episode 6303: reward = -24.29, steps = 21 00:26:43 [INFO] train episode 6304: reward = -51.83, steps = 38 00:26:43 [INFO] train episode 6305: reward = -36.55, steps = 36 00:26:44 [INFO] train episode 6306: reward = -33.49, steps = 24 00:26:44 [INFO] train episode 6307: reward = -39.95, steps = 50 00:26:44 [INFO] train episode 6308: reward = -40.62, steps = 23 00:26:44 [INFO] train episode 6309: reward = -40.94, steps = 42 00:26:45 [INFO] train episode 6310: reward = -49.40, steps = 25 00:26:45 [INFO] train episode 6311: reward = -32.13, steps = 27 00:26:45 [INFO] train episode 6312: reward = -48.32, steps = 30 00:26:45 [INFO] train episode 6313: reward = -15.41, steps = 32 00:26:45 [INFO] train episode 6314: reward = -28.95, steps = 28 00:26:46 [INFO] train episode 6315: reward = -82.54, steps = 38 00:26:46 [INFO] train episode 6316: reward = -44.70, steps = 34 00:26:46 [INFO] train episode 6317: reward = -36.97, steps = 29 00:26:46 [INFO] train episode 6318: reward = -46.64, steps = 34 00:26:46 [INFO] train episode 6319: reward = -34.79, steps = 35 00:26:47 [INFO] train episode 6320: reward = -18.12, steps = 37 00:26:47 [INFO] train episode 6321: reward = -31.01, steps = 24 00:26:47 [INFO] train episode 6322: reward = -57.98, steps = 32 00:26:47 [INFO] train episode 6323: reward = -38.86, steps = 32 00:26:48 [INFO] train episode 6324: reward = -40.22, steps = 29 00:26:48 [INFO] train episode 6325: reward = -32.19, steps = 26 00:26:48 [INFO] train episode 6326: reward = -34.34, steps = 25 00:26:48 [INFO] train episode 6327: reward = -58.70, steps = 27 00:26:48 [INFO] train episode 6328: reward = -36.29, steps = 27 00:26:48 [INFO] train episode 6329: reward = -39.73, steps = 23 00:26:49 [INFO] train episode 6330: reward = -50.93, steps = 43 00:26:49 [INFO] train episode 6331: reward = -57.49, steps = 47 00:26:49 [INFO] train episode 6332: reward = -29.03, steps = 37 00:26:50 [INFO] train episode 6333: reward = -31.59, steps = 26 00:26:50 [INFO] train episode 6334: reward = -43.96, steps = 48 00:26:50 [INFO] train episode 6335: reward = -54.94, steps = 29 00:26:50 [INFO] train episode 6336: reward = -44.71, steps = 25 00:26:51 [INFO] train episode 6337: reward = -49.59, steps = 33 00:26:51 [INFO] train episode 6338: reward = -28.27, steps = 35 00:26:51 [INFO] train episode 6339: reward = -64.55, steps = 44 00:26:51 [INFO] train episode 6340: reward = -32.46, steps = 26 00:26:51 [INFO] train episode 6341: reward = -57.20, steps = 40 00:26:52 [INFO] train episode 6342: reward = -42.01, steps = 37 00:26:52 [INFO] train episode 6343: reward = -63.50, steps = 56 00:26:52 [INFO] train episode 6344: reward = -45.40, steps = 24 00:26:52 [INFO] train episode 6345: reward = -40.18, steps = 26 00:26:53 [INFO] train episode 6346: reward = -20.45, steps = 46 00:26:53 [INFO] train episode 6347: reward = -49.50, steps = 31 00:26:53 [INFO] train episode 6348: reward = -34.60, steps = 26 00:26:53 [INFO] train episode 6349: reward = -31.92, steps = 34 00:26:54 [INFO] train episode 6350: reward = -32.62, steps = 31 00:26:54 [INFO] train episode 6351: reward = -25.50, steps = 26 00:26:54 [INFO] train episode 6352: reward = -42.31, steps = 31 00:26:54 [INFO] train episode 6353: reward = -39.79, steps = 22 00:26:54 [INFO] train episode 6354: reward = -68.51, steps = 31 00:26:55 [INFO] train episode 6355: reward = -60.99, steps = 21 00:26:55 [INFO] train episode 6356: reward = -39.62, steps = 20 00:26:55 [INFO] train episode 6357: reward = -45.94, steps = 32 00:26:55 [INFO] train episode 6358: reward = -47.50, steps = 25 00:26:55 [INFO] train episode 6359: reward = -33.94, steps = 23 00:26:55 [INFO] train episode 6360: reward = -49.25, steps = 32 00:26:56 [INFO] train episode 6361: reward = -42.28, steps = 29 00:26:56 [INFO] train episode 6362: reward = -29.40, steps = 22 00:26:56 [INFO] train episode 6363: reward = -40.32, steps = 38 00:26:56 [INFO] train episode 6364: reward = -37.02, steps = 28 00:26:56 [INFO] train episode 6365: reward = -44.72, steps = 26 00:26:57 [INFO] train episode 6366: reward = -43.75, steps = 36 00:26:57 [INFO] train episode 6367: reward = -31.48, steps = 24 00:26:57 [INFO] train episode 6368: reward = -36.31, steps = 29 00:26:57 [INFO] train episode 6369: reward = -23.15, steps = 29 00:26:57 [INFO] train episode 6370: reward = -33.72, steps = 33 00:26:58 [INFO] train episode 6371: reward = -50.29, steps = 34 00:26:58 [INFO] train episode 6372: reward = -47.48, steps = 34 00:26:58 [INFO] train episode 6373: reward = -46.93, steps = 35 00:26:58 [INFO] train episode 6374: reward = -36.26, steps = 45 00:26:59 [INFO] train episode 6375: reward = -60.80, steps = 32 00:26:59 [INFO] train episode 6376: reward = -38.66, steps = 34 00:26:59 [INFO] train episode 6377: reward = -34.45, steps = 27 00:26:59 [INFO] train episode 6378: reward = -62.83, steps = 29 00:27:00 [INFO] train episode 6379: reward = -40.05, steps = 31 00:27:00 [INFO] train episode 6380: reward = -36.33, steps = 40 00:27:00 [INFO] train episode 6381: reward = -51.88, steps = 31 00:27:00 [INFO] train episode 6382: reward = -32.20, steps = 34 00:27:00 [INFO] train episode 6383: reward = -34.05, steps = 24 00:27:01 [INFO] train episode 6384: reward = -38.57, steps = 25 00:27:01 [INFO] train episode 6385: reward = -49.67, steps = 27 00:27:01 [INFO] train episode 6386: reward = -40.48, steps = 26 00:27:01 [INFO] train episode 6387: reward = -30.21, steps = 36 00:27:01 [INFO] train episode 6388: reward = -42.30, steps = 32 00:27:02 [INFO] train episode 6389: reward = -48.84, steps = 26 00:27:02 [INFO] train episode 6390: reward = -33.01, steps = 27 00:27:02 [INFO] train episode 6391: reward = -38.30, steps = 38 00:27:02 [INFO] train episode 6392: reward = -32.23, steps = 20 00:27:03 [INFO] train episode 6393: reward = -38.93, steps = 30 00:27:03 [INFO] train episode 6394: reward = -32.09, steps = 21 00:27:03 [INFO] train episode 6395: reward = -5.31, steps = 47 00:27:03 [INFO] train episode 6396: reward = -44.02, steps = 22 00:27:04 [INFO] train episode 6397: reward = -29.50, steps = 31 00:27:04 [INFO] train episode 6398: reward = -47.59, steps = 43 00:27:04 [INFO] train episode 6399: reward = -63.47, steps = 46 00:27:04 [INFO] train episode 6400: reward = -25.61, steps = 33 00:27:05 [INFO] train episode 6401: reward = -40.53, steps = 35 00:27:05 [INFO] train episode 6402: reward = -22.07, steps = 45 00:27:05 [INFO] train episode 6403: reward = -25.63, steps = 34 00:27:05 [INFO] train episode 6404: reward = -26.97, steps = 25 00:27:06 [INFO] train episode 6405: reward = -38.89, steps = 26 00:27:06 [INFO] train episode 6406: reward = -36.09, steps = 27 00:27:06 [INFO] train episode 6407: reward = -21.46, steps = 21 00:27:06 [INFO] train episode 6408: reward = -56.15, steps = 44 00:27:06 [INFO] train episode 6409: reward = -58.18, steps = 44 00:27:07 [INFO] train episode 6410: reward = -36.30, steps = 23 00:27:07 [INFO] train episode 6411: reward = -42.68, steps = 23 00:27:07 [INFO] train episode 6412: reward = -43.38, steps = 25 00:27:07 [INFO] train episode 6413: reward = -37.03, steps = 34 00:27:07 [INFO] train episode 6414: reward = -31.21, steps = 29 00:27:08 [INFO] train episode 6415: reward = -35.98, steps = 33 00:27:08 [INFO] train episode 6416: reward = -74.17, steps = 47 00:27:08 [INFO] train episode 6417: reward = -66.59, steps = 33 00:27:08 [INFO] train episode 6418: reward = -55.88, steps = 27 00:27:09 [INFO] train episode 6419: reward = -37.57, steps = 26 00:27:09 [INFO] train episode 6420: reward = -35.53, steps = 25 00:27:09 [INFO] train episode 6421: reward = -39.17, steps = 22 00:27:09 [INFO] train episode 6422: reward = -51.34, steps = 35 00:27:09 [INFO] train episode 6423: reward = -39.84, steps = 23 00:27:10 [INFO] train episode 6424: reward = -36.64, steps = 36 00:27:10 [INFO] train episode 6425: reward = -32.29, steps = 37 00:27:10 [INFO] train episode 6426: reward = -32.72, steps = 21 00:27:10 [INFO] train episode 6427: reward = -40.19, steps = 32 00:27:10 [INFO] train episode 6428: reward = -49.15, steps = 27 00:27:11 [INFO] train episode 6429: reward = -48.75, steps = 36 00:27:11 [INFO] train episode 6430: reward = -38.14, steps = 34 00:27:11 [INFO] train episode 6431: reward = -41.68, steps = 33 00:27:11 [INFO] train episode 6432: reward = -24.76, steps = 26 00:27:11 [INFO] train episode 6433: reward = -27.88, steps = 34 00:27:12 [INFO] train episode 6434: reward = -49.39, steps = 47 00:27:12 [INFO] train episode 6435: reward = -37.97, steps = 29 00:27:12 [INFO] train episode 6436: reward = -17.96, steps = 34 00:27:12 [INFO] train episode 6437: reward = -31.24, steps = 22 00:27:13 [INFO] train episode 6438: reward = -38.63, steps = 24 00:27:13 [INFO] train episode 6439: reward = -27.63, steps = 29 00:27:13 [INFO] train episode 6440: reward = -47.13, steps = 25 00:27:13 [INFO] train episode 6441: reward = -43.15, steps = 28 00:27:13 [INFO] train episode 6442: reward = -62.98, steps = 41 00:27:14 [INFO] train episode 6443: reward = -57.22, steps = 25 00:27:14 [INFO] train episode 6444: reward = -44.81, steps = 29 00:27:14 [INFO] train episode 6445: reward = -43.45, steps = 23 00:27:14 [INFO] train episode 6446: reward = -51.04, steps = 46 00:27:14 [INFO] train episode 6447: reward = -38.59, steps = 35 00:27:15 [INFO] train episode 6448: reward = -22.25, steps = 41 00:27:15 [INFO] train episode 6449: reward = -45.31, steps = 36 00:27:15 [INFO] train episode 6450: reward = -45.79, steps = 30 00:27:15 [INFO] train episode 6451: reward = -36.65, steps = 36 00:27:16 [INFO] train episode 6452: reward = -41.27, steps = 40 00:27:16 [INFO] train episode 6453: reward = -42.42, steps = 31 00:27:16 [INFO] train episode 6454: reward = -29.80, steps = 41 00:27:17 [INFO] train episode 6455: reward = -52.60, steps = 27 00:27:17 [INFO] train episode 6456: reward = -52.62, steps = 24 00:27:17 [INFO] train episode 6457: reward = -41.53, steps = 23 00:27:17 [INFO] train episode 6458: reward = -40.11, steps = 18 00:27:17 [INFO] train episode 6459: reward = -21.73, steps = 37 00:27:17 [INFO] train episode 6460: reward = -30.19, steps = 22 00:27:18 [INFO] train episode 6461: reward = -35.12, steps = 31 00:27:18 [INFO] train episode 6462: reward = -65.46, steps = 53 00:27:18 [INFO] train episode 6463: reward = -55.79, steps = 46 00:27:19 [INFO] train episode 6464: reward = -57.21, steps = 46 00:27:19 [INFO] train episode 6465: reward = -30.91, steps = 47 00:27:19 [INFO] train episode 6466: reward = -57.20, steps = 28 00:27:19 [INFO] train episode 6467: reward = -67.66, steps = 39 00:27:20 [INFO] train episode 6468: reward = -21.77, steps = 45 00:27:20 [INFO] train episode 6469: reward = -51.75, steps = 36 00:27:20 [INFO] train episode 6470: reward = -46.71, steps = 22 00:27:20 [INFO] train episode 6471: reward = -56.72, steps = 35 00:27:21 [INFO] train episode 6472: reward = -37.02, steps = 29 00:27:21 [INFO] train episode 6473: reward = -48.67, steps = 26 00:27:21 [INFO] train episode 6474: reward = -41.05, steps = 29 00:27:21 [INFO] train episode 6475: reward = -61.75, steps = 24 00:27:21 [INFO] train episode 6476: reward = -41.38, steps = 30 00:27:21 [INFO] train episode 6477: reward = -38.58, steps = 28 00:27:22 [INFO] train episode 6478: reward = -24.26, steps = 18 00:27:22 [INFO] train episode 6479: reward = -37.49, steps = 32 00:27:22 [INFO] train episode 6480: reward = -28.18, steps = 25 00:27:22 [INFO] train episode 6481: reward = -41.46, steps = 20 00:27:22 [INFO] train episode 6482: reward = -26.65, steps = 41 00:27:23 [INFO] train episode 6483: reward = -61.54, steps = 34 00:27:23 [INFO] train episode 6484: reward = -36.57, steps = 39 00:27:23 [INFO] train episode 6485: reward = -41.65, steps = 40 00:27:23 [INFO] train episode 6486: reward = -40.71, steps = 38 00:27:24 [INFO] train episode 6487: reward = -54.60, steps = 39 00:27:24 [INFO] train episode 6488: reward = -45.35, steps = 34 00:27:24 [INFO] train episode 6489: reward = -28.59, steps = 31 00:27:24 [INFO] train episode 6490: reward = -32.84, steps = 25 00:27:25 [INFO] train episode 6491: reward = -30.82, steps = 39 00:27:25 [INFO] train episode 6492: reward = -88.03, steps = 92 00:27:25 [INFO] train episode 6493: reward = -25.87, steps = 33 00:27:26 [INFO] train episode 6494: reward = -51.82, steps = 32 00:27:26 [INFO] train episode 6495: reward = -35.23, steps = 23 00:27:26 [INFO] train episode 6496: reward = -41.43, steps = 40 00:27:26 [INFO] train episode 6497: reward = -53.29, steps = 39 00:27:27 [INFO] train episode 6498: reward = -28.43, steps = 27 00:27:27 [INFO] train episode 6499: reward = -43.20, steps = 32 00:27:27 [INFO] train episode 6500: reward = -45.16, steps = 29 00:27:27 [INFO] train episode 6501: reward = -67.54, steps = 42 00:27:27 [INFO] train episode 6502: reward = -32.29, steps = 23 00:27:28 [INFO] train episode 6503: reward = -35.80, steps = 27 00:27:28 [INFO] train episode 6504: reward = -51.73, steps = 33 00:27:28 [INFO] train episode 6505: reward = -30.45, steps = 31 00:27:28 [INFO] train episode 6506: reward = -89.54, steps = 71 00:27:29 [INFO] train episode 6507: reward = -33.53, steps = 23 00:27:29 [INFO] train episode 6508: reward = -38.59, steps = 28 00:27:29 [INFO] train episode 6509: reward = -48.00, steps = 32 00:27:29 [INFO] train episode 6510: reward = -43.43, steps = 28 00:27:30 [INFO] train episode 6511: reward = -41.15, steps = 26 00:27:30 [INFO] train episode 6512: reward = -50.54, steps = 23 00:27:30 [INFO] train episode 6513: reward = -13.64, steps = 45 00:27:30 [INFO] train episode 6514: reward = -71.16, steps = 38 00:27:31 [INFO] train episode 6515: reward = -28.02, steps = 43 00:27:31 [INFO] train episode 6516: reward = -66.79, steps = 34 00:27:31 [INFO] train episode 6517: reward = -39.00, steps = 24 00:27:31 [INFO] train episode 6518: reward = -39.95, steps = 26 00:27:32 [INFO] train episode 6519: reward = -43.74, steps = 38 00:27:32 [INFO] train episode 6520: reward = -42.56, steps = 36 00:27:32 [INFO] train episode 6521: reward = -45.39, steps = 18 00:27:32 [INFO] train episode 6522: reward = -34.77, steps = 26 00:27:32 [INFO] train episode 6523: reward = -50.27, steps = 32 00:27:33 [INFO] train episode 6524: reward = -42.42, steps = 23 00:27:33 [INFO] train episode 6525: reward = -24.37, steps = 31 00:27:33 [INFO] train episode 6526: reward = -37.84, steps = 38 00:27:33 [INFO] train episode 6527: reward = -64.10, steps = 35 00:27:34 [INFO] train episode 6528: reward = -40.06, steps = 35 00:27:34 [INFO] train episode 6529: reward = -47.78, steps = 44 00:27:34 [INFO] train episode 6530: reward = -59.85, steps = 52 00:27:34 [INFO] train episode 6531: reward = -38.72, steps = 31 00:27:35 [INFO] train episode 6532: reward = -61.12, steps = 56 00:27:35 [INFO] train episode 6533: reward = -75.78, steps = 86 00:27:35 [INFO] train episode 6534: reward = -36.31, steps = 36 00:27:36 [INFO] train episode 6535: reward = -26.85, steps = 35 00:27:36 [INFO] train episode 6536: reward = -53.77, steps = 28 00:27:36 [INFO] train episode 6537: reward = -42.16, steps = 40 00:27:36 [INFO] train episode 6538: reward = -42.56, steps = 42 00:27:37 [INFO] train episode 6539: reward = -43.61, steps = 20 00:27:37 [INFO] train episode 6540: reward = -22.75, steps = 32 00:27:37 [INFO] train episode 6541: reward = -32.82, steps = 33 00:27:37 [INFO] train episode 6542: reward = -44.33, steps = 32 00:27:37 [INFO] train episode 6543: reward = -29.51, steps = 33 00:27:38 [INFO] train episode 6544: reward = -33.56, steps = 21 00:27:38 [INFO] train episode 6545: reward = -37.27, steps = 24 00:27:38 [INFO] train episode 6546: reward = -38.67, steps = 35 00:27:38 [INFO] train episode 6547: reward = -57.52, steps = 51 00:27:39 [INFO] train episode 6548: reward = -23.59, steps = 34 00:27:39 [INFO] train episode 6549: reward = -35.49, steps = 23 00:27:39 [INFO] train episode 6550: reward = -74.14, steps = 63 00:27:39 [INFO] train episode 6551: reward = -52.74, steps = 40 00:27:40 [INFO] train episode 6552: reward = -49.36, steps = 26 00:27:40 [INFO] train episode 6553: reward = -74.68, steps = 38 00:27:40 [INFO] train episode 6554: reward = -31.10, steps = 24 00:27:40 [INFO] train episode 6555: reward = -43.04, steps = 26 00:27:40 [INFO] train episode 6556: reward = -42.73, steps = 26 00:27:41 [INFO] train episode 6557: reward = -38.37, steps = 22 00:27:41 [INFO] train episode 6558: reward = -36.07, steps = 27 00:27:41 [INFO] train episode 6559: reward = -38.98, steps = 43 00:27:41 [INFO] train episode 6560: reward = -51.18, steps = 54 00:27:42 [INFO] train episode 6561: reward = -48.58, steps = 35 00:27:42 [INFO] train episode 6562: reward = -51.86, steps = 29 00:27:42 [INFO] train episode 6563: reward = -31.93, steps = 34 00:27:42 [INFO] train episode 6564: reward = -48.53, steps = 30 00:27:42 [INFO] train episode 6565: reward = -37.51, steps = 36 00:27:43 [INFO] train episode 6566: reward = -38.13, steps = 16 00:27:43 [INFO] train episode 6567: reward = -54.21, steps = 30 00:27:43 [INFO] train episode 6568: reward = -27.73, steps = 36 00:27:44 [INFO] train episode 6569: reward = -24.96, steps = 49 00:27:44 [INFO] train episode 6570: reward = -42.03, steps = 41 00:27:44 [INFO] train episode 6571: reward = -22.09, steps = 49 00:27:44 [INFO] train episode 6572: reward = -27.61, steps = 27 00:27:45 [INFO] train episode 6573: reward = -35.49, steps = 27 00:27:45 [INFO] train episode 6574: reward = -43.69, steps = 36 00:27:45 [INFO] train episode 6575: reward = -53.67, steps = 42 00:27:45 [INFO] train episode 6576: reward = -50.82, steps = 44 00:27:46 [INFO] train episode 6577: reward = -58.90, steps = 25 00:27:46 [INFO] train episode 6578: reward = -50.09, steps = 37 00:27:46 [INFO] train episode 6579: reward = -36.81, steps = 27 00:27:46 [INFO] train episode 6580: reward = -40.79, steps = 38 00:27:47 [INFO] train episode 6581: reward = -28.22, steps = 19 00:27:47 [INFO] train episode 6582: reward = -52.06, steps = 40 00:27:47 [INFO] train episode 6583: reward = -54.10, steps = 52 00:27:47 [INFO] train episode 6584: reward = -43.82, steps = 25 00:27:47 [INFO] train episode 6585: reward = -37.94, steps = 26 00:27:48 [INFO] train episode 6586: reward = -39.52, steps = 25 00:27:48 [INFO] train episode 6587: reward = -35.17, steps = 47 00:27:48 [INFO] train episode 6588: reward = -34.89, steps = 29 00:27:48 [INFO] train episode 6589: reward = -38.19, steps = 23 00:27:48 [INFO] train episode 6590: reward = -40.59, steps = 21 00:27:49 [INFO] train episode 6591: reward = -53.99, steps = 29 00:27:49 [INFO] train episode 6592: reward = -40.85, steps = 20 00:27:49 [INFO] train episode 6593: reward = -43.55, steps = 28 00:27:49 [INFO] train episode 6594: reward = -66.72, steps = 28 00:27:49 [INFO] train episode 6595: reward = -40.32, steps = 27 00:27:50 [INFO] train episode 6596: reward = -41.12, steps = 20 00:27:50 [INFO] train episode 6597: reward = -30.96, steps = 23 00:27:50 [INFO] train episode 6598: reward = -36.48, steps = 28 00:27:50 [INFO] train episode 6599: reward = -22.64, steps = 25 00:27:50 [INFO] train episode 6600: reward = -38.10, steps = 20 00:27:51 [INFO] train episode 6601: reward = -53.42, steps = 34 00:27:51 [INFO] train episode 6602: reward = -41.92, steps = 29 00:27:51 [INFO] train episode 6603: reward = -46.61, steps = 23 00:27:51 [INFO] train episode 6604: reward = -33.17, steps = 31 00:27:51 [INFO] train episode 6605: reward = -40.41, steps = 40 00:27:52 [INFO] train episode 6606: reward = -55.69, steps = 38 00:27:52 [INFO] train episode 6607: reward = -51.56, steps = 37 00:27:52 [INFO] train episode 6608: reward = -52.78, steps = 28 00:27:52 [INFO] train episode 6609: reward = -33.25, steps = 33 00:27:53 [INFO] train episode 6610: reward = -45.53, steps = 26 00:27:53 [INFO] train episode 6611: reward = -38.37, steps = 21 00:27:53 [INFO] train episode 6612: reward = -45.98, steps = 29 00:27:53 [INFO] train episode 6613: reward = -64.89, steps = 50 00:27:53 [INFO] train episode 6614: reward = -37.63, steps = 31 00:27:54 [INFO] train episode 6615: reward = -29.54, steps = 22 00:27:54 [INFO] train episode 6616: reward = -18.70, steps = 51 00:27:54 [INFO] train episode 6617: reward = -29.74, steps = 29 00:27:54 [INFO] train episode 6618: reward = -48.91, steps = 37 00:27:55 [INFO] train episode 6619: reward = -43.25, steps = 41 00:27:55 [INFO] train episode 6620: reward = -93.35, steps = 82 00:27:55 [INFO] train episode 6621: reward = -33.96, steps = 23 00:27:56 [INFO] train episode 6622: reward = -55.39, steps = 28 00:27:56 [INFO] train episode 6623: reward = -37.97, steps = 24 00:27:56 [INFO] train episode 6624: reward = -46.45, steps = 44 00:27:56 [INFO] train episode 6625: reward = -44.79, steps = 30 00:27:56 [INFO] train episode 6626: reward = -51.45, steps = 27 00:27:57 [INFO] train episode 6627: reward = -53.35, steps = 31 00:27:57 [INFO] train episode 6628: reward = -24.72, steps = 30 00:27:57 [INFO] train episode 6629: reward = -43.75, steps = 38 00:27:58 [INFO] train episode 6630: reward = -49.58, steps = 26 00:27:58 [INFO] train episode 6631: reward = -96.30, steps = 57 00:27:58 [INFO] train episode 6632: reward = -38.60, steps = 25 00:27:58 [INFO] train episode 6633: reward = -36.98, steps = 29 00:27:59 [INFO] train episode 6634: reward = -29.54, steps = 32 00:27:59 [INFO] train episode 6635: reward = -25.19, steps = 40 00:27:59 [INFO] train episode 6636: reward = -32.20, steps = 20 00:27:59 [INFO] train episode 6637: reward = -22.82, steps = 25 00:27:59 [INFO] train episode 6638: reward = -41.87, steps = 25 00:28:00 [INFO] train episode 6639: reward = -46.54, steps = 37 00:28:00 [INFO] train episode 6640: reward = -45.69, steps = 32 00:28:00 [INFO] train episode 6641: reward = -28.81, steps = 39 00:28:00 [INFO] train episode 6642: reward = -8.81, steps = 43 00:28:01 [INFO] train episode 6643: reward = -53.32, steps = 30 00:28:01 [INFO] train episode 6644: reward = -36.59, steps = 28 00:28:01 [INFO] train episode 6645: reward = -25.92, steps = 46 00:28:01 [INFO] train episode 6646: reward = -61.82, steps = 38 00:28:02 [INFO] train episode 6647: reward = -26.13, steps = 38 00:28:02 [INFO] train episode 6648: reward = -36.43, steps = 23 00:28:02 [INFO] train episode 6649: reward = -37.22, steps = 45 00:28:02 [INFO] train episode 6650: reward = -32.86, steps = 21 00:28:02 [INFO] train episode 6651: reward = -36.65, steps = 22 00:28:03 [INFO] train episode 6652: reward = -36.23, steps = 22 00:28:03 [INFO] train episode 6653: reward = -47.95, steps = 43 00:28:03 [INFO] train episode 6654: reward = -36.89, steps = 29 00:28:03 [INFO] train episode 6655: reward = -47.77, steps = 35 00:28:04 [INFO] train episode 6656: reward = -42.55, steps = 42 00:28:04 [INFO] train episode 6657: reward = -39.47, steps = 21 00:28:04 [INFO] train episode 6658: reward = -31.90, steps = 30 00:28:04 [INFO] train episode 6659: reward = -78.41, steps = 55 00:28:04 [INFO] train episode 6660: reward = -48.84, steps = 33 00:28:05 [INFO] train episode 6661: reward = -30.54, steps = 33 00:28:05 [INFO] train episode 6662: reward = -41.31, steps = 23 00:28:05 [INFO] train episode 6663: reward = -29.04, steps = 36 00:28:05 [INFO] train episode 6664: reward = -23.28, steps = 35 00:28:06 [INFO] train episode 6665: reward = -58.31, steps = 34 00:28:06 [INFO] train episode 6666: reward = -52.65, steps = 38 00:28:06 [INFO] train episode 6667: reward = -40.95, steps = 32 00:28:06 [INFO] train episode 6668: reward = -27.60, steps = 28 00:28:06 [INFO] train episode 6669: reward = -42.01, steps = 25 00:28:07 [INFO] train episode 6670: reward = -55.43, steps = 36 00:28:07 [INFO] train episode 6671: reward = -31.82, steps = 37 00:28:07 [INFO] train episode 6672: reward = -28.43, steps = 42 00:28:07 [INFO] train episode 6673: reward = -36.44, steps = 38 00:28:08 [INFO] train episode 6674: reward = -45.28, steps = 31 00:28:08 [INFO] train episode 6675: reward = -57.10, steps = 57 00:28:08 [INFO] train episode 6676: reward = -49.31, steps = 32 00:28:08 [INFO] train episode 6677: reward = -23.95, steps = 36 00:28:09 [INFO] train episode 6678: reward = -37.74, steps = 26 00:28:09 [INFO] train episode 6679: reward = -20.30, steps = 25 00:28:09 [INFO] train episode 6680: reward = -42.85, steps = 24 00:28:09 [INFO] train episode 6681: reward = -42.25, steps = 38 00:28:09 [INFO] train episode 6682: reward = -41.39, steps = 23 00:28:10 [INFO] train episode 6683: reward = -40.92, steps = 43 00:28:10 [INFO] train episode 6684: reward = -30.23, steps = 27 00:28:10 [INFO] train episode 6685: reward = -40.59, steps = 29 00:28:10 [INFO] train episode 6686: reward = -54.74, steps = 36 00:28:11 [INFO] train episode 6687: reward = -21.30, steps = 40 00:28:11 [INFO] train episode 6688: reward = -48.87, steps = 29 00:28:11 [INFO] train episode 6689: reward = -53.44, steps = 31 00:28:11 [INFO] train episode 6690: reward = -33.13, steps = 43 00:28:12 [INFO] train episode 6691: reward = -42.09, steps = 21 00:28:12 [INFO] train episode 6692: reward = -34.70, steps = 21 00:28:12 [INFO] train episode 6693: reward = -32.94, steps = 30 00:28:12 [INFO] train episode 6694: reward = -38.74, steps = 36 00:28:12 [INFO] train episode 6695: reward = -40.20, steps = 31 00:28:13 [INFO] train episode 6696: reward = -29.83, steps = 21 00:28:13 [INFO] train episode 6697: reward = -47.39, steps = 31 00:28:13 [INFO] train episode 6698: reward = -37.71, steps = 33 00:28:13 [INFO] train episode 6699: reward = -29.49, steps = 36 00:28:14 [INFO] train episode 6700: reward = -28.00, steps = 38 00:28:14 [INFO] train episode 6701: reward = -38.46, steps = 27 00:28:14 [INFO] train episode 6702: reward = -25.99, steps = 30 00:28:14 [INFO] train episode 6703: reward = -36.11, steps = 27 00:28:14 [INFO] train episode 6704: reward = -44.01, steps = 35 00:28:15 [INFO] train episode 6705: reward = -35.65, steps = 31 00:28:15 [INFO] train episode 6706: reward = -42.54, steps = 30 00:28:15 [INFO] train episode 6707: reward = -29.24, steps = 22 00:28:15 [INFO] train episode 6708: reward = -59.95, steps = 60 00:28:16 [INFO] train episode 6709: reward = -44.65, steps = 35 00:28:16 [INFO] train episode 6710: reward = -32.63, steps = 27 00:28:16 [INFO] train episode 6711: reward = -43.76, steps = 28 00:28:16 [INFO] train episode 6712: reward = -29.91, steps = 23 00:28:16 [INFO] train episode 6713: reward = -30.90, steps = 39 00:28:17 [INFO] train episode 6714: reward = -31.96, steps = 20 00:28:17 [INFO] train episode 6715: reward = -42.96, steps = 22 00:28:17 [INFO] train episode 6716: reward = -38.13, steps = 37 00:28:17 [INFO] train episode 6717: reward = -53.25, steps = 39 00:28:18 [INFO] train episode 6718: reward = -27.51, steps = 30 00:28:18 [INFO] train episode 6719: reward = -58.29, steps = 38 00:28:18 [INFO] train episode 6720: reward = -26.21, steps = 26 00:28:18 [INFO] train episode 6721: reward = -52.59, steps = 32 00:28:18 [INFO] train episode 6722: reward = -24.80, steps = 28 00:28:19 [INFO] train episode 6723: reward = -33.66, steps = 33 00:28:19 [INFO] train episode 6724: reward = -40.54, steps = 22 00:28:19 [INFO] train episode 6725: reward = -38.33, steps = 22 00:28:19 [INFO] train episode 6726: reward = -39.73, steps = 33 00:28:19 [INFO] train episode 6727: reward = -37.84, steps = 39 00:28:20 [INFO] train episode 6728: reward = -49.11, steps = 49 00:28:20 [INFO] train episode 6729: reward = -33.51, steps = 26 00:28:20 [INFO] train episode 6730: reward = -41.05, steps = 24 00:28:20 [INFO] train episode 6731: reward = -46.44, steps = 22 00:28:21 [INFO] train episode 6732: reward = -32.03, steps = 43 00:28:21 [INFO] train episode 6733: reward = -58.75, steps = 29 00:28:21 [INFO] train episode 6734: reward = -43.21, steps = 27 00:28:21 [INFO] train episode 6735: reward = -38.23, steps = 22 00:28:21 [INFO] train episode 6736: reward = -37.63, steps = 30 00:28:22 [INFO] train episode 6737: reward = -49.95, steps = 30 00:28:22 [INFO] train episode 6738: reward = -40.55, steps = 39 00:28:22 [INFO] train episode 6739: reward = -35.80, steps = 58 00:28:22 [INFO] train episode 6740: reward = -28.26, steps = 34 00:28:23 [INFO] train episode 6741: reward = -36.87, steps = 37 00:28:23 [INFO] train episode 6742: reward = -54.75, steps = 46 00:28:23 [INFO] train episode 6743: reward = -32.97, steps = 37 00:28:23 [INFO] train episode 6744: reward = -57.38, steps = 38 00:28:24 [INFO] train episode 6745: reward = -40.82, steps = 29 00:28:24 [INFO] train episode 6746: reward = -24.51, steps = 42 00:28:24 [INFO] train episode 6747: reward = -43.68, steps = 20 00:28:25 [INFO] train episode 6748: reward = -48.75, steps = 33 00:28:25 [INFO] train episode 6749: reward = -41.28, steps = 48 00:28:25 [INFO] train episode 6750: reward = -31.35, steps = 22 00:28:25 [INFO] train episode 6751: reward = -15.50, steps = 41 00:28:26 [INFO] train episode 6752: reward = -37.40, steps = 31 00:28:26 [INFO] train episode 6753: reward = -34.45, steps = 20 00:28:26 [INFO] train episode 6754: reward = -61.75, steps = 58 00:28:26 [INFO] train episode 6755: reward = -39.11, steps = 35 00:28:27 [INFO] train episode 6756: reward = -46.92, steps = 29 00:28:27 [INFO] train episode 6757: reward = -41.22, steps = 33 00:28:27 [INFO] train episode 6758: reward = -38.77, steps = 49 00:28:27 [INFO] train episode 6759: reward = -31.76, steps = 39 00:28:28 [INFO] train episode 6760: reward = -46.03, steps = 39 00:28:28 [INFO] train episode 6761: reward = -36.30, steps = 25 00:28:28 [INFO] train episode 6762: reward = -51.81, steps = 36 00:28:28 [INFO] train episode 6763: reward = -31.81, steps = 49 00:28:29 [INFO] train episode 6764: reward = -52.95, steps = 31 00:28:29 [INFO] train episode 6765: reward = -28.73, steps = 39 00:28:29 [INFO] train episode 6766: reward = -75.58, steps = 49 00:28:29 [INFO] train episode 6767: reward = -39.90, steps = 17 00:28:30 [INFO] train episode 6768: reward = -37.55, steps = 41 00:28:30 [INFO] train episode 6769: reward = -24.34, steps = 22 00:28:30 [INFO] train episode 6770: reward = -32.81, steps = 45 00:28:30 [INFO] train episode 6771: reward = -43.88, steps = 27 00:28:30 [INFO] train episode 6772: reward = -49.32, steps = 28 00:28:31 [INFO] train episode 6773: reward = -39.57, steps = 28 00:28:31 [INFO] train episode 6774: reward = -46.03, steps = 22 00:28:31 [INFO] train episode 6775: reward = -85.81, steps = 56 00:28:31 [INFO] train episode 6776: reward = -32.84, steps = 38 00:28:32 [INFO] train episode 6777: reward = -36.73, steps = 26 00:28:32 [INFO] train episode 6778: reward = -48.61, steps = 40 00:28:32 [INFO] train episode 6779: reward = -54.86, steps = 53 00:28:32 [INFO] train episode 6780: reward = -37.38, steps = 38 00:28:33 [INFO] train episode 6781: reward = -44.00, steps = 27 00:28:33 [INFO] train episode 6782: reward = -47.74, steps = 42 00:28:33 [INFO] train episode 6783: reward = -54.18, steps = 40 00:28:34 [INFO] train episode 6784: reward = -80.52, steps = 55 00:28:34 [INFO] train episode 6785: reward = -43.53, steps = 44 00:28:34 [INFO] train episode 6786: reward = -39.54, steps = 47 00:28:34 [INFO] train episode 6787: reward = -63.27, steps = 41 00:28:35 [INFO] train episode 6788: reward = -47.90, steps = 61 00:28:35 [INFO] train episode 6789: reward = -25.97, steps = 28 00:28:35 [INFO] train episode 6790: reward = -37.79, steps = 27 00:28:35 [INFO] train episode 6791: reward = -37.53, steps = 22 00:28:36 [INFO] train episode 6792: reward = -33.26, steps = 56 00:28:36 [INFO] train episode 6793: reward = -32.92, steps = 31 00:28:36 [INFO] train episode 6794: reward = -60.45, steps = 27 00:28:36 [INFO] train episode 6795: reward = -39.53, steps = 32 00:28:37 [INFO] train episode 6796: reward = -27.58, steps = 35 00:28:37 [INFO] train episode 6797: reward = -38.25, steps = 30 00:28:37 [INFO] train episode 6798: reward = -38.84, steps = 24 00:28:37 [INFO] train episode 6799: reward = -36.38, steps = 22 00:28:37 [INFO] train episode 6800: reward = -30.55, steps = 34 00:28:38 [INFO] train episode 6801: reward = -20.76, steps = 38 00:28:38 [INFO] train episode 6802: reward = -38.91, steps = 27 00:28:38 [INFO] train episode 6803: reward = -38.60, steps = 26 00:28:38 [INFO] train episode 6804: reward = -36.91, steps = 27 00:28:39 [INFO] train episode 6805: reward = -35.04, steps = 22 00:28:39 [INFO] train episode 6806: reward = -41.28, steps = 21 00:28:39 [INFO] train episode 6807: reward = -32.51, steps = 34 00:28:39 [INFO] train episode 6808: reward = -79.32, steps = 42 00:28:39 [INFO] train episode 6809: reward = -36.74, steps = 44 00:28:40 [INFO] train episode 6810: reward = -30.26, steps = 45 00:28:40 [INFO] train episode 6811: reward = -118.70, steps = 91 00:28:41 [INFO] train episode 6812: reward = -43.33, steps = 23 00:28:41 [INFO] train episode 6813: reward = -34.72, steps = 22 00:28:41 [INFO] train episode 6814: reward = -40.09, steps = 28 00:28:41 [INFO] train episode 6815: reward = -46.66, steps = 37 00:28:41 [INFO] train episode 6816: reward = -40.15, steps = 21 00:28:41 [INFO] train episode 6817: reward = -39.75, steps = 19 00:28:42 [INFO] train episode 6818: reward = -39.71, steps = 32 00:28:42 [INFO] train episode 6819: reward = -40.21, steps = 34 00:28:42 [INFO] train episode 6820: reward = -38.12, steps = 24 00:28:42 [INFO] train episode 6821: reward = -42.72, steps = 46 00:28:43 [INFO] train episode 6822: reward = -30.71, steps = 35 00:28:43 [INFO] train episode 6823: reward = -95.17, steps = 57 00:28:43 [INFO] train episode 6824: reward = -46.68, steps = 41 00:28:43 [INFO] train episode 6825: reward = -31.42, steps = 44 00:28:44 [INFO] train episode 6826: reward = -34.13, steps = 37 00:28:44 [INFO] train episode 6827: reward = -36.68, steps = 21 00:28:44 [INFO] train episode 6828: reward = -42.75, steps = 35 00:28:44 [INFO] train episode 6829: reward = -22.03, steps = 37 00:28:45 [INFO] train episode 6830: reward = -84.28, steps = 46 00:28:45 [INFO] train episode 6831: reward = -29.80, steps = 31 00:28:45 [INFO] train episode 6832: reward = -45.97, steps = 30 00:28:45 [INFO] train episode 6833: reward = -34.97, steps = 23 00:28:45 [INFO] train episode 6834: reward = -45.45, steps = 25 00:28:46 [INFO] train episode 6835: reward = -41.90, steps = 24 00:28:46 [INFO] train episode 6836: reward = -51.51, steps = 41 00:28:46 [INFO] train episode 6837: reward = -76.39, steps = 33 00:28:46 [INFO] train episode 6838: reward = -45.81, steps = 29 00:28:47 [INFO] train episode 6839: reward = -57.41, steps = 35 00:28:47 [INFO] train episode 6840: reward = -17.01, steps = 31 00:28:47 [INFO] train episode 6841: reward = -34.08, steps = 28 00:28:47 [INFO] train episode 6842: reward = -35.20, steps = 47 00:28:47 [INFO] train episode 6843: reward = -39.10, steps = 27 00:28:48 [INFO] train episode 6844: reward = -31.37, steps = 44 00:28:48 [INFO] train episode 6845: reward = -33.50, steps = 22 00:28:48 [INFO] train episode 6846: reward = -54.75, steps = 47 00:28:49 [INFO] train episode 6847: reward = -70.84, steps = 62 00:28:49 [INFO] train episode 6848: reward = -37.20, steps = 24 00:28:49 [INFO] train episode 6849: reward = -43.87, steps = 32 00:28:49 [INFO] train episode 6850: reward = -46.42, steps = 43 00:28:50 [INFO] train episode 6851: reward = -26.91, steps = 31 00:28:50 [INFO] train episode 6852: reward = -27.83, steps = 31 00:28:50 [INFO] train episode 6853: reward = -41.53, steps = 31 00:28:50 [INFO] train episode 6854: reward = -32.44, steps = 23 00:28:50 [INFO] train episode 6855: reward = -55.58, steps = 39 00:28:51 [INFO] train episode 6856: reward = -36.20, steps = 28 00:28:51 [INFO] train episode 6857: reward = -42.76, steps = 27 00:28:51 [INFO] train episode 6858: reward = -36.20, steps = 24 00:28:51 [INFO] train episode 6859: reward = -44.47, steps = 25 00:28:51 [INFO] train episode 6860: reward = -16.00, steps = 30 00:28:52 [INFO] train episode 6861: reward = -61.55, steps = 40 00:28:52 [INFO] train episode 6862: reward = -47.96, steps = 48 00:28:52 [INFO] train episode 6863: reward = -34.87, steps = 25 00:28:53 [INFO] train episode 6864: reward = -41.98, steps = 58 00:28:53 [INFO] train episode 6865: reward = -31.22, steps = 36 00:28:53 [INFO] train episode 6866: reward = -59.77, steps = 43 00:28:53 [INFO] train episode 6867: reward = -42.66, steps = 27 00:28:54 [INFO] train episode 6868: reward = -19.25, steps = 51 00:28:54 [INFO] train episode 6869: reward = -18.63, steps = 38 00:28:54 [INFO] train episode 6870: reward = -78.70, steps = 43 00:28:55 [INFO] train episode 6871: reward = -32.60, steps = 29 00:28:55 [INFO] train episode 6872: reward = -69.94, steps = 34 00:28:55 [INFO] train episode 6873: reward = -67.92, steps = 52 00:28:55 [INFO] train episode 6874: reward = -59.70, steps = 28 00:28:55 [INFO] train episode 6875: reward = -41.39, steps = 24 00:28:56 [INFO] train episode 6876: reward = -35.09, steps = 21 00:28:56 [INFO] train episode 6877: reward = -37.96, steps = 43 00:28:56 [INFO] train episode 6878: reward = -58.23, steps = 28 00:28:56 [INFO] train episode 6879: reward = -25.86, steps = 32 00:28:57 [INFO] train episode 6880: reward = -36.24, steps = 32 00:28:57 [INFO] train episode 6881: reward = -33.07, steps = 32 00:28:57 [INFO] train episode 6882: reward = -34.41, steps = 26 00:28:57 [INFO] train episode 6883: reward = -20.67, steps = 58 00:28:58 [INFO] train episode 6884: reward = -37.81, steps = 31 00:28:58 [INFO] train episode 6885: reward = -55.31, steps = 43 00:28:58 [INFO] train episode 6886: reward = -28.63, steps = 23 00:28:58 [INFO] train episode 6887: reward = -24.42, steps = 25 00:28:58 [INFO] train episode 6888: reward = -63.08, steps = 48 00:28:59 [INFO] train episode 6889: reward = -40.53, steps = 39 00:28:59 [INFO] train episode 6890: reward = -33.27, steps = 31 00:28:59 [INFO] train episode 6891: reward = -24.57, steps = 27 00:28:59 [INFO] train episode 6892: reward = -30.69, steps = 27 00:29:00 [INFO] train episode 6893: reward = -57.14, steps = 36 00:29:00 [INFO] train episode 6894: reward = -32.76, steps = 32 00:29:00 [INFO] train episode 6895: reward = -33.92, steps = 39 00:29:00 [INFO] train episode 6896: reward = -26.53, steps = 36 00:29:01 [INFO] train episode 6897: reward = -61.70, steps = 49 00:29:01 [INFO] train episode 6898: reward = -44.17, steps = 37 00:29:01 [INFO] train episode 6899: reward = -40.77, steps = 21 00:29:01 [INFO] train episode 6900: reward = -38.32, steps = 32 00:29:02 [INFO] train episode 6901: reward = -53.81, steps = 42 00:29:02 [INFO] train episode 6902: reward = -49.38, steps = 27 00:29:03 [INFO] train episode 6903: reward = -36.58, steps = 20 00:29:03 [INFO] train episode 6904: reward = -41.39, steps = 25 00:29:03 [INFO] train episode 6905: reward = -33.90, steps = 31 00:29:03 [INFO] train episode 6906: reward = -41.10, steps = 36 00:29:03 [INFO] train episode 6907: reward = -22.55, steps = 25 00:29:04 [INFO] train episode 6908: reward = -32.59, steps = 42 00:29:04 [INFO] train episode 6909: reward = -73.42, steps = 39 00:29:05 [INFO] train episode 6910: reward = -47.60, steps = 37 00:29:05 [INFO] train episode 6911: reward = -32.29, steps = 31 00:29:05 [INFO] train episode 6912: reward = -30.34, steps = 23 00:29:05 [INFO] train episode 6913: reward = -38.45, steps = 31 00:29:06 [INFO] train episode 6914: reward = -11.76, steps = 46 00:29:06 [INFO] train episode 6915: reward = -36.42, steps = 36 00:29:06 [INFO] train episode 6916: reward = -77.36, steps = 42 00:29:07 [INFO] train episode 6917: reward = -51.30, steps = 41 00:29:07 [INFO] train episode 6918: reward = -93.41, steps = 61 00:29:08 [INFO] train episode 6919: reward = -56.67, steps = 21 00:29:08 [INFO] train episode 6920: reward = -56.19, steps = 51 00:29:08 [INFO] train episode 6921: reward = -47.80, steps = 32 00:29:08 [INFO] train episode 6922: reward = -58.84, steps = 38 00:29:09 [INFO] train episode 6923: reward = -55.43, steps = 59 00:29:09 [INFO] train episode 6924: reward = -36.46, steps = 31 00:29:09 [INFO] train episode 6925: reward = -59.37, steps = 31 00:29:09 [INFO] train episode 6926: reward = -60.95, steps = 35 00:29:10 [INFO] train episode 6927: reward = -30.94, steps = 36 00:29:10 [INFO] train episode 6928: reward = -29.17, steps = 35 00:29:10 [INFO] train episode 6929: reward = -57.17, steps = 36 00:29:10 [INFO] train episode 6930: reward = -32.44, steps = 22 00:29:11 [INFO] train episode 6931: reward = -25.11, steps = 41 00:29:11 [INFO] train episode 6932: reward = -14.72, steps = 38 00:29:11 [INFO] train episode 6933: reward = -19.01, steps = 26 00:29:11 [INFO] train episode 6934: reward = -65.80, steps = 40 00:29:11 [INFO] train episode 6935: reward = -34.85, steps = 18 00:29:12 [INFO] train episode 6936: reward = -59.17, steps = 43 00:29:12 [INFO] train episode 6937: reward = -26.81, steps = 31 00:29:12 [INFO] train episode 6938: reward = -62.96, steps = 39 00:29:12 [INFO] train episode 6939: reward = -49.51, steps = 35 00:29:13 [INFO] train episode 6940: reward = -26.69, steps = 30 00:29:13 [INFO] train episode 6941: reward = -46.17, steps = 31 00:29:13 [INFO] train episode 6942: reward = -45.95, steps = 55 00:29:13 [INFO] train episode 6943: reward = -20.38, steps = 40 00:29:14 [INFO] train episode 6944: reward = -55.50, steps = 67 00:29:14 [INFO] train episode 6945: reward = -27.75, steps = 30 00:29:14 [INFO] train episode 6946: reward = -46.55, steps = 41 00:29:15 [INFO] train episode 6947: reward = -17.57, steps = 39 00:29:15 [INFO] train episode 6948: reward = -61.19, steps = 33 00:29:15 [INFO] train episode 6949: reward = -28.12, steps = 41 00:29:15 [INFO] train episode 6950: reward = -53.11, steps = 38 00:29:16 [INFO] train episode 6951: reward = -44.75, steps = 52 00:29:16 [INFO] train episode 6952: reward = -20.28, steps = 31 00:29:16 [INFO] train episode 6953: reward = -41.06, steps = 21 00:29:16 [INFO] train episode 6954: reward = -46.48, steps = 31 00:29:16 [INFO] train episode 6955: reward = -35.90, steps = 23 00:29:17 [INFO] train episode 6956: reward = -49.24, steps = 21 00:29:17 [INFO] train episode 6957: reward = -51.45, steps = 25 00:29:17 [INFO] train episode 6958: reward = -24.20, steps = 46 00:29:17 [INFO] train episode 6959: reward = -45.53, steps = 44 00:29:18 [INFO] train episode 6960: reward = -42.75, steps = 62 00:29:18 [INFO] train episode 6961: reward = -43.05, steps = 26 00:29:18 [INFO] train episode 6962: reward = -31.34, steps = 34 00:29:19 [INFO] train episode 6963: reward = -11.85, steps = 53 00:29:19 [INFO] train episode 6964: reward = -49.55, steps = 50 00:29:19 [INFO] train episode 6965: reward = -71.99, steps = 50 00:29:19 [INFO] train episode 6966: reward = -14.97, steps = 53 00:29:20 [INFO] train episode 6967: reward = -34.84, steps = 51 00:29:20 [INFO] train episode 6968: reward = -65.63, steps = 32 00:29:21 [INFO] train episode 6969: reward = -37.26, steps = 31 00:29:21 [INFO] train episode 6970: reward = -38.00, steps = 32 00:29:21 [INFO] train episode 6971: reward = -26.41, steps = 44 00:29:21 [INFO] train episode 6972: reward = -32.28, steps = 33 00:29:22 [INFO] train episode 6973: reward = -37.77, steps = 35 00:29:22 [INFO] train episode 6974: reward = -53.22, steps = 34 00:29:22 [INFO] train episode 6975: reward = -41.37, steps = 46 00:29:22 [INFO] train episode 6976: reward = -62.76, steps = 46 00:29:23 [INFO] train episode 6977: reward = -50.15, steps = 46 00:29:23 [INFO] train episode 6978: reward = -99.77, steps = 50 00:29:23 [INFO] train episode 6979: reward = -68.69, steps = 56 00:29:24 [INFO] train episode 6980: reward = -57.84, steps = 32 00:29:24 [INFO] train episode 6981: reward = -40.03, steps = 52 00:29:24 [INFO] train episode 6982: reward = -53.08, steps = 55 00:29:25 [INFO] train episode 6983: reward = -20.87, steps = 70 00:29:25 [INFO] train episode 6984: reward = -37.92, steps = 52 00:29:26 [INFO] train episode 6985: reward = -74.62, steps = 93 00:29:26 [INFO] train episode 6986: reward = -48.40, steps = 41 00:29:26 [INFO] train episode 6987: reward = -86.50, steps = 53 00:29:26 [INFO] train episode 6988: reward = -25.34, steps = 32 00:29:27 [INFO] train episode 6989: reward = -62.11, steps = 60 00:29:27 [INFO] train episode 6990: reward = -59.69, steps = 55 00:29:27 [INFO] train episode 6991: reward = -42.51, steps = 25 00:29:27 [INFO] train episode 6992: reward = -36.08, steps = 40 00:29:28 [INFO] train episode 6993: reward = -30.36, steps = 34 00:29:28 [INFO] train episode 6994: reward = -76.49, steps = 51 00:29:28 [INFO] train episode 6995: reward = -54.10, steps = 42 00:29:28 [INFO] train episode 6996: reward = -55.23, steps = 31 00:29:29 [INFO] train episode 6997: reward = -41.97, steps = 25 00:29:29 [INFO] train episode 6998: reward = -40.99, steps = 21 00:29:29 [INFO] train episode 6999: reward = -45.89, steps = 28 00:29:29 [INFO] train episode 7000: reward = -46.13, steps = 39 00:29:29 [INFO] train episode 7001: reward = -49.44, steps = 24 00:29:30 [INFO] train episode 7002: reward = -63.55, steps = 36 00:29:30 [INFO] train episode 7003: reward = -53.58, steps = 41 00:29:30 [INFO] train episode 7004: reward = -46.06, steps = 31 00:29:31 [INFO] train episode 7005: reward = -50.41, steps = 55 00:29:31 [INFO] train episode 7006: reward = -37.15, steps = 47 00:29:31 [INFO] train episode 7007: reward = -49.86, steps = 46 00:29:31 [INFO] train episode 7008: reward = -48.22, steps = 29 00:29:32 [INFO] train episode 7009: reward = -42.35, steps = 32 00:29:32 [INFO] train episode 7010: reward = -43.84, steps = 22 00:29:32 [INFO] train episode 7011: reward = -15.16, steps = 45 00:29:32 [INFO] train episode 7012: reward = -45.56, steps = 22 00:29:33 [INFO] train episode 7013: reward = -32.71, steps = 49 00:29:33 [INFO] train episode 7014: reward = -57.53, steps = 51 00:29:33 [INFO] train episode 7015: reward = -22.61, steps = 41 00:29:34 [INFO] train episode 7016: reward = -32.85, steps = 43 00:29:34 [INFO] train episode 7017: reward = -45.13, steps = 46 00:29:34 [INFO] train episode 7018: reward = -127.48, steps = 63 00:29:35 [INFO] train episode 7019: reward = -53.79, steps = 61 00:29:35 [INFO] train episode 7020: reward = -76.99, steps = 46 00:29:35 [INFO] train episode 7021: reward = -42.35, steps = 35 00:29:36 [INFO] train episode 7022: reward = -60.41, steps = 60 00:29:36 [INFO] train episode 7023: reward = -90.86, steps = 49 00:29:36 [INFO] train episode 7024: reward = -53.49, steps = 37 00:29:36 [INFO] train episode 7025: reward = -22.98, steps = 44 00:29:37 [INFO] train episode 7026: reward = -41.23, steps = 21 00:29:37 [INFO] train episode 7027: reward = -45.95, steps = 19 00:29:37 [INFO] train episode 7028: reward = -38.49, steps = 39 00:29:37 [INFO] train episode 7029: reward = -27.61, steps = 36 00:29:38 [INFO] train episode 7030: reward = -66.53, steps = 45 00:29:38 [INFO] train episode 7031: reward = -61.21, steps = 36 00:29:38 [INFO] train episode 7032: reward = -37.64, steps = 23 00:29:38 [INFO] train episode 7033: reward = -39.40, steps = 22 00:29:38 [INFO] train episode 7034: reward = -74.38, steps = 41 00:29:39 [INFO] train episode 7035: reward = -61.98, steps = 40 00:29:39 [INFO] train episode 7036: reward = -44.76, steps = 26 00:29:39 [INFO] train episode 7037: reward = -48.84, steps = 29 00:29:39 [INFO] train episode 7038: reward = -56.58, steps = 51 00:29:40 [INFO] train episode 7039: reward = -35.04, steps = 23 00:29:40 [INFO] train episode 7040: reward = -49.42, steps = 23 00:29:40 [INFO] train episode 7041: reward = -65.35, steps = 51 00:29:40 [INFO] train episode 7042: reward = -40.31, steps = 27 00:29:40 [INFO] train episode 7043: reward = -37.37, steps = 44 00:29:41 [INFO] train episode 7044: reward = -46.11, steps = 26 00:29:41 [INFO] train episode 7045: reward = -23.37, steps = 57 00:29:41 [INFO] train episode 7046: reward = -39.92, steps = 41 00:29:42 [INFO] train episode 7047: reward = -40.37, steps = 42 00:29:42 [INFO] train episode 7048: reward = -50.66, steps = 37 00:29:42 [INFO] train episode 7049: reward = -34.72, steps = 69 00:29:42 [INFO] train episode 7050: reward = -34.32, steps = 25 00:29:43 [INFO] train episode 7051: reward = -35.42, steps = 27 00:29:43 [INFO] train episode 7052: reward = -87.31, steps = 58 00:29:43 [INFO] train episode 7053: reward = -35.75, steps = 33 00:29:43 [INFO] train episode 7054: reward = -43.28, steps = 38 00:29:44 [INFO] train episode 7055: reward = -41.85, steps = 25 00:29:44 [INFO] train episode 7056: reward = -47.10, steps = 41 00:29:44 [INFO] train episode 7057: reward = -78.59, steps = 45 00:29:44 [INFO] train episode 7058: reward = -41.66, steps = 23 00:29:45 [INFO] train episode 7059: reward = -33.73, steps = 18 00:29:45 [INFO] train episode 7060: reward = -50.58, steps = 22 00:29:45 [INFO] train episode 7061: reward = -53.10, steps = 32 00:29:45 [INFO] train episode 7062: reward = -46.14, steps = 56 00:29:45 [INFO] train episode 7063: reward = -38.33, steps = 23 00:29:46 [INFO] train episode 7064: reward = -22.96, steps = 47 00:29:46 [INFO] train episode 7065: reward = -87.04, steps = 66 00:29:47 [INFO] train episode 7066: reward = -58.75, steps = 39 00:29:47 [INFO] train episode 7067: reward = -33.06, steps = 20 00:29:47 [INFO] train episode 7068: reward = -68.10, steps = 29 00:29:47 [INFO] train episode 7069: reward = -42.99, steps = 41 00:29:48 [INFO] train episode 7070: reward = -46.16, steps = 31 00:29:48 [INFO] train episode 7071: reward = -76.05, steps = 39 00:29:48 [INFO] train episode 7072: reward = -55.76, steps = 25 00:29:48 [INFO] train episode 7073: reward = -50.81, steps = 38 00:29:48 [INFO] train episode 7074: reward = -25.42, steps = 36 00:29:49 [INFO] train episode 7075: reward = -40.60, steps = 23 00:29:49 [INFO] train episode 7076: reward = -63.99, steps = 49 00:29:49 [INFO] train episode 7077: reward = -86.33, steps = 44 00:29:49 [INFO] train episode 7078: reward = -52.68, steps = 39 00:29:50 [INFO] train episode 7079: reward = -28.97, steps = 45 00:29:50 [INFO] train episode 7080: reward = -75.09, steps = 52 00:29:50 [INFO] train episode 7081: reward = -85.62, steps = 47 00:29:51 [INFO] train episode 7082: reward = -63.80, steps = 44 00:29:51 [INFO] train episode 7083: reward = -47.57, steps = 22 00:29:51 [INFO] train episode 7084: reward = -74.23, steps = 52 00:29:51 [INFO] train episode 7085: reward = -40.94, steps = 43 00:29:52 [INFO] train episode 7086: reward = -38.64, steps = 31 00:29:52 [INFO] train episode 7087: reward = -60.62, steps = 49 00:29:52 [INFO] train episode 7088: reward = -54.77, steps = 33 00:29:52 [INFO] train episode 7089: reward = -14.15, steps = 41 00:29:53 [INFO] train episode 7090: reward = -49.39, steps = 36 00:29:53 [INFO] train episode 7091: reward = -60.14, steps = 35 00:29:53 [INFO] train episode 7092: reward = -37.51, steps = 25 00:29:53 [INFO] train episode 7093: reward = -44.51, steps = 28 00:29:54 [INFO] train episode 7094: reward = -69.70, steps = 44 00:29:54 [INFO] train episode 7095: reward = -90.28, steps = 48 00:29:54 [INFO] train episode 7096: reward = -25.77, steps = 38 00:29:54 [INFO] train episode 7097: reward = -41.66, steps = 22 00:29:55 [INFO] train episode 7098: reward = -23.30, steps = 48 00:29:55 [INFO] train episode 7099: reward = -29.39, steps = 44 00:29:55 [INFO] train episode 7100: reward = -78.22, steps = 63 00:29:55 [INFO] train episode 7101: reward = -43.08, steps = 35 00:29:56 [INFO] train episode 7102: reward = -53.66, steps = 47 00:29:56 [INFO] train episode 7103: reward = -26.36, steps = 48 00:29:56 [INFO] train episode 7104: reward = -53.00, steps = 59 00:29:57 [INFO] train episode 7105: reward = -40.91, steps = 31 00:29:57 [INFO] train episode 7106: reward = -47.44, steps = 29 00:29:57 [INFO] train episode 7107: reward = -48.29, steps = 51 00:29:57 [INFO] train episode 7108: reward = -31.57, steps = 44 00:29:58 [INFO] train episode 7109: reward = -87.69, steps = 51 00:29:58 [INFO] train episode 7110: reward = -44.80, steps = 27 00:29:58 [INFO] train episode 7111: reward = -38.96, steps = 57 00:29:59 [INFO] train episode 7112: reward = -79.32, steps = 56 00:29:59 [INFO] train episode 7113: reward = -31.94, steps = 27 00:29:59 [INFO] train episode 7114: reward = -74.52, steps = 60 00:30:00 [INFO] train episode 7115: reward = -33.23, steps = 51 00:30:00 [INFO] train episode 7116: reward = -39.53, steps = 42 00:30:00 [INFO] train episode 7117: reward = -93.05, steps = 52 00:30:01 [INFO] train episode 7118: reward = -52.19, steps = 56 00:30:01 [INFO] train episode 7119: reward = -64.52, steps = 53 00:30:01 [INFO] train episode 7120: reward = -38.59, steps = 18 00:30:01 [INFO] train episode 7121: reward = -36.94, steps = 35 00:30:02 [INFO] train episode 7122: reward = -24.52, steps = 43 00:30:02 [INFO] train episode 7123: reward = -67.46, steps = 41 00:30:02 [INFO] train episode 7124: reward = -64.64, steps = 40 00:30:03 [INFO] train episode 7125: reward = -35.93, steps = 49 00:30:03 [INFO] train episode 7126: reward = -59.21, steps = 38 00:30:03 [INFO] train episode 7127: reward = -98.95, steps = 51 00:30:03 [INFO] train episode 7128: reward = -42.67, steps = 23 00:30:04 [INFO] train episode 7129: reward = -36.00, steps = 40 00:30:04 [INFO] train episode 7130: reward = -34.97, steps = 25 00:30:04 [INFO] train episode 7131: reward = -59.83, steps = 32 00:30:04 [INFO] train episode 7132: reward = -21.21, steps = 47 00:30:05 [INFO] train episode 7133: reward = -42.24, steps = 65 00:30:05 [INFO] train episode 7134: reward = -26.21, steps = 58 00:30:06 [INFO] train episode 7135: reward = -114.81, steps = 78 00:30:06 [INFO] train episode 7136: reward = -23.85, steps = 44 00:30:06 [INFO] train episode 7137: reward = -14.58, steps = 39 00:30:07 [INFO] train episode 7138: reward = -56.31, steps = 67 00:30:07 [INFO] train episode 7139: reward = -66.77, steps = 38 00:30:07 [INFO] train episode 7140: reward = -46.31, steps = 34 00:30:07 [INFO] train episode 7141: reward = -63.76, steps = 46 00:30:08 [INFO] train episode 7142: reward = -22.93, steps = 64 00:30:08 [INFO] train episode 7143: reward = -25.95, steps = 37 00:30:09 [INFO] train episode 7144: reward = -126.60, steps = 83 00:30:09 [INFO] train episode 7145: reward = -70.55, steps = 47 00:30:09 [INFO] train episode 7146: reward = -20.78, steps = 33 00:30:09 [INFO] train episode 7147: reward = -43.27, steps = 25 00:30:10 [INFO] train episode 7148: reward = -31.91, steps = 35 00:30:10 [INFO] train episode 7149: reward = -58.97, steps = 31 00:30:10 [INFO] train episode 7150: reward = -34.29, steps = 45 00:30:10 [INFO] train episode 7151: reward = -46.19, steps = 45 00:30:10 [INFO] train episode 7152: reward = -47.09, steps = 24 00:30:11 [INFO] train episode 7153: reward = -50.18, steps = 47 00:30:11 [INFO] train episode 7154: reward = -50.43, steps = 42 00:30:11 [INFO] train episode 7155: reward = -60.93, steps = 25 00:30:11 [INFO] train episode 7156: reward = -37.77, steps = 28 00:30:12 [INFO] train episode 7157: reward = -27.51, steps = 45 00:30:12 [INFO] train episode 7158: reward = -37.66, steps = 19 00:30:12 [INFO] train episode 7159: reward = -77.84, steps = 45 00:30:12 [INFO] train episode 7160: reward = -57.59, steps = 37 00:30:13 [INFO] train episode 7161: reward = -51.84, steps = 30 00:30:13 [INFO] train episode 7162: reward = -69.88, steps = 39 00:30:13 [INFO] train episode 7163: reward = -22.10, steps = 38 00:30:14 [INFO] train episode 7164: reward = -67.03, steps = 55 00:30:14 [INFO] train episode 7165: reward = -91.20, steps = 72 00:30:14 [INFO] train episode 7166: reward = -26.68, steps = 48 00:30:15 [INFO] train episode 7167: reward = -19.73, steps = 59 00:30:15 [INFO] train episode 7168: reward = -27.17, steps = 33 00:30:15 [INFO] train episode 7169: reward = -63.89, steps = 48 00:30:16 [INFO] train episode 7170: reward = -32.11, steps = 22 00:30:16 [INFO] train episode 7171: reward = -65.19, steps = 44 00:30:16 [INFO] train episode 7172: reward = -46.08, steps = 49 00:30:16 [INFO] train episode 7173: reward = -24.96, steps = 43 00:30:17 [INFO] train episode 7174: reward = -42.38, steps = 24 00:30:17 [INFO] train episode 7175: reward = -64.41, steps = 50 00:30:17 [INFO] train episode 7176: reward = -61.74, steps = 30 00:30:17 [INFO] train episode 7177: reward = -72.44, steps = 43 00:30:18 [INFO] train episode 7178: reward = -40.17, steps = 49 00:30:18 [INFO] train episode 7179: reward = -46.62, steps = 23 00:30:18 [INFO] train episode 7180: reward = -58.21, steps = 37 00:30:18 [INFO] train episode 7181: reward = -14.54, steps = 43 00:30:19 [INFO] train episode 7182: reward = -19.67, steps = 37 00:30:19 [INFO] train episode 7183: reward = -44.58, steps = 21 00:30:19 [INFO] train episode 7184: reward = -31.07, steps = 48 00:30:20 [INFO] train episode 7185: reward = -101.44, steps = 77 00:30:20 [INFO] train episode 7186: reward = -54.59, steps = 58 00:30:20 [INFO] train episode 7187: reward = -59.52, steps = 38 00:30:20 [INFO] train episode 7188: reward = -64.21, steps = 42 00:30:21 [INFO] train episode 7189: reward = -35.30, steps = 39 00:30:21 [INFO] train episode 7190: reward = -86.50, steps = 80 00:30:21 [INFO] train episode 7191: reward = -96.09, steps = 52 00:30:22 [INFO] train episode 7192: reward = -42.57, steps = 26 00:30:22 [INFO] train episode 7193: reward = -63.87, steps = 53 00:30:22 [INFO] train episode 7194: reward = -74.44, steps = 53 00:30:23 [INFO] train episode 7195: reward = -73.08, steps = 35 00:30:23 [INFO] train episode 7196: reward = -67.13, steps = 31 00:30:23 [INFO] train episode 7197: reward = -79.65, steps = 52 00:30:23 [INFO] train episode 7198: reward = -52.39, steps = 24 00:30:24 [INFO] train episode 7199: reward = -44.67, steps = 49 00:30:24 [INFO] train episode 7200: reward = -61.41, steps = 45 00:30:24 [INFO] train episode 7201: reward = -36.99, steps = 27 00:30:24 [INFO] train episode 7202: reward = -59.95, steps = 40 00:30:24 [INFO] train episode 7203: reward = -34.10, steps = 18 00:30:25 [INFO] train episode 7204: reward = -30.15, steps = 38 00:30:25 [INFO] train episode 7205: reward = -49.31, steps = 44 00:30:25 [INFO] train episode 7206: reward = -48.91, steps = 20 00:30:25 [INFO] train episode 7207: reward = -54.74, steps = 27 00:30:26 [INFO] train episode 7208: reward = -91.82, steps = 45 00:30:26 [INFO] train episode 7209: reward = -44.80, steps = 27 00:30:26 [INFO] train episode 7210: reward = -19.85, steps = 45 00:30:27 [INFO] train episode 7211: reward = -39.89, steps = 24 00:30:27 [INFO] train episode 7212: reward = -33.21, steps = 37 00:30:27 [INFO] train episode 7213: reward = -45.82, steps = 58 00:30:27 [INFO] train episode 7214: reward = -42.42, steps = 18 00:30:28 [INFO] train episode 7215: reward = -27.02, steps = 32 00:30:28 [INFO] train episode 7216: reward = -63.29, steps = 42 00:30:28 [INFO] train episode 7217: reward = -70.75, steps = 52 00:30:28 [INFO] train episode 7218: reward = -98.23, steps = 52 00:30:29 [INFO] train episode 7219: reward = -68.95, steps = 31 00:30:29 [INFO] train episode 7220: reward = -33.67, steps = 61 00:30:29 [INFO] train episode 7221: reward = -58.94, steps = 37 00:30:30 [INFO] train episode 7222: reward = -52.09, steps = 52 00:30:30 [INFO] train episode 7223: reward = -43.69, steps = 20 00:30:30 [INFO] train episode 7224: reward = -48.20, steps = 20 00:30:30 [INFO] train episode 7225: reward = -36.28, steps = 44 00:30:31 [INFO] train episode 7226: reward = -75.11, steps = 49 00:30:31 [INFO] train episode 7227: reward = -32.79, steps = 60 00:30:31 [INFO] train episode 7228: reward = -38.32, steps = 61 00:30:32 [INFO] train episode 7229: reward = -57.27, steps = 46 00:30:32 [INFO] train episode 7230: reward = -66.12, steps = 61 00:30:32 [INFO] train episode 7231: reward = -42.03, steps = 33 00:30:33 [INFO] train episode 7232: reward = -79.52, steps = 52 00:30:33 [INFO] train episode 7233: reward = -75.54, steps = 35 00:30:33 [INFO] train episode 7234: reward = -45.80, steps = 39 00:30:33 [INFO] train episode 7235: reward = -45.88, steps = 25 00:30:33 [INFO] train episode 7236: reward = -23.22, steps = 39 00:30:34 [INFO] train episode 7237: reward = -28.35, steps = 47 00:30:34 [INFO] train episode 7238: reward = -39.92, steps = 39 00:30:34 [INFO] train episode 7239: reward = -50.75, steps = 44 00:30:35 [INFO] train episode 7240: reward = -58.48, steps = 45 00:30:35 [INFO] train episode 7241: reward = -38.07, steps = 52 00:30:35 [INFO] train episode 7242: reward = -36.51, steps = 32 00:30:35 [INFO] train episode 7243: reward = -35.76, steps = 23 00:30:35 [INFO] train episode 7244: reward = -37.95, steps = 32 00:30:36 [INFO] train episode 7245: reward = -34.84, steps = 38 00:30:36 [INFO] train episode 7246: reward = -62.13, steps = 42 00:30:36 [INFO] train episode 7247: reward = -44.07, steps = 25 00:30:36 [INFO] train episode 7248: reward = -38.71, steps = 53 00:30:37 [INFO] train episode 7249: reward = -41.36, steps = 27 00:30:37 [INFO] train episode 7250: reward = -72.06, steps = 53 00:30:37 [INFO] train episode 7251: reward = -42.39, steps = 38 00:30:37 [INFO] train episode 7252: reward = -27.58, steps = 40 00:30:38 [INFO] train episode 7253: reward = -27.07, steps = 43 00:30:38 [INFO] train episode 7254: reward = -52.11, steps = 49 00:30:38 [INFO] train episode 7255: reward = -58.12, steps = 45 00:30:39 [INFO] train episode 7256: reward = -60.73, steps = 57 00:30:39 [INFO] train episode 7257: reward = -58.92, steps = 42 00:30:40 [INFO] train episode 7258: reward = -41.40, steps = 46 00:30:40 [INFO] train episode 7259: reward = -62.10, steps = 69 00:30:40 [INFO] train episode 7260: reward = -70.25, steps = 35 00:30:40 [INFO] train episode 7261: reward = -37.09, steps = 23 00:30:41 [INFO] train episode 7262: reward = -35.63, steps = 39 00:30:41 [INFO] train episode 7263: reward = -38.19, steps = 31 00:30:41 [INFO] train episode 7264: reward = -43.59, steps = 50 00:30:42 [INFO] train episode 7265: reward = -44.35, steps = 71 00:30:42 [INFO] train episode 7266: reward = -27.32, steps = 34 00:30:42 [INFO] train episode 7267: reward = -28.81, steps = 38 00:30:42 [INFO] train episode 7268: reward = -25.91, steps = 39 00:30:43 [INFO] train episode 7269: reward = -25.56, steps = 34 00:30:43 [INFO] train episode 7270: reward = -25.81, steps = 49 00:30:43 [INFO] train episode 7271: reward = -55.20, steps = 34 00:30:43 [INFO] train episode 7272: reward = -36.74, steps = 46 00:30:44 [INFO] train episode 7273: reward = -52.86, steps = 57 00:30:44 [INFO] train episode 7274: reward = -79.96, steps = 103 00:30:45 [INFO] train episode 7275: reward = -53.30, steps = 54 00:30:45 [INFO] train episode 7276: reward = -65.13, steps = 44 00:30:46 [INFO] train episode 7277: reward = -84.76, steps = 84 00:30:46 [INFO] train episode 7278: reward = -45.53, steps = 22 00:30:46 [INFO] train episode 7279: reward = -42.95, steps = 40 00:30:46 [INFO] train episode 7280: reward = -32.02, steps = 42 00:30:47 [INFO] train episode 7281: reward = -41.88, steps = 39 00:30:47 [INFO] train episode 7282: reward = -35.72, steps = 40 00:30:47 [INFO] train episode 7283: reward = -39.43, steps = 39 00:30:47 [INFO] train episode 7284: reward = -60.05, steps = 74 00:30:48 [INFO] train episode 7285: reward = -23.37, steps = 44 00:30:48 [INFO] train episode 7286: reward = -40.69, steps = 39 00:30:48 [INFO] train episode 7287: reward = -46.28, steps = 24 00:30:48 [INFO] train episode 7288: reward = -37.99, steps = 21 00:30:49 [INFO] train episode 7289: reward = -64.17, steps = 32 00:30:49 [INFO] train episode 7290: reward = -48.64, steps = 48 00:30:49 [INFO] train episode 7291: reward = -18.87, steps = 40 00:30:50 [INFO] train episode 7292: reward = -73.13, steps = 60 00:30:50 [INFO] train episode 7293: reward = -89.18, steps = 71 00:30:50 [INFO] train episode 7294: reward = -80.92, steps = 55 00:30:51 [INFO] train episode 7295: reward = -83.39, steps = 68 00:30:51 [INFO] train episode 7296: reward = -33.04, steps = 21 00:30:51 [INFO] train episode 7297: reward = -95.97, steps = 62 00:30:52 [INFO] train episode 7298: reward = -41.86, steps = 25 00:30:52 [INFO] train episode 7299: reward = -40.07, steps = 49 00:30:52 [INFO] train episode 7300: reward = -95.08, steps = 47 00:30:53 [INFO] train episode 7301: reward = -49.81, steps = 41 00:30:53 [INFO] train episode 7302: reward = -49.13, steps = 72 00:30:53 [INFO] train episode 7303: reward = -51.08, steps = 42 00:30:54 [INFO] train episode 7304: reward = -97.86, steps = 56 00:30:54 [INFO] train episode 7305: reward = -64.22, steps = 41 00:30:54 [INFO] train episode 7306: reward = -57.37, steps = 62 00:30:55 [INFO] train episode 7307: reward = -52.34, steps = 37 00:30:55 [INFO] train episode 7308: reward = -87.72, steps = 64 00:30:55 [INFO] train episode 7309: reward = -41.33, steps = 47 00:30:56 [INFO] train episode 7310: reward = -33.87, steps = 37 00:30:56 [INFO] train episode 7311: reward = -61.12, steps = 49 00:30:56 [INFO] train episode 7312: reward = -46.13, steps = 39 00:30:57 [INFO] train episode 7313: reward = -39.29, steps = 44 00:30:57 [INFO] train episode 7314: reward = -39.46, steps = 59 00:30:57 [INFO] train episode 7315: reward = -31.24, steps = 61 00:30:58 [INFO] train episode 7316: reward = -69.59, steps = 51 00:30:58 [INFO] train episode 7317: reward = -100.77, steps = 65 00:30:58 [INFO] train episode 7318: reward = -43.71, steps = 55 00:30:59 [INFO] train episode 7319: reward = -41.51, steps = 41 00:30:59 [INFO] train episode 7320: reward = -48.51, steps = 25 00:30:59 [INFO] train episode 7321: reward = -45.86, steps = 52 00:30:59 [INFO] train episode 7322: reward = -31.35, steps = 46 00:31:00 [INFO] train episode 7323: reward = -37.64, steps = 33 00:31:00 [INFO] train episode 7324: reward = -34.29, steps = 32 00:31:00 [INFO] train episode 7325: reward = -31.67, steps = 44 00:31:00 [INFO] train episode 7326: reward = -65.14, steps = 44 00:31:01 [INFO] train episode 7327: reward = -31.11, steps = 37 00:31:01 [INFO] train episode 7328: reward = -93.07, steps = 53 00:31:01 [INFO] train episode 7329: reward = -76.52, steps = 42 00:31:02 [INFO] train episode 7330: reward = -55.97, steps = 55 00:31:02 [INFO] train episode 7331: reward = -17.88, steps = 65 00:31:02 [INFO] train episode 7332: reward = -44.99, steps = 40 00:31:03 [INFO] train episode 7333: reward = -81.25, steps = 42 00:31:03 [INFO] train episode 7334: reward = -38.36, steps = 34 00:31:03 [INFO] train episode 7335: reward = -32.88, steps = 52 00:31:04 [INFO] train episode 7336: reward = -66.56, steps = 65 00:31:04 [INFO] train episode 7337: reward = -43.68, steps = 33 00:31:04 [INFO] train episode 7338: reward = -46.22, steps = 29 00:31:04 [INFO] train episode 7339: reward = -26.64, steps = 34 00:31:05 [INFO] train episode 7340: reward = -37.55, steps = 43 00:31:05 [INFO] train episode 7341: reward = -28.56, steps = 51 00:31:06 [INFO] train episode 7342: reward = -72.87, steps = 64 00:31:06 [INFO] train episode 7343: reward = -46.51, steps = 41 00:31:06 [INFO] train episode 7344: reward = -30.65, steps = 32 00:31:06 [INFO] train episode 7345: reward = -57.37, steps = 24 00:31:07 [INFO] train episode 7346: reward = -39.51, steps = 32 00:31:07 [INFO] train episode 7347: reward = -22.06, steps = 41 00:31:07 [INFO] train episode 7348: reward = -35.44, steps = 32 00:31:07 [INFO] train episode 7349: reward = -16.14, steps = 45 00:31:08 [INFO] train episode 7350: reward = -35.28, steps = 43 00:31:08 [INFO] train episode 7351: reward = -69.03, steps = 53 00:31:08 [INFO] train episode 7352: reward = -44.09, steps = 54 00:31:09 [INFO] train episode 7353: reward = -41.95, steps = 25 00:31:09 [INFO] train episode 7354: reward = -49.57, steps = 35 00:31:09 [INFO] train episode 7355: reward = -63.06, steps = 70 00:31:10 [INFO] train episode 7356: reward = -62.35, steps = 69 00:31:10 [INFO] train episode 7357: reward = -58.48, steps = 47 00:31:10 [INFO] train episode 7358: reward = -38.66, steps = 47 00:31:11 [INFO] train episode 7359: reward = -58.78, steps = 44 00:31:11 [INFO] train episode 7360: reward = -58.93, steps = 42 00:31:11 [INFO] train episode 7361: reward = -61.82, steps = 35 00:31:11 [INFO] train episode 7362: reward = -49.09, steps = 64 00:31:12 [INFO] train episode 7363: reward = -69.58, steps = 57 00:31:12 [INFO] train episode 7364: reward = -39.81, steps = 52 00:31:13 [INFO] train episode 7365: reward = -71.21, steps = 77 00:31:13 [INFO] train episode 7366: reward = -25.72, steps = 39 00:31:13 [INFO] train episode 7367: reward = -69.57, steps = 49 00:31:14 [INFO] train episode 7368: reward = -86.36, steps = 75 00:31:14 [INFO] train episode 7369: reward = -58.78, steps = 46 00:31:14 [INFO] train episode 7370: reward = -77.26, steps = 42 00:31:15 [INFO] train episode 7371: reward = -66.48, steps = 49 00:31:15 [INFO] train episode 7372: reward = -34.13, steps = 52 00:31:15 [INFO] train episode 7373: reward = -27.87, steps = 58 00:31:16 [INFO] train episode 7374: reward = -88.47, steps = 59 00:31:16 [INFO] train episode 7375: reward = -27.26, steps = 52 00:31:16 [INFO] train episode 7376: reward = -39.70, steps = 36 00:31:16 [INFO] train episode 7377: reward = -51.26, steps = 25 00:31:17 [INFO] train episode 7378: reward = -66.24, steps = 69 00:31:17 [INFO] train episode 7379: reward = -49.30, steps = 39 00:31:17 [INFO] train episode 7380: reward = -28.92, steps = 50 00:31:18 [INFO] train episode 7381: reward = -42.27, steps = 38 00:31:18 [INFO] train episode 7382: reward = -54.35, steps = 46 00:31:18 [INFO] train episode 7383: reward = -36.59, steps = 40 00:31:18 [INFO] train episode 7384: reward = -43.04, steps = 27 00:31:19 [INFO] train episode 7385: reward = -39.94, steps = 33 00:31:19 [INFO] train episode 7386: reward = -45.27, steps = 49 00:31:20 [INFO] train episode 7387: reward = -13.33, steps = 43 00:31:20 [INFO] train episode 7388: reward = -24.51, steps = 67 00:31:20 [INFO] train episode 7389: reward = -44.14, steps = 54 00:31:21 [INFO] train episode 7390: reward = -16.45, steps = 50 00:31:21 [INFO] train episode 7391: reward = -78.03, steps = 49 00:31:21 [INFO] train episode 7392: reward = -39.31, steps = 22 00:31:21 [INFO] train episode 7393: reward = -43.87, steps = 23 00:31:22 [INFO] train episode 7394: reward = -33.91, steps = 32 00:31:22 [INFO] train episode 7395: reward = -91.89, steps = 67 00:31:23 [INFO] train episode 7396: reward = -120.83, steps = 90 00:31:23 [INFO] train episode 7397: reward = -12.89, steps = 69 00:31:23 [INFO] train episode 7398: reward = -74.62, steps = 51 00:31:24 [INFO] train episode 7399: reward = -31.22, steps = 45 00:31:24 [INFO] train episode 7400: reward = -36.61, steps = 62 00:31:24 [INFO] train episode 7401: reward = -31.73, steps = 53 00:31:25 [INFO] train episode 7402: reward = -77.51, steps = 52 00:31:25 [INFO] train episode 7403: reward = -81.35, steps = 50 00:31:25 [INFO] train episode 7404: reward = -86.96, steps = 64 00:31:26 [INFO] train episode 7405: reward = -23.74, steps = 39 00:31:26 [INFO] train episode 7406: reward = -27.77, steps = 46 00:31:26 [INFO] train episode 7407: reward = -49.60, steps = 26 00:31:27 [INFO] train episode 7408: reward = -73.70, steps = 72 00:31:27 [INFO] train episode 7409: reward = -72.97, steps = 42 00:31:27 [INFO] train episode 7410: reward = -41.17, steps = 59 00:31:27 [INFO] train episode 7411: reward = -78.57, steps = 46 00:31:28 [INFO] train episode 7412: reward = -64.20, steps = 37 00:31:28 [INFO] train episode 7413: reward = -29.94, steps = 47 00:31:28 [INFO] train episode 7414: reward = -68.08, steps = 63 00:31:29 [INFO] train episode 7415: reward = -46.71, steps = 42 00:31:29 [INFO] train episode 7416: reward = -39.71, steps = 46 00:31:30 [INFO] train episode 7417: reward = -87.43, steps = 94 00:31:30 [INFO] train episode 7418: reward = -25.91, steps = 54 00:31:30 [INFO] train episode 7419: reward = -79.71, steps = 44 00:31:30 [INFO] train episode 7420: reward = -58.22, steps = 47 00:31:31 [INFO] train episode 7421: reward = -51.98, steps = 28 00:31:31 [INFO] train episode 7422: reward = -50.48, steps = 44 00:31:31 [INFO] train episode 7423: reward = -47.40, steps = 24 00:31:31 [INFO] train episode 7424: reward = -48.97, steps = 43 00:31:32 [INFO] train episode 7425: reward = -28.60, steps = 62 00:31:32 [INFO] train episode 7426: reward = -77.24, steps = 35 00:31:33 [INFO] train episode 7427: reward = -39.89, steps = 72 00:31:33 [INFO] train episode 7428: reward = -58.48, steps = 53 00:31:33 [INFO] train episode 7429: reward = -33.08, steps = 37 00:31:34 [INFO] train episode 7430: reward = -68.43, steps = 45 00:31:34 [INFO] train episode 7431: reward = -61.00, steps = 61 00:31:34 [INFO] train episode 7432: reward = -49.74, steps = 39 00:31:35 [INFO] train episode 7433: reward = -57.02, steps = 31 00:31:35 [INFO] train episode 7434: reward = -98.00, steps = 26 00:31:35 [INFO] train episode 7435: reward = -37.74, steps = 38 00:31:35 [INFO] train episode 7436: reward = -48.42, steps = 61 00:31:36 [INFO] train episode 7437: reward = -79.38, steps = 53 00:31:36 [INFO] train episode 7438: reward = -59.18, steps = 27 00:31:36 [INFO] train episode 7439: reward = -23.08, steps = 51 00:31:37 [INFO] train episode 7440: reward = -44.13, steps = 70 00:31:37 [INFO] train episode 7441: reward = -53.59, steps = 53 00:31:37 [INFO] train episode 7442: reward = -20.37, steps = 55 00:31:38 [INFO] train episode 7443: reward = -65.64, steps = 48 00:31:38 [INFO] train episode 7444: reward = -68.98, steps = 64 00:31:38 [INFO] train episode 7445: reward = -35.03, steps = 70 00:31:39 [INFO] train episode 7446: reward = -88.82, steps = 72 00:31:39 [INFO] train episode 7447: reward = -35.84, steps = 76 00:31:40 [INFO] train episode 7448: reward = -54.81, steps = 26 00:31:40 [INFO] train episode 7449: reward = -109.27, steps = 48 00:31:40 [INFO] train episode 7450: reward = -66.16, steps = 64 00:31:41 [INFO] train episode 7451: reward = -24.31, steps = 50 00:31:41 [INFO] train episode 7452: reward = -29.38, steps = 47 00:31:41 [INFO] train episode 7453: reward = -59.21, steps = 37 00:31:42 [INFO] train episode 7454: reward = -83.08, steps = 64 00:31:42 [INFO] train episode 7455: reward = -59.97, steps = 42 00:31:42 [INFO] train episode 7456: reward = -24.27, steps = 33 00:31:42 [INFO] train episode 7457: reward = -97.15, steps = 47 00:31:43 [INFO] train episode 7458: reward = -46.06, steps = 42 00:31:43 [INFO] train episode 7459: reward = -74.00, steps = 57 00:31:43 [INFO] train episode 7460: reward = -53.62, steps = 19 00:31:44 [INFO] train episode 7461: reward = -53.39, steps = 35 00:31:44 [INFO] train episode 7462: reward = -42.51, steps = 22 00:31:44 [INFO] train episode 7463: reward = -88.83, steps = 70 00:31:44 [INFO] train episode 7464: reward = -35.46, steps = 49 00:31:45 [INFO] train episode 7465: reward = -33.55, steps = 33 00:31:45 [INFO] train episode 7466: reward = -66.06, steps = 54 00:31:46 [INFO] train episode 7467: reward = -46.64, steps = 45 00:31:46 [INFO] train episode 7468: reward = -119.45, steps = 76 00:31:46 [INFO] train episode 7469: reward = -17.44, steps = 58 00:31:47 [INFO] train episode 7470: reward = -32.53, steps = 56 00:31:47 [INFO] train episode 7471: reward = -33.97, steps = 50 00:31:47 [INFO] train episode 7472: reward = -44.12, steps = 37 00:31:48 [INFO] train episode 7473: reward = -58.54, steps = 63 00:31:48 [INFO] train episode 7474: reward = -52.44, steps = 41 00:31:48 [INFO] train episode 7475: reward = -30.69, steps = 49 00:31:49 [INFO] train episode 7476: reward = -25.12, steps = 46 00:31:49 [INFO] train episode 7477: reward = -40.09, steps = 44 00:31:49 [INFO] train episode 7478: reward = -38.27, steps = 58 00:31:49 [INFO] train episode 7479: reward = -34.58, steps = 38 00:31:50 [INFO] train episode 7480: reward = -51.47, steps = 59 00:31:50 [INFO] train episode 7481: reward = -26.14, steps = 59 00:31:50 [INFO] train episode 7482: reward = -42.84, steps = 35 00:31:51 [INFO] train episode 7483: reward = -30.33, steps = 43 00:31:51 [INFO] train episode 7484: reward = -90.60, steps = 77 00:31:52 [INFO] train episode 7485: reward = -38.59, steps = 52 00:31:52 [INFO] train episode 7486: reward = -47.18, steps = 30 00:31:52 [INFO] train episode 7487: reward = -17.92, steps = 43 00:31:52 [INFO] train episode 7488: reward = -34.06, steps = 24 00:31:53 [INFO] train episode 7489: reward = -45.79, steps = 52 00:31:53 [INFO] train episode 7490: reward = -83.27, steps = 45 00:31:53 [INFO] train episode 7491: reward = -53.08, steps = 77 00:31:54 [INFO] train episode 7492: reward = -43.64, steps = 22 00:31:54 [INFO] train episode 7493: reward = -29.31, steps = 41 00:31:54 [INFO] train episode 7494: reward = -39.74, steps = 35 00:31:54 [INFO] train episode 7495: reward = -40.38, steps = 42 00:31:55 [INFO] train episode 7496: reward = -30.68, steps = 61 00:31:55 [INFO] train episode 7497: reward = -42.10, steps = 35 00:31:55 [INFO] train episode 7498: reward = -50.39, steps = 42 00:31:55 [INFO] train episode 7499: reward = -50.01, steps = 35 00:31:56 [INFO] train episode 7500: reward = -47.67, steps = 18 00:31:56 [INFO] train episode 7501: reward = -28.47, steps = 43 00:31:56 [INFO] train episode 7502: reward = -66.07, steps = 99 00:31:57 [INFO] train episode 7503: reward = -39.80, steps = 47 00:31:57 [INFO] train episode 7504: reward = -55.91, steps = 22 00:31:57 [INFO] train episode 7505: reward = -40.60, steps = 37 00:31:57 [INFO] train episode 7506: reward = -26.49, steps = 39 00:31:58 [INFO] train episode 7507: reward = -43.71, steps = 29 00:31:58 [INFO] train episode 7508: reward = -42.45, steps = 47 00:31:58 [INFO] train episode 7509: reward = -47.61, steps = 32 00:31:58 [INFO] train episode 7510: reward = -38.77, steps = 27 00:31:59 [INFO] train episode 7511: reward = -40.40, steps = 42 00:31:59 [INFO] train episode 7512: reward = -37.69, steps = 33 00:31:59 [INFO] train episode 7513: reward = -52.16, steps = 63 00:32:00 [INFO] train episode 7514: reward = -46.76, steps = 44 00:32:00 [INFO] train episode 7515: reward = -39.07, steps = 58 00:32:01 [INFO] train episode 7516: reward = -86.63, steps = 83 00:32:01 [INFO] train episode 7517: reward = -62.78, steps = 44 00:32:01 [INFO] train episode 7518: reward = -94.56, steps = 63 00:32:02 [INFO] train episode 7519: reward = -50.24, steps = 112 00:32:02 [INFO] train episode 7520: reward = -87.40, steps = 45 00:32:03 [INFO] train episode 7521: reward = -36.30, steps = 50 00:32:03 [INFO] train episode 7522: reward = -33.64, steps = 55 00:32:03 [INFO] train episode 7523: reward = -55.93, steps = 47 00:32:04 [INFO] train episode 7524: reward = -74.93, steps = 64 00:32:04 [INFO] train episode 7525: reward = -55.25, steps = 44 00:32:04 [INFO] train episode 7526: reward = -43.16, steps = 57 00:32:05 [INFO] train episode 7527: reward = -69.07, steps = 51 00:32:05 [INFO] train episode 7528: reward = -79.95, steps = 59 00:32:05 [INFO] train episode 7529: reward = -67.75, steps = 57 00:32:06 [INFO] train episode 7530: reward = -41.42, steps = 47 00:32:06 [INFO] train episode 7531: reward = -20.73, steps = 52 00:32:06 [INFO] train episode 7532: reward = -69.80, steps = 73 00:32:07 [INFO] train episode 7533: reward = -45.06, steps = 54 00:32:07 [INFO] train episode 7534: reward = -13.69, steps = 50 00:32:07 [INFO] train episode 7535: reward = -39.50, steps = 47 00:32:08 [INFO] train episode 7536: reward = -54.28, steps = 49 00:32:08 [INFO] train episode 7537: reward = -81.72, steps = 55 00:32:08 [INFO] train episode 7538: reward = -50.32, steps = 51 00:32:09 [INFO] train episode 7539: reward = -125.47, steps = 65 00:32:09 [INFO] train episode 7540: reward = -41.99, steps = 47 00:32:09 [INFO] train episode 7541: reward = -36.49, steps = 40 00:32:10 [INFO] train episode 7542: reward = -72.05, steps = 52 00:32:10 [INFO] train episode 7543: reward = -30.02, steps = 44 00:32:10 [INFO] train episode 7544: reward = -99.83, steps = 43 00:32:11 [INFO] train episode 7545: reward = -86.26, steps = 61 00:32:11 [INFO] train episode 7546: reward = -94.86, steps = 68 00:32:12 [INFO] train episode 7547: reward = -25.60, steps = 51 00:32:12 [INFO] train episode 7548: reward = -54.87, steps = 26 00:32:12 [INFO] train episode 7549: reward = -27.31, steps = 43 00:32:12 [INFO] train episode 7550: reward = -59.65, steps = 23 00:32:13 [INFO] train episode 7551: reward = -42.51, steps = 49 00:32:13 [INFO] train episode 7552: reward = -32.52, steps = 33 00:32:13 [INFO] train episode 7553: reward = -80.07, steps = 49 00:32:14 [INFO] train episode 7554: reward = -105.31, steps = 66 00:32:14 [INFO] train episode 7555: reward = -29.85, steps = 39 00:32:14 [INFO] train episode 7556: reward = -37.03, steps = 54 00:32:15 [INFO] train episode 7557: reward = -39.96, steps = 37 00:32:15 [INFO] train episode 7558: reward = -55.86, steps = 53 00:32:15 [INFO] train episode 7559: reward = -90.29, steps = 69 00:32:16 [INFO] train episode 7560: reward = -101.75, steps = 72 00:32:16 [INFO] train episode 7561: reward = -48.18, steps = 32 00:32:16 [INFO] train episode 7562: reward = -26.07, steps = 42 00:32:17 [INFO] train episode 7563: reward = -34.15, steps = 45 00:32:17 [INFO] train episode 7564: reward = -72.01, steps = 33 00:32:17 [INFO] train episode 7565: reward = -50.95, steps = 47 00:32:17 [INFO] train episode 7566: reward = -95.91, steps = 65 00:32:18 [INFO] train episode 7567: reward = -52.89, steps = 62 00:32:18 [INFO] train episode 7568: reward = -42.24, steps = 67 00:32:19 [INFO] train episode 7569: reward = -20.10, steps = 67 00:32:19 [INFO] train episode 7570: reward = -66.99, steps = 60 00:32:19 [INFO] train episode 7571: reward = -19.36, steps = 69 00:32:20 [INFO] train episode 7572: reward = -48.46, steps = 33 00:32:20 [INFO] train episode 7573: reward = -26.82, steps = 81 00:32:20 [INFO] train episode 7574: reward = -28.46, steps = 43 00:32:21 [INFO] train episode 7575: reward = -83.38, steps = 49 00:32:21 [INFO] train episode 7576: reward = -23.50, steps = 41 00:32:21 [INFO] train episode 7577: reward = -42.93, steps = 36 00:32:22 [INFO] train episode 7578: reward = -23.07, steps = 37 00:32:22 [INFO] train episode 7579: reward = -31.60, steps = 39 00:32:22 [INFO] train episode 7580: reward = -106.57, steps = 66 00:32:23 [INFO] train episode 7581: reward = -58.77, steps = 35 00:32:23 [INFO] train episode 7582: reward = -29.60, steps = 41 00:32:23 [INFO] train episode 7583: reward = -24.65, steps = 43 00:32:23 [INFO] train episode 7584: reward = -71.49, steps = 57 00:32:24 [INFO] train episode 7585: reward = -37.67, steps = 52 00:32:24 [INFO] train episode 7586: reward = -19.29, steps = 60 00:32:25 [INFO] train episode 7587: reward = -49.66, steps = 50 00:32:25 [INFO] train episode 7588: reward = -44.82, steps = 35 00:32:25 [INFO] train episode 7589: reward = -47.49, steps = 34 00:32:25 [INFO] train episode 7590: reward = -44.32, steps = 41 00:32:26 [INFO] train episode 7591: reward = -76.34, steps = 57 00:32:26 [INFO] train episode 7592: reward = -61.23, steps = 49 00:32:26 [INFO] train episode 7593: reward = -49.40, steps = 58 00:32:27 [INFO] train episode 7594: reward = -78.71, steps = 53 00:32:27 [INFO] train episode 7595: reward = -25.58, steps = 50 00:32:27 [INFO] train episode 7596: reward = -33.89, steps = 53 00:32:28 [INFO] train episode 7597: reward = -28.81, steps = 64 00:32:28 [INFO] train episode 7598: reward = -34.38, steps = 49 00:32:29 [INFO] train episode 7599: reward = -36.44, steps = 45 00:32:29 [INFO] train episode 7600: reward = -27.37, steps = 41 00:32:29 [INFO] train episode 7601: reward = -71.13, steps = 69 00:32:30 [INFO] train episode 7602: reward = -41.05, steps = 40 00:32:30 [INFO] train episode 7603: reward = -25.23, steps = 69 00:32:30 [INFO] train episode 7604: reward = -70.89, steps = 71 00:32:31 [INFO] train episode 7605: reward = -56.93, steps = 27 00:32:31 [INFO] train episode 7606: reward = -46.03, steps = 75 00:32:31 [INFO] train episode 7607: reward = -50.62, steps = 57 00:32:32 [INFO] train episode 7608: reward = -29.94, steps = 61 00:32:32 [INFO] train episode 7609: reward = -28.33, steps = 48 00:32:32 [INFO] train episode 7610: reward = -77.80, steps = 61 00:32:33 [INFO] train episode 7611: reward = -74.61, steps = 52 00:32:33 [INFO] train episode 7612: reward = -62.77, steps = 55 00:32:33 [INFO] train episode 7613: reward = -34.61, steps = 37 00:32:34 [INFO] train episode 7614: reward = -33.13, steps = 28 00:32:34 [INFO] train episode 7615: reward = -44.21, steps = 49 00:32:34 [INFO] train episode 7616: reward = -73.45, steps = 49 00:32:35 [INFO] train episode 7617: reward = -71.18, steps = 64 00:32:35 [INFO] train episode 7618: reward = -34.02, steps = 43 00:32:35 [INFO] train episode 7619: reward = -44.26, steps = 56 00:32:36 [INFO] train episode 7620: reward = -34.70, steps = 50 00:32:36 [INFO] train episode 7621: reward = -63.55, steps = 63 00:32:36 [INFO] train episode 7622: reward = -57.67, steps = 47 00:32:37 [INFO] train episode 7623: reward = -97.34, steps = 75 00:32:37 [INFO] train episode 7624: reward = -97.17, steps = 52 00:32:38 [INFO] train episode 7625: reward = -80.86, steps = 75 00:32:38 [INFO] train episode 7626: reward = -90.35, steps = 48 00:32:39 [INFO] train episode 7627: reward = -29.77, steps = 47 00:32:39 [INFO] train episode 7628: reward = -37.10, steps = 64 00:32:39 [INFO] train episode 7629: reward = -43.42, steps = 52 00:32:40 [INFO] train episode 7630: reward = -72.71, steps = 42 00:32:40 [INFO] train episode 7631: reward = -46.50, steps = 40 00:32:40 [INFO] train episode 7632: reward = -54.40, steps = 45 00:32:40 [INFO] train episode 7633: reward = -65.41, steps = 41 00:32:41 [INFO] train episode 7634: reward = -37.54, steps = 36 00:32:41 [INFO] train episode 7635: reward = -23.04, steps = 44 00:32:41 [INFO] train episode 7636: reward = -49.80, steps = 54 00:32:42 [INFO] train episode 7637: reward = -68.01, steps = 57 00:32:42 [INFO] train episode 7638: reward = -47.32, steps = 33 00:32:42 [INFO] train episode 7639: reward = -32.60, steps = 50 00:32:43 [INFO] train episode 7640: reward = -53.55, steps = 62 00:32:43 [INFO] train episode 7641: reward = -39.49, steps = 42 00:32:43 [INFO] train episode 7642: reward = -60.84, steps = 43 00:32:44 [INFO] train episode 7643: reward = -83.46, steps = 58 00:32:44 [INFO] train episode 7644: reward = -38.06, steps = 53 00:32:44 [INFO] train episode 7645: reward = -21.62, steps = 50 00:32:45 [INFO] train episode 7646: reward = -45.17, steps = 54 00:32:45 [INFO] train episode 7647: reward = -29.17, steps = 38 00:32:45 [INFO] train episode 7648: reward = -49.88, steps = 29 00:32:45 [INFO] train episode 7649: reward = -45.34, steps = 38 00:32:46 [INFO] train episode 7650: reward = -24.31, steps = 41 00:32:46 [INFO] train episode 7651: reward = -29.54, steps = 49 00:32:46 [INFO] train episode 7652: reward = -53.12, steps = 50 00:32:47 [INFO] train episode 7653: reward = -85.50, steps = 84 00:32:47 [INFO] train episode 7654: reward = -54.49, steps = 56 00:32:47 [INFO] train episode 7655: reward = -41.22, steps = 32 00:32:48 [INFO] train episode 7656: reward = -53.30, steps = 44 00:32:48 [INFO] train episode 7657: reward = -20.99, steps = 39 00:32:48 [INFO] train episode 7658: reward = -71.40, steps = 55 00:32:49 [INFO] train episode 7659: reward = -71.19, steps = 65 00:32:49 [INFO] train episode 7660: reward = -55.80, steps = 38 00:32:49 [INFO] train episode 7661: reward = -54.21, steps = 34 00:32:49 [INFO] train episode 7662: reward = -43.48, steps = 36 00:32:50 [INFO] train episode 7663: reward = -28.53, steps = 38 00:32:50 [INFO] train episode 7664: reward = -26.86, steps = 102 00:32:51 [INFO] train episode 7665: reward = -24.29, steps = 47 00:32:51 [INFO] train episode 7666: reward = -33.03, steps = 35 00:32:51 [INFO] train episode 7667: reward = -33.84, steps = 35 00:32:52 [INFO] train episode 7668: reward = -60.25, steps = 94 00:32:52 [INFO] train episode 7669: reward = -41.52, steps = 34 00:32:52 [INFO] train episode 7670: reward = -75.61, steps = 50 00:32:53 [INFO] train episode 7671: reward = -44.28, steps = 56 00:32:53 [INFO] train episode 7672: reward = -50.52, steps = 55 00:32:53 [INFO] train episode 7673: reward = -80.67, steps = 46 00:32:54 [INFO] train episode 7674: reward = -28.63, steps = 43 00:32:54 [INFO] train episode 7675: reward = -30.84, steps = 37 00:32:54 [INFO] train episode 7676: reward = -69.64, steps = 50 00:32:55 [INFO] train episode 7677: reward = -31.06, steps = 68 00:32:55 [INFO] train episode 7678: reward = -68.47, steps = 61 00:32:55 [INFO] train episode 7679: reward = -43.16, steps = 46 00:32:56 [INFO] train episode 7680: reward = -66.03, steps = 44 00:32:56 [INFO] train episode 7681: reward = -36.89, steps = 65 00:32:57 [INFO] train episode 7682: reward = -38.62, steps = 52 00:32:57 [INFO] train episode 7683: reward = -40.17, steps = 40 00:32:57 [INFO] train episode 7684: reward = -33.29, steps = 52 00:32:57 [INFO] train episode 7685: reward = -33.58, steps = 44 00:32:58 [INFO] train episode 7686: reward = -56.99, steps = 39 00:32:58 [INFO] train episode 7687: reward = -36.54, steps = 81 00:32:59 [INFO] train episode 7688: reward = -25.05, steps = 47 00:32:59 [INFO] train episode 7689: reward = -34.29, steps = 58 00:32:59 [INFO] train episode 7690: reward = -50.56, steps = 38 00:32:59 [INFO] train episode 7691: reward = -36.78, steps = 50 00:33:00 [INFO] train episode 7692: reward = -70.88, steps = 42 00:33:00 [INFO] train episode 7693: reward = -40.12, steps = 44 00:33:00 [INFO] train episode 7694: reward = -55.70, steps = 60 00:33:01 [INFO] train episode 7695: reward = -37.57, steps = 86 00:33:01 [INFO] train episode 7696: reward = -68.18, steps = 46 00:33:02 [INFO] train episode 7697: reward = -104.11, steps = 79 00:33:02 [INFO] train episode 7698: reward = -28.59, steps = 42 00:33:03 [INFO] train episode 7699: reward = -31.48, steps = 78 00:33:03 [INFO] train episode 7700: reward = -75.63, steps = 63 00:33:03 [INFO] train episode 7701: reward = -48.29, steps = 41 00:33:04 [INFO] train episode 7702: reward = -76.96, steps = 63 00:33:04 [INFO] train episode 7703: reward = -19.71, steps = 69 00:33:05 [INFO] train episode 7704: reward = -41.80, steps = 45 00:33:05 [INFO] train episode 7705: reward = -46.32, steps = 45 00:33:05 [INFO] train episode 7706: reward = -78.27, steps = 81 00:33:06 [INFO] train episode 7707: reward = -38.55, steps = 63 00:33:06 [INFO] train episode 7708: reward = -52.58, steps = 17 00:33:06 [INFO] train episode 7709: reward = -50.47, steps = 71 00:33:07 [INFO] train episode 7710: reward = -24.60, steps = 40 00:33:07 [INFO] train episode 7711: reward = -65.73, steps = 39 00:33:07 [INFO] train episode 7712: reward = -35.80, steps = 39 00:33:08 [INFO] train episode 7713: reward = -56.41, steps = 73 00:33:08 [INFO] train episode 7714: reward = -48.65, steps = 42 00:33:08 [INFO] train episode 7715: reward = -47.06, steps = 46 00:33:09 [INFO] train episode 7716: reward = -46.54, steps = 47 00:33:09 [INFO] train episode 7717: reward = -44.13, steps = 78 00:33:10 [INFO] train episode 7718: reward = -48.75, steps = 65 00:33:10 [INFO] train episode 7719: reward = -40.47, steps = 29 00:33:10 [INFO] train episode 7720: reward = -35.98, steps = 45 00:33:10 [INFO] train episode 7721: reward = -53.87, steps = 55 00:33:11 [INFO] train episode 7722: reward = -41.98, steps = 58 00:33:11 [INFO] train episode 7723: reward = -37.26, steps = 45 00:33:12 [INFO] train episode 7724: reward = -32.33, steps = 67 00:33:12 [INFO] train episode 7725: reward = -21.87, steps = 49 00:33:12 [INFO] train episode 7726: reward = -35.17, steps = 45 00:33:12 [INFO] train episode 7727: reward = -76.13, steps = 49 00:33:13 [INFO] train episode 7728: reward = -71.21, steps = 65 00:33:13 [INFO] train episode 7729: reward = -37.24, steps = 46 00:33:14 [INFO] train episode 7730: reward = -37.77, steps = 66 00:33:14 [INFO] train episode 7731: reward = -45.08, steps = 44 00:33:14 [INFO] train episode 7732: reward = -51.29, steps = 44 00:33:15 [INFO] train episode 7733: reward = -59.96, steps = 52 00:33:15 [INFO] train episode 7734: reward = -42.18, steps = 58 00:33:15 [INFO] train episode 7735: reward = -27.39, steps = 47 00:33:16 [INFO] train episode 7736: reward = -29.32, steps = 46 00:33:16 [INFO] train episode 7737: reward = -31.51, steps = 49 00:33:17 [INFO] train episode 7738: reward = -64.43, steps = 95 00:33:17 [INFO] train episode 7739: reward = -41.65, steps = 44 00:33:17 [INFO] train episode 7740: reward = -30.90, steps = 31 00:33:18 [INFO] train episode 7741: reward = -53.20, steps = 68 00:33:18 [INFO] train episode 7742: reward = -53.00, steps = 59 00:33:18 [INFO] train episode 7743: reward = -39.51, steps = 42 00:33:19 [INFO] train episode 7744: reward = -25.10, steps = 37 00:33:19 [INFO] train episode 7745: reward = -47.01, steps = 87 00:33:20 [INFO] train episode 7746: reward = -73.76, steps = 68 00:33:20 [INFO] train episode 7747: reward = -25.44, steps = 34 00:33:20 [INFO] train episode 7748: reward = -64.16, steps = 65 00:33:21 [INFO] train episode 7749: reward = -40.32, steps = 47 00:33:21 [INFO] train episode 7750: reward = -32.14, steps = 36 00:33:21 [INFO] train episode 7751: reward = -66.50, steps = 48 00:33:21 [INFO] train episode 7752: reward = -36.22, steps = 42 00:33:22 [INFO] train episode 7753: reward = -29.03, steps = 40 00:33:22 [INFO] train episode 7754: reward = -47.60, steps = 63 00:33:22 [INFO] train episode 7755: reward = -39.58, steps = 45 00:33:23 [INFO] train episode 7756: reward = -33.48, steps = 77 00:33:23 [INFO] train episode 7757: reward = -29.28, steps = 47 00:33:23 [INFO] train episode 7758: reward = -28.90, steps = 40 00:33:24 [INFO] train episode 7759: reward = -46.35, steps = 56 00:33:24 [INFO] train episode 7760: reward = -59.11, steps = 62 00:33:25 [INFO] train episode 7761: reward = -85.31, steps = 71 00:33:25 [INFO] train episode 7762: reward = -30.13, steps = 39 00:33:25 [INFO] train episode 7763: reward = -50.86, steps = 54 00:33:26 [INFO] train episode 7764: reward = -15.53, steps = 58 00:33:26 [INFO] train episode 7765: reward = -74.38, steps = 62 00:33:26 [INFO] train episode 7766: reward = -46.33, steps = 32 00:33:27 [INFO] train episode 7767: reward = -56.92, steps = 82 00:33:27 [INFO] train episode 7768: reward = -60.57, steps = 63 00:33:27 [INFO] train episode 7769: reward = -16.44, steps = 46 00:33:28 [INFO] train episode 7770: reward = -5.54, steps = 49 00:33:28 [INFO] train episode 7771: reward = -96.53, steps = 66 00:33:29 [INFO] train episode 7772: reward = -74.34, steps = 66 00:33:29 [INFO] train episode 7773: reward = -48.22, steps = 25 00:33:29 [INFO] train episode 7774: reward = -86.70, steps = 48 00:33:29 [INFO] train episode 7775: reward = -26.80, steps = 63 00:33:30 [INFO] train episode 7776: reward = -37.45, steps = 46 00:33:30 [INFO] train episode 7777: reward = -41.13, steps = 34 00:33:31 [INFO] train episode 7778: reward = -21.29, steps = 45 00:33:31 [INFO] train episode 7779: reward = -88.38, steps = 66 00:33:31 [INFO] train episode 7780: reward = -26.80, steps = 43 00:33:32 [INFO] train episode 7781: reward = -61.00, steps = 60 00:33:32 [INFO] train episode 7782: reward = -67.51, steps = 56 00:33:32 [INFO] train episode 7783: reward = -43.42, steps = 38 00:33:33 [INFO] train episode 7784: reward = -13.17, steps = 42 00:33:33 [INFO] train episode 7785: reward = -80.80, steps = 67 00:33:33 [INFO] train episode 7786: reward = -29.73, steps = 47 00:33:34 [INFO] train episode 7787: reward = -34.92, steps = 67 00:33:34 [INFO] train episode 7788: reward = -37.46, steps = 39 00:33:34 [INFO] train episode 7789: reward = -35.13, steps = 55 00:33:35 [INFO] train episode 7790: reward = -24.57, steps = 56 00:33:35 [INFO] train episode 7791: reward = -45.19, steps = 27 00:33:35 [INFO] train episode 7792: reward = -85.10, steps = 68 00:33:36 [INFO] train episode 7793: reward = -42.95, steps = 37 00:33:36 [INFO] train episode 7794: reward = -77.54, steps = 63 00:33:36 [INFO] train episode 7795: reward = -26.08, steps = 40 00:33:37 [INFO] train episode 7796: reward = -121.16, steps = 116 00:33:37 [INFO] train episode 7797: reward = -27.10, steps = 32 00:33:37 [INFO] train episode 7798: reward = -40.47, steps = 51 00:33:38 [INFO] train episode 7799: reward = -36.38, steps = 50 00:33:38 [INFO] train episode 7800: reward = -48.35, steps = 72 00:33:39 [INFO] train episode 7801: reward = -39.51, steps = 43 00:33:39 [INFO] train episode 7802: reward = -84.66, steps = 79 00:33:39 [INFO] train episode 7803: reward = -74.83, steps = 44 00:33:40 [INFO] train episode 7804: reward = -53.34, steps = 67 00:33:40 [INFO] train episode 7805: reward = -51.48, steps = 51 00:33:40 [INFO] train episode 7806: reward = -36.18, steps = 29 00:33:41 [INFO] train episode 7807: reward = -36.96, steps = 49 00:33:41 [INFO] train episode 7808: reward = -32.33, steps = 99 00:33:42 [INFO] train episode 7809: reward = -31.75, steps = 49 00:33:42 [INFO] train episode 7810: reward = -23.16, steps = 46 00:33:42 [INFO] train episode 7811: reward = -45.76, steps = 60 00:33:43 [INFO] train episode 7812: reward = -95.44, steps = 65 00:33:43 [INFO] train episode 7813: reward = -39.07, steps = 55 00:33:43 [INFO] train episode 7814: reward = -32.19, steps = 39 00:33:44 [INFO] train episode 7815: reward = -38.86, steps = 57 00:33:44 [INFO] train episode 7816: reward = -37.29, steps = 50 00:33:45 [INFO] train episode 7817: reward = -26.59, steps = 49 00:33:45 [INFO] train episode 7818: reward = -6.13, steps = 59 00:33:45 [INFO] train episode 7819: reward = -44.02, steps = 25 00:33:45 [INFO] train episode 7820: reward = -35.07, steps = 35 00:33:46 [INFO] train episode 7821: reward = -33.33, steps = 48 00:33:46 [INFO] train episode 7822: reward = -54.58, steps = 27 00:33:46 [INFO] train episode 7823: reward = -61.10, steps = 58 00:33:47 [INFO] train episode 7824: reward = -15.19, steps = 50 00:33:47 [INFO] train episode 7825: reward = -24.16, steps = 40 00:33:47 [INFO] train episode 7826: reward = -36.90, steps = 68 00:33:48 [INFO] train episode 7827: reward = -36.31, steps = 42 00:33:48 [INFO] train episode 7828: reward = -24.19, steps = 57 00:33:48 [INFO] train episode 7829: reward = -17.99, steps = 39 00:33:49 [INFO] train episode 7830: reward = -16.97, steps = 66 00:33:49 [INFO] train episode 7831: reward = -66.66, steps = 71 00:33:49 [INFO] train episode 7832: reward = -35.84, steps = 34 00:33:50 [INFO] train episode 7833: reward = -47.56, steps = 54 00:33:50 [INFO] train episode 7834: reward = -31.76, steps = 50 00:33:50 [INFO] train episode 7835: reward = -37.48, steps = 53 00:33:51 [INFO] train episode 7836: reward = -21.10, steps = 58 00:33:51 [INFO] train episode 7837: reward = -36.86, steps = 39 00:33:51 [INFO] train episode 7838: reward = -14.79, steps = 58 00:33:51 [INFO] train episode 7839: reward = -26.31, steps = 47 00:33:52 [INFO] train episode 7840: reward = -27.85, steps = 34 00:33:52 [INFO] train episode 7841: reward = -27.94, steps = 39 00:33:52 [INFO] train episode 7842: reward = -34.47, steps = 39 00:33:53 [INFO] train episode 7843: reward = -32.91, steps = 58 00:33:53 [INFO] train episode 7844: reward = -32.20, steps = 45 00:33:53 [INFO] train episode 7845: reward = -58.41, steps = 63 00:33:54 [INFO] train episode 7846: reward = -59.28, steps = 40 00:33:54 [INFO] train episode 7847: reward = -23.60, steps = 36 00:33:54 [INFO] train episode 7848: reward = -32.88, steps = 87 00:33:55 [INFO] train episode 7849: reward = -33.70, steps = 53 00:33:55 [INFO] train episode 7850: reward = -88.59, steps = 88 00:33:56 [INFO] train episode 7851: reward = -35.92, steps = 56 00:33:56 [INFO] train episode 7852: reward = -29.00, steps = 61 00:33:57 [INFO] train episode 7853: reward = -22.35, steps = 67 00:33:57 [INFO] train episode 7854: reward = -35.21, steps = 51 00:33:57 [INFO] train episode 7855: reward = -32.91, steps = 45 00:33:58 [INFO] train episode 7856: reward = -13.59, steps = 45 00:33:58 [INFO] train episode 7857: reward = -34.43, steps = 44 00:33:58 [INFO] train episode 7858: reward = -25.69, steps = 53 00:33:59 [INFO] train episode 7859: reward = -37.89, steps = 43 00:33:59 [INFO] train episode 7860: reward = -24.30, steps = 46 00:33:59 [INFO] train episode 7861: reward = -42.26, steps = 54 00:34:00 [INFO] train episode 7862: reward = -37.69, steps = 53 00:34:00 [INFO] train episode 7863: reward = -34.45, steps = 67 00:34:00 [INFO] train episode 7864: reward = -31.04, steps = 38 00:34:01 [INFO] train episode 7865: reward = -21.44, steps = 47 00:34:01 [INFO] train episode 7866: reward = -22.59, steps = 49 00:34:01 [INFO] train episode 7867: reward = -29.38, steps = 23 00:34:01 [INFO] train episode 7868: reward = -3.07, steps = 42 00:34:02 [INFO] train episode 7869: reward = -32.03, steps = 41 00:34:02 [INFO] train episode 7870: reward = -48.99, steps = 22 00:34:02 [INFO] train episode 7871: reward = -55.61, steps = 46 00:34:02 [INFO] train episode 7872: reward = -32.20, steps = 37 00:34:03 [INFO] train episode 7873: reward = -45.22, steps = 33 00:34:03 [INFO] train episode 7874: reward = -25.35, steps = 59 00:34:03 [INFO] train episode 7875: reward = -17.02, steps = 47 00:34:03 [INFO] train episode 7876: reward = -31.34, steps = 18 00:34:04 [INFO] train episode 7877: reward = -24.26, steps = 51 00:34:04 [INFO] train episode 7878: reward = -73.66, steps = 42 00:34:05 [INFO] train episode 7879: reward = -50.69, steps = 74 00:34:05 [INFO] train episode 7880: reward = -25.93, steps = 28 00:34:05 [INFO] train episode 7881: reward = -94.28, steps = 62 00:34:06 [INFO] train episode 7882: reward = -28.98, steps = 61 00:34:06 [INFO] train episode 7883: reward = -28.06, steps = 54 00:34:06 [INFO] train episode 7884: reward = -85.54, steps = 67 00:34:07 [INFO] train episode 7885: reward = -28.02, steps = 57 00:34:07 [INFO] train episode 7886: reward = -33.06, steps = 53 00:34:07 [INFO] train episode 7887: reward = -20.55, steps = 41 00:34:08 [INFO] train episode 7888: reward = -55.23, steps = 46 00:34:08 [INFO] train episode 7889: reward = -7.82, steps = 50 00:34:08 [INFO] train episode 7890: reward = -39.53, steps = 50 00:34:09 [INFO] train episode 7891: reward = -60.55, steps = 44 00:34:09 [INFO] train episode 7892: reward = -33.02, steps = 35 00:34:09 [INFO] train episode 7893: reward = -27.07, steps = 35 00:34:10 [INFO] train episode 7894: reward = -26.87, steps = 44 00:34:10 [INFO] train episode 7895: reward = -85.23, steps = 77 00:34:11 [INFO] train episode 7896: reward = -59.23, steps = 79 00:34:11 [INFO] train episode 7897: reward = -45.66, steps = 40 00:34:11 [INFO] train episode 7898: reward = -50.87, steps = 51 00:34:11 [INFO] train episode 7899: reward = -52.59, steps = 33 00:34:12 [INFO] train episode 7900: reward = -2.68, steps = 61 00:34:12 [INFO] train episode 7901: reward = -27.65, steps = 31 00:34:12 [INFO] train episode 7902: reward = -59.02, steps = 49 00:34:13 [INFO] train episode 7903: reward = -27.71, steps = 30 00:34:13 [INFO] train episode 7904: reward = -38.95, steps = 41 00:34:13 [INFO] train episode 7905: reward = -33.76, steps = 43 00:34:13 [INFO] train episode 7906: reward = -16.48, steps = 40 00:34:14 [INFO] train episode 7907: reward = -34.40, steps = 41 00:34:14 [INFO] train episode 7908: reward = -62.64, steps = 58 00:34:14 [INFO] train episode 7909: reward = -51.89, steps = 51 00:34:15 [INFO] train episode 7910: reward = -22.10, steps = 55 00:34:15 [INFO] train episode 7911: reward = -82.06, steps = 65 00:34:15 [INFO] train episode 7912: reward = -43.34, steps = 47 00:34:16 [INFO] train episode 7913: reward = -18.54, steps = 51 00:34:16 [INFO] train episode 7914: reward = -20.75, steps = 44 00:34:16 [INFO] train episode 7915: reward = -10.72, steps = 34 00:34:17 [INFO] train episode 7916: reward = -45.44, steps = 74 00:34:17 [INFO] train episode 7917: reward = -34.92, steps = 23 00:34:17 [INFO] train episode 7918: reward = -5.70, steps = 41 00:34:17 [INFO] train episode 7919: reward = -27.06, steps = 43 00:34:18 [INFO] train episode 7920: reward = -27.13, steps = 49 00:34:18 [INFO] train episode 7921: reward = -35.62, steps = 41 00:34:18 [INFO] train episode 7922: reward = -57.20, steps = 22 00:34:18 [INFO] train episode 7923: reward = -25.32, steps = 29 00:34:19 [INFO] train episode 7924: reward = -28.28, steps = 48 00:34:19 [INFO] train episode 7925: reward = -32.17, steps = 44 00:34:19 [INFO] train episode 7926: reward = -5.06, steps = 51 00:34:20 [INFO] train episode 7927: reward = -23.65, steps = 49 00:34:20 [INFO] train episode 7928: reward = -28.10, steps = 25 00:34:20 [INFO] train episode 7929: reward = -25.58, steps = 43 00:34:20 [INFO] train episode 7930: reward = -33.38, steps = 54 00:34:21 [INFO] train episode 7931: reward = -36.62, steps = 54 00:34:21 [INFO] train episode 7932: reward = -17.03, steps = 46 00:34:21 [INFO] train episode 7933: reward = -69.55, steps = 48 00:34:22 [INFO] train episode 7934: reward = -36.14, steps = 76 00:34:22 [INFO] train episode 7935: reward = -14.28, steps = 38 00:34:23 [INFO] train episode 7936: reward = -7.79, steps = 53 00:34:23 [INFO] train episode 7937: reward = -65.14, steps = 60 00:34:24 [INFO] train episode 7938: reward = -11.99, steps = 60 00:34:24 [INFO] train episode 7939: reward = -22.39, steps = 41 00:34:24 [INFO] train episode 7940: reward = -13.09, steps = 47 00:34:24 [INFO] train episode 7941: reward = -24.65, steps = 39 00:34:25 [INFO] train episode 7942: reward = -20.23, steps = 34 00:34:25 [INFO] train episode 7943: reward = -52.06, steps = 54 00:34:25 [INFO] train episode 7944: reward = -33.10, steps = 31 00:34:26 [INFO] train episode 7945: reward = -21.50, steps = 52 00:34:26 [INFO] train episode 7946: reward = -30.10, steps = 43 00:34:26 [INFO] train episode 7947: reward = -37.92, steps = 31 00:34:26 [INFO] train episode 7948: reward = -6.08, steps = 36 00:34:27 [INFO] train episode 7949: reward = -25.52, steps = 35 00:34:27 [INFO] train episode 7950: reward = -2.97, steps = 45 00:34:27 [INFO] train episode 7951: reward = -14.14, steps = 43 00:34:27 [INFO] train episode 7952: reward = -63.49, steps = 63 00:34:28 [INFO] train episode 7953: reward = -31.09, steps = 49 00:34:28 [INFO] train episode 7954: reward = -21.11, steps = 34 00:34:28 [INFO] train episode 7955: reward = -33.30, steps = 18 00:34:28 [INFO] train episode 7956: reward = -30.46, steps = 19 00:34:29 [INFO] train episode 7957: reward = -45.16, steps = 61 00:34:29 [INFO] train episode 7958: reward = -4.73, steps = 40 00:34:29 [INFO] train episode 7959: reward = -29.53, steps = 23 00:34:29 [INFO] train episode 7960: reward = -22.77, steps = 48 00:34:30 [INFO] train episode 7961: reward = -29.56, steps = 30 00:34:30 [INFO] train episode 7962: reward = -28.66, steps = 23 00:34:30 [INFO] train episode 7963: reward = -18.36, steps = 46 00:34:30 [INFO] train episode 7964: reward = -42.07, steps = 48 00:34:31 [INFO] train episode 7965: reward = -33.67, steps = 49 00:34:31 [INFO] train episode 7966: reward = -23.89, steps = 38 00:34:31 [INFO] train episode 7967: reward = -10.81, steps = 43 00:34:32 [INFO] train episode 7968: reward = -20.86, steps = 33 00:34:32 [INFO] train episode 7969: reward = -22.87, steps = 38 00:34:32 [INFO] train episode 7970: reward = -19.69, steps = 57 00:34:32 [INFO] train episode 7971: reward = -26.68, steps = 22 00:34:33 [INFO] train episode 7972: reward = -37.95, steps = 37 00:34:33 [INFO] train episode 7973: reward = -22.60, steps = 43 00:34:33 [INFO] train episode 7974: reward = -23.74, steps = 44 00:34:33 [INFO] train episode 7975: reward = -40.81, steps = 31 00:34:34 [INFO] train episode 7976: reward = -14.89, steps = 49 00:34:34 [INFO] train episode 7977: reward = -11.99, steps = 44 00:34:34 [INFO] train episode 7978: reward = -30.05, steps = 82 00:34:35 [INFO] train episode 7979: reward = -29.31, steps = 36 00:34:35 [INFO] train episode 7980: reward = -31.93, steps = 40 00:34:35 [INFO] train episode 7981: reward = -34.61, steps = 33 00:34:35 [INFO] train episode 7982: reward = -25.98, steps = 39 00:34:36 [INFO] train episode 7983: reward = -32.80, steps = 39 00:34:36 [INFO] train episode 7984: reward = -35.52, steps = 30 00:34:36 [INFO] train episode 7985: reward = -37.28, steps = 39 00:34:37 [INFO] train episode 7986: reward = -28.71, steps = 63 00:34:37 [INFO] train episode 7987: reward = -31.35, steps = 20 00:34:37 [INFO] train episode 7988: reward = -34.69, steps = 53 00:34:38 [INFO] train episode 7989: reward = -39.33, steps = 43 00:34:38 [INFO] train episode 7990: reward = -24.21, steps = 33 00:34:38 [INFO] train episode 7991: reward = -23.18, steps = 31 00:34:38 [INFO] train episode 7992: reward = -34.06, steps = 51 00:34:39 [INFO] train episode 7993: reward = -41.17, steps = 57 00:34:39 [INFO] train episode 7994: reward = -78.20, steps = 60 00:34:39 [INFO] train episode 7995: reward = -21.83, steps = 31 00:34:39 [INFO] train episode 7996: reward = -41.95, steps = 22 00:34:40 [INFO] train episode 7997: reward = -9.98, steps = 52 00:34:40 [INFO] train episode 7998: reward = -36.59, steps = 58 00:34:40 [INFO] train episode 7999: reward = -19.51, steps = 22 00:34:41 [INFO] train episode 8000: reward = -27.29, steps = 38 00:34:41 [INFO] train episode 8001: reward = -47.53, steps = 16 00:34:41 [INFO] train episode 8002: reward = -26.65, steps = 66 00:34:41 [INFO] train episode 8003: reward = -60.92, steps = 53 00:34:42 [INFO] train episode 8004: reward = -40.53, steps = 28 00:34:42 [INFO] train episode 8005: reward = -41.34, steps = 27 00:34:42 [INFO] train episode 8006: reward = -29.32, steps = 50 00:34:42 [INFO] train episode 8007: reward = -20.25, steps = 41 00:34:43 [INFO] train episode 8008: reward = -34.20, steps = 31 00:34:43 [INFO] train episode 8009: reward = -35.99, steps = 38 00:34:43 [INFO] train episode 8010: reward = -34.22, steps = 27 00:34:43 [INFO] train episode 8011: reward = -30.37, steps = 24 00:34:44 [INFO] train episode 8012: reward = -28.97, steps = 36 00:34:44 [INFO] train episode 8013: reward = -19.98, steps = 32 00:34:44 [INFO] train episode 8014: reward = -34.70, steps = 45 00:34:44 [INFO] train episode 8015: reward = -48.76, steps = 39 00:34:45 [INFO] train episode 8016: reward = -23.29, steps = 47 00:34:45 [INFO] train episode 8017: reward = -20.94, steps = 32 00:34:45 [INFO] train episode 8018: reward = -13.83, steps = 37 00:34:45 [INFO] train episode 8019: reward = -41.99, steps = 27 00:34:46 [INFO] train episode 8020: reward = -18.63, steps = 41 00:34:46 [INFO] train episode 8021: reward = -10.64, steps = 47 00:34:46 [INFO] train episode 8022: reward = -30.64, steps = 30 00:34:46 [INFO] train episode 8023: reward = -19.92, steps = 41 00:34:47 [INFO] train episode 8024: reward = -45.66, steps = 24 00:34:47 [INFO] train episode 8025: reward = -41.33, steps = 22 00:34:47 [INFO] train episode 8026: reward = -31.36, steps = 45 00:34:47 [INFO] train episode 8027: reward = -60.40, steps = 65 00:34:48 [INFO] train episode 8028: reward = -40.16, steps = 35 00:34:48 [INFO] train episode 8029: reward = -9.17, steps = 36 00:34:48 [INFO] train episode 8030: reward = -49.07, steps = 30 00:34:48 [INFO] train episode 8031: reward = -21.41, steps = 35 00:34:49 [INFO] train episode 8032: reward = -47.12, steps = 43 00:34:49 [INFO] train episode 8033: reward = -22.97, steps = 47 00:34:49 [INFO] train episode 8034: reward = -25.58, steps = 42 00:34:50 [INFO] train episode 8035: reward = -21.68, steps = 44 00:34:50 [INFO] train episode 8036: reward = -15.91, steps = 31 00:34:50 [INFO] train episode 8037: reward = -50.27, steps = 31 00:34:50 [INFO] train episode 8038: reward = -23.89, steps = 25 00:34:51 [INFO] train episode 8039: reward = -26.46, steps = 35 00:34:51 [INFO] train episode 8040: reward = -32.00, steps = 31 00:34:51 [INFO] train episode 8041: reward = -28.43, steps = 36 00:34:51 [INFO] train episode 8042: reward = -34.20, steps = 52 00:34:52 [INFO] train episode 8043: reward = -26.01, steps = 29 00:34:52 [INFO] train episode 8044: reward = -16.15, steps = 44 00:34:52 [INFO] train episode 8045: reward = -23.38, steps = 29 00:34:52 [INFO] train episode 8046: reward = -38.55, steps = 23 00:34:52 [INFO] train episode 8047: reward = -28.38, steps = 21 00:34:53 [INFO] train episode 8048: reward = -65.54, steps = 59 00:34:53 [INFO] train episode 8049: reward = -34.15, steps = 39 00:34:53 [INFO] train episode 8050: reward = -24.39, steps = 23 00:34:53 [INFO] train episode 8051: reward = -32.36, steps = 27 00:34:54 [INFO] train episode 8052: reward = -28.07, steps = 32 00:34:54 [INFO] train episode 8053: reward = -42.51, steps = 30 00:34:54 [INFO] train episode 8054: reward = -37.43, steps = 32 00:34:54 [INFO] train episode 8055: reward = -18.87, steps = 30 00:34:54 [INFO] train episode 8056: reward = -37.70, steps = 28 00:34:55 [INFO] train episode 8057: reward = -45.80, steps = 31 00:34:55 [INFO] train episode 8058: reward = -32.68, steps = 26 00:34:55 [INFO] train episode 8059: reward = -12.53, steps = 37 00:34:55 [INFO] train episode 8060: reward = -35.10, steps = 40 00:34:56 [INFO] train episode 8061: reward = -45.66, steps = 69 00:34:56 [INFO] train episode 8062: reward = -9.24, steps = 40 00:34:56 [INFO] train episode 8063: reward = -36.15, steps = 28 00:34:56 [INFO] train episode 8064: reward = -36.67, steps = 34 00:34:57 [INFO] train episode 8065: reward = -88.05, steps = 60 00:34:57 [INFO] train episode 8066: reward = -32.68, steps = 23 00:34:57 [INFO] train episode 8067: reward = -16.60, steps = 39 00:34:57 [INFO] train episode 8068: reward = -32.75, steps = 30 00:34:58 [INFO] train episode 8069: reward = -42.20, steps = 35 00:34:58 [INFO] train episode 8070: reward = -16.46, steps = 46 00:34:58 [INFO] train episode 8071: reward = -27.42, steps = 31 00:34:58 [INFO] train episode 8072: reward = -26.02, steps = 23 00:34:59 [INFO] train episode 8073: reward = -30.34, steps = 27 00:34:59 [INFO] train episode 8074: reward = -43.57, steps = 35 00:34:59 [INFO] train episode 8075: reward = -29.11, steps = 39 00:34:59 [INFO] train episode 8076: reward = -38.68, steps = 22 00:35:00 [INFO] train episode 8077: reward = -47.43, steps = 43 00:35:00 [INFO] train episode 8078: reward = -25.64, steps = 33 00:35:00 [INFO] train episode 8079: reward = -29.23, steps = 50 00:35:00 [INFO] train episode 8080: reward = -8.52, steps = 37 00:35:01 [INFO] train episode 8081: reward = -34.00, steps = 34 00:35:01 [INFO] train episode 8082: reward = -34.01, steps = 35 00:35:01 [INFO] train episode 8083: reward = -50.58, steps = 31 00:35:01 [INFO] train episode 8084: reward = -27.82, steps = 39 00:35:01 [INFO] train episode 8085: reward = -27.14, steps = 27 00:35:02 [INFO] train episode 8086: reward = -18.76, steps = 45 00:35:02 [INFO] train episode 8087: reward = -36.42, steps = 45 00:35:02 [INFO] train episode 8088: reward = -35.23, steps = 59 00:35:03 [INFO] train episode 8089: reward = -41.57, steps = 41 00:35:03 [INFO] train episode 8090: reward = -5.48, steps = 42 00:35:04 [INFO] train episode 8091: reward = -56.82, steps = 36 00:35:04 [INFO] train episode 8092: reward = -14.39, steps = 31 00:35:04 [INFO] train episode 8093: reward = -29.78, steps = 32 00:35:04 [INFO] train episode 8094: reward = -35.62, steps = 24 00:35:04 [INFO] train episode 8095: reward = -38.73, steps = 22 00:35:05 [INFO] train episode 8096: reward = -29.26, steps = 51 00:35:05 [INFO] train episode 8097: reward = -31.93, steps = 38 00:35:06 [INFO] train episode 8098: reward = -30.16, steps = 51 00:35:06 [INFO] train episode 8099: reward = -47.42, steps = 47 00:35:06 [INFO] train episode 8100: reward = -39.60, steps = 25 00:35:06 [INFO] train episode 8101: reward = -41.88, steps = 42 00:35:07 [INFO] train episode 8102: reward = -30.47, steps = 37 00:35:07 [INFO] train episode 8103: reward = -24.20, steps = 28 00:35:07 [INFO] train episode 8104: reward = -35.95, steps = 25 00:35:07 [INFO] train episode 8105: reward = -35.84, steps = 29 00:35:07 [INFO] train episode 8106: reward = -45.75, steps = 33 00:35:08 [INFO] train episode 8107: reward = -35.37, steps = 28 00:35:08 [INFO] train episode 8108: reward = -36.67, steps = 37 00:35:08 [INFO] train episode 8109: reward = -46.40, steps = 23 00:35:08 [INFO] train episode 8110: reward = -35.31, steps = 42 00:35:09 [INFO] train episode 8111: reward = -14.72, steps = 47 00:35:09 [INFO] train episode 8112: reward = -24.81, steps = 34 00:35:09 [INFO] train episode 8113: reward = -36.45, steps = 19 00:35:09 [INFO] train episode 8114: reward = -34.78, steps = 27 00:35:09 [INFO] train episode 8115: reward = -39.27, steps = 38 00:35:10 [INFO] train episode 8116: reward = -17.12, steps = 25 00:35:10 [INFO] train episode 8117: reward = -27.00, steps = 33 00:35:10 [INFO] train episode 8118: reward = -20.61, steps = 39 00:35:10 [INFO] train episode 8119: reward = -34.31, steps = 25 00:35:11 [INFO] train episode 8120: reward = -41.35, steps = 46 00:35:11 [INFO] train episode 8121: reward = -42.66, steps = 25 00:35:11 [INFO] train episode 8122: reward = -28.12, steps = 23 00:35:11 [INFO] train episode 8123: reward = -25.61, steps = 26 00:35:11 [INFO] train episode 8124: reward = -25.71, steps = 28 00:35:12 [INFO] train episode 8125: reward = -33.17, steps = 21 00:35:12 [INFO] train episode 8126: reward = -45.62, steps = 42 00:35:12 [INFO] train episode 8127: reward = -22.57, steps = 21 00:35:12 [INFO] train episode 8128: reward = -21.71, steps = 32 00:35:12 [INFO] train episode 8129: reward = -29.39, steps = 34 00:35:13 [INFO] train episode 8130: reward = -26.26, steps = 34 00:35:13 [INFO] train episode 8131: reward = -28.44, steps = 20 00:35:13 [INFO] train episode 8132: reward = -31.09, steps = 35 00:35:13 [INFO] train episode 8133: reward = -23.91, steps = 35 00:35:14 [INFO] train episode 8134: reward = -26.49, steps = 36 00:35:14 [INFO] train episode 8135: reward = -21.65, steps = 27 00:35:14 [INFO] train episode 8136: reward = -9.67, steps = 40 00:35:14 [INFO] train episode 8137: reward = -33.80, steps = 28 00:35:14 [INFO] train episode 8138: reward = -21.03, steps = 42 00:35:15 [INFO] train episode 8139: reward = -36.43, steps = 40 00:35:15 [INFO] train episode 8140: reward = -26.38, steps = 30 00:35:15 [INFO] train episode 8141: reward = -85.09, steps = 63 00:35:16 [INFO] train episode 8142: reward = -28.90, steps = 31 00:35:16 [INFO] train episode 8143: reward = -77.54, steps = 64 00:35:16 [INFO] train episode 8144: reward = -28.44, steps = 38 00:35:17 [INFO] train episode 8145: reward = -18.28, steps = 51 00:35:17 [INFO] train episode 8146: reward = -27.67, steps = 25 00:35:17 [INFO] train episode 8147: reward = -25.21, steps = 21 00:35:17 [INFO] train episode 8148: reward = -25.99, steps = 39 00:35:18 [INFO] train episode 8149: reward = -35.00, steps = 49 00:35:18 [INFO] train episode 8150: reward = -16.45, steps = 26 00:35:18 [INFO] train episode 8151: reward = -39.77, steps = 25 00:35:18 [INFO] train episode 8152: reward = -25.84, steps = 22 00:35:18 [INFO] train episode 8153: reward = -33.57, steps = 23 00:35:19 [INFO] train episode 8154: reward = -20.30, steps = 29 00:35:19 [INFO] train episode 8155: reward = -29.85, steps = 25 00:35:19 [INFO] train episode 8156: reward = -37.32, steps = 23 00:35:19 [INFO] train episode 8157: reward = -27.75, steps = 27 00:35:19 [INFO] train episode 8158: reward = -30.35, steps = 33 00:35:19 [INFO] train episode 8159: reward = -31.96, steps = 25 00:35:20 [INFO] train episode 8160: reward = -37.99, steps = 60 00:35:20 [INFO] train episode 8161: reward = -66.15, steps = 30 00:35:20 [INFO] train episode 8162: reward = -47.65, steps = 49 00:35:21 [INFO] train episode 8163: reward = -19.36, steps = 28 00:35:21 [INFO] train episode 8164: reward = -29.55, steps = 30 00:35:21 [INFO] train episode 8165: reward = -34.83, steps = 31 00:35:21 [INFO] train episode 8166: reward = -31.82, steps = 20 00:35:21 [INFO] train episode 8167: reward = -31.73, steps = 32 00:35:22 [INFO] train episode 8168: reward = -36.74, steps = 30 00:35:22 [INFO] train episode 8169: reward = -29.69, steps = 31 00:35:22 [INFO] train episode 8170: reward = -29.46, steps = 24 00:35:22 [INFO] train episode 8171: reward = -32.61, steps = 29 00:35:22 [INFO] train episode 8172: reward = -33.08, steps = 21 00:35:23 [INFO] train episode 8173: reward = -23.77, steps = 43 00:35:23 [INFO] train episode 8174: reward = -25.03, steps = 29 00:35:23 [INFO] train episode 8175: reward = -40.68, steps = 28 00:35:23 [INFO] train episode 8176: reward = -22.77, steps = 31 00:35:24 [INFO] train episode 8177: reward = -24.51, steps = 26 00:35:24 [INFO] train episode 8178: reward = -35.51, steps = 31 00:35:24 [INFO] train episode 8179: reward = -30.17, steps = 38 00:35:24 [INFO] train episode 8180: reward = -21.17, steps = 28 00:35:24 [INFO] train episode 8181: reward = -26.78, steps = 21 00:35:25 [INFO] train episode 8182: reward = -36.27, steps = 39 00:35:25 [INFO] train episode 8183: reward = -28.91, steps = 23 00:35:25 [INFO] train episode 8184: reward = -17.34, steps = 32 00:35:25 [INFO] train episode 8185: reward = -34.32, steps = 22 00:35:25 [INFO] train episode 8186: reward = -34.42, steps = 24 00:35:25 [INFO] train episode 8187: reward = -41.65, steps = 22 00:35:26 [INFO] train episode 8188: reward = -39.32, steps = 26 00:35:26 [INFO] train episode 8189: reward = -35.29, steps = 26 00:35:26 [INFO] train episode 8190: reward = -31.84, steps = 37 00:35:26 [INFO] train episode 8191: reward = -46.29, steps = 24 00:35:26 [INFO] train episode 8192: reward = -33.00, steps = 25 00:35:27 [INFO] train episode 8193: reward = -30.55, steps = 28 00:35:27 [INFO] train episode 8194: reward = -33.60, steps = 39 00:35:27 [INFO] train episode 8195: reward = -29.83, steps = 32 00:35:27 [INFO] train episode 8196: reward = -36.35, steps = 21 00:35:27 [INFO] train episode 8197: reward = -25.38, steps = 29 00:35:28 [INFO] train episode 8198: reward = -36.30, steps = 29 00:35:28 [INFO] train episode 8199: reward = -27.36, steps = 45 00:35:28 [INFO] train episode 8200: reward = -24.75, steps = 34 00:35:28 [INFO] train episode 8201: reward = -24.81, steps = 29 00:35:29 [INFO] train episode 8202: reward = -50.79, steps = 23 00:35:29 [INFO] train episode 8203: reward = -22.85, steps = 25 00:35:29 [INFO] train episode 8204: reward = -26.16, steps = 21 00:35:29 [INFO] train episode 8205: reward = -77.24, steps = 71 00:35:29 [INFO] train episode 8206: reward = -38.63, steps = 25 00:35:30 [INFO] train episode 8207: reward = -31.89, steps = 38 00:35:30 [INFO] train episode 8208: reward = -18.37, steps = 36 00:35:30 [INFO] train episode 8209: reward = -49.03, steps = 34 00:35:31 [INFO] train episode 8210: reward = -38.21, steps = 45 00:35:31 [INFO] train episode 8211: reward = -35.74, steps = 40 00:35:31 [INFO] train episode 8212: reward = -40.28, steps = 26 00:35:31 [INFO] train episode 8213: reward = -41.90, steps = 33 00:35:32 [INFO] train episode 8214: reward = -38.23, steps = 20 00:35:32 [INFO] train episode 8215: reward = -31.32, steps = 30 00:35:32 [INFO] train episode 8216: reward = -31.94, steps = 26 00:35:32 [INFO] train episode 8217: reward = -25.35, steps = 27 00:35:32 [INFO] train episode 8218: reward = -32.63, steps = 24 00:35:32 [INFO] train episode 8219: reward = -40.32, steps = 22 00:35:33 [INFO] train episode 8220: reward = -29.34, steps = 30 00:35:33 [INFO] train episode 8221: reward = -22.91, steps = 31 00:35:33 [INFO] train episode 8222: reward = -31.04, steps = 31 00:35:33 [INFO] train episode 8223: reward = -29.72, steps = 34 00:35:34 [INFO] train episode 8224: reward = -25.05, steps = 43 00:35:34 [INFO] train episode 8225: reward = -29.38, steps = 29 00:35:34 [INFO] train episode 8226: reward = -26.53, steps = 26 00:35:34 [INFO] train episode 8227: reward = -28.02, steps = 45 00:35:34 [INFO] train episode 8228: reward = -50.06, steps = 19 00:35:35 [INFO] train episode 8229: reward = -34.74, steps = 25 00:35:35 [INFO] train episode 8230: reward = -35.10, steps = 25 00:35:35 [INFO] train episode 8231: reward = -33.47, steps = 25 00:35:35 [INFO] train episode 8232: reward = -29.26, steps = 34 00:35:35 [INFO] train episode 8233: reward = -25.75, steps = 29 00:35:35 [INFO] train episode 8234: reward = -33.47, steps = 29 00:35:36 [INFO] train episode 8235: reward = -32.08, steps = 44 00:35:36 [INFO] train episode 8236: reward = -30.92, steps = 35 00:35:36 [INFO] train episode 8237: reward = -33.98, steps = 22 00:35:36 [INFO] train episode 8238: reward = -28.15, steps = 19 00:35:36 [INFO] train episode 8239: reward = -33.39, steps = 27 00:35:37 [INFO] train episode 8240: reward = -27.33, steps = 21 00:35:37 [INFO] train episode 8241: reward = -32.35, steps = 33 00:35:37 [INFO] train episode 8242: reward = -23.02, steps = 40 00:35:37 [INFO] train episode 8243: reward = -21.06, steps = 27 00:35:37 [INFO] train episode 8244: reward = -22.83, steps = 27 00:35:38 [INFO] train episode 8245: reward = -27.71, steps = 30 00:35:38 [INFO] train episode 8246: reward = -41.57, steps = 26 00:35:38 [INFO] train episode 8247: reward = -32.08, steps = 30 00:35:38 [INFO] train episode 8248: reward = -19.95, steps = 47 00:35:39 [INFO] train episode 8249: reward = -35.98, steps = 20 00:35:39 [INFO] train episode 8250: reward = -72.04, steps = 57 00:35:39 [INFO] train episode 8251: reward = -43.02, steps = 25 00:35:39 [INFO] train episode 8252: reward = -39.79, steps = 22 00:35:39 [INFO] train episode 8253: reward = -30.28, steps = 29 00:35:40 [INFO] train episode 8254: reward = -41.69, steps = 32 00:35:40 [INFO] train episode 8255: reward = -42.84, steps = 22 00:35:40 [INFO] train episode 8256: reward = -33.64, steps = 24 00:35:40 [INFO] train episode 8257: reward = -26.25, steps = 27 00:35:40 [INFO] train episode 8258: reward = -23.05, steps = 21 00:35:40 [INFO] train episode 8259: reward = -24.09, steps = 26 00:35:41 [INFO] train episode 8260: reward = -31.10, steps = 26 00:35:41 [INFO] train episode 8261: reward = -33.06, steps = 39 00:35:41 [INFO] train episode 8262: reward = -33.34, steps = 32 00:35:41 [INFO] train episode 8263: reward = -41.83, steps = 34 00:35:41 [INFO] train episode 8264: reward = -36.07, steps = 21 00:35:42 [INFO] train episode 8265: reward = -39.38, steps = 32 00:35:42 [INFO] train episode 8266: reward = -37.11, steps = 28 00:35:42 [INFO] train episode 8267: reward = -35.73, steps = 41 00:35:42 [INFO] train episode 8268: reward = -27.69, steps = 28 00:35:42 [INFO] train episode 8269: reward = -29.17, steps = 20 00:35:43 [INFO] train episode 8270: reward = -32.83, steps = 38 00:35:43 [INFO] train episode 8271: reward = -41.49, steps = 34 00:35:43 [INFO] train episode 8272: reward = -37.87, steps = 18 00:35:43 [INFO] train episode 8273: reward = -27.16, steps = 35 00:35:44 [INFO] train episode 8274: reward = -33.09, steps = 23 00:35:44 [INFO] train episode 8275: reward = -46.60, steps = 34 00:35:44 [INFO] train episode 8276: reward = -37.26, steps = 27 00:35:44 [INFO] train episode 8277: reward = -48.03, steps = 44 00:35:45 [INFO] train episode 8278: reward = -22.69, steps = 27 00:35:45 [INFO] train episode 8279: reward = -28.91, steps = 26 00:35:45 [INFO] train episode 8280: reward = -20.76, steps = 21 00:35:45 [INFO] train episode 8281: reward = -48.36, steps = 30 00:35:46 [INFO] train episode 8282: reward = -51.12, steps = 36 00:35:46 [INFO] train episode 8283: reward = -31.33, steps = 34 00:35:46 [INFO] train episode 8284: reward = -37.71, steps = 23 00:35:46 [INFO] train episode 8285: reward = -49.49, steps = 36 00:35:46 [INFO] train episode 8286: reward = -30.90, steps = 53 00:35:47 [INFO] train episode 8287: reward = -33.25, steps = 34 00:35:47 [INFO] train episode 8288: reward = -31.42, steps = 27 00:35:47 [INFO] train episode 8289: reward = -26.50, steps = 27 00:35:47 [INFO] train episode 8290: reward = -59.10, steps = 48 00:35:48 [INFO] train episode 8291: reward = -41.47, steps = 21 00:35:48 [INFO] train episode 8292: reward = -35.46, steps = 28 00:35:48 [INFO] train episode 8293: reward = -33.60, steps = 19 00:35:48 [INFO] train episode 8294: reward = -27.02, steps = 28 00:35:48 [INFO] train episode 8295: reward = -40.37, steps = 26 00:35:48 [INFO] train episode 8296: reward = -44.02, steps = 21 00:35:49 [INFO] train episode 8297: reward = -30.34, steps = 42 00:35:49 [INFO] train episode 8298: reward = -33.96, steps = 25 00:35:49 [INFO] train episode 8299: reward = -27.60, steps = 30 00:35:49 [INFO] train episode 8300: reward = -44.71, steps = 28 00:35:49 [INFO] train episode 8301: reward = -27.46, steps = 34 00:35:50 [INFO] train episode 8302: reward = -12.78, steps = 54 00:35:50 [INFO] train episode 8303: reward = -24.66, steps = 32 00:35:50 [INFO] train episode 8304: reward = -25.13, steps = 43 00:35:51 [INFO] train episode 8305: reward = -28.39, steps = 38 00:35:51 [INFO] train episode 8306: reward = -37.47, steps = 39 00:35:51 [INFO] train episode 8307: reward = -24.99, steps = 37 00:35:51 [INFO] train episode 8308: reward = -48.11, steps = 37 00:35:52 [INFO] train episode 8309: reward = -32.65, steps = 22 00:35:52 [INFO] train episode 8310: reward = -44.05, steps = 20 00:35:52 [INFO] train episode 8311: reward = -25.69, steps = 28 00:35:52 [INFO] train episode 8312: reward = -31.12, steps = 32 00:35:52 [INFO] train episode 8313: reward = -28.95, steps = 41 00:35:53 [INFO] train episode 8314: reward = -42.82, steps = 43 00:35:53 [INFO] train episode 8315: reward = -37.53, steps = 26 00:35:53 [INFO] train episode 8316: reward = -44.99, steps = 34 00:35:53 [INFO] train episode 8317: reward = -32.17, steps = 21 00:35:53 [INFO] train episode 8318: reward = -43.11, steps = 31 00:35:54 [INFO] train episode 8319: reward = -36.47, steps = 27 00:35:54 [INFO] train episode 8320: reward = -42.05, steps = 36 00:35:54 [INFO] train episode 8321: reward = -31.01, steps = 27 00:35:54 [INFO] train episode 8322: reward = -23.48, steps = 21 00:35:54 [INFO] train episode 8323: reward = -21.59, steps = 24 00:35:55 [INFO] train episode 8324: reward = -46.01, steps = 28 00:35:55 [INFO] train episode 8325: reward = -30.64, steps = 61 00:35:55 [INFO] train episode 8326: reward = -40.44, steps = 44 00:35:55 [INFO] train episode 8327: reward = -25.32, steps = 28 00:35:56 [INFO] train episode 8328: reward = -55.39, steps = 31 00:35:56 [INFO] train episode 8329: reward = -31.60, steps = 30 00:35:56 [INFO] train episode 8330: reward = -32.54, steps = 30 00:35:56 [INFO] train episode 8331: reward = -40.73, steps = 28 00:35:56 [INFO] train episode 8332: reward = -38.75, steps = 23 00:35:57 [INFO] train episode 8333: reward = -33.91, steps = 26 00:35:57 [INFO] train episode 8334: reward = -21.18, steps = 29 00:35:57 [INFO] train episode 8335: reward = -32.47, steps = 33 00:35:57 [INFO] train episode 8336: reward = -34.57, steps = 31 00:35:57 [INFO] train episode 8337: reward = -44.63, steps = 30 00:35:58 [INFO] train episode 8338: reward = -29.02, steps = 21 00:35:58 [INFO] train episode 8339: reward = -47.02, steps = 25 00:35:58 [INFO] train episode 8340: reward = -9.05, steps = 50 00:35:59 [INFO] train episode 8341: reward = -15.87, steps = 26 00:35:59 [INFO] train episode 8342: reward = -52.13, steps = 25 00:35:59 [INFO] train episode 8343: reward = -23.11, steps = 31 00:35:59 [INFO] train episode 8344: reward = -28.31, steps = 57 00:36:00 [INFO] train episode 8345: reward = -33.45, steps = 27 00:36:00 [INFO] train episode 8346: reward = -38.35, steps = 26 00:36:00 [INFO] train episode 8347: reward = -31.01, steps = 21 00:36:00 [INFO] train episode 8348: reward = -34.71, steps = 28 00:36:00 [INFO] train episode 8349: reward = -26.09, steps = 32 00:36:00 [INFO] train episode 8350: reward = -36.65, steps = 32 00:36:01 [INFO] train episode 8351: reward = -30.71, steps = 32 00:36:01 [INFO] train episode 8352: reward = -22.87, steps = 20 00:36:01 [INFO] train episode 8353: reward = -33.70, steps = 35 00:36:01 [INFO] train episode 8354: reward = -30.27, steps = 30 00:36:02 [INFO] train episode 8355: reward = -28.14, steps = 33 00:36:02 [INFO] train episode 8356: reward = -33.38, steps = 22 00:36:02 [INFO] train episode 8357: reward = -21.51, steps = 31 00:36:02 [INFO] train episode 8358: reward = -32.21, steps = 32 00:36:02 [INFO] train episode 8359: reward = -38.82, steps = 24 00:36:02 [INFO] train episode 8360: reward = -24.78, steps = 26 00:36:03 [INFO] train episode 8361: reward = -35.57, steps = 21 00:36:03 [INFO] train episode 8362: reward = -40.82, steps = 27 00:36:03 [INFO] train episode 8363: reward = -35.28, steps = 25 00:36:03 [INFO] train episode 8364: reward = -34.39, steps = 26 00:36:03 [INFO] train episode 8365: reward = -31.27, steps = 22 00:36:04 [INFO] train episode 8366: reward = -39.47, steps = 27 00:36:04 [INFO] train episode 8367: reward = -40.76, steps = 24 00:36:04 [INFO] train episode 8368: reward = -27.66, steps = 27 00:36:04 [INFO] train episode 8369: reward = -18.31, steps = 35 00:36:04 [INFO] train episode 8370: reward = -37.84, steps = 25 00:36:04 [INFO] train episode 8371: reward = -28.54, steps = 22 00:36:05 [INFO] train episode 8372: reward = -26.39, steps = 29 00:36:05 [INFO] train episode 8373: reward = -42.21, steps = 22 00:36:05 [INFO] train episode 8374: reward = -33.38, steps = 21 00:36:05 [INFO] train episode 8375: reward = -21.17, steps = 38 00:36:05 [INFO] train episode 8376: reward = -24.32, steps = 27 00:36:06 [INFO] train episode 8377: reward = -30.15, steps = 33 00:36:06 [INFO] train episode 8378: reward = -22.43, steps = 30 00:36:06 [INFO] train episode 8379: reward = -31.66, steps = 39 00:36:06 [INFO] train episode 8380: reward = -51.57, steps = 24 00:36:06 [INFO] train episode 8381: reward = -37.85, steps = 22 00:36:07 [INFO] train episode 8382: reward = -25.89, steps = 27 00:36:07 [INFO] train episode 8383: reward = -39.82, steps = 26 00:36:07 [INFO] train episode 8384: reward = -43.89, steps = 30 00:36:07 [INFO] train episode 8385: reward = -43.93, steps = 33 00:36:07 [INFO] train episode 8386: reward = -27.98, steps = 33 00:36:08 [INFO] train episode 8387: reward = -48.14, steps = 30 00:36:08 [INFO] train episode 8388: reward = -28.90, steps = 36 00:36:08 [INFO] train episode 8389: reward = -38.66, steps = 30 00:36:08 [INFO] train episode 8390: reward = -37.97, steps = 28 00:36:09 [INFO] train episode 8391: reward = -41.17, steps = 25 00:36:09 [INFO] train episode 8392: reward = -36.24, steps = 21 00:36:09 [INFO] train episode 8393: reward = -37.42, steps = 29 00:36:09 [INFO] train episode 8394: reward = -35.02, steps = 25 00:36:09 [INFO] train episode 8395: reward = -34.68, steps = 31 00:36:10 [INFO] train episode 8396: reward = -23.14, steps = 32 00:36:10 [INFO] train episode 8397: reward = -30.24, steps = 31 00:36:10 [INFO] train episode 8398: reward = -44.77, steps = 22 00:36:10 [INFO] train episode 8399: reward = -38.40, steps = 38 00:36:10 [INFO] train episode 8400: reward = -13.90, steps = 44 00:36:11 [INFO] train episode 8401: reward = -31.97, steps = 24 00:36:11 [INFO] train episode 8402: reward = -34.17, steps = 25 00:36:11 [INFO] train episode 8403: reward = -35.85, steps = 25 00:36:11 [INFO] train episode 8404: reward = -35.80, steps = 32 00:36:12 [INFO] train episode 8405: reward = -37.73, steps = 27 00:36:12 [INFO] train episode 8406: reward = -22.40, steps = 21 00:36:12 [INFO] train episode 8407: reward = -39.60, steps = 36 00:36:12 [INFO] train episode 8408: reward = -30.63, steps = 23 00:36:12 [INFO] train episode 8409: reward = -35.85, steps = 30 00:36:13 [INFO] train episode 8410: reward = -32.30, steps = 26 00:36:13 [INFO] train episode 8411: reward = -30.00, steps = 25 00:36:13 [INFO] train episode 8412: reward = -38.05, steps = 30 00:36:13 [INFO] train episode 8413: reward = -50.84, steps = 42 00:36:14 [INFO] train episode 8414: reward = -53.33, steps = 44 00:36:14 [INFO] train episode 8415: reward = -52.12, steps = 28 00:36:14 [INFO] train episode 8416: reward = -26.37, steps = 31 00:36:14 [INFO] train episode 8417: reward = -39.98, steps = 30 00:36:14 [INFO] train episode 8418: reward = -42.42, steps = 30 00:36:15 [INFO] train episode 8419: reward = -35.04, steps = 27 00:36:15 [INFO] train episode 8420: reward = -39.95, steps = 22 00:36:15 [INFO] train episode 8421: reward = -37.82, steps = 32 00:36:15 [INFO] train episode 8422: reward = -34.04, steps = 20 00:36:15 [INFO] train episode 8423: reward = -36.20, steps = 26 00:36:15 [INFO] train episode 8424: reward = -34.31, steps = 28 00:36:16 [INFO] train episode 8425: reward = -21.35, steps = 29 00:36:16 [INFO] train episode 8426: reward = -46.11, steps = 23 00:36:16 [INFO] train episode 8427: reward = -30.94, steps = 31 00:36:16 [INFO] train episode 8428: reward = -37.45, steps = 21 00:36:16 [INFO] train episode 8429: reward = -15.84, steps = 37 00:36:17 [INFO] train episode 8430: reward = -33.36, steps = 33 00:36:17 [INFO] train episode 8431: reward = -30.86, steps = 21 00:36:17 [INFO] train episode 8432: reward = -22.85, steps = 24 00:36:17 [INFO] train episode 8433: reward = -37.69, steps = 31 00:36:17 [INFO] train episode 8434: reward = -23.34, steps = 28 00:36:18 [INFO] train episode 8435: reward = -38.36, steps = 31 00:36:18 [INFO] train episode 8436: reward = -35.33, steps = 29 00:36:18 [INFO] train episode 8437: reward = -32.83, steps = 22 00:36:18 [INFO] train episode 8438: reward = -37.26, steps = 28 00:36:18 [INFO] train episode 8439: reward = -47.98, steps = 36 00:36:19 [INFO] train episode 8440: reward = -53.38, steps = 20 00:36:19 [INFO] train episode 8441: reward = -39.42, steps = 36 00:36:19 [INFO] train episode 8442: reward = -29.59, steps = 25 00:36:19 [INFO] train episode 8443: reward = -38.84, steps = 21 00:36:19 [INFO] train episode 8444: reward = -37.82, steps = 31 00:36:20 [INFO] train episode 8445: reward = -36.26, steps = 21 00:36:20 [INFO] train episode 8446: reward = -31.95, steps = 21 00:36:20 [INFO] train episode 8447: reward = -34.35, steps = 24 00:36:20 [INFO] train episode 8448: reward = -35.10, steps = 26 00:36:20 [INFO] train episode 8449: reward = -34.06, steps = 20 00:36:20 [INFO] train episode 8450: reward = -21.16, steps = 40 00:36:21 [INFO] train episode 8451: reward = -47.35, steps = 44 00:36:21 [INFO] train episode 8452: reward = -30.32, steps = 24 00:36:21 [INFO] train episode 8453: reward = -23.21, steps = 19 00:36:21 [INFO] train episode 8454: reward = -31.16, steps = 30 00:36:22 [INFO] train episode 8455: reward = -46.56, steps = 33 00:36:22 [INFO] train episode 8456: reward = -28.26, steps = 25 00:36:22 [INFO] train episode 8457: reward = -68.83, steps = 50 00:36:22 [INFO] train episode 8458: reward = -38.97, steps = 21 00:36:22 [INFO] train episode 8459: reward = -30.56, steps = 25 00:36:23 [INFO] train episode 8460: reward = -38.29, steps = 31 00:36:23 [INFO] train episode 8461: reward = -29.29, steps = 29 00:36:23 [INFO] train episode 8462: reward = -54.44, steps = 25 00:36:23 [INFO] train episode 8463: reward = -61.09, steps = 51 00:36:23 [INFO] train episode 8464: reward = -36.17, steps = 21 00:36:24 [INFO] train episode 8465: reward = -24.20, steps = 48 00:36:24 [INFO] train episode 8466: reward = -39.22, steps = 21 00:36:24 [INFO] train episode 8467: reward = -28.68, steps = 22 00:36:24 [INFO] train episode 8468: reward = -28.29, steps = 28 00:36:24 [INFO] train episode 8469: reward = -29.59, steps = 29 00:36:25 [INFO] train episode 8470: reward = -27.90, steps = 33 00:36:25 [INFO] train episode 8471: reward = -43.15, steps = 26 00:36:25 [INFO] train episode 8472: reward = -41.51, steps = 28 00:36:26 [INFO] train episode 8473: reward = -37.17, steps = 35 00:36:26 [INFO] train episode 8474: reward = -23.63, steps = 41 00:36:26 [INFO] train episode 8475: reward = -28.04, steps = 53 00:36:26 [INFO] train episode 8476: reward = -33.99, steps = 26 00:36:27 [INFO] train episode 8477: reward = -58.11, steps = 62 00:36:27 [INFO] train episode 8478: reward = -28.74, steps = 21 00:36:27 [INFO] train episode 8479: reward = -30.92, steps = 21 00:36:27 [INFO] train episode 8480: reward = -34.60, steps = 28 00:36:27 [INFO] train episode 8481: reward = -34.04, steps = 30 00:36:28 [INFO] train episode 8482: reward = -38.76, steps = 23 00:36:28 [INFO] train episode 8483: reward = -44.49, steps = 30 00:36:28 [INFO] train episode 8484: reward = -35.79, steps = 29 00:36:28 [INFO] train episode 8485: reward = -30.41, steps = 24 00:36:28 [INFO] train episode 8486: reward = -24.88, steps = 30 00:36:29 [INFO] train episode 8487: reward = -38.24, steps = 32 00:36:29 [INFO] train episode 8488: reward = -38.74, steps = 30 00:36:29 [INFO] train episode 8489: reward = -31.69, steps = 31 00:36:29 [INFO] train episode 8490: reward = -41.14, steps = 36 00:36:30 [INFO] train episode 8491: reward = -26.30, steps = 24 00:36:30 [INFO] train episode 8492: reward = -39.62, steps = 27 00:36:30 [INFO] train episode 8493: reward = -37.87, steps = 23 00:36:30 [INFO] train episode 8494: reward = -47.24, steps = 26 00:36:30 [INFO] train episode 8495: reward = -57.47, steps = 26 00:36:30 [INFO] train episode 8496: reward = -40.27, steps = 26 00:36:31 [INFO] train episode 8497: reward = -33.85, steps = 31 00:36:31 [INFO] train episode 8498: reward = -42.45, steps = 26 00:36:31 [INFO] train episode 8499: reward = -39.83, steps = 34 00:36:31 [INFO] train episode 8500: reward = -37.03, steps = 22 00:36:31 [INFO] train episode 8501: reward = -28.70, steps = 31 00:36:32 [INFO] train episode 8502: reward = -46.70, steps = 33 00:36:32 [INFO] train episode 8503: reward = -41.74, steps = 34 00:36:32 [INFO] train episode 8504: reward = -46.64, steps = 42 00:36:32 [INFO] train episode 8505: reward = -32.61, steps = 34 00:36:33 [INFO] train episode 8506: reward = -40.23, steps = 23 00:36:33 [INFO] train episode 8507: reward = -34.08, steps = 19 00:36:33 [INFO] train episode 8508: reward = -25.66, steps = 22 00:36:33 [INFO] train episode 8509: reward = -41.30, steps = 32 00:36:33 [INFO] train episode 8510: reward = -25.89, steps = 31 00:36:34 [INFO] train episode 8511: reward = -47.04, steps = 33 00:36:34 [INFO] train episode 8512: reward = -40.13, steps = 22 00:36:34 [INFO] train episode 8513: reward = -27.78, steps = 28 00:36:34 [INFO] train episode 8514: reward = -27.58, steps = 34 00:36:34 [INFO] train episode 8515: reward = -26.43, steps = 39 00:36:34 [INFO] train episode 8516: reward = -32.31, steps = 21 00:36:35 [INFO] train episode 8517: reward = -43.86, steps = 29 00:36:35 [INFO] train episode 8518: reward = -35.94, steps = 32 00:36:35 [INFO] train episode 8519: reward = -38.32, steps = 31 00:36:35 [INFO] train episode 8520: reward = -39.36, steps = 35 00:36:36 [INFO] train episode 8521: reward = -49.61, steps = 29 00:36:36 [INFO] train episode 8522: reward = -18.51, steps = 32 00:36:36 [INFO] train episode 8523: reward = -33.20, steps = 25 00:36:36 [INFO] train episode 8524: reward = -45.11, steps = 22 00:36:36 [INFO] train episode 8525: reward = -35.78, steps = 29 00:36:37 [INFO] train episode 8526: reward = -18.18, steps = 35 00:36:37 [INFO] train episode 8527: reward = -51.75, steps = 27 00:36:37 [INFO] train episode 8528: reward = -38.98, steps = 33 00:36:37 [INFO] train episode 8529: reward = -43.98, steps = 27 00:36:37 [INFO] train episode 8530: reward = -41.77, steps = 24 00:36:37 [INFO] train episode 8531: reward = -29.58, steps = 28 00:36:38 [INFO] train episode 8532: reward = -48.65, steps = 21 00:36:38 [INFO] train episode 8533: reward = -49.80, steps = 33 00:36:38 [INFO] train episode 8534: reward = -32.70, steps = 30 00:36:38 [INFO] train episode 8535: reward = -35.93, steps = 29 00:36:39 [INFO] train episode 8536: reward = -43.13, steps = 32 00:36:39 [INFO] train episode 8537: reward = -41.72, steps = 28 00:36:39 [INFO] train episode 8538: reward = -20.43, steps = 30 00:36:39 [INFO] train episode 8539: reward = -26.45, steps = 40 00:36:40 [INFO] train episode 8540: reward = -32.82, steps = 30 00:36:40 [INFO] train episode 8541: reward = -36.32, steps = 30 00:36:40 [INFO] train episode 8542: reward = -31.80, steps = 32 00:36:40 [INFO] train episode 8543: reward = -33.12, steps = 21 00:36:40 [INFO] train episode 8544: reward = -33.45, steps = 22 00:36:41 [INFO] train episode 8545: reward = -45.72, steps = 32 00:36:41 [INFO] train episode 8546: reward = -27.16, steps = 35 00:36:41 [INFO] train episode 8547: reward = -30.23, steps = 22 00:36:41 [INFO] train episode 8548: reward = -37.54, steps = 21 00:36:41 [INFO] train episode 8549: reward = -30.03, steps = 25 00:36:42 [INFO] train episode 8550: reward = -43.65, steps = 34 00:36:42 [INFO] train episode 8551: reward = -24.35, steps = 25 00:36:42 [INFO] train episode 8552: reward = -40.61, steps = 22 00:36:42 [INFO] train episode 8553: reward = -24.14, steps = 32 00:36:42 [INFO] train episode 8554: reward = -37.23, steps = 22 00:36:42 [INFO] train episode 8555: reward = -40.91, steps = 23 00:36:43 [INFO] train episode 8556: reward = -47.14, steps = 24 00:36:43 [INFO] train episode 8557: reward = -33.06, steps = 30 00:36:43 [INFO] train episode 8558: reward = -35.66, steps = 21 00:36:43 [INFO] train episode 8559: reward = -32.35, steps = 35 00:36:43 [INFO] train episode 8560: reward = -29.84, steps = 24 00:36:44 [INFO] train episode 8561: reward = -43.03, steps = 28 00:36:44 [INFO] train episode 8562: reward = -38.42, steps = 22 00:36:44 [INFO] train episode 8563: reward = -35.82, steps = 33 00:36:44 [INFO] train episode 8564: reward = -40.90, steps = 28 00:36:44 [INFO] train episode 8565: reward = -36.39, steps = 20 00:36:44 [INFO] train episode 8566: reward = -43.54, steps = 25 00:36:45 [INFO] train episode 8567: reward = -35.21, steps = 20 00:36:45 [INFO] train episode 8568: reward = -50.77, steps = 42 00:36:45 [INFO] train episode 8569: reward = -25.76, steps = 26 00:36:45 [INFO] train episode 8570: reward = -41.11, steps = 23 00:36:45 [INFO] train episode 8571: reward = -27.99, steps = 26 00:36:46 [INFO] train episode 8572: reward = -44.66, steps = 35 00:36:46 [INFO] train episode 8573: reward = -38.73, steps = 31 00:36:46 [INFO] train episode 8574: reward = -42.65, steps = 24 00:36:46 [INFO] train episode 8575: reward = -38.43, steps = 28 00:36:47 [INFO] train episode 8576: reward = -42.38, steps = 39 00:36:47 [INFO] train episode 8577: reward = -23.86, steps = 30 00:36:47 [INFO] train episode 8578: reward = -45.59, steps = 40 00:36:47 [INFO] train episode 8579: reward = -45.84, steps = 34 00:36:47 [INFO] train episode 8580: reward = -38.84, steps = 22 00:36:48 [INFO] train episode 8581: reward = -34.13, steps = 22 00:36:48 [INFO] train episode 8582: reward = -43.65, steps = 43 00:36:48 [INFO] train episode 8583: reward = -34.07, steps = 22 00:36:48 [INFO] train episode 8584: reward = -37.63, steps = 27 00:36:48 [INFO] train episode 8585: reward = -42.87, steps = 35 00:36:49 [INFO] train episode 8586: reward = -36.95, steps = 25 00:36:49 [INFO] train episode 8587: reward = -33.36, steps = 28 00:36:49 [INFO] train episode 8588: reward = -19.26, steps = 48 00:36:49 [INFO] train episode 8589: reward = -33.07, steps = 24 00:36:49 [INFO] train episode 8590: reward = -35.90, steps = 26 00:36:50 [INFO] train episode 8591: reward = -47.68, steps = 30 00:36:50 [INFO] train episode 8592: reward = -36.42, steps = 28 00:36:50 [INFO] train episode 8593: reward = -26.60, steps = 21 00:36:50 [INFO] train episode 8594: reward = -57.13, steps = 28 00:36:50 [INFO] train episode 8595: reward = -36.59, steps = 22 00:36:50 [INFO] train episode 8596: reward = -35.98, steps = 22 00:36:51 [INFO] train episode 8597: reward = -50.73, steps = 22 00:36:51 [INFO] train episode 8598: reward = -33.22, steps = 29 00:36:51 [INFO] train episode 8599: reward = -17.41, steps = 34 00:36:51 [INFO] train episode 8600: reward = -60.00, steps = 40 00:36:51 [INFO] train episode 8601: reward = -36.57, steps = 21 00:36:52 [INFO] train episode 8602: reward = -28.16, steps = 23 00:36:52 [INFO] train episode 8603: reward = -32.70, steps = 35 00:36:52 [INFO] train episode 8604: reward = -32.99, steps = 27 00:36:52 [INFO] train episode 8605: reward = -22.30, steps = 34 00:36:52 [INFO] train episode 8606: reward = -39.18, steps = 24 00:36:53 [INFO] train episode 8607: reward = -41.41, steps = 21 00:36:53 [INFO] train episode 8608: reward = -33.53, steps = 25 00:36:53 [INFO] train episode 8609: reward = -38.50, steps = 27 00:36:53 [INFO] train episode 8610: reward = -57.28, steps = 36 00:36:54 [INFO] train episode 8611: reward = -41.72, steps = 31 00:36:54 [INFO] train episode 8612: reward = -40.23, steps = 28 00:36:54 [INFO] train episode 8613: reward = -43.12, steps = 24 00:36:54 [INFO] train episode 8614: reward = -30.08, steps = 28 00:36:54 [INFO] train episode 8615: reward = -23.77, steps = 20 00:36:55 [INFO] train episode 8616: reward = -45.41, steps = 30 00:36:55 [INFO] train episode 8617: reward = -36.75, steps = 20 00:36:55 [INFO] train episode 8618: reward = -36.42, steps = 23 00:36:55 [INFO] train episode 8619: reward = -25.60, steps = 34 00:36:55 [INFO] train episode 8620: reward = -34.60, steps = 21 00:36:55 [INFO] train episode 8621: reward = -45.02, steps = 27 00:36:56 [INFO] train episode 8622: reward = -36.58, steps = 24 00:36:56 [INFO] train episode 8623: reward = -38.27, steps = 28 00:36:56 [INFO] train episode 8624: reward = -35.43, steps = 34 00:36:56 [INFO] train episode 8625: reward = -26.59, steps = 37 00:36:56 [INFO] train episode 8626: reward = -30.27, steps = 22 00:36:57 [INFO] train episode 8627: reward = -28.65, steps = 35 00:36:57 [INFO] train episode 8628: reward = -44.69, steps = 25 00:36:57 [INFO] train episode 8629: reward = -25.43, steps = 28 00:36:57 [INFO] train episode 8630: reward = -37.64, steps = 24 00:36:57 [INFO] train episode 8631: reward = -30.85, steps = 28 00:36:58 [INFO] train episode 8632: reward = -41.02, steps = 35 00:36:58 [INFO] train episode 8633: reward = -29.86, steps = 26 00:36:58 [INFO] train episode 8634: reward = -27.40, steps = 25 00:36:58 [INFO] train episode 8635: reward = -32.51, steps = 26 00:36:58 [INFO] train episode 8636: reward = -40.47, steps = 32 00:36:59 [INFO] train episode 8637: reward = -39.21, steps = 24 00:36:59 [INFO] train episode 8638: reward = -36.61, steps = 30 00:36:59 [INFO] train episode 8639: reward = -29.20, steps = 20 00:36:59 [INFO] train episode 8640: reward = -28.84, steps = 21 00:36:59 [INFO] train episode 8641: reward = -34.13, steps = 38 00:37:00 [INFO] train episode 8642: reward = -42.75, steps = 32 00:37:00 [INFO] train episode 8643: reward = -46.90, steps = 29 00:37:00 [INFO] train episode 8644: reward = -34.97, steps = 26 00:37:00 [INFO] train episode 8645: reward = -43.96, steps = 25 00:37:00 [INFO] train episode 8646: reward = -39.22, steps = 40 00:37:01 [INFO] train episode 8647: reward = -32.80, steps = 28 00:37:01 [INFO] train episode 8648: reward = -40.73, steps = 24 00:37:01 [INFO] train episode 8649: reward = -38.54, steps = 26 00:37:01 [INFO] train episode 8650: reward = -39.16, steps = 42 00:37:02 [INFO] train episode 8651: reward = -40.16, steps = 25 00:37:02 [INFO] train episode 8652: reward = -36.34, steps = 26 00:37:02 [INFO] train episode 8653: reward = -46.04, steps = 32 00:37:02 [INFO] train episode 8654: reward = -24.25, steps = 24 00:37:02 [INFO] train episode 8655: reward = -44.13, steps = 27 00:37:03 [INFO] train episode 8656: reward = -37.14, steps = 26 00:37:03 [INFO] train episode 8657: reward = -32.49, steps = 27 00:37:03 [INFO] train episode 8658: reward = -30.61, steps = 27 00:37:03 [INFO] train episode 8659: reward = -48.88, steps = 20 00:37:03 [INFO] train episode 8660: reward = -36.83, steps = 43 00:37:04 [INFO] train episode 8661: reward = -38.59, steps = 27 00:37:04 [INFO] train episode 8662: reward = -34.64, steps = 24 00:37:04 [INFO] train episode 8663: reward = -42.61, steps = 26 00:37:04 [INFO] train episode 8664: reward = -37.11, steps = 33 00:37:04 [INFO] train episode 8665: reward = -49.90, steps = 23 00:37:05 [INFO] train episode 8666: reward = -46.35, steps = 28 00:37:05 [INFO] train episode 8667: reward = -29.75, steps = 43 00:37:05 [INFO] train episode 8668: reward = -40.23, steps = 36 00:37:05 [INFO] train episode 8669: reward = -39.97, steps = 26 00:37:06 [INFO] train episode 8670: reward = -37.18, steps = 29 00:37:06 [INFO] train episode 8671: reward = -40.14, steps = 30 00:37:06 [INFO] train episode 8672: reward = -30.06, steps = 21 00:37:06 [INFO] train episode 8673: reward = -46.31, steps = 31 00:37:06 [INFO] train episode 8674: reward = -25.69, steps = 19 00:37:06 [INFO] train episode 8675: reward = -20.89, steps = 31 00:37:07 [INFO] train episode 8676: reward = -34.72, steps = 21 00:37:07 [INFO] train episode 8677: reward = -48.87, steps = 32 00:37:07 [INFO] train episode 8678: reward = -31.59, steps = 26 00:37:07 [INFO] train episode 8679: reward = -29.51, steps = 21 00:37:08 [INFO] train episode 8680: reward = -22.05, steps = 43 00:37:08 [INFO] train episode 8681: reward = -46.70, steps = 30 00:37:08 [INFO] train episode 8682: reward = -55.46, steps = 38 00:37:08 [INFO] train episode 8683: reward = -29.06, steps = 22 00:37:09 [INFO] train episode 8684: reward = -36.91, steps = 25 00:37:09 [INFO] train episode 8685: reward = -49.49, steps = 27 00:37:09 [INFO] train episode 8686: reward = -53.70, steps = 33 00:37:09 [INFO] train episode 8687: reward = -39.52, steps = 33 00:37:09 [INFO] train episode 8688: reward = -35.45, steps = 20 00:37:09 [INFO] train episode 8689: reward = -27.72, steps = 23 00:37:10 [INFO] train episode 8690: reward = -36.18, steps = 23 00:37:10 [INFO] train episode 8691: reward = -41.76, steps = 27 00:37:10 [INFO] train episode 8692: reward = -41.34, steps = 29 00:37:10 [INFO] train episode 8693: reward = -36.42, steps = 30 00:37:10 [INFO] train episode 8694: reward = -44.40, steps = 26 00:37:11 [INFO] train episode 8695: reward = -27.53, steps = 22 00:37:11 [INFO] train episode 8696: reward = -42.55, steps = 32 00:37:11 [INFO] train episode 8697: reward = -21.44, steps = 32 00:37:11 [INFO] train episode 8698: reward = -43.67, steps = 29 00:37:11 [INFO] train episode 8699: reward = -52.36, steps = 21 00:37:12 [INFO] train episode 8700: reward = -30.13, steps = 22 00:37:12 [INFO] train episode 8701: reward = -38.33, steps = 28 00:37:12 [INFO] train episode 8702: reward = -36.14, steps = 27 00:37:12 [INFO] train episode 8703: reward = -36.26, steps = 26 00:37:12 [INFO] train episode 8704: reward = -72.96, steps = 48 00:37:13 [INFO] train episode 8705: reward = -28.19, steps = 29 00:37:13 [INFO] train episode 8706: reward = -49.37, steps = 31 00:37:13 [INFO] train episode 8707: reward = -49.92, steps = 21 00:37:13 [INFO] train episode 8708: reward = -45.92, steps = 34 00:37:13 [INFO] train episode 8709: reward = -38.78, steps = 31 00:37:14 [INFO] train episode 8710: reward = -12.29, steps = 29 00:37:14 [INFO] train episode 8711: reward = -27.53, steps = 25 00:37:14 [INFO] train episode 8712: reward = -42.40, steps = 28 00:37:14 [INFO] train episode 8713: reward = -29.68, steps = 21 00:37:14 [INFO] train episode 8714: reward = -42.75, steps = 36 00:37:15 [INFO] train episode 8715: reward = -36.16, steps = 30 00:37:15 [INFO] train episode 8716: reward = -41.92, steps = 24 00:37:15 [INFO] train episode 8717: reward = -48.22, steps = 33 00:37:15 [INFO] train episode 8718: reward = -45.74, steps = 27 00:37:16 [INFO] train episode 8719: reward = -33.51, steps = 35 00:37:16 [INFO] train episode 8720: reward = -40.10, steps = 26 00:37:16 [INFO] train episode 8721: reward = -30.75, steps = 25 00:37:16 [INFO] train episode 8722: reward = -36.76, steps = 22 00:37:16 [INFO] train episode 8723: reward = -58.96, steps = 36 00:37:17 [INFO] train episode 8724: reward = -43.37, steps = 22 00:37:17 [INFO] train episode 8725: reward = -35.94, steps = 26 00:37:17 [INFO] train episode 8726: reward = -49.21, steps = 36 00:37:17 [INFO] train episode 8727: reward = -39.10, steps = 29 00:37:17 [INFO] train episode 8728: reward = -48.05, steps = 33 00:37:18 [INFO] train episode 8729: reward = -37.18, steps = 26 00:37:18 [INFO] train episode 8730: reward = -40.04, steps = 48 00:37:18 [INFO] train episode 8731: reward = -35.87, steps = 24 00:37:18 [INFO] train episode 8732: reward = -53.99, steps = 34 00:37:18 [INFO] train episode 8733: reward = -41.09, steps = 32 00:37:19 [INFO] train episode 8734: reward = -31.80, steps = 37 00:37:19 [INFO] train episode 8735: reward = -44.43, steps = 27 00:37:19 [INFO] train episode 8736: reward = -53.86, steps = 31 00:37:19 [INFO] train episode 8737: reward = -39.70, steps = 26 00:37:19 [INFO] train episode 8738: reward = -34.35, steps = 23 00:37:20 [INFO] train episode 8739: reward = -54.78, steps = 22 00:37:20 [INFO] train episode 8740: reward = -29.46, steps = 33 00:37:20 [INFO] train episode 8741: reward = -31.41, steps = 21 00:37:20 [INFO] train episode 8742: reward = -27.86, steps = 29 00:37:20 [INFO] train episode 8743: reward = -38.43, steps = 29 00:37:21 [INFO] train episode 8744: reward = -28.32, steps = 31 00:37:21 [INFO] train episode 8745: reward = -36.27, steps = 21 00:37:21 [INFO] train episode 8746: reward = -36.14, steps = 24 00:37:21 [INFO] train episode 8747: reward = -37.26, steps = 24 00:37:22 [INFO] train episode 8748: reward = -33.19, steps = 34 00:37:22 [INFO] train episode 8749: reward = -24.25, steps = 23 00:37:22 [INFO] train episode 8750: reward = -43.22, steps = 33 00:37:22 [INFO] train episode 8751: reward = -37.88, steps = 22 00:37:22 [INFO] train episode 8752: reward = -31.33, steps = 24 00:37:23 [INFO] train episode 8753: reward = -41.09, steps = 30 00:37:23 [INFO] train episode 8754: reward = -30.75, steps = 24 00:37:23 [INFO] train episode 8755: reward = -29.68, steps = 25 00:37:23 [INFO] train episode 8756: reward = -35.40, steps = 28 00:37:23 [INFO] train episode 8757: reward = -32.79, steps = 35 00:37:24 [INFO] train episode 8758: reward = -35.10, steps = 20 00:37:24 [INFO] train episode 8759: reward = -32.29, steps = 29 00:37:24 [INFO] train episode 8760: reward = -27.49, steps = 56 00:37:24 [INFO] train episode 8761: reward = -41.18, steps = 20 00:37:24 [INFO] train episode 8762: reward = -34.28, steps = 41 00:37:25 [INFO] train episode 8763: reward = -52.36, steps = 28 00:37:25 [INFO] train episode 8764: reward = -53.57, steps = 33 00:37:25 [INFO] train episode 8765: reward = -28.83, steps = 35 00:37:25 [INFO] train episode 8766: reward = -28.68, steps = 28 00:37:25 [INFO] train episode 8767: reward = -37.34, steps = 28 00:37:26 [INFO] train episode 8768: reward = -32.92, steps = 31 00:37:26 [INFO] train episode 8769: reward = -34.02, steps = 21 00:37:26 [INFO] train episode 8770: reward = -24.46, steps = 29 00:37:26 [INFO] train episode 8771: reward = -15.03, steps = 39 00:37:26 [INFO] train episode 8772: reward = -31.45, steps = 24 00:37:27 [INFO] train episode 8773: reward = -32.16, steps = 28 00:37:27 [INFO] train episode 8774: reward = -26.26, steps = 26 00:37:27 [INFO] train episode 8775: reward = -37.73, steps = 30 00:37:27 [INFO] train episode 8776: reward = -43.25, steps = 24 00:37:27 [INFO] train episode 8777: reward = -33.63, steps = 35 00:37:28 [INFO] train episode 8778: reward = -34.79, steps = 28 00:37:28 [INFO] train episode 8779: reward = -31.39, steps = 21 00:37:28 [INFO] train episode 8780: reward = -56.71, steps = 40 00:37:28 [INFO] train episode 8781: reward = -40.48, steps = 26 00:37:28 [INFO] train episode 8782: reward = -35.48, steps = 24 00:37:29 [INFO] train episode 8783: reward = -38.44, steps = 39 00:37:29 [INFO] train episode 8784: reward = -35.16, steps = 27 00:37:29 [INFO] train episode 8785: reward = -48.96, steps = 43 00:37:29 [INFO] train episode 8786: reward = -37.99, steps = 36 00:37:30 [INFO] train episode 8787: reward = -55.62, steps = 47 00:37:30 [INFO] train episode 8788: reward = -28.35, steps = 28 00:37:30 [INFO] train episode 8789: reward = -48.07, steps = 28 00:37:30 [INFO] train episode 8790: reward = -24.35, steps = 33 00:37:30 [INFO] train episode 8791: reward = -28.30, steps = 27 00:37:31 [INFO] train episode 8792: reward = -35.89, steps = 31 00:37:31 [INFO] train episode 8793: reward = -53.00, steps = 39 00:37:31 [INFO] train episode 8794: reward = -39.15, steps = 43 00:37:31 [INFO] train episode 8795: reward = -35.61, steps = 30 00:37:32 [INFO] train episode 8796: reward = -36.32, steps = 27 00:37:32 [INFO] train episode 8797: reward = -35.59, steps = 36 00:37:32 [INFO] train episode 8798: reward = -32.29, steps = 23 00:37:32 [INFO] train episode 8799: reward = -31.72, steps = 27 00:37:33 [INFO] train episode 8800: reward = -43.29, steps = 39 00:37:33 [INFO] train episode 8801: reward = -49.52, steps = 25 00:37:33 [INFO] train episode 8802: reward = -47.82, steps = 24 00:37:33 [INFO] train episode 8803: reward = -41.94, steps = 27 00:37:33 [INFO] train episode 8804: reward = -36.60, steps = 28 00:37:33 [INFO] train episode 8805: reward = -45.81, steps = 30 00:37:34 [INFO] train episode 8806: reward = -31.19, steps = 27 00:37:34 [INFO] train episode 8807: reward = -32.21, steps = 26 00:37:34 [INFO] train episode 8808: reward = -32.47, steps = 27 00:37:34 [INFO] train episode 8809: reward = -35.58, steps = 32 00:37:34 [INFO] train episode 8810: reward = -25.65, steps = 21 00:37:35 [INFO] train episode 8811: reward = -43.22, steps = 27 00:37:35 [INFO] train episode 8812: reward = -32.75, steps = 22 00:37:35 [INFO] train episode 8813: reward = -63.21, steps = 33 00:37:36 [INFO] train episode 8814: reward = -52.51, steps = 44 00:37:36 [INFO] train episode 8815: reward = -39.12, steps = 23 00:37:36 [INFO] train episode 8816: reward = -26.19, steps = 30 00:37:36 [INFO] train episode 8817: reward = -25.41, steps = 28 00:37:36 [INFO] train episode 8818: reward = -39.34, steps = 31 00:37:37 [INFO] train episode 8819: reward = -30.82, steps = 25 00:37:37 [INFO] train episode 8820: reward = -35.65, steps = 25 00:37:37 [INFO] train episode 8821: reward = -44.68, steps = 25 00:37:37 [INFO] train episode 8822: reward = -24.18, steps = 23 00:37:37 [INFO] train episode 8823: reward = -45.19, steps = 28 00:37:37 [INFO] train episode 8824: reward = -29.12, steps = 31 00:37:38 [INFO] train episode 8825: reward = -33.56, steps = 26 00:37:38 [INFO] train episode 8826: reward = -38.59, steps = 29 00:37:38 [INFO] train episode 8827: reward = -30.08, steps = 25 00:37:38 [INFO] train episode 8828: reward = -42.37, steps = 30 00:37:38 [INFO] train episode 8829: reward = -48.25, steps = 24 00:37:39 [INFO] train episode 8830: reward = -26.82, steps = 28 00:37:39 [INFO] train episode 8831: reward = -67.48, steps = 31 00:37:39 [INFO] train episode 8832: reward = -19.51, steps = 27 00:37:39 [INFO] train episode 8833: reward = -45.20, steps = 29 00:37:39 [INFO] train episode 8834: reward = -41.85, steps = 28 00:37:39 [INFO] train episode 8835: reward = -33.65, steps = 18 00:37:40 [INFO] train episode 8836: reward = -44.72, steps = 24 00:37:40 [INFO] train episode 8837: reward = -29.48, steps = 23 00:37:40 [INFO] train episode 8838: reward = -35.06, steps = 25 00:37:40 [INFO] train episode 8839: reward = -44.15, steps = 31 00:37:40 [INFO] train episode 8840: reward = -37.66, steps = 27 00:37:41 [INFO] train episode 8841: reward = -46.24, steps = 27 00:37:41 [INFO] train episode 8842: reward = -36.18, steps = 40 00:37:41 [INFO] train episode 8843: reward = -29.66, steps = 25 00:37:41 [INFO] train episode 8844: reward = -36.95, steps = 23 00:37:41 [INFO] train episode 8845: reward = -32.27, steps = 21 00:37:42 [INFO] train episode 8846: reward = -29.93, steps = 30 00:37:42 [INFO] train episode 8847: reward = -32.91, steps = 28 00:37:42 [INFO] train episode 8848: reward = -37.73, steps = 27 00:37:42 [INFO] train episode 8849: reward = -35.69, steps = 25 00:37:42 [INFO] train episode 8850: reward = -42.38, steps = 44 00:37:43 [INFO] train episode 8851: reward = -16.95, steps = 62 00:37:43 [INFO] train episode 8852: reward = -32.01, steps = 25 00:37:43 [INFO] train episode 8853: reward = -33.32, steps = 36 00:37:43 [INFO] train episode 8854: reward = -47.02, steps = 30 00:37:44 [INFO] train episode 8855: reward = -27.28, steps = 23 00:37:44 [INFO] train episode 8856: reward = -51.84, steps = 34 00:37:44 [INFO] train episode 8857: reward = -35.05, steps = 25 00:37:44 [INFO] train episode 8858: reward = -52.06, steps = 34 00:37:44 [INFO] train episode 8859: reward = -51.33, steps = 29 00:37:45 [INFO] train episode 8860: reward = -35.68, steps = 26 00:37:45 [INFO] train episode 8861: reward = -35.56, steps = 33 00:37:45 [INFO] train episode 8862: reward = -34.22, steps = 38 00:37:45 [INFO] train episode 8863: reward = -40.26, steps = 26 00:37:45 [INFO] train episode 8864: reward = -40.03, steps = 24 00:37:46 [INFO] train episode 8865: reward = -31.37, steps = 31 00:37:46 [INFO] train episode 8866: reward = -31.15, steps = 24 00:37:46 [INFO] train episode 8867: reward = -25.91, steps = 28 00:37:46 [INFO] train episode 8868: reward = -30.83, steps = 27 00:37:46 [INFO] train episode 8869: reward = -41.93, steps = 30 00:37:47 [INFO] train episode 8870: reward = -43.93, steps = 23 00:37:47 [INFO] train episode 8871: reward = -45.78, steps = 25 00:37:47 [INFO] train episode 8872: reward = -31.15, steps = 21 00:37:47 [INFO] train episode 8873: reward = -31.28, steps = 30 00:37:47 [INFO] train episode 8874: reward = -34.83, steps = 24 00:37:47 [INFO] train episode 8875: reward = -39.56, steps = 28 00:37:48 [INFO] train episode 8876: reward = -43.52, steps = 29 00:37:48 [INFO] train episode 8877: reward = -38.31, steps = 26 00:37:48 [INFO] train episode 8878: reward = -35.40, steps = 37 00:37:49 [INFO] train episode 8879: reward = -35.78, steps = 27 00:37:49 [INFO] train episode 8880: reward = -32.01, steps = 39 00:37:49 [INFO] train episode 8881: reward = -38.30, steps = 38 00:37:49 [INFO] train episode 8882: reward = -34.17, steps = 28 00:37:49 [INFO] train episode 8883: reward = -41.37, steps = 26 00:37:50 [INFO] train episode 8884: reward = -40.99, steps = 24 00:37:50 [INFO] train episode 8885: reward = -38.76, steps = 21 00:37:50 [INFO] train episode 8886: reward = -71.82, steps = 48 00:37:50 [INFO] train episode 8887: reward = -46.02, steps = 27 00:37:50 [INFO] train episode 8888: reward = -34.43, steps = 23 00:37:51 [INFO] train episode 8889: reward = -47.36, steps = 34 00:37:51 [INFO] train episode 8890: reward = -35.19, steps = 25 00:37:51 [INFO] train episode 8891: reward = -23.73, steps = 34 00:37:51 [INFO] train episode 8892: reward = -27.46, steps = 25 00:37:51 [INFO] train episode 8893: reward = -22.58, steps = 26 00:37:52 [INFO] train episode 8894: reward = -39.75, steps = 28 00:37:52 [INFO] train episode 8895: reward = -48.03, steps = 26 00:37:52 [INFO] train episode 8896: reward = -43.61, steps = 21 00:37:52 [INFO] train episode 8897: reward = -65.41, steps = 41 00:37:52 [INFO] train episode 8898: reward = -38.47, steps = 25 00:37:53 [INFO] train episode 8899: reward = -48.96, steps = 30 00:37:53 [INFO] train episode 8900: reward = -38.59, steps = 33 00:37:53 [INFO] train episode 8901: reward = -37.94, steps = 31 00:37:53 [INFO] train episode 8902: reward = -37.75, steps = 30 00:37:53 [INFO] train episode 8903: reward = -33.55, steps = 26 00:37:54 [INFO] train episode 8904: reward = -30.93, steps = 22 00:37:54 [INFO] train episode 8905: reward = -41.28, steps = 22 00:37:54 [INFO] train episode 8906: reward = -43.62, steps = 27 00:37:54 [INFO] train episode 8907: reward = -36.76, steps = 25 00:37:54 [INFO] train episode 8908: reward = -42.79, steps = 25 00:37:55 [INFO] train episode 8909: reward = -39.87, steps = 26 00:37:55 [INFO] train episode 8910: reward = -41.26, steps = 41 00:37:55 [INFO] train episode 8911: reward = -44.89, steps = 31 00:37:55 [INFO] train episode 8912: reward = -47.50, steps = 23 00:37:55 [INFO] train episode 8913: reward = -39.97, steps = 22 00:37:55 [INFO] train episode 8914: reward = -31.69, steps = 22 00:37:56 [INFO] train episode 8915: reward = -29.64, steps = 34 00:37:56 [INFO] train episode 8916: reward = -38.96, steps = 33 00:37:56 [INFO] train episode 8917: reward = -39.72, steps = 28 00:37:56 [INFO] train episode 8918: reward = -30.43, steps = 30 00:37:57 [INFO] train episode 8919: reward = -38.78, steps = 28 00:37:57 [INFO] train episode 8920: reward = -43.69, steps = 31 00:37:57 [INFO] train episode 8921: reward = -57.43, steps = 35 00:37:57 [INFO] train episode 8922: reward = -39.38, steps = 31 00:37:57 [INFO] train episode 8923: reward = -23.63, steps = 28 00:37:58 [INFO] train episode 8924: reward = -24.91, steps = 31 00:37:58 [INFO] train episode 8925: reward = -50.29, steps = 25 00:37:58 [INFO] train episode 8926: reward = -22.08, steps = 40 00:37:58 [INFO] train episode 8927: reward = -36.44, steps = 24 00:37:58 [INFO] train episode 8928: reward = -26.83, steps = 21 00:37:59 [INFO] train episode 8929: reward = -46.92, steps = 31 00:37:59 [INFO] train episode 8930: reward = -49.11, steps = 28 00:37:59 [INFO] train episode 8931: reward = -42.01, steps = 25 00:37:59 [INFO] train episode 8932: reward = -36.08, steps = 24 00:37:59 [INFO] train episode 8933: reward = -30.23, steps = 27 00:38:00 [INFO] train episode 8934: reward = -40.82, steps = 38 00:38:00 [INFO] train episode 8935: reward = -40.94, steps = 22 00:38:00 [INFO] train episode 8936: reward = -46.17, steps = 30 00:38:00 [INFO] train episode 8937: reward = -33.22, steps = 30 00:38:00 [INFO] train episode 8938: reward = -26.17, steps = 30 00:38:01 [INFO] train episode 8939: reward = -28.06, steps = 22 00:38:01 [INFO] train episode 8940: reward = -56.27, steps = 32 00:38:01 [INFO] train episode 8941: reward = -30.29, steps = 23 00:38:01 [INFO] train episode 8942: reward = -28.67, steps = 35 00:38:01 [INFO] train episode 8943: reward = -29.91, steps = 34 00:38:02 [INFO] train episode 8944: reward = -33.98, steps = 26 00:38:02 [INFO] train episode 8945: reward = -18.97, steps = 39 00:38:02 [INFO] train episode 8946: reward = -30.28, steps = 23 00:38:02 [INFO] train episode 8947: reward = -46.15, steps = 32 00:38:03 [INFO] train episode 8948: reward = -30.95, steps = 35 00:38:03 [INFO] train episode 8949: reward = -39.56, steps = 31 00:38:03 [INFO] train episode 8950: reward = -47.43, steps = 30 00:38:03 [INFO] train episode 8951: reward = -29.16, steps = 26 00:38:03 [INFO] train episode 8952: reward = -45.38, steps = 31 00:38:04 [INFO] train episode 8953: reward = -41.53, steps = 25 00:38:04 [INFO] train episode 8954: reward = -36.08, steps = 21 00:38:04 [INFO] train episode 8955: reward = -34.50, steps = 22 00:38:04 [INFO] train episode 8956: reward = -37.60, steps = 32 00:38:04 [INFO] train episode 8957: reward = -48.98, steps = 29 00:38:05 [INFO] train episode 8958: reward = -21.62, steps = 29 00:38:05 [INFO] train episode 8959: reward = -32.75, steps = 22 00:38:05 [INFO] train episode 8960: reward = -32.44, steps = 26 00:38:05 [INFO] train episode 8961: reward = -57.23, steps = 31 00:38:05 [INFO] train episode 8962: reward = -31.12, steps = 27 00:38:06 [INFO] train episode 8963: reward = -42.53, steps = 36 00:38:06 [INFO] train episode 8964: reward = -19.07, steps = 35 00:38:06 [INFO] train episode 8965: reward = -31.06, steps = 21 00:38:06 [INFO] train episode 8966: reward = -46.81, steps = 26 00:38:06 [INFO] train episode 8967: reward = -33.25, steps = 32 00:38:06 [INFO] train episode 8968: reward = -34.92, steps = 19 00:38:07 [INFO] train episode 8969: reward = -27.84, steps = 24 00:38:07 [INFO] train episode 8970: reward = -40.10, steps = 23 00:38:07 [INFO] train episode 8971: reward = -24.46, steps = 32 00:38:07 [INFO] train episode 8972: reward = -39.64, steps = 31 00:38:07 [INFO] train episode 8973: reward = -33.63, steps = 25 00:38:08 [INFO] train episode 8974: reward = -38.61, steps = 27 00:38:08 [INFO] train episode 8975: reward = -17.41, steps = 39 00:38:08 [INFO] train episode 8976: reward = -28.58, steps = 22 00:38:08 [INFO] train episode 8977: reward = -33.18, steps = 29 00:38:08 [INFO] train episode 8978: reward = -42.26, steps = 29 00:38:09 [INFO] train episode 8979: reward = -34.28, steps = 31 00:38:09 [INFO] train episode 8980: reward = -46.92, steps = 29 00:38:09 [INFO] train episode 8981: reward = -45.43, steps = 29 00:38:09 [INFO] train episode 8982: reward = -50.34, steps = 32 00:38:10 [INFO] train episode 8983: reward = -24.88, steps = 36 00:38:10 [INFO] train episode 8984: reward = -35.63, steps = 24 00:38:10 [INFO] train episode 8985: reward = -38.68, steps = 37 00:38:10 [INFO] train episode 8986: reward = -25.43, steps = 27 00:38:10 [INFO] train episode 8987: reward = -25.20, steps = 43 00:38:11 [INFO] train episode 8988: reward = -42.34, steps = 29 00:38:11 [INFO] train episode 8989: reward = -39.96, steps = 34 00:38:11 [INFO] train episode 8990: reward = -35.93, steps = 28 00:38:11 [INFO] train episode 8991: reward = -45.43, steps = 29 00:38:11 [INFO] train episode 8992: reward = -37.46, steps = 28 00:38:12 [INFO] train episode 8993: reward = -41.34, steps = 27 00:38:12 [INFO] train episode 8994: reward = -37.78, steps = 31 00:38:12 [INFO] train episode 8995: reward = -36.50, steps = 29 00:38:12 [INFO] train episode 8996: reward = -43.31, steps = 33 00:38:12 [INFO] train episode 8997: reward = -48.48, steps = 30 00:38:13 [INFO] train episode 8998: reward = -29.67, steps = 22 00:38:13 [INFO] train episode 8999: reward = -29.32, steps = 27 00:38:13 [INFO] train episode 9000: reward = -50.62, steps = 32 00:38:13 [INFO] train episode 9001: reward = -37.20, steps = 46 00:38:14 [INFO] train episode 9002: reward = -36.67, steps = 36 00:38:14 [INFO] train episode 9003: reward = -31.64, steps = 22 00:38:14 [INFO] train episode 9004: reward = -32.95, steps = 20 00:38:14 [INFO] train episode 9005: reward = -28.38, steps = 29 00:38:14 [INFO] train episode 9006: reward = -46.65, steps = 33 00:38:15 [INFO] train episode 9007: reward = -41.21, steps = 37 00:38:15 [INFO] train episode 9008: reward = -21.97, steps = 29 00:38:15 [INFO] train episode 9009: reward = -48.31, steps = 35 00:38:15 [INFO] train episode 9010: reward = -37.61, steps = 33 00:38:16 [INFO] train episode 9011: reward = -35.24, steps = 36 00:38:16 [INFO] train episode 9012: reward = -11.63, steps = 40 00:38:16 [INFO] train episode 9013: reward = -39.71, steps = 28 00:38:16 [INFO] train episode 9014: reward = -34.23, steps = 27 00:38:17 [INFO] train episode 9015: reward = -30.59, steps = 21 00:38:17 [INFO] train episode 9016: reward = -25.51, steps = 37 00:38:17 [INFO] train episode 9017: reward = -19.53, steps = 37 00:38:17 [INFO] train episode 9018: reward = -39.91, steps = 29 00:38:18 [INFO] train episode 9019: reward = -33.49, steps = 30 00:38:18 [INFO] train episode 9020: reward = -42.91, steps = 37 00:38:18 [INFO] train episode 9021: reward = -42.77, steps = 26 00:38:18 [INFO] train episode 9022: reward = -23.24, steps = 35 00:38:18 [INFO] train episode 9023: reward = -41.71, steps = 22 00:38:19 [INFO] train episode 9024: reward = -53.40, steps = 24 00:38:19 [INFO] train episode 9025: reward = -37.80, steps = 25 00:38:19 [INFO] train episode 9026: reward = -35.41, steps = 24 00:38:19 [INFO] train episode 9027: reward = -19.01, steps = 33 00:38:19 [INFO] train episode 9028: reward = -30.72, steps = 34 00:38:19 [INFO] train episode 9029: reward = -43.27, steps = 21 00:38:20 [INFO] train episode 9030: reward = -30.68, steps = 33 00:38:20 [INFO] train episode 9031: reward = -41.81, steps = 18 00:38:20 [INFO] train episode 9032: reward = -31.75, steps = 31 00:38:20 [INFO] train episode 9033: reward = -33.32, steps = 19 00:38:20 [INFO] train episode 9034: reward = -49.10, steps = 38 00:38:21 [INFO] train episode 9035: reward = -34.38, steps = 42 00:38:21 [INFO] train episode 9036: reward = -38.13, steps = 22 00:38:21 [INFO] train episode 9037: reward = -34.65, steps = 31 00:38:21 [INFO] train episode 9038: reward = -29.37, steps = 30 00:38:21 [INFO] train episode 9039: reward = -29.26, steps = 33 00:38:22 [INFO] train episode 9040: reward = -39.79, steps = 30 00:38:22 [INFO] train episode 9041: reward = -44.14, steps = 33 00:38:22 [INFO] train episode 9042: reward = -30.82, steps = 38 00:38:22 [INFO] train episode 9043: reward = -36.75, steps = 21 00:38:22 [INFO] train episode 9044: reward = -34.65, steps = 23 00:38:23 [INFO] train episode 9045: reward = -22.57, steps = 34 00:38:23 [INFO] train episode 9046: reward = -32.45, steps = 22 00:38:23 [INFO] train episode 9047: reward = -39.73, steps = 20 00:38:23 [INFO] train episode 9048: reward = -50.85, steps = 30 00:38:23 [INFO] train episode 9049: reward = -42.25, steps = 29 00:38:24 [INFO] train episode 9050: reward = -25.52, steps = 26 00:38:24 [INFO] train episode 9051: reward = -22.94, steps = 29 00:38:24 [INFO] train episode 9052: reward = -44.24, steps = 64 00:38:24 [INFO] train episode 9053: reward = -48.46, steps = 43 00:38:25 [INFO] train episode 9054: reward = -48.36, steps = 30 00:38:25 [INFO] train episode 9055: reward = -28.13, steps = 38 00:38:25 [INFO] train episode 9056: reward = -38.61, steps = 26 00:38:25 [INFO] train episode 9057: reward = -33.34, steps = 25 00:38:25 [INFO] train episode 9058: reward = -31.53, steps = 28 00:38:26 [INFO] train episode 9059: reward = -40.62, steps = 24 00:38:26 [INFO] train episode 9060: reward = -43.77, steps = 32 00:38:26 [INFO] train episode 9061: reward = -42.56, steps = 22 00:38:26 [INFO] train episode 9062: reward = -32.07, steps = 19 00:38:26 [INFO] train episode 9063: reward = -33.78, steps = 26 00:38:26 [INFO] train episode 9064: reward = -37.82, steps = 29 00:38:27 [INFO] train episode 9065: reward = -37.20, steps = 24 00:38:27 [INFO] train episode 9066: reward = -32.30, steps = 21 00:38:27 [INFO] train episode 9067: reward = -55.12, steps = 36 00:38:27 [INFO] train episode 9068: reward = -36.00, steps = 22 00:38:27 [INFO] train episode 9069: reward = -40.19, steps = 32 00:38:28 [INFO] train episode 9070: reward = -35.75, steps = 23 00:38:28 [INFO] train episode 9071: reward = -46.57, steps = 29 00:38:28 [INFO] train episode 9072: reward = -37.90, steps = 20 00:38:28 [INFO] train episode 9073: reward = -46.80, steps = 34 00:38:28 [INFO] train episode 9074: reward = -33.42, steps = 21 00:38:29 [INFO] train episode 9075: reward = -20.36, steps = 37 00:38:29 [INFO] train episode 9076: reward = -40.03, steps = 30 00:38:29 [INFO] train episode 9077: reward = -35.98, steps = 23 00:38:29 [INFO] train episode 9078: reward = -24.20, steps = 26 00:38:29 [INFO] train episode 9079: reward = -40.68, steps = 23 00:38:30 [INFO] train episode 9080: reward = -30.58, steps = 32 00:38:30 [INFO] train episode 9081: reward = -47.07, steps = 25 00:38:30 [INFO] train episode 9082: reward = -43.63, steps = 27 00:38:30 [INFO] train episode 9083: reward = -51.74, steps = 43 00:38:31 [INFO] train episode 9084: reward = -44.52, steps = 45 00:38:31 [INFO] train episode 9085: reward = -29.26, steps = 35 00:38:31 [INFO] train episode 9086: reward = -38.84, steps = 21 00:38:31 [INFO] train episode 9087: reward = -19.60, steps = 32 00:38:32 [INFO] train episode 9088: reward = -39.50, steps = 20 00:38:32 [INFO] train episode 9089: reward = -28.53, steps = 30 00:38:32 [INFO] train episode 9090: reward = -45.08, steps = 32 00:38:32 [INFO] train episode 9091: reward = -41.01, steps = 29 00:38:32 [INFO] train episode 9092: reward = -50.26, steps = 31 00:38:33 [INFO] train episode 9093: reward = -30.27, steps = 29 00:38:33 [INFO] train episode 9094: reward = -42.14, steps = 30 00:38:33 [INFO] train episode 9095: reward = -37.48, steps = 32 00:38:33 [INFO] train episode 9096: reward = -30.64, steps = 36 00:38:33 [INFO] train episode 9097: reward = -38.63, steps = 33 00:38:34 [INFO] train episode 9098: reward = -32.74, steps = 26 00:38:34 [INFO] train episode 9099: reward = -34.63, steps = 22 00:38:34 [INFO] train episode 9100: reward = -45.10, steps = 29 00:38:34 [INFO] train episode 9101: reward = -25.80, steps = 28 00:38:34 [INFO] train episode 9102: reward = -55.22, steps = 33 00:38:35 [INFO] train episode 9103: reward = -30.74, steps = 44 00:38:35 [INFO] train episode 9104: reward = -31.05, steps = 37 00:38:35 [INFO] train episode 9105: reward = -34.81, steps = 26 00:38:35 [INFO] train episode 9106: reward = -25.60, steps = 39 00:38:36 [INFO] train episode 9107: reward = -32.78, steps = 24 00:38:36 [INFO] train episode 9108: reward = -23.81, steps = 30 00:38:36 [INFO] train episode 9109: reward = -48.65, steps = 40 00:38:36 [INFO] train episode 9110: reward = -38.92, steps = 23 00:38:36 [INFO] train episode 9111: reward = -36.95, steps = 24 00:38:37 [INFO] train episode 9112: reward = -28.68, steps = 27 00:38:37 [INFO] train episode 9113: reward = -27.44, steps = 34 00:38:37 [INFO] train episode 9114: reward = -38.87, steps = 28 00:38:37 [INFO] train episode 9115: reward = -27.33, steps = 30 00:38:37 [INFO] train episode 9116: reward = -36.66, steps = 28 00:38:38 [INFO] train episode 9117: reward = -26.87, steps = 25 00:38:38 [INFO] train episode 9118: reward = -42.14, steps = 27 00:38:38 [INFO] train episode 9119: reward = -31.07, steps = 24 00:38:38 [INFO] train episode 9120: reward = -37.06, steps = 35 00:38:38 [INFO] train episode 9121: reward = -39.26, steps = 26 00:38:38 [INFO] train episode 9122: reward = -31.28, steps = 25 00:38:39 [INFO] train episode 9123: reward = -58.29, steps = 31 00:38:39 [INFO] train episode 9124: reward = -29.20, steps = 20 00:38:39 [INFO] train episode 9125: reward = -41.03, steps = 32 00:38:39 [INFO] train episode 9126: reward = -61.63, steps = 34 00:38:40 [INFO] train episode 9127: reward = -29.11, steps = 23 00:38:40 [INFO] train episode 9128: reward = -27.10, steps = 27 00:38:40 [INFO] train episode 9129: reward = -31.80, steps = 26 00:38:40 [INFO] train episode 9130: reward = -15.61, steps = 31 00:38:40 [INFO] train episode 9131: reward = -41.62, steps = 30 00:38:40 [INFO] train episode 9132: reward = -34.32, steps = 20 00:38:41 [INFO] train episode 9133: reward = -35.64, steps = 25 00:38:41 [INFO] train episode 9134: reward = -35.28, steps = 37 00:38:41 [INFO] train episode 9135: reward = -25.32, steps = 33 00:38:41 [INFO] train episode 9136: reward = -24.93, steps = 21 00:38:41 [INFO] train episode 9137: reward = -27.29, steps = 18 00:38:42 [INFO] train episode 9138: reward = -34.13, steps = 24 00:38:42 [INFO] train episode 9139: reward = -43.68, steps = 29 00:38:42 [INFO] train episode 9140: reward = -33.79, steps = 18 00:38:42 [INFO] train episode 9141: reward = -35.43, steps = 36 00:38:42 [INFO] train episode 9142: reward = -35.82, steps = 27 00:38:43 [INFO] train episode 9143: reward = -45.74, steps = 28 00:38:43 [INFO] train episode 9144: reward = -43.81, steps = 36 00:38:43 [INFO] train episode 9145: reward = -45.12, steps = 34 00:38:43 [INFO] train episode 9146: reward = -43.21, steps = 29 00:38:44 [INFO] train episode 9147: reward = -25.18, steps = 22 00:38:44 [INFO] train episode 9148: reward = -31.32, steps = 24 00:38:44 [INFO] train episode 9149: reward = -35.72, steps = 40 00:38:44 [INFO] train episode 9150: reward = -34.64, steps = 23 00:38:44 [INFO] train episode 9151: reward = -37.58, steps = 24 00:38:45 [INFO] train episode 9152: reward = -38.17, steps = 27 00:38:45 [INFO] train episode 9153: reward = -41.32, steps = 29 00:38:45 [INFO] train episode 9154: reward = -36.12, steps = 24 00:38:45 [INFO] train episode 9155: reward = -32.18, steps = 23 00:38:45 [INFO] train episode 9156: reward = -34.80, steps = 20 00:38:46 [INFO] train episode 9157: reward = -40.63, steps = 36 00:38:46 [INFO] train episode 9158: reward = -33.55, steps = 42 00:38:46 [INFO] train episode 9159: reward = -32.73, steps = 26 00:38:46 [INFO] train episode 9160: reward = -66.45, steps = 61 00:38:47 [INFO] train episode 9161: reward = -39.50, steps = 24 00:38:47 [INFO] train episode 9162: reward = -29.51, steps = 36 00:38:47 [INFO] train episode 9163: reward = -46.39, steps = 27 00:38:47 [INFO] train episode 9164: reward = -40.28, steps = 23 00:38:47 [INFO] train episode 9165: reward = -41.44, steps = 20 00:38:48 [INFO] train episode 9166: reward = -50.23, steps = 32 00:38:48 [INFO] train episode 9167: reward = -31.90, steps = 27 00:38:48 [INFO] train episode 9168: reward = -54.65, steps = 39 00:38:48 [INFO] train episode 9169: reward = -34.83, steps = 22 00:38:48 [INFO] train episode 9170: reward = -41.12, steps = 31 00:38:49 [INFO] train episode 9171: reward = -28.76, steps = 27 00:38:49 [INFO] train episode 9172: reward = -39.59, steps = 27 00:38:49 [INFO] train episode 9173: reward = -21.26, steps = 47 00:38:49 [INFO] train episode 9174: reward = -38.20, steps = 21 00:38:49 [INFO] train episode 9175: reward = -28.52, steps = 21 00:38:50 [INFO] train episode 9176: reward = -34.17, steps = 30 00:38:50 [INFO] train episode 9177: reward = -19.40, steps = 32 00:38:50 [INFO] train episode 9178: reward = -42.79, steps = 28 00:38:50 [INFO] train episode 9179: reward = -44.96, steps = 46 00:38:51 [INFO] train episode 9180: reward = -66.44, steps = 57 00:38:51 [INFO] train episode 9181: reward = -38.14, steps = 31 00:38:51 [INFO] train episode 9182: reward = -45.69, steps = 36 00:38:51 [INFO] train episode 9183: reward = -35.06, steps = 29 00:38:52 [INFO] train episode 9184: reward = -17.52, steps = 35 00:38:52 [INFO] train episode 9185: reward = -14.40, steps = 33 00:38:52 [INFO] train episode 9186: reward = -23.60, steps = 32 00:38:52 [INFO] train episode 9187: reward = -53.13, steps = 38 00:38:53 [INFO] train episode 9188: reward = -44.21, steps = 24 00:38:53 [INFO] train episode 9189: reward = -45.23, steps = 27 00:38:53 [INFO] train episode 9190: reward = -37.72, steps = 37 00:38:53 [INFO] train episode 9191: reward = -42.17, steps = 28 00:38:53 [INFO] train episode 9192: reward = -45.58, steps = 39 00:38:54 [INFO] train episode 9193: reward = -29.95, steps = 33 00:38:54 [INFO] train episode 9194: reward = -40.60, steps = 20 00:38:54 [INFO] train episode 9195: reward = -48.43, steps = 38 00:38:54 [INFO] train episode 9196: reward = -37.21, steps = 26 00:38:54 [INFO] train episode 9197: reward = -36.84, steps = 20 00:38:55 [INFO] train episode 9198: reward = -29.61, steps = 28 00:38:55 [INFO] train episode 9199: reward = -41.53, steps = 25 00:38:55 [INFO] train episode 9200: reward = -41.91, steps = 30 00:38:55 [INFO] train episode 9201: reward = -30.60, steps = 32 00:38:55 [INFO] train episode 9202: reward = -41.92, steps = 22 00:38:56 [INFO] train episode 9203: reward = -25.70, steps = 30 00:38:56 [INFO] train episode 9204: reward = -22.37, steps = 30 00:38:56 [INFO] train episode 9205: reward = -19.56, steps = 43 00:38:56 [INFO] train episode 9206: reward = -40.85, steps = 21 00:38:56 [INFO] train episode 9207: reward = -48.16, steps = 24 00:38:57 [INFO] train episode 9208: reward = -36.64, steps = 43 00:38:57 [INFO] train episode 9209: reward = -40.14, steps = 33 00:38:57 [INFO] train episode 9210: reward = -27.21, steps = 29 00:38:58 [INFO] train episode 9211: reward = -24.08, steps = 32 00:38:58 [INFO] train episode 9212: reward = -62.85, steps = 41 00:38:58 [INFO] train episode 9213: reward = -33.48, steps = 22 00:38:58 [INFO] train episode 9214: reward = -31.37, steps = 31 00:38:58 [INFO] train episode 9215: reward = -27.67, steps = 27 00:38:59 [INFO] train episode 9216: reward = -33.85, steps = 24 00:38:59 [INFO] train episode 9217: reward = -55.86, steps = 46 00:38:59 [INFO] train episode 9218: reward = -33.24, steps = 28 00:38:59 [INFO] train episode 9219: reward = -26.24, steps = 21 00:38:59 [INFO] train episode 9220: reward = -19.85, steps = 28 00:39:00 [INFO] train episode 9221: reward = -48.37, steps = 26 00:39:00 [INFO] train episode 9222: reward = -30.04, steps = 20 00:39:00 [INFO] train episode 9223: reward = -37.82, steps = 35 00:39:00 [INFO] train episode 9224: reward = -28.52, steps = 20 00:39:00 [INFO] train episode 9225: reward = -30.28, steps = 40 00:39:01 [INFO] train episode 9226: reward = -37.48, steps = 29 00:39:01 [INFO] train episode 9227: reward = -42.42, steps = 36 00:39:01 [INFO] train episode 9228: reward = -31.36, steps = 26 00:39:01 [INFO] train episode 9229: reward = -52.57, steps = 26 00:39:02 [INFO] train episode 9230: reward = -57.50, steps = 47 00:39:02 [INFO] train episode 9231: reward = -39.72, steps = 25 00:39:02 [INFO] train episode 9232: reward = -47.90, steps = 23 00:39:02 [INFO] train episode 9233: reward = -38.81, steps = 44 00:39:02 [INFO] train episode 9234: reward = -97.20, steps = 20 00:39:03 [INFO] train episode 9235: reward = -49.73, steps = 36 00:39:03 [INFO] train episode 9236: reward = -50.44, steps = 34 00:39:03 [INFO] train episode 9237: reward = -24.18, steps = 35 00:39:03 [INFO] train episode 9238: reward = -34.81, steps = 22 00:39:04 [INFO] train episode 9239: reward = -28.01, steps = 37 00:39:04 [INFO] train episode 9240: reward = -43.63, steps = 42 00:39:04 [INFO] train episode 9241: reward = -34.13, steps = 24 00:39:04 [INFO] train episode 9242: reward = -40.12, steps = 28 00:39:04 [INFO] train episode 9243: reward = -42.62, steps = 22 00:39:05 [INFO] train episode 9244: reward = -36.82, steps = 28 00:39:05 [INFO] train episode 9245: reward = -42.36, steps = 34 00:39:05 [INFO] train episode 9246: reward = -47.83, steps = 37 00:39:05 [INFO] train episode 9247: reward = -29.30, steps = 27 00:39:06 [INFO] train episode 9248: reward = -40.39, steps = 26 00:39:06 [INFO] train episode 9249: reward = -39.20, steps = 27 00:39:06 [INFO] train episode 9250: reward = -36.17, steps = 20 00:39:06 [INFO] train episode 9251: reward = -29.77, steps = 25 00:39:06 [INFO] train episode 9252: reward = -23.35, steps = 42 00:39:07 [INFO] train episode 9253: reward = -31.65, steps = 29 00:39:07 [INFO] train episode 9254: reward = -38.73, steps = 59 00:39:07 [INFO] train episode 9255: reward = -29.24, steps = 38 00:39:07 [INFO] train episode 9256: reward = -44.79, steps = 21 00:39:08 [INFO] train episode 9257: reward = -47.98, steps = 64 00:39:08 [INFO] train episode 9258: reward = -43.98, steps = 26 00:39:08 [INFO] train episode 9259: reward = -38.39, steps = 25 00:39:08 [INFO] train episode 9260: reward = -51.85, steps = 28 00:39:08 [INFO] train episode 9261: reward = -32.31, steps = 21 00:39:09 [INFO] train episode 9262: reward = -25.50, steps = 31 00:39:09 [INFO] train episode 9263: reward = -31.95, steps = 20 00:39:09 [INFO] train episode 9264: reward = -31.01, steps = 24 00:39:09 [INFO] train episode 9265: reward = -25.28, steps = 35 00:39:09 [INFO] train episode 9266: reward = -34.36, steps = 23 00:39:10 [INFO] train episode 9267: reward = -39.89, steps = 27 00:39:10 [INFO] train episode 9268: reward = -31.62, steps = 22 00:39:10 [INFO] train episode 9269: reward = -49.34, steps = 28 00:39:10 [INFO] train episode 9270: reward = -37.56, steps = 28 00:39:10 [INFO] train episode 9271: reward = -34.22, steps = 33 00:39:11 [INFO] train episode 9272: reward = -51.33, steps = 28 00:39:11 [INFO] train episode 9273: reward = -38.34, steps = 19 00:39:11 [INFO] train episode 9274: reward = -36.18, steps = 36 00:39:11 [INFO] train episode 9275: reward = -28.38, steps = 20 00:39:11 [INFO] train episode 9276: reward = -43.03, steps = 24 00:39:12 [INFO] train episode 9277: reward = -44.04, steps = 35 00:39:12 [INFO] train episode 9278: reward = -42.22, steps = 28 00:39:12 [INFO] train episode 9279: reward = -35.59, steps = 23 00:39:12 [INFO] train episode 9280: reward = -38.09, steps = 24 00:39:12 [INFO] train episode 9281: reward = -38.49, steps = 33 00:39:13 [INFO] train episode 9282: reward = -46.67, steps = 33 00:39:13 [INFO] train episode 9283: reward = -31.57, steps = 29 00:39:13 [INFO] train episode 9284: reward = -39.12, steps = 43 00:39:13 [INFO] train episode 9285: reward = -43.82, steps = 34 00:39:14 [INFO] train episode 9286: reward = -18.47, steps = 44 00:39:14 [INFO] train episode 9287: reward = -42.51, steps = 40 00:39:14 [INFO] train episode 9288: reward = -26.42, steps = 28 00:39:14 [INFO] train episode 9289: reward = -54.59, steps = 30 00:39:14 [INFO] train episode 9290: reward = -20.04, steps = 32 00:39:15 [INFO] train episode 9291: reward = -34.28, steps = 32 00:39:15 [INFO] train episode 9292: reward = -32.00, steps = 32 00:39:15 [INFO] train episode 9293: reward = -53.78, steps = 34 00:39:15 [INFO] train episode 9294: reward = -33.81, steps = 24 00:39:16 [INFO] train episode 9295: reward = -26.85, steps = 25 00:39:16 [INFO] train episode 9296: reward = -34.21, steps = 30 00:39:16 [INFO] train episode 9297: reward = -45.09, steps = 41 00:39:16 [INFO] train episode 9298: reward = -44.86, steps = 22 00:39:16 [INFO] train episode 9299: reward = -40.03, steps = 27 00:39:17 [INFO] train episode 9300: reward = -41.04, steps = 31 00:39:17 [INFO] train episode 9301: reward = -27.11, steps = 20 00:39:17 [INFO] train episode 9302: reward = -45.38, steps = 25 00:39:17 [INFO] train episode 9303: reward = -32.24, steps = 26 00:39:17 [INFO] train episode 9304: reward = -32.88, steps = 37 00:39:18 [INFO] train episode 9305: reward = -39.62, steps = 34 00:39:18 [INFO] train episode 9306: reward = -49.12, steps = 41 00:39:18 [INFO] train episode 9307: reward = -33.12, steps = 25 00:39:18 [INFO] train episode 9308: reward = -36.23, steps = 27 00:39:18 [INFO] train episode 9309: reward = -32.19, steps = 32 00:39:19 [INFO] train episode 9310: reward = -35.96, steps = 21 00:39:19 [INFO] train episode 9311: reward = -44.62, steps = 31 00:39:19 [INFO] train episode 9312: reward = -22.37, steps = 28 00:39:19 [INFO] train episode 9313: reward = -44.18, steps = 34 00:39:19 [INFO] train episode 9314: reward = -25.02, steps = 32 00:39:20 [INFO] train episode 9315: reward = -45.51, steps = 37 00:39:20 [INFO] train episode 9316: reward = -31.02, steps = 31 00:39:20 [INFO] train episode 9317: reward = -24.49, steps = 28 00:39:20 [INFO] train episode 9318: reward = -40.50, steps = 21 00:39:20 [INFO] train episode 9319: reward = -37.75, steps = 31 00:39:21 [INFO] train episode 9320: reward = -63.20, steps = 43 00:39:21 [INFO] train episode 9321: reward = -24.52, steps = 33 00:39:21 [INFO] train episode 9322: reward = -33.50, steps = 32 00:39:21 [INFO] train episode 9323: reward = -36.27, steps = 19 00:39:22 [INFO] train episode 9324: reward = -35.80, steps = 27 00:39:22 [INFO] train episode 9325: reward = -34.24, steps = 25 00:39:22 [INFO] train episode 9326: reward = -21.54, steps = 38 00:39:22 [INFO] train episode 9327: reward = -28.10, steps = 33 00:39:22 [INFO] train episode 9328: reward = -40.03, steps = 31 00:39:23 [INFO] train episode 9329: reward = -25.15, steps = 36 00:39:23 [INFO] train episode 9330: reward = -26.99, steps = 22 00:39:23 [INFO] train episode 9331: reward = -53.41, steps = 24 00:39:23 [INFO] train episode 9332: reward = -28.70, steps = 18 00:39:23 [INFO] train episode 9333: reward = -37.29, steps = 33 00:39:24 [INFO] train episode 9334: reward = -36.78, steps = 25 00:39:24 [INFO] train episode 9335: reward = -32.55, steps = 28 00:39:24 [INFO] train episode 9336: reward = -54.37, steps = 33 00:39:24 [INFO] train episode 9337: reward = -44.61, steps = 37 00:39:24 [INFO] train episode 9338: reward = -35.44, steps = 29 00:39:25 [INFO] train episode 9339: reward = -53.65, steps = 35 00:39:25 [INFO] train episode 9340: reward = -37.24, steps = 24 00:39:25 [INFO] train episode 9341: reward = -35.03, steps = 28 00:39:25 [INFO] train episode 9342: reward = -37.15, steps = 24 00:39:26 [INFO] train episode 9343: reward = -32.02, steps = 22 00:39:26 [INFO] train episode 9344: reward = -37.04, steps = 32 00:39:26 [INFO] train episode 9345: reward = -35.36, steps = 26 00:39:26 [INFO] train episode 9346: reward = -27.69, steps = 32 00:39:26 [INFO] train episode 9347: reward = -52.99, steps = 32 00:39:27 [INFO] train episode 9348: reward = -42.10, steps = 41 00:39:27 [INFO] train episode 9349: reward = -28.60, steps = 42 00:39:27 [INFO] train episode 9350: reward = -39.18, steps = 31 00:39:27 [INFO] train episode 9351: reward = -40.16, steps = 27 00:39:28 [INFO] train episode 9352: reward = -41.38, steps = 23 00:39:28 [INFO] train episode 9353: reward = -42.71, steps = 25 00:39:28 [INFO] train episode 9354: reward = -46.47, steps = 35 00:39:28 [INFO] train episode 9355: reward = -30.20, steps = 23 00:39:28 [INFO] train episode 9356: reward = -33.93, steps = 20 00:39:29 [INFO] train episode 9357: reward = -51.11, steps = 38 00:39:29 [INFO] train episode 9358: reward = -66.82, steps = 46 00:39:29 [INFO] train episode 9359: reward = -29.38, steps = 22 00:39:29 [INFO] train episode 9360: reward = -28.79, steps = 30 00:39:29 [INFO] train episode 9361: reward = -22.09, steps = 38 00:39:30 [INFO] train episode 9362: reward = -41.99, steps = 22 00:39:30 [INFO] train episode 9363: reward = -37.10, steps = 22 00:39:30 [INFO] train episode 9364: reward = -29.63, steps = 21 00:39:30 [INFO] train episode 9365: reward = -42.43, steps = 40 00:39:30 [INFO] train episode 9366: reward = -47.06, steps = 29 00:39:31 [INFO] train episode 9367: reward = -25.76, steps = 40 00:39:31 [INFO] train episode 9368: reward = -18.64, steps = 48 00:39:31 [INFO] train episode 9369: reward = -33.11, steps = 37 00:39:31 [INFO] train episode 9370: reward = -42.82, steps = 33 00:39:32 [INFO] train episode 9371: reward = -52.06, steps = 29 00:39:32 [INFO] train episode 9372: reward = -40.04, steps = 25 00:39:32 [INFO] train episode 9373: reward = -29.05, steps = 26 00:39:32 [INFO] train episode 9374: reward = -36.04, steps = 34 00:39:32 [INFO] train episode 9375: reward = -37.43, steps = 29 00:39:33 [INFO] train episode 9376: reward = -53.88, steps = 26 00:39:33 [INFO] train episode 9377: reward = -38.47, steps = 30 00:39:33 [INFO] train episode 9378: reward = -31.16, steps = 29 00:39:33 [INFO] train episode 9379: reward = -29.91, steps = 21 00:39:33 [INFO] train episode 9380: reward = -32.03, steps = 28 00:39:34 [INFO] train episode 9381: reward = -49.20, steps = 32 00:39:34 [INFO] train episode 9382: reward = -31.31, steps = 39 00:39:34 [INFO] train episode 9383: reward = -38.28, steps = 32 00:39:34 [INFO] train episode 9384: reward = -23.83, steps = 23 00:39:34 [INFO] train episode 9385: reward = -23.42, steps = 22 00:39:34 [INFO] train episode 9386: reward = -43.97, steps = 24 00:39:35 [INFO] train episode 9387: reward = -23.65, steps = 30 00:39:35 [INFO] train episode 9388: reward = -27.30, steps = 23 00:39:35 [INFO] train episode 9389: reward = -47.32, steps = 29 00:39:35 [INFO] train episode 9390: reward = -37.30, steps = 26 00:39:36 [INFO] train episode 9391: reward = -32.20, steps = 38 00:39:36 [INFO] train episode 9392: reward = -28.70, steps = 25 00:39:36 [INFO] train episode 9393: reward = -26.89, steps = 21 00:39:36 [INFO] train episode 9394: reward = -51.64, steps = 33 00:39:36 [INFO] train episode 9395: reward = -33.29, steps = 20 00:39:36 [INFO] train episode 9396: reward = -35.60, steps = 20 00:39:37 [INFO] train episode 9397: reward = -38.77, steps = 23 00:39:37 [INFO] train episode 9398: reward = -26.71, steps = 34 00:39:37 [INFO] train episode 9399: reward = -66.11, steps = 63 00:39:37 [INFO] train episode 9400: reward = -21.50, steps = 34 00:39:38 [INFO] train episode 9401: reward = -58.87, steps = 32 00:39:38 [INFO] train episode 9402: reward = -44.31, steps = 42 00:39:38 [INFO] train episode 9403: reward = -31.52, steps = 31 00:39:38 [INFO] train episode 9404: reward = -37.81, steps = 32 00:39:39 [INFO] train episode 9405: reward = -54.86, steps = 32 00:39:39 [INFO] train episode 9406: reward = -52.78, steps = 33 00:39:39 [INFO] train episode 9407: reward = -38.46, steps = 28 00:39:39 [INFO] train episode 9408: reward = -35.83, steps = 28 00:39:40 [INFO] train episode 9409: reward = -32.26, steps = 27 00:39:40 [INFO] train episode 9410: reward = -29.98, steps = 29 00:39:40 [INFO] train episode 9411: reward = -25.49, steps = 28 00:39:40 [INFO] train episode 9412: reward = -50.51, steps = 36 00:39:40 [INFO] train episode 9413: reward = -53.48, steps = 33 00:39:41 [INFO] train episode 9414: reward = -30.60, steps = 23 00:39:41 [INFO] train episode 9415: reward = -41.19, steps = 28 00:39:41 [INFO] train episode 9416: reward = -35.20, steps = 28 00:39:41 [INFO] train episode 9417: reward = -28.66, steps = 40 00:39:42 [INFO] train episode 9418: reward = -37.27, steps = 30 00:39:42 [INFO] train episode 9419: reward = -41.11, steps = 28 00:39:42 [INFO] train episode 9420: reward = -39.42, steps = 20 00:39:42 [INFO] train episode 9421: reward = -31.41, steps = 30 00:39:42 [INFO] train episode 9422: reward = -36.14, steps = 30 00:39:43 [INFO] train episode 9423: reward = -45.41, steps = 23 00:39:43 [INFO] train episode 9424: reward = -44.74, steps = 22 00:39:43 [INFO] train episode 9425: reward = -5.31, steps = 51 00:39:43 [INFO] train episode 9426: reward = -41.49, steps = 38 00:39:43 [INFO] train episode 9427: reward = -49.39, steps = 27 00:39:44 [INFO] train episode 9428: reward = -39.24, steps = 30 00:39:44 [INFO] train episode 9429: reward = -28.81, steps = 35 00:39:44 [INFO] train episode 9430: reward = -43.69, steps = 22 00:39:44 [INFO] train episode 9431: reward = -26.12, steps = 29 00:39:45 [INFO] train episode 9432: reward = -53.20, steps = 38 00:39:45 [INFO] train episode 9433: reward = -33.38, steps = 31 00:39:45 [INFO] train episode 9434: reward = -45.75, steps = 25 00:39:45 [INFO] train episode 9435: reward = -27.81, steps = 46 00:39:45 [INFO] train episode 9436: reward = -30.76, steps = 27 00:39:46 [INFO] train episode 9437: reward = -50.12, steps = 40 00:39:46 [INFO] train episode 9438: reward = -27.04, steps = 27 00:39:46 [INFO] train episode 9439: reward = -31.65, steps = 31 00:39:46 [INFO] train episode 9440: reward = -53.50, steps = 42 00:39:47 [INFO] train episode 9441: reward = -46.22, steps = 32 00:39:47 [INFO] train episode 9442: reward = -31.47, steps = 35 00:39:47 [INFO] train episode 9443: reward = -40.35, steps = 31 00:39:47 [INFO] train episode 9444: reward = -22.14, steps = 38 00:39:48 [INFO] train episode 9445: reward = -43.41, steps = 32 00:39:48 [INFO] train episode 9446: reward = -40.00, steps = 27 00:39:48 [INFO] train episode 9447: reward = -30.55, steps = 24 00:39:48 [INFO] train episode 9448: reward = -37.47, steps = 32 00:39:49 [INFO] train episode 9449: reward = -45.03, steps = 79 00:39:49 [INFO] train episode 9450: reward = -43.90, steps = 34 00:39:49 [INFO] train episode 9451: reward = -24.70, steps = 32 00:39:49 [INFO] train episode 9452: reward = -42.78, steps = 20 00:39:49 [INFO] train episode 9453: reward = -36.27, steps = 26 00:39:50 [INFO] train episode 9454: reward = -35.40, steps = 29 00:39:50 [INFO] train episode 9455: reward = -25.83, steps = 33 00:39:50 [INFO] train episode 9456: reward = -32.81, steps = 27 00:39:50 [INFO] train episode 9457: reward = -41.97, steps = 24 00:39:50 [INFO] train episode 9458: reward = -36.68, steps = 31 00:39:51 [INFO] train episode 9459: reward = -43.38, steps = 45 00:39:51 [INFO] train episode 9460: reward = -43.80, steps = 29 00:39:51 [INFO] train episode 9461: reward = -41.09, steps = 39 00:39:51 [INFO] train episode 9462: reward = -37.66, steps = 41 00:39:52 [INFO] train episode 9463: reward = -57.10, steps = 53 00:39:52 [INFO] train episode 9464: reward = -27.56, steps = 30 00:39:52 [INFO] train episode 9465: reward = -22.40, steps = 27 00:39:53 [INFO] train episode 9466: reward = -38.63, steps = 24 00:39:53 [INFO] train episode 9467: reward = -23.53, steps = 27 00:39:53 [INFO] train episode 9468: reward = -34.88, steps = 24 00:39:53 [INFO] train episode 9469: reward = -20.72, steps = 22 00:39:53 [INFO] train episode 9470: reward = -41.58, steps = 25 00:39:54 [INFO] train episode 9471: reward = -31.57, steps = 35 00:39:54 [INFO] train episode 9472: reward = -49.50, steps = 30 00:39:54 [INFO] train episode 9473: reward = -26.82, steps = 39 00:39:54 [INFO] train episode 9474: reward = -42.37, steps = 27 00:39:54 [INFO] train episode 9475: reward = -30.93, steps = 29 00:39:55 [INFO] train episode 9476: reward = -23.95, steps = 32 00:39:55 [INFO] train episode 9477: reward = -27.87, steps = 41 00:39:55 [INFO] train episode 9478: reward = -50.59, steps = 30 00:39:55 [INFO] train episode 9479: reward = -33.05, steps = 23 00:39:55 [INFO] train episode 9480: reward = -38.53, steps = 23 00:39:56 [INFO] train episode 9481: reward = -21.56, steps = 40 00:39:56 [INFO] train episode 9482: reward = -46.62, steps = 33 00:39:56 [INFO] train episode 9483: reward = -28.00, steps = 36 00:39:56 [INFO] train episode 9484: reward = -36.70, steps = 33 00:39:57 [INFO] train episode 9485: reward = -30.01, steps = 29 00:39:57 [INFO] train episode 9486: reward = -45.66, steps = 33 00:39:57 [INFO] train episode 9487: reward = -39.45, steps = 30 00:39:57 [INFO] train episode 9488: reward = -28.41, steps = 27 00:39:57 [INFO] train episode 9489: reward = -33.94, steps = 20 00:39:58 [INFO] train episode 9490: reward = -21.39, steps = 35 00:39:58 [INFO] train episode 9491: reward = -39.47, steps = 42 00:39:58 [INFO] train episode 9492: reward = -34.96, steps = 22 00:39:58 [INFO] train episode 9493: reward = -38.66, steps = 40 00:39:58 [INFO] train episode 9494: reward = -23.51, steps = 27 00:39:59 [INFO] train episode 9495: reward = -26.83, steps = 23 00:39:59 [INFO] train episode 9496: reward = -30.68, steps = 27 00:39:59 [INFO] train episode 9497: reward = -44.52, steps = 41 00:39:59 [INFO] train episode 9498: reward = -26.23, steps = 31 00:39:59 [INFO] train episode 9499: reward = -38.53, steps = 27 00:40:00 [INFO] train episode 9500: reward = -31.47, steps = 30 00:40:00 [INFO] train episode 9501: reward = -30.50, steps = 27 00:40:00 [INFO] train episode 9502: reward = -39.83, steps = 26 00:40:00 [INFO] train episode 9503: reward = -32.67, steps = 40 00:40:01 [INFO] train episode 9504: reward = -29.93, steps = 23 00:40:01 [INFO] train episode 9505: reward = -41.91, steps = 37 00:40:01 [INFO] train episode 9506: reward = -36.95, steps = 24 00:40:01 [INFO] train episode 9507: reward = -35.93, steps = 31 00:40:01 [INFO] train episode 9508: reward = -24.47, steps = 32 00:40:02 [INFO] train episode 9509: reward = -60.68, steps = 41 00:40:02 [INFO] train episode 9510: reward = -32.82, steps = 27 00:40:02 [INFO] train episode 9511: reward = -36.39, steps = 24 00:40:02 [INFO] train episode 9512: reward = -51.00, steps = 53 00:40:02 [INFO] train episode 9513: reward = -41.65, steps = 27 00:40:03 [INFO] train episode 9514: reward = -41.76, steps = 28 00:40:03 [INFO] train episode 9515: reward = -34.88, steps = 34 00:40:03 [INFO] train episode 9516: reward = -47.28, steps = 24 00:40:03 [INFO] train episode 9517: reward = -19.28, steps = 42 00:40:04 [INFO] train episode 9518: reward = -30.61, steps = 32 00:40:04 [INFO] train episode 9519: reward = -30.45, steps = 25 00:40:04 [INFO] train episode 9520: reward = -40.01, steps = 29 00:40:04 [INFO] train episode 9521: reward = -42.35, steps = 34 00:40:04 [INFO] train episode 9522: reward = -31.24, steps = 30 00:40:05 [INFO] train episode 9523: reward = -37.17, steps = 32 00:40:05 [INFO] train episode 9524: reward = -37.43, steps = 23 00:40:05 [INFO] train episode 9525: reward = -43.69, steps = 31 00:40:05 [INFO] train episode 9526: reward = -35.78, steps = 21 00:40:05 [INFO] train episode 9527: reward = -53.48, steps = 27 00:40:06 [INFO] train episode 9528: reward = -27.04, steps = 28 00:40:06 [INFO] train episode 9529: reward = -28.02, steps = 36 00:40:06 [INFO] train episode 9530: reward = -26.12, steps = 20 00:40:06 [INFO] train episode 9531: reward = -36.32, steps = 25 00:40:07 [INFO] train episode 9532: reward = -25.95, steps = 36 00:40:07 [INFO] train episode 9533: reward = -21.95, steps = 35 00:40:07 [INFO] train episode 9534: reward = -41.28, steps = 30 00:40:07 [INFO] train episode 9535: reward = -41.16, steps = 27 00:40:07 [INFO] train episode 9536: reward = -37.85, steps = 30 00:40:08 [INFO] train episode 9537: reward = -40.05, steps = 36 00:40:08 [INFO] train episode 9538: reward = -29.08, steps = 35 00:40:08 [INFO] train episode 9539: reward = -42.75, steps = 37 00:40:08 [INFO] train episode 9540: reward = -38.23, steps = 25 00:40:08 [INFO] train episode 9541: reward = -34.94, steps = 24 00:40:09 [INFO] train episode 9542: reward = -39.99, steps = 23 00:40:09 [INFO] train episode 9543: reward = -30.44, steps = 23 00:40:09 [INFO] train episode 9544: reward = -38.92, steps = 19 00:40:09 [INFO] train episode 9545: reward = -43.13, steps = 31 00:40:09 [INFO] train episode 9546: reward = -41.52, steps = 21 00:40:10 [INFO] train episode 9547: reward = -43.82, steps = 42 00:40:10 [INFO] train episode 9548: reward = -28.23, steps = 23 00:40:10 [INFO] train episode 9549: reward = -40.00, steps = 45 00:40:10 [INFO] train episode 9550: reward = -28.26, steps = 22 00:40:11 [INFO] train episode 9551: reward = -49.03, steps = 45 00:40:11 [INFO] train episode 9552: reward = -30.59, steps = 33 00:40:11 [INFO] train episode 9553: reward = -28.78, steps = 36 00:40:11 [INFO] train episode 9554: reward = -33.59, steps = 32 00:40:11 [INFO] train episode 9555: reward = -39.25, steps = 28 00:40:12 [INFO] train episode 9556: reward = -23.89, steps = 26 00:40:12 [INFO] train episode 9557: reward = -33.59, steps = 26 00:40:12 [INFO] train episode 9558: reward = -33.61, steps = 31 00:40:12 [INFO] train episode 9559: reward = -33.26, steps = 20 00:40:12 [INFO] train episode 9560: reward = -56.93, steps = 28 00:40:12 [INFO] train episode 9561: reward = -52.29, steps = 31 00:40:13 [INFO] train episode 9562: reward = -32.20, steps = 22 00:40:13 [INFO] train episode 9563: reward = -27.80, steps = 28 00:40:13 [INFO] train episode 9564: reward = -33.89, steps = 31 00:40:13 [INFO] train episode 9565: reward = -61.17, steps = 67 00:40:14 [INFO] train episode 9566: reward = -20.47, steps = 40 00:40:14 [INFO] train episode 9567: reward = -45.01, steps = 29 00:40:14 [INFO] train episode 9568: reward = -42.37, steps = 44 00:40:14 [INFO] train episode 9569: reward = -23.31, steps = 34 00:40:15 [INFO] train episode 9570: reward = -37.04, steps = 28 00:40:15 [INFO] train episode 9571: reward = -33.30, steps = 42 00:40:15 [INFO] train episode 9572: reward = -43.72, steps = 37 00:40:15 [INFO] train episode 9573: reward = -22.24, steps = 30 00:40:16 [INFO] train episode 9574: reward = -26.42, steps = 21 00:40:16 [INFO] train episode 9575: reward = -35.02, steps = 25 00:40:16 [INFO] train episode 9576: reward = -55.78, steps = 34 00:40:16 [INFO] train episode 9577: reward = -37.03, steps = 22 00:40:16 [INFO] train episode 9578: reward = -30.95, steps = 34 00:40:16 [INFO] train episode 9579: reward = -28.94, steps = 20 00:40:17 [INFO] train episode 9580: reward = -28.71, steps = 28 00:40:17 [INFO] train episode 9581: reward = -55.42, steps = 31 00:40:17 [INFO] train episode 9582: reward = -34.52, steps = 33 00:40:17 [INFO] train episode 9583: reward = -52.00, steps = 32 00:40:18 [INFO] train episode 9584: reward = -32.95, steps = 36 00:40:18 [INFO] train episode 9585: reward = -44.98, steps = 30 00:40:18 [INFO] train episode 9586: reward = -21.07, steps = 41 00:40:18 [INFO] train episode 9587: reward = -29.87, steps = 21 00:40:19 [INFO] train episode 9588: reward = -34.90, steps = 44 00:40:19 [INFO] train episode 9589: reward = -42.34, steps = 44 00:40:19 [INFO] train episode 9590: reward = -24.81, steps = 20 00:40:19 [INFO] train episode 9591: reward = -25.85, steps = 22 00:40:19 [INFO] train episode 9592: reward = -36.81, steps = 38 00:40:20 [INFO] train episode 9593: reward = -40.88, steps = 31 00:40:20 [INFO] train episode 9594: reward = -28.29, steps = 21 00:40:20 [INFO] train episode 9595: reward = -37.50, steps = 22 00:40:20 [INFO] train episode 9596: reward = -35.69, steps = 27 00:40:20 [INFO] train episode 9597: reward = -24.51, steps = 30 00:40:21 [INFO] train episode 9598: reward = -29.94, steps = 28 00:40:21 [INFO] train episode 9599: reward = -40.76, steps = 30 00:40:21 [INFO] train episode 9600: reward = -46.14, steps = 36 00:40:21 [INFO] train episode 9601: reward = -27.17, steps = 28 00:40:22 [INFO] train episode 9602: reward = -45.27, steps = 27 00:40:22 [INFO] train episode 9603: reward = -40.73, steps = 41 00:40:22 [INFO] train episode 9604: reward = -47.92, steps = 36 00:40:22 [INFO] train episode 9605: reward = -26.99, steps = 28 00:40:22 [INFO] train episode 9606: reward = -38.15, steps = 28 00:40:23 [INFO] train episode 9607: reward = -44.02, steps = 24 00:40:23 [INFO] train episode 9608: reward = -33.20, steps = 25 00:40:23 [INFO] train episode 9609: reward = -34.05, steps = 39 00:40:23 [INFO] train episode 9610: reward = -31.54, steps = 26 00:40:24 [INFO] train episode 9611: reward = -51.83, steps = 44 00:40:24 [INFO] train episode 9612: reward = -29.84, steps = 24 00:40:24 [INFO] train episode 9613: reward = -35.22, steps = 24 00:40:24 [INFO] train episode 9614: reward = -37.79, steps = 44 00:40:24 [INFO] train episode 9615: reward = -38.94, steps = 25 00:40:25 [INFO] train episode 9616: reward = -37.38, steps = 32 00:40:25 [INFO] train episode 9617: reward = -33.79, steps = 33 00:40:25 [INFO] train episode 9618: reward = -83.51, steps = 65 00:40:25 [INFO] train episode 9619: reward = -43.73, steps = 34 00:40:26 [INFO] train episode 9620: reward = -40.70, steps = 25 00:40:26 [INFO] train episode 9621: reward = -35.65, steps = 31 00:40:26 [INFO] train episode 9622: reward = -37.02, steps = 22 00:40:26 [INFO] train episode 9623: reward = -12.86, steps = 24 00:40:26 [INFO] train episode 9624: reward = -27.12, steps = 26 00:40:27 [INFO] train episode 9625: reward = -52.77, steps = 30 00:40:27 [INFO] train episode 9626: reward = -38.21, steps = 24 00:40:27 [INFO] train episode 9627: reward = -26.85, steps = 21 00:40:27 [INFO] train episode 9628: reward = -36.56, steps = 40 00:40:27 [INFO] train episode 9629: reward = -35.45, steps = 21 00:40:28 [INFO] train episode 9630: reward = -18.14, steps = 40 00:40:28 [INFO] train episode 9631: reward = -44.41, steps = 22 00:40:28 [INFO] train episode 9632: reward = -39.38, steps = 30 00:40:28 [INFO] train episode 9633: reward = -53.99, steps = 39 00:40:29 [INFO] train episode 9634: reward = -32.14, steps = 31 00:40:29 [INFO] train episode 9635: reward = -43.13, steps = 31 00:40:29 [INFO] train episode 9636: reward = -37.34, steps = 31 00:40:29 [INFO] train episode 9637: reward = -31.84, steps = 21 00:40:29 [INFO] train episode 9638: reward = -47.26, steps = 41 00:40:30 [INFO] train episode 9639: reward = -33.04, steps = 28 00:40:30 [INFO] train episode 9640: reward = -38.75, steps = 32 00:40:30 [INFO] train episode 9641: reward = -20.06, steps = 38 00:40:30 [INFO] train episode 9642: reward = -32.04, steps = 29 00:40:30 [INFO] train episode 9643: reward = -28.82, steps = 19 00:40:31 [INFO] train episode 9644: reward = -29.88, steps = 20 00:40:31 [INFO] train episode 9645: reward = -43.26, steps = 33 00:40:31 [INFO] train episode 9646: reward = -28.73, steps = 22 00:40:31 [INFO] train episode 9647: reward = -60.97, steps = 39 00:40:32 [INFO] train episode 9648: reward = -60.36, steps = 37 00:40:32 [INFO] train episode 9649: reward = -47.48, steps = 30 00:40:32 [INFO] train episode 9650: reward = -41.21, steps = 33 00:40:32 [INFO] train episode 9651: reward = -16.05, steps = 35 00:40:32 [INFO] train episode 9652: reward = -47.58, steps = 33 00:40:33 [INFO] train episode 9653: reward = -24.68, steps = 21 00:40:33 [INFO] train episode 9654: reward = -36.44, steps = 26 00:40:33 [INFO] train episode 9655: reward = -4.43, steps = 48 00:40:33 [INFO] train episode 9656: reward = -36.35, steps = 29 00:40:34 [INFO] train episode 9657: reward = -34.41, steps = 26 00:40:34 [INFO] train episode 9658: reward = -23.60, steps = 22 00:40:34 [INFO] train episode 9659: reward = -38.40, steps = 27 00:40:34 [INFO] train episode 9660: reward = -38.00, steps = 37 00:40:35 [INFO] train episode 9661: reward = -37.43, steps = 30 00:40:35 [INFO] train episode 9662: reward = -30.17, steps = 40 00:40:35 [INFO] train episode 9663: reward = -36.39, steps = 38 00:40:35 [INFO] train episode 9664: reward = -39.99, steps = 26 00:40:35 [INFO] train episode 9665: reward = -53.49, steps = 25 00:40:36 [INFO] train episode 9666: reward = -28.98, steps = 31 00:40:36 [INFO] train episode 9667: reward = -68.51, steps = 42 00:40:36 [INFO] train episode 9668: reward = -14.21, steps = 37 00:40:36 [INFO] train episode 9669: reward = -34.10, steps = 24 00:40:37 [INFO] train episode 9670: reward = -67.91, steps = 37 00:40:37 [INFO] train episode 9671: reward = -30.57, steps = 28 00:40:37 [INFO] train episode 9672: reward = -29.79, steps = 31 00:40:37 [INFO] train episode 9673: reward = -29.59, steps = 31 00:40:38 [INFO] train episode 9674: reward = -53.20, steps = 40 00:40:38 [INFO] train episode 9675: reward = -18.09, steps = 29 00:40:38 [INFO] train episode 9676: reward = -21.25, steps = 28 00:40:38 [INFO] train episode 9677: reward = -53.90, steps = 43 00:40:38 [INFO] train episode 9678: reward = -46.27, steps = 40 00:40:39 [INFO] train episode 9679: reward = -28.84, steps = 32 00:40:39 [INFO] train episode 9680: reward = -27.99, steps = 29 00:40:39 [INFO] train episode 9681: reward = -49.97, steps = 37 00:40:39 [INFO] train episode 9682: reward = -52.62, steps = 44 00:40:40 [INFO] train episode 9683: reward = -25.45, steps = 23 00:40:40 [INFO] train episode 9684: reward = -24.62, steps = 26 00:40:40 [INFO] train episode 9685: reward = -60.89, steps = 40 00:40:40 [INFO] train episode 9686: reward = -13.14, steps = 36 00:40:40 [INFO] train episode 9687: reward = -32.43, steps = 19 00:40:41 [INFO] train episode 9688: reward = -44.81, steps = 31 00:40:41 [INFO] train episode 9689: reward = -40.34, steps = 28 00:40:41 [INFO] train episode 9690: reward = -26.76, steps = 33 00:40:41 [INFO] train episode 9691: reward = -20.34, steps = 31 00:40:42 [INFO] train episode 9692: reward = -24.34, steps = 34 00:40:42 [INFO] train episode 9693: reward = -35.61, steps = 21 00:40:42 [INFO] train episode 9694: reward = -31.63, steps = 19 00:40:42 [INFO] train episode 9695: reward = -33.46, steps = 23 00:40:42 [INFO] train episode 9696: reward = -33.90, steps = 32 00:40:42 [INFO] train episode 9697: reward = -36.31, steps = 26 00:40:43 [INFO] train episode 9698: reward = -33.93, steps = 27 00:40:43 [INFO] train episode 9699: reward = -20.17, steps = 31 00:40:43 [INFO] train episode 9700: reward = -47.82, steps = 29 00:40:43 [INFO] train episode 9701: reward = -57.24, steps = 25 00:40:43 [INFO] train episode 9702: reward = -39.46, steps = 27 00:40:44 [INFO] train episode 9703: reward = -36.58, steps = 31 00:40:44 [INFO] train episode 9704: reward = -33.32, steps = 36 00:40:44 [INFO] train episode 9705: reward = -30.12, steps = 33 00:40:44 [INFO] train episode 9706: reward = -35.05, steps = 26 00:40:44 [INFO] train episode 9707: reward = -29.48, steps = 24 00:40:45 [INFO] train episode 9708: reward = -61.73, steps = 37 00:40:45 [INFO] train episode 9709: reward = -36.23, steps = 20 00:40:45 [INFO] train episode 9710: reward = -31.70, steps = 28 00:40:45 [INFO] train episode 9711: reward = -29.31, steps = 34 00:40:45 [INFO] train episode 9712: reward = -30.35, steps = 25 00:40:46 [INFO] train episode 9713: reward = -33.38, steps = 34 00:40:46 [INFO] train episode 9714: reward = -37.27, steps = 25 00:40:46 [INFO] train episode 9715: reward = -29.42, steps = 27 00:40:46 [INFO] train episode 9716: reward = -88.53, steps = 64 00:40:47 [INFO] train episode 9717: reward = -38.89, steps = 25 00:40:47 [INFO] train episode 9718: reward = -31.99, steps = 59 00:40:47 [INFO] train episode 9719: reward = -36.20, steps = 35 00:40:48 [INFO] train episode 9720: reward = -47.99, steps = 39 00:40:48 [INFO] train episode 9721: reward = -37.44, steps = 26 00:40:48 [INFO] train episode 9722: reward = -35.89, steps = 31 00:40:48 [INFO] train episode 9723: reward = -41.75, steps = 33 00:40:49 [INFO] train episode 9724: reward = -37.21, steps = 31 00:40:49 [INFO] train episode 9725: reward = -35.89, steps = 27 00:40:49 [INFO] train episode 9726: reward = -61.62, steps = 36 00:40:49 [INFO] train episode 9727: reward = -36.98, steps = 34 00:40:49 [INFO] train episode 9728: reward = -42.79, steps = 31 00:40:50 [INFO] train episode 9729: reward = -24.24, steps = 30 00:40:50 [INFO] train episode 9730: reward = -24.38, steps = 29 00:40:50 [INFO] train episode 9731: reward = -57.91, steps = 60 00:40:50 [INFO] train episode 9732: reward = -18.53, steps = 29 00:40:51 [INFO] train episode 9733: reward = -28.92, steps = 34 00:40:51 [INFO] train episode 9734: reward = -27.02, steps = 21 00:40:51 [INFO] train episode 9735: reward = -14.49, steps = 36 00:40:51 [INFO] train episode 9736: reward = -19.54, steps = 29 00:40:51 [INFO] train episode 9737: reward = -48.29, steps = 36 00:40:52 [INFO] train episode 9738: reward = -26.70, steps = 34 00:40:52 [INFO] train episode 9739: reward = -9.26, steps = 37 00:40:52 [INFO] train episode 9740: reward = -49.25, steps = 30 00:40:53 [INFO] train episode 9741: reward = -61.22, steps = 51 00:40:53 [INFO] train episode 9742: reward = -29.56, steps = 28 00:40:53 [INFO] train episode 9743: reward = -31.64, steps = 37 00:40:53 [INFO] train episode 9744: reward = -43.92, steps = 30 00:40:53 [INFO] train episode 9745: reward = -33.05, steps = 30 00:40:54 [INFO] train episode 9746: reward = -20.66, steps = 23 00:40:54 [INFO] train episode 9747: reward = -44.03, steps = 39 00:40:54 [INFO] train episode 9748: reward = -20.64, steps = 27 00:40:54 [INFO] train episode 9749: reward = -40.61, steps = 30 00:40:54 [INFO] train episode 9750: reward = -41.37, steps = 30 00:40:55 [INFO] train episode 9751: reward = -47.81, steps = 41 00:40:55 [INFO] train episode 9752: reward = -22.78, steps = 41 00:40:55 [INFO] train episode 9753: reward = -31.14, steps = 21 00:40:55 [INFO] train episode 9754: reward = -30.02, steps = 37 00:40:56 [INFO] train episode 9755: reward = -14.17, steps = 37 00:40:56 [INFO] train episode 9756: reward = -33.13, steps = 34 00:40:56 [INFO] train episode 9757: reward = -22.22, steps = 33 00:40:56 [INFO] train episode 9758: reward = -24.16, steps = 23 00:40:57 [INFO] train episode 9759: reward = -42.52, steps = 37 00:40:57 [INFO] train episode 9760: reward = -36.59, steps = 19 00:40:57 [INFO] train episode 9761: reward = -20.01, steps = 34 00:40:57 [INFO] train episode 9762: reward = -38.17, steps = 30 00:40:57 [INFO] train episode 9763: reward = -20.01, steps = 25 00:40:58 [INFO] train episode 9764: reward = -41.35, steps = 26 00:40:58 [INFO] train episode 9765: reward = -40.55, steps = 33 00:40:58 [INFO] train episode 9766: reward = -27.64, steps = 39 00:40:58 [INFO] train episode 9767: reward = -26.57, steps = 19 00:40:58 [INFO] train episode 9768: reward = -32.82, steps = 26 00:40:59 [INFO] train episode 9769: reward = -30.23, steps = 26 00:40:59 [INFO] train episode 9770: reward = -33.61, steps = 25 00:40:59 [INFO] train episode 9771: reward = -39.58, steps = 30 00:40:59 [INFO] train episode 9772: reward = -43.84, steps = 36 00:40:59 [INFO] train episode 9773: reward = -48.94, steps = 40 00:41:00 [INFO] train episode 9774: reward = -30.61, steps = 25 00:41:00 [INFO] train episode 9775: reward = -18.39, steps = 27 00:41:00 [INFO] train episode 9776: reward = -36.24, steps = 20 00:41:00 [INFO] train episode 9777: reward = -72.03, steps = 52 00:41:01 [INFO] train episode 9778: reward = -44.62, steps = 34 00:41:01 [INFO] train episode 9779: reward = -37.01, steps = 40 00:41:01 [INFO] train episode 9780: reward = -26.66, steps = 32 00:41:01 [INFO] train episode 9781: reward = -36.36, steps = 23 00:41:02 [INFO] train episode 9782: reward = -48.47, steps = 41 00:41:02 [INFO] train episode 9783: reward = -27.47, steps = 45 00:41:02 [INFO] train episode 9784: reward = -30.08, steps = 40 00:41:02 [INFO] train episode 9785: reward = -49.86, steps = 29 00:41:03 [INFO] train episode 9786: reward = -75.60, steps = 76 00:41:03 [INFO] train episode 9787: reward = -34.58, steps = 28 00:41:04 [INFO] train episode 9788: reward = -30.58, steps = 43 00:41:04 [INFO] train episode 9789: reward = -35.93, steps = 40 00:41:04 [INFO] train episode 9790: reward = -12.95, steps = 33 00:41:04 [INFO] train episode 9791: reward = -34.54, steps = 20 00:41:05 [INFO] train episode 9792: reward = -25.17, steps = 56 00:41:05 [INFO] train episode 9793: reward = -30.38, steps = 31 00:41:05 [INFO] train episode 9794: reward = -16.40, steps = 30 00:41:05 [INFO] train episode 9795: reward = -39.80, steps = 31 00:41:06 [INFO] train episode 9796: reward = -24.23, steps = 34 00:41:06 [INFO] train episode 9797: reward = -35.62, steps = 31 00:41:06 [INFO] train episode 9798: reward = -22.49, steps = 24 00:41:06 [INFO] train episode 9799: reward = -14.87, steps = 39 00:41:06 [INFO] train episode 9800: reward = -30.83, steps = 23 00:41:07 [INFO] train episode 9801: reward = -8.00, steps = 43 00:41:07 [INFO] train episode 9802: reward = -38.53, steps = 26 00:41:07 [INFO] train episode 9803: reward = -24.19, steps = 23 00:41:07 [INFO] train episode 9804: reward = -21.13, steps = 24 00:41:07 [INFO] train episode 9805: reward = -16.60, steps = 28 00:41:08 [INFO] train episode 9806: reward = -54.25, steps = 44 00:41:08 [INFO] train episode 9807: reward = -15.20, steps = 36 00:41:08 [INFO] train episode 9808: reward = -29.84, steps = 26 00:41:08 [INFO] train episode 9809: reward = -34.27, steps = 37 00:41:09 [INFO] train episode 9810: reward = -32.76, steps = 35 00:41:09 [INFO] train episode 9811: reward = -42.29, steps = 28 00:41:09 [INFO] train episode 9812: reward = -38.70, steps = 28 00:41:09 [INFO] train episode 9813: reward = -39.53, steps = 24 00:41:09 [INFO] train episode 9814: reward = -24.53, steps = 39 00:41:10 [INFO] train episode 9815: reward = -33.13, steps = 46 00:41:10 [INFO] train episode 9816: reward = -26.89, steps = 47 00:41:10 [INFO] train episode 9817: reward = -38.19, steps = 24 00:41:10 [INFO] train episode 9818: reward = -47.95, steps = 34 00:41:11 [INFO] train episode 9819: reward = -27.94, steps = 31 00:41:11 [INFO] train episode 9820: reward = -31.71, steps = 34 00:41:11 [INFO] train episode 9821: reward = -48.66, steps = 38 00:41:11 [INFO] train episode 9822: reward = -25.73, steps = 32 00:41:12 [INFO] train episode 9823: reward = -32.63, steps = 33 00:41:12 [INFO] train episode 9824: reward = -35.65, steps = 30 00:41:12 [INFO] train episode 9825: reward = -23.75, steps = 20 00:41:12 [INFO] train episode 9826: reward = -34.36, steps = 31 00:41:12 [INFO] train episode 9827: reward = -44.41, steps = 21 00:41:13 [INFO] train episode 9828: reward = -38.75, steps = 43 00:41:13 [INFO] train episode 9829: reward = -43.52, steps = 25 00:41:13 [INFO] train episode 9830: reward = -18.38, steps = 34 00:41:13 [INFO] train episode 9831: reward = -24.84, steps = 24 00:41:14 [INFO] train episode 9832: reward = -38.03, steps = 44 00:41:14 [INFO] train episode 9833: reward = -17.98, steps = 22 00:41:14 [INFO] train episode 9834: reward = -27.22, steps = 25 00:41:14 [INFO] train episode 9835: reward = -31.63, steps = 26 00:41:14 [INFO] train episode 9836: reward = -57.75, steps = 49 00:41:15 [INFO] train episode 9837: reward = -39.70, steps = 32 00:41:15 [INFO] train episode 9838: reward = -40.61, steps = 30 00:41:16 [INFO] train episode 9839: reward = -47.64, steps = 39 00:41:16 [INFO] train episode 9840: reward = -48.26, steps = 34 00:41:16 [INFO] train episode 9841: reward = -32.42, steps = 37 00:41:16 [INFO] train episode 9842: reward = -34.14, steps = 28 00:41:17 [INFO] train episode 9843: reward = -26.27, steps = 46 00:41:17 [INFO] train episode 9844: reward = -5.29, steps = 37 00:41:17 [INFO] train episode 9845: reward = -16.44, steps = 29 00:41:17 [INFO] train episode 9846: reward = -35.13, steps = 34 00:41:18 [INFO] train episode 9847: reward = -19.38, steps = 26 00:41:18 [INFO] train episode 9848: reward = -31.21, steps = 38 00:41:18 [INFO] train episode 9849: reward = -29.66, steps = 35 00:41:18 [INFO] train episode 9850: reward = -40.18, steps = 27 00:41:19 [INFO] train episode 9851: reward = -25.51, steps = 33 00:41:19 [INFO] train episode 9852: reward = -63.80, steps = 43 00:41:19 [INFO] train episode 9853: reward = -36.61, steps = 31 00:41:19 [INFO] train episode 9854: reward = -34.85, steps = 23 00:41:19 [INFO] train episode 9855: reward = -38.45, steps = 44 00:41:20 [INFO] train episode 9856: reward = -30.05, steps = 23 00:41:20 [INFO] train episode 9857: reward = -21.64, steps = 79 00:41:20 [INFO] train episode 9858: reward = -18.34, steps = 20 00:41:21 [INFO] train episode 9859: reward = -19.09, steps = 45 00:41:21 [INFO] train episode 9860: reward = -43.64, steps = 37 00:41:21 [INFO] train episode 9861: reward = -26.63, steps = 31 00:41:21 [INFO] train episode 9862: reward = -24.01, steps = 33 00:41:22 [INFO] train episode 9863: reward = -61.38, steps = 35 00:41:22 [INFO] train episode 9864: reward = -35.62, steps = 40 00:41:22 [INFO] train episode 9865: reward = -34.03, steps = 44 00:41:23 [INFO] train episode 9866: reward = -12.72, steps = 62 00:41:23 [INFO] train episode 9867: reward = -57.74, steps = 43 00:41:23 [INFO] train episode 9868: reward = -57.88, steps = 31 00:41:23 [INFO] train episode 9869: reward = -30.80, steps = 25 00:41:23 [INFO] train episode 9870: reward = -48.60, steps = 32 00:41:24 [INFO] train episode 9871: reward = -16.77, steps = 42 00:41:24 [INFO] train episode 9872: reward = -29.15, steps = 29 00:41:24 [INFO] train episode 9873: reward = -35.34, steps = 31 00:41:24 [INFO] train episode 9874: reward = -24.39, steps = 25 00:41:25 [INFO] train episode 9875: reward = -25.21, steps = 31 00:41:25 [INFO] train episode 9876: reward = -14.27, steps = 29 00:41:25 [INFO] train episode 9877: reward = -28.98, steps = 46 00:41:25 [INFO] train episode 9878: reward = -35.55, steps = 33 00:41:25 [INFO] train episode 9879: reward = -24.41, steps = 29 00:41:26 [INFO] train episode 9880: reward = -40.99, steps = 24 00:41:26 [INFO] train episode 9881: reward = -24.33, steps = 37 00:41:26 [INFO] train episode 9882: reward = -24.33, steps = 26 00:41:26 [INFO] train episode 9883: reward = -46.61, steps = 40 00:41:27 [INFO] train episode 9884: reward = -41.01, steps = 35 00:41:27 [INFO] train episode 9885: reward = -30.65, steps = 21 00:41:27 [INFO] train episode 9886: reward = -30.84, steps = 28 00:41:27 [INFO] train episode 9887: reward = -58.73, steps = 50 00:41:27 [INFO] train episode 9888: reward = -33.50, steps = 30 00:41:28 [INFO] train episode 9889: reward = -18.22, steps = 33 00:41:28 [INFO] train episode 9890: reward = -41.03, steps = 31 00:41:28 [INFO] train episode 9891: reward = -31.86, steps = 27 00:41:28 [INFO] train episode 9892: reward = -29.16, steps = 22 00:41:29 [INFO] train episode 9893: reward = -49.44, steps = 55 00:41:29 [INFO] train episode 9894: reward = -27.47, steps = 45 00:41:29 [INFO] train episode 9895: reward = -53.75, steps = 48 00:41:30 [INFO] train episode 9896: reward = -48.68, steps = 31 00:41:30 [INFO] train episode 9897: reward = -25.66, steps = 22 00:41:30 [INFO] train episode 9898: reward = -17.42, steps = 30 00:41:30 [INFO] train episode 9899: reward = -25.39, steps = 21 00:41:30 [INFO] train episode 9900: reward = -24.42, steps = 21 00:41:31 [INFO] train episode 9901: reward = -48.20, steps = 21 00:41:31 [INFO] train episode 9902: reward = -45.40, steps = 34 00:41:31 [INFO] train episode 9903: reward = -32.81, steps = 33 00:41:31 [INFO] train episode 9904: reward = -15.19, steps = 25 00:41:31 [INFO] train episode 9905: reward = -22.48, steps = 38 00:41:32 [INFO] train episode 9906: reward = -32.57, steps = 45 00:41:32 [INFO] train episode 9907: reward = -35.89, steps = 32 00:41:32 [INFO] train episode 9908: reward = -23.96, steps = 35 00:41:33 [INFO] train episode 9909: reward = -34.27, steps = 50 00:41:33 [INFO] train episode 9910: reward = -34.43, steps = 30 00:41:33 [INFO] train episode 9911: reward = -30.09, steps = 29 00:41:33 [INFO] train episode 9912: reward = -27.46, steps = 22 00:41:33 [INFO] train episode 9913: reward = -16.00, steps = 35 00:41:34 [INFO] train episode 9914: reward = -24.74, steps = 27 00:41:34 [INFO] train episode 9915: reward = -29.34, steps = 26 00:41:34 [INFO] train episode 9916: reward = -12.81, steps = 42 00:41:34 [INFO] train episode 9917: reward = -38.68, steps = 23 00:41:34 [INFO] train episode 9918: reward = -14.05, steps = 34 00:41:35 [INFO] train episode 9919: reward = 0.89, steps = 62 00:41:35 [INFO] train episode 9920: reward = -20.67, steps = 29 00:41:35 [INFO] train episode 9921: reward = -16.19, steps = 36 00:41:35 [INFO] train episode 9922: reward = -38.10, steps = 25 00:41:36 [INFO] train episode 9923: reward = -36.76, steps = 23 00:41:36 [INFO] train episode 9924: reward = -39.17, steps = 42 00:41:36 [INFO] train episode 9925: reward = -23.43, steps = 24 00:41:36 [INFO] train episode 9926: reward = -43.43, steps = 27 00:41:37 [INFO] train episode 9927: reward = -12.43, steps = 36 00:41:37 [INFO] train episode 9928: reward = -56.16, steps = 42 00:41:37 [INFO] train episode 9929: reward = -34.25, steps = 25 00:41:37 [INFO] train episode 9930: reward = -18.79, steps = 46 00:41:38 [INFO] train episode 9931: reward = -61.02, steps = 41 00:41:38 [INFO] train episode 9932: reward = -43.89, steps = 24 00:41:38 [INFO] train episode 9933: reward = -20.56, steps = 36 00:41:38 [INFO] train episode 9934: reward = -73.64, steps = 68 00:41:39 [INFO] train episode 9935: reward = -10.16, steps = 47 00:41:39 [INFO] train episode 9936: reward = -25.76, steps = 28 00:41:39 [INFO] train episode 9937: reward = -22.25, steps = 44 00:41:39 [INFO] train episode 9938: reward = -29.90, steps = 22 00:41:40 [INFO] train episode 9939: reward = -33.10, steps = 24 00:41:40 [INFO] train episode 9940: reward = -28.00, steps = 28 00:41:40 [INFO] train episode 9941: reward = -33.00, steps = 25 00:41:40 [INFO] train episode 9942: reward = -33.66, steps = 24 00:41:40 [INFO] train episode 9943: reward = -43.57, steps = 47 00:41:41 [INFO] train episode 9944: reward = -29.64, steps = 33 00:41:41 [INFO] train episode 9945: reward = -38.19, steps = 38 00:41:41 [INFO] train episode 9946: reward = -31.13, steps = 32 00:41:41 [INFO] train episode 9947: reward = -38.12, steps = 61 00:41:42 [INFO] train episode 9948: reward = -28.39, steps = 27 00:41:42 [INFO] train episode 9949: reward = -38.28, steps = 26 00:41:42 [INFO] train episode 9950: reward = -34.93, steps = 40 00:41:42 [INFO] train episode 9951: reward = -34.43, steps = 43 00:41:43 [INFO] train episode 9952: reward = -21.88, steps = 29 00:41:43 [INFO] train episode 9953: reward = -30.68, steps = 26 00:41:43 [INFO] train episode 9954: reward = -48.03, steps = 29 00:41:44 [INFO] train episode 9955: reward = -31.23, steps = 38 00:41:44 [INFO] train episode 9956: reward = -20.48, steps = 37 00:41:44 [INFO] train episode 9957: reward = -36.60, steps = 33 00:41:44 [INFO] train episode 9958: reward = -29.54, steps = 25 00:41:44 [INFO] train episode 9959: reward = -33.09, steps = 36 00:41:45 [INFO] train episode 9960: reward = -32.26, steps = 22 00:41:45 [INFO] train episode 9961: reward = -43.33, steps = 21 00:41:45 [INFO] train episode 9962: reward = -28.28, steps = 27 00:41:45 [INFO] train episode 9963: reward = -24.15, steps = 47 00:41:46 [INFO] train episode 9964: reward = -19.02, steps = 42 00:41:46 [INFO] train episode 9965: reward = -25.60, steps = 31 00:41:46 [INFO] train episode 9966: reward = -28.31, steps = 27 00:41:46 [INFO] train episode 9967: reward = -44.28, steps = 22 00:41:46 [INFO] train episode 9968: reward = -39.14, steps = 30 00:41:46 [INFO] train episode 9969: reward = -24.99, steps = 26 00:41:47 [INFO] train episode 9970: reward = -20.95, steps = 38 00:41:47 [INFO] train episode 9971: reward = -35.55, steps = 35 00:41:47 [INFO] train episode 9972: reward = -33.21, steps = 45 00:41:47 [INFO] train episode 9973: reward = -32.41, steps = 26 00:41:48 [INFO] train episode 9974: reward = -13.00, steps = 41 00:41:48 [INFO] train episode 9975: reward = -29.20, steps = 60 00:41:48 [INFO] train episode 9976: reward = -27.93, steps = 27 00:41:49 [INFO] train episode 9977: reward = -38.31, steps = 67 00:41:49 [INFO] train episode 9978: reward = -26.13, steps = 35 00:41:49 [INFO] train episode 9979: reward = -22.00, steps = 26 00:41:49 [INFO] train episode 9980: reward = -37.53, steps = 38 00:41:50 [INFO] train episode 9981: reward = -26.38, steps = 49 00:41:50 [INFO] train episode 9982: reward = -23.71, steps = 28 00:41:50 [INFO] train episode 9983: reward = -43.89, steps = 25 00:41:50 [INFO] train episode 9984: reward = -24.21, steps = 24 00:41:50 [INFO] train episode 9985: reward = -30.43, steps = 23 00:41:51 [INFO] train episode 9986: reward = -38.38, steps = 37 00:41:51 [INFO] train episode 9987: reward = -29.42, steps = 37 00:41:51 [INFO] train episode 9988: reward = -47.14, steps = 39 00:41:51 [INFO] train episode 9989: reward = -17.48, steps = 28 00:41:52 [INFO] train episode 9990: reward = -23.68, steps = 27 00:41:52 [INFO] train episode 9991: reward = -20.41, steps = 22 00:41:52 [INFO] train episode 9992: reward = -41.98, steps = 36 00:41:52 [INFO] train episode 9993: reward = -33.24, steps = 24 00:41:52 [INFO] train episode 9994: reward = -37.43, steps = 31 00:41:53 [INFO] train episode 9995: reward = -56.41, steps = 41 00:41:53 [INFO] train episode 9996: reward = -21.06, steps = 35 00:41:53 [INFO] train episode 9997: reward = -46.56, steps = 38 00:41:53 [INFO] train episode 9998: reward = -22.69, steps = 30 00:41:54 [INFO] train episode 9999: reward = -49.68, steps = 50 00:41:54 [INFO] train episode 10000: reward = -27.91, steps = 39 00:41:54 [INFO] train episode 10001: reward = -26.25, steps = 24 00:41:54 [INFO] train episode 10002: reward = -28.16, steps = 39 00:41:55 [INFO] train episode 10003: reward = -34.62, steps = 34 00:41:55 [INFO] train episode 10004: reward = -29.95, steps = 31 00:41:55 [INFO] train episode 10005: reward = -40.79, steps = 26 00:41:55 [INFO] train episode 10006: reward = -25.27, steps = 20 00:41:55 [INFO] train episode 10007: reward = -20.35, steps = 38 00:41:56 [INFO] train episode 10008: reward = -37.10, steps = 42 00:41:56 [INFO] train episode 10009: reward = -25.21, steps = 49 00:41:56 [INFO] train episode 10010: reward = -13.58, steps = 38 00:41:56 [INFO] train episode 10011: reward = -45.42, steps = 24 00:41:57 [INFO] train episode 10012: reward = -19.76, steps = 22 00:41:57 [INFO] train episode 10013: reward = -25.66, steps = 32 00:41:57 [INFO] train episode 10014: reward = -16.31, steps = 42 00:41:58 [INFO] train episode 10015: reward = -70.91, steps = 49 00:41:58 [INFO] train episode 10016: reward = -31.05, steps = 26 00:41:58 [INFO] train episode 10017: reward = -16.95, steps = 29 00:41:58 [INFO] train episode 10018: reward = -21.20, steps = 26 00:41:58 [INFO] train episode 10019: reward = -19.59, steps = 27 00:41:59 [INFO] train episode 10020: reward = -25.27, steps = 23 00:41:59 [INFO] train episode 10021: reward = -27.24, steps = 38 00:41:59 [INFO] train episode 10022: reward = -25.53, steps = 30 00:41:59 [INFO] train episode 10023: reward = -65.63, steps = 52 00:42:00 [INFO] train episode 10024: reward = -22.87, steps = 29 00:42:00 [INFO] train episode 10025: reward = -40.54, steps = 47 00:42:00 [INFO] train episode 10026: reward = -22.49, steps = 43 00:42:01 [INFO] train episode 10027: reward = -20.27, steps = 43 00:42:01 [INFO] train episode 10028: reward = -31.44, steps = 20 00:42:01 [INFO] train episode 10029: reward = -44.64, steps = 42 00:42:01 [INFO] train episode 10030: reward = -25.81, steps = 31 00:42:01 [INFO] train episode 10031: reward = -29.96, steps = 22 00:42:02 [INFO] train episode 10032: reward = -51.83, steps = 42 00:42:02 [INFO] train episode 10033: reward = -29.12, steps = 30 00:42:02 [INFO] train episode 10034: reward = -35.20, steps = 28 00:42:02 [INFO] train episode 10035: reward = -31.17, steps = 31 00:42:03 [INFO] train episode 10036: reward = -17.09, steps = 53 00:42:03 [INFO] train episode 10037: reward = -26.38, steps = 22 00:42:03 [INFO] train episode 10038: reward = -27.74, steps = 39 00:42:03 [INFO] train episode 10039: reward = -25.33, steps = 51 00:42:04 [INFO] train episode 10040: reward = -31.57, steps = 38 00:42:04 [INFO] train episode 10041: reward = -33.33, steps = 27 00:42:04 [INFO] train episode 10042: reward = -22.34, steps = 24 00:42:04 [INFO] train episode 10043: reward = -45.12, steps = 37 00:42:05 [INFO] train episode 10044: reward = -62.99, steps = 50 00:42:05 [INFO] train episode 10045: reward = -33.22, steps = 28 00:42:05 [INFO] train episode 10046: reward = -41.84, steps = 36 00:42:05 [INFO] train episode 10047: reward = -26.16, steps = 36 00:42:06 [INFO] train episode 10048: reward = -31.60, steps = 38 00:42:06 [INFO] train episode 10049: reward = -31.39, steps = 40 00:42:06 [INFO] train episode 10050: reward = -25.08, steps = 39 00:42:06 [INFO] train episode 10051: reward = -6.95, steps = 47 00:42:07 [INFO] train episode 10052: reward = -13.07, steps = 38 00:42:07 [INFO] train episode 10053: reward = -0.58, steps = 55 00:42:07 [INFO] train episode 10054: reward = -30.80, steps = 30 00:42:07 [INFO] train episode 10055: reward = -29.88, steps = 31 00:42:08 [INFO] train episode 10056: reward = -32.48, steps = 29 00:42:08 [INFO] train episode 10057: reward = -25.45, steps = 23 00:42:08 [INFO] train episode 10058: reward = -32.17, steps = 22 00:42:08 [INFO] train episode 10059: reward = -27.19, steps = 37 00:42:08 [INFO] train episode 10060: reward = -41.24, steps = 43 00:42:09 [INFO] train episode 10061: reward = -22.48, steps = 38 00:42:09 [INFO] train episode 10062: reward = -25.06, steps = 20 00:42:09 [INFO] train episode 10063: reward = -10.70, steps = 31 00:42:09 [INFO] train episode 10064: reward = -31.56, steps = 32 00:42:10 [INFO] train episode 10065: reward = -53.79, steps = 42 00:42:10 [INFO] train episode 10066: reward = -26.70, steps = 29 00:42:10 [INFO] train episode 10067: reward = -26.83, steps = 41 00:42:11 [INFO] train episode 10068: reward = -16.52, steps = 24 00:42:11 [INFO] train episode 10069: reward = -42.51, steps = 44 00:42:11 [INFO] train episode 10070: reward = -34.83, steps = 25 00:42:11 [INFO] train episode 10071: reward = -27.65, steps = 39 00:42:12 [INFO] train episode 10072: reward = -12.01, steps = 42 00:42:12 [INFO] train episode 10073: reward = -31.71, steps = 27 00:42:12 [INFO] train episode 10074: reward = -48.53, steps = 57 00:42:12 [INFO] train episode 10075: reward = -40.98, steps = 29 00:42:12 [INFO] train episode 10076: reward = -33.65, steps = 23 00:42:13 [INFO] train episode 10077: reward = -25.97, steps = 21 00:42:13 [INFO] train episode 10078: reward = -25.87, steps = 38 00:42:13 [INFO] train episode 10079: reward = -5.71, steps = 57 00:42:13 [INFO] train episode 10080: reward = -24.82, steps = 33 00:42:14 [INFO] train episode 10081: reward = -39.86, steps = 41 00:42:14 [INFO] train episode 10082: reward = -38.75, steps = 32 00:42:14 [INFO] train episode 10083: reward = -30.06, steps = 19 00:42:14 [INFO] train episode 10084: reward = -34.26, steps = 29 00:42:15 [INFO] train episode 10085: reward = -24.33, steps = 29 00:42:15 [INFO] train episode 10086: reward = -27.51, steps = 24 00:42:15 [INFO] train episode 10087: reward = -57.62, steps = 47 00:42:15 [INFO] train episode 10088: reward = -31.77, steps = 31 00:42:15 [INFO] train episode 10089: reward = -29.64, steps = 22 00:42:16 [INFO] train episode 10090: reward = -11.74, steps = 35 00:42:16 [INFO] train episode 10091: reward = -36.31, steps = 24 00:42:16 [INFO] train episode 10092: reward = -20.36, steps = 28 00:42:16 [INFO] train episode 10093: reward = -18.32, steps = 33 00:42:17 [INFO] train episode 10094: reward = -10.00, steps = 35 00:42:17 [INFO] train episode 10095: reward = -16.28, steps = 23 00:42:17 [INFO] train episode 10096: reward = -18.58, steps = 54 00:42:17 [INFO] train episode 10097: reward = -44.81, steps = 31 00:42:17 [INFO] train episode 10098: reward = -31.11, steps = 21 00:42:18 [INFO] train episode 10099: reward = -20.74, steps = 30 00:42:18 [INFO] train episode 10100: reward = -38.28, steps = 31 00:42:18 [INFO] train episode 10101: reward = -27.33, steps = 36 00:42:18 [INFO] train episode 10102: reward = -25.47, steps = 24 00:42:19 [INFO] train episode 10103: reward = -61.89, steps = 66 00:42:19 [INFO] train episode 10104: reward = -32.18, steps = 42 00:42:19 [INFO] train episode 10105: reward = -38.39, steps = 58 00:42:19 [INFO] train episode 10106: reward = -24.25, steps = 21 00:42:20 [INFO] train episode 10107: reward = -50.97, steps = 34 00:42:20 [INFO] train episode 10108: reward = -23.32, steps = 45 00:42:20 [INFO] train episode 10109: reward = -23.60, steps = 41 00:42:21 [INFO] train episode 10110: reward = -41.40, steps = 47 00:42:21 [INFO] train episode 10111: reward = -26.01, steps = 28 00:42:21 [INFO] train episode 10112: reward = -31.02, steps = 34 00:42:21 [INFO] train episode 10113: reward = -56.06, steps = 43 00:42:22 [INFO] train episode 10114: reward = -44.80, steps = 43 00:42:22 [INFO] train episode 10115: reward = -30.28, steps = 35 00:42:22 [INFO] train episode 10116: reward = -30.02, steps = 46 00:42:22 [INFO] train episode 10117: reward = -22.11, steps = 31 00:42:23 [INFO] train episode 10118: reward = -27.59, steps = 30 00:42:23 [INFO] train episode 10119: reward = -25.34, steps = 18 00:42:23 [INFO] train episode 10120: reward = -36.69, steps = 35 00:42:23 [INFO] train episode 10121: reward = -42.56, steps = 23 00:42:23 [INFO] train episode 10122: reward = -9.36, steps = 29 00:42:24 [INFO] train episode 10123: reward = -25.09, steps = 36 00:42:24 [INFO] train episode 10124: reward = -33.33, steps = 40 00:42:24 [INFO] train episode 10125: reward = -58.67, steps = 48 00:42:25 [INFO] train episode 10126: reward = -31.86, steps = 25 00:42:25 [INFO] train episode 10127: reward = 2.94, steps = 68 00:42:25 [INFO] train episode 10128: reward = -23.32, steps = 20 00:42:25 [INFO] train episode 10129: reward = -21.38, steps = 22 00:42:26 [INFO] train episode 10130: reward = -35.89, steps = 30 00:42:26 [INFO] train episode 10131: reward = -46.74, steps = 56 00:42:26 [INFO] train episode 10132: reward = -21.40, steps = 32 00:42:26 [INFO] train episode 10133: reward = -1.34, steps = 37 00:42:27 [INFO] train episode 10134: reward = -22.89, steps = 24 00:42:27 [INFO] train episode 10135: reward = 4.82, steps = 61 00:42:27 [INFO] train episode 10136: reward = -28.54, steps = 25 00:42:28 [INFO] train episode 10137: reward = -58.69, steps = 58 00:42:28 [INFO] train episode 10138: reward = -26.93, steps = 28 00:42:28 [INFO] train episode 10139: reward = -25.93, steps = 47 00:42:28 [INFO] train episode 10140: reward = -61.67, steps = 54 00:42:29 [INFO] train episode 10141: reward = -26.58, steps = 34 00:42:29 [INFO] train episode 10142: reward = -34.38, steps = 37 00:42:29 [INFO] train episode 10143: reward = -44.82, steps = 36 00:42:29 [INFO] train episode 10144: reward = -20.23, steps = 34 00:42:30 [INFO] train episode 10145: reward = -18.51, steps = 35 00:42:30 [INFO] train episode 10146: reward = -22.84, steps = 23 00:42:30 [INFO] train episode 10147: reward = -16.95, steps = 42 00:42:31 [INFO] train episode 10148: reward = -17.94, steps = 72 00:42:31 [INFO] train episode 10149: reward = -17.97, steps = 52 00:42:31 [INFO] train episode 10150: reward = -49.85, steps = 48 00:42:31 [INFO] train episode 10151: reward = -27.31, steps = 47 00:42:32 [INFO] train episode 10152: reward = -27.21, steps = 40 00:42:32 [INFO] train episode 10153: reward = -42.34, steps = 37 00:42:32 [INFO] train episode 10154: reward = -26.82, steps = 37 00:42:33 [INFO] train episode 10155: reward = -25.22, steps = 43 00:42:33 [INFO] train episode 10156: reward = -29.58, steps = 40 00:42:33 [INFO] train episode 10157: reward = -38.33, steps = 22 00:42:33 [INFO] train episode 10158: reward = -25.41, steps = 33 00:42:33 [INFO] train episode 10159: reward = -20.57, steps = 30 00:42:34 [INFO] train episode 10160: reward = -32.83, steps = 35 00:42:34 [INFO] train episode 10161: reward = -30.86, steps = 23 00:42:34 [INFO] train episode 10162: reward = -34.71, steps = 37 00:42:34 [INFO] train episode 10163: reward = -24.60, steps = 31 00:42:35 [INFO] train episode 10164: reward = -20.75, steps = 52 00:42:35 [INFO] train episode 10165: reward = -34.86, steps = 33 00:42:35 [INFO] train episode 10166: reward = -24.95, steps = 40 00:42:35 [INFO] train episode 10167: reward = -22.09, steps = 36 00:42:36 [INFO] train episode 10168: reward = -3.64, steps = 53 00:42:36 [INFO] train episode 10169: reward = -43.89, steps = 43 00:42:36 [INFO] train episode 10170: reward = -19.65, steps = 21 00:42:37 [INFO] train episode 10171: reward = -35.11, steps = 42 00:42:37 [INFO] train episode 10172: reward = -14.78, steps = 40 00:42:37 [INFO] train episode 10173: reward = -32.99, steps = 31 00:42:37 [INFO] train episode 10174: reward = -22.38, steps = 29 00:42:38 [INFO] train episode 10175: reward = -15.02, steps = 54 00:42:38 [INFO] train episode 10176: reward = -29.66, steps = 42 00:42:38 [INFO] train episode 10177: reward = -56.20, steps = 54 00:42:39 [INFO] train episode 10178: reward = -28.95, steps = 24 00:42:39 [INFO] train episode 10179: reward = 9.99, steps = 51 00:42:39 [INFO] train episode 10180: reward = -35.48, steps = 38 00:42:40 [INFO] train episode 10181: reward = -5.33, steps = 56 00:42:40 [INFO] train episode 10182: reward = -36.78, steps = 24 00:42:40 [INFO] train episode 10183: reward = -15.38, steps = 39 00:42:40 [INFO] train episode 10184: reward = -8.64, steps = 38 00:42:41 [INFO] train episode 10185: reward = -14.81, steps = 37 00:42:41 [INFO] train episode 10186: reward = -31.88, steps = 30 00:42:41 [INFO] train episode 10187: reward = -20.53, steps = 24 00:42:41 [INFO] train episode 10188: reward = -47.28, steps = 57 00:42:42 [INFO] train episode 10189: reward = -41.37, steps = 56 00:42:42 [INFO] train episode 10190: reward = -24.87, steps = 29 00:42:42 [INFO] train episode 10191: reward = -6.67, steps = 47 00:42:43 [INFO] train episode 10192: reward = -32.52, steps = 45 00:42:43 [INFO] train episode 10193: reward = -14.46, steps = 35 00:42:43 [INFO] train episode 10194: reward = 0.96, steps = 42 00:42:43 [INFO] train episode 10195: reward = -12.68, steps = 33 00:42:44 [INFO] train episode 10196: reward = -35.64, steps = 34 00:42:44 [INFO] train episode 10197: reward = -26.19, steps = 27 00:42:44 [INFO] train episode 10198: reward = -5.09, steps = 40 00:42:44 [INFO] train episode 10199: reward = -18.03, steps = 50 00:42:45 [INFO] train episode 10200: reward = -18.72, steps = 32 00:42:45 [INFO] train episode 10201: reward = -12.73, steps = 35 00:42:45 [INFO] train episode 10202: reward = -27.60, steps = 36 00:42:45 [INFO] train episode 10203: reward = -23.25, steps = 28 00:42:45 [INFO] train episode 10204: reward = -38.37, steps = 20 00:42:46 [INFO] train episode 10205: reward = -38.16, steps = 29 00:42:46 [INFO] train episode 10206: reward = -30.75, steps = 45 00:42:46 [INFO] train episode 10207: reward = -74.07, steps = 56 00:42:47 [INFO] train episode 10208: reward = -45.92, steps = 29 00:42:47 [INFO] train episode 10209: reward = -20.37, steps = 40 00:42:47 [INFO] train episode 10210: reward = -8.92, steps = 37 00:42:47 [INFO] train episode 10211: reward = -61.81, steps = 37 00:42:48 [INFO] train episode 10212: reward = -16.95, steps = 50 00:42:48 [INFO] train episode 10213: reward = -1.15, steps = 55 00:42:48 [INFO] train episode 10214: reward = 2.08, steps = 45 00:42:49 [INFO] train episode 10215: reward = -31.47, steps = 21 00:42:49 [INFO] train episode 10216: reward = -15.16, steps = 22 00:42:49 [INFO] train episode 10217: reward = -16.85, steps = 32 00:42:49 [INFO] train episode 10218: reward = -25.51, steps = 23 00:42:49 [INFO] train episode 10219: reward = -23.28, steps = 21 00:42:49 [INFO] train episode 10220: reward = -53.11, steps = 32 00:42:50 [INFO] train episode 10221: reward = -50.63, steps = 48 00:42:50 [INFO] train episode 10222: reward = -30.77, steps = 44 00:42:50 [INFO] train episode 10223: reward = -23.59, steps = 28 00:42:51 [INFO] train episode 10224: reward = -20.91, steps = 39 00:42:51 [INFO] train episode 10225: reward = -18.10, steps = 40 00:42:51 [INFO] train episode 10226: reward = -49.33, steps = 39 00:42:51 [INFO] train episode 10227: reward = -1.96, steps = 49 00:42:52 [INFO] train episode 10228: reward = -12.88, steps = 47 00:42:52 [INFO] train episode 10229: reward = -25.51, steps = 41 00:42:53 [INFO] train episode 10230: reward = -24.31, steps = 30 00:42:53 [INFO] train episode 10231: reward = -28.11, steps = 20 00:42:53 [INFO] train episode 10232: reward = -1.40, steps = 39 00:42:53 [INFO] train episode 10233: reward = -33.54, steps = 24 00:42:53 [INFO] train episode 10234: reward = -38.04, steps = 31 00:42:54 [INFO] train episode 10235: reward = -28.19, steps = 28 00:42:54 [INFO] train episode 10236: reward = -36.90, steps = 37 00:42:54 [INFO] train episode 10237: reward = -38.87, steps = 32 00:42:54 [INFO] train episode 10238: reward = -28.02, steps = 51 00:42:55 [INFO] train episode 10239: reward = -32.84, steps = 31 00:42:55 [INFO] train episode 10240: reward = -29.30, steps = 60 00:42:55 [INFO] train episode 10241: reward = -28.66, steps = 59 00:42:56 [INFO] train episode 10242: reward = -30.97, steps = 33 00:42:56 [INFO] train episode 10243: reward = -33.18, steps = 40 00:42:56 [INFO] train episode 10244: reward = -14.27, steps = 28 00:42:56 [INFO] train episode 10245: reward = -54.42, steps = 48 00:42:57 [INFO] train episode 10246: reward = -27.73, steps = 36 00:42:57 [INFO] train episode 10247: reward = -15.38, steps = 40 00:42:57 [INFO] train episode 10248: reward = -23.88, steps = 36 00:42:58 [INFO] train episode 10249: reward = -13.57, steps = 57 00:42:58 [INFO] train episode 10250: reward = -22.43, steps = 24 00:42:58 [INFO] train episode 10251: reward = -24.35, steps = 25 00:42:58 [INFO] train episode 10252: reward = -26.89, steps = 22 00:42:58 [INFO] train episode 10253: reward = -12.76, steps = 46 00:42:59 [INFO] train episode 10254: reward = -16.50, steps = 24 00:42:59 [INFO] train episode 10255: reward = -16.29, steps = 58 00:42:59 [INFO] train episode 10256: reward = -17.97, steps = 24 00:42:59 [INFO] train episode 10257: reward = -29.90, steps = 24 00:42:59 [INFO] train episode 10258: reward = -31.00, steps = 21 00:43:00 [INFO] train episode 10259: reward = -32.53, steps = 63 00:43:00 [INFO] train episode 10260: reward = -29.89, steps = 56 00:43:01 [INFO] train episode 10261: reward = -25.71, steps = 50 00:43:01 [INFO] train episode 10262: reward = -26.04, steps = 36 00:43:01 [INFO] train episode 10263: reward = -11.48, steps = 54 00:43:02 [INFO] train episode 10264: reward = -23.36, steps = 46 00:43:02 [INFO] train episode 10265: reward = -23.52, steps = 42 00:43:02 [INFO] train episode 10266: reward = -41.36, steps = 33 00:43:02 [INFO] train episode 10267: reward = -33.04, steps = 23 00:43:02 [INFO] train episode 10268: reward = -54.63, steps = 39 00:43:03 [INFO] train episode 10269: reward = -17.39, steps = 43 00:43:03 [INFO] train episode 10270: reward = -5.32, steps = 60 00:43:03 [INFO] train episode 10271: reward = -50.16, steps = 38 00:43:04 [INFO] train episode 10272: reward = -29.71, steps = 21 00:43:04 [INFO] train episode 10273: reward = -28.32, steps = 33 00:43:04 [INFO] train episode 10274: reward = -4.06, steps = 56 00:43:05 [INFO] train episode 10275: reward = -8.68, steps = 47 00:43:05 [INFO] train episode 10276: reward = -52.74, steps = 39 00:43:05 [INFO] train episode 10277: reward = -61.12, steps = 58 00:43:05 [INFO] train episode 10278: reward = -31.36, steps = 30 00:43:06 [INFO] train episode 10279: reward = -37.76, steps = 19 00:43:06 [INFO] train episode 10280: reward = -30.41, steps = 32 00:43:06 [INFO] train episode 10281: reward = -38.31, steps = 41 00:43:07 [INFO] train episode 10282: reward = -27.18, steps = 22 00:43:07 [INFO] train episode 10283: reward = -8.74, steps = 41 00:43:07 [INFO] train episode 10284: reward = -33.13, steps = 29 00:43:07 [INFO] train episode 10285: reward = -15.95, steps = 44 00:43:08 [INFO] train episode 10286: reward = 16.43, steps = 51 00:43:08 [INFO] train episode 10287: reward = -26.35, steps = 20 00:43:08 [INFO] train episode 10288: reward = -15.70, steps = 47 00:43:08 [INFO] train episode 10289: reward = -2.49, steps = 33 00:43:09 [INFO] train episode 10290: reward = -56.28, steps = 54 00:43:09 [INFO] train episode 10291: reward = -26.68, steps = 27 00:43:09 [INFO] train episode 10292: reward = -2.21, steps = 45 00:43:09 [INFO] train episode 10293: reward = -32.08, steps = 26 00:43:10 [INFO] train episode 10294: reward = -57.43, steps = 60 00:43:10 [INFO] train episode 10295: reward = -32.23, steps = 30 00:43:10 [INFO] train episode 10296: reward = -29.17, steps = 35 00:43:11 [INFO] train episode 10297: reward = -29.22, steps = 54 00:43:11 [INFO] train episode 10298: reward = -26.00, steps = 20 00:43:11 [INFO] train episode 10299: reward = -16.29, steps = 30 00:43:11 [INFO] train episode 10300: reward = -22.45, steps = 34 00:43:12 [INFO] train episode 10301: reward = -31.14, steps = 42 00:43:12 [INFO] train episode 10302: reward = -34.72, steps = 29 00:43:12 [INFO] train episode 10303: reward = -33.79, steps = 45 00:43:12 [INFO] train episode 10304: reward = -5.31, steps = 45 00:43:13 [INFO] train episode 10305: reward = -12.40, steps = 65 00:43:13 [INFO] train episode 10306: reward = -23.87, steps = 32 00:43:13 [INFO] train episode 10307: reward = -36.16, steps = 23 00:43:13 [INFO] train episode 10308: reward = -24.75, steps = 49 00:43:14 [INFO] train episode 10309: reward = -7.23, steps = 45 00:43:14 [INFO] train episode 10310: reward = 6.93, steps = 55 00:43:15 [INFO] train episode 10311: reward = -41.67, steps = 63 00:43:15 [INFO] train episode 10312: reward = -12.44, steps = 41 00:43:15 [INFO] train episode 10313: reward = -6.78, steps = 50 00:43:15 [INFO] train episode 10314: reward = -24.62, steps = 30 00:43:16 [INFO] train episode 10315: reward = -22.88, steps = 53 00:43:16 [INFO] train episode 10316: reward = -10.96, steps = 32 00:43:16 [INFO] train episode 10317: reward = -24.60, steps = 38 00:43:17 [INFO] train episode 10318: reward = -15.35, steps = 56 00:43:17 [INFO] train episode 10319: reward = -19.54, steps = 37 00:43:17 [INFO] train episode 10320: reward = -17.05, steps = 43 00:43:17 [INFO] train episode 10321: reward = -17.53, steps = 39 00:43:18 [INFO] train episode 10322: reward = -15.72, steps = 39 00:43:18 [INFO] train episode 10323: reward = -10.04, steps = 39 00:43:18 [INFO] train episode 10324: reward = -11.09, steps = 40 00:43:18 [INFO] train episode 10325: reward = -9.74, steps = 40 00:43:19 [INFO] train episode 10326: reward = -46.77, steps = 48 00:43:19 [INFO] train episode 10327: reward = -25.49, steps = 22 00:43:20 [INFO] train episode 10328: reward = -59.28, steps = 76 00:43:20 [INFO] train episode 10329: reward = -0.78, steps = 36 00:43:20 [INFO] train episode 10330: reward = -33.49, steps = 37 00:43:20 [INFO] train episode 10331: reward = -29.78, steps = 23 00:43:21 [INFO] train episode 10332: reward = -23.97, steps = 39 00:43:21 [INFO] train episode 10333: reward = -38.95, steps = 27 00:43:21 [INFO] train episode 10334: reward = -27.41, steps = 28 00:43:21 [INFO] train episode 10335: reward = 11.25, steps = 46 00:43:22 [INFO] train episode 10336: reward = -31.59, steps = 21 00:43:22 [INFO] train episode 10337: reward = -44.98, steps = 54 00:43:22 [INFO] train episode 10338: reward = -24.39, steps = 23 00:43:22 [INFO] train episode 10339: reward = -20.93, steps = 27 00:43:22 [INFO] train episode 10340: reward = -33.19, steps = 23 00:43:23 [INFO] train episode 10341: reward = -18.27, steps = 46 00:43:23 [INFO] train episode 10342: reward = -38.65, steps = 45 00:43:23 [INFO] train episode 10343: reward = -18.59, steps = 49 00:43:24 [INFO] train episode 10344: reward = -31.10, steps = 28 00:43:24 [INFO] train episode 10345: reward = -18.84, steps = 25 00:43:24 [INFO] train episode 10346: reward = -21.64, steps = 28 00:43:24 [INFO] train episode 10347: reward = -17.77, steps = 45 00:43:24 [INFO] train episode 10348: reward = -20.38, steps = 27 00:43:25 [INFO] train episode 10349: reward = -9.74, steps = 49 00:43:25 [INFO] train episode 10350: reward = -28.28, steps = 46 00:43:25 [INFO] train episode 10351: reward = -48.47, steps = 22 00:43:25 [INFO] train episode 10352: reward = -24.98, steps = 33 00:43:26 [INFO] train episode 10353: reward = -25.82, steps = 56 00:43:26 [INFO] train episode 10354: reward = -30.01, steps = 25 00:43:26 [INFO] train episode 10355: reward = -53.39, steps = 52 00:43:27 [INFO] train episode 10356: reward = -12.85, steps = 37 00:43:27 [INFO] train episode 10357: reward = -33.11, steps = 35 00:43:27 [INFO] train episode 10358: reward = -13.78, steps = 58 00:43:28 [INFO] train episode 10359: reward = -33.76, steps = 69 00:43:28 [INFO] train episode 10360: reward = -40.98, steps = 39 00:43:28 [INFO] train episode 10361: reward = 9.69, steps = 46 00:43:29 [INFO] train episode 10362: reward = -24.13, steps = 37 00:43:29 [INFO] train episode 10363: reward = -18.78, steps = 30 00:43:29 [INFO] train episode 10364: reward = -16.15, steps = 42 00:43:29 [INFO] train episode 10365: reward = -42.04, steps = 35 00:43:29 [INFO] train episode 10366: reward = -39.36, steps = 23 00:43:30 [INFO] train episode 10367: reward = -35.90, steps = 58 00:43:30 [INFO] train episode 10368: reward = -15.83, steps = 43 00:43:30 [INFO] train episode 10369: reward = -30.68, steps = 42 00:43:31 [INFO] train episode 10370: reward = -16.40, steps = 50 00:43:31 [INFO] train episode 10371: reward = 1.26, steps = 62 00:43:31 [INFO] train episode 10372: reward = -28.78, steps = 40 00:43:32 [INFO] train episode 10373: reward = -9.45, steps = 46 00:43:32 [INFO] train episode 10374: reward = -63.85, steps = 88 00:43:32 [INFO] train episode 10375: reward = -18.39, steps = 25 00:43:33 [INFO] train episode 10376: reward = -23.01, steps = 47 00:43:33 [INFO] train episode 10377: reward = -15.58, steps = 60 00:43:34 [INFO] train episode 10378: reward = 2.86, steps = 54 00:43:34 [INFO] train episode 10379: reward = -26.89, steps = 45 00:43:34 [INFO] train episode 10380: reward = -28.42, steps = 22 00:43:35 [INFO] train episode 10381: reward = -6.50, steps = 63 00:43:35 [INFO] train episode 10382: reward = -11.00, steps = 38 00:43:35 [INFO] train episode 10383: reward = 10.41, steps = 55 00:43:36 [INFO] train episode 10384: reward = -2.36, steps = 38 00:43:36 [INFO] train episode 10385: reward = -18.94, steps = 36 00:43:36 [INFO] train episode 10386: reward = -26.63, steps = 28 00:43:36 [INFO] train episode 10387: reward = -15.39, steps = 52 00:43:36 [INFO] train episode 10388: reward = -35.56, steps = 24 00:43:37 [INFO] train episode 10389: reward = -23.47, steps = 46 00:43:37 [INFO] train episode 10390: reward = 6.92, steps = 46 00:43:37 [INFO] train episode 10391: reward = -38.39, steps = 22 00:43:38 [INFO] train episode 10392: reward = -21.12, steps = 46 00:43:38 [INFO] train episode 10393: reward = -10.00, steps = 37 00:43:38 [INFO] train episode 10394: reward = -21.83, steps = 48 00:43:38 [INFO] train episode 10395: reward = -1.59, steps = 40 00:43:39 [INFO] train episode 10396: reward = -43.26, steps = 53 00:43:39 [INFO] train episode 10397: reward = -23.05, steps = 59 00:43:39 [INFO] train episode 10398: reward = -10.59, steps = 33 00:43:40 [INFO] train episode 10399: reward = -0.84, steps = 41 00:43:40 [INFO] train episode 10400: reward = -7.38, steps = 39 00:43:40 [INFO] train episode 10401: reward = -32.63, steps = 23 00:43:40 [INFO] train episode 10402: reward = -49.65, steps = 59 00:43:41 [INFO] train episode 10403: reward = -13.53, steps = 37 00:43:41 [INFO] train episode 10404: reward = -33.85, steps = 54 00:43:41 [INFO] train episode 10405: reward = -35.42, steps = 40 00:43:42 [INFO] train episode 10406: reward = -12.93, steps = 45 00:43:42 [INFO] train episode 10407: reward = -21.74, steps = 56 00:43:42 [INFO] train episode 10408: reward = -51.69, steps = 48 00:43:43 [INFO] train episode 10409: reward = -19.67, steps = 34 00:43:43 [INFO] train episode 10410: reward = -36.60, steps = 23 00:43:43 [INFO] train episode 10411: reward = -49.06, steps = 51 00:43:43 [INFO] train episode 10412: reward = -1.16, steps = 44 00:43:44 [INFO] train episode 10413: reward = -10.66, steps = 47 00:43:44 [INFO] train episode 10414: reward = -7.98, steps = 41 00:43:44 [INFO] train episode 10415: reward = -64.97, steps = 37 00:43:44 [INFO] train episode 10416: reward = -23.85, steps = 24 00:43:45 [INFO] train episode 10417: reward = -4.26, steps = 52 00:43:45 [INFO] train episode 10418: reward = -40.04, steps = 33 00:43:45 [INFO] train episode 10419: reward = -27.24, steps = 38 00:43:45 [INFO] train episode 10420: reward = -34.02, steps = 55 00:43:46 [INFO] train episode 10421: reward = -5.44, steps = 41 00:43:46 [INFO] train episode 10422: reward = -14.21, steps = 47 00:43:46 [INFO] train episode 10423: reward = -24.22, steps = 40 00:43:47 [INFO] train episode 10424: reward = -18.22, steps = 46 00:43:47 [INFO] train episode 10425: reward = -37.24, steps = 22 00:43:47 [INFO] train episode 10426: reward = -39.03, steps = 37 00:43:48 [INFO] train episode 10427: reward = -51.05, steps = 53 00:43:48 [INFO] train episode 10428: reward = -36.80, steps = 41 00:43:48 [INFO] train episode 10429: reward = -34.94, steps = 45 00:43:48 [INFO] train episode 10430: reward = -37.00, steps = 21 00:43:49 [INFO] train episode 10431: reward = -20.18, steps = 42 00:43:49 [INFO] train episode 10432: reward = -16.60, steps = 46 00:43:49 [INFO] train episode 10433: reward = -42.04, steps = 26 00:43:49 [INFO] train episode 10434: reward = -22.72, steps = 23 00:43:50 [INFO] train episode 10435: reward = -23.35, steps = 42 00:43:50 [INFO] train episode 10436: reward = -36.34, steps = 21 00:43:50 [INFO] train episode 10437: reward = 2.49, steps = 37 00:43:50 [INFO] train episode 10438: reward = -41.19, steps = 28 00:43:51 [INFO] train episode 10439: reward = -22.23, steps = 31 00:43:51 [INFO] train episode 10440: reward = -27.58, steps = 41 00:43:51 [INFO] train episode 10441: reward = 5.85, steps = 45 00:43:51 [INFO] train episode 10442: reward = -15.13, steps = 45 00:43:52 [INFO] train episode 10443: reward = -29.36, steps = 22 00:43:52 [INFO] train episode 10444: reward = -12.51, steps = 46 00:43:52 [INFO] train episode 10445: reward = -26.27, steps = 48 00:43:52 [INFO] train episode 10446: reward = -50.10, steps = 41 00:43:53 [INFO] train episode 10447: reward = -12.25, steps = 44 00:43:53 [INFO] train episode 10448: reward = -31.89, steps = 20 00:43:53 [INFO] train episode 10449: reward = 2.67, steps = 57 00:43:53 [INFO] train episode 10450: reward = -27.86, steps = 22 00:43:54 [INFO] train episode 10451: reward = -24.61, steps = 53 00:43:54 [INFO] train episode 10452: reward = -10.87, steps = 45 00:43:54 [INFO] train episode 10453: reward = -56.83, steps = 46 00:43:55 [INFO] train episode 10454: reward = -43.65, steps = 19 00:43:55 [INFO] train episode 10455: reward = -11.71, steps = 42 00:43:55 [INFO] train episode 10456: reward = -27.53, steps = 30 00:43:55 [INFO] train episode 10457: reward = -1.17, steps = 42 00:43:56 [INFO] train episode 10458: reward = -56.06, steps = 35 00:43:56 [INFO] train episode 10459: reward = -16.92, steps = 46 00:43:56 [INFO] train episode 10460: reward = -22.33, steps = 67 00:43:57 [INFO] train episode 10461: reward = -2.75, steps = 41 00:43:57 [INFO] train episode 10462: reward = -38.86, steps = 22 00:43:57 [INFO] train episode 10463: reward = -20.25, steps = 26 00:43:57 [INFO] train episode 10464: reward = -54.63, steps = 55 00:43:58 [INFO] train episode 10465: reward = -49.58, steps = 71 00:43:58 [INFO] train episode 10466: reward = -17.43, steps = 41 00:43:58 [INFO] train episode 10467: reward = -18.08, steps = 34 00:43:59 [INFO] train episode 10468: reward = -19.91, steps = 25 00:43:59 [INFO] train episode 10469: reward = -30.85, steps = 24 00:43:59 [INFO] train episode 10470: reward = -33.00, steps = 30 00:43:59 [INFO] train episode 10471: reward = -4.98, steps = 40 00:44:00 [INFO] train episode 10472: reward = -32.55, steps = 51 00:44:00 [INFO] train episode 10473: reward = -12.72, steps = 35 00:44:00 [INFO] train episode 10474: reward = 1.21, steps = 52 00:44:01 [INFO] train episode 10475: reward = -5.49, steps = 55 00:44:01 [INFO] train episode 10476: reward = -32.34, steps = 28 00:44:01 [INFO] train episode 10477: reward = -2.56, steps = 43 00:44:02 [INFO] train episode 10478: reward = -26.77, steps = 51 00:44:02 [INFO] train episode 10479: reward = -46.04, steps = 29 00:44:02 [INFO] train episode 10480: reward = -37.53, steps = 34 00:44:02 [INFO] train episode 10481: reward = -34.04, steps = 42 00:44:03 [INFO] train episode 10482: reward = -6.72, steps = 73 00:44:03 [INFO] train episode 10483: reward = -1.92, steps = 58 00:44:04 [INFO] train episode 10484: reward = -21.44, steps = 49 00:44:04 [INFO] train episode 10485: reward = -53.27, steps = 46 00:44:04 [INFO] train episode 10486: reward = -32.84, steps = 43 00:44:04 [INFO] train episode 10487: reward = -42.74, steps = 19 00:44:04 [INFO] train episode 10488: reward = -42.14, steps = 19 00:44:05 [INFO] train episode 10489: reward = 0.59, steps = 40 00:44:05 [INFO] train episode 10490: reward = -29.33, steps = 21 00:44:05 [INFO] train episode 10491: reward = -35.19, steps = 40 00:44:05 [INFO] train episode 10492: reward = -31.02, steps = 34 00:44:06 [INFO] train episode 10493: reward = -1.64, steps = 47 00:44:06 [INFO] train episode 10494: reward = -25.92, steps = 24 00:44:06 [INFO] train episode 10495: reward = -6.16, steps = 42 00:44:06 [INFO] train episode 10496: reward = -33.46, steps = 21 00:44:07 [INFO] train episode 10497: reward = -17.33, steps = 64 00:44:07 [INFO] train episode 10498: reward = -34.17, steps = 48 00:44:08 [INFO] train episode 10499: reward = -21.06, steps = 60 00:44:08 [INFO] train episode 10500: reward = -26.66, steps = 29 00:44:08 [INFO] train episode 10501: reward = -6.48, steps = 31 00:44:08 [INFO] train episode 10502: reward = -16.53, steps = 45 00:44:08 [INFO] train episode 10503: reward = -38.30, steps = 26 00:44:09 [INFO] train episode 10504: reward = -21.68, steps = 39 00:44:09 [INFO] train episode 10505: reward = -18.44, steps = 55 00:44:09 [INFO] train episode 10506: reward = -12.44, steps = 46 00:44:10 [INFO] train episode 10507: reward = -6.12, steps = 50 00:44:10 [INFO] train episode 10508: reward = -30.98, steps = 21 00:44:10 [INFO] train episode 10509: reward = -29.73, steps = 27 00:44:10 [INFO] train episode 10510: reward = 6.79, steps = 55 00:44:11 [INFO] train episode 10511: reward = -16.68, steps = 65 00:44:11 [INFO] train episode 10512: reward = -25.65, steps = 46 00:44:11 [INFO] train episode 10513: reward = -28.03, steps = 27 00:44:12 [INFO] train episode 10514: reward = -7.58, steps = 49 00:44:12 [INFO] train episode 10515: reward = -35.31, steps = 66 00:44:12 [INFO] train episode 10516: reward = -18.07, steps = 39 00:44:13 [INFO] train episode 10517: reward = -12.18, steps = 42 00:44:13 [INFO] train episode 10518: reward = -50.78, steps = 39 00:44:13 [INFO] train episode 10519: reward = -38.17, steps = 62 00:44:14 [INFO] train episode 10520: reward = -0.04, steps = 54 00:44:14 [INFO] train episode 10521: reward = -19.22, steps = 28 00:44:14 [INFO] train episode 10522: reward = -3.82, steps = 38 00:44:15 [INFO] train episode 10523: reward = -41.14, steps = 24 00:44:15 [INFO] train episode 10524: reward = -37.56, steps = 27 00:44:15 [INFO] train episode 10525: reward = -9.51, steps = 31 00:44:15 [INFO] train episode 10526: reward = -39.38, steps = 51 00:44:16 [INFO] train episode 10527: reward = 4.54, steps = 50 00:44:16 [INFO] train episode 10528: reward = 0.72, steps = 43 00:44:16 [INFO] train episode 10529: reward = -39.77, steps = 21 00:44:16 [INFO] train episode 10530: reward = -33.57, steps = 30 00:44:17 [INFO] train episode 10531: reward = -3.41, steps = 48 00:44:17 [INFO] train episode 10532: reward = -32.04, steps = 25 00:44:17 [INFO] train episode 10533: reward = -1.08, steps = 40 00:44:17 [INFO] train episode 10534: reward = -25.07, steps = 24 00:44:18 [INFO] train episode 10535: reward = -37.06, steps = 51 00:44:18 [INFO] train episode 10536: reward = -24.59, steps = 31 00:44:18 [INFO] train episode 10537: reward = 3.13, steps = 54 00:44:18 [INFO] train episode 10538: reward = -16.61, steps = 28 00:44:19 [INFO] train episode 10539: reward = -9.48, steps = 52 00:44:19 [INFO] train episode 10540: reward = -6.64, steps = 39 00:44:19 [INFO] train episode 10541: reward = -39.27, steps = 22 00:44:19 [INFO] train episode 10542: reward = -38.24, steps = 29 00:44:20 [INFO] train episode 10543: reward = -11.84, steps = 37 00:44:20 [INFO] train episode 10544: reward = -2.94, steps = 66 00:44:20 [INFO] train episode 10545: reward = -32.81, steps = 20 00:44:20 [INFO] train episode 10546: reward = -21.92, steps = 37 00:44:21 [INFO] train episode 10547: reward = -6.29, steps = 44 00:44:21 [INFO] train episode 10548: reward = -15.53, steps = 55 00:44:21 [INFO] train episode 10549: reward = -31.48, steps = 31 00:44:22 [INFO] train episode 10550: reward = -45.78, steps = 29 00:44:22 [INFO] train episode 10551: reward = 1.27, steps = 40 00:44:22 [INFO] train episode 10552: reward = -26.41, steps = 17 00:44:22 [INFO] train episode 10553: reward = -16.74, steps = 48 00:44:23 [INFO] train episode 10554: reward = -23.33, steps = 33 00:44:23 [INFO] train episode 10555: reward = -23.82, steps = 43 00:44:23 [INFO] train episode 10556: reward = -7.38, steps = 45 00:44:24 [INFO] train episode 10557: reward = 1.25, steps = 57 00:44:24 [INFO] train episode 10558: reward = -28.47, steps = 98 00:44:25 [INFO] train episode 10559: reward = -35.05, steps = 79 00:44:25 [INFO] train episode 10560: reward = -29.42, steps = 26 00:44:25 [INFO] train episode 10561: reward = -42.43, steps = 21 00:44:25 [INFO] train episode 10562: reward = -26.55, steps = 22 00:44:26 [INFO] train episode 10563: reward = 1.68, steps = 52 00:44:26 [INFO] train episode 10564: reward = -13.29, steps = 52 00:44:26 [INFO] train episode 10565: reward = -33.20, steps = 30 00:44:26 [INFO] train episode 10566: reward = -12.46, steps = 43 00:44:27 [INFO] train episode 10567: reward = -47.80, steps = 43 00:44:27 [INFO] train episode 10568: reward = -20.30, steps = 52 00:44:27 [INFO] train episode 10569: reward = -1.70, steps = 51 00:44:28 [INFO] train episode 10570: reward = -15.32, steps = 37 00:44:28 [INFO] train episode 10571: reward = -7.10, steps = 38 00:44:29 [INFO] train episode 10572: reward = -52.96, steps = 87 00:44:29 [INFO] train episode 10573: reward = -28.83, steps = 22 00:44:29 [INFO] train episode 10574: reward = -29.59, steps = 38 00:44:29 [INFO] train episode 10575: reward = -40.66, steps = 22 00:44:30 [INFO] train episode 10576: reward = -14.32, steps = 30 00:44:30 [INFO] train episode 10577: reward = 12.45, steps = 53 00:44:30 [INFO] train episode 10578: reward = -31.79, steps = 32 00:44:30 [INFO] train episode 10579: reward = 4.36, steps = 52 00:44:31 [INFO] train episode 10580: reward = -40.21, steps = 19 00:44:31 [INFO] train episode 10581: reward = -0.03, steps = 42 00:44:31 [INFO] train episode 10582: reward = 3.35, steps = 43 00:44:31 [INFO] train episode 10583: reward = -26.23, steps = 32 00:44:32 [INFO] train episode 10584: reward = -30.77, steps = 24 00:44:32 [INFO] train episode 10585: reward = -11.81, steps = 50 00:44:32 [INFO] train episode 10586: reward = -15.00, steps = 42 00:44:32 [INFO] train episode 10587: reward = -2.53, steps = 47 00:44:33 [INFO] train episode 10588: reward = -37.12, steps = 22 00:44:33 [INFO] train episode 10589: reward = -19.13, steps = 33 00:44:33 [INFO] train episode 10590: reward = -29.27, steps = 21 00:44:33 [INFO] train episode 10591: reward = -0.21, steps = 49 00:44:34 [INFO] train episode 10592: reward = -5.51, steps = 45 00:44:34 [INFO] train episode 10593: reward = 14.12, steps = 59 00:44:34 [INFO] train episode 10594: reward = 4.62, steps = 37 00:44:35 [INFO] train episode 10595: reward = -1.93, steps = 46 00:44:35 [INFO] train episode 10596: reward = 11.03, steps = 58 00:44:35 [INFO] train episode 10597: reward = -9.31, steps = 43 00:44:36 [INFO] train episode 10598: reward = 2.96, steps = 49 00:44:36 [INFO] train episode 10599: reward = -71.09, steps = 45 00:44:36 [INFO] train episode 10600: reward = -1.48, steps = 49 00:44:37 [INFO] train episode 10601: reward = -16.43, steps = 32 00:44:37 [INFO] train episode 10602: reward = -28.37, steps = 25 00:44:37 [INFO] train episode 10603: reward = -7.57, steps = 37 00:44:37 [INFO] train episode 10604: reward = -10.39, steps = 33 00:44:38 [INFO] train episode 10605: reward = 1.24, steps = 50 00:44:38 [INFO] train episode 10606: reward = -18.11, steps = 34 00:44:38 [INFO] train episode 10607: reward = -34.41, steps = 27 00:44:38 [INFO] train episode 10608: reward = -10.04, steps = 43 00:44:38 [INFO] train episode 10609: reward = -16.14, steps = 31 00:44:39 [INFO] train episode 10610: reward = -17.24, steps = 59 00:44:39 [INFO] train episode 10611: reward = 9.64, steps = 83 00:44:40 [INFO] train episode 10612: reward = -40.64, steps = 17 00:44:40 [INFO] train episode 10613: reward = -51.36, steps = 17 00:44:40 [INFO] train episode 10614: reward = -19.65, steps = 35 00:44:40 [INFO] train episode 10615: reward = -12.48, steps = 44 00:44:41 [INFO] train episode 10616: reward = -45.96, steps = 44 00:44:41 [INFO] train episode 10617: reward = -15.99, steps = 29 00:44:41 [INFO] train episode 10618: reward = -27.00, steps = 43 00:44:41 [INFO] train episode 10619: reward = -6.97, steps = 40 00:44:41 [INFO] train episode 10620: reward = -62.80, steps = 20 00:44:42 [INFO] train episode 10621: reward = -27.56, steps = 41 00:44:42 [INFO] train episode 10622: reward = -19.09, steps = 30 00:44:43 [INFO] train episode 10623: reward = 0.81, steps = 45 00:44:43 [INFO] train episode 10624: reward = -17.64, steps = 34 00:44:43 [INFO] train episode 10625: reward = -15.04, steps = 55 00:44:43 [INFO] train episode 10626: reward = -23.31, steps = 32 00:44:44 [INFO] train episode 10627: reward = -9.70, steps = 32 00:44:44 [INFO] train episode 10628: reward = -7.73, steps = 35 00:44:44 [INFO] train episode 10629: reward = -1.22, steps = 40 00:44:44 [INFO] train episode 10630: reward = -16.10, steps = 31 00:44:44 [INFO] train episode 10631: reward = -26.56, steps = 23 00:44:45 [INFO] train episode 10632: reward = -30.55, steps = 35 00:44:45 [INFO] train episode 10633: reward = -19.73, steps = 34 00:44:45 [INFO] train episode 10634: reward = -20.31, steps = 34 00:44:45 [INFO] train episode 10635: reward = -6.92, steps = 36 00:44:46 [INFO] train episode 10636: reward = -13.42, steps = 35 00:44:46 [INFO] train episode 10637: reward = 7.54, steps = 52 00:44:47 [INFO] train episode 10638: reward = 5.85, steps = 88 00:44:47 [INFO] train episode 10639: reward = -4.52, steps = 33 00:44:47 [INFO] train episode 10640: reward = -22.64, steps = 31 00:44:47 [INFO] train episode 10641: reward = 7.06, steps = 47 00:44:47 [INFO] train episode 10642: reward = -2.15, steps = 38 00:44:48 [INFO] train episode 10643: reward = -30.93, steps = 20 00:44:48 [INFO] train episode 10644: reward = -26.76, steps = 59 00:44:48 [INFO] train episode 10645: reward = -8.30, steps = 37 00:44:49 [INFO] train episode 10646: reward = -43.28, steps = 54 00:44:49 [INFO] train episode 10647: reward = -11.84, steps = 36 00:44:49 [INFO] train episode 10648: reward = -48.05, steps = 27 00:44:49 [INFO] train episode 10649: reward = -5.32, steps = 39 00:44:50 [INFO] train episode 10650: reward = -25.13, steps = 39 00:44:50 [INFO] train episode 10651: reward = 1.17, steps = 41 00:44:50 [INFO] train episode 10652: reward = -25.88, steps = 21 00:44:50 [INFO] train episode 10653: reward = -12.24, steps = 34 00:44:51 [INFO] train episode 10654: reward = 0.26, steps = 37 00:44:51 [INFO] train episode 10655: reward = -15.85, steps = 40 00:44:51 [INFO] train episode 10656: reward = -4.58, steps = 38 00:44:51 [INFO] train episode 10657: reward = 3.43, steps = 40 00:44:51 [INFO] train episode 10658: reward = -42.39, steps = 21 00:44:52 [INFO] train episode 10659: reward = -32.49, steps = 32 00:44:52 [INFO] train episode 10660: reward = -26.91, steps = 21 00:44:52 [INFO] train episode 10661: reward = -17.67, steps = 31 00:44:52 [INFO] train episode 10662: reward = -19.99, steps = 40 00:44:53 [INFO] train episode 10663: reward = -25.65, steps = 41 00:44:53 [INFO] train episode 10664: reward = -19.56, steps = 31 00:44:53 [INFO] train episode 10665: reward = -38.30, steps = 24 00:44:53 [INFO] train episode 10666: reward = -31.29, steps = 22 00:44:54 [INFO] train episode 10667: reward = -0.74, steps = 50 00:44:54 [INFO] train episode 10668: reward = -9.66, steps = 31 00:44:54 [INFO] train episode 10669: reward = -2.53, steps = 55 00:44:54 [INFO] train episode 10670: reward = -9.98, steps = 38 00:44:55 [INFO] train episode 10671: reward = -13.52, steps = 52 00:44:55 [INFO] train episode 10672: reward = -21.40, steps = 66 00:44:56 [INFO] train episode 10673: reward = -33.24, steps = 26 00:44:56 [INFO] train episode 10674: reward = -16.42, steps = 53 00:44:56 [INFO] train episode 10675: reward = 6.09, steps = 38 00:44:56 [INFO] train episode 10676: reward = -12.69, steps = 36 00:44:57 [INFO] train episode 10677: reward = 3.40, steps = 60 00:44:57 [INFO] train episode 10678: reward = -22.37, steps = 27 00:44:57 [INFO] train episode 10679: reward = -4.67, steps = 35 00:44:58 [INFO] train episode 10680: reward = 6.80, steps = 53 00:44:58 [INFO] train episode 10681: reward = -0.48, steps = 69 00:44:58 [INFO] train episode 10682: reward = -16.51, steps = 30 00:44:59 [INFO] train episode 10683: reward = 1.64, steps = 36 00:44:59 [INFO] train episode 10684: reward = -46.74, steps = 19 00:44:59 [INFO] train episode 10685: reward = -3.72, steps = 65 00:44:59 [INFO] train episode 10686: reward = -13.90, steps = 31 00:45:00 [INFO] train episode 10687: reward = -25.03, steps = 28 00:45:00 [INFO] train episode 10688: reward = -12.54, steps = 34 00:45:00 [INFO] train episode 10689: reward = -22.28, steps = 21 00:45:00 [INFO] train episode 10690: reward = -5.97, steps = 34 00:45:01 [INFO] train episode 10691: reward = 16.60, steps = 43 00:45:01 [INFO] train episode 10692: reward = -27.43, steps = 34 00:45:01 [INFO] train episode 10693: reward = -4.12, steps = 49 00:45:01 [INFO] train episode 10694: reward = -25.94, steps = 22 00:45:02 [INFO] train episode 10695: reward = 0.01, steps = 49 00:45:02 [INFO] train episode 10696: reward = -8.05, steps = 43 00:45:02 [INFO] train episode 10697: reward = -37.18, steps = 28 00:45:02 [INFO] train episode 10698: reward = -6.34, steps = 37 00:45:03 [INFO] train episode 10699: reward = -7.03, steps = 38 00:45:03 [INFO] train episode 10700: reward = 10.44, steps = 59 00:45:03 [INFO] train episode 10701: reward = -6.71, steps = 57 00:45:04 [INFO] train episode 10702: reward = -9.67, steps = 34 00:45:04 [INFO] train episode 10703: reward = -13.06, steps = 36 00:45:04 [INFO] train episode 10704: reward = -19.61, steps = 30 00:45:04 [INFO] train episode 10705: reward = -12.29, steps = 43 00:45:05 [INFO] train episode 10706: reward = -4.48, steps = 36 00:45:05 [INFO] train episode 10707: reward = -19.98, steps = 28 00:45:05 [INFO] train episode 10708: reward = -0.71, steps = 37 00:45:05 [INFO] train episode 10709: reward = -9.98, steps = 34 00:45:06 [INFO] train episode 10710: reward = -14.23, steps = 34 00:45:06 [INFO] train episode 10711: reward = -15.86, steps = 27 00:45:06 [INFO] train episode 10712: reward = -12.50, steps = 36 00:45:06 [INFO] train episode 10713: reward = -16.37, steps = 35 00:45:07 [INFO] train episode 10714: reward = -50.79, steps = 49 00:45:07 [INFO] train episode 10715: reward = -1.94, steps = 36 00:45:07 [INFO] train episode 10716: reward = -19.11, steps = 35 00:45:07 [INFO] train episode 10717: reward = -1.64, steps = 38 00:45:08 [INFO] train episode 10718: reward = -10.85, steps = 33 00:45:08 [INFO] train episode 10719: reward = 5.98, steps = 48 00:45:08 [INFO] train episode 10720: reward = 4.27, steps = 55 00:45:09 [INFO] train episode 10721: reward = 9.25, steps = 53 00:45:09 [INFO] train episode 10722: reward = -19.93, steps = 33 00:45:10 [INFO] train episode 10723: reward = 15.24, steps = 59 00:45:10 [INFO] train episode 10724: reward = -35.57, steps = 20 00:45:10 [INFO] train episode 10725: reward = -9.48, steps = 35 00:45:10 [INFO] train episode 10726: reward = -0.76, steps = 51 00:45:11 [INFO] train episode 10727: reward = -19.69, steps = 29 00:45:11 [INFO] train episode 10728: reward = -4.10, steps = 37 00:45:11 [INFO] train episode 10729: reward = 10.97, steps = 64 00:45:12 [INFO] train episode 10730: reward = 3.48, steps = 44 00:45:12 [INFO] train episode 10731: reward = -11.66, steps = 65 00:45:12 [INFO] train episode 10732: reward = -21.58, steps = 45 00:45:12 [INFO] train episode 10733: reward = -57.41, steps = 16 00:45:13 [INFO] train episode 10734: reward = -0.84, steps = 32 00:45:13 [INFO] train episode 10735: reward = -32.92, steps = 22 00:45:13 [INFO] train episode 10736: reward = 5.62, steps = 38 00:45:13 [INFO] train episode 10737: reward = -4.26, steps = 41 00:45:14 [INFO] train episode 10738: reward = 10.31, steps = 58 00:45:14 [INFO] train episode 10739: reward = -22.74, steps = 36 00:45:14 [INFO] train episode 10740: reward = 4.78, steps = 48 00:45:15 [INFO] train episode 10741: reward = 0.06, steps = 40 00:45:15 [INFO] train episode 10742: reward = -4.99, steps = 38 00:45:15 [INFO] train episode 10743: reward = 1.94, steps = 34 00:45:15 [INFO] train episode 10744: reward = -19.55, steps = 28 00:45:16 [INFO] train episode 10745: reward = 0.32, steps = 43 00:45:16 [INFO] train episode 10746: reward = 4.26, steps = 46 00:45:16 [INFO] train episode 10747: reward = 0.32, steps = 38 00:45:16 [INFO] train episode 10748: reward = 4.12, steps = 36 00:45:17 [INFO] train episode 10749: reward = -23.66, steps = 22 00:45:17 [INFO] train episode 10750: reward = -30.00, steps = 24 00:45:17 [INFO] train episode 10751: reward = -12.74, steps = 36 00:45:17 [INFO] train episode 10752: reward = -5.34, steps = 40 00:45:17 [INFO] train episode 10753: reward = -20.69, steps = 26 00:45:18 [INFO] train episode 10754: reward = 16.79, steps = 43 00:45:18 [INFO] train episode 10755: reward = -10.31, steps = 37 00:45:18 [INFO] train episode 10756: reward = -10.86, steps = 35 00:45:19 [INFO] train episode 10757: reward = -1.66, steps = 38 00:45:19 [INFO] train episode 10758: reward = -6.77, steps = 45 00:45:19 [INFO] train episode 10759: reward = -4.89, steps = 39 00:45:19 [INFO] train episode 10760: reward = 0.36, steps = 34 00:45:20 [INFO] train episode 10761: reward = -11.97, steps = 34 00:45:20 [INFO] train episode 10762: reward = -3.58, steps = 41 00:45:20 [INFO] train episode 10763: reward = -6.66, steps = 37 00:45:20 [INFO] train episode 10764: reward = -12.09, steps = 36 00:45:21 [INFO] train episode 10765: reward = 1.17, steps = 47 00:45:21 [INFO] train episode 10766: reward = 9.29, steps = 45 00:45:21 [INFO] train episode 10767: reward = -13.82, steps = 29 00:45:21 [INFO] train episode 10768: reward = -30.79, steps = 22 00:45:22 [INFO] train episode 10769: reward = -6.87, steps = 44 00:45:22 [INFO] train episode 10770: reward = 2.88, steps = 37 00:45:22 [INFO] train episode 10771: reward = -1.43, steps = 56 00:45:22 [INFO] train episode 10772: reward = -31.17, steps = 22 00:45:23 [INFO] train episode 10773: reward = 3.10, steps = 40 00:45:23 [INFO] train episode 10774: reward = -12.22, steps = 52 00:45:23 [INFO] train episode 10775: reward = -55.19, steps = 20 00:45:24 [INFO] train episode 10776: reward = -66.91, steps = 85 00:45:24 [INFO] train episode 10777: reward = 6.40, steps = 47 00:45:25 [INFO] train episode 10778: reward = -17.70, steps = 33 00:45:25 [INFO] train episode 10779: reward = -2.33, steps = 44 00:45:25 [INFO] train episode 10780: reward = -11.20, steps = 36 00:45:25 [INFO] train episode 10781: reward = -6.17, steps = 49 00:45:26 [INFO] train episode 10782: reward = -28.64, steps = 25 00:45:26 [INFO] train episode 10783: reward = -28.64, steps = 18 00:45:26 [INFO] train episode 10784: reward = -1.24, steps = 42 00:45:26 [INFO] train episode 10785: reward = -7.58, steps = 36 00:45:27 [INFO] train episode 10786: reward = -0.26, steps = 38 00:45:27 [INFO] train episode 10787: reward = -25.88, steps = 39 00:45:27 [INFO] train episode 10788: reward = -25.56, steps = 33 00:45:27 [INFO] train episode 10789: reward = -4.11, steps = 36 00:45:28 [INFO] train episode 10790: reward = 12.99, steps = 41 00:45:28 [INFO] train episode 10791: reward = -6.01, steps = 30 00:45:28 [INFO] train episode 10792: reward = 2.10, steps = 41 00:45:28 [INFO] train episode 10793: reward = -6.46, steps = 50 00:45:29 [INFO] train episode 10794: reward = 2.51, steps = 40 00:45:29 [INFO] train episode 10795: reward = 0.48, steps = 35 00:45:29 [INFO] train episode 10796: reward = -14.53, steps = 31 00:45:29 [INFO] train episode 10797: reward = 2.24, steps = 42 00:45:30 [INFO] train episode 10798: reward = -0.63, steps = 41 00:45:30 [INFO] train episode 10799: reward = -36.44, steps = 19 00:45:30 [INFO] train episode 10800: reward = -10.25, steps = 37 00:45:30 [INFO] train episode 10801: reward = -38.13, steps = 17 00:45:31 [INFO] train episode 10802: reward = 13.72, steps = 84 00:45:31 [INFO] train episode 10803: reward = -26.91, steps = 40 00:45:31 [INFO] train episode 10804: reward = 5.68, steps = 46 00:45:31 [INFO] train episode 10805: reward = -36.84, steps = 22 00:45:32 [INFO] train episode 10806: reward = -0.67, steps = 30 00:45:32 [INFO] train episode 10807: reward = -26.13, steps = 33 00:45:32 [INFO] train episode 10808: reward = -23.16, steps = 32 00:45:32 [INFO] train episode 10809: reward = 19.86, steps = 48 00:45:33 [INFO] train episode 10810: reward = -28.30, steps = 22 00:45:33 [INFO] train episode 10811: reward = -2.55, steps = 33 00:45:33 [INFO] train episode 10812: reward = 24.77, steps = 45 00:45:33 [INFO] train episode 10813: reward = -18.35, steps = 40 00:45:34 [INFO] train episode 10814: reward = -7.61, steps = 39 00:45:34 [INFO] train episode 10815: reward = -9.48, steps = 54 00:45:34 [INFO] train episode 10816: reward = -30.53, steps = 31 00:45:35 [INFO] train episode 10817: reward = 3.63, steps = 50 00:45:35 [INFO] train episode 10818: reward = -19.58, steps = 56 00:45:35 [INFO] train episode 10819: reward = -27.84, steps = 22 00:45:35 [INFO] train episode 10820: reward = 4.87, steps = 41 00:45:36 [INFO] train episode 10821: reward = -5.72, steps = 33 00:45:36 [INFO] train episode 10822: reward = -5.38, steps = 33 00:45:36 [INFO] train episode 10823: reward = 0.49, steps = 32 00:45:36 [INFO] train episode 10824: reward = -14.10, steps = 28 00:45:37 [INFO] train episode 10825: reward = 5.26, steps = 41 00:45:37 [INFO] train episode 10826: reward = -14.20, steps = 27 00:45:37 [INFO] train episode 10827: reward = 1.43, steps = 46 00:45:38 [INFO] train episode 10828: reward = 6.72, steps = 42 00:45:38 [INFO] train episode 10829: reward = -1.41, steps = 44 00:45:38 [INFO] train episode 10830: reward = -20.92, steps = 23 00:45:38 [INFO] train episode 10831: reward = -8.58, steps = 35 00:45:38 [INFO] train episode 10832: reward = -26.31, steps = 24 00:45:39 [INFO] train episode 10833: reward = -3.20, steps = 45 00:45:39 [INFO] train episode 10834: reward = -4.32, steps = 33 00:45:39 [INFO] train episode 10835: reward = 7.44, steps = 39 00:45:39 [INFO] train episode 10836: reward = -5.90, steps = 37 00:45:40 [INFO] train episode 10837: reward = -21.66, steps = 51 00:45:40 [INFO] train episode 10838: reward = -29.25, steps = 22 00:45:40 [INFO] train episode 10839: reward = -21.68, steps = 34 00:45:41 [INFO] train episode 10840: reward = 0.91, steps = 41 00:45:41 [INFO] train episode 10841: reward = -8.70, steps = 30 00:45:41 [INFO] train episode 10842: reward = -29.77, steps = 26 00:45:41 [INFO] train episode 10843: reward = -3.76, steps = 38 00:45:41 [INFO] train episode 10844: reward = -15.24, steps = 28 00:45:42 [INFO] train episode 10845: reward = -6.49, steps = 32 00:45:42 [INFO] train episode 10846: reward = -12.57, steps = 32 00:45:42 [INFO] train episode 10847: reward = -10.99, steps = 35 00:45:42 [INFO] train episode 10848: reward = 3.53, steps = 39 00:45:43 [INFO] train episode 10849: reward = -17.14, steps = 31 00:45:43 [INFO] train episode 10850: reward = -0.93, steps = 34 00:45:43 [INFO] train episode 10851: reward = 9.86, steps = 46 00:45:43 [INFO] train episode 10852: reward = -8.07, steps = 35 00:45:44 [INFO] train episode 10853: reward = 2.87, steps = 46 00:45:44 [INFO] train episode 10854: reward = -8.48, steps = 33 00:45:44 [INFO] train episode 10855: reward = -14.07, steps = 95 00:45:45 [INFO] train episode 10856: reward = 4.76, steps = 58 00:45:45 [INFO] train episode 10857: reward = -9.49, steps = 52 00:45:45 [INFO] train episode 10858: reward = 1.16, steps = 41 00:45:46 [INFO] train episode 10859: reward = 6.02, steps = 42 00:45:46 [INFO] train episode 10860: reward = -1.10, steps = 49 00:45:46 [INFO] train episode 10861: reward = 3.45, steps = 38 00:45:46 [INFO] train episode 10862: reward = -26.79, steps = 21 00:45:47 [INFO] train episode 10863: reward = 12.25, steps = 53 00:45:47 [INFO] train episode 10864: reward = 2.75, steps = 38 00:45:47 [INFO] train episode 10865: reward = 0.81, steps = 42 00:45:48 [INFO] train episode 10866: reward = 2.15, steps = 38 00:45:48 [INFO] train episode 10867: reward = 10.72, steps = 37 00:45:48 [INFO] train episode 10868: reward = 1.90, steps = 39 00:45:48 [INFO] train episode 10869: reward = 12.12, steps = 45 00:45:49 [INFO] train episode 10870: reward = -7.83, steps = 37 00:45:49 [INFO] train episode 10871: reward = 6.37, steps = 39 00:45:49 [INFO] train episode 10872: reward = -18.90, steps = 24 00:45:50 [INFO] train episode 10873: reward = 21.74, steps = 47 00:45:50 [INFO] train episode 10874: reward = -2.60, steps = 39 00:45:50 [INFO] train episode 10875: reward = -2.69, steps = 42 00:45:50 [INFO] train episode 10876: reward = -9.81, steps = 47 00:45:51 [INFO] train episode 10877: reward = 13.15, steps = 71 00:45:51 [INFO] train episode 10878: reward = -28.53, steps = 25 00:45:51 [INFO] train episode 10879: reward = 3.21, steps = 43 00:45:52 [INFO] train episode 10880: reward = -17.88, steps = 47 00:45:52 [INFO] train episode 10881: reward = -5.59, steps = 32 00:45:52 [INFO] train episode 10882: reward = -9.82, steps = 34 00:45:52 [INFO] train episode 10883: reward = -16.04, steps = 28 00:45:53 [INFO] train episode 10884: reward = 8.10, steps = 44 00:45:53 [INFO] train episode 10885: reward = -2.66, steps = 34 00:45:53 [INFO] train episode 10886: reward = 7.01, steps = 35 00:45:53 [INFO] train episode 10887: reward = -12.49, steps = 30 00:45:54 [INFO] train episode 10888: reward = -8.90, steps = 43 00:45:54 [INFO] train episode 10889: reward = 1.62, steps = 33 00:45:54 [INFO] train episode 10890: reward = -0.26, steps = 38 00:45:55 [INFO] train episode 10891: reward = 9.56, steps = 44 00:45:55 [INFO] train episode 10892: reward = -3.59, steps = 54 00:45:55 [INFO] train episode 10893: reward = -8.42, steps = 31 00:45:55 [INFO] train episode 10894: reward = 3.60, steps = 34 00:45:56 [INFO] train episode 10895: reward = 0.02, steps = 33 00:45:56 [INFO] train episode 10896: reward = 4.19, steps = 44 00:45:56 [INFO] train episode 10897: reward = -0.22, steps = 44 00:45:56 [INFO] train episode 10898: reward = 1.01, steps = 36 00:45:57 [INFO] train episode 10899: reward = -3.12, steps = 41 00:45:57 [INFO] train episode 10900: reward = 4.75, steps = 46 00:45:57 [INFO] train episode 10901: reward = 10.73, steps = 39 00:45:58 [INFO] train episode 10902: reward = -6.20, steps = 54 00:45:58 [INFO] train episode 10903: reward = 17.57, steps = 48 00:45:58 [INFO] train episode 10904: reward = -22.86, steps = 26 00:45:58 [INFO] train episode 10905: reward = 14.01, steps = 44 00:45:59 [INFO] train episode 10906: reward = 9.66, steps = 44 00:45:59 [INFO] train episode 10907: reward = -4.20, steps = 38 00:45:59 [INFO] train episode 10908: reward = -56.52, steps = 17 00:45:59 [INFO] train episode 10909: reward = -14.67, steps = 37 00:46:00 [INFO] train episode 10910: reward = -18.42, steps = 27 00:46:00 [INFO] train episode 10911: reward = 11.05, steps = 45 00:46:00 [INFO] train episode 10912: reward = 9.40, steps = 40 00:46:01 [INFO] train episode 10913: reward = -14.40, steps = 38 00:46:01 [INFO] train episode 10914: reward = -8.10, steps = 33 00:46:01 [INFO] train episode 10915: reward = 1.69, steps = 37 00:46:01 [INFO] train episode 10916: reward = 12.04, steps = 41 00:46:02 [INFO] train episode 10917: reward = 5.90, steps = 40 00:46:02 [INFO] train episode 10918: reward = -10.19, steps = 38 00:46:02 [INFO] train episode 10919: reward = -8.77, steps = 34 00:46:02 [INFO] train episode 10920: reward = -17.22, steps = 40 00:46:03 [INFO] train episode 10921: reward = -1.12, steps = 34 00:46:03 [INFO] train episode 10922: reward = -19.53, steps = 28 00:46:03 [INFO] train episode 10923: reward = 9.54, steps = 41 00:46:03 [INFO] train episode 10924: reward = 2.75, steps = 38 00:46:03 [INFO] train episode 10925: reward = -10.51, steps = 24 00:46:04 [INFO] train episode 10926: reward = -28.64, steps = 37 00:46:04 [INFO] train episode 10927: reward = -19.00, steps = 22 00:46:04 [INFO] train episode 10928: reward = -22.70, steps = 45 00:46:04 [INFO] train episode 10929: reward = -5.63, steps = 30 00:46:05 [INFO] train episode 10930: reward = 6.16, steps = 48 00:46:05 [INFO] train episode 10931: reward = -0.27, steps = 36 00:46:06 [INFO] train episode 10932: reward = 9.25, steps = 58 00:46:06 [INFO] train episode 10933: reward = 1.35, steps = 33 00:46:06 [INFO] train episode 10934: reward = -1.28, steps = 39 00:46:06 [INFO] train episode 10935: reward = -5.73, steps = 30 00:46:07 [INFO] train episode 10936: reward = 8.89, steps = 41 00:46:07 [INFO] train episode 10937: reward = -0.88, steps = 38 00:46:07 [INFO] train episode 10938: reward = -10.73, steps = 35 00:46:07 [INFO] train episode 10939: reward = 9.61, steps = 48 00:46:08 [INFO] train episode 10940: reward = 14.98, steps = 48 00:46:08 [INFO] train episode 10941: reward = 8.63, steps = 44 00:46:08 [INFO] train episode 10942: reward = 8.50, steps = 39 00:46:08 [INFO] train episode 10943: reward = -4.16, steps = 35 00:46:09 [INFO] train episode 10944: reward = 9.30, steps = 39 00:46:09 [INFO] train episode 10945: reward = -25.01, steps = 32 00:46:09 [INFO] train episode 10946: reward = 17.96, steps = 45 00:46:10 [INFO] train episode 10947: reward = 14.73, steps = 42 00:46:10 [INFO] train episode 10948: reward = -4.47, steps = 40 00:46:10 [INFO] train episode 10949: reward = -3.97, steps = 43 00:46:10 [INFO] train episode 10950: reward = 10.52, steps = 53 00:46:11 [INFO] train episode 10951: reward = 1.00, steps = 40 00:46:11 [INFO] train episode 10952: reward = 6.89, steps = 45 00:46:11 [INFO] train episode 10953: reward = 11.88, steps = 45 00:46:12 [INFO] train episode 10954: reward = 2.59, steps = 37 00:46:12 [INFO] train episode 10955: reward = 14.48, steps = 47 00:46:12 [INFO] train episode 10956: reward = -2.04, steps = 38 00:46:12 [INFO] train episode 10957: reward = -25.26, steps = 23 00:46:13 [INFO] train episode 10958: reward = -10.52, steps = 36 00:46:13 [INFO] train episode 10959: reward = 2.99, steps = 53 00:46:13 [INFO] train episode 10960: reward = 2.54, steps = 44 00:46:13 [INFO] train episode 10961: reward = -15.42, steps = 29 00:46:14 [INFO] train episode 10962: reward = -4.81, steps = 39 00:46:14 [INFO] train episode 10963: reward = 2.52, steps = 31 00:46:14 [INFO] train episode 10964: reward = -1.15, steps = 33 00:46:14 [INFO] train episode 10965: reward = 8.18, steps = 43 00:46:15 [INFO] train episode 10966: reward = -10.29, steps = 35 00:46:15 [INFO] train episode 10967: reward = -15.48, steps = 39 00:46:15 [INFO] train episode 10968: reward = 19.41, steps = 47 00:46:15 [INFO] train episode 10969: reward = -7.54, steps = 32 00:46:16 [INFO] train episode 10970: reward = 6.70, steps = 41 00:46:16 [INFO] train episode 10971: reward = 7.67, steps = 40 00:46:16 [INFO] train episode 10972: reward = -9.92, steps = 37 00:46:17 [INFO] train episode 10973: reward = 3.93, steps = 51 00:46:17 [INFO] train episode 10974: reward = -0.36, steps = 42 00:46:17 [INFO] train episode 10975: reward = -10.52, steps = 30 00:46:17 [INFO] train episode 10976: reward = 7.61, steps = 46 00:46:18 [INFO] train episode 10977: reward = -10.97, steps = 39 00:46:18 [INFO] train episode 10978: reward = -7.18, steps = 31 00:46:18 [INFO] train episode 10979: reward = 1.96, steps = 39 00:46:19 [INFO] train episode 10980: reward = -15.70, steps = 39 00:46:19 [INFO] train episode 10981: reward = -2.34, steps = 34 00:46:19 [INFO] train episode 10982: reward = -17.47, steps = 21 00:46:19 [INFO] train episode 10983: reward = -13.85, steps = 31 00:46:20 [INFO] train episode 10984: reward = 1.39, steps = 51 00:46:20 [INFO] train episode 10985: reward = -0.74, steps = 39 00:46:20 [INFO] train episode 10986: reward = 3.45, steps = 38 00:46:20 [INFO] train episode 10987: reward = -7.32, steps = 36 00:46:21 [INFO] train episode 10988: reward = 9.37, steps = 41 00:46:21 [INFO] train episode 10989: reward = 4.47, steps = 48 00:46:21 [INFO] train episode 10990: reward = -10.09, steps = 41 00:46:21 [INFO] train episode 10991: reward = -13.24, steps = 33 00:46:22 [INFO] train episode 10992: reward = -20.60, steps = 24 00:46:22 [INFO] train episode 10993: reward = -5.21, steps = 39 00:46:22 [INFO] train episode 10994: reward = -7.75, steps = 33 00:46:22 [INFO] train episode 10995: reward = 18.31, steps = 47 00:46:23 [INFO] train episode 10996: reward = -27.45, steps = 43 00:46:23 [INFO] train episode 10997: reward = -16.89, steps = 31 00:46:23 [INFO] train episode 10998: reward = 5.14, steps = 38 00:46:23 [INFO] train episode 10999: reward = -7.62, steps = 35 00:46:24 [INFO] train episode 11000: reward = -33.67, steps = 45 00:46:24 [INFO] train episode 11001: reward = 16.26, steps = 46 00:46:24 [INFO] train episode 11002: reward = -16.88, steps = 24 00:46:24 [INFO] train episode 11003: reward = 6.07, steps = 42 00:46:25 [INFO] train episode 11004: reward = -7.56, steps = 40 00:46:25 [INFO] train episode 11005: reward = 2.65, steps = 42 00:46:25 [INFO] train episode 11006: reward = 18.02, steps = 41 00:46:26 [INFO] train episode 11007: reward = 8.69, steps = 41 00:46:26 [INFO] train episode 11008: reward = -7.64, steps = 33 00:46:26 [INFO] train episode 11009: reward = 9.34, steps = 50 00:46:26 [INFO] train episode 11010: reward = 13.49, steps = 36 00:46:27 [INFO] train episode 11011: reward = -2.26, steps = 33 00:46:27 [INFO] train episode 11012: reward = 4.75, steps = 45 00:46:27 [INFO] train episode 11013: reward = 0.27, steps = 44 00:46:27 [INFO] train episode 11014: reward = 7.53, steps = 47 00:46:28 [INFO] train episode 11015: reward = 2.48, steps = 40 00:46:28 [INFO] train episode 11016: reward = 13.93, steps = 42 00:46:28 [INFO] train episode 11017: reward = -24.26, steps = 24 00:46:28 [INFO] train episode 11018: reward = 16.00, steps = 42 00:46:29 [INFO] train episode 11019: reward = -4.50, steps = 32 00:46:29 [INFO] train episode 11020: reward = 8.92, steps = 41 00:46:29 [INFO] train episode 11021: reward = 2.46, steps = 40 00:46:29 [INFO] train episode 11022: reward = -11.18, steps = 37 00:46:30 [INFO] train episode 11023: reward = -5.98, steps = 28 00:46:30 [INFO] train episode 11024: reward = -11.12, steps = 37 00:46:30 [INFO] train episode 11025: reward = -0.59, steps = 52 00:46:31 [INFO] train episode 11026: reward = 3.78, steps = 46 00:46:31 [INFO] train episode 11027: reward = -26.47, steps = 40 00:46:31 [INFO] train episode 11028: reward = -9.57, steps = 35 00:46:31 [INFO] train episode 11029: reward = 2.01, steps = 37 00:46:32 [INFO] train episode 11030: reward = 4.24, steps = 47 00:46:32 [INFO] train episode 11031: reward = 10.32, steps = 56 00:46:32 [INFO] train episode 11032: reward = -37.40, steps = 17 00:46:33 [INFO] train episode 11033: reward = 3.08, steps = 37 00:46:33 [INFO] train episode 11034: reward = 0.49, steps = 42 00:46:33 [INFO] train episode 11035: reward = -11.89, steps = 30 00:46:33 [INFO] train episode 11036: reward = 6.86, steps = 36 00:46:34 [INFO] train episode 11037: reward = 3.13, steps = 45 00:46:34 [INFO] train episode 11038: reward = -19.60, steps = 38 00:46:34 [INFO] train episode 11039: reward = 5.05, steps = 53 00:46:34 [INFO] train episode 11040: reward = -18.36, steps = 41 00:46:35 [INFO] train episode 11041: reward = 3.99, steps = 49 00:46:35 [INFO] train episode 11042: reward = 1.55, steps = 38 00:46:35 [INFO] train episode 11043: reward = -16.94, steps = 25 00:46:36 [INFO] train episode 11044: reward = 10.58, steps = 45 00:46:36 [INFO] train episode 11045: reward = -4.53, steps = 34 00:46:36 [INFO] train episode 11046: reward = -11.20, steps = 30 00:46:36 [INFO] train episode 11047: reward = 23.46, steps = 59 00:46:37 [INFO] train episode 11048: reward = -21.95, steps = 29 00:46:37 [INFO] train episode 11049: reward = -1.65, steps = 34 00:46:37 [INFO] train episode 11050: reward = -8.77, steps = 34 00:46:37 [INFO] train episode 11051: reward = 4.12, steps = 38 00:46:38 [INFO] train episode 11052: reward = 3.14, steps = 41 00:46:38 [INFO] train episode 11053: reward = 12.59, steps = 37 00:46:38 [INFO] train episode 11054: reward = 8.10, steps = 36 00:46:38 [INFO] train episode 11055: reward = -8.27, steps = 41 00:46:39 [INFO] train episode 11056: reward = -8.07, steps = 31 00:46:39 [INFO] train episode 11057: reward = 11.32, steps = 58 00:46:39 [INFO] train episode 11058: reward = 16.12, steps = 57 00:46:40 [INFO] train episode 11059: reward = 1.43, steps = 40 00:46:40 [INFO] train episode 11060: reward = -18.84, steps = 25 00:46:40 [INFO] train episode 11061: reward = -3.75, steps = 35 00:46:40 [INFO] train episode 11062: reward = 4.58, steps = 44 00:46:41 [INFO] train episode 11063: reward = -4.32, steps = 37 00:46:41 [INFO] train episode 11064: reward = 12.14, steps = 39 00:46:41 [INFO] train episode 11065: reward = -5.80, steps = 45 00:46:41 [INFO] train episode 11066: reward = -7.31, steps = 40 00:46:42 [INFO] train episode 11067: reward = -22.11, steps = 28 00:46:42 [INFO] train episode 11068: reward = 0.26, steps = 38 00:46:42 [INFO] train episode 11069: reward = 17.92, steps = 56 00:46:42 [INFO] train episode 11070: reward = 0.32, steps = 38 00:46:43 [INFO] train episode 11071: reward = -3.26, steps = 39 00:46:43 [INFO] train episode 11072: reward = 8.11, steps = 49 00:46:43 [INFO] train episode 11073: reward = 12.95, steps = 44 00:46:44 [INFO] train episode 11074: reward = 19.91, steps = 51 00:46:44 [INFO] train episode 11075: reward = -21.36, steps = 24 00:46:44 [INFO] train episode 11076: reward = 7.20, steps = 34 00:46:44 [INFO] train episode 11077: reward = 6.00, steps = 41 00:46:45 [INFO] train episode 11078: reward = -6.13, steps = 33 00:46:45 [INFO] train episode 11079: reward = 1.82, steps = 31 00:46:45 [INFO] train episode 11080: reward = 0.70, steps = 38 00:46:45 [INFO] train episode 11081: reward = -5.18, steps = 37 00:46:46 [INFO] train episode 11082: reward = 5.93, steps = 47 00:46:46 [INFO] train episode 11083: reward = -9.06, steps = 33 00:46:46 [INFO] train episode 11084: reward = -21.12, steps = 34 00:46:47 [INFO] train episode 11085: reward = -0.93, steps = 38 00:46:47 [INFO] train episode 11086: reward = 9.20, steps = 47 00:46:47 [INFO] train episode 11087: reward = 11.59, steps = 39 00:46:47 [INFO] train episode 11088: reward = 10.61, steps = 42 00:46:48 [INFO] train episode 11089: reward = 2.90, steps = 31 00:46:48 [INFO] train episode 11090: reward = -12.65, steps = 31 00:46:48 [INFO] train episode 11091: reward = 7.35, steps = 41 00:46:48 [INFO] train episode 11092: reward = -8.72, steps = 31 00:46:49 [INFO] train episode 11093: reward = -30.48, steps = 17 00:46:49 [INFO] train episode 11094: reward = -16.04, steps = 38 00:46:49 [INFO] train episode 11095: reward = 4.47, steps = 39 00:46:49 [INFO] train episode 11096: reward = -2.40, steps = 41 00:46:50 [INFO] train episode 11097: reward = -12.16, steps = 39 00:46:50 [INFO] train episode 11098: reward = 4.82, steps = 37 00:46:50 [INFO] train episode 11099: reward = 23.07, steps = 50 00:46:51 [INFO] train episode 11100: reward = -7.50, steps = 40 00:46:51 [INFO] train episode 11101: reward = 11.50, steps = 52 00:46:51 [INFO] train episode 11102: reward = -3.76, steps = 34 00:46:51 [INFO] train episode 11103: reward = -8.31, steps = 35 00:46:51 [INFO] train episode 11104: reward = -9.71, steps = 26 00:46:52 [INFO] train episode 11105: reward = 6.53, steps = 46 00:46:52 [INFO] train episode 11106: reward = -4.39, steps = 34 00:46:52 [INFO] train episode 11107: reward = -16.66, steps = 21 00:46:52 [INFO] train episode 11108: reward = 7.05, steps = 43 00:46:53 [INFO] train episode 11109: reward = 12.79, steps = 53 00:46:53 [INFO] train episode 11110: reward = 7.28, steps = 35 00:46:53 [INFO] train episode 11111: reward = -16.99, steps = 30 00:46:54 [INFO] train episode 11112: reward = -2.79, steps = 60 00:46:54 [INFO] train episode 11113: reward = -9.08, steps = 38 00:46:54 [INFO] train episode 11114: reward = 8.48, steps = 41 00:46:54 [INFO] train episode 11115: reward = -27.30, steps = 38 00:46:55 [INFO] train episode 11116: reward = 5.01, steps = 43 00:46:55 [INFO] train episode 11117: reward = -4.31, steps = 32 00:46:55 [INFO] train episode 11118: reward = -14.97, steps = 42 00:46:55 [INFO] train episode 11119: reward = -16.00, steps = 39 00:46:56 [INFO] train episode 11120: reward = -5.50, steps = 35 00:46:56 [INFO] train episode 11121: reward = 0.64, steps = 35 00:46:56 [INFO] train episode 11122: reward = -1.57, steps = 41 00:46:57 [INFO] train episode 11123: reward = 15.76, steps = 43 00:46:57 [INFO] train episode 11124: reward = -2.00, steps = 34 00:46:57 [INFO] train episode 11125: reward = -2.04, steps = 41 00:46:57 [INFO] train episode 11126: reward = 10.24, steps = 45 00:46:58 [INFO] train episode 11127: reward = 2.63, steps = 42 00:46:58 [INFO] train episode 11128: reward = 12.37, steps = 46 00:46:58 [INFO] train episode 11129: reward = -0.43, steps = 31 00:46:58 [INFO] train episode 11130: reward = 0.95, steps = 42 00:46:59 [INFO] train episode 11131: reward = 0.95, steps = 37 00:46:59 [INFO] train episode 11132: reward = 19.75, steps = 46 00:47:00 [INFO] train episode 11133: reward = 23.68, steps = 50 00:47:00 [INFO] train episode 11134: reward = 11.24, steps = 35 00:47:00 [INFO] train episode 11135: reward = -8.41, steps = 31 00:47:00 [INFO] train episode 11136: reward = 11.18, steps = 39 00:47:01 [INFO] train episode 11137: reward = 4.44, steps = 47 00:47:01 [INFO] train episode 11138: reward = 12.56, steps = 52 00:47:01 [INFO] train episode 11139: reward = 0.87, steps = 36 00:47:01 [INFO] train episode 11140: reward = 12.33, steps = 40 00:47:02 [INFO] train episode 11141: reward = -23.66, steps = 69 00:47:02 [INFO] train episode 11142: reward = 16.39, steps = 48 00:47:03 [INFO] train episode 11143: reward = 10.14, steps = 42 00:47:03 [INFO] train episode 11144: reward = -0.23, steps = 31 00:47:03 [INFO] train episode 11145: reward = 11.02, steps = 39 00:47:03 [INFO] train episode 11146: reward = -10.69, steps = 39 00:47:04 [INFO] train episode 11147: reward = 10.08, steps = 50 00:47:04 [INFO] train episode 11148: reward = 8.77, steps = 40 00:47:04 [INFO] train episode 11149: reward = 13.77, steps = 48 00:47:05 [INFO] train episode 11150: reward = 4.02, steps = 45 00:47:05 [INFO] train episode 11151: reward = -16.45, steps = 31 00:47:05 [INFO] train episode 11152: reward = 3.04, steps = 36 00:47:05 [INFO] train episode 11153: reward = -25.82, steps = 23 00:47:06 [INFO] train episode 11154: reward = 17.00, steps = 48 00:47:06 [INFO] train episode 11155: reward = 7.63, steps = 42 00:47:06 [INFO] train episode 11156: reward = -6.31, steps = 41 00:47:06 [INFO] train episode 11157: reward = 6.95, steps = 35 00:47:07 [INFO] train episode 11158: reward = 13.73, steps = 44 00:47:07 [INFO] train episode 11159: reward = -4.16, steps = 37 00:47:07 [INFO] train episode 11160: reward = 3.61, steps = 57 00:47:08 [INFO] train episode 11161: reward = -4.57, steps = 38 00:47:08 [INFO] train episode 11162: reward = -32.76, steps = 22 00:47:08 [INFO] train episode 11163: reward = -10.61, steps = 34 00:47:08 [INFO] train episode 11164: reward = 3.18, steps = 48 00:47:08 [INFO] train episode 11165: reward = 2.35, steps = 39 00:47:09 [INFO] train episode 11166: reward = -0.40, steps = 37 00:47:09 [INFO] train episode 11167: reward = -4.96, steps = 31 00:47:09 [INFO] train episode 11168: reward = -8.32, steps = 40 00:47:09 [INFO] train episode 11169: reward = -0.09, steps = 37 00:47:10 [INFO] train episode 11170: reward = 12.35, steps = 40 00:47:10 [INFO] train episode 11171: reward = -2.03, steps = 37 00:47:10 [INFO] train episode 11172: reward = -4.81, steps = 30 00:47:11 [INFO] train episode 11173: reward = 8.93, steps = 48 00:47:11 [INFO] train episode 11174: reward = -20.23, steps = 33 00:47:11 [INFO] train episode 11175: reward = 5.63, steps = 46 00:47:11 [INFO] train episode 11176: reward = 0.70, steps = 47 00:47:12 [INFO] train episode 11177: reward = 7.72, steps = 55 00:47:12 [INFO] train episode 11178: reward = -10.08, steps = 28 00:47:12 [INFO] train episode 11179: reward = 13.43, steps = 46 00:47:12 [INFO] train episode 11180: reward = 8.57, steps = 44 00:47:13 [INFO] train episode 11181: reward = 1.05, steps = 34 00:47:13 [INFO] train episode 11182: reward = 12.42, steps = 43 00:47:13 [INFO] train episode 11183: reward = 3.08, steps = 42 00:47:14 [INFO] train episode 11184: reward = -2.79, steps = 36 00:47:14 [INFO] train episode 11185: reward = 4.79, steps = 39 00:47:14 [INFO] train episode 11186: reward = 6.39, steps = 40 00:47:15 [INFO] train episode 11187: reward = -18.76, steps = 36 00:47:15 [INFO] train episode 11188: reward = -0.35, steps = 37 00:47:15 [INFO] train episode 11189: reward = -11.72, steps = 32 00:47:15 [INFO] train episode 11190: reward = -7.93, steps = 55 00:47:16 [INFO] train episode 11191: reward = -2.92, steps = 39 00:47:16 [INFO] train episode 11192: reward = -15.77, steps = 28 00:47:16 [INFO] train episode 11193: reward = 11.36, steps = 47 00:47:16 [INFO] train episode 11194: reward = 6.40, steps = 43 00:47:17 [INFO] train episode 11195: reward = 0.35, steps = 40 00:47:17 [INFO] train episode 11196: reward = 2.17, steps = 38 00:47:17 [INFO] train episode 11197: reward = -18.22, steps = 26 00:47:18 [INFO] train episode 11198: reward = -5.94, steps = 67 00:47:18 [INFO] train episode 11199: reward = 18.65, steps = 49 00:47:18 [INFO] train episode 11200: reward = -1.58, steps = 33 00:47:18 [INFO] train episode 11201: reward = 19.84, steps = 46 00:47:19 [INFO] train episode 11202: reward = -29.31, steps = 19 00:47:19 [INFO] train episode 11203: reward = 1.36, steps = 41 00:47:19 [INFO] train episode 11204: reward = -8.16, steps = 32 00:47:19 [INFO] train episode 11205: reward = 17.61, steps = 48 00:47:20 [INFO] train episode 11206: reward = 15.20, steps = 48 00:47:20 [INFO] train episode 11207: reward = 1.75, steps = 57 00:47:20 [INFO] train episode 11208: reward = 3.04, steps = 47 00:47:21 [INFO] train episode 11209: reward = 14.27, steps = 39 00:47:21 [INFO] train episode 11210: reward = -7.46, steps = 34 00:47:21 [INFO] train episode 11211: reward = 9.98, steps = 47 00:47:21 [INFO] train episode 11212: reward = -0.55, steps = 43 00:47:22 [INFO] train episode 11213: reward = -9.45, steps = 35 00:47:22 [INFO] train episode 11214: reward = 1.63, steps = 39 00:47:22 [INFO] train episode 11215: reward = 28.52, steps = 76 00:47:23 [INFO] train episode 11216: reward = 2.35, steps = 41 00:47:23 [INFO] train episode 11217: reward = 12.01, steps = 37 00:47:23 [INFO] train episode 11218: reward = -2.76, steps = 34 00:47:23 [INFO] train episode 11219: reward = 13.91, steps = 43 00:47:24 [INFO] train episode 11220: reward = -5.40, steps = 35 00:47:24 [INFO] train episode 11221: reward = -6.15, steps = 30 00:47:24 [INFO] train episode 11222: reward = 3.96, steps = 50 00:47:25 [INFO] train episode 11223: reward = 1.26, steps = 44 00:47:25 [INFO] train episode 11224: reward = 14.24, steps = 45 00:47:25 [INFO] train episode 11225: reward = -6.75, steps = 55 00:47:26 [INFO] train episode 11226: reward = -1.09, steps = 41 00:47:26 [INFO] train episode 11227: reward = -9.18, steps = 48 00:47:26 [INFO] train episode 11228: reward = -18.00, steps = 41 00:47:27 [INFO] train episode 11229: reward = 8.79, steps = 46 00:47:27 [INFO] train episode 11230: reward = 7.50, steps = 40 00:47:27 [INFO] train episode 11231: reward = 0.14, steps = 46 00:47:27 [INFO] train episode 11232: reward = 3.33, steps = 37 00:47:28 [INFO] train episode 11233: reward = -5.44, steps = 50 00:47:28 [INFO] train episode 11234: reward = 7.98, steps = 57 00:47:28 [INFO] train episode 11235: reward = 3.43, steps = 40 00:47:29 [INFO] train episode 11236: reward = 1.60, steps = 42 00:47:29 [INFO] train episode 11237: reward = 11.88, steps = 37 00:47:29 [INFO] train episode 11238: reward = -1.85, steps = 60 00:47:30 [INFO] train episode 11239: reward = -1.73, steps = 45 00:47:30 [INFO] train episode 11240: reward = 3.41, steps = 30 00:47:30 [INFO] train episode 11241: reward = 8.38, steps = 65 00:47:31 [INFO] train episode 11242: reward = 10.02, steps = 37 00:47:31 [INFO] train episode 11243: reward = -14.97, steps = 66 00:47:31 [INFO] train episode 11244: reward = -14.89, steps = 38 00:47:31 [INFO] train episode 11245: reward = -20.75, steps = 39 00:47:32 [INFO] train episode 11246: reward = 4.46, steps = 59 00:47:32 [INFO] train episode 11247: reward = -3.74, steps = 42 00:47:32 [INFO] train episode 11248: reward = 12.64, steps = 44 00:47:33 [INFO] train episode 11249: reward = 0.06, steps = 42 00:47:33 [INFO] train episode 11250: reward = 17.18, steps = 76 00:47:33 [INFO] train episode 11251: reward = -17.15, steps = 34 00:47:34 [INFO] train episode 11252: reward = -2.24, steps = 39 00:47:34 [INFO] train episode 11253: reward = 7.03, steps = 43 00:47:34 [INFO] train episode 11254: reward = -15.44, steps = 41 00:47:34 [INFO] train episode 11255: reward = 16.19, steps = 44 00:47:35 [INFO] train episode 11256: reward = -14.68, steps = 41 00:47:35 [INFO] train episode 11257: reward = 2.15, steps = 46 00:47:35 [INFO] train episode 11258: reward = 8.77, steps = 42 00:47:36 [INFO] train episode 11259: reward = 16.69, steps = 45 00:47:36 [INFO] train episode 11260: reward = -2.86, steps = 37 00:47:36 [INFO] train episode 11261: reward = 13.30, steps = 42 00:47:36 [INFO] train episode 11262: reward = -25.57, steps = 17 00:47:36 [INFO] train episode 11263: reward = 7.30, steps = 41 00:47:37 [INFO] train episode 11264: reward = 11.38, steps = 42 00:47:37 [INFO] train episode 11265: reward = 17.34, steps = 44 00:47:37 [INFO] train episode 11266: reward = 13.61, steps = 33 00:47:37 [INFO] train episode 11267: reward = 12.27, steps = 34 00:47:38 [INFO] train episode 11268: reward = 8.15, steps = 42 00:47:38 [INFO] train episode 11269: reward = -9.78, steps = 42 00:47:38 [INFO] train episode 11270: reward = 0.47, steps = 45 00:47:39 [INFO] train episode 11271: reward = 11.05, steps = 47 00:47:39 [INFO] train episode 11272: reward = -9.58, steps = 28 00:47:39 [INFO] train episode 11273: reward = -0.68, steps = 46 00:47:39 [INFO] train episode 11274: reward = 5.06, steps = 44 00:47:40 [INFO] train episode 11275: reward = -42.19, steps = 53 00:47:40 [INFO] train episode 11276: reward = -5.16, steps = 34 00:47:41 [INFO] train episode 11277: reward = -0.12, steps = 42 00:47:41 [INFO] train episode 11278: reward = -9.48, steps = 45 00:47:41 [INFO] train episode 11279: reward = -8.69, steps = 44 00:47:41 [INFO] train episode 11280: reward = 3.77, steps = 43 00:47:42 [INFO] train episode 11281: reward = 18.81, steps = 57 00:47:42 [INFO] train episode 11282: reward = -10.60, steps = 36 00:47:42 [INFO] train episode 11283: reward = 15.18, steps = 47 00:47:43 [INFO] train episode 11284: reward = -0.21, steps = 37 00:47:43 [INFO] train episode 11285: reward = 14.07, steps = 46 00:47:43 [INFO] train episode 11286: reward = -6.04, steps = 44 00:47:44 [INFO] train episode 11287: reward = -12.25, steps = 48 00:47:44 [INFO] train episode 11288: reward = 11.97, steps = 49 00:47:44 [INFO] train episode 11289: reward = 9.43, steps = 35 00:47:44 [INFO] train episode 11290: reward = -5.55, steps = 41 00:47:45 [INFO] train episode 11291: reward = -3.88, steps = 34 00:47:45 [INFO] train episode 11292: reward = 2.59, steps = 48 00:47:45 [INFO] train episode 11293: reward = 13.63, steps = 51 00:47:46 [INFO] train episode 11294: reward = -20.23, steps = 40 00:47:46 [INFO] train episode 11295: reward = 1.94, steps = 38 00:47:46 [INFO] train episode 11296: reward = 10.09, steps = 44 00:47:46 [INFO] train episode 11297: reward = 16.03, steps = 44 00:47:47 [INFO] train episode 11298: reward = -11.35, steps = 43 00:47:47 [INFO] train episode 11299: reward = -8.73, steps = 44 00:47:47 [INFO] train episode 11300: reward = 11.98, steps = 37 00:47:48 [INFO] train episode 11301: reward = 10.20, steps = 45 00:47:48 [INFO] train episode 11302: reward = 2.42, steps = 43 00:47:48 [INFO] train episode 11303: reward = 0.31, steps = 40 00:47:48 [INFO] train episode 11304: reward = -16.14, steps = 29 00:47:49 [INFO] train episode 11305: reward = 2.04, steps = 40 00:47:49 [INFO] train episode 11306: reward = -2.12, steps = 43 00:47:49 [INFO] train episode 11307: reward = 6.82, steps = 44 00:47:50 [INFO] train episode 11308: reward = -4.95, steps = 52 00:47:50 [INFO] train episode 11309: reward = 4.16, steps = 50 00:47:50 [INFO] train episode 11310: reward = 4.35, steps = 39 00:47:50 [INFO] train episode 11311: reward = -13.59, steps = 36 00:47:51 [INFO] train episode 11312: reward = 8.08, steps = 54 00:47:51 [INFO] train episode 11313: reward = -0.98, steps = 40 00:47:51 [INFO] train episode 11314: reward = -27.86, steps = 20 00:47:51 [INFO] train episode 11315: reward = -3.31, steps = 31 00:47:52 [INFO] train episode 11316: reward = 10.68, steps = 48 00:47:52 [INFO] train episode 11317: reward = 16.26, steps = 51 00:47:52 [INFO] train episode 11318: reward = -15.93, steps = 27 00:47:52 [INFO] train episode 11319: reward = 4.64, steps = 44 00:47:53 [INFO] train episode 11320: reward = -3.32, steps = 45 00:47:53 [INFO] train episode 11321: reward = -8.30, steps = 28 00:47:53 [INFO] train episode 11322: reward = -1.69, steps = 43 00:47:54 [INFO] train episode 11323: reward = -4.74, steps = 36 00:47:54 [INFO] train episode 11324: reward = 8.90, steps = 49 00:47:54 [INFO] train episode 11325: reward = -15.96, steps = 45 00:47:54 [INFO] train episode 11326: reward = -5.46, steps = 30 00:47:55 [INFO] train episode 11327: reward = 0.64, steps = 42 00:47:55 [INFO] train episode 11328: reward = -23.40, steps = 22 00:47:55 [INFO] train episode 11329: reward = -5.12, steps = 28 00:47:56 [INFO] train episode 11330: reward = 2.11, steps = 46 00:47:56 [INFO] train episode 11331: reward = -3.27, steps = 42 00:47:56 [INFO] train episode 11332: reward = -22.53, steps = 23 00:47:56 [INFO] train episode 11333: reward = -11.83, steps = 36 00:47:56 [INFO] train episode 11334: reward = -24.84, steps = 35 00:47:57 [INFO] train episode 11335: reward = 8.07, steps = 43 00:47:57 [INFO] train episode 11336: reward = 19.75, steps = 42 00:47:57 [INFO] train episode 11337: reward = -5.47, steps = 41 00:47:58 [INFO] train episode 11338: reward = 3.86, steps = 69 00:47:58 [INFO] train episode 11339: reward = 4.72, steps = 49 00:47:58 [INFO] train episode 11340: reward = 23.71, steps = 76 00:47:59 [INFO] train episode 11341: reward = 0.10, steps = 29 00:47:59 [INFO] train episode 11342: reward = 17.69, steps = 44 00:47:59 [INFO] train episode 11343: reward = 15.68, steps = 46 00:48:00 [INFO] train episode 11344: reward = -14.32, steps = 40 00:48:00 [INFO] train episode 11345: reward = -0.75, steps = 39 00:48:00 [INFO] train episode 11346: reward = 19.53, steps = 50 00:48:00 [INFO] train episode 11347: reward = 9.43, steps = 52 00:48:01 [INFO] train episode 11348: reward = 12.48, steps = 61 00:48:01 [INFO] train episode 11349: reward = 14.30, steps = 49 00:48:02 [INFO] train episode 11350: reward = 5.55, steps = 46 00:48:02 [INFO] train episode 11351: reward = 12.05, steps = 51 00:48:02 [INFO] train episode 11352: reward = 6.21, steps = 40 00:48:02 [INFO] train episode 11353: reward = 7.63, steps = 53 00:48:03 [INFO] train episode 11354: reward = 5.82, steps = 39 00:48:03 [INFO] train episode 11355: reward = 4.57, steps = 45 00:48:03 [INFO] train episode 11356: reward = 4.12, steps = 41 00:48:04 [INFO] train episode 11357: reward = -1.41, steps = 38 00:48:04 [INFO] train episode 11358: reward = -5.99, steps = 45 00:48:04 [INFO] train episode 11359: reward = 1.43, steps = 38 00:48:04 [INFO] train episode 11360: reward = 12.48, steps = 47 00:48:05 [INFO] train episode 11361: reward = -11.44, steps = 53 00:48:05 [INFO] train episode 11362: reward = -19.32, steps = 39 00:48:05 [INFO] train episode 11363: reward = 2.09, steps = 49 00:48:06 [INFO] train episode 11364: reward = 6.14, steps = 49 00:48:06 [INFO] train episode 11365: reward = -9.25, steps = 39 00:48:06 [INFO] train episode 11366: reward = -29.80, steps = 18 00:48:06 [INFO] train episode 11367: reward = -29.76, steps = 23 00:48:07 [INFO] train episode 11368: reward = 8.99, steps = 43 00:48:07 [INFO] train episode 11369: reward = 0.91, steps = 52 00:48:07 [INFO] train episode 11370: reward = 6.69, steps = 48 00:48:08 [INFO] train episode 11371: reward = -14.78, steps = 36 00:48:08 [INFO] train episode 11372: reward = -30.53, steps = 19 00:48:08 [INFO] train episode 11373: reward = 13.78, steps = 45 00:48:08 [INFO] train episode 11374: reward = -31.03, steps = 31 00:48:09 [INFO] train episode 11375: reward = 6.70, steps = 39 00:48:09 [INFO] train episode 11376: reward = 4.51, steps = 47 00:48:09 [INFO] train episode 11377: reward = -15.75, steps = 33 00:48:09 [INFO] train episode 11378: reward = -2.39, steps = 36 00:48:10 [INFO] train episode 11379: reward = -2.39, steps = 65 00:48:10 [INFO] train episode 11380: reward = -0.93, steps = 49 00:48:10 [INFO] train episode 11381: reward = -3.33, steps = 43 00:48:11 [INFO] train episode 11382: reward = 10.89, steps = 49 00:48:11 [INFO] train episode 11383: reward = 6.64, steps = 39 00:48:11 [INFO] train episode 11384: reward = -2.46, steps = 45 00:48:12 [INFO] train episode 11385: reward = -10.31, steps = 45 00:48:12 [INFO] train episode 11386: reward = -23.66, steps = 18 00:48:12 [INFO] train episode 11387: reward = 19.33, steps = 47 00:48:12 [INFO] train episode 11388: reward = 4.22, steps = 38 00:48:13 [INFO] train episode 11389: reward = 6.91, steps = 37 00:48:13 [INFO] train episode 11390: reward = 9.76, steps = 45 00:48:13 [INFO] train episode 11391: reward = 5.92, steps = 44 00:48:13 [INFO] train episode 11392: reward = -4.80, steps = 35 00:48:14 [INFO] train episode 11393: reward = -5.79, steps = 25 00:48:14 [INFO] train episode 11394: reward = -27.45, steps = 45 00:48:14 [INFO] train episode 11395: reward = -11.54, steps = 30 00:48:15 [INFO] train episode 11396: reward = 0.57, steps = 70 00:48:15 [INFO] train episode 11397: reward = 20.64, steps = 53 00:48:15 [INFO] train episode 11398: reward = 0.05, steps = 36 00:48:15 [INFO] train episode 11399: reward = 1.72, steps = 33 00:48:16 [INFO] train episode 11400: reward = -0.30, steps = 36 00:48:16 [INFO] train episode 11401: reward = -21.58, steps = 19 00:48:16 [INFO] train episode 11402: reward = 16.32, steps = 44 00:48:16 [INFO] train episode 11403: reward = 3.07, steps = 37 00:48:17 [INFO] train episode 11404: reward = -10.33, steps = 29 00:48:17 [INFO] train episode 11405: reward = -1.54, steps = 40 00:48:17 [INFO] train episode 11406: reward = -12.63, steps = 27 00:48:17 [INFO] train episode 11407: reward = -5.77, steps = 48 00:48:18 [INFO] train episode 11408: reward = 3.99, steps = 49 00:48:18 [INFO] train episode 11409: reward = -20.79, steps = 39 00:48:18 [INFO] train episode 11410: reward = 7.79, steps = 41 00:48:18 [INFO] train episode 11411: reward = 3.17, steps = 50 00:48:19 [INFO] train episode 11412: reward = -8.03, steps = 43 00:48:19 [INFO] train episode 11413: reward = -2.88, steps = 37 00:48:19 [INFO] train episode 11414: reward = -5.73, steps = 39 00:48:20 [INFO] train episode 11415: reward = 14.26, steps = 41 00:48:20 [INFO] train episode 11416: reward = -8.92, steps = 48 00:48:20 [INFO] train episode 11417: reward = -0.42, steps = 43 00:48:21 [INFO] train episode 11418: reward = 5.06, steps = 57 00:48:21 [INFO] train episode 11419: reward = -3.09, steps = 47 00:48:21 [INFO] train episode 11420: reward = 1.96, steps = 46 00:48:22 [INFO] train episode 11421: reward = -2.65, steps = 50 00:48:22 [INFO] train episode 11422: reward = 6.00, steps = 38 00:48:22 [INFO] train episode 11423: reward = -30.45, steps = 18 00:48:22 [INFO] train episode 11424: reward = -7.59, steps = 32 00:48:23 [INFO] train episode 11425: reward = -24.11, steps = 44 00:48:23 [INFO] train episode 11426: reward = -48.97, steps = 19 00:48:23 [INFO] train episode 11427: reward = -6.94, steps = 41 00:48:23 [INFO] train episode 11428: reward = 3.51, steps = 41 00:48:23 [INFO] train episode 11429: reward = -32.27, steps = 19 00:48:24 [INFO] train episode 11430: reward = -2.15, steps = 35 00:48:24 [INFO] train episode 11431: reward = -16.23, steps = 38 00:48:24 [INFO] train episode 11432: reward = 10.68, steps = 45 00:48:24 [INFO] train episode 11433: reward = -1.43, steps = 39 00:48:25 [INFO] train episode 11434: reward = 7.35, steps = 43 00:48:25 [INFO] train episode 11435: reward = 2.67, steps = 40 00:48:25 [INFO] train episode 11436: reward = 2.89, steps = 48 00:48:26 [INFO] train episode 11437: reward = 8.04, steps = 42 00:48:26 [INFO] train episode 11438: reward = 12.93, steps = 40 00:48:26 [INFO] train episode 11439: reward = 9.08, steps = 47 00:48:26 [INFO] train episode 11440: reward = -16.51, steps = 37 00:48:27 [INFO] train episode 11441: reward = 9.13, steps = 47 00:48:27 [INFO] train episode 11442: reward = 9.09, steps = 41 00:48:27 [INFO] train episode 11443: reward = -23.30, steps = 20 00:48:27 [INFO] train episode 11444: reward = 1.43, steps = 40 00:48:28 [INFO] train episode 11445: reward = -14.45, steps = 39 00:48:28 [INFO] train episode 11446: reward = 23.90, steps = 54 00:48:28 [INFO] train episode 11447: reward = 1.32, steps = 34 00:48:29 [INFO] train episode 11448: reward = -10.99, steps = 61 00:48:29 [INFO] train episode 11449: reward = -2.56, steps = 38 00:48:29 [INFO] train episode 11450: reward = 2.03, steps = 42 00:48:29 [INFO] train episode 11451: reward = -26.90, steps = 29 00:48:30 [INFO] train episode 11452: reward = -8.98, steps = 40 00:48:30 [INFO] train episode 11453: reward = 18.68, steps = 52 00:48:30 [INFO] train episode 11454: reward = 3.07, steps = 42 00:48:31 [INFO] train episode 11455: reward = -11.97, steps = 41 00:48:31 [INFO] train episode 11456: reward = 13.57, steps = 56 00:48:31 [INFO] train episode 11457: reward = 5.92, steps = 43 00:48:32 [INFO] train episode 11458: reward = 4.21, steps = 44 00:48:32 [INFO] train episode 11459: reward = -2.12, steps = 47 00:48:32 [INFO] train episode 11460: reward = -4.18, steps = 37 00:48:32 [INFO] train episode 11461: reward = 3.05, steps = 39 00:48:33 [INFO] train episode 11462: reward = -9.18, steps = 36 00:48:33 [INFO] train episode 11463: reward = 1.40, steps = 36 00:48:33 [INFO] train episode 11464: reward = 15.47, steps = 56 00:48:33 [INFO] train episode 11465: reward = -25.42, steps = 18 00:48:34 [INFO] train episode 11466: reward = -7.53, steps = 38 00:48:34 [INFO] train episode 11467: reward = 9.80, steps = 42 00:48:34 [INFO] train episode 11468: reward = -8.55, steps = 38 00:48:35 [INFO] train episode 11469: reward = 11.05, steps = 96 00:48:35 [INFO] train episode 11470: reward = -6.65, steps = 34 00:48:36 [INFO] train episode 11471: reward = 15.79, steps = 50 00:48:36 [INFO] train episode 11472: reward = 7.83, steps = 40 00:48:36 [INFO] train episode 11473: reward = 2.17, steps = 39 00:48:36 [INFO] train episode 11474: reward = 10.16, steps = 44 00:48:37 [INFO] train episode 11475: reward = -16.97, steps = 28 00:48:37 [INFO] train episode 11476: reward = 3.83, steps = 36 00:48:37 [INFO] train episode 11477: reward = 6.04, steps = 59 00:48:38 [INFO] train episode 11478: reward = -9.34, steps = 44 00:48:38 [INFO] train episode 11479: reward = -0.82, steps = 34 00:48:38 [INFO] train episode 11480: reward = -12.16, steps = 48 00:48:38 [INFO] train episode 11481: reward = -14.11, steps = 45 00:48:39 [INFO] train episode 11482: reward = 16.57, steps = 51 00:48:39 [INFO] train episode 11483: reward = -9.79, steps = 42 00:48:39 [INFO] train episode 11484: reward = 24.43, steps = 73 00:48:40 [INFO] train episode 11485: reward = -25.50, steps = 19 00:48:40 [INFO] train episode 11486: reward = 9.72, steps = 40 00:48:40 [INFO] train episode 11487: reward = -19.52, steps = 17 00:48:40 [INFO] train episode 11488: reward = 3.98, steps = 65 00:48:41 [INFO] train episode 11489: reward = 0.64, steps = 36 00:48:41 [INFO] train episode 11490: reward = 8.67, steps = 52 00:48:41 [INFO] train episode 11491: reward = 19.18, steps = 54 00:48:42 [INFO] train episode 11492: reward = 13.84, steps = 55 00:48:42 [INFO] train episode 11493: reward = 12.30, steps = 36 00:48:42 [INFO] train episode 11494: reward = -7.61, steps = 56 00:48:43 [INFO] train episode 11495: reward = 10.20, steps = 52 00:48:43 [INFO] train episode 11496: reward = 2.70, steps = 42 00:48:43 [INFO] train episode 11497: reward = -0.05, steps = 35 00:48:43 [INFO] train episode 11498: reward = 3.53, steps = 48 00:48:44 [INFO] train episode 11499: reward = 3.23, steps = 49 00:48:44 [INFO] train episode 11500: reward = 6.34, steps = 37 00:48:44 [INFO] train episode 11501: reward = -28.67, steps = 25 00:48:45 [INFO] train episode 11502: reward = 4.12, steps = 54 00:48:45 [INFO] train episode 11503: reward = 16.80, steps = 46 00:48:45 [INFO] train episode 11504: reward = 7.81, steps = 41 00:48:45 [INFO] train episode 11505: reward = 9.00, steps = 38 00:48:46 [INFO] train episode 11506: reward = -6.66, steps = 47 00:48:46 [INFO] train episode 11507: reward = -27.22, steps = 37 00:48:46 [INFO] train episode 11508: reward = -9.36, steps = 40 00:48:46 [INFO] train episode 11509: reward = -0.83, steps = 46 00:48:47 [INFO] train episode 11510: reward = -30.45, steps = 24 00:48:47 [INFO] train episode 11511: reward = -17.20, steps = 36 00:48:48 [INFO] train episode 11512: reward = -26.06, steps = 58 00:48:48 [INFO] train episode 11513: reward = 7.20, steps = 38 00:48:48 [INFO] train episode 11514: reward = -10.75, steps = 30 00:48:48 [INFO] train episode 11515: reward = 7.98, steps = 55 00:48:49 [INFO] train episode 11516: reward = -3.90, steps = 45 00:48:49 [INFO] train episode 11517: reward = -12.02, steps = 40 00:48:49 [INFO] train episode 11518: reward = 3.01, steps = 41 00:48:50 [INFO] train episode 11519: reward = 4.14, steps = 40 00:48:50 [INFO] train episode 11520: reward = 0.45, steps = 43 00:48:50 [INFO] train episode 11521: reward = -9.86, steps = 35 00:48:50 [INFO] train episode 11522: reward = -1.66, steps = 46 00:48:51 [INFO] train episode 11523: reward = -16.46, steps = 38 00:48:51 [INFO] train episode 11524: reward = -0.84, steps = 35 00:48:51 [INFO] train episode 11525: reward = -12.42, steps = 31 00:48:51 [INFO] train episode 11526: reward = -14.48, steps = 33 00:48:52 [INFO] train episode 11527: reward = -1.17, steps = 42 00:48:52 [INFO] train episode 11528: reward = 23.46, steps = 54 00:48:52 [INFO] train episode 11529: reward = 2.61, steps = 42 00:48:52 [INFO] train episode 11530: reward = -24.90, steps = 34 00:48:53 [INFO] train episode 11531: reward = -24.99, steps = 43 00:48:53 [INFO] train episode 11532: reward = -7.76, steps = 37 00:48:53 [INFO] train episode 11533: reward = -22.42, steps = 30 00:48:54 [INFO] train episode 11534: reward = -3.56, steps = 45 00:48:54 [INFO] train episode 11535: reward = -5.94, steps = 40 00:48:54 [INFO] train episode 11536: reward = -2.06, steps = 40 00:48:54 [INFO] train episode 11537: reward = 11.87, steps = 42 00:48:55 [INFO] train episode 11538: reward = -2.36, steps = 46 00:48:55 [INFO] train episode 11539: reward = -23.03, steps = 23 00:48:55 [INFO] train episode 11540: reward = -23.26, steps = 28 00:48:55 [INFO] train episode 11541: reward = 10.77, steps = 47 00:48:56 [INFO] train episode 11542: reward = -11.36, steps = 36 00:48:56 [INFO] train episode 11543: reward = -11.41, steps = 49 00:48:56 [INFO] train episode 11544: reward = 4.36, steps = 40 00:48:56 [INFO] train episode 11545: reward = -6.14, steps = 40 00:48:57 [INFO] train episode 11546: reward = -8.77, steps = 53 00:48:57 [INFO] train episode 11547: reward = -10.58, steps = 47 00:48:57 [INFO] train episode 11548: reward = -25.47, steps = 23 00:48:58 [INFO] train episode 11549: reward = -10.99, steps = 47 00:48:58 [INFO] train episode 11550: reward = 2.07, steps = 56 00:48:58 [INFO] train episode 11551: reward = 1.07, steps = 35 00:48:58 [INFO] train episode 11552: reward = -12.78, steps = 34 00:48:59 [INFO] train episode 11553: reward = -10.82, steps = 32 00:48:59 [INFO] train episode 11554: reward = 5.71, steps = 40 00:48:59 [INFO] train episode 11555: reward = -4.87, steps = 32 00:49:00 [INFO] train episode 11556: reward = -68.32, steps = 80 00:49:00 [INFO] train episode 11557: reward = -7.08, steps = 40 00:49:00 [INFO] train episode 11558: reward = 6.22, steps = 54 00:49:01 [INFO] train episode 11559: reward = 3.80, steps = 43 00:49:01 [INFO] train episode 11560: reward = 11.55, steps = 59 00:49:02 [INFO] train episode 11561: reward = 1.25, steps = 41 00:49:02 [INFO] train episode 11562: reward = -8.00, steps = 34 00:49:02 [INFO] train episode 11563: reward = 2.47, steps = 37 00:49:02 [INFO] train episode 11564: reward = 3.04, steps = 42 00:49:03 [INFO] train episode 11565: reward = -27.14, steps = 45 00:49:03 [INFO] train episode 11566: reward = -19.32, steps = 43 00:49:03 [INFO] train episode 11567: reward = -3.35, steps = 43 00:49:03 [INFO] train episode 11568: reward = -23.51, steps = 38 00:49:04 [INFO] train episode 11569: reward = -3.79, steps = 35 00:49:04 [INFO] train episode 11570: reward = -4.11, steps = 37 00:49:04 [INFO] train episode 11571: reward = -12.58, steps = 47 00:49:05 [INFO] train episode 11572: reward = -28.45, steps = 53 00:49:05 [INFO] train episode 11573: reward = -35.33, steps = 19 00:49:05 [INFO] train episode 11574: reward = 17.64, steps = 44 00:49:05 [INFO] train episode 11575: reward = 2.23, steps = 43 00:49:06 [INFO] train episode 11576: reward = -5.71, steps = 45 00:49:06 [INFO] train episode 11577: reward = -15.40, steps = 17 00:49:06 [INFO] train episode 11578: reward = 18.13, steps = 46 00:49:06 [INFO] train episode 11579: reward = -15.68, steps = 51 00:49:07 [INFO] train episode 11580: reward = 5.87, steps = 36 00:49:07 [INFO] train episode 11581: reward = -8.29, steps = 35 00:49:07 [INFO] train episode 11582: reward = -15.11, steps = 42 00:49:07 [INFO] train episode 11583: reward = -29.23, steps = 33 00:49:08 [INFO] train episode 11584: reward = 6.29, steps = 40 00:49:08 [INFO] train episode 11585: reward = -0.11, steps = 49 00:49:08 [INFO] train episode 11586: reward = -16.07, steps = 47 00:49:09 [INFO] train episode 11587: reward = -7.56, steps = 38 00:49:09 [INFO] train episode 11588: reward = -21.37, steps = 40 00:49:09 [INFO] train episode 11589: reward = -13.94, steps = 33 00:49:09 [INFO] train episode 11590: reward = -3.06, steps = 43 00:49:10 [INFO] train episode 11591: reward = -9.30, steps = 38 00:49:10 [INFO] train episode 11592: reward = 10.58, steps = 42 00:49:10 [INFO] train episode 11593: reward = -4.72, steps = 38 00:49:11 [INFO] train episode 11594: reward = -10.29, steps = 37 00:49:11 [INFO] train episode 11595: reward = -7.46, steps = 39 00:49:11 [INFO] train episode 11596: reward = 3.53, steps = 44 00:49:11 [INFO] train episode 11597: reward = -0.63, steps = 47 00:49:12 [INFO] train episode 11598: reward = 2.86, steps = 33 00:49:12 [INFO] train episode 11599: reward = -3.82, steps = 44 00:49:12 [INFO] train episode 11600: reward = -8.56, steps = 43 00:49:12 [INFO] train episode 11601: reward = -6.02, steps = 37 00:49:13 [INFO] train episode 11602: reward = 6.37, steps = 52 00:49:13 [INFO] train episode 11603: reward = 8.94, steps = 64 00:49:13 [INFO] train episode 11604: reward = 11.15, steps = 41 00:49:14 [INFO] train episode 11605: reward = -4.38, steps = 43 00:49:14 [INFO] train episode 11606: reward = -6.86, steps = 40 00:49:15 [INFO] train episode 11607: reward = 1.04, steps = 33 00:49:15 [INFO] train episode 11608: reward = -22.16, steps = 31 00:49:15 [INFO] train episode 11609: reward = -8.42, steps = 41 00:49:15 [INFO] train episode 11610: reward = -3.19, steps = 37 00:49:16 [INFO] train episode 11611: reward = -14.82, steps = 45 00:49:16 [INFO] train episode 11612: reward = 0.80, steps = 44 00:49:16 [INFO] train episode 11613: reward = -6.05, steps = 45 00:49:17 [INFO] train episode 11614: reward = 13.82, steps = 48 00:49:17 [INFO] train episode 11615: reward = 8.35, steps = 47 00:49:17 [INFO] train episode 11616: reward = 3.82, steps = 47 00:49:17 [INFO] train episode 11617: reward = -12.57, steps = 42 00:49:18 [INFO] train episode 11618: reward = -18.01, steps = 32 00:49:18 [INFO] train episode 11619: reward = -4.39, steps = 45 00:49:18 [INFO] train episode 11620: reward = -5.34, steps = 39 00:49:18 [INFO] train episode 11621: reward = -9.78, steps = 23 00:49:19 [INFO] train episode 11622: reward = -3.80, steps = 40 00:49:19 [INFO] train episode 11623: reward = 2.16, steps = 41 00:49:19 [INFO] train episode 11624: reward = -33.77, steps = 21 00:49:19 [INFO] train episode 11625: reward = -31.19, steps = 25 00:49:20 [INFO] train episode 11626: reward = -19.51, steps = 40 00:49:20 [INFO] train episode 11627: reward = -0.19, steps = 46 00:49:20 [INFO] train episode 11628: reward = -9.74, steps = 56 00:49:20 [INFO] train episode 11629: reward = -15.99, steps = 39 00:49:21 [INFO] train episode 11630: reward = -26.14, steps = 19 00:49:21 [INFO] train episode 11631: reward = 6.26, steps = 45 00:49:21 [INFO] train episode 11632: reward = -29.07, steps = 50 00:49:21 [INFO] train episode 11633: reward = -36.77, steps = 33 00:49:22 [INFO] train episode 11634: reward = -24.30, steps = 18 00:49:22 [INFO] train episode 11635: reward = -16.06, steps = 47 00:49:22 [INFO] train episode 11636: reward = 3.44, steps = 32 00:49:22 [INFO] train episode 11637: reward = -8.12, steps = 44 00:49:23 [INFO] train episode 11638: reward = -4.93, steps = 41 00:49:23 [INFO] train episode 11639: reward = 14.43, steps = 48 00:49:23 [INFO] train episode 11640: reward = 0.25, steps = 46 00:49:24 [INFO] train episode 11641: reward = -18.74, steps = 37 00:49:24 [INFO] train episode 11642: reward = -5.04, steps = 43 00:49:24 [INFO] train episode 11643: reward = -5.20, steps = 39 00:49:24 [INFO] train episode 11644: reward = -9.92, steps = 29 00:49:25 [INFO] train episode 11645: reward = -0.69, steps = 59 00:49:25 [INFO] train episode 11646: reward = -20.40, steps = 37 00:49:25 [INFO] train episode 11647: reward = -24.37, steps = 28 00:49:25 [INFO] train episode 11648: reward = -10.85, steps = 36 00:49:26 [INFO] train episode 11649: reward = -19.07, steps = 36 00:49:26 [INFO] train episode 11650: reward = -25.58, steps = 17 00:49:26 [INFO] train episode 11651: reward = -9.54, steps = 34 00:49:26 [INFO] train episode 11652: reward = -26.33, steps = 20 00:49:26 [INFO] train episode 11653: reward = 8.68, steps = 41 00:49:27 [INFO] train episode 11654: reward = -2.35, steps = 48 00:49:27 [INFO] train episode 11655: reward = 11.78, steps = 46 00:49:27 [INFO] train episode 11656: reward = 14.95, steps = 51 00:49:28 [INFO] train episode 11657: reward = -23.39, steps = 105 00:49:28 [INFO] train episode 11658: reward = -4.92, steps = 33 00:49:29 [INFO] train episode 11659: reward = -22.51, steps = 35 00:49:29 [INFO] train episode 11660: reward = -15.42, steps = 38 00:49:29 [INFO] train episode 11661: reward = -24.54, steps = 30 00:49:29 [INFO] train episode 11662: reward = -7.11, steps = 36 00:49:29 [INFO] train episode 11663: reward = -22.10, steps = 18 00:49:30 [INFO] train episode 11664: reward = -0.32, steps = 44 00:49:30 [INFO] train episode 11665: reward = -34.55, steps = 33 00:49:30 [INFO] train episode 11666: reward = 5.22, steps = 45 00:49:31 [INFO] train episode 11667: reward = -3.59, steps = 37 00:49:31 [INFO] train episode 11668: reward = 8.44, steps = 54 00:49:31 [INFO] train episode 11669: reward = 4.19, steps = 38 00:49:31 [INFO] train episode 11670: reward = -6.33, steps = 32 00:49:32 [INFO] train episode 11671: reward = -17.22, steps = 27 00:49:32 [INFO] train episode 11672: reward = -24.08, steps = 18 00:49:32 [INFO] train episode 11673: reward = -1.56, steps = 31 00:49:32 [INFO] train episode 11674: reward = -6.55, steps = 43 00:49:33 [INFO] train episode 11675: reward = -12.26, steps = 59 00:49:33 [INFO] train episode 11676: reward = -12.08, steps = 40 00:49:33 [INFO] train episode 11677: reward = -4.77, steps = 37 00:49:33 [INFO] train episode 11678: reward = 7.32, steps = 38 00:49:34 [INFO] train episode 11679: reward = -14.74, steps = 38 00:49:34 [INFO] train episode 11680: reward = 8.69, steps = 40 00:49:34 [INFO] train episode 11681: reward = 1.14, steps = 43 00:49:34 [INFO] train episode 11682: reward = -10.92, steps = 37 00:49:35 [INFO] train episode 11683: reward = -10.95, steps = 39 00:49:35 [INFO] train episode 11684: reward = -30.74, steps = 23 00:49:35 [INFO] train episode 11685: reward = -12.13, steps = 35 00:49:35 [INFO] train episode 11686: reward = 5.46, steps = 38 00:49:35 [INFO] train episode 11687: reward = -18.14, steps = 38 00:49:36 [INFO] train episode 11688: reward = -11.93, steps = 35 00:49:36 [INFO] train episode 11689: reward = -28.40, steps = 19 00:49:36 [INFO] train episode 11690: reward = -31.72, steps = 18 00:49:36 [INFO] train episode 11691: reward = -20.49, steps = 37 00:49:37 [INFO] train episode 11692: reward = -10.47, steps = 43 00:49:37 [INFO] train episode 11693: reward = -15.48, steps = 41 00:49:37 [INFO] train episode 11694: reward = -6.28, steps = 43 00:49:37 [INFO] train episode 11695: reward = -5.17, steps = 35 00:49:38 [INFO] train episode 11696: reward = -2.24, steps = 42 00:49:38 [INFO] train episode 11697: reward = -3.56, steps = 28 00:49:38 [INFO] train episode 11698: reward = -16.28, steps = 36 00:49:38 [INFO] train episode 11699: reward = -26.70, steps = 33 00:49:39 [INFO] train episode 11700: reward = 2.08, steps = 41 00:49:39 [INFO] train episode 11701: reward = 7.26, steps = 47 00:49:39 [INFO] train episode 11702: reward = -34.50, steps = 19 00:49:39 [INFO] train episode 11703: reward = -4.78, steps = 42 00:49:39 [INFO] train episode 11704: reward = -19.97, steps = 26 00:49:40 [INFO] train episode 11705: reward = -8.99, steps = 41 00:49:40 [INFO] train episode 11706: reward = 2.30, steps = 41 00:49:40 [INFO] train episode 11707: reward = 5.43, steps = 42 00:49:41 [INFO] train episode 11708: reward = -6.28, steps = 52 00:49:41 [INFO] train episode 11709: reward = -2.32, steps = 29 00:49:41 [INFO] train episode 11710: reward = -12.19, steps = 35 00:49:42 [INFO] train episode 11711: reward = -0.86, steps = 49 00:49:42 [INFO] train episode 11712: reward = -4.97, steps = 39 00:49:42 [INFO] train episode 11713: reward = -8.27, steps = 43 00:49:42 [INFO] train episode 11714: reward = -15.70, steps = 27 00:49:42 [INFO] train episode 11715: reward = -22.62, steps = 19 00:49:43 [INFO] train episode 11716: reward = 18.64, steps = 51 00:49:43 [INFO] train episode 11717: reward = 0.11, steps = 44 00:49:43 [INFO] train episode 11718: reward = 13.68, steps = 44 00:49:44 [INFO] train episode 11719: reward = -0.08, steps = 53 00:49:44 [INFO] train episode 11720: reward = -9.86, steps = 41 00:49:44 [INFO] train episode 11721: reward = -6.79, steps = 36 00:49:44 [INFO] train episode 11722: reward = -5.10, steps = 29 00:49:45 [INFO] train episode 11723: reward = 7.24, steps = 40 00:49:45 [INFO] train episode 11724: reward = 0.07, steps = 36 00:49:45 [INFO] train episode 11725: reward = -9.82, steps = 36 00:49:45 [INFO] train episode 11726: reward = -0.01, steps = 37 00:49:46 [INFO] train episode 11727: reward = -0.25, steps = 47 00:49:46 [INFO] train episode 11728: reward = -11.02, steps = 38 00:49:46 [INFO] train episode 11729: reward = -10.00, steps = 40 00:49:46 [INFO] train episode 11730: reward = -1.53, steps = 41 00:49:47 [INFO] train episode 11731: reward = -8.70, steps = 43 00:49:47 [INFO] train episode 11732: reward = -20.49, steps = 33 00:49:47 [INFO] train episode 11733: reward = -18.11, steps = 56 00:49:48 [INFO] train episode 11734: reward = 11.86, steps = 75 00:49:48 [INFO] train episode 11735: reward = -13.56, steps = 34 00:49:48 [INFO] train episode 11736: reward = -20.33, steps = 46 00:49:49 [INFO] train episode 11737: reward = -1.70, steps = 35 00:49:49 [INFO] train episode 11738: reward = -12.44, steps = 34 00:49:49 [INFO] train episode 11739: reward = -12.50, steps = 57 00:49:49 [INFO] train episode 11740: reward = -8.67, steps = 25 00:49:50 [INFO] train episode 11741: reward = -5.83, steps = 48 00:49:50 [INFO] train episode 11742: reward = -12.91, steps = 29 00:49:50 [INFO] train episode 11743: reward = -5.06, steps = 36 00:49:50 [INFO] train episode 11744: reward = -8.39, steps = 38 00:49:51 [INFO] train episode 11745: reward = -26.97, steps = 19 00:49:51 [INFO] train episode 11746: reward = -5.51, steps = 27 00:49:51 [INFO] train episode 11747: reward = -15.27, steps = 25 00:49:51 [INFO] train episode 11748: reward = -15.77, steps = 39 00:49:51 [INFO] train episode 11749: reward = -3.05, steps = 39 00:49:52 [INFO] train episode 11750: reward = -18.83, steps = 27 00:49:52 [INFO] train episode 11751: reward = -18.36, steps = 22 00:49:52 [INFO] train episode 11752: reward = -0.14, steps = 36 00:49:52 [INFO] train episode 11753: reward = -10.52, steps = 37 00:49:53 [INFO] train episode 11754: reward = -23.30, steps = 34 00:49:53 [INFO] train episode 11755: reward = -18.96, steps = 41 00:49:53 [INFO] train episode 11756: reward = -9.77, steps = 38 00:49:53 [INFO] train episode 11757: reward = -7.17, steps = 45 00:49:54 [INFO] train episode 11758: reward = 0.21, steps = 37 00:49:54 [INFO] train episode 11759: reward = 1.79, steps = 47 00:49:54 [INFO] train episode 11760: reward = -6.27, steps = 41 00:49:55 [INFO] train episode 11761: reward = -8.26, steps = 49 00:49:55 [INFO] train episode 11762: reward = 8.62, steps = 37 00:49:55 [INFO] train episode 11763: reward = -10.77, steps = 29 00:49:55 [INFO] train episode 11764: reward = -7.47, steps = 36 00:49:56 [INFO] train episode 11765: reward = -27.44, steps = 46 00:49:56 [INFO] train episode 11766: reward = -11.80, steps = 29 00:49:56 [INFO] train episode 11767: reward = -1.52, steps = 32 00:49:56 [INFO] train episode 11768: reward = -2.10, steps = 47 00:49:57 [INFO] train episode 11769: reward = 1.48, steps = 44 00:49:57 [INFO] train episode 11770: reward = -6.16, steps = 39 00:49:57 [INFO] train episode 11771: reward = -7.13, steps = 36 00:49:58 [INFO] train episode 11772: reward = -60.45, steps = 65 00:49:58 [INFO] train episode 11773: reward = 4.24, steps = 56 00:49:58 [INFO] train episode 11774: reward = -0.03, steps = 33 00:49:59 [INFO] train episode 11775: reward = 5.37, steps = 37 00:49:59 [INFO] train episode 11776: reward = -20.81, steps = 35 00:49:59 [INFO] train episode 11777: reward = 6.54, steps = 43 00:49:59 [INFO] train episode 11778: reward = 19.40, steps = 57 00:50:00 [INFO] train episode 11779: reward = -8.55, steps = 40 00:50:00 [INFO] train episode 11780: reward = -23.22, steps = 29 00:50:00 [INFO] train episode 11781: reward = 0.07, steps = 34 00:50:00 [INFO] train episode 11782: reward = 2.96, steps = 36 00:50:01 [INFO] train episode 11783: reward = -1.18, steps = 43 00:50:01 [INFO] train episode 11784: reward = -1.60, steps = 49 00:50:01 [INFO] train episode 11785: reward = 0.51, steps = 43 00:50:02 [INFO] train episode 11786: reward = -5.57, steps = 39 00:50:02 [INFO] train episode 11787: reward = -1.70, steps = 39 00:50:02 [INFO] train episode 11788: reward = -19.55, steps = 38 00:50:02 [INFO] train episode 11789: reward = -18.47, steps = 23 00:50:03 [INFO] train episode 11790: reward = -2.77, steps = 43 00:50:03 [INFO] train episode 11791: reward = -14.05, steps = 43 00:50:03 [INFO] train episode 11792: reward = -7.25, steps = 40 00:50:03 [INFO] train episode 11793: reward = -16.86, steps = 21 00:50:03 [INFO] train episode 11794: reward = -9.63, steps = 37 00:50:04 [INFO] train episode 11795: reward = -27.81, steps = 37 00:50:04 [INFO] train episode 11796: reward = -2.78, steps = 40 00:50:04 [INFO] train episode 11797: reward = 0.67, steps = 31 00:50:04 [INFO] train episode 11798: reward = 5.68, steps = 37 00:50:05 [INFO] train episode 11799: reward = -6.03, steps = 43 00:50:05 [INFO] train episode 11800: reward = -6.78, steps = 38 00:50:05 [INFO] train episode 11801: reward = -4.88, steps = 45 00:50:06 [INFO] train episode 11802: reward = -1.72, steps = 31 00:50:06 [INFO] train episode 11803: reward = -10.82, steps = 39 00:50:06 [INFO] train episode 11804: reward = -28.98, steps = 37 00:50:06 [INFO] train episode 11805: reward = -17.27, steps = 31 00:50:07 [INFO] train episode 11806: reward = -3.10, steps = 48 00:50:07 [INFO] train episode 11807: reward = 11.29, steps = 53 00:50:07 [INFO] train episode 11808: reward = -17.59, steps = 36 00:50:07 [INFO] train episode 11809: reward = -11.47, steps = 26 00:50:08 [INFO] train episode 11810: reward = 1.08, steps = 42 00:50:08 [INFO] train episode 11811: reward = -7.55, steps = 40 00:50:08 [INFO] train episode 11812: reward = -8.84, steps = 29 00:50:09 [INFO] train episode 11813: reward = -21.64, steps = 44 00:50:09 [INFO] train episode 11814: reward = 7.73, steps = 40 00:50:09 [INFO] train episode 11815: reward = -6.12, steps = 46 00:50:10 [INFO] train episode 11816: reward = 5.19, steps = 35 00:50:10 [INFO] train episode 11817: reward = -4.01, steps = 36 00:50:10 [INFO] train episode 11818: reward = -37.53, steps = 72 00:50:11 [INFO] train episode 11819: reward = -20.33, steps = 31 00:50:11 [INFO] train episode 11820: reward = -4.87, steps = 37 00:50:11 [INFO] train episode 11821: reward = 3.66, steps = 35 00:50:11 [INFO] train episode 11822: reward = -15.17, steps = 38 00:50:12 [INFO] train episode 11823: reward = 4.85, steps = 62 00:50:12 [INFO] train episode 11824: reward = -8.77, steps = 40 00:50:12 [INFO] train episode 11825: reward = -3.24, steps = 37 00:50:13 [INFO] train episode 11826: reward = 8.46, steps = 45 00:50:13 [INFO] train episode 11827: reward = -8.00, steps = 38 00:50:13 [INFO] train episode 11828: reward = 5.26, steps = 49 00:50:13 [INFO] train episode 11829: reward = -7.35, steps = 34 00:50:14 [INFO] train episode 11830: reward = -9.72, steps = 36 00:50:14 [INFO] train episode 11831: reward = -3.76, steps = 34 00:50:14 [INFO] train episode 11832: reward = 0.98, steps = 45 00:50:15 [INFO] train episode 11833: reward = -5.35, steps = 36 00:50:15 [INFO] train episode 11834: reward = -13.01, steps = 37 00:50:15 [INFO] train episode 11835: reward = -13.65, steps = 43 00:50:15 [INFO] train episode 11836: reward = -20.44, steps = 27 00:50:16 [INFO] train episode 11837: reward = -14.09, steps = 40 00:50:16 [INFO] train episode 11838: reward = -7.61, steps = 31 00:50:16 [INFO] train episode 11839: reward = -6.43, steps = 40 00:50:16 [INFO] train episode 11840: reward = -7.14, steps = 45 00:50:17 [INFO] train episode 11841: reward = -16.46, steps = 38 00:50:17 [INFO] train episode 11842: reward = -18.81, steps = 26 00:50:17 [INFO] train episode 11843: reward = -0.33, steps = 40 00:50:17 [INFO] train episode 11844: reward = -28.24, steps = 34 00:50:18 [INFO] train episode 11845: reward = -54.52, steps = 63 00:50:18 [INFO] train episode 11846: reward = -21.30, steps = 45 00:50:18 [INFO] train episode 11847: reward = -12.45, steps = 39 00:50:19 [INFO] train episode 11848: reward = -1.09, steps = 50 00:50:19 [INFO] train episode 11849: reward = 1.26, steps = 39 00:50:19 [INFO] train episode 11850: reward = -7.82, steps = 27 00:50:19 [INFO] train episode 11851: reward = 1.43, steps = 41 00:50:20 [INFO] train episode 11852: reward = -7.50, steps = 39 00:50:20 [INFO] train episode 11853: reward = 13.76, steps = 39 00:50:20 [INFO] train episode 11854: reward = -33.42, steps = 21 00:50:20 [INFO] train episode 11855: reward = -1.12, steps = 34 00:50:20 [INFO] train episode 11856: reward = -0.87, steps = 34 00:50:21 [INFO] train episode 11857: reward = -6.55, steps = 49 00:50:21 [INFO] train episode 11858: reward = 19.52, steps = 49 00:50:21 [INFO] train episode 11859: reward = -14.51, steps = 35 00:50:22 [INFO] train episode 11860: reward = -26.49, steps = 57 00:50:22 [INFO] train episode 11861: reward = -6.34, steps = 35 00:50:22 [INFO] train episode 11862: reward = 10.07, steps = 41 00:50:23 [INFO] train episode 11863: reward = -7.83, steps = 36 00:50:23 [INFO] train episode 11864: reward = 10.04, steps = 40 00:50:23 [INFO] train episode 11865: reward = -5.65, steps = 38 00:50:23 [INFO] train episode 11866: reward = -20.32, steps = 32 00:50:24 [INFO] train episode 11867: reward = -27.01, steps = 36 00:50:24 [INFO] train episode 11868: reward = -5.06, steps = 35 00:50:24 [INFO] train episode 11869: reward = -2.38, steps = 59 00:50:24 [INFO] train episode 11870: reward = -16.05, steps = 33 00:50:25 [INFO] train episode 11871: reward = -28.49, steps = 40 00:50:25 [INFO] train episode 11872: reward = -15.81, steps = 40 00:50:25 [INFO] train episode 11873: reward = -14.92, steps = 25 00:50:25 [INFO] train episode 11874: reward = -22.42, steps = 27 00:50:26 [INFO] train episode 11875: reward = 4.41, steps = 33 00:50:26 [INFO] train episode 11876: reward = -4.30, steps = 38 00:50:26 [INFO] train episode 11877: reward = 1.63, steps = 33 00:50:26 [INFO] train episode 11878: reward = 1.97, steps = 34 00:50:27 [INFO] train episode 11879: reward = 3.45, steps = 36 00:50:27 [INFO] train episode 11880: reward = -17.53, steps = 39 00:50:27 [INFO] train episode 11881: reward = -17.27, steps = 44 00:50:27 [INFO] train episode 11882: reward = -21.56, steps = 39 00:50:28 [INFO] train episode 11883: reward = -33.67, steps = 36 00:50:28 [INFO] train episode 11884: reward = 10.15, steps = 46 00:50:28 [INFO] train episode 11885: reward = -8.98, steps = 27 00:50:28 [INFO] train episode 11886: reward = 0.54, steps = 36 00:50:29 [INFO] train episode 11887: reward = -2.61, steps = 39 00:50:29 [INFO] train episode 11888: reward = -8.76, steps = 41 00:50:29 [INFO] train episode 11889: reward = -10.81, steps = 28 00:50:29 [INFO] train episode 11890: reward = -25.37, steps = 21 00:50:29 [INFO] train episode 11891: reward = 17.86, steps = 48 00:50:30 [INFO] train episode 11892: reward = -17.43, steps = 18 00:50:30 [INFO] train episode 11893: reward = -6.75, steps = 30 00:50:30 [INFO] train episode 11894: reward = 3.12, steps = 39 00:50:30 [INFO] train episode 11895: reward = -6.85, steps = 44 00:50:31 [INFO] train episode 11896: reward = 15.66, steps = 62 00:50:31 [INFO] train episode 11897: reward = 5.53, steps = 47 00:50:31 [INFO] train episode 11898: reward = -2.72, steps = 36 00:50:32 [INFO] train episode 11899: reward = -18.28, steps = 39 00:50:32 [INFO] train episode 11900: reward = -14.35, steps = 45 00:50:32 [INFO] train episode 11901: reward = 8.94, steps = 44 00:50:33 [INFO] train episode 11902: reward = 0.63, steps = 42 00:50:33 [INFO] train episode 11903: reward = -2.60, steps = 40 00:50:33 [INFO] train episode 11904: reward = -3.98, steps = 38 00:50:33 [INFO] train episode 11905: reward = -7.02, steps = 31 00:50:33 [INFO] train episode 11906: reward = -6.84, steps = 36 00:50:34 [INFO] train episode 11907: reward = -69.09, steps = 91 00:50:34 [INFO] train episode 11908: reward = -16.66, steps = 29 00:50:34 [INFO] train episode 11909: reward = -26.41, steps = 42 00:50:35 [INFO] train episode 11910: reward = 22.97, steps = 49 00:50:35 [INFO] train episode 11911: reward = -4.23, steps = 42 00:50:36 [INFO] train episode 11912: reward = 1.44, steps = 48 00:50:36 [INFO] train episode 11913: reward = -1.73, steps = 54 00:50:36 [INFO] train episode 11914: reward = -5.72, steps = 36 00:50:37 [INFO] train episode 11915: reward = 10.44, steps = 43 00:50:37 [INFO] train episode 11916: reward = -16.06, steps = 45 00:50:37 [INFO] train episode 11917: reward = 3.69, steps = 53 00:50:38 [INFO] train episode 11918: reward = -6.83, steps = 45 00:50:38 [INFO] train episode 11919: reward = -4.42, steps = 33 00:50:38 [INFO] train episode 11920: reward = -11.19, steps = 39 00:50:38 [INFO] train episode 11921: reward = -5.96, steps = 36 00:50:38 [INFO] train episode 11922: reward = -2.91, steps = 35 00:50:39 [INFO] train episode 11923: reward = -10.21, steps = 52 00:50:39 [INFO] train episode 11924: reward = -2.01, steps = 37 00:50:39 [INFO] train episode 11925: reward = 1.41, steps = 39 00:50:40 [INFO] train episode 11926: reward = -3.42, steps = 32 00:50:40 [INFO] train episode 11927: reward = -0.69, steps = 51 00:50:40 [INFO] train episode 11928: reward = -15.27, steps = 26 00:50:40 [INFO] train episode 11929: reward = 11.27, steps = 56 00:50:41 [INFO] train episode 11930: reward = -14.38, steps = 43 00:50:41 [INFO] train episode 11931: reward = -4.44, steps = 37 00:50:41 [INFO] train episode 11932: reward = 1.91, steps = 38 00:50:41 [INFO] train episode 11933: reward = 3.29, steps = 38 00:50:42 [INFO] train episode 11934: reward = -12.71, steps = 23 00:50:42 [INFO] train episode 11935: reward = -0.35, steps = 36 00:50:42 [INFO] train episode 11936: reward = -17.99, steps = 31 00:50:42 [INFO] train episode 11937: reward = 13.99, steps = 46 00:50:43 [INFO] train episode 11938: reward = -9.93, steps = 35 00:50:43 [INFO] train episode 11939: reward = 2.05, steps = 40 00:50:43 [INFO] train episode 11940: reward = -11.82, steps = 31 00:50:43 [INFO] train episode 11941: reward = 0.64, steps = 36 00:50:44 [INFO] train episode 11942: reward = -8.41, steps = 33 00:50:44 [INFO] train episode 11943: reward = -32.51, steps = 17 00:50:44 [INFO] train episode 11944: reward = -32.92, steps = 18 00:50:44 [INFO] train episode 11945: reward = 7.77, steps = 52 00:50:44 [INFO] train episode 11946: reward = -3.29, steps = 37 00:50:45 [INFO] train episode 11947: reward = 3.81, steps = 46 00:50:45 [INFO] train episode 11948: reward = -35.95, steps = 31 00:50:45 [INFO] train episode 11949: reward = -16.86, steps = 33 00:50:46 [INFO] train episode 11950: reward = 0.70, steps = 47 00:50:46 [INFO] train episode 11951: reward = 10.16, steps = 38 00:50:46 [INFO] train episode 11952: reward = -20.49, steps = 26 00:50:46 [INFO] train episode 11953: reward = -9.28, steps = 48 00:50:46 [INFO] train episode 11954: reward = -1.22, steps = 33 00:50:47 [INFO] train episode 11955: reward = -2.08, steps = 49 00:50:47 [INFO] train episode 11956: reward = -2.97, steps = 39 00:50:47 [INFO] train episode 11957: reward = 5.22, steps = 49 00:50:48 [INFO] train episode 11958: reward = -13.26, steps = 30 00:50:48 [INFO] train episode 11959: reward = 1.27, steps = 51 00:50:48 [INFO] train episode 11960: reward = -15.60, steps = 48 00:50:48 [INFO] train episode 11961: reward = -4.97, steps = 34 00:50:49 [INFO] train episode 11962: reward = -29.56, steps = 25 00:50:49 [INFO] train episode 11963: reward = 1.68, steps = 37 00:50:49 [INFO] train episode 11964: reward = -29.23, steps = 35 00:50:50 [INFO] train episode 11965: reward = -11.61, steps = 37 00:50:50 [INFO] train episode 11966: reward = -23.30, steps = 34 00:50:50 [INFO] train episode 11967: reward = -11.34, steps = 36 00:50:50 [INFO] train episode 11968: reward = 0.38, steps = 43 00:50:51 [INFO] train episode 11969: reward = -2.43, steps = 48 00:50:51 [INFO] train episode 11970: reward = 1.78, steps = 39 00:50:51 [INFO] train episode 11971: reward = 1.35, steps = 41 00:50:52 [INFO] train episode 11972: reward = 10.07, steps = 53 00:50:52 [INFO] train episode 11973: reward = -17.55, steps = 34 00:50:52 [INFO] train episode 11974: reward = -13.45, steps = 37 00:50:53 [INFO] train episode 11975: reward = -11.60, steps = 57 00:50:53 [INFO] train episode 11976: reward = -6.16, steps = 47 00:50:53 [INFO] train episode 11977: reward = -13.36, steps = 23 00:50:53 [INFO] train episode 11978: reward = 9.30, steps = 55 00:50:54 [INFO] train episode 11979: reward = -8.64, steps = 32 00:50:54 [INFO] train episode 11980: reward = 5.73, steps = 44 00:50:54 [INFO] train episode 11981: reward = 5.34, steps = 38 00:50:54 [INFO] train episode 11982: reward = -7.02, steps = 30 00:50:55 [INFO] train episode 11983: reward = -6.99, steps = 46 00:50:55 [INFO] train episode 11984: reward = 7.24, steps = 56 00:50:55 [INFO] train episode 11985: reward = 9.70, steps = 49 00:50:56 [INFO] train episode 11986: reward = -8.87, steps = 46 00:50:56 [INFO] train episode 11987: reward = -11.01, steps = 33 00:50:56 [INFO] train episode 11988: reward = -40.17, steps = 59 00:50:56 [INFO] train episode 11989: reward = -15.32, steps = 50 00:50:57 [INFO] train episode 11990: reward = -4.51, steps = 40 00:50:57 [INFO] train episode 11991: reward = -0.27, steps = 43 00:50:57 [INFO] train episode 11992: reward = -18.54, steps = 35 00:50:57 [INFO] train episode 11993: reward = -23.07, steps = 20 00:50:58 [INFO] train episode 11994: reward = 16.69, steps = 54 00:50:58 [INFO] train episode 11995: reward = -17.24, steps = 44 00:50:58 [INFO] train episode 11996: reward = -27.25, steps = 32 00:50:59 [INFO] train episode 11997: reward = -8.18, steps = 31 00:50:59 [INFO] train episode 11998: reward = -14.86, steps = 38 00:50:59 [INFO] train episode 11999: reward = 2.59, steps = 40 00:50:59 [INFO] train episode 12000: reward = -16.10, steps = 24 00:51:00 [INFO] train episode 12001: reward = -1.04, steps = 47 00:51:00 [INFO] train episode 12002: reward = -0.93, steps = 43 00:51:00 [INFO] train episode 12003: reward = 0.87, steps = 42 00:51:00 [INFO] train episode 12004: reward = -17.63, steps = 26 00:51:01 [INFO] train episode 12005: reward = -9.78, steps = 36 00:51:01 [INFO] train episode 12006: reward = -8.90, steps = 35 00:51:01 [INFO] train episode 12007: reward = 14.54, steps = 45 00:51:01 [INFO] train episode 12008: reward = 3.67, steps = 37 00:51:02 [INFO] train episode 12009: reward = -17.08, steps = 39 00:51:02 [INFO] train episode 12010: reward = 0.67, steps = 30 00:51:02 [INFO] train episode 12011: reward = 14.36, steps = 46 00:51:03 [INFO] train episode 12012: reward = -8.31, steps = 31 00:51:03 [INFO] train episode 12013: reward = -4.42, steps = 49 00:51:03 [INFO] train episode 12014: reward = 7.20, steps = 64 00:51:04 [INFO] train episode 12015: reward = 2.27, steps = 40 00:51:04 [INFO] train episode 12016: reward = -7.58, steps = 32 00:51:04 [INFO] train episode 12017: reward = -11.68, steps = 33 00:51:04 [INFO] train episode 12018: reward = 0.01, steps = 39 00:51:05 [INFO] train episode 12019: reward = -0.97, steps = 38 00:51:05 [INFO] train episode 12020: reward = -2.72, steps = 42 00:51:05 [INFO] train episode 12021: reward = -4.07, steps = 44 00:51:06 [INFO] train episode 12022: reward = 1.60, steps = 43 00:51:06 [INFO] train episode 12023: reward = 5.02, steps = 51 00:51:06 [INFO] train episode 12024: reward = 13.90, steps = 69 00:51:07 [INFO] train episode 12025: reward = -24.24, steps = 30 00:51:07 [INFO] train episode 12026: reward = 6.98, steps = 39 00:51:07 [INFO] train episode 12027: reward = 1.11, steps = 26 00:51:07 [INFO] train episode 12028: reward = -9.59, steps = 29 00:51:07 [INFO] train episode 12029: reward = -17.49, steps = 25 00:51:08 [INFO] train episode 12030: reward = 2.33, steps = 36 00:51:08 [INFO] train episode 12031: reward = -13.49, steps = 34 00:51:08 [INFO] train episode 12032: reward = 3.61, steps = 35 00:51:08 [INFO] train episode 12033: reward = -26.21, steps = 22 00:51:09 [INFO] train episode 12034: reward = -17.58, steps = 46 00:51:09 [INFO] train episode 12035: reward = 8.74, steps = 48 00:51:09 [INFO] train episode 12036: reward = 1.50, steps = 43 00:51:09 [INFO] train episode 12037: reward = -10.47, steps = 33 00:51:10 [INFO] train episode 12038: reward = 2.84, steps = 31 00:51:10 [INFO] train episode 12039: reward = -27.87, steps = 18 00:51:10 [INFO] train episode 12040: reward = 4.67, steps = 51 00:51:10 [INFO] train episode 12041: reward = -6.56, steps = 31 00:51:11 [INFO] train episode 12042: reward = -2.74, steps = 38 00:51:11 [INFO] train episode 12043: reward = 5.78, steps = 47 00:51:11 [INFO] train episode 12044: reward = -2.08, steps = 55 00:51:11 [INFO] train episode 12045: reward = -25.53, steps = 25 00:51:12 [INFO] train episode 12046: reward = 8.89, steps = 41 00:51:12 [INFO] train episode 12047: reward = -25.40, steps = 17 00:51:12 [INFO] train episode 12048: reward = -28.07, steps = 17 00:51:12 [INFO] train episode 12049: reward = 6.11, steps = 47 00:51:13 [INFO] train episode 12050: reward = -10.65, steps = 46 00:51:13 [INFO] train episode 12051: reward = -21.57, steps = 25 00:51:13 [INFO] train episode 12052: reward = -2.92, steps = 45 00:51:13 [INFO] train episode 12053: reward = 3.74, steps = 57 00:51:14 [INFO] train episode 12054: reward = -14.35, steps = 49 00:51:14 [INFO] train episode 12055: reward = -8.12, steps = 42 00:51:14 [INFO] train episode 12056: reward = 12.20, steps = 52 00:51:15 [INFO] train episode 12057: reward = 1.01, steps = 37 00:51:15 [INFO] train episode 12058: reward = -8.68, steps = 41 00:51:15 [INFO] train episode 12059: reward = -6.88, steps = 29 00:51:15 [INFO] train episode 12060: reward = 1.11, steps = 43 00:51:16 [INFO] train episode 12061: reward = 2.06, steps = 45 00:51:16 [INFO] train episode 12062: reward = 13.51, steps = 41 00:51:16 [INFO] train episode 12063: reward = -23.06, steps = 35 00:51:17 [INFO] train episode 12064: reward = -28.68, steps = 32 00:51:17 [INFO] train episode 12065: reward = 1.09, steps = 50 00:51:17 [INFO] train episode 12066: reward = -1.19, steps = 31 00:51:18 [INFO] train episode 12067: reward = -0.97, steps = 44 00:51:18 [INFO] train episode 12068: reward = 6.63, steps = 40 00:51:18 [INFO] train episode 12069: reward = 8.52, steps = 37 00:51:18 [INFO] train episode 12070: reward = 9.65, steps = 57 00:51:19 [INFO] train episode 12071: reward = 6.45, steps = 37 00:51:19 [INFO] train episode 12072: reward = 18.42, steps = 45 00:51:19 [INFO] train episode 12073: reward = -3.41, steps = 40 00:51:19 [INFO] train episode 12074: reward = -4.26, steps = 28 00:51:20 [INFO] train episode 12075: reward = -3.56, steps = 32 00:51:20 [INFO] train episode 12076: reward = -8.85, steps = 36 00:51:20 [INFO] train episode 12077: reward = -3.94, steps = 42 00:51:20 [INFO] train episode 12078: reward = 2.83, steps = 53 00:51:21 [INFO] train episode 12079: reward = -1.63, steps = 37 00:51:21 [INFO] train episode 12080: reward = -18.95, steps = 36 00:51:21 [INFO] train episode 12081: reward = -6.85, steps = 38 00:51:21 [INFO] train episode 12082: reward = -12.03, steps = 34 00:51:22 [INFO] train episode 12083: reward = 1.15, steps = 51 00:51:22 [INFO] train episode 12084: reward = -11.93, steps = 25 00:51:22 [INFO] train episode 12085: reward = -22.04, steps = 22 00:51:22 [INFO] train episode 12086: reward = -6.42, steps = 48 00:51:23 [INFO] train episode 12087: reward = -21.31, steps = 26 00:51:23 [INFO] train episode 12088: reward = -5.50, steps = 49 00:51:23 [INFO] train episode 12089: reward = 10.41, steps = 53 00:51:24 [INFO] train episode 12090: reward = -8.77, steps = 35 00:51:24 [INFO] train episode 12091: reward = -15.15, steps = 26 00:51:24 [INFO] train episode 12092: reward = 2.46, steps = 42 00:51:24 [INFO] train episode 12093: reward = -7.31, steps = 40 00:51:25 [INFO] train episode 12094: reward = 2.28, steps = 37 00:51:25 [INFO] train episode 12095: reward = 2.95, steps = 36 00:51:25 [INFO] train episode 12096: reward = -8.07, steps = 33 00:51:25 [INFO] train episode 12097: reward = 6.32, steps = 44 00:51:26 [INFO] train episode 12098: reward = -13.34, steps = 19 00:51:26 [INFO] train episode 12099: reward = -12.82, steps = 22 00:51:26 [INFO] train episode 12100: reward = -3.18, steps = 34 00:51:26 [INFO] train episode 12101: reward = 0.62, steps = 29 00:51:26 [INFO] train episode 12102: reward = -8.04, steps = 45 00:51:27 [INFO] train episode 12103: reward = -17.03, steps = 26 00:51:27 [INFO] train episode 12104: reward = -11.28, steps = 30 00:51:27 [INFO] train episode 12105: reward = -23.38, steps = 28 00:51:27 [INFO] train episode 12106: reward = -6.33, steps = 35 00:51:27 [INFO] train episode 12107: reward = 2.24, steps = 41 00:51:28 [INFO] train episode 12108: reward = -15.43, steps = 33 00:51:28 [INFO] train episode 12109: reward = 3.81, steps = 34 00:51:28 [INFO] train episode 12110: reward = 10.56, steps = 40 00:51:28 [INFO] train episode 12111: reward = -5.40, steps = 41 00:51:29 [INFO] train episode 12112: reward = -14.78, steps = 22 00:51:29 [INFO] train episode 12113: reward = -14.21, steps = 25 00:51:29 [INFO] train episode 12114: reward = -11.53, steps = 28 00:51:29 [INFO] train episode 12115: reward = 4.72, steps = 33 00:51:30 [INFO] train episode 12116: reward = -29.68, steps = 33 00:51:30 [INFO] train episode 12117: reward = -7.50, steps = 39 00:51:30 [INFO] train episode 12118: reward = 19.02, steps = 55 00:51:31 [INFO] train episode 12119: reward = -13.23, steps = 41 00:51:31 [INFO] train episode 12120: reward = 13.46, steps = 44 00:51:31 [INFO] train episode 12121: reward = -18.52, steps = 19 00:51:31 [INFO] train episode 12122: reward = 21.70, steps = 57 00:51:32 [INFO] train episode 12123: reward = 3.43, steps = 41 00:51:32 [INFO] train episode 12124: reward = 1.89, steps = 41 00:51:32 [INFO] train episode 12125: reward = -4.14, steps = 30 00:51:32 [INFO] train episode 12126: reward = -17.57, steps = 25 00:51:32 [INFO] train episode 12127: reward = -2.62, steps = 33 00:51:33 [INFO] train episode 12128: reward = 18.82, steps = 44 00:51:33 [INFO] train episode 12129: reward = -5.32, steps = 40 00:51:33 [INFO] train episode 12130: reward = 8.09, steps = 34 00:51:33 [INFO] train episode 12131: reward = -30.41, steps = 23 00:51:34 [INFO] train episode 12132: reward = 9.21, steps = 37 00:51:34 [INFO] train episode 12133: reward = -1.21, steps = 36 00:51:34 [INFO] train episode 12134: reward = -0.68, steps = 47 00:51:34 [INFO] train episode 12135: reward = 5.60, steps = 40 00:51:35 [INFO] train episode 12136: reward = 10.24, steps = 51 00:51:35 [INFO] train episode 12137: reward = -0.30, steps = 37 00:51:35 [INFO] train episode 12138: reward = -24.07, steps = 48 00:51:36 [INFO] train episode 12139: reward = -7.94, steps = 29 00:51:36 [INFO] train episode 12140: reward = -18.22, steps = 26 00:51:36 [INFO] train episode 12141: reward = 19.83, steps = 45 00:51:36 [INFO] train episode 12142: reward = -6.37, steps = 41 00:51:37 [INFO] train episode 12143: reward = 2.24, steps = 38 00:51:37 [INFO] train episode 12144: reward = 1.87, steps = 34 00:51:37 [INFO] train episode 12145: reward = -11.24, steps = 38 00:51:37 [INFO] train episode 12146: reward = -36.65, steps = 19 00:51:37 [INFO] train episode 12147: reward = -18.71, steps = 27 00:51:38 [INFO] train episode 12148: reward = 2.61, steps = 49 00:51:38 [INFO] train episode 12149: reward = -31.36, steps = 25 00:51:38 [INFO] train episode 12150: reward = -23.40, steps = 23 00:51:38 [INFO] train episode 12151: reward = 3.74, steps = 44 00:51:39 [INFO] train episode 12152: reward = 3.37, steps = 45 00:51:39 [INFO] train episode 12153: reward = 1.57, steps = 34 00:51:39 [INFO] train episode 12154: reward = -7.44, steps = 35 00:51:39 [INFO] train episode 12155: reward = -1.90, steps = 42 00:51:40 [INFO] train episode 12156: reward = -19.76, steps = 19 00:51:40 [INFO] train episode 12157: reward = 0.94, steps = 48 00:51:40 [INFO] train episode 12158: reward = -18.57, steps = 30 00:51:40 [INFO] train episode 12159: reward = -16.66, steps = 27 00:51:41 [INFO] train episode 12160: reward = 23.49, steps = 55 00:51:41 [INFO] train episode 12161: reward = -11.40, steps = 34 00:51:41 [INFO] train episode 12162: reward = 2.43, steps = 34 00:51:41 [INFO] train episode 12163: reward = 2.02, steps = 35 00:51:42 [INFO] train episode 12164: reward = 4.86, steps = 39 00:51:42 [INFO] train episode 12165: reward = -5.91, steps = 44 00:51:42 [INFO] train episode 12166: reward = 12.23, steps = 46 00:51:42 [INFO] train episode 12167: reward = 2.96, steps = 40 00:51:43 [INFO] train episode 12168: reward = 3.07, steps = 43 00:51:43 [INFO] train episode 12169: reward = 23.22, steps = 56 00:51:44 [INFO] train episode 12170: reward = 4.76, steps = 38 00:51:44 [INFO] train episode 12171: reward = -2.35, steps = 33 00:51:44 [INFO] train episode 12172: reward = 19.93, steps = 51 00:51:44 [INFO] train episode 12173: reward = 5.19, steps = 35 00:51:45 [INFO] train episode 12174: reward = -1.84, steps = 43 00:51:45 [INFO] train episode 12175: reward = -7.91, steps = 31 00:51:45 [INFO] train episode 12176: reward = 2.53, steps = 45 00:51:45 [INFO] train episode 12177: reward = 0.80, steps = 37 00:51:46 [INFO] train episode 12178: reward = 3.64, steps = 46 00:51:46 [INFO] train episode 12179: reward = -19.30, steps = 20 00:51:46 [INFO] train episode 12180: reward = 4.40, steps = 43 00:51:46 [INFO] train episode 12181: reward = -2.10, steps = 43 00:51:47 [INFO] train episode 12182: reward = 5.08, steps = 31 00:51:47 [INFO] train episode 12183: reward = -18.80, steps = 24 00:51:47 [INFO] train episode 12184: reward = -10.19, steps = 28 00:51:47 [INFO] train episode 12185: reward = 7.18, steps = 43 00:51:47 [INFO] train episode 12186: reward = -19.43, steps = 19 00:51:48 [INFO] train episode 12187: reward = 5.37, steps = 45 00:51:48 [INFO] train episode 12188: reward = -8.00, steps = 30 00:51:48 [INFO] train episode 12189: reward = -10.60, steps = 39 00:51:48 [INFO] train episode 12190: reward = 7.40, steps = 36 00:51:49 [INFO] train episode 12191: reward = 13.32, steps = 36 00:51:49 [INFO] train episode 12192: reward = 12.84, steps = 36 00:51:49 [INFO] train episode 12193: reward = -0.67, steps = 39 00:51:50 [INFO] train episode 12194: reward = 10.48, steps = 38 00:51:50 [INFO] train episode 12195: reward = 19.20, steps = 43 00:51:50 [INFO] train episode 12196: reward = 0.06, steps = 32 00:51:50 [INFO] train episode 12197: reward = 0.58, steps = 33 00:51:51 [INFO] train episode 12198: reward = 9.38, steps = 38 00:51:51 [INFO] train episode 12199: reward = 18.31, steps = 41 00:51:51 [INFO] train episode 12200: reward = -12.55, steps = 29 00:51:51 [INFO] train episode 12201: reward = -8.15, steps = 37 00:51:51 [INFO] train episode 12202: reward = 1.96, steps = 39 00:51:52 [INFO] train episode 12203: reward = -20.04, steps = 23 00:51:52 [INFO] train episode 12204: reward = 12.55, steps = 37 00:51:52 [INFO] train episode 12205: reward = 12.97, steps = 43 00:51:52 [INFO] train episode 12206: reward = 5.91, steps = 38 00:51:53 [INFO] train episode 12207: reward = 19.42, steps = 50 00:51:53 [INFO] train episode 12208: reward = 14.11, steps = 42 00:51:53 [INFO] train episode 12209: reward = -22.20, steps = 37 00:51:53 [INFO] train episode 12210: reward = -19.83, steps = 25 00:51:54 [INFO] train episode 12211: reward = -21.20, steps = 23 00:51:54 [INFO] train episode 12212: reward = 11.09, steps = 38 00:51:54 [INFO] train episode 12213: reward = -17.19, steps = 31 00:51:54 [INFO] train episode 12214: reward = 7.40, steps = 53 00:51:55 [INFO] train episode 12215: reward = -1.58, steps = 35 00:51:55 [INFO] train episode 12216: reward = -1.56, steps = 36 00:51:55 [INFO] train episode 12217: reward = 12.11, steps = 36 00:51:55 [INFO] train episode 12218: reward = 4.87, steps = 39 00:51:56 [INFO] train episode 12219: reward = 8.09, steps = 35 00:51:56 [INFO] train episode 12220: reward = -42.22, steps = 18 00:51:56 [INFO] train episode 12221: reward = 8.41, steps = 36 00:51:57 [INFO] train episode 12222: reward = -1.99, steps = 40 00:51:57 [INFO] train episode 12223: reward = -25.43, steps = 21 00:51:57 [INFO] train episode 12224: reward = 14.23, steps = 43 00:51:57 [INFO] train episode 12225: reward = 4.64, steps = 38 00:51:58 [INFO] train episode 12226: reward = 19.40, steps = 45 00:51:58 [INFO] train episode 12227: reward = -34.43, steps = 29 00:51:58 [INFO] train episode 12228: reward = 1.68, steps = 26 00:51:58 [INFO] train episode 12229: reward = -16.20, steps = 20 00:51:58 [INFO] train episode 12230: reward = 9.24, steps = 41 00:51:59 [INFO] train episode 12231: reward = 7.33, steps = 32 00:51:59 [INFO] train episode 12232: reward = -1.89, steps = 36 00:51:59 [INFO] train episode 12233: reward = 9.12, steps = 39 00:51:59 [INFO] train episode 12234: reward = -0.26, steps = 32 00:52:00 [INFO] train episode 12235: reward = 11.64, steps = 37 00:52:00 [INFO] train episode 12236: reward = -5.76, steps = 26 00:52:00 [INFO] train episode 12237: reward = 10.69, steps = 33 00:52:00 [INFO] train episode 12238: reward = -14.65, steps = 22 00:52:00 [INFO] train episode 12239: reward = 0.14, steps = 39 00:52:01 [INFO] train episode 12240: reward = -6.83, steps = 26 00:52:01 [INFO] train episode 12241: reward = 4.72, steps = 39 00:52:01 [INFO] train episode 12242: reward = 5.21, steps = 39 00:52:01 [INFO] train episode 12243: reward = 8.44, steps = 41 00:52:02 [INFO] train episode 12244: reward = -22.43, steps = 21 00:52:02 [INFO] train episode 12245: reward = 15.08, steps = 48 00:52:02 [INFO] train episode 12246: reward = 8.91, steps = 39 00:52:03 [INFO] train episode 12247: reward = 16.19, steps = 52 00:52:03 [INFO] train episode 12248: reward = 5.33, steps = 43 00:52:03 [INFO] train episode 12249: reward = 18.04, steps = 47 00:52:03 [INFO] train episode 12250: reward = 3.36, steps = 39 00:52:04 [INFO] train episode 12251: reward = 9.86, steps = 34 00:52:04 [INFO] train episode 12252: reward = -8.79, steps = 27 00:52:04 [INFO] train episode 12253: reward = 3.01, steps = 36 00:52:04 [INFO] train episode 12254: reward = 6.23, steps = 54 00:52:05 [INFO] train episode 12255: reward = -10.24, steps = 34 00:52:05 [INFO] train episode 12256: reward = -20.12, steps = 19 00:52:05 [INFO] train episode 12257: reward = -17.79, steps = 23 00:52:05 [INFO] train episode 12258: reward = -3.61, steps = 36 00:52:05 [INFO] train episode 12259: reward = -3.32, steps = 39 00:52:06 [INFO] train episode 12260: reward = -35.94, steps = 19 00:52:06 [INFO] train episode 12261: reward = 6.50, steps = 35 00:52:06 [INFO] train episode 12262: reward = -6.40, steps = 28 00:52:06 [INFO] train episode 12263: reward = 12.56, steps = 41 00:52:06 [INFO] train episode 12264: reward = 5.17, steps = 35 00:52:07 [INFO] train episode 12265: reward = 1.87, steps = 37 00:52:07 [INFO] train episode 12266: reward = 15.62, steps = 38 00:52:07 [INFO] train episode 12267: reward = 4.34, steps = 36 00:52:08 [INFO] train episode 12268: reward = 12.15, steps = 45 00:52:08 [INFO] train episode 12269: reward = 0.61, steps = 31 00:52:08 [INFO] train episode 12270: reward = 5.87, steps = 37 00:52:08 [INFO] train episode 12271: reward = -1.97, steps = 46 00:52:09 [INFO] train episode 12272: reward = -18.30, steps = 38 00:52:09 [INFO] train episode 12273: reward = 8.99, steps = 40 00:52:09 [INFO] train episode 12274: reward = 12.46, steps = 41 00:52:09 [INFO] train episode 12275: reward = 5.14, steps = 44 00:52:10 [INFO] train episode 12276: reward = 2.15, steps = 41 00:52:10 [INFO] train episode 12277: reward = 12.72, steps = 44 00:52:10 [INFO] train episode 12278: reward = 11.46, steps = 37 00:52:11 [INFO] train episode 12279: reward = 12.33, steps = 42 00:52:11 [INFO] train episode 12280: reward = -2.91, steps = 34 00:52:11 [INFO] train episode 12281: reward = 3.53, steps = 40 00:52:12 [INFO] train episode 12282: reward = -12.72, steps = 49 00:52:12 [INFO] train episode 12283: reward = 2.24, steps = 34 00:52:12 [INFO] train episode 12284: reward = -2.71, steps = 32 00:52:12 [INFO] train episode 12285: reward = 0.90, steps = 41 00:52:12 [INFO] train episode 12286: reward = 8.38, steps = 39 00:52:13 [INFO] train episode 12287: reward = -9.11, steps = 39 00:52:13 [INFO] train episode 12288: reward = 9.55, steps = 44 00:52:13 [INFO] train episode 12289: reward = 5.21, steps = 32 00:52:13 [INFO] train episode 12290: reward = -5.82, steps = 34 00:52:14 [INFO] train episode 12291: reward = -46.21, steps = 17 00:52:14 [INFO] train episode 12292: reward = 0.35, steps = 38 00:52:14 [INFO] train episode 12293: reward = -17.46, steps = 26 00:52:14 [INFO] train episode 12294: reward = 6.16, steps = 32 00:52:15 [INFO] train episode 12295: reward = 21.60, steps = 44 00:52:15 [INFO] train episode 12296: reward = 22.14, steps = 49 00:52:15 [INFO] train episode 12297: reward = -10.88, steps = 64 00:52:16 [INFO] train episode 12298: reward = 6.84, steps = 35 00:52:16 [INFO] train episode 12299: reward = -6.31, steps = 33 00:52:16 [INFO] train episode 12300: reward = -10.83, steps = 30 00:52:16 [INFO] train episode 12301: reward = -27.53, steps = 16 00:52:16 [INFO] train episode 12302: reward = -13.39, steps = 26 00:52:17 [INFO] train episode 12303: reward = 12.27, steps = 43 00:52:17 [INFO] train episode 12304: reward = -1.39, steps = 34 00:52:17 [INFO] train episode 12305: reward = -16.75, steps = 23 00:52:17 [INFO] train episode 12306: reward = 8.62, steps = 38 00:52:17 [INFO] train episode 12307: reward = 1.97, steps = 38 00:52:18 [INFO] train episode 12308: reward = -2.50, steps = 31 00:52:18 [INFO] train episode 12309: reward = -25.33, steps = 31 00:52:18 [INFO] train episode 12310: reward = 19.44, steps = 41 00:52:18 [INFO] train episode 12311: reward = 10.96, steps = 43 00:52:19 [INFO] train episode 12312: reward = -9.05, steps = 36 00:52:19 [INFO] train episode 12313: reward = 13.45, steps = 52 00:52:19 [INFO] train episode 12314: reward = 16.62, steps = 41 00:52:20 [INFO] train episode 12315: reward = 16.86, steps = 44 00:52:20 [INFO] train episode 12316: reward = -14.45, steps = 21 00:52:20 [INFO] train episode 12317: reward = 10.95, steps = 48 00:52:20 [INFO] train episode 12318: reward = -3.71, steps = 35 00:52:20 [INFO] train episode 12319: reward = 3.23, steps = 35 00:52:21 [INFO] train episode 12320: reward = 6.78, steps = 33 00:52:21 [INFO] train episode 12321: reward = 14.14, steps = 47 00:52:21 [INFO] train episode 12322: reward = -6.21, steps = 27 00:52:21 [INFO] train episode 12323: reward = 12.84, steps = 36 00:52:22 [INFO] train episode 12324: reward = 11.25, steps = 47 00:52:22 [INFO] train episode 12325: reward = -5.64, steps = 32 00:52:22 [INFO] train episode 12326: reward = 19.87, steps = 47 00:52:23 [INFO] train episode 12327: reward = -6.95, steps = 31 00:52:23 [INFO] train episode 12328: reward = -24.56, steps = 36 00:52:23 [INFO] train episode 12329: reward = 10.04, steps = 44 00:52:24 [INFO] train episode 12330: reward = 4.36, steps = 45 00:52:24 [INFO] train episode 12331: reward = -14.36, steps = 35 00:52:24 [INFO] train episode 12332: reward = -3.16, steps = 31 00:52:24 [INFO] train episode 12333: reward = 8.47, steps = 44 00:52:25 [INFO] train episode 12334: reward = 22.40, steps = 40 00:52:25 [INFO] train episode 12335: reward = -31.44, steps = 18 00:52:25 [INFO] train episode 12336: reward = 15.42, steps = 46 00:52:25 [INFO] train episode 12337: reward = 11.40, steps = 39 00:52:26 [INFO] train episode 12338: reward = 21.21, steps = 48 00:52:26 [INFO] train episode 12339: reward = 0.13, steps = 28 00:52:26 [INFO] train episode 12340: reward = 9.70, steps = 38 00:52:26 [INFO] train episode 12341: reward = 1.54, steps = 50 00:52:27 [INFO] train episode 12342: reward = -1.58, steps = 32 00:52:27 [INFO] train episode 12343: reward = -8.34, steps = 27 00:52:27 [INFO] train episode 12344: reward = 1.74, steps = 35 00:52:27 [INFO] train episode 12345: reward = 10.02, steps = 41 00:52:28 [INFO] train episode 12346: reward = 10.40, steps = 40 00:52:28 [INFO] train episode 12347: reward = -5.56, steps = 40 00:52:28 [INFO] train episode 12348: reward = -2.95, steps = 34 00:52:28 [INFO] train episode 12349: reward = 4.43, steps = 34 00:52:28 [INFO] train episode 12350: reward = -9.55, steps = 31 00:52:29 [INFO] train episode 12351: reward = -3.29, steps = 36 00:52:29 [INFO] train episode 12352: reward = 1.97, steps = 36 00:52:29 [INFO] train episode 12353: reward = -20.12, steps = 18 00:52:29 [INFO] train episode 12354: reward = 23.56, steps = 46 00:52:30 [INFO] train episode 12355: reward = -11.77, steps = 36 00:52:30 [INFO] train episode 12356: reward = -5.97, steps = 31 00:52:30 [INFO] train episode 12357: reward = 12.38, steps = 47 00:52:30 [INFO] train episode 12358: reward = -8.70, steps = 33 00:52:31 [INFO] train episode 12359: reward = 15.00, steps = 38 00:52:31 [INFO] train episode 12360: reward = -17.37, steps = 21 00:52:31 [INFO] train episode 12361: reward = 3.88, steps = 41 00:52:31 [INFO] train episode 12362: reward = -15.47, steps = 19 00:52:31 [INFO] train episode 12363: reward = -3.90, steps = 29 00:52:32 [INFO] train episode 12364: reward = 8.45, steps = 44 00:52:32 [INFO] train episode 12365: reward = -6.76, steps = 33 00:52:32 [INFO] train episode 12366: reward = -8.25, steps = 30 00:52:32 [INFO] train episode 12367: reward = 12.49, steps = 37 00:52:33 [INFO] train episode 12368: reward = 9.03, steps = 36 00:52:33 [INFO] train episode 12369: reward = 11.10, steps = 34 00:52:33 [INFO] train episode 12370: reward = -17.19, steps = 19 00:52:33 [INFO] train episode 12371: reward = -9.58, steps = 28 00:52:33 [INFO] train episode 12372: reward = 7.10, steps = 38 00:52:34 [INFO] train episode 12373: reward = 6.87, steps = 35 00:52:34 [INFO] train episode 12374: reward = -2.11, steps = 33 00:52:34 [INFO] train episode 12375: reward = 6.93, steps = 36 00:52:34 [INFO] train episode 12376: reward = -4.60, steps = 28 00:52:35 [INFO] train episode 12377: reward = 1.52, steps = 54 00:52:35 [INFO] train episode 12378: reward = 1.94, steps = 37 00:52:35 [INFO] train episode 12379: reward = 4.40, steps = 38 00:52:35 [INFO] train episode 12380: reward = -8.14, steps = 31 00:52:36 [INFO] train episode 12381: reward = -1.69, steps = 50 00:52:36 [INFO] train episode 12382: reward = 15.10, steps = 46 00:52:36 [INFO] train episode 12383: reward = 2.19, steps = 38 00:52:37 [INFO] train episode 12384: reward = -0.04, steps = 35 00:52:37 [INFO] train episode 12385: reward = 7.98, steps = 31 00:52:37 [INFO] train episode 12386: reward = 10.83, steps = 43 00:52:37 [INFO] train episode 12387: reward = -7.07, steps = 30 00:52:38 [INFO] train episode 12388: reward = 11.48, steps = 36 00:52:38 [INFO] train episode 12389: reward = 3.49, steps = 36 00:52:38 [INFO] train episode 12390: reward = -15.36, steps = 22 00:52:38 [INFO] train episode 12391: reward = 8.94, steps = 41 00:52:39 [INFO] train episode 12392: reward = 13.99, steps = 49 00:52:39 [INFO] train episode 12393: reward = 12.73, steps = 36 00:52:39 [INFO] train episode 12394: reward = 6.05, steps = 30 00:52:39 [INFO] train episode 12395: reward = -4.68, steps = 29 00:52:39 [INFO] train episode 12396: reward = -16.81, steps = 20 00:52:40 [INFO] train episode 12397: reward = 5.24, steps = 38 00:52:40 [INFO] train episode 12398: reward = 14.75, steps = 60 00:52:40 [INFO] train episode 12399: reward = 17.32, steps = 48 00:52:41 [INFO] train episode 12400: reward = 1.30, steps = 36 00:52:41 [INFO] train episode 12401: reward = 15.65, steps = 39 00:52:41 [INFO] train episode 12402: reward = 11.19, steps = 48 00:52:42 [INFO] train episode 12403: reward = 0.25, steps = 34 00:52:42 [INFO] train episode 12404: reward = 5.88, steps = 33 00:52:42 [INFO] train episode 12405: reward = 17.77, steps = 40 00:52:42 [INFO] train episode 12406: reward = 11.65, steps = 44 00:52:42 [INFO] train episode 12407: reward = -1.63, steps = 32 00:52:43 [INFO] train episode 12408: reward = 2.30, steps = 43 00:52:43 [INFO] train episode 12409: reward = -6.79, steps = 34 00:52:43 [INFO] train episode 12410: reward = 10.56, steps = 34 00:52:43 [INFO] train episode 12411: reward = -21.88, steps = 21 00:52:44 [INFO] train episode 12412: reward = 24.99, steps = 51 00:52:44 [INFO] train episode 12413: reward = 7.92, steps = 36 00:52:44 [INFO] train episode 12414: reward = 10.15, steps = 40 00:52:45 [INFO] train episode 12415: reward = 15.67, steps = 51 00:52:45 [INFO] train episode 12416: reward = 4.37, steps = 39 00:52:45 [INFO] train episode 12417: reward = -3.07, steps = 40 00:52:45 [INFO] train episode 12418: reward = 12.32, steps = 40 00:52:46 [INFO] train episode 12419: reward = 4.24, steps = 39 00:52:46 [INFO] train episode 12420: reward = -32.45, steps = 14 00:52:46 [INFO] train episode 12421: reward = -16.41, steps = 31 00:52:46 [INFO] train episode 12422: reward = 12.98, steps = 48 00:52:47 [INFO] train episode 12423: reward = -0.23, steps = 35 00:52:47 [INFO] train episode 12424: reward = -7.82, steps = 38 00:52:47 [INFO] train episode 12425: reward = 5.14, steps = 33 00:52:47 [INFO] train episode 12426: reward = 9.67, steps = 33 00:52:47 [INFO] train episode 12427: reward = 8.69, steps = 39 00:52:48 [INFO] train episode 12428: reward = 19.87, steps = 59 00:52:48 [INFO] train episode 12429: reward = 16.53, steps = 49 00:52:48 [INFO] train episode 12430: reward = 10.71, steps = 44 00:52:49 [INFO] train episode 12431: reward = -11.77, steps = 22 00:52:49 [INFO] train episode 12432: reward = -1.17, steps = 34 00:52:49 [INFO] train episode 12433: reward = -8.37, steps = 39 00:52:49 [INFO] train episode 12434: reward = -17.23, steps = 36 00:52:50 [INFO] train episode 12435: reward = 5.33, steps = 39 00:52:50 [INFO] train episode 12436: reward = -45.85, steps = 17 00:52:50 [INFO] train episode 12437: reward = 4.56, steps = 38 00:52:51 [INFO] train episode 12438: reward = 10.19, steps = 45 00:52:51 [INFO] train episode 12439: reward = 9.90, steps = 47 00:52:51 [INFO] train episode 12440: reward = -1.30, steps = 37 00:52:51 [INFO] train episode 12441: reward = -5.56, steps = 41 00:52:52 [INFO] train episode 12442: reward = 3.51, steps = 32 00:52:52 [INFO] train episode 12443: reward = 14.00, steps = 42 00:52:52 [INFO] train episode 12444: reward = 10.91, steps = 43 00:52:52 [INFO] train episode 12445: reward = -4.87, steps = 35 00:52:53 [INFO] train episode 12446: reward = -10.51, steps = 35 00:52:53 [INFO] train episode 12447: reward = -0.23, steps = 37 00:52:53 [INFO] train episode 12448: reward = 5.04, steps = 37 00:52:53 [INFO] train episode 12449: reward = -25.58, steps = 22 00:52:54 [INFO] train episode 12450: reward = -3.42, steps = 42 00:52:54 [INFO] train episode 12451: reward = 11.37, steps = 35 00:52:54 [INFO] train episode 12452: reward = 18.61, steps = 61 00:52:54 [INFO] train episode 12453: reward = 14.47, steps = 46 00:52:55 [INFO] train episode 12454: reward = -26.38, steps = 17 00:52:55 [INFO] train episode 12455: reward = 7.94, steps = 41 00:52:55 [INFO] train episode 12456: reward = 4.18, steps = 45 00:52:55 [INFO] train episode 12457: reward = -1.92, steps = 41 00:52:56 [INFO] train episode 12458: reward = -11.45, steps = 41 00:52:56 [INFO] train episode 12459: reward = 8.83, steps = 44 00:52:56 [INFO] train episode 12460: reward = 3.71, steps = 38 00:52:56 [INFO] train episode 12461: reward = -19.97, steps = 26 00:52:57 [INFO] train episode 12462: reward = -5.44, steps = 40 00:52:57 [INFO] train episode 12463: reward = 1.80, steps = 44 00:52:57 [INFO] train episode 12464: reward = -25.09, steps = 19 00:52:57 [INFO] train episode 12465: reward = 7.78, steps = 45 00:52:58 [INFO] train episode 12466: reward = 11.38, steps = 39 00:52:58 [INFO] train episode 12467: reward = 12.24, steps = 39 00:52:58 [INFO] train episode 12468: reward = -12.36, steps = 18 00:52:58 [INFO] train episode 12469: reward = -1.42, steps = 38 00:52:59 [INFO] train episode 12470: reward = 12.20, steps = 46 00:52:59 [INFO] train episode 12471: reward = 4.28, steps = 34 00:52:59 [INFO] train episode 12472: reward = 10.65, steps = 41 00:52:59 [INFO] train episode 12473: reward = -19.84, steps = 25 00:53:00 [INFO] train episode 12474: reward = -0.46, steps = 45 00:53:00 [INFO] train episode 12475: reward = 9.09, steps = 39 00:53:00 [INFO] train episode 12476: reward = 1.73, steps = 43 00:53:00 [INFO] train episode 12477: reward = -15.77, steps = 19 00:53:01 [INFO] train episode 12478: reward = 21.04, steps = 46 00:53:01 [INFO] train episode 12479: reward = 24.92, steps = 47 00:53:01 [INFO] train episode 12480: reward = -25.96, steps = 26 00:53:01 [INFO] train episode 12481: reward = 0.02, steps = 36 00:53:02 [INFO] train episode 12482: reward = 8.86, steps = 36 00:53:02 [INFO] train episode 12483: reward = -20.95, steps = 23 00:53:02 [INFO] train episode 12484: reward = 10.51, steps = 34 00:53:02 [INFO] train episode 12485: reward = 9.53, steps = 34 00:53:03 [INFO] train episode 12486: reward = 5.24, steps = 33 00:53:03 [INFO] train episode 12487: reward = -2.93, steps = 32 00:53:03 [INFO] train episode 12488: reward = 7.19, steps = 37 00:53:03 [INFO] train episode 12489: reward = 11.37, steps = 38 00:53:04 [INFO] train episode 12490: reward = 5.66, steps = 39 00:53:04 [INFO] train episode 12491: reward = 9.19, steps = 41 00:53:04 [INFO] train episode 12492: reward = 0.50, steps = 34 00:53:05 [INFO] train episode 12493: reward = 21.28, steps = 49 00:53:05 [INFO] train episode 12494: reward = -2.30, steps = 29 00:53:05 [INFO] train episode 12495: reward = 10.98, steps = 37 00:53:06 [INFO] train episode 12496: reward = 0.48, steps = 44 00:53:06 [INFO] train episode 12497: reward = 2.27, steps = 37 00:53:06 [INFO] train episode 12498: reward = 8.62, steps = 37 00:53:06 [INFO] train episode 12499: reward = 4.66, steps = 41 00:53:07 [INFO] train episode 12500: reward = -7.69, steps = 47 00:53:07 [INFO] train episode 12501: reward = 0.16, steps = 29 00:53:07 [INFO] train episode 12502: reward = -19.46, steps = 19 00:53:07 [INFO] train episode 12503: reward = 18.00, steps = 50 00:53:08 [INFO] train episode 12504: reward = 2.06, steps = 41 00:53:08 [INFO] train episode 12505: reward = 0.15, steps = 32 00:53:08 [INFO] train episode 12506: reward = -7.81, steps = 38 00:53:08 [INFO] train episode 12507: reward = 2.08, steps = 36 00:53:09 [INFO] train episode 12508: reward = -9.55, steps = 30 00:53:09 [INFO] train episode 12509: reward = 4.85, steps = 36 00:53:09 [INFO] train episode 12510: reward = 13.68, steps = 32 00:53:09 [INFO] train episode 12511: reward = -10.87, steps = 41 00:53:10 [INFO] train episode 12512: reward = -3.73, steps = 30 00:53:10 [INFO] train episode 12513: reward = -5.95, steps = 44 00:53:10 [INFO] train episode 12514: reward = 12.26, steps = 40 00:53:10 [INFO] train episode 12515: reward = -12.92, steps = 31 00:53:11 [INFO] train episode 12516: reward = 8.07, steps = 51 00:53:11 [INFO] train episode 12517: reward = -7.50, steps = 32 00:53:11 [INFO] train episode 12518: reward = -8.22, steps = 23 00:53:11 [INFO] train episode 12519: reward = 3.10, steps = 35 00:53:12 [INFO] train episode 12520: reward = 6.51, steps = 46 00:53:12 [INFO] train episode 12521: reward = 15.58, steps = 43 00:53:12 [INFO] train episode 12522: reward = 20.34, steps = 52 00:53:12 [INFO] train episode 12523: reward = -2.57, steps = 29 00:53:13 [INFO] train episode 12524: reward = -0.75, steps = 36 00:53:13 [INFO] train episode 12525: reward = 3.98, steps = 37 00:53:13 [INFO] train episode 12526: reward = 0.33, steps = 45 00:53:13 [INFO] train episode 12527: reward = -7.42, steps = 31 00:53:14 [INFO] train episode 12528: reward = -2.45, steps = 35 00:53:14 [INFO] train episode 12529: reward = 0.05, steps = 37 00:53:14 [INFO] train episode 12530: reward = 6.82, steps = 40 00:53:14 [INFO] train episode 12531: reward = 9.17, steps = 41 00:53:15 [INFO] train episode 12532: reward = -5.93, steps = 38 00:53:15 [INFO] train episode 12533: reward = -5.33, steps = 34 00:53:15 [INFO] train episode 12534: reward = -11.10, steps = 29 00:53:15 [INFO] train episode 12535: reward = -4.27, steps = 34 00:53:16 [INFO] train episode 12536: reward = -1.15, steps = 33 00:53:16 [INFO] train episode 12537: reward = 5.95, steps = 40 00:53:16 [INFO] train episode 12538: reward = 23.76, steps = 45 00:53:16 [INFO] train episode 12539: reward = -9.69, steps = 25 00:53:17 [INFO] train episode 12540: reward = 1.14, steps = 39 00:53:17 [INFO] train episode 12541: reward = 7.14, steps = 43 00:53:17 [INFO] train episode 12542: reward = 18.57, steps = 39 00:53:17 [INFO] train episode 12543: reward = 9.24, steps = 32 00:53:18 [INFO] train episode 12544: reward = -21.52, steps = 21 00:53:18 [INFO] train episode 12545: reward = 0.04, steps = 49 00:53:18 [INFO] train episode 12546: reward = 1.97, steps = 40 00:53:19 [INFO] train episode 12547: reward = 17.98, steps = 41 00:53:19 [INFO] train episode 12548: reward = -14.69, steps = 38 00:53:19 [INFO] train episode 12549: reward = -8.09, steps = 41 00:53:19 [INFO] train episode 12550: reward = 0.66, steps = 39 00:53:20 [INFO] train episode 12551: reward = -6.41, steps = 42 00:53:20 [INFO] train episode 12552: reward = 21.35, steps = 40 00:53:20 [INFO] train episode 12553: reward = -5.35, steps = 29 00:53:20 [INFO] train episode 12554: reward = 5.89, steps = 36 00:53:21 [INFO] train episode 12555: reward = 9.81, steps = 47 00:53:21 [INFO] train episode 12556: reward = 0.20, steps = 33 00:53:21 [INFO] train episode 12557: reward = 9.45, steps = 39 00:53:21 [INFO] train episode 12558: reward = 10.75, steps = 49 00:53:22 [INFO] train episode 12559: reward = 4.54, steps = 33 00:53:22 [INFO] train episode 12560: reward = 12.27, steps = 38 00:53:22 [INFO] train episode 12561: reward = 11.24, steps = 40 00:53:23 [INFO] train episode 12562: reward = 10.18, steps = 36 00:53:23 [INFO] train episode 12563: reward = 14.57, steps = 40 00:53:23 [INFO] train episode 12564: reward = -4.13, steps = 31 00:53:23 [INFO] train episode 12565: reward = 3.38, steps = 41 00:53:24 [INFO] train episode 12566: reward = -0.23, steps = 48 00:53:24 [INFO] train episode 12567: reward = 0.15, steps = 43 00:53:24 [INFO] train episode 12568: reward = 0.09, steps = 45 00:53:24 [INFO] train episode 12569: reward = -0.17, steps = 33 00:53:25 [INFO] train episode 12570: reward = 17.72, steps = 49 00:53:25 [INFO] train episode 12571: reward = -17.15, steps = 30 00:53:25 [INFO] train episode 12572: reward = 6.96, steps = 46 00:53:25 [INFO] train episode 12573: reward = 2.07, steps = 35 00:53:26 [INFO] train episode 12574: reward = 8.61, steps = 37 00:53:26 [INFO] train episode 12575: reward = -4.74, steps = 33 00:53:26 [INFO] train episode 12576: reward = 2.63, steps = 42 00:53:26 [INFO] train episode 12577: reward = 11.03, steps = 38 00:53:27 [INFO] train episode 12578: reward = 5.62, steps = 41 00:53:27 [INFO] train episode 12579: reward = 11.74, steps = 40 00:53:27 [INFO] train episode 12580: reward = 13.01, steps = 35 00:53:27 [INFO] train episode 12581: reward = 9.53, steps = 41 00:53:28 [INFO] train episode 12582: reward = 13.12, steps = 42 00:53:28 [INFO] train episode 12583: reward = 11.90, steps = 47 00:53:28 [INFO] train episode 12584: reward = 4.74, steps = 36 00:53:29 [INFO] train episode 12585: reward = -6.89, steps = 33 00:53:29 [INFO] train episode 12586: reward = 4.82, steps = 30 00:53:29 [INFO] train episode 12587: reward = -20.87, steps = 33 00:53:29 [INFO] train episode 12588: reward = 12.89, steps = 45 00:53:30 [INFO] train episode 12589: reward = 6.27, steps = 34 00:53:30 [INFO] train episode 12590: reward = 14.36, steps = 31 00:53:30 [INFO] train episode 12591: reward = 14.03, steps = 49 00:53:30 [INFO] train episode 12592: reward = -15.72, steps = 23 00:53:31 [INFO] train episode 12593: reward = 15.26, steps = 39 00:53:31 [INFO] train episode 12594: reward = 6.55, steps = 44 00:53:31 [INFO] train episode 12595: reward = 12.93, steps = 48 00:53:32 [INFO] train episode 12596: reward = -23.31, steps = 41 00:53:32 [INFO] train episode 12597: reward = 13.13, steps = 41 00:53:32 [INFO] train episode 12598: reward = 20.06, steps = 48 00:53:32 [INFO] train episode 12599: reward = 11.74, steps = 38 00:53:33 [INFO] train episode 12600: reward = 0.19, steps = 36 00:53:33 [INFO] train episode 12601: reward = -8.51, steps = 33 00:53:33 [INFO] train episode 12602: reward = 8.45, steps = 38 00:53:34 [INFO] train episode 12603: reward = 15.55, steps = 62 00:53:34 [INFO] train episode 12604: reward = 6.10, steps = 37 00:53:34 [INFO] train episode 12605: reward = -27.03, steps = 17 00:53:34 [INFO] train episode 12606: reward = 14.61, steps = 49 00:53:35 [INFO] train episode 12607: reward = -9.61, steps = 28 00:53:35 [INFO] train episode 12608: reward = 19.24, steps = 43 00:53:35 [INFO] train episode 12609: reward = 12.37, steps = 46 00:53:35 [INFO] train episode 12610: reward = -27.39, steps = 17 00:53:35 [INFO] train episode 12611: reward = 7.67, steps = 42 00:53:36 [INFO] train episode 12612: reward = -4.79, steps = 34 00:53:36 [INFO] train episode 12613: reward = 4.38, steps = 39 00:53:36 [INFO] train episode 12614: reward = 16.60, steps = 41 00:53:37 [INFO] train episode 12615: reward = 16.28, steps = 45 00:53:37 [INFO] train episode 12616: reward = 13.20, steps = 45 00:53:37 [INFO] train episode 12617: reward = 15.60, steps = 42 00:53:37 [INFO] train episode 12618: reward = -1.54, steps = 32 00:53:38 [INFO] train episode 12619: reward = -9.63, steps = 24 00:53:38 [INFO] train episode 12620: reward = 0.65, steps = 35 00:53:38 [INFO] train episode 12621: reward = 22.00, steps = 46 00:53:38 [INFO] train episode 12622: reward = 7.72, steps = 46 00:53:39 [INFO] train episode 12623: reward = -5.51, steps = 39 00:53:39 [INFO] train episode 12624: reward = 8.29, steps = 39 00:53:39 [INFO] train episode 12625: reward = 5.85, steps = 42 00:53:39 [INFO] train episode 12626: reward = 4.71, steps = 32 00:53:40 [INFO] train episode 12627: reward = 15.55, steps = 44 00:53:40 [INFO] train episode 12628: reward = -8.89, steps = 26 00:53:40 [INFO] train episode 12629: reward = 9.27, steps = 43 00:53:40 [INFO] train episode 12630: reward = 5.22, steps = 37 00:53:41 [INFO] train episode 12631: reward = 7.79, steps = 34 00:53:41 [INFO] train episode 12632: reward = 2.65, steps = 56 00:53:41 [INFO] train episode 12633: reward = 8.85, steps = 38 00:53:42 [INFO] train episode 12634: reward = -2.05, steps = 43 00:53:42 [INFO] train episode 12635: reward = -4.44, steps = 26 00:53:42 [INFO] train episode 12636: reward = -20.40, steps = 22 00:53:42 [INFO] train episode 12637: reward = -25.14, steps = 29 00:53:42 [INFO] train episode 12638: reward = 9.93, steps = 52 00:53:43 [INFO] train episode 12639: reward = 18.94, steps = 38 00:53:43 [INFO] train episode 12640: reward = -14.26, steps = 24 00:53:43 [INFO] train episode 12641: reward = 4.93, steps = 36 00:53:43 [INFO] train episode 12642: reward = 3.38, steps = 38 00:53:44 [INFO] train episode 12643: reward = 1.26, steps = 38 00:53:44 [INFO] train episode 12644: reward = 7.99, steps = 38 00:53:44 [INFO] train episode 12645: reward = 6.63, steps = 37 00:53:44 [INFO] train episode 12646: reward = -1.25, steps = 37 00:53:45 [INFO] train episode 12647: reward = -0.04, steps = 47 00:53:45 [INFO] train episode 12648: reward = 6.54, steps = 39 00:53:45 [INFO] train episode 12649: reward = -10.59, steps = 21 00:53:46 [INFO] train episode 12650: reward = -21.64, steps = 27 00:53:46 [INFO] train episode 12651: reward = -13.54, steps = 33 00:53:46 [INFO] train episode 12652: reward = 19.59, steps = 44 00:53:46 [INFO] train episode 12653: reward = 8.62, steps = 45 00:53:47 [INFO] train episode 12654: reward = 11.46, steps = 46 00:53:47 [INFO] train episode 12655: reward = -12.23, steps = 30 00:53:47 [INFO] train episode 12656: reward = 10.07, steps = 33 00:53:47 [INFO] train episode 12657: reward = 12.95, steps = 43 00:53:48 [INFO] train episode 12658: reward = 3.89, steps = 34 00:53:48 [INFO] train episode 12659: reward = 5.34, steps = 49 00:53:48 [INFO] train episode 12660: reward = 4.36, steps = 34 00:53:48 [INFO] train episode 12661: reward = 25.23, steps = 43 00:53:49 [INFO] train episode 12662: reward = 8.06, steps = 38 00:53:49 [INFO] train episode 12663: reward = -0.90, steps = 34 00:53:49 [INFO] train episode 12664: reward = 3.07, steps = 46 00:53:49 [INFO] train episode 12665: reward = 3.77, steps = 35 00:53:50 [INFO] train episode 12666: reward = 5.15, steps = 39 00:53:50 [INFO] train episode 12667: reward = 15.72, steps = 40 00:53:50 [INFO] train episode 12668: reward = 8.08, steps = 40 00:53:50 [INFO] train episode 12669: reward = -7.39, steps = 34 00:53:51 [INFO] train episode 12670: reward = 21.81, steps = 43 00:53:51 [INFO] train episode 12671: reward = 9.87, steps = 40 00:53:51 [INFO] train episode 12672: reward = 6.76, steps = 47 00:53:51 [INFO] train episode 12673: reward = 14.44, steps = 37 00:53:52 [INFO] train episode 12674: reward = -45.33, steps = 19 00:53:52 [INFO] train episode 12675: reward = 18.35, steps = 58 00:53:52 [INFO] train episode 12676: reward = 1.42, steps = 41 00:53:52 [INFO] train episode 12677: reward = 6.73, steps = 36 00:53:53 [INFO] train episode 12678: reward = 4.37, steps = 48 00:53:53 [INFO] train episode 12679: reward = 6.88, steps = 40 00:53:53 [INFO] train episode 12680: reward = -18.14, steps = 34 00:53:54 [INFO] train episode 12681: reward = -0.92, steps = 41 00:53:54 [INFO] train episode 12682: reward = 3.50, steps = 36 00:53:54 [INFO] train episode 12683: reward = -18.56, steps = 20 00:53:54 [INFO] train episode 12684: reward = 13.27, steps = 44 00:53:55 [INFO] train episode 12685: reward = 16.13, steps = 54 00:53:55 [INFO] train episode 12686: reward = 9.36, steps = 38 00:53:55 [INFO] train episode 12687: reward = 6.95, steps = 43 00:53:55 [INFO] train episode 12688: reward = 8.27, steps = 30 00:53:56 [INFO] train episode 12689: reward = 15.14, steps = 42 00:53:56 [INFO] train episode 12690: reward = -1.34, steps = 52 00:53:56 [INFO] train episode 12691: reward = 20.18, steps = 49 00:53:56 [INFO] train episode 12692: reward = -8.95, steps = 35 00:53:57 [INFO] train episode 12693: reward = 6.50, steps = 39 00:53:57 [INFO] train episode 12694: reward = -23.24, steps = 16 00:53:57 [INFO] train episode 12695: reward = 28.50, steps = 45 00:53:57 [INFO] train episode 12696: reward = -1.85, steps = 44 00:53:58 [INFO] train episode 12697: reward = 5.26, steps = 30 00:53:58 [INFO] train episode 12698: reward = -6.71, steps = 37 00:53:58 [INFO] train episode 12699: reward = -15.61, steps = 21 00:53:59 [INFO] train episode 12700: reward = 22.72, steps = 50 00:53:59 [INFO] train episode 12701: reward = 12.15, steps = 51 00:53:59 [INFO] train episode 12702: reward = 5.00, steps = 49 00:54:00 [INFO] train episode 12703: reward = 9.19, steps = 44 00:54:00 [INFO] train episode 12704: reward = -14.09, steps = 30 00:54:00 [INFO] train episode 12705: reward = 14.65, steps = 38 00:54:00 [INFO] train episode 12706: reward = -14.77, steps = 31 00:54:01 [INFO] train episode 12707: reward = 18.19, steps = 44 00:54:01 [INFO] train episode 12708: reward = -7.85, steps = 29 00:54:01 [INFO] train episode 12709: reward = -4.15, steps = 45 00:54:01 [INFO] train episode 12710: reward = 2.10, steps = 36 00:54:02 [INFO] train episode 12711: reward = -11.51, steps = 27 00:54:02 [INFO] train episode 12712: reward = 2.13, steps = 40 00:54:02 [INFO] train episode 12713: reward = -13.97, steps = 38 00:54:02 [INFO] train episode 12714: reward = 9.48, steps = 42 00:54:03 [INFO] train episode 12715: reward = 8.71, steps = 36 00:54:03 [INFO] train episode 12716: reward = -6.37, steps = 28 00:54:03 [INFO] train episode 12717: reward = 11.20, steps = 51 00:54:03 [INFO] train episode 12718: reward = 16.35, steps = 34 00:54:04 [INFO] train episode 12719: reward = 2.14, steps = 37 00:54:04 [INFO] train episode 12720: reward = 1.26, steps = 28 00:54:04 [INFO] train episode 12721: reward = 1.34, steps = 55 00:54:04 [INFO] train episode 12722: reward = 6.29, steps = 35 00:54:05 [INFO] train episode 12723: reward = -2.28, steps = 36 00:54:05 [INFO] train episode 12724: reward = 0.02, steps = 35 00:54:05 [INFO] train episode 12725: reward = 10.25, steps = 43 00:54:06 [INFO] train episode 12726: reward = 10.61, steps = 47 00:54:06 [INFO] train episode 12727: reward = 18.61, steps = 50 00:54:06 [INFO] train episode 12728: reward = -6.74, steps = 31 00:54:06 [INFO] train episode 12729: reward = 6.40, steps = 42 00:54:07 [INFO] train episode 12730: reward = -5.96, steps = 36 00:54:07 [INFO] train episode 12731: reward = -9.22, steps = 27 00:54:07 [INFO] train episode 12732: reward = -3.43, steps = 35 00:54:07 [INFO] train episode 12733: reward = -1.24, steps = 31 00:54:08 [INFO] train episode 12734: reward = -0.67, steps = 35 00:54:08 [INFO] train episode 12735: reward = 7.05, steps = 36 00:54:08 [INFO] train episode 12736: reward = -9.84, steps = 35 00:54:08 [INFO] train episode 12737: reward = 22.07, steps = 57 00:54:09 [INFO] train episode 12738: reward = 7.45, steps = 42 00:54:09 [INFO] train episode 12739: reward = -15.26, steps = 28 00:54:09 [INFO] train episode 12740: reward = 0.41, steps = 39 00:54:09 [INFO] train episode 12741: reward = 3.38, steps = 36 00:54:10 [INFO] train episode 12742: reward = -1.29, steps = 34 00:54:10 [INFO] train episode 12743: reward = -12.60, steps = 30 00:54:10 [INFO] train episode 12744: reward = 7.47, steps = 43 00:54:10 [INFO] train episode 12745: reward = 12.19, steps = 47 00:54:11 [INFO] train episode 12746: reward = -4.43, steps = 30 00:54:11 [INFO] train episode 12747: reward = 30.69, steps = 55 00:54:11 [INFO] train episode 12748: reward = 6.20, steps = 42 00:54:11 [INFO] train episode 12749: reward = -9.45, steps = 24 00:54:12 [INFO] train episode 12750: reward = -8.21, steps = 25 00:54:12 [INFO] train episode 12751: reward = 11.43, steps = 37 00:54:12 [INFO] train episode 12752: reward = 3.49, steps = 27 00:54:13 [INFO] train episode 12753: reward = -3.26, steps = 40 00:54:13 [INFO] train episode 12754: reward = 12.03, steps = 42 00:54:13 [INFO] train episode 12755: reward = -12.68, steps = 35 00:54:13 [INFO] train episode 12756: reward = -28.83, steps = 33 00:54:14 [INFO] train episode 12757: reward = 8.78, steps = 54 00:54:14 [INFO] train episode 12758: reward = -1.76, steps = 41 00:54:14 [INFO] train episode 12759: reward = 13.56, steps = 56 00:54:15 [INFO] train episode 12760: reward = 10.02, steps = 35 00:54:15 [INFO] train episode 12761: reward = -12.46, steps = 23 00:54:15 [INFO] train episode 12762: reward = -2.17, steps = 33 00:54:15 [INFO] train episode 12763: reward = 3.62, steps = 36 00:54:15 [INFO] train episode 12764: reward = -1.77, steps = 47 00:54:16 [INFO] train episode 12765: reward = -0.20, steps = 47 00:54:16 [INFO] train episode 12766: reward = -7.56, steps = 32 00:54:16 [INFO] train episode 12767: reward = 2.22, steps = 44 00:54:17 [INFO] train episode 12768: reward = 12.86, steps = 41 00:54:17 [INFO] train episode 12769: reward = -1.15, steps = 35 00:54:17 [INFO] train episode 12770: reward = -26.55, steps = 18 00:54:17 [INFO] train episode 12771: reward = -8.11, steps = 44 00:54:17 [INFO] train episode 12772: reward = -16.59, steps = 20 00:54:18 [INFO] train episode 12773: reward = -4.31, steps = 31 00:54:18 [INFO] train episode 12774: reward = -19.03, steps = 17 00:54:18 [INFO] train episode 12775: reward = 5.38, steps = 38 00:54:18 [INFO] train episode 12776: reward = -13.06, steps = 39 00:54:19 [INFO] train episode 12777: reward = 16.72, steps = 41 00:54:19 [INFO] train episode 12778: reward = 8.82, steps = 45 00:54:19 [INFO] train episode 12779: reward = -7.96, steps = 24 00:54:19 [INFO] train episode 12780: reward = 2.07, steps = 32 00:54:19 [INFO] train episode 12781: reward = -25.23, steps = 20 00:54:20 [INFO] train episode 12782: reward = -18.75, steps = 39 00:54:20 [INFO] train episode 12783: reward = 9.64, steps = 39 00:54:20 [INFO] train episode 12784: reward = 8.48, steps = 39 00:54:20 [INFO] train episode 12785: reward = 3.85, steps = 45 00:54:21 [INFO] train episode 12786: reward = -3.65, steps = 38 00:54:21 [INFO] train episode 12787: reward = 6.44, steps = 38 00:54:21 [INFO] train episode 12788: reward = 13.59, steps = 40 00:54:21 [INFO] train episode 12789: reward = -9.54, steps = 26 00:54:22 [INFO] train episode 12790: reward = -4.44, steps = 36 00:54:22 [INFO] train episode 12791: reward = 23.08, steps = 56 00:54:22 [INFO] train episode 12792: reward = -5.66, steps = 57 00:54:23 [INFO] train episode 12793: reward = -7.18, steps = 40 00:54:23 [INFO] train episode 12794: reward = 14.90, steps = 50 00:54:23 [INFO] train episode 12795: reward = 16.08, steps = 53 00:54:24 [INFO] train episode 12796: reward = 6.81, steps = 41 00:54:24 [INFO] train episode 12797: reward = -9.92, steps = 34 00:54:24 [INFO] train episode 12798: reward = 7.15, steps = 34 00:54:24 [INFO] train episode 12799: reward = -5.70, steps = 50 00:54:25 [INFO] train episode 12800: reward = -27.81, steps = 32 00:54:25 [INFO] train episode 12801: reward = 13.27, steps = 51 00:54:25 [INFO] train episode 12802: reward = -33.49, steps = 35 00:54:26 [INFO] train episode 12803: reward = 15.86, steps = 53 00:54:26 [INFO] train episode 12804: reward = -21.95, steps = 43 00:54:26 [INFO] train episode 12805: reward = 3.98, steps = 43 00:54:27 [INFO] train episode 12806: reward = 0.07, steps = 33 00:54:27 [INFO] train episode 12807: reward = 33.38, steps = 56 00:54:27 [INFO] train episode 12808: reward = 1.30, steps = 39 00:54:27 [INFO] train episode 12809: reward = -6.48, steps = 33 00:54:28 [INFO] train episode 12810: reward = 7.76, steps = 35 00:54:28 [INFO] train episode 12811: reward = -34.16, steps = 29 00:54:28 [INFO] train episode 12812: reward = 10.78, steps = 50 00:54:28 [INFO] train episode 12813: reward = -4.15, steps = 31 00:54:29 [INFO] train episode 12814: reward = -11.64, steps = 25 00:54:29 [INFO] train episode 12815: reward = 3.38, steps = 38 00:54:29 [INFO] train episode 12816: reward = 5.78, steps = 37 00:54:29 [INFO] train episode 12817: reward = 7.73, steps = 56 00:54:30 [INFO] train episode 12818: reward = 17.83, steps = 47 00:54:30 [INFO] train episode 12819: reward = 11.71, steps = 46 00:54:30 [INFO] train episode 12820: reward = -16.43, steps = 22 00:54:30 [INFO] train episode 12821: reward = -3.38, steps = 45 00:54:31 [INFO] train episode 12822: reward = 9.40, steps = 38 00:54:31 [INFO] train episode 12823: reward = 8.94, steps = 39 00:54:31 [INFO] train episode 12824: reward = 0.83, steps = 32 00:54:31 [INFO] train episode 12825: reward = -10.80, steps = 29 00:54:31 [INFO] train episode 12826: reward = -25.40, steps = 17 00:54:32 [INFO] train episode 12827: reward = 19.55, steps = 53 00:54:32 [INFO] train episode 12828: reward = 0.42, steps = 34 00:54:32 [INFO] train episode 12829: reward = -19.97, steps = 39 00:54:33 [INFO] train episode 12830: reward = 7.62, steps = 42 00:54:33 [INFO] train episode 12831: reward = 1.21, steps = 44 00:54:33 [INFO] train episode 12832: reward = 7.72, steps = 39 00:54:33 [INFO] train episode 12833: reward = 5.49, steps = 34 00:54:34 [INFO] train episode 12834: reward = -16.05, steps = 31 00:54:34 [INFO] train episode 12835: reward = 5.04, steps = 45 00:54:34 [INFO] train episode 12836: reward = -2.33, steps = 44 00:54:35 [INFO] train episode 12837: reward = 6.03, steps = 63 00:54:35 [INFO] train episode 12838: reward = -3.75, steps = 40 00:54:35 [INFO] train episode 12839: reward = 6.86, steps = 51 00:54:35 [INFO] train episode 12840: reward = 2.44, steps = 36 00:54:36 [INFO] train episode 12841: reward = 11.06, steps = 35 00:54:36 [INFO] train episode 12842: reward = 12.64, steps = 39 00:54:36 [INFO] train episode 12843: reward = 13.19, steps = 42 00:54:36 [INFO] train episode 12844: reward = 0.73, steps = 39 00:54:37 [INFO] train episode 12845: reward = 15.80, steps = 43 00:54:37 [INFO] train episode 12846: reward = 14.69, steps = 35 00:54:37 [INFO] train episode 12847: reward = 4.40, steps = 39 00:54:38 [INFO] train episode 12848: reward = -17.17, steps = 35 00:54:38 [INFO] train episode 12849: reward = 9.55, steps = 39 00:54:38 [INFO] train episode 12850: reward = 1.93, steps = 36 00:54:38 [INFO] train episode 12851: reward = -9.20, steps = 37 00:54:39 [INFO] train episode 12852: reward = 6.04, steps = 36 00:54:39 [INFO] train episode 12853: reward = -7.18, steps = 43 00:54:39 [INFO] train episode 12854: reward = -3.28, steps = 34 00:54:39 [INFO] train episode 12855: reward = -14.44, steps = 24 00:54:40 [INFO] train episode 12856: reward = 0.91, steps = 46 00:54:40 [INFO] train episode 12857: reward = 16.08, steps = 44 00:54:40 [INFO] train episode 12858: reward = -23.11, steps = 21 00:54:40 [INFO] train episode 12859: reward = 12.99, steps = 46 00:54:41 [INFO] train episode 12860: reward = 1.32, steps = 32 00:54:41 [INFO] train episode 12861: reward = -20.04, steps = 21 00:54:41 [INFO] train episode 12862: reward = 22.03, steps = 47 00:54:41 [INFO] train episode 12863: reward = 1.45, steps = 43 00:54:42 [INFO] train episode 12864: reward = 26.42, steps = 52 00:54:42 [INFO] train episode 12865: reward = 2.63, steps = 45 00:54:42 [INFO] train episode 12866: reward = -0.54, steps = 37 00:54:43 [INFO] train episode 12867: reward = 6.48, steps = 51 00:54:43 [INFO] train episode 12868: reward = -4.44, steps = 45 00:54:43 [INFO] train episode 12869: reward = 17.23, steps = 54 00:54:44 [INFO] train episode 12870: reward = 1.02, steps = 38 00:54:44 [INFO] train episode 12871: reward = -4.99, steps = 28 00:54:44 [INFO] train episode 12872: reward = -7.57, steps = 39 00:54:44 [INFO] train episode 12873: reward = -18.44, steps = 38 00:54:45 [INFO] train episode 12874: reward = -1.40, steps = 37 00:54:45 [INFO] train episode 12875: reward = 11.02, steps = 36 00:54:45 [INFO] train episode 12876: reward = 7.74, steps = 42 00:54:45 [INFO] train episode 12877: reward = 0.22, steps = 43 00:54:46 [INFO] train episode 12878: reward = 9.95, steps = 46 00:54:46 [INFO] train episode 12879: reward = -2.21, steps = 28 00:54:46 [INFO] train episode 12880: reward = -4.60, steps = 45 00:54:46 [INFO] train episode 12881: reward = -6.76, steps = 42 00:54:47 [INFO] train episode 12882: reward = 4.53, steps = 38 00:54:47 [INFO] train episode 12883: reward = 14.57, steps = 46 00:54:47 [INFO] train episode 12884: reward = 5.64, steps = 40 00:54:48 [INFO] train episode 12885: reward = -0.58, steps = 36 00:54:48 [INFO] train episode 12886: reward = -14.62, steps = 22 00:54:48 [INFO] train episode 12887: reward = -5.73, steps = 35 00:54:48 [INFO] train episode 12888: reward = 7.28, steps = 45 00:54:48 [INFO] train episode 12889: reward = 0.99, steps = 33 00:54:49 [INFO] train episode 12890: reward = 2.21, steps = 41 00:54:49 [INFO] train episode 12891: reward = 18.77, steps = 35 00:54:49 [INFO] train episode 12892: reward = -14.56, steps = 40 00:54:49 [INFO] train episode 12893: reward = -1.74, steps = 42 00:54:50 [INFO] train episode 12894: reward = -13.84, steps = 31 00:54:50 [INFO] train episode 12895: reward = -21.18, steps = 17 00:54:50 [INFO] train episode 12896: reward = -10.61, steps = 32 00:54:50 [INFO] train episode 12897: reward = 7.15, steps = 46 00:54:51 [INFO] train episode 12898: reward = 22.60, steps = 44 00:54:51 [INFO] train episode 12899: reward = 14.98, steps = 49 00:54:51 [INFO] train episode 12900: reward = -14.35, steps = 25 00:54:51 [INFO] train episode 12901: reward = -10.91, steps = 21 00:54:51 [INFO] train episode 12902: reward = -12.69, steps = 31 00:54:52 [INFO] train episode 12903: reward = -18.03, steps = 41 00:54:52 [INFO] train episode 12904: reward = -7.70, steps = 35 00:54:52 [INFO] train episode 12905: reward = -25.52, steps = 25 00:54:53 [INFO] train episode 12906: reward = -4.64, steps = 25 00:54:53 [INFO] train episode 12907: reward = 7.18, steps = 43 00:54:53 [INFO] train episode 12908: reward = -3.27, steps = 35 00:54:53 [INFO] train episode 12909: reward = 12.78, steps = 47 00:54:54 [INFO] train episode 12910: reward = -4.44, steps = 36 00:54:54 [INFO] train episode 12911: reward = 9.49, steps = 40 00:54:54 [INFO] train episode 12912: reward = 21.64, steps = 70 00:54:55 [INFO] train episode 12913: reward = -11.75, steps = 25 00:54:55 [INFO] train episode 12914: reward = 9.91, steps = 49 00:54:55 [INFO] train episode 12915: reward = 10.57, steps = 41 00:54:55 [INFO] train episode 12916: reward = -12.26, steps = 35 00:54:56 [INFO] train episode 12917: reward = 0.20, steps = 35 00:54:56 [INFO] train episode 12918: reward = -7.38, steps = 40 00:54:56 [INFO] train episode 12919: reward = -3.96, steps = 42 00:54:56 [INFO] train episode 12920: reward = -3.03, steps = 26 00:54:57 [INFO] train episode 12921: reward = -2.86, steps = 38 00:54:57 [INFO] train episode 12922: reward = 12.11, steps = 38 00:54:57 [INFO] train episode 12923: reward = 11.08, steps = 36 00:54:57 [INFO] train episode 12924: reward = -15.93, steps = 37 00:54:58 [INFO] train episode 12925: reward = 2.91, steps = 55 00:54:58 [INFO] train episode 12926: reward = 13.37, steps = 51 00:54:58 [INFO] train episode 12927: reward = -3.20, steps = 36 00:54:59 [INFO] train episode 12928: reward = 5.93, steps = 38 00:54:59 [INFO] train episode 12929: reward = -12.42, steps = 24 00:54:59 [INFO] train episode 12930: reward = -1.61, steps = 36 00:54:59 [INFO] train episode 12931: reward = 1.50, steps = 42 00:55:00 [INFO] train episode 12932: reward = 15.65, steps = 49 00:55:00 [INFO] train episode 12933: reward = -26.05, steps = 20 00:55:00 [INFO] train episode 12934: reward = -22.10, steps = 27 00:55:00 [INFO] train episode 12935: reward = 5.60, steps = 44 00:55:01 [INFO] train episode 12936: reward = -12.17, steps = 29 00:55:01 [INFO] train episode 12937: reward = -12.47, steps = 22 00:55:01 [INFO] train episode 12938: reward = -5.16, steps = 31 00:55:01 [INFO] train episode 12939: reward = 7.67, steps = 73 00:55:02 [INFO] train episode 12940: reward = 10.55, steps = 39 00:55:02 [INFO] train episode 12941: reward = -2.02, steps = 42 00:55:02 [INFO] train episode 12942: reward = 3.87, steps = 39 00:55:02 [INFO] train episode 12943: reward = 2.23, steps = 36 00:55:03 [INFO] train episode 12944: reward = -13.21, steps = 56 00:55:03 [INFO] train episode 12945: reward = 15.24, steps = 39 00:55:03 [INFO] train episode 12946: reward = -4.77, steps = 35 00:55:04 [INFO] train episode 12947: reward = 7.01, steps = 36 00:55:04 [INFO] train episode 12948: reward = 19.17, steps = 49 00:55:04 [INFO] train episode 12949: reward = -11.55, steps = 37 00:55:05 [INFO] train episode 12950: reward = 3.34, steps = 51 00:55:05 [INFO] train episode 12951: reward = -14.42, steps = 39 00:55:05 [INFO] train episode 12952: reward = 7.59, steps = 39 00:55:05 [INFO] train episode 12953: reward = -9.27, steps = 32 00:55:06 [INFO] train episode 12954: reward = -11.30, steps = 19 00:55:06 [INFO] train episode 12955: reward = -2.06, steps = 38 00:55:06 [INFO] train episode 12956: reward = -0.61, steps = 41 00:55:07 [INFO] train episode 12957: reward = 1.17, steps = 46 00:55:07 [INFO] train episode 12958: reward = -8.08, steps = 33 00:55:07 [INFO] train episode 12959: reward = 0.24, steps = 37 00:55:07 [INFO] train episode 12960: reward = -6.91, steps = 30 00:55:08 [INFO] train episode 12961: reward = -6.82, steps = 26 00:55:08 [INFO] train episode 12962: reward = -23.07, steps = 30 00:55:08 [INFO] train episode 12963: reward = -0.32, steps = 47 00:55:08 [INFO] train episode 12964: reward = -7.85, steps = 29 00:55:09 [INFO] train episode 12965: reward = -2.97, steps = 38 00:55:09 [INFO] train episode 12966: reward = 0.30, steps = 43 00:55:09 [INFO] train episode 12967: reward = -14.57, steps = 35 00:55:09 [INFO] train episode 12968: reward = -2.10, steps = 33 00:55:10 [INFO] train episode 12969: reward = -6.47, steps = 47 00:55:10 [INFO] train episode 12970: reward = 0.46, steps = 37 00:55:10 [INFO] train episode 12971: reward = -10.01, steps = 21 00:55:10 [INFO] train episode 12972: reward = -0.07, steps = 49 00:55:11 [INFO] train episode 12973: reward = 17.92, steps = 49 00:55:11 [INFO] train episode 12974: reward = 2.05, steps = 39 00:55:11 [INFO] train episode 12975: reward = 23.35, steps = 57 00:55:11 [INFO] train episode 12976: reward = -22.75, steps = 30 00:55:12 [INFO] train episode 12977: reward = -9.80, steps = 31 00:55:12 [INFO] train episode 12978: reward = -3.00, steps = 36 00:55:12 [INFO] train episode 12979: reward = 9.41, steps = 55 00:55:13 [INFO] train episode 12980: reward = 11.73, steps = 45 00:55:13 [INFO] train episode 12981: reward = 0.45, steps = 38 00:55:13 [INFO] train episode 12982: reward = -13.45, steps = 43 00:55:13 [INFO] train episode 12983: reward = -13.43, steps = 27 00:55:14 [INFO] train episode 12984: reward = 19.21, steps = 44 00:55:14 [INFO] train episode 12985: reward = 9.29, steps = 43 00:55:14 [INFO] train episode 12986: reward = 2.61, steps = 59 00:55:15 [INFO] train episode 12987: reward = 8.98, steps = 60 00:55:15 [INFO] train episode 12988: reward = -2.52, steps = 44 00:55:15 [INFO] train episode 12989: reward = -9.58, steps = 36 00:55:16 [INFO] train episode 12990: reward = 7.04, steps = 33 00:55:16 [INFO] train episode 12991: reward = -20.73, steps = 24 00:55:16 [INFO] train episode 12992: reward = 17.81, steps = 43 00:55:16 [INFO] train episode 12993: reward = 27.12, steps = 52 00:55:17 [INFO] train episode 12994: reward = 20.54, steps = 47 00:55:17 [INFO] train episode 12995: reward = 8.20, steps = 46 00:55:17 [INFO] train episode 12996: reward = 1.77, steps = 34 00:55:17 [INFO] train episode 12997: reward = -6.08, steps = 39 00:55:18 [INFO] train episode 12998: reward = -7.15, steps = 30 00:55:18 [INFO] train episode 12999: reward = 6.27, steps = 35 00:55:18 [INFO] train episode 13000: reward = 15.21, steps = 57 00:55:19 [INFO] train episode 13001: reward = 5.25, steps = 41 00:55:19 [INFO] train episode 13002: reward = 2.57, steps = 50 00:55:20 [INFO] train episode 13003: reward = -39.01, steps = 70 00:55:20 [INFO] train episode 13004: reward = 2.96, steps = 33 00:55:20 [INFO] train episode 13005: reward = -16.36, steps = 33 00:55:20 [INFO] train episode 13006: reward = 2.12, steps = 49 00:55:21 [INFO] train episode 13007: reward = 9.62, steps = 50 00:55:21 [INFO] train episode 13008: reward = 25.57, steps = 66 00:55:21 [INFO] train episode 13009: reward = 13.11, steps = 46 00:55:22 [INFO] train episode 13010: reward = 5.85, steps = 40 00:55:22 [INFO] train episode 13011: reward = -9.73, steps = 33 00:55:22 [INFO] train episode 13012: reward = -4.23, steps = 43 00:55:22 [INFO] train episode 13013: reward = 1.13, steps = 40 00:55:23 [INFO] train episode 13014: reward = -11.73, steps = 45 00:55:23 [INFO] train episode 13015: reward = 6.94, steps = 37 00:55:23 [INFO] train episode 13016: reward = -0.55, steps = 48 00:55:24 [INFO] train episode 13017: reward = 2.86, steps = 37 00:55:24 [INFO] train episode 13018: reward = -10.44, steps = 24 00:55:24 [INFO] train episode 13019: reward = 11.55, steps = 45 00:55:24 [INFO] train episode 13020: reward = -7.67, steps = 34 00:55:24 [INFO] train episode 13021: reward = -14.44, steps = 23 00:55:25 [INFO] train episode 13022: reward = 21.39, steps = 78 00:55:25 [INFO] train episode 13023: reward = 1.61, steps = 52 00:55:25 [INFO] train episode 13024: reward = -19.38, steps = 19 00:55:26 [INFO] train episode 13025: reward = 1.17, steps = 48 00:55:26 [INFO] train episode 13026: reward = -18.12, steps = 21 00:55:26 [INFO] train episode 13027: reward = 6.72, steps = 60 00:55:26 [INFO] train episode 13028: reward = -17.98, steps = 17 00:55:27 [INFO] train episode 13029: reward = 9.44, steps = 34 00:55:27 [INFO] train episode 13030: reward = 1.09, steps = 37 00:55:27 [INFO] train episode 13031: reward = -6.49, steps = 36 00:55:27 [INFO] train episode 13032: reward = -4.75, steps = 41 00:55:28 [INFO] train episode 13033: reward = 11.80, steps = 46 00:55:28 [INFO] train episode 13034: reward = -13.27, steps = 28 00:55:28 [INFO] train episode 13035: reward = -27.48, steps = 32 00:55:29 [INFO] train episode 13036: reward = -33.65, steps = 87 00:55:29 [INFO] train episode 13037: reward = 2.02, steps = 37 00:55:29 [INFO] train episode 13038: reward = -20.76, steps = 32 00:55:29 [INFO] train episode 13039: reward = -19.02, steps = 23 00:55:30 [INFO] train episode 13040: reward = 6.77, steps = 35 00:55:30 [INFO] train episode 13041: reward = -13.51, steps = 38 00:55:30 [INFO] train episode 13042: reward = 4.23, steps = 37 00:55:30 [INFO] train episode 13043: reward = -2.89, steps = 40 00:55:31 [INFO] train episode 13044: reward = 1.86, steps = 36 00:55:31 [INFO] train episode 13045: reward = 2.31, steps = 39 00:55:31 [INFO] train episode 13046: reward = -5.99, steps = 44 00:55:31 [INFO] train episode 13047: reward = -11.79, steps = 31 00:55:32 [INFO] train episode 13048: reward = 10.79, steps = 45 00:55:32 [INFO] train episode 13049: reward = -8.19, steps = 40 00:55:32 [INFO] train episode 13050: reward = 7.21, steps = 41 00:55:33 [INFO] train episode 13051: reward = -9.67, steps = 64 00:55:33 [INFO] train episode 13052: reward = 8.59, steps = 40 00:55:33 [INFO] train episode 13053: reward = -5.31, steps = 39 00:55:34 [INFO] train episode 13054: reward = -4.53, steps = 37 00:55:34 [INFO] train episode 13055: reward = -5.24, steps = 46 00:55:34 [INFO] train episode 13056: reward = -1.86, steps = 41 00:55:34 [INFO] train episode 13057: reward = 7.51, steps = 48 00:55:35 [INFO] train episode 13058: reward = 14.07, steps = 41 00:55:35 [INFO] train episode 13059: reward = -5.27, steps = 46 00:55:35 [INFO] train episode 13060: reward = -18.66, steps = 49 00:55:36 [INFO] train episode 13061: reward = 10.12, steps = 51 00:55:36 [INFO] train episode 13062: reward = -33.41, steps = 32 00:55:36 [INFO] train episode 13063: reward = 18.78, steps = 56 00:55:37 [INFO] train episode 13064: reward = -5.96, steps = 46 00:55:37 [INFO] train episode 13065: reward = 1.54, steps = 37 00:55:37 [INFO] train episode 13066: reward = -4.66, steps = 34 00:55:37 [INFO] train episode 13067: reward = -6.35, steps = 29 00:55:38 [INFO] train episode 13068: reward = 23.48, steps = 50 00:55:38 [INFO] train episode 13069: reward = -8.26, steps = 29 00:55:38 [INFO] train episode 13070: reward = 11.28, steps = 38 00:55:38 [INFO] train episode 13071: reward = 21.15, steps = 43 00:55:39 [INFO] train episode 13072: reward = 8.74, steps = 45 00:55:39 [INFO] train episode 13073: reward = -29.49, steps = 21 00:55:39 [INFO] train episode 13074: reward = -16.57, steps = 61 00:55:39 [INFO] train episode 13075: reward = -6.05, steps = 42 00:55:40 [INFO] train episode 13076: reward = -23.63, steps = 20 00:55:40 [INFO] train episode 13077: reward = 2.79, steps = 38 00:55:40 [INFO] train episode 13078: reward = -6.26, steps = 34 00:55:40 [INFO] train episode 13079: reward = -25.15, steps = 20 00:55:40 [INFO] train episode 13080: reward = -8.34, steps = 27 00:55:41 [INFO] train episode 13081: reward = 10.01, steps = 43 00:55:41 [INFO] train episode 13082: reward = 11.50, steps = 42 00:55:41 [INFO] train episode 13083: reward = -6.27, steps = 34 00:55:41 [INFO] train episode 13084: reward = 6.56, steps = 42 00:55:42 [INFO] train episode 13085: reward = -10.98, steps = 29 00:55:42 [INFO] train episode 13086: reward = -21.63, steps = 17 00:55:42 [INFO] train episode 13087: reward = -17.25, steps = 30 00:55:42 [INFO] train episode 13088: reward = -21.87, steps = 35 00:55:42 [INFO] train episode 13089: reward = 25.10, steps = 47 00:55:43 [INFO] train episode 13090: reward = 11.87, steps = 45 00:55:43 [INFO] train episode 13091: reward = -1.89, steps = 33 00:55:43 [INFO] train episode 13092: reward = 11.95, steps = 50 00:55:44 [INFO] train episode 13093: reward = -8.76, steps = 23 00:55:44 [INFO] train episode 13094: reward = -18.70, steps = 31 00:55:44 [INFO] train episode 13095: reward = 3.62, steps = 36 00:55:44 [INFO] train episode 13096: reward = -9.29, steps = 39 00:55:45 [INFO] train episode 13097: reward = -17.10, steps = 31 00:55:45 [INFO] train episode 13098: reward = -7.02, steps = 31 00:55:45 [INFO] train episode 13099: reward = 11.54, steps = 47 00:55:45 [INFO] train episode 13100: reward = -13.83, steps = 23 00:55:45 [INFO] train episode 13101: reward = 10.02, steps = 35 00:55:46 [INFO] train episode 13102: reward = 0.93, steps = 33 00:55:46 [INFO] train episode 13103: reward = 11.54, steps = 40 00:55:46 [INFO] train episode 13104: reward = 2.27, steps = 44 00:55:47 [INFO] train episode 13105: reward = -7.11, steps = 35 00:55:47 [INFO] train episode 13106: reward = -8.26, steps = 29 00:55:47 [INFO] train episode 13107: reward = 6.13, steps = 39 00:55:47 [INFO] train episode 13108: reward = 17.80, steps = 42 00:55:48 [INFO] train episode 13109: reward = -3.52, steps = 33 00:55:48 [INFO] train episode 13110: reward = 13.24, steps = 50 00:55:48 [INFO] train episode 13111: reward = 0.68, steps = 41 00:55:48 [INFO] train episode 13112: reward = -10.83, steps = 27 00:55:49 [INFO] train episode 13113: reward = -1.24, steps = 33 00:55:49 [INFO] train episode 13114: reward = -9.88, steps = 25 00:55:49 [INFO] train episode 13115: reward = 1.07, steps = 41 00:55:49 [INFO] train episode 13116: reward = -0.07, steps = 37 00:55:50 [INFO] train episode 13117: reward = -8.91, steps = 26 00:55:50 [INFO] train episode 13118: reward = 5.11, steps = 65 00:55:50 [INFO] train episode 13119: reward = -13.91, steps = 25 00:55:50 [INFO] train episode 13120: reward = 9.62, steps = 39 00:55:51 [INFO] train episode 13121: reward = -2.94, steps = 31 00:55:51 [INFO] train episode 13122: reward = 3.92, steps = 48 00:55:51 [INFO] train episode 13123: reward = -2.92, steps = 49 00:55:52 [INFO] train episode 13124: reward = 10.10, steps = 41 00:55:52 [INFO] train episode 13125: reward = 0.85, steps = 35 00:55:52 [INFO] train episode 13126: reward = 3.78, steps = 46 00:55:52 [INFO] train episode 13127: reward = 4.21, steps = 49 00:55:53 [INFO] train episode 13128: reward = -20.57, steps = 22 00:55:53 [INFO] train episode 13129: reward = -6.63, steps = 45 00:55:53 [INFO] train episode 13130: reward = 35.72, steps = 52 00:55:53 [INFO] train episode 13131: reward = 4.32, steps = 36 00:55:54 [INFO] train episode 13132: reward = -21.01, steps = 28 00:55:54 [INFO] train episode 13133: reward = 1.45, steps = 32 00:55:54 [INFO] train episode 13134: reward = -11.19, steps = 26 00:55:54 [INFO] train episode 13135: reward = -11.73, steps = 50 00:55:55 [INFO] train episode 13136: reward = 15.78, steps = 49 00:55:55 [INFO] train episode 13137: reward = -8.08, steps = 35 00:55:55 [INFO] train episode 13138: reward = -0.96, steps = 30 00:55:55 [INFO] train episode 13139: reward = 18.23, steps = 53 00:55:56 [INFO] train episode 13140: reward = -14.85, steps = 64 00:55:56 [INFO] train episode 13141: reward = -0.56, steps = 39 00:55:56 [INFO] train episode 13142: reward = -12.22, steps = 41 00:55:57 [INFO] train episode 13143: reward = -0.70, steps = 34 00:55:57 [INFO] train episode 13144: reward = -14.26, steps = 39 00:55:57 [INFO] train episode 13145: reward = 5.12, steps = 48 00:55:58 [INFO] train episode 13146: reward = 10.28, steps = 56 00:55:58 [INFO] train episode 13147: reward = -14.50, steps = 22 00:55:58 [INFO] train episode 13148: reward = 18.00, steps = 38 00:55:58 [INFO] train episode 13149: reward = 0.33, steps = 36 00:55:59 [INFO] train episode 13150: reward = 0.40, steps = 54 00:55:59 [INFO] train episode 13151: reward = -8.10, steps = 33 00:55:59 [INFO] train episode 13152: reward = 5.92, steps = 37 00:55:59 [INFO] train episode 13153: reward = 5.05, steps = 44 00:56:00 [INFO] train episode 13154: reward = -0.22, steps = 40 00:56:00 [INFO] train episode 13155: reward = 4.04, steps = 43 00:56:00 [INFO] train episode 13156: reward = -10.63, steps = 39 00:56:01 [INFO] train episode 13157: reward = -11.03, steps = 18 00:56:01 [INFO] train episode 13158: reward = 6.55, steps = 42 00:56:01 [INFO] train episode 13159: reward = -19.93, steps = 20 00:56:01 [INFO] train episode 13160: reward = 6.90, steps = 40 00:56:01 [INFO] train episode 13161: reward = 15.91, steps = 45 00:56:02 [INFO] train episode 13162: reward = -0.94, steps = 34 00:56:02 [INFO] train episode 13163: reward = 9.69, steps = 45 00:56:02 [INFO] train episode 13164: reward = -2.63, steps = 44 00:56:03 [INFO] train episode 13165: reward = -35.98, steps = 51 00:56:03 [INFO] train episode 13166: reward = 13.78, steps = 40 00:56:03 [INFO] train episode 13167: reward = -3.50, steps = 34 00:56:03 [INFO] train episode 13168: reward = -6.33, steps = 35 00:56:04 [INFO] train episode 13169: reward = 5.97, steps = 44 00:56:04 [INFO] train episode 13170: reward = -14.18, steps = 51 00:56:04 [INFO] train episode 13171: reward = 6.10, steps = 38 00:56:05 [INFO] train episode 13172: reward = -3.46, steps = 40 00:56:05 [INFO] train episode 13173: reward = -13.34, steps = 26 00:56:05 [INFO] train episode 13174: reward = -10.25, steps = 31 00:56:05 [INFO] train episode 13175: reward = -47.07, steps = 54 00:56:06 [INFO] train episode 13176: reward = -26.42, steps = 31 00:56:06 [INFO] train episode 13177: reward = -37.80, steps = 18 00:56:06 [INFO] train episode 13178: reward = 6.04, steps = 50 00:56:06 [INFO] train episode 13179: reward = 1.26, steps = 68 00:56:07 [INFO] train episode 13180: reward = -5.16, steps = 36 00:56:07 [INFO] train episode 13181: reward = 19.44, steps = 43 00:56:07 [INFO] train episode 13182: reward = 9.49, steps = 37 00:56:08 [INFO] train episode 13183: reward = -26.66, steps = 56 00:56:08 [INFO] train episode 13184: reward = 16.98, steps = 47 00:56:08 [INFO] train episode 13185: reward = -15.24, steps = 57 00:56:08 [INFO] train episode 13186: reward = -6.28, steps = 38 00:56:09 [INFO] train episode 13187: reward = -3.68, steps = 41 00:56:09 [INFO] train episode 13188: reward = -16.70, steps = 77 00:56:10 [INFO] train episode 13189: reward = -11.11, steps = 47 00:56:10 [INFO] train episode 13190: reward = -16.14, steps = 49 00:56:10 [INFO] train episode 13191: reward = 29.02, steps = 56 00:56:11 [INFO] train episode 13192: reward = 10.88, steps = 48 00:56:11 [INFO] train episode 13193: reward = -8.44, steps = 55 00:56:11 [INFO] train episode 13194: reward = -1.06, steps = 48 00:56:12 [INFO] train episode 13195: reward = 18.90, steps = 53 00:56:12 [INFO] train episode 13196: reward = -0.09, steps = 35 00:56:12 [INFO] train episode 13197: reward = 26.12, steps = 56 00:56:13 [INFO] train episode 13198: reward = -29.65, steps = 58 00:56:13 [INFO] train episode 13199: reward = 1.34, steps = 59 00:56:13 [INFO] train episode 13200: reward = 3.46, steps = 39 00:56:14 [INFO] train episode 13201: reward = 2.96, steps = 45 00:56:14 [INFO] train episode 13202: reward = 1.06, steps = 53 00:56:14 [INFO] train episode 13203: reward = -6.23, steps = 38 00:56:15 [INFO] train episode 13204: reward = -19.06, steps = 21 00:56:15 [INFO] train episode 13205: reward = -7.93, steps = 36 00:56:15 [INFO] train episode 13206: reward = -1.38, steps = 31 00:56:15 [INFO] train episode 13207: reward = 7.07, steps = 46 00:56:16 [INFO] train episode 13208: reward = -33.66, steps = 47 00:56:16 [INFO] train episode 13209: reward = 19.56, steps = 72 00:56:17 [INFO] train episode 13210: reward = 12.24, steps = 46 00:56:17 [INFO] train episode 13211: reward = 39.42, steps = 62 00:56:17 [INFO] train episode 13212: reward = -3.60, steps = 39 00:56:18 [INFO] train episode 13213: reward = -3.04, steps = 32 00:56:18 [INFO] train episode 13214: reward = 5.59, steps = 41 00:56:18 [INFO] train episode 13215: reward = -19.58, steps = 18 00:56:18 [INFO] train episode 13216: reward = -30.01, steps = 18 00:56:18 [INFO] train episode 13217: reward = 0.44, steps = 37 00:56:19 [INFO] train episode 13218: reward = -13.16, steps = 34 00:56:19 [INFO] train episode 13219: reward = -17.19, steps = 39 00:56:19 [INFO] train episode 13220: reward = -3.13, steps = 44 00:56:20 [INFO] train episode 13221: reward = -7.04, steps = 75 00:56:20 [INFO] train episode 13222: reward = -14.72, steps = 29 00:56:20 [INFO] train episode 13223: reward = 3.24, steps = 40 00:56:21 [INFO] train episode 13224: reward = 14.99, steps = 57 00:56:21 [INFO] train episode 13225: reward = -4.17, steps = 42 00:56:21 [INFO] train episode 13226: reward = -18.04, steps = 25 00:56:21 [INFO] train episode 13227: reward = 3.11, steps = 33 00:56:22 [INFO] train episode 13228: reward = -16.54, steps = 36 00:56:22 [INFO] train episode 13229: reward = 2.93, steps = 55 00:56:22 [INFO] train episode 13230: reward = -17.85, steps = 20 00:56:22 [INFO] train episode 13231: reward = 5.42, steps = 45 00:56:23 [INFO] train episode 13232: reward = -8.06, steps = 43 00:56:23 [INFO] train episode 13233: reward = 26.83, steps = 46 00:56:23 [INFO] train episode 13234: reward = 3.41, steps = 40 00:56:24 [INFO] train episode 13235: reward = 1.02, steps = 53 00:56:24 [INFO] train episode 13236: reward = -8.49, steps = 45 00:56:24 [INFO] train episode 13237: reward = -23.06, steps = 17 00:56:24 [INFO] train episode 13238: reward = 19.20, steps = 65 00:56:25 [INFO] train episode 13239: reward = -10.16, steps = 43 00:56:25 [INFO] train episode 13240: reward = -16.85, steps = 32 00:56:25 [INFO] train episode 13241: reward = -2.94, steps = 38 00:56:26 [INFO] train episode 13242: reward = 13.93, steps = 49 00:56:26 [INFO] train episode 13243: reward = 14.31, steps = 45 00:56:26 [INFO] train episode 13244: reward = -24.94, steps = 49 00:56:27 [INFO] train episode 13245: reward = 6.34, steps = 46 00:56:27 [INFO] train episode 13246: reward = 10.18, steps = 39 00:56:27 [INFO] train episode 13247: reward = 17.88, steps = 51 00:56:28 [INFO] train episode 13248: reward = -11.69, steps = 35 00:56:28 [INFO] train episode 13249: reward = 12.63, steps = 38 00:56:28 [INFO] train episode 13250: reward = 13.99, steps = 44 00:56:28 [INFO] train episode 13251: reward = -8.54, steps = 43 00:56:29 [INFO] train episode 13252: reward = -8.77, steps = 45 00:56:29 [INFO] train episode 13253: reward = -24.79, steps = 43 00:56:29 [INFO] train episode 13254: reward = -12.98, steps = 43 00:56:30 [INFO] train episode 13255: reward = -25.00, steps = 48 00:56:30 [INFO] train episode 13256: reward = -25.96, steps = 21 00:56:30 [INFO] train episode 13257: reward = 9.19, steps = 44 00:56:30 [INFO] train episode 13258: reward = -22.51, steps = 19 00:56:30 [INFO] train episode 13259: reward = -17.63, steps = 24 00:56:31 [INFO] train episode 13260: reward = -23.20, steps = 20 00:56:31 [INFO] train episode 13261: reward = 9.15, steps = 38 00:56:31 [INFO] train episode 13262: reward = -1.86, steps = 31 00:56:31 [INFO] train episode 13263: reward = 4.62, steps = 45 00:56:32 [INFO] train episode 13264: reward = 16.50, steps = 50 00:56:32 [INFO] train episode 13265: reward = 2.85, steps = 41 00:56:32 [INFO] train episode 13266: reward = 5.64, steps = 40 00:56:32 [INFO] train episode 13267: reward = -12.52, steps = 43 00:56:33 [INFO] train episode 13268: reward = -9.14, steps = 24 00:56:33 [INFO] train episode 13269: reward = -19.98, steps = 24 00:56:33 [INFO] train episode 13270: reward = 16.50, steps = 36 00:56:33 [INFO] train episode 13271: reward = 11.59, steps = 38 00:56:34 [INFO] train episode 13272: reward = -17.45, steps = 46 00:56:34 [INFO] train episode 13273: reward = 17.38, steps = 78 00:56:34 [INFO] train episode 13274: reward = 20.11, steps = 54 00:56:35 [INFO] train episode 13275: reward = 6.39, steps = 50 00:56:35 [INFO] train episode 13276: reward = -7.75, steps = 35 00:56:35 [INFO] train episode 13277: reward = -2.79, steps = 62 00:56:36 [INFO] train episode 13278: reward = -15.45, steps = 55 00:56:36 [INFO] train episode 13279: reward = 0.90, steps = 48 00:56:36 [INFO] train episode 13280: reward = 0.11, steps = 56 00:56:37 [INFO] train episode 13281: reward = -2.72, steps = 40 00:56:37 [INFO] train episode 13282: reward = -12.05, steps = 40 00:56:37 [INFO] train episode 13283: reward = -1.58, steps = 61 00:56:38 [INFO] train episode 13284: reward = 7.21, steps = 43 00:56:38 [INFO] train episode 13285: reward = 12.78, steps = 46 00:56:38 [INFO] train episode 13286: reward = 8.51, steps = 41 00:56:39 [INFO] train episode 13287: reward = 7.09, steps = 38 00:56:39 [INFO] train episode 13288: reward = 0.82, steps = 38 00:56:39 [INFO] train episode 13289: reward = -4.42, steps = 58 00:56:40 [INFO] train episode 13290: reward = -15.81, steps = 50 00:56:40 [INFO] train episode 13291: reward = -19.29, steps = 52 00:56:40 [INFO] train episode 13292: reward = -10.06, steps = 39 00:56:40 [INFO] train episode 13293: reward = -11.56, steps = 21 00:56:41 [INFO] train episode 13294: reward = -0.62, steps = 37 00:56:41 [INFO] train episode 13295: reward = -0.14, steps = 46 00:56:41 [INFO] train episode 13296: reward = -15.75, steps = 26 00:56:42 [INFO] train episode 13297: reward = -6.08, steps = 47 00:56:42 [INFO] train episode 13298: reward = 21.84, steps = 46 00:56:42 [INFO] train episode 13299: reward = 9.69, steps = 40 00:56:42 [INFO] train episode 13300: reward = -5.74, steps = 33 00:56:43 [INFO] train episode 13301: reward = 4.89, steps = 37 00:56:43 [INFO] train episode 13302: reward = -17.40, steps = 18 00:56:43 [INFO] train episode 13303: reward = -2.96, steps = 32 00:56:43 [INFO] train episode 13304: reward = -21.80, steps = 38 00:56:43 [INFO] train episode 13305: reward = 0.57, steps = 41 00:56:44 [INFO] train episode 13306: reward = 1.43, steps = 49 00:56:44 [INFO] train episode 13307: reward = 1.97, steps = 39 00:56:44 [INFO] train episode 13308: reward = -11.18, steps = 25 00:56:45 [INFO] train episode 13309: reward = 6.77, steps = 47 00:56:45 [INFO] train episode 13310: reward = 15.51, steps = 42 00:56:45 [INFO] train episode 13311: reward = -4.89, steps = 47 00:56:45 [INFO] train episode 13312: reward = -6.64, steps = 38 00:56:46 [INFO] train episode 13313: reward = -0.31, steps = 30 00:56:46 [INFO] train episode 13314: reward = 10.84, steps = 39 00:56:46 [INFO] train episode 13315: reward = 0.92, steps = 56 00:56:47 [INFO] train episode 13316: reward = 21.53, steps = 45 00:56:47 [INFO] train episode 13317: reward = 0.48, steps = 52 00:56:47 [INFO] train episode 13318: reward = -0.17, steps = 33 00:56:47 [INFO] train episode 13319: reward = -8.95, steps = 25 00:56:48 [INFO] train episode 13320: reward = -3.62, steps = 44 00:56:48 [INFO] train episode 13321: reward = 10.39, steps = 48 00:56:48 [INFO] train episode 13322: reward = -5.91, steps = 28 00:56:48 [INFO] train episode 13323: reward = -21.27, steps = 25 00:56:49 [INFO] train episode 13324: reward = -15.90, steps = 32 00:56:49 [INFO] train episode 13325: reward = 4.45, steps = 41 00:56:49 [INFO] train episode 13326: reward = -5.78, steps = 46 00:56:49 [INFO] train episode 13327: reward = 2.93, steps = 48 00:56:50 [INFO] train episode 13328: reward = -3.42, steps = 31 00:56:50 [INFO] train episode 13329: reward = -10.80, steps = 49 00:56:50 [INFO] train episode 13330: reward = -5.77, steps = 56 00:56:50 [INFO] train episode 13331: reward = -32.79, steps = 19 00:56:51 [INFO] train episode 13332: reward = -11.38, steps = 33 00:56:51 [INFO] train episode 13333: reward = -15.22, steps = 88 00:56:52 [INFO] train episode 13334: reward = 24.63, steps = 57 00:56:52 [INFO] train episode 13335: reward = 2.97, steps = 38 00:56:52 [INFO] train episode 13336: reward = -14.02, steps = 33 00:56:52 [INFO] train episode 13337: reward = -1.27, steps = 30 00:56:53 [INFO] train episode 13338: reward = 6.23, steps = 39 00:56:53 [INFO] train episode 13339: reward = -14.26, steps = 28 00:56:53 [INFO] train episode 13340: reward = -9.44, steps = 30 00:56:53 [INFO] train episode 13341: reward = 10.58, steps = 54 00:56:54 [INFO] train episode 13342: reward = 13.81, steps = 43 00:56:54 [INFO] train episode 13343: reward = -5.67, steps = 58 00:56:55 [INFO] train episode 13344: reward = -2.28, steps = 41 00:56:55 [INFO] train episode 13345: reward = -20.45, steps = 63 00:56:55 [INFO] train episode 13346: reward = -7.07, steps = 27 00:56:55 [INFO] train episode 13347: reward = -3.57, steps = 46 00:56:56 [INFO] train episode 13348: reward = 18.78, steps = 64 00:56:56 [INFO] train episode 13349: reward = 10.21, steps = 41 00:56:56 [INFO] train episode 13350: reward = -7.53, steps = 26 00:56:57 [INFO] train episode 13351: reward = -2.43, steps = 38 00:56:57 [INFO] train episode 13352: reward = 17.41, steps = 45 00:56:57 [INFO] train episode 13353: reward = 16.86, steps = 45 00:56:58 [INFO] train episode 13354: reward = -4.37, steps = 37 00:56:58 [INFO] train episode 13355: reward = 19.02, steps = 41 00:56:58 [INFO] train episode 13356: reward = -6.06, steps = 59 00:56:58 [INFO] train episode 13357: reward = 4.55, steps = 35 00:56:59 [INFO] train episode 13358: reward = -9.89, steps = 32 00:56:59 [INFO] train episode 13359: reward = -18.77, steps = 25 00:56:59 [INFO] train episode 13360: reward = -2.13, steps = 45 00:57:00 [INFO] train episode 13361: reward = -11.37, steps = 71 00:57:00 [INFO] train episode 13362: reward = 4.29, steps = 44 00:57:00 [INFO] train episode 13363: reward = 8.74, steps = 76 00:57:01 [INFO] train episode 13364: reward = -30.38, steps = 22 00:57:01 [INFO] train episode 13365: reward = 13.01, steps = 47 00:57:01 [INFO] train episode 13366: reward = -6.48, steps = 35 00:57:01 [INFO] train episode 13367: reward = -11.86, steps = 40 00:57:02 [INFO] train episode 13368: reward = 0.46, steps = 50 00:57:02 [INFO] train episode 13369: reward = -12.67, steps = 36 00:57:02 [INFO] train episode 13370: reward = 25.87, steps = 54 00:57:03 [INFO] train episode 13371: reward = -19.80, steps = 51 00:57:03 [INFO] train episode 13372: reward = 0.20, steps = 39 00:57:03 [INFO] train episode 13373: reward = 12.90, steps = 40 00:57:04 [INFO] train episode 13374: reward = 3.66, steps = 37 00:57:04 [INFO] train episode 13375: reward = -3.77, steps = 86 00:57:04 [INFO] train episode 13376: reward = 2.21, steps = 34 00:57:05 [INFO] train episode 13377: reward = -19.44, steps = 39 00:57:05 [INFO] train episode 13378: reward = -2.43, steps = 36 00:57:05 [INFO] train episode 13379: reward = 27.59, steps = 60 00:57:06 [INFO] train episode 13380: reward = -3.19, steps = 33 00:57:06 [INFO] train episode 13381: reward = -10.26, steps = 25 00:57:06 [INFO] train episode 13382: reward = -7.45, steps = 32 00:57:06 [INFO] train episode 13383: reward = 9.68, steps = 44 00:57:07 [INFO] train episode 13384: reward = -8.08, steps = 47 00:57:07 [INFO] train episode 13385: reward = -1.22, steps = 44 00:57:07 [INFO] train episode 13386: reward = -6.49, steps = 44 00:57:08 [INFO] train episode 13387: reward = 15.33, steps = 49 00:57:08 [INFO] train episode 13388: reward = 25.29, steps = 64 00:57:09 [INFO] train episode 13389: reward = 3.47, steps = 43 00:57:09 [INFO] train episode 13390: reward = -0.88, steps = 35 00:57:09 [INFO] train episode 13391: reward = -21.46, steps = 31 00:57:09 [INFO] train episode 13392: reward = 10.06, steps = 39 00:57:10 [INFO] train episode 13393: reward = 5.20, steps = 43 00:57:10 [INFO] train episode 13394: reward = -21.57, steps = 20 00:57:10 [INFO] train episode 13395: reward = -3.92, steps = 41 00:57:10 [INFO] train episode 13396: reward = 12.92, steps = 51 00:57:11 [INFO] train episode 13397: reward = 9.78, steps = 46 00:57:11 [INFO] train episode 13398: reward = -1.66, steps = 59 00:57:11 [INFO] train episode 13399: reward = -3.15, steps = 34 00:57:12 [INFO] train episode 13400: reward = 16.76, steps = 52 00:57:12 [INFO] train episode 13401: reward = 4.53, steps = 40 00:57:12 [INFO] train episode 13402: reward = 27.07, steps = 57 00:57:12 [INFO] train episode 13403: reward = 8.31, steps = 51 00:57:13 [INFO] train episode 13404: reward = -29.65, steps = 20 00:57:13 [INFO] train episode 13405: reward = 21.37, steps = 45 00:57:13 [INFO] train episode 13406: reward = -4.52, steps = 63 00:57:14 [INFO] train episode 13407: reward = 7.77, steps = 53 00:57:14 [INFO] train episode 13408: reward = 20.29, steps = 54 00:57:14 [INFO] train episode 13409: reward = -4.24, steps = 52 00:57:15 [INFO] train episode 13410: reward = 11.88, steps = 40 00:57:15 [INFO] train episode 13411: reward = 8.41, steps = 57 00:57:15 [INFO] train episode 13412: reward = -8.54, steps = 51 00:57:16 [INFO] train episode 13413: reward = -21.56, steps = 27 00:57:16 [INFO] train episode 13414: reward = 3.09, steps = 44 00:57:16 [INFO] train episode 13415: reward = -5.18, steps = 28 00:57:16 [INFO] train episode 13416: reward = 17.03, steps = 44 00:57:17 [INFO] train episode 13417: reward = 8.89, steps = 51 00:57:17 [INFO] train episode 13418: reward = 6.95, steps = 36 00:57:17 [INFO] train episode 13419: reward = 26.42, steps = 54 00:57:17 [INFO] train episode 13420: reward = -23.99, steps = 30 00:57:18 [INFO] train episode 13421: reward = -21.26, steps = 42 00:57:18 [INFO] train episode 13422: reward = 13.46, steps = 49 00:57:18 [INFO] train episode 13423: reward = -7.00, steps = 33 00:57:19 [INFO] train episode 13424: reward = 1.07, steps = 34 00:57:19 [INFO] train episode 13425: reward = -20.62, steps = 26 00:57:19 [INFO] train episode 13426: reward = 14.64, steps = 51 00:57:19 [INFO] train episode 13427: reward = -13.89, steps = 38 00:57:20 [INFO] train episode 13428: reward = -10.76, steps = 39 00:57:20 [INFO] train episode 13429: reward = -18.15, steps = 62 00:57:20 [INFO] train episode 13430: reward = 10.82, steps = 70 00:57:21 [INFO] train episode 13431: reward = -34.86, steps = 19 00:57:21 [INFO] train episode 13432: reward = -37.49, steps = 60 00:57:21 [INFO] train episode 13433: reward = -4.07, steps = 34 00:57:22 [INFO] train episode 13434: reward = 22.69, steps = 49 00:57:22 [INFO] train episode 13435: reward = 3.52, steps = 53 00:57:22 [INFO] train episode 13436: reward = 7.83, steps = 39 00:57:23 [INFO] train episode 13437: reward = 3.74, steps = 43 00:57:23 [INFO] train episode 13438: reward = -11.75, steps = 25 00:57:23 [INFO] train episode 13439: reward = 18.91, steps = 44 00:57:23 [INFO] train episode 13440: reward = -11.13, steps = 33 00:57:23 [INFO] train episode 13441: reward = -13.46, steps = 25 00:57:24 [INFO] train episode 13442: reward = 1.63, steps = 37 00:57:24 [INFO] train episode 13443: reward = -2.65, steps = 50 00:57:24 [INFO] train episode 13444: reward = 3.82, steps = 42 00:57:25 [INFO] train episode 13445: reward = 1.66, steps = 33 00:57:25 [INFO] train episode 13446: reward = 2.74, steps = 46 00:57:25 [INFO] train episode 13447: reward = 4.28, steps = 50 00:57:26 [INFO] train episode 13448: reward = -14.32, steps = 31 00:57:26 [INFO] train episode 13449: reward = 18.72, steps = 48 00:57:26 [INFO] train episode 13450: reward = 8.85, steps = 49 00:57:26 [INFO] train episode 13451: reward = -9.35, steps = 33 00:57:27 [INFO] train episode 13452: reward = 11.43, steps = 53 00:57:27 [INFO] train episode 13453: reward = 1.59, steps = 34 00:57:27 [INFO] train episode 13454: reward = 16.17, steps = 72 00:57:28 [INFO] train episode 13455: reward = 25.53, steps = 49 00:57:28 [INFO] train episode 13456: reward = 8.71, steps = 44 00:57:28 [INFO] train episode 13457: reward = -21.49, steps = 36 00:57:29 [INFO] train episode 13458: reward = -6.09, steps = 33 00:57:29 [INFO] train episode 13459: reward = 4.57, steps = 47 00:57:29 [INFO] train episode 13460: reward = 19.03, steps = 42 00:57:29 [INFO] train episode 13461: reward = -1.74, steps = 40 00:57:30 [INFO] train episode 13462: reward = -16.22, steps = 39 00:57:30 [INFO] train episode 13463: reward = 20.04, steps = 82 00:57:30 [INFO] train episode 13464: reward = -14.36, steps = 21 00:57:31 [INFO] train episode 13465: reward = 17.22, steps = 53 00:57:31 [INFO] train episode 13466: reward = 12.35, steps = 40 00:57:31 [INFO] train episode 13467: reward = -0.82, steps = 42 00:57:31 [INFO] train episode 13468: reward = -6.39, steps = 36 00:57:32 [INFO] train episode 13469: reward = 0.99, steps = 43 00:57:32 [INFO] train episode 13470: reward = 6.31, steps = 62 00:57:32 [INFO] train episode 13471: reward = -2.25, steps = 37 00:57:33 [INFO] train episode 13472: reward = 1.11, steps = 45 00:57:33 [INFO] train episode 13473: reward = -5.59, steps = 33 00:57:33 [INFO] train episode 13474: reward = -11.54, steps = 30 00:57:33 [INFO] train episode 13475: reward = -2.77, steps = 37 00:57:34 [INFO] train episode 13476: reward = 9.02, steps = 41 00:57:34 [INFO] train episode 13477: reward = 10.77, steps = 45 00:57:34 [INFO] train episode 13478: reward = 2.57, steps = 38 00:57:35 [INFO] train episode 13479: reward = 20.18, steps = 59 00:57:35 [INFO] train episode 13480: reward = 7.59, steps = 61 00:57:36 [INFO] train episode 13481: reward = 9.25, steps = 66 00:57:36 [INFO] train episode 13482: reward = -0.46, steps = 42 00:57:36 [INFO] train episode 13483: reward = -16.39, steps = 27 00:57:36 [INFO] train episode 13484: reward = -18.43, steps = 18 00:57:37 [INFO] train episode 13485: reward = -12.29, steps = 32 00:57:37 [INFO] train episode 13486: reward = 11.03, steps = 38 00:57:37 [INFO] train episode 13487: reward = 2.86, steps = 55 00:57:37 [INFO] train episode 13488: reward = -12.80, steps = 56 00:57:38 [INFO] train episode 13489: reward = 21.30, steps = 44 00:57:38 [INFO] train episode 13490: reward = -3.31, steps = 31 00:57:38 [INFO] train episode 13491: reward = -12.24, steps = 52 00:57:39 [INFO] train episode 13492: reward = 5.57, steps = 34 00:57:39 [INFO] train episode 13493: reward = 7.68, steps = 48 00:57:39 [INFO] train episode 13494: reward = 13.59, steps = 66 00:57:40 [INFO] train episode 13495: reward = 1.23, steps = 50 00:57:40 [INFO] train episode 13496: reward = 18.51, steps = 39 00:57:40 [INFO] train episode 13497: reward = 16.42, steps = 45 00:57:40 [INFO] train episode 13498: reward = -19.79, steps = 39 00:57:41 [INFO] train episode 13499: reward = 10.18, steps = 44 00:57:41 [INFO] train episode 13500: reward = -22.77, steps = 36 00:57:41 [INFO] train episode 13501: reward = 30.69, steps = 69 00:57:42 [INFO] train episode 13502: reward = 14.02, steps = 46 00:57:42 [INFO] train episode 13503: reward = -0.05, steps = 44 00:57:42 [INFO] train episode 13504: reward = 19.42, steps = 64 00:57:43 [INFO] train episode 13505: reward = -12.66, steps = 20 00:57:43 [INFO] train episode 13506: reward = 1.10, steps = 46 00:57:43 [INFO] train episode 13507: reward = -6.89, steps = 41 00:57:43 [INFO] train episode 13508: reward = -9.74, steps = 28 00:57:44 [INFO] train episode 13509: reward = -18.46, steps = 37 00:57:44 [INFO] train episode 13510: reward = -5.39, steps = 37 00:57:44 [INFO] train episode 13511: reward = 11.53, steps = 39 00:57:44 [INFO] train episode 13512: reward = 13.71, steps = 50 00:57:45 [INFO] train episode 13513: reward = 9.54, steps = 46 00:57:45 [INFO] train episode 13514: reward = 26.11, steps = 52 00:57:45 [INFO] train episode 13515: reward = -1.12, steps = 33 00:57:46 [INFO] train episode 13516: reward = 1.64, steps = 72 00:57:46 [INFO] train episode 13517: reward = -14.78, steps = 24 00:57:46 [INFO] train episode 13518: reward = -10.81, steps = 35 00:57:46 [INFO] train episode 13519: reward = -13.07, steps = 28 00:57:47 [INFO] train episode 13520: reward = 16.28, steps = 60 00:57:47 [INFO] train episode 13521: reward = 33.06, steps = 48 00:57:47 [INFO] train episode 13522: reward = 21.51, steps = 46 00:57:48 [INFO] train episode 13523: reward = -13.84, steps = 62 00:57:48 [INFO] train episode 13524: reward = -25.74, steps = 30 00:57:49 [INFO] train episode 13525: reward = -22.76, steps = 45 00:57:49 [INFO] train episode 13526: reward = 22.44, steps = 47 00:57:49 [INFO] train episode 13527: reward = 9.68, steps = 40 00:57:49 [INFO] train episode 13528: reward = -17.47, steps = 35 00:57:50 [INFO] train episode 13529: reward = 11.00, steps = 61 00:57:50 [INFO] train episode 13530: reward = -4.09, steps = 63 00:57:50 [INFO] train episode 13531: reward = -22.51, steps = 49 00:57:51 [INFO] train episode 13532: reward = -15.08, steps = 21 00:57:51 [INFO] train episode 13533: reward = 25.08, steps = 57 00:57:51 [INFO] train episode 13534: reward = 6.14, steps = 60 00:57:52 [INFO] train episode 13535: reward = 4.17, steps = 39 00:57:52 [INFO] train episode 13536: reward = 9.37, steps = 54 00:57:52 [INFO] train episode 13537: reward = 22.00, steps = 44 00:57:53 [INFO] train episode 13538: reward = -35.82, steps = 67 00:57:53 [INFO] train episode 13539: reward = 13.90, steps = 46 00:57:53 [INFO] train episode 13540: reward = -2.93, steps = 43 00:57:54 [INFO] train episode 13541: reward = -18.28, steps = 58 00:57:54 [INFO] train episode 13542: reward = 9.37, steps = 39 00:57:54 [INFO] train episode 13543: reward = 11.54, steps = 41 00:57:55 [INFO] train episode 13544: reward = 1.30, steps = 47 00:57:55 [INFO] train episode 13545: reward = 10.70, steps = 69 00:57:55 [INFO] train episode 13546: reward = 17.77, steps = 58 00:57:56 [INFO] train episode 13547: reward = -17.70, steps = 38 00:57:56 [INFO] train episode 13548: reward = 3.06, steps = 41 00:57:56 [INFO] train episode 13549: reward = 8.75, steps = 45 00:57:56 [INFO] train episode 13550: reward = -10.20, steps = 29 00:57:57 [INFO] train episode 13551: reward = 4.84, steps = 38 00:57:57 [INFO] train episode 13552: reward = 34.91, steps = 52 00:57:57 [INFO] train episode 13553: reward = 4.50, steps = 35 00:57:58 [INFO] train episode 13554: reward = -12.90, steps = 47 00:57:58 [INFO] train episode 13555: reward = 9.03, steps = 47 00:57:58 [INFO] train episode 13556: reward = -0.55, steps = 42 00:57:59 [INFO] train episode 13557: reward = 15.62, steps = 70 00:57:59 [INFO] train episode 13558: reward = 26.67, steps = 49 00:57:59 [INFO] train episode 13559: reward = -22.41, steps = 18 00:57:59 [INFO] train episode 13560: reward = -10.61, steps = 46 00:58:00 [INFO] train episode 13561: reward = -16.32, steps = 28 00:58:00 [INFO] train episode 13562: reward = 14.41, steps = 43 00:58:00 [INFO] train episode 13563: reward = 24.24, steps = 47 00:58:00 [INFO] train episode 13564: reward = -13.64, steps = 25 00:58:01 [INFO] train episode 13565: reward = 3.89, steps = 36 00:58:01 [INFO] train episode 13566: reward = -2.38, steps = 30 00:58:01 [INFO] train episode 13567: reward = 0.50, steps = 44 00:58:01 [INFO] train episode 13568: reward = 4.98, steps = 44 00:58:02 [INFO] train episode 13569: reward = 14.25, steps = 43 00:58:02 [INFO] train episode 13570: reward = 10.71, steps = 46 00:58:03 [INFO] train episode 13571: reward = -24.01, steps = 45 00:58:03 [INFO] train episode 13572: reward = 6.72, steps = 44 00:58:03 [INFO] train episode 13573: reward = 7.59, steps = 50 00:58:03 [INFO] train episode 13574: reward = -3.76, steps = 40 00:58:04 [INFO] train episode 13575: reward = -7.32, steps = 33 00:58:04 [INFO] train episode 13576: reward = 20.60, steps = 61 00:58:04 [INFO] train episode 13577: reward = 3.23, steps = 45 00:58:05 [INFO] train episode 13578: reward = 16.68, steps = 51 00:58:05 [INFO] train episode 13579: reward = -12.59, steps = 24 00:58:05 [INFO] train episode 13580: reward = -0.74, steps = 36 00:58:06 [INFO] train episode 13581: reward = 27.64, steps = 61 00:58:06 [INFO] train episode 13582: reward = 23.36, steps = 47 00:58:06 [INFO] train episode 13583: reward = 16.41, steps = 51 00:58:07 [INFO] train episode 13584: reward = 11.50, steps = 54 00:58:07 [INFO] train episode 13585: reward = 5.81, steps = 46 00:58:07 [INFO] train episode 13586: reward = -6.16, steps = 47 00:58:07 [INFO] train episode 13587: reward = 20.67, steps = 42 00:58:08 [INFO] train episode 13588: reward = 11.06, steps = 42 00:58:08 [INFO] train episode 13589: reward = -16.27, steps = 25 00:58:08 [INFO] train episode 13590: reward = -6.77, steps = 37 00:58:09 [INFO] train episode 13591: reward = 29.46, steps = 58 00:58:09 [INFO] train episode 13592: reward = 4.75, steps = 52 00:58:09 [INFO] train episode 13593: reward = -18.53, steps = 24 00:58:09 [INFO] train episode 13594: reward = -2.62, steps = 30 00:58:10 [INFO] train episode 13595: reward = 3.84, steps = 33 00:58:10 [INFO] train episode 13596: reward = 11.73, steps = 45 00:58:10 [INFO] train episode 13597: reward = -8.94, steps = 42 00:58:10 [INFO] train episode 13598: reward = 3.79, steps = 36 00:58:11 [INFO] train episode 13599: reward = 29.54, steps = 60 00:58:11 [INFO] train episode 13600: reward = 1.90, steps = 45 00:58:11 [INFO] train episode 13601: reward = -9.19, steps = 44 00:58:12 [INFO] train episode 13602: reward = -11.64, steps = 41 00:58:12 [INFO] train episode 13603: reward = 14.66, steps = 48 00:58:12 [INFO] train episode 13604: reward = -9.74, steps = 38 00:58:12 [INFO] train episode 13605: reward = -1.55, steps = 42 00:58:13 [INFO] train episode 13606: reward = -7.71, steps = 31 00:58:13 [INFO] train episode 13607: reward = 3.04, steps = 32 00:58:13 [INFO] train episode 13608: reward = -10.14, steps = 40 00:58:13 [INFO] train episode 13609: reward = -15.23, steps = 58 00:58:14 [INFO] train episode 13610: reward = -2.43, steps = 51 00:58:14 [INFO] train episode 13611: reward = -19.02, steps = 22 00:58:14 [INFO] train episode 13612: reward = 21.73, steps = 61 00:58:15 [INFO] train episode 13613: reward = -9.28, steps = 25 00:58:15 [INFO] train episode 13614: reward = -16.63, steps = 47 00:58:15 [INFO] train episode 13615: reward = -18.11, steps = 22 00:58:16 [INFO] train episode 13616: reward = -21.61, steps = 41 00:58:16 [INFO] train episode 13617: reward = 0.06, steps = 42 00:58:16 [INFO] train episode 13618: reward = -13.54, steps = 46 00:58:16 [INFO] train episode 13619: reward = -22.49, steps = 43 00:58:17 [INFO] train episode 13620: reward = 2.39, steps = 38 00:58:17 [INFO] train episode 13621: reward = -13.00, steps = 34 00:58:17 [INFO] train episode 13622: reward = 6.98, steps = 38 00:58:18 [INFO] train episode 13623: reward = 33.59, steps = 53 00:58:18 [INFO] train episode 13624: reward = 8.09, steps = 52 00:58:18 [INFO] train episode 13625: reward = -12.63, steps = 38 00:58:19 [INFO] train episode 13626: reward = 25.62, steps = 75 00:58:19 [INFO] train episode 13627: reward = -23.19, steps = 34 00:58:19 [INFO] train episode 13628: reward = 0.40, steps = 33 00:58:19 [INFO] train episode 13629: reward = -15.77, steps = 28 00:58:20 [INFO] train episode 13630: reward = 0.61, steps = 41 00:58:20 [INFO] train episode 13631: reward = -5.48, steps = 30 00:58:20 [INFO] train episode 13632: reward = 0.49, steps = 49 00:58:20 [INFO] train episode 13633: reward = -0.79, steps = 54 00:58:21 [INFO] train episode 13634: reward = -10.61, steps = 48 00:58:21 [INFO] train episode 13635: reward = 7.51, steps = 52 00:58:21 [INFO] train episode 13636: reward = -4.79, steps = 36 00:58:22 [INFO] train episode 13637: reward = -12.42, steps = 32 00:58:22 [INFO] train episode 13638: reward = 3.92, steps = 33 00:58:22 [INFO] train episode 13639: reward = -5.13, steps = 28 00:58:23 [INFO] train episode 13640: reward = -23.91, steps = 75 00:58:23 [INFO] train episode 13641: reward = 16.72, steps = 46 00:58:23 [INFO] train episode 13642: reward = 13.66, steps = 45 00:58:23 [INFO] train episode 13643: reward = 16.19, steps = 44 00:58:24 [INFO] train episode 13644: reward = 24.56, steps = 55 00:58:24 [INFO] train episode 13645: reward = -15.39, steps = 22 00:58:24 [INFO] train episode 13646: reward = -7.17, steps = 31 00:58:25 [INFO] train episode 13647: reward = 14.09, steps = 50 00:58:25 [INFO] train episode 13648: reward = 8.57, steps = 42 00:58:25 [INFO] train episode 13649: reward = -6.12, steps = 45 00:58:25 [INFO] train episode 13650: reward = 29.36, steps = 45 00:58:26 [INFO] train episode 13651: reward = -0.51, steps = 37 00:58:26 [INFO] train episode 13652: reward = -3.17, steps = 49 00:58:26 [INFO] train episode 13653: reward = 3.11, steps = 46 00:58:27 [INFO] train episode 13654: reward = 29.83, steps = 80 00:58:27 [INFO] train episode 13655: reward = -18.98, steps = 20 00:58:27 [INFO] train episode 13656: reward = 4.23, steps = 38 00:58:27 [INFO] train episode 13657: reward = 19.13, steps = 44 00:58:28 [INFO] train episode 13658: reward = 20.99, steps = 55 00:58:28 [INFO] train episode 13659: reward = -19.04, steps = 20 00:58:28 [INFO] train episode 13660: reward = 1.25, steps = 49 00:58:29 [INFO] train episode 13661: reward = 3.13, steps = 42 00:58:29 [INFO] train episode 13662: reward = 2.40, steps = 36 00:58:29 [INFO] train episode 13663: reward = 5.07, steps = 42 00:58:30 [INFO] train episode 13664: reward = -6.36, steps = 23 00:58:30 [INFO] train episode 13665: reward = 29.24, steps = 58 00:58:30 [INFO] train episode 13666: reward = 3.24, steps = 36 00:58:30 [INFO] train episode 13667: reward = -8.17, steps = 23 00:58:31 [INFO] train episode 13668: reward = -9.00, steps = 28 00:58:31 [INFO] train episode 13669: reward = 6.36, steps = 38 00:58:31 [INFO] train episode 13670: reward = 7.14, steps = 53 00:58:31 [INFO] train episode 13671: reward = 7.92, steps = 51 00:58:32 [INFO] train episode 13672: reward = -37.17, steps = 64 00:58:32 [INFO] train episode 13673: reward = 12.68, steps = 49 00:58:32 [INFO] train episode 13674: reward = 7.11, steps = 32 00:58:33 [INFO] train episode 13675: reward = 2.86, steps = 44 00:58:33 [INFO] train episode 13676: reward = -9.51, steps = 33 00:58:33 [INFO] train episode 13677: reward = 1.66, steps = 33 00:58:33 [INFO] train episode 13678: reward = 16.52, steps = 40 00:58:34 [INFO] train episode 13679: reward = -2.02, steps = 53 00:58:34 [INFO] train episode 13680: reward = -9.36, steps = 28 00:58:34 [INFO] train episode 13681: reward = 10.96, steps = 49 00:58:35 [INFO] train episode 13682: reward = -9.35, steps = 23 00:58:35 [INFO] train episode 13683: reward = -0.83, steps = 40 00:58:35 [INFO] train episode 13684: reward = -15.09, steps = 30 00:58:35 [INFO] train episode 13685: reward = -8.47, steps = 29 00:58:35 [INFO] train episode 13686: reward = 13.63, steps = 47 00:58:36 [INFO] train episode 13687: reward = -4.20, steps = 36 00:58:36 [INFO] train episode 13688: reward = 18.94, steps = 70 00:58:36 [INFO] train episode 13689: reward = 25.31, steps = 52 00:58:37 [INFO] train episode 13690: reward = -4.54, steps = 27 00:58:37 [INFO] train episode 13691: reward = -10.16, steps = 44 00:58:37 [INFO] train episode 13692: reward = -2.39, steps = 41 00:58:38 [INFO] train episode 13693: reward = 0.07, steps = 38 00:58:38 [INFO] train episode 13694: reward = 0.28, steps = 49 00:58:38 [INFO] train episode 13695: reward = 6.24, steps = 56 00:58:38 [INFO] train episode 13696: reward = 0.85, steps = 41 00:58:39 [INFO] train episode 13697: reward = 17.03, steps = 55 00:58:39 [INFO] train episode 13698: reward = -16.77, steps = 41 00:58:39 [INFO] train episode 13699: reward = -8.58, steps = 32 00:58:40 [INFO] train episode 13700: reward = -11.04, steps = 45 00:58:40 [INFO] train episode 13701: reward = -11.29, steps = 35 00:58:40 [INFO] train episode 13702: reward = -20.35, steps = 31 00:58:40 [INFO] train episode 13703: reward = 11.20, steps = 41 00:58:41 [INFO] train episode 13704: reward = -6.56, steps = 26 00:58:41 [INFO] train episode 13705: reward = 16.82, steps = 46 00:58:41 [INFO] train episode 13706: reward = 5.35, steps = 43 00:58:41 [INFO] train episode 13707: reward = -14.54, steps = 24 00:58:42 [INFO] train episode 13708: reward = -7.66, steps = 32 00:58:42 [INFO] train episode 13709: reward = 13.93, steps = 68 00:58:42 [INFO] train episode 13710: reward = -6.29, steps = 31 00:58:43 [INFO] train episode 13711: reward = -13.18, steps = 24 00:58:43 [INFO] train episode 13712: reward = 1.29, steps = 42 00:58:43 [INFO] train episode 13713: reward = -1.75, steps = 36 00:58:43 [INFO] train episode 13714: reward = -6.35, steps = 35 00:58:44 [INFO] train episode 13715: reward = 17.78, steps = 62 00:58:44 [INFO] train episode 13716: reward = -15.34, steps = 26 00:58:45 [INFO] train episode 13717: reward = -0.58, steps = 89 00:58:45 [INFO] train episode 13718: reward = 29.79, steps = 64 00:58:45 [INFO] train episode 13719: reward = -22.11, steps = 22 00:58:45 [INFO] train episode 13720: reward = 9.80, steps = 41 00:58:46 [INFO] train episode 13721: reward = -19.22, steps = 32 00:58:46 [INFO] train episode 13722: reward = 8.60, steps = 44 00:58:46 [INFO] train episode 13723: reward = -5.85, steps = 34 00:58:46 [INFO] train episode 13724: reward = 12.45, steps = 49 00:58:47 [INFO] train episode 13725: reward = 18.45, steps = 42 00:58:47 [INFO] train episode 13726: reward = 18.30, steps = 51 00:58:47 [INFO] train episode 13727: reward = -18.59, steps = 36 00:58:48 [INFO] train episode 13728: reward = -0.42, steps = 47 00:58:48 [INFO] train episode 13729: reward = 2.35, steps = 33 00:58:48 [INFO] train episode 13730: reward = 4.08, steps = 42 00:58:49 [INFO] train episode 13731: reward = -8.88, steps = 47 00:58:49 [INFO] train episode 13732: reward = 2.31, steps = 39 00:58:49 [INFO] train episode 13733: reward = 4.25, steps = 33 00:58:49 [INFO] train episode 13734: reward = 4.31, steps = 36 00:58:50 [INFO] train episode 13735: reward = -0.17, steps = 40 00:58:50 [INFO] train episode 13736: reward = 8.79, steps = 45 00:58:50 [INFO] train episode 13737: reward = -2.91, steps = 37 00:58:50 [INFO] train episode 13738: reward = 10.04, steps = 46 00:58:51 [INFO] train episode 13739: reward = 13.06, steps = 46 00:58:51 [INFO] train episode 13740: reward = 12.10, steps = 44 00:58:51 [INFO] train episode 13741: reward = -8.74, steps = 26 00:58:52 [INFO] train episode 13742: reward = 8.26, steps = 57 00:58:52 [INFO] train episode 13743: reward = -14.83, steps = 23 00:58:52 [INFO] train episode 13744: reward = -0.12, steps = 38 00:58:52 [INFO] train episode 13745: reward = -15.81, steps = 24 00:58:52 [INFO] train episode 13746: reward = 0.24, steps = 46 00:58:53 [INFO] train episode 13747: reward = 8.03, steps = 51 00:58:53 [INFO] train episode 13748: reward = -20.58, steps = 50 00:58:53 [INFO] train episode 13749: reward = 19.37, steps = 50 00:58:54 [INFO] train episode 13750: reward = -12.40, steps = 31 00:58:54 [INFO] train episode 13751: reward = -0.03, steps = 39 00:58:54 [INFO] train episode 13752: reward = 6.37, steps = 47 00:58:55 [INFO] train episode 13753: reward = 9.29, steps = 60 00:58:55 [INFO] train episode 13754: reward = 25.29, steps = 56 00:58:55 [INFO] train episode 13755: reward = 17.26, steps = 59 00:58:56 [INFO] train episode 13756: reward = -3.48, steps = 40 00:58:56 [INFO] train episode 13757: reward = -16.77, steps = 25 00:58:56 [INFO] train episode 13758: reward = -9.40, steps = 32 00:58:56 [INFO] train episode 13759: reward = -17.82, steps = 23 00:58:57 [INFO] train episode 13760: reward = 7.01, steps = 42 00:58:57 [INFO] train episode 13761: reward = 8.68, steps = 55 00:58:57 [INFO] train episode 13762: reward = -5.89, steps = 36 00:58:58 [INFO] train episode 13763: reward = 24.82, steps = 53 00:58:58 [INFO] train episode 13764: reward = 11.24, steps = 34 00:58:58 [INFO] train episode 13765: reward = 1.35, steps = 42 00:58:58 [INFO] train episode 13766: reward = -12.38, steps = 31 00:58:59 [INFO] train episode 13767: reward = -10.87, steps = 26 00:58:59 [INFO] train episode 13768: reward = -37.22, steps = 67 00:58:59 [INFO] train episode 13769: reward = 4.98, steps = 46 00:59:00 [INFO] train episode 13770: reward = 14.66, steps = 95 00:59:00 [INFO] train episode 13771: reward = 11.14, steps = 43 00:59:01 [INFO] train episode 13772: reward = -0.75, steps = 121 00:59:01 [INFO] train episode 13773: reward = -15.08, steps = 33 00:59:01 [INFO] train episode 13774: reward = 11.44, steps = 41 00:59:02 [INFO] train episode 13775: reward = -9.66, steps = 26 00:59:02 [INFO] train episode 13776: reward = 22.11, steps = 64 00:59:02 [INFO] train episode 13777: reward = -12.17, steps = 40 00:59:03 [INFO] train episode 13778: reward = -5.54, steps = 31 00:59:03 [INFO] train episode 13779: reward = 3.03, steps = 37 00:59:03 [INFO] train episode 13780: reward = -17.02, steps = 20 00:59:03 [INFO] train episode 13781: reward = 33.25, steps = 67 00:59:04 [INFO] train episode 13782: reward = -7.54, steps = 33 00:59:04 [INFO] train episode 13783: reward = -0.57, steps = 50 00:59:04 [INFO] train episode 13784: reward = -21.41, steps = 29 00:59:05 [INFO] train episode 13785: reward = -7.38, steps = 41 00:59:05 [INFO] train episode 13786: reward = 8.29, steps = 41 00:59:05 [INFO] train episode 13787: reward = 6.80, steps = 41 00:59:05 [INFO] train episode 13788: reward = -11.65, steps = 23 00:59:06 [INFO] train episode 13789: reward = -4.10, steps = 31 00:59:06 [INFO] train episode 13790: reward = -14.83, steps = 27 00:59:06 [INFO] train episode 13791: reward = 2.23, steps = 38 00:59:06 [INFO] train episode 13792: reward = -37.36, steps = 55 00:59:07 [INFO] train episode 13793: reward = 25.62, steps = 52 00:59:07 [INFO] train episode 13794: reward = -4.88, steps = 36 00:59:07 [INFO] train episode 13795: reward = -8.28, steps = 24 00:59:07 [INFO] train episode 13796: reward = -2.94, steps = 34 00:59:08 [INFO] train episode 13797: reward = 8.32, steps = 43 00:59:08 [INFO] train episode 13798: reward = -12.43, steps = 22 00:59:08 [INFO] train episode 13799: reward = 1.59, steps = 39 00:59:08 [INFO] train episode 13800: reward = -2.13, steps = 44 00:59:09 [INFO] train episode 13801: reward = -7.79, steps = 33 00:59:09 [INFO] train episode 13802: reward = -7.03, steps = 48 00:59:09 [INFO] train episode 13803: reward = -5.51, steps = 38 00:59:10 [INFO] train episode 13804: reward = 5.18, steps = 39 00:59:10 [INFO] train episode 13805: reward = 12.57, steps = 38 00:59:10 [INFO] train episode 13806: reward = 14.78, steps = 44 00:59:11 [INFO] train episode 13807: reward = 5.51, steps = 43 00:59:11 [INFO] train episode 13808: reward = 6.51, steps = 59 00:59:11 [INFO] train episode 13809: reward = -1.43, steps = 39 00:59:11 [INFO] train episode 13810: reward = 9.95, steps = 39 00:59:12 [INFO] train episode 13811: reward = 14.59, steps = 56 00:59:12 [INFO] train episode 13812: reward = -4.18, steps = 47 00:59:12 [INFO] train episode 13813: reward = -3.54, steps = 30 00:59:13 [INFO] train episode 13814: reward = -7.34, steps = 38 00:59:13 [INFO] train episode 13815: reward = -16.97, steps = 22 00:59:13 [INFO] train episode 13816: reward = 1.86, steps = 38 00:59:13 [INFO] train episode 13817: reward = 11.56, steps = 43 00:59:14 [INFO] train episode 13818: reward = 13.19, steps = 36 00:59:14 [INFO] train episode 13819: reward = 4.16, steps = 51 00:59:14 [INFO] train episode 13820: reward = -4.98, steps = 32 00:59:14 [INFO] train episode 13821: reward = -16.49, steps = 24 00:59:14 [INFO] train episode 13822: reward = -16.71, steps = 31 00:59:15 [INFO] train episode 13823: reward = 7.65, steps = 44 00:59:15 [INFO] train episode 13824: reward = -1.07, steps = 39 00:59:15 [INFO] train episode 13825: reward = 10.03, steps = 46 00:59:16 [INFO] train episode 13826: reward = 8.87, steps = 46 00:59:16 [INFO] train episode 13827: reward = 6.68, steps = 38 00:59:16 [INFO] train episode 13828: reward = -32.22, steps = 42 00:59:16 [INFO] train episode 13829: reward = 0.03, steps = 42 00:59:17 [INFO] train episode 13830: reward = -17.16, steps = 25 00:59:17 [INFO] train episode 13831: reward = 3.67, steps = 42 00:59:17 [INFO] train episode 13832: reward = -4.63, steps = 29 00:59:17 [INFO] train episode 13833: reward = 12.26, steps = 43 00:59:18 [INFO] train episode 13834: reward = 9.16, steps = 49 00:59:18 [INFO] train episode 13835: reward = 34.11, steps = 71 00:59:18 [INFO] train episode 13836: reward = -7.07, steps = 45 00:59:19 [INFO] train episode 13837: reward = -15.29, steps = 32 00:59:19 [INFO] train episode 13838: reward = 22.04, steps = 44 00:59:19 [INFO] train episode 13839: reward = -2.87, steps = 36 00:59:20 [INFO] train episode 13840: reward = 2.68, steps = 83 00:59:20 [INFO] train episode 13841: reward = 16.02, steps = 43 00:59:20 [INFO] train episode 13842: reward = 10.07, steps = 62 00:59:21 [INFO] train episode 13843: reward = -25.76, steps = 35 00:59:21 [INFO] train episode 13844: reward = 20.93, steps = 59 00:59:22 [INFO] train episode 13845: reward = 45.31, steps = 78 00:59:22 [INFO] train episode 13846: reward = 5.19, steps = 37 00:59:22 [INFO] train episode 13847: reward = -20.72, steps = 20 00:59:23 [INFO] train episode 13848: reward = -5.53, steps = 37 00:59:23 [INFO] train episode 13849: reward = 13.07, steps = 49 00:59:24 [INFO] train episode 13850: reward = 1.64, steps = 53 00:59:24 [INFO] train episode 13851: reward = -20.60, steps = 53 00:59:25 [INFO] train episode 13852: reward = 34.96, steps = 48 00:59:25 [INFO] train episode 13853: reward = 8.12, steps = 50 00:59:25 [INFO] train episode 13854: reward = 20.61, steps = 54 00:59:25 [INFO] train episode 13855: reward = -18.95, steps = 28 00:59:26 [INFO] train episode 13856: reward = 4.59, steps = 37 00:59:26 [INFO] train episode 13857: reward = 15.18, steps = 44 00:59:26 [INFO] train episode 13858: reward = -28.27, steps = 22 00:59:26 [INFO] train episode 13859: reward = -4.41, steps = 31 00:59:27 [INFO] train episode 13860: reward = 17.71, steps = 50 00:59:27 [INFO] train episode 13861: reward = -22.16, steps = 19 00:59:27 [INFO] train episode 13862: reward = 16.67, steps = 50 00:59:27 [INFO] train episode 13863: reward = 11.59, steps = 40 00:59:28 [INFO] train episode 13864: reward = 19.52, steps = 48 00:59:28 [INFO] train episode 13865: reward = -4.56, steps = 40 00:59:28 [INFO] train episode 13866: reward = 2.62, steps = 43 00:59:29 [INFO] train episode 13867: reward = 1.82, steps = 36 00:59:29 [INFO] train episode 13868: reward = 16.89, steps = 40 00:59:29 [INFO] train episode 13869: reward = 8.57, steps = 40 00:59:29 [INFO] train episode 13870: reward = 9.58, steps = 47 00:59:30 [INFO] train episode 13871: reward = -0.82, steps = 30 00:59:30 [INFO] train episode 13872: reward = 24.46, steps = 55 00:59:30 [INFO] train episode 13873: reward = 4.52, steps = 49 00:59:31 [INFO] train episode 13874: reward = -0.45, steps = 48 00:59:31 [INFO] train episode 13875: reward = -9.91, steps = 36 00:59:31 [INFO] train episode 13876: reward = 22.98, steps = 44 00:59:31 [INFO] train episode 13877: reward = -3.84, steps = 39 00:59:32 [INFO] train episode 13878: reward = -4.19, steps = 35 00:59:32 [INFO] train episode 13879: reward = 14.70, steps = 70 00:59:32 [INFO] train episode 13880: reward = -3.71, steps = 44 00:59:33 [INFO] train episode 13881: reward = 3.50, steps = 50 00:59:33 [INFO] train episode 13882: reward = -0.03, steps = 30 00:59:33 [INFO] train episode 13883: reward = 8.87, steps = 43 00:59:34 [INFO] train episode 13884: reward = 13.08, steps = 57 00:59:34 [INFO] train episode 13885: reward = 17.41, steps = 58 00:59:34 [INFO] train episode 13886: reward = 8.26, steps = 45 00:59:35 [INFO] train episode 13887: reward = -23.92, steps = 54 00:59:35 [INFO] train episode 13888: reward = 9.17, steps = 38 00:59:35 [INFO] train episode 13889: reward = -1.57, steps = 38 00:59:36 [INFO] train episode 13890: reward = 12.65, steps = 48 00:59:36 [INFO] train episode 13891: reward = 9.83, steps = 36 00:59:36 [INFO] train episode 13892: reward = 17.81, steps = 46 00:59:36 [INFO] train episode 13893: reward = 7.68, steps = 37 00:59:37 [INFO] train episode 13894: reward = 0.19, steps = 54 00:59:37 [INFO] train episode 13895: reward = -3.39, steps = 46 00:59:38 [INFO] train episode 13896: reward = 18.75, steps = 44 00:59:38 [INFO] train episode 13897: reward = 16.82, steps = 67 00:59:38 [INFO] train episode 13898: reward = 4.32, steps = 49 00:59:39 [INFO] train episode 13899: reward = 15.27, steps = 48 00:59:39 [INFO] train episode 13900: reward = 9.87, steps = 36 00:59:39 [INFO] train episode 13901: reward = 19.94, steps = 49 00:59:39 [INFO] train episode 13902: reward = 0.05, steps = 40 00:59:40 [INFO] train episode 13903: reward = 11.90, steps = 44 00:59:40 [INFO] train episode 13904: reward = -3.55, steps = 30 00:59:40 [INFO] train episode 13905: reward = -1.79, steps = 36 00:59:40 [INFO] train episode 13906: reward = 9.98, steps = 39 00:59:41 [INFO] train episode 13907: reward = 14.02, steps = 55 00:59:41 [INFO] train episode 13908: reward = 2.32, steps = 44 00:59:41 [INFO] train episode 13909: reward = -9.64, steps = 22 00:59:42 [INFO] train episode 13910: reward = -15.76, steps = 43 00:59:42 [INFO] train episode 13911: reward = 1.87, steps = 43 00:59:42 [INFO] train episode 13912: reward = 17.60, steps = 49 00:59:42 [INFO] train episode 13913: reward = 1.58, steps = 44 00:59:43 [INFO] train episode 13914: reward = 13.61, steps = 46 00:59:43 [INFO] train episode 13915: reward = 16.00, steps = 63 00:59:44 [INFO] train episode 13916: reward = 16.87, steps = 54 00:59:44 [INFO] train episode 13917: reward = -7.23, steps = 26 00:59:44 [INFO] train episode 13918: reward = -15.78, steps = 25 00:59:44 [INFO] train episode 13919: reward = -11.22, steps = 26 00:59:44 [INFO] train episode 13920: reward = 16.48, steps = 60 00:59:45 [INFO] train episode 13921: reward = 13.24, steps = 41 00:59:45 [INFO] train episode 13922: reward = 10.73, steps = 46 00:59:45 [INFO] train episode 13923: reward = -16.83, steps = 23 00:59:45 [INFO] train episode 13924: reward = 0.23, steps = 29 00:59:46 [INFO] train episode 13925: reward = -20.83, steps = 48 00:59:46 [INFO] train episode 13926: reward = 21.00, steps = 57 00:59:46 [INFO] train episode 13927: reward = 15.14, steps = 45 00:59:47 [INFO] train episode 13928: reward = 3.77, steps = 40 00:59:47 [INFO] train episode 13929: reward = -15.35, steps = 50 00:59:48 [INFO] train episode 13930: reward = -23.34, steps = 90 00:59:48 [INFO] train episode 13931: reward = 9.95, steps = 34 00:59:48 [INFO] train episode 13932: reward = 13.84, steps = 41 00:59:48 [INFO] train episode 13933: reward = -18.01, steps = 28 00:59:48 [INFO] train episode 13934: reward = -16.45, steps = 28 00:59:49 [INFO] train episode 13935: reward = -13.82, steps = 30 00:59:49 [INFO] train episode 13936: reward = 14.47, steps = 50 00:59:49 [INFO] train episode 13937: reward = 1.37, steps = 41 00:59:50 [INFO] train episode 13938: reward = -9.14, steps = 43 00:59:50 [INFO] train episode 13939: reward = -5.22, steps = 38 00:59:50 [INFO] train episode 13940: reward = -32.95, steps = 24 00:59:50 [INFO] train episode 13941: reward = 3.46, steps = 66 00:59:51 [INFO] train episode 13942: reward = 13.33, steps = 50 00:59:51 [INFO] train episode 13943: reward = -13.25, steps = 23 00:59:51 [INFO] train episode 13944: reward = 10.57, steps = 50 00:59:52 [INFO] train episode 13945: reward = 0.08, steps = 56 00:59:52 [INFO] train episode 13946: reward = -15.42, steps = 40 00:59:52 [INFO] train episode 13947: reward = -0.73, steps = 40 00:59:53 [INFO] train episode 13948: reward = 14.38, steps = 59 00:59:53 [INFO] train episode 13949: reward = -14.68, steps = 25 00:59:53 [INFO] train episode 13950: reward = 10.03, steps = 54 00:59:54 [INFO] train episode 13951: reward = 28.01, steps = 61 00:59:54 [INFO] train episode 13952: reward = -18.23, steps = 22 00:59:54 [INFO] train episode 13953: reward = 15.07, steps = 41 00:59:55 [INFO] train episode 13954: reward = 28.88, steps = 59 00:59:55 [INFO] train episode 13955: reward = 10.42, steps = 45 00:59:55 [INFO] train episode 13956: reward = 3.73, steps = 57 00:59:55 [INFO] train episode 13957: reward = 13.86, steps = 39 00:59:56 [INFO] train episode 13958: reward = 1.99, steps = 74 00:59:56 [INFO] train episode 13959: reward = -11.88, steps = 43 00:59:56 [INFO] train episode 13960: reward = 25.98, steps = 47 00:59:57 [INFO] train episode 13961: reward = 7.42, steps = 42 00:59:57 [INFO] train episode 13962: reward = -1.88, steps = 39 00:59:57 [INFO] train episode 13963: reward = 16.47, steps = 41 00:59:57 [INFO] train episode 13964: reward = -12.43, steps = 20 00:59:58 [INFO] train episode 13965: reward = 11.73, steps = 35 00:59:58 [INFO] train episode 13966: reward = -9.88, steps = 37 00:59:58 [INFO] train episode 13967: reward = 3.50, steps = 41 00:59:58 [INFO] train episode 13968: reward = 3.98, steps = 40 00:59:59 [INFO] train episode 13969: reward = 20.98, steps = 47 00:59:59 [INFO] train episode 13970: reward = 0.50, steps = 40 00:59:59 [INFO] train episode 13971: reward = 10.05, steps = 39 01:00:00 [INFO] train episode 13972: reward = 3.70, steps = 43 01:00:00 [INFO] train episode 13973: reward = -0.33, steps = 36 01:00:00 [INFO] train episode 13974: reward = -7.03, steps = 34 01:00:00 [INFO] train episode 13975: reward = 9.05, steps = 34 01:00:01 [INFO] train episode 13976: reward = 2.00, steps = 44 01:00:01 [INFO] train episode 13977: reward = 18.75, steps = 44 01:00:01 [INFO] train episode 13978: reward = 14.27, steps = 46 01:00:01 [INFO] train episode 13979: reward = -6.88, steps = 27 01:00:02 [INFO] train episode 13980: reward = 21.11, steps = 47 01:00:02 [INFO] train episode 13981: reward = -21.14, steps = 32 01:00:02 [INFO] train episode 13982: reward = 1.00, steps = 39 01:00:03 [INFO] train episode 13983: reward = 32.65, steps = 64 01:00:03 [INFO] train episode 13984: reward = -7.83, steps = 28 01:00:03 [INFO] train episode 13985: reward = -36.70, steps = 55 01:00:04 [INFO] train episode 13986: reward = 7.70, steps = 39 01:00:04 [INFO] train episode 13987: reward = 17.02, steps = 47 01:00:04 [INFO] train episode 13988: reward = -1.13, steps = 49 01:00:05 [INFO] train episode 13989: reward = 2.21, steps = 48 01:00:05 [INFO] train episode 13990: reward = -22.54, steps = 36 01:00:05 [INFO] train episode 13991: reward = 5.49, steps = 35 01:00:05 [INFO] train episode 13992: reward = 7.65, steps = 36 01:00:06 [INFO] train episode 13993: reward = 34.37, steps = 123 01:00:07 [INFO] train episode 13994: reward = 19.31, steps = 45 01:00:07 [INFO] train episode 13995: reward = 8.26, steps = 44 01:00:07 [INFO] train episode 13996: reward = 0.17, steps = 37 01:00:07 [INFO] train episode 13997: reward = 15.35, steps = 45 01:00:08 [INFO] train episode 13998: reward = -28.30, steps = 47 01:00:08 [INFO] train episode 13999: reward = -4.03, steps = 34 01:00:08 [INFO] train episode 14000: reward = 17.72, steps = 47 01:00:08 [INFO] train episode 14001: reward = 5.69, steps = 38 01:00:09 [INFO] train episode 14002: reward = -12.70, steps = 19 01:00:09 [INFO] train episode 14003: reward = 6.08, steps = 35 01:00:09 [INFO] train episode 14004: reward = 1.33, steps = 78 01:00:10 [INFO] train episode 14005: reward = 13.50, steps = 54 01:00:10 [INFO] train episode 14006: reward = 24.15, steps = 47 01:00:10 [INFO] train episode 14007: reward = 21.32, steps = 40 01:00:10 [INFO] train episode 14008: reward = -8.73, steps = 39 01:00:11 [INFO] train episode 14009: reward = 5.98, steps = 50 01:00:11 [INFO] train episode 14010: reward = 0.98, steps = 45 01:00:11 [INFO] train episode 14011: reward = 0.82, steps = 35 01:00:12 [INFO] train episode 14012: reward = 1.91, steps = 32 01:00:12 [INFO] train episode 14013: reward = 14.39, steps = 35 01:00:12 [INFO] train episode 14014: reward = -14.66, steps = 47 01:00:13 [INFO] train episode 14015: reward = -10.54, steps = 67 01:00:13 [INFO] train episode 14016: reward = 5.90, steps = 50 01:00:13 [INFO] train episode 14017: reward = 9.39, steps = 57 01:00:14 [INFO] train episode 14018: reward = 0.95, steps = 58 01:00:14 [INFO] train episode 14019: reward = -0.05, steps = 34 01:00:14 [INFO] train episode 14020: reward = 22.42, steps = 56 01:00:15 [INFO] train episode 14021: reward = -2.96, steps = 52 01:00:15 [INFO] train episode 14022: reward = -0.86, steps = 30 01:00:15 [INFO] train episode 14023: reward = 7.54, steps = 52 01:00:15 [INFO] train episode 14024: reward = -22.37, steps = 21 01:00:16 [INFO] train episode 14025: reward = 29.25, steps = 64 01:00:16 [INFO] train episode 14026: reward = 13.08, steps = 54 01:00:16 [INFO] train episode 14027: reward = -10.10, steps = 39 01:00:17 [INFO] train episode 14028: reward = 11.20, steps = 38 01:00:17 [INFO] train episode 14029: reward = -3.24, steps = 34 01:00:17 [INFO] train episode 14030: reward = -16.58, steps = 26 01:00:17 [INFO] train episode 14031: reward = -17.47, steps = 22 01:00:18 [INFO] train episode 14032: reward = 12.05, steps = 46 01:00:18 [INFO] train episode 14033: reward = 21.09, steps = 53 01:00:18 [INFO] train episode 14034: reward = -18.82, steps = 24 01:00:19 [INFO] train episode 14035: reward = 13.55, steps = 45 01:00:19 [INFO] train episode 14036: reward = 6.86, steps = 38 01:00:19 [INFO] train episode 14037: reward = 10.54, steps = 40 01:00:20 [INFO] train episode 14038: reward = 20.10, steps = 52 01:00:20 [INFO] train episode 14039: reward = 10.40, steps = 46 01:00:20 [INFO] train episode 14040: reward = -8.73, steps = 43 01:00:20 [INFO] train episode 14041: reward = -10.26, steps = 36 01:00:21 [INFO] train episode 14042: reward = -10.03, steps = 30 01:00:21 [INFO] train episode 14043: reward = 13.18, steps = 47 01:00:21 [INFO] train episode 14044: reward = 21.33, steps = 53 01:00:22 [INFO] train episode 14045: reward = 14.97, steps = 43 01:00:22 [INFO] train episode 14046: reward = 16.77, steps = 41 01:00:22 [INFO] train episode 14047: reward = -21.98, steps = 24 01:00:22 [INFO] train episode 14048: reward = 5.41, steps = 50 01:00:22 [INFO] train episode 14049: reward = -5.43, steps = 27 01:00:23 [INFO] train episode 14050: reward = 10.77, steps = 43 01:00:23 [INFO] train episode 14051: reward = -6.49, steps = 27 01:00:23 [INFO] train episode 14052: reward = -7.26, steps = 28 01:00:23 [INFO] train episode 14053: reward = 23.78, steps = 52 01:00:24 [INFO] train episode 14054: reward = -0.52, steps = 38 01:00:24 [INFO] train episode 14055: reward = -0.74, steps = 53 01:00:24 [INFO] train episode 14056: reward = 7.04, steps = 40 01:00:25 [INFO] train episode 14057: reward = -8.46, steps = 22 01:00:25 [INFO] train episode 14058: reward = -13.80, steps = 31 01:00:25 [INFO] train episode 14059: reward = -3.97, steps = 39 01:00:25 [INFO] train episode 14060: reward = 24.16, steps = 77 01:00:26 [INFO] train episode 14061: reward = 7.64, steps = 32 01:00:26 [INFO] train episode 14062: reward = -19.17, steps = 27 01:00:26 [INFO] train episode 14063: reward = -7.62, steps = 26 01:00:26 [INFO] train episode 14064: reward = -0.55, steps = 28 01:00:27 [INFO] train episode 14065: reward = 8.33, steps = 54 01:00:27 [INFO] train episode 14066: reward = 13.53, steps = 47 01:00:27 [INFO] train episode 14067: reward = 17.25, steps = 43 01:00:28 [INFO] train episode 14068: reward = 7.29, steps = 42 01:00:28 [INFO] train episode 14069: reward = -18.81, steps = 60 01:00:28 [INFO] train episode 14070: reward = 14.26, steps = 44 01:00:28 [INFO] train episode 14071: reward = -5.78, steps = 37 01:00:29 [INFO] train episode 14072: reward = 7.64, steps = 42 01:00:29 [INFO] train episode 14073: reward = 11.71, steps = 41 01:00:29 [INFO] train episode 14074: reward = 14.91, steps = 56 01:00:30 [INFO] train episode 14075: reward = -15.37, steps = 23 01:00:30 [INFO] train episode 14076: reward = -2.49, steps = 54 01:00:30 [INFO] train episode 14077: reward = 7.24, steps = 34 01:00:30 [INFO] train episode 14078: reward = 15.60, steps = 46 01:00:31 [INFO] train episode 14079: reward = 42.52, steps = 65 01:00:31 [INFO] train episode 14080: reward = -8.90, steps = 30 01:00:32 [INFO] train episode 14081: reward = -10.15, steps = 44 01:00:32 [INFO] train episode 14082: reward = 7.29, steps = 38 01:00:32 [INFO] train episode 14083: reward = 18.07, steps = 43 01:00:32 [INFO] train episode 14084: reward = 5.29, steps = 36 01:00:33 [INFO] train episode 14085: reward = 17.59, steps = 60 01:00:33 [INFO] train episode 14086: reward = 2.12, steps = 44 01:00:33 [INFO] train episode 14087: reward = 3.31, steps = 38 01:00:34 [INFO] train episode 14088: reward = 10.90, steps = 39 01:00:34 [INFO] train episode 14089: reward = 8.71, steps = 45 01:00:34 [INFO] train episode 14090: reward = 24.21, steps = 53 01:00:34 [INFO] train episode 14091: reward = -18.90, steps = 25 01:00:35 [INFO] train episode 14092: reward = -18.78, steps = 78 01:00:35 [INFO] train episode 14093: reward = 12.07, steps = 54 01:00:36 [INFO] train episode 14094: reward = 2.21, steps = 60 01:00:36 [INFO] train episode 14095: reward = 10.07, steps = 49 01:00:36 [INFO] train episode 14096: reward = 3.65, steps = 39 01:00:36 [INFO] train episode 14097: reward = 1.65, steps = 49 01:00:37 [INFO] train episode 14098: reward = -4.46, steps = 23 01:00:37 [INFO] train episode 14099: reward = 23.59, steps = 51 01:00:37 [INFO] train episode 14100: reward = 13.56, steps = 45 01:00:38 [INFO] train episode 14101: reward = 2.90, steps = 47 01:00:38 [INFO] train episode 14102: reward = 3.85, steps = 44 01:00:38 [INFO] train episode 14103: reward = 14.07, steps = 39 01:00:39 [INFO] train episode 14104: reward = 32.61, steps = 52 01:00:39 [INFO] train episode 14105: reward = 1.89, steps = 43 01:00:39 [INFO] train episode 14106: reward = 19.80, steps = 61 01:00:39 [INFO] train episode 14107: reward = -10.57, steps = 29 01:00:40 [INFO] train episode 14108: reward = 20.29, steps = 48 01:00:40 [INFO] train episode 14109: reward = -5.63, steps = 46 01:00:40 [INFO] train episode 14110: reward = 4.00, steps = 37 01:00:41 [INFO] train episode 14111: reward = -4.57, steps = 37 01:00:41 [INFO] train episode 14112: reward = -13.46, steps = 33 01:00:41 [INFO] train episode 14113: reward = 22.94, steps = 51 01:00:41 [INFO] train episode 14114: reward = -3.72, steps = 55 01:00:42 [INFO] train episode 14115: reward = 0.41, steps = 35 01:00:42 [INFO] train episode 14116: reward = -0.36, steps = 68 01:00:42 [INFO] train episode 14117: reward = 7.60, steps = 37 01:00:43 [INFO] train episode 14118: reward = 10.75, steps = 38 01:00:43 [INFO] train episode 14119: reward = 8.35, steps = 58 01:00:43 [INFO] train episode 14120: reward = -1.84, steps = 29 01:00:43 [INFO] train episode 14121: reward = 3.99, steps = 39 01:00:44 [INFO] train episode 14122: reward = 29.92, steps = 63 01:00:44 [INFO] train episode 14123: reward = 26.05, steps = 48 01:00:45 [INFO] train episode 14124: reward = 14.21, steps = 44 01:00:45 [INFO] train episode 14125: reward = -8.52, steps = 28 01:00:45 [INFO] train episode 14126: reward = -4.93, steps = 27 01:00:45 [INFO] train episode 14127: reward = 8.10, steps = 31 01:00:46 [INFO] train episode 14128: reward = -27.05, steps = 30 01:00:46 [INFO] train episode 14129: reward = 18.53, steps = 50 01:00:46 [INFO] train episode 14130: reward = 15.67, steps = 50 01:00:46 [INFO] train episode 14131: reward = -9.20, steps = 30 01:00:47 [INFO] train episode 14132: reward = 7.76, steps = 54 01:00:47 [INFO] train episode 14133: reward = 8.48, steps = 36 01:00:47 [INFO] train episode 14134: reward = -10.12, steps = 28 01:00:47 [INFO] train episode 14135: reward = 14.81, steps = 49 01:00:48 [INFO] train episode 14136: reward = 8.14, steps = 37 01:00:48 [INFO] train episode 14137: reward = 24.72, steps = 47 01:00:49 [INFO] train episode 14138: reward = 31.39, steps = 82 01:00:49 [INFO] train episode 14139: reward = -2.79, steps = 47 01:00:49 [INFO] train episode 14140: reward = 10.91, steps = 45 01:00:49 [INFO] train episode 14141: reward = 30.85, steps = 45 01:00:50 [INFO] train episode 14142: reward = 16.07, steps = 47 01:00:50 [INFO] train episode 14143: reward = 9.75, steps = 39 01:00:50 [INFO] train episode 14144: reward = 3.73, steps = 32 01:00:50 [INFO] train episode 14145: reward = 5.59, steps = 29 01:00:51 [INFO] train episode 14146: reward = 15.81, steps = 44 01:00:51 [INFO] train episode 14147: reward = -7.56, steps = 40 01:00:51 [INFO] train episode 14148: reward = 2.82, steps = 30 01:00:52 [INFO] train episode 14149: reward = -1.75, steps = 45 01:00:52 [INFO] train episode 14150: reward = 9.57, steps = 38 01:00:52 [INFO] train episode 14151: reward = 32.86, steps = 74 01:00:53 [INFO] train episode 14152: reward = -0.48, steps = 42 01:00:53 [INFO] train episode 14153: reward = -0.17, steps = 32 01:00:53 [INFO] train episode 14154: reward = -17.42, steps = 33 01:00:53 [INFO] train episode 14155: reward = 12.95, steps = 45 01:00:54 [INFO] train episode 14156: reward = 7.52, steps = 45 01:00:54 [INFO] train episode 14157: reward = 1.51, steps = 36 01:00:54 [INFO] train episode 14158: reward = -4.08, steps = 28 01:00:54 [INFO] train episode 14159: reward = 12.42, steps = 41 01:00:55 [INFO] train episode 14160: reward = 6.02, steps = 37 01:00:55 [INFO] train episode 14161: reward = -8.01, steps = 33 01:00:55 [INFO] train episode 14162: reward = -31.61, steps = 23 01:00:55 [INFO] train episode 14163: reward = 5.95, steps = 52 01:00:56 [INFO] train episode 14164: reward = 1.12, steps = 42 01:00:56 [INFO] train episode 14165: reward = 5.56, steps = 39 01:00:56 [INFO] train episode 14166: reward = 5.21, steps = 54 01:00:56 [INFO] train episode 14167: reward = 4.99, steps = 30 01:00:57 [INFO] train episode 14168: reward = 10.51, steps = 43 01:00:57 [INFO] train episode 14169: reward = 3.75, steps = 42 01:00:57 [INFO] train episode 14170: reward = 11.73, steps = 43 01:00:58 [INFO] train episode 14171: reward = 9.43, steps = 53 01:00:58 [INFO] train episode 14172: reward = 0.76, steps = 45 01:00:58 [INFO] train episode 14173: reward = 11.79, steps = 44 01:00:59 [INFO] train episode 14174: reward = 2.36, steps = 38 01:00:59 [INFO] train episode 14175: reward = 1.02, steps = 37 01:00:59 [INFO] train episode 14176: reward = -3.85, steps = 34 01:00:59 [INFO] train episode 14177: reward = -1.47, steps = 33 01:01:00 [INFO] train episode 14178: reward = 11.56, steps = 49 01:01:00 [INFO] train episode 14179: reward = 21.54, steps = 50 01:01:00 [INFO] train episode 14180: reward = 18.98, steps = 45 01:01:01 [INFO] train episode 14181: reward = -11.29, steps = 28 01:01:01 [INFO] train episode 14182: reward = -8.56, steps = 41 01:01:01 [INFO] train episode 14183: reward = 19.46, steps = 52 01:01:01 [INFO] train episode 14184: reward = 17.18, steps = 39 01:01:02 [INFO] train episode 14185: reward = 9.08, steps = 36 01:01:02 [INFO] train episode 14186: reward = 12.05, steps = 42 01:01:02 [INFO] train episode 14187: reward = -30.72, steps = 18 01:01:02 [INFO] train episode 14188: reward = 20.02, steps = 53 01:01:03 [INFO] train episode 14189: reward = -1.66, steps = 71 01:01:03 [INFO] train episode 14190: reward = -42.42, steps = 59 01:01:04 [INFO] train episode 14191: reward = 5.68, steps = 35 01:01:04 [INFO] train episode 14192: reward = 7.72, steps = 55 01:01:04 [INFO] train episode 14193: reward = -15.82, steps = 29 01:01:04 [INFO] train episode 14194: reward = -12.31, steps = 26 01:01:05 [INFO] train episode 14195: reward = -2.21, steps = 26 01:01:05 [INFO] train episode 14196: reward = 6.08, steps = 44 01:01:05 [INFO] train episode 14197: reward = 16.57, steps = 48 01:01:05 [INFO] train episode 14198: reward = -12.17, steps = 37 01:01:06 [INFO] train episode 14199: reward = -9.22, steps = 34 01:01:06 [INFO] train episode 14200: reward = -10.69, steps = 35 01:01:06 [INFO] train episode 14201: reward = -0.71, steps = 49 01:01:07 [INFO] train episode 14202: reward = 9.28, steps = 39 01:01:07 [INFO] train episode 14203: reward = 8.76, steps = 43 01:01:07 [INFO] train episode 14204: reward = 21.87, steps = 54 01:01:08 [INFO] train episode 14205: reward = 0.72, steps = 42 01:01:08 [INFO] train episode 14206: reward = 16.73, steps = 50 01:01:08 [INFO] train episode 14207: reward = 26.95, steps = 57 01:01:08 [INFO] train episode 14208: reward = -8.32, steps = 25 01:01:09 [INFO] train episode 14209: reward = 2.41, steps = 39 01:01:09 [INFO] train episode 14210: reward = 20.58, steps = 57 01:01:09 [INFO] train episode 14211: reward = 1.79, steps = 51 01:01:10 [INFO] train episode 14212: reward = 19.97, steps = 53 01:01:10 [INFO] train episode 14213: reward = 8.94, steps = 43 01:01:10 [INFO] train episode 14214: reward = -0.47, steps = 33 01:01:11 [INFO] train episode 14215: reward = -38.25, steps = 68 01:01:11 [INFO] train episode 14216: reward = -6.10, steps = 35 01:01:11 [INFO] train episode 14217: reward = 11.06, steps = 44 01:01:12 [INFO] train episode 14218: reward = 15.40, steps = 44 01:01:12 [INFO] train episode 14219: reward = -22.16, steps = 25 01:01:12 [INFO] train episode 14220: reward = 24.34, steps = 54 01:01:12 [INFO] train episode 14221: reward = -5.19, steps = 46 01:01:13 [INFO] train episode 14222: reward = -16.94, steps = 52 01:01:13 [INFO] train episode 14223: reward = 13.19, steps = 47 01:01:14 [INFO] train episode 14224: reward = 18.15, steps = 63 01:01:14 [INFO] train episode 14225: reward = -8.05, steps = 68 01:01:14 [INFO] train episode 14226: reward = -9.03, steps = 38 01:01:14 [INFO] train episode 14227: reward = 0.10, steps = 31 01:01:15 [INFO] train episode 14228: reward = 5.87, steps = 44 01:01:15 [INFO] train episode 14229: reward = 12.18, steps = 39 01:01:15 [INFO] train episode 14230: reward = 22.17, steps = 52 01:01:16 [INFO] train episode 14231: reward = 3.74, steps = 43 01:01:16 [INFO] train episode 14232: reward = 21.53, steps = 51 01:01:16 [INFO] train episode 14233: reward = 21.94, steps = 51 01:01:17 [INFO] train episode 14234: reward = 3.23, steps = 38 01:01:17 [INFO] train episode 14235: reward = -0.85, steps = 47 01:01:17 [INFO] train episode 14236: reward = 28.38, steps = 52 01:01:17 [INFO] train episode 14237: reward = -13.67, steps = 32 01:01:18 [INFO] train episode 14238: reward = -0.24, steps = 32 01:01:18 [INFO] train episode 14239: reward = 5.54, steps = 38 01:01:18 [INFO] train episode 14240: reward = 4.27, steps = 38 01:01:19 [INFO] train episode 14241: reward = 14.80, steps = 43 01:01:19 [INFO] train episode 14242: reward = 0.48, steps = 39 01:01:19 [INFO] train episode 14243: reward = -3.64, steps = 41 01:01:19 [INFO] train episode 14244: reward = 14.57, steps = 46 01:01:19 [INFO] train episode 14245: reward = -24.20, steps = 21 01:01:20 [INFO] train episode 14246: reward = 15.92, steps = 58 01:01:20 [INFO] train episode 14247: reward = -3.51, steps = 38 01:01:20 [INFO] train episode 14248: reward = 11.41, steps = 33 01:01:21 [INFO] train episode 14249: reward = 14.41, steps = 37 01:01:21 [INFO] train episode 14250: reward = 8.72, steps = 43 01:01:21 [INFO] train episode 14251: reward = 5.15, steps = 36 01:01:21 [INFO] train episode 14252: reward = -3.31, steps = 44 01:01:22 [INFO] train episode 14253: reward = 38.67, steps = 53 01:01:22 [INFO] train episode 14254: reward = 14.46, steps = 35 01:01:22 [INFO] train episode 14255: reward = 15.09, steps = 46 01:01:23 [INFO] train episode 14256: reward = -0.73, steps = 25 01:01:23 [INFO] train episode 14257: reward = 0.50, steps = 36 01:01:23 [INFO] train episode 14258: reward = -0.83, steps = 45 01:01:23 [INFO] train episode 14259: reward = 4.05, steps = 40 01:01:24 [INFO] train episode 14260: reward = -1.15, steps = 36 01:01:24 [INFO] train episode 14261: reward = 23.12, steps = 54 01:01:24 [INFO] train episode 14262: reward = -8.67, steps = 43 01:01:25 [INFO] train episode 14263: reward = 19.47, steps = 46 01:01:25 [INFO] train episode 14264: reward = 21.48, steps = 47 01:01:25 [INFO] train episode 14265: reward = -3.54, steps = 41 01:01:26 [INFO] train episode 14266: reward = 6.20, steps = 70 01:01:26 [INFO] train episode 14267: reward = -3.00, steps = 31 01:01:26 [INFO] train episode 14268: reward = 8.07, steps = 50 01:01:27 [INFO] train episode 14269: reward = 3.20, steps = 46 01:01:27 [INFO] train episode 14270: reward = 7.35, steps = 48 01:01:27 [INFO] train episode 14271: reward = 9.44, steps = 44 01:01:28 [INFO] train episode 14272: reward = 4.55, steps = 42 01:01:28 [INFO] train episode 14273: reward = -1.53, steps = 57 01:01:28 [INFO] train episode 14274: reward = 24.08, steps = 54 01:01:29 [INFO] train episode 14275: reward = 19.87, steps = 38 01:01:29 [INFO] train episode 14276: reward = -16.57, steps = 37 01:01:29 [INFO] train episode 14277: reward = 22.07, steps = 50 01:01:29 [INFO] train episode 14278: reward = 14.68, steps = 45 01:01:30 [INFO] train episode 14279: reward = -4.98, steps = 32 01:01:30 [INFO] train episode 14280: reward = -22.84, steps = 33 01:01:30 [INFO] train episode 14281: reward = -33.51, steps = 64 01:01:30 [INFO] train episode 14282: reward = -26.53, steps = 20 01:01:31 [INFO] train episode 14283: reward = 0.65, steps = 41 01:01:31 [INFO] train episode 14284: reward = 15.46, steps = 61 01:01:31 [INFO] train episode 14285: reward = 7.09, steps = 34 01:01:31 [INFO] train episode 14286: reward = -14.52, steps = 20 01:01:32 [INFO] train episode 14287: reward = 21.64, steps = 49 01:01:32 [INFO] train episode 14288: reward = -12.87, steps = 32 01:01:32 [INFO] train episode 14289: reward = 17.96, steps = 53 01:01:33 [INFO] train episode 14290: reward = 10.57, steps = 49 01:01:33 [INFO] train episode 14291: reward = 2.37, steps = 37 01:01:33 [INFO] train episode 14292: reward = 20.87, steps = 45 01:01:34 [INFO] train episode 14293: reward = 26.19, steps = 76 01:01:34 [INFO] train episode 14294: reward = 29.42, steps = 58 01:01:34 [INFO] train episode 14295: reward = -5.39, steps = 27 01:01:35 [INFO] train episode 14296: reward = 6.00, steps = 35 01:01:35 [INFO] train episode 14297: reward = -0.43, steps = 48 01:01:35 [INFO] train episode 14298: reward = 11.54, steps = 42 01:01:35 [INFO] train episode 14299: reward = 21.01, steps = 47 01:01:36 [INFO] train episode 14300: reward = 22.39, steps = 52 01:01:36 [INFO] train episode 14301: reward = -14.21, steps = 28 01:01:36 [INFO] train episode 14302: reward = 10.22, steps = 40 01:01:37 [INFO] train episode 14303: reward = 14.04, steps = 60 01:01:37 [INFO] train episode 14304: reward = 18.56, steps = 36 01:01:37 [INFO] train episode 14305: reward = 8.12, steps = 34 01:01:38 [INFO] train episode 14306: reward = -1.81, steps = 104 01:01:38 [INFO] train episode 14307: reward = -1.06, steps = 36 01:01:39 [INFO] train episode 14308: reward = 37.76, steps = 55 01:01:39 [INFO] train episode 14309: reward = 10.45, steps = 64 01:01:39 [INFO] train episode 14310: reward = -8.95, steps = 29 01:01:39 [INFO] train episode 14311: reward = -0.24, steps = 34 01:01:40 [INFO] train episode 14312: reward = 15.03, steps = 49 01:01:40 [INFO] train episode 14313: reward = -12.32, steps = 25 01:01:40 [INFO] train episode 14314: reward = 16.11, steps = 39 01:01:40 [INFO] train episode 14315: reward = 11.53, steps = 35 01:01:41 [INFO] train episode 14316: reward = 4.96, steps = 35 01:01:41 [INFO] train episode 14317: reward = -10.38, steps = 24 01:01:41 [INFO] train episode 14318: reward = 11.85, steps = 43 01:01:41 [INFO] train episode 14319: reward = -3.56, steps = 40 01:01:42 [INFO] train episode 14320: reward = 15.82, steps = 55 01:01:42 [INFO] train episode 14321: reward = 34.07, steps = 58 01:01:42 [INFO] train episode 14322: reward = -8.94, steps = 24 01:01:43 [INFO] train episode 14323: reward = -17.85, steps = 84 01:01:43 [INFO] train episode 14324: reward = 19.44, steps = 41 01:01:43 [INFO] train episode 14325: reward = -13.74, steps = 23 01:01:43 [INFO] train episode 14326: reward = -15.31, steps = 22 01:01:44 [INFO] train episode 14327: reward = 0.30, steps = 32 01:01:44 [INFO] train episode 14328: reward = 21.91, steps = 56 01:01:44 [INFO] train episode 14329: reward = 12.89, steps = 41 01:01:45 [INFO] train episode 14330: reward = -0.34, steps = 36 01:01:45 [INFO] train episode 14331: reward = -9.28, steps = 24 01:01:45 [INFO] train episode 14332: reward = -13.36, steps = 23 01:01:45 [INFO] train episode 14333: reward = 11.61, steps = 40 01:01:45 [INFO] train episode 14334: reward = -2.47, steps = 30 01:01:46 [INFO] train episode 14335: reward = 10.41, steps = 39 01:01:46 [INFO] train episode 14336: reward = 9.36, steps = 77 01:01:46 [INFO] train episode 14337: reward = -24.56, steps = 22 01:01:47 [INFO] train episode 14338: reward = 6.42, steps = 39 01:01:47 [INFO] train episode 14339: reward = 6.86, steps = 37 01:01:47 [INFO] train episode 14340: reward = -0.94, steps = 27 01:01:47 [INFO] train episode 14341: reward = 20.71, steps = 43 01:01:47 [INFO] train episode 14342: reward = 0.17, steps = 39 01:01:48 [INFO] train episode 14343: reward = 36.09, steps = 52 01:01:48 [INFO] train episode 14344: reward = -11.98, steps = 36 01:01:48 [INFO] train episode 14345: reward = -8.49, steps = 35 01:01:49 [INFO] train episode 14346: reward = 9.46, steps = 37 01:01:49 [INFO] train episode 14347: reward = 13.49, steps = 41 01:01:49 [INFO] train episode 14348: reward = 12.93, steps = 39 01:01:49 [INFO] train episode 14349: reward = -1.67, steps = 37 01:01:50 [INFO] train episode 14350: reward = -10.73, steps = 27 01:01:50 [INFO] train episode 14351: reward = 16.10, steps = 45 01:01:50 [INFO] train episode 14352: reward = 23.62, steps = 56 01:01:50 [INFO] train episode 14353: reward = 10.33, steps = 48 01:01:51 [INFO] train episode 14354: reward = 20.60, steps = 49 01:01:51 [INFO] train episode 14355: reward = -0.79, steps = 40 01:01:51 [INFO] train episode 14356: reward = 0.99, steps = 40 01:01:52 [INFO] train episode 14357: reward = 25.93, steps = 54 01:01:52 [INFO] train episode 14358: reward = 1.20, steps = 33 01:01:52 [INFO] train episode 14359: reward = 16.85, steps = 40 01:01:53 [INFO] train episode 14360: reward = 9.29, steps = 33 01:01:53 [INFO] train episode 14361: reward = -15.08, steps = 24 01:01:53 [INFO] train episode 14362: reward = 7.98, steps = 37 01:01:53 [INFO] train episode 14363: reward = 19.87, steps = 62 01:01:54 [INFO] train episode 14364: reward = 21.67, steps = 44 01:01:54 [INFO] train episode 14365: reward = -1.18, steps = 37 01:01:54 [INFO] train episode 14366: reward = -4.89, steps = 25 01:01:54 [INFO] train episode 14367: reward = 17.95, steps = 45 01:01:55 [INFO] train episode 14368: reward = 16.87, steps = 38 01:01:55 [INFO] train episode 14369: reward = 1.36, steps = 39 01:01:55 [INFO] train episode 14370: reward = 13.86, steps = 63 01:01:56 [INFO] train episode 14371: reward = 13.28, steps = 87 01:01:56 [INFO] train episode 14372: reward = 10.43, steps = 40 01:01:56 [INFO] train episode 14373: reward = 8.13, steps = 36 01:01:57 [INFO] train episode 14374: reward = 10.59, steps = 45 01:01:57 [INFO] train episode 14375: reward = 15.07, steps = 51 01:01:57 [INFO] train episode 14376: reward = 16.68, steps = 54 01:01:58 [INFO] train episode 14377: reward = 9.57, steps = 36 01:01:58 [INFO] train episode 14378: reward = 15.82, steps = 46 01:01:58 [INFO] train episode 14379: reward = 2.04, steps = 43 01:01:58 [INFO] train episode 14380: reward = -12.75, steps = 32 01:01:59 [INFO] train episode 14381: reward = -4.61, steps = 68 01:01:59 [INFO] train episode 14382: reward = 9.79, steps = 42 01:02:00 [INFO] train episode 14383: reward = 25.64, steps = 52 01:02:00 [INFO] train episode 14384: reward = 3.76, steps = 28 01:02:00 [INFO] train episode 14385: reward = 16.39, steps = 45 01:02:00 [INFO] train episode 14386: reward = 16.77, steps = 43 01:02:01 [INFO] train episode 14387: reward = -2.47, steps = 31 01:02:01 [INFO] train episode 14388: reward = 20.19, steps = 41 01:02:01 [INFO] train episode 14389: reward = 8.99, steps = 38 01:02:01 [INFO] train episode 14390: reward = 6.18, steps = 40 01:02:02 [INFO] train episode 14391: reward = -27.05, steps = 54 01:02:02 [INFO] train episode 14392: reward = 14.46, steps = 61 01:02:02 [INFO] train episode 14393: reward = 18.66, steps = 45 01:02:03 [INFO] train episode 14394: reward = 2.60, steps = 46 01:02:03 [INFO] train episode 14395: reward = 4.34, steps = 42 01:02:03 [INFO] train episode 14396: reward = 7.44, steps = 45 01:02:04 [INFO] train episode 14397: reward = 15.04, steps = 43 01:02:04 [INFO] train episode 14398: reward = 12.06, steps = 37 01:02:04 [INFO] train episode 14399: reward = -1.72, steps = 47 01:02:04 [INFO] train episode 14400: reward = 12.47, steps = 45 01:02:05 [INFO] train episode 14401: reward = -1.45, steps = 25 01:02:05 [INFO] train episode 14402: reward = 11.56, steps = 45 01:02:06 [INFO] train episode 14403: reward = 26.09, steps = 76 01:02:06 [INFO] train episode 14404: reward = 26.47, steps = 49 01:02:06 [INFO] train episode 14405: reward = -0.96, steps = 40 01:02:06 [INFO] train episode 14406: reward = 18.80, steps = 47 01:02:07 [INFO] train episode 14407: reward = 16.51, steps = 42 01:02:07 [INFO] train episode 14408: reward = 29.29, steps = 62 01:02:07 [INFO] train episode 14409: reward = 6.26, steps = 35 01:02:08 [INFO] train episode 14410: reward = -10.83, steps = 21 01:02:08 [INFO] train episode 14411: reward = 10.33, steps = 35 01:02:08 [INFO] train episode 14412: reward = 9.58, steps = 47 01:02:09 [INFO] train episode 14413: reward = -29.02, steps = 91 01:02:09 [INFO] train episode 14414: reward = 16.24, steps = 43 01:02:09 [INFO] train episode 14415: reward = -0.02, steps = 30 01:02:09 [INFO] train episode 14416: reward = 21.54, steps = 46 01:02:10 [INFO] train episode 14417: reward = 13.28, steps = 47 01:02:10 [INFO] train episode 14418: reward = 6.13, steps = 35 01:02:10 [INFO] train episode 14419: reward = 23.23, steps = 50 01:02:11 [INFO] train episode 14420: reward = 29.98, steps = 77 01:02:11 [INFO] train episode 14421: reward = 27.39, steps = 64 01:02:12 [INFO] train episode 14422: reward = 16.93, steps = 47 01:02:12 [INFO] train episode 14423: reward = 25.95, steps = 65 01:02:12 [INFO] train episode 14424: reward = 27.39, steps = 57 01:02:13 [INFO] train episode 14425: reward = -2.04, steps = 42 01:02:13 [INFO] train episode 14426: reward = 25.07, steps = 42 01:02:13 [INFO] train episode 14427: reward = -22.11, steps = 71 01:02:14 [INFO] train episode 14428: reward = 5.37, steps = 36 01:02:14 [INFO] train episode 14429: reward = 20.18, steps = 51 01:02:14 [INFO] train episode 14430: reward = 28.67, steps = 51 01:02:15 [INFO] train episode 14431: reward = 14.53, steps = 45 01:02:15 [INFO] train episode 14432: reward = 27.33, steps = 57 01:02:15 [INFO] train episode 14433: reward = 18.95, steps = 45 01:02:16 [INFO] train episode 14434: reward = 14.12, steps = 43 01:02:16 [INFO] train episode 14435: reward = 7.91, steps = 40 01:02:16 [INFO] train episode 14436: reward = 27.11, steps = 49 01:02:16 [INFO] train episode 14437: reward = 20.66, steps = 45 01:02:17 [INFO] train episode 14438: reward = 42.67, steps = 62 01:02:17 [INFO] train episode 14439: reward = 6.88, steps = 40 01:02:17 [INFO] train episode 14440: reward = 17.48, steps = 44 01:02:18 [INFO] train episode 14441: reward = 9.29, steps = 40 01:02:18 [INFO] train episode 14442: reward = 10.82, steps = 44 01:02:18 [INFO] train episode 14443: reward = 1.90, steps = 39 01:02:19 [INFO] train episode 14444: reward = -18.73, steps = 73 01:02:19 [INFO] train episode 14445: reward = -1.15, steps = 48 01:02:19 [INFO] train episode 14446: reward = -7.01, steps = 29 01:02:20 [INFO] train episode 14447: reward = 9.17, steps = 42 01:02:20 [INFO] train episode 14448: reward = 19.80, steps = 59 01:02:20 [INFO] train episode 14449: reward = 3.63, steps = 35 01:02:20 [INFO] train episode 14450: reward = 18.43, steps = 39 01:02:21 [INFO] train episode 14451: reward = 17.98, steps = 68 01:02:21 [INFO] train episode 14452: reward = -5.77, steps = 39 01:02:21 [INFO] train episode 14453: reward = -2.38, steps = 36 01:02:22 [INFO] train episode 14454: reward = 24.78, steps = 64 01:02:22 [INFO] train episode 14455: reward = 13.85, steps = 44 01:02:22 [INFO] train episode 14456: reward = 16.14, steps = 42 01:02:23 [INFO] train episode 14457: reward = -22.09, steps = 76 01:02:23 [INFO] train episode 14458: reward = -1.20, steps = 27 01:02:23 [INFO] train episode 14459: reward = -11.80, steps = 28 01:02:23 [INFO] train episode 14460: reward = 1.12, steps = 28 01:02:24 [INFO] train episode 14461: reward = -7.06, steps = 27 01:02:24 [INFO] train episode 14462: reward = 5.67, steps = 33 01:02:24 [INFO] train episode 14463: reward = 45.15, steps = 68 01:02:24 [INFO] train episode 14464: reward = -15.62, steps = 22 01:02:25 [INFO] train episode 14465: reward = 20.22, steps = 58 01:02:25 [INFO] train episode 14466: reward = 13.45, steps = 52 01:02:25 [INFO] train episode 14467: reward = 9.83, steps = 47 01:02:26 [INFO] train episode 14468: reward = 16.79, steps = 38 01:02:26 [INFO] train episode 14469: reward = 16.66, steps = 56 01:02:26 [INFO] train episode 14470: reward = 11.31, steps = 47 01:02:27 [INFO] train episode 14471: reward = 28.26, steps = 55 01:02:27 [INFO] train episode 14472: reward = -6.99, steps = 30 01:02:27 [INFO] train episode 14473: reward = 13.54, steps = 56 01:02:27 [INFO] train episode 14474: reward = 2.89, steps = 29 01:02:28 [INFO] train episode 14475: reward = -7.91, steps = 47 01:02:28 [INFO] train episode 14476: reward = 21.69, steps = 48 01:02:28 [INFO] train episode 14477: reward = 5.67, steps = 50 01:02:29 [INFO] train episode 14478: reward = -5.70, steps = 49 01:02:29 [INFO] train episode 14479: reward = 16.77, steps = 47 01:02:29 [INFO] train episode 14480: reward = 1.26, steps = 37 01:02:29 [INFO] train episode 14481: reward = 9.37, steps = 44 01:02:30 [INFO] train episode 14482: reward = 18.14, steps = 39 01:02:30 [INFO] train episode 14483: reward = 0.25, steps = 35 01:02:30 [INFO] train episode 14484: reward = -1.55, steps = 34 01:02:30 [INFO] train episode 14485: reward = 8.60, steps = 43 01:02:31 [INFO] train episode 14486: reward = 20.81, steps = 47 01:02:31 [INFO] train episode 14487: reward = 20.23, steps = 56 01:02:31 [INFO] train episode 14488: reward = 12.54, steps = 51 01:02:32 [INFO] train episode 14489: reward = 11.57, steps = 47 01:02:32 [INFO] train episode 14490: reward = 7.38, steps = 29 01:02:33 [INFO] train episode 14491: reward = 10.94, steps = 45 01:02:33 [INFO] train episode 14492: reward = -1.28, steps = 46 01:02:33 [INFO] train episode 14493: reward = 16.35, steps = 39 01:02:33 [INFO] train episode 14494: reward = -14.63, steps = 23 01:02:34 [INFO] train episode 14495: reward = -7.11, steps = 45 01:02:34 [INFO] train episode 14496: reward = 3.76, steps = 43 01:02:34 [INFO] train episode 14497: reward = 10.97, steps = 49 01:02:34 [INFO] train episode 14498: reward = -1.25, steps = 39 01:02:35 [INFO] train episode 14499: reward = 17.72, steps = 42 01:02:35 [INFO] train episode 14500: reward = -3.33, steps = 26 01:02:35 [INFO] train episode 14501: reward = 25.39, steps = 52 01:02:35 [INFO] train episode 14502: reward = 10.43, steps = 40 01:02:36 [INFO] train episode 14503: reward = -15.77, steps = 44 01:02:36 [INFO] train episode 14504: reward = 7.62, steps = 49 01:02:36 [INFO] train episode 14505: reward = 23.33, steps = 43 01:02:37 [INFO] train episode 14506: reward = 6.77, steps = 41 01:02:37 [INFO] train episode 14507: reward = 7.36, steps = 38 01:02:37 [INFO] train episode 14508: reward = 0.34, steps = 42 01:02:37 [INFO] train episode 14509: reward = 15.95, steps = 47 01:02:38 [INFO] train episode 14510: reward = 22.54, steps = 38 01:02:38 [INFO] train episode 14511: reward = 4.57, steps = 43 01:02:38 [INFO] train episode 14512: reward = 22.18, steps = 45 01:02:39 [INFO] train episode 14513: reward = 5.79, steps = 39 01:02:39 [INFO] train episode 14514: reward = 21.32, steps = 46 01:02:39 [INFO] train episode 14515: reward = 19.64, steps = 43 01:02:39 [INFO] train episode 14516: reward = 18.84, steps = 34 01:02:40 [INFO] train episode 14517: reward = -7.49, steps = 26 01:02:40 [INFO] train episode 14518: reward = 3.44, steps = 43 01:02:40 [INFO] train episode 14519: reward = 23.00, steps = 49 01:02:41 [INFO] train episode 14520: reward = 11.64, steps = 44 01:02:41 [INFO] train episode 14521: reward = -3.84, steps = 39 01:02:41 [INFO] train episode 14522: reward = 10.14, steps = 48 01:02:41 [INFO] train episode 14523: reward = 18.00, steps = 37 01:02:42 [INFO] train episode 14524: reward = 16.86, steps = 34 01:02:42 [INFO] train episode 14525: reward = 12.17, steps = 47 01:02:42 [INFO] train episode 14526: reward = 7.24, steps = 42 01:02:42 [INFO] train episode 14527: reward = 16.51, steps = 45 01:02:43 [INFO] train episode 14528: reward = 12.39, steps = 44 01:02:43 [INFO] train episode 14529: reward = 10.32, steps = 29 01:02:43 [INFO] train episode 14530: reward = 10.03, steps = 53 01:02:44 [INFO] train episode 14531: reward = 16.66, steps = 46 01:02:44 [INFO] train episode 14532: reward = -19.30, steps = 17 01:02:44 [INFO] train episode 14533: reward = 21.43, steps = 42 01:02:44 [INFO] train episode 14534: reward = 8.38, steps = 36 01:02:45 [INFO] train episode 14535: reward = 14.75, steps = 41 01:02:45 [INFO] train episode 14536: reward = 18.92, steps = 49 01:02:45 [INFO] train episode 14537: reward = 24.69, steps = 51 01:02:46 [INFO] train episode 14538: reward = 11.71, steps = 44 01:02:46 [INFO] train episode 14539: reward = -5.06, steps = 37 01:02:46 [INFO] train episode 14540: reward = 17.69, steps = 46 01:02:47 [INFO] train episode 14541: reward = -5.88, steps = 46 01:02:47 [INFO] train episode 14542: reward = 2.93, steps = 31 01:02:47 [INFO] train episode 14543: reward = -0.65, steps = 29 01:02:47 [INFO] train episode 14544: reward = 10.78, steps = 40 01:02:47 [INFO] train episode 14545: reward = 0.61, steps = 35 01:02:48 [INFO] train episode 14546: reward = 7.48, steps = 57 01:02:48 [INFO] train episode 14547: reward = 2.58, steps = 29 01:02:49 [INFO] train episode 14548: reward = 17.86, steps = 92 01:02:49 [INFO] train episode 14549: reward = -17.51, steps = 23 01:02:49 [INFO] train episode 14550: reward = 8.70, steps = 37 01:02:49 [INFO] train episode 14551: reward = 13.31, steps = 33 01:02:49 [INFO] train episode 14552: reward = 23.80, steps = 56 01:02:50 [INFO] train episode 14553: reward = 6.79, steps = 37 01:02:50 [INFO] train episode 14554: reward = 10.67, steps = 43 01:02:50 [INFO] train episode 14555: reward = -4.63, steps = 27 01:02:51 [INFO] train episode 14556: reward = 22.19, steps = 50 01:02:51 [INFO] train episode 14557: reward = 20.82, steps = 49 01:02:51 [INFO] train episode 14558: reward = 14.39, steps = 43 01:02:51 [INFO] train episode 14559: reward = -2.71, steps = 28 01:02:52 [INFO] train episode 14560: reward = 7.27, steps = 33 01:02:52 [INFO] train episode 14561: reward = 22.83, steps = 39 01:02:52 [INFO] train episode 14562: reward = -0.81, steps = 37 01:02:52 [INFO] train episode 14563: reward = -11.44, steps = 25 01:02:53 [INFO] train episode 14564: reward = 8.25, steps = 65 01:02:53 [INFO] train episode 14565: reward = 28.00, steps = 54 01:02:53 [INFO] train episode 14566: reward = 1.64, steps = 38 01:02:53 [INFO] train episode 14567: reward = 4.26, steps = 33 01:02:54 [INFO] train episode 14568: reward = 12.72, steps = 39 01:02:54 [INFO] train episode 14569: reward = 16.54, steps = 39 01:02:54 [INFO] train episode 14570: reward = 22.70, steps = 47 01:02:55 [INFO] train episode 14571: reward = 31.22, steps = 64 01:02:55 [INFO] train episode 14572: reward = -12.20, steps = 24 01:02:55 [INFO] train episode 14573: reward = 8.69, steps = 45 01:02:56 [INFO] train episode 14574: reward = 19.01, steps = 59 01:02:56 [INFO] train episode 14575: reward = 14.54, steps = 44 01:02:56 [INFO] train episode 14576: reward = -40.11, steps = 68 01:02:57 [INFO] train episode 14577: reward = 25.12, steps = 55 01:02:57 [INFO] train episode 14578: reward = 2.76, steps = 32 01:02:57 [INFO] train episode 14579: reward = 15.49, steps = 44 01:02:57 [INFO] train episode 14580: reward = 2.63, steps = 32 01:02:58 [INFO] train episode 14581: reward = 42.30, steps = 77 01:02:58 [INFO] train episode 14582: reward = 14.91, steps = 43 01:02:59 [INFO] train episode 14583: reward = -9.83, steps = 32 01:02:59 [INFO] train episode 14584: reward = 20.46, steps = 40 01:02:59 [INFO] train episode 14585: reward = 14.59, steps = 48 01:02:59 [INFO] train episode 14586: reward = -9.36, steps = 32 01:03:00 [INFO] train episode 14587: reward = 11.32, steps = 41 01:03:00 [INFO] train episode 14588: reward = 33.11, steps = 56 01:03:00 [INFO] train episode 14589: reward = 20.35, steps = 39 01:03:01 [INFO] train episode 14590: reward = 23.68, steps = 45 01:03:01 [INFO] train episode 14591: reward = -4.75, steps = 26 01:03:01 [INFO] train episode 14592: reward = -8.50, steps = 24 01:03:01 [INFO] train episode 14593: reward = -6.67, steps = 24 01:03:01 [INFO] train episode 14594: reward = -14.25, steps = 30 01:03:02 [INFO] train episode 14595: reward = 15.84, steps = 33 01:03:02 [INFO] train episode 14596: reward = 5.16, steps = 46 01:03:02 [INFO] train episode 14597: reward = -8.46, steps = 22 01:03:02 [INFO] train episode 14598: reward = 28.78, steps = 49 01:03:03 [INFO] train episode 14599: reward = 12.54, steps = 61 01:03:03 [INFO] train episode 14600: reward = 4.67, steps = 44 01:03:03 [INFO] train episode 14601: reward = -7.17, steps = 31 01:03:04 [INFO] train episode 14602: reward = 27.47, steps = 49 01:03:04 [INFO] train episode 14603: reward = 23.58, steps = 91 01:03:04 [INFO] train episode 14604: reward = -13.67, steps = 24 01:03:05 [INFO] train episode 14605: reward = 27.18, steps = 62 01:03:05 [INFO] train episode 14606: reward = 2.19, steps = 29 01:03:05 [INFO] train episode 14607: reward = 0.94, steps = 44 01:03:06 [INFO] train episode 14608: reward = 40.62, steps = 60 01:03:06 [INFO] train episode 14609: reward = 19.92, steps = 54 01:03:06 [INFO] train episode 14610: reward = 7.27, steps = 39 01:03:07 [INFO] train episode 14611: reward = -1.25, steps = 51 01:03:07 [INFO] train episode 14612: reward = 6.21, steps = 34 01:03:07 [INFO] train episode 14613: reward = 0.64, steps = 26 01:03:07 [INFO] train episode 14614: reward = 9.78, steps = 37 01:03:08 [INFO] train episode 14615: reward = -7.33, steps = 46 01:03:08 [INFO] train episode 14616: reward = 12.68, steps = 36 01:03:08 [INFO] train episode 14617: reward = -12.27, steps = 25 01:03:08 [INFO] train episode 14618: reward = 20.72, steps = 40 01:03:09 [INFO] train episode 14619: reward = 11.24, steps = 109 01:03:09 [INFO] train episode 14620: reward = 11.48, steps = 36 01:03:10 [INFO] train episode 14621: reward = -8.39, steps = 25 01:03:10 [INFO] train episode 14622: reward = 20.21, steps = 48 01:03:10 [INFO] train episode 14623: reward = 14.75, steps = 39 01:03:10 [INFO] train episode 14624: reward = -12.29, steps = 27 01:03:11 [INFO] train episode 14625: reward = 6.56, steps = 44 01:03:11 [INFO] train episode 14626: reward = 4.25, steps = 33 01:03:11 [INFO] train episode 14627: reward = 17.41, steps = 42 01:03:12 [INFO] train episode 14628: reward = 29.36, steps = 56 01:03:12 [INFO] train episode 14629: reward = 27.61, steps = 40 01:03:12 [INFO] train episode 14630: reward = -9.68, steps = 31 01:03:13 [INFO] train episode 14631: reward = 21.19, steps = 41 01:03:13 [INFO] train episode 14632: reward = 3.56, steps = 29 01:03:13 [INFO] train episode 14633: reward = 6.48, steps = 50 01:03:13 [INFO] train episode 14634: reward = 8.13, steps = 39 01:03:14 [INFO] train episode 14635: reward = -5.12, steps = 25 01:03:14 [INFO] train episode 14636: reward = 17.61, steps = 45 01:03:14 [INFO] train episode 14637: reward = -0.42, steps = 26 01:03:14 [INFO] train episode 14638: reward = 4.55, steps = 50 01:03:15 [INFO] train episode 14639: reward = 12.40, steps = 44 01:03:15 [INFO] train episode 14640: reward = 4.86, steps = 46 01:03:15 [INFO] train episode 14641: reward = 13.53, steps = 49 01:03:15 [INFO] train episode 14642: reward = 0.78, steps = 27 01:03:16 [INFO] train episode 14643: reward = 26.30, steps = 41 01:03:16 [INFO] train episode 14644: reward = 23.29, steps = 44 01:03:16 [INFO] train episode 14645: reward = 22.10, steps = 45 01:03:17 [INFO] train episode 14646: reward = 37.24, steps = 68 01:03:17 [INFO] train episode 14647: reward = 4.02, steps = 33 01:03:17 [INFO] train episode 14648: reward = -21.35, steps = 26 01:03:17 [INFO] train episode 14649: reward = 3.95, steps = 39 01:03:18 [INFO] train episode 14650: reward = 16.06, steps = 37 01:03:18 [INFO] train episode 14651: reward = 15.94, steps = 35 01:03:18 [INFO] train episode 14652: reward = 20.09, steps = 46 01:03:18 [INFO] train episode 14653: reward = 11.73, steps = 39 01:03:19 [INFO] train episode 14654: reward = -0.92, steps = 35 01:03:19 [INFO] train episode 14655: reward = 0.84, steps = 35 01:03:19 [INFO] train episode 14656: reward = -12.44, steps = 21 01:03:19 [INFO] train episode 14657: reward = 2.77, steps = 31 01:03:20 [INFO] train episode 14658: reward = 12.06, steps = 34 01:03:20 [INFO] train episode 14659: reward = 11.72, steps = 43 01:03:20 [INFO] train episode 14660: reward = 0.15, steps = 29 01:03:20 [INFO] train episode 14661: reward = 6.44, steps = 61 01:03:21 [INFO] train episode 14662: reward = 13.50, steps = 35 01:03:21 [INFO] train episode 14663: reward = 12.76, steps = 36 01:03:21 [INFO] train episode 14664: reward = 22.14, steps = 50 01:03:22 [INFO] train episode 14665: reward = 45.51, steps = 78 01:03:22 [INFO] train episode 14666: reward = -1.96, steps = 54 01:03:22 [INFO] train episode 14667: reward = 25.69, steps = 50 01:03:23 [INFO] train episode 14668: reward = 36.30, steps = 77 01:03:23 [INFO] train episode 14669: reward = -7.92, steps = 23 01:03:23 [INFO] train episode 14670: reward = 12.62, steps = 50 01:03:24 [INFO] train episode 14671: reward = 18.82, steps = 51 01:03:24 [INFO] train episode 14672: reward = -18.49, steps = 70 01:03:24 [INFO] train episode 14673: reward = 7.42, steps = 33 01:03:25 [INFO] train episode 14674: reward = 2.91, steps = 36 01:03:25 [INFO] train episode 14675: reward = 2.26, steps = 32 01:03:25 [INFO] train episode 14676: reward = -5.86, steps = 31 01:03:25 [INFO] train episode 14677: reward = -10.64, steps = 20 01:03:26 [INFO] train episode 14678: reward = 6.51, steps = 36 01:03:26 [INFO] train episode 14679: reward = 14.09, steps = 42 01:03:26 [INFO] train episode 14680: reward = 7.89, steps = 36 01:03:27 [INFO] train episode 14681: reward = 14.15, steps = 44 01:03:27 [INFO] train episode 14682: reward = 2.39, steps = 31 01:03:27 [INFO] train episode 14683: reward = 1.61, steps = 46 01:03:27 [INFO] train episode 14684: reward = 24.64, steps = 49 01:03:28 [INFO] train episode 14685: reward = 17.94, steps = 47 01:03:28 [INFO] train episode 14686: reward = -3.59, steps = 44 01:03:28 [INFO] train episode 14687: reward = -27.19, steps = 64 01:03:29 [INFO] train episode 14688: reward = 7.72, steps = 47 01:03:29 [INFO] train episode 14689: reward = 14.90, steps = 38 01:03:29 [INFO] train episode 14690: reward = 14.25, steps = 35 01:03:30 [INFO] train episode 14691: reward = 22.38, steps = 52 01:03:30 [INFO] train episode 14692: reward = 14.26, steps = 44 01:03:30 [INFO] train episode 14693: reward = 7.94, steps = 31 01:03:30 [INFO] train episode 14694: reward = -5.41, steps = 43 01:03:31 [INFO] train episode 14695: reward = -6.86, steps = 31 01:03:31 [INFO] train episode 14696: reward = 7.06, steps = 43 01:03:31 [INFO] train episode 14697: reward = 14.38, steps = 43 01:03:31 [INFO] train episode 14698: reward = 12.63, steps = 42 01:03:32 [INFO] train episode 14699: reward = 17.72, steps = 59 01:03:32 [INFO] train episode 14700: reward = 10.24, steps = 40 01:03:32 [INFO] train episode 14701: reward = 26.74, steps = 49 01:03:33 [INFO] train episode 14702: reward = 17.94, steps = 42 01:03:33 [INFO] train episode 14703: reward = 23.66, steps = 39 01:03:33 [INFO] train episode 14704: reward = 16.89, steps = 50 01:03:33 [INFO] train episode 14705: reward = 4.06, steps = 30 01:03:34 [INFO] train episode 14706: reward = 6.70, steps = 36 01:03:34 [INFO] train episode 14707: reward = 9.22, steps = 40 01:03:34 [INFO] train episode 14708: reward = -3.48, steps = 40 01:03:34 [INFO] train episode 14709: reward = 13.24, steps = 39 01:03:35 [INFO] train episode 14710: reward = 19.41, steps = 45 01:03:35 [INFO] train episode 14711: reward = 9.22, steps = 46 01:03:35 [INFO] train episode 14712: reward = 33.74, steps = 65 01:03:36 [INFO] train episode 14713: reward = 7.84, steps = 40 01:03:36 [INFO] train episode 14714: reward = 1.79, steps = 71 01:03:37 [INFO] train episode 14715: reward = 21.14, steps = 51 01:03:37 [INFO] train episode 14716: reward = -8.78, steps = 25 01:03:37 [INFO] train episode 14717: reward = 24.20, steps = 42 01:03:37 [INFO] train episode 14718: reward = -0.59, steps = 38 01:03:38 [INFO] train episode 14719: reward = 15.00, steps = 42 01:03:38 [INFO] train episode 14720: reward = -27.42, steps = 18 01:03:38 [INFO] train episode 14721: reward = 12.76, steps = 37 01:03:38 [INFO] train episode 14722: reward = 5.15, steps = 48 01:03:39 [INFO] train episode 14723: reward = -9.76, steps = 67 01:03:39 [INFO] train episode 14724: reward = -13.00, steps = 23 01:03:39 [INFO] train episode 14725: reward = 6.07, steps = 46 01:03:40 [INFO] train episode 14726: reward = -6.03, steps = 37 01:03:40 [INFO] train episode 14727: reward = 18.41, steps = 40 01:03:40 [INFO] train episode 14728: reward = 5.56, steps = 30 01:03:40 [INFO] train episode 14729: reward = 9.00, steps = 30 01:03:41 [INFO] train episode 14730: reward = -2.05, steps = 28 01:03:41 [INFO] train episode 14731: reward = 9.86, steps = 39 01:03:41 [INFO] train episode 14732: reward = 27.27, steps = 71 01:03:42 [INFO] train episode 14733: reward = -31.74, steps = 42 01:03:42 [INFO] train episode 14734: reward = 1.87, steps = 33 01:03:42 [INFO] train episode 14735: reward = 7.33, steps = 34 01:03:42 [INFO] train episode 14736: reward = -2.70, steps = 22 01:03:42 [INFO] train episode 14737: reward = -15.20, steps = 19 01:03:43 [INFO] train episode 14738: reward = 32.04, steps = 47 01:03:43 [INFO] train episode 14739: reward = 3.11, steps = 39 01:03:43 [INFO] train episode 14740: reward = 7.77, steps = 45 01:03:43 [INFO] train episode 14741: reward = -29.89, steps = 46 01:03:44 [INFO] train episode 14742: reward = -4.70, steps = 24 01:03:44 [INFO] train episode 14743: reward = 6.55, steps = 39 01:03:44 [INFO] train episode 14744: reward = 17.60, steps = 38 01:03:44 [INFO] train episode 14745: reward = 24.97, steps = 50 01:03:45 [INFO] train episode 14746: reward = 17.38, steps = 40 01:03:45 [INFO] train episode 14747: reward = 22.30, steps = 47 01:03:45 [INFO] train episode 14748: reward = 16.69, steps = 41 01:03:46 [INFO] train episode 14749: reward = 2.08, steps = 31 01:03:46 [INFO] train episode 14750: reward = -9.43, steps = 21 01:03:46 [INFO] train episode 14751: reward = 25.25, steps = 47 01:03:46 [INFO] train episode 14752: reward = 21.27, steps = 42 01:03:47 [INFO] train episode 14753: reward = 18.74, steps = 52 01:03:47 [INFO] train episode 14754: reward = 17.00, steps = 49 01:03:47 [INFO] train episode 14755: reward = 21.27, steps = 67 01:03:48 [INFO] train episode 14756: reward = 11.26, steps = 37 01:03:48 [INFO] train episode 14757: reward = 6.45, steps = 31 01:03:48 [INFO] train episode 14758: reward = 17.11, steps = 62 01:03:49 [INFO] train episode 14759: reward = 14.21, steps = 84 01:03:49 [INFO] train episode 14760: reward = 18.49, steps = 63 01:03:49 [INFO] train episode 14761: reward = 4.58, steps = 32 01:03:50 [INFO] train episode 14762: reward = 19.47, steps = 39 01:03:50 [INFO] train episode 14763: reward = -0.26, steps = 42 01:03:50 [INFO] train episode 14764: reward = 9.80, steps = 51 01:03:50 [INFO] train episode 14765: reward = -7.72, steps = 26 01:03:51 [INFO] train episode 14766: reward = -7.27, steps = 41 01:03:51 [INFO] train episode 14767: reward = 9.26, steps = 40 01:03:51 [INFO] train episode 14768: reward = 19.20, steps = 46 01:03:52 [INFO] train episode 14769: reward = 14.72, steps = 43 01:03:52 [INFO] train episode 14770: reward = -6.98, steps = 28 01:03:52 [INFO] train episode 14771: reward = 23.04, steps = 41 01:03:53 [INFO] train episode 14772: reward = 17.37, steps = 51 01:03:53 [INFO] train episode 14773: reward = 14.98, steps = 40 01:03:53 [INFO] train episode 14774: reward = 13.78, steps = 44 01:03:53 [INFO] train episode 14775: reward = 1.79, steps = 42 01:03:54 [INFO] train episode 14776: reward = 0.79, steps = 37 01:03:54 [INFO] train episode 14777: reward = 5.11, steps = 32 01:03:54 [INFO] train episode 14778: reward = -10.11, steps = 25 01:03:54 [INFO] train episode 14779: reward = 12.57, steps = 48 01:03:55 [INFO] train episode 14780: reward = -12.88, steps = 21 01:03:55 [INFO] train episode 14781: reward = 21.88, steps = 45 01:03:55 [INFO] train episode 14782: reward = 5.58, steps = 47 01:03:55 [INFO] train episode 14783: reward = 10.99, steps = 50 01:03:56 [INFO] train episode 14784: reward = -6.49, steps = 25 01:03:56 [INFO] train episode 14785: reward = 13.34, steps = 43 01:03:56 [INFO] train episode 14786: reward = 24.61, steps = 42 01:03:56 [INFO] train episode 14787: reward = -10.28, steps = 23 01:03:57 [INFO] train episode 14788: reward = 17.18, steps = 43 01:03:57 [INFO] train episode 14789: reward = -12.30, steps = 31 01:03:57 [INFO] train episode 14790: reward = 6.65, steps = 43 01:03:57 [INFO] train episode 14791: reward = 4.02, steps = 29 01:03:58 [INFO] train episode 14792: reward = 14.53, steps = 40 01:03:58 [INFO] train episode 14793: reward = 14.07, steps = 32 01:03:58 [INFO] train episode 14794: reward = 25.30, steps = 46 01:03:58 [INFO] train episode 14795: reward = 15.05, steps = 39 01:03:59 [INFO] train episode 14796: reward = 2.27, steps = 28 01:03:59 [INFO] train episode 14797: reward = -10.30, steps = 48 01:03:59 [INFO] train episode 14798: reward = 6.13, steps = 37 01:03:59 [INFO] train episode 14799: reward = 12.99, steps = 37 01:04:00 [INFO] train episode 14800: reward = 13.46, steps = 39 01:04:00 [INFO] train episode 14801: reward = 8.75, steps = 48 01:04:00 [INFO] train episode 14802: reward = 4.72, steps = 35 01:04:00 [INFO] train episode 14803: reward = 7.82, steps = 35 01:04:01 [INFO] train episode 14804: reward = 9.26, steps = 37 01:04:01 [INFO] train episode 14805: reward = 15.63, steps = 66 01:04:01 [INFO] train episode 14806: reward = 9.38, steps = 45 01:04:02 [INFO] train episode 14807: reward = 23.57, steps = 44 01:04:02 [INFO] train episode 14808: reward = 11.56, steps = 41 01:04:02 [INFO] train episode 14809: reward = 2.56, steps = 31 01:04:03 [INFO] train episode 14810: reward = 29.61, steps = 42 01:04:03 [INFO] train episode 14811: reward = -3.96, steps = 28 01:04:03 [INFO] train episode 14812: reward = 12.37, steps = 40 01:04:03 [INFO] train episode 14813: reward = 23.97, steps = 52 01:04:04 [INFO] train episode 14814: reward = 10.59, steps = 44 01:04:04 [INFO] train episode 14815: reward = -3.44, steps = 21 01:04:04 [INFO] train episode 14816: reward = 14.77, steps = 42 01:04:04 [INFO] train episode 14817: reward = 20.65, steps = 46 01:04:05 [INFO] train episode 14818: reward = -4.60, steps = 34 01:04:05 [INFO] train episode 14819: reward = 14.71, steps = 59 01:04:05 [INFO] train episode 14820: reward = 24.18, steps = 40 01:04:06 [INFO] train episode 14821: reward = 30.35, steps = 56 01:04:06 [INFO] train episode 14822: reward = -11.06, steps = 28 01:04:07 [INFO] train episode 14823: reward = -6.09, steps = 64 01:04:07 [INFO] train episode 14824: reward = -9.31, steps = 26 01:04:07 [INFO] train episode 14825: reward = -6.10, steps = 27 01:04:07 [INFO] train episode 14826: reward = -0.80, steps = 30 01:04:07 [INFO] train episode 14827: reward = 13.78, steps = 42 01:04:08 [INFO] train episode 14828: reward = 20.47, steps = 42 01:04:08 [INFO] train episode 14829: reward = 23.02, steps = 47 01:04:08 [INFO] train episode 14830: reward = 0.02, steps = 28 01:04:09 [INFO] train episode 14831: reward = 33.36, steps = 56 01:04:09 [INFO] train episode 14832: reward = -17.98, steps = 26 01:04:09 [INFO] train episode 14833: reward = 22.44, steps = 45 01:04:09 [INFO] train episode 14834: reward = -17.54, steps = 62 01:04:10 [INFO] train episode 14835: reward = -1.31, steps = 27 01:04:10 [INFO] train episode 14836: reward = 8.82, steps = 35 01:04:10 [INFO] train episode 14837: reward = 13.61, steps = 50 01:04:11 [INFO] train episode 14838: reward = 29.62, steps = 56 01:04:11 [INFO] train episode 14839: reward = 18.03, steps = 39 01:04:11 [INFO] train episode 14840: reward = 13.93, steps = 44 01:04:11 [INFO] train episode 14841: reward = 22.06, steps = 48 01:04:12 [INFO] train episode 14842: reward = 24.03, steps = 43 01:04:12 [INFO] train episode 14843: reward = 7.16, steps = 38 01:04:12 [INFO] train episode 14844: reward = 17.35, steps = 43 01:04:12 [INFO] train episode 14845: reward = -5.91, steps = 24 01:04:13 [INFO] train episode 14846: reward = 12.86, steps = 39 01:04:13 [INFO] train episode 14847: reward = 8.05, steps = 32 01:04:13 [INFO] train episode 14848: reward = 13.84, steps = 41 01:04:13 [INFO] train episode 14849: reward = 19.53, steps = 38 01:04:14 [INFO] train episode 14850: reward = -7.01, steps = 24 01:04:14 [INFO] train episode 14851: reward = 20.64, steps = 41 01:04:14 [INFO] train episode 14852: reward = 18.71, steps = 52 01:04:14 [INFO] train episode 14853: reward = 13.27, steps = 40 01:04:15 [INFO] train episode 14854: reward = 22.06, steps = 64 01:04:15 [INFO] train episode 14855: reward = 0.05, steps = 27 01:04:15 [INFO] train episode 14856: reward = -3.68, steps = 33 01:04:16 [INFO] train episode 14857: reward = -19.73, steps = 78 01:04:16 [INFO] train episode 14858: reward = 8.40, steps = 46 01:04:16 [INFO] train episode 14859: reward = -1.83, steps = 25 01:04:17 [INFO] train episode 14860: reward = 17.11, steps = 48 01:04:17 [INFO] train episode 14861: reward = 20.96, steps = 57 01:04:17 [INFO] train episode 14862: reward = 17.68, steps = 47 01:04:18 [INFO] train episode 14863: reward = 27.25, steps = 62 01:04:18 [INFO] train episode 14864: reward = 11.18, steps = 38 01:04:18 [INFO] train episode 14865: reward = 12.48, steps = 41 01:04:18 [INFO] train episode 14866: reward = 8.59, steps = 40 01:04:19 [INFO] train episode 14867: reward = 35.33, steps = 64 01:04:19 [INFO] train episode 14868: reward = -5.88, steps = 28 01:04:20 [INFO] train episode 14869: reward = 4.48, steps = 36 01:04:20 [INFO] train episode 14870: reward = 0.77, steps = 29 01:04:20 [INFO] train episode 14871: reward = 18.44, steps = 48 01:04:20 [INFO] train episode 14872: reward = 11.92, steps = 39 01:04:21 [INFO] train episode 14873: reward = 10.47, steps = 40 01:04:21 [INFO] train episode 14874: reward = 20.48, steps = 42 01:04:21 [INFO] train episode 14875: reward = 39.36, steps = 68 01:04:22 [INFO] train episode 14876: reward = -0.86, steps = 29 01:04:22 [INFO] train episode 14877: reward = 39.73, steps = 68 01:04:22 [INFO] train episode 14878: reward = -11.51, steps = 21 01:04:22 [INFO] train episode 14879: reward = 23.07, steps = 42 01:04:23 [INFO] train episode 14880: reward = 12.44, steps = 36 01:04:23 [INFO] train episode 14881: reward = -20.56, steps = 61 01:04:23 [INFO] train episode 14882: reward = -9.03, steps = 23 01:04:24 [INFO] train episode 14883: reward = 13.32, steps = 49 01:04:24 [INFO] train episode 14884: reward = 26.67, steps = 58 01:04:24 [INFO] train episode 14885: reward = -0.95, steps = 24 01:04:24 [INFO] train episode 14886: reward = -4.23, steps = 35 01:04:25 [INFO] train episode 14887: reward = 54.57, steps = 117 01:04:25 [INFO] train episode 14888: reward = -11.57, steps = 36 01:04:26 [INFO] train episode 14889: reward = 14.90, steps = 47 01:04:26 [INFO] train episode 14890: reward = 26.56, steps = 51 01:04:26 [INFO] train episode 14891: reward = 11.03, steps = 44 01:04:27 [INFO] train episode 14892: reward = 18.69, steps = 49 01:04:27 [INFO] train episode 14893: reward = 19.61, steps = 43 01:04:27 [INFO] train episode 14894: reward = -2.67, steps = 29 01:04:28 [INFO] train episode 14895: reward = 25.98, steps = 58 01:04:28 [INFO] train episode 14896: reward = 31.67, steps = 63 01:04:28 [INFO] train episode 14897: reward = 33.91, steps = 45 01:04:29 [INFO] train episode 14898: reward = 16.65, steps = 37 01:04:29 [INFO] train episode 14899: reward = 26.66, steps = 54 01:04:29 [INFO] train episode 14900: reward = 12.94, steps = 40 01:04:29 [INFO] train episode 14901: reward = -7.94, steps = 35 01:04:30 [INFO] train episode 14902: reward = 27.63, steps = 37 01:04:30 [INFO] train episode 14903: reward = 19.91, steps = 50 01:04:30 [INFO] train episode 14904: reward = 32.28, steps = 52 01:04:31 [INFO] train episode 14905: reward = -16.55, steps = 28 01:04:31 [INFO] train episode 14906: reward = -10.28, steps = 61 01:04:31 [INFO] train episode 14907: reward = -15.45, steps = 61 01:04:32 [INFO] train episode 14908: reward = 11.23, steps = 42 01:04:32 [INFO] train episode 14909: reward = 15.70, steps = 43 01:04:32 [INFO] train episode 14910: reward = -1.22, steps = 28 01:04:32 [INFO] train episode 14911: reward = 0.77, steps = 28 01:04:33 [INFO] train episode 14912: reward = -14.17, steps = 131 01:04:34 [INFO] train episode 14913: reward = 21.65, steps = 41 01:04:34 [INFO] train episode 14914: reward = 24.18, steps = 46 01:04:34 [INFO] train episode 14915: reward = 19.00, steps = 45 01:04:35 [INFO] train episode 14916: reward = 25.24, steps = 45 01:04:35 [INFO] train episode 14917: reward = -3.06, steps = 42 01:04:35 [INFO] train episode 14918: reward = 31.93, steps = 57 01:04:35 [INFO] train episode 14919: reward = 13.20, steps = 35 01:04:36 [INFO] train episode 14920: reward = 18.64, steps = 41 01:04:36 [INFO] train episode 14921: reward = 29.58, steps = 60 01:04:36 [INFO] train episode 14922: reward = 13.64, steps = 46 01:04:37 [INFO] train episode 14923: reward = 20.13, steps = 45 01:04:37 [INFO] train episode 14924: reward = -13.78, steps = 63 01:04:38 [INFO] train episode 14925: reward = 8.18, steps = 43 01:04:38 [INFO] train episode 14926: reward = 19.12, steps = 49 01:04:38 [INFO] train episode 14927: reward = 23.02, steps = 51 01:04:39 [INFO] train episode 14928: reward = 26.41, steps = 49 01:04:39 [INFO] train episode 14929: reward = -25.58, steps = 84 01:04:40 [INFO] train episode 14930: reward = 4.84, steps = 54 01:04:40 [INFO] train episode 14931: reward = 22.97, steps = 62 01:04:40 [INFO] train episode 14932: reward = -9.15, steps = 25 01:04:41 [INFO] train episode 14933: reward = -33.33, steps = 90 01:04:41 [INFO] train episode 14934: reward = 37.26, steps = 93 01:04:42 [INFO] train episode 14935: reward = 2.81, steps = 30 01:04:42 [INFO] train episode 14936: reward = 7.26, steps = 46 01:04:42 [INFO] train episode 14937: reward = 13.70, steps = 39 01:04:42 [INFO] train episode 14938: reward = 13.80, steps = 41 01:04:43 [INFO] train episode 14939: reward = 23.84, steps = 45 01:04:43 [INFO] train episode 14940: reward = -2.09, steps = 23 01:04:43 [INFO] train episode 14941: reward = 28.51, steps = 53 01:04:44 [INFO] train episode 14942: reward = 13.24, steps = 45 01:04:44 [INFO] train episode 14943: reward = 17.77, steps = 38 01:04:44 [INFO] train episode 14944: reward = -4.71, steps = 25 01:04:44 [INFO] train episode 14945: reward = 2.31, steps = 30 01:04:44 [INFO] train episode 14946: reward = 17.33, steps = 39 01:04:45 [INFO] train episode 14947: reward = 12.12, steps = 46 01:04:45 [INFO] train episode 14948: reward = 20.16, steps = 49 01:04:45 [INFO] train episode 14949: reward = 4.74, steps = 31 01:04:46 [INFO] train episode 14950: reward = 9.48, steps = 39 01:04:46 [INFO] train episode 14951: reward = 22.91, steps = 44 01:04:46 [INFO] train episode 14952: reward = 1.88, steps = 29 01:04:46 [INFO] train episode 14953: reward = 17.98, steps = 44 01:04:47 [INFO] train episode 14954: reward = 24.50, steps = 39 01:04:47 [INFO] train episode 14955: reward = 11.73, steps = 33 01:04:47 [INFO] train episode 14956: reward = 6.19, steps = 45 01:04:48 [INFO] train episode 14957: reward = 12.97, steps = 41 01:04:48 [INFO] train episode 14958: reward = 28.13, steps = 57 01:04:48 [INFO] train episode 14959: reward = 10.91, steps = 40 01:04:49 [INFO] train episode 14960: reward = 22.85, steps = 44 01:04:49 [INFO] train episode 14961: reward = 15.15, steps = 44 01:04:49 [INFO] train episode 14962: reward = 16.38, steps = 42 01:04:49 [INFO] train episode 14963: reward = 17.58, steps = 41 01:04:50 [INFO] train episode 14964: reward = -3.89, steps = 26 01:04:50 [INFO] train episode 14965: reward = 9.29, steps = 40 01:04:50 [INFO] train episode 14966: reward = 10.37, steps = 35 01:04:50 [INFO] train episode 14967: reward = 19.55, steps = 45 01:04:51 [INFO] train episode 14968: reward = -5.42, steps = 37 01:04:51 [INFO] train episode 14969: reward = 19.58, steps = 42 01:04:51 [INFO] train episode 14970: reward = 28.02, steps = 55 01:04:51 [INFO] train episode 14971: reward = -10.69, steps = 22 01:04:52 [INFO] train episode 14972: reward = 26.03, steps = 43 01:04:52 [INFO] train episode 14973: reward = -6.89, steps = 23 01:04:52 [INFO] train episode 14974: reward = 25.05, steps = 57 01:04:53 [INFO] train episode 14975: reward = 8.77, steps = 43 01:04:53 [INFO] train episode 14976: reward = 35.60, steps = 83 01:04:53 [INFO] train episode 14977: reward = 7.99, steps = 40 01:04:54 [INFO] train episode 14978: reward = -6.60, steps = 24 01:04:54 [INFO] train episode 14979: reward = -0.54, steps = 27 01:04:54 [INFO] train episode 14980: reward = 21.37, steps = 41 01:04:55 [INFO] train episode 14981: reward = -27.64, steps = 68 01:04:55 [INFO] train episode 14982: reward = 13.02, steps = 32 01:04:55 [INFO] train episode 14983: reward = -0.54, steps = 44 01:04:55 [INFO] train episode 14984: reward = 2.73, steps = 42 01:04:56 [INFO] train episode 14985: reward = 28.36, steps = 59 01:04:56 [INFO] train episode 14986: reward = -5.23, steps = 42 01:04:56 [INFO] train episode 14987: reward = -22.44, steps = 64 01:04:57 [INFO] train episode 14988: reward = 21.39, steps = 51 01:04:57 [INFO] train episode 14989: reward = 23.82, steps = 42 01:04:57 [INFO] train episode 14990: reward = 13.56, steps = 34 01:04:58 [INFO] train episode 14991: reward = 25.74, steps = 45 01:04:58 [INFO] train episode 14992: reward = 26.38, steps = 54 01:04:58 [INFO] train episode 14993: reward = 32.95, steps = 59 01:04:59 [INFO] train episode 14994: reward = 5.33, steps = 35 01:04:59 [INFO] train episode 14995: reward = -9.97, steps = 30 01:04:59 [INFO] train episode 14996: reward = 7.07, steps = 37 01:04:59 [INFO] train episode 14997: reward = 26.75, steps = 67 01:05:00 [INFO] train episode 14998: reward = 22.99, steps = 48 01:05:00 [INFO] train episode 14999: reward = 15.67, steps = 42 01:05:01 [INFO] train episode 15000: reward = 6.44, steps = 35 01:05:01 [INFO] train episode 15001: reward = -2.70, steps = 32 01:05:01 [INFO] train episode 15002: reward = 3.19, steps = 32 01:05:01 [INFO] train episode 15003: reward = 14.09, steps = 42 01:05:02 [INFO] train episode 15004: reward = 20.82, steps = 43 01:05:02 [INFO] train episode 15005: reward = 7.21, steps = 34 01:05:02 [INFO] train episode 15006: reward = 5.26, steps = 69 01:05:02 [INFO] train episode 15007: reward = 0.30, steps = 27 01:05:03 [INFO] train episode 15008: reward = 19.41, steps = 38 01:05:03 [INFO] train episode 15009: reward = -1.03, steps = 31 01:05:03 [INFO] train episode 15010: reward = 23.10, steps = 49 01:05:04 [INFO] train episode 15011: reward = 16.50, steps = 42 01:05:04 [INFO] train episode 15012: reward = 8.02, steps = 36 01:05:04 [INFO] train episode 15013: reward = 25.91, steps = 48 01:05:05 [INFO] train episode 15014: reward = 17.83, steps = 78 01:05:05 [INFO] train episode 15015: reward = 32.00, steps = 48 01:05:06 [INFO] train episode 15016: reward = 51.40, steps = 109 01:05:06 [INFO] train episode 15017: reward = 52.35, steps = 75 01:05:07 [INFO] train episode 15018: reward = 7.46, steps = 32 01:05:07 [INFO] train episode 15019: reward = -22.15, steps = 102 01:05:07 [INFO] train episode 15020: reward = 13.52, steps = 39 01:05:08 [INFO] train episode 15021: reward = -12.20, steps = 29 01:05:08 [INFO] train episode 15022: reward = 2.54, steps = 44 01:05:08 [INFO] train episode 15023: reward = 15.85, steps = 44 01:05:09 [INFO] train episode 15024: reward = 9.88, steps = 37 01:05:09 [INFO] train episode 15025: reward = -14.98, steps = 63 01:05:09 [INFO] train episode 15026: reward = 31.90, steps = 43 01:05:10 [INFO] train episode 15027: reward = 17.54, steps = 69 01:05:10 [INFO] train episode 15028: reward = 21.10, steps = 55 01:05:10 [INFO] train episode 15029: reward = -11.37, steps = 22 01:05:11 [INFO] train episode 15030: reward = 18.91, steps = 50 01:05:11 [INFO] train episode 15031: reward = 20.66, steps = 41 01:05:11 [INFO] train episode 15032: reward = -7.53, steps = 26 01:05:11 [INFO] train episode 15033: reward = 26.81, steps = 53 01:05:12 [INFO] train episode 15034: reward = -7.95, steps = 25 01:05:12 [INFO] train episode 15035: reward = 20.40, steps = 50 01:05:12 [INFO] train episode 15036: reward = 13.46, steps = 41 01:05:12 [INFO] train episode 15037: reward = -5.40, steps = 21 01:05:13 [INFO] train episode 15038: reward = 0.40, steps = 33 01:05:13 [INFO] train episode 15039: reward = 22.87, steps = 49 01:05:13 [INFO] train episode 15040: reward = 17.58, steps = 47 01:05:14 [INFO] train episode 15041: reward = 16.13, steps = 43 01:05:14 [INFO] train episode 15042: reward = 27.59, steps = 88 01:05:15 [INFO] train episode 15043: reward = 18.18, steps = 36 01:05:15 [INFO] train episode 15044: reward = 12.40, steps = 44 01:05:15 [INFO] train episode 15045: reward = 9.92, steps = 41 01:05:16 [INFO] train episode 15046: reward = 4.47, steps = 52 01:05:16 [INFO] train episode 15047: reward = 5.16, steps = 31 01:05:16 [INFO] train episode 15048: reward = 14.03, steps = 32 01:05:17 [INFO] train episode 15049: reward = 13.83, steps = 60 01:05:17 [INFO] train episode 15050: reward = 8.69, steps = 39 01:05:17 [INFO] train episode 15051: reward = 5.61, steps = 33 01:05:17 [INFO] train episode 15052: reward = 23.05, steps = 41 01:05:18 [INFO] train episode 15053: reward = 4.49, steps = 28 01:05:18 [INFO] train episode 15054: reward = 16.03, steps = 41 01:05:18 [INFO] train episode 15055: reward = 17.69, steps = 46 01:05:19 [INFO] train episode 15056: reward = 21.57, steps = 41 01:05:19 [INFO] train episode 15057: reward = 41.15, steps = 67 01:05:19 [INFO] train episode 15058: reward = -7.69, steps = 22 01:05:19 [INFO] train episode 15059: reward = 15.02, steps = 41 01:05:20 [INFO] train episode 15060: reward = 19.89, steps = 42 01:05:20 [INFO] train episode 15061: reward = 31.31, steps = 56 01:05:20 [INFO] train episode 15062: reward = 31.72, steps = 56 01:05:21 [INFO] train episode 15063: reward = 26.48, steps = 54 01:05:21 [INFO] train episode 15064: reward = -10.17, steps = 90 01:05:22 [INFO] train episode 15065: reward = 20.34, steps = 43 01:05:22 [INFO] train episode 15066: reward = 14.34, steps = 48 01:05:22 [INFO] train episode 15067: reward = 3.57, steps = 37 01:05:23 [INFO] train episode 15068: reward = 26.22, steps = 46 01:05:23 [INFO] train episode 15069: reward = 21.61, steps = 52 01:05:23 [INFO] train episode 15070: reward = 8.75, steps = 40 01:05:24 [INFO] train episode 15071: reward = 25.22, steps = 53 01:05:24 [INFO] train episode 15072: reward = -7.38, steps = 26 01:05:24 [INFO] train episode 15073: reward = -12.78, steps = 21 01:05:24 [INFO] train episode 15074: reward = 1.58, steps = 29 01:05:24 [INFO] train episode 15075: reward = 18.73, steps = 47 01:05:25 [INFO] train episode 15076: reward = -5.39, steps = 24 01:05:25 [INFO] train episode 15077: reward = 33.39, steps = 56 01:05:25 [INFO] train episode 15078: reward = 34.25, steps = 75 01:05:26 [INFO] train episode 15079: reward = 8.58, steps = 38 01:05:26 [INFO] train episode 15080: reward = 8.01, steps = 38 01:05:26 [INFO] train episode 15081: reward = 7.88, steps = 40 01:05:27 [INFO] train episode 15082: reward = 11.35, steps = 63 01:05:27 [INFO] train episode 15083: reward = 10.65, steps = 48 01:05:27 [INFO] train episode 15084: reward = -5.92, steps = 25 01:05:27 [INFO] train episode 15085: reward = 19.53, steps = 41 01:05:28 [INFO] train episode 15086: reward = 23.95, steps = 56 01:05:28 [INFO] train episode 15087: reward = -5.86, steps = 25 01:05:28 [INFO] train episode 15088: reward = -1.97, steps = 27 01:05:29 [INFO] train episode 15089: reward = 5.26, steps = 35 01:05:29 [INFO] train episode 15090: reward = -7.16, steps = 74 01:05:29 [INFO] train episode 15091: reward = 20.31, steps = 43 01:05:30 [INFO] train episode 15092: reward = -4.72, steps = 29 01:05:30 [INFO] train episode 15093: reward = 9.31, steps = 42 01:05:30 [INFO] train episode 15094: reward = -4.42, steps = 23 01:05:30 [INFO] train episode 15095: reward = 22.48, steps = 44 01:05:31 [INFO] train episode 15096: reward = 43.33, steps = 78 01:05:31 [INFO] train episode 15097: reward = -9.55, steps = 26 01:05:31 [INFO] train episode 15098: reward = -10.52, steps = 21 01:05:31 [INFO] train episode 15099: reward = 17.74, steps = 48 01:05:32 [INFO] train episode 15100: reward = 15.68, steps = 42 01:05:32 [INFO] train episode 15101: reward = 8.18, steps = 37 01:05:32 [INFO] train episode 15102: reward = 16.27, steps = 42 01:05:33 [INFO] train episode 15103: reward = -34.65, steps = 50 01:05:33 [INFO] train episode 15104: reward = 24.17, steps = 38 01:05:33 [INFO] train episode 15105: reward = 20.65, steps = 40 01:05:33 [INFO] train episode 15106: reward = -4.56, steps = 22 01:05:33 [INFO] train episode 15107: reward = -2.19, steps = 32 01:05:34 [INFO] train episode 15108: reward = 21.23, steps = 39 01:05:34 [INFO] train episode 15109: reward = 22.56, steps = 50 01:05:34 [INFO] train episode 15110: reward = 16.82, steps = 39 01:05:35 [INFO] train episode 15111: reward = 0.88, steps = 29 01:05:35 [INFO] train episode 15112: reward = 22.38, steps = 46 01:05:35 [INFO] train episode 15113: reward = 1.67, steps = 50 01:05:35 [INFO] train episode 15114: reward = 5.16, steps = 31 01:05:36 [INFO] train episode 15115: reward = 28.66, steps = 49 01:05:36 [INFO] train episode 15116: reward = 0.43, steps = 28 01:05:36 [INFO] train episode 15117: reward = -0.93, steps = 37 01:05:36 [INFO] train episode 15118: reward = 16.38, steps = 40 01:05:37 [INFO] train episode 15119: reward = 26.78, steps = 47 01:05:37 [INFO] train episode 15120: reward = -12.69, steps = 23 01:05:37 [INFO] train episode 15121: reward = 11.08, steps = 40 01:05:37 [INFO] train episode 15122: reward = 18.18, steps = 43 01:05:38 [INFO] train episode 15123: reward = 11.90, steps = 34 01:05:38 [INFO] train episode 15124: reward = 19.75, steps = 49 01:05:38 [INFO] train episode 15125: reward = 24.94, steps = 43 01:05:39 [INFO] train episode 15126: reward = 26.14, steps = 46 01:05:39 [INFO] train episode 15127: reward = 11.50, steps = 37 01:05:39 [INFO] train episode 15128: reward = -19.34, steps = 64 01:05:40 [INFO] train episode 15129: reward = 1.10, steps = 34 01:05:40 [INFO] train episode 15130: reward = -28.23, steps = 56 01:05:40 [INFO] train episode 15131: reward = 20.81, steps = 48 01:05:41 [INFO] train episode 15132: reward = 18.55, steps = 53 01:05:41 [INFO] train episode 15133: reward = 6.70, steps = 39 01:05:41 [INFO] train episode 15134: reward = 7.54, steps = 30 01:05:42 [INFO] train episode 15135: reward = 20.69, steps = 60 01:05:42 [INFO] train episode 15136: reward = 33.27, steps = 46 01:05:42 [INFO] train episode 15137: reward = 18.72, steps = 50 01:05:43 [INFO] train episode 15138: reward = 15.50, steps = 51 01:05:43 [INFO] train episode 15139: reward = 20.48, steps = 49 01:05:43 [INFO] train episode 15140: reward = -3.60, steps = 24 01:05:43 [INFO] train episode 15141: reward = 30.28, steps = 50 01:05:44 [INFO] train episode 15142: reward = -9.49, steps = 20 01:05:44 [INFO] train episode 15143: reward = -0.23, steps = 29 01:05:44 [INFO] train episode 15144: reward = 26.92, steps = 44 01:05:44 [INFO] train episode 15145: reward = 9.01, steps = 50 01:05:45 [INFO] train episode 15146: reward = 19.82, steps = 45 01:05:45 [INFO] train episode 15147: reward = 27.49, steps = 44 01:05:45 [INFO] train episode 15148: reward = 29.81, steps = 56 01:05:46 [INFO] train episode 15149: reward = -3.25, steps = 29 01:05:46 [INFO] train episode 15150: reward = 17.46, steps = 44 01:05:46 [INFO] train episode 15151: reward = -51.52, steps = 78 01:05:46 [INFO] train episode 15152: reward = -6.60, steps = 24 01:05:47 [INFO] train episode 15153: reward = 14.48, steps = 54 01:05:47 [INFO] train episode 15154: reward = 4.27, steps = 77 01:05:47 [INFO] train episode 15155: reward = -5.45, steps = 24 01:05:48 [INFO] train episode 15156: reward = 4.21, steps = 30 01:05:48 [INFO] train episode 15157: reward = 6.48, steps = 37 01:05:48 [INFO] train episode 15158: reward = 21.68, steps = 49 01:05:49 [INFO] train episode 15159: reward = 22.74, steps = 47 01:05:49 [INFO] train episode 15160: reward = 18.51, steps = 55 01:05:49 [INFO] train episode 15161: reward = 11.28, steps = 43 01:05:50 [INFO] train episode 15162: reward = 10.81, steps = 48 01:05:50 [INFO] train episode 15163: reward = -9.37, steps = 32 01:05:50 [INFO] train episode 15164: reward = 16.06, steps = 34 01:05:50 [INFO] train episode 15165: reward = 24.08, steps = 38 01:05:50 [INFO] train episode 15166: reward = 12.37, steps = 35 01:05:51 [INFO] train episode 15167: reward = 24.37, steps = 44 01:05:51 [INFO] train episode 15168: reward = 10.62, steps = 44 01:05:51 [INFO] train episode 15169: reward = 14.99, steps = 40 01:05:52 [INFO] train episode 15170: reward = -4.05, steps = 33 01:05:52 [INFO] train episode 15171: reward = 9.80, steps = 42 01:05:52 [INFO] train episode 15172: reward = 1.14, steps = 88 01:05:53 [INFO] train episode 15173: reward = 12.34, steps = 43 01:05:53 [INFO] train episode 15174: reward = 17.31, steps = 45 01:05:53 [INFO] train episode 15175: reward = -7.58, steps = 55 01:05:54 [INFO] train episode 15176: reward = 27.06, steps = 51 01:05:54 [INFO] train episode 15177: reward = 34.25, steps = 56 01:05:54 [INFO] train episode 15178: reward = 31.51, steps = 61 01:05:55 [INFO] train episode 15179: reward = 17.92, steps = 41 01:05:55 [INFO] train episode 15180: reward = 18.27, steps = 48 01:05:55 [INFO] train episode 15181: reward = 12.39, steps = 36 01:05:56 [INFO] train episode 15182: reward = 11.31, steps = 37 01:05:56 [INFO] train episode 15183: reward = -10.56, steps = 43 01:05:56 [INFO] train episode 15184: reward = 2.65, steps = 38 01:05:56 [INFO] train episode 15185: reward = 15.70, steps = 37 01:05:57 [INFO] train episode 15186: reward = 25.19, steps = 54 01:05:57 [INFO] train episode 15187: reward = 6.99, steps = 40 01:05:57 [INFO] train episode 15188: reward = 33.03, steps = 42 01:05:58 [INFO] train episode 15189: reward = -2.26, steps = 32 01:05:58 [INFO] train episode 15190: reward = 19.11, steps = 37 01:05:58 [INFO] train episode 15191: reward = 33.14, steps = 48 01:05:58 [INFO] train episode 15192: reward = 0.05, steps = 29 01:05:59 [INFO] train episode 15193: reward = 17.50, steps = 47 01:05:59 [INFO] train episode 15194: reward = 0.63, steps = 31 01:05:59 [INFO] train episode 15195: reward = -6.06, steps = 32 01:05:59 [INFO] train episode 15196: reward = 14.05, steps = 45 01:06:00 [INFO] train episode 15197: reward = 20.82, steps = 46 01:06:00 [INFO] train episode 15198: reward = 18.44, steps = 35 01:06:00 [INFO] train episode 15199: reward = -6.39, steps = 32 01:06:00 [INFO] train episode 15200: reward = 3.06, steps = 36 01:06:01 [INFO] train episode 15201: reward = 32.09, steps = 66 01:06:01 [INFO] train episode 15202: reward = 20.88, steps = 46 01:06:02 [INFO] train episode 15203: reward = 19.68, steps = 56 01:06:02 [INFO] train episode 15204: reward = 27.22, steps = 54 01:06:02 [INFO] train episode 15205: reward = 14.88, steps = 43 01:06:03 [INFO] train episode 15206: reward = 39.22, steps = 68 01:06:03 [INFO] train episode 15207: reward = -6.92, steps = 25 01:06:03 [INFO] train episode 15208: reward = 1.82, steps = 31 01:06:03 [INFO] train episode 15209: reward = 26.44, steps = 53 01:06:03 [INFO] train episode 15210: reward = -2.62, steps = 22 01:06:04 [INFO] train episode 15211: reward = -7.05, steps = 26 01:06:04 [INFO] train episode 15212: reward = 0.07, steps = 77 01:06:04 [INFO] train episode 15213: reward = -0.04, steps = 31 01:06:05 [INFO] train episode 15214: reward = 12.66, steps = 42 01:06:05 [INFO] train episode 15215: reward = -34.75, steps = 22 01:06:05 [INFO] train episode 15216: reward = -2.96, steps = 34 01:06:05 [INFO] train episode 15217: reward = 18.73, steps = 39 01:06:05 [INFO] train episode 15218: reward = -6.55, steps = 28 01:06:06 [INFO] train episode 15219: reward = 20.72, steps = 42 01:06:06 [INFO] train episode 15220: reward = 27.47, steps = 47 01:06:06 [INFO] train episode 15221: reward = 23.44, steps = 50 01:06:07 [INFO] train episode 15222: reward = 42.45, steps = 55 01:06:07 [INFO] train episode 15223: reward = 13.20, steps = 37 01:06:07 [INFO] train episode 15224: reward = 12.36, steps = 41 01:06:07 [INFO] train episode 15225: reward = 12.64, steps = 36 01:06:08 [INFO] train episode 15226: reward = -6.14, steps = 29 01:06:08 [INFO] train episode 15227: reward = 8.37, steps = 44 01:06:08 [INFO] train episode 15228: reward = -9.66, steps = 25 01:06:09 [INFO] train episode 15229: reward = -4.80, steps = 25 01:06:09 [INFO] train episode 15230: reward = 23.30, steps = 48 01:06:09 [INFO] train episode 15231: reward = 15.62, steps = 36 01:06:09 [INFO] train episode 15232: reward = 13.57, steps = 55 01:06:10 [INFO] train episode 15233: reward = 12.44, steps = 40 01:06:10 [INFO] train episode 15234: reward = 20.19, steps = 65 01:06:10 [INFO] train episode 15235: reward = 10.59, steps = 41 01:06:11 [INFO] train episode 15236: reward = 4.18, steps = 42 01:06:11 [INFO] train episode 15237: reward = 21.31, steps = 45 01:06:11 [INFO] train episode 15238: reward = 14.20, steps = 36 01:06:11 [INFO] train episode 15239: reward = -6.86, steps = 22 01:06:12 [INFO] train episode 15240: reward = 44.45, steps = 73 01:06:12 [INFO] train episode 15241: reward = 3.03, steps = 28 01:06:12 [INFO] train episode 15242: reward = 17.54, steps = 45 01:06:13 [INFO] train episode 15243: reward = 4.47, steps = 31 01:06:13 [INFO] train episode 15244: reward = 0.22, steps = 35 01:06:13 [INFO] train episode 15245: reward = 15.11, steps = 40 01:06:13 [INFO] train episode 15246: reward = 7.53, steps = 36 01:06:14 [INFO] train episode 15247: reward = 32.92, steps = 40 01:06:14 [INFO] train episode 15248: reward = -9.34, steps = 23 01:06:14 [INFO] train episode 15249: reward = 11.05, steps = 40 01:06:14 [INFO] train episode 15250: reward = -11.48, steps = 27 01:06:14 [INFO] train episode 15251: reward = 13.17, steps = 44 01:06:15 [INFO] train episode 15252: reward = 13.65, steps = 42 01:06:15 [INFO] train episode 15253: reward = 26.23, steps = 45 01:06:15 [INFO] train episode 15254: reward = 26.61, steps = 55 01:06:16 [INFO] train episode 15255: reward = 22.62, steps = 39 01:06:16 [INFO] train episode 15256: reward = 20.64, steps = 40 01:06:16 [INFO] train episode 15257: reward = -0.82, steps = 29 01:06:16 [INFO] train episode 15258: reward = 2.70, steps = 37 01:06:17 [INFO] train episode 15259: reward = -0.59, steps = 30 01:06:17 [INFO] train episode 15260: reward = 21.54, steps = 60 01:06:17 [INFO] train episode 15261: reward = 12.33, steps = 33 01:06:18 [INFO] train episode 15262: reward = 9.95, steps = 44 01:06:18 [INFO] train episode 15263: reward = 17.80, steps = 42 01:06:18 [INFO] train episode 15264: reward = -6.73, steps = 22 01:06:18 [INFO] train episode 15265: reward = 3.24, steps = 28 01:06:18 [INFO] train episode 15266: reward = 17.56, steps = 42 01:06:19 [INFO] train episode 15267: reward = 8.28, steps = 34 01:06:19 [INFO] train episode 15268: reward = 8.48, steps = 34 01:06:19 [INFO] train episode 15269: reward = 19.37, steps = 53 01:06:20 [INFO] train episode 15270: reward = 23.85, steps = 49 01:06:20 [INFO] train episode 15271: reward = 14.61, steps = 43 01:06:20 [INFO] train episode 15272: reward = 16.43, steps = 43 01:06:21 [INFO] train episode 15273: reward = -20.00, steps = 72 01:06:21 [INFO] train episode 15274: reward = 35.60, steps = 47 01:06:22 [INFO] train episode 15275: reward = 31.63, steps = 66 01:06:22 [INFO] train episode 15276: reward = 2.31, steps = 37 01:06:22 [INFO] train episode 15277: reward = -10.57, steps = 24 01:06:22 [INFO] train episode 15278: reward = 1.71, steps = 36 01:06:23 [INFO] train episode 15279: reward = 2.10, steps = 29 01:06:23 [INFO] train episode 15280: reward = 21.94, steps = 50 01:06:23 [INFO] train episode 15281: reward = 5.85, steps = 35 01:06:23 [INFO] train episode 15282: reward = 26.17, steps = 47 01:06:24 [INFO] train episode 15283: reward = 6.33, steps = 38 01:06:24 [INFO] train episode 15284: reward = 17.40, steps = 40 01:06:24 [INFO] train episode 15285: reward = -9.01, steps = 34 01:06:24 [INFO] train episode 15286: reward = 1.62, steps = 35 01:06:25 [INFO] train episode 15287: reward = 14.88, steps = 44 01:06:25 [INFO] train episode 15288: reward = -14.55, steps = 24 01:06:25 [INFO] train episode 15289: reward = 22.36, steps = 65 01:06:26 [INFO] train episode 15290: reward = 20.53, steps = 49 01:06:26 [INFO] train episode 15291: reward = -2.09, steps = 26 01:06:26 [INFO] train episode 15292: reward = -5.31, steps = 20 01:06:26 [INFO] train episode 15293: reward = -3.07, steps = 30 01:06:26 [INFO] train episode 15294: reward = 13.47, steps = 38 01:06:27 [INFO] train episode 15295: reward = 2.87, steps = 30 01:06:27 [INFO] train episode 15296: reward = 7.09, steps = 50 01:06:27 [INFO] train episode 15297: reward = 14.43, steps = 40 01:06:27 [INFO] train episode 15298: reward = 5.67, steps = 38 01:06:28 [INFO] train episode 15299: reward = 17.25, steps = 44 01:06:28 [INFO] train episode 15300: reward = 4.93, steps = 39 01:06:28 [INFO] train episode 15301: reward = 28.59, steps = 43 01:06:29 [INFO] train episode 15302: reward = 23.09, steps = 52 01:06:29 [INFO] train episode 15303: reward = 7.23, steps = 34 01:06:29 [INFO] train episode 15304: reward = 3.99, steps = 36 01:06:29 [INFO] train episode 15305: reward = 12.43, steps = 48 01:06:30 [INFO] train episode 15306: reward = 27.53, steps = 44 01:06:30 [INFO] train episode 15307: reward = 2.78, steps = 37 01:06:30 [INFO] train episode 15308: reward = -5.13, steps = 24 01:06:30 [INFO] train episode 15309: reward = 14.99, steps = 37 01:06:31 [INFO] train episode 15310: reward = 12.69, steps = 44 01:06:31 [INFO] train episode 15311: reward = 24.89, steps = 49 01:06:31 [INFO] train episode 15312: reward = -8.56, steps = 54 01:06:32 [INFO] train episode 15313: reward = 11.77, steps = 46 01:06:32 [INFO] train episode 15314: reward = 21.97, steps = 49 01:06:32 [INFO] train episode 15315: reward = 32.97, steps = 51 01:06:33 [INFO] train episode 15316: reward = 5.97, steps = 36 01:06:33 [INFO] train episode 15317: reward = -15.41, steps = 21 01:06:33 [INFO] train episode 15318: reward = 14.13, steps = 40 01:06:33 [INFO] train episode 15319: reward = 4.03, steps = 30 01:06:33 [INFO] train episode 15320: reward = 8.48, steps = 39 01:06:34 [INFO] train episode 15321: reward = -27.46, steps = 70 01:06:34 [INFO] train episode 15322: reward = 10.81, steps = 36 01:06:34 [INFO] train episode 15323: reward = 34.64, steps = 57 01:06:35 [INFO] train episode 15324: reward = 43.48, steps = 65 01:06:35 [INFO] train episode 15325: reward = 28.81, steps = 45 01:06:36 [INFO] train episode 15326: reward = -0.96, steps = 29 01:06:36 [INFO] train episode 15327: reward = 27.55, steps = 68 01:06:36 [INFO] train episode 15328: reward = 27.01, steps = 47 01:06:37 [INFO] train episode 15329: reward = 25.06, steps = 54 01:06:37 [INFO] train episode 15330: reward = 32.38, steps = 52 01:06:37 [INFO] train episode 15331: reward = 12.25, steps = 56 01:06:38 [INFO] train episode 15332: reward = 15.82, steps = 40 01:06:38 [INFO] train episode 15333: reward = -9.12, steps = 24 01:06:38 [INFO] train episode 15334: reward = 1.96, steps = 31 01:06:38 [INFO] train episode 15335: reward = 9.94, steps = 33 01:06:39 [INFO] train episode 15336: reward = 5.85, steps = 39 01:06:39 [INFO] train episode 15337: reward = -23.23, steps = 77 01:06:39 [INFO] train episode 15338: reward = 8.04, steps = 33 01:06:40 [INFO] train episode 15339: reward = -27.76, steps = 57 01:06:40 [INFO] train episode 15340: reward = 30.56, steps = 59 01:06:40 [INFO] train episode 15341: reward = 25.31, steps = 42 01:06:41 [INFO] train episode 15342: reward = 12.87, steps = 46 01:06:41 [INFO] train episode 15343: reward = 18.23, steps = 40 01:06:41 [INFO] train episode 15344: reward = -7.83, steps = 24 01:06:41 [INFO] train episode 15345: reward = 26.79, steps = 42 01:06:42 [INFO] train episode 15346: reward = 31.76, steps = 46 01:06:42 [INFO] train episode 15347: reward = 13.84, steps = 36 01:06:42 [INFO] train episode 15348: reward = -11.94, steps = 23 01:06:42 [INFO] train episode 15349: reward = -9.44, steps = 54 01:06:43 [INFO] train episode 15350: reward = 17.21, steps = 41 01:06:43 [INFO] train episode 15351: reward = 27.36, steps = 42 01:06:43 [INFO] train episode 15352: reward = 17.27, steps = 50 01:06:44 [INFO] train episode 15353: reward = 17.32, steps = 40 01:06:44 [INFO] train episode 15354: reward = -15.49, steps = 21 01:06:44 [INFO] train episode 15355: reward = 15.57, steps = 38 01:06:44 [INFO] train episode 15356: reward = 19.48, steps = 55 01:06:45 [INFO] train episode 15357: reward = 18.38, steps = 46 01:06:45 [INFO] train episode 15358: reward = 18.42, steps = 42 01:06:45 [INFO] train episode 15359: reward = 31.18, steps = 53 01:06:46 [INFO] train episode 15360: reward = 26.80, steps = 44 01:06:46 [INFO] train episode 15361: reward = -15.44, steps = 22 01:06:46 [INFO] train episode 15362: reward = 13.63, steps = 47 01:06:46 [INFO] train episode 15363: reward = 21.13, steps = 35 01:06:47 [INFO] train episode 15364: reward = 8.93, steps = 56 01:06:47 [INFO] train episode 15365: reward = -16.08, steps = 30 01:06:47 [INFO] train episode 15366: reward = 12.15, steps = 47 01:06:47 [INFO] train episode 15367: reward = -7.77, steps = 20 01:06:48 [INFO] train episode 15368: reward = 23.98, steps = 49 01:06:48 [INFO] train episode 15369: reward = 15.64, steps = 35 01:06:48 [INFO] train episode 15370: reward = 4.56, steps = 32 01:06:49 [INFO] train episode 15371: reward = 19.67, steps = 41 01:06:49 [INFO] train episode 15372: reward = 20.81, steps = 52 01:06:49 [INFO] train episode 15373: reward = -12.01, steps = 23 01:06:49 [INFO] train episode 15374: reward = -0.47, steps = 31 01:06:50 [INFO] train episode 15375: reward = 8.90, steps = 32 01:06:50 [INFO] train episode 15376: reward = 14.97, steps = 42 01:06:50 [INFO] train episode 15377: reward = 20.31, steps = 44 01:06:50 [INFO] train episode 15378: reward = 24.64, steps = 44 01:06:51 [INFO] train episode 15379: reward = 35.87, steps = 62 01:06:51 [INFO] train episode 15380: reward = 15.78, steps = 36 01:06:51 [INFO] train episode 15381: reward = 17.60, steps = 60 01:06:52 [INFO] train episode 15382: reward = 6.61, steps = 35 01:06:52 [INFO] train episode 15383: reward = 19.24, steps = 49 01:06:52 [INFO] train episode 15384: reward = -14.00, steps = 44 01:06:52 [INFO] train episode 15385: reward = -7.65, steps = 29 01:06:53 [INFO] train episode 15386: reward = 10.56, steps = 43 01:06:53 [INFO] train episode 15387: reward = 13.95, steps = 65 01:06:53 [INFO] train episode 15388: reward = -11.50, steps = 29 01:06:54 [INFO] train episode 15389: reward = 17.68, steps = 52 01:06:54 [INFO] train episode 15390: reward = 9.15, steps = 45 01:06:54 [INFO] train episode 15391: reward = 17.76, steps = 42 01:06:55 [INFO] train episode 15392: reward = 16.77, steps = 65 01:06:55 [INFO] train episode 15393: reward = 26.42, steps = 43 01:06:55 [INFO] train episode 15394: reward = -1.73, steps = 30 01:06:55 [INFO] train episode 15395: reward = -5.09, steps = 24 01:06:56 [INFO] train episode 15396: reward = -1.00, steps = 30 01:06:56 [INFO] train episode 15397: reward = -1.76, steps = 55 01:06:56 [INFO] train episode 15398: reward = -15.51, steps = 19 01:06:56 [INFO] train episode 15399: reward = 7.07, steps = 42 01:06:57 [INFO] train episode 15400: reward = -2.38, steps = 36 01:06:57 [INFO] train episode 15401: reward = 18.59, steps = 50 01:06:57 [INFO] train episode 15402: reward = -2.26, steps = 30 01:06:57 [INFO] train episode 15403: reward = 24.69, steps = 47 01:06:58 [INFO] train episode 15404: reward = 0.52, steps = 29 01:06:58 [INFO] train episode 15405: reward = 8.44, steps = 36 01:06:58 [INFO] train episode 15406: reward = -4.79, steps = 27 01:06:58 [INFO] train episode 15407: reward = 30.11, steps = 55 01:06:59 [INFO] train episode 15408: reward = -3.48, steps = 34 01:06:59 [INFO] train episode 15409: reward = 1.53, steps = 70 01:06:59 [INFO] train episode 15410: reward = 21.45, steps = 34 01:07:00 [INFO] train episode 15411: reward = 8.88, steps = 36 01:07:00 [INFO] train episode 15412: reward = 12.58, steps = 42 01:07:00 [INFO] train episode 15413: reward = 16.41, steps = 50 01:07:01 [INFO] train episode 15414: reward = 8.09, steps = 39 01:07:01 [INFO] train episode 15415: reward = -13.35, steps = 68 01:07:01 [INFO] train episode 15416: reward = 33.22, steps = 59 01:07:02 [INFO] train episode 15417: reward = 14.34, steps = 45 01:07:02 [INFO] train episode 15418: reward = -0.40, steps = 39 01:07:02 [INFO] train episode 15419: reward = 31.69, steps = 59 01:07:03 [INFO] train episode 15420: reward = 13.96, steps = 40 01:07:03 [INFO] train episode 15421: reward = 0.51, steps = 28 01:07:03 [INFO] train episode 15422: reward = -17.06, steps = 21 01:07:03 [INFO] train episode 15423: reward = 3.51, steps = 32 01:07:04 [INFO] train episode 15424: reward = 16.48, steps = 41 01:07:04 [INFO] train episode 15425: reward = 38.63, steps = 108 01:07:05 [INFO] train episode 15426: reward = -1.63, steps = 53 01:07:05 [INFO] train episode 15427: reward = 23.72, steps = 44 01:07:05 [INFO] train episode 15428: reward = 24.11, steps = 45 01:07:06 [INFO] train episode 15429: reward = 10.51, steps = 34 01:07:06 [INFO] train episode 15430: reward = -4.22, steps = 26 01:07:06 [INFO] train episode 15431: reward = 3.70, steps = 33 01:07:06 [INFO] train episode 15432: reward = 30.92, steps = 56 01:07:07 [INFO] train episode 15433: reward = -2.97, steps = 25 01:07:07 [INFO] train episode 15434: reward = 1.22, steps = 24 01:07:07 [INFO] train episode 15435: reward = 12.30, steps = 36 01:07:07 [INFO] train episode 15436: reward = 22.49, steps = 45 01:07:07 [INFO] train episode 15437: reward = -8.58, steps = 23 01:07:08 [INFO] train episode 15438: reward = -4.47, steps = 26 01:07:08 [INFO] train episode 15439: reward = -2.98, steps = 23 01:07:08 [INFO] train episode 15440: reward = -13.12, steps = 58 01:07:08 [INFO] train episode 15441: reward = -9.98, steps = 22 01:07:09 [INFO] train episode 15442: reward = 21.92, steps = 49 01:07:09 [INFO] train episode 15443: reward = 2.74, steps = 34 01:07:09 [INFO] train episode 15444: reward = 21.96, steps = 37 01:07:09 [INFO] train episode 15445: reward = 14.43, steps = 31 01:07:10 [INFO] train episode 15446: reward = 14.48, steps = 39 01:07:10 [INFO] train episode 15447: reward = 7.46, steps = 29 01:07:10 [INFO] train episode 15448: reward = 13.97, steps = 43 01:07:10 [INFO] train episode 15449: reward = 17.17, steps = 42 01:07:11 [INFO] train episode 15450: reward = -4.66, steps = 20 01:07:11 [INFO] train episode 15451: reward = 33.24, steps = 49 01:07:11 [INFO] train episode 15452: reward = 17.39, steps = 45 01:07:11 [INFO] train episode 15453: reward = 19.03, steps = 44 01:07:12 [INFO] train episode 15454: reward = 6.09, steps = 35 01:07:12 [INFO] train episode 15455: reward = 24.43, steps = 59 01:07:12 [INFO] train episode 15456: reward = 6.83, steps = 40 01:07:13 [INFO] train episode 15457: reward = 36.80, steps = 56 01:07:13 [INFO] train episode 15458: reward = -4.73, steps = 37 01:07:13 [INFO] train episode 15459: reward = 1.52, steps = 31 01:07:13 [INFO] train episode 15460: reward = 3.18, steps = 45 01:07:14 [INFO] train episode 15461: reward = 7.05, steps = 26 01:07:14 [INFO] train episode 15462: reward = -4.20, steps = 40 01:07:14 [INFO] train episode 15463: reward = 13.24, steps = 38 01:07:14 [INFO] train episode 15464: reward = 17.87, steps = 43 01:07:15 [INFO] train episode 15465: reward = 16.63, steps = 45 01:07:15 [INFO] train episode 15466: reward = 3.94, steps = 35 01:07:16 [INFO] train episode 15467: reward = -1.05, steps = 27 01:07:16 [INFO] train episode 15468: reward = -12.74, steps = 25 01:07:16 [INFO] train episode 15469: reward = -6.94, steps = 31 01:07:16 [INFO] train episode 15470: reward = -1.01, steps = 35 01:07:17 [INFO] train episode 15471: reward = -1.01, steps = 48 01:07:17 [INFO] train episode 15472: reward = 29.66, steps = 54 01:07:17 [INFO] train episode 15473: reward = 3.69, steps = 40 01:07:17 [INFO] train episode 15474: reward = -20.39, steps = 29 01:07:18 [INFO] train episode 15475: reward = 24.16, steps = 48 01:07:18 [INFO] train episode 15476: reward = -1.22, steps = 23 01:07:18 [INFO] train episode 15477: reward = 19.10, steps = 39 01:07:18 [INFO] train episode 15478: reward = 11.97, steps = 37 01:07:19 [INFO] train episode 15479: reward = 19.39, steps = 38 01:07:19 [INFO] train episode 15480: reward = 21.46, steps = 52 01:07:19 [INFO] train episode 15481: reward = 3.50, steps = 30 01:07:19 [INFO] train episode 15482: reward = 3.87, steps = 29 01:07:19 [INFO] train episode 15483: reward = -6.73, steps = 24 01:07:20 [INFO] train episode 15484: reward = -11.84, steps = 22 01:07:20 [INFO] train episode 15485: reward = 6.17, steps = 42 01:07:20 [INFO] train episode 15486: reward = 15.39, steps = 36 01:07:20 [INFO] train episode 15487: reward = -6.93, steps = 33 01:07:21 [INFO] train episode 15488: reward = 16.30, steps = 38 01:07:21 [INFO] train episode 15489: reward = 7.58, steps = 38 01:07:21 [INFO] train episode 15490: reward = -16.96, steps = 22 01:07:21 [INFO] train episode 15491: reward = 19.64, steps = 62 01:07:22 [INFO] train episode 15492: reward = -11.02, steps = 18 01:07:22 [INFO] train episode 15493: reward = 18.25, steps = 65 01:07:22 [INFO] train episode 15494: reward = -15.65, steps = 22 01:07:22 [INFO] train episode 15495: reward = 18.47, steps = 33 01:07:23 [INFO] train episode 15496: reward = 12.38, steps = 46 01:07:23 [INFO] train episode 15497: reward = -11.00, steps = 23 01:07:23 [INFO] train episode 15498: reward = 3.90, steps = 35 01:07:23 [INFO] train episode 15499: reward = -3.90, steps = 30 01:07:24 [INFO] train episode 15500: reward = 19.31, steps = 45 01:07:24 [INFO] train episode 15501: reward = 19.45, steps = 44 01:07:24 [INFO] train episode 15502: reward = 16.18, steps = 41 01:07:25 [INFO] train episode 15503: reward = 13.02, steps = 66 01:07:25 [INFO] train episode 15504: reward = 14.26, steps = 36 01:07:25 [INFO] train episode 15505: reward = 31.88, steps = 43 01:07:25 [INFO] train episode 15506: reward = -14.65, steps = 45 01:07:26 [INFO] train episode 15507: reward = -9.79, steps = 25 01:07:26 [INFO] train episode 15508: reward = 13.90, steps = 35 01:07:26 [INFO] train episode 15509: reward = 32.55, steps = 61 01:07:27 [INFO] train episode 15510: reward = 2.08, steps = 45 01:07:27 [INFO] train episode 15511: reward = 32.16, steps = 52 01:07:27 [INFO] train episode 15512: reward = 21.09, steps = 41 01:07:27 [INFO] train episode 15513: reward = 7.06, steps = 48 01:07:28 [INFO] train episode 15514: reward = 0.30, steps = 33 01:07:28 [INFO] train episode 15515: reward = -14.35, steps = 21 01:07:28 [INFO] train episode 15516: reward = -10.09, steps = 32 01:07:28 [INFO] train episode 15517: reward = 22.57, steps = 41 01:07:29 [INFO] train episode 15518: reward = -8.98, steps = 26 01:07:29 [INFO] train episode 15519: reward = 13.45, steps = 39 01:07:29 [INFO] train episode 15520: reward = -8.03, steps = 23 01:07:30 [INFO] train episode 15521: reward = 9.48, steps = 49 01:07:30 [INFO] train episode 15522: reward = 8.19, steps = 39 01:07:30 [INFO] train episode 15523: reward = 16.20, steps = 37 01:07:30 [INFO] train episode 15524: reward = 22.42, steps = 49 01:07:31 [INFO] train episode 15525: reward = 15.37, steps = 62 01:07:31 [INFO] train episode 15526: reward = -5.79, steps = 47 01:07:31 [INFO] train episode 15527: reward = 6.32, steps = 36 01:07:32 [INFO] train episode 15528: reward = 25.13, steps = 50 01:07:32 [INFO] train episode 15529: reward = -11.46, steps = 24 01:07:32 [INFO] train episode 15530: reward = 14.12, steps = 44 01:07:32 [INFO] train episode 15531: reward = 4.50, steps = 32 01:07:33 [INFO] train episode 15532: reward = 22.22, steps = 47 01:07:33 [INFO] train episode 15533: reward = 12.10, steps = 32 01:07:33 [INFO] train episode 15534: reward = -17.22, steps = 53 01:07:34 [INFO] train episode 15535: reward = 15.86, steps = 44 01:07:34 [INFO] train episode 15536: reward = 1.54, steps = 31 01:07:34 [INFO] train episode 15537: reward = -3.92, steps = 25 01:07:34 [INFO] train episode 15538: reward = 7.24, steps = 41 01:07:34 [INFO] train episode 15539: reward = -2.26, steps = 24 01:07:35 [INFO] train episode 15540: reward = 28.06, steps = 65 01:07:35 [INFO] train episode 15541: reward = 18.93, steps = 40 01:07:35 [INFO] train episode 15542: reward = 23.04, steps = 62 01:07:36 [INFO] train episode 15543: reward = 18.42, steps = 64 01:07:36 [INFO] train episode 15544: reward = 9.77, steps = 32 01:07:36 [INFO] train episode 15545: reward = 2.06, steps = 31 01:07:36 [INFO] train episode 15546: reward = -6.54, steps = 21 01:07:37 [INFO] train episode 15547: reward = 13.66, steps = 39 01:07:37 [INFO] train episode 15548: reward = 26.51, steps = 39 01:07:37 [INFO] train episode 15549: reward = -6.42, steps = 23 01:07:37 [INFO] train episode 15550: reward = -16.28, steps = 23 01:07:38 [INFO] train episode 15551: reward = -3.07, steps = 31 01:07:38 [INFO] train episode 15552: reward = 10.46, steps = 46 01:07:38 [INFO] train episode 15553: reward = -4.81, steps = 32 01:07:38 [INFO] train episode 15554: reward = 6.72, steps = 47 01:07:39 [INFO] train episode 15555: reward = 13.07, steps = 52 01:07:39 [INFO] train episode 15556: reward = 14.02, steps = 42 01:07:39 [INFO] train episode 15557: reward = 29.31, steps = 52 01:07:39 [INFO] train episode 15558: reward = -11.68, steps = 25 01:07:40 [INFO] train episode 15559: reward = -10.60, steps = 25 01:07:40 [INFO] train episode 15560: reward = 17.42, steps = 41 01:07:40 [INFO] train episode 15561: reward = 12.18, steps = 35 01:07:40 [INFO] train episode 15562: reward = 21.29, steps = 42 01:07:41 [INFO] train episode 15563: reward = 4.38, steps = 29 01:07:41 [INFO] train episode 15564: reward = 18.96, steps = 44 01:07:41 [INFO] train episode 15565: reward = -9.75, steps = 27 01:07:41 [INFO] train episode 15566: reward = 6.21, steps = 32 01:07:42 [INFO] train episode 15567: reward = 11.97, steps = 43 01:07:42 [INFO] train episode 15568: reward = -8.92, steps = 25 01:07:42 [INFO] train episode 15569: reward = -9.73, steps = 34 01:07:43 [INFO] train episode 15570: reward = -1.98, steps = 39 01:07:43 [INFO] train episode 15571: reward = -12.83, steps = 27 01:07:43 [INFO] train episode 15572: reward = 6.10, steps = 53 01:07:43 [INFO] train episode 15573: reward = 16.66, steps = 57 01:07:44 [INFO] train episode 15574: reward = 26.18, steps = 46 01:07:44 [INFO] train episode 15575: reward = 25.52, steps = 47 01:07:44 [INFO] train episode 15576: reward = 11.38, steps = 31 01:07:45 [INFO] train episode 15577: reward = 10.48, steps = 45 01:07:45 [INFO] train episode 15578: reward = -9.33, steps = 26 01:07:45 [INFO] train episode 15579: reward = 2.06, steps = 27 01:07:45 [INFO] train episode 15580: reward = 19.29, steps = 45 01:07:46 [INFO] train episode 15581: reward = 9.95, steps = 43 01:07:46 [INFO] train episode 15582: reward = 7.59, steps = 35 01:07:46 [INFO] train episode 15583: reward = 20.01, steps = 45 01:07:46 [INFO] train episode 15584: reward = 11.89, steps = 49 01:07:47 [INFO] train episode 15585: reward = -5.61, steps = 23 01:07:47 [INFO] train episode 15586: reward = 21.91, steps = 42 01:07:47 [INFO] train episode 15587: reward = 14.84, steps = 35 01:07:47 [INFO] train episode 15588: reward = 8.71, steps = 35 01:07:48 [INFO] train episode 15589: reward = 23.43, steps = 45 01:07:48 [INFO] train episode 15590: reward = 17.43, steps = 36 01:07:48 [INFO] train episode 15591: reward = 33.98, steps = 50 01:07:49 [INFO] train episode 15592: reward = 8.92, steps = 39 01:07:49 [INFO] train episode 15593: reward = 33.31, steps = 52 01:07:49 [INFO] train episode 15594: reward = 11.81, steps = 46 01:07:50 [INFO] train episode 15595: reward = 44.71, steps = 66 01:07:50 [INFO] train episode 15596: reward = 16.53, steps = 44 01:07:50 [INFO] train episode 15597: reward = 6.20, steps = 35 01:07:50 [INFO] train episode 15598: reward = 4.31, steps = 35 01:07:51 [INFO] train episode 15599: reward = 41.46, steps = 63 01:07:51 [INFO] train episode 15600: reward = 0.45, steps = 28 01:07:51 [INFO] train episode 15601: reward = 18.89, steps = 45 01:07:52 [INFO] train episode 15602: reward = 21.89, steps = 66 01:07:52 [INFO] train episode 15603: reward = -6.27, steps = 23 01:07:52 [INFO] train episode 15604: reward = 0.61, steps = 63 01:07:52 [INFO] train episode 15605: reward = -1.28, steps = 30 01:07:53 [INFO] train episode 15606: reward = -9.11, steps = 34 01:07:53 [INFO] train episode 15607: reward = 7.45, steps = 34 01:07:53 [INFO] train episode 15608: reward = -11.68, steps = 28 01:07:53 [INFO] train episode 15609: reward = -4.65, steps = 28 01:07:54 [INFO] train episode 15610: reward = 16.37, steps = 45 01:07:54 [INFO] train episode 15611: reward = -2.04, steps = 29 01:07:54 [INFO] train episode 15612: reward = 20.94, steps = 43 01:07:54 [INFO] train episode 15613: reward = 2.22, steps = 38 01:07:55 [INFO] train episode 15614: reward = -6.28, steps = 35 01:07:55 [INFO] train episode 15615: reward = -1.05, steps = 25 01:07:55 [INFO] train episode 15616: reward = 23.65, steps = 59 01:07:55 [INFO] train episode 15617: reward = -2.65, steps = 22 01:07:56 [INFO] train episode 15618: reward = 41.60, steps = 65 01:07:56 [INFO] train episode 15619: reward = 2.77, steps = 35 01:07:56 [INFO] train episode 15620: reward = -7.28, steps = 25 01:07:57 [INFO] train episode 15621: reward = -8.69, steps = 31 01:07:57 [INFO] train episode 15622: reward = 19.45, steps = 47 01:07:57 [INFO] train episode 15623: reward = -8.02, steps = 22 01:07:57 [INFO] train episode 15624: reward = 19.77, steps = 49 01:07:58 [INFO] train episode 15625: reward = 28.58, steps = 42 01:07:58 [INFO] train episode 15626: reward = 19.08, steps = 47 01:07:58 [INFO] train episode 15627: reward = 11.59, steps = 35 01:07:58 [INFO] train episode 15628: reward = -1.05, steps = 32 01:07:59 [INFO] train episode 15629: reward = 7.85, steps = 36 01:07:59 [INFO] train episode 15630: reward = 14.90, steps = 43 01:07:59 [INFO] train episode 15631: reward = 21.22, steps = 39 01:07:59 [INFO] train episode 15632: reward = 29.14, steps = 51 01:08:00 [INFO] train episode 15633: reward = 16.28, steps = 35 01:08:00 [INFO] train episode 15634: reward = 9.28, steps = 48 01:08:00 [INFO] train episode 15635: reward = 27.14, steps = 48 01:08:01 [INFO] train episode 15636: reward = 0.89, steps = 30 01:08:01 [INFO] train episode 15637: reward = -0.79, steps = 38 01:08:01 [INFO] train episode 15638: reward = 30.67, steps = 73 01:08:02 [INFO] train episode 15639: reward = 4.16, steps = 42 01:08:02 [INFO] train episode 15640: reward = 36.75, steps = 65 01:08:02 [INFO] train episode 15641: reward = 33.94, steps = 56 01:08:03 [INFO] train episode 15642: reward = 15.33, steps = 41 01:08:03 [INFO] train episode 15643: reward = -8.39, steps = 30 01:08:03 [INFO] train episode 15644: reward = -7.46, steps = 22 01:08:03 [INFO] train episode 15645: reward = 14.55, steps = 34 01:08:04 [INFO] train episode 15646: reward = 38.06, steps = 74 01:08:04 [INFO] train episode 15647: reward = 5.77, steps = 32 01:08:04 [INFO] train episode 15648: reward = 14.40, steps = 40 01:08:04 [INFO] train episode 15649: reward = -4.16, steps = 28 01:08:05 [INFO] train episode 15650: reward = -10.30, steps = 25 01:08:05 [INFO] train episode 15651: reward = 33.19, steps = 55 01:08:05 [INFO] train episode 15652: reward = 14.08, steps = 40 01:08:06 [INFO] train episode 15653: reward = 44.79, steps = 65 01:08:06 [INFO] train episode 15654: reward = -1.99, steps = 30 01:08:06 [INFO] train episode 15655: reward = 3.61, steps = 30 01:08:06 [INFO] train episode 15656: reward = -0.25, steps = 35 01:08:07 [INFO] train episode 15657: reward = 5.64, steps = 34 01:08:07 [INFO] train episode 15658: reward = -13.96, steps = 20 01:08:07 [INFO] train episode 15659: reward = 1.18, steps = 26 01:08:07 [INFO] train episode 15660: reward = -17.98, steps = 66 01:08:08 [INFO] train episode 15661: reward = 6.34, steps = 32 01:08:08 [INFO] train episode 15662: reward = 14.93, steps = 38 01:08:08 [INFO] train episode 15663: reward = 39.95, steps = 61 01:08:09 [INFO] train episode 15664: reward = 34.35, steps = 58 01:08:09 [INFO] train episode 15665: reward = 19.68, steps = 35 01:08:09 [INFO] train episode 15666: reward = -7.78, steps = 22 01:08:09 [INFO] train episode 15667: reward = -0.78, steps = 29 01:08:10 [INFO] train episode 15668: reward = 33.23, steps = 51 01:08:10 [INFO] train episode 15669: reward = 11.89, steps = 36 01:08:10 [INFO] train episode 15670: reward = 14.24, steps = 47 01:08:11 [INFO] train episode 15671: reward = 20.03, steps = 42 01:08:11 [INFO] train episode 15672: reward = 18.39, steps = 44 01:08:11 [INFO] train episode 15673: reward = 18.61, steps = 38 01:08:11 [INFO] train episode 15674: reward = -6.82, steps = 28 01:08:12 [INFO] train episode 15675: reward = 8.22, steps = 36 01:08:12 [INFO] train episode 15676: reward = -2.27, steps = 35 01:08:12 [INFO] train episode 15677: reward = 27.30, steps = 46 01:08:12 [INFO] train episode 15678: reward = 4.82, steps = 39 01:08:13 [INFO] train episode 15679: reward = 43.19, steps = 55 01:08:13 [INFO] train episode 15680: reward = -5.51, steps = 35 01:08:13 [INFO] train episode 15681: reward = 1.78, steps = 48 01:08:14 [INFO] train episode 15682: reward = 21.11, steps = 46 01:08:14 [INFO] train episode 15683: reward = 15.04, steps = 36 01:08:14 [INFO] train episode 15684: reward = 33.61, steps = 48 01:08:14 [INFO] train episode 15685: reward = 11.85, steps = 42 01:08:15 [INFO] train episode 15686: reward = 23.69, steps = 40 01:08:15 [INFO] train episode 15687: reward = 32.40, steps = 56 01:08:15 [INFO] train episode 15688: reward = -8.02, steps = 24 01:08:15 [INFO] train episode 15689: reward = 7.22, steps = 29 01:08:16 [INFO] train episode 15690: reward = 0.15, steps = 25 01:08:16 [INFO] train episode 15691: reward = 2.06, steps = 29 01:08:16 [INFO] train episode 15692: reward = -2.97, steps = 29 01:08:16 [INFO] train episode 15693: reward = 21.56, steps = 46 01:08:17 [INFO] train episode 15694: reward = -0.52, steps = 33 01:08:17 [INFO] train episode 15695: reward = -3.05, steps = 31 01:08:17 [INFO] train episode 15696: reward = 11.52, steps = 34 01:08:17 [INFO] train episode 15697: reward = -6.09, steps = 24 01:08:17 [INFO] train episode 15698: reward = 0.11, steps = 29 01:08:17 [INFO] train episode 15699: reward = -11.07, steps = 22 01:08:18 [INFO] train episode 15700: reward = -6.27, steps = 24 01:08:18 [INFO] train episode 15701: reward = 27.37, steps = 46 01:08:18 [INFO] train episode 15702: reward = 15.54, steps = 78 01:08:19 [INFO] train episode 15703: reward = 35.98, steps = 56 01:08:19 [INFO] train episode 15704: reward = -4.62, steps = 28 01:08:19 [INFO] train episode 15705: reward = 20.99, steps = 43 01:08:20 [INFO] train episode 15706: reward = 12.36, steps = 33 01:08:20 [INFO] train episode 15707: reward = 22.51, steps = 53 01:08:20 [INFO] train episode 15708: reward = 15.71, steps = 42 01:08:20 [INFO] train episode 15709: reward = -9.88, steps = 29 01:08:21 [INFO] train episode 15710: reward = -8.97, steps = 21 01:08:21 [INFO] train episode 15711: reward = 11.87, steps = 46 01:08:21 [INFO] train episode 15712: reward = 25.32, steps = 38 01:08:21 [INFO] train episode 15713: reward = 23.26, steps = 48 01:08:22 [INFO] train episode 15714: reward = 3.64, steps = 28 01:08:22 [INFO] train episode 15715: reward = 16.44, steps = 35 01:08:22 [INFO] train episode 15716: reward = 7.30, steps = 46 01:08:22 [INFO] train episode 15717: reward = -2.05, steps = 34 01:08:23 [INFO] train episode 15718: reward = 26.53, steps = 38 01:08:23 [INFO] train episode 15719: reward = 19.40, steps = 47 01:08:24 [INFO] train episode 15720: reward = 4.94, steps = 43 01:08:24 [INFO] train episode 15721: reward = -1.00, steps = 28 01:08:24 [INFO] train episode 15722: reward = 14.44, steps = 40 01:08:24 [INFO] train episode 15723: reward = 1.36, steps = 40 01:08:25 [INFO] train episode 15724: reward = 18.04, steps = 43 01:08:25 [INFO] train episode 15725: reward = 13.61, steps = 37 01:08:25 [INFO] train episode 15726: reward = 2.02, steps = 30 01:08:25 [INFO] train episode 15727: reward = 40.41, steps = 65 01:08:26 [INFO] train episode 15728: reward = 21.16, steps = 65 01:08:26 [INFO] train episode 15729: reward = 12.62, steps = 43 01:08:26 [INFO] train episode 15730: reward = -5.63, steps = 29 01:08:27 [INFO] train episode 15731: reward = 25.10, steps = 45 01:08:27 [INFO] train episode 15732: reward = -6.81, steps = 24 01:08:27 [INFO] train episode 15733: reward = 5.32, steps = 46 01:08:28 [INFO] train episode 15734: reward = -5.30, steps = 78 01:08:28 [INFO] train episode 15735: reward = 12.75, steps = 34 01:08:28 [INFO] train episode 15736: reward = 25.51, steps = 41 01:08:28 [INFO] train episode 15737: reward = 36.51, steps = 61 01:08:29 [INFO] train episode 15738: reward = -0.56, steps = 28 01:08:29 [INFO] train episode 15739: reward = -5.69, steps = 21 01:08:29 [INFO] train episode 15740: reward = -0.18, steps = 29 01:08:29 [INFO] train episode 15741: reward = 7.52, steps = 41 01:08:30 [INFO] train episode 15742: reward = 29.60, steps = 53 01:08:30 [INFO] train episode 15743: reward = 5.92, steps = 38 01:08:31 [INFO] train episode 15744: reward = 29.71, steps = 95 01:08:31 [INFO] train episode 15745: reward = 2.64, steps = 34 01:08:31 [INFO] train episode 15746: reward = 16.87, steps = 38 01:08:31 [INFO] train episode 15747: reward = -5.63, steps = 28 01:08:32 [INFO] train episode 15748: reward = 32.91, steps = 56 01:08:32 [INFO] train episode 15749: reward = -2.25, steps = 25 01:08:32 [INFO] train episode 15750: reward = 13.95, steps = 37 01:08:32 [INFO] train episode 15751: reward = 17.15, steps = 44 01:08:33 [INFO] train episode 15752: reward = 15.70, steps = 47 01:08:33 [INFO] train episode 15753: reward = -6.97, steps = 22 01:08:33 [INFO] train episode 15754: reward = 4.21, steps = 25 01:08:33 [INFO] train episode 15755: reward = 26.14, steps = 49 01:08:34 [INFO] train episode 15756: reward = 15.10, steps = 45 01:08:34 [INFO] train episode 15757: reward = 24.84, steps = 55 01:08:34 [INFO] train episode 15758: reward = -0.00, steps = 30 01:08:34 [INFO] train episode 15759: reward = 12.20, steps = 36 01:08:35 [INFO] train episode 15760: reward = 17.85, steps = 54 01:08:35 [INFO] train episode 15761: reward = 9.32, steps = 39 01:08:35 [INFO] train episode 15762: reward = 4.86, steps = 30 01:08:35 [INFO] train episode 15763: reward = 28.36, steps = 43 01:08:36 [INFO] train episode 15764: reward = -4.83, steps = 21 01:08:36 [INFO] train episode 15765: reward = -0.21, steps = 30 01:08:36 [INFO] train episode 15766: reward = 11.16, steps = 35 01:08:37 [INFO] train episode 15767: reward = -0.90, steps = 26 01:08:37 [INFO] train episode 15768: reward = 25.29, steps = 43 01:08:37 [INFO] train episode 15769: reward = 4.50, steps = 35 01:08:37 [INFO] train episode 15770: reward = -0.42, steps = 33 01:08:38 [INFO] train episode 15771: reward = 23.15, steps = 41 01:08:38 [INFO] train episode 15772: reward = 27.48, steps = 55 01:08:38 [INFO] train episode 15773: reward = 27.95, steps = 39 01:08:38 [INFO] train episode 15774: reward = -5.97, steps = 22 01:08:39 [INFO] train episode 15775: reward = 17.05, steps = 49 01:08:39 [INFO] train episode 15776: reward = 19.05, steps = 43 01:08:39 [INFO] train episode 15777: reward = -10.86, steps = 20 01:08:39 [INFO] train episode 15778: reward = 22.70, steps = 38 01:08:40 [INFO] train episode 15779: reward = 0.28, steps = 32 01:08:40 [INFO] train episode 15780: reward = 3.51, steps = 39 01:08:40 [INFO] train episode 15781: reward = -12.41, steps = 22 01:08:40 [INFO] train episode 15782: reward = 3.76, steps = 36 01:08:40 [INFO] train episode 15783: reward = -9.16, steps = 23 01:08:41 [INFO] train episode 15784: reward = -4.43, steps = 26 01:08:41 [INFO] train episode 15785: reward = 21.43, steps = 51 01:08:41 [INFO] train episode 15786: reward = 2.57, steps = 29 01:08:42 [INFO] train episode 15787: reward = 32.68, steps = 53 01:08:42 [INFO] train episode 15788: reward = 34.92, steps = 57 01:08:42 [INFO] train episode 15789: reward = 7.06, steps = 34 01:08:43 [INFO] train episode 15790: reward = -9.63, steps = 23 01:08:43 [INFO] train episode 15791: reward = 18.82, steps = 37 01:08:43 [INFO] train episode 15792: reward = 26.95, steps = 53 01:08:43 [INFO] train episode 15793: reward = -5.48, steps = 32 01:08:44 [INFO] train episode 15794: reward = 38.99, steps = 56 01:08:44 [INFO] train episode 15795: reward = 35.66, steps = 56 01:08:45 [INFO] train episode 15796: reward = 29.91, steps = 45 01:08:45 [INFO] train episode 15797: reward = 32.83, steps = 48 01:08:45 [INFO] train episode 15798: reward = -5.37, steps = 27 01:08:46 [INFO] train episode 15799: reward = 14.19, steps = 53 01:08:46 [INFO] train episode 15800: reward = 8.28, steps = 36 01:08:47 [INFO] train episode 15801: reward = 22.41, steps = 51 01:08:47 [INFO] train episode 15802: reward = -8.90, steps = 20 01:08:47 [INFO] train episode 15803: reward = 24.73, steps = 41 01:08:48 [INFO] train episode 15804: reward = 42.32, steps = 56 01:08:49 [INFO] train episode 15805: reward = 28.66, steps = 54 01:08:49 [INFO] train episode 15806: reward = 14.40, steps = 37 01:08:49 [INFO] train episode 15807: reward = 37.20, steps = 66 01:08:50 [INFO] train episode 15808: reward = 0.22, steps = 26 01:08:50 [INFO] train episode 15809: reward = 15.10, steps = 35 01:08:50 [INFO] train episode 15810: reward = 3.69, steps = 32 01:08:50 [INFO] train episode 15811: reward = 5.70, steps = 38 01:08:51 [INFO] train episode 15812: reward = 2.95, steps = 25 01:08:51 [INFO] train episode 15813: reward = 12.62, steps = 42 01:08:51 [INFO] train episode 15814: reward = 38.03, steps = 71 01:08:52 [INFO] train episode 15815: reward = 22.68, steps = 39 01:08:52 [INFO] train episode 15816: reward = 4.69, steps = 49 01:08:53 [INFO] train episode 15817: reward = 25.99, steps = 54 01:08:53 [INFO] train episode 15818: reward = -9.19, steps = 31 01:08:53 [INFO] train episode 15819: reward = -6.99, steps = 22 01:08:53 [INFO] train episode 15820: reward = 19.14, steps = 37 01:08:53 [INFO] train episode 15821: reward = 20.86, steps = 38 01:08:54 [INFO] train episode 15822: reward = 2.35, steps = 30 01:08:54 [INFO] train episode 15823: reward = -5.28, steps = 31 01:08:54 [INFO] train episode 15824: reward = 28.16, steps = 47 01:08:54 [INFO] train episode 15825: reward = 8.05, steps = 38 01:08:55 [INFO] train episode 15826: reward = 21.88, steps = 40 01:08:55 [INFO] train episode 15827: reward = 18.65, steps = 40 01:08:55 [INFO] train episode 15828: reward = -4.70, steps = 20 01:08:55 [INFO] train episode 15829: reward = 11.16, steps = 35 01:08:56 [INFO] train episode 15830: reward = 39.86, steps = 55 01:08:56 [INFO] train episode 15831: reward = 6.25, steps = 34 01:08:56 [INFO] train episode 15832: reward = 25.48, steps = 38 01:08:56 [INFO] train episode 15833: reward = -4.19, steps = 25 01:08:57 [INFO] train episode 15834: reward = -1.43, steps = 26 01:08:57 [INFO] train episode 15835: reward = 11.24, steps = 32 01:08:57 [INFO] train episode 15836: reward = -4.55, steps = 27 01:08:57 [INFO] train episode 15837: reward = -8.28, steps = 26 01:08:58 [INFO] train episode 15838: reward = 15.97, steps = 41 01:08:58 [INFO] train episode 15839: reward = 23.32, steps = 49 01:08:58 [INFO] train episode 15840: reward = 33.66, steps = 61 01:08:59 [INFO] train episode 15841: reward = 27.39, steps = 41 01:08:59 [INFO] train episode 15842: reward = -11.14, steps = 24 01:08:59 [INFO] train episode 15843: reward = 35.78, steps = 59 01:08:59 [INFO] train episode 15844: reward = -4.83, steps = 27 01:09:00 [INFO] train episode 15845: reward = 30.76, steps = 47 01:09:00 [INFO] train episode 15846: reward = 23.10, steps = 52 01:09:00 [INFO] train episode 15847: reward = 3.32, steps = 33 01:09:01 [INFO] train episode 15848: reward = 33.63, steps = 55 01:09:01 [INFO] train episode 15849: reward = 10.21, steps = 33 01:09:01 [INFO] train episode 15850: reward = 27.25, steps = 50 01:09:01 [INFO] train episode 15851: reward = 6.12, steps = 35 01:09:02 [INFO] train episode 15852: reward = 8.53, steps = 36 01:09:02 [INFO] train episode 15853: reward = 15.76, steps = 39 01:09:02 [INFO] train episode 15854: reward = 24.72, steps = 44 01:09:02 [INFO] train episode 15855: reward = -5.64, steps = 25 01:09:03 [INFO] train episode 15856: reward = 20.97, steps = 40 01:09:03 [INFO] train episode 15857: reward = -1.62, steps = 26 01:09:03 [INFO] train episode 15858: reward = 17.24, steps = 55 01:09:04 [INFO] train episode 15859: reward = 15.64, steps = 38 01:09:04 [INFO] train episode 15860: reward = -6.12, steps = 24 01:09:04 [INFO] train episode 15861: reward = -3.17, steps = 33 01:09:04 [INFO] train episode 15862: reward = 23.87, steps = 48 01:09:05 [INFO] train episode 15863: reward = 6.51, steps = 32 01:09:05 [INFO] train episode 15864: reward = -7.49, steps = 22 01:09:05 [INFO] train episode 15865: reward = 18.73, steps = 36 01:09:05 [INFO] train episode 15866: reward = 21.39, steps = 40 01:09:06 [INFO] train episode 15867: reward = 41.70, steps = 63 01:09:06 [INFO] train episode 15868: reward = 8.74, steps = 54 01:09:07 [INFO] train episode 15869: reward = 33.47, steps = 45 01:09:07 [INFO] train episode 15870: reward = 23.47, steps = 42 01:09:07 [INFO] train episode 15871: reward = 12.67, steps = 44 01:09:07 [INFO] train episode 15872: reward = -6.24, steps = 25 01:09:08 [INFO] train episode 15873: reward = 22.34, steps = 47 01:09:08 [INFO] train episode 15874: reward = 32.02, steps = 51 01:09:08 [INFO] train episode 15875: reward = 4.73, steps = 33 01:09:09 [INFO] train episode 15876: reward = 13.35, steps = 36 01:09:09 [INFO] train episode 15877: reward = -6.92, steps = 24 01:09:09 [INFO] train episode 15878: reward = 20.46, steps = 41 01:09:09 [INFO] train episode 15879: reward = -0.76, steps = 30 01:09:09 [INFO] train episode 15880: reward = -8.27, steps = 25 01:09:10 [INFO] train episode 15881: reward = 23.75, steps = 57 01:09:10 [INFO] train episode 15882: reward = 5.04, steps = 36 01:09:10 [INFO] train episode 15883: reward = 1.26, steps = 30 01:09:10 [INFO] train episode 15884: reward = 4.64, steps = 26 01:09:11 [INFO] train episode 15885: reward = 9.73, steps = 45 01:09:11 [INFO] train episode 15886: reward = 0.16, steps = 34 01:09:11 [INFO] train episode 15887: reward = 0.35, steps = 32 01:09:12 [INFO] train episode 15888: reward = 35.04, steps = 48 01:09:12 [INFO] train episode 15889: reward = -3.99, steps = 24 01:09:12 [INFO] train episode 15890: reward = -1.27, steps = 40 01:09:12 [INFO] train episode 15891: reward = 23.88, steps = 42 01:09:12 [INFO] train episode 15892: reward = -4.48, steps = 22 01:09:13 [INFO] train episode 15893: reward = -2.92, steps = 28 01:09:13 [INFO] train episode 15894: reward = -22.87, steps = 56 01:09:13 [INFO] train episode 15895: reward = 3.90, steps = 34 01:09:13 [INFO] train episode 15896: reward = -6.35, steps = 32 01:09:14 [INFO] train episode 15897: reward = 37.53, steps = 74 01:09:14 [INFO] train episode 15898: reward = 5.24, steps = 31 01:09:14 [INFO] train episode 15899: reward = 0.48, steps = 30 01:09:14 [INFO] train episode 15900: reward = -2.14, steps = 21 01:09:15 [INFO] train episode 15901: reward = 42.30, steps = 65 01:09:15 [INFO] train episode 15902: reward = -1.05, steps = 26 01:09:15 [INFO] train episode 15903: reward = 31.99, steps = 47 01:09:16 [INFO] train episode 15904: reward = -0.23, steps = 34 01:09:16 [INFO] train episode 15905: reward = -7.92, steps = 24 01:09:16 [INFO] train episode 15906: reward = 10.97, steps = 38 01:09:16 [INFO] train episode 15907: reward = -10.76, steps = 25 01:09:16 [INFO] train episode 15908: reward = -4.66, steps = 20 01:09:17 [INFO] train episode 15909: reward = -9.52, steps = 23 01:09:17 [INFO] train episode 15910: reward = 28.60, steps = 43 01:09:17 [INFO] train episode 15911: reward = 16.18, steps = 34 01:09:17 [INFO] train episode 15912: reward = 5.90, steps = 38 01:09:18 [INFO] train episode 15913: reward = 19.74, steps = 39 01:09:18 [INFO] train episode 15914: reward = 20.40, steps = 44 01:09:18 [INFO] train episode 15915: reward = 5.81, steps = 34 01:09:18 [INFO] train episode 15916: reward = 38.43, steps = 53 01:09:19 [INFO] train episode 15917: reward = 28.45, steps = 44 01:09:19 [INFO] train episode 15918: reward = -0.72, steps = 35 01:09:19 [INFO] train episode 15919: reward = 2.31, steps = 24 01:09:19 [INFO] train episode 15920: reward = 19.37, steps = 43 01:09:20 [INFO] train episode 15921: reward = 0.75, steps = 31 01:09:20 [INFO] train episode 15922: reward = 3.45, steps = 32 01:09:21 [INFO] train episode 15923: reward = 33.35, steps = 53 01:09:21 [INFO] train episode 15924: reward = 22.91, steps = 41 01:09:21 [INFO] train episode 15925: reward = -3.36, steps = 26 01:09:21 [INFO] train episode 15926: reward = 17.94, steps = 37 01:09:21 [INFO] train episode 15927: reward = 0.40, steps = 21 01:09:22 [INFO] train episode 15928: reward = 26.80, steps = 46 01:09:22 [INFO] train episode 15929: reward = 0.65, steps = 31 01:09:22 [INFO] train episode 15930: reward = 19.19, steps = 47 01:09:22 [INFO] train episode 15931: reward = -9.27, steps = 30 01:09:23 [INFO] train episode 15932: reward = -0.04, steps = 28 01:09:23 [INFO] train episode 15933: reward = 13.43, steps = 40 01:09:23 [INFO] train episode 15934: reward = 15.38, steps = 46 01:09:24 [INFO] train episode 15935: reward = 21.64, steps = 42 01:09:24 [INFO] train episode 15936: reward = 12.79, steps = 45 01:09:24 [INFO] train episode 15937: reward = -4.00, steps = 21 01:09:24 [INFO] train episode 15938: reward = 30.01, steps = 52 01:09:25 [INFO] train episode 15939: reward = 27.77, steps = 58 01:09:25 [INFO] train episode 15940: reward = 36.21, steps = 48 01:09:25 [INFO] train episode 15941: reward = 39.45, steps = 59 01:09:26 [INFO] train episode 15942: reward = 25.97, steps = 38 01:09:26 [INFO] train episode 15943: reward = 18.69, steps = 41 01:09:26 [INFO] train episode 15944: reward = 28.28, steps = 59 01:09:27 [INFO] train episode 15945: reward = -7.35, steps = 25 01:09:27 [INFO] train episode 15946: reward = 27.29, steps = 44 01:09:27 [INFO] train episode 15947: reward = 4.37, steps = 31 01:09:27 [INFO] train episode 15948: reward = 22.65, steps = 38 01:09:27 [INFO] train episode 15949: reward = -0.71, steps = 26 01:09:28 [INFO] train episode 15950: reward = 9.41, steps = 31 01:09:28 [INFO] train episode 15951: reward = 54.43, steps = 71 01:09:28 [INFO] train episode 15952: reward = 22.35, steps = 41 01:09:29 [INFO] train episode 15953: reward = 8.80, steps = 35 01:09:29 [INFO] train episode 15954: reward = 33.78, steps = 46 01:09:29 [INFO] train episode 15955: reward = 11.56, steps = 34 01:09:29 [INFO] train episode 15956: reward = 6.27, steps = 29 01:09:30 [INFO] train episode 15957: reward = 12.78, steps = 38 01:09:30 [INFO] train episode 15958: reward = 19.03, steps = 40 01:09:30 [INFO] train episode 15959: reward = 6.22, steps = 43 01:09:30 [INFO] train episode 15960: reward = -5.91, steps = 27 01:09:31 [INFO] train episode 15961: reward = 3.96, steps = 29 01:09:31 [INFO] train episode 15962: reward = 31.67, steps = 60 01:09:31 [INFO] train episode 15963: reward = -9.14, steps = 23 01:09:32 [INFO] train episode 15964: reward = 32.13, steps = 60 01:09:32 [INFO] train episode 15965: reward = 5.00, steps = 35 01:09:32 [INFO] train episode 15966: reward = -7.07, steps = 21 01:09:32 [INFO] train episode 15967: reward = 12.67, steps = 34 01:09:32 [INFO] train episode 15968: reward = 14.46, steps = 37 01:09:33 [INFO] train episode 15969: reward = 28.02, steps = 46 01:09:33 [INFO] train episode 15970: reward = 17.71, steps = 50 01:09:34 [INFO] train episode 15971: reward = 22.49, steps = 48 01:09:34 [INFO] train episode 15972: reward = -2.20, steps = 22 01:09:34 [INFO] train episode 15973: reward = 32.62, steps = 55 01:09:34 [INFO] train episode 15974: reward = 26.04, steps = 39 01:09:35 [INFO] train episode 15975: reward = 17.63, steps = 50 01:09:35 [INFO] train episode 15976: reward = 20.39, steps = 40 01:09:35 [INFO] train episode 15977: reward = -2.87, steps = 30 01:09:36 [INFO] train episode 15978: reward = 10.44, steps = 39 01:09:36 [INFO] train episode 15979: reward = -0.94, steps = 26 01:09:36 [INFO] train episode 15980: reward = 1.60, steps = 33 01:09:36 [INFO] train episode 15981: reward = 12.01, steps = 44 01:09:37 [INFO] train episode 15982: reward = 37.96, steps = 52 01:09:37 [INFO] train episode 15983: reward = 19.95, steps = 37 01:09:37 [INFO] train episode 15984: reward = 30.12, steps = 39 01:09:37 [INFO] train episode 15985: reward = 30.33, steps = 64 01:09:38 [INFO] train episode 15986: reward = 32.12, steps = 41 01:09:38 [INFO] train episode 15987: reward = 54.95, steps = 88 01:09:39 [INFO] train episode 15988: reward = 20.92, steps = 39 01:09:39 [INFO] train episode 15989: reward = 0.26, steps = 31 01:09:39 [INFO] train episode 15990: reward = -3.32, steps = 30 01:09:39 [INFO] train episode 15991: reward = -6.93, steps = 23 01:09:39 [INFO] train episode 15992: reward = 23.74, steps = 41 01:09:40 [INFO] train episode 15993: reward = -12.07, steps = 24 01:09:40 [INFO] train episode 15994: reward = 1.84, steps = 33 01:09:40 [INFO] train episode 15995: reward = 13.93, steps = 32 01:09:40 [INFO] train episode 15996: reward = 28.18, steps = 46 01:09:41 [INFO] train episode 15997: reward = -5.00, steps = 35 01:09:41 [INFO] train episode 15998: reward = -3.33, steps = 37 01:09:41 [INFO] train episode 15999: reward = 8.54, steps = 35 01:09:41 [INFO] train episode 16000: reward = 7.98, steps = 32 01:09:42 [INFO] train episode 16001: reward = 36.80, steps = 55 01:09:42 [INFO] train episode 16002: reward = 19.60, steps = 40 01:09:42 [INFO] train episode 16003: reward = 36.08, steps = 51 01:09:42 [INFO] train episode 16004: reward = -4.32, steps = 27 01:09:43 [INFO] train episode 16005: reward = 10.41, steps = 60 01:09:43 [INFO] train episode 16006: reward = 37.15, steps = 62 01:09:44 [INFO] train episode 16007: reward = 29.00, steps = 66 01:09:44 [INFO] train episode 16008: reward = 22.51, steps = 50 01:09:44 [INFO] train episode 16009: reward = 35.38, steps = 49 01:09:45 [INFO] train episode 16010: reward = 31.67, steps = 51 01:09:45 [INFO] train episode 16011: reward = 23.97, steps = 51 01:09:45 [INFO] train episode 16012: reward = -0.43, steps = 25 01:09:45 [INFO] train episode 16013: reward = -7.32, steps = 23 01:09:46 [INFO] train episode 16014: reward = -7.02, steps = 20 01:09:46 [INFO] train episode 16015: reward = -5.29, steps = 21 01:09:46 [INFO] train episode 16016: reward = 23.80, steps = 46 01:09:46 [INFO] train episode 16017: reward = 11.91, steps = 34 01:09:47 [INFO] train episode 16018: reward = 15.25, steps = 44 01:09:47 [INFO] train episode 16019: reward = 24.88, steps = 42 01:09:48 [INFO] train episode 16020: reward = 31.45, steps = 56 01:09:48 [INFO] train episode 16021: reward = 22.43, steps = 48 01:09:48 [INFO] train episode 16022: reward = 18.87, steps = 38 01:09:48 [INFO] train episode 16023: reward = 33.29, steps = 39 01:09:49 [INFO] train episode 16024: reward = 10.82, steps = 33 01:09:49 [INFO] train episode 16025: reward = 34.24, steps = 44 01:09:49 [INFO] train episode 16026: reward = -6.03, steps = 31 01:09:49 [INFO] train episode 16027: reward = 19.33, steps = 39 01:09:50 [INFO] train episode 16028: reward = 37.96, steps = 52 01:09:50 [INFO] train episode 16029: reward = 31.00, steps = 45 01:09:50 [INFO] train episode 16030: reward = 43.82, steps = 58 01:09:51 [INFO] train episode 16031: reward = 45.77, steps = 59 01:09:51 [INFO] train episode 16032: reward = 39.27, steps = 57 01:09:51 [INFO] train episode 16033: reward = 18.99, steps = 47 01:09:52 [INFO] train episode 16034: reward = 35.33, steps = 48 01:09:52 [INFO] train episode 16035: reward = -2.46, steps = 27 01:09:52 [INFO] train episode 16036: reward = 0.96, steps = 26 01:09:52 [INFO] train episode 16037: reward = -5.67, steps = 22 01:09:53 [INFO] train episode 16038: reward = 28.94, steps = 42 01:09:53 [INFO] train episode 16039: reward = -21.95, steps = 19 01:09:53 [INFO] train episode 16040: reward = -0.73, steps = 25 01:09:53 [INFO] train episode 16041: reward = -13.53, steps = 25 01:09:53 [INFO] train episode 16042: reward = 41.62, steps = 47 01:09:54 [INFO] train episode 16043: reward = 49.57, steps = 76 01:09:54 [INFO] train episode 16044: reward = 6.11, steps = 26 01:09:54 [INFO] train episode 16045: reward = 16.32, steps = 36 01:09:55 [INFO] train episode 16046: reward = 10.58, steps = 35 01:09:55 [INFO] train episode 16047: reward = 36.49, steps = 58 01:09:55 [INFO] train episode 16048: reward = -6.29, steps = 22 01:09:55 [INFO] train episode 16049: reward = 4.60, steps = 28 01:09:56 [INFO] train episode 16050: reward = 8.40, steps = 29 01:09:56 [INFO] train episode 16051: reward = 14.82, steps = 53 01:09:56 [INFO] train episode 16052: reward = 23.11, steps = 37 01:09:56 [INFO] train episode 16053: reward = 14.13, steps = 38 01:09:57 [INFO] train episode 16054: reward = 5.48, steps = 31 01:09:57 [INFO] train episode 16055: reward = -8.64, steps = 22 01:09:57 [INFO] train episode 16056: reward = -3.32, steps = 26 01:09:57 [INFO] train episode 16057: reward = 17.75, steps = 48 01:09:58 [INFO] train episode 16058: reward = 18.57, steps = 53 01:09:58 [INFO] train episode 16059: reward = 39.31, steps = 57 01:09:58 [INFO] train episode 16060: reward = 21.46, steps = 55 01:09:58 [INFO] train episode 16061: reward = -8.72, steps = 23 01:09:59 [INFO] train episode 16062: reward = -6.52, steps = 24 01:09:59 [INFO] train episode 16063: reward = 12.35, steps = 32 01:09:59 [INFO] train episode 16064: reward = 21.55, steps = 42 01:09:59 [INFO] train episode 16065: reward = 1.89, steps = 26 01:10:00 [INFO] train episode 16066: reward = 33.49, steps = 45 01:10:00 [INFO] train episode 16067: reward = 2.97, steps = 29 01:10:00 [INFO] train episode 16068: reward = -6.86, steps = 32 01:10:01 [INFO] train episode 16069: reward = 21.75, steps = 42 01:10:01 [INFO] train episode 16070: reward = -16.14, steps = 27 01:10:01 [INFO] train episode 16071: reward = -7.06, steps = 33 01:10:01 [INFO] train episode 16072: reward = 18.29, steps = 40 01:10:01 [INFO] train episode 16073: reward = 4.44, steps = 29 01:10:02 [INFO] train episode 16074: reward = 20.76, steps = 43 01:10:02 [INFO] train episode 16075: reward = 25.12, steps = 43 01:10:02 [INFO] train episode 16076: reward = 44.46, steps = 48 01:10:03 [INFO] train episode 16077: reward = 17.23, steps = 43 01:10:03 [INFO] train episode 16078: reward = 53.50, steps = 74 01:10:03 [INFO] train episode 16079: reward = 3.26, steps = 28 01:10:03 [INFO] train episode 16080: reward = 8.48, steps = 36 01:10:04 [INFO] train episode 16081: reward = 44.30, steps = 63 01:10:04 [INFO] train episode 16082: reward = 7.24, steps = 32 01:10:04 [INFO] train episode 16083: reward = 4.07, steps = 30 01:10:04 [INFO] train episode 16084: reward = 10.98, steps = 33 01:10:05 [INFO] train episode 16085: reward = 39.31, steps = 45 01:10:05 [INFO] train episode 16086: reward = -4.50, steps = 28 01:10:05 [INFO] train episode 16087: reward = 14.63, steps = 35 01:10:06 [INFO] train episode 16088: reward = 24.73, steps = 44 01:10:06 [INFO] train episode 16089: reward = 18.81, steps = 38 01:10:06 [INFO] train episode 16090: reward = 30.48, steps = 50 01:10:06 [INFO] train episode 16091: reward = 30.51, steps = 51 01:10:07 [INFO] train episode 16092: reward = -8.43, steps = 23 01:10:07 [INFO] train episode 16093: reward = 3.04, steps = 28 01:10:07 [INFO] train episode 16094: reward = 20.72, steps = 54 01:10:07 [INFO] train episode 16095: reward = 27.95, steps = 45 01:10:08 [INFO] train episode 16096: reward = 13.61, steps = 40 01:10:08 [INFO] train episode 16097: reward = 14.16, steps = 39 01:10:08 [INFO] train episode 16098: reward = -7.57, steps = 27 01:10:08 [INFO] train episode 16099: reward = -0.94, steps = 26 01:10:09 [INFO] train episode 16100: reward = 51.03, steps = 82 01:10:09 [INFO] train episode 16101: reward = -1.40, steps = 31 01:10:09 [INFO] train episode 16102: reward = 28.04, steps = 54 01:10:10 [INFO] train episode 16103: reward = 16.18, steps = 59 01:10:10 [INFO] train episode 16104: reward = 45.53, steps = 56 01:10:10 [INFO] train episode 16105: reward = 39.41, steps = 46 01:10:11 [INFO] train episode 16106: reward = 3.07, steps = 37 01:10:11 [INFO] train episode 16107: reward = -8.65, steps = 36 01:10:11 [INFO] train episode 16108: reward = -2.75, steps = 23 01:10:11 [INFO] train episode 16109: reward = 9.04, steps = 36 01:10:12 [INFO] train episode 16110: reward = 33.69, steps = 48 01:10:12 [INFO] train episode 16111: reward = 23.21, steps = 42 01:10:12 [INFO] train episode 16112: reward = 14.10, steps = 31 01:10:12 [INFO] train episode 16113: reward = -0.14, steps = 24 01:10:13 [INFO] train episode 16114: reward = 5.82, steps = 27 01:10:13 [INFO] train episode 16115: reward = 22.49, steps = 38 01:10:13 [INFO] train episode 16116: reward = -6.47, steps = 22 01:10:13 [INFO] train episode 16117: reward = 20.80, steps = 42 01:10:13 [INFO] train episode 16118: reward = 1.17, steps = 28 01:10:14 [INFO] train episode 16119: reward = 19.06, steps = 44 01:10:14 [INFO] train episode 16120: reward = 30.89, steps = 45 01:10:15 [INFO] train episode 16121: reward = 11.98, steps = 36 01:10:15 [INFO] train episode 16122: reward = 0.28, steps = 33 01:10:15 [INFO] train episode 16123: reward = 22.43, steps = 45 01:10:15 [INFO] train episode 16124: reward = 36.35, steps = 58 01:10:16 [INFO] train episode 16125: reward = 10.86, steps = 34 01:10:16 [INFO] train episode 16126: reward = -6.53, steps = 21 01:10:16 [INFO] train episode 16127: reward = 32.27, steps = 43 01:10:16 [INFO] train episode 16128: reward = 33.62, steps = 45 01:10:17 [INFO] train episode 16129: reward = 19.24, steps = 40 01:10:17 [INFO] train episode 16130: reward = 21.24, steps = 42 01:10:17 [INFO] train episode 16131: reward = 29.36, steps = 44 01:10:18 [INFO] train episode 16132: reward = 26.63, steps = 48 01:10:18 [INFO] train episode 16133: reward = 36.36, steps = 54 01:10:18 [INFO] train episode 16134: reward = -2.34, steps = 34 01:10:19 [INFO] train episode 16135: reward = 23.08, steps = 39 01:10:19 [INFO] train episode 16136: reward = 34.06, steps = 49 01:10:19 [INFO] train episode 16137: reward = 45.47, steps = 52 01:10:20 [INFO] train episode 16138: reward = -2.15, steps = 45 01:10:20 [INFO] train episode 16139: reward = 26.13, steps = 45 01:10:20 [INFO] train episode 16140: reward = -3.76, steps = 27 01:10:20 [INFO] train episode 16141: reward = 21.98, steps = 41 01:10:21 [INFO] train episode 16142: reward = 15.68, steps = 39 01:10:21 [INFO] train episode 16143: reward = 4.36, steps = 32 01:10:21 [INFO] train episode 16144: reward = -1.64, steps = 34 01:10:21 [INFO] train episode 16145: reward = 0.99, steps = 30 01:10:22 [INFO] train episode 16146: reward = 19.55, steps = 39 01:10:22 [INFO] train episode 16147: reward = 24.59, steps = 43 01:10:22 [INFO] train episode 16148: reward = 27.36, steps = 52 01:10:22 [INFO] train episode 16149: reward = -2.24, steps = 23 01:10:23 [INFO] train episode 16150: reward = 32.95, steps = 46 01:10:23 [INFO] train episode 16151: reward = -6.95, steps = 21 01:10:23 [INFO] train episode 16152: reward = 32.83, steps = 49 01:10:23 [INFO] train episode 16153: reward = 19.05, steps = 40 01:10:24 [INFO] train episode 16154: reward = 8.87, steps = 34 01:10:24 [INFO] train episode 16155: reward = -2.46, steps = 22 01:10:24 [INFO] train episode 16156: reward = 21.56, steps = 43 01:10:24 [INFO] train episode 16157: reward = 13.50, steps = 33 01:10:24 [INFO] train episode 16158: reward = -11.61, steps = 25 01:10:25 [INFO] train episode 16159: reward = 17.32, steps = 35 01:10:25 [INFO] train episode 16160: reward = 28.27, steps = 41 01:10:25 [INFO] train episode 16161: reward = 0.23, steps = 29 01:10:25 [INFO] train episode 16162: reward = -3.42, steps = 27 01:10:26 [INFO] train episode 16163: reward = 32.01, steps = 51 01:10:26 [INFO] train episode 16164: reward = 10.86, steps = 39 01:10:26 [INFO] train episode 16165: reward = 0.11, steps = 81 01:10:27 [INFO] train episode 16166: reward = 2.44, steps = 27 01:10:27 [INFO] train episode 16167: reward = 13.19, steps = 32 01:10:27 [INFO] train episode 16168: reward = 31.79, steps = 39 01:10:28 [INFO] train episode 16169: reward = 38.59, steps = 51 01:10:28 [INFO] train episode 16170: reward = 12.13, steps = 38 01:10:28 [INFO] train episode 16171: reward = 3.74, steps = 28 01:10:28 [INFO] train episode 16172: reward = 27.94, steps = 44 01:10:29 [INFO] train episode 16173: reward = 15.91, steps = 32 01:10:29 [INFO] train episode 16174: reward = 29.63, steps = 48 01:10:29 [INFO] train episode 16175: reward = 18.99, steps = 41 01:10:30 [INFO] train episode 16176: reward = 19.05, steps = 41 01:10:30 [INFO] train episode 16177: reward = 11.43, steps = 38 01:10:30 [INFO] train episode 16178: reward = -2.25, steps = 23 01:10:30 [INFO] train episode 16179: reward = 8.53, steps = 34 01:10:31 [INFO] train episode 16180: reward = -1.82, steps = 72 01:10:31 [INFO] train episode 16181: reward = 3.67, steps = 32 01:10:31 [INFO] train episode 16182: reward = 5.81, steps = 34 01:10:31 [INFO] train episode 16183: reward = 18.09, steps = 40 01:10:32 [INFO] train episode 16184: reward = 5.68, steps = 31 01:10:32 [INFO] train episode 16185: reward = -11.40, steps = 22 01:10:32 [INFO] train episode 16186: reward = 16.64, steps = 38 01:10:32 [INFO] train episode 16187: reward = 0.37, steps = 25 01:10:33 [INFO] train episode 16188: reward = 51.42, steps = 61 01:10:33 [INFO] train episode 16189: reward = 4.89, steps = 30 01:10:33 [INFO] train episode 16190: reward = 34.27, steps = 50 01:10:34 [INFO] train episode 16191: reward = 23.58, steps = 44 01:10:34 [INFO] train episode 16192: reward = -0.75, steps = 29 01:10:34 [INFO] train episode 16193: reward = 36.08, steps = 58 01:10:34 [INFO] train episode 16194: reward = 9.91, steps = 35 01:10:35 [INFO] train episode 16195: reward = -13.31, steps = 23 01:10:35 [INFO] train episode 16196: reward = 24.89, steps = 62 01:10:35 [INFO] train episode 16197: reward = 4.10, steps = 32 01:10:36 [INFO] train episode 16198: reward = 34.62, steps = 51 01:10:36 [INFO] train episode 16199: reward = 20.91, steps = 46 01:10:36 [INFO] train episode 16200: reward = 3.91, steps = 28 01:10:36 [INFO] train episode 16201: reward = 34.17, steps = 46 01:10:37 [INFO] train episode 16202: reward = -1.29, steps = 29 01:10:37 [INFO] train episode 16203: reward = 18.44, steps = 39 01:10:37 [INFO] train episode 16204: reward = 36.90, steps = 60 01:10:37 [INFO] train episode 16205: reward = 33.24, steps = 48 01:10:38 [INFO] train episode 16206: reward = 25.81, steps = 46 01:10:38 [INFO] train episode 16207: reward = 16.99, steps = 40 01:10:38 [INFO] train episode 16208: reward = 3.62, steps = 27 01:10:39 [INFO] train episode 16209: reward = 21.87, steps = 43 01:10:39 [INFO] train episode 16210: reward = -8.90, steps = 25 01:10:39 [INFO] train episode 16211: reward = 22.63, steps = 37 01:10:39 [INFO] train episode 16212: reward = 28.53, steps = 44 01:10:40 [INFO] train episode 16213: reward = 52.71, steps = 80 01:10:40 [INFO] train episode 16214: reward = -4.50, steps = 25 01:10:40 [INFO] train episode 16215: reward = -12.90, steps = 20 01:10:40 [INFO] train episode 16216: reward = 5.54, steps = 33 01:10:41 [INFO] train episode 16217: reward = 2.00, steps = 33 01:10:41 [INFO] train episode 16218: reward = 7.95, steps = 42 01:10:41 [INFO] train episode 16219: reward = 24.81, steps = 36 01:10:42 [INFO] train episode 16220: reward = -13.73, steps = 43 01:10:42 [INFO] train episode 16221: reward = 9.27, steps = 35 01:10:42 [INFO] train episode 16222: reward = 8.24, steps = 42 01:10:42 [INFO] train episode 16223: reward = -6.49, steps = 22 01:10:43 [INFO] train episode 16224: reward = 4.56, steps = 33 01:10:43 [INFO] train episode 16225: reward = 29.59, steps = 38 01:10:43 [INFO] train episode 16226: reward = 14.10, steps = 38 01:10:43 [INFO] train episode 16227: reward = 41.23, steps = 52 01:10:44 [INFO] train episode 16228: reward = 20.53, steps = 40 01:10:44 [INFO] train episode 16229: reward = 5.53, steps = 31 01:10:44 [INFO] train episode 16230: reward = 28.79, steps = 50 01:10:44 [INFO] train episode 16231: reward = 2.63, steps = 25 01:10:45 [INFO] train episode 16232: reward = 26.06, steps = 37 01:10:45 [INFO] train episode 16233: reward = -4.50, steps = 26 01:10:45 [INFO] train episode 16234: reward = 20.62, steps = 34 01:10:45 [INFO] train episode 16235: reward = 37.18, steps = 49 01:10:46 [INFO] train episode 16236: reward = 23.41, steps = 37 01:10:46 [INFO] train episode 16237: reward = 53.54, steps = 67 01:10:46 [INFO] train episode 16238: reward = 39.10, steps = 56 01:10:47 [INFO] train episode 16239: reward = -6.34, steps = 36 01:10:47 [INFO] train episode 16240: reward = 10.33, steps = 28 01:10:47 [INFO] train episode 16241: reward = 0.89, steps = 25 01:10:47 [INFO] train episode 16242: reward = 9.25, steps = 34 01:10:48 [INFO] train episode 16243: reward = 40.94, steps = 51 01:10:48 [INFO] train episode 16244: reward = 32.67, steps = 43 01:10:48 [INFO] train episode 16245: reward = 23.95, steps = 43 01:10:48 [INFO] train episode 16246: reward = -2.67, steps = 21 01:10:49 [INFO] train episode 16247: reward = 28.20, steps = 40 01:10:49 [INFO] train episode 16248: reward = -6.24, steps = 24 01:10:49 [INFO] train episode 16249: reward = 26.84, steps = 47 01:10:49 [INFO] train episode 16250: reward = 15.79, steps = 33 01:10:50 [INFO] train episode 16251: reward = -6.27, steps = 25 01:10:50 [INFO] train episode 16252: reward = 32.13, steps = 43 01:10:50 [INFO] train episode 16253: reward = 30.42, steps = 44 01:10:50 [INFO] train episode 16254: reward = 45.24, steps = 54 01:10:51 [INFO] train episode 16255: reward = 31.86, steps = 50 01:10:51 [INFO] train episode 16256: reward = 29.43, steps = 41 01:10:51 [INFO] train episode 16257: reward = 10.90, steps = 41 01:10:52 [INFO] train episode 16258: reward = 24.22, steps = 38 01:10:52 [INFO] train episode 16259: reward = -5.04, steps = 23 01:10:52 [INFO] train episode 16260: reward = 9.61, steps = 32 01:10:52 [INFO] train episode 16261: reward = -4.34, steps = 28 01:10:53 [INFO] train episode 16262: reward = 52.35, steps = 61 01:10:53 [INFO] train episode 16263: reward = 13.24, steps = 46 01:10:53 [INFO] train episode 16264: reward = 20.53, steps = 37 01:10:53 [INFO] train episode 16265: reward = -0.52, steps = 27 01:10:54 [INFO] train episode 16266: reward = 38.52, steps = 48 01:10:54 [INFO] train episode 16267: reward = 5.59, steps = 32 01:10:54 [INFO] train episode 16268: reward = 26.81, steps = 52 01:10:54 [INFO] train episode 16269: reward = -7.16, steps = 23 01:10:55 [INFO] train episode 16270: reward = 41.54, steps = 60 01:10:55 [INFO] train episode 16271: reward = -4.37, steps = 31 01:10:56 [INFO] train episode 16272: reward = 47.01, steps = 62 01:10:56 [INFO] train episode 16273: reward = 9.14, steps = 31 01:10:56 [INFO] train episode 16274: reward = 17.35, steps = 33 01:10:56 [INFO] train episode 16275: reward = 18.17, steps = 39 01:10:57 [INFO] train episode 16276: reward = 37.13, steps = 54 01:10:57 [INFO] train episode 16277: reward = 16.47, steps = 40 01:10:57 [INFO] train episode 16278: reward = -14.09, steps = 25 01:10:58 [INFO] train episode 16279: reward = 33.89, steps = 61 01:10:58 [INFO] train episode 16280: reward = 2.18, steps = 40 01:10:58 [INFO] train episode 16281: reward = 6.06, steps = 26 01:10:58 [INFO] train episode 16282: reward = 34.28, steps = 57 01:10:59 [INFO] train episode 16283: reward = 37.01, steps = 64 01:10:59 [INFO] train episode 16284: reward = 17.58, steps = 35 01:10:59 [INFO] train episode 16285: reward = 2.59, steps = 28 01:10:59 [INFO] train episode 16286: reward = -5.03, steps = 22 01:11:00 [INFO] train episode 16287: reward = 2.13, steps = 30 01:11:00 [INFO] train episode 16288: reward = 27.09, steps = 44 01:11:00 [INFO] train episode 16289: reward = 13.51, steps = 36 01:11:00 [INFO] train episode 16290: reward = 33.78, steps = 39 01:11:01 [INFO] train episode 16291: reward = 35.47, steps = 46 01:11:01 [INFO] train episode 16292: reward = 12.62, steps = 27 01:11:01 [INFO] train episode 16293: reward = 39.30, steps = 50 01:11:02 [INFO] train episode 16294: reward = 25.40, steps = 47 01:11:02 [INFO] train episode 16295: reward = 37.01, steps = 47 01:11:02 [INFO] train episode 16296: reward = 29.52, steps = 39 01:11:02 [INFO] train episode 16297: reward = 10.10, steps = 29 01:11:03 [INFO] train episode 16298: reward = 24.71, steps = 38 01:11:03 [INFO] train episode 16299: reward = 16.32, steps = 37 01:11:03 [INFO] train episode 16300: reward = 32.61, steps = 40 01:11:03 [INFO] train episode 16301: reward = 2.51, steps = 26 01:11:03 [INFO] train episode 16302: reward = -4.86, steps = 22 01:11:04 [INFO] train episode 16303: reward = -4.06, steps = 23 01:11:04 [INFO] train episode 16304: reward = 39.53, steps = 60 01:11:04 [INFO] train episode 16305: reward = 30.11, steps = 40 01:11:05 [INFO] train episode 16306: reward = 38.35, steps = 50 01:11:05 [INFO] train episode 16307: reward = 13.44, steps = 50 01:11:05 [INFO] train episode 16308: reward = 17.11, steps = 42 01:11:06 [INFO] train episode 16309: reward = 17.05, steps = 39 01:11:06 [INFO] train episode 16310: reward = -11.73, steps = 22 01:11:06 [INFO] train episode 16311: reward = 25.28, steps = 41 01:11:06 [INFO] train episode 16312: reward = 36.64, steps = 47 01:11:07 [INFO] train episode 16313: reward = 35.63, steps = 45 01:11:07 [INFO] train episode 16314: reward = -0.70, steps = 31 01:11:07 [INFO] train episode 16315: reward = 34.92, steps = 55 01:11:08 [INFO] train episode 16316: reward = -0.49, steps = 23 01:11:08 [INFO] train episode 16317: reward = 28.35, steps = 44 01:11:08 [INFO] train episode 16318: reward = -0.96, steps = 56 01:11:08 [INFO] train episode 16319: reward = -4.30, steps = 27 01:11:09 [INFO] train episode 16320: reward = 34.51, steps = 46 01:11:09 [INFO] train episode 16321: reward = 6.93, steps = 31 01:11:09 [INFO] train episode 16322: reward = -2.58, steps = 26 01:11:10 [INFO] train episode 16323: reward = 8.37, steps = 36 01:11:10 [INFO] train episode 16324: reward = 0.59, steps = 23 01:11:10 [INFO] train episode 16325: reward = 30.48, steps = 48 01:11:10 [INFO] train episode 16326: reward = 16.07, steps = 51 01:11:11 [INFO] train episode 16327: reward = 14.21, steps = 32 01:11:11 [INFO] train episode 16328: reward = 3.64, steps = 29 01:11:11 [INFO] train episode 16329: reward = 43.21, steps = 58 01:11:12 [INFO] train episode 16330: reward = 32.46, steps = 46 01:11:12 [INFO] train episode 16331: reward = 32.85, steps = 48 01:11:12 [INFO] train episode 16332: reward = -12.47, steps = 22 01:11:12 [INFO] train episode 16333: reward = 21.36, steps = 45 01:11:13 [INFO] train episode 16334: reward = 21.12, steps = 43 01:11:13 [INFO] train episode 16335: reward = 16.95, steps = 39 01:11:13 [INFO] train episode 16336: reward = 36.69, steps = 56 01:11:14 [INFO] train episode 16337: reward = 41.26, steps = 47 01:11:14 [INFO] train episode 16338: reward = 0.14, steps = 27 01:11:14 [INFO] train episode 16339: reward = 36.66, steps = 46 01:11:14 [INFO] train episode 16340: reward = -8.29, steps = 22 01:11:14 [INFO] train episode 16341: reward = -4.13, steps = 25 01:11:15 [INFO] train episode 16342: reward = 0.74, steps = 31 01:11:15 [INFO] train episode 16343: reward = 9.47, steps = 29 01:11:15 [INFO] train episode 16344: reward = 4.89, steps = 31 01:11:15 [INFO] train episode 16345: reward = 4.67, steps = 30 01:11:16 [INFO] train episode 16346: reward = 38.18, steps = 67 01:11:16 [INFO] train episode 16347: reward = 37.92, steps = 51 01:11:16 [INFO] train episode 16348: reward = 7.28, steps = 29 01:11:17 [INFO] train episode 16349: reward = 11.78, steps = 33 01:11:17 [INFO] train episode 16350: reward = 0.82, steps = 26 01:11:17 [INFO] train episode 16351: reward = 31.50, steps = 45 01:11:18 [INFO] train episode 16352: reward = 35.53, steps = 44 01:11:18 [INFO] train episode 16353: reward = 8.23, steps = 31 01:11:18 [INFO] train episode 16354: reward = 39.06, steps = 47 01:11:19 [INFO] train episode 16355: reward = 53.57, steps = 69 01:11:19 [INFO] train episode 16356: reward = 37.67, steps = 44 01:11:19 [INFO] train episode 16357: reward = 7.54, steps = 27 01:11:20 [INFO] train episode 16358: reward = 47.47, steps = 56 01:11:20 [INFO] train episode 16359: reward = 20.28, steps = 38 01:11:20 [INFO] train episode 16360: reward = -5.28, steps = 28 01:11:20 [INFO] train episode 16361: reward = -16.08, steps = 17 01:11:20 [INFO] train episode 16362: reward = 28.21, steps = 43 01:11:21 [INFO] train episode 16363: reward = 1.15, steps = 32 01:11:21 [INFO] train episode 16364: reward = 0.81, steps = 33 01:11:21 [INFO] train episode 16365: reward = -14.07, steps = 17 01:11:21 [INFO] train episode 16366: reward = 27.25, steps = 51 01:11:22 [INFO] train episode 16367: reward = 16.05, steps = 49 01:11:22 [INFO] train episode 16368: reward = -10.54, steps = 26 01:11:22 [INFO] train episode 16369: reward = 4.52, steps = 39 01:11:22 [INFO] train episode 16370: reward = 36.58, steps = 50 01:11:23 [INFO] train episode 16371: reward = 4.87, steps = 39 01:11:23 [INFO] train episode 16372: reward = 1.47, steps = 30 01:11:23 [INFO] train episode 16373: reward = 4.00, steps = 32 01:11:24 [INFO] train episode 16374: reward = 1.24, steps = 27 01:11:24 [INFO] train episode 16375: reward = 42.12, steps = 70 01:11:24 [INFO] train episode 16376: reward = -0.08, steps = 28 01:11:24 [INFO] train episode 16377: reward = 14.03, steps = 37 01:11:25 [INFO] train episode 16378: reward = 22.30, steps = 39 01:11:25 [INFO] train episode 16379: reward = 4.00, steps = 31 01:11:25 [INFO] train episode 16380: reward = 4.04, steps = 31 01:11:25 [INFO] train episode 16381: reward = 35.56, steps = 44 01:11:26 [INFO] train episode 16382: reward = 2.67, steps = 24 01:11:26 [INFO] train episode 16383: reward = 9.46, steps = 32 01:11:26 [INFO] train episode 16384: reward = 16.49, steps = 34 01:11:26 [INFO] train episode 16385: reward = 24.84, steps = 37 01:11:27 [INFO] train episode 16386: reward = -0.64, steps = 29 01:11:27 [INFO] train episode 16387: reward = 20.65, steps = 42 01:11:27 [INFO] train episode 16388: reward = 31.31, steps = 41 01:11:27 [INFO] train episode 16389: reward = 23.86, steps = 49 01:11:28 [INFO] train episode 16390: reward = 35.69, steps = 65 01:11:28 [INFO] train episode 16391: reward = 9.99, steps = 31 01:11:28 [INFO] train episode 16392: reward = 35.29, steps = 50 01:11:29 [INFO] train episode 16393: reward = 17.42, steps = 31 01:11:29 [INFO] train episode 16394: reward = 16.69, steps = 34 01:11:29 [INFO] train episode 16395: reward = 22.40, steps = 42 01:11:29 [INFO] train episode 16396: reward = 21.37, steps = 42 01:11:30 [INFO] train episode 16397: reward = 36.15, steps = 42 01:11:30 [INFO] train episode 16398: reward = 12.20, steps = 30 01:11:30 [INFO] train episode 16399: reward = 26.44, steps = 44 01:11:31 [INFO] train episode 16400: reward = 41.95, steps = 55 01:11:31 [INFO] train episode 16401: reward = 22.12, steps = 42 01:11:31 [INFO] train episode 16402: reward = 35.10, steps = 49 01:11:32 [INFO] train episode 16403: reward = 54.35, steps = 79 01:11:32 [INFO] train episode 16404: reward = 26.59, steps = 44 01:11:32 [INFO] train episode 16405: reward = 30.49, steps = 38 01:11:32 [INFO] ==== test ==== 01:11:33 [INFO] test episode 0: reward = 32.99, steps = 35 01:11:33 [INFO] test episode 1: reward = 45.09, steps = 42 01:11:33 [INFO] test episode 2: reward = 73.86, steps = 52 01:11:33 [INFO] test episode 3: reward = 63.51, steps = 56 01:11:34 [INFO] test episode 4: reward = 27.00, steps = 30 01:11:34 [INFO] test episode 5: reward = 67.52, steps = 45 01:11:34 [INFO] test episode 6: reward = 44.17, steps = 46 01:11:34 [INFO] test episode 7: reward = 33.88, steps = 32 01:11:35 [INFO] test episode 8: reward = 39.97, steps = 39 01:11:35 [INFO] test episode 9: reward = 43.67, steps = 45 01:11:35 [INFO] test episode 10: reward = 48.24, steps = 41 01:11:35 [INFO] test episode 11: reward = 35.04, steps = 35 01:11:36 [INFO] test episode 12: reward = 66.92, steps = 52 01:11:36 [INFO] test episode 13: reward = 37.91, steps = 37 01:11:36 [INFO] test episode 14: reward = 30.62, steps = 34 01:11:36 [INFO] test episode 15: reward = 83.14, steps = 64 01:11:37 [INFO] test episode 16: reward = 68.36, steps = 51 01:11:37 [INFO] test episode 17: reward = 35.05, steps = 36 01:11:37 [INFO] test episode 18: reward = 56.51, steps = 40 01:11:37 [INFO] test episode 19: reward = 63.13, steps = 44 01:11:38 [INFO] test episode 20: reward = 60.88, steps = 44 01:11:38 [INFO] test episode 21: reward = 81.05, steps = 61 01:11:38 [INFO] test episode 22: reward = 60.77, steps = 43 01:11:38 [INFO] test episode 23: reward = 10.42, steps = 26 01:11:39 [INFO] test episode 24: reward = 22.35, steps = 31 01:11:39 [INFO] test episode 25: reward = 54.70, steps = 40 01:11:39 [INFO] test episode 26: reward = 69.13, steps = 48 01:11:39 [INFO] test episode 27: reward = 64.42, steps = 46 01:11:40 [INFO] test episode 28: reward = 14.15, steps = 25 01:11:40 [INFO] test episode 29: reward = 63.68, steps = 43 01:11:40 [INFO] test episode 30: reward = 69.44, steps = 67 01:11:40 [INFO] test episode 31: reward = 40.86, steps = 36 01:11:41 [INFO] test episode 32: reward = 60.49, steps = 43 01:11:41 [INFO] test episode 33: reward = 56.78, steps = 54 01:11:41 [INFO] test episode 34: reward = 54.47, steps = 41 01:11:42 [INFO] test episode 35: reward = 72.12, steps = 50 01:11:42 [INFO] test episode 36: reward = 65.98, steps = 51 01:11:42 [INFO] test episode 37: reward = 26.88, steps = 35 01:11:42 [INFO] test episode 38: reward = 31.71, steps = 30 01:11:43 [INFO] test episode 39: reward = 59.69, steps = 46 01:11:43 [INFO] test episode 40: reward = 49.91, steps = 40 01:11:43 [INFO] test episode 41: reward = 78.49, steps = 55 01:11:43 [INFO] test episode 42: reward = 69.91, steps = 51 01:11:44 [INFO] test episode 43: reward = 70.37, steps = 54 01:11:44 [INFO] test episode 44: reward = 72.42, steps = 70 01:11:45 [INFO] test episode 45: reward = 66.97, steps = 47 01:11:45 [INFO] test episode 46: reward = 68.63, steps = 63 01:11:45 [INFO] test episode 47: reward = 53.17, steps = 47 01:11:45 [INFO] test episode 48: reward = 31.42, steps = 35 01:11:46 [INFO] test episode 49: reward = 27.76, steps = 30 01:11:46 [INFO] test episode 50: reward = 69.05, steps = 51 01:11:46 [INFO] test episode 51: reward = 43.95, steps = 39 01:11:46 [INFO] test episode 52: reward = 69.37, steps = 46 01:11:47 [INFO] test episode 53: reward = 25.99, steps = 31 01:11:47 [INFO] test episode 54: reward = 74.10, steps = 54 01:11:47 [INFO] test episode 55: reward = 69.58, steps = 52 01:11:48 [INFO] test episode 56: reward = 67.07, steps = 49 01:11:48 [INFO] test episode 57: reward = 67.19, steps = 47 01:11:48 [INFO] test episode 58: reward = 41.45, steps = 39 01:11:48 [INFO] test episode 59: reward = 33.48, steps = 34 01:11:49 [INFO] test episode 60: reward = 81.44, steps = 58 01:11:49 [INFO] test episode 61: reward = 73.15, steps = 63 01:11:49 [INFO] test episode 62: reward = 63.93, steps = 47 01:11:49 [INFO] test episode 63: reward = 35.16, steps = 32 01:11:50 [INFO] test episode 64: reward = 60.69, steps = 49 01:11:50 [INFO] test episode 65: reward = 76.33, steps = 63 01:11:50 [INFO] test episode 66: reward = 66.04, steps = 48 01:11:51 [INFO] test episode 67: reward = 57.50, steps = 39 01:11:51 [INFO] test episode 68: reward = 72.22, steps = 57 01:11:51 [INFO] test episode 69: reward = 37.42, steps = 37 01:11:52 [INFO] test episode 70: reward = 61.00, steps = 44 01:11:52 [INFO] test episode 71: reward = 38.35, steps = 37 01:11:52 [INFO] test episode 72: reward = 37.74, steps = 35 01:11:52 [INFO] test episode 73: reward = 22.35, steps = 30 01:11:52 [INFO] test episode 74: reward = 29.01, steps = 33 01:11:53 [INFO] test episode 75: reward = 66.50, steps = 47 01:11:53 [INFO] test episode 76: reward = 61.17, steps = 43 01:11:53 [INFO] test episode 77: reward = 34.96, steps = 39 01:11:53 [INFO] test episode 78: reward = 3.02, steps = 26 01:11:53 [INFO] test episode 79: reward = -4.46, steps = 22 01:11:54 [INFO] test episode 80: reward = 76.77, steps = 56 01:11:54 [INFO] test episode 81: reward = 43.30, steps = 39 01:11:54 [INFO] test episode 82: reward = 24.80, steps = 30 01:11:54 [INFO] test episode 83: reward = 29.76, steps = 31 01:11:55 [INFO] test episode 84: reward = 57.91, steps = 42 01:11:55 [INFO] test episode 85: reward = 64.39, steps = 44 01:11:55 [INFO] test episode 86: reward = 47.97, steps = 45 01:11:56 [INFO] test episode 87: reward = 66.68, steps = 47 01:11:56 [INFO] test episode 88: reward = 19.49, steps = 28 01:11:56 [INFO] test episode 89: reward = 61.09, steps = 41 01:11:56 [INFO] test episode 90: reward = 71.79, steps = 53 01:11:56 [INFO] test episode 91: reward = 58.48, steps = 41 01:11:57 [INFO] test episode 92: reward = 73.68, steps = 53 01:11:57 [INFO] test episode 93: reward = 53.30, steps = 44 01:11:57 [INFO] test episode 94: reward = 49.93, steps = 38 01:11:58 [INFO] test episode 95: reward = 65.35, steps = 47 01:11:58 [INFO] test episode 96: reward = 46.08, steps = 39 01:11:58 [INFO] test episode 97: reward = 59.30, steps = 40 01:11:58 [INFO] test episode 98: reward = 28.69, steps = 32 01:11:59 [INFO] test episode 99: reward = 70.10, steps = 46 01:11:59 [INFO] average episode reward = 52.29 ± 19.07
