Use Off-Policy VPG to Play CartPole-v0¶

PyTorch version

In [1]:
%matplotlib inline

import sys
import logging
import itertools

import numpy as np
np.random.seed(0)
import pandas as pd
import gym
import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.optim as optim
import torch.distributions as distributions
torch.manual_seed(0)

logging.basicConfig(level=logging.INFO,
        format='%(asctime)s [%(levelname)s] %(message)s',
        stream=sys.stdout, datefmt='%H:%M:%S')
In [2]:
env = gym.make('CartPole-v0')
for key in vars(env):
    logging.info('%s: %s', key, vars(env)[key])
for key in vars(env.spec):
    logging.info('%s: %s', key, vars(env.spec)[key])
22:54:44 [INFO] env: <CartPoleEnv<CartPole-v0>>
22:54:44 [INFO] action_space: Discrete(2)
22:54:44 [INFO] observation_space: Box(-3.4028234663852886e+38, 3.4028234663852886e+38, (4,), float32)
22:54:44 [INFO] reward_range: (-inf, inf)
22:54:44 [INFO] metadata: {'render.modes': ['human', 'rgb_array'], 'video.frames_per_second': 50}
22:54:44 [INFO] _max_episode_steps: 200
22:54:44 [INFO] _elapsed_steps: None
22:54:44 [INFO] id: CartPole-v0
22:54:44 [INFO] entry_point: gym.envs.classic_control:CartPoleEnv
22:54:44 [INFO] reward_threshold: 195.0
22:54:44 [INFO] nondeterministic: False
22:54:44 [INFO] max_episode_steps: 200
22:54:44 [INFO] _kwargs: {}
22:54:44 [INFO] _env_name: CartPole
In [3]:
class OffPolicyVPGAgent:
    def __init__(self, env):
        self.action_n = env.action_space.n
        self.gamma = 0.99

        self.policy_net = self.build_net(
                input_size=env.observation_space.shape[0],
                hidden_sizes=[],
                output_size=self.action_n, output_activator=nn.Softmax(1))
        self.optimizer = optim.Adam(self.policy_net.parameters(), lr=0.06)

    def build_net(self, input_size, hidden_sizes, output_size,
            output_activator=None, use_bias=False):
        layers = []
        for input_size, output_size in zip(
                [input_size,] + hidden_sizes, hidden_sizes + [output_size,]):
            layers.append(nn.Linear(input_size, output_size, bias=use_bias))
            layers.append(nn.ReLU())
        layers = layers[:-1]
        if output_activator:
            layers.append(output_activator)
        model = nn.Sequential(*layers)
        return model

    def reset(self, mode=None):
        self.mode = mode
        if self.mode == 'train':
            self.trajectory = []

    def step(self, observation, reward, terminated):
        if self.mode == 'train':
            action = np.random.choice(self.action_n)  # use random policy
            self.trajectory += [observation, reward, terminated, action]
        else:
            state_tensor = torch.as_tensor(observation,
                    dtype=torch.float).unsqueeze(0)
            prob_tensor = self.policy_net(state_tensor)
            action_tensor = distributions.Categorical(prob_tensor).sample()
            action = action_tensor.numpy()[0]
        return action

    def close(self):
        if self.mode == 'train':
            self.learn()

    def learn(self):
        state_tensor = torch.as_tensor(self.trajectory[0::4], dtype=torch.float)
        reward_tensor = torch.as_tensor(self.trajectory[1::4], dtype=torch.float)
        action_tensor = torch.as_tensor(self.trajectory[3::4], dtype=torch.long)
        arange_tensor = torch.arange(state_tensor.shape[0], dtype=torch.float)
        discount_tensor = self.gamma ** arange_tensor
        discounted_reward_tensor = discount_tensor * reward_tensor
        discounted_return_tensor = discounted_reward_tensor.flip(0).cumsum(0).flip(0)
        all_pi_tensor = self.policy_net(state_tensor)
        pi_tensor = torch.gather(all_pi_tensor, 1,
                action_tensor.unsqueeze(1)).squeeze(1)
        behavior_prob = 1. / self.action_n
        loss_tensor = -(discounted_return_tensor / behavior_prob *
                pi_tensor).mean()
        self.optimizer.zero_grad()
        loss_tensor.backward()
        self.optimizer.step()


agent = OffPolicyVPGAgent(env)
In [4]:
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('==== train ====')
episode_rewards = []
for episode in itertools.count():
    play_episode(env, agent, seed=episode,
            mode='train')
    episode_reward, elapsed_steps = play_episode(env, agent)
    episode_rewards.append(episode_reward)
    logging.info('train episode %d: reward = %.2f, steps = %d',
            episode, episode_reward, elapsed_steps)
    if np.mean(episode_rewards[-20:]) > 199:
        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))
22:54:44 [INFO] ==== train ====
22:54:45 [INFO] train episode 0: reward = 30.00, steps = 30
22:54:45 [INFO] train episode 1: reward = 71.00, steps = 71
22:54:45 [INFO] train episode 2: reward = 42.00, steps = 42
22:54:45 [INFO] train episode 3: reward = 18.00, steps = 18
22:54:45 [INFO] train episode 4: reward = 26.00, steps = 26
22:54:45 [INFO] train episode 5: reward = 19.00, steps = 19
22:54:45 [INFO] train episode 6: reward = 15.00, steps = 15
22:54:45 [INFO] train episode 7: reward = 66.00, steps = 66
22:54:45 [INFO] train episode 8: reward = 21.00, steps = 21
22:54:45 [INFO] train episode 9: reward = 64.00, steps = 64
22:54:45 [INFO] train episode 10: reward = 31.00, steps = 31
22:54:45 [INFO] train episode 11: reward = 38.00, steps = 38
22:54:45 [INFO] train episode 12: reward = 36.00, steps = 36
22:54:45 [INFO] train episode 13: reward = 13.00, steps = 13
22:54:45 [INFO] train episode 14: reward = 21.00, steps = 21
22:54:45 [INFO] train episode 15: reward = 16.00, steps = 16
22:54:45 [INFO] train episode 16: reward = 52.00, steps = 52
22:54:45 [INFO] train episode 17: reward = 54.00, steps = 54
22:54:45 [INFO] train episode 18: reward = 40.00, steps = 40
22:54:45 [INFO] train episode 19: reward = 19.00, steps = 19
22:54:45 [INFO] train episode 20: reward = 28.00, steps = 28
22:54:45 [INFO] train episode 21: reward = 54.00, steps = 54
22:54:45 [INFO] train episode 22: reward = 28.00, steps = 28
22:54:45 [INFO] train episode 23: reward = 24.00, steps = 24
22:54:45 [INFO] train episode 24: reward = 13.00, steps = 13
22:54:45 [INFO] train episode 25: reward = 38.00, steps = 38
22:54:45 [INFO] train episode 26: reward = 24.00, steps = 24
22:54:45 [INFO] train episode 27: reward = 77.00, steps = 77
22:54:45 [INFO] train episode 28: reward = 17.00, steps = 17
22:54:45 [INFO] train episode 29: reward = 90.00, steps = 90
22:54:45 [INFO] train episode 30: reward = 43.00, steps = 43
22:54:45 [INFO] train episode 31: reward = 91.00, steps = 91
22:54:45 [INFO] train episode 32: reward = 37.00, steps = 37
22:54:45 [INFO] train episode 33: reward = 93.00, steps = 93
22:54:45 [INFO] train episode 34: reward = 13.00, steps = 13
22:54:45 [INFO] train episode 35: reward = 59.00, steps = 59
22:54:45 [INFO] train episode 36: reward = 21.00, steps = 21
22:54:45 [INFO] train episode 37: reward = 44.00, steps = 44
22:54:45 [INFO] train episode 38: reward = 80.00, steps = 80
22:54:45 [INFO] train episode 39: reward = 88.00, steps = 88
22:54:45 [INFO] train episode 40: reward = 32.00, steps = 32
22:54:45 [INFO] train episode 41: reward = 24.00, steps = 24
22:54:45 [INFO] train episode 42: reward = 72.00, steps = 72
22:54:45 [INFO] train episode 43: reward = 50.00, steps = 50
22:54:45 [INFO] train episode 44: reward = 23.00, steps = 23
22:54:45 [INFO] train episode 45: reward = 23.00, steps = 23
22:54:46 [INFO] train episode 46: reward = 56.00, steps = 56
22:54:46 [INFO] train episode 47: reward = 26.00, steps = 26
22:54:46 [INFO] train episode 48: reward = 45.00, steps = 45
22:54:46 [INFO] train episode 49: reward = 61.00, steps = 61
22:54:46 [INFO] train episode 50: reward = 24.00, steps = 24
22:54:46 [INFO] train episode 51: reward = 76.00, steps = 76
22:54:46 [INFO] train episode 52: reward = 82.00, steps = 82
22:54:46 [INFO] train episode 53: reward = 72.00, steps = 72
22:54:46 [INFO] train episode 54: reward = 68.00, steps = 68
22:54:46 [INFO] train episode 55: reward = 82.00, steps = 82
22:54:46 [INFO] train episode 56: reward = 59.00, steps = 59
22:54:46 [INFO] train episode 57: reward = 22.00, steps = 22
22:54:46 [INFO] train episode 58: reward = 49.00, steps = 49
22:54:46 [INFO] train episode 59: reward = 66.00, steps = 66
22:54:46 [INFO] train episode 60: reward = 64.00, steps = 64
22:54:46 [INFO] train episode 61: reward = 59.00, steps = 59
22:54:46 [INFO] train episode 62: reward = 37.00, steps = 37
22:54:46 [INFO] train episode 63: reward = 44.00, steps = 44
22:54:46 [INFO] train episode 64: reward = 53.00, steps = 53
22:54:46 [INFO] train episode 65: reward = 70.00, steps = 70
22:54:46 [INFO] train episode 66: reward = 82.00, steps = 82
22:54:46 [INFO] train episode 67: reward = 57.00, steps = 57
22:54:46 [INFO] train episode 68: reward = 66.00, steps = 66
22:54:46 [INFO] train episode 69: reward = 123.00, steps = 123
22:54:46 [INFO] train episode 70: reward = 22.00, steps = 22
22:54:46 [INFO] train episode 71: reward = 78.00, steps = 78
22:54:46 [INFO] train episode 72: reward = 67.00, steps = 67
22:54:46 [INFO] train episode 73: reward = 38.00, steps = 38
22:54:46 [INFO] train episode 74: reward = 53.00, steps = 53
22:54:46 [INFO] train episode 75: reward = 79.00, steps = 79
22:54:46 [INFO] train episode 76: reward = 50.00, steps = 50
22:54:46 [INFO] train episode 77: reward = 69.00, steps = 69
22:54:46 [INFO] train episode 78: reward = 58.00, steps = 58
22:54:46 [INFO] train episode 79: reward = 70.00, steps = 70
22:54:46 [INFO] train episode 80: reward = 57.00, steps = 57
22:54:47 [INFO] train episode 81: reward = 40.00, steps = 40
22:54:47 [INFO] train episode 82: reward = 72.00, steps = 72
22:54:47 [INFO] train episode 83: reward = 46.00, steps = 46
22:54:47 [INFO] train episode 84: reward = 105.00, steps = 105
22:54:47 [INFO] train episode 85: reward = 22.00, steps = 22
22:54:47 [INFO] train episode 86: reward = 50.00, steps = 50
22:54:47 [INFO] train episode 87: reward = 27.00, steps = 27
22:54:47 [INFO] train episode 88: reward = 68.00, steps = 68
22:54:47 [INFO] train episode 89: reward = 47.00, steps = 47
22:54:47 [INFO] train episode 90: reward = 83.00, steps = 83
22:54:47 [INFO] train episode 91: reward = 119.00, steps = 119
22:54:47 [INFO] train episode 92: reward = 27.00, steps = 27
22:54:47 [INFO] train episode 93: reward = 59.00, steps = 59
22:54:47 [INFO] train episode 94: reward = 74.00, steps = 74
22:54:47 [INFO] train episode 95: reward = 64.00, steps = 64
22:54:47 [INFO] train episode 96: reward = 61.00, steps = 61
22:54:47 [INFO] train episode 97: reward = 55.00, steps = 55
22:54:47 [INFO] train episode 98: reward = 55.00, steps = 55
22:54:47 [INFO] train episode 99: reward = 66.00, steps = 66
22:54:47 [INFO] train episode 100: reward = 75.00, steps = 75
22:54:47 [INFO] train episode 101: reward = 31.00, steps = 31
22:54:47 [INFO] train episode 102: reward = 85.00, steps = 85
22:54:47 [INFO] train episode 103: reward = 74.00, steps = 74
22:54:47 [INFO] train episode 104: reward = 31.00, steps = 31
22:54:47 [INFO] train episode 105: reward = 51.00, steps = 51
22:54:47 [INFO] train episode 106: reward = 138.00, steps = 138
22:54:47 [INFO] train episode 107: reward = 101.00, steps = 101
22:54:47 [INFO] train episode 108: reward = 65.00, steps = 65
22:54:47 [INFO] train episode 109: reward = 126.00, steps = 126
22:54:47 [INFO] train episode 110: reward = 74.00, steps = 74
22:54:47 [INFO] train episode 111: reward = 86.00, steps = 86
22:54:48 [INFO] train episode 112: reward = 97.00, steps = 97
22:54:48 [INFO] train episode 113: reward = 87.00, steps = 87
22:54:48 [INFO] train episode 114: reward = 40.00, steps = 40
22:54:48 [INFO] train episode 115: reward = 38.00, steps = 38
22:54:48 [INFO] train episode 116: reward = 43.00, steps = 43
22:54:48 [INFO] train episode 117: reward = 54.00, steps = 54
22:54:48 [INFO] train episode 118: reward = 84.00, steps = 84
22:54:48 [INFO] train episode 119: reward = 41.00, steps = 41
22:54:48 [INFO] train episode 120: reward = 47.00, steps = 47
22:54:48 [INFO] train episode 121: reward = 73.00, steps = 73
22:54:48 [INFO] train episode 122: reward = 79.00, steps = 79
22:54:48 [INFO] train episode 123: reward = 60.00, steps = 60
22:54:48 [INFO] train episode 124: reward = 38.00, steps = 38
22:54:48 [INFO] train episode 125: reward = 46.00, steps = 46
22:54:48 [INFO] train episode 126: reward = 97.00, steps = 97
22:54:48 [INFO] train episode 127: reward = 54.00, steps = 54
22:54:48 [INFO] train episode 128: reward = 98.00, steps = 98
22:54:48 [INFO] train episode 129: reward = 54.00, steps = 54
22:54:48 [INFO] train episode 130: reward = 62.00, steps = 62
22:54:48 [INFO] train episode 131: reward = 68.00, steps = 68
22:54:48 [INFO] train episode 132: reward = 84.00, steps = 84
22:54:48 [INFO] train episode 133: reward = 28.00, steps = 28
22:54:48 [INFO] train episode 134: reward = 110.00, steps = 110
22:54:48 [INFO] train episode 135: reward = 47.00, steps = 47
22:54:48 [INFO] train episode 136: reward = 60.00, steps = 60
22:54:48 [INFO] train episode 137: reward = 60.00, steps = 60
22:54:48 [INFO] train episode 138: reward = 64.00, steps = 64
22:54:48 [INFO] train episode 139: reward = 103.00, steps = 103
22:54:48 [INFO] train episode 140: reward = 50.00, steps = 50
22:54:49 [INFO] train episode 141: reward = 116.00, steps = 116
22:54:49 [INFO] train episode 142: reward = 149.00, steps = 149
22:54:49 [INFO] train episode 143: reward = 62.00, steps = 62
22:54:49 [INFO] train episode 144: reward = 46.00, steps = 46
22:54:49 [INFO] train episode 145: reward = 47.00, steps = 47
22:54:49 [INFO] train episode 146: reward = 60.00, steps = 60
22:54:49 [INFO] train episode 147: reward = 61.00, steps = 61
22:54:49 [INFO] train episode 148: reward = 200.00, steps = 200
22:54:49 [INFO] train episode 149: reward = 106.00, steps = 106
22:54:49 [INFO] train episode 150: reward = 61.00, steps = 61
22:54:49 [INFO] train episode 151: reward = 77.00, steps = 77
22:54:49 [INFO] train episode 152: reward = 54.00, steps = 54
22:54:49 [INFO] train episode 153: reward = 70.00, steps = 70
22:54:49 [INFO] train episode 154: reward = 31.00, steps = 31
22:54:49 [INFO] train episode 155: reward = 55.00, steps = 55
22:54:49 [INFO] train episode 156: reward = 55.00, steps = 55
22:54:49 [INFO] train episode 157: reward = 32.00, steps = 32
22:54:49 [INFO] train episode 158: reward = 50.00, steps = 50
22:54:49 [INFO] train episode 159: reward = 53.00, steps = 53
22:54:49 [INFO] train episode 160: reward = 94.00, steps = 94
22:54:49 [INFO] train episode 161: reward = 102.00, steps = 102
22:54:49 [INFO] train episode 162: reward = 54.00, steps = 54
22:54:49 [INFO] train episode 163: reward = 96.00, steps = 96
22:54:49 [INFO] train episode 164: reward = 98.00, steps = 98
22:54:49 [INFO] train episode 165: reward = 59.00, steps = 59
22:54:49 [INFO] train episode 166: reward = 74.00, steps = 74
22:54:49 [INFO] train episode 167: reward = 58.00, steps = 58
22:54:50 [INFO] train episode 168: reward = 31.00, steps = 31
22:54:50 [INFO] train episode 169: reward = 79.00, steps = 79
22:54:50 [INFO] train episode 170: reward = 50.00, steps = 50
22:54:50 [INFO] train episode 171: reward = 75.00, steps = 75
22:54:50 [INFO] train episode 172: reward = 66.00, steps = 66
22:54:50 [INFO] train episode 173: reward = 45.00, steps = 45
22:54:50 [INFO] train episode 174: reward = 36.00, steps = 36
22:54:50 [INFO] train episode 175: reward = 68.00, steps = 68
22:54:50 [INFO] train episode 176: reward = 66.00, steps = 66
22:54:50 [INFO] train episode 177: reward = 58.00, steps = 58
22:54:50 [INFO] train episode 178: reward = 58.00, steps = 58
22:54:50 [INFO] train episode 179: reward = 78.00, steps = 78
22:54:50 [INFO] train episode 180: reward = 49.00, steps = 49
22:54:50 [INFO] train episode 181: reward = 57.00, steps = 57
22:54:50 [INFO] train episode 182: reward = 50.00, steps = 50
22:54:50 [INFO] train episode 183: reward = 70.00, steps = 70
22:54:50 [INFO] train episode 184: reward = 61.00, steps = 61
22:54:50 [INFO] train episode 185: reward = 57.00, steps = 57
22:54:50 [INFO] train episode 186: reward = 33.00, steps = 33
22:54:50 [INFO] train episode 187: reward = 74.00, steps = 74
22:54:50 [INFO] train episode 188: reward = 64.00, steps = 64
22:54:50 [INFO] train episode 189: reward = 69.00, steps = 69
22:54:50 [INFO] train episode 190: reward = 73.00, steps = 73
22:54:50 [INFO] train episode 191: reward = 89.00, steps = 89
22:54:50 [INFO] train episode 192: reward = 68.00, steps = 68
22:54:50 [INFO] train episode 193: reward = 41.00, steps = 41
22:54:50 [INFO] train episode 194: reward = 70.00, steps = 70
22:54:50 [INFO] train episode 195: reward = 46.00, steps = 46
22:54:50 [INFO] train episode 196: reward = 35.00, steps = 35
22:54:50 [INFO] train episode 197: reward = 89.00, steps = 89
22:54:50 [INFO] train episode 198: reward = 64.00, steps = 64
22:54:50 [INFO] train episode 199: reward = 135.00, steps = 135
22:54:51 [INFO] train episode 200: reward = 168.00, steps = 168
22:54:51 [INFO] train episode 201: reward = 36.00, steps = 36
22:54:51 [INFO] train episode 202: reward = 42.00, steps = 42
22:54:51 [INFO] train episode 203: reward = 51.00, steps = 51
22:54:51 [INFO] train episode 204: reward = 89.00, steps = 89
22:54:51 [INFO] train episode 205: reward = 51.00, steps = 51
22:54:51 [INFO] train episode 206: reward = 59.00, steps = 59
22:54:51 [INFO] train episode 207: reward = 117.00, steps = 117
22:54:51 [INFO] train episode 208: reward = 40.00, steps = 40
22:54:51 [INFO] train episode 209: reward = 60.00, steps = 60
22:54:51 [INFO] train episode 210: reward = 74.00, steps = 74
22:54:51 [INFO] train episode 211: reward = 63.00, steps = 63
22:54:51 [INFO] train episode 212: reward = 38.00, steps = 38
22:54:51 [INFO] train episode 213: reward = 49.00, steps = 49
22:54:51 [INFO] train episode 214: reward = 48.00, steps = 48
22:54:51 [INFO] train episode 215: reward = 57.00, steps = 57
22:54:51 [INFO] train episode 216: reward = 81.00, steps = 81
22:54:51 [INFO] train episode 217: reward = 90.00, steps = 90
22:54:51 [INFO] train episode 218: reward = 74.00, steps = 74
22:54:51 [INFO] train episode 219: reward = 43.00, steps = 43
22:54:51 [INFO] train episode 220: reward = 72.00, steps = 72
22:54:51 [INFO] train episode 221: reward = 60.00, steps = 60
22:54:51 [INFO] train episode 222: reward = 105.00, steps = 105
22:54:51 [INFO] train episode 223: reward = 42.00, steps = 42
22:54:51 [INFO] train episode 224: reward = 41.00, steps = 41
22:54:51 [INFO] train episode 225: reward = 90.00, steps = 90
22:54:51 [INFO] train episode 226: reward = 39.00, steps = 39
22:54:51 [INFO] train episode 227: reward = 98.00, steps = 98
22:54:51 [INFO] train episode 228: reward = 48.00, steps = 48
22:54:51 [INFO] train episode 229: reward = 74.00, steps = 74
22:54:52 [INFO] train episode 230: reward = 67.00, steps = 67
22:54:52 [INFO] train episode 231: reward = 55.00, steps = 55
22:54:52 [INFO] train episode 232: reward = 38.00, steps = 38
22:54:52 [INFO] train episode 233: reward = 46.00, steps = 46
22:54:52 [INFO] train episode 234: reward = 55.00, steps = 55
22:54:52 [INFO] train episode 235: reward = 73.00, steps = 73
22:54:52 [INFO] train episode 236: reward = 62.00, steps = 62
22:54:52 [INFO] train episode 237: reward = 61.00, steps = 61
22:54:52 [INFO] train episode 238: reward = 83.00, steps = 83
22:54:52 [INFO] train episode 239: reward = 49.00, steps = 49
22:54:52 [INFO] train episode 240: reward = 44.00, steps = 44
22:54:52 [INFO] train episode 241: reward = 88.00, steps = 88
22:54:52 [INFO] train episode 242: reward = 54.00, steps = 54
22:54:52 [INFO] train episode 243: reward = 170.00, steps = 170
22:54:52 [INFO] train episode 244: reward = 130.00, steps = 130
22:54:52 [INFO] train episode 245: reward = 98.00, steps = 98
22:54:52 [INFO] train episode 246: reward = 19.00, steps = 19
22:54:52 [INFO] train episode 247: reward = 30.00, steps = 30
22:54:52 [INFO] train episode 248: reward = 45.00, steps = 45
22:54:52 [INFO] train episode 249: reward = 56.00, steps = 56
22:54:52 [INFO] train episode 250: reward = 52.00, steps = 52
22:54:52 [INFO] train episode 251: reward = 95.00, steps = 95
22:54:52 [INFO] train episode 252: reward = 45.00, steps = 45
22:54:52 [INFO] train episode 253: reward = 59.00, steps = 59
22:54:52 [INFO] train episode 254: reward = 82.00, steps = 82
22:54:52 [INFO] train episode 255: reward = 89.00, steps = 89
22:54:52 [INFO] train episode 256: reward = 98.00, steps = 98
22:54:52 [INFO] train episode 257: reward = 77.00, steps = 77
22:54:53 [INFO] train episode 258: reward = 67.00, steps = 67
22:54:53 [INFO] train episode 259: reward = 64.00, steps = 64
22:54:53 [INFO] train episode 260: reward = 40.00, steps = 40
22:54:53 [INFO] train episode 261: reward = 107.00, steps = 107
22:54:53 [INFO] train episode 262: reward = 51.00, steps = 51
22:54:53 [INFO] train episode 263: reward = 52.00, steps = 52
22:54:53 [INFO] train episode 264: reward = 49.00, steps = 49
22:54:53 [INFO] train episode 265: reward = 49.00, steps = 49
22:54:53 [INFO] train episode 266: reward = 75.00, steps = 75
22:54:53 [INFO] train episode 267: reward = 135.00, steps = 135
22:54:53 [INFO] train episode 268: reward = 43.00, steps = 43
22:54:53 [INFO] train episode 269: reward = 41.00, steps = 41
22:54:53 [INFO] train episode 270: reward = 54.00, steps = 54
22:54:53 [INFO] train episode 271: reward = 76.00, steps = 76
22:54:53 [INFO] train episode 272: reward = 53.00, steps = 53
22:54:53 [INFO] train episode 273: reward = 69.00, steps = 69
22:54:53 [INFO] train episode 274: reward = 98.00, steps = 98
22:54:53 [INFO] train episode 275: reward = 61.00, steps = 61
22:54:53 [INFO] train episode 276: reward = 66.00, steps = 66
22:54:53 [INFO] train episode 277: reward = 61.00, steps = 61
22:54:53 [INFO] train episode 278: reward = 70.00, steps = 70
22:54:53 [INFO] train episode 279: reward = 67.00, steps = 67
22:54:53 [INFO] train episode 280: reward = 31.00, steps = 31
22:54:53 [INFO] train episode 281: reward = 103.00, steps = 103
22:54:53 [INFO] train episode 282: reward = 47.00, steps = 47
22:54:53 [INFO] train episode 283: reward = 26.00, steps = 26
22:54:53 [INFO] train episode 284: reward = 68.00, steps = 68
22:54:53 [INFO] train episode 285: reward = 86.00, steps = 86
22:54:53 [INFO] train episode 286: reward = 52.00, steps = 52
22:54:53 [INFO] train episode 287: reward = 57.00, steps = 57
22:54:54 [INFO] train episode 288: reward = 62.00, steps = 62
22:54:54 [INFO] train episode 289: reward = 166.00, steps = 166
22:54:54 [INFO] train episode 290: reward = 61.00, steps = 61
22:54:54 [INFO] train episode 291: reward = 83.00, steps = 83
22:54:54 [INFO] train episode 292: reward = 65.00, steps = 65
22:54:54 [INFO] train episode 293: reward = 43.00, steps = 43
22:54:54 [INFO] train episode 294: reward = 64.00, steps = 64
22:54:54 [INFO] train episode 295: reward = 55.00, steps = 55
22:54:54 [INFO] train episode 296: reward = 56.00, steps = 56
22:54:54 [INFO] train episode 297: reward = 35.00, steps = 35
22:54:54 [INFO] train episode 298: reward = 73.00, steps = 73
22:54:54 [INFO] train episode 299: reward = 51.00, steps = 51
22:54:54 [INFO] train episode 300: reward = 40.00, steps = 40
22:54:54 [INFO] train episode 301: reward = 54.00, steps = 54
22:54:54 [INFO] train episode 302: reward = 78.00, steps = 78
22:54:54 [INFO] train episode 303: reward = 115.00, steps = 115
22:54:54 [INFO] train episode 304: reward = 117.00, steps = 117
22:54:54 [INFO] train episode 305: reward = 68.00, steps = 68
22:54:54 [INFO] train episode 306: reward = 50.00, steps = 50
22:54:54 [INFO] train episode 307: reward = 86.00, steps = 86
22:54:54 [INFO] train episode 308: reward = 30.00, steps = 30
22:54:54 [INFO] train episode 309: reward = 44.00, steps = 44
22:54:54 [INFO] train episode 310: reward = 101.00, steps = 101
22:54:54 [INFO] train episode 311: reward = 110.00, steps = 110
22:54:54 [INFO] train episode 312: reward = 48.00, steps = 48
22:54:54 [INFO] train episode 313: reward = 85.00, steps = 85
22:54:54 [INFO] train episode 314: reward = 89.00, steps = 89
22:54:54 [INFO] train episode 315: reward = 128.00, steps = 128
22:54:55 [INFO] train episode 316: reward = 94.00, steps = 94
22:54:55 [INFO] train episode 317: reward = 43.00, steps = 43
22:54:55 [INFO] train episode 318: reward = 108.00, steps = 108
22:54:55 [INFO] train episode 319: reward = 70.00, steps = 70
22:54:55 [INFO] train episode 320: reward = 90.00, steps = 90
22:54:55 [INFO] train episode 321: reward = 40.00, steps = 40
22:54:55 [INFO] train episode 322: reward = 88.00, steps = 88
22:54:55 [INFO] train episode 323: reward = 65.00, steps = 65
22:54:55 [INFO] train episode 324: reward = 56.00, steps = 56
22:54:55 [INFO] train episode 325: reward = 55.00, steps = 55
22:54:55 [INFO] train episode 326: reward = 79.00, steps = 79
22:54:55 [INFO] train episode 327: reward = 46.00, steps = 46
22:54:55 [INFO] train episode 328: reward = 56.00, steps = 56
22:54:55 [INFO] train episode 329: reward = 47.00, steps = 47
22:54:55 [INFO] train episode 330: reward = 54.00, steps = 54
22:54:55 [INFO] train episode 331: reward = 57.00, steps = 57
22:54:55 [INFO] train episode 332: reward = 123.00, steps = 123
22:54:55 [INFO] train episode 333: reward = 34.00, steps = 34
22:54:55 [INFO] train episode 334: reward = 62.00, steps = 62
22:54:55 [INFO] train episode 335: reward = 63.00, steps = 63
22:54:55 [INFO] train episode 336: reward = 54.00, steps = 54
22:54:55 [INFO] train episode 337: reward = 92.00, steps = 92
22:54:55 [INFO] train episode 338: reward = 73.00, steps = 73
22:54:55 [INFO] train episode 339: reward = 68.00, steps = 68
22:54:55 [INFO] train episode 340: reward = 88.00, steps = 88
22:54:55 [INFO] train episode 341: reward = 97.00, steps = 97
22:54:55 [INFO] train episode 342: reward = 69.00, steps = 69
22:54:55 [INFO] train episode 343: reward = 53.00, steps = 53
22:54:55 [INFO] train episode 344: reward = 60.00, steps = 60
22:54:55 [INFO] train episode 345: reward = 42.00, steps = 42
22:54:55 [INFO] train episode 346: reward = 43.00, steps = 43
22:54:55 [INFO] train episode 347: reward = 48.00, steps = 48
22:54:56 [INFO] train episode 348: reward = 109.00, steps = 109
22:54:56 [INFO] train episode 349: reward = 105.00, steps = 105
22:54:56 [INFO] train episode 350: reward = 75.00, steps = 75
22:54:56 [INFO] train episode 351: reward = 49.00, steps = 49
22:54:56 [INFO] train episode 352: reward = 93.00, steps = 93
22:54:56 [INFO] train episode 353: reward = 56.00, steps = 56
22:54:56 [INFO] train episode 354: reward = 101.00, steps = 101
22:54:56 [INFO] train episode 355: reward = 54.00, steps = 54
22:54:56 [INFO] train episode 356: reward = 48.00, steps = 48
22:54:56 [INFO] train episode 357: reward = 49.00, steps = 49
22:54:56 [INFO] train episode 358: reward = 64.00, steps = 64
22:54:56 [INFO] train episode 359: reward = 73.00, steps = 73
22:54:56 [INFO] train episode 360: reward = 66.00, steps = 66
22:54:56 [INFO] train episode 361: reward = 47.00, steps = 47
22:54:56 [INFO] train episode 362: reward = 42.00, steps = 42
22:54:56 [INFO] train episode 363: reward = 55.00, steps = 55
22:54:56 [INFO] train episode 364: reward = 43.00, steps = 43
22:54:56 [INFO] train episode 365: reward = 55.00, steps = 55
22:54:56 [INFO] train episode 366: reward = 76.00, steps = 76
22:54:56 [INFO] train episode 367: reward = 45.00, steps = 45
22:54:56 [INFO] train episode 368: reward = 59.00, steps = 59
22:54:56 [INFO] train episode 369: reward = 48.00, steps = 48
22:54:56 [INFO] train episode 370: reward = 80.00, steps = 80
22:54:56 [INFO] train episode 371: reward = 61.00, steps = 61
22:54:56 [INFO] train episode 372: reward = 36.00, steps = 36
22:54:56 [INFO] train episode 373: reward = 79.00, steps = 79
22:54:56 [INFO] train episode 374: reward = 45.00, steps = 45
22:54:56 [INFO] train episode 375: reward = 45.00, steps = 45
22:54:56 [INFO] train episode 376: reward = 68.00, steps = 68
22:54:56 [INFO] train episode 377: reward = 116.00, steps = 116
22:54:56 [INFO] train episode 378: reward = 52.00, steps = 52
22:54:56 [INFO] train episode 379: reward = 53.00, steps = 53
22:54:57 [INFO] train episode 380: reward = 57.00, steps = 57
22:54:57 [INFO] train episode 381: reward = 88.00, steps = 88
22:54:57 [INFO] train episode 382: reward = 46.00, steps = 46
22:54:57 [INFO] train episode 383: reward = 66.00, steps = 66
22:54:57 [INFO] train episode 384: reward = 55.00, steps = 55
22:54:57 [INFO] train episode 385: reward = 52.00, steps = 52
22:54:57 [INFO] train episode 386: reward = 140.00, steps = 140
22:54:57 [INFO] train episode 387: reward = 108.00, steps = 108
22:54:57 [INFO] train episode 388: reward = 133.00, steps = 133
22:54:57 [INFO] train episode 389: reward = 77.00, steps = 77
22:54:57 [INFO] train episode 390: reward = 48.00, steps = 48
22:54:57 [INFO] train episode 391: reward = 43.00, steps = 43
22:54:57 [INFO] train episode 392: reward = 64.00, steps = 64
22:54:57 [INFO] train episode 393: reward = 66.00, steps = 66
22:54:57 [INFO] train episode 394: reward = 72.00, steps = 72
22:54:57 [INFO] train episode 395: reward = 68.00, steps = 68
22:54:57 [INFO] train episode 396: reward = 56.00, steps = 56
22:54:57 [INFO] train episode 397: reward = 83.00, steps = 83
22:54:57 [INFO] train episode 398: reward = 87.00, steps = 87
22:54:57 [INFO] train episode 399: reward = 81.00, steps = 81
22:54:57 [INFO] train episode 400: reward = 48.00, steps = 48
22:54:57 [INFO] train episode 401: reward = 54.00, steps = 54
22:54:57 [INFO] train episode 402: reward = 81.00, steps = 81
22:54:57 [INFO] train episode 403: reward = 72.00, steps = 72
22:54:57 [INFO] train episode 404: reward = 89.00, steps = 89
22:54:57 [INFO] train episode 405: reward = 80.00, steps = 80
22:54:57 [INFO] train episode 406: reward = 74.00, steps = 74
22:54:57 [INFO] train episode 407: reward = 62.00, steps = 62
22:54:57 [INFO] train episode 408: reward = 51.00, steps = 51
22:54:58 [INFO] train episode 409: reward = 53.00, steps = 53
22:54:58 [INFO] train episode 410: reward = 62.00, steps = 62
22:54:58 [INFO] train episode 411: reward = 64.00, steps = 64
22:54:58 [INFO] train episode 412: reward = 59.00, steps = 59
22:54:58 [INFO] train episode 413: reward = 41.00, steps = 41
22:54:58 [INFO] train episode 414: reward = 99.00, steps = 99
22:54:58 [INFO] train episode 415: reward = 78.00, steps = 78
22:54:58 [INFO] train episode 416: reward = 74.00, steps = 74
22:54:58 [INFO] train episode 417: reward = 43.00, steps = 43
22:54:58 [INFO] train episode 418: reward = 45.00, steps = 45
22:54:58 [INFO] train episode 419: reward = 60.00, steps = 60
22:54:58 [INFO] train episode 420: reward = 64.00, steps = 64
22:54:58 [INFO] train episode 421: reward = 51.00, steps = 51
22:54:58 [INFO] train episode 422: reward = 87.00, steps = 87
22:54:58 [INFO] train episode 423: reward = 46.00, steps = 46
22:54:58 [INFO] train episode 424: reward = 51.00, steps = 51
22:54:58 [INFO] train episode 425: reward = 129.00, steps = 129
22:54:58 [INFO] train episode 426: reward = 92.00, steps = 92
22:54:58 [INFO] train episode 427: reward = 42.00, steps = 42
22:54:58 [INFO] train episode 428: reward = 85.00, steps = 85
22:54:58 [INFO] train episode 429: reward = 54.00, steps = 54
22:54:58 [INFO] train episode 430: reward = 53.00, steps = 53
22:54:58 [INFO] train episode 431: reward = 62.00, steps = 62
22:54:58 [INFO] train episode 432: reward = 72.00, steps = 72
22:54:58 [INFO] train episode 433: reward = 44.00, steps = 44
22:54:58 [INFO] train episode 434: reward = 72.00, steps = 72
22:54:58 [INFO] train episode 435: reward = 67.00, steps = 67
22:54:58 [INFO] train episode 436: reward = 45.00, steps = 45
22:54:58 [INFO] train episode 437: reward = 147.00, steps = 147
22:54:59 [INFO] train episode 438: reward = 54.00, steps = 54
22:54:59 [INFO] train episode 439: reward = 77.00, steps = 77
22:54:59 [INFO] train episode 440: reward = 129.00, steps = 129
22:54:59 [INFO] train episode 441: reward = 55.00, steps = 55
22:54:59 [INFO] train episode 442: reward = 55.00, steps = 55
22:54:59 [INFO] train episode 443: reward = 67.00, steps = 67
22:54:59 [INFO] train episode 444: reward = 57.00, steps = 57
22:54:59 [INFO] train episode 445: reward = 83.00, steps = 83
22:54:59 [INFO] train episode 446: reward = 41.00, steps = 41
22:54:59 [INFO] train episode 447: reward = 67.00, steps = 67
22:54:59 [INFO] train episode 448: reward = 82.00, steps = 82
22:54:59 [INFO] train episode 449: reward = 64.00, steps = 64
22:54:59 [INFO] train episode 450: reward = 73.00, steps = 73
22:54:59 [INFO] train episode 451: reward = 110.00, steps = 110
22:54:59 [INFO] train episode 452: reward = 43.00, steps = 43
22:54:59 [INFO] train episode 453: reward = 43.00, steps = 43
22:54:59 [INFO] train episode 454: reward = 56.00, steps = 56
22:54:59 [INFO] train episode 455: reward = 40.00, steps = 40
22:54:59 [INFO] train episode 456: reward = 86.00, steps = 86
22:54:59 [INFO] train episode 457: reward = 66.00, steps = 66
22:54:59 [INFO] train episode 458: reward = 75.00, steps = 75
22:54:59 [INFO] train episode 459: reward = 154.00, steps = 154
22:54:59 [INFO] train episode 460: reward = 71.00, steps = 71
22:54:59 [INFO] train episode 461: reward = 76.00, steps = 76
22:54:59 [INFO] train episode 462: reward = 58.00, steps = 58
22:54:59 [INFO] train episode 463: reward = 78.00, steps = 78
22:54:59 [INFO] train episode 464: reward = 55.00, steps = 55
22:54:59 [INFO] train episode 465: reward = 63.00, steps = 63
22:54:59 [INFO] train episode 466: reward = 45.00, steps = 45
22:55:00 [INFO] train episode 467: reward = 108.00, steps = 108
22:55:00 [INFO] train episode 468: reward = 74.00, steps = 74
22:55:00 [INFO] train episode 469: reward = 157.00, steps = 157
22:55:00 [INFO] train episode 470: reward = 77.00, steps = 77
22:55:00 [INFO] train episode 471: reward = 93.00, steps = 93
22:55:00 [INFO] train episode 472: reward = 110.00, steps = 110
22:55:00 [INFO] train episode 473: reward = 73.00, steps = 73
22:55:00 [INFO] train episode 474: reward = 52.00, steps = 52
22:55:00 [INFO] train episode 475: reward = 70.00, steps = 70
22:55:00 [INFO] train episode 476: reward = 54.00, steps = 54
22:55:00 [INFO] train episode 477: reward = 74.00, steps = 74
22:55:00 [INFO] train episode 478: reward = 49.00, steps = 49
22:55:00 [INFO] train episode 479: reward = 94.00, steps = 94
22:55:00 [INFO] train episode 480: reward = 55.00, steps = 55
22:55:00 [INFO] train episode 481: reward = 60.00, steps = 60
22:55:00 [INFO] train episode 482: reward = 101.00, steps = 101
22:55:00 [INFO] train episode 483: reward = 83.00, steps = 83
22:55:00 [INFO] train episode 484: reward = 60.00, steps = 60
22:55:00 [INFO] train episode 485: reward = 55.00, steps = 55
22:55:00 [INFO] train episode 486: reward = 96.00, steps = 96
22:55:00 [INFO] train episode 487: reward = 42.00, steps = 42
22:55:00 [INFO] train episode 488: reward = 77.00, steps = 77
22:55:00 [INFO] train episode 489: reward = 44.00, steps = 44
22:55:01 [INFO] train episode 490: reward = 81.00, steps = 81
22:55:01 [INFO] train episode 491: reward = 79.00, steps = 79
22:55:01 [INFO] train episode 492: reward = 59.00, steps = 59
22:55:01 [INFO] train episode 493: reward = 97.00, steps = 97
22:55:01 [INFO] train episode 494: reward = 65.00, steps = 65
22:55:01 [INFO] train episode 495: reward = 67.00, steps = 67
22:55:01 [INFO] train episode 496: reward = 41.00, steps = 41
22:55:01 [INFO] train episode 497: reward = 45.00, steps = 45
22:55:01 [INFO] train episode 498: reward = 60.00, steps = 60
22:55:01 [INFO] train episode 499: reward = 52.00, steps = 52
22:55:01 [INFO] train episode 500: reward = 58.00, steps = 58
22:55:01 [INFO] train episode 501: reward = 86.00, steps = 86
22:55:01 [INFO] train episode 502: reward = 52.00, steps = 52
22:55:01 [INFO] train episode 503: reward = 45.00, steps = 45
22:55:01 [INFO] train episode 504: reward = 70.00, steps = 70
22:55:01 [INFO] train episode 505: reward = 54.00, steps = 54
22:55:01 [INFO] train episode 506: reward = 90.00, steps = 90
22:55:01 [INFO] train episode 507: reward = 44.00, steps = 44
22:55:01 [INFO] train episode 508: reward = 69.00, steps = 69
22:55:01 [INFO] train episode 509: reward = 113.00, steps = 113
22:55:01 [INFO] train episode 510: reward = 71.00, steps = 71
22:55:01 [INFO] train episode 511: reward = 81.00, steps = 81
22:55:01 [INFO] train episode 512: reward = 65.00, steps = 65
22:55:01 [INFO] train episode 513: reward = 78.00, steps = 78
22:55:01 [INFO] train episode 514: reward = 67.00, steps = 67
22:55:01 [INFO] train episode 515: reward = 119.00, steps = 119
22:55:01 [INFO] train episode 516: reward = 51.00, steps = 51
22:55:01 [INFO] train episode 517: reward = 71.00, steps = 71
22:55:02 [INFO] train episode 518: reward = 84.00, steps = 84
22:55:02 [INFO] train episode 519: reward = 51.00, steps = 51
22:55:02 [INFO] train episode 520: reward = 118.00, steps = 118
22:55:02 [INFO] train episode 521: reward = 45.00, steps = 45
22:55:02 [INFO] train episode 522: reward = 62.00, steps = 62
22:55:02 [INFO] train episode 523: reward = 53.00, steps = 53
22:55:02 [INFO] train episode 524: reward = 110.00, steps = 110
22:55:02 [INFO] train episode 525: reward = 39.00, steps = 39
22:55:02 [INFO] train episode 526: reward = 45.00, steps = 45
22:55:02 [INFO] train episode 527: reward = 51.00, steps = 51
22:55:02 [INFO] train episode 528: reward = 127.00, steps = 127
22:55:02 [INFO] train episode 529: reward = 58.00, steps = 58
22:55:02 [INFO] train episode 530: reward = 55.00, steps = 55
22:55:02 [INFO] train episode 531: reward = 63.00, steps = 63
22:55:02 [INFO] train episode 532: reward = 57.00, steps = 57
22:55:02 [INFO] train episode 533: reward = 89.00, steps = 89
22:55:02 [INFO] train episode 534: reward = 92.00, steps = 92
22:55:02 [INFO] train episode 535: reward = 61.00, steps = 61
22:55:02 [INFO] train episode 536: reward = 78.00, steps = 78
22:55:02 [INFO] train episode 537: reward = 71.00, steps = 71
22:55:02 [INFO] train episode 538: reward = 77.00, steps = 77
22:55:02 [INFO] train episode 539: reward = 61.00, steps = 61
22:55:02 [INFO] train episode 540: reward = 59.00, steps = 59
22:55:02 [INFO] train episode 541: reward = 44.00, steps = 44
22:55:02 [INFO] train episode 542: reward = 83.00, steps = 83
22:55:02 [INFO] train episode 543: reward = 73.00, steps = 73
22:55:02 [INFO] train episode 544: reward = 74.00, steps = 74
22:55:02 [INFO] train episode 545: reward = 41.00, steps = 41
22:55:03 [INFO] train episode 546: reward = 94.00, steps = 94
22:55:03 [INFO] train episode 547: reward = 100.00, steps = 100
22:55:03 [INFO] train episode 548: reward = 88.00, steps = 88
22:55:03 [INFO] train episode 549: reward = 45.00, steps = 45
22:55:03 [INFO] train episode 550: reward = 94.00, steps = 94
22:55:03 [INFO] train episode 551: reward = 48.00, steps = 48
22:55:03 [INFO] train episode 552: reward = 71.00, steps = 71
22:55:03 [INFO] train episode 553: reward = 69.00, steps = 69
22:55:03 [INFO] train episode 554: reward = 75.00, steps = 75
22:55:03 [INFO] train episode 555: reward = 57.00, steps = 57
22:55:03 [INFO] train episode 556: reward = 85.00, steps = 85
22:55:03 [INFO] train episode 557: reward = 68.00, steps = 68
22:55:03 [INFO] train episode 558: reward = 82.00, steps = 82
22:55:03 [INFO] train episode 559: reward = 48.00, steps = 48
22:55:03 [INFO] train episode 560: reward = 123.00, steps = 123
22:55:03 [INFO] train episode 561: reward = 64.00, steps = 64
22:55:03 [INFO] train episode 562: reward = 61.00, steps = 61
22:55:03 [INFO] train episode 563: reward = 67.00, steps = 67
22:55:03 [INFO] train episode 564: reward = 59.00, steps = 59
22:55:03 [INFO] train episode 565: reward = 58.00, steps = 58
22:55:03 [INFO] train episode 566: reward = 52.00, steps = 52
22:55:03 [INFO] train episode 567: reward = 74.00, steps = 74
22:55:03 [INFO] train episode 568: reward = 74.00, steps = 74
22:55:03 [INFO] train episode 569: reward = 55.00, steps = 55
22:55:03 [INFO] train episode 570: reward = 64.00, steps = 64
22:55:03 [INFO] train episode 571: reward = 47.00, steps = 47
22:55:03 [INFO] train episode 572: reward = 56.00, steps = 56
22:55:03 [INFO] train episode 573: reward = 61.00, steps = 61
22:55:03 [INFO] train episode 574: reward = 60.00, steps = 60
22:55:03 [INFO] train episode 575: reward = 49.00, steps = 49
22:55:03 [INFO] train episode 576: reward = 52.00, steps = 52
22:55:03 [INFO] train episode 577: reward = 82.00, steps = 82
22:55:04 [INFO] train episode 578: reward = 58.00, steps = 58
22:55:04 [INFO] train episode 579: reward = 91.00, steps = 91
22:55:04 [INFO] train episode 580: reward = 131.00, steps = 131
22:55:04 [INFO] train episode 581: reward = 49.00, steps = 49
22:55:04 [INFO] train episode 582: reward = 64.00, steps = 64
22:55:04 [INFO] train episode 583: reward = 80.00, steps = 80
22:55:04 [INFO] train episode 584: reward = 55.00, steps = 55
22:55:04 [INFO] train episode 585: reward = 78.00, steps = 78
22:55:04 [INFO] train episode 586: reward = 104.00, steps = 104
22:55:04 [INFO] train episode 587: reward = 113.00, steps = 113
22:55:04 [INFO] train episode 588: reward = 58.00, steps = 58
22:55:04 [INFO] train episode 589: reward = 37.00, steps = 37
22:55:04 [INFO] train episode 590: reward = 55.00, steps = 55
22:55:04 [INFO] train episode 591: reward = 57.00, steps = 57
22:55:04 [INFO] train episode 592: reward = 75.00, steps = 75
22:55:04 [INFO] train episode 593: reward = 68.00, steps = 68
22:55:04 [INFO] train episode 594: reward = 69.00, steps = 69
22:55:04 [INFO] train episode 595: reward = 39.00, steps = 39
22:55:04 [INFO] train episode 596: reward = 47.00, steps = 47
22:55:04 [INFO] train episode 597: reward = 79.00, steps = 79
22:55:04 [INFO] train episode 598: reward = 53.00, steps = 53
22:55:04 [INFO] train episode 599: reward = 102.00, steps = 102
22:55:04 [INFO] train episode 600: reward = 107.00, steps = 107
22:55:04 [INFO] train episode 601: reward = 63.00, steps = 63
22:55:04 [INFO] train episode 602: reward = 69.00, steps = 69
22:55:04 [INFO] train episode 603: reward = 79.00, steps = 79
22:55:04 [INFO] train episode 604: reward = 75.00, steps = 75
22:55:05 [INFO] train episode 605: reward = 114.00, steps = 114
22:55:05 [INFO] train episode 606: reward = 79.00, steps = 79
22:55:05 [INFO] train episode 607: reward = 74.00, steps = 74
22:55:05 [INFO] train episode 608: reward = 87.00, steps = 87
22:55:05 [INFO] train episode 609: reward = 52.00, steps = 52
22:55:05 [INFO] train episode 610: reward = 70.00, steps = 70
22:55:05 [INFO] train episode 611: reward = 95.00, steps = 95
22:55:05 [INFO] train episode 612: reward = 74.00, steps = 74
22:55:05 [INFO] train episode 613: reward = 67.00, steps = 67
22:55:05 [INFO] train episode 614: reward = 73.00, steps = 73
22:55:05 [INFO] train episode 615: reward = 50.00, steps = 50
22:55:05 [INFO] train episode 616: reward = 107.00, steps = 107
22:55:05 [INFO] train episode 617: reward = 57.00, steps = 57
22:55:05 [INFO] train episode 618: reward = 50.00, steps = 50
22:55:05 [INFO] train episode 619: reward = 74.00, steps = 74
22:55:05 [INFO] train episode 620: reward = 89.00, steps = 89
22:55:05 [INFO] train episode 621: reward = 76.00, steps = 76
22:55:05 [INFO] train episode 622: reward = 46.00, steps = 46
22:55:05 [INFO] train episode 623: reward = 41.00, steps = 41
22:55:05 [INFO] train episode 624: reward = 74.00, steps = 74
22:55:05 [INFO] train episode 625: reward = 60.00, steps = 60
22:55:05 [INFO] train episode 626: reward = 57.00, steps = 57
22:55:05 [INFO] train episode 627: reward = 74.00, steps = 74
22:55:05 [INFO] train episode 628: reward = 73.00, steps = 73
22:55:06 [INFO] train episode 629: reward = 58.00, steps = 58
22:55:06 [INFO] train episode 630: reward = 46.00, steps = 46
22:55:06 [INFO] train episode 631: reward = 69.00, steps = 69
22:55:06 [INFO] train episode 632: reward = 73.00, steps = 73
22:55:06 [INFO] train episode 633: reward = 83.00, steps = 83
22:55:06 [INFO] train episode 634: reward = 62.00, steps = 62
22:55:06 [INFO] train episode 635: reward = 113.00, steps = 113
22:55:06 [INFO] train episode 636: reward = 94.00, steps = 94
22:55:06 [INFO] train episode 637: reward = 51.00, steps = 51
22:55:06 [INFO] train episode 638: reward = 104.00, steps = 104
22:55:06 [INFO] train episode 639: reward = 49.00, steps = 49
22:55:06 [INFO] train episode 640: reward = 82.00, steps = 82
22:55:06 [INFO] train episode 641: reward = 77.00, steps = 77
22:55:06 [INFO] train episode 642: reward = 79.00, steps = 79
22:55:06 [INFO] train episode 643: reward = 78.00, steps = 78
22:55:06 [INFO] train episode 644: reward = 57.00, steps = 57
22:55:06 [INFO] train episode 645: reward = 50.00, steps = 50
22:55:06 [INFO] train episode 646: reward = 66.00, steps = 66
22:55:06 [INFO] train episode 647: reward = 53.00, steps = 53
22:55:06 [INFO] train episode 648: reward = 58.00, steps = 58
22:55:06 [INFO] train episode 649: reward = 59.00, steps = 59
22:55:06 [INFO] train episode 650: reward = 96.00, steps = 96
22:55:06 [INFO] train episode 651: reward = 65.00, steps = 65
22:55:06 [INFO] train episode 652: reward = 70.00, steps = 70
22:55:06 [INFO] train episode 653: reward = 62.00, steps = 62
22:55:06 [INFO] train episode 654: reward = 86.00, steps = 86
22:55:06 [INFO] train episode 655: reward = 101.00, steps = 101
22:55:07 [INFO] train episode 656: reward = 66.00, steps = 66
22:55:07 [INFO] train episode 657: reward = 76.00, steps = 76
22:55:07 [INFO] train episode 658: reward = 90.00, steps = 90
22:55:07 [INFO] train episode 659: reward = 65.00, steps = 65
22:55:07 [INFO] train episode 660: reward = 51.00, steps = 51
22:55:07 [INFO] train episode 661: reward = 86.00, steps = 86
22:55:07 [INFO] train episode 662: reward = 60.00, steps = 60
22:55:07 [INFO] train episode 663: reward = 161.00, steps = 161
22:55:07 [INFO] train episode 664: reward = 53.00, steps = 53
22:55:07 [INFO] train episode 665: reward = 45.00, steps = 45
22:55:07 [INFO] train episode 666: reward = 92.00, steps = 92
22:55:07 [INFO] train episode 667: reward = 66.00, steps = 66
22:55:07 [INFO] train episode 668: reward = 144.00, steps = 144
22:55:07 [INFO] train episode 669: reward = 166.00, steps = 166
22:55:07 [INFO] train episode 670: reward = 53.00, steps = 53
22:55:07 [INFO] train episode 671: reward = 53.00, steps = 53
22:55:07 [INFO] train episode 672: reward = 98.00, steps = 98
22:55:07 [INFO] train episode 673: reward = 75.00, steps = 75
22:55:07 [INFO] train episode 674: reward = 73.00, steps = 73
22:55:07 [INFO] train episode 675: reward = 50.00, steps = 50
22:55:07 [INFO] train episode 676: reward = 66.00, steps = 66
22:55:08 [INFO] train episode 677: reward = 140.00, steps = 140
22:55:08 [INFO] train episode 678: reward = 56.00, steps = 56
22:55:08 [INFO] train episode 679: reward = 77.00, steps = 77
22:55:08 [INFO] train episode 680: reward = 76.00, steps = 76
22:55:08 [INFO] train episode 681: reward = 48.00, steps = 48
22:55:08 [INFO] train episode 682: reward = 60.00, steps = 60
22:55:08 [INFO] train episode 683: reward = 61.00, steps = 61
22:55:08 [INFO] train episode 684: reward = 81.00, steps = 81
22:55:08 [INFO] train episode 685: reward = 72.00, steps = 72
22:55:08 [INFO] train episode 686: reward = 81.00, steps = 81
22:55:08 [INFO] train episode 687: reward = 102.00, steps = 102
22:55:08 [INFO] train episode 688: reward = 80.00, steps = 80
22:55:08 [INFO] train episode 689: reward = 82.00, steps = 82
22:55:08 [INFO] train episode 690: reward = 82.00, steps = 82
22:55:08 [INFO] train episode 691: reward = 65.00, steps = 65
22:55:08 [INFO] train episode 692: reward = 109.00, steps = 109
22:55:08 [INFO] train episode 693: reward = 46.00, steps = 46
22:55:08 [INFO] train episode 694: reward = 65.00, steps = 65
22:55:08 [INFO] train episode 695: reward = 74.00, steps = 74
22:55:08 [INFO] train episode 696: reward = 58.00, steps = 58
22:55:08 [INFO] train episode 697: reward = 59.00, steps = 59
22:55:08 [INFO] train episode 698: reward = 72.00, steps = 72
22:55:08 [INFO] train episode 699: reward = 62.00, steps = 62
22:55:08 [INFO] train episode 700: reward = 79.00, steps = 79
22:55:08 [INFO] train episode 701: reward = 185.00, steps = 185
22:55:08 [INFO] train episode 702: reward = 70.00, steps = 70
22:55:09 [INFO] train episode 703: reward = 115.00, steps = 115
22:55:09 [INFO] train episode 704: reward = 117.00, steps = 117
22:55:09 [INFO] train episode 705: reward = 135.00, steps = 135
22:55:09 [INFO] train episode 706: reward = 78.00, steps = 78
22:55:09 [INFO] train episode 707: reward = 146.00, steps = 146
22:55:09 [INFO] train episode 708: reward = 60.00, steps = 60
22:55:09 [INFO] train episode 709: reward = 67.00, steps = 67
22:55:09 [INFO] train episode 710: reward = 71.00, steps = 71
22:55:09 [INFO] train episode 711: reward = 76.00, steps = 76
22:55:09 [INFO] train episode 712: reward = 68.00, steps = 68
22:55:09 [INFO] train episode 713: reward = 68.00, steps = 68
22:55:09 [INFO] train episode 714: reward = 51.00, steps = 51
22:55:09 [INFO] train episode 715: reward = 56.00, steps = 56
22:55:09 [INFO] train episode 716: reward = 50.00, steps = 50
22:55:09 [INFO] train episode 717: reward = 95.00, steps = 95
22:55:09 [INFO] train episode 718: reward = 99.00, steps = 99
22:55:09 [INFO] train episode 719: reward = 116.00, steps = 116
22:55:09 [INFO] train episode 720: reward = 74.00, steps = 74
22:55:09 [INFO] train episode 721: reward = 69.00, steps = 69
22:55:09 [INFO] train episode 722: reward = 93.00, steps = 93
22:55:09 [INFO] train episode 723: reward = 131.00, steps = 131
22:55:09 [INFO] train episode 724: reward = 53.00, steps = 53
22:55:09 [INFO] train episode 725: reward = 88.00, steps = 88
22:55:10 [INFO] train episode 726: reward = 70.00, steps = 70
22:55:10 [INFO] train episode 727: reward = 114.00, steps = 114
22:55:10 [INFO] train episode 728: reward = 129.00, steps = 129
22:55:10 [INFO] train episode 729: reward = 79.00, steps = 79
22:55:10 [INFO] train episode 730: reward = 57.00, steps = 57
22:55:10 [INFO] train episode 731: reward = 154.00, steps = 154
22:55:10 [INFO] train episode 732: reward = 94.00, steps = 94
22:55:10 [INFO] train episode 733: reward = 77.00, steps = 77
22:55:10 [INFO] train episode 734: reward = 52.00, steps = 52
22:55:10 [INFO] train episode 735: reward = 129.00, steps = 129
22:55:10 [INFO] train episode 736: reward = 82.00, steps = 82
22:55:10 [INFO] train episode 737: reward = 86.00, steps = 86
22:55:10 [INFO] train episode 738: reward = 81.00, steps = 81
22:55:10 [INFO] train episode 739: reward = 98.00, steps = 98
22:55:10 [INFO] train episode 740: reward = 68.00, steps = 68
22:55:10 [INFO] train episode 741: reward = 60.00, steps = 60
22:55:10 [INFO] train episode 742: reward = 109.00, steps = 109
22:55:10 [INFO] train episode 743: reward = 69.00, steps = 69
22:55:10 [INFO] train episode 744: reward = 71.00, steps = 71
22:55:10 [INFO] train episode 745: reward = 72.00, steps = 72
22:55:10 [INFO] train episode 746: reward = 50.00, steps = 50
22:55:10 [INFO] train episode 747: reward = 67.00, steps = 67
22:55:10 [INFO] train episode 748: reward = 127.00, steps = 127
22:55:10 [INFO] train episode 749: reward = 75.00, steps = 75
22:55:11 [INFO] train episode 750: reward = 73.00, steps = 73
22:55:11 [INFO] train episode 751: reward = 187.00, steps = 187
22:55:11 [INFO] train episode 752: reward = 84.00, steps = 84
22:55:11 [INFO] train episode 753: reward = 68.00, steps = 68
22:55:11 [INFO] train episode 754: reward = 101.00, steps = 101
22:55:11 [INFO] train episode 755: reward = 82.00, steps = 82
22:55:11 [INFO] train episode 756: reward = 108.00, steps = 108
22:55:11 [INFO] train episode 757: reward = 105.00, steps = 105
22:55:11 [INFO] train episode 758: reward = 59.00, steps = 59
22:55:11 [INFO] train episode 759: reward = 48.00, steps = 48
22:55:11 [INFO] train episode 760: reward = 65.00, steps = 65
22:55:11 [INFO] train episode 761: reward = 51.00, steps = 51
22:55:11 [INFO] train episode 762: reward = 53.00, steps = 53
22:55:11 [INFO] train episode 763: reward = 84.00, steps = 84
22:55:11 [INFO] train episode 764: reward = 70.00, steps = 70
22:55:11 [INFO] train episode 765: reward = 63.00, steps = 63
22:55:11 [INFO] train episode 766: reward = 155.00, steps = 155
22:55:11 [INFO] train episode 767: reward = 78.00, steps = 78
22:55:11 [INFO] train episode 768: reward = 166.00, steps = 166
22:55:11 [INFO] train episode 769: reward = 109.00, steps = 109
22:55:12 [INFO] train episode 770: reward = 95.00, steps = 95
22:55:12 [INFO] train episode 771: reward = 62.00, steps = 62
22:55:12 [INFO] train episode 772: reward = 74.00, steps = 74
22:55:12 [INFO] train episode 773: reward = 78.00, steps = 78
22:55:12 [INFO] train episode 774: reward = 81.00, steps = 81
22:55:12 [INFO] train episode 775: reward = 158.00, steps = 158
22:55:12 [INFO] train episode 776: reward = 78.00, steps = 78
22:55:12 [INFO] train episode 777: reward = 67.00, steps = 67
22:55:12 [INFO] train episode 778: reward = 137.00, steps = 137
22:55:12 [INFO] train episode 779: reward = 105.00, steps = 105
22:55:12 [INFO] train episode 780: reward = 51.00, steps = 51
22:55:12 [INFO] train episode 781: reward = 71.00, steps = 71
22:55:12 [INFO] train episode 782: reward = 61.00, steps = 61
22:55:12 [INFO] train episode 783: reward = 70.00, steps = 70
22:55:12 [INFO] train episode 784: reward = 46.00, steps = 46
22:55:12 [INFO] train episode 785: reward = 65.00, steps = 65
22:55:12 [INFO] train episode 786: reward = 62.00, steps = 62
22:55:12 [INFO] train episode 787: reward = 62.00, steps = 62
22:55:12 [INFO] train episode 788: reward = 67.00, steps = 67
22:55:12 [INFO] train episode 789: reward = 63.00, steps = 63
22:55:13 [INFO] train episode 790: reward = 78.00, steps = 78
22:55:13 [INFO] train episode 791: reward = 119.00, steps = 119
22:55:13 [INFO] train episode 792: reward = 97.00, steps = 97
22:55:13 [INFO] train episode 793: reward = 66.00, steps = 66
22:55:13 [INFO] train episode 794: reward = 78.00, steps = 78
22:55:13 [INFO] train episode 795: reward = 63.00, steps = 63
22:55:13 [INFO] train episode 796: reward = 79.00, steps = 79
22:55:13 [INFO] train episode 797: reward = 96.00, steps = 96
22:55:13 [INFO] train episode 798: reward = 113.00, steps = 113
22:55:13 [INFO] train episode 799: reward = 131.00, steps = 131
22:55:13 [INFO] train episode 800: reward = 105.00, steps = 105
22:55:13 [INFO] train episode 801: reward = 101.00, steps = 101
22:55:13 [INFO] train episode 802: reward = 70.00, steps = 70
22:55:13 [INFO] train episode 803: reward = 98.00, steps = 98
22:55:13 [INFO] train episode 804: reward = 75.00, steps = 75
22:55:13 [INFO] train episode 805: reward = 64.00, steps = 64
22:55:13 [INFO] train episode 806: reward = 54.00, steps = 54
22:55:13 [INFO] train episode 807: reward = 72.00, steps = 72
22:55:13 [INFO] train episode 808: reward = 53.00, steps = 53
22:55:13 [INFO] train episode 809: reward = 58.00, steps = 58
22:55:13 [INFO] train episode 810: reward = 75.00, steps = 75
22:55:13 [INFO] train episode 811: reward = 70.00, steps = 70
22:55:14 [INFO] train episode 812: reward = 87.00, steps = 87
22:55:14 [INFO] train episode 813: reward = 163.00, steps = 163
22:55:14 [INFO] train episode 814: reward = 74.00, steps = 74
22:55:14 [INFO] train episode 815: reward = 64.00, steps = 64
22:55:14 [INFO] train episode 816: reward = 62.00, steps = 62
22:55:14 [INFO] train episode 817: reward = 114.00, steps = 114
22:55:14 [INFO] train episode 818: reward = 99.00, steps = 99
22:55:14 [INFO] train episode 819: reward = 200.00, steps = 200
22:55:14 [INFO] train episode 820: reward = 46.00, steps = 46
22:55:14 [INFO] train episode 821: reward = 51.00, steps = 51
22:55:14 [INFO] train episode 822: reward = 152.00, steps = 152
22:55:14 [INFO] train episode 823: reward = 88.00, steps = 88
22:55:14 [INFO] train episode 824: reward = 82.00, steps = 82
22:55:14 [INFO] train episode 825: reward = 89.00, steps = 89
22:55:14 [INFO] train episode 826: reward = 58.00, steps = 58
22:55:14 [INFO] train episode 827: reward = 57.00, steps = 57
22:55:14 [INFO] train episode 828: reward = 131.00, steps = 131
22:55:14 [INFO] train episode 829: reward = 50.00, steps = 50
22:55:14 [INFO] train episode 830: reward = 71.00, steps = 71
22:55:14 [INFO] train episode 831: reward = 81.00, steps = 81
22:55:14 [INFO] train episode 832: reward = 68.00, steps = 68
22:55:15 [INFO] train episode 833: reward = 71.00, steps = 71
22:55:15 [INFO] train episode 834: reward = 66.00, steps = 66
22:55:15 [INFO] train episode 835: reward = 68.00, steps = 68
22:55:15 [INFO] train episode 836: reward = 104.00, steps = 104
22:55:15 [INFO] train episode 837: reward = 84.00, steps = 84
22:55:15 [INFO] train episode 838: reward = 92.00, steps = 92
22:55:15 [INFO] train episode 839: reward = 107.00, steps = 107
22:55:15 [INFO] train episode 840: reward = 140.00, steps = 140
22:55:15 [INFO] train episode 841: reward = 78.00, steps = 78
22:55:15 [INFO] train episode 842: reward = 75.00, steps = 75
22:55:15 [INFO] train episode 843: reward = 65.00, steps = 65
22:55:15 [INFO] train episode 844: reward = 64.00, steps = 64
22:55:15 [INFO] train episode 845: reward = 70.00, steps = 70
22:55:15 [INFO] train episode 846: reward = 55.00, steps = 55
22:55:15 [INFO] train episode 847: reward = 78.00, steps = 78
22:55:15 [INFO] train episode 848: reward = 87.00, steps = 87
22:55:15 [INFO] train episode 849: reward = 101.00, steps = 101
22:55:15 [INFO] train episode 850: reward = 73.00, steps = 73
22:55:15 [INFO] train episode 851: reward = 167.00, steps = 167
22:55:15 [INFO] train episode 852: reward = 64.00, steps = 64
22:55:15 [INFO] train episode 853: reward = 80.00, steps = 80
22:55:16 [INFO] train episode 854: reward = 90.00, steps = 90
22:55:16 [INFO] train episode 855: reward = 115.00, steps = 115
22:55:16 [INFO] train episode 856: reward = 113.00, steps = 113
22:55:16 [INFO] train episode 857: reward = 70.00, steps = 70
22:55:16 [INFO] train episode 858: reward = 85.00, steps = 85
22:55:16 [INFO] train episode 859: reward = 101.00, steps = 101
22:55:16 [INFO] train episode 860: reward = 72.00, steps = 72
22:55:16 [INFO] train episode 861: reward = 76.00, steps = 76
22:55:16 [INFO] train episode 862: reward = 74.00, steps = 74
22:55:16 [INFO] train episode 863: reward = 69.00, steps = 69
22:55:16 [INFO] train episode 864: reward = 51.00, steps = 51
22:55:16 [INFO] train episode 865: reward = 87.00, steps = 87
22:55:16 [INFO] train episode 866: reward = 55.00, steps = 55
22:55:16 [INFO] train episode 867: reward = 98.00, steps = 98
22:55:16 [INFO] train episode 868: reward = 63.00, steps = 63
22:55:16 [INFO] train episode 869: reward = 108.00, steps = 108
22:55:16 [INFO] train episode 870: reward = 67.00, steps = 67
22:55:16 [INFO] train episode 871: reward = 104.00, steps = 104
22:55:16 [INFO] train episode 872: reward = 98.00, steps = 98
22:55:16 [INFO] train episode 873: reward = 108.00, steps = 108
22:55:16 [INFO] train episode 874: reward = 85.00, steps = 85
22:55:16 [INFO] train episode 875: reward = 71.00, steps = 71
22:55:16 [INFO] train episode 876: reward = 57.00, steps = 57
22:55:16 [INFO] train episode 877: reward = 116.00, steps = 116
22:55:16 [INFO] train episode 878: reward = 105.00, steps = 105
22:55:17 [INFO] train episode 879: reward = 108.00, steps = 108
22:55:17 [INFO] train episode 880: reward = 139.00, steps = 139
22:55:17 [INFO] train episode 881: reward = 103.00, steps = 103
22:55:17 [INFO] train episode 882: reward = 61.00, steps = 61
22:55:17 [INFO] train episode 883: reward = 89.00, steps = 89
22:55:17 [INFO] train episode 884: reward = 73.00, steps = 73
22:55:17 [INFO] train episode 885: reward = 88.00, steps = 88
22:55:17 [INFO] train episode 886: reward = 97.00, steps = 97
22:55:17 [INFO] train episode 887: reward = 106.00, steps = 106
22:55:17 [INFO] train episode 888: reward = 66.00, steps = 66
22:55:17 [INFO] train episode 889: reward = 55.00, steps = 55
22:55:17 [INFO] train episode 890: reward = 102.00, steps = 102
22:55:17 [INFO] train episode 891: reward = 87.00, steps = 87
22:55:17 [INFO] train episode 892: reward = 93.00, steps = 93
22:55:17 [INFO] train episode 893: reward = 69.00, steps = 69
22:55:17 [INFO] train episode 894: reward = 65.00, steps = 65
22:55:17 [INFO] train episode 895: reward = 110.00, steps = 110
22:55:18 [INFO] train episode 896: reward = 200.00, steps = 200
22:55:18 [INFO] train episode 897: reward = 79.00, steps = 79
22:55:18 [INFO] train episode 898: reward = 141.00, steps = 141
22:55:18 [INFO] train episode 899: reward = 75.00, steps = 75
22:55:18 [INFO] train episode 900: reward = 74.00, steps = 74
22:55:18 [INFO] train episode 901: reward = 96.00, steps = 96
22:55:18 [INFO] train episode 902: reward = 98.00, steps = 98
22:55:18 [INFO] train episode 903: reward = 103.00, steps = 103
22:55:18 [INFO] train episode 904: reward = 74.00, steps = 74
22:55:18 [INFO] train episode 905: reward = 59.00, steps = 59
22:55:18 [INFO] train episode 906: reward = 111.00, steps = 111
22:55:18 [INFO] train episode 907: reward = 79.00, steps = 79
22:55:18 [INFO] train episode 908: reward = 89.00, steps = 89
22:55:18 [INFO] train episode 909: reward = 112.00, steps = 112
22:55:18 [INFO] train episode 910: reward = 64.00, steps = 64
22:55:18 [INFO] train episode 911: reward = 54.00, steps = 54
22:55:18 [INFO] train episode 912: reward = 51.00, steps = 51
22:55:18 [INFO] train episode 913: reward = 133.00, steps = 133
22:55:18 [INFO] train episode 914: reward = 77.00, steps = 77
22:55:18 [INFO] train episode 915: reward = 94.00, steps = 94
22:55:19 [INFO] train episode 916: reward = 91.00, steps = 91
22:55:19 [INFO] train episode 917: reward = 104.00, steps = 104
22:55:19 [INFO] train episode 918: reward = 85.00, steps = 85
22:55:19 [INFO] train episode 919: reward = 67.00, steps = 67
22:55:19 [INFO] train episode 920: reward = 71.00, steps = 71
22:55:19 [INFO] train episode 921: reward = 79.00, steps = 79
22:55:19 [INFO] train episode 922: reward = 80.00, steps = 80
22:55:19 [INFO] train episode 923: reward = 69.00, steps = 69
22:55:19 [INFO] train episode 924: reward = 99.00, steps = 99
22:55:19 [INFO] train episode 925: reward = 68.00, steps = 68
22:55:19 [INFO] train episode 926: reward = 71.00, steps = 71
22:55:19 [INFO] train episode 927: reward = 87.00, steps = 87
22:55:19 [INFO] train episode 928: reward = 61.00, steps = 61
22:55:19 [INFO] train episode 929: reward = 93.00, steps = 93
22:55:19 [INFO] train episode 930: reward = 127.00, steps = 127
22:55:19 [INFO] train episode 931: reward = 115.00, steps = 115
22:55:19 [INFO] train episode 932: reward = 98.00, steps = 98
22:55:19 [INFO] train episode 933: reward = 94.00, steps = 94
22:55:19 [INFO] train episode 934: reward = 86.00, steps = 86
22:55:19 [INFO] train episode 935: reward = 91.00, steps = 91
22:55:20 [INFO] train episode 936: reward = 136.00, steps = 136
22:55:20 [INFO] train episode 937: reward = 75.00, steps = 75
22:55:20 [INFO] train episode 938: reward = 74.00, steps = 74
22:55:20 [INFO] train episode 939: reward = 67.00, steps = 67
22:55:20 [INFO] train episode 940: reward = 88.00, steps = 88
22:55:20 [INFO] train episode 941: reward = 88.00, steps = 88
22:55:20 [INFO] train episode 942: reward = 136.00, steps = 136
22:55:20 [INFO] train episode 943: reward = 56.00, steps = 56
22:55:20 [INFO] train episode 944: reward = 120.00, steps = 120
22:55:20 [INFO] train episode 945: reward = 86.00, steps = 86
22:55:20 [INFO] train episode 946: reward = 165.00, steps = 165
22:55:20 [INFO] train episode 947: reward = 90.00, steps = 90
22:55:20 [INFO] train episode 948: reward = 69.00, steps = 69
22:55:20 [INFO] train episode 949: reward = 120.00, steps = 120
22:55:20 [INFO] train episode 950: reward = 118.00, steps = 118
22:55:20 [INFO] train episode 951: reward = 61.00, steps = 61
22:55:20 [INFO] train episode 952: reward = 69.00, steps = 69
22:55:20 [INFO] train episode 953: reward = 82.00, steps = 82
22:55:20 [INFO] train episode 954: reward = 113.00, steps = 113
22:55:20 [INFO] train episode 955: reward = 64.00, steps = 64
22:55:20 [INFO] train episode 956: reward = 148.00, steps = 148
22:55:20 [INFO] train episode 957: reward = 70.00, steps = 70
22:55:21 [INFO] train episode 958: reward = 119.00, steps = 119
22:55:21 [INFO] train episode 959: reward = 78.00, steps = 78
22:55:21 [INFO] train episode 960: reward = 100.00, steps = 100
22:55:21 [INFO] train episode 961: reward = 129.00, steps = 129
22:55:21 [INFO] train episode 962: reward = 105.00, steps = 105
22:55:21 [INFO] train episode 963: reward = 58.00, steps = 58
22:55:21 [INFO] train episode 964: reward = 93.00, steps = 93
22:55:21 [INFO] train episode 965: reward = 93.00, steps = 93
22:55:21 [INFO] train episode 966: reward = 67.00, steps = 67
22:55:21 [INFO] train episode 967: reward = 78.00, steps = 78
22:55:21 [INFO] train episode 968: reward = 71.00, steps = 71
22:55:21 [INFO] train episode 969: reward = 153.00, steps = 153
22:55:21 [INFO] train episode 970: reward = 77.00, steps = 77
22:55:21 [INFO] train episode 971: reward = 73.00, steps = 73
22:55:21 [INFO] train episode 972: reward = 87.00, steps = 87
22:55:21 [INFO] train episode 973: reward = 78.00, steps = 78
22:55:21 [INFO] train episode 974: reward = 97.00, steps = 97
22:55:21 [INFO] train episode 975: reward = 123.00, steps = 123
22:55:21 [INFO] train episode 976: reward = 95.00, steps = 95
22:55:21 [INFO] train episode 977: reward = 74.00, steps = 74
22:55:21 [INFO] train episode 978: reward = 74.00, steps = 74
22:55:21 [INFO] train episode 979: reward = 131.00, steps = 131
22:55:21 [INFO] train episode 980: reward = 126.00, steps = 126
22:55:22 [INFO] train episode 981: reward = 108.00, steps = 108
22:55:22 [INFO] train episode 982: reward = 138.00, steps = 138
22:55:22 [INFO] train episode 983: reward = 136.00, steps = 136
22:55:22 [INFO] train episode 984: reward = 69.00, steps = 69
22:55:22 [INFO] train episode 985: reward = 77.00, steps = 77
22:55:22 [INFO] train episode 986: reward = 94.00, steps = 94
22:55:22 [INFO] train episode 987: reward = 73.00, steps = 73
22:55:22 [INFO] train episode 988: reward = 76.00, steps = 76
22:55:22 [INFO] train episode 989: reward = 94.00, steps = 94
22:55:22 [INFO] train episode 990: reward = 99.00, steps = 99
22:55:22 [INFO] train episode 991: reward = 67.00, steps = 67
22:55:22 [INFO] train episode 992: reward = 67.00, steps = 67
22:55:22 [INFO] train episode 993: reward = 61.00, steps = 61
22:55:22 [INFO] train episode 994: reward = 83.00, steps = 83
22:55:22 [INFO] train episode 995: reward = 84.00, steps = 84
22:55:22 [INFO] train episode 996: reward = 77.00, steps = 77
22:55:22 [INFO] train episode 997: reward = 76.00, steps = 76
22:55:22 [INFO] train episode 998: reward = 89.00, steps = 89
22:55:22 [INFO] train episode 999: reward = 68.00, steps = 68
22:55:22 [INFO] train episode 1000: reward = 98.00, steps = 98
22:55:22 [INFO] train episode 1001: reward = 71.00, steps = 71
22:55:22 [INFO] train episode 1002: reward = 71.00, steps = 71
22:55:22 [INFO] train episode 1003: reward = 57.00, steps = 57
22:55:22 [INFO] train episode 1004: reward = 97.00, steps = 97
22:55:23 [INFO] train episode 1005: reward = 113.00, steps = 113
22:55:23 [INFO] train episode 1006: reward = 81.00, steps = 81
22:55:23 [INFO] train episode 1007: reward = 107.00, steps = 107
22:55:23 [INFO] train episode 1008: reward = 77.00, steps = 77
22:55:23 [INFO] train episode 1009: reward = 97.00, steps = 97
22:55:23 [INFO] train episode 1010: reward = 101.00, steps = 101
22:55:23 [INFO] train episode 1011: reward = 56.00, steps = 56
22:55:23 [INFO] train episode 1012: reward = 130.00, steps = 130
22:55:23 [INFO] train episode 1013: reward = 113.00, steps = 113
22:55:23 [INFO] train episode 1014: reward = 103.00, steps = 103
22:55:23 [INFO] train episode 1015: reward = 123.00, steps = 123
22:55:23 [INFO] train episode 1016: reward = 95.00, steps = 95
22:55:23 [INFO] train episode 1017: reward = 84.00, steps = 84
22:55:23 [INFO] train episode 1018: reward = 95.00, steps = 95
22:55:23 [INFO] train episode 1019: reward = 79.00, steps = 79
22:55:23 [INFO] train episode 1020: reward = 166.00, steps = 166
22:55:23 [INFO] train episode 1021: reward = 62.00, steps = 62
22:55:23 [INFO] train episode 1022: reward = 130.00, steps = 130
22:55:23 [INFO] train episode 1023: reward = 97.00, steps = 97
22:55:23 [INFO] train episode 1024: reward = 89.00, steps = 89
22:55:24 [INFO] train episode 1025: reward = 95.00, steps = 95
22:55:24 [INFO] train episode 1026: reward = 157.00, steps = 157
22:55:24 [INFO] train episode 1027: reward = 106.00, steps = 106
22:55:24 [INFO] train episode 1028: reward = 76.00, steps = 76
22:55:24 [INFO] train episode 1029: reward = 72.00, steps = 72
22:55:24 [INFO] train episode 1030: reward = 76.00, steps = 76
22:55:24 [INFO] train episode 1031: reward = 72.00, steps = 72
22:55:24 [INFO] train episode 1032: reward = 72.00, steps = 72
22:55:24 [INFO] train episode 1033: reward = 93.00, steps = 93
22:55:24 [INFO] train episode 1034: reward = 84.00, steps = 84
22:55:24 [INFO] train episode 1035: reward = 90.00, steps = 90
22:55:24 [INFO] train episode 1036: reward = 71.00, steps = 71
22:55:24 [INFO] train episode 1037: reward = 58.00, steps = 58
22:55:24 [INFO] train episode 1038: reward = 122.00, steps = 122
22:55:24 [INFO] train episode 1039: reward = 87.00, steps = 87
22:55:24 [INFO] train episode 1040: reward = 81.00, steps = 81
22:55:24 [INFO] train episode 1041: reward = 82.00, steps = 82
22:55:24 [INFO] train episode 1042: reward = 59.00, steps = 59
22:55:24 [INFO] train episode 1043: reward = 91.00, steps = 91
22:55:24 [INFO] train episode 1044: reward = 132.00, steps = 132
22:55:24 [INFO] train episode 1045: reward = 113.00, steps = 113
22:55:25 [INFO] train episode 1046: reward = 174.00, steps = 174
22:55:25 [INFO] train episode 1047: reward = 99.00, steps = 99
22:55:25 [INFO] train episode 1048: reward = 111.00, steps = 111
22:55:25 [INFO] train episode 1049: reward = 70.00, steps = 70
22:55:25 [INFO] train episode 1050: reward = 63.00, steps = 63
22:55:25 [INFO] train episode 1051: reward = 66.00, steps = 66
22:55:25 [INFO] train episode 1052: reward = 95.00, steps = 95
22:55:25 [INFO] train episode 1053: reward = 103.00, steps = 103
22:55:25 [INFO] train episode 1054: reward = 76.00, steps = 76
22:55:25 [INFO] train episode 1055: reward = 114.00, steps = 114
22:55:25 [INFO] train episode 1056: reward = 57.00, steps = 57
22:55:25 [INFO] train episode 1057: reward = 72.00, steps = 72
22:55:25 [INFO] train episode 1058: reward = 68.00, steps = 68
22:55:25 [INFO] train episode 1059: reward = 78.00, steps = 78
22:55:25 [INFO] train episode 1060: reward = 83.00, steps = 83
22:55:25 [INFO] train episode 1061: reward = 71.00, steps = 71
22:55:25 [INFO] train episode 1062: reward = 69.00, steps = 69
22:55:25 [INFO] train episode 1063: reward = 70.00, steps = 70
22:55:26 [INFO] train episode 1064: reward = 104.00, steps = 104
22:55:26 [INFO] train episode 1065: reward = 86.00, steps = 86
22:55:26 [INFO] train episode 1066: reward = 81.00, steps = 81
22:55:26 [INFO] train episode 1067: reward = 62.00, steps = 62
22:55:26 [INFO] train episode 1068: reward = 93.00, steps = 93
22:55:26 [INFO] train episode 1069: reward = 99.00, steps = 99
22:55:26 [INFO] train episode 1070: reward = 200.00, steps = 200
22:55:26 [INFO] train episode 1071: reward = 98.00, steps = 98
22:55:26 [INFO] train episode 1072: reward = 149.00, steps = 149
22:55:26 [INFO] train episode 1073: reward = 78.00, steps = 78
22:55:26 [INFO] train episode 1074: reward = 71.00, steps = 71
22:55:26 [INFO] train episode 1075: reward = 53.00, steps = 53
22:55:26 [INFO] train episode 1076: reward = 123.00, steps = 123
22:55:26 [INFO] train episode 1077: reward = 124.00, steps = 124
22:55:26 [INFO] train episode 1078: reward = 105.00, steps = 105
22:55:26 [INFO] train episode 1079: reward = 92.00, steps = 92
22:55:26 [INFO] train episode 1080: reward = 127.00, steps = 127
22:55:27 [INFO] train episode 1081: reward = 111.00, steps = 111
22:55:27 [INFO] train episode 1082: reward = 129.00, steps = 129
22:55:27 [INFO] train episode 1083: reward = 117.00, steps = 117
22:55:27 [INFO] train episode 1084: reward = 100.00, steps = 100
22:55:27 [INFO] train episode 1085: reward = 78.00, steps = 78
22:55:27 [INFO] train episode 1086: reward = 63.00, steps = 63
22:55:27 [INFO] train episode 1087: reward = 130.00, steps = 130
22:55:27 [INFO] train episode 1088: reward = 78.00, steps = 78
22:55:27 [INFO] train episode 1089: reward = 93.00, steps = 93
22:55:27 [INFO] train episode 1090: reward = 114.00, steps = 114
22:55:27 [INFO] train episode 1091: reward = 136.00, steps = 136
22:55:27 [INFO] train episode 1092: reward = 69.00, steps = 69
22:55:27 [INFO] train episode 1093: reward = 71.00, steps = 71
22:55:27 [INFO] train episode 1094: reward = 89.00, steps = 89
22:55:27 [INFO] train episode 1095: reward = 72.00, steps = 72
22:55:27 [INFO] train episode 1096: reward = 79.00, steps = 79
22:55:27 [INFO] train episode 1097: reward = 99.00, steps = 99
22:55:27 [INFO] train episode 1098: reward = 86.00, steps = 86
22:55:27 [INFO] train episode 1099: reward = 71.00, steps = 71
22:55:27 [INFO] train episode 1100: reward = 81.00, steps = 81
22:55:27 [INFO] train episode 1101: reward = 89.00, steps = 89
22:55:28 [INFO] train episode 1102: reward = 88.00, steps = 88
22:55:28 [INFO] train episode 1103: reward = 82.00, steps = 82
22:55:28 [INFO] train episode 1104: reward = 113.00, steps = 113
22:55:28 [INFO] train episode 1105: reward = 105.00, steps = 105
22:55:28 [INFO] train episode 1106: reward = 75.00, steps = 75
22:55:28 [INFO] train episode 1107: reward = 111.00, steps = 111
22:55:28 [INFO] train episode 1108: reward = 100.00, steps = 100
22:55:28 [INFO] train episode 1109: reward = 93.00, steps = 93
22:55:28 [INFO] train episode 1110: reward = 79.00, steps = 79
22:55:28 [INFO] train episode 1111: reward = 63.00, steps = 63
22:55:28 [INFO] train episode 1112: reward = 81.00, steps = 81
22:55:28 [INFO] train episode 1113: reward = 87.00, steps = 87
22:55:28 [INFO] train episode 1114: reward = 112.00, steps = 112
22:55:28 [INFO] train episode 1115: reward = 84.00, steps = 84
22:55:28 [INFO] train episode 1116: reward = 74.00, steps = 74
22:55:28 [INFO] train episode 1117: reward = 65.00, steps = 65
22:55:28 [INFO] train episode 1118: reward = 76.00, steps = 76
22:55:28 [INFO] train episode 1119: reward = 68.00, steps = 68
22:55:28 [INFO] train episode 1120: reward = 85.00, steps = 85
22:55:28 [INFO] train episode 1121: reward = 52.00, steps = 52
22:55:28 [INFO] train episode 1122: reward = 76.00, steps = 76
22:55:28 [INFO] train episode 1123: reward = 81.00, steps = 81
22:55:28 [INFO] train episode 1124: reward = 132.00, steps = 132
22:55:29 [INFO] train episode 1125: reward = 88.00, steps = 88
22:55:29 [INFO] train episode 1126: reward = 99.00, steps = 99
22:55:29 [INFO] train episode 1127: reward = 68.00, steps = 68
22:55:29 [INFO] train episode 1128: reward = 74.00, steps = 74
22:55:29 [INFO] train episode 1129: reward = 145.00, steps = 145
22:55:29 [INFO] train episode 1130: reward = 72.00, steps = 72
22:55:29 [INFO] train episode 1131: reward = 111.00, steps = 111
22:55:29 [INFO] train episode 1132: reward = 70.00, steps = 70
22:55:29 [INFO] train episode 1133: reward = 75.00, steps = 75
22:55:29 [INFO] train episode 1134: reward = 87.00, steps = 87
22:55:29 [INFO] train episode 1135: reward = 98.00, steps = 98
22:55:29 [INFO] train episode 1136: reward = 86.00, steps = 86
22:55:29 [INFO] train episode 1137: reward = 85.00, steps = 85
22:55:29 [INFO] train episode 1138: reward = 71.00, steps = 71
22:55:29 [INFO] train episode 1139: reward = 76.00, steps = 76
22:55:29 [INFO] train episode 1140: reward = 95.00, steps = 95
22:55:29 [INFO] train episode 1141: reward = 89.00, steps = 89
22:55:29 [INFO] train episode 1142: reward = 100.00, steps = 100
22:55:29 [INFO] train episode 1143: reward = 85.00, steps = 85
22:55:29 [INFO] train episode 1144: reward = 74.00, steps = 74
22:55:29 [INFO] train episode 1145: reward = 98.00, steps = 98
22:55:29 [INFO] train episode 1146: reward = 94.00, steps = 94
22:55:30 [INFO] train episode 1147: reward = 159.00, steps = 159
22:55:30 [INFO] train episode 1148: reward = 74.00, steps = 74
22:55:30 [INFO] train episode 1149: reward = 69.00, steps = 69
22:55:30 [INFO] train episode 1150: reward = 79.00, steps = 79
22:55:30 [INFO] train episode 1151: reward = 75.00, steps = 75
22:55:30 [INFO] train episode 1152: reward = 76.00, steps = 76
22:55:30 [INFO] train episode 1153: reward = 155.00, steps = 155
22:55:30 [INFO] train episode 1154: reward = 104.00, steps = 104
22:55:30 [INFO] train episode 1155: reward = 77.00, steps = 77
22:55:30 [INFO] train episode 1156: reward = 80.00, steps = 80
22:55:30 [INFO] train episode 1157: reward = 87.00, steps = 87
22:55:30 [INFO] train episode 1158: reward = 78.00, steps = 78
22:55:30 [INFO] train episode 1159: reward = 64.00, steps = 64
22:55:30 [INFO] train episode 1160: reward = 71.00, steps = 71
22:55:30 [INFO] train episode 1161: reward = 150.00, steps = 150
22:55:30 [INFO] train episode 1162: reward = 58.00, steps = 58
22:55:30 [INFO] train episode 1163: reward = 98.00, steps = 98
22:55:30 [INFO] train episode 1164: reward = 142.00, steps = 142
22:55:30 [INFO] train episode 1165: reward = 147.00, steps = 147
22:55:30 [INFO] train episode 1166: reward = 137.00, steps = 137
22:55:31 [INFO] train episode 1167: reward = 103.00, steps = 103
22:55:31 [INFO] train episode 1168: reward = 123.00, steps = 123
22:55:31 [INFO] train episode 1169: reward = 82.00, steps = 82
22:55:31 [INFO] train episode 1170: reward = 60.00, steps = 60
22:55:31 [INFO] train episode 1171: reward = 76.00, steps = 76
22:55:31 [INFO] train episode 1172: reward = 64.00, steps = 64
22:55:31 [INFO] train episode 1173: reward = 79.00, steps = 79
22:55:31 [INFO] train episode 1174: reward = 133.00, steps = 133
22:55:31 [INFO] train episode 1175: reward = 68.00, steps = 68
22:55:31 [INFO] train episode 1176: reward = 80.00, steps = 80
22:55:31 [INFO] train episode 1177: reward = 75.00, steps = 75
22:55:31 [INFO] train episode 1178: reward = 92.00, steps = 92
22:55:31 [INFO] train episode 1179: reward = 108.00, steps = 108
22:55:31 [INFO] train episode 1180: reward = 143.00, steps = 143
22:55:31 [INFO] train episode 1181: reward = 145.00, steps = 145
22:55:32 [INFO] train episode 1182: reward = 66.00, steps = 66
22:55:32 [INFO] train episode 1183: reward = 61.00, steps = 61
22:55:32 [INFO] train episode 1184: reward = 51.00, steps = 51
22:55:32 [INFO] train episode 1185: reward = 95.00, steps = 95
22:55:32 [INFO] train episode 1186: reward = 96.00, steps = 96
22:55:32 [INFO] train episode 1187: reward = 80.00, steps = 80
22:55:32 [INFO] train episode 1188: reward = 76.00, steps = 76
22:55:32 [INFO] train episode 1189: reward = 80.00, steps = 80
22:55:32 [INFO] train episode 1190: reward = 75.00, steps = 75
22:55:32 [INFO] train episode 1191: reward = 97.00, steps = 97
22:55:32 [INFO] train episode 1192: reward = 74.00, steps = 74
22:55:32 [INFO] train episode 1193: reward = 115.00, steps = 115
22:55:32 [INFO] train episode 1194: reward = 85.00, steps = 85
22:55:32 [INFO] train episode 1195: reward = 114.00, steps = 114
22:55:32 [INFO] train episode 1196: reward = 79.00, steps = 79
22:55:32 [INFO] train episode 1197: reward = 95.00, steps = 95
22:55:32 [INFO] train episode 1198: reward = 69.00, steps = 69
22:55:32 [INFO] train episode 1199: reward = 73.00, steps = 73
22:55:32 [INFO] train episode 1200: reward = 72.00, steps = 72
22:55:32 [INFO] train episode 1201: reward = 98.00, steps = 98
22:55:32 [INFO] train episode 1202: reward = 74.00, steps = 74
22:55:32 [INFO] train episode 1203: reward = 115.00, steps = 115
22:55:33 [INFO] train episode 1204: reward = 149.00, steps = 149
22:55:33 [INFO] train episode 1205: reward = 106.00, steps = 106
22:55:33 [INFO] train episode 1206: reward = 97.00, steps = 97
22:55:33 [INFO] train episode 1207: reward = 91.00, steps = 91
22:55:33 [INFO] train episode 1208: reward = 65.00, steps = 65
22:55:33 [INFO] train episode 1209: reward = 135.00, steps = 135
22:55:33 [INFO] train episode 1210: reward = 85.00, steps = 85
22:55:33 [INFO] train episode 1211: reward = 71.00, steps = 71
22:55:33 [INFO] train episode 1212: reward = 100.00, steps = 100
22:55:33 [INFO] train episode 1213: reward = 117.00, steps = 117
22:55:33 [INFO] train episode 1214: reward = 122.00, steps = 122
22:55:33 [INFO] train episode 1215: reward = 144.00, steps = 144
22:55:33 [INFO] train episode 1216: reward = 111.00, steps = 111
22:55:33 [INFO] train episode 1217: reward = 188.00, steps = 188
22:55:33 [INFO] train episode 1218: reward = 92.00, steps = 92
22:55:33 [INFO] train episode 1219: reward = 71.00, steps = 71
22:55:33 [INFO] train episode 1220: reward = 83.00, steps = 83
22:55:34 [INFO] train episode 1221: reward = 103.00, steps = 103
22:55:34 [INFO] train episode 1222: reward = 123.00, steps = 123
22:55:34 [INFO] train episode 1223: reward = 84.00, steps = 84
22:55:34 [INFO] train episode 1224: reward = 68.00, steps = 68
22:55:34 [INFO] train episode 1225: reward = 100.00, steps = 100
22:55:34 [INFO] train episode 1226: reward = 87.00, steps = 87
22:55:34 [INFO] train episode 1227: reward = 86.00, steps = 86
22:55:34 [INFO] train episode 1228: reward = 121.00, steps = 121
22:55:34 [INFO] train episode 1229: reward = 89.00, steps = 89
22:55:34 [INFO] train episode 1230: reward = 123.00, steps = 123
22:55:34 [INFO] train episode 1231: reward = 94.00, steps = 94
22:55:34 [INFO] train episode 1232: reward = 84.00, steps = 84
22:55:34 [INFO] train episode 1233: reward = 91.00, steps = 91
22:55:34 [INFO] train episode 1234: reward = 103.00, steps = 103
22:55:34 [INFO] train episode 1235: reward = 113.00, steps = 113
22:55:34 [INFO] train episode 1236: reward = 165.00, steps = 165
22:55:34 [INFO] train episode 1237: reward = 111.00, steps = 111
22:55:35 [INFO] train episode 1238: reward = 108.00, steps = 108
22:55:35 [INFO] train episode 1239: reward = 88.00, steps = 88
22:55:35 [INFO] train episode 1240: reward = 75.00, steps = 75
22:55:35 [INFO] train episode 1241: reward = 136.00, steps = 136
22:55:35 [INFO] train episode 1242: reward = 74.00, steps = 74
22:55:35 [INFO] train episode 1243: reward = 88.00, steps = 88
22:55:35 [INFO] train episode 1244: reward = 81.00, steps = 81
22:55:35 [INFO] train episode 1245: reward = 87.00, steps = 87
22:55:35 [INFO] train episode 1246: reward = 92.00, steps = 92
22:55:35 [INFO] train episode 1247: reward = 92.00, steps = 92
22:55:35 [INFO] train episode 1248: reward = 200.00, steps = 200
22:55:35 [INFO] train episode 1249: reward = 107.00, steps = 107
22:55:35 [INFO] train episode 1250: reward = 190.00, steps = 190
22:55:35 [INFO] train episode 1251: reward = 81.00, steps = 81
22:55:35 [INFO] train episode 1252: reward = 105.00, steps = 105
22:55:35 [INFO] train episode 1253: reward = 108.00, steps = 108
22:55:35 [INFO] train episode 1254: reward = 92.00, steps = 92
22:55:36 [INFO] train episode 1255: reward = 125.00, steps = 125
22:55:36 [INFO] train episode 1256: reward = 89.00, steps = 89
22:55:36 [INFO] train episode 1257: reward = 119.00, steps = 119
22:55:36 [INFO] train episode 1258: reward = 103.00, steps = 103
22:55:36 [INFO] train episode 1259: reward = 127.00, steps = 127
22:55:36 [INFO] train episode 1260: reward = 130.00, steps = 130
22:55:36 [INFO] train episode 1261: reward = 116.00, steps = 116
22:55:36 [INFO] train episode 1262: reward = 72.00, steps = 72
22:55:36 [INFO] train episode 1263: reward = 102.00, steps = 102
22:55:36 [INFO] train episode 1264: reward = 116.00, steps = 116
22:55:36 [INFO] train episode 1265: reward = 107.00, steps = 107
22:55:36 [INFO] train episode 1266: reward = 118.00, steps = 118
22:55:36 [INFO] train episode 1267: reward = 94.00, steps = 94
22:55:36 [INFO] train episode 1268: reward = 79.00, steps = 79
22:55:36 [INFO] train episode 1269: reward = 105.00, steps = 105
22:55:36 [INFO] train episode 1270: reward = 87.00, steps = 87
22:55:37 [INFO] train episode 1271: reward = 100.00, steps = 100
22:55:37 [INFO] train episode 1272: reward = 68.00, steps = 68
22:55:37 [INFO] train episode 1273: reward = 73.00, steps = 73
22:55:37 [INFO] train episode 1274: reward = 77.00, steps = 77
22:55:37 [INFO] train episode 1275: reward = 82.00, steps = 82
22:55:37 [INFO] train episode 1276: reward = 191.00, steps = 191
22:55:37 [INFO] train episode 1277: reward = 89.00, steps = 89
22:55:37 [INFO] train episode 1278: reward = 140.00, steps = 140
22:55:37 [INFO] train episode 1279: reward = 82.00, steps = 82
22:55:37 [INFO] train episode 1280: reward = 85.00, steps = 85
22:55:37 [INFO] train episode 1281: reward = 126.00, steps = 126
22:55:37 [INFO] train episode 1282: reward = 133.00, steps = 133
22:55:37 [INFO] train episode 1283: reward = 180.00, steps = 180
22:55:37 [INFO] train episode 1284: reward = 143.00, steps = 143
22:55:37 [INFO] train episode 1285: reward = 122.00, steps = 122
22:55:37 [INFO] train episode 1286: reward = 134.00, steps = 134
22:55:37 [INFO] train episode 1287: reward = 104.00, steps = 104
22:55:38 [INFO] train episode 1288: reward = 86.00, steps = 86
22:55:38 [INFO] train episode 1289: reward = 87.00, steps = 87
22:55:38 [INFO] train episode 1290: reward = 101.00, steps = 101
22:55:38 [INFO] train episode 1291: reward = 96.00, steps = 96
22:55:38 [INFO] train episode 1292: reward = 74.00, steps = 74
22:55:38 [INFO] train episode 1293: reward = 144.00, steps = 144
22:55:38 [INFO] train episode 1294: reward = 120.00, steps = 120
22:55:38 [INFO] train episode 1295: reward = 121.00, steps = 121
22:55:38 [INFO] train episode 1296: reward = 125.00, steps = 125
22:55:38 [INFO] train episode 1297: reward = 137.00, steps = 137
22:55:38 [INFO] train episode 1298: reward = 130.00, steps = 130
22:55:38 [INFO] train episode 1299: reward = 91.00, steps = 91
22:55:38 [INFO] train episode 1300: reward = 128.00, steps = 128
22:55:38 [INFO] train episode 1301: reward = 68.00, steps = 68
22:55:38 [INFO] train episode 1302: reward = 92.00, steps = 92
22:55:38 [INFO] train episode 1303: reward = 81.00, steps = 81
22:55:39 [INFO] train episode 1304: reward = 89.00, steps = 89
22:55:39 [INFO] train episode 1305: reward = 109.00, steps = 109
22:55:39 [INFO] train episode 1306: reward = 81.00, steps = 81
22:55:39 [INFO] train episode 1307: reward = 150.00, steps = 150
22:55:39 [INFO] train episode 1308: reward = 90.00, steps = 90
22:55:39 [INFO] train episode 1309: reward = 93.00, steps = 93
22:55:39 [INFO] train episode 1310: reward = 85.00, steps = 85
22:55:39 [INFO] train episode 1311: reward = 147.00, steps = 147
22:55:39 [INFO] train episode 1312: reward = 74.00, steps = 74
22:55:39 [INFO] train episode 1313: reward = 101.00, steps = 101
22:55:39 [INFO] train episode 1314: reward = 74.00, steps = 74
22:55:39 [INFO] train episode 1315: reward = 87.00, steps = 87
22:55:39 [INFO] train episode 1316: reward = 85.00, steps = 85
22:55:39 [INFO] train episode 1317: reward = 100.00, steps = 100
22:55:39 [INFO] train episode 1318: reward = 174.00, steps = 174
22:55:39 [INFO] train episode 1319: reward = 140.00, steps = 140
22:55:39 [INFO] train episode 1320: reward = 81.00, steps = 81
22:55:39 [INFO] train episode 1321: reward = 185.00, steps = 185
22:55:40 [INFO] train episode 1322: reward = 125.00, steps = 125
22:55:40 [INFO] train episode 1323: reward = 122.00, steps = 122
22:55:40 [INFO] train episode 1324: reward = 99.00, steps = 99
22:55:40 [INFO] train episode 1325: reward = 106.00, steps = 106
22:55:40 [INFO] train episode 1326: reward = 116.00, steps = 116
22:55:40 [INFO] train episode 1327: reward = 103.00, steps = 103
22:55:40 [INFO] train episode 1328: reward = 112.00, steps = 112
22:55:40 [INFO] train episode 1329: reward = 182.00, steps = 182
22:55:40 [INFO] train episode 1330: reward = 105.00, steps = 105
22:55:40 [INFO] train episode 1331: reward = 87.00, steps = 87
22:55:40 [INFO] train episode 1332: reward = 128.00, steps = 128
22:55:40 [INFO] train episode 1333: reward = 124.00, steps = 124
22:55:40 [INFO] train episode 1334: reward = 137.00, steps = 137
22:55:40 [INFO] train episode 1335: reward = 153.00, steps = 153
22:55:40 [INFO] train episode 1336: reward = 108.00, steps = 108
22:55:41 [INFO] train episode 1337: reward = 95.00, steps = 95
22:55:41 [INFO] train episode 1338: reward = 142.00, steps = 142
22:55:41 [INFO] train episode 1339: reward = 85.00, steps = 85
22:55:41 [INFO] train episode 1340: reward = 111.00, steps = 111
22:55:41 [INFO] train episode 1341: reward = 94.00, steps = 94
22:55:41 [INFO] train episode 1342: reward = 145.00, steps = 145
22:55:41 [INFO] train episode 1343: reward = 159.00, steps = 159
22:55:41 [INFO] train episode 1344: reward = 94.00, steps = 94
22:55:41 [INFO] train episode 1345: reward = 95.00, steps = 95
22:55:41 [INFO] train episode 1346: reward = 175.00, steps = 175
22:55:41 [INFO] train episode 1347: reward = 127.00, steps = 127
22:55:41 [INFO] train episode 1348: reward = 181.00, steps = 181
22:55:41 [INFO] train episode 1349: reward = 95.00, steps = 95
22:55:41 [INFO] train episode 1350: reward = 100.00, steps = 100
22:55:41 [INFO] train episode 1351: reward = 129.00, steps = 129
22:55:42 [INFO] train episode 1352: reward = 166.00, steps = 166
22:55:42 [INFO] train episode 1353: reward = 147.00, steps = 147
22:55:42 [INFO] train episode 1354: reward = 103.00, steps = 103
22:55:42 [INFO] train episode 1355: reward = 152.00, steps = 152
22:55:42 [INFO] train episode 1356: reward = 93.00, steps = 93
22:55:42 [INFO] train episode 1357: reward = 175.00, steps = 175
22:55:42 [INFO] train episode 1358: reward = 126.00, steps = 126
22:55:42 [INFO] train episode 1359: reward = 137.00, steps = 137
22:55:42 [INFO] train episode 1360: reward = 115.00, steps = 115
22:55:42 [INFO] train episode 1361: reward = 106.00, steps = 106
22:55:42 [INFO] train episode 1362: reward = 133.00, steps = 133
22:55:42 [INFO] train episode 1363: reward = 108.00, steps = 108
22:55:42 [INFO] train episode 1364: reward = 136.00, steps = 136
22:55:43 [INFO] train episode 1365: reward = 162.00, steps = 162
22:55:43 [INFO] train episode 1366: reward = 117.00, steps = 117
22:55:43 [INFO] train episode 1367: reward = 140.00, steps = 140
22:55:43 [INFO] train episode 1368: reward = 114.00, steps = 114
22:55:43 [INFO] train episode 1369: reward = 200.00, steps = 200
22:55:43 [INFO] train episode 1370: reward = 116.00, steps = 116
22:55:43 [INFO] train episode 1371: reward = 168.00, steps = 168
22:55:43 [INFO] train episode 1372: reward = 200.00, steps = 200
22:55:43 [INFO] train episode 1373: reward = 197.00, steps = 197
22:55:43 [INFO] train episode 1374: reward = 135.00, steps = 135
22:55:43 [INFO] train episode 1375: reward = 161.00, steps = 161
22:55:43 [INFO] train episode 1376: reward = 107.00, steps = 107
22:55:43 [INFO] train episode 1377: reward = 112.00, steps = 112
22:55:44 [INFO] train episode 1378: reward = 132.00, steps = 132
22:55:44 [INFO] train episode 1379: reward = 117.00, steps = 117
22:55:44 [INFO] train episode 1380: reward = 159.00, steps = 159
22:55:44 [INFO] train episode 1381: reward = 91.00, steps = 91
22:55:44 [INFO] train episode 1382: reward = 91.00, steps = 91
22:55:44 [INFO] train episode 1383: reward = 99.00, steps = 99
22:55:44 [INFO] train episode 1384: reward = 161.00, steps = 161
22:55:44 [INFO] train episode 1385: reward = 125.00, steps = 125
22:55:44 [INFO] train episode 1386: reward = 169.00, steps = 169
22:55:44 [INFO] train episode 1387: reward = 94.00, steps = 94
22:55:44 [INFO] train episode 1388: reward = 200.00, steps = 200
22:55:44 [INFO] train episode 1389: reward = 99.00, steps = 99
22:55:44 [INFO] train episode 1390: reward = 200.00, steps = 200
22:55:44 [INFO] train episode 1391: reward = 97.00, steps = 97
22:55:44 [INFO] train episode 1392: reward = 133.00, steps = 133
22:55:45 [INFO] train episode 1393: reward = 141.00, steps = 141
22:55:45 [INFO] train episode 1394: reward = 128.00, steps = 128
22:55:45 [INFO] train episode 1395: reward = 128.00, steps = 128
22:55:45 [INFO] train episode 1396: reward = 92.00, steps = 92
22:55:45 [INFO] train episode 1397: reward = 111.00, steps = 111
22:55:45 [INFO] train episode 1398: reward = 72.00, steps = 72
22:55:45 [INFO] train episode 1399: reward = 95.00, steps = 95
22:55:45 [INFO] train episode 1400: reward = 161.00, steps = 161
22:55:45 [INFO] train episode 1401: reward = 112.00, steps = 112
22:55:45 [INFO] train episode 1402: reward = 99.00, steps = 99
22:55:45 [INFO] train episode 1403: reward = 90.00, steps = 90
22:55:45 [INFO] train episode 1404: reward = 97.00, steps = 97
22:55:45 [INFO] train episode 1405: reward = 123.00, steps = 123
22:55:45 [INFO] train episode 1406: reward = 174.00, steps = 174
22:55:46 [INFO] train episode 1407: reward = 179.00, steps = 179
22:55:46 [INFO] train episode 1408: reward = 150.00, steps = 150
22:55:46 [INFO] train episode 1409: reward = 143.00, steps = 143
22:55:46 [INFO] train episode 1410: reward = 132.00, steps = 132
22:55:46 [INFO] train episode 1411: reward = 133.00, steps = 133
22:55:46 [INFO] train episode 1412: reward = 119.00, steps = 119
22:55:46 [INFO] train episode 1413: reward = 96.00, steps = 96
22:55:46 [INFO] train episode 1414: reward = 200.00, steps = 200
22:55:46 [INFO] train episode 1415: reward = 93.00, steps = 93
22:55:46 [INFO] train episode 1416: reward = 99.00, steps = 99
22:55:46 [INFO] train episode 1417: reward = 103.00, steps = 103
22:55:46 [INFO] train episode 1418: reward = 89.00, steps = 89
22:55:46 [INFO] train episode 1419: reward = 144.00, steps = 144
22:55:46 [INFO] train episode 1420: reward = 124.00, steps = 124
22:55:46 [INFO] train episode 1421: reward = 103.00, steps = 103
22:55:46 [INFO] train episode 1422: reward = 122.00, steps = 122
22:55:47 [INFO] train episode 1423: reward = 161.00, steps = 161
22:55:47 [INFO] train episode 1424: reward = 139.00, steps = 139
22:55:47 [INFO] train episode 1425: reward = 131.00, steps = 131
22:55:47 [INFO] train episode 1426: reward = 188.00, steps = 188
22:55:47 [INFO] train episode 1427: reward = 132.00, steps = 132
22:55:47 [INFO] train episode 1428: reward = 92.00, steps = 92
22:55:47 [INFO] train episode 1429: reward = 125.00, steps = 125
22:55:47 [INFO] train episode 1430: reward = 106.00, steps = 106
22:55:47 [INFO] train episode 1431: reward = 86.00, steps = 86
22:55:47 [INFO] train episode 1432: reward = 96.00, steps = 96
22:55:47 [INFO] train episode 1433: reward = 200.00, steps = 200
22:55:47 [INFO] train episode 1434: reward = 119.00, steps = 119
22:55:47 [INFO] train episode 1435: reward = 141.00, steps = 141
22:55:48 [INFO] train episode 1436: reward = 106.00, steps = 106
22:55:48 [INFO] train episode 1437: reward = 200.00, steps = 200
22:55:48 [INFO] train episode 1438: reward = 99.00, steps = 99
22:55:48 [INFO] train episode 1439: reward = 128.00, steps = 128
22:55:48 [INFO] train episode 1440: reward = 119.00, steps = 119
22:55:48 [INFO] train episode 1441: reward = 166.00, steps = 166
22:55:48 [INFO] train episode 1442: reward = 105.00, steps = 105
22:55:48 [INFO] train episode 1443: reward = 104.00, steps = 104
22:55:48 [INFO] train episode 1444: reward = 143.00, steps = 143
22:55:48 [INFO] train episode 1445: reward = 123.00, steps = 123
22:55:48 [INFO] train episode 1446: reward = 90.00, steps = 90
22:55:48 [INFO] train episode 1447: reward = 129.00, steps = 129
22:55:48 [INFO] train episode 1448: reward = 98.00, steps = 98
22:55:48 [INFO] train episode 1449: reward = 188.00, steps = 188
22:55:49 [INFO] train episode 1450: reward = 116.00, steps = 116
22:55:49 [INFO] train episode 1451: reward = 112.00, steps = 112
22:55:49 [INFO] train episode 1452: reward = 108.00, steps = 108
22:55:49 [INFO] train episode 1453: reward = 158.00, steps = 158
22:55:49 [INFO] train episode 1454: reward = 171.00, steps = 171
22:55:49 [INFO] train episode 1455: reward = 168.00, steps = 168
22:55:49 [INFO] train episode 1456: reward = 178.00, steps = 178
22:55:49 [INFO] train episode 1457: reward = 82.00, steps = 82
22:55:49 [INFO] train episode 1458: reward = 94.00, steps = 94
22:55:49 [INFO] train episode 1459: reward = 165.00, steps = 165
22:55:49 [INFO] train episode 1460: reward = 116.00, steps = 116
22:55:49 [INFO] train episode 1461: reward = 103.00, steps = 103
22:55:49 [INFO] train episode 1462: reward = 128.00, steps = 128
22:55:49 [INFO] train episode 1463: reward = 97.00, steps = 97
22:55:50 [INFO] train episode 1464: reward = 131.00, steps = 131
22:55:50 [INFO] train episode 1465: reward = 117.00, steps = 117
22:55:50 [INFO] train episode 1466: reward = 159.00, steps = 159
22:55:50 [INFO] train episode 1467: reward = 158.00, steps = 158
22:55:50 [INFO] train episode 1468: reward = 109.00, steps = 109
22:55:50 [INFO] train episode 1469: reward = 119.00, steps = 119
22:55:50 [INFO] train episode 1470: reward = 200.00, steps = 200
22:55:50 [INFO] train episode 1471: reward = 194.00, steps = 194
22:55:50 [INFO] train episode 1472: reward = 92.00, steps = 92
22:55:50 [INFO] train episode 1473: reward = 200.00, steps = 200
22:55:50 [INFO] train episode 1474: reward = 129.00, steps = 129
22:55:51 [INFO] train episode 1475: reward = 139.00, steps = 139
22:55:51 [INFO] train episode 1476: reward = 132.00, steps = 132
22:55:51 [INFO] train episode 1477: reward = 102.00, steps = 102
22:55:51 [INFO] train episode 1478: reward = 155.00, steps = 155
22:55:51 [INFO] train episode 1479: reward = 200.00, steps = 200
22:55:51 [INFO] train episode 1480: reward = 149.00, steps = 149
22:55:51 [INFO] train episode 1481: reward = 86.00, steps = 86
22:55:51 [INFO] train episode 1482: reward = 155.00, steps = 155
22:55:51 [INFO] train episode 1483: reward = 107.00, steps = 107
22:55:51 [INFO] train episode 1484: reward = 184.00, steps = 184
22:55:51 [INFO] train episode 1485: reward = 174.00, steps = 174
22:55:51 [INFO] train episode 1486: reward = 172.00, steps = 172
22:55:52 [INFO] train episode 1487: reward = 182.00, steps = 182
22:55:52 [INFO] train episode 1488: reward = 135.00, steps = 135
22:55:52 [INFO] train episode 1489: reward = 195.00, steps = 195
22:55:52 [INFO] train episode 1490: reward = 127.00, steps = 127
22:55:52 [INFO] train episode 1491: reward = 199.00, steps = 199
22:55:52 [INFO] train episode 1492: reward = 200.00, steps = 200
22:55:52 [INFO] train episode 1493: reward = 135.00, steps = 135
22:55:52 [INFO] train episode 1494: reward = 97.00, steps = 97
22:55:52 [INFO] train episode 1495: reward = 125.00, steps = 125
22:55:52 [INFO] train episode 1496: reward = 131.00, steps = 131
22:55:52 [INFO] train episode 1497: reward = 130.00, steps = 130
22:55:52 [INFO] train episode 1498: reward = 154.00, steps = 154
22:55:52 [INFO] train episode 1499: reward = 122.00, steps = 122
22:55:53 [INFO] train episode 1500: reward = 196.00, steps = 196
22:55:53 [INFO] train episode 1501: reward = 146.00, steps = 146
22:55:53 [INFO] train episode 1502: reward = 150.00, steps = 150
22:55:53 [INFO] train episode 1503: reward = 184.00, steps = 184
22:55:53 [INFO] train episode 1504: reward = 134.00, steps = 134
22:55:53 [INFO] train episode 1505: reward = 148.00, steps = 148
22:55:53 [INFO] train episode 1506: reward = 94.00, steps = 94
22:55:53 [INFO] train episode 1507: reward = 148.00, steps = 148
22:55:53 [INFO] train episode 1508: reward = 99.00, steps = 99
22:55:53 [INFO] train episode 1509: reward = 147.00, steps = 147
22:55:53 [INFO] train episode 1510: reward = 200.00, steps = 200
22:55:53 [INFO] train episode 1511: reward = 151.00, steps = 151
22:55:53 [INFO] train episode 1512: reward = 153.00, steps = 153
22:55:54 [INFO] train episode 1513: reward = 160.00, steps = 160
22:55:54 [INFO] train episode 1514: reward = 150.00, steps = 150
22:55:54 [INFO] train episode 1515: reward = 175.00, steps = 175
22:55:54 [INFO] train episode 1516: reward = 200.00, steps = 200
22:55:54 [INFO] train episode 1517: reward = 130.00, steps = 130
22:55:54 [INFO] train episode 1518: reward = 145.00, steps = 145
22:55:54 [INFO] train episode 1519: reward = 119.00, steps = 119
22:55:54 [INFO] train episode 1520: reward = 200.00, steps = 200
22:55:54 [INFO] train episode 1521: reward = 113.00, steps = 113
22:55:54 [INFO] train episode 1522: reward = 130.00, steps = 130
22:55:54 [INFO] train episode 1523: reward = 200.00, steps = 200
22:55:54 [INFO] train episode 1524: reward = 149.00, steps = 149
22:55:55 [INFO] train episode 1525: reward = 178.00, steps = 178
22:55:55 [INFO] train episode 1526: reward = 153.00, steps = 153
22:55:55 [INFO] train episode 1527: reward = 180.00, steps = 180
22:55:55 [INFO] train episode 1528: reward = 167.00, steps = 167
22:55:55 [INFO] train episode 1529: reward = 139.00, steps = 139
22:55:55 [INFO] train episode 1530: reward = 127.00, steps = 127
22:55:55 [INFO] train episode 1531: reward = 181.00, steps = 181
22:55:55 [INFO] train episode 1532: reward = 104.00, steps = 104
22:55:55 [INFO] train episode 1533: reward = 130.00, steps = 130
22:55:55 [INFO] train episode 1534: reward = 121.00, steps = 121
22:55:55 [INFO] train episode 1535: reward = 135.00, steps = 135
22:55:55 [INFO] train episode 1536: reward = 121.00, steps = 121
22:55:55 [INFO] train episode 1537: reward = 154.00, steps = 154
22:55:56 [INFO] train episode 1538: reward = 200.00, steps = 200
22:55:56 [INFO] train episode 1539: reward = 99.00, steps = 99
22:55:56 [INFO] train episode 1540: reward = 124.00, steps = 124
22:55:56 [INFO] train episode 1541: reward = 112.00, steps = 112
22:55:56 [INFO] train episode 1542: reward = 154.00, steps = 154
22:55:56 [INFO] train episode 1543: reward = 181.00, steps = 181
22:55:56 [INFO] train episode 1544: reward = 132.00, steps = 132
22:55:56 [INFO] train episode 1545: reward = 127.00, steps = 127
22:55:56 [INFO] train episode 1546: reward = 200.00, steps = 200
22:55:56 [INFO] train episode 1547: reward = 126.00, steps = 126
22:55:56 [INFO] train episode 1548: reward = 155.00, steps = 155
22:55:56 [INFO] train episode 1549: reward = 200.00, steps = 200
22:55:56 [INFO] train episode 1550: reward = 127.00, steps = 127
22:55:57 [INFO] train episode 1551: reward = 161.00, steps = 161
22:55:57 [INFO] train episode 1552: reward = 170.00, steps = 170
22:55:57 [INFO] train episode 1553: reward = 128.00, steps = 128
22:55:57 [INFO] train episode 1554: reward = 132.00, steps = 132
22:55:57 [INFO] train episode 1555: reward = 162.00, steps = 162
22:55:57 [INFO] train episode 1556: reward = 120.00, steps = 120
22:55:57 [INFO] train episode 1557: reward = 136.00, steps = 136
22:55:57 [INFO] train episode 1558: reward = 135.00, steps = 135
22:55:57 [INFO] train episode 1559: reward = 175.00, steps = 175
22:55:57 [INFO] train episode 1560: reward = 159.00, steps = 159
22:55:57 [INFO] train episode 1561: reward = 111.00, steps = 111
22:55:57 [INFO] train episode 1562: reward = 149.00, steps = 149
22:55:57 [INFO] train episode 1563: reward = 88.00, steps = 88
22:55:57 [INFO] train episode 1564: reward = 99.00, steps = 99
22:55:57 [INFO] train episode 1565: reward = 136.00, steps = 136
22:55:58 [INFO] train episode 1566: reward = 179.00, steps = 179
22:55:58 [INFO] train episode 1567: reward = 121.00, steps = 121
22:55:58 [INFO] train episode 1568: reward = 93.00, steps = 93
22:55:58 [INFO] train episode 1569: reward = 144.00, steps = 144
22:55:58 [INFO] train episode 1570: reward = 134.00, steps = 134
22:55:58 [INFO] train episode 1571: reward = 165.00, steps = 165
22:55:58 [INFO] train episode 1572: reward = 108.00, steps = 108
22:55:58 [INFO] train episode 1573: reward = 90.00, steps = 90
22:55:58 [INFO] train episode 1574: reward = 148.00, steps = 148
22:55:58 [INFO] train episode 1575: reward = 106.00, steps = 106
22:55:58 [INFO] train episode 1576: reward = 131.00, steps = 131
22:55:58 [INFO] train episode 1577: reward = 181.00, steps = 181
22:55:58 [INFO] train episode 1578: reward = 114.00, steps = 114
22:55:59 [INFO] train episode 1579: reward = 95.00, steps = 95
22:55:59 [INFO] train episode 1580: reward = 100.00, steps = 100
22:55:59 [INFO] train episode 1581: reward = 111.00, steps = 111
22:55:59 [INFO] train episode 1582: reward = 120.00, steps = 120
22:55:59 [INFO] train episode 1583: reward = 129.00, steps = 129
22:55:59 [INFO] train episode 1584: reward = 110.00, steps = 110
22:55:59 [INFO] train episode 1585: reward = 129.00, steps = 129
22:55:59 [INFO] train episode 1586: reward = 101.00, steps = 101
22:55:59 [INFO] train episode 1587: reward = 153.00, steps = 153
22:55:59 [INFO] train episode 1588: reward = 114.00, steps = 114
22:55:59 [INFO] train episode 1589: reward = 122.00, steps = 122
22:55:59 [INFO] train episode 1590: reward = 124.00, steps = 124
22:55:59 [INFO] train episode 1591: reward = 177.00, steps = 177
22:55:59 [INFO] train episode 1592: reward = 106.00, steps = 106
22:56:00 [INFO] train episode 1593: reward = 136.00, steps = 136
22:56:00 [INFO] train episode 1594: reward = 146.00, steps = 146
22:56:00 [INFO] train episode 1595: reward = 166.00, steps = 166
22:56:00 [INFO] train episode 1596: reward = 106.00, steps = 106
22:56:00 [INFO] train episode 1597: reward = 123.00, steps = 123
22:56:00 [INFO] train episode 1598: reward = 125.00, steps = 125
22:56:00 [INFO] train episode 1599: reward = 156.00, steps = 156
22:56:00 [INFO] train episode 1600: reward = 143.00, steps = 143
22:56:00 [INFO] train episode 1601: reward = 101.00, steps = 101
22:56:00 [INFO] train episode 1602: reward = 134.00, steps = 134
22:56:00 [INFO] train episode 1603: reward = 113.00, steps = 113
22:56:00 [INFO] train episode 1604: reward = 106.00, steps = 106
22:56:00 [INFO] train episode 1605: reward = 123.00, steps = 123
22:56:01 [INFO] train episode 1606: reward = 155.00, steps = 155
22:56:01 [INFO] train episode 1607: reward = 140.00, steps = 140
22:56:01 [INFO] train episode 1608: reward = 189.00, steps = 189
22:56:01 [INFO] train episode 1609: reward = 131.00, steps = 131
22:56:01 [INFO] train episode 1610: reward = 156.00, steps = 156
22:56:01 [INFO] train episode 1611: reward = 166.00, steps = 166
22:56:01 [INFO] train episode 1612: reward = 139.00, steps = 139
22:56:01 [INFO] train episode 1613: reward = 187.00, steps = 187
22:56:01 [INFO] train episode 1614: reward = 161.00, steps = 161
22:56:01 [INFO] train episode 1615: reward = 124.00, steps = 124
22:56:01 [INFO] train episode 1616: reward = 115.00, steps = 115
22:56:01 [INFO] train episode 1617: reward = 107.00, steps = 107
22:56:01 [INFO] train episode 1618: reward = 127.00, steps = 127
22:56:01 [INFO] train episode 1619: reward = 161.00, steps = 161
22:56:02 [INFO] train episode 1620: reward = 200.00, steps = 200
22:56:02 [INFO] train episode 1621: reward = 146.00, steps = 146
22:56:02 [INFO] train episode 1622: reward = 173.00, steps = 173
22:56:02 [INFO] train episode 1623: reward = 115.00, steps = 115
22:56:02 [INFO] train episode 1624: reward = 154.00, steps = 154
22:56:02 [INFO] train episode 1625: reward = 133.00, steps = 133
22:56:02 [INFO] train episode 1626: reward = 158.00, steps = 158
22:56:02 [INFO] train episode 1627: reward = 116.00, steps = 116
22:56:02 [INFO] train episode 1628: reward = 137.00, steps = 137
22:56:02 [INFO] train episode 1629: reward = 87.00, steps = 87
22:56:02 [INFO] train episode 1630: reward = 89.00, steps = 89
22:56:02 [INFO] train episode 1631: reward = 102.00, steps = 102
22:56:02 [INFO] train episode 1632: reward = 109.00, steps = 109
22:56:02 [INFO] train episode 1633: reward = 141.00, steps = 141
22:56:02 [INFO] train episode 1634: reward = 115.00, steps = 115
22:56:03 [INFO] train episode 1635: reward = 169.00, steps = 169
22:56:03 [INFO] train episode 1636: reward = 99.00, steps = 99
22:56:03 [INFO] train episode 1637: reward = 103.00, steps = 103
22:56:03 [INFO] train episode 1638: reward = 200.00, steps = 200
22:56:03 [INFO] train episode 1639: reward = 170.00, steps = 170
22:56:03 [INFO] train episode 1640: reward = 91.00, steps = 91
22:56:03 [INFO] train episode 1641: reward = 138.00, steps = 138
22:56:03 [INFO] train episode 1642: reward = 125.00, steps = 125
22:56:03 [INFO] train episode 1643: reward = 139.00, steps = 139
22:56:03 [INFO] train episode 1644: reward = 160.00, steps = 160
22:56:03 [INFO] train episode 1645: reward = 96.00, steps = 96
22:56:03 [INFO] train episode 1646: reward = 129.00, steps = 129
22:56:03 [INFO] train episode 1647: reward = 109.00, steps = 109
22:56:04 [INFO] train episode 1648: reward = 137.00, steps = 137
22:56:04 [INFO] train episode 1649: reward = 178.00, steps = 178
22:56:04 [INFO] train episode 1650: reward = 102.00, steps = 102
22:56:04 [INFO] train episode 1651: reward = 129.00, steps = 129
22:56:04 [INFO] train episode 1652: reward = 158.00, steps = 158
22:56:04 [INFO] train episode 1653: reward = 97.00, steps = 97
22:56:04 [INFO] train episode 1654: reward = 129.00, steps = 129
22:56:04 [INFO] train episode 1655: reward = 119.00, steps = 119
22:56:04 [INFO] train episode 1656: reward = 141.00, steps = 141
22:56:04 [INFO] train episode 1657: reward = 186.00, steps = 186
22:56:04 [INFO] train episode 1658: reward = 115.00, steps = 115
22:56:04 [INFO] train episode 1659: reward = 117.00, steps = 117
22:56:04 [INFO] train episode 1660: reward = 164.00, steps = 164
22:56:05 [INFO] train episode 1661: reward = 200.00, steps = 200
22:56:05 [INFO] train episode 1662: reward = 115.00, steps = 115
22:56:05 [INFO] train episode 1663: reward = 132.00, steps = 132
22:56:05 [INFO] train episode 1664: reward = 130.00, steps = 130
22:56:05 [INFO] train episode 1665: reward = 189.00, steps = 189
22:56:05 [INFO] train episode 1666: reward = 181.00, steps = 181
22:56:05 [INFO] train episode 1667: reward = 130.00, steps = 130
22:56:05 [INFO] train episode 1668: reward = 193.00, steps = 193
22:56:05 [INFO] train episode 1669: reward = 139.00, steps = 139
22:56:05 [INFO] train episode 1670: reward = 137.00, steps = 137
22:56:05 [INFO] train episode 1671: reward = 115.00, steps = 115
22:56:05 [INFO] train episode 1672: reward = 120.00, steps = 120
22:56:05 [INFO] train episode 1673: reward = 101.00, steps = 101
22:56:06 [INFO] train episode 1674: reward = 200.00, steps = 200
22:56:06 [INFO] train episode 1675: reward = 111.00, steps = 111
22:56:06 [INFO] train episode 1676: reward = 128.00, steps = 128
22:56:06 [INFO] train episode 1677: reward = 127.00, steps = 127
22:56:06 [INFO] train episode 1678: reward = 140.00, steps = 140
22:56:06 [INFO] train episode 1679: reward = 128.00, steps = 128
22:56:06 [INFO] train episode 1680: reward = 195.00, steps = 195
22:56:06 [INFO] train episode 1681: reward = 165.00, steps = 165
22:56:06 [INFO] train episode 1682: reward = 200.00, steps = 200
22:56:06 [INFO] train episode 1683: reward = 173.00, steps = 173
22:56:06 [INFO] train episode 1684: reward = 174.00, steps = 174
22:56:07 [INFO] train episode 1685: reward = 146.00, steps = 146
22:56:07 [INFO] train episode 1686: reward = 127.00, steps = 127
22:56:07 [INFO] train episode 1687: reward = 132.00, steps = 132
22:56:07 [INFO] train episode 1688: reward = 108.00, steps = 108
22:56:07 [INFO] train episode 1689: reward = 121.00, steps = 121
22:56:07 [INFO] train episode 1690: reward = 146.00, steps = 146
22:56:07 [INFO] train episode 1691: reward = 188.00, steps = 188
22:56:07 [INFO] train episode 1692: reward = 106.00, steps = 106
22:56:07 [INFO] train episode 1693: reward = 195.00, steps = 195
22:56:07 [INFO] train episode 1694: reward = 125.00, steps = 125
22:56:07 [INFO] train episode 1695: reward = 149.00, steps = 149
22:56:07 [INFO] train episode 1696: reward = 148.00, steps = 148
22:56:08 [INFO] train episode 1697: reward = 116.00, steps = 116
22:56:08 [INFO] train episode 1698: reward = 151.00, steps = 151
22:56:08 [INFO] train episode 1699: reward = 97.00, steps = 97
22:56:08 [INFO] train episode 1700: reward = 118.00, steps = 118
22:56:08 [INFO] train episode 1701: reward = 131.00, steps = 131
22:56:08 [INFO] train episode 1702: reward = 193.00, steps = 193
22:56:08 [INFO] train episode 1703: reward = 200.00, steps = 200
22:56:08 [INFO] train episode 1704: reward = 200.00, steps = 200
22:56:08 [INFO] train episode 1705: reward = 147.00, steps = 147
22:56:08 [INFO] train episode 1706: reward = 123.00, steps = 123
22:56:08 [INFO] train episode 1707: reward = 145.00, steps = 145
22:56:09 [INFO] train episode 1708: reward = 132.00, steps = 132
22:56:09 [INFO] train episode 1709: reward = 117.00, steps = 117
22:56:09 [INFO] train episode 1710: reward = 130.00, steps = 130
22:56:09 [INFO] train episode 1711: reward = 140.00, steps = 140
22:56:09 [INFO] train episode 1712: reward = 148.00, steps = 148
22:56:09 [INFO] train episode 1713: reward = 122.00, steps = 122
22:56:09 [INFO] train episode 1714: reward = 116.00, steps = 116
22:56:09 [INFO] train episode 1715: reward = 126.00, steps = 126
22:56:09 [INFO] train episode 1716: reward = 147.00, steps = 147
22:56:09 [INFO] train episode 1717: reward = 200.00, steps = 200
22:56:10 [INFO] train episode 1718: reward = 123.00, steps = 123
22:56:10 [INFO] train episode 1719: reward = 169.00, steps = 169
22:56:10 [INFO] train episode 1720: reward = 143.00, steps = 143
22:56:10 [INFO] train episode 1721: reward = 134.00, steps = 134
22:56:10 [INFO] train episode 1722: reward = 150.00, steps = 150
22:56:10 [INFO] train episode 1723: reward = 166.00, steps = 166
22:56:10 [INFO] train episode 1724: reward = 163.00, steps = 163
22:56:10 [INFO] train episode 1725: reward = 170.00, steps = 170
22:56:10 [INFO] train episode 1726: reward = 161.00, steps = 161
22:56:10 [INFO] train episode 1727: reward = 195.00, steps = 195
22:56:11 [INFO] train episode 1728: reward = 106.00, steps = 106
22:56:11 [INFO] train episode 1729: reward = 142.00, steps = 142
22:56:11 [INFO] train episode 1730: reward = 143.00, steps = 143
22:56:11 [INFO] train episode 1731: reward = 143.00, steps = 143
22:56:11 [INFO] train episode 1732: reward = 155.00, steps = 155
22:56:11 [INFO] train episode 1733: reward = 118.00, steps = 118
22:56:11 [INFO] train episode 1734: reward = 144.00, steps = 144
22:56:11 [INFO] train episode 1735: reward = 131.00, steps = 131
22:56:11 [INFO] train episode 1736: reward = 108.00, steps = 108
22:56:11 [INFO] train episode 1737: reward = 200.00, steps = 200
22:56:11 [INFO] train episode 1738: reward = 159.00, steps = 159
22:56:12 [INFO] train episode 1739: reward = 118.00, steps = 118
22:56:12 [INFO] train episode 1740: reward = 136.00, steps = 136
22:56:12 [INFO] train episode 1741: reward = 147.00, steps = 147
22:56:12 [INFO] train episode 1742: reward = 132.00, steps = 132
22:56:12 [INFO] train episode 1743: reward = 135.00, steps = 135
22:56:12 [INFO] train episode 1744: reward = 129.00, steps = 129
22:56:12 [INFO] train episode 1745: reward = 188.00, steps = 188
22:56:12 [INFO] train episode 1746: reward = 157.00, steps = 157
22:56:12 [INFO] train episode 1747: reward = 148.00, steps = 148
22:56:12 [INFO] train episode 1748: reward = 150.00, steps = 150
22:56:12 [INFO] train episode 1749: reward = 127.00, steps = 127
22:56:12 [INFO] train episode 1750: reward = 132.00, steps = 132
22:56:13 [INFO] train episode 1751: reward = 196.00, steps = 196
22:56:13 [INFO] train episode 1752: reward = 129.00, steps = 129
22:56:13 [INFO] train episode 1753: reward = 177.00, steps = 177
22:56:13 [INFO] train episode 1754: reward = 200.00, steps = 200
22:56:13 [INFO] train episode 1755: reward = 118.00, steps = 118
22:56:13 [INFO] train episode 1756: reward = 143.00, steps = 143
22:56:13 [INFO] train episode 1757: reward = 144.00, steps = 144
22:56:13 [INFO] train episode 1758: reward = 200.00, steps = 200
22:56:13 [INFO] train episode 1759: reward = 110.00, steps = 110
22:56:13 [INFO] train episode 1760: reward = 129.00, steps = 129
22:56:13 [INFO] train episode 1761: reward = 129.00, steps = 129
22:56:14 [INFO] train episode 1762: reward = 148.00, steps = 148
22:56:14 [INFO] train episode 1763: reward = 152.00, steps = 152
22:56:14 [INFO] train episode 1764: reward = 158.00, steps = 158
22:56:14 [INFO] train episode 1765: reward = 153.00, steps = 153
22:56:14 [INFO] train episode 1766: reward = 142.00, steps = 142
22:56:14 [INFO] train episode 1767: reward = 144.00, steps = 144
22:56:14 [INFO] train episode 1768: reward = 122.00, steps = 122
22:56:14 [INFO] train episode 1769: reward = 181.00, steps = 181
22:56:14 [INFO] train episode 1770: reward = 200.00, steps = 200
22:56:14 [INFO] train episode 1771: reward = 172.00, steps = 172
22:56:15 [INFO] train episode 1772: reward = 166.00, steps = 166
22:56:15 [INFO] train episode 1773: reward = 146.00, steps = 146
22:56:15 [INFO] train episode 1774: reward = 200.00, steps = 200
22:56:15 [INFO] train episode 1775: reward = 150.00, steps = 150
22:56:15 [INFO] train episode 1776: reward = 200.00, steps = 200
22:56:15 [INFO] train episode 1777: reward = 191.00, steps = 191
22:56:15 [INFO] train episode 1778: reward = 130.00, steps = 130
22:56:15 [INFO] train episode 1779: reward = 163.00, steps = 163
22:56:15 [INFO] train episode 1780: reward = 200.00, steps = 200
22:56:16 [INFO] train episode 1781: reward = 200.00, steps = 200
22:56:16 [INFO] train episode 1782: reward = 166.00, steps = 166
22:56:16 [INFO] train episode 1783: reward = 200.00, steps = 200
22:56:16 [INFO] train episode 1784: reward = 200.00, steps = 200
22:56:16 [INFO] train episode 1785: reward = 157.00, steps = 157
22:56:16 [INFO] train episode 1786: reward = 200.00, steps = 200
22:56:16 [INFO] train episode 1787: reward = 200.00, steps = 200
22:56:16 [INFO] train episode 1788: reward = 200.00, steps = 200
22:56:16 [INFO] train episode 1789: reward = 131.00, steps = 131
22:56:17 [INFO] train episode 1790: reward = 200.00, steps = 200
22:56:17 [INFO] train episode 1791: reward = 200.00, steps = 200
22:56:17 [INFO] train episode 1792: reward = 200.00, steps = 200
22:56:17 [INFO] train episode 1793: reward = 200.00, steps = 200
22:56:17 [INFO] train episode 1794: reward = 200.00, steps = 200
22:56:17 [INFO] train episode 1795: reward = 200.00, steps = 200
22:56:17 [INFO] train episode 1796: reward = 200.00, steps = 200
22:56:17 [INFO] train episode 1797: reward = 180.00, steps = 180
22:56:17 [INFO] train episode 1798: reward = 200.00, steps = 200
22:56:18 [INFO] train episode 1799: reward = 200.00, steps = 200
22:56:18 [INFO] train episode 1800: reward = 158.00, steps = 158
22:56:18 [INFO] train episode 1801: reward = 200.00, steps = 200
22:56:18 [INFO] train episode 1802: reward = 190.00, steps = 190
22:56:18 [INFO] train episode 1803: reward = 200.00, steps = 200
22:56:18 [INFO] train episode 1804: reward = 200.00, steps = 200
22:56:18 [INFO] train episode 1805: reward = 193.00, steps = 193
22:56:18 [INFO] train episode 1806: reward = 155.00, steps = 155
22:56:18 [INFO] train episode 1807: reward = 200.00, steps = 200
22:56:18 [INFO] train episode 1808: reward = 135.00, steps = 135
22:56:19 [INFO] train episode 1809: reward = 196.00, steps = 196
22:56:19 [INFO] train episode 1810: reward = 200.00, steps = 200
22:56:19 [INFO] train episode 1811: reward = 200.00, steps = 200
22:56:19 [INFO] train episode 1812: reward = 144.00, steps = 144
22:56:19 [INFO] train episode 1813: reward = 121.00, steps = 121
22:56:19 [INFO] train episode 1814: reward = 200.00, steps = 200
22:56:19 [INFO] train episode 1815: reward = 150.00, steps = 150
22:56:19 [INFO] train episode 1816: reward = 97.00, steps = 97
22:56:19 [INFO] train episode 1817: reward = 136.00, steps = 136
22:56:19 [INFO] train episode 1818: reward = 121.00, steps = 121
22:56:20 [INFO] train episode 1819: reward = 200.00, steps = 200
22:56:20 [INFO] train episode 1820: reward = 200.00, steps = 200
22:56:20 [INFO] train episode 1821: reward = 200.00, steps = 200
22:56:20 [INFO] train episode 1822: reward = 142.00, steps = 142
22:56:20 [INFO] train episode 1823: reward = 174.00, steps = 174
22:56:20 [INFO] train episode 1824: reward = 163.00, steps = 163
22:56:20 [INFO] train episode 1825: reward = 153.00, steps = 153
22:56:20 [INFO] train episode 1826: reward = 147.00, steps = 147
22:56:20 [INFO] train episode 1827: reward = 153.00, steps = 153
22:56:20 [INFO] train episode 1828: reward = 142.00, steps = 142
22:56:20 [INFO] train episode 1829: reward = 159.00, steps = 159
22:56:21 [INFO] train episode 1830: reward = 200.00, steps = 200
22:56:21 [INFO] train episode 1831: reward = 149.00, steps = 149
22:56:21 [INFO] train episode 1832: reward = 160.00, steps = 160
22:56:21 [INFO] train episode 1833: reward = 185.00, steps = 185
22:56:21 [INFO] train episode 1834: reward = 143.00, steps = 143
22:56:21 [INFO] train episode 1835: reward = 132.00, steps = 132
22:56:21 [INFO] train episode 1836: reward = 200.00, steps = 200
22:56:21 [INFO] train episode 1837: reward = 185.00, steps = 185
22:56:21 [INFO] train episode 1838: reward = 112.00, steps = 112
22:56:22 [INFO] train episode 1839: reward = 109.00, steps = 109
22:56:22 [INFO] train episode 1840: reward = 142.00, steps = 142
22:56:22 [INFO] train episode 1841: reward = 119.00, steps = 119
22:56:22 [INFO] train episode 1842: reward = 141.00, steps = 141
22:56:22 [INFO] train episode 1843: reward = 157.00, steps = 157
22:56:22 [INFO] train episode 1844: reward = 192.00, steps = 192
22:56:22 [INFO] train episode 1845: reward = 189.00, steps = 189
22:56:22 [INFO] train episode 1846: reward = 200.00, steps = 200
22:56:22 [INFO] train episode 1847: reward = 200.00, steps = 200
22:56:22 [INFO] train episode 1848: reward = 180.00, steps = 180
22:56:22 [INFO] train episode 1849: reward = 124.00, steps = 124
22:56:23 [INFO] train episode 1850: reward = 200.00, steps = 200
22:56:23 [INFO] train episode 1851: reward = 185.00, steps = 185
22:56:23 [INFO] train episode 1852: reward = 200.00, steps = 200
22:56:23 [INFO] train episode 1853: reward = 126.00, steps = 126
22:56:23 [INFO] train episode 1854: reward = 138.00, steps = 138
22:56:23 [INFO] train episode 1855: reward = 150.00, steps = 150
22:56:23 [INFO] train episode 1856: reward = 157.00, steps = 157
22:56:23 [INFO] train episode 1857: reward = 111.00, steps = 111
22:56:23 [INFO] train episode 1858: reward = 158.00, steps = 158
22:56:23 [INFO] train episode 1859: reward = 139.00, steps = 139
22:56:24 [INFO] train episode 1860: reward = 137.00, steps = 137
22:56:24 [INFO] train episode 1861: reward = 199.00, steps = 199
22:56:24 [INFO] train episode 1862: reward = 151.00, steps = 151
22:56:24 [INFO] train episode 1863: reward = 175.00, steps = 175
22:56:24 [INFO] train episode 1864: reward = 149.00, steps = 149
22:56:24 [INFO] train episode 1865: reward = 191.00, steps = 191
22:56:24 [INFO] train episode 1866: reward = 159.00, steps = 159
22:56:24 [INFO] train episode 1867: reward = 155.00, steps = 155
22:56:24 [INFO] train episode 1868: reward = 200.00, steps = 200
22:56:24 [INFO] train episode 1869: reward = 198.00, steps = 198
22:56:24 [INFO] train episode 1870: reward = 113.00, steps = 113
22:56:24 [INFO] train episode 1871: reward = 170.00, steps = 170
22:56:25 [INFO] train episode 1872: reward = 199.00, steps = 199
22:56:25 [INFO] train episode 1873: reward = 147.00, steps = 147
22:56:25 [INFO] train episode 1874: reward = 200.00, steps = 200
22:56:25 [INFO] train episode 1875: reward = 200.00, steps = 200
22:56:25 [INFO] train episode 1876: reward = 200.00, steps = 200
22:56:25 [INFO] train episode 1877: reward = 200.00, steps = 200
22:56:25 [INFO] train episode 1878: reward = 185.00, steps = 185
22:56:25 [INFO] train episode 1879: reward = 126.00, steps = 126
22:56:25 [INFO] train episode 1880: reward = 200.00, steps = 200
22:56:26 [INFO] train episode 1881: reward = 148.00, steps = 148
22:56:26 [INFO] train episode 1882: reward = 148.00, steps = 148
22:56:26 [INFO] train episode 1883: reward = 200.00, steps = 200
22:56:26 [INFO] train episode 1884: reward = 129.00, steps = 129
22:56:26 [INFO] train episode 1885: reward = 144.00, steps = 144
22:56:26 [INFO] train episode 1886: reward = 159.00, steps = 159
22:56:26 [INFO] train episode 1887: reward = 142.00, steps = 142
22:56:26 [INFO] train episode 1888: reward = 133.00, steps = 133
22:56:26 [INFO] train episode 1889: reward = 131.00, steps = 131
22:56:26 [INFO] train episode 1890: reward = 186.00, steps = 186
22:56:26 [INFO] train episode 1891: reward = 127.00, steps = 127
22:56:27 [INFO] train episode 1892: reward = 157.00, steps = 157
22:56:27 [INFO] train episode 1893: reward = 200.00, steps = 200
22:56:27 [INFO] train episode 1894: reward = 156.00, steps = 156
22:56:27 [INFO] train episode 1895: reward = 200.00, steps = 200
22:56:27 [INFO] train episode 1896: reward = 190.00, steps = 190
22:56:27 [INFO] train episode 1897: reward = 159.00, steps = 159
22:56:27 [INFO] train episode 1898: reward = 160.00, steps = 160
22:56:27 [INFO] train episode 1899: reward = 120.00, steps = 120
22:56:28 [INFO] train episode 1900: reward = 115.00, steps = 115
22:56:28 [INFO] train episode 1901: reward = 200.00, steps = 200
22:56:28 [INFO] train episode 1902: reward = 200.00, steps = 200
22:56:28 [INFO] train episode 1903: reward = 145.00, steps = 145
22:56:28 [INFO] train episode 1904: reward = 193.00, steps = 193
22:56:28 [INFO] train episode 1905: reward = 169.00, steps = 169
22:56:28 [INFO] train episode 1906: reward = 116.00, steps = 116
22:56:28 [INFO] train episode 1907: reward = 174.00, steps = 174
22:56:28 [INFO] train episode 1908: reward = 187.00, steps = 187
22:56:28 [INFO] train episode 1909: reward = 170.00, steps = 170
22:56:28 [INFO] train episode 1910: reward = 148.00, steps = 148
22:56:29 [INFO] train episode 1911: reward = 145.00, steps = 145
22:56:29 [INFO] train episode 1912: reward = 188.00, steps = 188
22:56:29 [INFO] train episode 1913: reward = 177.00, steps = 177
22:56:29 [INFO] train episode 1914: reward = 163.00, steps = 163
22:56:29 [INFO] train episode 1915: reward = 200.00, steps = 200
22:56:29 [INFO] train episode 1916: reward = 200.00, steps = 200
22:56:29 [INFO] train episode 1917: reward = 175.00, steps = 175
22:56:29 [INFO] train episode 1918: reward = 200.00, steps = 200
22:56:29 [INFO] train episode 1919: reward = 200.00, steps = 200
22:56:30 [INFO] train episode 1920: reward = 200.00, steps = 200
22:56:30 [INFO] train episode 1921: reward = 177.00, steps = 177
22:56:30 [INFO] train episode 1922: reward = 200.00, steps = 200
22:56:30 [INFO] train episode 1923: reward = 200.00, steps = 200
22:56:30 [INFO] train episode 1924: reward = 177.00, steps = 177
22:56:30 [INFO] train episode 1925: reward = 200.00, steps = 200
22:56:30 [INFO] train episode 1926: reward = 157.00, steps = 157
22:56:30 [INFO] train episode 1927: reward = 178.00, steps = 178
22:56:31 [INFO] train episode 1928: reward = 200.00, steps = 200
22:56:31 [INFO] train episode 1929: reward = 200.00, steps = 200
22:56:31 [INFO] train episode 1930: reward = 200.00, steps = 200
22:56:31 [INFO] train episode 1931: reward = 172.00, steps = 172
22:56:31 [INFO] train episode 1932: reward = 171.00, steps = 171
22:56:31 [INFO] train episode 1933: reward = 166.00, steps = 166
22:56:31 [INFO] train episode 1934: reward = 200.00, steps = 200
22:56:31 [INFO] train episode 1935: reward = 200.00, steps = 200
22:56:31 [INFO] train episode 1936: reward = 165.00, steps = 165
22:56:32 [INFO] train episode 1937: reward = 153.00, steps = 153
22:56:32 [INFO] train episode 1938: reward = 185.00, steps = 185
22:56:32 [INFO] train episode 1939: reward = 200.00, steps = 200
22:56:32 [INFO] train episode 1940: reward = 200.00, steps = 200
22:56:32 [INFO] train episode 1941: reward = 156.00, steps = 156
22:56:32 [INFO] train episode 1942: reward = 200.00, steps = 200
22:56:32 [INFO] train episode 1943: reward = 162.00, steps = 162
22:56:32 [INFO] train episode 1944: reward = 200.00, steps = 200
22:56:32 [INFO] train episode 1945: reward = 200.00, steps = 200
22:56:33 [INFO] train episode 1946: reward = 195.00, steps = 195
22:56:33 [INFO] train episode 1947: reward = 110.00, steps = 110
22:56:33 [INFO] train episode 1948: reward = 180.00, steps = 180
22:56:33 [INFO] train episode 1949: reward = 189.00, steps = 189
22:56:33 [INFO] train episode 1950: reward = 200.00, steps = 200
22:56:33 [INFO] train episode 1951: reward = 167.00, steps = 167
22:56:33 [INFO] train episode 1952: reward = 145.00, steps = 145
22:56:33 [INFO] train episode 1953: reward = 178.00, steps = 178
22:56:33 [INFO] train episode 1954: reward = 136.00, steps = 136
22:56:33 [INFO] train episode 1955: reward = 173.00, steps = 173
22:56:33 [INFO] train episode 1956: reward = 140.00, steps = 140
22:56:34 [INFO] train episode 1957: reward = 165.00, steps = 165
22:56:34 [INFO] train episode 1958: reward = 200.00, steps = 200
22:56:34 [INFO] train episode 1959: reward = 185.00, steps = 185
22:56:34 [INFO] train episode 1960: reward = 150.00, steps = 150
22:56:34 [INFO] train episode 1961: reward = 200.00, steps = 200
22:56:34 [INFO] train episode 1962: reward = 199.00, steps = 199
22:56:34 [INFO] train episode 1963: reward = 114.00, steps = 114
22:56:34 [INFO] train episode 1964: reward = 131.00, steps = 131
22:56:34 [INFO] train episode 1965: reward = 128.00, steps = 128
22:56:34 [INFO] train episode 1966: reward = 171.00, steps = 171
22:56:34 [INFO] train episode 1967: reward = 200.00, steps = 200
22:56:34 [INFO] train episode 1968: reward = 162.00, steps = 162
22:56:35 [INFO] train episode 1969: reward = 188.00, steps = 188
22:56:35 [INFO] train episode 1970: reward = 143.00, steps = 143
22:56:35 [INFO] train episode 1971: reward = 200.00, steps = 200
22:56:35 [INFO] train episode 1972: reward = 200.00, steps = 200
22:56:35 [INFO] train episode 1973: reward = 164.00, steps = 164
22:56:35 [INFO] train episode 1974: reward = 174.00, steps = 174
22:56:35 [INFO] train episode 1975: reward = 200.00, steps = 200
22:56:35 [INFO] train episode 1976: reward = 139.00, steps = 139
22:56:35 [INFO] train episode 1977: reward = 182.00, steps = 182
22:56:36 [INFO] train episode 1978: reward = 125.00, steps = 125
22:56:36 [INFO] train episode 1979: reward = 148.00, steps = 148
22:56:36 [INFO] train episode 1980: reward = 138.00, steps = 138
22:56:36 [INFO] train episode 1981: reward = 107.00, steps = 107
22:56:36 [INFO] train episode 1982: reward = 128.00, steps = 128
22:56:36 [INFO] train episode 1983: reward = 200.00, steps = 200
22:56:36 [INFO] train episode 1984: reward = 133.00, steps = 133
22:56:36 [INFO] train episode 1985: reward = 153.00, steps = 153
22:56:36 [INFO] train episode 1986: reward = 133.00, steps = 133
22:56:36 [INFO] train episode 1987: reward = 176.00, steps = 176
22:56:36 [INFO] train episode 1988: reward = 161.00, steps = 161
22:56:36 [INFO] train episode 1989: reward = 200.00, steps = 200
22:56:37 [INFO] train episode 1990: reward = 200.00, steps = 200
22:56:37 [INFO] train episode 1991: reward = 194.00, steps = 194
22:56:37 [INFO] train episode 1992: reward = 122.00, steps = 122
22:56:37 [INFO] train episode 1993: reward = 146.00, steps = 146
22:56:37 [INFO] train episode 1994: reward = 126.00, steps = 126
22:56:37 [INFO] train episode 1995: reward = 200.00, steps = 200
22:56:37 [INFO] train episode 1996: reward = 187.00, steps = 187
22:56:37 [INFO] train episode 1997: reward = 173.00, steps = 173
22:56:37 [INFO] train episode 1998: reward = 156.00, steps = 156
22:56:37 [INFO] train episode 1999: reward = 200.00, steps = 200
22:56:38 [INFO] train episode 2000: reward = 173.00, steps = 173
22:56:38 [INFO] train episode 2001: reward = 200.00, steps = 200
22:56:38 [INFO] train episode 2002: reward = 127.00, steps = 127
22:56:38 [INFO] train episode 2003: reward = 185.00, steps = 185
22:56:38 [INFO] train episode 2004: reward = 178.00, steps = 178
22:56:38 [INFO] train episode 2005: reward = 178.00, steps = 178
22:56:38 [INFO] train episode 2006: reward = 200.00, steps = 200
22:56:38 [INFO] train episode 2007: reward = 150.00, steps = 150
22:56:39 [INFO] train episode 2008: reward = 162.00, steps = 162
22:56:39 [INFO] train episode 2009: reward = 171.00, steps = 171
22:56:39 [INFO] train episode 2010: reward = 131.00, steps = 131
22:56:39 [INFO] train episode 2011: reward = 200.00, steps = 200
22:56:39 [INFO] train episode 2012: reward = 117.00, steps = 117
22:56:39 [INFO] train episode 2013: reward = 200.00, steps = 200
22:56:39 [INFO] train episode 2014: reward = 180.00, steps = 180
22:56:39 [INFO] train episode 2015: reward = 146.00, steps = 146
22:56:39 [INFO] train episode 2016: reward = 171.00, steps = 171
22:56:39 [INFO] train episode 2017: reward = 141.00, steps = 141
22:56:40 [INFO] train episode 2018: reward = 143.00, steps = 143
22:56:40 [INFO] train episode 2019: reward = 200.00, steps = 200
22:56:40 [INFO] train episode 2020: reward = 200.00, steps = 200
22:56:40 [INFO] train episode 2021: reward = 185.00, steps = 185
22:56:40 [INFO] train episode 2022: reward = 125.00, steps = 125
22:56:40 [INFO] train episode 2023: reward = 174.00, steps = 174
22:56:40 [INFO] train episode 2024: reward = 153.00, steps = 153
22:56:40 [INFO] train episode 2025: reward = 162.00, steps = 162
22:56:40 [INFO] train episode 2026: reward = 178.00, steps = 178
22:56:41 [INFO] train episode 2027: reward = 160.00, steps = 160
22:56:41 [INFO] train episode 2028: reward = 146.00, steps = 146
22:56:41 [INFO] train episode 2029: reward = 149.00, steps = 149
22:56:41 [INFO] train episode 2030: reward = 128.00, steps = 128
22:56:41 [INFO] train episode 2031: reward = 200.00, steps = 200
22:56:41 [INFO] train episode 2032: reward = 165.00, steps = 165
22:56:41 [INFO] train episode 2033: reward = 156.00, steps = 156
22:56:41 [INFO] train episode 2034: reward = 198.00, steps = 198
22:56:41 [INFO] train episode 2035: reward = 140.00, steps = 140
22:56:42 [INFO] train episode 2036: reward = 163.00, steps = 163
22:56:42 [INFO] train episode 2037: reward = 138.00, steps = 138
22:56:42 [INFO] train episode 2038: reward = 117.00, steps = 117
22:56:42 [INFO] train episode 2039: reward = 142.00, steps = 142
22:56:42 [INFO] train episode 2040: reward = 188.00, steps = 188
22:56:42 [INFO] train episode 2041: reward = 200.00, steps = 200
22:56:42 [INFO] train episode 2042: reward = 200.00, steps = 200
22:56:42 [INFO] train episode 2043: reward = 157.00, steps = 157
22:56:42 [INFO] train episode 2044: reward = 140.00, steps = 140
22:56:43 [INFO] train episode 2045: reward = 152.00, steps = 152
22:56:43 [INFO] train episode 2046: reward = 185.00, steps = 185
22:56:43 [INFO] train episode 2047: reward = 160.00, steps = 160
22:56:43 [INFO] train episode 2048: reward = 194.00, steps = 194
22:56:43 [INFO] train episode 2049: reward = 195.00, steps = 195
22:56:43 [INFO] train episode 2050: reward = 200.00, steps = 200
22:56:43 [INFO] train episode 2051: reward = 121.00, steps = 121
22:56:43 [INFO] train episode 2052: reward = 170.00, steps = 170
22:56:43 [INFO] train episode 2053: reward = 200.00, steps = 200
22:56:44 [INFO] train episode 2054: reward = 200.00, steps = 200
22:56:44 [INFO] train episode 2055: reward = 200.00, steps = 200
22:56:44 [INFO] train episode 2056: reward = 158.00, steps = 158
22:56:44 [INFO] train episode 2057: reward = 135.00, steps = 135
22:56:44 [INFO] train episode 2058: reward = 170.00, steps = 170
22:56:44 [INFO] train episode 2059: reward = 134.00, steps = 134
22:56:44 [INFO] train episode 2060: reward = 133.00, steps = 133
22:56:44 [INFO] train episode 2061: reward = 172.00, steps = 172
22:56:45 [INFO] train episode 2062: reward = 141.00, steps = 141
22:56:45 [INFO] train episode 2063: reward = 182.00, steps = 182
22:56:45 [INFO] train episode 2064: reward = 145.00, steps = 145
22:56:45 [INFO] train episode 2065: reward = 162.00, steps = 162
22:56:45 [INFO] train episode 2066: reward = 198.00, steps = 198
22:56:45 [INFO] train episode 2067: reward = 128.00, steps = 128
22:56:45 [INFO] train episode 2068: reward = 167.00, steps = 167
22:56:45 [INFO] train episode 2069: reward = 162.00, steps = 162
22:56:45 [INFO] train episode 2070: reward = 135.00, steps = 135
22:56:45 [INFO] train episode 2071: reward = 146.00, steps = 146
22:56:46 [INFO] train episode 2072: reward = 200.00, steps = 200
22:56:46 [INFO] train episode 2073: reward = 126.00, steps = 126
22:56:46 [INFO] train episode 2074: reward = 153.00, steps = 153
22:56:46 [INFO] train episode 2075: reward = 167.00, steps = 167
22:56:46 [INFO] train episode 2076: reward = 185.00, steps = 185
22:56:46 [INFO] train episode 2077: reward = 174.00, steps = 174
22:56:46 [INFO] train episode 2078: reward = 129.00, steps = 129
22:56:46 [INFO] train episode 2079: reward = 196.00, steps = 196
22:56:46 [INFO] train episode 2080: reward = 109.00, steps = 109
22:56:47 [INFO] train episode 2081: reward = 139.00, steps = 139
22:56:47 [INFO] train episode 2082: reward = 133.00, steps = 133
22:56:47 [INFO] train episode 2083: reward = 108.00, steps = 108
22:56:47 [INFO] train episode 2084: reward = 200.00, steps = 200
22:56:47 [INFO] train episode 2085: reward = 138.00, steps = 138
22:56:47 [INFO] train episode 2086: reward = 130.00, steps = 130
22:56:47 [INFO] train episode 2087: reward = 200.00, steps = 200
22:56:47 [INFO] train episode 2088: reward = 128.00, steps = 128
22:56:47 [INFO] train episode 2089: reward = 146.00, steps = 146
22:56:47 [INFO] train episode 2090: reward = 108.00, steps = 108
22:56:47 [INFO] train episode 2091: reward = 200.00, steps = 200
22:56:48 [INFO] train episode 2092: reward = 112.00, steps = 112
22:56:48 [INFO] train episode 2093: reward = 132.00, steps = 132
22:56:48 [INFO] train episode 2094: reward = 178.00, steps = 178
22:56:48 [INFO] train episode 2095: reward = 200.00, steps = 200
22:56:48 [INFO] train episode 2096: reward = 116.00, steps = 116
22:56:48 [INFO] train episode 2097: reward = 167.00, steps = 167
22:56:48 [INFO] train episode 2098: reward = 200.00, steps = 200
22:56:48 [INFO] train episode 2099: reward = 200.00, steps = 200
22:56:48 [INFO] train episode 2100: reward = 134.00, steps = 134
22:56:48 [INFO] train episode 2101: reward = 156.00, steps = 156
22:56:49 [INFO] train episode 2102: reward = 143.00, steps = 143
22:56:49 [INFO] train episode 2103: reward = 144.00, steps = 144
22:56:49 [INFO] train episode 2104: reward = 98.00, steps = 98
22:56:49 [INFO] train episode 2105: reward = 131.00, steps = 131
22:56:49 [INFO] train episode 2106: reward = 125.00, steps = 125
22:56:49 [INFO] train episode 2107: reward = 91.00, steps = 91
22:56:49 [INFO] train episode 2108: reward = 110.00, steps = 110
22:56:49 [INFO] train episode 2109: reward = 200.00, steps = 200
22:56:49 [INFO] train episode 2110: reward = 124.00, steps = 124
22:56:49 [INFO] train episode 2111: reward = 200.00, steps = 200
22:56:49 [INFO] train episode 2112: reward = 87.00, steps = 87
22:56:49 [INFO] train episode 2113: reward = 100.00, steps = 100
22:56:49 [INFO] train episode 2114: reward = 96.00, steps = 96
22:56:50 [INFO] train episode 2115: reward = 105.00, steps = 105
22:56:50 [INFO] train episode 2116: reward = 200.00, steps = 200
22:56:50 [INFO] train episode 2117: reward = 170.00, steps = 170
22:56:50 [INFO] train episode 2118: reward = 109.00, steps = 109
22:56:50 [INFO] train episode 2119: reward = 200.00, steps = 200
22:56:50 [INFO] train episode 2120: reward = 113.00, steps = 113
22:56:50 [INFO] train episode 2121: reward = 144.00, steps = 144
22:56:50 [INFO] train episode 2122: reward = 165.00, steps = 165
22:56:50 [INFO] train episode 2123: reward = 87.00, steps = 87
22:56:50 [INFO] train episode 2124: reward = 176.00, steps = 176
22:56:51 [INFO] train episode 2125: reward = 200.00, steps = 200
22:56:51 [INFO] train episode 2126: reward = 99.00, steps = 99
22:56:51 [INFO] train episode 2127: reward = 125.00, steps = 125
22:56:51 [INFO] train episode 2128: reward = 103.00, steps = 103
22:56:51 [INFO] train episode 2129: reward = 89.00, steps = 89
22:56:51 [INFO] train episode 2130: reward = 164.00, steps = 164
22:56:51 [INFO] train episode 2131: reward = 200.00, steps = 200
22:56:51 [INFO] train episode 2132: reward = 104.00, steps = 104
22:56:51 [INFO] train episode 2133: reward = 119.00, steps = 119
22:56:51 [INFO] train episode 2134: reward = 200.00, steps = 200
22:56:51 [INFO] train episode 2135: reward = 189.00, steps = 189
22:56:52 [INFO] train episode 2136: reward = 178.00, steps = 178
22:56:52 [INFO] train episode 2137: reward = 169.00, steps = 169
22:56:52 [INFO] train episode 2138: reward = 151.00, steps = 151
22:56:52 [INFO] train episode 2139: reward = 117.00, steps = 117
22:56:52 [INFO] train episode 2140: reward = 170.00, steps = 170
22:56:52 [INFO] train episode 2141: reward = 110.00, steps = 110
22:56:52 [INFO] train episode 2142: reward = 200.00, steps = 200
22:56:52 [INFO] train episode 2143: reward = 125.00, steps = 125
22:56:52 [INFO] train episode 2144: reward = 140.00, steps = 140
22:56:52 [INFO] train episode 2145: reward = 107.00, steps = 107
22:56:52 [INFO] train episode 2146: reward = 119.00, steps = 119
22:56:52 [INFO] train episode 2147: reward = 125.00, steps = 125
22:56:53 [INFO] train episode 2148: reward = 132.00, steps = 132
22:56:53 [INFO] train episode 2149: reward = 160.00, steps = 160
22:56:53 [INFO] train episode 2150: reward = 111.00, steps = 111
22:56:53 [INFO] train episode 2151: reward = 123.00, steps = 123
22:56:53 [INFO] train episode 2152: reward = 116.00, steps = 116
22:56:53 [INFO] train episode 2153: reward = 200.00, steps = 200
22:56:53 [INFO] train episode 2154: reward = 110.00, steps = 110
22:56:53 [INFO] train episode 2155: reward = 114.00, steps = 114
22:56:53 [INFO] train episode 2156: reward = 115.00, steps = 115
22:56:53 [INFO] train episode 2157: reward = 111.00, steps = 111
22:56:53 [INFO] train episode 2158: reward = 97.00, steps = 97
22:56:54 [INFO] train episode 2159: reward = 125.00, steps = 125
22:56:54 [INFO] train episode 2160: reward = 122.00, steps = 122
22:56:54 [INFO] train episode 2161: reward = 135.00, steps = 135
22:56:54 [INFO] train episode 2162: reward = 132.00, steps = 132
22:56:54 [INFO] train episode 2163: reward = 100.00, steps = 100
22:56:54 [INFO] train episode 2164: reward = 127.00, steps = 127
22:56:54 [INFO] train episode 2165: reward = 108.00, steps = 108
22:56:54 [INFO] train episode 2166: reward = 149.00, steps = 149
22:56:54 [INFO] train episode 2167: reward = 121.00, steps = 121
22:56:54 [INFO] train episode 2168: reward = 125.00, steps = 125
22:56:54 [INFO] train episode 2169: reward = 104.00, steps = 104
22:56:54 [INFO] train episode 2170: reward = 200.00, steps = 200
22:56:55 [INFO] train episode 2171: reward = 160.00, steps = 160
22:56:55 [INFO] train episode 2172: reward = 104.00, steps = 104
22:56:55 [INFO] train episode 2173: reward = 137.00, steps = 137
22:56:55 [INFO] train episode 2174: reward = 174.00, steps = 174
22:56:55 [INFO] train episode 2175: reward = 157.00, steps = 157
22:56:55 [INFO] train episode 2176: reward = 146.00, steps = 146
22:56:55 [INFO] train episode 2177: reward = 200.00, steps = 200
22:56:55 [INFO] train episode 2178: reward = 200.00, steps = 200
22:56:55 [INFO] train episode 2179: reward = 137.00, steps = 137
22:56:55 [INFO] train episode 2180: reward = 119.00, steps = 119
22:56:55 [INFO] train episode 2181: reward = 104.00, steps = 104
22:56:55 [INFO] train episode 2182: reward = 120.00, steps = 120
22:56:56 [INFO] train episode 2183: reward = 108.00, steps = 108
22:56:56 [INFO] train episode 2184: reward = 146.00, steps = 146
22:56:56 [INFO] train episode 2185: reward = 112.00, steps = 112
22:56:56 [INFO] train episode 2186: reward = 200.00, steps = 200
22:56:56 [INFO] train episode 2187: reward = 181.00, steps = 181
22:56:56 [INFO] train episode 2188: reward = 139.00, steps = 139
22:56:56 [INFO] train episode 2189: reward = 172.00, steps = 172
22:56:56 [INFO] train episode 2190: reward = 135.00, steps = 135
22:56:56 [INFO] train episode 2191: reward = 145.00, steps = 145
22:56:56 [INFO] train episode 2192: reward = 200.00, steps = 200
22:56:56 [INFO] train episode 2193: reward = 116.00, steps = 116
22:56:57 [INFO] train episode 2194: reward = 185.00, steps = 185
22:56:57 [INFO] train episode 2195: reward = 163.00, steps = 163
22:56:57 [INFO] train episode 2196: reward = 134.00, steps = 134
22:56:57 [INFO] train episode 2197: reward = 200.00, steps = 200
22:56:57 [INFO] train episode 2198: reward = 196.00, steps = 196
22:56:57 [INFO] train episode 2199: reward = 147.00, steps = 147
22:56:57 [INFO] train episode 2200: reward = 130.00, steps = 130
22:56:57 [INFO] train episode 2201: reward = 146.00, steps = 146
22:56:57 [INFO] train episode 2202: reward = 112.00, steps = 112
22:56:57 [INFO] train episode 2203: reward = 154.00, steps = 154
22:56:58 [INFO] train episode 2204: reward = 111.00, steps = 111
22:56:58 [INFO] train episode 2205: reward = 197.00, steps = 197
22:56:58 [INFO] train episode 2206: reward = 94.00, steps = 94
22:56:58 [INFO] train episode 2207: reward = 142.00, steps = 142
22:56:58 [INFO] train episode 2208: reward = 123.00, steps = 123
22:56:58 [INFO] train episode 2209: reward = 132.00, steps = 132
22:56:58 [INFO] train episode 2210: reward = 99.00, steps = 99
22:56:58 [INFO] train episode 2211: reward = 103.00, steps = 103
22:56:58 [INFO] train episode 2212: reward = 123.00, steps = 123
22:56:58 [INFO] train episode 2213: reward = 115.00, steps = 115
22:56:59 [INFO] train episode 2214: reward = 106.00, steps = 106
22:56:59 [INFO] train episode 2215: reward = 116.00, steps = 116
22:56:59 [INFO] train episode 2216: reward = 144.00, steps = 144
22:56:59 [INFO] train episode 2217: reward = 114.00, steps = 114
22:56:59 [INFO] train episode 2218: reward = 189.00, steps = 189
22:56:59 [INFO] train episode 2219: reward = 142.00, steps = 142
22:56:59 [INFO] train episode 2220: reward = 109.00, steps = 109
22:56:59 [INFO] train episode 2221: reward = 123.00, steps = 123
22:56:59 [INFO] train episode 2222: reward = 181.00, steps = 181
22:56:59 [INFO] train episode 2223: reward = 124.00, steps = 124
22:56:59 [INFO] train episode 2224: reward = 115.00, steps = 115
22:57:00 [INFO] train episode 2225: reward = 113.00, steps = 113
22:57:00 [INFO] train episode 2226: reward = 126.00, steps = 126
22:57:00 [INFO] train episode 2227: reward = 159.00, steps = 159
22:57:00 [INFO] train episode 2228: reward = 141.00, steps = 141
22:57:00 [INFO] train episode 2229: reward = 129.00, steps = 129
22:57:00 [INFO] train episode 2230: reward = 190.00, steps = 190
22:57:00 [INFO] train episode 2231: reward = 200.00, steps = 200
22:57:00 [INFO] train episode 2232: reward = 158.00, steps = 158
22:57:01 [INFO] train episode 2233: reward = 127.00, steps = 127
22:57:01 [INFO] train episode 2234: reward = 200.00, steps = 200
22:57:01 [INFO] train episode 2235: reward = 200.00, steps = 200
22:57:01 [INFO] train episode 2236: reward = 128.00, steps = 128
22:57:01 [INFO] train episode 2237: reward = 159.00, steps = 159
22:57:01 [INFO] train episode 2238: reward = 105.00, steps = 105
22:57:01 [INFO] train episode 2239: reward = 122.00, steps = 122
22:57:01 [INFO] train episode 2240: reward = 141.00, steps = 141
22:57:01 [INFO] train episode 2241: reward = 97.00, steps = 97
22:57:02 [INFO] train episode 2242: reward = 102.00, steps = 102
22:57:02 [INFO] train episode 2243: reward = 111.00, steps = 111
22:57:02 [INFO] train episode 2244: reward = 121.00, steps = 121
22:57:02 [INFO] train episode 2245: reward = 110.00, steps = 110
22:57:02 [INFO] train episode 2246: reward = 83.00, steps = 83
22:57:02 [INFO] train episode 2247: reward = 129.00, steps = 129
22:57:02 [INFO] train episode 2248: reward = 120.00, steps = 120
22:57:02 [INFO] train episode 2249: reward = 149.00, steps = 149
22:57:02 [INFO] train episode 2250: reward = 144.00, steps = 144
22:57:02 [INFO] train episode 2251: reward = 102.00, steps = 102
22:57:02 [INFO] train episode 2252: reward = 124.00, steps = 124
22:57:02 [INFO] train episode 2253: reward = 101.00, steps = 101
22:57:02 [INFO] train episode 2254: reward = 197.00, steps = 197
22:57:03 [INFO] train episode 2255: reward = 120.00, steps = 120
22:57:03 [INFO] train episode 2256: reward = 96.00, steps = 96
22:57:03 [INFO] train episode 2257: reward = 123.00, steps = 123
22:57:03 [INFO] train episode 2258: reward = 97.00, steps = 97
22:57:03 [INFO] train episode 2259: reward = 109.00, steps = 109
22:57:03 [INFO] train episode 2260: reward = 119.00, steps = 119
22:57:03 [INFO] train episode 2261: reward = 155.00, steps = 155
22:57:03 [INFO] train episode 2262: reward = 185.00, steps = 185
22:57:03 [INFO] train episode 2263: reward = 129.00, steps = 129
22:57:03 [INFO] train episode 2264: reward = 120.00, steps = 120
22:57:03 [INFO] train episode 2265: reward = 119.00, steps = 119
22:57:03 [INFO] train episode 2266: reward = 123.00, steps = 123
22:57:03 [INFO] train episode 2267: reward = 149.00, steps = 149
22:57:04 [INFO] train episode 2268: reward = 101.00, steps = 101
22:57:04 [INFO] train episode 2269: reward = 128.00, steps = 128
22:57:04 [INFO] train episode 2270: reward = 121.00, steps = 121
22:57:04 [INFO] train episode 2271: reward = 110.00, steps = 110
22:57:04 [INFO] train episode 2272: reward = 96.00, steps = 96
22:57:04 [INFO] train episode 2273: reward = 145.00, steps = 145
22:57:04 [INFO] train episode 2274: reward = 158.00, steps = 158
22:57:04 [INFO] train episode 2275: reward = 94.00, steps = 94
22:57:04 [INFO] train episode 2276: reward = 118.00, steps = 118
22:57:04 [INFO] train episode 2277: reward = 112.00, steps = 112
22:57:04 [INFO] train episode 2278: reward = 158.00, steps = 158
22:57:04 [INFO] train episode 2279: reward = 101.00, steps = 101
22:57:05 [INFO] train episode 2280: reward = 166.00, steps = 166
22:57:05 [INFO] train episode 2281: reward = 115.00, steps = 115
22:57:05 [INFO] train episode 2282: reward = 89.00, steps = 89
22:57:05 [INFO] train episode 2283: reward = 118.00, steps = 118
22:57:05 [INFO] train episode 2284: reward = 133.00, steps = 133
22:57:05 [INFO] train episode 2285: reward = 90.00, steps = 90
22:57:05 [INFO] train episode 2286: reward = 131.00, steps = 131
22:57:05 [INFO] train episode 2287: reward = 116.00, steps = 116
22:57:05 [INFO] train episode 2288: reward = 113.00, steps = 113
22:57:05 [INFO] train episode 2289: reward = 115.00, steps = 115
22:57:05 [INFO] train episode 2290: reward = 105.00, steps = 105
22:57:05 [INFO] train episode 2291: reward = 200.00, steps = 200
22:57:05 [INFO] train episode 2292: reward = 110.00, steps = 110
22:57:06 [INFO] train episode 2293: reward = 119.00, steps = 119
22:57:06 [INFO] train episode 2294: reward = 110.00, steps = 110
22:57:06 [INFO] train episode 2295: reward = 200.00, steps = 200
22:57:06 [INFO] train episode 2296: reward = 122.00, steps = 122
22:57:06 [INFO] train episode 2297: reward = 109.00, steps = 109
22:57:06 [INFO] train episode 2298: reward = 135.00, steps = 135
22:57:06 [INFO] train episode 2299: reward = 111.00, steps = 111
22:57:06 [INFO] train episode 2300: reward = 92.00, steps = 92
22:57:06 [INFO] train episode 2301: reward = 135.00, steps = 135
22:57:06 [INFO] train episode 2302: reward = 127.00, steps = 127
22:57:06 [INFO] train episode 2303: reward = 139.00, steps = 139
22:57:06 [INFO] train episode 2304: reward = 137.00, steps = 137
22:57:06 [INFO] train episode 2305: reward = 101.00, steps = 101
22:57:06 [INFO] train episode 2306: reward = 134.00, steps = 134
22:57:07 [INFO] train episode 2307: reward = 115.00, steps = 115
22:57:07 [INFO] train episode 2308: reward = 130.00, steps = 130
22:57:07 [INFO] train episode 2309: reward = 121.00, steps = 121
22:57:07 [INFO] train episode 2310: reward = 132.00, steps = 132
22:57:07 [INFO] train episode 2311: reward = 101.00, steps = 101
22:57:07 [INFO] train episode 2312: reward = 128.00, steps = 128
22:57:07 [INFO] train episode 2313: reward = 116.00, steps = 116
22:57:07 [INFO] train episode 2314: reward = 200.00, steps = 200
22:57:07 [INFO] train episode 2315: reward = 131.00, steps = 131
22:57:07 [INFO] train episode 2316: reward = 115.00, steps = 115
22:57:07 [INFO] train episode 2317: reward = 93.00, steps = 93
22:57:07 [INFO] train episode 2318: reward = 107.00, steps = 107
22:57:07 [INFO] train episode 2319: reward = 139.00, steps = 139
22:57:08 [INFO] train episode 2320: reward = 129.00, steps = 129
22:57:08 [INFO] train episode 2321: reward = 119.00, steps = 119
22:57:08 [INFO] train episode 2322: reward = 187.00, steps = 187
22:57:08 [INFO] train episode 2323: reward = 145.00, steps = 145
22:57:08 [INFO] train episode 2324: reward = 101.00, steps = 101
22:57:08 [INFO] train episode 2325: reward = 159.00, steps = 159
22:57:08 [INFO] train episode 2326: reward = 84.00, steps = 84
22:57:08 [INFO] train episode 2327: reward = 98.00, steps = 98
22:57:08 [INFO] train episode 2328: reward = 128.00, steps = 128
22:57:08 [INFO] train episode 2329: reward = 125.00, steps = 125
22:57:08 [INFO] train episode 2330: reward = 97.00, steps = 97
22:57:08 [INFO] train episode 2331: reward = 124.00, steps = 124
22:57:08 [INFO] train episode 2332: reward = 143.00, steps = 143
22:57:09 [INFO] train episode 2333: reward = 159.00, steps = 159
22:57:09 [INFO] train episode 2334: reward = 200.00, steps = 200
22:57:09 [INFO] train episode 2335: reward = 135.00, steps = 135
22:57:09 [INFO] train episode 2336: reward = 108.00, steps = 108
22:57:09 [INFO] train episode 2337: reward = 105.00, steps = 105
22:57:09 [INFO] train episode 2338: reward = 106.00, steps = 106
22:57:09 [INFO] train episode 2339: reward = 172.00, steps = 172
22:57:09 [INFO] train episode 2340: reward = 97.00, steps = 97
22:57:09 [INFO] train episode 2341: reward = 113.00, steps = 113
22:57:09 [INFO] train episode 2342: reward = 169.00, steps = 169
22:57:09 [INFO] train episode 2343: reward = 137.00, steps = 137
22:57:09 [INFO] train episode 2344: reward = 103.00, steps = 103
22:57:09 [INFO] train episode 2345: reward = 97.00, steps = 97
22:57:10 [INFO] train episode 2346: reward = 170.00, steps = 170
22:57:10 [INFO] train episode 2347: reward = 176.00, steps = 176
22:57:10 [INFO] train episode 2348: reward = 138.00, steps = 138
22:57:10 [INFO] train episode 2349: reward = 113.00, steps = 113
22:57:10 [INFO] train episode 2350: reward = 119.00, steps = 119
22:57:10 [INFO] train episode 2351: reward = 105.00, steps = 105
22:57:10 [INFO] train episode 2352: reward = 145.00, steps = 145
22:57:10 [INFO] train episode 2353: reward = 123.00, steps = 123
22:57:10 [INFO] train episode 2354: reward = 174.00, steps = 174
22:57:10 [INFO] train episode 2355: reward = 88.00, steps = 88
22:57:10 [INFO] train episode 2356: reward = 175.00, steps = 175
22:57:10 [INFO] train episode 2357: reward = 91.00, steps = 91
22:57:10 [INFO] train episode 2358: reward = 123.00, steps = 123
22:57:11 [INFO] train episode 2359: reward = 138.00, steps = 138
22:57:11 [INFO] train episode 2360: reward = 121.00, steps = 121
22:57:11 [INFO] train episode 2361: reward = 127.00, steps = 127
22:57:11 [INFO] train episode 2362: reward = 107.00, steps = 107
22:57:11 [INFO] train episode 2363: reward = 111.00, steps = 111
22:57:11 [INFO] train episode 2364: reward = 118.00, steps = 118
22:57:11 [INFO] train episode 2365: reward = 177.00, steps = 177
22:57:11 [INFO] train episode 2366: reward = 117.00, steps = 117
22:57:11 [INFO] train episode 2367: reward = 74.00, steps = 74
22:57:11 [INFO] train episode 2368: reward = 105.00, steps = 105
22:57:12 [INFO] train episode 2369: reward = 82.00, steps = 82
22:57:12 [INFO] train episode 2370: reward = 103.00, steps = 103
22:57:12 [INFO] train episode 2371: reward = 135.00, steps = 135
22:57:12 [INFO] train episode 2372: reward = 117.00, steps = 117
22:57:12 [INFO] train episode 2373: reward = 109.00, steps = 109
22:57:12 [INFO] train episode 2374: reward = 112.00, steps = 112
22:57:12 [INFO] train episode 2375: reward = 197.00, steps = 197
22:57:12 [INFO] train episode 2376: reward = 115.00, steps = 115
22:57:12 [INFO] train episode 2377: reward = 113.00, steps = 113
22:57:12 [INFO] train episode 2378: reward = 93.00, steps = 93
22:57:12 [INFO] train episode 2379: reward = 106.00, steps = 106
22:57:12 [INFO] train episode 2380: reward = 163.00, steps = 163
22:57:13 [INFO] train episode 2381: reward = 118.00, steps = 118
22:57:13 [INFO] train episode 2382: reward = 157.00, steps = 157
22:57:13 [INFO] train episode 2383: reward = 113.00, steps = 113
22:57:13 [INFO] train episode 2384: reward = 144.00, steps = 144
22:57:13 [INFO] train episode 2385: reward = 140.00, steps = 140
22:57:13 [INFO] train episode 2386: reward = 130.00, steps = 130
22:57:13 [INFO] train episode 2387: reward = 150.00, steps = 150
22:57:13 [INFO] train episode 2388: reward = 94.00, steps = 94
22:57:13 [INFO] train episode 2389: reward = 144.00, steps = 144
22:57:13 [INFO] train episode 2390: reward = 200.00, steps = 200
22:57:13 [INFO] train episode 2391: reward = 93.00, steps = 93
22:57:13 [INFO] train episode 2392: reward = 108.00, steps = 108
22:57:13 [INFO] train episode 2393: reward = 112.00, steps = 112
22:57:14 [INFO] train episode 2394: reward = 103.00, steps = 103
22:57:14 [INFO] train episode 2395: reward = 108.00, steps = 108
22:57:14 [INFO] train episode 2396: reward = 171.00, steps = 171
22:57:14 [INFO] train episode 2397: reward = 129.00, steps = 129
22:57:14 [INFO] train episode 2398: reward = 165.00, steps = 165
22:57:14 [INFO] train episode 2399: reward = 126.00, steps = 126
22:57:14 [INFO] train episode 2400: reward = 199.00, steps = 199
22:57:14 [INFO] train episode 2401: reward = 131.00, steps = 131
22:57:14 [INFO] train episode 2402: reward = 186.00, steps = 186
22:57:14 [INFO] train episode 2403: reward = 134.00, steps = 134
22:57:14 [INFO] train episode 2404: reward = 180.00, steps = 180
22:57:15 [INFO] train episode 2405: reward = 121.00, steps = 121
22:57:15 [INFO] train episode 2406: reward = 186.00, steps = 186
22:57:15 [INFO] train episode 2407: reward = 139.00, steps = 139
22:57:15 [INFO] train episode 2408: reward = 95.00, steps = 95
22:57:15 [INFO] train episode 2409: reward = 188.00, steps = 188
22:57:15 [INFO] train episode 2410: reward = 136.00, steps = 136
22:57:15 [INFO] train episode 2411: reward = 175.00, steps = 175
22:57:15 [INFO] train episode 2412: reward = 133.00, steps = 133
22:57:15 [INFO] train episode 2413: reward = 127.00, steps = 127
22:57:15 [INFO] train episode 2414: reward = 132.00, steps = 132
22:57:16 [INFO] train episode 2415: reward = 162.00, steps = 162
22:57:16 [INFO] train episode 2416: reward = 111.00, steps = 111
22:57:16 [INFO] train episode 2417: reward = 118.00, steps = 118
22:57:16 [INFO] train episode 2418: reward = 200.00, steps = 200
22:57:16 [INFO] train episode 2419: reward = 149.00, steps = 149
22:57:16 [INFO] train episode 2420: reward = 108.00, steps = 108
22:57:16 [INFO] train episode 2421: reward = 106.00, steps = 106
22:57:16 [INFO] train episode 2422: reward = 141.00, steps = 141
22:57:16 [INFO] train episode 2423: reward = 108.00, steps = 108
22:57:16 [INFO] train episode 2424: reward = 135.00, steps = 135
22:57:16 [INFO] train episode 2425: reward = 108.00, steps = 108
22:57:16 [INFO] train episode 2426: reward = 145.00, steps = 145
22:57:16 [INFO] train episode 2427: reward = 200.00, steps = 200
22:57:17 [INFO] train episode 2428: reward = 200.00, steps = 200
22:57:17 [INFO] train episode 2429: reward = 114.00, steps = 114
22:57:17 [INFO] train episode 2430: reward = 140.00, steps = 140
22:57:17 [INFO] train episode 2431: reward = 103.00, steps = 103
22:57:17 [INFO] train episode 2432: reward = 139.00, steps = 139
22:57:17 [INFO] train episode 2433: reward = 94.00, steps = 94
22:57:17 [INFO] train episode 2434: reward = 136.00, steps = 136
22:57:17 [INFO] train episode 2435: reward = 131.00, steps = 131
22:57:17 [INFO] train episode 2436: reward = 124.00, steps = 124
22:57:17 [INFO] train episode 2437: reward = 104.00, steps = 104
22:57:17 [INFO] train episode 2438: reward = 101.00, steps = 101
22:57:17 [INFO] train episode 2439: reward = 107.00, steps = 107
22:57:17 [INFO] train episode 2440: reward = 108.00, steps = 108
22:57:17 [INFO] train episode 2441: reward = 200.00, steps = 200
22:57:18 [INFO] train episode 2442: reward = 116.00, steps = 116
22:57:18 [INFO] train episode 2443: reward = 96.00, steps = 96
22:57:18 [INFO] train episode 2444: reward = 200.00, steps = 200
22:57:18 [INFO] train episode 2445: reward = 127.00, steps = 127
22:57:18 [INFO] train episode 2446: reward = 109.00, steps = 109
22:57:18 [INFO] train episode 2447: reward = 131.00, steps = 131
22:57:18 [INFO] train episode 2448: reward = 99.00, steps = 99
22:57:18 [INFO] train episode 2449: reward = 113.00, steps = 113
22:57:18 [INFO] train episode 2450: reward = 151.00, steps = 151
22:57:18 [INFO] train episode 2451: reward = 111.00, steps = 111
22:57:18 [INFO] train episode 2452: reward = 105.00, steps = 105
22:57:18 [INFO] train episode 2453: reward = 126.00, steps = 126
22:57:19 [INFO] train episode 2454: reward = 164.00, steps = 164
22:57:19 [INFO] train episode 2455: reward = 168.00, steps = 168
22:57:19 [INFO] train episode 2456: reward = 105.00, steps = 105
22:57:19 [INFO] train episode 2457: reward = 148.00, steps = 148
22:57:19 [INFO] train episode 2458: reward = 135.00, steps = 135
22:57:19 [INFO] train episode 2459: reward = 102.00, steps = 102
22:57:19 [INFO] train episode 2460: reward = 172.00, steps = 172
22:57:19 [INFO] train episode 2461: reward = 123.00, steps = 123
22:57:19 [INFO] train episode 2462: reward = 115.00, steps = 115
22:57:19 [INFO] train episode 2463: reward = 96.00, steps = 96
22:57:19 [INFO] train episode 2464: reward = 144.00, steps = 144
22:57:19 [INFO] train episode 2465: reward = 128.00, steps = 128
22:57:19 [INFO] train episode 2466: reward = 94.00, steps = 94
22:57:20 [INFO] train episode 2467: reward = 170.00, steps = 170
22:57:20 [INFO] train episode 2468: reward = 200.00, steps = 200
22:57:20 [INFO] train episode 2469: reward = 200.00, steps = 200
22:57:20 [INFO] train episode 2470: reward = 139.00, steps = 139
22:57:20 [INFO] train episode 2471: reward = 93.00, steps = 93
22:57:20 [INFO] train episode 2472: reward = 164.00, steps = 164
22:57:20 [INFO] train episode 2473: reward = 148.00, steps = 148
22:57:20 [INFO] train episode 2474: reward = 200.00, steps = 200
22:57:21 [INFO] train episode 2475: reward = 126.00, steps = 126
22:57:21 [INFO] train episode 2476: reward = 154.00, steps = 154
22:57:21 [INFO] train episode 2477: reward = 150.00, steps = 150
22:57:21 [INFO] train episode 2478: reward = 118.00, steps = 118
22:57:21 [INFO] train episode 2479: reward = 161.00, steps = 161
22:57:21 [INFO] train episode 2480: reward = 108.00, steps = 108
22:57:21 [INFO] train episode 2481: reward = 154.00, steps = 154
22:57:21 [INFO] train episode 2482: reward = 122.00, steps = 122
22:57:21 [INFO] train episode 2483: reward = 128.00, steps = 128
22:57:21 [INFO] train episode 2484: reward = 133.00, steps = 133
22:57:21 [INFO] train episode 2485: reward = 121.00, steps = 121
22:57:22 [INFO] train episode 2486: reward = 132.00, steps = 132
22:57:22 [INFO] train episode 2487: reward = 100.00, steps = 100
22:57:22 [INFO] train episode 2488: reward = 152.00, steps = 152
22:57:22 [INFO] train episode 2489: reward = 97.00, steps = 97
22:57:22 [INFO] train episode 2490: reward = 169.00, steps = 169
22:57:22 [INFO] train episode 2491: reward = 97.00, steps = 97
22:57:22 [INFO] train episode 2492: reward = 124.00, steps = 124
22:57:22 [INFO] train episode 2493: reward = 189.00, steps = 189
22:57:22 [INFO] train episode 2494: reward = 146.00, steps = 146
22:57:22 [INFO] train episode 2495: reward = 137.00, steps = 137
22:57:22 [INFO] train episode 2496: reward = 98.00, steps = 98
22:57:22 [INFO] train episode 2497: reward = 117.00, steps = 117
22:57:22 [INFO] train episode 2498: reward = 105.00, steps = 105
22:57:22 [INFO] train episode 2499: reward = 106.00, steps = 106
22:57:23 [INFO] train episode 2500: reward = 191.00, steps = 191
22:57:23 [INFO] train episode 2501: reward = 146.00, steps = 146
22:57:23 [INFO] train episode 2502: reward = 165.00, steps = 165
22:57:23 [INFO] train episode 2503: reward = 180.00, steps = 180
22:57:23 [INFO] train episode 2504: reward = 94.00, steps = 94
22:57:23 [INFO] train episode 2505: reward = 189.00, steps = 189
22:57:23 [INFO] train episode 2506: reward = 113.00, steps = 113
22:57:23 [INFO] train episode 2507: reward = 167.00, steps = 167
22:57:23 [INFO] train episode 2508: reward = 140.00, steps = 140
22:57:23 [INFO] train episode 2509: reward = 92.00, steps = 92
22:57:24 [INFO] train episode 2510: reward = 156.00, steps = 156
22:57:24 [INFO] train episode 2511: reward = 125.00, steps = 125
22:57:24 [INFO] train episode 2512: reward = 130.00, steps = 130
22:57:24 [INFO] train episode 2513: reward = 200.00, steps = 200
22:57:24 [INFO] train episode 2514: reward = 200.00, steps = 200
22:57:24 [INFO] train episode 2515: reward = 159.00, steps = 159
22:57:24 [INFO] train episode 2516: reward = 103.00, steps = 103
22:57:24 [INFO] train episode 2517: reward = 113.00, steps = 113
22:57:24 [INFO] train episode 2518: reward = 117.00, steps = 117
22:57:24 [INFO] train episode 2519: reward = 118.00, steps = 118
22:57:24 [INFO] train episode 2520: reward = 141.00, steps = 141
22:57:24 [INFO] train episode 2521: reward = 84.00, steps = 84
22:57:24 [INFO] train episode 2522: reward = 118.00, steps = 118
22:57:25 [INFO] train episode 2523: reward = 137.00, steps = 137
22:57:25 [INFO] train episode 2524: reward = 107.00, steps = 107
22:57:25 [INFO] train episode 2525: reward = 127.00, steps = 127
22:57:25 [INFO] train episode 2526: reward = 145.00, steps = 145
22:57:25 [INFO] train episode 2527: reward = 124.00, steps = 124
22:57:25 [INFO] train episode 2528: reward = 132.00, steps = 132
22:57:25 [INFO] train episode 2529: reward = 189.00, steps = 189
22:57:25 [INFO] train episode 2530: reward = 143.00, steps = 143
22:57:25 [INFO] train episode 2531: reward = 142.00, steps = 142
22:57:25 [INFO] train episode 2532: reward = 104.00, steps = 104
22:57:25 [INFO] train episode 2533: reward = 118.00, steps = 118
22:57:25 [INFO] train episode 2534: reward = 124.00, steps = 124
22:57:26 [INFO] train episode 2535: reward = 163.00, steps = 163
22:57:26 [INFO] train episode 2536: reward = 120.00, steps = 120
22:57:26 [INFO] train episode 2537: reward = 183.00, steps = 183
22:57:26 [INFO] train episode 2538: reward = 139.00, steps = 139
22:57:26 [INFO] train episode 2539: reward = 136.00, steps = 136
22:57:26 [INFO] train episode 2540: reward = 107.00, steps = 107
22:57:26 [INFO] train episode 2541: reward = 117.00, steps = 117
22:57:26 [INFO] train episode 2542: reward = 145.00, steps = 145
22:57:26 [INFO] train episode 2543: reward = 146.00, steps = 146
22:57:26 [INFO] train episode 2544: reward = 179.00, steps = 179
22:57:27 [INFO] train episode 2545: reward = 200.00, steps = 200
22:57:27 [INFO] train episode 2546: reward = 113.00, steps = 113
22:57:27 [INFO] train episode 2547: reward = 169.00, steps = 169
22:57:27 [INFO] train episode 2548: reward = 200.00, steps = 200
22:57:27 [INFO] train episode 2549: reward = 132.00, steps = 132
22:57:27 [INFO] train episode 2550: reward = 171.00, steps = 171
22:57:27 [INFO] train episode 2551: reward = 155.00, steps = 155
22:57:27 [INFO] train episode 2552: reward = 192.00, steps = 192
22:57:27 [INFO] train episode 2553: reward = 155.00, steps = 155
22:57:27 [INFO] train episode 2554: reward = 102.00, steps = 102
22:57:27 [INFO] train episode 2555: reward = 116.00, steps = 116
22:57:27 [INFO] train episode 2556: reward = 96.00, steps = 96
22:57:28 [INFO] train episode 2557: reward = 100.00, steps = 100
22:57:28 [INFO] train episode 2558: reward = 153.00, steps = 153
22:57:28 [INFO] train episode 2559: reward = 96.00, steps = 96
22:57:28 [INFO] train episode 2560: reward = 146.00, steps = 146
22:57:28 [INFO] train episode 2561: reward = 173.00, steps = 173
22:57:28 [INFO] train episode 2562: reward = 113.00, steps = 113
22:57:28 [INFO] train episode 2563: reward = 200.00, steps = 200
22:57:28 [INFO] train episode 2564: reward = 143.00, steps = 143
22:57:28 [INFO] train episode 2565: reward = 129.00, steps = 129
22:57:28 [INFO] train episode 2566: reward = 141.00, steps = 141
22:57:28 [INFO] train episode 2567: reward = 159.00, steps = 159
22:57:29 [INFO] train episode 2568: reward = 200.00, steps = 200
22:57:29 [INFO] train episode 2569: reward = 103.00, steps = 103
22:57:29 [INFO] train episode 2570: reward = 162.00, steps = 162
22:57:29 [INFO] train episode 2571: reward = 135.00, steps = 135
22:57:29 [INFO] train episode 2572: reward = 176.00, steps = 176
22:57:29 [INFO] train episode 2573: reward = 174.00, steps = 174
22:57:29 [INFO] train episode 2574: reward = 127.00, steps = 127
22:57:29 [INFO] train episode 2575: reward = 161.00, steps = 161
22:57:29 [INFO] train episode 2576: reward = 177.00, steps = 177
22:57:29 [INFO] train episode 2577: reward = 115.00, steps = 115
22:57:29 [INFO] train episode 2578: reward = 115.00, steps = 115
22:57:30 [INFO] train episode 2579: reward = 164.00, steps = 164
22:57:30 [INFO] train episode 2580: reward = 101.00, steps = 101
22:57:30 [INFO] train episode 2581: reward = 110.00, steps = 110
22:57:30 [INFO] train episode 2582: reward = 157.00, steps = 157
22:57:30 [INFO] train episode 2583: reward = 146.00, steps = 146
22:57:30 [INFO] train episode 2584: reward = 98.00, steps = 98
22:57:30 [INFO] train episode 2585: reward = 200.00, steps = 200
22:57:30 [INFO] train episode 2586: reward = 137.00, steps = 137
22:57:30 [INFO] train episode 2587: reward = 109.00, steps = 109
22:57:30 [INFO] train episode 2588: reward = 200.00, steps = 200
22:57:30 [INFO] train episode 2589: reward = 133.00, steps = 133
22:57:30 [INFO] train episode 2590: reward = 104.00, steps = 104
22:57:31 [INFO] train episode 2591: reward = 132.00, steps = 132
22:57:31 [INFO] train episode 2592: reward = 175.00, steps = 175
22:57:31 [INFO] train episode 2593: reward = 135.00, steps = 135
22:57:31 [INFO] train episode 2594: reward = 98.00, steps = 98
22:57:31 [INFO] train episode 2595: reward = 110.00, steps = 110
22:57:31 [INFO] train episode 2596: reward = 117.00, steps = 117
22:57:31 [INFO] train episode 2597: reward = 184.00, steps = 184
22:57:31 [INFO] train episode 2598: reward = 143.00, steps = 143
22:57:31 [INFO] train episode 2599: reward = 140.00, steps = 140
22:57:31 [INFO] train episode 2600: reward = 167.00, steps = 167
22:57:31 [INFO] train episode 2601: reward = 152.00, steps = 152
22:57:31 [INFO] train episode 2602: reward = 103.00, steps = 103
22:57:32 [INFO] train episode 2603: reward = 128.00, steps = 128
22:57:32 [INFO] train episode 2604: reward = 135.00, steps = 135
22:57:32 [INFO] train episode 2605: reward = 115.00, steps = 115
22:57:32 [INFO] train episode 2606: reward = 119.00, steps = 119
22:57:32 [INFO] train episode 2607: reward = 106.00, steps = 106
22:57:32 [INFO] train episode 2608: reward = 182.00, steps = 182
22:57:32 [INFO] train episode 2609: reward = 168.00, steps = 168
22:57:32 [INFO] train episode 2610: reward = 120.00, steps = 120
22:57:32 [INFO] train episode 2611: reward = 110.00, steps = 110
22:57:32 [INFO] train episode 2612: reward = 121.00, steps = 121
22:57:32 [INFO] train episode 2613: reward = 199.00, steps = 199
22:57:33 [INFO] train episode 2614: reward = 152.00, steps = 152
22:57:33 [INFO] train episode 2615: reward = 149.00, steps = 149
22:57:33 [INFO] train episode 2616: reward = 200.00, steps = 200
22:57:33 [INFO] train episode 2617: reward = 142.00, steps = 142
22:57:33 [INFO] train episode 2618: reward = 128.00, steps = 128
22:57:33 [INFO] train episode 2619: reward = 167.00, steps = 167
22:57:33 [INFO] train episode 2620: reward = 200.00, steps = 200
22:57:33 [INFO] train episode 2621: reward = 115.00, steps = 115
22:57:33 [INFO] train episode 2622: reward = 122.00, steps = 122
22:57:34 [INFO] train episode 2623: reward = 116.00, steps = 116
22:57:34 [INFO] train episode 2624: reward = 113.00, steps = 113
22:57:34 [INFO] train episode 2625: reward = 120.00, steps = 120
22:57:34 [INFO] train episode 2626: reward = 140.00, steps = 140
22:57:34 [INFO] train episode 2627: reward = 112.00, steps = 112
22:57:34 [INFO] train episode 2628: reward = 123.00, steps = 123
22:57:34 [INFO] train episode 2629: reward = 114.00, steps = 114
22:57:34 [INFO] train episode 2630: reward = 200.00, steps = 200
22:57:34 [INFO] train episode 2631: reward = 148.00, steps = 148
22:57:34 [INFO] train episode 2632: reward = 132.00, steps = 132
22:57:34 [INFO] train episode 2633: reward = 101.00, steps = 101
22:57:34 [INFO] train episode 2634: reward = 200.00, steps = 200
22:57:35 [INFO] train episode 2635: reward = 138.00, steps = 138
22:57:35 [INFO] train episode 2636: reward = 167.00, steps = 167
22:57:35 [INFO] train episode 2637: reward = 200.00, steps = 200
22:57:35 [INFO] train episode 2638: reward = 167.00, steps = 167
22:57:35 [INFO] train episode 2639: reward = 141.00, steps = 141
22:57:35 [INFO] train episode 2640: reward = 200.00, steps = 200
22:57:35 [INFO] train episode 2641: reward = 143.00, steps = 143
22:57:35 [INFO] train episode 2642: reward = 155.00, steps = 155
22:57:35 [INFO] train episode 2643: reward = 152.00, steps = 152
22:57:36 [INFO] train episode 2644: reward = 181.00, steps = 181
22:57:36 [INFO] train episode 2645: reward = 138.00, steps = 138
22:57:36 [INFO] train episode 2646: reward = 200.00, steps = 200
22:57:36 [INFO] train episode 2647: reward = 200.00, steps = 200
22:57:36 [INFO] train episode 2648: reward = 181.00, steps = 181
22:57:36 [INFO] train episode 2649: reward = 160.00, steps = 160
22:57:36 [INFO] train episode 2650: reward = 200.00, steps = 200
22:57:36 [INFO] train episode 2651: reward = 98.00, steps = 98
22:57:36 [INFO] train episode 2652: reward = 113.00, steps = 113
22:57:36 [INFO] train episode 2653: reward = 122.00, steps = 122
22:57:36 [INFO] train episode 2654: reward = 168.00, steps = 168
22:57:36 [INFO] train episode 2655: reward = 157.00, steps = 157
22:57:37 [INFO] train episode 2656: reward = 156.00, steps = 156
22:57:37 [INFO] train episode 2657: reward = 128.00, steps = 128
22:57:37 [INFO] train episode 2658: reward = 108.00, steps = 108
22:57:37 [INFO] train episode 2659: reward = 107.00, steps = 107
22:57:37 [INFO] train episode 2660: reward = 187.00, steps = 187
22:57:37 [INFO] train episode 2661: reward = 118.00, steps = 118
22:57:37 [INFO] train episode 2662: reward = 160.00, steps = 160
22:57:37 [INFO] train episode 2663: reward = 134.00, steps = 134
22:57:37 [INFO] train episode 2664: reward = 200.00, steps = 200
22:57:37 [INFO] train episode 2665: reward = 136.00, steps = 136
22:57:37 [INFO] train episode 2666: reward = 200.00, steps = 200
22:57:37 [INFO] train episode 2667: reward = 139.00, steps = 139
22:57:38 [INFO] train episode 2668: reward = 124.00, steps = 124
22:57:38 [INFO] train episode 2669: reward = 126.00, steps = 126
22:57:38 [INFO] train episode 2670: reward = 200.00, steps = 200
22:57:38 [INFO] train episode 2671: reward = 200.00, steps = 200
22:57:38 [INFO] train episode 2672: reward = 200.00, steps = 200
22:57:38 [INFO] train episode 2673: reward = 141.00, steps = 141
22:57:38 [INFO] train episode 2674: reward = 115.00, steps = 115
22:57:38 [INFO] train episode 2675: reward = 200.00, steps = 200
22:57:38 [INFO] train episode 2676: reward = 178.00, steps = 178
22:57:38 [INFO] train episode 2677: reward = 155.00, steps = 155
22:57:38 [INFO] train episode 2678: reward = 123.00, steps = 123
22:57:38 [INFO] train episode 2679: reward = 147.00, steps = 147
22:57:39 [INFO] train episode 2680: reward = 179.00, steps = 179
22:57:39 [INFO] train episode 2681: reward = 130.00, steps = 130
22:57:39 [INFO] train episode 2682: reward = 160.00, steps = 160
22:57:39 [INFO] train episode 2683: reward = 200.00, steps = 200
22:57:39 [INFO] train episode 2684: reward = 127.00, steps = 127
22:57:39 [INFO] train episode 2685: reward = 158.00, steps = 158
22:57:39 [INFO] train episode 2686: reward = 193.00, steps = 193
22:57:39 [INFO] train episode 2687: reward = 129.00, steps = 129
22:57:39 [INFO] train episode 2688: reward = 188.00, steps = 188
22:57:39 [INFO] train episode 2689: reward = 200.00, steps = 200
22:57:39 [INFO] train episode 2690: reward = 135.00, steps = 135
22:57:40 [INFO] train episode 2691: reward = 114.00, steps = 114
22:57:40 [INFO] train episode 2692: reward = 145.00, steps = 145
22:57:40 [INFO] train episode 2693: reward = 182.00, steps = 182
22:57:40 [INFO] train episode 2694: reward = 128.00, steps = 128
22:57:40 [INFO] train episode 2695: reward = 199.00, steps = 199
22:57:40 [INFO] train episode 2696: reward = 133.00, steps = 133
22:57:40 [INFO] train episode 2697: reward = 153.00, steps = 153
22:57:40 [INFO] train episode 2698: reward = 200.00, steps = 200
22:57:40 [INFO] train episode 2699: reward = 128.00, steps = 128
22:57:41 [INFO] train episode 2700: reward = 182.00, steps = 182
22:57:41 [INFO] train episode 2701: reward = 160.00, steps = 160
22:57:41 [INFO] train episode 2702: reward = 137.00, steps = 137
22:57:41 [INFO] train episode 2703: reward = 200.00, steps = 200
22:57:41 [INFO] train episode 2704: reward = 200.00, steps = 200
22:57:41 [INFO] train episode 2705: reward = 196.00, steps = 196
22:57:41 [INFO] train episode 2706: reward = 185.00, steps = 185
22:57:41 [INFO] train episode 2707: reward = 132.00, steps = 132
22:57:41 [INFO] train episode 2708: reward = 138.00, steps = 138
22:57:41 [INFO] train episode 2709: reward = 148.00, steps = 148
22:57:41 [INFO] train episode 2710: reward = 163.00, steps = 163
22:57:41 [INFO] train episode 2711: reward = 190.00, steps = 190
22:57:42 [INFO] train episode 2712: reward = 161.00, steps = 161
22:57:42 [INFO] train episode 2713: reward = 200.00, steps = 200
22:57:42 [INFO] train episode 2714: reward = 200.00, steps = 200
22:57:42 [INFO] train episode 2715: reward = 142.00, steps = 142
22:57:42 [INFO] train episode 2716: reward = 200.00, steps = 200
22:57:42 [INFO] train episode 2717: reward = 200.00, steps = 200
22:57:42 [INFO] train episode 2718: reward = 200.00, steps = 200
22:57:42 [INFO] train episode 2719: reward = 187.00, steps = 187
22:57:42 [INFO] train episode 2720: reward = 168.00, steps = 168
22:57:42 [INFO] train episode 2721: reward = 192.00, steps = 192
22:57:43 [INFO] train episode 2722: reward = 174.00, steps = 174
22:57:43 [INFO] train episode 2723: reward = 181.00, steps = 181
22:57:43 [INFO] train episode 2724: reward = 157.00, steps = 157
22:57:43 [INFO] train episode 2725: reward = 156.00, steps = 156
22:57:43 [INFO] train episode 2726: reward = 157.00, steps = 157
22:57:43 [INFO] train episode 2727: reward = 190.00, steps = 190
22:57:43 [INFO] train episode 2728: reward = 200.00, steps = 200
22:57:43 [INFO] train episode 2729: reward = 168.00, steps = 168
22:57:43 [INFO] train episode 2730: reward = 152.00, steps = 152
22:57:43 [INFO] train episode 2731: reward = 177.00, steps = 177
22:57:43 [INFO] train episode 2732: reward = 154.00, steps = 154
22:57:44 [INFO] train episode 2733: reward = 193.00, steps = 193
22:57:44 [INFO] train episode 2734: reward = 200.00, steps = 200
22:57:44 [INFO] train episode 2735: reward = 200.00, steps = 200
22:57:44 [INFO] train episode 2736: reward = 200.00, steps = 200
22:57:44 [INFO] train episode 2737: reward = 200.00, steps = 200
22:57:44 [INFO] train episode 2738: reward = 200.00, steps = 200
22:57:44 [INFO] train episode 2739: reward = 200.00, steps = 200
22:57:44 [INFO] train episode 2740: reward = 161.00, steps = 161
22:57:44 [INFO] train episode 2741: reward = 190.00, steps = 190
22:57:44 [INFO] train episode 2742: reward = 190.00, steps = 190
22:57:44 [INFO] train episode 2743: reward = 200.00, steps = 200
22:57:45 [INFO] train episode 2744: reward = 198.00, steps = 198
22:57:45 [INFO] train episode 2745: reward = 178.00, steps = 178
22:57:45 [INFO] train episode 2746: reward = 194.00, steps = 194
22:57:45 [INFO] train episode 2747: reward = 178.00, steps = 178
22:57:45 [INFO] train episode 2748: reward = 200.00, steps = 200
22:57:45 [INFO] train episode 2749: reward = 166.00, steps = 166
22:57:45 [INFO] train episode 2750: reward = 200.00, steps = 200
22:57:45 [INFO] train episode 2751: reward = 200.00, steps = 200
22:57:45 [INFO] train episode 2752: reward = 168.00, steps = 168
22:57:46 [INFO] train episode 2753: reward = 195.00, steps = 195
22:57:46 [INFO] train episode 2754: reward = 200.00, steps = 200
22:57:46 [INFO] train episode 2755: reward = 193.00, steps = 193
22:57:46 [INFO] train episode 2756: reward = 200.00, steps = 200
22:57:46 [INFO] train episode 2757: reward = 185.00, steps = 185
22:57:46 [INFO] train episode 2758: reward = 200.00, steps = 200
22:57:46 [INFO] train episode 2759: reward = 180.00, steps = 180
22:57:46 [INFO] train episode 2760: reward = 192.00, steps = 192
22:57:46 [INFO] train episode 2761: reward = 200.00, steps = 200
22:57:46 [INFO] train episode 2762: reward = 200.00, steps = 200
22:57:46 [INFO] train episode 2763: reward = 200.00, steps = 200
22:57:47 [INFO] train episode 2764: reward = 200.00, steps = 200
22:57:47 [INFO] train episode 2765: reward = 200.00, steps = 200
22:57:47 [INFO] train episode 2766: reward = 180.00, steps = 180
22:57:47 [INFO] train episode 2767: reward = 200.00, steps = 200
22:57:47 [INFO] train episode 2768: reward = 189.00, steps = 189
22:57:47 [INFO] train episode 2769: reward = 200.00, steps = 200
22:57:47 [INFO] train episode 2770: reward = 183.00, steps = 183
22:57:47 [INFO] train episode 2771: reward = 148.00, steps = 148
22:57:47 [INFO] train episode 2772: reward = 181.00, steps = 181
22:57:47 [INFO] train episode 2773: reward = 200.00, steps = 200
22:57:48 [INFO] train episode 2774: reward = 200.00, steps = 200
22:57:48 [INFO] train episode 2775: reward = 200.00, steps = 200
22:57:48 [INFO] train episode 2776: reward = 200.00, steps = 200
22:57:48 [INFO] train episode 2777: reward = 200.00, steps = 200
22:57:48 [INFO] train episode 2778: reward = 200.00, steps = 200
22:57:48 [INFO] train episode 2779: reward = 150.00, steps = 150
22:57:48 [INFO] train episode 2780: reward = 168.00, steps = 168
22:57:48 [INFO] train episode 2781: reward = 200.00, steps = 200
22:57:48 [INFO] train episode 2782: reward = 200.00, steps = 200
22:57:48 [INFO] train episode 2783: reward = 149.00, steps = 149
22:57:48 [INFO] train episode 2784: reward = 200.00, steps = 200
22:57:49 [INFO] train episode 2785: reward = 200.00, steps = 200
22:57:49 [INFO] train episode 2786: reward = 182.00, steps = 182
22:57:49 [INFO] train episode 2787: reward = 200.00, steps = 200
22:57:49 [INFO] train episode 2788: reward = 187.00, steps = 187
22:57:49 [INFO] train episode 2789: reward = 200.00, steps = 200
22:57:49 [INFO] train episode 2790: reward = 197.00, steps = 197
22:57:49 [INFO] train episode 2791: reward = 191.00, steps = 191
22:57:49 [INFO] train episode 2792: reward = 200.00, steps = 200
22:57:49 [INFO] train episode 2793: reward = 156.00, steps = 156
22:57:49 [INFO] train episode 2794: reward = 200.00, steps = 200
22:57:49 [INFO] train episode 2795: reward = 200.00, steps = 200
22:57:50 [INFO] train episode 2796: reward = 193.00, steps = 193
22:57:50 [INFO] train episode 2797: reward = 188.00, steps = 188
22:57:50 [INFO] train episode 2798: reward = 193.00, steps = 193
22:57:50 [INFO] train episode 2799: reward = 178.00, steps = 178
22:57:50 [INFO] train episode 2800: reward = 200.00, steps = 200
22:57:50 [INFO] train episode 2801: reward = 184.00, steps = 184
22:57:50 [INFO] train episode 2802: reward = 200.00, steps = 200
22:57:50 [INFO] train episode 2803: reward = 200.00, steps = 200
22:57:50 [INFO] train episode 2804: reward = 200.00, steps = 200
22:57:51 [INFO] train episode 2805: reward = 200.00, steps = 200
22:57:51 [INFO] train episode 2806: reward = 200.00, steps = 200
22:57:51 [INFO] train episode 2807: reward = 200.00, steps = 200
22:57:51 [INFO] train episode 2808: reward = 186.00, steps = 186
22:57:51 [INFO] train episode 2809: reward = 200.00, steps = 200
22:57:51 [INFO] train episode 2810: reward = 148.00, steps = 148
22:57:51 [INFO] train episode 2811: reward = 142.00, steps = 142
22:57:51 [INFO] train episode 2812: reward = 165.00, steps = 165
22:57:51 [INFO] train episode 2813: reward = 176.00, steps = 176
22:57:51 [INFO] train episode 2814: reward = 200.00, steps = 200
22:57:51 [INFO] train episode 2815: reward = 162.00, steps = 162
22:57:52 [INFO] train episode 2816: reward = 200.00, steps = 200
22:57:52 [INFO] train episode 2817: reward = 193.00, steps = 193
22:57:52 [INFO] train episode 2818: reward = 200.00, steps = 200
22:57:52 [INFO] train episode 2819: reward = 154.00, steps = 154
22:57:52 [INFO] train episode 2820: reward = 146.00, steps = 146
22:57:52 [INFO] train episode 2821: reward = 127.00, steps = 127
22:57:52 [INFO] train episode 2822: reward = 132.00, steps = 132
22:57:52 [INFO] train episode 2823: reward = 149.00, steps = 149
22:57:52 [INFO] train episode 2824: reward = 118.00, steps = 118
22:57:52 [INFO] train episode 2825: reward = 110.00, steps = 110
22:57:52 [INFO] train episode 2826: reward = 173.00, steps = 173
22:57:52 [INFO] train episode 2827: reward = 143.00, steps = 143
22:57:52 [INFO] train episode 2828: reward = 153.00, steps = 153
22:57:53 [INFO] train episode 2829: reward = 137.00, steps = 137
22:57:53 [INFO] train episode 2830: reward = 165.00, steps = 165
22:57:53 [INFO] train episode 2831: reward = 133.00, steps = 133
22:57:53 [INFO] train episode 2832: reward = 137.00, steps = 137
22:57:53 [INFO] train episode 2833: reward = 181.00, steps = 181
22:57:53 [INFO] train episode 2834: reward = 157.00, steps = 157
22:57:53 [INFO] train episode 2835: reward = 141.00, steps = 141
22:57:53 [INFO] train episode 2836: reward = 122.00, steps = 122
22:57:53 [INFO] train episode 2837: reward = 132.00, steps = 132
22:57:53 [INFO] train episode 2838: reward = 154.00, steps = 154
22:57:53 [INFO] train episode 2839: reward = 151.00, steps = 151
22:57:53 [INFO] train episode 2840: reward = 135.00, steps = 135
22:57:53 [INFO] train episode 2841: reward = 158.00, steps = 158
22:57:54 [INFO] train episode 2842: reward = 119.00, steps = 119
22:57:54 [INFO] train episode 2843: reward = 90.00, steps = 90
22:57:54 [INFO] train episode 2844: reward = 200.00, steps = 200
22:57:54 [INFO] train episode 2845: reward = 96.00, steps = 96
22:57:54 [INFO] train episode 2846: reward = 154.00, steps = 154
22:57:54 [INFO] train episode 2847: reward = 126.00, steps = 126
22:57:54 [INFO] train episode 2848: reward = 122.00, steps = 122
22:57:54 [INFO] train episode 2849: reward = 130.00, steps = 130
22:57:54 [INFO] train episode 2850: reward = 200.00, steps = 200
22:57:54 [INFO] train episode 2851: reward = 144.00, steps = 144
22:57:54 [INFO] train episode 2852: reward = 160.00, steps = 160
22:57:55 [INFO] train episode 2853: reward = 157.00, steps = 157
22:57:55 [INFO] train episode 2854: reward = 200.00, steps = 200
22:57:55 [INFO] train episode 2855: reward = 124.00, steps = 124
22:57:55 [INFO] train episode 2856: reward = 114.00, steps = 114
22:57:55 [INFO] train episode 2857: reward = 100.00, steps = 100
22:57:55 [INFO] train episode 2858: reward = 135.00, steps = 135
22:57:55 [INFO] train episode 2859: reward = 200.00, steps = 200
22:57:55 [INFO] train episode 2860: reward = 146.00, steps = 146
22:57:55 [INFO] train episode 2861: reward = 176.00, steps = 176
22:57:55 [INFO] train episode 2862: reward = 147.00, steps = 147
22:57:56 [INFO] train episode 2863: reward = 132.00, steps = 132
22:57:56 [INFO] train episode 2864: reward = 200.00, steps = 200
22:57:56 [INFO] train episode 2865: reward = 168.00, steps = 168
22:57:56 [INFO] train episode 2866: reward = 142.00, steps = 142
22:57:56 [INFO] train episode 2867: reward = 145.00, steps = 145
22:57:56 [INFO] train episode 2868: reward = 131.00, steps = 131
22:57:56 [INFO] train episode 2869: reward = 149.00, steps = 149
22:57:56 [INFO] train episode 2870: reward = 168.00, steps = 168
22:57:56 [INFO] train episode 2871: reward = 170.00, steps = 170
22:57:56 [INFO] train episode 2872: reward = 200.00, steps = 200
22:57:56 [INFO] train episode 2873: reward = 158.00, steps = 158
22:57:57 [INFO] train episode 2874: reward = 200.00, steps = 200
22:57:57 [INFO] train episode 2875: reward = 156.00, steps = 156
22:57:57 [INFO] train episode 2876: reward = 167.00, steps = 167
22:57:57 [INFO] train episode 2877: reward = 104.00, steps = 104
22:57:57 [INFO] train episode 2878: reward = 189.00, steps = 189
22:57:57 [INFO] train episode 2879: reward = 147.00, steps = 147
22:57:57 [INFO] train episode 2880: reward = 143.00, steps = 143
22:57:57 [INFO] train episode 2881: reward = 161.00, steps = 161
22:57:57 [INFO] train episode 2882: reward = 121.00, steps = 121
22:57:57 [INFO] train episode 2883: reward = 152.00, steps = 152
22:57:57 [INFO] train episode 2884: reward = 103.00, steps = 103
22:57:57 [INFO] train episode 2885: reward = 186.00, steps = 186
22:57:58 [INFO] train episode 2886: reward = 142.00, steps = 142
22:57:58 [INFO] train episode 2887: reward = 123.00, steps = 123
22:57:58 [INFO] train episode 2888: reward = 198.00, steps = 198
22:57:58 [INFO] train episode 2889: reward = 115.00, steps = 115
22:57:58 [INFO] train episode 2890: reward = 176.00, steps = 176
22:57:58 [INFO] train episode 2891: reward = 200.00, steps = 200
22:57:58 [INFO] train episode 2892: reward = 180.00, steps = 180
22:57:58 [INFO] train episode 2893: reward = 188.00, steps = 188
22:57:58 [INFO] train episode 2894: reward = 200.00, steps = 200
22:57:58 [INFO] train episode 2895: reward = 175.00, steps = 175
22:57:58 [INFO] train episode 2896: reward = 133.00, steps = 133
22:57:59 [INFO] train episode 2897: reward = 162.00, steps = 162
22:57:59 [INFO] train episode 2898: reward = 152.00, steps = 152
22:57:59 [INFO] train episode 2899: reward = 186.00, steps = 186
22:57:59 [INFO] train episode 2900: reward = 141.00, steps = 141
22:57:59 [INFO] train episode 2901: reward = 194.00, steps = 194
22:57:59 [INFO] train episode 2902: reward = 189.00, steps = 189
22:57:59 [INFO] train episode 2903: reward = 150.00, steps = 150
22:57:59 [INFO] train episode 2904: reward = 138.00, steps = 138
22:57:59 [INFO] train episode 2905: reward = 200.00, steps = 200
22:57:59 [INFO] train episode 2906: reward = 155.00, steps = 155
22:57:59 [INFO] train episode 2907: reward = 184.00, steps = 184
22:58:00 [INFO] train episode 2908: reward = 171.00, steps = 171
22:58:00 [INFO] train episode 2909: reward = 162.00, steps = 162
22:58:00 [INFO] train episode 2910: reward = 146.00, steps = 146
22:58:00 [INFO] train episode 2911: reward = 135.00, steps = 135
22:58:00 [INFO] train episode 2912: reward = 152.00, steps = 152
22:58:00 [INFO] train episode 2913: reward = 150.00, steps = 150
22:58:00 [INFO] train episode 2914: reward = 163.00, steps = 163
22:58:00 [INFO] train episode 2915: reward = 200.00, steps = 200
22:58:00 [INFO] train episode 2916: reward = 200.00, steps = 200
22:58:00 [INFO] train episode 2917: reward = 135.00, steps = 135
22:58:00 [INFO] train episode 2918: reward = 132.00, steps = 132
22:58:00 [INFO] train episode 2919: reward = 195.00, steps = 195
22:58:01 [INFO] train episode 2920: reward = 147.00, steps = 147
22:58:01 [INFO] train episode 2921: reward = 151.00, steps = 151
22:58:01 [INFO] train episode 2922: reward = 200.00, steps = 200
22:58:01 [INFO] train episode 2923: reward = 141.00, steps = 141
22:58:01 [INFO] train episode 2924: reward = 200.00, steps = 200
22:58:01 [INFO] train episode 2925: reward = 186.00, steps = 186
22:58:01 [INFO] train episode 2926: reward = 200.00, steps = 200
22:58:01 [INFO] train episode 2927: reward = 168.00, steps = 168
22:58:01 [INFO] train episode 2928: reward = 196.00, steps = 196
22:58:01 [INFO] train episode 2929: reward = 174.00, steps = 174
22:58:02 [INFO] train episode 2930: reward = 185.00, steps = 185
22:58:02 [INFO] train episode 2931: reward = 112.00, steps = 112
22:58:02 [INFO] train episode 2932: reward = 110.00, steps = 110
22:58:02 [INFO] train episode 2933: reward = 200.00, steps = 200
22:58:02 [INFO] train episode 2934: reward = 168.00, steps = 168
22:58:02 [INFO] train episode 2935: reward = 159.00, steps = 159
22:58:02 [INFO] train episode 2936: reward = 123.00, steps = 123
22:58:02 [INFO] train episode 2937: reward = 171.00, steps = 171
22:58:02 [INFO] train episode 2938: reward = 160.00, steps = 160
22:58:02 [INFO] train episode 2939: reward = 128.00, steps = 128
22:58:02 [INFO] train episode 2940: reward = 193.00, steps = 193
22:58:03 [INFO] train episode 2941: reward = 159.00, steps = 159
22:58:03 [INFO] train episode 2942: reward = 182.00, steps = 182
22:58:03 [INFO] train episode 2943: reward = 175.00, steps = 175
22:58:03 [INFO] train episode 2944: reward = 138.00, steps = 138
22:58:03 [INFO] train episode 2945: reward = 137.00, steps = 137
22:58:03 [INFO] train episode 2946: reward = 191.00, steps = 191
22:58:03 [INFO] train episode 2947: reward = 126.00, steps = 126
22:58:03 [INFO] train episode 2948: reward = 129.00, steps = 129
22:58:03 [INFO] train episode 2949: reward = 200.00, steps = 200
22:58:03 [INFO] train episode 2950: reward = 200.00, steps = 200
22:58:03 [INFO] train episode 2951: reward = 138.00, steps = 138
22:58:03 [INFO] train episode 2952: reward = 140.00, steps = 140
22:58:04 [INFO] train episode 2953: reward = 200.00, steps = 200
22:58:04 [INFO] train episode 2954: reward = 158.00, steps = 158
22:58:04 [INFO] train episode 2955: reward = 161.00, steps = 161
22:58:04 [INFO] train episode 2956: reward = 200.00, steps = 200
22:58:04 [INFO] train episode 2957: reward = 143.00, steps = 143
22:58:04 [INFO] train episode 2958: reward = 124.00, steps = 124
22:58:04 [INFO] train episode 2959: reward = 200.00, steps = 200
22:58:04 [INFO] train episode 2960: reward = 150.00, steps = 150
22:58:04 [INFO] train episode 2961: reward = 162.00, steps = 162
22:58:04 [INFO] train episode 2962: reward = 163.00, steps = 163
22:58:04 [INFO] train episode 2963: reward = 185.00, steps = 185
22:58:04 [INFO] train episode 2964: reward = 148.00, steps = 148
22:58:04 [INFO] train episode 2965: reward = 194.00, steps = 194
22:58:05 [INFO] train episode 2966: reward = 200.00, steps = 200
22:58:05 [INFO] train episode 2967: reward = 146.00, steps = 146
22:58:05 [INFO] train episode 2968: reward = 184.00, steps = 184
22:58:05 [INFO] train episode 2969: reward = 149.00, steps = 149
22:58:05 [INFO] train episode 2970: reward = 174.00, steps = 174
22:58:05 [INFO] train episode 2971: reward = 200.00, steps = 200
22:58:05 [INFO] train episode 2972: reward = 105.00, steps = 105
22:58:05 [INFO] train episode 2973: reward = 200.00, steps = 200
22:58:05 [INFO] train episode 2974: reward = 142.00, steps = 142
22:58:05 [INFO] train episode 2975: reward = 118.00, steps = 118
22:58:05 [INFO] train episode 2976: reward = 174.00, steps = 174
22:58:05 [INFO] train episode 2977: reward = 200.00, steps = 200
22:58:06 [INFO] train episode 2978: reward = 200.00, steps = 200
22:58:06 [INFO] train episode 2979: reward = 154.00, steps = 154
22:58:06 [INFO] train episode 2980: reward = 142.00, steps = 142
22:58:06 [INFO] train episode 2981: reward = 140.00, steps = 140
22:58:06 [INFO] train episode 2982: reward = 193.00, steps = 193
22:58:06 [INFO] train episode 2983: reward = 145.00, steps = 145
22:58:06 [INFO] train episode 2984: reward = 189.00, steps = 189
22:58:06 [INFO] train episode 2985: reward = 179.00, steps = 179
22:58:06 [INFO] train episode 2986: reward = 133.00, steps = 133
22:58:06 [INFO] train episode 2987: reward = 200.00, steps = 200
22:58:06 [INFO] train episode 2988: reward = 200.00, steps = 200
22:58:06 [INFO] train episode 2989: reward = 200.00, steps = 200
22:58:06 [INFO] train episode 2990: reward = 198.00, steps = 198
22:58:07 [INFO] train episode 2991: reward = 169.00, steps = 169
22:58:07 [INFO] train episode 2992: reward = 200.00, steps = 200
22:58:07 [INFO] train episode 2993: reward = 130.00, steps = 130
22:58:07 [INFO] train episode 2994: reward = 179.00, steps = 179
22:58:07 [INFO] train episode 2995: reward = 142.00, steps = 142
22:58:07 [INFO] train episode 2996: reward = 133.00, steps = 133
22:58:07 [INFO] train episode 2997: reward = 129.00, steps = 129
22:58:07 [INFO] train episode 2998: reward = 200.00, steps = 200
22:58:07 [INFO] train episode 2999: reward = 200.00, steps = 200
22:58:07 [INFO] train episode 3000: reward = 200.00, steps = 200
22:58:07 [INFO] train episode 3001: reward = 166.00, steps = 166
22:58:07 [INFO] train episode 3002: reward = 152.00, steps = 152
22:58:07 [INFO] train episode 3003: reward = 200.00, steps = 200
22:58:08 [INFO] train episode 3004: reward = 200.00, steps = 200
22:58:08 [INFO] train episode 3005: reward = 188.00, steps = 188
22:58:08 [INFO] train episode 3006: reward = 175.00, steps = 175
22:58:08 [INFO] train episode 3007: reward = 144.00, steps = 144
22:58:08 [INFO] train episode 3008: reward = 200.00, steps = 200
22:58:08 [INFO] train episode 3009: reward = 191.00, steps = 191
22:58:08 [INFO] train episode 3010: reward = 126.00, steps = 126
22:58:08 [INFO] train episode 3011: reward = 200.00, steps = 200
22:58:08 [INFO] train episode 3012: reward = 200.00, steps = 200
22:58:08 [INFO] train episode 3013: reward = 200.00, steps = 200
22:58:08 [INFO] train episode 3014: reward = 200.00, steps = 200
22:58:08 [INFO] train episode 3015: reward = 154.00, steps = 154
22:58:09 [INFO] train episode 3016: reward = 200.00, steps = 200
22:58:09 [INFO] train episode 3017: reward = 178.00, steps = 178
22:58:09 [INFO] train episode 3018: reward = 200.00, steps = 200
22:58:09 [INFO] train episode 3019: reward = 169.00, steps = 169
22:58:09 [INFO] train episode 3020: reward = 138.00, steps = 138
22:58:09 [INFO] train episode 3021: reward = 145.00, steps = 145
22:58:09 [INFO] train episode 3022: reward = 200.00, steps = 200
22:58:09 [INFO] train episode 3023: reward = 183.00, steps = 183
22:58:09 [INFO] train episode 3024: reward = 200.00, steps = 200
22:58:09 [INFO] train episode 3025: reward = 183.00, steps = 183
22:58:10 [INFO] train episode 3026: reward = 200.00, steps = 200
22:58:10 [INFO] train episode 3027: reward = 200.00, steps = 200
22:58:10 [INFO] train episode 3028: reward = 161.00, steps = 161
22:58:10 [INFO] train episode 3029: reward = 168.00, steps = 168
22:58:10 [INFO] train episode 3030: reward = 200.00, steps = 200
22:58:10 [INFO] train episode 3031: reward = 200.00, steps = 200
22:58:10 [INFO] train episode 3032: reward = 191.00, steps = 191
22:58:10 [INFO] train episode 3033: reward = 199.00, steps = 199
22:58:10 [INFO] train episode 3034: reward = 155.00, steps = 155
22:58:10 [INFO] train episode 3035: reward = 200.00, steps = 200
22:58:10 [INFO] train episode 3036: reward = 139.00, steps = 139
22:58:11 [INFO] train episode 3037: reward = 200.00, steps = 200
22:58:11 [INFO] train episode 3038: reward = 145.00, steps = 145
22:58:11 [INFO] train episode 3039: reward = 168.00, steps = 168
22:58:11 [INFO] train episode 3040: reward = 200.00, steps = 200
22:58:11 [INFO] train episode 3041: reward = 148.00, steps = 148
22:58:11 [INFO] train episode 3042: reward = 175.00, steps = 175
22:58:11 [INFO] train episode 3043: reward = 173.00, steps = 173
22:58:11 [INFO] train episode 3044: reward = 162.00, steps = 162
22:58:11 [INFO] train episode 3045: reward = 200.00, steps = 200
22:58:11 [INFO] train episode 3046: reward = 158.00, steps = 158
22:58:11 [INFO] train episode 3047: reward = 200.00, steps = 200
22:58:11 [INFO] train episode 3048: reward = 180.00, steps = 180
22:58:11 [INFO] train episode 3049: reward = 141.00, steps = 141
22:58:12 [INFO] train episode 3050: reward = 200.00, steps = 200
22:58:12 [INFO] train episode 3051: reward = 183.00, steps = 183
22:58:12 [INFO] train episode 3052: reward = 155.00, steps = 155
22:58:12 [INFO] train episode 3053: reward = 200.00, steps = 200
22:58:12 [INFO] train episode 3054: reward = 200.00, steps = 200
22:58:12 [INFO] train episode 3055: reward = 185.00, steps = 185
22:58:12 [INFO] train episode 3056: reward = 186.00, steps = 186
22:58:12 [INFO] train episode 3057: reward = 162.00, steps = 162
22:58:12 [INFO] train episode 3058: reward = 165.00, steps = 165
22:58:12 [INFO] train episode 3059: reward = 144.00, steps = 144
22:58:12 [INFO] train episode 3060: reward = 200.00, steps = 200
22:58:13 [INFO] train episode 3061: reward = 200.00, steps = 200
22:58:13 [INFO] train episode 3062: reward = 152.00, steps = 152
22:58:13 [INFO] train episode 3063: reward = 200.00, steps = 200
22:58:13 [INFO] train episode 3064: reward = 200.00, steps = 200
22:58:13 [INFO] train episode 3065: reward = 200.00, steps = 200
22:58:13 [INFO] train episode 3066: reward = 199.00, steps = 199
22:58:13 [INFO] train episode 3067: reward = 200.00, steps = 200
22:58:13 [INFO] train episode 3068: reward = 151.00, steps = 151
22:58:13 [INFO] train episode 3069: reward = 200.00, steps = 200
22:58:13 [INFO] train episode 3070: reward = 200.00, steps = 200
22:58:13 [INFO] train episode 3071: reward = 181.00, steps = 181
22:58:13 [INFO] train episode 3072: reward = 153.00, steps = 153
22:58:14 [INFO] train episode 3073: reward = 200.00, steps = 200
22:58:14 [INFO] train episode 3074: reward = 199.00, steps = 199
22:58:14 [INFO] train episode 3075: reward = 191.00, steps = 191
22:58:14 [INFO] train episode 3076: reward = 200.00, steps = 200
22:58:14 [INFO] train episode 3077: reward = 200.00, steps = 200
22:58:14 [INFO] train episode 3078: reward = 200.00, steps = 200
22:58:14 [INFO] train episode 3079: reward = 200.00, steps = 200
22:58:14 [INFO] train episode 3080: reward = 200.00, steps = 200
22:58:14 [INFO] train episode 3081: reward = 200.00, steps = 200
22:58:14 [INFO] train episode 3082: reward = 188.00, steps = 188
22:58:14 [INFO] train episode 3083: reward = 200.00, steps = 200
22:58:14 [INFO] train episode 3084: reward = 176.00, steps = 176
22:58:14 [INFO] train episode 3085: reward = 136.00, steps = 136
22:58:15 [INFO] train episode 3086: reward = 156.00, steps = 156
22:58:15 [INFO] train episode 3087: reward = 146.00, steps = 146
22:58:15 [INFO] train episode 3088: reward = 200.00, steps = 200
22:58:15 [INFO] train episode 3089: reward = 165.00, steps = 165
22:58:15 [INFO] train episode 3090: reward = 200.00, steps = 200
22:58:15 [INFO] train episode 3091: reward = 169.00, steps = 169
22:58:15 [INFO] train episode 3092: reward = 200.00, steps = 200
22:58:15 [INFO] train episode 3093: reward = 141.00, steps = 141
22:58:15 [INFO] train episode 3094: reward = 139.00, steps = 139
22:58:15 [INFO] train episode 3095: reward = 200.00, steps = 200
22:58:15 [INFO] train episode 3096: reward = 200.00, steps = 200
22:58:15 [INFO] train episode 3097: reward = 200.00, steps = 200
22:58:15 [INFO] train episode 3098: reward = 160.00, steps = 160
22:58:15 [INFO] train episode 3099: reward = 155.00, steps = 155
22:58:16 [INFO] train episode 3100: reward = 154.00, steps = 154
22:58:16 [INFO] train episode 3101: reward = 158.00, steps = 158
22:58:16 [INFO] train episode 3102: reward = 149.00, steps = 149
22:58:16 [INFO] train episode 3103: reward = 193.00, steps = 193
22:58:16 [INFO] train episode 3104: reward = 200.00, steps = 200
22:58:16 [INFO] train episode 3105: reward = 144.00, steps = 144
22:58:16 [INFO] train episode 3106: reward = 173.00, steps = 173
22:58:16 [INFO] train episode 3107: reward = 157.00, steps = 157
22:58:16 [INFO] train episode 3108: reward = 154.00, steps = 154
22:58:16 [INFO] train episode 3109: reward = 172.00, steps = 172
22:58:16 [INFO] train episode 3110: reward = 187.00, steps = 187
22:58:16 [INFO] train episode 3111: reward = 180.00, steps = 180
22:58:16 [INFO] train episode 3112: reward = 172.00, steps = 172
22:58:16 [INFO] train episode 3113: reward = 147.00, steps = 147
22:58:16 [INFO] train episode 3114: reward = 142.00, steps = 142
22:58:16 [INFO] train episode 3115: reward = 137.00, steps = 137
22:58:17 [INFO] train episode 3116: reward = 200.00, steps = 200
22:58:17 [INFO] train episode 3117: reward = 191.00, steps = 191
22:58:17 [INFO] train episode 3118: reward = 157.00, steps = 157
22:58:17 [INFO] train episode 3119: reward = 189.00, steps = 189
22:58:17 [INFO] train episode 3120: reward = 138.00, steps = 138
22:58:17 [INFO] train episode 3121: reward = 158.00, steps = 158
22:58:17 [INFO] train episode 3122: reward = 154.00, steps = 154
22:58:17 [INFO] train episode 3123: reward = 150.00, steps = 150
22:58:17 [INFO] train episode 3124: reward = 129.00, steps = 129
22:58:17 [INFO] train episode 3125: reward = 185.00, steps = 185
22:58:17 [INFO] train episode 3126: reward = 200.00, steps = 200
22:58:17 [INFO] train episode 3127: reward = 163.00, steps = 163
22:58:18 [INFO] train episode 3128: reward = 125.00, steps = 125
22:58:18 [INFO] train episode 3129: reward = 200.00, steps = 200
22:58:18 [INFO] train episode 3130: reward = 200.00, steps = 200
22:58:18 [INFO] train episode 3131: reward = 134.00, steps = 134
22:58:18 [INFO] train episode 3132: reward = 200.00, steps = 200
22:58:18 [INFO] train episode 3133: reward = 194.00, steps = 194
22:58:18 [INFO] train episode 3134: reward = 168.00, steps = 168
22:58:18 [INFO] train episode 3135: reward = 184.00, steps = 184
22:58:18 [INFO] train episode 3136: reward = 200.00, steps = 200
22:58:18 [INFO] train episode 3137: reward = 149.00, steps = 149
22:58:18 [INFO] train episode 3138: reward = 135.00, steps = 135
22:58:18 [INFO] train episode 3139: reward = 167.00, steps = 167
22:58:18 [INFO] train episode 3140: reward = 141.00, steps = 141
22:58:19 [INFO] train episode 3141: reward = 167.00, steps = 167
22:58:19 [INFO] train episode 3142: reward = 190.00, steps = 190
22:58:19 [INFO] train episode 3143: reward = 184.00, steps = 184
22:58:19 [INFO] train episode 3144: reward = 174.00, steps = 174
22:58:19 [INFO] train episode 3145: reward = 200.00, steps = 200
22:58:19 [INFO] train episode 3146: reward = 174.00, steps = 174
22:58:19 [INFO] train episode 3147: reward = 145.00, steps = 145
22:58:19 [INFO] train episode 3148: reward = 148.00, steps = 148
22:58:19 [INFO] train episode 3149: reward = 150.00, steps = 150
22:58:19 [INFO] train episode 3150: reward = 158.00, steps = 158
22:58:19 [INFO] train episode 3151: reward = 159.00, steps = 159
22:58:19 [INFO] train episode 3152: reward = 154.00, steps = 154
22:58:19 [INFO] train episode 3153: reward = 153.00, steps = 153
22:58:19 [INFO] train episode 3154: reward = 151.00, steps = 151
22:58:20 [INFO] train episode 3155: reward = 193.00, steps = 193
22:58:20 [INFO] train episode 3156: reward = 200.00, steps = 200
22:58:20 [INFO] train episode 3157: reward = 200.00, steps = 200
22:58:20 [INFO] train episode 3158: reward = 200.00, steps = 200
22:58:20 [INFO] train episode 3159: reward = 92.00, steps = 92
22:58:20 [INFO] train episode 3160: reward = 183.00, steps = 183
22:58:20 [INFO] train episode 3161: reward = 126.00, steps = 126
22:58:20 [INFO] train episode 3162: reward = 113.00, steps = 113
22:58:20 [INFO] train episode 3163: reward = 116.00, steps = 116
22:58:20 [INFO] train episode 3164: reward = 135.00, steps = 135
22:58:20 [INFO] train episode 3165: reward = 200.00, steps = 200
22:58:20 [INFO] train episode 3166: reward = 115.00, steps = 115
22:58:20 [INFO] train episode 3167: reward = 196.00, steps = 196
22:58:20 [INFO] train episode 3168: reward = 200.00, steps = 200
22:58:20 [INFO] train episode 3169: reward = 108.00, steps = 108
22:58:20 [INFO] train episode 3170: reward = 200.00, steps = 200
22:58:21 [INFO] train episode 3171: reward = 178.00, steps = 178
22:58:21 [INFO] train episode 3172: reward = 114.00, steps = 114
22:58:21 [INFO] train episode 3173: reward = 200.00, steps = 200
22:58:21 [INFO] train episode 3174: reward = 177.00, steps = 177
22:58:21 [INFO] train episode 3175: reward = 153.00, steps = 153
22:58:21 [INFO] train episode 3176: reward = 147.00, steps = 147
22:58:21 [INFO] train episode 3177: reward = 130.00, steps = 130
22:58:21 [INFO] train episode 3178: reward = 159.00, steps = 159
22:58:21 [INFO] train episode 3179: reward = 199.00, steps = 199
22:58:21 [INFO] train episode 3180: reward = 175.00, steps = 175
22:58:21 [INFO] train episode 3181: reward = 135.00, steps = 135
22:58:21 [INFO] train episode 3182: reward = 200.00, steps = 200
22:58:21 [INFO] train episode 3183: reward = 112.00, steps = 112
22:58:21 [INFO] train episode 3184: reward = 124.00, steps = 124
22:58:21 [INFO] train episode 3185: reward = 200.00, steps = 200
22:58:22 [INFO] train episode 3186: reward = 136.00, steps = 136
22:58:22 [INFO] train episode 3187: reward = 122.00, steps = 122
22:58:22 [INFO] train episode 3188: reward = 157.00, steps = 157
22:58:22 [INFO] train episode 3189: reward = 163.00, steps = 163
22:58:22 [INFO] train episode 3190: reward = 135.00, steps = 135
22:58:22 [INFO] train episode 3191: reward = 162.00, steps = 162
22:58:22 [INFO] train episode 3192: reward = 136.00, steps = 136
22:58:22 [INFO] train episode 3193: reward = 200.00, steps = 200
22:58:22 [INFO] train episode 3194: reward = 147.00, steps = 147
22:58:22 [INFO] train episode 3195: reward = 200.00, steps = 200
22:58:22 [INFO] train episode 3196: reward = 136.00, steps = 136
22:58:22 [INFO] train episode 3197: reward = 123.00, steps = 123
22:58:22 [INFO] train episode 3198: reward = 200.00, steps = 200
22:58:22 [INFO] train episode 3199: reward = 137.00, steps = 137
22:58:22 [INFO] train episode 3200: reward = 121.00, steps = 121
22:58:22 [INFO] train episode 3201: reward = 171.00, steps = 171
22:58:22 [INFO] train episode 3202: reward = 143.00, steps = 143
22:58:23 [INFO] train episode 3203: reward = 160.00, steps = 160
22:58:23 [INFO] train episode 3204: reward = 129.00, steps = 129
22:58:23 [INFO] train episode 3205: reward = 191.00, steps = 191
22:58:23 [INFO] train episode 3206: reward = 153.00, steps = 153
22:58:23 [INFO] train episode 3207: reward = 200.00, steps = 200
22:58:23 [INFO] train episode 3208: reward = 131.00, steps = 131
22:58:23 [INFO] train episode 3209: reward = 200.00, steps = 200
22:58:23 [INFO] train episode 3210: reward = 135.00, steps = 135
22:58:23 [INFO] train episode 3211: reward = 150.00, steps = 150
22:58:23 [INFO] train episode 3212: reward = 200.00, steps = 200
22:58:23 [INFO] train episode 3213: reward = 121.00, steps = 121
22:58:23 [INFO] train episode 3214: reward = 200.00, steps = 200
22:58:23 [INFO] train episode 3215: reward = 161.00, steps = 161
22:58:23 [INFO] train episode 3216: reward = 200.00, steps = 200
22:58:23 [INFO] train episode 3217: reward = 134.00, steps = 134
22:58:23 [INFO] train episode 3218: reward = 132.00, steps = 132
22:58:24 [INFO] train episode 3219: reward = 144.00, steps = 144
22:58:24 [INFO] train episode 3220: reward = 200.00, steps = 200
22:58:24 [INFO] train episode 3221: reward = 191.00, steps = 191
22:58:24 [INFO] train episode 3222: reward = 137.00, steps = 137
22:58:24 [INFO] train episode 3223: reward = 173.00, steps = 173
22:58:24 [INFO] train episode 3224: reward = 168.00, steps = 168
22:58:24 [INFO] train episode 3225: reward = 178.00, steps = 178
22:58:24 [INFO] train episode 3226: reward = 185.00, steps = 185
22:58:24 [INFO] train episode 3227: reward = 143.00, steps = 143
22:58:24 [INFO] train episode 3228: reward = 200.00, steps = 200
22:58:24 [INFO] train episode 3229: reward = 200.00, steps = 200
22:58:24 [INFO] train episode 3230: reward = 154.00, steps = 154
22:58:24 [INFO] train episode 3231: reward = 200.00, steps = 200
22:58:24 [INFO] train episode 3232: reward = 151.00, steps = 151
22:58:24 [INFO] train episode 3233: reward = 147.00, steps = 147
22:58:25 [INFO] train episode 3234: reward = 200.00, steps = 200
22:58:25 [INFO] train episode 3235: reward = 192.00, steps = 192
22:58:25 [INFO] train episode 3236: reward = 193.00, steps = 193
22:58:25 [INFO] train episode 3237: reward = 200.00, steps = 200
22:58:25 [INFO] train episode 3238: reward = 147.00, steps = 147
22:58:25 [INFO] train episode 3239: reward = 200.00, steps = 200
22:58:25 [INFO] train episode 3240: reward = 200.00, steps = 200
22:58:25 [INFO] train episode 3241: reward = 200.00, steps = 200
22:58:25 [INFO] train episode 3242: reward = 139.00, steps = 139
22:58:25 [INFO] train episode 3243: reward = 200.00, steps = 200
22:58:25 [INFO] train episode 3244: reward = 200.00, steps = 200
22:58:25 [INFO] train episode 3245: reward = 124.00, steps = 124
22:58:25 [INFO] train episode 3246: reward = 200.00, steps = 200
22:58:25 [INFO] train episode 3247: reward = 200.00, steps = 200
22:58:26 [INFO] train episode 3248: reward = 155.00, steps = 155
22:58:26 [INFO] train episode 3249: reward = 168.00, steps = 168
22:58:26 [INFO] train episode 3250: reward = 187.00, steps = 187
22:58:26 [INFO] train episode 3251: reward = 200.00, steps = 200
22:58:26 [INFO] train episode 3252: reward = 192.00, steps = 192
22:58:26 [INFO] train episode 3253: reward = 195.00, steps = 195
22:58:26 [INFO] train episode 3254: reward = 180.00, steps = 180
22:58:26 [INFO] train episode 3255: reward = 200.00, steps = 200
22:58:26 [INFO] train episode 3256: reward = 187.00, steps = 187
22:58:26 [INFO] train episode 3257: reward = 200.00, steps = 200
22:58:26 [INFO] train episode 3258: reward = 161.00, steps = 161
22:58:26 [INFO] train episode 3259: reward = 200.00, steps = 200
22:58:27 [INFO] train episode 3260: reward = 159.00, steps = 159
22:58:27 [INFO] train episode 3261: reward = 200.00, steps = 200
22:58:27 [INFO] train episode 3262: reward = 168.00, steps = 168
22:58:27 [INFO] train episode 3263: reward = 200.00, steps = 200
22:58:27 [INFO] train episode 3264: reward = 135.00, steps = 135
22:58:27 [INFO] train episode 3265: reward = 200.00, steps = 200
22:58:27 [INFO] train episode 3266: reward = 190.00, steps = 190
22:58:27 [INFO] train episode 3267: reward = 200.00, steps = 200
22:58:27 [INFO] train episode 3268: reward = 200.00, steps = 200
22:58:27 [INFO] train episode 3269: reward = 174.00, steps = 174
22:58:27 [INFO] train episode 3270: reward = 200.00, steps = 200
22:58:27 [INFO] train episode 3271: reward = 152.00, steps = 152
22:58:27 [INFO] train episode 3272: reward = 181.00, steps = 181
22:58:27 [INFO] train episode 3273: reward = 174.00, steps = 174
22:58:28 [INFO] train episode 3274: reward = 200.00, steps = 200
22:58:28 [INFO] train episode 3275: reward = 170.00, steps = 170
22:58:28 [INFO] train episode 3276: reward = 200.00, steps = 200
22:58:28 [INFO] train episode 3277: reward = 200.00, steps = 200
22:58:28 [INFO] train episode 3278: reward = 200.00, steps = 200
22:58:28 [INFO] train episode 3279: reward = 159.00, steps = 159
22:58:28 [INFO] train episode 3280: reward = 155.00, steps = 155
22:58:28 [INFO] train episode 3281: reward = 188.00, steps = 188
22:58:28 [INFO] train episode 3282: reward = 200.00, steps = 200
22:58:28 [INFO] train episode 3283: reward = 200.00, steps = 200
22:58:28 [INFO] train episode 3284: reward = 182.00, steps = 182
22:58:28 [INFO] train episode 3285: reward = 200.00, steps = 200
22:58:29 [INFO] train episode 3286: reward = 200.00, steps = 200
22:58:29 [INFO] train episode 3287: reward = 186.00, steps = 186
22:58:29 [INFO] train episode 3288: reward = 189.00, steps = 189
22:58:29 [INFO] train episode 3289: reward = 171.00, steps = 171
22:58:29 [INFO] train episode 3290: reward = 200.00, steps = 200
22:58:29 [INFO] train episode 3291: reward = 191.00, steps = 191
22:58:29 [INFO] train episode 3292: reward = 178.00, steps = 178
22:58:29 [INFO] train episode 3293: reward = 200.00, steps = 200
22:58:29 [INFO] train episode 3294: reward = 177.00, steps = 177
22:58:29 [INFO] train episode 3295: reward = 197.00, steps = 197
22:58:29 [INFO] train episode 3296: reward = 197.00, steps = 197
22:58:29 [INFO] train episode 3297: reward = 191.00, steps = 191
22:58:30 [INFO] train episode 3298: reward = 200.00, steps = 200
22:58:30 [INFO] train episode 3299: reward = 200.00, steps = 200
22:58:30 [INFO] train episode 3300: reward = 192.00, steps = 192
22:58:30 [INFO] train episode 3301: reward = 194.00, steps = 194
22:58:30 [INFO] train episode 3302: reward = 200.00, steps = 200
22:58:30 [INFO] train episode 3303: reward = 200.00, steps = 200
22:58:30 [INFO] train episode 3304: reward = 163.00, steps = 163
22:58:30 [INFO] train episode 3305: reward = 200.00, steps = 200
22:58:30 [INFO] train episode 3306: reward = 185.00, steps = 185
22:58:30 [INFO] train episode 3307: reward = 159.00, steps = 159
22:58:30 [INFO] train episode 3308: reward = 153.00, steps = 153
22:58:30 [INFO] train episode 3309: reward = 153.00, steps = 153
22:58:30 [INFO] train episode 3310: reward = 200.00, steps = 200
22:58:30 [INFO] train episode 3311: reward = 120.00, steps = 120
22:58:31 [INFO] train episode 3312: reward = 200.00, steps = 200
22:58:31 [INFO] train episode 3313: reward = 190.00, steps = 190
22:58:31 [INFO] train episode 3314: reward = 154.00, steps = 154
22:58:31 [INFO] train episode 3315: reward = 136.00, steps = 136
22:58:31 [INFO] train episode 3316: reward = 158.00, steps = 158
22:58:31 [INFO] train episode 3317: reward = 200.00, steps = 200
22:58:31 [INFO] train episode 3318: reward = 159.00, steps = 159
22:58:31 [INFO] train episode 3319: reward = 157.00, steps = 157
22:58:31 [INFO] train episode 3320: reward = 200.00, steps = 200
22:58:31 [INFO] train episode 3321: reward = 152.00, steps = 152
22:58:31 [INFO] train episode 3322: reward = 176.00, steps = 176
22:58:31 [INFO] train episode 3323: reward = 156.00, steps = 156
22:58:31 [INFO] train episode 3324: reward = 200.00, steps = 200
22:58:31 [INFO] train episode 3325: reward = 151.00, steps = 151
22:58:32 [INFO] train episode 3326: reward = 186.00, steps = 186
22:58:32 [INFO] train episode 3327: reward = 122.00, steps = 122
22:58:32 [INFO] train episode 3328: reward = 176.00, steps = 176
22:58:32 [INFO] train episode 3329: reward = 164.00, steps = 164
22:58:32 [INFO] train episode 3330: reward = 200.00, steps = 200
22:58:32 [INFO] train episode 3331: reward = 200.00, steps = 200
22:58:32 [INFO] train episode 3332: reward = 178.00, steps = 178
22:58:32 [INFO] train episode 3333: reward = 123.00, steps = 123
22:58:32 [INFO] train episode 3334: reward = 141.00, steps = 141
22:58:32 [INFO] train episode 3335: reward = 182.00, steps = 182
22:58:32 [INFO] train episode 3336: reward = 162.00, steps = 162
22:58:32 [INFO] train episode 3337: reward = 200.00, steps = 200
22:58:32 [INFO] train episode 3338: reward = 147.00, steps = 147
22:58:32 [INFO] train episode 3339: reward = 147.00, steps = 147
22:58:32 [INFO] train episode 3340: reward = 126.00, steps = 126
22:58:32 [INFO] train episode 3341: reward = 139.00, steps = 139
22:58:33 [INFO] train episode 3342: reward = 128.00, steps = 128
22:58:33 [INFO] train episode 3343: reward = 200.00, steps = 200
22:58:33 [INFO] train episode 3344: reward = 192.00, steps = 192
22:58:33 [INFO] train episode 3345: reward = 123.00, steps = 123
22:58:33 [INFO] train episode 3346: reward = 133.00, steps = 133
22:58:33 [INFO] train episode 3347: reward = 113.00, steps = 113
22:58:33 [INFO] train episode 3348: reward = 200.00, steps = 200
22:58:33 [INFO] train episode 3349: reward = 200.00, steps = 200
22:58:33 [INFO] train episode 3350: reward = 128.00, steps = 128
22:58:33 [INFO] train episode 3351: reward = 134.00, steps = 134
22:58:33 [INFO] train episode 3352: reward = 128.00, steps = 128
22:58:33 [INFO] train episode 3353: reward = 200.00, steps = 200
22:58:33 [INFO] train episode 3354: reward = 179.00, steps = 179
22:58:33 [INFO] train episode 3355: reward = 200.00, steps = 200
22:58:33 [INFO] train episode 3356: reward = 200.00, steps = 200
22:58:34 [INFO] train episode 3357: reward = 200.00, steps = 200
22:58:34 [INFO] train episode 3358: reward = 148.00, steps = 148
22:58:34 [INFO] train episode 3359: reward = 175.00, steps = 175
22:58:34 [INFO] train episode 3360: reward = 200.00, steps = 200
22:58:34 [INFO] train episode 3361: reward = 187.00, steps = 187
22:58:34 [INFO] train episode 3362: reward = 181.00, steps = 181
22:58:34 [INFO] train episode 3363: reward = 168.00, steps = 168
22:58:34 [INFO] train episode 3364: reward = 149.00, steps = 149
22:58:34 [INFO] train episode 3365: reward = 165.00, steps = 165
22:58:34 [INFO] train episode 3366: reward = 178.00, steps = 178
22:58:34 [INFO] train episode 3367: reward = 200.00, steps = 200
22:58:34 [INFO] train episode 3368: reward = 153.00, steps = 153
22:58:34 [INFO] train episode 3369: reward = 120.00, steps = 120
22:58:34 [INFO] train episode 3370: reward = 176.00, steps = 176
22:58:34 [INFO] train episode 3371: reward = 200.00, steps = 200
22:58:35 [INFO] train episode 3372: reward = 173.00, steps = 173
22:58:35 [INFO] train episode 3373: reward = 179.00, steps = 179
22:58:35 [INFO] train episode 3374: reward = 200.00, steps = 200
22:58:35 [INFO] train episode 3375: reward = 141.00, steps = 141
22:58:35 [INFO] train episode 3376: reward = 127.00, steps = 127
22:58:35 [INFO] train episode 3377: reward = 176.00, steps = 176
22:58:35 [INFO] train episode 3378: reward = 200.00, steps = 200
22:58:35 [INFO] train episode 3379: reward = 122.00, steps = 122
22:58:35 [INFO] train episode 3380: reward = 178.00, steps = 178
22:58:35 [INFO] train episode 3381: reward = 166.00, steps = 166
22:58:35 [INFO] train episode 3382: reward = 179.00, steps = 179
22:58:35 [INFO] train episode 3383: reward = 146.00, steps = 146
22:58:35 [INFO] train episode 3384: reward = 187.00, steps = 187
22:58:35 [INFO] train episode 3385: reward = 127.00, steps = 127
22:58:36 [INFO] train episode 3386: reward = 144.00, steps = 144
22:58:36 [INFO] train episode 3387: reward = 127.00, steps = 127
22:58:36 [INFO] train episode 3388: reward = 174.00, steps = 174
22:58:36 [INFO] train episode 3389: reward = 200.00, steps = 200
22:58:36 [INFO] train episode 3390: reward = 165.00, steps = 165
22:58:36 [INFO] train episode 3391: reward = 118.00, steps = 118
22:58:36 [INFO] train episode 3392: reward = 109.00, steps = 109
22:58:36 [INFO] train episode 3393: reward = 182.00, steps = 182
22:58:36 [INFO] train episode 3394: reward = 200.00, steps = 200
22:58:36 [INFO] train episode 3395: reward = 191.00, steps = 191
22:58:36 [INFO] train episode 3396: reward = 162.00, steps = 162
22:58:36 [INFO] train episode 3397: reward = 172.00, steps = 172
22:58:36 [INFO] train episode 3398: reward = 145.00, steps = 145
22:58:36 [INFO] train episode 3399: reward = 141.00, steps = 141
22:58:36 [INFO] train episode 3400: reward = 168.00, steps = 168
22:58:36 [INFO] train episode 3401: reward = 151.00, steps = 151
22:58:37 [INFO] train episode 3402: reward = 200.00, steps = 200
22:58:37 [INFO] train episode 3403: reward = 155.00, steps = 155
22:58:37 [INFO] train episode 3404: reward = 183.00, steps = 183
22:58:37 [INFO] train episode 3405: reward = 200.00, steps = 200
22:58:37 [INFO] train episode 3406: reward = 136.00, steps = 136
22:58:37 [INFO] train episode 3407: reward = 200.00, steps = 200
22:58:37 [INFO] train episode 3408: reward = 153.00, steps = 153
22:58:37 [INFO] train episode 3409: reward = 200.00, steps = 200
22:58:37 [INFO] train episode 3410: reward = 139.00, steps = 139
22:58:37 [INFO] train episode 3411: reward = 148.00, steps = 148
22:58:37 [INFO] train episode 3412: reward = 141.00, steps = 141
22:58:37 [INFO] train episode 3413: reward = 143.00, steps = 143
22:58:37 [INFO] train episode 3414: reward = 166.00, steps = 166
22:58:37 [INFO] train episode 3415: reward = 175.00, steps = 175
22:58:37 [INFO] train episode 3416: reward = 155.00, steps = 155
22:58:38 [INFO] train episode 3417: reward = 139.00, steps = 139
22:58:38 [INFO] train episode 3418: reward = 145.00, steps = 145
22:58:38 [INFO] train episode 3419: reward = 163.00, steps = 163
22:58:38 [INFO] train episode 3420: reward = 165.00, steps = 165
22:58:38 [INFO] train episode 3421: reward = 125.00, steps = 125
22:58:38 [INFO] train episode 3422: reward = 153.00, steps = 153
22:58:38 [INFO] train episode 3423: reward = 120.00, steps = 120
22:58:38 [INFO] train episode 3424: reward = 128.00, steps = 128
22:58:38 [INFO] train episode 3425: reward = 194.00, steps = 194
22:58:38 [INFO] train episode 3426: reward = 122.00, steps = 122
22:58:38 [INFO] train episode 3427: reward = 200.00, steps = 200
22:58:38 [INFO] train episode 3428: reward = 200.00, steps = 200
22:58:39 [INFO] train episode 3429: reward = 130.00, steps = 130
22:58:39 [INFO] train episode 3430: reward = 193.00, steps = 193
22:58:39 [INFO] train episode 3431: reward = 133.00, steps = 133
22:58:39 [INFO] train episode 3432: reward = 200.00, steps = 200
22:58:39 [INFO] train episode 3433: reward = 190.00, steps = 190
22:58:39 [INFO] train episode 3434: reward = 200.00, steps = 200
22:58:39 [INFO] train episode 3435: reward = 200.00, steps = 200
22:58:39 [INFO] train episode 3436: reward = 146.00, steps = 146
22:58:39 [INFO] train episode 3437: reward = 159.00, steps = 159
22:58:39 [INFO] train episode 3438: reward = 142.00, steps = 142
22:58:39 [INFO] train episode 3439: reward = 160.00, steps = 160
22:58:39 [INFO] train episode 3440: reward = 182.00, steps = 182
22:58:39 [INFO] train episode 3441: reward = 153.00, steps = 153
22:58:40 [INFO] train episode 3442: reward = 186.00, steps = 186
22:58:40 [INFO] train episode 3443: reward = 147.00, steps = 147
22:58:40 [INFO] train episode 3444: reward = 200.00, steps = 200
22:58:40 [INFO] train episode 3445: reward = 169.00, steps = 169
22:58:40 [INFO] train episode 3446: reward = 200.00, steps = 200
22:58:40 [INFO] train episode 3447: reward = 152.00, steps = 152
22:58:40 [INFO] train episode 3448: reward = 200.00, steps = 200
22:58:40 [INFO] train episode 3449: reward = 198.00, steps = 198
22:58:40 [INFO] train episode 3450: reward = 141.00, steps = 141
22:58:40 [INFO] train episode 3451: reward = 200.00, steps = 200
22:58:40 [INFO] train episode 3452: reward = 200.00, steps = 200
22:58:40 [INFO] train episode 3453: reward = 121.00, steps = 121
22:58:41 [INFO] train episode 3454: reward = 130.00, steps = 130
22:58:41 [INFO] train episode 3455: reward = 138.00, steps = 138
22:58:41 [INFO] train episode 3456: reward = 130.00, steps = 130
22:58:41 [INFO] train episode 3457: reward = 104.00, steps = 104
22:58:41 [INFO] train episode 3458: reward = 188.00, steps = 188
22:58:41 [INFO] train episode 3459: reward = 166.00, steps = 166
22:58:41 [INFO] train episode 3460: reward = 200.00, steps = 200
22:58:41 [INFO] train episode 3461: reward = 200.00, steps = 200
22:58:41 [INFO] train episode 3462: reward = 162.00, steps = 162
22:58:41 [INFO] train episode 3463: reward = 160.00, steps = 160
22:58:41 [INFO] train episode 3464: reward = 200.00, steps = 200
22:58:41 [INFO] train episode 3465: reward = 182.00, steps = 182
22:58:41 [INFO] train episode 3466: reward = 200.00, steps = 200
22:58:41 [INFO] train episode 3467: reward = 145.00, steps = 145
22:58:42 [INFO] train episode 3468: reward = 157.00, steps = 157
22:58:42 [INFO] train episode 3469: reward = 132.00, steps = 132
22:58:42 [INFO] train episode 3470: reward = 169.00, steps = 169
22:58:42 [INFO] train episode 3471: reward = 200.00, steps = 200
22:58:42 [INFO] train episode 3472: reward = 144.00, steps = 144
22:58:42 [INFO] train episode 3473: reward = 200.00, steps = 200
22:58:42 [INFO] train episode 3474: reward = 162.00, steps = 162
22:58:42 [INFO] train episode 3475: reward = 138.00, steps = 138
22:58:42 [INFO] train episode 3476: reward = 162.00, steps = 162
22:58:42 [INFO] train episode 3477: reward = 200.00, steps = 200
22:58:42 [INFO] train episode 3478: reward = 200.00, steps = 200
22:58:42 [INFO] train episode 3479: reward = 171.00, steps = 171
22:58:42 [INFO] train episode 3480: reward = 200.00, steps = 200
22:58:43 [INFO] train episode 3481: reward = 200.00, steps = 200
22:58:43 [INFO] train episode 3482: reward = 200.00, steps = 200
22:58:43 [INFO] train episode 3483: reward = 200.00, steps = 200
22:58:43 [INFO] train episode 3484: reward = 198.00, steps = 198
22:58:43 [INFO] train episode 3485: reward = 200.00, steps = 200
22:58:43 [INFO] train episode 3486: reward = 200.00, steps = 200
22:58:43 [INFO] train episode 3487: reward = 200.00, steps = 200
22:58:43 [INFO] train episode 3488: reward = 200.00, steps = 200
22:58:43 [INFO] train episode 3489: reward = 194.00, steps = 194
22:58:44 [INFO] train episode 3490: reward = 167.00, steps = 167
22:58:44 [INFO] train episode 3491: reward = 172.00, steps = 172
22:58:44 [INFO] train episode 3492: reward = 200.00, steps = 200
22:58:44 [INFO] train episode 3493: reward = 180.00, steps = 180
22:58:44 [INFO] train episode 3494: reward = 172.00, steps = 172
22:58:44 [INFO] train episode 3495: reward = 190.00, steps = 190
22:58:44 [INFO] train episode 3496: reward = 200.00, steps = 200
22:58:44 [INFO] train episode 3497: reward = 152.00, steps = 152
22:58:44 [INFO] train episode 3498: reward = 200.00, steps = 200
22:58:44 [INFO] train episode 3499: reward = 151.00, steps = 151
22:58:44 [INFO] train episode 3500: reward = 200.00, steps = 200
22:58:44 [INFO] train episode 3501: reward = 200.00, steps = 200
22:58:45 [INFO] train episode 3502: reward = 200.00, steps = 200
22:58:45 [INFO] train episode 3503: reward = 143.00, steps = 143
22:58:45 [INFO] train episode 3504: reward = 180.00, steps = 180
22:58:45 [INFO] train episode 3505: reward = 145.00, steps = 145
22:58:45 [INFO] train episode 3506: reward = 165.00, steps = 165
22:58:45 [INFO] train episode 3507: reward = 159.00, steps = 159
22:58:45 [INFO] train episode 3508: reward = 173.00, steps = 173
22:58:45 [INFO] train episode 3509: reward = 200.00, steps = 200
22:58:45 [INFO] train episode 3510: reward = 200.00, steps = 200
22:58:45 [INFO] train episode 3511: reward = 148.00, steps = 148
22:58:45 [INFO] train episode 3512: reward = 145.00, steps = 145
22:58:45 [INFO] train episode 3513: reward = 200.00, steps = 200
22:58:46 [INFO] train episode 3514: reward = 200.00, steps = 200
22:58:46 [INFO] train episode 3515: reward = 156.00, steps = 156
22:58:46 [INFO] train episode 3516: reward = 158.00, steps = 158
22:58:46 [INFO] train episode 3517: reward = 171.00, steps = 171
22:58:46 [INFO] train episode 3518: reward = 164.00, steps = 164
22:58:46 [INFO] train episode 3519: reward = 171.00, steps = 171
22:58:46 [INFO] train episode 3520: reward = 200.00, steps = 200
22:58:46 [INFO] train episode 3521: reward = 172.00, steps = 172
22:58:46 [INFO] train episode 3522: reward = 178.00, steps = 178
22:58:46 [INFO] train episode 3523: reward = 141.00, steps = 141
22:58:46 [INFO] train episode 3524: reward = 198.00, steps = 198
22:58:46 [INFO] train episode 3525: reward = 200.00, steps = 200
22:58:46 [INFO] train episode 3526: reward = 141.00, steps = 141
22:58:46 [INFO] train episode 3527: reward = 137.00, steps = 137
22:58:46 [INFO] train episode 3528: reward = 170.00, steps = 170
22:58:46 [INFO] train episode 3529: reward = 152.00, steps = 152
22:58:47 [INFO] train episode 3530: reward = 137.00, steps = 137
22:58:47 [INFO] train episode 3531: reward = 144.00, steps = 144
22:58:47 [INFO] train episode 3532: reward = 200.00, steps = 200
22:58:47 [INFO] train episode 3533: reward = 130.00, steps = 130
22:58:47 [INFO] train episode 3534: reward = 196.00, steps = 196
22:58:47 [INFO] train episode 3535: reward = 200.00, steps = 200
22:58:47 [INFO] train episode 3536: reward = 164.00, steps = 164
22:58:47 [INFO] train episode 3537: reward = 181.00, steps = 181
22:58:47 [INFO] train episode 3538: reward = 175.00, steps = 175
22:58:47 [INFO] train episode 3539: reward = 150.00, steps = 150
22:58:47 [INFO] train episode 3540: reward = 200.00, steps = 200
22:58:47 [INFO] train episode 3541: reward = 147.00, steps = 147
22:58:47 [INFO] train episode 3542: reward = 152.00, steps = 152
22:58:47 [INFO] train episode 3543: reward = 142.00, steps = 142
22:58:47 [INFO] train episode 3544: reward = 200.00, steps = 200
22:58:47 [INFO] train episode 3545: reward = 144.00, steps = 144
22:58:48 [INFO] train episode 3546: reward = 177.00, steps = 177
22:58:48 [INFO] train episode 3547: reward = 140.00, steps = 140
22:58:48 [INFO] train episode 3548: reward = 200.00, steps = 200
22:58:48 [INFO] train episode 3549: reward = 197.00, steps = 197
22:58:48 [INFO] train episode 3550: reward = 149.00, steps = 149
22:58:48 [INFO] train episode 3551: reward = 148.00, steps = 148
22:58:48 [INFO] train episode 3552: reward = 179.00, steps = 179
22:58:48 [INFO] train episode 3553: reward = 168.00, steps = 168
22:58:48 [INFO] train episode 3554: reward = 200.00, steps = 200
22:58:48 [INFO] train episode 3555: reward = 199.00, steps = 199
22:58:48 [INFO] train episode 3556: reward = 144.00, steps = 144
22:58:48 [INFO] train episode 3557: reward = 148.00, steps = 148
22:58:48 [INFO] train episode 3558: reward = 176.00, steps = 176
22:58:48 [INFO] train episode 3559: reward = 147.00, steps = 147
22:58:48 [INFO] train episode 3560: reward = 115.00, steps = 115
22:58:48 [INFO] train episode 3561: reward = 153.00, steps = 153
22:58:49 [INFO] train episode 3562: reward = 137.00, steps = 137
22:58:49 [INFO] train episode 3563: reward = 147.00, steps = 147
22:58:49 [INFO] train episode 3564: reward = 152.00, steps = 152
22:58:49 [INFO] train episode 3565: reward = 137.00, steps = 137
22:58:49 [INFO] train episode 3566: reward = 200.00, steps = 200
22:58:49 [INFO] train episode 3567: reward = 140.00, steps = 140
22:58:49 [INFO] train episode 3568: reward = 200.00, steps = 200
22:58:49 [INFO] train episode 3569: reward = 186.00, steps = 186
22:58:49 [INFO] train episode 3570: reward = 121.00, steps = 121
22:58:49 [INFO] train episode 3571: reward = 200.00, steps = 200
22:58:49 [INFO] train episode 3572: reward = 124.00, steps = 124
22:58:49 [INFO] train episode 3573: reward = 155.00, steps = 155
22:58:49 [INFO] train episode 3574: reward = 132.00, steps = 132
22:58:49 [INFO] train episode 3575: reward = 114.00, steps = 114
22:58:49 [INFO] train episode 3576: reward = 134.00, steps = 134
22:58:49 [INFO] train episode 3577: reward = 138.00, steps = 138
22:58:49 [INFO] train episode 3578: reward = 119.00, steps = 119
22:58:49 [INFO] train episode 3579: reward = 109.00, steps = 109
22:58:50 [INFO] train episode 3580: reward = 157.00, steps = 157
22:58:50 [INFO] train episode 3581: reward = 165.00, steps = 165
22:58:50 [INFO] train episode 3582: reward = 151.00, steps = 151
22:58:50 [INFO] train episode 3583: reward = 124.00, steps = 124
22:58:50 [INFO] train episode 3584: reward = 133.00, steps = 133
22:58:50 [INFO] train episode 3585: reward = 200.00, steps = 200
22:58:50 [INFO] train episode 3586: reward = 131.00, steps = 131
22:58:50 [INFO] train episode 3587: reward = 192.00, steps = 192
22:58:50 [INFO] train episode 3588: reward = 156.00, steps = 156
22:58:50 [INFO] train episode 3589: reward = 125.00, steps = 125
22:58:50 [INFO] train episode 3590: reward = 150.00, steps = 150
22:58:50 [INFO] train episode 3591: reward = 164.00, steps = 164
22:58:50 [INFO] train episode 3592: reward = 137.00, steps = 137
22:58:50 [INFO] train episode 3593: reward = 200.00, steps = 200
22:58:50 [INFO] train episode 3594: reward = 200.00, steps = 200
22:58:50 [INFO] train episode 3595: reward = 132.00, steps = 132
22:58:50 [INFO] train episode 3596: reward = 114.00, steps = 114
22:58:51 [INFO] train episode 3597: reward = 200.00, steps = 200
22:58:51 [INFO] train episode 3598: reward = 170.00, steps = 170
22:58:51 [INFO] train episode 3599: reward = 116.00, steps = 116
22:58:51 [INFO] train episode 3600: reward = 135.00, steps = 135
22:58:51 [INFO] train episode 3601: reward = 139.00, steps = 139
22:58:51 [INFO] train episode 3602: reward = 111.00, steps = 111
22:58:51 [INFO] train episode 3603: reward = 200.00, steps = 200
22:58:51 [INFO] train episode 3604: reward = 190.00, steps = 190
22:58:51 [INFO] train episode 3605: reward = 200.00, steps = 200
22:58:51 [INFO] train episode 3606: reward = 189.00, steps = 189
22:58:51 [INFO] train episode 3607: reward = 114.00, steps = 114
22:58:51 [INFO] train episode 3608: reward = 200.00, steps = 200
22:58:51 [INFO] train episode 3609: reward = 101.00, steps = 101
22:58:51 [INFO] train episode 3610: reward = 110.00, steps = 110
22:58:51 [INFO] train episode 3611: reward = 128.00, steps = 128
22:58:51 [INFO] train episode 3612: reward = 104.00, steps = 104
22:58:52 [INFO] train episode 3613: reward = 126.00, steps = 126
22:58:52 [INFO] train episode 3614: reward = 145.00, steps = 145
22:58:52 [INFO] train episode 3615: reward = 144.00, steps = 144
22:58:52 [INFO] train episode 3616: reward = 126.00, steps = 126
22:58:52 [INFO] train episode 3617: reward = 169.00, steps = 169
22:58:52 [INFO] train episode 3618: reward = 190.00, steps = 190
22:58:52 [INFO] train episode 3619: reward = 111.00, steps = 111
22:58:52 [INFO] train episode 3620: reward = 127.00, steps = 127
22:58:52 [INFO] train episode 3621: reward = 144.00, steps = 144
22:58:52 [INFO] train episode 3622: reward = 187.00, steps = 187
22:58:52 [INFO] train episode 3623: reward = 177.00, steps = 177
22:58:52 [INFO] train episode 3624: reward = 141.00, steps = 141
22:58:52 [INFO] train episode 3625: reward = 154.00, steps = 154
22:58:52 [INFO] train episode 3626: reward = 115.00, steps = 115
22:58:52 [INFO] train episode 3627: reward = 160.00, steps = 160
22:58:52 [INFO] train episode 3628: reward = 200.00, steps = 200
22:58:52 [INFO] train episode 3629: reward = 179.00, steps = 179
22:58:52 [INFO] train episode 3630: reward = 151.00, steps = 151
22:58:53 [INFO] train episode 3631: reward = 158.00, steps = 158
22:58:53 [INFO] train episode 3632: reward = 142.00, steps = 142
22:58:53 [INFO] train episode 3633: reward = 99.00, steps = 99
22:58:53 [INFO] train episode 3634: reward = 129.00, steps = 129
22:58:53 [INFO] train episode 3635: reward = 128.00, steps = 128
22:58:53 [INFO] train episode 3636: reward = 200.00, steps = 200
22:58:53 [INFO] train episode 3637: reward = 117.00, steps = 117
22:58:53 [INFO] train episode 3638: reward = 158.00, steps = 158
22:58:53 [INFO] train episode 3639: reward = 105.00, steps = 105
22:58:53 [INFO] train episode 3640: reward = 99.00, steps = 99
22:58:53 [INFO] train episode 3641: reward = 200.00, steps = 200
22:58:53 [INFO] train episode 3642: reward = 100.00, steps = 100
22:58:53 [INFO] train episode 3643: reward = 179.00, steps = 179
22:58:53 [INFO] train episode 3644: reward = 189.00, steps = 189
22:58:53 [INFO] train episode 3645: reward = 160.00, steps = 160
22:58:53 [INFO] train episode 3646: reward = 156.00, steps = 156
22:58:53 [INFO] train episode 3647: reward = 155.00, steps = 155
22:58:54 [INFO] train episode 3648: reward = 139.00, steps = 139
22:58:54 [INFO] train episode 3649: reward = 123.00, steps = 123
22:58:54 [INFO] train episode 3650: reward = 126.00, steps = 126
22:58:54 [INFO] train episode 3651: reward = 188.00, steps = 188
22:58:54 [INFO] train episode 3652: reward = 98.00, steps = 98
22:58:54 [INFO] train episode 3653: reward = 143.00, steps = 143
22:58:54 [INFO] train episode 3654: reward = 159.00, steps = 159
22:58:54 [INFO] train episode 3655: reward = 118.00, steps = 118
22:58:54 [INFO] train episode 3656: reward = 134.00, steps = 134
22:58:54 [INFO] train episode 3657: reward = 115.00, steps = 115
22:58:54 [INFO] train episode 3658: reward = 175.00, steps = 175
22:58:54 [INFO] train episode 3659: reward = 118.00, steps = 118
22:58:54 [INFO] train episode 3660: reward = 183.00, steps = 183
22:58:54 [INFO] train episode 3661: reward = 152.00, steps = 152
22:58:54 [INFO] train episode 3662: reward = 125.00, steps = 125
22:58:54 [INFO] train episode 3663: reward = 141.00, steps = 141
22:58:54 [INFO] train episode 3664: reward = 97.00, steps = 97
22:58:54 [INFO] train episode 3665: reward = 97.00, steps = 97
22:58:54 [INFO] train episode 3666: reward = 138.00, steps = 138
22:58:54 [INFO] train episode 3667: reward = 148.00, steps = 148
22:58:55 [INFO] train episode 3668: reward = 138.00, steps = 138
22:58:55 [INFO] train episode 3669: reward = 118.00, steps = 118
22:58:55 [INFO] train episode 3670: reward = 200.00, steps = 200
22:58:55 [INFO] train episode 3671: reward = 124.00, steps = 124
22:58:55 [INFO] train episode 3672: reward = 200.00, steps = 200
22:58:55 [INFO] train episode 3673: reward = 121.00, steps = 121
22:58:55 [INFO] train episode 3674: reward = 94.00, steps = 94
22:58:55 [INFO] train episode 3675: reward = 136.00, steps = 136
22:58:55 [INFO] train episode 3676: reward = 200.00, steps = 200
22:58:55 [INFO] train episode 3677: reward = 113.00, steps = 113
22:58:55 [INFO] train episode 3678: reward = 178.00, steps = 178
22:58:55 [INFO] train episode 3679: reward = 106.00, steps = 106
22:58:55 [INFO] train episode 3680: reward = 181.00, steps = 181
22:58:55 [INFO] train episode 3681: reward = 126.00, steps = 126
22:58:55 [INFO] train episode 3682: reward = 134.00, steps = 134
22:58:55 [INFO] train episode 3683: reward = 105.00, steps = 105
22:58:55 [INFO] train episode 3684: reward = 198.00, steps = 198
22:58:55 [INFO] train episode 3685: reward = 166.00, steps = 166
22:58:55 [INFO] train episode 3686: reward = 124.00, steps = 124
22:58:56 [INFO] train episode 3687: reward = 173.00, steps = 173
22:58:56 [INFO] train episode 3688: reward = 123.00, steps = 123
22:58:56 [INFO] train episode 3689: reward = 99.00, steps = 99
22:58:56 [INFO] train episode 3690: reward = 159.00, steps = 159
22:58:56 [INFO] train episode 3691: reward = 148.00, steps = 148
22:58:56 [INFO] train episode 3692: reward = 200.00, steps = 200
22:58:56 [INFO] train episode 3693: reward = 144.00, steps = 144
22:58:56 [INFO] train episode 3694: reward = 133.00, steps = 133
22:58:56 [INFO] train episode 3695: reward = 145.00, steps = 145
22:58:56 [INFO] train episode 3696: reward = 89.00, steps = 89
22:58:56 [INFO] train episode 3697: reward = 103.00, steps = 103
22:58:56 [INFO] train episode 3698: reward = 157.00, steps = 157
22:58:56 [INFO] train episode 3699: reward = 116.00, steps = 116
22:58:56 [INFO] train episode 3700: reward = 190.00, steps = 190
22:58:56 [INFO] train episode 3701: reward = 200.00, steps = 200
22:58:56 [INFO] train episode 3702: reward = 139.00, steps = 139
22:58:56 [INFO] train episode 3703: reward = 104.00, steps = 104
22:58:56 [INFO] train episode 3704: reward = 131.00, steps = 131
22:58:56 [INFO] train episode 3705: reward = 141.00, steps = 141
22:58:57 [INFO] train episode 3706: reward = 153.00, steps = 153
22:58:57 [INFO] train episode 3707: reward = 200.00, steps = 200
22:58:57 [INFO] train episode 3708: reward = 124.00, steps = 124
22:58:57 [INFO] train episode 3709: reward = 113.00, steps = 113
22:58:57 [INFO] train episode 3710: reward = 134.00, steps = 134
22:58:57 [INFO] train episode 3711: reward = 127.00, steps = 127
22:58:57 [INFO] train episode 3712: reward = 130.00, steps = 130
22:58:57 [INFO] train episode 3713: reward = 121.00, steps = 121
22:58:57 [INFO] train episode 3714: reward = 167.00, steps = 167
22:58:57 [INFO] train episode 3715: reward = 149.00, steps = 149
22:58:57 [INFO] train episode 3716: reward = 130.00, steps = 130
22:58:57 [INFO] train episode 3717: reward = 105.00, steps = 105
22:58:57 [INFO] train episode 3718: reward = 152.00, steps = 152
22:58:57 [INFO] train episode 3719: reward = 107.00, steps = 107
22:58:57 [INFO] train episode 3720: reward = 121.00, steps = 121
22:58:57 [INFO] train episode 3721: reward = 96.00, steps = 96
22:58:57 [INFO] train episode 3722: reward = 82.00, steps = 82
22:58:57 [INFO] train episode 3723: reward = 95.00, steps = 95
22:58:57 [INFO] train episode 3724: reward = 146.00, steps = 146
22:58:57 [INFO] train episode 3725: reward = 116.00, steps = 116
22:58:58 [INFO] train episode 3726: reward = 149.00, steps = 149
22:58:58 [INFO] train episode 3727: reward = 98.00, steps = 98
22:58:58 [INFO] train episode 3728: reward = 110.00, steps = 110
22:58:58 [INFO] train episode 3729: reward = 200.00, steps = 200
22:58:58 [INFO] train episode 3730: reward = 96.00, steps = 96
22:58:58 [INFO] train episode 3731: reward = 157.00, steps = 157
22:58:58 [INFO] train episode 3732: reward = 159.00, steps = 159
22:58:58 [INFO] train episode 3733: reward = 107.00, steps = 107
22:58:58 [INFO] train episode 3734: reward = 100.00, steps = 100
22:58:58 [INFO] train episode 3735: reward = 125.00, steps = 125
22:58:58 [INFO] train episode 3736: reward = 144.00, steps = 144
22:58:58 [INFO] train episode 3737: reward = 104.00, steps = 104
22:58:58 [INFO] train episode 3738: reward = 161.00, steps = 161
22:58:58 [INFO] train episode 3739: reward = 103.00, steps = 103
22:58:58 [INFO] train episode 3740: reward = 200.00, steps = 200
22:58:58 [INFO] train episode 3741: reward = 111.00, steps = 111
22:58:58 [INFO] train episode 3742: reward = 128.00, steps = 128
22:58:58 [INFO] train episode 3743: reward = 96.00, steps = 96
22:58:58 [INFO] train episode 3744: reward = 126.00, steps = 126
22:58:58 [INFO] train episode 3745: reward = 106.00, steps = 106
22:58:58 [INFO] train episode 3746: reward = 125.00, steps = 125
22:58:58 [INFO] train episode 3747: reward = 119.00, steps = 119
22:58:58 [INFO] train episode 3748: reward = 107.00, steps = 107
22:58:58 [INFO] train episode 3749: reward = 166.00, steps = 166
22:58:59 [INFO] train episode 3750: reward = 152.00, steps = 152
22:58:59 [INFO] train episode 3751: reward = 108.00, steps = 108
22:58:59 [INFO] train episode 3752: reward = 143.00, steps = 143
22:58:59 [INFO] train episode 3753: reward = 164.00, steps = 164
22:58:59 [INFO] train episode 3754: reward = 149.00, steps = 149
22:58:59 [INFO] train episode 3755: reward = 96.00, steps = 96
22:58:59 [INFO] train episode 3756: reward = 94.00, steps = 94
22:58:59 [INFO] train episode 3757: reward = 200.00, steps = 200
22:58:59 [INFO] train episode 3758: reward = 155.00, steps = 155
22:58:59 [INFO] train episode 3759: reward = 148.00, steps = 148
22:58:59 [INFO] train episode 3760: reward = 200.00, steps = 200
22:58:59 [INFO] train episode 3761: reward = 121.00, steps = 121
22:58:59 [INFO] train episode 3762: reward = 135.00, steps = 135
22:58:59 [INFO] train episode 3763: reward = 141.00, steps = 141
22:58:59 [INFO] train episode 3764: reward = 200.00, steps = 200
22:58:59 [INFO] train episode 3765: reward = 180.00, steps = 180
22:58:59 [INFO] train episode 3766: reward = 116.00, steps = 116
22:58:59 [INFO] train episode 3767: reward = 200.00, steps = 200
22:59:00 [INFO] train episode 3768: reward = 200.00, steps = 200
22:59:00 [INFO] train episode 3769: reward = 200.00, steps = 200
22:59:00 [INFO] train episode 3770: reward = 126.00, steps = 126
22:59:00 [INFO] train episode 3771: reward = 132.00, steps = 132
22:59:00 [INFO] train episode 3772: reward = 112.00, steps = 112
22:59:00 [INFO] train episode 3773: reward = 133.00, steps = 133
22:59:00 [INFO] train episode 3774: reward = 120.00, steps = 120
22:59:00 [INFO] train episode 3775: reward = 98.00, steps = 98
22:59:00 [INFO] train episode 3776: reward = 110.00, steps = 110
22:59:00 [INFO] train episode 3777: reward = 135.00, steps = 135
22:59:00 [INFO] train episode 3778: reward = 137.00, steps = 137
22:59:00 [INFO] train episode 3779: reward = 181.00, steps = 181
22:59:00 [INFO] train episode 3780: reward = 194.00, steps = 194
22:59:00 [INFO] train episode 3781: reward = 115.00, steps = 115
22:59:00 [INFO] train episode 3782: reward = 172.00, steps = 172
22:59:00 [INFO] train episode 3783: reward = 147.00, steps = 147
22:59:00 [INFO] train episode 3784: reward = 147.00, steps = 147
22:59:00 [INFO] train episode 3785: reward = 169.00, steps = 169
22:59:01 [INFO] train episode 3786: reward = 141.00, steps = 141
22:59:01 [INFO] train episode 3787: reward = 153.00, steps = 153
22:59:01 [INFO] train episode 3788: reward = 131.00, steps = 131
22:59:01 [INFO] train episode 3789: reward = 127.00, steps = 127
22:59:01 [INFO] train episode 3790: reward = 169.00, steps = 169
22:59:01 [INFO] train episode 3791: reward = 155.00, steps = 155
22:59:01 [INFO] train episode 3792: reward = 116.00, steps = 116
22:59:01 [INFO] train episode 3793: reward = 133.00, steps = 133
22:59:01 [INFO] train episode 3794: reward = 114.00, steps = 114
22:59:01 [INFO] train episode 3795: reward = 143.00, steps = 143
22:59:01 [INFO] train episode 3796: reward = 119.00, steps = 119
22:59:01 [INFO] train episode 3797: reward = 137.00, steps = 137
22:59:01 [INFO] train episode 3798: reward = 121.00, steps = 121
22:59:01 [INFO] train episode 3799: reward = 150.00, steps = 150
22:59:01 [INFO] train episode 3800: reward = 146.00, steps = 146
22:59:01 [INFO] train episode 3801: reward = 142.00, steps = 142
22:59:01 [INFO] train episode 3802: reward = 135.00, steps = 135
22:59:01 [INFO] train episode 3803: reward = 153.00, steps = 153
22:59:01 [INFO] train episode 3804: reward = 200.00, steps = 200
22:59:01 [INFO] train episode 3805: reward = 105.00, steps = 105
22:59:01 [INFO] train episode 3806: reward = 114.00, steps = 114
22:59:02 [INFO] train episode 3807: reward = 191.00, steps = 191
22:59:02 [INFO] train episode 3808: reward = 166.00, steps = 166
22:59:02 [INFO] train episode 3809: reward = 140.00, steps = 140
22:59:02 [INFO] train episode 3810: reward = 115.00, steps = 115
22:59:02 [INFO] train episode 3811: reward = 173.00, steps = 173
22:59:02 [INFO] train episode 3812: reward = 121.00, steps = 121
22:59:02 [INFO] train episode 3813: reward = 148.00, steps = 148
22:59:02 [INFO] train episode 3814: reward = 120.00, steps = 120
22:59:02 [INFO] train episode 3815: reward = 153.00, steps = 153
22:59:02 [INFO] train episode 3816: reward = 160.00, steps = 160
22:59:02 [INFO] train episode 3817: reward = 200.00, steps = 200
22:59:02 [INFO] train episode 3818: reward = 155.00, steps = 155
22:59:02 [INFO] train episode 3819: reward = 175.00, steps = 175
22:59:02 [INFO] train episode 3820: reward = 156.00, steps = 156
22:59:02 [INFO] train episode 3821: reward = 129.00, steps = 129
22:59:02 [INFO] train episode 3822: reward = 200.00, steps = 200
22:59:02 [INFO] train episode 3823: reward = 105.00, steps = 105
22:59:02 [INFO] train episode 3824: reward = 100.00, steps = 100
22:59:02 [INFO] train episode 3825: reward = 184.00, steps = 184
22:59:02 [INFO] train episode 3826: reward = 132.00, steps = 132
22:59:02 [INFO] train episode 3827: reward = 154.00, steps = 154
22:59:03 [INFO] train episode 3828: reward = 200.00, steps = 200
22:59:03 [INFO] train episode 3829: reward = 200.00, steps = 200
22:59:03 [INFO] train episode 3830: reward = 148.00, steps = 148
22:59:03 [INFO] train episode 3831: reward = 135.00, steps = 135
22:59:03 [INFO] train episode 3832: reward = 157.00, steps = 157
22:59:03 [INFO] train episode 3833: reward = 200.00, steps = 200
22:59:03 [INFO] train episode 3834: reward = 134.00, steps = 134
22:59:03 [INFO] train episode 3835: reward = 145.00, steps = 145
22:59:03 [INFO] train episode 3836: reward = 152.00, steps = 152
22:59:03 [INFO] train episode 3837: reward = 200.00, steps = 200
22:59:03 [INFO] train episode 3838: reward = 136.00, steps = 136
22:59:03 [INFO] train episode 3839: reward = 177.00, steps = 177
22:59:03 [INFO] train episode 3840: reward = 193.00, steps = 193
22:59:03 [INFO] train episode 3841: reward = 200.00, steps = 200
22:59:03 [INFO] train episode 3842: reward = 146.00, steps = 146
22:59:03 [INFO] train episode 3843: reward = 166.00, steps = 166
22:59:03 [INFO] train episode 3844: reward = 154.00, steps = 154
22:59:03 [INFO] train episode 3845: reward = 154.00, steps = 154
22:59:04 [INFO] train episode 3846: reward = 138.00, steps = 138
22:59:04 [INFO] train episode 3847: reward = 165.00, steps = 165
22:59:04 [INFO] train episode 3848: reward = 158.00, steps = 158
22:59:04 [INFO] train episode 3849: reward = 151.00, steps = 151
22:59:04 [INFO] train episode 3850: reward = 200.00, steps = 200
22:59:04 [INFO] train episode 3851: reward = 190.00, steps = 190
22:59:04 [INFO] train episode 3852: reward = 148.00, steps = 148
22:59:04 [INFO] train episode 3853: reward = 161.00, steps = 161
22:59:04 [INFO] train episode 3854: reward = 123.00, steps = 123
22:59:04 [INFO] train episode 3855: reward = 127.00, steps = 127
22:59:04 [INFO] train episode 3856: reward = 200.00, steps = 200
22:59:04 [INFO] train episode 3857: reward = 165.00, steps = 165
22:59:04 [INFO] train episode 3858: reward = 158.00, steps = 158
22:59:04 [INFO] train episode 3859: reward = 194.00, steps = 194
22:59:04 [INFO] train episode 3860: reward = 200.00, steps = 200
22:59:04 [INFO] train episode 3861: reward = 145.00, steps = 145
22:59:04 [INFO] train episode 3862: reward = 200.00, steps = 200
22:59:04 [INFO] train episode 3863: reward = 169.00, steps = 169
22:59:05 [INFO] train episode 3864: reward = 140.00, steps = 140
22:59:05 [INFO] train episode 3865: reward = 156.00, steps = 156
22:59:05 [INFO] train episode 3866: reward = 133.00, steps = 133
22:59:05 [INFO] train episode 3867: reward = 178.00, steps = 178
22:59:05 [INFO] train episode 3868: reward = 154.00, steps = 154
22:59:05 [INFO] train episode 3869: reward = 192.00, steps = 192
22:59:05 [INFO] train episode 3870: reward = 141.00, steps = 141
22:59:05 [INFO] train episode 3871: reward = 179.00, steps = 179
22:59:05 [INFO] train episode 3872: reward = 136.00, steps = 136
22:59:05 [INFO] train episode 3873: reward = 200.00, steps = 200
22:59:05 [INFO] train episode 3874: reward = 165.00, steps = 165
22:59:05 [INFO] train episode 3875: reward = 131.00, steps = 131
22:59:05 [INFO] train episode 3876: reward = 155.00, steps = 155
22:59:05 [INFO] train episode 3877: reward = 142.00, steps = 142
22:59:05 [INFO] train episode 3878: reward = 165.00, steps = 165
22:59:05 [INFO] train episode 3879: reward = 144.00, steps = 144
22:59:05 [INFO] train episode 3880: reward = 168.00, steps = 168
22:59:05 [INFO] train episode 3881: reward = 136.00, steps = 136
22:59:06 [INFO] train episode 3882: reward = 137.00, steps = 137
22:59:06 [INFO] train episode 3883: reward = 159.00, steps = 159
22:59:06 [INFO] train episode 3884: reward = 157.00, steps = 157
22:59:06 [INFO] train episode 3885: reward = 160.00, steps = 160
22:59:06 [INFO] train episode 3886: reward = 109.00, steps = 109
22:59:06 [INFO] train episode 3887: reward = 103.00, steps = 103
22:59:06 [INFO] train episode 3888: reward = 159.00, steps = 159
22:59:06 [INFO] train episode 3889: reward = 196.00, steps = 196
22:59:06 [INFO] train episode 3890: reward = 155.00, steps = 155
22:59:06 [INFO] train episode 3891: reward = 200.00, steps = 200
22:59:06 [INFO] train episode 3892: reward = 169.00, steps = 169
22:59:06 [INFO] train episode 3893: reward = 151.00, steps = 151
22:59:06 [INFO] train episode 3894: reward = 165.00, steps = 165
22:59:06 [INFO] train episode 3895: reward = 125.00, steps = 125
22:59:06 [INFO] train episode 3896: reward = 134.00, steps = 134
22:59:06 [INFO] train episode 3897: reward = 145.00, steps = 145
22:59:06 [INFO] train episode 3898: reward = 109.00, steps = 109
22:59:06 [INFO] train episode 3899: reward = 169.00, steps = 169
22:59:06 [INFO] train episode 3900: reward = 147.00, steps = 147
22:59:06 [INFO] train episode 3901: reward = 175.00, steps = 175
22:59:07 [INFO] train episode 3902: reward = 115.00, steps = 115
22:59:07 [INFO] train episode 3903: reward = 144.00, steps = 144
22:59:07 [INFO] train episode 3904: reward = 132.00, steps = 132
22:59:07 [INFO] train episode 3905: reward = 200.00, steps = 200
22:59:07 [INFO] train episode 3906: reward = 180.00, steps = 180
22:59:07 [INFO] train episode 3907: reward = 135.00, steps = 135
22:59:07 [INFO] train episode 3908: reward = 153.00, steps = 153
22:59:07 [INFO] train episode 3909: reward = 200.00, steps = 200
22:59:07 [INFO] train episode 3910: reward = 200.00, steps = 200
22:59:07 [INFO] train episode 3911: reward = 156.00, steps = 156
22:59:07 [INFO] train episode 3912: reward = 191.00, steps = 191
22:59:07 [INFO] train episode 3913: reward = 176.00, steps = 176
22:59:07 [INFO] train episode 3914: reward = 179.00, steps = 179
22:59:07 [INFO] train episode 3915: reward = 150.00, steps = 150
22:59:07 [INFO] train episode 3916: reward = 179.00, steps = 179
22:59:07 [INFO] train episode 3917: reward = 134.00, steps = 134
22:59:07 [INFO] train episode 3918: reward = 200.00, steps = 200
22:59:08 [INFO] train episode 3919: reward = 149.00, steps = 149
22:59:08 [INFO] train episode 3920: reward = 200.00, steps = 200
22:59:08 [INFO] train episode 3921: reward = 158.00, steps = 158
22:59:08 [INFO] train episode 3922: reward = 141.00, steps = 141
22:59:08 [INFO] train episode 3923: reward = 200.00, steps = 200
22:59:08 [INFO] train episode 3924: reward = 200.00, steps = 200
22:59:08 [INFO] train episode 3925: reward = 197.00, steps = 197
22:59:08 [INFO] train episode 3926: reward = 136.00, steps = 136
22:59:08 [INFO] train episode 3927: reward = 183.00, steps = 183
22:59:08 [INFO] train episode 3928: reward = 130.00, steps = 130
22:59:08 [INFO] train episode 3929: reward = 162.00, steps = 162
22:59:08 [INFO] train episode 3930: reward = 140.00, steps = 140
22:59:08 [INFO] train episode 3931: reward = 187.00, steps = 187
22:59:08 [INFO] train episode 3932: reward = 200.00, steps = 200
22:59:08 [INFO] train episode 3933: reward = 143.00, steps = 143
22:59:08 [INFO] train episode 3934: reward = 184.00, steps = 184
22:59:08 [INFO] train episode 3935: reward = 132.00, steps = 132
22:59:09 [INFO] train episode 3936: reward = 147.00, steps = 147
22:59:09 [INFO] train episode 3937: reward = 124.00, steps = 124
22:59:09 [INFO] train episode 3938: reward = 120.00, steps = 120
22:59:09 [INFO] train episode 3939: reward = 200.00, steps = 200
22:59:09 [INFO] train episode 3940: reward = 134.00, steps = 134
22:59:09 [INFO] train episode 3941: reward = 175.00, steps = 175
22:59:09 [INFO] train episode 3942: reward = 174.00, steps = 174
22:59:09 [INFO] train episode 3943: reward = 139.00, steps = 139
22:59:09 [INFO] train episode 3944: reward = 183.00, steps = 183
22:59:09 [INFO] train episode 3945: reward = 122.00, steps = 122
22:59:09 [INFO] train episode 3946: reward = 170.00, steps = 170
22:59:09 [INFO] train episode 3947: reward = 194.00, steps = 194
22:59:09 [INFO] train episode 3948: reward = 142.00, steps = 142
22:59:09 [INFO] train episode 3949: reward = 122.00, steps = 122
22:59:09 [INFO] train episode 3950: reward = 176.00, steps = 176
22:59:09 [INFO] train episode 3951: reward = 149.00, steps = 149
22:59:09 [INFO] train episode 3952: reward = 137.00, steps = 137
22:59:09 [INFO] train episode 3953: reward = 115.00, steps = 115
22:59:09 [INFO] train episode 3954: reward = 133.00, steps = 133
22:59:10 [INFO] train episode 3955: reward = 173.00, steps = 173
22:59:10 [INFO] train episode 3956: reward = 200.00, steps = 200
22:59:10 [INFO] train episode 3957: reward = 156.00, steps = 156
22:59:10 [INFO] train episode 3958: reward = 156.00, steps = 156
22:59:10 [INFO] train episode 3959: reward = 200.00, steps = 200
22:59:10 [INFO] train episode 3960: reward = 187.00, steps = 187
22:59:10 [INFO] train episode 3961: reward = 163.00, steps = 163
22:59:10 [INFO] train episode 3962: reward = 171.00, steps = 171
22:59:10 [INFO] train episode 3963: reward = 167.00, steps = 167
22:59:10 [INFO] train episode 3964: reward = 160.00, steps = 160
22:59:10 [INFO] train episode 3965: reward = 163.00, steps = 163
22:59:10 [INFO] train episode 3966: reward = 124.00, steps = 124
22:59:10 [INFO] train episode 3967: reward = 175.00, steps = 175
22:59:10 [INFO] train episode 3968: reward = 169.00, steps = 169
22:59:10 [INFO] train episode 3969: reward = 135.00, steps = 135
22:59:10 [INFO] train episode 3970: reward = 124.00, steps = 124
22:59:10 [INFO] train episode 3971: reward = 180.00, steps = 180
22:59:10 [INFO] train episode 3972: reward = 182.00, steps = 182
22:59:10 [INFO] train episode 3973: reward = 99.00, steps = 99
22:59:11 [INFO] train episode 3974: reward = 161.00, steps = 161
22:59:11 [INFO] train episode 3975: reward = 131.00, steps = 131
22:59:11 [INFO] train episode 3976: reward = 173.00, steps = 173
22:59:11 [INFO] train episode 3977: reward = 146.00, steps = 146
22:59:11 [INFO] train episode 3978: reward = 172.00, steps = 172
22:59:11 [INFO] train episode 3979: reward = 166.00, steps = 166
22:59:11 [INFO] train episode 3980: reward = 191.00, steps = 191
22:59:11 [INFO] train episode 3981: reward = 148.00, steps = 148
22:59:11 [INFO] train episode 3982: reward = 120.00, steps = 120
22:59:11 [INFO] train episode 3983: reward = 200.00, steps = 200
22:59:11 [INFO] train episode 3984: reward = 187.00, steps = 187
22:59:11 [INFO] train episode 3985: reward = 151.00, steps = 151
22:59:11 [INFO] train episode 3986: reward = 129.00, steps = 129
22:59:11 [INFO] train episode 3987: reward = 194.00, steps = 194
22:59:11 [INFO] train episode 3988: reward = 124.00, steps = 124
22:59:11 [INFO] train episode 3989: reward = 162.00, steps = 162
22:59:11 [INFO] train episode 3990: reward = 111.00, steps = 111
22:59:11 [INFO] train episode 3991: reward = 200.00, steps = 200
22:59:12 [INFO] train episode 3992: reward = 128.00, steps = 128
22:59:12 [INFO] train episode 3993: reward = 180.00, steps = 180
22:59:12 [INFO] train episode 3994: reward = 102.00, steps = 102
22:59:12 [INFO] train episode 3995: reward = 119.00, steps = 119
22:59:12 [INFO] train episode 3996: reward = 128.00, steps = 128
22:59:12 [INFO] train episode 3997: reward = 130.00, steps = 130
22:59:12 [INFO] train episode 3998: reward = 103.00, steps = 103
22:59:12 [INFO] train episode 3999: reward = 200.00, steps = 200
22:59:12 [INFO] train episode 4000: reward = 101.00, steps = 101
22:59:12 [INFO] train episode 4001: reward = 200.00, steps = 200
22:59:12 [INFO] train episode 4002: reward = 117.00, steps = 117
22:59:12 [INFO] train episode 4003: reward = 152.00, steps = 152
22:59:12 [INFO] train episode 4004: reward = 142.00, steps = 142
22:59:12 [INFO] train episode 4005: reward = 115.00, steps = 115
22:59:12 [INFO] train episode 4006: reward = 200.00, steps = 200
22:59:12 [INFO] train episode 4007: reward = 99.00, steps = 99
22:59:12 [INFO] train episode 4008: reward = 99.00, steps = 99
22:59:12 [INFO] train episode 4009: reward = 181.00, steps = 181
22:59:12 [INFO] train episode 4010: reward = 148.00, steps = 148
22:59:12 [INFO] train episode 4011: reward = 188.00, steps = 188
22:59:12 [INFO] train episode 4012: reward = 200.00, steps = 200
22:59:13 [INFO] train episode 4013: reward = 161.00, steps = 161
22:59:13 [INFO] train episode 4014: reward = 166.00, steps = 166
22:59:13 [INFO] train episode 4015: reward = 175.00, steps = 175
22:59:13 [INFO] train episode 4016: reward = 200.00, steps = 200
22:59:13 [INFO] train episode 4017: reward = 200.00, steps = 200
22:59:13 [INFO] train episode 4018: reward = 118.00, steps = 118
22:59:13 [INFO] train episode 4019: reward = 145.00, steps = 145
22:59:13 [INFO] train episode 4020: reward = 200.00, steps = 200
22:59:13 [INFO] train episode 4021: reward = 200.00, steps = 200
22:59:13 [INFO] train episode 4022: reward = 115.00, steps = 115
22:59:13 [INFO] train episode 4023: reward = 136.00, steps = 136
22:59:13 [INFO] train episode 4024: reward = 133.00, steps = 133
22:59:13 [INFO] train episode 4025: reward = 138.00, steps = 138
22:59:13 [INFO] train episode 4026: reward = 111.00, steps = 111
22:59:13 [INFO] train episode 4027: reward = 153.00, steps = 153
22:59:13 [INFO] train episode 4028: reward = 174.00, steps = 174
22:59:13 [INFO] train episode 4029: reward = 100.00, steps = 100
22:59:13 [INFO] train episode 4030: reward = 129.00, steps = 129
22:59:13 [INFO] train episode 4031: reward = 200.00, steps = 200
22:59:14 [INFO] train episode 4032: reward = 153.00, steps = 153
22:59:14 [INFO] train episode 4033: reward = 130.00, steps = 130
22:59:14 [INFO] train episode 4034: reward = 142.00, steps = 142
22:59:14 [INFO] train episode 4035: reward = 103.00, steps = 103
22:59:14 [INFO] train episode 4036: reward = 181.00, steps = 181
22:59:14 [INFO] train episode 4037: reward = 148.00, steps = 148
22:59:14 [INFO] train episode 4038: reward = 94.00, steps = 94
22:59:14 [INFO] train episode 4039: reward = 133.00, steps = 133
22:59:14 [INFO] train episode 4040: reward = 159.00, steps = 159
22:59:14 [INFO] train episode 4041: reward = 186.00, steps = 186
22:59:14 [INFO] train episode 4042: reward = 200.00, steps = 200
22:59:14 [INFO] train episode 4043: reward = 142.00, steps = 142
22:59:14 [INFO] train episode 4044: reward = 200.00, steps = 200
22:59:14 [INFO] train episode 4045: reward = 185.00, steps = 185
22:59:14 [INFO] train episode 4046: reward = 200.00, steps = 200
22:59:14 [INFO] train episode 4047: reward = 200.00, steps = 200
22:59:14 [INFO] train episode 4048: reward = 198.00, steps = 198
22:59:15 [INFO] train episode 4049: reward = 160.00, steps = 160
22:59:15 [INFO] train episode 4050: reward = 127.00, steps = 127
22:59:15 [INFO] train episode 4051: reward = 150.00, steps = 150
22:59:15 [INFO] train episode 4052: reward = 125.00, steps = 125
22:59:15 [INFO] train episode 4053: reward = 152.00, steps = 152
22:59:15 [INFO] train episode 4054: reward = 191.00, steps = 191
22:59:15 [INFO] train episode 4055: reward = 200.00, steps = 200
22:59:15 [INFO] train episode 4056: reward = 161.00, steps = 161
22:59:15 [INFO] train episode 4057: reward = 172.00, steps = 172
22:59:15 [INFO] train episode 4058: reward = 200.00, steps = 200
22:59:15 [INFO] train episode 4059: reward = 200.00, steps = 200
22:59:15 [INFO] train episode 4060: reward = 200.00, steps = 200
22:59:15 [INFO] train episode 4061: reward = 131.00, steps = 131
22:59:15 [INFO] train episode 4062: reward = 200.00, steps = 200
22:59:15 [INFO] train episode 4063: reward = 145.00, steps = 145
22:59:15 [INFO] train episode 4064: reward = 161.00, steps = 161
22:59:15 [INFO] train episode 4065: reward = 173.00, steps = 173
22:59:15 [INFO] train episode 4066: reward = 200.00, steps = 200
22:59:16 [INFO] train episode 4067: reward = 161.00, steps = 161
22:59:16 [INFO] train episode 4068: reward = 200.00, steps = 200
22:59:16 [INFO] train episode 4069: reward = 200.00, steps = 200
22:59:16 [INFO] train episode 4070: reward = 145.00, steps = 145
22:59:16 [INFO] train episode 4071: reward = 185.00, steps = 185
22:59:16 [INFO] train episode 4072: reward = 150.00, steps = 150
22:59:16 [INFO] train episode 4073: reward = 193.00, steps = 193
22:59:16 [INFO] train episode 4074: reward = 174.00, steps = 174
22:59:16 [INFO] train episode 4075: reward = 153.00, steps = 153
22:59:16 [INFO] train episode 4076: reward = 158.00, steps = 158
22:59:16 [INFO] train episode 4077: reward = 195.00, steps = 195
22:59:16 [INFO] train episode 4078: reward = 140.00, steps = 140
22:59:16 [INFO] train episode 4079: reward = 158.00, steps = 158
22:59:16 [INFO] train episode 4080: reward = 200.00, steps = 200
22:59:16 [INFO] train episode 4081: reward = 161.00, steps = 161
22:59:16 [INFO] train episode 4082: reward = 162.00, steps = 162
22:59:16 [INFO] train episode 4083: reward = 200.00, steps = 200
22:59:16 [INFO] train episode 4084: reward = 133.00, steps = 133
22:59:17 [INFO] train episode 4085: reward = 200.00, steps = 200
22:59:17 [INFO] train episode 4086: reward = 200.00, steps = 200
22:59:17 [INFO] train episode 4087: reward = 200.00, steps = 200
22:59:17 [INFO] train episode 4088: reward = 177.00, steps = 177
22:59:17 [INFO] train episode 4089: reward = 200.00, steps = 200
22:59:17 [INFO] train episode 4090: reward = 139.00, steps = 139
22:59:17 [INFO] train episode 4091: reward = 192.00, steps = 192
22:59:17 [INFO] train episode 4092: reward = 200.00, steps = 200
22:59:17 [INFO] train episode 4093: reward = 200.00, steps = 200
22:59:17 [INFO] train episode 4094: reward = 166.00, steps = 166
22:59:17 [INFO] train episode 4095: reward = 200.00, steps = 200
22:59:17 [INFO] train episode 4096: reward = 200.00, steps = 200
22:59:17 [INFO] train episode 4097: reward = 200.00, steps = 200
22:59:17 [INFO] train episode 4098: reward = 200.00, steps = 200
22:59:17 [INFO] train episode 4099: reward = 166.00, steps = 166
22:59:18 [INFO] train episode 4100: reward = 182.00, steps = 182
22:59:18 [INFO] train episode 4101: reward = 158.00, steps = 158
22:59:18 [INFO] train episode 4102: reward = 162.00, steps = 162
22:59:18 [INFO] train episode 4103: reward = 145.00, steps = 145
22:59:18 [INFO] train episode 4104: reward = 169.00, steps = 169
22:59:18 [INFO] train episode 4105: reward = 150.00, steps = 150
22:59:18 [INFO] train episode 4106: reward = 161.00, steps = 161
22:59:18 [INFO] train episode 4107: reward = 154.00, steps = 154
22:59:18 [INFO] train episode 4108: reward = 200.00, steps = 200
22:59:18 [INFO] train episode 4109: reward = 159.00, steps = 159
22:59:18 [INFO] train episode 4110: reward = 200.00, steps = 200
22:59:18 [INFO] train episode 4111: reward = 200.00, steps = 200
22:59:18 [INFO] train episode 4112: reward = 200.00, steps = 200
22:59:18 [INFO] train episode 4113: reward = 170.00, steps = 170
22:59:18 [INFO] train episode 4114: reward = 166.00, steps = 166
22:59:19 [INFO] train episode 4115: reward = 200.00, steps = 200
22:59:19 [INFO] train episode 4116: reward = 200.00, steps = 200
22:59:19 [INFO] train episode 4117: reward = 159.00, steps = 159
22:59:19 [INFO] train episode 4118: reward = 200.00, steps = 200
22:59:19 [INFO] train episode 4119: reward = 179.00, steps = 179
22:59:19 [INFO] train episode 4120: reward = 198.00, steps = 198
22:59:19 [INFO] train episode 4121: reward = 200.00, steps = 200
22:59:19 [INFO] train episode 4122: reward = 190.00, steps = 190
22:59:19 [INFO] train episode 4123: reward = 169.00, steps = 169
22:59:19 [INFO] train episode 4124: reward = 200.00, steps = 200
22:59:19 [INFO] train episode 4125: reward = 168.00, steps = 168
22:59:19 [INFO] train episode 4126: reward = 200.00, steps = 200
22:59:19 [INFO] train episode 4127: reward = 200.00, steps = 200
22:59:19 [INFO] train episode 4128: reward = 167.00, steps = 167
22:59:19 [INFO] train episode 4129: reward = 148.00, steps = 148
22:59:19 [INFO] train episode 4130: reward = 191.00, steps = 191
22:59:20 [INFO] train episode 4131: reward = 192.00, steps = 192
22:59:20 [INFO] train episode 4132: reward = 200.00, steps = 200
22:59:20 [INFO] train episode 4133: reward = 200.00, steps = 200
22:59:20 [INFO] train episode 4134: reward = 183.00, steps = 183
22:59:20 [INFO] train episode 4135: reward = 200.00, steps = 200
22:59:20 [INFO] train episode 4136: reward = 153.00, steps = 153
22:59:20 [INFO] train episode 4137: reward = 180.00, steps = 180
22:59:20 [INFO] train episode 4138: reward = 183.00, steps = 183
22:59:20 [INFO] train episode 4139: reward = 200.00, steps = 200
22:59:20 [INFO] train episode 4140: reward = 200.00, steps = 200
22:59:20 [INFO] train episode 4141: reward = 171.00, steps = 171
22:59:20 [INFO] train episode 4142: reward = 200.00, steps = 200
22:59:20 [INFO] train episode 4143: reward = 170.00, steps = 170
22:59:20 [INFO] train episode 4144: reward = 200.00, steps = 200
22:59:20 [INFO] train episode 4145: reward = 200.00, steps = 200
22:59:20 [INFO] train episode 4146: reward = 200.00, steps = 200
22:59:21 [INFO] train episode 4147: reward = 173.00, steps = 173
22:59:21 [INFO] train episode 4148: reward = 150.00, steps = 150
22:59:21 [INFO] train episode 4149: reward = 177.00, steps = 177
22:59:21 [INFO] train episode 4150: reward = 173.00, steps = 173
22:59:21 [INFO] train episode 4151: reward = 181.00, steps = 181
22:59:21 [INFO] train episode 4152: reward = 200.00, steps = 200
22:59:21 [INFO] train episode 4153: reward = 200.00, steps = 200
22:59:21 [INFO] train episode 4154: reward = 172.00, steps = 172
22:59:21 [INFO] train episode 4155: reward = 184.00, steps = 184
22:59:21 [INFO] train episode 4156: reward = 192.00, steps = 192
22:59:21 [INFO] train episode 4157: reward = 193.00, steps = 193
22:59:21 [INFO] train episode 4158: reward = 200.00, steps = 200
22:59:21 [INFO] train episode 4159: reward = 200.00, steps = 200
22:59:21 [INFO] train episode 4160: reward = 182.00, steps = 182
22:59:21 [INFO] train episode 4161: reward = 198.00, steps = 198
22:59:22 [INFO] train episode 4162: reward = 200.00, steps = 200
22:59:22 [INFO] train episode 4163: reward = 127.00, steps = 127
22:59:22 [INFO] train episode 4164: reward = 193.00, steps = 193
22:59:22 [INFO] train episode 4165: reward = 200.00, steps = 200
22:59:22 [INFO] train episode 4166: reward = 151.00, steps = 151
22:59:22 [INFO] train episode 4167: reward = 163.00, steps = 163
22:59:22 [INFO] train episode 4168: reward = 158.00, steps = 158
22:59:22 [INFO] train episode 4169: reward = 173.00, steps = 173
22:59:22 [INFO] train episode 4170: reward = 200.00, steps = 200
22:59:22 [INFO] train episode 4171: reward = 200.00, steps = 200
22:59:22 [INFO] train episode 4172: reward = 200.00, steps = 200
22:59:22 [INFO] train episode 4173: reward = 200.00, steps = 200
22:59:22 [INFO] train episode 4174: reward = 200.00, steps = 200
22:59:22 [INFO] train episode 4175: reward = 152.00, steps = 152
22:59:22 [INFO] train episode 4176: reward = 200.00, steps = 200
22:59:23 [INFO] train episode 4177: reward = 200.00, steps = 200
22:59:23 [INFO] train episode 4178: reward = 146.00, steps = 146
22:59:23 [INFO] train episode 4179: reward = 176.00, steps = 176
22:59:23 [INFO] train episode 4180: reward = 200.00, steps = 200
22:59:23 [INFO] train episode 4181: reward = 193.00, steps = 193
22:59:23 [INFO] train episode 4182: reward = 133.00, steps = 133
22:59:23 [INFO] train episode 4183: reward = 200.00, steps = 200
22:59:23 [INFO] train episode 4184: reward = 200.00, steps = 200
22:59:23 [INFO] train episode 4185: reward = 187.00, steps = 187
22:59:23 [INFO] train episode 4186: reward = 182.00, steps = 182
22:59:23 [INFO] train episode 4187: reward = 200.00, steps = 200
22:59:23 [INFO] train episode 4188: reward = 125.00, steps = 125
22:59:23 [INFO] train episode 4189: reward = 158.00, steps = 158
22:59:23 [INFO] train episode 4190: reward = 159.00, steps = 159
22:59:23 [INFO] train episode 4191: reward = 170.00, steps = 170
22:59:23 [INFO] train episode 4192: reward = 177.00, steps = 177
22:59:23 [INFO] train episode 4193: reward = 173.00, steps = 173
22:59:24 [INFO] train episode 4194: reward = 200.00, steps = 200
22:59:24 [INFO] train episode 4195: reward = 200.00, steps = 200
22:59:24 [INFO] train episode 4196: reward = 200.00, steps = 200
22:59:24 [INFO] train episode 4197: reward = 184.00, steps = 184
22:59:24 [INFO] train episode 4198: reward = 177.00, steps = 177
22:59:24 [INFO] train episode 4199: reward = 158.00, steps = 158
22:59:24 [INFO] train episode 4200: reward = 156.00, steps = 156
22:59:24 [INFO] train episode 4201: reward = 199.00, steps = 199
22:59:24 [INFO] train episode 4202: reward = 183.00, steps = 183
22:59:24 [INFO] train episode 4203: reward = 179.00, steps = 179
22:59:24 [INFO] train episode 4204: reward = 197.00, steps = 197
22:59:24 [INFO] train episode 4205: reward = 200.00, steps = 200
22:59:24 [INFO] train episode 4206: reward = 200.00, steps = 200
22:59:24 [INFO] train episode 4207: reward = 177.00, steps = 177
22:59:24 [INFO] train episode 4208: reward = 194.00, steps = 194
22:59:24 [INFO] train episode 4209: reward = 140.00, steps = 140
22:59:25 [INFO] train episode 4210: reward = 149.00, steps = 149
22:59:25 [INFO] train episode 4211: reward = 200.00, steps = 200
22:59:25 [INFO] train episode 4212: reward = 180.00, steps = 180
22:59:25 [INFO] train episode 4213: reward = 162.00, steps = 162
22:59:25 [INFO] train episode 4214: reward = 200.00, steps = 200
22:59:25 [INFO] train episode 4215: reward = 200.00, steps = 200
22:59:25 [INFO] train episode 4216: reward = 190.00, steps = 190
22:59:25 [INFO] train episode 4217: reward = 200.00, steps = 200
22:59:25 [INFO] train episode 4218: reward = 162.00, steps = 162
22:59:25 [INFO] train episode 4219: reward = 193.00, steps = 193
22:59:25 [INFO] train episode 4220: reward = 147.00, steps = 147
22:59:25 [INFO] train episode 4221: reward = 200.00, steps = 200
22:59:25 [INFO] train episode 4222: reward = 200.00, steps = 200
22:59:25 [INFO] train episode 4223: reward = 134.00, steps = 134
22:59:25 [INFO] train episode 4224: reward = 180.00, steps = 180
22:59:25 [INFO] train episode 4225: reward = 200.00, steps = 200
22:59:26 [INFO] train episode 4226: reward = 200.00, steps = 200
22:59:26 [INFO] train episode 4227: reward = 200.00, steps = 200
22:59:26 [INFO] train episode 4228: reward = 133.00, steps = 133
22:59:26 [INFO] train episode 4229: reward = 136.00, steps = 136
22:59:26 [INFO] train episode 4230: reward = 198.00, steps = 198
22:59:26 [INFO] train episode 4231: reward = 153.00, steps = 153
22:59:26 [INFO] train episode 4232: reward = 187.00, steps = 187
22:59:26 [INFO] train episode 4233: reward = 200.00, steps = 200
22:59:26 [INFO] train episode 4234: reward = 200.00, steps = 200
22:59:26 [INFO] train episode 4235: reward = 169.00, steps = 169
22:59:26 [INFO] train episode 4236: reward = 200.00, steps = 200
22:59:26 [INFO] train episode 4237: reward = 139.00, steps = 139
22:59:26 [INFO] train episode 4238: reward = 158.00, steps = 158
22:59:26 [INFO] train episode 4239: reward = 173.00, steps = 173
22:59:26 [INFO] train episode 4240: reward = 155.00, steps = 155
22:59:26 [INFO] train episode 4241: reward = 200.00, steps = 200
22:59:26 [INFO] train episode 4242: reward = 175.00, steps = 175
22:59:27 [INFO] train episode 4243: reward = 200.00, steps = 200
22:59:27 [INFO] train episode 4244: reward = 138.00, steps = 138
22:59:27 [INFO] train episode 4245: reward = 200.00, steps = 200
22:59:27 [INFO] train episode 4246: reward = 191.00, steps = 191
22:59:27 [INFO] train episode 4247: reward = 177.00, steps = 177
22:59:27 [INFO] train episode 4248: reward = 200.00, steps = 200
22:59:27 [INFO] train episode 4249: reward = 161.00, steps = 161
22:59:27 [INFO] train episode 4250: reward = 134.00, steps = 134
22:59:27 [INFO] train episode 4251: reward = 147.00, steps = 147
22:59:27 [INFO] train episode 4252: reward = 154.00, steps = 154
22:59:27 [INFO] train episode 4253: reward = 176.00, steps = 176
22:59:27 [INFO] train episode 4254: reward = 181.00, steps = 181
22:59:27 [INFO] train episode 4255: reward = 164.00, steps = 164
22:59:27 [INFO] train episode 4256: reward = 200.00, steps = 200
22:59:27 [INFO] train episode 4257: reward = 200.00, steps = 200
22:59:27 [INFO] train episode 4258: reward = 200.00, steps = 200
22:59:27 [INFO] train episode 4259: reward = 126.00, steps = 126
22:59:27 [INFO] train episode 4260: reward = 132.00, steps = 132
22:59:28 [INFO] train episode 4261: reward = 113.00, steps = 113
22:59:28 [INFO] train episode 4262: reward = 200.00, steps = 200
22:59:28 [INFO] train episode 4263: reward = 143.00, steps = 143
22:59:28 [INFO] train episode 4264: reward = 186.00, steps = 186
22:59:28 [INFO] train episode 4265: reward = 116.00, steps = 116
22:59:28 [INFO] train episode 4266: reward = 200.00, steps = 200
22:59:28 [INFO] train episode 4267: reward = 182.00, steps = 182
22:59:28 [INFO] train episode 4268: reward = 141.00, steps = 141
22:59:28 [INFO] train episode 4269: reward = 200.00, steps = 200
22:59:28 [INFO] train episode 4270: reward = 187.00, steps = 187
22:59:28 [INFO] train episode 4271: reward = 200.00, steps = 200
22:59:28 [INFO] train episode 4272: reward = 128.00, steps = 128
22:59:28 [INFO] train episode 4273: reward = 111.00, steps = 111
22:59:28 [INFO] train episode 4274: reward = 127.00, steps = 127
22:59:28 [INFO] train episode 4275: reward = 200.00, steps = 200
22:59:28 [INFO] train episode 4276: reward = 200.00, steps = 200
22:59:29 [INFO] train episode 4277: reward = 200.00, steps = 200
22:59:29 [INFO] train episode 4278: reward = 144.00, steps = 144
22:59:29 [INFO] train episode 4279: reward = 178.00, steps = 178
22:59:29 [INFO] train episode 4280: reward = 153.00, steps = 153
22:59:29 [INFO] train episode 4281: reward = 181.00, steps = 181
22:59:29 [INFO] train episode 4282: reward = 168.00, steps = 168
22:59:29 [INFO] train episode 4283: reward = 163.00, steps = 163
22:59:29 [INFO] train episode 4284: reward = 200.00, steps = 200
22:59:29 [INFO] train episode 4285: reward = 155.00, steps = 155
22:59:29 [INFO] train episode 4286: reward = 117.00, steps = 117
22:59:29 [INFO] train episode 4287: reward = 137.00, steps = 137
22:59:29 [INFO] train episode 4288: reward = 154.00, steps = 154
22:59:29 [INFO] train episode 4289: reward = 148.00, steps = 148
22:59:29 [INFO] train episode 4290: reward = 132.00, steps = 132
22:59:29 [INFO] train episode 4291: reward = 157.00, steps = 157
22:59:29 [INFO] train episode 4292: reward = 200.00, steps = 200
22:59:29 [INFO] train episode 4293: reward = 187.00, steps = 187
22:59:30 [INFO] train episode 4294: reward = 192.00, steps = 192
22:59:30 [INFO] train episode 4295: reward = 200.00, steps = 200
22:59:30 [INFO] train episode 4296: reward = 117.00, steps = 117
22:59:30 [INFO] train episode 4297: reward = 192.00, steps = 192
22:59:30 [INFO] train episode 4298: reward = 149.00, steps = 149
22:59:30 [INFO] train episode 4299: reward = 113.00, steps = 113
22:59:30 [INFO] train episode 4300: reward = 149.00, steps = 149
22:59:30 [INFO] train episode 4301: reward = 154.00, steps = 154
22:59:30 [INFO] train episode 4302: reward = 200.00, steps = 200
22:59:30 [INFO] train episode 4303: reward = 135.00, steps = 135
22:59:30 [INFO] train episode 4304: reward = 136.00, steps = 136
22:59:30 [INFO] train episode 4305: reward = 137.00, steps = 137
22:59:30 [INFO] train episode 4306: reward = 200.00, steps = 200
22:59:30 [INFO] train episode 4307: reward = 147.00, steps = 147
22:59:30 [INFO] train episode 4308: reward = 123.00, steps = 123
22:59:30 [INFO] train episode 4309: reward = 179.00, steps = 179
22:59:30 [INFO] train episode 4310: reward = 200.00, steps = 200
22:59:30 [INFO] train episode 4311: reward = 200.00, steps = 200
22:59:31 [INFO] train episode 4312: reward = 170.00, steps = 170
22:59:31 [INFO] train episode 4313: reward = 126.00, steps = 126
22:59:31 [INFO] train episode 4314: reward = 170.00, steps = 170
22:59:31 [INFO] train episode 4315: reward = 200.00, steps = 200
22:59:31 [INFO] train episode 4316: reward = 131.00, steps = 131
22:59:31 [INFO] train episode 4317: reward = 125.00, steps = 125
22:59:31 [INFO] train episode 4318: reward = 200.00, steps = 200
22:59:31 [INFO] train episode 4319: reward = 189.00, steps = 189
22:59:31 [INFO] train episode 4320: reward = 123.00, steps = 123
22:59:31 [INFO] train episode 4321: reward = 200.00, steps = 200
22:59:31 [INFO] train episode 4322: reward = 141.00, steps = 141
22:59:31 [INFO] train episode 4323: reward = 157.00, steps = 157
22:59:31 [INFO] train episode 4324: reward = 106.00, steps = 106
22:59:31 [INFO] train episode 4325: reward = 131.00, steps = 131
22:59:31 [INFO] train episode 4326: reward = 139.00, steps = 139
22:59:31 [INFO] train episode 4327: reward = 183.00, steps = 183
22:59:31 [INFO] train episode 4328: reward = 200.00, steps = 200
22:59:31 [INFO] train episode 4329: reward = 155.00, steps = 155
22:59:31 [INFO] train episode 4330: reward = 200.00, steps = 200
22:59:31 [INFO] train episode 4331: reward = 200.00, steps = 200
22:59:32 [INFO] train episode 4332: reward = 163.00, steps = 163
22:59:32 [INFO] train episode 4333: reward = 142.00, steps = 142
22:59:32 [INFO] train episode 4334: reward = 147.00, steps = 147
22:59:32 [INFO] train episode 4335: reward = 162.00, steps = 162
22:59:32 [INFO] train episode 4336: reward = 199.00, steps = 199
22:59:32 [INFO] train episode 4337: reward = 156.00, steps = 156
22:59:32 [INFO] train episode 4338: reward = 153.00, steps = 153
22:59:32 [INFO] train episode 4339: reward = 200.00, steps = 200
22:59:32 [INFO] train episode 4340: reward = 196.00, steps = 196
22:59:32 [INFO] train episode 4341: reward = 166.00, steps = 166
22:59:32 [INFO] train episode 4342: reward = 140.00, steps = 140
22:59:32 [INFO] train episode 4343: reward = 185.00, steps = 185
22:59:32 [INFO] train episode 4344: reward = 162.00, steps = 162
22:59:32 [INFO] train episode 4345: reward = 151.00, steps = 151
22:59:32 [INFO] train episode 4346: reward = 151.00, steps = 151
22:59:32 [INFO] train episode 4347: reward = 127.00, steps = 127
22:59:32 [INFO] train episode 4348: reward = 138.00, steps = 138
22:59:32 [INFO] train episode 4349: reward = 129.00, steps = 129
22:59:32 [INFO] train episode 4350: reward = 135.00, steps = 135
22:59:33 [INFO] train episode 4351: reward = 167.00, steps = 167
22:59:33 [INFO] train episode 4352: reward = 120.00, steps = 120
22:59:33 [INFO] train episode 4353: reward = 136.00, steps = 136
22:59:33 [INFO] train episode 4354: reward = 200.00, steps = 200
22:59:33 [INFO] train episode 4355: reward = 134.00, steps = 134
22:59:33 [INFO] train episode 4356: reward = 157.00, steps = 157
22:59:33 [INFO] train episode 4357: reward = 182.00, steps = 182
22:59:33 [INFO] train episode 4358: reward = 200.00, steps = 200
22:59:33 [INFO] train episode 4359: reward = 182.00, steps = 182
22:59:33 [INFO] train episode 4360: reward = 200.00, steps = 200
22:59:33 [INFO] train episode 4361: reward = 137.00, steps = 137
22:59:33 [INFO] train episode 4362: reward = 200.00, steps = 200
22:59:33 [INFO] train episode 4363: reward = 130.00, steps = 130
22:59:33 [INFO] train episode 4364: reward = 182.00, steps = 182
22:59:33 [INFO] train episode 4365: reward = 167.00, steps = 167
22:59:33 [INFO] train episode 4366: reward = 200.00, steps = 200
22:59:34 [INFO] train episode 4367: reward = 139.00, steps = 139
22:59:34 [INFO] train episode 4368: reward = 154.00, steps = 154
22:59:34 [INFO] train episode 4369: reward = 134.00, steps = 134
22:59:34 [INFO] train episode 4370: reward = 144.00, steps = 144
22:59:34 [INFO] train episode 4371: reward = 200.00, steps = 200
22:59:34 [INFO] train episode 4372: reward = 139.00, steps = 139
22:59:34 [INFO] train episode 4373: reward = 200.00, steps = 200
22:59:34 [INFO] train episode 4374: reward = 177.00, steps = 177
22:59:34 [INFO] train episode 4375: reward = 161.00, steps = 161
22:59:34 [INFO] train episode 4376: reward = 200.00, steps = 200
22:59:34 [INFO] train episode 4377: reward = 165.00, steps = 165
22:59:34 [INFO] train episode 4378: reward = 130.00, steps = 130
22:59:34 [INFO] train episode 4379: reward = 172.00, steps = 172
22:59:34 [INFO] train episode 4380: reward = 200.00, steps = 200
22:59:34 [INFO] train episode 4381: reward = 122.00, steps = 122
22:59:34 [INFO] train episode 4382: reward = 139.00, steps = 139
22:59:34 [INFO] train episode 4383: reward = 200.00, steps = 200
22:59:34 [INFO] train episode 4384: reward = 126.00, steps = 126
22:59:34 [INFO] train episode 4385: reward = 200.00, steps = 200
22:59:35 [INFO] train episode 4386: reward = 130.00, steps = 130
22:59:35 [INFO] train episode 4387: reward = 177.00, steps = 177
22:59:35 [INFO] train episode 4388: reward = 126.00, steps = 126
22:59:35 [INFO] train episode 4389: reward = 133.00, steps = 133
22:59:35 [INFO] train episode 4390: reward = 167.00, steps = 167
22:59:35 [INFO] train episode 4391: reward = 143.00, steps = 143
22:59:35 [INFO] train episode 4392: reward = 194.00, steps = 194
22:59:35 [INFO] train episode 4393: reward = 165.00, steps = 165
22:59:35 [INFO] train episode 4394: reward = 127.00, steps = 127
22:59:35 [INFO] train episode 4395: reward = 124.00, steps = 124
22:59:35 [INFO] train episode 4396: reward = 116.00, steps = 116
22:59:35 [INFO] train episode 4397: reward = 153.00, steps = 153
22:59:35 [INFO] train episode 4398: reward = 141.00, steps = 141
22:59:35 [INFO] train episode 4399: reward = 167.00, steps = 167
22:59:35 [INFO] train episode 4400: reward = 119.00, steps = 119
22:59:35 [INFO] train episode 4401: reward = 129.00, steps = 129
22:59:35 [INFO] train episode 4402: reward = 150.00, steps = 150
22:59:35 [INFO] train episode 4403: reward = 129.00, steps = 129
22:59:35 [INFO] train episode 4404: reward = 185.00, steps = 185
22:59:35 [INFO] train episode 4405: reward = 168.00, steps = 168
22:59:36 [INFO] train episode 4406: reward = 131.00, steps = 131
22:59:36 [INFO] train episode 4407: reward = 121.00, steps = 121
22:59:36 [INFO] train episode 4408: reward = 120.00, steps = 120
22:59:36 [INFO] train episode 4409: reward = 128.00, steps = 128
22:59:36 [INFO] train episode 4410: reward = 143.00, steps = 143
22:59:36 [INFO] train episode 4411: reward = 130.00, steps = 130
22:59:36 [INFO] train episode 4412: reward = 165.00, steps = 165
22:59:36 [INFO] train episode 4413: reward = 159.00, steps = 159
22:59:36 [INFO] train episode 4414: reward = 167.00, steps = 167
22:59:36 [INFO] train episode 4415: reward = 111.00, steps = 111
22:59:36 [INFO] train episode 4416: reward = 185.00, steps = 185
22:59:36 [INFO] train episode 4417: reward = 171.00, steps = 171
22:59:36 [INFO] train episode 4418: reward = 133.00, steps = 133
22:59:36 [INFO] train episode 4419: reward = 114.00, steps = 114
22:59:36 [INFO] train episode 4420: reward = 184.00, steps = 184
22:59:36 [INFO] train episode 4421: reward = 124.00, steps = 124
22:59:36 [INFO] train episode 4422: reward = 180.00, steps = 180
22:59:36 [INFO] train episode 4423: reward = 159.00, steps = 159
22:59:36 [INFO] train episode 4424: reward = 165.00, steps = 165
22:59:36 [INFO] train episode 4425: reward = 156.00, steps = 156
22:59:37 [INFO] train episode 4426: reward = 200.00, steps = 200
22:59:37 [INFO] train episode 4427: reward = 166.00, steps = 166
22:59:37 [INFO] train episode 4428: reward = 173.00, steps = 173
22:59:37 [INFO] train episode 4429: reward = 197.00, steps = 197
22:59:37 [INFO] train episode 4430: reward = 156.00, steps = 156
22:59:37 [INFO] train episode 4431: reward = 187.00, steps = 187
22:59:37 [INFO] train episode 4432: reward = 122.00, steps = 122
22:59:37 [INFO] train episode 4433: reward = 176.00, steps = 176
22:59:37 [INFO] train episode 4434: reward = 111.00, steps = 111
22:59:37 [INFO] train episode 4435: reward = 155.00, steps = 155
22:59:37 [INFO] train episode 4436: reward = 130.00, steps = 130
22:59:37 [INFO] train episode 4437: reward = 97.00, steps = 97
22:59:37 [INFO] train episode 4438: reward = 131.00, steps = 131
22:59:37 [INFO] train episode 4439: reward = 177.00, steps = 177
22:59:37 [INFO] train episode 4440: reward = 137.00, steps = 137
22:59:37 [INFO] train episode 4441: reward = 186.00, steps = 186
22:59:37 [INFO] train episode 4442: reward = 198.00, steps = 198
22:59:37 [INFO] train episode 4443: reward = 140.00, steps = 140
22:59:37 [INFO] train episode 4444: reward = 122.00, steps = 122
22:59:38 [INFO] train episode 4445: reward = 169.00, steps = 169
22:59:38 [INFO] train episode 4446: reward = 114.00, steps = 114
22:59:38 [INFO] train episode 4447: reward = 123.00, steps = 123
22:59:38 [INFO] train episode 4448: reward = 156.00, steps = 156
22:59:38 [INFO] train episode 4449: reward = 175.00, steps = 175
22:59:38 [INFO] train episode 4450: reward = 200.00, steps = 200
22:59:38 [INFO] train episode 4451: reward = 187.00, steps = 187
22:59:38 [INFO] train episode 4452: reward = 132.00, steps = 132
22:59:38 [INFO] train episode 4453: reward = 200.00, steps = 200
22:59:38 [INFO] train episode 4454: reward = 125.00, steps = 125
22:59:38 [INFO] train episode 4455: reward = 144.00, steps = 144
22:59:38 [INFO] train episode 4456: reward = 181.00, steps = 181
22:59:38 [INFO] train episode 4457: reward = 120.00, steps = 120
22:59:38 [INFO] train episode 4458: reward = 126.00, steps = 126
22:59:38 [INFO] train episode 4459: reward = 130.00, steps = 130
22:59:38 [INFO] train episode 4460: reward = 155.00, steps = 155
22:59:38 [INFO] train episode 4461: reward = 178.00, steps = 178
22:59:38 [INFO] train episode 4462: reward = 154.00, steps = 154
22:59:39 [INFO] train episode 4463: reward = 200.00, steps = 200
22:59:39 [INFO] train episode 4464: reward = 142.00, steps = 142
22:59:39 [INFO] train episode 4465: reward = 200.00, steps = 200
22:59:39 [INFO] train episode 4466: reward = 155.00, steps = 155
22:59:39 [INFO] train episode 4467: reward = 122.00, steps = 122
22:59:39 [INFO] train episode 4468: reward = 138.00, steps = 138
22:59:39 [INFO] train episode 4469: reward = 150.00, steps = 150
22:59:39 [INFO] train episode 4470: reward = 144.00, steps = 144
22:59:39 [INFO] train episode 4471: reward = 165.00, steps = 165
22:59:39 [INFO] train episode 4472: reward = 129.00, steps = 129
22:59:39 [INFO] train episode 4473: reward = 158.00, steps = 158
22:59:39 [INFO] train episode 4474: reward = 200.00, steps = 200
22:59:39 [INFO] train episode 4475: reward = 132.00, steps = 132
22:59:39 [INFO] train episode 4476: reward = 109.00, steps = 109
22:59:39 [INFO] train episode 4477: reward = 130.00, steps = 130
22:59:39 [INFO] train episode 4478: reward = 200.00, steps = 200
22:59:39 [INFO] train episode 4479: reward = 134.00, steps = 134
22:59:39 [INFO] train episode 4480: reward = 132.00, steps = 132
22:59:39 [INFO] train episode 4481: reward = 114.00, steps = 114
22:59:39 [INFO] train episode 4482: reward = 196.00, steps = 196
22:59:40 [INFO] train episode 4483: reward = 135.00, steps = 135
22:59:40 [INFO] train episode 4484: reward = 118.00, steps = 118
22:59:40 [INFO] train episode 4485: reward = 121.00, steps = 121
22:59:40 [INFO] train episode 4486: reward = 96.00, steps = 96
22:59:40 [INFO] train episode 4487: reward = 124.00, steps = 124
22:59:40 [INFO] train episode 4488: reward = 126.00, steps = 126
22:59:40 [INFO] train episode 4489: reward = 145.00, steps = 145
22:59:40 [INFO] train episode 4490: reward = 156.00, steps = 156
22:59:40 [INFO] train episode 4491: reward = 127.00, steps = 127
22:59:40 [INFO] train episode 4492: reward = 200.00, steps = 200
22:59:40 [INFO] train episode 4493: reward = 123.00, steps = 123
22:59:40 [INFO] train episode 4494: reward = 149.00, steps = 149
22:59:40 [INFO] train episode 4495: reward = 157.00, steps = 157
22:59:40 [INFO] train episode 4496: reward = 200.00, steps = 200
22:59:40 [INFO] train episode 4497: reward = 110.00, steps = 110
22:59:40 [INFO] train episode 4498: reward = 200.00, steps = 200
22:59:40 [INFO] train episode 4499: reward = 147.00, steps = 147
22:59:40 [INFO] train episode 4500: reward = 178.00, steps = 178
22:59:40 [INFO] train episode 4501: reward = 126.00, steps = 126
22:59:40 [INFO] train episode 4502: reward = 121.00, steps = 121
22:59:41 [INFO] train episode 4503: reward = 164.00, steps = 164
22:59:41 [INFO] train episode 4504: reward = 165.00, steps = 165
22:59:41 [INFO] train episode 4505: reward = 133.00, steps = 133
22:59:41 [INFO] train episode 4506: reward = 136.00, steps = 136
22:59:41 [INFO] train episode 4507: reward = 156.00, steps = 156
22:59:41 [INFO] train episode 4508: reward = 114.00, steps = 114
22:59:41 [INFO] train episode 4509: reward = 161.00, steps = 161
22:59:41 [INFO] train episode 4510: reward = 135.00, steps = 135
22:59:41 [INFO] train episode 4511: reward = 133.00, steps = 133
22:59:41 [INFO] train episode 4512: reward = 158.00, steps = 158
22:59:41 [INFO] train episode 4513: reward = 183.00, steps = 183
22:59:41 [INFO] train episode 4514: reward = 145.00, steps = 145
22:59:41 [INFO] train episode 4515: reward = 145.00, steps = 145
22:59:41 [INFO] train episode 4516: reward = 200.00, steps = 200
22:59:41 [INFO] train episode 4517: reward = 124.00, steps = 124
22:59:41 [INFO] train episode 4518: reward = 154.00, steps = 154
22:59:41 [INFO] train episode 4519: reward = 176.00, steps = 176
22:59:41 [INFO] train episode 4520: reward = 200.00, steps = 200
22:59:41 [INFO] train episode 4521: reward = 118.00, steps = 118
22:59:42 [INFO] train episode 4522: reward = 200.00, steps = 200
22:59:42 [INFO] train episode 4523: reward = 136.00, steps = 136
22:59:42 [INFO] train episode 4524: reward = 155.00, steps = 155
22:59:42 [INFO] train episode 4525: reward = 164.00, steps = 164
22:59:42 [INFO] train episode 4526: reward = 173.00, steps = 173
22:59:42 [INFO] train episode 4527: reward = 155.00, steps = 155
22:59:42 [INFO] train episode 4528: reward = 197.00, steps = 197
22:59:42 [INFO] train episode 4529: reward = 126.00, steps = 126
22:59:42 [INFO] train episode 4530: reward = 154.00, steps = 154
22:59:42 [INFO] train episode 4531: reward = 156.00, steps = 156
22:59:42 [INFO] train episode 4532: reward = 108.00, steps = 108
22:59:42 [INFO] train episode 4533: reward = 140.00, steps = 140
22:59:42 [INFO] train episode 4534: reward = 185.00, steps = 185
22:59:42 [INFO] train episode 4535: reward = 147.00, steps = 147
22:59:42 [INFO] train episode 4536: reward = 163.00, steps = 163
22:59:42 [INFO] train episode 4537: reward = 177.00, steps = 177
22:59:42 [INFO] train episode 4538: reward = 200.00, steps = 200
22:59:42 [INFO] train episode 4539: reward = 117.00, steps = 117
22:59:43 [INFO] train episode 4540: reward = 200.00, steps = 200
22:59:43 [INFO] train episode 4541: reward = 139.00, steps = 139
22:59:43 [INFO] train episode 4542: reward = 200.00, steps = 200
22:59:43 [INFO] train episode 4543: reward = 171.00, steps = 171
22:59:43 [INFO] train episode 4544: reward = 129.00, steps = 129
22:59:43 [INFO] train episode 4545: reward = 129.00, steps = 129
22:59:43 [INFO] train episode 4546: reward = 166.00, steps = 166
22:59:43 [INFO] train episode 4547: reward = 180.00, steps = 180
22:59:43 [INFO] train episode 4548: reward = 200.00, steps = 200
22:59:43 [INFO] train episode 4549: reward = 140.00, steps = 140
22:59:43 [INFO] train episode 4550: reward = 195.00, steps = 195
22:59:43 [INFO] train episode 4551: reward = 116.00, steps = 116
22:59:43 [INFO] train episode 4552: reward = 200.00, steps = 200
22:59:43 [INFO] train episode 4553: reward = 169.00, steps = 169
22:59:43 [INFO] train episode 4554: reward = 190.00, steps = 190
22:59:43 [INFO] train episode 4555: reward = 111.00, steps = 111
22:59:44 [INFO] train episode 4556: reward = 179.00, steps = 179
22:59:44 [INFO] train episode 4557: reward = 116.00, steps = 116
22:59:44 [INFO] train episode 4558: reward = 106.00, steps = 106
22:59:44 [INFO] train episode 4559: reward = 155.00, steps = 155
22:59:44 [INFO] train episode 4560: reward = 114.00, steps = 114
22:59:44 [INFO] train episode 4561: reward = 161.00, steps = 161
22:59:44 [INFO] train episode 4562: reward = 102.00, steps = 102
22:59:44 [INFO] train episode 4563: reward = 158.00, steps = 158
22:59:44 [INFO] train episode 4564: reward = 124.00, steps = 124
22:59:44 [INFO] train episode 4565: reward = 135.00, steps = 135
22:59:44 [INFO] train episode 4566: reward = 115.00, steps = 115
22:59:44 [INFO] train episode 4567: reward = 142.00, steps = 142
22:59:44 [INFO] train episode 4568: reward = 200.00, steps = 200
22:59:44 [INFO] train episode 4569: reward = 179.00, steps = 179
22:59:44 [INFO] train episode 4570: reward = 161.00, steps = 161
22:59:44 [INFO] train episode 4571: reward = 161.00, steps = 161
22:59:44 [INFO] train episode 4572: reward = 200.00, steps = 200
22:59:45 [INFO] train episode 4573: reward = 200.00, steps = 200
22:59:45 [INFO] train episode 4574: reward = 199.00, steps = 199
22:59:45 [INFO] train episode 4575: reward = 191.00, steps = 191
22:59:45 [INFO] train episode 4576: reward = 166.00, steps = 166
22:59:45 [INFO] train episode 4577: reward = 172.00, steps = 172
22:59:45 [INFO] train episode 4578: reward = 200.00, steps = 200
22:59:45 [INFO] train episode 4579: reward = 171.00, steps = 171
22:59:45 [INFO] train episode 4580: reward = 200.00, steps = 200
22:59:45 [INFO] train episode 4581: reward = 200.00, steps = 200
22:59:45 [INFO] train episode 4582: reward = 134.00, steps = 134
22:59:45 [INFO] train episode 4583: reward = 167.00, steps = 167
22:59:45 [INFO] train episode 4584: reward = 126.00, steps = 126
22:59:45 [INFO] train episode 4585: reward = 121.00, steps = 121
22:59:45 [INFO] train episode 4586: reward = 177.00, steps = 177
22:59:45 [INFO] train episode 4587: reward = 195.00, steps = 195
22:59:45 [INFO] train episode 4588: reward = 143.00, steps = 143
22:59:45 [INFO] train episode 4589: reward = 147.00, steps = 147
22:59:46 [INFO] train episode 4590: reward = 154.00, steps = 154
22:59:46 [INFO] train episode 4591: reward = 200.00, steps = 200
22:59:46 [INFO] train episode 4592: reward = 200.00, steps = 200
22:59:46 [INFO] train episode 4593: reward = 174.00, steps = 174
22:59:46 [INFO] train episode 4594: reward = 117.00, steps = 117
22:59:46 [INFO] train episode 4595: reward = 164.00, steps = 164
22:59:46 [INFO] train episode 4596: reward = 189.00, steps = 189
22:59:46 [INFO] train episode 4597: reward = 141.00, steps = 141
22:59:46 [INFO] train episode 4598: reward = 157.00, steps = 157
22:59:46 [INFO] train episode 4599: reward = 128.00, steps = 128
22:59:46 [INFO] train episode 4600: reward = 127.00, steps = 127
22:59:46 [INFO] train episode 4601: reward = 146.00, steps = 146
22:59:46 [INFO] train episode 4602: reward = 115.00, steps = 115
22:59:46 [INFO] train episode 4603: reward = 173.00, steps = 173
22:59:46 [INFO] train episode 4604: reward = 157.00, steps = 157
22:59:46 [INFO] train episode 4605: reward = 158.00, steps = 158
22:59:46 [INFO] train episode 4606: reward = 200.00, steps = 200
22:59:47 [INFO] train episode 4607: reward = 148.00, steps = 148
22:59:47 [INFO] train episode 4608: reward = 179.00, steps = 179
22:59:47 [INFO] train episode 4609: reward = 143.00, steps = 143
22:59:47 [INFO] train episode 4610: reward = 138.00, steps = 138
22:59:47 [INFO] train episode 4611: reward = 200.00, steps = 200
22:59:47 [INFO] train episode 4612: reward = 188.00, steps = 188
22:59:47 [INFO] train episode 4613: reward = 122.00, steps = 122
22:59:47 [INFO] train episode 4614: reward = 149.00, steps = 149
22:59:47 [INFO] train episode 4615: reward = 149.00, steps = 149
22:59:47 [INFO] train episode 4616: reward = 175.00, steps = 175
22:59:47 [INFO] train episode 4617: reward = 165.00, steps = 165
22:59:47 [INFO] train episode 4618: reward = 200.00, steps = 200
22:59:47 [INFO] train episode 4619: reward = 175.00, steps = 175
22:59:47 [INFO] train episode 4620: reward = 130.00, steps = 130
22:59:47 [INFO] train episode 4621: reward = 200.00, steps = 200
22:59:47 [INFO] train episode 4622: reward = 137.00, steps = 137
22:59:47 [INFO] train episode 4623: reward = 148.00, steps = 148
22:59:48 [INFO] train episode 4624: reward = 199.00, steps = 199
22:59:48 [INFO] train episode 4625: reward = 97.00, steps = 97
22:59:48 [INFO] train episode 4626: reward = 171.00, steps = 171
22:59:48 [INFO] train episode 4627: reward = 186.00, steps = 186
22:59:48 [INFO] train episode 4628: reward = 161.00, steps = 161
22:59:48 [INFO] train episode 4629: reward = 162.00, steps = 162
22:59:48 [INFO] train episode 4630: reward = 150.00, steps = 150
22:59:48 [INFO] train episode 4631: reward = 185.00, steps = 185
22:59:48 [INFO] train episode 4632: reward = 120.00, steps = 120
22:59:48 [INFO] train episode 4633: reward = 141.00, steps = 141
22:59:48 [INFO] train episode 4634: reward = 151.00, steps = 151
22:59:48 [INFO] train episode 4635: reward = 173.00, steps = 173
22:59:48 [INFO] train episode 4636: reward = 123.00, steps = 123
22:59:48 [INFO] train episode 4637: reward = 138.00, steps = 138
22:59:48 [INFO] train episode 4638: reward = 146.00, steps = 146
22:59:48 [INFO] train episode 4639: reward = 200.00, steps = 200
22:59:48 [INFO] train episode 4640: reward = 144.00, steps = 144
22:59:48 [INFO] train episode 4641: reward = 149.00, steps = 149
22:59:49 [INFO] train episode 4642: reward = 164.00, steps = 164
22:59:49 [INFO] train episode 4643: reward = 200.00, steps = 200
22:59:49 [INFO] train episode 4644: reward = 198.00, steps = 198
22:59:49 [INFO] train episode 4645: reward = 162.00, steps = 162
22:59:49 [INFO] train episode 4646: reward = 119.00, steps = 119
22:59:49 [INFO] train episode 4647: reward = 153.00, steps = 153
22:59:49 [INFO] train episode 4648: reward = 168.00, steps = 168
22:59:49 [INFO] train episode 4649: reward = 139.00, steps = 139
22:59:49 [INFO] train episode 4650: reward = 183.00, steps = 183
22:59:49 [INFO] train episode 4651: reward = 200.00, steps = 200
22:59:49 [INFO] train episode 4652: reward = 134.00, steps = 134
22:59:49 [INFO] train episode 4653: reward = 200.00, steps = 200
22:59:49 [INFO] train episode 4654: reward = 177.00, steps = 177
22:59:49 [INFO] train episode 4655: reward = 149.00, steps = 149
22:59:49 [INFO] train episode 4656: reward = 200.00, steps = 200
22:59:49 [INFO] train episode 4657: reward = 130.00, steps = 130
22:59:49 [INFO] train episode 4658: reward = 166.00, steps = 166
22:59:50 [INFO] train episode 4659: reward = 200.00, steps = 200
22:59:50 [INFO] train episode 4660: reward = 153.00, steps = 153
22:59:50 [INFO] train episode 4661: reward = 200.00, steps = 200
22:59:50 [INFO] train episode 4662: reward = 153.00, steps = 153
22:59:50 [INFO] train episode 4663: reward = 175.00, steps = 175
22:59:50 [INFO] train episode 4664: reward = 157.00, steps = 157
22:59:50 [INFO] train episode 4665: reward = 200.00, steps = 200
22:59:50 [INFO] train episode 4666: reward = 129.00, steps = 129
22:59:50 [INFO] train episode 4667: reward = 158.00, steps = 158
22:59:50 [INFO] train episode 4668: reward = 200.00, steps = 200
22:59:50 [INFO] train episode 4669: reward = 166.00, steps = 166
22:59:50 [INFO] train episode 4670: reward = 194.00, steps = 194
22:59:50 [INFO] train episode 4671: reward = 188.00, steps = 188
22:59:50 [INFO] train episode 4672: reward = 200.00, steps = 200
22:59:50 [INFO] train episode 4673: reward = 189.00, steps = 189
22:59:51 [INFO] train episode 4674: reward = 180.00, steps = 180
22:59:51 [INFO] train episode 4675: reward = 200.00, steps = 200
22:59:51 [INFO] train episode 4676: reward = 159.00, steps = 159
22:59:51 [INFO] train episode 4677: reward = 172.00, steps = 172
22:59:51 [INFO] train episode 4678: reward = 200.00, steps = 200
22:59:51 [INFO] train episode 4679: reward = 186.00, steps = 186
22:59:51 [INFO] train episode 4680: reward = 189.00, steps = 189
22:59:51 [INFO] train episode 4681: reward = 200.00, steps = 200
22:59:51 [INFO] train episode 4682: reward = 183.00, steps = 183
22:59:51 [INFO] train episode 4683: reward = 167.00, steps = 167
22:59:51 [INFO] train episode 4684: reward = 189.00, steps = 189
22:59:51 [INFO] train episode 4685: reward = 200.00, steps = 200
22:59:51 [INFO] train episode 4686: reward = 158.00, steps = 158
22:59:51 [INFO] train episode 4687: reward = 179.00, steps = 179
22:59:51 [INFO] train episode 4688: reward = 171.00, steps = 171
22:59:52 [INFO] train episode 4689: reward = 181.00, steps = 181
22:59:52 [INFO] train episode 4690: reward = 150.00, steps = 150
22:59:52 [INFO] train episode 4691: reward = 174.00, steps = 174
22:59:52 [INFO] train episode 4692: reward = 178.00, steps = 178
22:59:52 [INFO] train episode 4693: reward = 200.00, steps = 200
22:59:52 [INFO] train episode 4694: reward = 200.00, steps = 200
22:59:52 [INFO] train episode 4695: reward = 169.00, steps = 169
22:59:52 [INFO] train episode 4696: reward = 200.00, steps = 200
22:59:52 [INFO] train episode 4697: reward = 200.00, steps = 200
22:59:52 [INFO] train episode 4698: reward = 200.00, steps = 200
22:59:52 [INFO] train episode 4699: reward = 200.00, steps = 200
22:59:52 [INFO] train episode 4700: reward = 200.00, steps = 200
22:59:52 [INFO] train episode 4701: reward = 189.00, steps = 189
22:59:52 [INFO] train episode 4702: reward = 192.00, steps = 192
22:59:52 [INFO] train episode 4703: reward = 176.00, steps = 176
22:59:52 [INFO] train episode 4704: reward = 178.00, steps = 178
22:59:53 [INFO] train episode 4705: reward = 149.00, steps = 149
22:59:53 [INFO] train episode 4706: reward = 157.00, steps = 157
22:59:53 [INFO] train episode 4707: reward = 160.00, steps = 160
22:59:53 [INFO] train episode 4708: reward = 170.00, steps = 170
22:59:53 [INFO] train episode 4709: reward = 157.00, steps = 157
22:59:53 [INFO] train episode 4710: reward = 200.00, steps = 200
22:59:53 [INFO] train episode 4711: reward = 130.00, steps = 130
22:59:53 [INFO] train episode 4712: reward = 141.00, steps = 141
22:59:53 [INFO] train episode 4713: reward = 200.00, steps = 200
22:59:53 [INFO] train episode 4714: reward = 197.00, steps = 197
22:59:53 [INFO] train episode 4715: reward = 175.00, steps = 175
22:59:53 [INFO] train episode 4716: reward = 200.00, steps = 200
22:59:53 [INFO] train episode 4717: reward = 170.00, steps = 170
22:59:53 [INFO] train episode 4718: reward = 200.00, steps = 200
22:59:53 [INFO] train episode 4719: reward = 183.00, steps = 183
22:59:53 [INFO] train episode 4720: reward = 200.00, steps = 200
22:59:53 [INFO] train episode 4721: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4722: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4723: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4724: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4725: reward = 193.00, steps = 193
22:59:54 [INFO] train episode 4726: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4727: reward = 191.00, steps = 191
22:59:54 [INFO] train episode 4728: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4729: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4730: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4731: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4732: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4733: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4734: reward = 197.00, steps = 197
22:59:54 [INFO] train episode 4735: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4736: reward = 200.00, steps = 200
22:59:54 [INFO] train episode 4737: reward = 200.00, steps = 200
22:59:55 [INFO] train episode 4738: reward = 200.00, steps = 200
22:59:55 [INFO] train episode 4739: reward = 200.00, steps = 200
22:59:55 [INFO] ==== test ====
22:59:55 [INFO] test episode 0: reward = 200.00, steps = 200
22:59:55 [INFO] test episode 1: reward = 200.00, steps = 200
22:59:55 [INFO] test episode 2: reward = 200.00, steps = 200
22:59:55 [INFO] test episode 3: reward = 200.00, steps = 200
22:59:55 [INFO] test episode 4: reward = 200.00, steps = 200
22:59:55 [INFO] test episode 5: reward = 199.00, steps = 199
22:59:55 [INFO] test episode 6: reward = 200.00, steps = 200
22:59:55 [INFO] test episode 7: reward = 190.00, steps = 190
22:59:55 [INFO] test episode 8: reward = 200.00, steps = 200
22:59:55 [INFO] test episode 9: reward = 193.00, steps = 193
22:59:55 [INFO] test episode 10: reward = 166.00, steps = 166
22:59:55 [INFO] test episode 11: reward = 200.00, steps = 200
22:59:55 [INFO] test episode 12: reward = 189.00, steps = 189
22:59:55 [INFO] test episode 13: reward = 200.00, steps = 200
22:59:55 [INFO] test episode 14: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 15: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 16: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 17: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 18: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 19: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 20: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 21: reward = 185.00, steps = 185
22:59:56 [INFO] test episode 22: reward = 196.00, steps = 196
22:59:56 [INFO] test episode 23: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 24: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 25: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 26: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 27: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 28: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 29: reward = 200.00, steps = 200
22:59:56 [INFO] test episode 30: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 31: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 32: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 33: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 34: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 35: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 36: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 37: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 38: reward = 179.00, steps = 179
22:59:57 [INFO] test episode 39: reward = 184.00, steps = 184
22:59:57 [INFO] test episode 40: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 41: reward = 177.00, steps = 177
22:59:57 [INFO] test episode 42: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 43: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 44: reward = 179.00, steps = 179
22:59:57 [INFO] test episode 45: reward = 173.00, steps = 173
22:59:57 [INFO] test episode 46: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 47: reward = 200.00, steps = 200
22:59:57 [INFO] test episode 48: reward = 186.00, steps = 186
22:59:58 [INFO] test episode 49: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 50: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 51: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 52: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 53: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 54: reward = 177.00, steps = 177
22:59:58 [INFO] test episode 55: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 56: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 57: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 58: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 59: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 60: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 61: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 62: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 63: reward = 184.00, steps = 184
22:59:58 [INFO] test episode 64: reward = 200.00, steps = 200
22:59:58 [INFO] test episode 65: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 66: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 67: reward = 192.00, steps = 192
22:59:59 [INFO] test episode 68: reward = 189.00, steps = 189
22:59:59 [INFO] test episode 69: reward = 199.00, steps = 199
22:59:59 [INFO] test episode 70: reward = 165.00, steps = 165
22:59:59 [INFO] test episode 71: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 72: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 73: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 74: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 75: reward = 176.00, steps = 176
22:59:59 [INFO] test episode 76: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 77: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 78: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 79: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 80: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 81: reward = 200.00, steps = 200
22:59:59 [INFO] test episode 82: reward = 195.00, steps = 195
23:00:00 [INFO] test episode 83: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 84: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 85: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 86: reward = 198.00, steps = 198
23:00:00 [INFO] test episode 87: reward = 188.00, steps = 188
23:00:00 [INFO] test episode 88: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 89: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 90: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 91: reward = 179.00, steps = 179
23:00:00 [INFO] test episode 92: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 93: reward = 198.00, steps = 198
23:00:00 [INFO] test episode 94: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 95: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 96: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 97: reward = 200.00, steps = 200
23:00:00 [INFO] test episode 98: reward = 200.00, steps = 200
23:00:01 [INFO] test episode 99: reward = 200.00, steps = 200
23:00:01 [INFO] average episode reward = 196.36 ± 7.95
In [5]:
env.close()