Use VPG with Baseline to Play CartPole-v0

PyTorch version

%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
torch.manual_seed(0)
import torch.nn as nn
import torch.optim as optim
import torch.distributions as distributions

logging.basicConfig(level=logging.INFO,
        format='%(asctime)s [%(levelname)s] %(message)s',
        stream=sys.stdout, datefmt='%H:%M:%S')

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])

00:00:41 [INFO] env: <CartPoleEnv<CartPole-v0>>
00:00:41 [INFO] action_space: Discrete(2)
00:00:41 [INFO] observation_space: Box(-3.4028234663852886e+38, 3.4028234663852886e+38, (4,), float32)
00:00:41 [INFO] reward_range: (-inf, inf)
00:00:41 [INFO] metadata: {'render.modes': ['human', 'rgb_array'], 'video.frames_per_second': 50}
00:00:41 [INFO] _max_episode_steps: 200
00:00:41 [INFO] _elapsed_steps: None
00:00:41 [INFO] id: CartPole-v0
00:00:41 [INFO] entry_point: gym.envs.classic_control:CartPoleEnv
00:00:41 [INFO] reward_threshold: 195.0
00:00:41 [INFO] nondeterministic: False
00:00:41 [INFO] max_episode_steps: 200
00:00:41 [INFO] _kwargs: {}
00:00:41 [INFO] _env_name: CartPole

class VPGwBaselineAgent:
    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.policy_optimizer = optim.Adam(self.policy_net.parameters(), lr=0.005)
        self.baseline_net = self.build_net(
                input_size=env.observation_space.shape[0],
                hidden_sizes=[])
        self.baseline_optimizer = optim.Adam(self.policy_net.parameters(), lr=0.01)
        self.baseline_loss = nn.MSELoss()

    def build_net(self, input_size, hidden_sizes, output_size=1,
            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):
        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]
        if self.mode == 'train':
            self.trajectory += [observation, reward, terminated, action]
        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)

        # update baseline
        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)
        return_tensor = discounted_return_tensor / discount_tensor
        pred_tensor = self.baseline_net(state_tensor)
        psi_tensor = (discounted_return_tensor - discount_tensor *
                pred_tensor).detach()
        baseline_loss_tensor = self.baseline_loss(pred_tensor,
                return_tensor.unsqueeze(1))
        self.baseline_optimizer.zero_grad()
        baseline_loss_tensor.backward()
        self.baseline_optimizer.step()

        # update policy
        all_pi_tensor = self.policy_net(state_tensor)
        pi_tensor = torch.gather(all_pi_tensor, 1,
                action_tensor.unsqueeze(1)).squeeze(1)
        log_pi_tensor = torch.log(torch.clamp(pi_tensor, 1e-6, 1.))
        policy_loss_tensor = -(psi_tensor * log_pi_tensor).mean()
        self.policy_optimizer.zero_grad()
        policy_loss_tensor.backward()
        self.policy_optimizer.step()


agent = VPGwBaselineAgent(env)

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():
    episode_reward, elapsed_steps = play_episode(env, agent, seed=episode,
            mode='train')
    episode_rewards.append(episode_reward)
    logging.info('train episode %d: reward = %.2f, steps = %d',
            episode, episode_reward, elapsed_steps)
    if np.mean(episode_rewards[-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))

00:00:41 [INFO] ==== train ====
00:00:42 [INFO] train episode 0: reward = 21.00, steps = 21
00:00:42 [INFO] train episode 1: reward = 45.00, steps = 45
00:00:42 [INFO] train episode 2: reward = 17.00, steps = 17
00:00:42 [INFO] train episode 3: reward = 38.00, steps = 38
00:00:42 [INFO] train episode 4: reward = 28.00, steps = 28
00:00:42 [INFO] train episode 5: reward = 101.00, steps = 101
00:00:42 [INFO] train episode 6: reward = 10.00, steps = 10
00:00:42 [INFO] train episode 7: reward = 63.00, steps = 63
00:00:42 [INFO] train episode 8: reward = 39.00, steps = 39
00:00:42 [INFO] train episode 9: reward = 30.00, steps = 30
00:00:42 [INFO] train episode 10: reward = 77.00, steps = 77
00:00:42 [INFO] train episode 11: reward = 21.00, steps = 21
00:00:42 [INFO] train episode 12: reward = 17.00, steps = 17
00:00:42 [INFO] train episode 13: reward = 25.00, steps = 25
00:00:42 [INFO] train episode 14: reward = 40.00, steps = 40
00:00:42 [INFO] train episode 15: reward = 19.00, steps = 19
00:00:42 [INFO] train episode 16: reward = 23.00, steps = 23
00:00:42 [INFO] train episode 17: reward = 24.00, steps = 24
00:00:42 [INFO] train episode 18: reward = 29.00, steps = 29
00:00:42 [INFO] train episode 19: reward = 30.00, steps = 30
00:00:42 [INFO] train episode 20: reward = 26.00, steps = 26
00:00:42 [INFO] train episode 21: reward = 38.00, steps = 38
00:00:42 [INFO] train episode 22: reward = 14.00, steps = 14
00:00:42 [INFO] train episode 23: reward = 21.00, steps = 21
00:00:42 [INFO] train episode 24: reward = 24.00, steps = 24
00:00:42 [INFO] train episode 25: reward = 20.00, steps = 20
00:00:42 [INFO] train episode 26: reward = 52.00, steps = 52
00:00:42 [INFO] train episode 27: reward = 46.00, steps = 46
00:00:42 [INFO] train episode 28: reward = 22.00, steps = 22
00:00:42 [INFO] train episode 29: reward = 44.00, steps = 44
00:00:42 [INFO] train episode 30: reward = 47.00, steps = 47
00:00:42 [INFO] train episode 31: reward = 46.00, steps = 46
00:00:42 [INFO] train episode 32: reward = 20.00, steps = 20
00:00:42 [INFO] train episode 33: reward = 100.00, steps = 100
00:00:42 [INFO] train episode 34: reward = 12.00, steps = 12
00:00:42 [INFO] train episode 35: reward = 18.00, steps = 18
00:00:42 [INFO] train episode 36: reward = 76.00, steps = 76
00:00:42 [INFO] train episode 37: reward = 49.00, steps = 49
00:00:42 [INFO] train episode 38: reward = 14.00, steps = 14
00:00:42 [INFO] train episode 39: reward = 38.00, steps = 38
00:00:42 [INFO] train episode 40: reward = 81.00, steps = 81
00:00:42 [INFO] train episode 41: reward = 51.00, steps = 51
00:00:42 [INFO] train episode 42: reward = 23.00, steps = 23
00:00:42 [INFO] train episode 43: reward = 19.00, steps = 19
00:00:42 [INFO] train episode 44: reward = 23.00, steps = 23
00:00:42 [INFO] train episode 45: reward = 35.00, steps = 35
00:00:42 [INFO] train episode 46: reward = 26.00, steps = 26
00:00:42 [INFO] train episode 47: reward = 50.00, steps = 50
00:00:42 [INFO] train episode 48: reward = 46.00, steps = 46
00:00:42 [INFO] train episode 49: reward = 26.00, steps = 26
00:00:42 [INFO] train episode 50: reward = 25.00, steps = 25
00:00:42 [INFO] train episode 51: reward = 14.00, steps = 14
00:00:42 [INFO] train episode 52: reward = 16.00, steps = 16
00:00:42 [INFO] train episode 53: reward = 14.00, steps = 14
00:00:42 [INFO] train episode 54: reward = 42.00, steps = 42
00:00:42 [INFO] train episode 55: reward = 44.00, steps = 44
00:00:42 [INFO] train episode 56: reward = 27.00, steps = 27
00:00:42 [INFO] train episode 57: reward = 108.00, steps = 108
00:00:42 [INFO] train episode 58: reward = 18.00, steps = 18
00:00:42 [INFO] train episode 59: reward = 69.00, steps = 69
00:00:43 [INFO] train episode 60: reward = 24.00, steps = 24
00:00:43 [INFO] train episode 61: reward = 38.00, steps = 38
00:00:43 [INFO] train episode 62: reward = 34.00, steps = 34
00:00:43 [INFO] train episode 63: reward = 38.00, steps = 38
00:00:43 [INFO] train episode 64: reward = 15.00, steps = 15
00:00:43 [INFO] train episode 65: reward = 33.00, steps = 33
00:00:43 [INFO] train episode 66: reward = 20.00, steps = 20
00:00:43 [INFO] train episode 67: reward = 33.00, steps = 33
00:00:43 [INFO] train episode 68: reward = 84.00, steps = 84
00:00:43 [INFO] train episode 69: reward = 21.00, steps = 21
00:00:43 [INFO] train episode 70: reward = 39.00, steps = 39
00:00:43 [INFO] train episode 71: reward = 28.00, steps = 28
00:00:43 [INFO] train episode 72: reward = 59.00, steps = 59
00:00:43 [INFO] train episode 73: reward = 23.00, steps = 23
00:00:43 [INFO] train episode 74: reward = 19.00, steps = 19
00:00:43 [INFO] train episode 75: reward = 100.00, steps = 100
00:00:43 [INFO] train episode 76: reward = 23.00, steps = 23
00:00:43 [INFO] train episode 77: reward = 58.00, steps = 58
00:00:43 [INFO] train episode 78: reward = 34.00, steps = 34
00:00:43 [INFO] train episode 79: reward = 27.00, steps = 27
00:00:43 [INFO] train episode 80: reward = 71.00, steps = 71
00:00:43 [INFO] train episode 81: reward = 34.00, steps = 34
00:00:43 [INFO] train episode 82: reward = 66.00, steps = 66
00:00:43 [INFO] train episode 83: reward = 15.00, steps = 15
00:00:43 [INFO] train episode 84: reward = 15.00, steps = 15
00:00:43 [INFO] train episode 85: reward = 49.00, steps = 49
00:00:43 [INFO] train episode 86: reward = 32.00, steps = 32
00:00:43 [INFO] train episode 87: reward = 27.00, steps = 27
00:00:43 [INFO] train episode 88: reward = 26.00, steps = 26
00:00:43 [INFO] train episode 89: reward = 42.00, steps = 42
00:00:43 [INFO] train episode 90: reward = 33.00, steps = 33
00:00:43 [INFO] train episode 91: reward = 38.00, steps = 38
00:00:43 [INFO] train episode 92: reward = 23.00, steps = 23
00:00:43 [INFO] train episode 93: reward = 63.00, steps = 63
00:00:43 [INFO] train episode 94: reward = 38.00, steps = 38
00:00:43 [INFO] train episode 95: reward = 43.00, steps = 43
00:00:43 [INFO] train episode 96: reward = 41.00, steps = 41
00:00:43 [INFO] train episode 97: reward = 49.00, steps = 49
00:00:43 [INFO] train episode 98: reward = 20.00, steps = 20
00:00:43 [INFO] train episode 99: reward = 31.00, steps = 31
00:00:43 [INFO] train episode 100: reward = 19.00, steps = 19
00:00:43 [INFO] train episode 101: reward = 21.00, steps = 21
00:00:43 [INFO] train episode 102: reward = 37.00, steps = 37
00:00:43 [INFO] train episode 103: reward = 53.00, steps = 53
00:00:43 [INFO] train episode 104: reward = 112.00, steps = 112
00:00:43 [INFO] train episode 105: reward = 40.00, steps = 40
00:00:43 [INFO] train episode 106: reward = 30.00, steps = 30
00:00:43 [INFO] train episode 107: reward = 43.00, steps = 43
00:00:43 [INFO] train episode 108: reward = 30.00, steps = 30
00:00:43 [INFO] train episode 109: reward = 55.00, steps = 55
00:00:43 [INFO] train episode 110: reward = 96.00, steps = 96
00:00:43 [INFO] train episode 111: reward = 24.00, steps = 24
00:00:43 [INFO] train episode 112: reward = 47.00, steps = 47
00:00:43 [INFO] train episode 113: reward = 32.00, steps = 32
00:00:43 [INFO] train episode 114: reward = 26.00, steps = 26
00:00:43 [INFO] train episode 115: reward = 11.00, steps = 11
00:00:43 [INFO] train episode 116: reward = 21.00, steps = 21
00:00:43 [INFO] train episode 117: reward = 26.00, steps = 26
00:00:43 [INFO] train episode 118: reward = 40.00, steps = 40
00:00:43 [INFO] train episode 119: reward = 32.00, steps = 32
00:00:43 [INFO] train episode 120: reward = 20.00, steps = 20
00:00:44 [INFO] train episode 121: reward = 158.00, steps = 158
00:00:44 [INFO] train episode 122: reward = 34.00, steps = 34
00:00:44 [INFO] train episode 123: reward = 58.00, steps = 58
00:00:44 [INFO] train episode 124: reward = 39.00, steps = 39
00:00:44 [INFO] train episode 125: reward = 10.00, steps = 10
00:00:44 [INFO] train episode 126: reward = 44.00, steps = 44
00:00:44 [INFO] train episode 127: reward = 26.00, steps = 26
00:00:44 [INFO] train episode 128: reward = 28.00, steps = 28
00:00:44 [INFO] train episode 129: reward = 45.00, steps = 45
00:00:44 [INFO] train episode 130: reward = 50.00, steps = 50
00:00:44 [INFO] train episode 131: reward = 98.00, steps = 98
00:00:44 [INFO] train episode 132: reward = 42.00, steps = 42
00:00:44 [INFO] train episode 133: reward = 14.00, steps = 14
00:00:44 [INFO] train episode 134: reward = 33.00, steps = 33
00:00:44 [INFO] train episode 135: reward = 77.00, steps = 77
00:00:44 [INFO] train episode 136: reward = 22.00, steps = 22
00:00:44 [INFO] train episode 137: reward = 39.00, steps = 39
00:00:44 [INFO] train episode 138: reward = 36.00, steps = 36
00:00:44 [INFO] train episode 139: reward = 21.00, steps = 21
00:00:44 [INFO] train episode 140: reward = 53.00, steps = 53
00:00:44 [INFO] train episode 141: reward = 23.00, steps = 23
00:00:44 [INFO] train episode 142: reward = 53.00, steps = 53
00:00:44 [INFO] train episode 143: reward = 34.00, steps = 34
00:00:44 [INFO] train episode 144: reward = 14.00, steps = 14
00:00:44 [INFO] train episode 145: reward = 53.00, steps = 53
00:00:44 [INFO] train episode 146: reward = 72.00, steps = 72
00:00:44 [INFO] train episode 147: reward = 63.00, steps = 63
00:00:44 [INFO] train episode 148: reward = 29.00, steps = 29
00:00:44 [INFO] train episode 149: reward = 48.00, steps = 48
00:00:44 [INFO] train episode 150: reward = 78.00, steps = 78
00:00:44 [INFO] train episode 151: reward = 49.00, steps = 49
00:00:44 [INFO] train episode 152: reward = 66.00, steps = 66
00:00:44 [INFO] train episode 153: reward = 68.00, steps = 68
00:00:44 [INFO] train episode 154: reward = 41.00, steps = 41
00:00:44 [INFO] train episode 155: reward = 43.00, steps = 43
00:00:44 [INFO] train episode 156: reward = 69.00, steps = 69
00:00:44 [INFO] train episode 157: reward = 74.00, steps = 74
00:00:44 [INFO] train episode 158: reward = 48.00, steps = 48
00:00:44 [INFO] train episode 159: reward = 34.00, steps = 34
00:00:44 [INFO] train episode 160: reward = 57.00, steps = 57
00:00:44 [INFO] train episode 161: reward = 12.00, steps = 12
00:00:44 [INFO] train episode 162: reward = 22.00, steps = 22
00:00:44 [INFO] train episode 163: reward = 88.00, steps = 88
00:00:44 [INFO] train episode 164: reward = 24.00, steps = 24
00:00:44 [INFO] train episode 165: reward = 86.00, steps = 86
00:00:44 [INFO] train episode 166: reward = 22.00, steps = 22
00:00:44 [INFO] train episode 167: reward = 61.00, steps = 61
00:00:44 [INFO] train episode 168: reward = 45.00, steps = 45
00:00:44 [INFO] train episode 169: reward = 17.00, steps = 17
00:00:44 [INFO] train episode 170: reward = 19.00, steps = 19
00:00:44 [INFO] train episode 171: reward = 13.00, steps = 13
00:00:44 [INFO] train episode 172: reward = 33.00, steps = 33
00:00:44 [INFO] train episode 173: reward = 130.00, steps = 130
00:00:44 [INFO] train episode 174: reward = 40.00, steps = 40
00:00:44 [INFO] train episode 175: reward = 70.00, steps = 70
00:00:45 [INFO] train episode 176: reward = 20.00, steps = 20
00:00:45 [INFO] train episode 177: reward = 42.00, steps = 42
00:00:45 [INFO] train episode 178: reward = 59.00, steps = 59
00:00:45 [INFO] train episode 179: reward = 70.00, steps = 70
00:00:45 [INFO] train episode 180: reward = 78.00, steps = 78
00:00:45 [INFO] train episode 181: reward = 32.00, steps = 32
00:00:45 [INFO] train episode 182: reward = 17.00, steps = 17
00:00:45 [INFO] train episode 183: reward = 55.00, steps = 55
00:00:45 [INFO] train episode 184: reward = 30.00, steps = 30
00:00:45 [INFO] train episode 185: reward = 39.00, steps = 39
00:00:45 [INFO] train episode 186: reward = 53.00, steps = 53
00:00:45 [INFO] train episode 187: reward = 33.00, steps = 33
00:00:45 [INFO] train episode 188: reward = 17.00, steps = 17
00:00:45 [INFO] train episode 189: reward = 81.00, steps = 81
00:00:45 [INFO] train episode 190: reward = 15.00, steps = 15
00:00:45 [INFO] train episode 191: reward = 42.00, steps = 42
00:00:45 [INFO] train episode 192: reward = 56.00, steps = 56
00:00:45 [INFO] train episode 193: reward = 64.00, steps = 64
00:00:45 [INFO] train episode 194: reward = 83.00, steps = 83
00:00:45 [INFO] train episode 195: reward = 15.00, steps = 15
00:00:45 [INFO] train episode 196: reward = 25.00, steps = 25
00:00:45 [INFO] train episode 197: reward = 21.00, steps = 21
00:00:45 [INFO] train episode 198: reward = 18.00, steps = 18
00:00:45 [INFO] train episode 199: reward = 26.00, steps = 26
00:00:45 [INFO] train episode 200: reward = 28.00, steps = 28
00:00:45 [INFO] train episode 201: reward = 52.00, steps = 52
00:00:45 [INFO] train episode 202: reward = 29.00, steps = 29
00:00:45 [INFO] train episode 203: reward = 19.00, steps = 19
00:00:45 [INFO] train episode 204: reward = 19.00, steps = 19
00:00:45 [INFO] train episode 205: reward = 10.00, steps = 10
00:00:45 [INFO] train episode 206: reward = 57.00, steps = 57
00:00:45 [INFO] train episode 207: reward = 37.00, steps = 37
00:00:45 [INFO] train episode 208: reward = 34.00, steps = 34
00:00:45 [INFO] train episode 209: reward = 93.00, steps = 93
00:00:45 [INFO] train episode 210: reward = 49.00, steps = 49
00:00:45 [INFO] train episode 211: reward = 36.00, steps = 36
00:00:45 [INFO] train episode 212: reward = 19.00, steps = 19
00:00:45 [INFO] train episode 213: reward = 31.00, steps = 31
00:00:45 [INFO] train episode 214: reward = 23.00, steps = 23
00:00:45 [INFO] train episode 215: reward = 21.00, steps = 21
00:00:45 [INFO] train episode 216: reward = 80.00, steps = 80
00:00:45 [INFO] train episode 217: reward = 79.00, steps = 79
00:00:45 [INFO] train episode 218: reward = 45.00, steps = 45
00:00:45 [INFO] train episode 219: reward = 32.00, steps = 32
00:00:45 [INFO] train episode 220: reward = 18.00, steps = 18
00:00:45 [INFO] train episode 221: reward = 71.00, steps = 71
00:00:45 [INFO] train episode 222: reward = 29.00, steps = 29
00:00:45 [INFO] train episode 223: reward = 58.00, steps = 58
00:00:45 [INFO] train episode 224: reward = 16.00, steps = 16
00:00:45 [INFO] train episode 225: reward = 82.00, steps = 82
00:00:45 [INFO] train episode 226: reward = 41.00, steps = 41
00:00:45 [INFO] train episode 227: reward = 38.00, steps = 38
00:00:45 [INFO] train episode 228: reward = 93.00, steps = 93
00:00:45 [INFO] train episode 229: reward = 33.00, steps = 33
00:00:45 [INFO] train episode 230: reward = 21.00, steps = 21
00:00:45 [INFO] train episode 231: reward = 45.00, steps = 45
00:00:45 [INFO] train episode 232: reward = 37.00, steps = 37
00:00:45 [INFO] train episode 233: reward = 29.00, steps = 29
00:00:45 [INFO] train episode 234: reward = 74.00, steps = 74
00:00:46 [INFO] train episode 235: reward = 81.00, steps = 81
00:00:46 [INFO] train episode 236: reward = 49.00, steps = 49
00:00:46 [INFO] train episode 237: reward = 60.00, steps = 60
00:00:46 [INFO] train episode 238: reward = 56.00, steps = 56
00:00:46 [INFO] train episode 239: reward = 28.00, steps = 28
00:00:46 [INFO] train episode 240: reward = 19.00, steps = 19
00:00:46 [INFO] train episode 241: reward = 41.00, steps = 41
00:00:46 [INFO] train episode 242: reward = 81.00, steps = 81
00:00:46 [INFO] train episode 243: reward = 72.00, steps = 72
00:00:46 [INFO] train episode 244: reward = 79.00, steps = 79
00:00:46 [INFO] train episode 245: reward = 35.00, steps = 35
00:00:46 [INFO] train episode 246: reward = 38.00, steps = 38
00:00:46 [INFO] train episode 247: reward = 24.00, steps = 24
00:00:46 [INFO] train episode 248: reward = 29.00, steps = 29
00:00:46 [INFO] train episode 249: reward = 16.00, steps = 16
00:00:46 [INFO] train episode 250: reward = 47.00, steps = 47
00:00:46 [INFO] train episode 251: reward = 51.00, steps = 51
00:00:46 [INFO] train episode 252: reward = 17.00, steps = 17
00:00:46 [INFO] train episode 253: reward = 58.00, steps = 58
00:00:46 [INFO] train episode 254: reward = 30.00, steps = 30
00:00:46 [INFO] train episode 255: reward = 59.00, steps = 59
00:00:46 [INFO] train episode 256: reward = 24.00, steps = 24
00:00:46 [INFO] train episode 257: reward = 20.00, steps = 20
00:00:46 [INFO] train episode 258: reward = 132.00, steps = 132
00:00:46 [INFO] train episode 259: reward = 88.00, steps = 88
00:00:46 [INFO] train episode 260: reward = 33.00, steps = 33
00:00:46 [INFO] train episode 261: reward = 63.00, steps = 63
00:00:46 [INFO] train episode 262: reward = 20.00, steps = 20
00:00:46 [INFO] train episode 263: reward = 55.00, steps = 55
00:00:46 [INFO] train episode 264: reward = 48.00, steps = 48
00:00:46 [INFO] train episode 265: reward = 105.00, steps = 105
00:00:46 [INFO] train episode 266: reward = 73.00, steps = 73
00:00:46 [INFO] train episode 267: reward = 66.00, steps = 66
00:00:46 [INFO] train episode 268: reward = 60.00, steps = 60
00:00:46 [INFO] train episode 269: reward = 27.00, steps = 27
00:00:46 [INFO] train episode 270: reward = 71.00, steps = 71
00:00:46 [INFO] train episode 271: reward = 46.00, steps = 46
00:00:46 [INFO] train episode 272: reward = 21.00, steps = 21
00:00:46 [INFO] train episode 273: reward = 27.00, steps = 27
00:00:46 [INFO] train episode 274: reward = 69.00, steps = 69
00:00:46 [INFO] train episode 275: reward = 22.00, steps = 22
00:00:46 [INFO] train episode 276: reward = 35.00, steps = 35
00:00:46 [INFO] train episode 277: reward = 25.00, steps = 25
00:00:46 [INFO] train episode 278: reward = 97.00, steps = 97
00:00:46 [INFO] train episode 279: reward = 56.00, steps = 56
00:00:46 [INFO] train episode 280: reward = 118.00, steps = 118
00:00:46 [INFO] train episode 281: reward = 57.00, steps = 57
00:00:46 [INFO] train episode 282: reward = 68.00, steps = 68
00:00:46 [INFO] train episode 283: reward = 94.00, steps = 94
00:00:46 [INFO] train episode 284: reward = 40.00, steps = 40
00:00:46 [INFO] train episode 285: reward = 21.00, steps = 21
00:00:46 [INFO] train episode 286: reward = 46.00, steps = 46
00:00:47 [INFO] train episode 287: reward = 73.00, steps = 73
00:00:47 [INFO] train episode 288: reward = 25.00, steps = 25
00:00:47 [INFO] train episode 289: reward = 55.00, steps = 55
00:00:47 [INFO] train episode 290: reward = 34.00, steps = 34
00:00:47 [INFO] train episode 291: reward = 15.00, steps = 15
00:00:47 [INFO] train episode 292: reward = 28.00, steps = 28
00:00:47 [INFO] train episode 293: reward = 79.00, steps = 79
00:00:47 [INFO] train episode 294: reward = 57.00, steps = 57
00:00:47 [INFO] train episode 295: reward = 24.00, steps = 24
00:00:47 [INFO] train episode 296: reward = 49.00, steps = 49
00:00:47 [INFO] train episode 297: reward = 24.00, steps = 24
00:00:47 [INFO] train episode 298: reward = 128.00, steps = 128
00:00:47 [INFO] train episode 299: reward = 41.00, steps = 41
00:00:47 [INFO] train episode 300: reward = 45.00, steps = 45
00:00:47 [INFO] train episode 301: reward = 13.00, steps = 13
00:00:47 [INFO] train episode 302: reward = 73.00, steps = 73
00:00:47 [INFO] train episode 303: reward = 78.00, steps = 78
00:00:47 [INFO] train episode 304: reward = 24.00, steps = 24
00:00:47 [INFO] train episode 305: reward = 53.00, steps = 53
00:00:47 [INFO] train episode 306: reward = 50.00, steps = 50
00:00:47 [INFO] train episode 307: reward = 31.00, steps = 31
00:00:47 [INFO] train episode 308: reward = 24.00, steps = 24
00:00:47 [INFO] train episode 309: reward = 18.00, steps = 18
00:00:47 [INFO] train episode 310: reward = 47.00, steps = 47
00:00:47 [INFO] train episode 311: reward = 32.00, steps = 32
00:00:47 [INFO] train episode 312: reward = 31.00, steps = 31
00:00:47 [INFO] train episode 313: reward = 111.00, steps = 111
00:00:47 [INFO] train episode 314: reward = 45.00, steps = 45
00:00:47 [INFO] train episode 315: reward = 35.00, steps = 35
00:00:47 [INFO] train episode 316: reward = 73.00, steps = 73
00:00:47 [INFO] train episode 317: reward = 91.00, steps = 91
00:00:47 [INFO] train episode 318: reward = 46.00, steps = 46
00:00:47 [INFO] train episode 319: reward = 72.00, steps = 72
00:00:47 [INFO] train episode 320: reward = 44.00, steps = 44
00:00:47 [INFO] train episode 321: reward = 44.00, steps = 44
00:00:47 [INFO] train episode 322: reward = 22.00, steps = 22
00:00:47 [INFO] train episode 323: reward = 22.00, steps = 22
00:00:47 [INFO] train episode 324: reward = 77.00, steps = 77
00:00:47 [INFO] train episode 325: reward = 151.00, steps = 151
00:00:47 [INFO] train episode 326: reward = 99.00, steps = 99
00:00:47 [INFO] train episode 327: reward = 45.00, steps = 45
00:00:47 [INFO] train episode 328: reward = 47.00, steps = 47
00:00:47 [INFO] train episode 329: reward = 36.00, steps = 36
00:00:47 [INFO] train episode 330: reward = 81.00, steps = 81
00:00:47 [INFO] train episode 331: reward = 49.00, steps = 49
00:00:47 [INFO] train episode 332: reward = 47.00, steps = 47
00:00:47 [INFO] train episode 333: reward = 28.00, steps = 28
00:00:47 [INFO] train episode 334: reward = 34.00, steps = 34
00:00:47 [INFO] train episode 335: reward = 17.00, steps = 17
00:00:47 [INFO] train episode 336: reward = 31.00, steps = 31
00:00:47 [INFO] train episode 337: reward = 121.00, steps = 121
00:00:48 [INFO] train episode 338: reward = 61.00, steps = 61
00:00:48 [INFO] train episode 339: reward = 41.00, steps = 41
00:00:48 [INFO] train episode 340: reward = 26.00, steps = 26
00:00:48 [INFO] train episode 341: reward = 40.00, steps = 40
00:00:48 [INFO] train episode 342: reward = 41.00, steps = 41
00:00:48 [INFO] train episode 343: reward = 26.00, steps = 26
00:00:48 [INFO] train episode 344: reward = 138.00, steps = 138
00:00:48 [INFO] train episode 345: reward = 18.00, steps = 18
00:00:48 [INFO] train episode 346: reward = 69.00, steps = 69
00:00:48 [INFO] train episode 347: reward = 103.00, steps = 103
00:00:48 [INFO] train episode 348: reward = 49.00, steps = 49
00:00:48 [INFO] train episode 349: reward = 87.00, steps = 87
00:00:48 [INFO] train episode 350: reward = 18.00, steps = 18
00:00:48 [INFO] train episode 351: reward = 90.00, steps = 90
00:00:48 [INFO] train episode 352: reward = 41.00, steps = 41
00:00:48 [INFO] train episode 353: reward = 46.00, steps = 46
00:00:48 [INFO] train episode 354: reward = 52.00, steps = 52
00:00:48 [INFO] train episode 355: reward = 56.00, steps = 56
00:00:48 [INFO] train episode 356: reward = 74.00, steps = 74
00:00:48 [INFO] train episode 357: reward = 56.00, steps = 56
00:00:48 [INFO] train episode 358: reward = 67.00, steps = 67
00:00:48 [INFO] train episode 359: reward = 70.00, steps = 70
00:00:48 [INFO] train episode 360: reward = 48.00, steps = 48
00:00:48 [INFO] train episode 361: reward = 82.00, steps = 82
00:00:48 [INFO] train episode 362: reward = 200.00, steps = 200
00:00:48 [INFO] train episode 363: reward = 23.00, steps = 23
00:00:48 [INFO] train episode 364: reward = 115.00, steps = 115
00:00:48 [INFO] train episode 365: reward = 140.00, steps = 140
00:00:48 [INFO] train episode 366: reward = 67.00, steps = 67
00:00:48 [INFO] train episode 367: reward = 58.00, steps = 58
00:00:48 [INFO] train episode 368: reward = 89.00, steps = 89
00:00:48 [INFO] train episode 369: reward = 63.00, steps = 63
00:00:48 [INFO] train episode 370: reward = 93.00, steps = 93
00:00:48 [INFO] train episode 371: reward = 35.00, steps = 35
00:00:48 [INFO] train episode 372: reward = 23.00, steps = 23
00:00:48 [INFO] train episode 373: reward = 17.00, steps = 17
00:00:48 [INFO] train episode 374: reward = 103.00, steps = 103
00:00:48 [INFO] train episode 375: reward = 70.00, steps = 70
00:00:48 [INFO] train episode 376: reward = 28.00, steps = 28
00:00:48 [INFO] train episode 377: reward = 70.00, steps = 70
00:00:48 [INFO] train episode 378: reward = 22.00, steps = 22
00:00:48 [INFO] train episode 379: reward = 42.00, steps = 42
00:00:49 [INFO] train episode 380: reward = 200.00, steps = 200
00:00:49 [INFO] train episode 381: reward = 45.00, steps = 45
00:00:49 [INFO] train episode 382: reward = 53.00, steps = 53
00:00:49 [INFO] train episode 383: reward = 72.00, steps = 72
00:00:49 [INFO] train episode 384: reward = 41.00, steps = 41
00:00:49 [INFO] train episode 385: reward = 23.00, steps = 23
00:00:49 [INFO] train episode 386: reward = 60.00, steps = 60
00:00:49 [INFO] train episode 387: reward = 31.00, steps = 31
00:00:49 [INFO] train episode 388: reward = 74.00, steps = 74
00:00:49 [INFO] train episode 389: reward = 26.00, steps = 26
00:00:49 [INFO] train episode 390: reward = 32.00, steps = 32
00:00:49 [INFO] train episode 391: reward = 64.00, steps = 64
00:00:49 [INFO] train episode 392: reward = 68.00, steps = 68
00:00:49 [INFO] train episode 393: reward = 28.00, steps = 28
00:00:49 [INFO] train episode 394: reward = 63.00, steps = 63
00:00:49 [INFO] train episode 395: reward = 25.00, steps = 25
00:00:49 [INFO] train episode 396: reward = 60.00, steps = 60
00:00:49 [INFO] train episode 397: reward = 29.00, steps = 29
00:00:49 [INFO] train episode 398: reward = 51.00, steps = 51
00:00:49 [INFO] train episode 399: reward = 32.00, steps = 32
00:00:49 [INFO] train episode 400: reward = 115.00, steps = 115
00:00:49 [INFO] train episode 401: reward = 40.00, steps = 40
00:00:49 [INFO] train episode 402: reward = 37.00, steps = 37
00:00:49 [INFO] train episode 403: reward = 78.00, steps = 78
00:00:49 [INFO] train episode 404: reward = 77.00, steps = 77
00:00:49 [INFO] train episode 405: reward = 124.00, steps = 124
00:00:49 [INFO] train episode 406: reward = 53.00, steps = 53
00:00:49 [INFO] train episode 407: reward = 71.00, steps = 71
00:00:49 [INFO] train episode 408: reward = 13.00, steps = 13
00:00:49 [INFO] train episode 409: reward = 33.00, steps = 33
00:00:49 [INFO] train episode 410: reward = 55.00, steps = 55
00:00:49 [INFO] train episode 411: reward = 110.00, steps = 110
00:00:49 [INFO] train episode 412: reward = 146.00, steps = 146
00:00:49 [INFO] train episode 413: reward = 104.00, steps = 104
00:00:49 [INFO] train episode 414: reward = 18.00, steps = 18
00:00:49 [INFO] train episode 415: reward = 73.00, steps = 73
00:00:49 [INFO] train episode 416: reward = 79.00, steps = 79
00:00:49 [INFO] train episode 417: reward = 85.00, steps = 85
00:00:49 [INFO] train episode 418: reward = 48.00, steps = 48
00:00:49 [INFO] train episode 419: reward = 80.00, steps = 80
00:00:49 [INFO] train episode 420: reward = 32.00, steps = 32
00:00:49 [INFO] train episode 421: reward = 155.00, steps = 155
00:00:49 [INFO] train episode 422: reward = 54.00, steps = 54
00:00:49 [INFO] train episode 423: reward = 29.00, steps = 29
00:00:50 [INFO] train episode 424: reward = 79.00, steps = 79
00:00:50 [INFO] train episode 425: reward = 108.00, steps = 108
00:00:50 [INFO] train episode 426: reward = 58.00, steps = 58
00:00:50 [INFO] train episode 427: reward = 66.00, steps = 66
00:00:50 [INFO] train episode 428: reward = 90.00, steps = 90
00:00:50 [INFO] train episode 429: reward = 27.00, steps = 27
00:00:50 [INFO] train episode 430: reward = 42.00, steps = 42
00:00:50 [INFO] train episode 431: reward = 65.00, steps = 65
00:00:50 [INFO] train episode 432: reward = 30.00, steps = 30
00:00:50 [INFO] train episode 433: reward = 32.00, steps = 32
00:00:50 [INFO] train episode 434: reward = 88.00, steps = 88
00:00:50 [INFO] train episode 435: reward = 23.00, steps = 23
00:00:50 [INFO] train episode 436: reward = 31.00, steps = 31
00:00:50 [INFO] train episode 437: reward = 107.00, steps = 107
00:00:50 [INFO] train episode 438: reward = 32.00, steps = 32
00:00:50 [INFO] train episode 439: reward = 48.00, steps = 48
00:00:50 [INFO] train episode 440: reward = 21.00, steps = 21
00:00:50 [INFO] train episode 441: reward = 52.00, steps = 52
00:00:50 [INFO] train episode 442: reward = 93.00, steps = 93
00:00:50 [INFO] train episode 443: reward = 65.00, steps = 65
00:00:50 [INFO] train episode 444: reward = 115.00, steps = 115
00:00:50 [INFO] train episode 445: reward = 146.00, steps = 146
00:00:50 [INFO] train episode 446: reward = 104.00, steps = 104
00:00:50 [INFO] train episode 447: reward = 200.00, steps = 200
00:00:50 [INFO] train episode 448: reward = 119.00, steps = 119
00:00:50 [INFO] train episode 449: reward = 132.00, steps = 132
00:00:50 [INFO] train episode 450: reward = 135.00, steps = 135
00:00:50 [INFO] train episode 451: reward = 16.00, steps = 16
00:00:50 [INFO] train episode 452: reward = 14.00, steps = 14
00:00:50 [INFO] train episode 453: reward = 22.00, steps = 22
00:00:50 [INFO] train episode 454: reward = 162.00, steps = 162
00:00:50 [INFO] train episode 455: reward = 34.00, steps = 34
00:00:50 [INFO] train episode 456: reward = 92.00, steps = 92
00:00:50 [INFO] train episode 457: reward = 100.00, steps = 100
00:00:50 [INFO] train episode 458: reward = 26.00, steps = 26
00:00:51 [INFO] train episode 459: reward = 107.00, steps = 107
00:00:51 [INFO] train episode 460: reward = 28.00, steps = 28
00:00:51 [INFO] train episode 461: reward = 58.00, steps = 58
00:00:51 [INFO] train episode 462: reward = 32.00, steps = 32
00:00:51 [INFO] train episode 463: reward = 43.00, steps = 43
00:00:51 [INFO] train episode 464: reward = 49.00, steps = 49
00:00:51 [INFO] train episode 465: reward = 39.00, steps = 39
00:00:51 [INFO] train episode 466: reward = 20.00, steps = 20
00:00:51 [INFO] train episode 467: reward = 52.00, steps = 52
00:00:51 [INFO] train episode 468: reward = 61.00, steps = 61
00:00:51 [INFO] train episode 469: reward = 183.00, steps = 183
00:00:51 [INFO] train episode 470: reward = 93.00, steps = 93
00:00:51 [INFO] train episode 471: reward = 54.00, steps = 54
00:00:51 [INFO] train episode 472: reward = 78.00, steps = 78
00:00:51 [INFO] train episode 473: reward = 40.00, steps = 40
00:00:51 [INFO] train episode 474: reward = 91.00, steps = 91
00:00:51 [INFO] train episode 475: reward = 35.00, steps = 35
00:00:51 [INFO] train episode 476: reward = 29.00, steps = 29
00:00:51 [INFO] train episode 477: reward = 73.00, steps = 73
00:00:51 [INFO] train episode 478: reward = 151.00, steps = 151
00:00:51 [INFO] train episode 479: reward = 36.00, steps = 36
00:00:51 [INFO] train episode 480: reward = 41.00, steps = 41
00:00:51 [INFO] train episode 481: reward = 54.00, steps = 54
00:00:51 [INFO] train episode 482: reward = 22.00, steps = 22
00:00:51 [INFO] train episode 483: reward = 30.00, steps = 30
00:00:51 [INFO] train episode 484: reward = 17.00, steps = 17
00:00:51 [INFO] train episode 485: reward = 83.00, steps = 83
00:00:51 [INFO] train episode 486: reward = 36.00, steps = 36
00:00:51 [INFO] train episode 487: reward = 72.00, steps = 72
00:00:51 [INFO] train episode 488: reward = 50.00, steps = 50
00:00:51 [INFO] train episode 489: reward = 46.00, steps = 46
00:00:51 [INFO] train episode 490: reward = 30.00, steps = 30
00:00:51 [INFO] train episode 491: reward = 20.00, steps = 20
00:00:51 [INFO] train episode 492: reward = 96.00, steps = 96
00:00:51 [INFO] train episode 493: reward = 24.00, steps = 24
00:00:51 [INFO] train episode 494: reward = 31.00, steps = 31
00:00:51 [INFO] train episode 495: reward = 100.00, steps = 100
00:00:51 [INFO] train episode 496: reward = 40.00, steps = 40
00:00:51 [INFO] train episode 497: reward = 38.00, steps = 38
00:00:51 [INFO] train episode 498: reward = 122.00, steps = 122
00:00:51 [INFO] train episode 499: reward = 83.00, steps = 83
00:00:51 [INFO] train episode 500: reward = 78.00, steps = 78
00:00:52 [INFO] train episode 501: reward = 52.00, steps = 52
00:00:52 [INFO] train episode 502: reward = 55.00, steps = 55
00:00:52 [INFO] train episode 503: reward = 64.00, steps = 64
00:00:52 [INFO] train episode 504: reward = 30.00, steps = 30
00:00:52 [INFO] train episode 505: reward = 65.00, steps = 65
00:00:52 [INFO] train episode 506: reward = 146.00, steps = 146
00:00:52 [INFO] train episode 507: reward = 38.00, steps = 38
00:00:52 [INFO] train episode 508: reward = 34.00, steps = 34
00:00:52 [INFO] train episode 509: reward = 48.00, steps = 48
00:00:52 [INFO] train episode 510: reward = 44.00, steps = 44
00:00:52 [INFO] train episode 511: reward = 123.00, steps = 123
00:00:52 [INFO] train episode 512: reward = 26.00, steps = 26
00:00:52 [INFO] train episode 513: reward = 122.00, steps = 122
00:00:52 [INFO] train episode 514: reward = 139.00, steps = 139
00:00:52 [INFO] train episode 515: reward = 38.00, steps = 38
00:00:52 [INFO] train episode 516: reward = 83.00, steps = 83
00:00:52 [INFO] train episode 517: reward = 41.00, steps = 41
00:00:52 [INFO] train episode 518: reward = 141.00, steps = 141
00:00:52 [INFO] train episode 519: reward = 118.00, steps = 118
00:00:52 [INFO] train episode 520: reward = 40.00, steps = 40
00:00:52 [INFO] train episode 521: reward = 124.00, steps = 124
00:00:52 [INFO] train episode 522: reward = 38.00, steps = 38
00:00:52 [INFO] train episode 523: reward = 32.00, steps = 32
00:00:52 [INFO] train episode 524: reward = 97.00, steps = 97
00:00:52 [INFO] train episode 525: reward = 162.00, steps = 162
00:00:52 [INFO] train episode 526: reward = 200.00, steps = 200
00:00:52 [INFO] train episode 527: reward = 78.00, steps = 78
00:00:52 [INFO] train episode 528: reward = 24.00, steps = 24
00:00:52 [INFO] train episode 529: reward = 80.00, steps = 80
00:00:52 [INFO] train episode 530: reward = 103.00, steps = 103
00:00:52 [INFO] train episode 531: reward = 69.00, steps = 69
00:00:52 [INFO] train episode 532: reward = 55.00, steps = 55
00:00:52 [INFO] train episode 533: reward = 15.00, steps = 15
00:00:52 [INFO] train episode 534: reward = 132.00, steps = 132
00:00:53 [INFO] train episode 535: reward = 94.00, steps = 94
00:00:53 [INFO] train episode 536: reward = 21.00, steps = 21
00:00:53 [INFO] train episode 537: reward = 140.00, steps = 140
00:00:53 [INFO] train episode 538: reward = 24.00, steps = 24
00:00:53 [INFO] train episode 539: reward = 79.00, steps = 79
00:00:53 [INFO] train episode 540: reward = 25.00, steps = 25
00:00:53 [INFO] train episode 541: reward = 71.00, steps = 71
00:00:53 [INFO] train episode 542: reward = 50.00, steps = 50
00:00:53 [INFO] train episode 543: reward = 117.00, steps = 117
00:00:53 [INFO] train episode 544: reward = 128.00, steps = 128
00:00:53 [INFO] train episode 545: reward = 69.00, steps = 69
00:00:53 [INFO] train episode 546: reward = 126.00, steps = 126
00:00:53 [INFO] train episode 547: reward = 92.00, steps = 92
00:00:53 [INFO] train episode 548: reward = 42.00, steps = 42
00:00:53 [INFO] train episode 549: reward = 122.00, steps = 122
00:00:53 [INFO] train episode 550: reward = 49.00, steps = 49
00:00:53 [INFO] train episode 551: reward = 79.00, steps = 79
00:00:53 [INFO] train episode 552: reward = 135.00, steps = 135
00:00:53 [INFO] train episode 553: reward = 24.00, steps = 24
00:00:53 [INFO] train episode 554: reward = 125.00, steps = 125
00:00:53 [INFO] train episode 555: reward = 44.00, steps = 44
00:00:53 [INFO] train episode 556: reward = 110.00, steps = 110
00:00:53 [INFO] train episode 557: reward = 117.00, steps = 117
00:00:53 [INFO] train episode 558: reward = 72.00, steps = 72
00:00:53 [INFO] train episode 559: reward = 175.00, steps = 175
00:00:53 [INFO] train episode 560: reward = 64.00, steps = 64
00:00:53 [INFO] train episode 561: reward = 29.00, steps = 29
00:00:53 [INFO] train episode 562: reward = 140.00, steps = 140
00:00:53 [INFO] train episode 563: reward = 24.00, steps = 24
00:00:53 [INFO] train episode 564: reward = 106.00, steps = 106
00:00:53 [INFO] train episode 565: reward = 143.00, steps = 143
00:00:53 [INFO] train episode 566: reward = 19.00, steps = 19
00:00:53 [INFO] train episode 567: reward = 78.00, steps = 78
00:00:53 [INFO] train episode 568: reward = 21.00, steps = 21
00:00:53 [INFO] train episode 569: reward = 65.00, steps = 65
00:00:54 [INFO] train episode 570: reward = 24.00, steps = 24
00:00:54 [INFO] train episode 571: reward = 24.00, steps = 24
00:00:54 [INFO] train episode 572: reward = 75.00, steps = 75
00:00:54 [INFO] train episode 573: reward = 149.00, steps = 149
00:00:54 [INFO] train episode 574: reward = 47.00, steps = 47
00:00:54 [INFO] train episode 575: reward = 200.00, steps = 200
00:00:54 [INFO] train episode 576: reward = 200.00, steps = 200
00:00:54 [INFO] train episode 577: reward = 31.00, steps = 31
00:00:54 [INFO] train episode 578: reward = 97.00, steps = 97
00:00:54 [INFO] train episode 579: reward = 46.00, steps = 46
00:00:54 [INFO] train episode 580: reward = 110.00, steps = 110
00:00:54 [INFO] train episode 581: reward = 122.00, steps = 122
00:00:54 [INFO] train episode 582: reward = 182.00, steps = 182
00:00:54 [INFO] train episode 583: reward = 81.00, steps = 81
00:00:54 [INFO] train episode 584: reward = 47.00, steps = 47
00:00:54 [INFO] train episode 585: reward = 134.00, steps = 134
00:00:54 [INFO] train episode 586: reward = 52.00, steps = 52
00:00:54 [INFO] train episode 587: reward = 125.00, steps = 125
00:00:54 [INFO] train episode 588: reward = 103.00, steps = 103
00:00:54 [INFO] train episode 589: reward = 123.00, steps = 123
00:00:54 [INFO] train episode 590: reward = 36.00, steps = 36
00:00:54 [INFO] train episode 591: reward = 54.00, steps = 54
00:00:54 [INFO] train episode 592: reward = 132.00, steps = 132
00:00:54 [INFO] train episode 593: reward = 29.00, steps = 29
00:00:54 [INFO] train episode 594: reward = 102.00, steps = 102
00:00:54 [INFO] train episode 595: reward = 65.00, steps = 65
00:00:54 [INFO] train episode 596: reward = 147.00, steps = 147
00:00:55 [INFO] train episode 597: reward = 58.00, steps = 58
00:00:55 [INFO] train episode 598: reward = 55.00, steps = 55
00:00:55 [INFO] train episode 599: reward = 59.00, steps = 59
00:00:55 [INFO] train episode 600: reward = 200.00, steps = 200
00:00:55 [INFO] train episode 601: reward = 104.00, steps = 104
00:00:55 [INFO] train episode 602: reward = 172.00, steps = 172
00:00:55 [INFO] train episode 603: reward = 11.00, steps = 11
00:00:55 [INFO] train episode 604: reward = 113.00, steps = 113
00:00:55 [INFO] train episode 605: reward = 52.00, steps = 52
00:00:55 [INFO] train episode 606: reward = 190.00, steps = 190
00:00:55 [INFO] train episode 607: reward = 85.00, steps = 85
00:00:55 [INFO] train episode 608: reward = 91.00, steps = 91
00:00:55 [INFO] train episode 609: reward = 117.00, steps = 117
00:00:55 [INFO] train episode 610: reward = 21.00, steps = 21
00:00:55 [INFO] train episode 611: reward = 23.00, steps = 23
00:00:55 [INFO] train episode 612: reward = 40.00, steps = 40
00:00:55 [INFO] train episode 613: reward = 25.00, steps = 25
00:00:55 [INFO] train episode 614: reward = 117.00, steps = 117
00:00:55 [INFO] train episode 615: reward = 92.00, steps = 92
00:00:55 [INFO] train episode 616: reward = 90.00, steps = 90
00:00:55 [INFO] train episode 617: reward = 36.00, steps = 36
00:00:55 [INFO] train episode 618: reward = 107.00, steps = 107
00:00:55 [INFO] train episode 619: reward = 38.00, steps = 38
00:00:55 [INFO] train episode 620: reward = 183.00, steps = 183
00:00:55 [INFO] train episode 621: reward = 24.00, steps = 24
00:00:55 [INFO] train episode 622: reward = 79.00, steps = 79
00:00:55 [INFO] train episode 623: reward = 200.00, steps = 200
00:00:56 [INFO] train episode 624: reward = 108.00, steps = 108
00:00:56 [INFO] train episode 625: reward = 34.00, steps = 34
00:00:56 [INFO] train episode 626: reward = 80.00, steps = 80
00:00:56 [INFO] train episode 627: reward = 42.00, steps = 42
00:00:56 [INFO] train episode 628: reward = 78.00, steps = 78
00:00:56 [INFO] train episode 629: reward = 58.00, steps = 58
00:00:56 [INFO] train episode 630: reward = 40.00, steps = 40
00:00:56 [INFO] train episode 631: reward = 150.00, steps = 150
00:00:56 [INFO] train episode 632: reward = 109.00, steps = 109
00:00:56 [INFO] train episode 633: reward = 98.00, steps = 98
00:00:56 [INFO] train episode 634: reward = 32.00, steps = 32
00:00:56 [INFO] train episode 635: reward = 56.00, steps = 56
00:00:56 [INFO] train episode 636: reward = 83.00, steps = 83
00:00:56 [INFO] train episode 637: reward = 47.00, steps = 47
00:00:56 [INFO] train episode 638: reward = 120.00, steps = 120
00:00:56 [INFO] train episode 639: reward = 105.00, steps = 105
00:00:56 [INFO] train episode 640: reward = 190.00, steps = 190
00:00:56 [INFO] train episode 641: reward = 25.00, steps = 25
00:00:56 [INFO] train episode 642: reward = 54.00, steps = 54
00:00:56 [INFO] train episode 643: reward = 18.00, steps = 18
00:00:56 [INFO] train episode 644: reward = 105.00, steps = 105
00:00:56 [INFO] train episode 645: reward = 25.00, steps = 25
00:00:56 [INFO] train episode 646: reward = 51.00, steps = 51
00:00:56 [INFO] train episode 647: reward = 167.00, steps = 167
00:00:56 [INFO] train episode 648: reward = 54.00, steps = 54
00:00:56 [INFO] train episode 649: reward = 125.00, steps = 125
00:00:56 [INFO] train episode 650: reward = 200.00, steps = 200
00:00:56 [INFO] train episode 651: reward = 101.00, steps = 101
00:00:57 [INFO] train episode 652: reward = 144.00, steps = 144
00:00:57 [INFO] train episode 653: reward = 175.00, steps = 175
00:00:57 [INFO] train episode 654: reward = 71.00, steps = 71
00:00:57 [INFO] train episode 655: reward = 11.00, steps = 11
00:00:57 [INFO] train episode 656: reward = 68.00, steps = 68
00:00:57 [INFO] train episode 657: reward = 68.00, steps = 68
00:00:57 [INFO] train episode 658: reward = 151.00, steps = 151
00:00:57 [INFO] train episode 659: reward = 109.00, steps = 109
00:00:57 [INFO] train episode 660: reward = 81.00, steps = 81
00:00:57 [INFO] train episode 661: reward = 42.00, steps = 42
00:00:57 [INFO] train episode 662: reward = 172.00, steps = 172
00:00:57 [INFO] train episode 663: reward = 28.00, steps = 28
00:00:57 [INFO] train episode 664: reward = 200.00, steps = 200
00:00:57 [INFO] train episode 665: reward = 83.00, steps = 83
00:00:57 [INFO] train episode 666: reward = 148.00, steps = 148
00:00:57 [INFO] train episode 667: reward = 103.00, steps = 103
00:00:57 [INFO] train episode 668: reward = 200.00, steps = 200
00:00:57 [INFO] train episode 669: reward = 177.00, steps = 177
00:00:57 [INFO] train episode 670: reward = 35.00, steps = 35
00:00:57 [INFO] train episode 671: reward = 37.00, steps = 37
00:00:57 [INFO] train episode 672: reward = 110.00, steps = 110
00:00:57 [INFO] train episode 673: reward = 60.00, steps = 60
00:00:57 [INFO] train episode 674: reward = 22.00, steps = 22
00:00:57 [INFO] train episode 675: reward = 84.00, steps = 84
00:00:57 [INFO] train episode 676: reward = 22.00, steps = 22
00:00:57 [INFO] train episode 677: reward = 200.00, steps = 200
00:00:58 [INFO] train episode 678: reward = 200.00, steps = 200
00:00:58 [INFO] train episode 679: reward = 73.00, steps = 73
00:00:58 [INFO] train episode 680: reward = 76.00, steps = 76
00:00:58 [INFO] train episode 681: reward = 200.00, steps = 200
00:00:58 [INFO] train episode 682: reward = 155.00, steps = 155
00:00:58 [INFO] train episode 683: reward = 54.00, steps = 54
00:00:58 [INFO] train episode 684: reward = 47.00, steps = 47
00:00:58 [INFO] train episode 685: reward = 137.00, steps = 137
00:00:58 [INFO] train episode 686: reward = 59.00, steps = 59
00:00:58 [INFO] train episode 687: reward = 16.00, steps = 16
00:00:58 [INFO] train episode 688: reward = 200.00, steps = 200
00:00:58 [INFO] train episode 689: reward = 90.00, steps = 90
00:00:58 [INFO] train episode 690: reward = 35.00, steps = 35
00:00:58 [INFO] train episode 691: reward = 15.00, steps = 15
00:00:58 [INFO] train episode 692: reward = 65.00, steps = 65
00:00:58 [INFO] train episode 693: reward = 115.00, steps = 115
00:00:58 [INFO] train episode 694: reward = 25.00, steps = 25
00:00:58 [INFO] train episode 695: reward = 63.00, steps = 63
00:00:58 [INFO] train episode 696: reward = 136.00, steps = 136
00:00:58 [INFO] train episode 697: reward = 74.00, steps = 74
00:00:58 [INFO] train episode 698: reward = 119.00, steps = 119
00:00:58 [INFO] train episode 699: reward = 80.00, steps = 80
00:00:58 [INFO] train episode 700: reward = 200.00, steps = 200
00:00:58 [INFO] train episode 701: reward = 21.00, steps = 21
00:00:58 [INFO] train episode 702: reward = 62.00, steps = 62
00:00:59 [INFO] train episode 703: reward = 200.00, steps = 200
00:00:59 [INFO] train episode 704: reward = 38.00, steps = 38
00:00:59 [INFO] train episode 705: reward = 200.00, steps = 200
00:00:59 [INFO] train episode 706: reward = 27.00, steps = 27
00:00:59 [INFO] train episode 707: reward = 43.00, steps = 43
00:00:59 [INFO] train episode 708: reward = 168.00, steps = 168
00:00:59 [INFO] train episode 709: reward = 14.00, steps = 14
00:00:59 [INFO] train episode 710: reward = 78.00, steps = 78
00:00:59 [INFO] train episode 711: reward = 99.00, steps = 99
00:00:59 [INFO] train episode 712: reward = 38.00, steps = 38
00:00:59 [INFO] train episode 713: reward = 53.00, steps = 53
00:00:59 [INFO] train episode 714: reward = 92.00, steps = 92
00:00:59 [INFO] train episode 715: reward = 200.00, steps = 200
00:00:59 [INFO] train episode 716: reward = 72.00, steps = 72
00:00:59 [INFO] train episode 717: reward = 174.00, steps = 174
00:00:59 [INFO] train episode 718: reward = 57.00, steps = 57
00:00:59 [INFO] train episode 719: reward = 115.00, steps = 115
00:00:59 [INFO] train episode 720: reward = 77.00, steps = 77
00:00:59 [INFO] train episode 721: reward = 200.00, steps = 200
00:00:59 [INFO] train episode 722: reward = 190.00, steps = 190
00:00:59 [INFO] train episode 723: reward = 51.00, steps = 51
00:01:00 [INFO] train episode 724: reward = 172.00, steps = 172
00:01:00 [INFO] train episode 725: reward = 92.00, steps = 92
00:01:00 [INFO] train episode 726: reward = 68.00, steps = 68
00:01:00 [INFO] train episode 727: reward = 37.00, steps = 37
00:01:00 [INFO] train episode 728: reward = 127.00, steps = 127
00:01:00 [INFO] train episode 729: reward = 79.00, steps = 79
00:01:00 [INFO] train episode 730: reward = 31.00, steps = 31
00:01:00 [INFO] train episode 731: reward = 58.00, steps = 58
00:01:00 [INFO] train episode 732: reward = 148.00, steps = 148
00:01:00 [INFO] train episode 733: reward = 139.00, steps = 139
00:01:00 [INFO] train episode 734: reward = 35.00, steps = 35
00:01:00 [INFO] train episode 735: reward = 26.00, steps = 26
00:01:00 [INFO] train episode 736: reward = 32.00, steps = 32
00:01:00 [INFO] train episode 737: reward = 60.00, steps = 60
00:01:00 [INFO] train episode 738: reward = 130.00, steps = 130
00:01:00 [INFO] train episode 739: reward = 178.00, steps = 178
00:01:00 [INFO] train episode 740: reward = 36.00, steps = 36
00:01:00 [INFO] train episode 741: reward = 114.00, steps = 114
00:01:00 [INFO] train episode 742: reward = 182.00, steps = 182
00:01:00 [INFO] train episode 743: reward = 119.00, steps = 119
00:01:00 [INFO] train episode 744: reward = 77.00, steps = 77
00:01:00 [INFO] train episode 745: reward = 155.00, steps = 155
00:01:00 [INFO] train episode 746: reward = 159.00, steps = 159
00:01:00 [INFO] train episode 747: reward = 198.00, steps = 198
00:01:00 [INFO] train episode 748: reward = 200.00, steps = 200
00:01:00 [INFO] train episode 749: reward = 18.00, steps = 18
00:01:00 [INFO] train episode 750: reward = 45.00, steps = 45
00:01:01 [INFO] train episode 751: reward = 52.00, steps = 52
00:01:01 [INFO] train episode 752: reward = 25.00, steps = 25
00:01:01 [INFO] train episode 753: reward = 107.00, steps = 107
00:01:01 [INFO] train episode 754: reward = 200.00, steps = 200
00:01:01 [INFO] train episode 755: reward = 144.00, steps = 144
00:01:01 [INFO] train episode 756: reward = 76.00, steps = 76
00:01:01 [INFO] train episode 757: reward = 97.00, steps = 97
00:01:01 [INFO] train episode 758: reward = 200.00, steps = 200
00:01:01 [INFO] train episode 759: reward = 200.00, steps = 200
00:01:01 [INFO] train episode 760: reward = 134.00, steps = 134
00:01:01 [INFO] train episode 761: reward = 41.00, steps = 41
00:01:01 [INFO] train episode 762: reward = 38.00, steps = 38
00:01:01 [INFO] train episode 763: reward = 200.00, steps = 200
00:01:01 [INFO] train episode 764: reward = 95.00, steps = 95
00:01:01 [INFO] train episode 765: reward = 188.00, steps = 188
00:01:01 [INFO] train episode 766: reward = 193.00, steps = 193
00:01:01 [INFO] train episode 767: reward = 200.00, steps = 200
00:01:01 [INFO] train episode 768: reward = 172.00, steps = 172
00:01:01 [INFO] train episode 769: reward = 135.00, steps = 135
00:01:02 [INFO] train episode 770: reward = 127.00, steps = 127
00:01:02 [INFO] train episode 771: reward = 187.00, steps = 187
00:01:02 [INFO] train episode 772: reward = 92.00, steps = 92
00:01:02 [INFO] train episode 773: reward = 63.00, steps = 63
00:01:02 [INFO] train episode 774: reward = 200.00, steps = 200
00:01:02 [INFO] train episode 775: reward = 156.00, steps = 156
00:01:02 [INFO] train episode 776: reward = 35.00, steps = 35
00:01:02 [INFO] train episode 777: reward = 117.00, steps = 117
00:01:02 [INFO] train episode 778: reward = 96.00, steps = 96
00:01:02 [INFO] train episode 779: reward = 200.00, steps = 200
00:01:02 [INFO] train episode 780: reward = 46.00, steps = 46
00:01:02 [INFO] train episode 781: reward = 105.00, steps = 105
00:01:02 [INFO] train episode 782: reward = 139.00, steps = 139
00:01:02 [INFO] train episode 783: reward = 145.00, steps = 145
00:01:02 [INFO] train episode 784: reward = 109.00, steps = 109
00:01:02 [INFO] train episode 785: reward = 43.00, steps = 43
00:01:02 [INFO] train episode 786: reward = 69.00, steps = 69
00:01:02 [INFO] train episode 787: reward = 200.00, steps = 200
00:01:02 [INFO] train episode 788: reward = 112.00, steps = 112
00:01:02 [INFO] train episode 789: reward = 83.00, steps = 83
00:01:02 [INFO] train episode 790: reward = 52.00, steps = 52
00:01:02 [INFO] train episode 791: reward = 84.00, steps = 84
00:01:02 [INFO] train episode 792: reward = 178.00, steps = 178
00:01:03 [INFO] train episode 793: reward = 46.00, steps = 46
00:01:03 [INFO] train episode 794: reward = 200.00, steps = 200
00:01:03 [INFO] train episode 795: reward = 123.00, steps = 123
00:01:03 [INFO] train episode 796: reward = 82.00, steps = 82
00:01:03 [INFO] train episode 797: reward = 165.00, steps = 165
00:01:03 [INFO] train episode 798: reward = 35.00, steps = 35
00:01:03 [INFO] train episode 799: reward = 30.00, steps = 30
00:01:03 [INFO] train episode 800: reward = 194.00, steps = 194
00:01:03 [INFO] train episode 801: reward = 200.00, steps = 200
00:01:03 [INFO] train episode 802: reward = 152.00, steps = 152
00:01:03 [INFO] train episode 803: reward = 98.00, steps = 98
00:01:03 [INFO] train episode 804: reward = 53.00, steps = 53
00:01:03 [INFO] train episode 805: reward = 157.00, steps = 157
00:01:03 [INFO] train episode 806: reward = 19.00, steps = 19
00:01:03 [INFO] train episode 807: reward = 48.00, steps = 48
00:01:03 [INFO] train episode 808: reward = 34.00, steps = 34
00:01:03 [INFO] train episode 809: reward = 184.00, steps = 184
00:01:03 [INFO] train episode 810: reward = 54.00, steps = 54
00:01:03 [INFO] train episode 811: reward = 133.00, steps = 133
00:01:03 [INFO] train episode 812: reward = 98.00, steps = 98
00:01:03 [INFO] train episode 813: reward = 44.00, steps = 44
00:01:03 [INFO] train episode 814: reward = 32.00, steps = 32
00:01:03 [INFO] train episode 815: reward = 184.00, steps = 184
00:01:03 [INFO] train episode 816: reward = 70.00, steps = 70
00:01:03 [INFO] train episode 817: reward = 45.00, steps = 45
00:01:03 [INFO] train episode 818: reward = 98.00, steps = 98
00:01:04 [INFO] train episode 819: reward = 200.00, steps = 200
00:01:04 [INFO] train episode 820: reward = 78.00, steps = 78
00:01:04 [INFO] train episode 821: reward = 159.00, steps = 159
00:01:04 [INFO] train episode 822: reward = 49.00, steps = 49
00:01:04 [INFO] train episode 823: reward = 200.00, steps = 200
00:01:04 [INFO] train episode 824: reward = 200.00, steps = 200
00:01:04 [INFO] train episode 825: reward = 72.00, steps = 72
00:01:04 [INFO] train episode 826: reward = 122.00, steps = 122
00:01:04 [INFO] train episode 827: reward = 30.00, steps = 30
00:01:04 [INFO] train episode 828: reward = 118.00, steps = 118
00:01:04 [INFO] train episode 829: reward = 101.00, steps = 101
00:01:04 [INFO] train episode 830: reward = 83.00, steps = 83
00:01:04 [INFO] train episode 831: reward = 123.00, steps = 123
00:01:04 [INFO] train episode 832: reward = 109.00, steps = 109
00:01:04 [INFO] train episode 833: reward = 60.00, steps = 60
00:01:04 [INFO] train episode 834: reward = 163.00, steps = 163
00:01:04 [INFO] train episode 835: reward = 96.00, steps = 96
00:01:04 [INFO] train episode 836: reward = 193.00, steps = 193
00:01:04 [INFO] train episode 837: reward = 105.00, steps = 105
00:01:04 [INFO] train episode 838: reward = 47.00, steps = 47
00:01:04 [INFO] train episode 839: reward = 172.00, steps = 172
00:01:04 [INFO] train episode 840: reward = 24.00, steps = 24
00:01:04 [INFO] train episode 841: reward = 75.00, steps = 75
00:01:04 [INFO] train episode 842: reward = 146.00, steps = 146
00:01:05 [INFO] train episode 843: reward = 200.00, steps = 200
00:01:05 [INFO] train episode 844: reward = 111.00, steps = 111
00:01:05 [INFO] train episode 845: reward = 200.00, steps = 200
00:01:05 [INFO] train episode 846: reward = 114.00, steps = 114
00:01:05 [INFO] train episode 847: reward = 174.00, steps = 174
00:01:05 [INFO] train episode 848: reward = 58.00, steps = 58
00:01:05 [INFO] train episode 849: reward = 112.00, steps = 112
00:01:05 [INFO] train episode 850: reward = 200.00, steps = 200
00:01:05 [INFO] train episode 851: reward = 160.00, steps = 160
00:01:05 [INFO] train episode 852: reward = 200.00, steps = 200
00:01:05 [INFO] train episode 853: reward = 73.00, steps = 73
00:01:05 [INFO] train episode 854: reward = 130.00, steps = 130
00:01:05 [INFO] train episode 855: reward = 200.00, steps = 200
00:01:05 [INFO] train episode 856: reward = 48.00, steps = 48
00:01:05 [INFO] train episode 857: reward = 97.00, steps = 97
00:01:05 [INFO] train episode 858: reward = 58.00, steps = 58
00:01:05 [INFO] train episode 859: reward = 116.00, steps = 116
00:01:05 [INFO] train episode 860: reward = 200.00, steps = 200
00:01:05 [INFO] train episode 861: reward = 76.00, steps = 76
00:01:05 [INFO] train episode 862: reward = 60.00, steps = 60
00:01:05 [INFO] train episode 863: reward = 138.00, steps = 138
00:01:05 [INFO] train episode 864: reward = 65.00, steps = 65
00:01:06 [INFO] train episode 865: reward = 151.00, steps = 151
00:01:06 [INFO] train episode 866: reward = 116.00, steps = 116
00:01:06 [INFO] train episode 867: reward = 35.00, steps = 35
00:01:06 [INFO] train episode 868: reward = 190.00, steps = 190
00:01:06 [INFO] train episode 869: reward = 126.00, steps = 126
00:01:06 [INFO] train episode 870: reward = 106.00, steps = 106
00:01:06 [INFO] train episode 871: reward = 180.00, steps = 180
00:01:06 [INFO] train episode 872: reward = 130.00, steps = 130
00:01:06 [INFO] train episode 873: reward = 163.00, steps = 163
00:01:06 [INFO] train episode 874: reward = 200.00, steps = 200
00:01:06 [INFO] train episode 875: reward = 154.00, steps = 154
00:01:06 [INFO] train episode 876: reward = 117.00, steps = 117
00:01:06 [INFO] train episode 877: reward = 152.00, steps = 152
00:01:06 [INFO] train episode 878: reward = 200.00, steps = 200
00:01:06 [INFO] train episode 879: reward = 35.00, steps = 35
00:01:06 [INFO] train episode 880: reward = 192.00, steps = 192
00:01:06 [INFO] train episode 881: reward = 162.00, steps = 162
00:01:06 [INFO] train episode 882: reward = 200.00, steps = 200
00:01:06 [INFO] train episode 883: reward = 44.00, steps = 44
00:01:06 [INFO] train episode 884: reward = 69.00, steps = 69
00:01:07 [INFO] train episode 885: reward = 130.00, steps = 130
00:01:07 [INFO] train episode 886: reward = 200.00, steps = 200
00:01:07 [INFO] train episode 887: reward = 174.00, steps = 174
00:01:07 [INFO] train episode 888: reward = 66.00, steps = 66
00:01:07 [INFO] train episode 889: reward = 24.00, steps = 24
00:01:07 [INFO] train episode 890: reward = 171.00, steps = 171
00:01:07 [INFO] train episode 891: reward = 155.00, steps = 155
00:01:07 [INFO] train episode 892: reward = 155.00, steps = 155
00:01:07 [INFO] train episode 893: reward = 114.00, steps = 114
00:01:07 [INFO] train episode 894: reward = 153.00, steps = 153
00:01:07 [INFO] train episode 895: reward = 68.00, steps = 68
00:01:07 [INFO] train episode 896: reward = 200.00, steps = 200
00:01:07 [INFO] train episode 897: reward = 200.00, steps = 200
00:01:07 [INFO] train episode 898: reward = 47.00, steps = 47
00:01:07 [INFO] train episode 899: reward = 191.00, steps = 191
00:01:07 [INFO] train episode 900: reward = 125.00, steps = 125
00:01:07 [INFO] train episode 901: reward = 124.00, steps = 124
00:01:08 [INFO] train episode 902: reward = 138.00, steps = 138
00:01:08 [INFO] train episode 903: reward = 47.00, steps = 47
00:01:08 [INFO] train episode 904: reward = 162.00, steps = 162
00:01:08 [INFO] train episode 905: reward = 200.00, steps = 200
00:01:08 [INFO] train episode 906: reward = 140.00, steps = 140
00:01:08 [INFO] train episode 907: reward = 126.00, steps = 126
00:01:08 [INFO] train episode 908: reward = 140.00, steps = 140
00:01:08 [INFO] train episode 909: reward = 200.00, steps = 200
00:01:08 [INFO] train episode 910: reward = 126.00, steps = 126
00:01:08 [INFO] train episode 911: reward = 128.00, steps = 128
00:01:08 [INFO] train episode 912: reward = 157.00, steps = 157
00:01:08 [INFO] train episode 913: reward = 200.00, steps = 200
00:01:08 [INFO] train episode 914: reward = 200.00, steps = 200
00:01:08 [INFO] train episode 915: reward = 139.00, steps = 139
00:01:08 [INFO] train episode 916: reward = 65.00, steps = 65
00:01:08 [INFO] train episode 917: reward = 171.00, steps = 171
00:01:08 [INFO] train episode 918: reward = 200.00, steps = 200
00:01:08 [INFO] train episode 919: reward = 104.00, steps = 104
00:01:09 [INFO] train episode 920: reward = 200.00, steps = 200
00:01:09 [INFO] train episode 921: reward = 200.00, steps = 200
00:01:09 [INFO] train episode 922: reward = 76.00, steps = 76
00:01:09 [INFO] train episode 923: reward = 200.00, steps = 200
00:01:09 [INFO] train episode 924: reward = 28.00, steps = 28
00:01:09 [INFO] train episode 925: reward = 200.00, steps = 200
00:01:09 [INFO] train episode 926: reward = 64.00, steps = 64
00:01:09 [INFO] train episode 927: reward = 143.00, steps = 143
00:01:09 [INFO] train episode 928: reward = 152.00, steps = 152
00:01:09 [INFO] train episode 929: reward = 177.00, steps = 177
00:01:09 [INFO] train episode 930: reward = 187.00, steps = 187
00:01:09 [INFO] train episode 931: reward = 187.00, steps = 187
00:01:09 [INFO] train episode 932: reward = 125.00, steps = 125
00:01:09 [INFO] train episode 933: reward = 162.00, steps = 162
00:01:09 [INFO] train episode 934: reward = 32.00, steps = 32
00:01:09 [INFO] train episode 935: reward = 32.00, steps = 32
00:01:09 [INFO] train episode 936: reward = 29.00, steps = 29
00:01:09 [INFO] train episode 937: reward = 175.00, steps = 175
00:01:09 [INFO] train episode 938: reward = 38.00, steps = 38
00:01:10 [INFO] train episode 939: reward = 200.00, steps = 200
00:01:10 [INFO] train episode 940: reward = 18.00, steps = 18
00:01:10 [INFO] train episode 941: reward = 200.00, steps = 200
00:01:10 [INFO] train episode 942: reward = 129.00, steps = 129
00:01:10 [INFO] train episode 943: reward = 44.00, steps = 44
00:01:10 [INFO] train episode 944: reward = 131.00, steps = 131
00:01:10 [INFO] train episode 945: reward = 170.00, steps = 170
00:01:10 [INFO] train episode 946: reward = 135.00, steps = 135
00:01:10 [INFO] train episode 947: reward = 176.00, steps = 176
00:01:10 [INFO] train episode 948: reward = 177.00, steps = 177
00:01:10 [INFO] train episode 949: reward = 200.00, steps = 200
00:01:10 [INFO] train episode 950: reward = 51.00, steps = 51
00:01:10 [INFO] train episode 951: reward = 21.00, steps = 21
00:01:10 [INFO] train episode 952: reward = 102.00, steps = 102
00:01:10 [INFO] train episode 953: reward = 187.00, steps = 187
00:01:10 [INFO] train episode 954: reward = 188.00, steps = 188
00:01:10 [INFO] train episode 955: reward = 86.00, steps = 86
00:01:10 [INFO] train episode 956: reward = 25.00, steps = 25
00:01:10 [INFO] train episode 957: reward = 200.00, steps = 200
00:01:10 [INFO] train episode 958: reward = 119.00, steps = 119
00:01:11 [INFO] train episode 959: reward = 200.00, steps = 200
00:01:11 [INFO] train episode 960: reward = 200.00, steps = 200
00:01:11 [INFO] train episode 961: reward = 83.00, steps = 83
00:01:11 [INFO] train episode 962: reward = 123.00, steps = 123
00:01:11 [INFO] train episode 963: reward = 200.00, steps = 200
00:01:11 [INFO] train episode 964: reward = 196.00, steps = 196
00:01:11 [INFO] train episode 965: reward = 200.00, steps = 200
00:01:11 [INFO] train episode 966: reward = 200.00, steps = 200
00:01:11 [INFO] train episode 967: reward = 100.00, steps = 100
00:01:11 [INFO] train episode 968: reward = 200.00, steps = 200
00:01:11 [INFO] train episode 969: reward = 37.00, steps = 37
00:01:11 [INFO] train episode 970: reward = 200.00, steps = 200
00:01:11 [INFO] train episode 971: reward = 58.00, steps = 58
00:01:11 [INFO] train episode 972: reward = 200.00, steps = 200
00:01:12 [INFO] train episode 973: reward = 200.00, steps = 200
00:01:12 [INFO] train episode 974: reward = 133.00, steps = 133
00:01:12 [INFO] train episode 975: reward = 42.00, steps = 42
00:01:12 [INFO] train episode 976: reward = 109.00, steps = 109
00:01:12 [INFO] train episode 977: reward = 160.00, steps = 160
00:01:12 [INFO] train episode 978: reward = 168.00, steps = 168
00:01:12 [INFO] train episode 979: reward = 12.00, steps = 12
00:01:12 [INFO] train episode 980: reward = 146.00, steps = 146
00:01:12 [INFO] train episode 981: reward = 28.00, steps = 28
00:01:12 [INFO] train episode 982: reward = 193.00, steps = 193
00:01:12 [INFO] train episode 983: reward = 35.00, steps = 35
00:01:12 [INFO] train episode 984: reward = 200.00, steps = 200
00:01:12 [INFO] train episode 985: reward = 142.00, steps = 142
00:01:12 [INFO] train episode 986: reward = 93.00, steps = 93
00:01:12 [INFO] train episode 987: reward = 178.00, steps = 178
00:01:12 [INFO] train episode 988: reward = 127.00, steps = 127
00:01:12 [INFO] train episode 989: reward = 200.00, steps = 200
00:01:12 [INFO] train episode 990: reward = 153.00, steps = 153
00:01:12 [INFO] train episode 991: reward = 175.00, steps = 175
00:01:13 [INFO] train episode 992: reward = 153.00, steps = 153
00:01:13 [INFO] train episode 993: reward = 22.00, steps = 22
00:01:13 [INFO] train episode 994: reward = 132.00, steps = 132
00:01:13 [INFO] train episode 995: reward = 200.00, steps = 200
00:01:13 [INFO] train episode 996: reward = 144.00, steps = 144
00:01:13 [INFO] train episode 997: reward = 193.00, steps = 193
00:01:13 [INFO] train episode 998: reward = 44.00, steps = 44
00:01:13 [INFO] train episode 999: reward = 176.00, steps = 176
00:01:13 [INFO] train episode 1000: reward = 200.00, steps = 200
00:01:13 [INFO] train episode 1001: reward = 122.00, steps = 122
00:01:13 [INFO] train episode 1002: reward = 185.00, steps = 185
00:01:13 [INFO] train episode 1003: reward = 143.00, steps = 143
00:01:13 [INFO] train episode 1004: reward = 46.00, steps = 46
00:01:13 [INFO] train episode 1005: reward = 65.00, steps = 65
00:01:13 [INFO] train episode 1006: reward = 76.00, steps = 76
00:01:13 [INFO] train episode 1007: reward = 21.00, steps = 21
00:01:13 [INFO] train episode 1008: reward = 107.00, steps = 107
00:01:13 [INFO] train episode 1009: reward = 172.00, steps = 172
00:01:13 [INFO] train episode 1010: reward = 92.00, steps = 92
00:01:13 [INFO] train episode 1011: reward = 188.00, steps = 188
00:01:13 [INFO] train episode 1012: reward = 68.00, steps = 68
00:01:14 [INFO] train episode 1013: reward = 200.00, steps = 200
00:01:14 [INFO] train episode 1014: reward = 200.00, steps = 200
00:01:14 [INFO] train episode 1015: reward = 58.00, steps = 58
00:01:14 [INFO] train episode 1016: reward = 147.00, steps = 147
00:01:14 [INFO] train episode 1017: reward = 100.00, steps = 100
00:01:14 [INFO] train episode 1018: reward = 200.00, steps = 200
00:01:14 [INFO] train episode 1019: reward = 84.00, steps = 84
00:01:14 [INFO] train episode 1020: reward = 200.00, steps = 200
00:01:14 [INFO] train episode 1021: reward = 75.00, steps = 75
00:01:14 [INFO] train episode 1022: reward = 200.00, steps = 200
00:01:14 [INFO] train episode 1023: reward = 190.00, steps = 190
00:01:14 [INFO] train episode 1024: reward = 153.00, steps = 153
00:01:14 [INFO] train episode 1025: reward = 65.00, steps = 65
00:01:14 [INFO] train episode 1026: reward = 176.00, steps = 176
00:01:14 [INFO] train episode 1027: reward = 163.00, steps = 163
00:01:14 [INFO] train episode 1028: reward = 200.00, steps = 200
00:01:15 [INFO] train episode 1029: reward = 200.00, steps = 200
00:01:15 [INFO] train episode 1030: reward = 70.00, steps = 70
00:01:15 [INFO] train episode 1031: reward = 24.00, steps = 24
00:01:15 [INFO] train episode 1032: reward = 200.00, steps = 200
00:01:15 [INFO] train episode 1033: reward = 200.00, steps = 200
00:01:15 [INFO] train episode 1034: reward = 145.00, steps = 145
00:01:15 [INFO] train episode 1035: reward = 46.00, steps = 46
00:01:15 [INFO] train episode 1036: reward = 22.00, steps = 22
00:01:15 [INFO] train episode 1037: reward = 189.00, steps = 189
00:01:15 [INFO] train episode 1038: reward = 200.00, steps = 200
00:01:15 [INFO] train episode 1039: reward = 200.00, steps = 200
00:01:15 [INFO] train episode 1040: reward = 19.00, steps = 19
00:01:15 [INFO] train episode 1041: reward = 47.00, steps = 47
00:01:15 [INFO] train episode 1042: reward = 155.00, steps = 155
00:01:15 [INFO] train episode 1043: reward = 67.00, steps = 67
00:01:15 [INFO] train episode 1044: reward = 200.00, steps = 200
00:01:15 [INFO] train episode 1045: reward = 183.00, steps = 183
00:01:15 [INFO] train episode 1046: reward = 200.00, steps = 200
00:01:15 [INFO] train episode 1047: reward = 200.00, steps = 200
00:01:16 [INFO] train episode 1048: reward = 136.00, steps = 136
00:01:16 [INFO] train episode 1049: reward = 200.00, steps = 200
00:01:16 [INFO] train episode 1050: reward = 200.00, steps = 200
00:01:16 [INFO] train episode 1051: reward = 181.00, steps = 181
00:01:16 [INFO] train episode 1052: reward = 200.00, steps = 200
00:01:16 [INFO] train episode 1053: reward = 106.00, steps = 106
00:01:16 [INFO] train episode 1054: reward = 59.00, steps = 59
00:01:16 [INFO] train episode 1055: reward = 142.00, steps = 142
00:01:16 [INFO] train episode 1056: reward = 200.00, steps = 200
00:01:16 [INFO] train episode 1057: reward = 83.00, steps = 83
00:01:16 [INFO] train episode 1058: reward = 200.00, steps = 200
00:01:16 [INFO] train episode 1059: reward = 151.00, steps = 151
00:01:16 [INFO] train episode 1060: reward = 79.00, steps = 79
00:01:16 [INFO] train episode 1061: reward = 19.00, steps = 19
00:01:16 [INFO] train episode 1062: reward = 28.00, steps = 28
00:01:16 [INFO] train episode 1063: reward = 111.00, steps = 111
00:01:16 [INFO] train episode 1064: reward = 149.00, steps = 149
00:01:16 [INFO] train episode 1065: reward = 189.00, steps = 189
00:01:17 [INFO] train episode 1066: reward = 114.00, steps = 114
00:01:17 [INFO] train episode 1067: reward = 31.00, steps = 31
00:01:17 [INFO] train episode 1068: reward = 113.00, steps = 113
00:01:17 [INFO] train episode 1069: reward = 200.00, steps = 200
00:01:17 [INFO] train episode 1070: reward = 42.00, steps = 42
00:01:17 [INFO] train episode 1071: reward = 200.00, steps = 200
00:01:17 [INFO] train episode 1072: reward = 16.00, steps = 16
00:01:17 [INFO] train episode 1073: reward = 111.00, steps = 111
00:01:17 [INFO] train episode 1074: reward = 200.00, steps = 200
00:01:17 [INFO] train episode 1075: reward = 200.00, steps = 200
00:01:17 [INFO] train episode 1076: reward = 200.00, steps = 200
00:01:17 [INFO] train episode 1077: reward = 200.00, steps = 200
00:01:17 [INFO] train episode 1078: reward = 95.00, steps = 95
00:01:17 [INFO] train episode 1079: reward = 200.00, steps = 200
00:01:17 [INFO] train episode 1080: reward = 200.00, steps = 200
00:01:17 [INFO] train episode 1081: reward = 200.00, steps = 200
00:01:18 [INFO] train episode 1082: reward = 181.00, steps = 181
00:01:18 [INFO] train episode 1083: reward = 145.00, steps = 145
00:01:18 [INFO] train episode 1084: reward = 123.00, steps = 123
00:01:18 [INFO] train episode 1085: reward = 59.00, steps = 59
00:01:18 [INFO] train episode 1086: reward = 97.00, steps = 97
00:01:18 [INFO] train episode 1087: reward = 200.00, steps = 200
00:01:18 [INFO] train episode 1088: reward = 200.00, steps = 200
00:01:18 [INFO] train episode 1089: reward = 200.00, steps = 200
00:01:18 [INFO] train episode 1090: reward = 168.00, steps = 168
00:01:18 [INFO] train episode 1091: reward = 200.00, steps = 200
00:01:18 [INFO] train episode 1092: reward = 170.00, steps = 170
00:01:18 [INFO] train episode 1093: reward = 91.00, steps = 91
00:01:18 [INFO] train episode 1094: reward = 200.00, steps = 200
00:01:18 [INFO] train episode 1095: reward = 109.00, steps = 109
00:01:18 [INFO] train episode 1096: reward = 200.00, steps = 200
00:01:18 [INFO] train episode 1097: reward = 98.00, steps = 98
00:01:19 [INFO] train episode 1098: reward = 113.00, steps = 113
00:01:19 [INFO] train episode 1099: reward = 200.00, steps = 200
00:01:19 [INFO] train episode 1100: reward = 169.00, steps = 169
00:01:19 [INFO] train episode 1101: reward = 190.00, steps = 190
00:01:19 [INFO] train episode 1102: reward = 200.00, steps = 200
00:01:19 [INFO] train episode 1103: reward = 109.00, steps = 109
00:01:19 [INFO] train episode 1104: reward = 104.00, steps = 104
00:01:19 [INFO] train episode 1105: reward = 164.00, steps = 164
00:01:19 [INFO] train episode 1106: reward = 200.00, steps = 200
00:01:19 [INFO] train episode 1107: reward = 164.00, steps = 164
00:01:19 [INFO] train episode 1108: reward = 200.00, steps = 200
00:01:19 [INFO] train episode 1109: reward = 145.00, steps = 145
00:01:19 [INFO] train episode 1110: reward = 99.00, steps = 99
00:01:19 [INFO] train episode 1111: reward = 200.00, steps = 200
00:01:19 [INFO] train episode 1112: reward = 86.00, steps = 86
00:01:20 [INFO] train episode 1113: reward = 200.00, steps = 200
00:01:20 [INFO] train episode 1114: reward = 128.00, steps = 128
00:01:20 [INFO] train episode 1115: reward = 120.00, steps = 120
00:01:20 [INFO] train episode 1116: reward = 54.00, steps = 54
00:01:20 [INFO] train episode 1117: reward = 119.00, steps = 119
00:01:20 [INFO] train episode 1118: reward = 200.00, steps = 200
00:01:20 [INFO] train episode 1119: reward = 200.00, steps = 200
00:01:20 [INFO] train episode 1120: reward = 200.00, steps = 200
00:01:20 [INFO] train episode 1121: reward = 113.00, steps = 113
00:01:20 [INFO] train episode 1122: reward = 200.00, steps = 200
00:01:20 [INFO] train episode 1123: reward = 19.00, steps = 19
00:01:20 [INFO] train episode 1124: reward = 200.00, steps = 200
00:01:20 [INFO] train episode 1125: reward = 200.00, steps = 200
00:01:20 [INFO] train episode 1126: reward = 69.00, steps = 69
00:01:20 [INFO] train episode 1127: reward = 140.00, steps = 140
00:01:20 [INFO] train episode 1128: reward = 200.00, steps = 200
00:01:20 [INFO] train episode 1129: reward = 168.00, steps = 168
00:01:21 [INFO] train episode 1130: reward = 167.00, steps = 167
00:01:21 [INFO] train episode 1131: reward = 24.00, steps = 24
00:01:21 [INFO] train episode 1132: reward = 200.00, steps = 200
00:01:21 [INFO] train episode 1133: reward = 54.00, steps = 54
00:01:21 [INFO] train episode 1134: reward = 64.00, steps = 64
00:01:21 [INFO] train episode 1135: reward = 200.00, steps = 200
00:01:21 [INFO] train episode 1136: reward = 152.00, steps = 152
00:01:21 [INFO] train episode 1137: reward = 200.00, steps = 200
00:01:21 [INFO] train episode 1138: reward = 51.00, steps = 51
00:01:21 [INFO] train episode 1139: reward = 200.00, steps = 200
00:01:21 [INFO] train episode 1140: reward = 200.00, steps = 200
00:01:21 [INFO] train episode 1141: reward = 200.00, steps = 200
00:01:21 [INFO] train episode 1142: reward = 200.00, steps = 200
00:01:21 [INFO] train episode 1143: reward = 117.00, steps = 117
00:01:21 [INFO] train episode 1144: reward = 61.00, steps = 61
00:01:21 [INFO] train episode 1145: reward = 200.00, steps = 200
00:01:21 [INFO] train episode 1146: reward = 70.00, steps = 70
00:01:21 [INFO] train episode 1147: reward = 200.00, steps = 200
00:01:22 [INFO] train episode 1148: reward = 29.00, steps = 29
00:01:22 [INFO] train episode 1149: reward = 95.00, steps = 95
00:01:22 [INFO] train episode 1150: reward = 200.00, steps = 200
00:01:22 [INFO] train episode 1151: reward = 109.00, steps = 109
00:01:22 [INFO] train episode 1152: reward = 101.00, steps = 101
00:01:22 [INFO] train episode 1153: reward = 178.00, steps = 178
00:01:22 [INFO] train episode 1154: reward = 136.00, steps = 136
00:01:22 [INFO] train episode 1155: reward = 179.00, steps = 179
00:01:22 [INFO] train episode 1156: reward = 93.00, steps = 93
00:01:22 [INFO] train episode 1157: reward = 148.00, steps = 148
00:01:22 [INFO] train episode 1158: reward = 200.00, steps = 200
00:01:22 [INFO] train episode 1159: reward = 37.00, steps = 37
00:01:22 [INFO] train episode 1160: reward = 200.00, steps = 200
00:01:22 [INFO] train episode 1161: reward = 200.00, steps = 200
00:01:22 [INFO] train episode 1162: reward = 154.00, steps = 154
00:01:22 [INFO] train episode 1163: reward = 117.00, steps = 117
00:01:22 [INFO] train episode 1164: reward = 66.00, steps = 66
00:01:22 [INFO] train episode 1165: reward = 135.00, steps = 135
00:01:23 [INFO] train episode 1166: reward = 200.00, steps = 200
00:01:23 [INFO] train episode 1167: reward = 37.00, steps = 37
00:01:23 [INFO] train episode 1168: reward = 46.00, steps = 46
00:01:23 [INFO] train episode 1169: reward = 31.00, steps = 31
00:01:23 [INFO] train episode 1170: reward = 191.00, steps = 191
00:01:23 [INFO] train episode 1171: reward = 200.00, steps = 200
00:01:23 [INFO] train episode 1172: reward = 54.00, steps = 54
00:01:23 [INFO] train episode 1173: reward = 142.00, steps = 142
00:01:23 [INFO] train episode 1174: reward = 84.00, steps = 84
00:01:23 [INFO] train episode 1175: reward = 22.00, steps = 22
00:01:23 [INFO] train episode 1176: reward = 200.00, steps = 200
00:01:23 [INFO] train episode 1177: reward = 200.00, steps = 200
00:01:23 [INFO] train episode 1178: reward = 146.00, steps = 146
00:01:23 [INFO] train episode 1179: reward = 200.00, steps = 200
00:01:23 [INFO] train episode 1180: reward = 76.00, steps = 76
00:01:23 [INFO] train episode 1181: reward = 104.00, steps = 104
00:01:23 [INFO] train episode 1182: reward = 174.00, steps = 174
00:01:23 [INFO] train episode 1183: reward = 200.00, steps = 200
00:01:23 [INFO] train episode 1184: reward = 200.00, steps = 200
00:01:23 [INFO] train episode 1185: reward = 148.00, steps = 148
00:01:24 [INFO] train episode 1186: reward = 135.00, steps = 135
00:01:24 [INFO] train episode 1187: reward = 200.00, steps = 200
00:01:24 [INFO] train episode 1188: reward = 200.00, steps = 200
00:01:24 [INFO] train episode 1189: reward = 149.00, steps = 149
00:01:24 [INFO] train episode 1190: reward = 200.00, steps = 200
00:01:24 [INFO] train episode 1191: reward = 157.00, steps = 157
00:01:24 [INFO] train episode 1192: reward = 142.00, steps = 142
00:01:24 [INFO] train episode 1193: reward = 200.00, steps = 200
00:01:24 [INFO] train episode 1194: reward = 200.00, steps = 200
00:01:24 [INFO] train episode 1195: reward = 179.00, steps = 179
00:01:24 [INFO] train episode 1196: reward = 200.00, steps = 200
00:01:24 [INFO] train episode 1197: reward = 123.00, steps = 123
00:01:24 [INFO] train episode 1198: reward = 28.00, steps = 28
00:01:24 [INFO] train episode 1199: reward = 200.00, steps = 200
00:01:25 [INFO] train episode 1200: reward = 151.00, steps = 151
00:01:25 [INFO] train episode 1201: reward = 105.00, steps = 105
00:01:25 [INFO] train episode 1202: reward = 200.00, steps = 200
00:01:25 [INFO] train episode 1203: reward = 124.00, steps = 124
00:01:25 [INFO] train episode 1204: reward = 63.00, steps = 63
00:01:25 [INFO] train episode 1205: reward = 200.00, steps = 200
00:01:25 [INFO] train episode 1206: reward = 174.00, steps = 174
00:01:25 [INFO] train episode 1207: reward = 114.00, steps = 114
00:01:25 [INFO] train episode 1208: reward = 162.00, steps = 162
00:01:25 [INFO] train episode 1209: reward = 51.00, steps = 51
00:01:25 [INFO] train episode 1210: reward = 195.00, steps = 195
00:01:25 [INFO] train episode 1211: reward = 191.00, steps = 191
00:01:25 [INFO] train episode 1212: reward = 200.00, steps = 200
00:01:25 [INFO] train episode 1213: reward = 180.00, steps = 180
00:01:25 [INFO] train episode 1214: reward = 106.00, steps = 106
00:01:25 [INFO] train episode 1215: reward = 41.00, steps = 41
00:01:25 [INFO] train episode 1216: reward = 157.00, steps = 157
00:01:25 [INFO] train episode 1217: reward = 116.00, steps = 116
00:01:25 [INFO] train episode 1218: reward = 35.00, steps = 35
00:01:26 [INFO] train episode 1219: reward = 200.00, steps = 200
00:01:26 [INFO] train episode 1220: reward = 143.00, steps = 143
00:01:26 [INFO] train episode 1221: reward = 200.00, steps = 200
00:01:26 [INFO] train episode 1222: reward = 150.00, steps = 150
00:01:26 [INFO] train episode 1223: reward = 200.00, steps = 200
00:01:26 [INFO] train episode 1224: reward = 200.00, steps = 200
00:01:26 [INFO] train episode 1225: reward = 200.00, steps = 200
00:01:26 [INFO] train episode 1226: reward = 200.00, steps = 200
00:01:26 [INFO] train episode 1227: reward = 43.00, steps = 43
00:01:26 [INFO] train episode 1228: reward = 61.00, steps = 61
00:01:26 [INFO] train episode 1229: reward = 195.00, steps = 195
00:01:26 [INFO] train episode 1230: reward = 166.00, steps = 166
00:01:26 [INFO] train episode 1231: reward = 200.00, steps = 200
00:01:26 [INFO] train episode 1232: reward = 200.00, steps = 200
00:01:26 [INFO] train episode 1233: reward = 200.00, steps = 200
00:01:26 [INFO] train episode 1234: reward = 165.00, steps = 165
00:01:27 [INFO] train episode 1235: reward = 189.00, steps = 189
00:01:27 [INFO] train episode 1236: reward = 200.00, steps = 200
00:01:27 [INFO] train episode 1237: reward = 200.00, steps = 200
00:01:27 [INFO] train episode 1238: reward = 150.00, steps = 150
00:01:27 [INFO] train episode 1239: reward = 126.00, steps = 126
00:01:27 [INFO] train episode 1240: reward = 200.00, steps = 200
00:01:27 [INFO] train episode 1241: reward = 136.00, steps = 136
00:01:27 [INFO] train episode 1242: reward = 38.00, steps = 38
00:01:27 [INFO] train episode 1243: reward = 131.00, steps = 131
00:01:27 [INFO] train episode 1244: reward = 177.00, steps = 177
00:01:27 [INFO] train episode 1245: reward = 200.00, steps = 200
00:01:27 [INFO] train episode 1246: reward = 200.00, steps = 200
00:01:27 [INFO] train episode 1247: reward = 53.00, steps = 53
00:01:27 [INFO] train episode 1248: reward = 200.00, steps = 200
00:01:27 [INFO] train episode 1249: reward = 200.00, steps = 200
00:01:28 [INFO] train episode 1250: reward = 181.00, steps = 181
00:01:28 [INFO] train episode 1251: reward = 200.00, steps = 200
00:01:28 [INFO] train episode 1252: reward = 145.00, steps = 145
00:01:28 [INFO] train episode 1253: reward = 200.00, steps = 200
00:01:28 [INFO] train episode 1254: reward = 109.00, steps = 109
00:01:28 [INFO] train episode 1255: reward = 200.00, steps = 200
00:01:28 [INFO] train episode 1256: reward = 152.00, steps = 152
00:01:28 [INFO] train episode 1257: reward = 183.00, steps = 183
00:01:28 [INFO] train episode 1258: reward = 200.00, steps = 200
00:01:28 [INFO] train episode 1259: reward = 200.00, steps = 200
00:01:28 [INFO] train episode 1260: reward = 97.00, steps = 97
00:01:28 [INFO] train episode 1261: reward = 200.00, steps = 200
00:01:28 [INFO] train episode 1262: reward = 23.00, steps = 23
00:01:28 [INFO] train episode 1263: reward = 135.00, steps = 135
00:01:28 [INFO] train episode 1264: reward = 63.00, steps = 63
00:01:28 [INFO] train episode 1265: reward = 200.00, steps = 200
00:01:29 [INFO] train episode 1266: reward = 109.00, steps = 109
00:01:29 [INFO] train episode 1267: reward = 200.00, steps = 200
00:01:29 [INFO] train episode 1268: reward = 200.00, steps = 200
00:01:29 [INFO] train episode 1269: reward = 200.00, steps = 200
00:01:29 [INFO] train episode 1270: reward = 87.00, steps = 87
00:01:29 [INFO] train episode 1271: reward = 110.00, steps = 110
00:01:29 [INFO] train episode 1272: reward = 160.00, steps = 160
00:01:29 [INFO] train episode 1273: reward = 94.00, steps = 94
00:01:29 [INFO] train episode 1274: reward = 143.00, steps = 143
00:01:29 [INFO] train episode 1275: reward = 200.00, steps = 200
00:01:29 [INFO] train episode 1276: reward = 184.00, steps = 184
00:01:29 [INFO] train episode 1277: reward = 200.00, steps = 200
00:01:29 [INFO] train episode 1278: reward = 186.00, steps = 186
00:01:29 [INFO] train episode 1279: reward = 143.00, steps = 143
00:01:29 [INFO] train episode 1280: reward = 133.00, steps = 133
00:01:29 [INFO] train episode 1281: reward = 200.00, steps = 200
00:01:29 [INFO] train episode 1282: reward = 41.00, steps = 41
00:01:30 [INFO] train episode 1283: reward = 169.00, steps = 169
00:01:30 [INFO] train episode 1284: reward = 200.00, steps = 200
00:01:30 [INFO] train episode 1285: reward = 200.00, steps = 200
00:01:30 [INFO] train episode 1286: reward = 153.00, steps = 153
00:01:30 [INFO] train episode 1287: reward = 200.00, steps = 200
00:01:30 [INFO] train episode 1288: reward = 200.00, steps = 200
00:01:30 [INFO] train episode 1289: reward = 153.00, steps = 153
00:01:30 [INFO] train episode 1290: reward = 116.00, steps = 116
00:01:30 [INFO] train episode 1291: reward = 75.00, steps = 75
00:01:30 [INFO] train episode 1292: reward = 73.00, steps = 73
00:01:30 [INFO] train episode 1293: reward = 200.00, steps = 200
00:01:30 [INFO] train episode 1294: reward = 200.00, steps = 200
00:01:30 [INFO] train episode 1295: reward = 38.00, steps = 38
00:01:30 [INFO] train episode 1296: reward = 200.00, steps = 200
00:01:30 [INFO] train episode 1297: reward = 200.00, steps = 200
00:01:31 [INFO] train episode 1298: reward = 172.00, steps = 172
00:01:31 [INFO] train episode 1299: reward = 99.00, steps = 99
00:01:31 [INFO] train episode 1300: reward = 50.00, steps = 50
00:01:31 [INFO] train episode 1301: reward = 109.00, steps = 109
00:01:31 [INFO] train episode 1302: reward = 195.00, steps = 195
00:01:31 [INFO] train episode 1303: reward = 168.00, steps = 168
00:01:31 [INFO] train episode 1304: reward = 200.00, steps = 200
00:01:31 [INFO] train episode 1305: reward = 191.00, steps = 191
00:01:31 [INFO] train episode 1306: reward = 200.00, steps = 200
00:01:31 [INFO] train episode 1307: reward = 42.00, steps = 42
00:01:31 [INFO] train episode 1308: reward = 200.00, steps = 200
00:01:31 [INFO] train episode 1309: reward = 159.00, steps = 159
00:01:31 [INFO] train episode 1310: reward = 47.00, steps = 47
00:01:31 [INFO] train episode 1311: reward = 163.00, steps = 163
00:01:31 [INFO] train episode 1312: reward = 200.00, steps = 200
00:01:31 [INFO] train episode 1313: reward = 200.00, steps = 200
00:01:31 [INFO] train episode 1314: reward = 47.00, steps = 47
00:01:32 [INFO] train episode 1315: reward = 200.00, steps = 200
00:01:32 [INFO] train episode 1316: reward = 70.00, steps = 70
00:01:32 [INFO] train episode 1317: reward = 38.00, steps = 38
00:01:32 [INFO] train episode 1318: reward = 200.00, steps = 200
00:01:32 [INFO] train episode 1319: reward = 168.00, steps = 168
00:01:32 [INFO] train episode 1320: reward = 104.00, steps = 104
00:01:32 [INFO] train episode 1321: reward = 49.00, steps = 49
00:01:32 [INFO] train episode 1322: reward = 105.00, steps = 105
00:01:32 [INFO] train episode 1323: reward = 128.00, steps = 128
00:01:32 [INFO] train episode 1324: reward = 53.00, steps = 53
00:01:32 [INFO] train episode 1325: reward = 71.00, steps = 71
00:01:32 [INFO] train episode 1326: reward = 200.00, steps = 200
00:01:32 [INFO] train episode 1327: reward = 117.00, steps = 117
00:01:32 [INFO] train episode 1328: reward = 200.00, steps = 200
00:01:32 [INFO] train episode 1329: reward = 86.00, steps = 86
00:01:32 [INFO] train episode 1330: reward = 200.00, steps = 200
00:01:32 [INFO] train episode 1331: reward = 200.00, steps = 200
00:01:32 [INFO] train episode 1332: reward = 200.00, steps = 200
00:01:32 [INFO] train episode 1333: reward = 142.00, steps = 142
00:01:33 [INFO] train episode 1334: reward = 200.00, steps = 200
00:01:33 [INFO] train episode 1335: reward = 137.00, steps = 137
00:01:33 [INFO] train episode 1336: reward = 169.00, steps = 169
00:01:33 [INFO] train episode 1337: reward = 200.00, steps = 200
00:01:33 [INFO] train episode 1338: reward = 134.00, steps = 134
00:01:33 [INFO] train episode 1339: reward = 200.00, steps = 200
00:01:33 [INFO] train episode 1340: reward = 200.00, steps = 200
00:01:33 [INFO] train episode 1341: reward = 86.00, steps = 86
00:01:33 [INFO] train episode 1342: reward = 130.00, steps = 130
00:01:33 [INFO] train episode 1343: reward = 200.00, steps = 200
00:01:33 [INFO] train episode 1344: reward = 200.00, steps = 200
00:01:33 [INFO] train episode 1345: reward = 145.00, steps = 145
00:01:33 [INFO] train episode 1346: reward = 200.00, steps = 200
00:01:33 [INFO] train episode 1347: reward = 111.00, steps = 111
00:01:33 [INFO] train episode 1348: reward = 183.00, steps = 183
00:01:34 [INFO] train episode 1349: reward = 200.00, steps = 200
00:01:34 [INFO] train episode 1350: reward = 199.00, steps = 199
00:01:34 [INFO] train episode 1351: reward = 200.00, steps = 200
00:01:34 [INFO] train episode 1352: reward = 107.00, steps = 107
00:01:34 [INFO] train episode 1353: reward = 166.00, steps = 166
00:01:34 [INFO] train episode 1354: reward = 145.00, steps = 145
00:01:34 [INFO] train episode 1355: reward = 177.00, steps = 177
00:01:34 [INFO] train episode 1356: reward = 33.00, steps = 33
00:01:34 [INFO] train episode 1357: reward = 83.00, steps = 83
00:01:34 [INFO] train episode 1358: reward = 200.00, steps = 200
00:01:34 [INFO] train episode 1359: reward = 152.00, steps = 152
00:01:34 [INFO] train episode 1360: reward = 200.00, steps = 200
00:01:34 [INFO] train episode 1361: reward = 133.00, steps = 133
00:01:34 [INFO] train episode 1362: reward = 200.00, steps = 200
00:01:34 [INFO] train episode 1363: reward = 153.00, steps = 153
00:01:34 [INFO] train episode 1364: reward = 200.00, steps = 200
00:01:35 [INFO] train episode 1365: reward = 200.00, steps = 200
00:01:35 [INFO] train episode 1366: reward = 157.00, steps = 157
00:01:35 [INFO] train episode 1367: reward = 191.00, steps = 191
00:01:35 [INFO] train episode 1368: reward = 132.00, steps = 132
00:01:35 [INFO] train episode 1369: reward = 33.00, steps = 33
00:01:35 [INFO] train episode 1370: reward = 145.00, steps = 145
00:01:35 [INFO] train episode 1371: reward = 200.00, steps = 200
00:01:35 [INFO] train episode 1372: reward = 200.00, steps = 200
00:01:35 [INFO] train episode 1373: reward = 152.00, steps = 152
00:01:35 [INFO] train episode 1374: reward = 42.00, steps = 42
00:01:35 [INFO] train episode 1375: reward = 200.00, steps = 200
00:01:35 [INFO] train episode 1376: reward = 200.00, steps = 200
00:01:35 [INFO] train episode 1377: reward = 141.00, steps = 141
00:01:35 [INFO] train episode 1378: reward = 90.00, steps = 90
00:01:35 [INFO] train episode 1379: reward = 200.00, steps = 200
00:01:35 [INFO] train episode 1380: reward = 124.00, steps = 124
00:01:36 [INFO] train episode 1381: reward = 72.00, steps = 72
00:01:36 [INFO] train episode 1382: reward = 163.00, steps = 163
00:01:36 [INFO] train episode 1383: reward = 126.00, steps = 126
00:01:36 [INFO] train episode 1384: reward = 42.00, steps = 42
00:01:36 [INFO] train episode 1385: reward = 119.00, steps = 119
00:01:36 [INFO] train episode 1386: reward = 121.00, steps = 121
00:01:36 [INFO] train episode 1387: reward = 200.00, steps = 200
00:01:36 [INFO] train episode 1388: reward = 200.00, steps = 200
00:01:36 [INFO] train episode 1389: reward = 200.00, steps = 200
00:01:36 [INFO] train episode 1390: reward = 179.00, steps = 179
00:01:36 [INFO] train episode 1391: reward = 51.00, steps = 51
00:01:36 [INFO] train episode 1392: reward = 200.00, steps = 200
00:01:36 [INFO] train episode 1393: reward = 123.00, steps = 123
00:01:36 [INFO] train episode 1394: reward = 186.00, steps = 186
00:01:36 [INFO] train episode 1395: reward = 200.00, steps = 200
00:01:36 [INFO] train episode 1396: reward = 149.00, steps = 149
00:01:37 [INFO] train episode 1397: reward = 200.00, steps = 200
00:01:37 [INFO] train episode 1398: reward = 32.00, steps = 32
00:01:37 [INFO] train episode 1399: reward = 200.00, steps = 200
00:01:37 [INFO] train episode 1400: reward = 112.00, steps = 112
00:01:37 [INFO] train episode 1401: reward = 164.00, steps = 164
00:01:37 [INFO] train episode 1402: reward = 200.00, steps = 200
00:01:37 [INFO] train episode 1403: reward = 130.00, steps = 130
00:01:37 [INFO] train episode 1404: reward = 170.00, steps = 170
00:01:37 [INFO] train episode 1405: reward = 146.00, steps = 146
00:01:37 [INFO] train episode 1406: reward = 151.00, steps = 151
00:01:37 [INFO] train episode 1407: reward = 34.00, steps = 34
00:01:37 [INFO] train episode 1408: reward = 130.00, steps = 130
00:01:37 [INFO] train episode 1409: reward = 200.00, steps = 200
00:01:37 [INFO] train episode 1410: reward = 200.00, steps = 200
00:01:37 [INFO] train episode 1411: reward = 200.00, steps = 200
00:01:37 [INFO] train episode 1412: reward = 200.00, steps = 200
00:01:37 [INFO] train episode 1413: reward = 161.00, steps = 161
00:01:38 [INFO] train episode 1414: reward = 129.00, steps = 129
00:01:38 [INFO] train episode 1415: reward = 190.00, steps = 190
00:01:38 [INFO] train episode 1416: reward = 200.00, steps = 200
00:01:38 [INFO] train episode 1417: reward = 101.00, steps = 101
00:01:38 [INFO] train episode 1418: reward = 200.00, steps = 200
00:01:38 [INFO] train episode 1419: reward = 69.00, steps = 69
00:01:38 [INFO] train episode 1420: reward = 200.00, steps = 200
00:01:38 [INFO] train episode 1421: reward = 200.00, steps = 200
00:01:38 [INFO] train episode 1422: reward = 61.00, steps = 61
00:01:38 [INFO] train episode 1423: reward = 71.00, steps = 71
00:01:38 [INFO] train episode 1424: reward = 200.00, steps = 200
00:01:38 [INFO] train episode 1425: reward = 200.00, steps = 200
00:01:38 [INFO] train episode 1426: reward = 136.00, steps = 136
00:01:38 [INFO] train episode 1427: reward = 107.00, steps = 107
00:01:38 [INFO] train episode 1428: reward = 200.00, steps = 200
00:01:39 [INFO] train episode 1429: reward = 152.00, steps = 152
00:01:39 [INFO] train episode 1430: reward = 200.00, steps = 200
00:01:39 [INFO] train episode 1431: reward = 182.00, steps = 182
00:01:39 [INFO] train episode 1432: reward = 200.00, steps = 200
00:01:39 [INFO] train episode 1433: reward = 200.00, steps = 200
00:01:39 [INFO] train episode 1434: reward = 28.00, steps = 28
00:01:39 [INFO] train episode 1435: reward = 199.00, steps = 199
00:01:39 [INFO] train episode 1436: reward = 198.00, steps = 198
00:01:39 [INFO] train episode 1437: reward = 199.00, steps = 199
00:01:39 [INFO] train episode 1438: reward = 200.00, steps = 200
00:01:39 [INFO] train episode 1439: reward = 200.00, steps = 200
00:01:39 [INFO] train episode 1440: reward = 200.00, steps = 200
00:01:39 [INFO] train episode 1441: reward = 200.00, steps = 200
00:01:40 [INFO] train episode 1442: reward = 200.00, steps = 200
00:01:40 [INFO] train episode 1443: reward = 200.00, steps = 200
00:01:40 [INFO] train episode 1444: reward = 124.00, steps = 124
00:01:40 [INFO] train episode 1445: reward = 116.00, steps = 116
00:01:40 [INFO] train episode 1446: reward = 58.00, steps = 58
00:01:40 [INFO] train episode 1447: reward = 200.00, steps = 200
00:01:40 [INFO] train episode 1448: reward = 200.00, steps = 200
00:01:40 [INFO] train episode 1449: reward = 94.00, steps = 94
00:01:40 [INFO] train episode 1450: reward = 146.00, steps = 146
00:01:40 [INFO] train episode 1451: reward = 192.00, steps = 192
00:01:40 [INFO] train episode 1452: reward = 153.00, steps = 153
00:01:40 [INFO] train episode 1453: reward = 165.00, steps = 165
00:01:40 [INFO] train episode 1454: reward = 135.00, steps = 135
00:01:40 [INFO] train episode 1455: reward = 189.00, steps = 189
00:01:40 [INFO] train episode 1456: reward = 103.00, steps = 103
00:01:40 [INFO] train episode 1457: reward = 200.00, steps = 200
00:01:41 [INFO] train episode 1458: reward = 198.00, steps = 198
00:01:41 [INFO] train episode 1459: reward = 41.00, steps = 41
00:01:41 [INFO] train episode 1460: reward = 200.00, steps = 200
00:01:41 [INFO] train episode 1461: reward = 120.00, steps = 120
00:01:41 [INFO] train episode 1462: reward = 168.00, steps = 168
00:01:41 [INFO] train episode 1463: reward = 131.00, steps = 131
00:01:41 [INFO] train episode 1464: reward = 144.00, steps = 144
00:01:41 [INFO] train episode 1465: reward = 144.00, steps = 144
00:01:41 [INFO] train episode 1466: reward = 150.00, steps = 150
00:01:41 [INFO] train episode 1467: reward = 200.00, steps = 200
00:01:41 [INFO] train episode 1468: reward = 147.00, steps = 147
00:01:41 [INFO] train episode 1469: reward = 131.00, steps = 131
00:01:41 [INFO] train episode 1470: reward = 50.00, steps = 50
00:01:41 [INFO] train episode 1471: reward = 200.00, steps = 200
00:01:41 [INFO] train episode 1472: reward = 186.00, steps = 186
00:01:41 [INFO] train episode 1473: reward = 151.00, steps = 151
00:01:41 [INFO] train episode 1474: reward = 189.00, steps = 189
00:01:41 [INFO] train episode 1475: reward = 200.00, steps = 200
00:01:42 [INFO] train episode 1476: reward = 159.00, steps = 159
00:01:42 [INFO] train episode 1477: reward = 200.00, steps = 200
00:01:42 [INFO] train episode 1478: reward = 176.00, steps = 176
00:01:42 [INFO] train episode 1479: reward = 145.00, steps = 145
00:01:42 [INFO] train episode 1480: reward = 127.00, steps = 127
00:01:42 [INFO] train episode 1481: reward = 200.00, steps = 200
00:01:42 [INFO] train episode 1482: reward = 141.00, steps = 141
00:01:42 [INFO] train episode 1483: reward = 165.00, steps = 165
00:01:42 [INFO] train episode 1484: reward = 93.00, steps = 93
00:01:42 [INFO] train episode 1485: reward = 76.00, steps = 76
00:01:42 [INFO] train episode 1486: reward = 114.00, steps = 114
00:01:42 [INFO] train episode 1487: reward = 144.00, steps = 144
00:01:42 [INFO] train episode 1488: reward = 159.00, steps = 159
00:01:42 [INFO] train episode 1489: reward = 138.00, steps = 138
00:01:42 [INFO] train episode 1490: reward = 200.00, steps = 200
00:01:42 [INFO] train episode 1491: reward = 134.00, steps = 134
00:01:42 [INFO] train episode 1492: reward = 125.00, steps = 125
00:01:43 [INFO] train episode 1493: reward = 137.00, steps = 137
00:01:43 [INFO] train episode 1494: reward = 70.00, steps = 70
00:01:43 [INFO] train episode 1495: reward = 200.00, steps = 200
00:01:43 [INFO] train episode 1496: reward = 174.00, steps = 174
00:01:43 [INFO] train episode 1497: reward = 107.00, steps = 107
00:01:43 [INFO] train episode 1498: reward = 142.00, steps = 142
00:01:43 [INFO] train episode 1499: reward = 200.00, steps = 200
00:01:43 [INFO] train episode 1500: reward = 174.00, steps = 174
00:01:43 [INFO] train episode 1501: reward = 151.00, steps = 151
00:01:43 [INFO] train episode 1502: reward = 200.00, steps = 200
00:01:43 [INFO] train episode 1503: reward = 156.00, steps = 156
00:01:43 [INFO] train episode 1504: reward = 140.00, steps = 140
00:01:43 [INFO] train episode 1505: reward = 200.00, steps = 200
00:01:43 [INFO] train episode 1506: reward = 200.00, steps = 200
00:01:43 [INFO] train episode 1507: reward = 156.00, steps = 156
00:01:44 [INFO] train episode 1508: reward = 128.00, steps = 128
00:01:44 [INFO] train episode 1509: reward = 200.00, steps = 200
00:01:44 [INFO] train episode 1510: reward = 200.00, steps = 200
00:01:44 [INFO] train episode 1511: reward = 189.00, steps = 189
00:01:44 [INFO] train episode 1512: reward = 200.00, steps = 200
00:01:44 [INFO] train episode 1513: reward = 61.00, steps = 61
00:01:44 [INFO] train episode 1514: reward = 196.00, steps = 196
00:01:44 [INFO] train episode 1515: reward = 125.00, steps = 125
00:01:44 [INFO] train episode 1516: reward = 200.00, steps = 200
00:01:44 [INFO] train episode 1517: reward = 117.00, steps = 117
00:01:44 [INFO] train episode 1518: reward = 117.00, steps = 117
00:01:44 [INFO] train episode 1519: reward = 200.00, steps = 200
00:01:44 [INFO] train episode 1520: reward = 26.00, steps = 26
00:01:44 [INFO] train episode 1521: reward = 200.00, steps = 200
00:01:44 [INFO] train episode 1522: reward = 142.00, steps = 142
00:01:45 [INFO] train episode 1523: reward = 150.00, steps = 150
00:01:45 [INFO] train episode 1524: reward = 87.00, steps = 87
00:01:45 [INFO] train episode 1525: reward = 154.00, steps = 154
00:01:45 [INFO] train episode 1526: reward = 165.00, steps = 165
00:01:45 [INFO] train episode 1527: reward = 200.00, steps = 200
00:01:45 [INFO] train episode 1528: reward = 145.00, steps = 145
00:01:45 [INFO] train episode 1529: reward = 99.00, steps = 99
00:01:45 [INFO] train episode 1530: reward = 111.00, steps = 111
00:01:45 [INFO] train episode 1531: reward = 120.00, steps = 120
00:01:45 [INFO] train episode 1532: reward = 142.00, steps = 142
00:01:45 [INFO] train episode 1533: reward = 156.00, steps = 156
00:01:45 [INFO] train episode 1534: reward = 123.00, steps = 123
00:01:45 [INFO] train episode 1535: reward = 200.00, steps = 200
00:01:45 [INFO] train episode 1536: reward = 200.00, steps = 200
00:01:45 [INFO] train episode 1537: reward = 174.00, steps = 174
00:01:45 [INFO] train episode 1538: reward = 200.00, steps = 200
00:01:45 [INFO] train episode 1539: reward = 135.00, steps = 135
00:01:45 [INFO] train episode 1540: reward = 200.00, steps = 200
00:01:46 [INFO] train episode 1541: reward = 200.00, steps = 200
00:01:46 [INFO] train episode 1542: reward = 197.00, steps = 197
00:01:46 [INFO] train episode 1543: reward = 117.00, steps = 117
00:01:46 [INFO] train episode 1544: reward = 155.00, steps = 155
00:01:46 [INFO] train episode 1545: reward = 137.00, steps = 137
00:01:46 [INFO] train episode 1546: reward = 167.00, steps = 167
00:01:46 [INFO] train episode 1547: reward = 200.00, steps = 200
00:01:46 [INFO] train episode 1548: reward = 121.00, steps = 121
00:01:46 [INFO] train episode 1549: reward = 66.00, steps = 66
00:01:46 [INFO] train episode 1550: reward = 200.00, steps = 200
00:01:46 [INFO] train episode 1551: reward = 200.00, steps = 200
00:01:46 [INFO] train episode 1552: reward = 200.00, steps = 200
00:01:46 [INFO] train episode 1553: reward = 165.00, steps = 165
00:01:46 [INFO] train episode 1554: reward = 199.00, steps = 199
00:01:46 [INFO] train episode 1555: reward = 198.00, steps = 198
00:01:47 [INFO] train episode 1556: reward = 161.00, steps = 161
00:01:47 [INFO] train episode 1557: reward = 125.00, steps = 125
00:01:47 [INFO] train episode 1558: reward = 85.00, steps = 85
00:01:47 [INFO] train episode 1559: reward = 165.00, steps = 165
00:01:47 [INFO] train episode 1560: reward = 200.00, steps = 200
00:01:47 [INFO] train episode 1561: reward = 200.00, steps = 200
00:01:47 [INFO] train episode 1562: reward = 200.00, steps = 200
00:01:47 [INFO] train episode 1563: reward = 200.00, steps = 200
00:01:47 [INFO] train episode 1564: reward = 87.00, steps = 87
00:01:47 [INFO] train episode 1565: reward = 126.00, steps = 126
00:01:47 [INFO] train episode 1566: reward = 200.00, steps = 200
00:01:47 [INFO] train episode 1567: reward = 200.00, steps = 200
00:01:47 [INFO] train episode 1568: reward = 58.00, steps = 58
00:01:47 [INFO] train episode 1569: reward = 200.00, steps = 200
00:01:47 [INFO] train episode 1570: reward = 200.00, steps = 200
00:01:48 [INFO] train episode 1571: reward = 200.00, steps = 200
00:01:48 [INFO] train episode 1572: reward = 28.00, steps = 28
00:01:48 [INFO] train episode 1573: reward = 200.00, steps = 200
00:01:48 [INFO] train episode 1574: reward = 108.00, steps = 108
00:01:48 [INFO] train episode 1575: reward = 141.00, steps = 141
00:01:48 [INFO] train episode 1576: reward = 29.00, steps = 29
00:01:48 [INFO] train episode 1577: reward = 200.00, steps = 200
00:01:48 [INFO] train episode 1578: reward = 119.00, steps = 119
00:01:48 [INFO] train episode 1579: reward = 200.00, steps = 200
00:01:48 [INFO] train episode 1580: reward = 200.00, steps = 200
00:01:48 [INFO] train episode 1581: reward = 200.00, steps = 200
00:01:48 [INFO] train episode 1582: reward = 200.00, steps = 200
00:01:48 [INFO] train episode 1583: reward = 200.00, steps = 200
00:01:48 [INFO] train episode 1584: reward = 179.00, steps = 179
00:01:48 [INFO] train episode 1585: reward = 167.00, steps = 167
00:01:49 [INFO] train episode 1586: reward = 200.00, steps = 200
00:01:49 [INFO] train episode 1587: reward = 189.00, steps = 189
00:01:49 [INFO] train episode 1588: reward = 200.00, steps = 200
00:01:49 [INFO] train episode 1589: reward = 195.00, steps = 195
00:01:49 [INFO] train episode 1590: reward = 200.00, steps = 200
00:01:49 [INFO] train episode 1591: reward = 200.00, steps = 200
00:01:49 [INFO] train episode 1592: reward = 187.00, steps = 187
00:01:49 [INFO] train episode 1593: reward = 128.00, steps = 128
00:01:49 [INFO] train episode 1594: reward = 200.00, steps = 200
00:01:49 [INFO] train episode 1595: reward = 118.00, steps = 118
00:01:49 [INFO] train episode 1596: reward = 113.00, steps = 113
00:01:49 [INFO] train episode 1597: reward = 116.00, steps = 116
00:01:49 [INFO] train episode 1598: reward = 178.00, steps = 178
00:01:49 [INFO] train episode 1599: reward = 200.00, steps = 200
00:01:49 [INFO] train episode 1600: reward = 193.00, steps = 193
00:01:50 [INFO] train episode 1601: reward = 162.00, steps = 162
00:01:50 [INFO] train episode 1602: reward = 200.00, steps = 200
00:01:50 [INFO] train episode 1603: reward = 25.00, steps = 25
00:01:50 [INFO] train episode 1604: reward = 200.00, steps = 200
00:01:50 [INFO] train episode 1605: reward = 196.00, steps = 196
00:01:50 [INFO] train episode 1606: reward = 200.00, steps = 200
00:01:50 [INFO] train episode 1607: reward = 200.00, steps = 200
00:01:50 [INFO] train episode 1608: reward = 200.00, steps = 200
00:01:50 [INFO] train episode 1609: reward = 178.00, steps = 178
00:01:50 [INFO] train episode 1610: reward = 182.00, steps = 182
00:01:50 [INFO] train episode 1611: reward = 91.00, steps = 91
00:01:50 [INFO] train episode 1612: reward = 200.00, steps = 200
00:01:50 [INFO] train episode 1613: reward = 142.00, steps = 142
00:01:50 [INFO] train episode 1614: reward = 200.00, steps = 200
00:01:50 [INFO] train episode 1615: reward = 113.00, steps = 113
00:01:51 [INFO] train episode 1616: reward = 115.00, steps = 115
00:01:51 [INFO] train episode 1617: reward = 71.00, steps = 71
00:01:51 [INFO] train episode 1618: reward = 76.00, steps = 76
00:01:51 [INFO] train episode 1619: reward = 200.00, steps = 200
00:01:51 [INFO] train episode 1620: reward = 163.00, steps = 163
00:01:51 [INFO] train episode 1621: reward = 200.00, steps = 200
00:01:51 [INFO] train episode 1622: reward = 200.00, steps = 200
00:01:51 [INFO] train episode 1623: reward = 117.00, steps = 117
00:01:51 [INFO] train episode 1624: reward = 172.00, steps = 172
00:01:51 [INFO] train episode 1625: reward = 200.00, steps = 200
00:01:51 [INFO] train episode 1626: reward = 100.00, steps = 100
00:01:51 [INFO] train episode 1627: reward = 119.00, steps = 119
00:01:51 [INFO] train episode 1628: reward = 200.00, steps = 200
00:01:51 [INFO] train episode 1629: reward = 163.00, steps = 163
00:01:51 [INFO] train episode 1630: reward = 31.00, steps = 31
00:01:51 [INFO] train episode 1631: reward = 200.00, steps = 200
00:01:51 [INFO] train episode 1632: reward = 97.00, steps = 97
00:01:52 [INFO] train episode 1633: reward = 200.00, steps = 200
00:01:52 [INFO] train episode 1634: reward = 69.00, steps = 69
00:01:52 [INFO] train episode 1635: reward = 200.00, steps = 200
00:01:52 [INFO] train episode 1636: reward = 174.00, steps = 174
00:01:52 [INFO] train episode 1637: reward = 200.00, steps = 200
00:01:52 [INFO] train episode 1638: reward = 62.00, steps = 62
00:01:52 [INFO] train episode 1639: reward = 200.00, steps = 200
00:01:52 [INFO] train episode 1640: reward = 200.00, steps = 200
00:01:52 [INFO] train episode 1641: reward = 163.00, steps = 163
00:01:52 [INFO] train episode 1642: reward = 145.00, steps = 145
00:01:52 [INFO] train episode 1643: reward = 65.00, steps = 65
00:01:52 [INFO] train episode 1644: reward = 120.00, steps = 120
00:01:52 [INFO] train episode 1645: reward = 200.00, steps = 200
00:01:52 [INFO] train episode 1646: reward = 145.00, steps = 145
00:01:52 [INFO] train episode 1647: reward = 123.00, steps = 123
00:01:52 [INFO] train episode 1648: reward = 150.00, steps = 150
00:01:52 [INFO] train episode 1649: reward = 200.00, steps = 200
00:01:53 [INFO] train episode 1650: reward = 126.00, steps = 126
00:01:53 [INFO] train episode 1651: reward = 105.00, steps = 105
00:01:53 [INFO] train episode 1652: reward = 200.00, steps = 200
00:01:53 [INFO] train episode 1653: reward = 161.00, steps = 161
00:01:53 [INFO] train episode 1654: reward = 200.00, steps = 200
00:01:53 [INFO] train episode 1655: reward = 200.00, steps = 200
00:01:53 [INFO] train episode 1656: reward = 104.00, steps = 104
00:01:53 [INFO] train episode 1657: reward = 172.00, steps = 172
00:01:53 [INFO] train episode 1658: reward = 200.00, steps = 200
00:01:53 [INFO] train episode 1659: reward = 200.00, steps = 200
00:01:53 [INFO] train episode 1660: reward = 150.00, steps = 150
00:01:53 [INFO] train episode 1661: reward = 162.00, steps = 162
00:01:53 [INFO] train episode 1662: reward = 191.00, steps = 191
00:01:53 [INFO] train episode 1663: reward = 200.00, steps = 200
00:01:54 [INFO] train episode 1664: reward = 90.00, steps = 90
00:01:54 [INFO] train episode 1665: reward = 160.00, steps = 160
00:01:54 [INFO] train episode 1666: reward = 163.00, steps = 163
00:01:54 [INFO] train episode 1667: reward = 200.00, steps = 200
00:01:54 [INFO] train episode 1668: reward = 163.00, steps = 163
00:01:54 [INFO] train episode 1669: reward = 200.00, steps = 200
00:01:54 [INFO] train episode 1670: reward = 200.00, steps = 200
00:01:54 [INFO] train episode 1671: reward = 200.00, steps = 200
00:01:54 [INFO] train episode 1672: reward = 200.00, steps = 200
00:01:54 [INFO] train episode 1673: reward = 106.00, steps = 106
00:01:54 [INFO] train episode 1674: reward = 162.00, steps = 162
00:01:54 [INFO] train episode 1675: reward = 138.00, steps = 138
00:01:54 [INFO] train episode 1676: reward = 155.00, steps = 155
00:01:54 [INFO] train episode 1677: reward = 200.00, steps = 200
00:01:54 [INFO] train episode 1678: reward = 200.00, steps = 200
00:01:54 [INFO] train episode 1679: reward = 200.00, steps = 200
00:01:55 [INFO] train episode 1680: reward = 200.00, steps = 200
00:01:55 [INFO] train episode 1681: reward = 200.00, steps = 200
00:01:55 [INFO] train episode 1682: reward = 200.00, steps = 200
00:01:55 [INFO] train episode 1683: reward = 200.00, steps = 200
00:01:55 [INFO] train episode 1684: reward = 108.00, steps = 108
00:01:55 [INFO] train episode 1685: reward = 186.00, steps = 186
00:01:55 [INFO] train episode 1686: reward = 132.00, steps = 132
00:01:55 [INFO] train episode 1687: reward = 200.00, steps = 200
00:01:55 [INFO] train episode 1688: reward = 200.00, steps = 200
00:01:55 [INFO] train episode 1689: reward = 29.00, steps = 29
00:01:55 [INFO] train episode 1690: reward = 200.00, steps = 200
00:01:55 [INFO] train episode 1691: reward = 200.00, steps = 200
00:01:55 [INFO] train episode 1692: reward = 184.00, steps = 184
00:01:55 [INFO] train episode 1693: reward = 176.00, steps = 176
00:01:56 [INFO] train episode 1694: reward = 150.00, steps = 150
00:01:56 [INFO] train episode 1695: reward = 155.00, steps = 155
00:01:56 [INFO] train episode 1696: reward = 200.00, steps = 200
00:01:56 [INFO] train episode 1697: reward = 108.00, steps = 108
00:01:56 [INFO] train episode 1698: reward = 181.00, steps = 181
00:01:56 [INFO] train episode 1699: reward = 200.00, steps = 200
00:01:56 [INFO] train episode 1700: reward = 164.00, steps = 164
00:01:56 [INFO] train episode 1701: reward = 24.00, steps = 24
00:01:56 [INFO] train episode 1702: reward = 200.00, steps = 200
00:01:56 [INFO] train episode 1703: reward = 200.00, steps = 200
00:01:56 [INFO] train episode 1704: reward = 116.00, steps = 116
00:01:56 [INFO] train episode 1705: reward = 174.00, steps = 174
00:01:56 [INFO] train episode 1706: reward = 169.00, steps = 169
00:01:56 [INFO] train episode 1707: reward = 107.00, steps = 107
00:01:56 [INFO] train episode 1708: reward = 200.00, steps = 200
00:01:57 [INFO] train episode 1709: reward = 200.00, steps = 200
00:01:57 [INFO] train episode 1710: reward = 133.00, steps = 133
00:01:57 [INFO] train episode 1711: reward = 150.00, steps = 150
00:01:57 [INFO] train episode 1712: reward = 200.00, steps = 200
00:01:57 [INFO] train episode 1713: reward = 200.00, steps = 200
00:01:57 [INFO] train episode 1714: reward = 179.00, steps = 179
00:01:57 [INFO] train episode 1715: reward = 200.00, steps = 200
00:01:57 [INFO] train episode 1716: reward = 200.00, steps = 200
00:01:57 [INFO] train episode 1717: reward = 55.00, steps = 55
00:01:57 [INFO] train episode 1718: reward = 200.00, steps = 200
00:01:57 [INFO] train episode 1719: reward = 200.00, steps = 200
00:01:57 [INFO] train episode 1720: reward = 200.00, steps = 200
00:01:57 [INFO] train episode 1721: reward = 200.00, steps = 200
00:01:57 [INFO] train episode 1722: reward = 200.00, steps = 200
00:01:58 [INFO] train episode 1723: reward = 193.00, steps = 193
00:01:58 [INFO] train episode 1724: reward = 200.00, steps = 200
00:01:58 [INFO] train episode 1725: reward = 160.00, steps = 160
00:01:58 [INFO] train episode 1726: reward = 113.00, steps = 113
00:01:58 [INFO] train episode 1727: reward = 146.00, steps = 146
00:01:58 [INFO] train episode 1728: reward = 150.00, steps = 150
00:01:58 [INFO] train episode 1729: reward = 193.00, steps = 193
00:01:58 [INFO] train episode 1730: reward = 188.00, steps = 188
00:01:58 [INFO] train episode 1731: reward = 200.00, steps = 200
00:01:58 [INFO] train episode 1732: reward = 200.00, steps = 200
00:01:58 [INFO] train episode 1733: reward = 200.00, steps = 200
00:01:58 [INFO] train episode 1734: reward = 127.00, steps = 127
00:01:58 [INFO] train episode 1735: reward = 84.00, steps = 84
00:01:58 [INFO] train episode 1736: reward = 151.00, steps = 151
00:01:58 [INFO] train episode 1737: reward = 64.00, steps = 64
00:01:59 [INFO] train episode 1738: reward = 200.00, steps = 200
00:01:59 [INFO] train episode 1739: reward = 200.00, steps = 200
00:01:59 [INFO] train episode 1740: reward = 200.00, steps = 200
00:01:59 [INFO] train episode 1741: reward = 169.00, steps = 169
00:01:59 [INFO] train episode 1742: reward = 200.00, steps = 200
00:01:59 [INFO] train episode 1743: reward = 200.00, steps = 200
00:01:59 [INFO] train episode 1744: reward = 200.00, steps = 200
00:01:59 [INFO] train episode 1745: reward = 200.00, steps = 200
00:01:59 [INFO] train episode 1746: reward = 115.00, steps = 115
00:01:59 [INFO] train episode 1747: reward = 200.00, steps = 200
00:01:59 [INFO] train episode 1748: reward = 200.00, steps = 200
00:01:59 [INFO] train episode 1749: reward = 119.00, steps = 119
00:01:59 [INFO] train episode 1750: reward = 200.00, steps = 200
00:01:59 [INFO] train episode 1751: reward = 131.00, steps = 131
00:02:00 [INFO] train episode 1752: reward = 200.00, steps = 200
00:02:00 [INFO] train episode 1753: reward = 25.00, steps = 25
00:02:00 [INFO] train episode 1754: reward = 200.00, steps = 200
00:02:00 [INFO] train episode 1755: reward = 171.00, steps = 171
00:02:00 [INFO] train episode 1756: reward = 128.00, steps = 128
00:02:00 [INFO] train episode 1757: reward = 200.00, steps = 200
00:02:00 [INFO] train episode 1758: reward = 136.00, steps = 136
00:02:00 [INFO] train episode 1759: reward = 81.00, steps = 81
00:02:00 [INFO] train episode 1760: reward = 200.00, steps = 200
00:02:00 [INFO] train episode 1761: reward = 200.00, steps = 200
00:02:00 [INFO] train episode 1762: reward = 159.00, steps = 159
00:02:00 [INFO] train episode 1763: reward = 59.00, steps = 59
00:02:00 [INFO] train episode 1764: reward = 200.00, steps = 200
00:02:00 [INFO] train episode 1765: reward = 200.00, steps = 200
00:02:00 [INFO] train episode 1766: reward = 200.00, steps = 200
00:02:00 [INFO] train episode 1767: reward = 64.00, steps = 64
00:02:01 [INFO] train episode 1768: reward = 200.00, steps = 200
00:02:01 [INFO] train episode 1769: reward = 195.00, steps = 195
00:02:01 [INFO] train episode 1770: reward = 144.00, steps = 144
00:02:01 [INFO] train episode 1771: reward = 200.00, steps = 200
00:02:01 [INFO] train episode 1772: reward = 102.00, steps = 102
00:02:01 [INFO] train episode 1773: reward = 156.00, steps = 156
00:02:01 [INFO] train episode 1774: reward = 200.00, steps = 200
00:02:01 [INFO] train episode 1775: reward = 135.00, steps = 135
00:02:01 [INFO] train episode 1776: reward = 79.00, steps = 79
00:02:01 [INFO] train episode 1777: reward = 28.00, steps = 28
00:02:01 [INFO] train episode 1778: reward = 157.00, steps = 157
00:02:01 [INFO] train episode 1779: reward = 114.00, steps = 114
00:02:01 [INFO] train episode 1780: reward = 57.00, steps = 57
00:02:01 [INFO] train episode 1781: reward = 138.00, steps = 138
00:02:01 [INFO] train episode 1782: reward = 200.00, steps = 200
00:02:01 [INFO] train episode 1783: reward = 200.00, steps = 200
00:02:01 [INFO] train episode 1784: reward = 181.00, steps = 181
00:02:02 [INFO] train episode 1785: reward = 200.00, steps = 200
00:02:02 [INFO] train episode 1786: reward = 200.00, steps = 200
00:02:02 [INFO] train episode 1787: reward = 97.00, steps = 97
00:02:02 [INFO] train episode 1788: reward = 139.00, steps = 139
00:02:02 [INFO] train episode 1789: reward = 109.00, steps = 109
00:02:02 [INFO] train episode 1790: reward = 200.00, steps = 200
00:02:02 [INFO] train episode 1791: reward = 168.00, steps = 168
00:02:02 [INFO] train episode 1792: reward = 200.00, steps = 200
00:02:02 [INFO] train episode 1793: reward = 200.00, steps = 200
00:02:02 [INFO] train episode 1794: reward = 200.00, steps = 200
00:02:02 [INFO] train episode 1795: reward = 200.00, steps = 200
00:02:02 [INFO] train episode 1796: reward = 133.00, steps = 133
00:02:02 [INFO] train episode 1797: reward = 200.00, steps = 200
00:02:02 [INFO] train episode 1798: reward = 200.00, steps = 200
00:02:03 [INFO] train episode 1799: reward = 178.00, steps = 178
00:02:03 [INFO] train episode 1800: reward = 163.00, steps = 163
00:02:03 [INFO] train episode 1801: reward = 196.00, steps = 196
00:02:03 [INFO] train episode 1802: reward = 200.00, steps = 200
00:02:03 [INFO] train episode 1803: reward = 156.00, steps = 156
00:02:03 [INFO] train episode 1804: reward = 130.00, steps = 130
00:02:03 [INFO] train episode 1805: reward = 200.00, steps = 200
00:02:03 [INFO] train episode 1806: reward = 200.00, steps = 200
00:02:03 [INFO] train episode 1807: reward = 200.00, steps = 200
00:02:03 [INFO] train episode 1808: reward = 200.00, steps = 200
00:02:03 [INFO] train episode 1809: reward = 200.00, steps = 200
00:02:03 [INFO] train episode 1810: reward = 200.00, steps = 200
00:02:03 [INFO] train episode 1811: reward = 200.00, steps = 200
00:02:03 [INFO] train episode 1812: reward = 200.00, steps = 200
00:02:04 [INFO] train episode 1813: reward = 200.00, steps = 200
00:02:04 [INFO] train episode 1814: reward = 200.00, steps = 200
00:02:04 [INFO] train episode 1815: reward = 170.00, steps = 170
00:02:04 [INFO] train episode 1816: reward = 200.00, steps = 200
00:02:04 [INFO] train episode 1817: reward = 200.00, steps = 200
00:02:04 [INFO] train episode 1818: reward = 159.00, steps = 159
00:02:04 [INFO] train episode 1819: reward = 200.00, steps = 200
00:02:04 [INFO] train episode 1820: reward = 200.00, steps = 200
00:02:04 [INFO] train episode 1821: reward = 200.00, steps = 200
00:02:04 [INFO] train episode 1822: reward = 200.00, steps = 200
00:02:04 [INFO] train episode 1823: reward = 159.00, steps = 159
00:02:04 [INFO] train episode 1824: reward = 147.00, steps = 147
00:02:04 [INFO] train episode 1825: reward = 200.00, steps = 200
00:02:05 [INFO] train episode 1826: reward = 200.00, steps = 200
00:02:05 [INFO] train episode 1827: reward = 200.00, steps = 200
00:02:05 [INFO] train episode 1828: reward = 177.00, steps = 177
00:02:05 [INFO] train episode 1829: reward = 118.00, steps = 118
00:02:05 [INFO] train episode 1830: reward = 153.00, steps = 153
00:02:05 [INFO] train episode 1831: reward = 72.00, steps = 72
00:02:05 [INFO] train episode 1832: reward = 200.00, steps = 200
00:02:05 [INFO] train episode 1833: reward = 200.00, steps = 200
00:02:05 [INFO] train episode 1834: reward = 200.00, steps = 200
00:02:05 [INFO] train episode 1835: reward = 102.00, steps = 102
00:02:05 [INFO] train episode 1836: reward = 104.00, steps = 104
00:02:05 [INFO] train episode 1837: reward = 145.00, steps = 145
00:02:05 [INFO] train episode 1838: reward = 200.00, steps = 200
00:02:05 [INFO] train episode 1839: reward = 200.00, steps = 200
00:02:06 [INFO] train episode 1840: reward = 200.00, steps = 200
00:02:06 [INFO] train episode 1841: reward = 151.00, steps = 151
00:02:06 [INFO] train episode 1842: reward = 195.00, steps = 195
00:02:06 [INFO] train episode 1843: reward = 129.00, steps = 129
00:02:06 [INFO] train episode 1844: reward = 200.00, steps = 200
00:02:06 [INFO] train episode 1845: reward = 65.00, steps = 65
00:02:06 [INFO] train episode 1846: reward = 200.00, steps = 200
00:02:06 [INFO] train episode 1847: reward = 200.00, steps = 200
00:02:06 [INFO] train episode 1848: reward = 64.00, steps = 64
00:02:06 [INFO] train episode 1849: reward = 81.00, steps = 81
00:02:06 [INFO] train episode 1850: reward = 200.00, steps = 200
00:02:06 [INFO] train episode 1851: reward = 63.00, steps = 63
00:02:06 [INFO] train episode 1852: reward = 200.00, steps = 200
00:02:06 [INFO] train episode 1853: reward = 138.00, steps = 138
00:02:06 [INFO] train episode 1854: reward = 200.00, steps = 200
00:02:06 [INFO] train episode 1855: reward = 194.00, steps = 194
00:02:07 [INFO] train episode 1856: reward = 183.00, steps = 183
00:02:07 [INFO] train episode 1857: reward = 200.00, steps = 200
00:02:07 [INFO] train episode 1858: reward = 200.00, steps = 200
00:02:07 [INFO] train episode 1859: reward = 200.00, steps = 200
00:02:07 [INFO] train episode 1860: reward = 182.00, steps = 182
00:02:07 [INFO] train episode 1861: reward = 64.00, steps = 64
00:02:07 [INFO] train episode 1862: reward = 118.00, steps = 118
00:02:07 [INFO] train episode 1863: reward = 193.00, steps = 193
00:02:07 [INFO] train episode 1864: reward = 144.00, steps = 144
00:02:07 [INFO] train episode 1865: reward = 177.00, steps = 177
00:02:07 [INFO] train episode 1866: reward = 200.00, steps = 200
00:02:07 [INFO] train episode 1867: reward = 141.00, steps = 141
00:02:07 [INFO] train episode 1868: reward = 200.00, steps = 200
00:02:07 [INFO] train episode 1869: reward = 200.00, steps = 200
00:02:07 [INFO] train episode 1870: reward = 121.00, steps = 121
00:02:07 [INFO] train episode 1871: reward = 127.00, steps = 127
00:02:08 [INFO] train episode 1872: reward = 135.00, steps = 135
00:02:08 [INFO] train episode 1873: reward = 200.00, steps = 200
00:02:08 [INFO] train episode 1874: reward = 152.00, steps = 152
00:02:08 [INFO] train episode 1875: reward = 188.00, steps = 188
00:02:08 [INFO] train episode 1876: reward = 200.00, steps = 200
00:02:08 [INFO] train episode 1877: reward = 200.00, steps = 200
00:02:08 [INFO] train episode 1878: reward = 166.00, steps = 166
00:02:08 [INFO] train episode 1879: reward = 200.00, steps = 200
00:02:08 [INFO] train episode 1880: reward = 200.00, steps = 200
00:02:08 [INFO] train episode 1881: reward = 140.00, steps = 140
00:02:08 [INFO] train episode 1882: reward = 143.00, steps = 143
00:02:08 [INFO] train episode 1883: reward = 200.00, steps = 200
00:02:08 [INFO] train episode 1884: reward = 127.00, steps = 127
00:02:08 [INFO] train episode 1885: reward = 182.00, steps = 182
00:02:09 [INFO] train episode 1886: reward = 200.00, steps = 200
00:02:09 [INFO] train episode 1887: reward = 200.00, steps = 200
00:02:09 [INFO] train episode 1888: reward = 145.00, steps = 145
00:02:09 [INFO] train episode 1889: reward = 77.00, steps = 77
00:02:09 [INFO] train episode 1890: reward = 138.00, steps = 138
00:02:09 [INFO] train episode 1891: reward = 178.00, steps = 178
00:02:09 [INFO] train episode 1892: reward = 185.00, steps = 185
00:02:09 [INFO] train episode 1893: reward = 200.00, steps = 200
00:02:09 [INFO] train episode 1894: reward = 200.00, steps = 200
00:02:09 [INFO] train episode 1895: reward = 200.00, steps = 200
00:02:09 [INFO] train episode 1896: reward = 123.00, steps = 123
00:02:09 [INFO] train episode 1897: reward = 107.00, steps = 107
00:02:09 [INFO] train episode 1898: reward = 109.00, steps = 109
00:02:09 [INFO] train episode 1899: reward = 58.00, steps = 58
00:02:09 [INFO] train episode 1900: reward = 182.00, steps = 182
00:02:09 [INFO] train episode 1901: reward = 200.00, steps = 200
00:02:10 [INFO] train episode 1902: reward = 200.00, steps = 200
00:02:10 [INFO] train episode 1903: reward = 170.00, steps = 170
00:02:10 [INFO] train episode 1904: reward = 200.00, steps = 200
00:02:10 [INFO] train episode 1905: reward = 200.00, steps = 200
00:02:10 [INFO] train episode 1906: reward = 180.00, steps = 180
00:02:10 [INFO] train episode 1907: reward = 54.00, steps = 54
00:02:10 [INFO] train episode 1908: reward = 139.00, steps = 139
00:02:10 [INFO] train episode 1909: reward = 200.00, steps = 200
00:02:10 [INFO] train episode 1910: reward = 200.00, steps = 200
00:02:10 [INFO] train episode 1911: reward = 200.00, steps = 200
00:02:10 [INFO] train episode 1912: reward = 153.00, steps = 153
00:02:10 [INFO] train episode 1913: reward = 166.00, steps = 166
00:02:10 [INFO] train episode 1914: reward = 150.00, steps = 150
00:02:10 [INFO] train episode 1915: reward = 136.00, steps = 136
00:02:10 [INFO] train episode 1916: reward = 139.00, steps = 139
00:02:10 [INFO] train episode 1917: reward = 200.00, steps = 200
00:02:11 [INFO] train episode 1918: reward = 108.00, steps = 108
00:02:11 [INFO] train episode 1919: reward = 161.00, steps = 161
00:02:11 [INFO] train episode 1920: reward = 162.00, steps = 162
00:02:11 [INFO] train episode 1921: reward = 200.00, steps = 200
00:02:11 [INFO] train episode 1922: reward = 67.00, steps = 67
00:02:11 [INFO] train episode 1923: reward = 108.00, steps = 108
00:02:11 [INFO] train episode 1924: reward = 200.00, steps = 200
00:02:11 [INFO] train episode 1925: reward = 157.00, steps = 157
00:02:11 [INFO] train episode 1926: reward = 106.00, steps = 106
00:02:11 [INFO] train episode 1927: reward = 200.00, steps = 200
00:02:11 [INFO] train episode 1928: reward = 119.00, steps = 119
00:02:11 [INFO] train episode 1929: reward = 200.00, steps = 200
00:02:11 [INFO] train episode 1930: reward = 136.00, steps = 136
00:02:11 [INFO] train episode 1931: reward = 200.00, steps = 200
00:02:11 [INFO] train episode 1932: reward = 200.00, steps = 200
00:02:11 [INFO] train episode 1933: reward = 200.00, steps = 200
00:02:12 [INFO] train episode 1934: reward = 176.00, steps = 176
00:02:12 [INFO] train episode 1935: reward = 200.00, steps = 200
00:02:12 [INFO] train episode 1936: reward = 183.00, steps = 183
00:02:12 [INFO] train episode 1937: reward = 200.00, steps = 200
00:02:12 [INFO] train episode 1938: reward = 200.00, steps = 200
00:02:12 [INFO] train episode 1939: reward = 200.00, steps = 200
00:02:12 [INFO] train episode 1940: reward = 166.00, steps = 166
00:02:12 [INFO] train episode 1941: reward = 97.00, steps = 97
00:02:12 [INFO] train episode 1942: reward = 163.00, steps = 163
00:02:12 [INFO] train episode 1943: reward = 195.00, steps = 195
00:02:12 [INFO] train episode 1944: reward = 188.00, steps = 188
00:02:12 [INFO] train episode 1945: reward = 200.00, steps = 200
00:02:12 [INFO] train episode 1946: reward = 200.00, steps = 200
00:02:12 [INFO] train episode 1947: reward = 164.00, steps = 164
00:02:13 [INFO] train episode 1948: reward = 200.00, steps = 200
00:02:13 [INFO] train episode 1949: reward = 141.00, steps = 141
00:02:13 [INFO] train episode 1950: reward = 180.00, steps = 180
00:02:13 [INFO] train episode 1951: reward = 200.00, steps = 200
00:02:13 [INFO] train episode 1952: reward = 200.00, steps = 200
00:02:13 [INFO] train episode 1953: reward = 142.00, steps = 142
00:02:13 [INFO] train episode 1954: reward = 115.00, steps = 115
00:02:13 [INFO] train episode 1955: reward = 200.00, steps = 200
00:02:13 [INFO] train episode 1956: reward = 152.00, steps = 152
00:02:13 [INFO] train episode 1957: reward = 200.00, steps = 200
00:02:13 [INFO] train episode 1958: reward = 158.00, steps = 158
00:02:13 [INFO] train episode 1959: reward = 200.00, steps = 200
00:02:13 [INFO] train episode 1960: reward = 200.00, steps = 200
00:02:13 [INFO] train episode 1961: reward = 79.00, steps = 79
00:02:13 [INFO] train episode 1962: reward = 160.00, steps = 160
00:02:14 [INFO] train episode 1963: reward = 200.00, steps = 200
00:02:14 [INFO] train episode 1964: reward = 200.00, steps = 200
00:02:14 [INFO] train episode 1965: reward = 200.00, steps = 200
00:02:14 [INFO] train episode 1966: reward = 200.00, steps = 200
00:02:14 [INFO] train episode 1967: reward = 134.00, steps = 134
00:02:14 [INFO] train episode 1968: reward = 200.00, steps = 200
00:02:14 [INFO] train episode 1969: reward = 166.00, steps = 166
00:02:14 [INFO] train episode 1970: reward = 146.00, steps = 146
00:02:14 [INFO] train episode 1971: reward = 180.00, steps = 180
00:02:14 [INFO] train episode 1972: reward = 200.00, steps = 200
00:02:14 [INFO] train episode 1973: reward = 170.00, steps = 170
00:02:14 [INFO] train episode 1974: reward = 200.00, steps = 200
00:02:14 [INFO] train episode 1975: reward = 152.00, steps = 152
00:02:14 [INFO] train episode 1976: reward = 200.00, steps = 200
00:02:15 [INFO] train episode 1977: reward = 200.00, steps = 200
00:02:15 [INFO] train episode 1978: reward = 186.00, steps = 186
00:02:15 [INFO] train episode 1979: reward = 189.00, steps = 189
00:02:15 [INFO] train episode 1980: reward = 121.00, steps = 121
00:02:15 [INFO] train episode 1981: reward = 54.00, steps = 54
00:02:15 [INFO] train episode 1982: reward = 139.00, steps = 139
00:02:15 [INFO] train episode 1983: reward = 38.00, steps = 38
00:02:15 [INFO] train episode 1984: reward = 146.00, steps = 146
00:02:15 [INFO] train episode 1985: reward = 200.00, steps = 200
00:02:15 [INFO] train episode 1986: reward = 171.00, steps = 171
00:02:15 [INFO] train episode 1987: reward = 176.00, steps = 176
00:02:15 [INFO] train episode 1988: reward = 192.00, steps = 192
00:02:15 [INFO] train episode 1989: reward = 195.00, steps = 195
00:02:15 [INFO] train episode 1990: reward = 51.00, steps = 51
00:02:15 [INFO] train episode 1991: reward = 176.00, steps = 176
00:02:15 [INFO] train episode 1992: reward = 200.00, steps = 200
00:02:15 [INFO] train episode 1993: reward = 128.00, steps = 128
00:02:15 [INFO] train episode 1994: reward = 200.00, steps = 200
00:02:16 [INFO] train episode 1995: reward = 173.00, steps = 173
00:02:16 [INFO] train episode 1996: reward = 166.00, steps = 166
00:02:16 [INFO] train episode 1997: reward = 200.00, steps = 200
00:02:16 [INFO] train episode 1998: reward = 200.00, steps = 200
00:02:16 [INFO] train episode 1999: reward = 145.00, steps = 145
00:02:16 [INFO] train episode 2000: reward = 199.00, steps = 199
00:02:16 [INFO] train episode 2001: reward = 200.00, steps = 200
00:02:16 [INFO] train episode 2002: reward = 200.00, steps = 200
00:02:16 [INFO] train episode 2003: reward = 200.00, steps = 200
00:02:16 [INFO] train episode 2004: reward = 31.00, steps = 31
00:02:16 [INFO] train episode 2005: reward = 42.00, steps = 42
00:02:16 [INFO] train episode 2006: reward = 200.00, steps = 200
00:02:16 [INFO] train episode 2007: reward = 141.00, steps = 141
00:02:16 [INFO] train episode 2008: reward = 180.00, steps = 180
00:02:16 [INFO] train episode 2009: reward = 200.00, steps = 200
00:02:17 [INFO] train episode 2010: reward = 200.00, steps = 200
00:02:17 [INFO] train episode 2011: reward = 108.00, steps = 108
00:02:17 [INFO] train episode 2012: reward = 200.00, steps = 200
00:02:17 [INFO] train episode 2013: reward = 97.00, steps = 97
00:02:17 [INFO] train episode 2014: reward = 130.00, steps = 130
00:02:17 [INFO] train episode 2015: reward = 200.00, steps = 200
00:02:17 [INFO] train episode 2016: reward = 200.00, steps = 200
00:02:17 [INFO] train episode 2017: reward = 130.00, steps = 130
00:02:17 [INFO] train episode 2018: reward = 105.00, steps = 105
00:02:17 [INFO] train episode 2019: reward = 156.00, steps = 156
00:02:17 [INFO] train episode 2020: reward = 200.00, steps = 200
00:02:17 [INFO] train episode 2021: reward = 200.00, steps = 200
00:02:17 [INFO] train episode 2022: reward = 98.00, steps = 98
00:02:17 [INFO] train episode 2023: reward = 200.00, steps = 200
00:02:17 [INFO] train episode 2024: reward = 200.00, steps = 200
00:02:17 [INFO] train episode 2025: reward = 200.00, steps = 200
00:02:18 [INFO] train episode 2026: reward = 200.00, steps = 200
00:02:18 [INFO] train episode 2027: reward = 200.00, steps = 200
00:02:18 [INFO] train episode 2028: reward = 129.00, steps = 129
00:02:18 [INFO] train episode 2029: reward = 200.00, steps = 200
00:02:18 [INFO] train episode 2030: reward = 200.00, steps = 200
00:02:18 [INFO] train episode 2031: reward = 200.00, steps = 200
00:02:18 [INFO] train episode 2032: reward = 200.00, steps = 200
00:02:18 [INFO] train episode 2033: reward = 149.00, steps = 149
00:02:18 [INFO] train episode 2034: reward = 200.00, steps = 200
00:02:18 [INFO] train episode 2035: reward = 162.00, steps = 162
00:02:18 [INFO] train episode 2036: reward = 200.00, steps = 200
00:02:18 [INFO] train episode 2037: reward = 162.00, steps = 162
00:02:18 [INFO] train episode 2038: reward = 190.00, steps = 190
00:02:18 [INFO] train episode 2039: reward = 23.00, steps = 23
00:02:19 [INFO] train episode 2040: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2041: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2042: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2043: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2044: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2045: reward = 79.00, steps = 79
00:02:19 [INFO] train episode 2046: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2047: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2048: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2049: reward = 72.00, steps = 72
00:02:19 [INFO] train episode 2050: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2051: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2052: reward = 164.00, steps = 164
00:02:19 [INFO] train episode 2053: reward = 200.00, steps = 200
00:02:19 [INFO] train episode 2054: reward = 200.00, steps = 200
00:02:20 [INFO] train episode 2055: reward = 200.00, steps = 200
00:02:20 [INFO] train episode 2056: reward = 200.00, steps = 200
00:02:20 [INFO] train episode 2057: reward = 200.00, steps = 200
00:02:20 [INFO] train episode 2058: reward = 200.00, steps = 200
00:02:20 [INFO] train episode 2059: reward = 200.00, steps = 200
00:02:20 [INFO] train episode 2060: reward = 173.00, steps = 173
00:02:20 [INFO] train episode 2061: reward = 200.00, steps = 200
00:02:20 [INFO] train episode 2062: reward = 150.00, steps = 150
00:02:20 [INFO] train episode 2063: reward = 199.00, steps = 199
00:02:20 [INFO] train episode 2064: reward = 200.00, steps = 200
00:02:20 [INFO] train episode 2065: reward = 200.00, steps = 200
00:02:20 [INFO] train episode 2066: reward = 200.00, steps = 200
00:02:20 [INFO] train episode 2067: reward = 144.00, steps = 144
00:02:21 [INFO] train episode 2068: reward = 200.00, steps = 200
00:02:21 [INFO] train episode 2069: reward = 200.00, steps = 200
00:02:21 [INFO] train episode 2070: reward = 129.00, steps = 129
00:02:21 [INFO] train episode 2071: reward = 144.00, steps = 144
00:02:21 [INFO] train episode 2072: reward = 200.00, steps = 200
00:02:21 [INFO] train episode 2073: reward = 200.00, steps = 200
00:02:21 [INFO] train episode 2074: reward = 200.00, steps = 200
00:02:21 [INFO] train episode 2075: reward = 180.00, steps = 180
00:02:21 [INFO] train episode 2076: reward = 200.00, steps = 200
00:02:21 [INFO] train episode 2077: reward = 200.00, steps = 200
00:02:21 [INFO] train episode 2078: reward = 200.00, steps = 200
00:02:21 [INFO] train episode 2079: reward = 150.00, steps = 150
00:02:21 [INFO] train episode 2080: reward = 177.00, steps = 177
00:02:21 [INFO] train episode 2081: reward = 182.00, steps = 182
00:02:21 [INFO] train episode 2082: reward = 169.00, steps = 169
00:02:22 [INFO] train episode 2083: reward = 166.00, steps = 166
00:02:22 [INFO] train episode 2084: reward = 200.00, steps = 200
00:02:22 [INFO] train episode 2085: reward = 78.00, steps = 78
00:02:22 [INFO] train episode 2086: reward = 200.00, steps = 200
00:02:22 [INFO] train episode 2087: reward = 141.00, steps = 141
00:02:22 [INFO] train episode 2088: reward = 200.00, steps = 200
00:02:22 [INFO] train episode 2089: reward = 200.00, steps = 200
00:02:22 [INFO] train episode 2090: reward = 200.00, steps = 200
00:02:22 [INFO] train episode 2091: reward = 200.00, steps = 200
00:02:22 [INFO] train episode 2092: reward = 200.00, steps = 200
00:02:22 [INFO] train episode 2093: reward = 132.00, steps = 132
00:02:22 [INFO] train episode 2094: reward = 200.00, steps = 200
00:02:22 [INFO] train episode 2095: reward = 200.00, steps = 200
00:02:23 [INFO] train episode 2096: reward = 200.00, steps = 200
00:02:23 [INFO] train episode 2097: reward = 200.00, steps = 200
00:02:23 [INFO] train episode 2098: reward = 24.00, steps = 24
00:02:23 [INFO] train episode 2099: reward = 19.00, steps = 19
00:02:23 [INFO] train episode 2100: reward = 185.00, steps = 185
00:02:23 [INFO] train episode 2101: reward = 200.00, steps = 200
00:02:23 [INFO] train episode 2102: reward = 35.00, steps = 35
00:02:23 [INFO] train episode 2103: reward = 29.00, steps = 29
00:02:23 [INFO] train episode 2104: reward = 125.00, steps = 125
00:02:23 [INFO] train episode 2105: reward = 200.00, steps = 200
00:02:23 [INFO] train episode 2106: reward = 165.00, steps = 165
00:02:23 [INFO] train episode 2107: reward = 200.00, steps = 200
00:02:23 [INFO] train episode 2108: reward = 200.00, steps = 200
00:02:23 [INFO] train episode 2109: reward = 200.00, steps = 200
00:02:23 [INFO] train episode 2110: reward = 72.00, steps = 72
00:02:23 [INFO] train episode 2111: reward = 200.00, steps = 200
00:02:23 [INFO] train episode 2112: reward = 200.00, steps = 200
00:02:24 [INFO] train episode 2113: reward = 200.00, steps = 200
00:02:24 [INFO] train episode 2114: reward = 196.00, steps = 196
00:02:24 [INFO] train episode 2115: reward = 192.00, steps = 192
00:02:24 [INFO] train episode 2116: reward = 94.00, steps = 94
00:02:24 [INFO] train episode 2117: reward = 129.00, steps = 129
00:02:24 [INFO] train episode 2118: reward = 111.00, steps = 111
00:02:24 [INFO] train episode 2119: reward = 200.00, steps = 200
00:02:24 [INFO] train episode 2120: reward = 183.00, steps = 183
00:02:24 [INFO] train episode 2121: reward = 200.00, steps = 200
00:02:24 [INFO] train episode 2122: reward = 94.00, steps = 94
00:02:24 [INFO] train episode 2123: reward = 200.00, steps = 200
00:02:24 [INFO] train episode 2124: reward = 190.00, steps = 190
00:02:24 [INFO] train episode 2125: reward = 200.00, steps = 200
00:02:24 [INFO] train episode 2126: reward = 200.00, steps = 200
00:02:24 [INFO] train episode 2127: reward = 153.00, steps = 153
00:02:24 [INFO] train episode 2128: reward = 57.00, steps = 57
00:02:25 [INFO] train episode 2129: reward = 200.00, steps = 200
00:02:25 [INFO] train episode 2130: reward = 200.00, steps = 200
00:02:25 [INFO] train episode 2131: reward = 200.00, steps = 200
00:02:25 [INFO] train episode 2132: reward = 117.00, steps = 117
00:02:25 [INFO] train episode 2133: reward = 200.00, steps = 200
00:02:25 [INFO] train episode 2134: reward = 116.00, steps = 116
00:02:25 [INFO] train episode 2135: reward = 194.00, steps = 194
00:02:25 [INFO] train episode 2136: reward = 200.00, steps = 200
00:02:25 [INFO] train episode 2137: reward = 200.00, steps = 200
00:02:25 [INFO] train episode 2138: reward = 200.00, steps = 200
00:02:25 [INFO] train episode 2139: reward = 163.00, steps = 163
00:02:25 [INFO] train episode 2140: reward = 154.00, steps = 154
00:02:25 [INFO] train episode 2141: reward = 200.00, steps = 200
00:02:25 [INFO] train episode 2142: reward = 147.00, steps = 147
00:02:26 [INFO] train episode 2143: reward = 200.00, steps = 200
00:02:26 [INFO] train episode 2144: reward = 200.00, steps = 200
00:02:26 [INFO] train episode 2145: reward = 181.00, steps = 181
00:02:26 [INFO] train episode 2146: reward = 200.00, steps = 200
00:02:26 [INFO] train episode 2147: reward = 170.00, steps = 170
00:02:26 [INFO] train episode 2148: reward = 58.00, steps = 58
00:02:26 [INFO] train episode 2149: reward = 196.00, steps = 196
00:02:26 [INFO] train episode 2150: reward = 144.00, steps = 144
00:02:26 [INFO] train episode 2151: reward = 200.00, steps = 200
00:02:26 [INFO] train episode 2152: reward = 134.00, steps = 134
00:02:26 [INFO] train episode 2153: reward = 80.00, steps = 80
00:02:26 [INFO] train episode 2154: reward = 179.00, steps = 179
00:02:26 [INFO] train episode 2155: reward = 191.00, steps = 191
00:02:26 [INFO] train episode 2156: reward = 200.00, steps = 200
00:02:26 [INFO] train episode 2157: reward = 37.00, steps = 37
00:02:26 [INFO] train episode 2158: reward = 151.00, steps = 151
00:02:26 [INFO] train episode 2159: reward = 196.00, steps = 196
00:02:27 [INFO] train episode 2160: reward = 193.00, steps = 193
00:02:27 [INFO] train episode 2161: reward = 200.00, steps = 200
00:02:27 [INFO] train episode 2162: reward = 200.00, steps = 200
00:02:27 [INFO] train episode 2163: reward = 51.00, steps = 51
00:02:27 [INFO] train episode 2164: reward = 200.00, steps = 200
00:02:27 [INFO] train episode 2165: reward = 59.00, steps = 59
00:02:27 [INFO] train episode 2166: reward = 138.00, steps = 138
00:02:27 [INFO] train episode 2167: reward = 146.00, steps = 146
00:02:27 [INFO] train episode 2168: reward = 197.00, steps = 197
00:02:27 [INFO] train episode 2169: reward = 115.00, steps = 115
00:02:27 [INFO] train episode 2170: reward = 200.00, steps = 200
00:02:27 [INFO] train episode 2171: reward = 161.00, steps = 161
00:02:27 [INFO] train episode 2172: reward = 170.00, steps = 170
00:02:27 [INFO] train episode 2173: reward = 200.00, steps = 200
00:02:27 [INFO] train episode 2174: reward = 81.00, steps = 81
00:02:27 [INFO] train episode 2175: reward = 145.00, steps = 145
00:02:28 [INFO] train episode 2176: reward = 200.00, steps = 200
00:02:28 [INFO] train episode 2177: reward = 200.00, steps = 200
00:02:28 [INFO] train episode 2178: reward = 196.00, steps = 196
00:02:28 [INFO] train episode 2179: reward = 163.00, steps = 163
00:02:28 [INFO] train episode 2180: reward = 195.00, steps = 195
00:02:28 [INFO] train episode 2181: reward = 200.00, steps = 200
00:02:28 [INFO] train episode 2182: reward = 198.00, steps = 198
00:02:28 [INFO] train episode 2183: reward = 193.00, steps = 193
00:02:28 [INFO] train episode 2184: reward = 200.00, steps = 200
00:02:28 [INFO] train episode 2185: reward = 200.00, steps = 200
00:02:28 [INFO] train episode 2186: reward = 137.00, steps = 137
00:02:28 [INFO] train episode 2187: reward = 122.00, steps = 122
00:02:28 [INFO] train episode 2188: reward = 200.00, steps = 200
00:02:28 [INFO] train episode 2189: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2190: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2191: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2192: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2193: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2194: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2195: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2196: reward = 125.00, steps = 125
00:02:29 [INFO] train episode 2197: reward = 170.00, steps = 170
00:02:29 [INFO] train episode 2198: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2199: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2200: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2201: reward = 200.00, steps = 200
00:02:29 [INFO] train episode 2202: reward = 120.00, steps = 120
00:02:29 [INFO] train episode 2203: reward = 192.00, steps = 192
00:02:29 [INFO] train episode 2204: reward = 126.00, steps = 126
00:02:30 [INFO] train episode 2205: reward = 184.00, steps = 184
00:02:30 [INFO] train episode 2206: reward = 200.00, steps = 200
00:02:30 [INFO] train episode 2207: reward = 200.00, steps = 200
00:02:30 [INFO] train episode 2208: reward = 200.00, steps = 200
00:02:30 [INFO] train episode 2209: reward = 138.00, steps = 138
00:02:30 [INFO] train episode 2210: reward = 200.00, steps = 200
00:02:30 [INFO] train episode 2211: reward = 121.00, steps = 121
00:02:30 [INFO] train episode 2212: reward = 140.00, steps = 140
00:02:30 [INFO] train episode 2213: reward = 121.00, steps = 121
00:02:30 [INFO] train episode 2214: reward = 151.00, steps = 151
00:02:30 [INFO] train episode 2215: reward = 200.00, steps = 200
00:02:30 [INFO] train episode 2216: reward = 200.00, steps = 200
00:02:30 [INFO] train episode 2217: reward = 200.00, steps = 200
00:02:30 [INFO] train episode 2218: reward = 80.00, steps = 80
00:02:30 [INFO] train episode 2219: reward = 184.00, steps = 184
00:02:31 [INFO] train episode 2220: reward = 200.00, steps = 200
00:02:31 [INFO] train episode 2221: reward = 200.00, steps = 200
00:02:31 [INFO] train episode 2222: reward = 200.00, steps = 200
00:02:31 [INFO] train episode 2223: reward = 200.00, steps = 200
00:02:31 [INFO] train episode 2224: reward = 200.00, steps = 200
00:02:31 [INFO] train episode 2225: reward = 181.00, steps = 181
00:02:31 [INFO] train episode 2226: reward = 92.00, steps = 92
00:02:31 [INFO] train episode 2227: reward = 200.00, steps = 200
00:02:31 [INFO] train episode 2228: reward = 200.00, steps = 200
00:02:31 [INFO] train episode 2229: reward = 65.00, steps = 65
00:02:31 [INFO] train episode 2230: reward = 200.00, steps = 200
00:02:31 [INFO] train episode 2231: reward = 143.00, steps = 143
00:02:31 [INFO] train episode 2232: reward = 122.00, steps = 122
00:02:31 [INFO] train episode 2233: reward = 200.00, steps = 200
00:02:31 [INFO] train episode 2234: reward = 18.00, steps = 18
00:02:31 [INFO] train episode 2235: reward = 74.00, steps = 74
00:02:31 [INFO] train episode 2236: reward = 53.00, steps = 53
00:02:32 [INFO] train episode 2237: reward = 200.00, steps = 200
00:02:32 [INFO] train episode 2238: reward = 139.00, steps = 139
00:02:32 [INFO] train episode 2239: reward = 200.00, steps = 200
00:02:32 [INFO] train episode 2240: reward = 182.00, steps = 182
00:02:32 [INFO] train episode 2241: reward = 200.00, steps = 200
00:02:32 [INFO] train episode 2242: reward = 87.00, steps = 87
00:02:32 [INFO] train episode 2243: reward = 200.00, steps = 200
00:02:32 [INFO] train episode 2244: reward = 158.00, steps = 158
00:02:32 [INFO] train episode 2245: reward = 200.00, steps = 200
00:02:32 [INFO] train episode 2246: reward = 200.00, steps = 200
00:02:32 [INFO] train episode 2247: reward = 173.00, steps = 173
00:02:32 [INFO] train episode 2248: reward = 123.00, steps = 123
00:02:32 [INFO] train episode 2249: reward = 143.00, steps = 143
00:02:32 [INFO] train episode 2250: reward = 200.00, steps = 200
00:02:33 [INFO] train episode 2251: reward = 152.00, steps = 152
00:02:33 [INFO] train episode 2252: reward = 114.00, steps = 114
00:02:33 [INFO] train episode 2253: reward = 200.00, steps = 200
00:02:33 [INFO] train episode 2254: reward = 178.00, steps = 178
00:02:33 [INFO] train episode 2255: reward = 200.00, steps = 200
00:02:33 [INFO] train episode 2256: reward = 200.00, steps = 200
00:02:33 [INFO] train episode 2257: reward = 126.00, steps = 126
00:02:33 [INFO] train episode 2258: reward = 187.00, steps = 187
00:02:33 [INFO] train episode 2259: reward = 200.00, steps = 200
00:02:33 [INFO] train episode 2260: reward = 173.00, steps = 173
00:02:33 [INFO] train episode 2261: reward = 109.00, steps = 109
00:02:33 [INFO] train episode 2262: reward = 26.00, steps = 26
00:02:33 [INFO] train episode 2263: reward = 151.00, steps = 151
00:02:33 [INFO] train episode 2264: reward = 161.00, steps = 161
00:02:33 [INFO] train episode 2265: reward = 152.00, steps = 152
00:02:33 [INFO] train episode 2266: reward = 79.00, steps = 79
00:02:33 [INFO] train episode 2267: reward = 200.00, steps = 200
00:02:34 [INFO] train episode 2268: reward = 200.00, steps = 200
00:02:34 [INFO] train episode 2269: reward = 200.00, steps = 200
00:02:34 [INFO] train episode 2270: reward = 200.00, steps = 200
00:02:34 [INFO] train episode 2271: reward = 200.00, steps = 200
00:02:34 [INFO] train episode 2272: reward = 200.00, steps = 200
00:02:34 [INFO] train episode 2273: reward = 200.00, steps = 200
00:02:34 [INFO] train episode 2274: reward = 176.00, steps = 176
00:02:34 [INFO] train episode 2275: reward = 170.00, steps = 170
00:02:34 [INFO] train episode 2276: reward = 200.00, steps = 200
00:02:34 [INFO] train episode 2277: reward = 200.00, steps = 200
00:02:34 [INFO] train episode 2278: reward = 123.00, steps = 123
00:02:34 [INFO] train episode 2279: reward = 200.00, steps = 200
00:02:34 [INFO] train episode 2280: reward = 154.00, steps = 154
00:02:34 [INFO] train episode 2281: reward = 152.00, steps = 152
00:02:35 [INFO] train episode 2282: reward = 200.00, steps = 200
00:02:35 [INFO] train episode 2283: reward = 200.00, steps = 200
00:02:35 [INFO] train episode 2284: reward = 135.00, steps = 135
00:02:35 [INFO] train episode 2285: reward = 200.00, steps = 200
00:02:35 [INFO] train episode 2286: reward = 200.00, steps = 200
00:02:35 [INFO] train episode 2287: reward = 43.00, steps = 43
00:02:35 [INFO] train episode 2288: reward = 87.00, steps = 87
00:02:35 [INFO] train episode 2289: reward = 200.00, steps = 200
00:02:35 [INFO] train episode 2290: reward = 27.00, steps = 27
00:02:35 [INFO] train episode 2291: reward = 133.00, steps = 133
00:02:35 [INFO] train episode 2292: reward = 182.00, steps = 182
00:02:35 [INFO] train episode 2293: reward = 190.00, steps = 190
00:02:35 [INFO] train episode 2294: reward = 200.00, steps = 200
00:02:35 [INFO] train episode 2295: reward = 104.00, steps = 104
00:02:35 [INFO] train episode 2296: reward = 120.00, steps = 120
00:02:35 [INFO] train episode 2297: reward = 200.00, steps = 200
00:02:35 [INFO] train episode 2298: reward = 189.00, steps = 189
00:02:36 [INFO] train episode 2299: reward = 200.00, steps = 200
00:02:36 [INFO] train episode 2300: reward = 69.00, steps = 69
00:02:36 [INFO] train episode 2301: reward = 52.00, steps = 52
00:02:36 [INFO] train episode 2302: reward = 167.00, steps = 167
00:02:36 [INFO] train episode 2303: reward = 200.00, steps = 200
00:02:36 [INFO] train episode 2304: reward = 38.00, steps = 38
00:02:36 [INFO] train episode 2305: reward = 200.00, steps = 200
00:02:36 [INFO] train episode 2306: reward = 200.00, steps = 200
00:02:36 [INFO] train episode 2307: reward = 170.00, steps = 170
00:02:36 [INFO] train episode 2308: reward = 130.00, steps = 130
00:02:36 [INFO] train episode 2309: reward = 200.00, steps = 200
00:02:36 [INFO] train episode 2310: reward = 115.00, steps = 115
00:02:36 [INFO] train episode 2311: reward = 200.00, steps = 200
00:02:36 [INFO] train episode 2312: reward = 200.00, steps = 200
00:02:36 [INFO] train episode 2313: reward = 198.00, steps = 198
00:02:36 [INFO] train episode 2314: reward = 116.00, steps = 116
00:02:36 [INFO] train episode 2315: reward = 149.00, steps = 149
00:02:37 [INFO] train episode 2316: reward = 186.00, steps = 186
00:02:37 [INFO] train episode 2317: reward = 153.00, steps = 153
00:02:37 [INFO] train episode 2318: reward = 200.00, steps = 200
00:02:37 [INFO] train episode 2319: reward = 25.00, steps = 25
00:02:37 [INFO] train episode 2320: reward = 200.00, steps = 200
00:02:37 [INFO] train episode 2321: reward = 200.00, steps = 200
00:02:37 [INFO] train episode 2322: reward = 129.00, steps = 129
00:02:37 [INFO] train episode 2323: reward = 200.00, steps = 200
00:02:37 [INFO] train episode 2324: reward = 200.00, steps = 200
00:02:37 [INFO] train episode 2325: reward = 183.00, steps = 183
00:02:37 [INFO] train episode 2326: reward = 168.00, steps = 168
00:02:37 [INFO] train episode 2327: reward = 155.00, steps = 155
00:02:37 [INFO] train episode 2328: reward = 200.00, steps = 200
00:02:37 [INFO] train episode 2329: reward = 200.00, steps = 200
00:02:37 [INFO] train episode 2330: reward = 145.00, steps = 145
00:02:38 [INFO] train episode 2331: reward = 200.00, steps = 200
00:02:38 [INFO] train episode 2332: reward = 61.00, steps = 61
00:02:38 [INFO] train episode 2333: reward = 200.00, steps = 200
00:02:38 [INFO] train episode 2334: reward = 200.00, steps = 200
00:02:38 [INFO] train episode 2335: reward = 148.00, steps = 148
00:02:38 [INFO] train episode 2336: reward = 200.00, steps = 200
00:02:38 [INFO] train episode 2337: reward = 200.00, steps = 200
00:02:38 [INFO] train episode 2338: reward = 200.00, steps = 200
00:02:38 [INFO] train episode 2339: reward = 161.00, steps = 161
00:02:38 [INFO] train episode 2340: reward = 178.00, steps = 178
00:02:38 [INFO] train episode 2341: reward = 200.00, steps = 200
00:02:38 [INFO] train episode 2342: reward = 200.00, steps = 200
00:02:38 [INFO] train episode 2343: reward = 153.00, steps = 153
00:02:38 [INFO] train episode 2344: reward = 156.00, steps = 156
00:02:38 [INFO] train episode 2345: reward = 200.00, steps = 200
00:02:39 [INFO] train episode 2346: reward = 156.00, steps = 156
00:02:39 [INFO] train episode 2347: reward = 200.00, steps = 200
00:02:39 [INFO] train episode 2348: reward = 200.00, steps = 200
00:02:39 [INFO] train episode 2349: reward = 138.00, steps = 138
00:02:39 [INFO] train episode 2350: reward = 139.00, steps = 139
00:02:39 [INFO] train episode 2351: reward = 200.00, steps = 200
00:02:39 [INFO] train episode 2352: reward = 200.00, steps = 200
00:02:39 [INFO] train episode 2353: reward = 171.00, steps = 171
00:02:39 [INFO] train episode 2354: reward = 171.00, steps = 171
00:02:39 [INFO] train episode 2355: reward = 200.00, steps = 200
00:02:39 [INFO] train episode 2356: reward = 97.00, steps = 97
00:02:39 [INFO] train episode 2357: reward = 195.00, steps = 195
00:02:39 [INFO] train episode 2358: reward = 200.00, steps = 200
00:02:39 [INFO] train episode 2359: reward = 200.00, steps = 200
00:02:39 [INFO] train episode 2360: reward = 177.00, steps = 177
00:02:40 [INFO] train episode 2361: reward = 172.00, steps = 172
00:02:40 [INFO] train episode 2362: reward = 200.00, steps = 200
00:02:40 [INFO] train episode 2363: reward = 200.00, steps = 200
00:02:40 [INFO] train episode 2364: reward = 200.00, steps = 200
00:02:40 [INFO] train episode 2365: reward = 134.00, steps = 134
00:02:40 [INFO] train episode 2366: reward = 200.00, steps = 200
00:02:40 [INFO] train episode 2367: reward = 200.00, steps = 200
00:02:40 [INFO] train episode 2368: reward = 200.00, steps = 200
00:02:40 [INFO] train episode 2369: reward = 145.00, steps = 145
00:02:40 [INFO] train episode 2370: reward = 179.00, steps = 179
00:02:40 [INFO] train episode 2371: reward = 173.00, steps = 173
00:02:40 [INFO] train episode 2372: reward = 200.00, steps = 200
00:02:40 [INFO] train episode 2373: reward = 200.00, steps = 200
00:02:40 [INFO] train episode 2374: reward = 200.00, steps = 200
00:02:40 [INFO] train episode 2375: reward = 30.00, steps = 30
00:02:40 [INFO] train episode 2376: reward = 130.00, steps = 130
00:02:41 [INFO] train episode 2377: reward = 174.00, steps = 174
00:02:41 [INFO] train episode 2378: reward = 48.00, steps = 48
00:02:41 [INFO] train episode 2379: reward = 200.00, steps = 200
00:02:41 [INFO] train episode 2380: reward = 200.00, steps = 200
00:02:41 [INFO] train episode 2381: reward = 200.00, steps = 200
00:02:41 [INFO] train episode 2382: reward = 13.00, steps = 13
00:02:41 [INFO] train episode 2383: reward = 200.00, steps = 200
00:02:41 [INFO] train episode 2384: reward = 189.00, steps = 189
00:02:41 [INFO] train episode 2385: reward = 73.00, steps = 73
00:02:41 [INFO] train episode 2386: reward = 200.00, steps = 200
00:02:41 [INFO] train episode 2387: reward = 200.00, steps = 200
00:02:41 [INFO] train episode 2388: reward = 200.00, steps = 200
00:02:41 [INFO] train episode 2389: reward = 200.00, steps = 200
00:02:41 [INFO] train episode 2390: reward = 200.00, steps = 200
00:02:41 [INFO] train episode 2391: reward = 135.00, steps = 135
00:02:41 [INFO] train episode 2392: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2393: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2394: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2395: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2396: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2397: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2398: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2399: reward = 176.00, steps = 176
00:02:42 [INFO] train episode 2400: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2401: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2402: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2403: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2404: reward = 200.00, steps = 200
00:02:42 [INFO] train episode 2405: reward = 175.00, steps = 175
00:02:43 [INFO] train episode 2406: reward = 200.00, steps = 200
00:02:43 [INFO] train episode 2407: reward = 200.00, steps = 200
00:02:43 [INFO] train episode 2408: reward = 200.00, steps = 200
00:02:43 [INFO] train episode 2409: reward = 182.00, steps = 182
00:02:43 [INFO] train episode 2410: reward = 182.00, steps = 182
00:02:43 [INFO] train episode 2411: reward = 200.00, steps = 200
00:02:43 [INFO] train episode 2412: reward = 200.00, steps = 200
00:02:43 [INFO] train episode 2413: reward = 141.00, steps = 141
00:02:43 [INFO] train episode 2414: reward = 174.00, steps = 174
00:02:43 [INFO] train episode 2415: reward = 169.00, steps = 169
00:02:43 [INFO] train episode 2416: reward = 200.00, steps = 200
00:02:43 [INFO] train episode 2417: reward = 200.00, steps = 200
00:02:43 [INFO] train episode 2418: reward = 147.00, steps = 147
00:02:43 [INFO] train episode 2419: reward = 200.00, steps = 200
00:02:43 [INFO] train episode 2420: reward = 200.00, steps = 200
00:02:44 [INFO] train episode 2421: reward = 200.00, steps = 200
00:02:44 [INFO] train episode 2422: reward = 200.00, steps = 200
00:02:44 [INFO] train episode 2423: reward = 200.00, steps = 200
00:02:44 [INFO] train episode 2424: reward = 129.00, steps = 129
00:02:44 [INFO] train episode 2425: reward = 200.00, steps = 200
00:02:44 [INFO] train episode 2426: reward = 146.00, steps = 146
00:02:44 [INFO] train episode 2427: reward = 105.00, steps = 105
00:02:44 [INFO] train episode 2428: reward = 200.00, steps = 200
00:02:44 [INFO] train episode 2429: reward = 200.00, steps = 200
00:02:44 [INFO] train episode 2430: reward = 156.00, steps = 156
00:02:44 [INFO] train episode 2431: reward = 200.00, steps = 200
00:02:44 [INFO] train episode 2432: reward = 200.00, steps = 200
00:02:44 [INFO] train episode 2433: reward = 200.00, steps = 200
00:02:44 [INFO] train episode 2434: reward = 200.00, steps = 200
00:02:45 [INFO] train episode 2435: reward = 200.00, steps = 200
00:02:45 [INFO] train episode 2436: reward = 200.00, steps = 200
00:02:45 [INFO] train episode 2437: reward = 200.00, steps = 200
00:02:45 [INFO] train episode 2438: reward = 139.00, steps = 139
00:02:45 [INFO] train episode 2439: reward = 170.00, steps = 170
00:02:45 [INFO] train episode 2440: reward = 200.00, steps = 200
00:02:45 [INFO] train episode 2441: reward = 77.00, steps = 77
00:02:45 [INFO] train episode 2442: reward = 157.00, steps = 157
00:02:45 [INFO] train episode 2443: reward = 200.00, steps = 200
00:02:45 [INFO] train episode 2444: reward = 200.00, steps = 200
00:02:45 [INFO] train episode 2445: reward = 66.00, steps = 66
00:02:45 [INFO] train episode 2446: reward = 200.00, steps = 200
00:02:45 [INFO] train episode 2447: reward = 200.00, steps = 200
00:02:45 [INFO] train episode 2448: reward = 200.00, steps = 200
00:02:45 [INFO] train episode 2449: reward = 157.00, steps = 157
00:02:46 [INFO] train episode 2450: reward = 200.00, steps = 200
00:02:46 [INFO] train episode 2451: reward = 200.00, steps = 200
00:02:46 [INFO] train episode 2452: reward = 200.00, steps = 200
00:02:46 [INFO] train episode 2453: reward = 74.00, steps = 74
00:02:46 [INFO] train episode 2454: reward = 194.00, steps = 194
00:02:46 [INFO] train episode 2455: reward = 185.00, steps = 185
00:02:46 [INFO] train episode 2456: reward = 200.00, steps = 200
00:02:46 [INFO] train episode 2457: reward = 146.00, steps = 146
00:02:46 [INFO] train episode 2458: reward = 137.00, steps = 137
00:02:46 [INFO] train episode 2459: reward = 181.00, steps = 181
00:02:46 [INFO] train episode 2460: reward = 200.00, steps = 200
00:02:46 [INFO] train episode 2461: reward = 200.00, steps = 200
00:02:46 [INFO] train episode 2462: reward = 102.00, steps = 102
00:02:46 [INFO] train episode 2463: reward = 200.00, steps = 200
00:02:46 [INFO] train episode 2464: reward = 173.00, steps = 173
00:02:47 [INFO] train episode 2465: reward = 140.00, steps = 140
00:02:47 [INFO] train episode 2466: reward = 135.00, steps = 135
00:02:47 [INFO] train episode 2467: reward = 200.00, steps = 200
00:02:47 [INFO] train episode 2468: reward = 52.00, steps = 52
00:02:47 [INFO] train episode 2469: reward = 200.00, steps = 200
00:02:47 [INFO] train episode 2470: reward = 200.00, steps = 200
00:02:47 [INFO] train episode 2471: reward = 200.00, steps = 200
00:02:47 [INFO] train episode 2472: reward = 199.00, steps = 199
00:02:47 [INFO] train episode 2473: reward = 200.00, steps = 200
00:02:47 [INFO] train episode 2474: reward = 200.00, steps = 200
00:02:47 [INFO] train episode 2475: reward = 200.00, steps = 200
00:02:47 [INFO] train episode 2476: reward = 200.00, steps = 200
00:02:47 [INFO] train episode 2477: reward = 157.00, steps = 157
00:02:47 [INFO] train episode 2478: reward = 200.00, steps = 200
00:02:48 [INFO] train episode 2479: reward = 200.00, steps = 200
00:02:48 [INFO] train episode 2480: reward = 200.00, steps = 200
00:02:48 [INFO] train episode 2481: reward = 86.00, steps = 86
00:02:48 [INFO] train episode 2482: reward = 169.00, steps = 169
00:02:48 [INFO] train episode 2483: reward = 200.00, steps = 200
00:02:48 [INFO] train episode 2484: reward = 181.00, steps = 181
00:02:48 [INFO] train episode 2485: reward = 200.00, steps = 200
00:02:48 [INFO] train episode 2486: reward = 200.00, steps = 200
00:02:48 [INFO] train episode 2487: reward = 200.00, steps = 200
00:02:48 [INFO] train episode 2488: reward = 200.00, steps = 200
00:02:48 [INFO] train episode 2489: reward = 200.00, steps = 200
00:02:48 [INFO] train episode 2490: reward = 87.00, steps = 87
00:02:48 [INFO] train episode 2491: reward = 77.00, steps = 77
00:02:48 [INFO] train episode 2492: reward = 200.00, steps = 200
00:02:48 [INFO] train episode 2493: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2494: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2495: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2496: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2497: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2498: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2499: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2500: reward = 144.00, steps = 144
00:02:49 [INFO] train episode 2501: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2502: reward = 184.00, steps = 184
00:02:49 [INFO] train episode 2503: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2504: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2505: reward = 200.00, steps = 200
00:02:49 [INFO] train episode 2506: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2507: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2508: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2509: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2510: reward = 108.00, steps = 108
00:02:50 [INFO] train episode 2511: reward = 112.00, steps = 112
00:02:50 [INFO] train episode 2512: reward = 126.00, steps = 126
00:02:50 [INFO] train episode 2513: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2514: reward = 78.00, steps = 78
00:02:50 [INFO] train episode 2515: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2516: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2517: reward = 86.00, steps = 86
00:02:50 [INFO] train episode 2518: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2519: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2520: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2521: reward = 200.00, steps = 200
00:02:50 [INFO] train episode 2522: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2523: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2524: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2525: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2526: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2527: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2528: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2529: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2530: reward = 110.00, steps = 110
00:02:51 [INFO] train episode 2531: reward = 122.00, steps = 122
00:02:51 [INFO] train episode 2532: reward = 138.00, steps = 138
00:02:51 [INFO] train episode 2533: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2534: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2535: reward = 200.00, steps = 200
00:02:51 [INFO] train episode 2536: reward = 111.00, steps = 111
00:02:52 [INFO] train episode 2537: reward = 200.00, steps = 200
00:02:52 [INFO] train episode 2538: reward = 200.00, steps = 200
00:02:52 [INFO] train episode 2539: reward = 200.00, steps = 200
00:02:52 [INFO] train episode 2540: reward = 200.00, steps = 200
00:02:52 [INFO] train episode 2541: reward = 112.00, steps = 112
00:02:52 [INFO] train episode 2542: reward = 200.00, steps = 200
00:02:52 [INFO] train episode 2543: reward = 169.00, steps = 169
00:02:52 [INFO] train episode 2544: reward = 200.00, steps = 200
00:02:52 [INFO] train episode 2545: reward = 200.00, steps = 200
00:02:52 [INFO] train episode 2546: reward = 200.00, steps = 200
00:02:52 [INFO] train episode 2547: reward = 101.00, steps = 101
00:02:52 [INFO] train episode 2548: reward = 95.00, steps = 95
00:02:52 [INFO] train episode 2549: reward = 200.00, steps = 200
00:02:52 [INFO] train episode 2550: reward = 200.00, steps = 200
00:02:52 [INFO] train episode 2551: reward = 101.00, steps = 101
00:02:53 [INFO] train episode 2552: reward = 200.00, steps = 200
00:02:53 [INFO] train episode 2553: reward = 200.00, steps = 200
00:02:53 [INFO] train episode 2554: reward = 200.00, steps = 200
00:02:53 [INFO] train episode 2555: reward = 178.00, steps = 178
00:02:53 [INFO] train episode 2556: reward = 200.00, steps = 200
00:02:53 [INFO] train episode 2557: reward = 134.00, steps = 134
00:02:53 [INFO] train episode 2558: reward = 200.00, steps = 200
00:02:53 [INFO] train episode 2559: reward = 200.00, steps = 200
00:02:53 [INFO] train episode 2560: reward = 163.00, steps = 163
00:02:53 [INFO] train episode 2561: reward = 200.00, steps = 200
00:02:53 [INFO] train episode 2562: reward = 200.00, steps = 200
00:02:53 [INFO] train episode 2563: reward = 107.00, steps = 107
00:02:53 [INFO] train episode 2564: reward = 110.00, steps = 110
00:02:53 [INFO] train episode 2565: reward = 73.00, steps = 73
00:02:53 [INFO] train episode 2566: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2567: reward = 159.00, steps = 159
00:02:54 [INFO] train episode 2568: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2569: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2570: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2571: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2572: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2573: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2574: reward = 53.00, steps = 53
00:02:54 [INFO] train episode 2575: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2576: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2577: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2578: reward = 53.00, steps = 53
00:02:54 [INFO] train episode 2579: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2580: reward = 184.00, steps = 184
00:02:54 [INFO] train episode 2581: reward = 200.00, steps = 200
00:02:54 [INFO] train episode 2582: reward = 62.00, steps = 62
00:02:55 [INFO] train episode 2583: reward = 119.00, steps = 119
00:02:55 [INFO] train episode 2584: reward = 85.00, steps = 85
00:02:55 [INFO] train episode 2585: reward = 149.00, steps = 149
00:02:55 [INFO] train episode 2586: reward = 200.00, steps = 200
00:02:55 [INFO] train episode 2587: reward = 200.00, steps = 200
00:02:55 [INFO] train episode 2588: reward = 60.00, steps = 60
00:02:55 [INFO] train episode 2589: reward = 200.00, steps = 200
00:02:55 [INFO] train episode 2590: reward = 69.00, steps = 69
00:02:55 [INFO] train episode 2591: reward = 200.00, steps = 200
00:02:55 [INFO] train episode 2592: reward = 200.00, steps = 200
00:02:55 [INFO] train episode 2593: reward = 100.00, steps = 100
00:02:55 [INFO] train episode 2594: reward = 200.00, steps = 200
00:02:55 [INFO] train episode 2595: reward = 200.00, steps = 200
00:02:55 [INFO] train episode 2596: reward = 125.00, steps = 125
00:02:55 [INFO] train episode 2597: reward = 200.00, steps = 200
00:02:55 [INFO] train episode 2598: reward = 200.00, steps = 200
00:02:55 [INFO] train episode 2599: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2600: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2601: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2602: reward = 104.00, steps = 104
00:02:56 [INFO] train episode 2603: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2604: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2605: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2606: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2607: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2608: reward = 113.00, steps = 113
00:02:56 [INFO] train episode 2609: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2610: reward = 157.00, steps = 157
00:02:56 [INFO] train episode 2611: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2612: reward = 200.00, steps = 200
00:02:56 [INFO] train episode 2613: reward = 111.00, steps = 111
00:02:57 [INFO] train episode 2614: reward = 200.00, steps = 200
00:02:57 [INFO] train episode 2615: reward = 200.00, steps = 200
00:02:57 [INFO] train episode 2616: reward = 200.00, steps = 200
00:02:57 [INFO] train episode 2617: reward = 110.00, steps = 110
00:02:57 [INFO] train episode 2618: reward = 200.00, steps = 200
00:02:57 [INFO] train episode 2619: reward = 200.00, steps = 200
00:02:57 [INFO] train episode 2620: reward = 153.00, steps = 153
00:02:57 [INFO] train episode 2621: reward = 182.00, steps = 182
00:02:57 [INFO] train episode 2622: reward = 200.00, steps = 200
00:02:57 [INFO] train episode 2623: reward = 200.00, steps = 200
00:02:57 [INFO] train episode 2624: reward = 200.00, steps = 200
00:02:57 [INFO] train episode 2625: reward = 200.00, steps = 200
00:02:57 [INFO] train episode 2626: reward = 200.00, steps = 200
00:02:57 [INFO] train episode 2627: reward = 200.00, steps = 200
00:02:58 [INFO] train episode 2628: reward = 200.00, steps = 200
00:02:58 [INFO] train episode 2629: reward = 200.00, steps = 200
00:02:58 [INFO] train episode 2630: reward = 200.00, steps = 200
00:02:58 [INFO] train episode 2631: reward = 163.00, steps = 163
00:02:58 [INFO] train episode 2632: reward = 200.00, steps = 200
00:02:58 [INFO] train episode 2633: reward = 200.00, steps = 200
00:02:58 [INFO] train episode 2634: reward = 184.00, steps = 184
00:02:58 [INFO] train episode 2635: reward = 200.00, steps = 200
00:02:58 [INFO] train episode 2636: reward = 200.00, steps = 200
00:02:58 [INFO] train episode 2637: reward = 161.00, steps = 161
00:02:58 [INFO] train episode 2638: reward = 138.00, steps = 138
00:02:58 [INFO] train episode 2639: reward = 200.00, steps = 200
00:02:58 [INFO] train episode 2640: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2641: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2642: reward = 110.00, steps = 110
00:02:59 [INFO] train episode 2643: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2644: reward = 174.00, steps = 174
00:02:59 [INFO] train episode 2645: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2646: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2647: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2648: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2649: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2650: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2651: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2652: reward = 200.00, steps = 200
00:02:59 [INFO] train episode 2653: reward = 121.00, steps = 121
00:02:59 [INFO] train episode 2654: reward = 200.00, steps = 200
00:03:00 [INFO] train episode 2655: reward = 136.00, steps = 136
00:03:00 [INFO] train episode 2656: reward = 200.00, steps = 200
00:03:00 [INFO] train episode 2657: reward = 200.00, steps = 200
00:03:00 [INFO] train episode 2658: reward = 137.00, steps = 137
00:03:00 [INFO] train episode 2659: reward = 200.00, steps = 200
00:03:00 [INFO] train episode 2660: reward = 36.00, steps = 36
00:03:00 [INFO] train episode 2661: reward = 111.00, steps = 111
00:03:00 [INFO] train episode 2662: reward = 200.00, steps = 200
00:03:00 [INFO] train episode 2663: reward = 200.00, steps = 200
00:03:00 [INFO] train episode 2664: reward = 144.00, steps = 144
00:03:00 [INFO] train episode 2665: reward = 200.00, steps = 200
00:03:00 [INFO] train episode 2666: reward = 200.00, steps = 200
00:03:00 [INFO] train episode 2667: reward = 200.00, steps = 200
00:03:00 [INFO] train episode 2668: reward = 200.00, steps = 200
00:03:00 [INFO] train episode 2669: reward = 200.00, steps = 200
00:03:01 [INFO] train episode 2670: reward = 200.00, steps = 200
00:03:01 [INFO] train episode 2671: reward = 200.00, steps = 200
00:03:01 [INFO] train episode 2672: reward = 160.00, steps = 160
00:03:01 [INFO] train episode 2673: reward = 200.00, steps = 200
00:03:01 [INFO] train episode 2674: reward = 131.00, steps = 131
00:03:01 [INFO] train episode 2675: reward = 163.00, steps = 163
00:03:01 [INFO] train episode 2676: reward = 200.00, steps = 200
00:03:01 [INFO] train episode 2677: reward = 200.00, steps = 200
00:03:01 [INFO] train episode 2678: reward = 196.00, steps = 196
00:03:01 [INFO] train episode 2679: reward = 200.00, steps = 200
00:03:01 [INFO] train episode 2680: reward = 194.00, steps = 194
00:03:01 [INFO] train episode 2681: reward = 200.00, steps = 200
00:03:01 [INFO] train episode 2682: reward = 145.00, steps = 145
00:03:01 [INFO] train episode 2683: reward = 166.00, steps = 166
00:03:02 [INFO] train episode 2684: reward = 200.00, steps = 200
00:03:02 [INFO] train episode 2685: reward = 188.00, steps = 188
00:03:02 [INFO] train episode 2686: reward = 200.00, steps = 200
00:03:02 [INFO] train episode 2687: reward = 200.00, steps = 200
00:03:02 [INFO] train episode 2688: reward = 200.00, steps = 200
00:03:02 [INFO] train episode 2689: reward = 200.00, steps = 200
00:03:02 [INFO] train episode 2690: reward = 200.00, steps = 200
00:03:02 [INFO] train episode 2691: reward = 200.00, steps = 200
00:03:02 [INFO] train episode 2692: reward = 200.00, steps = 200
00:03:02 [INFO] train episode 2693: reward = 200.00, steps = 200
00:03:02 [INFO] train episode 2694: reward = 200.00, steps = 200
00:03:02 [INFO] train episode 2695: reward = 125.00, steps = 125
00:03:02 [INFO] train episode 2696: reward = 157.00, steps = 157
00:03:02 [INFO] train episode 2697: reward = 200.00, steps = 200
00:03:03 [INFO] train episode 2698: reward = 200.00, steps = 200
00:03:03 [INFO] train episode 2699: reward = 150.00, steps = 150
00:03:03 [INFO] train episode 2700: reward = 200.00, steps = 200
00:03:03 [INFO] train episode 2701: reward = 174.00, steps = 174
00:03:03 [INFO] train episode 2702: reward = 200.00, steps = 200
00:03:03 [INFO] train episode 2703: reward = 200.00, steps = 200
00:03:03 [INFO] train episode 2704: reward = 200.00, steps = 200
00:03:03 [INFO] train episode 2705: reward = 177.00, steps = 177
00:03:03 [INFO] train episode 2706: reward = 200.00, steps = 200
00:03:03 [INFO] train episode 2707: reward = 151.00, steps = 151
00:03:03 [INFO] train episode 2708: reward = 126.00, steps = 126
00:03:03 [INFO] train episode 2709: reward = 200.00, steps = 200
00:03:03 [INFO] train episode 2710: reward = 200.00, steps = 200
00:03:03 [INFO] train episode 2711: reward = 200.00, steps = 200
00:03:03 [INFO] train episode 2712: reward = 96.00, steps = 96
00:03:04 [INFO] train episode 2713: reward = 157.00, steps = 157
00:03:04 [INFO] train episode 2714: reward = 200.00, steps = 200
00:03:04 [INFO] train episode 2715: reward = 102.00, steps = 102
00:03:04 [INFO] train episode 2716: reward = 114.00, steps = 114
00:03:04 [INFO] train episode 2717: reward = 200.00, steps = 200
00:03:04 [INFO] train episode 2718: reward = 147.00, steps = 147
00:03:04 [INFO] train episode 2719: reward = 200.00, steps = 200
00:03:04 [INFO] train episode 2720: reward = 77.00, steps = 77
00:03:04 [INFO] train episode 2721: reward = 158.00, steps = 158
00:03:04 [INFO] train episode 2722: reward = 200.00, steps = 200
00:03:04 [INFO] train episode 2723: reward = 200.00, steps = 200
00:03:04 [INFO] train episode 2724: reward = 200.00, steps = 200
00:03:04 [INFO] train episode 2725: reward = 200.00, steps = 200
00:03:05 [INFO] train episode 2726: reward = 147.00, steps = 147
00:03:05 [INFO] train episode 2727: reward = 200.00, steps = 200
00:03:05 [INFO] train episode 2728: reward = 200.00, steps = 200
00:03:05 [INFO] train episode 2729: reward = 200.00, steps = 200
00:03:05 [INFO] train episode 2730: reward = 176.00, steps = 176
00:03:05 [INFO] train episode 2731: reward = 162.00, steps = 162
00:03:05 [INFO] train episode 2732: reward = 200.00, steps = 200
00:03:05 [INFO] train episode 2733: reward = 200.00, steps = 200
00:03:05 [INFO] train episode 2734: reward = 200.00, steps = 200
00:03:05 [INFO] train episode 2735: reward = 200.00, steps = 200
00:03:05 [INFO] train episode 2736: reward = 158.00, steps = 158
00:03:05 [INFO] train episode 2737: reward = 198.00, steps = 198
00:03:05 [INFO] train episode 2738: reward = 200.00, steps = 200
00:03:06 [INFO] train episode 2739: reward = 200.00, steps = 200
00:03:06 [INFO] train episode 2740: reward = 146.00, steps = 146
00:03:06 [INFO] train episode 2741: reward = 200.00, steps = 200
00:03:06 [INFO] train episode 2742: reward = 200.00, steps = 200
00:03:06 [INFO] train episode 2743: reward = 200.00, steps = 200
00:03:06 [INFO] train episode 2744: reward = 165.00, steps = 165
00:03:06 [INFO] train episode 2745: reward = 200.00, steps = 200
00:03:06 [INFO] train episode 2746: reward = 200.00, steps = 200
00:03:06 [INFO] train episode 2747: reward = 200.00, steps = 200
00:03:06 [INFO] train episode 2748: reward = 200.00, steps = 200
00:03:06 [INFO] train episode 2749: reward = 200.00, steps = 200
00:03:06 [INFO] train episode 2750: reward = 167.00, steps = 167
00:03:06 [INFO] train episode 2751: reward = 160.00, steps = 160
00:03:06 [INFO] train episode 2752: reward = 200.00, steps = 200
00:03:07 [INFO] train episode 2753: reward = 104.00, steps = 104
00:03:07 [INFO] train episode 2754: reward = 200.00, steps = 200
00:03:07 [INFO] train episode 2755: reward = 159.00, steps = 159
00:03:07 [INFO] train episode 2756: reward = 200.00, steps = 200
00:03:07 [INFO] train episode 2757: reward = 200.00, steps = 200
00:03:07 [INFO] train episode 2758: reward = 197.00, steps = 197
00:03:07 [INFO] train episode 2759: reward = 200.00, steps = 200
00:03:07 [INFO] train episode 2760: reward = 200.00, steps = 200
00:03:07 [INFO] train episode 2761: reward = 200.00, steps = 200
00:03:07 [INFO] train episode 2762: reward = 200.00, steps = 200
00:03:07 [INFO] train episode 2763: reward = 146.00, steps = 146
00:03:07 [INFO] train episode 2764: reward = 200.00, steps = 200
00:03:07 [INFO] train episode 2765: reward = 200.00, steps = 200
00:03:07 [INFO] train episode 2766: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2767: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2768: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2769: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2770: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2771: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2772: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2773: reward = 173.00, steps = 173
00:03:08 [INFO] train episode 2774: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2775: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2776: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2777: reward = 200.00, steps = 200
00:03:08 [INFO] train episode 2778: reward = 132.00, steps = 132
00:03:09 [INFO] train episode 2779: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2780: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2781: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2782: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2783: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2784: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2785: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2786: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2787: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2788: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2789: reward = 200.00, steps = 200
00:03:09 [INFO] train episode 2790: reward = 144.00, steps = 144
00:03:09 [INFO] train episode 2791: reward = 149.00, steps = 149
00:03:10 [INFO] train episode 2792: reward = 200.00, steps = 200
00:03:10 [INFO] train episode 2793: reward = 162.00, steps = 162
00:03:10 [INFO] train episode 2794: reward = 200.00, steps = 200
00:03:10 [INFO] train episode 2795: reward = 200.00, steps = 200
00:03:10 [INFO] train episode 2796: reward = 200.00, steps = 200
00:03:10 [INFO] train episode 2797: reward = 198.00, steps = 198
00:03:10 [INFO] train episode 2798: reward = 172.00, steps = 172
00:03:10 [INFO] train episode 2799: reward = 117.00, steps = 117
00:03:10 [INFO] train episode 2800: reward = 200.00, steps = 200
00:03:10 [INFO] train episode 2801: reward = 200.00, steps = 200
00:03:10 [INFO] train episode 2802: reward = 125.00, steps = 125
00:03:10 [INFO] train episode 2803: reward = 114.00, steps = 114
00:03:10 [INFO] train episode 2804: reward = 200.00, steps = 200
00:03:10 [INFO] train episode 2805: reward = 129.00, steps = 129
00:03:10 [INFO] train episode 2806: reward = 63.00, steps = 63
00:03:10 [INFO] train episode 2807: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2808: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2809: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2810: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2811: reward = 195.00, steps = 195
00:03:11 [INFO] train episode 2812: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2813: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2814: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2815: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2816: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2817: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2818: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2819: reward = 200.00, steps = 200
00:03:11 [INFO] train episode 2820: reward = 200.00, steps = 200
00:03:12 [INFO] train episode 2821: reward = 140.00, steps = 140
00:03:12 [INFO] train episode 2822: reward = 200.00, steps = 200
00:03:12 [INFO] train episode 2823: reward = 200.00, steps = 200
00:03:12 [INFO] train episode 2824: reward = 200.00, steps = 200
00:03:12 [INFO] train episode 2825: reward = 200.00, steps = 200
00:03:12 [INFO] train episode 2826: reward = 200.00, steps = 200
00:03:12 [INFO] train episode 2827: reward = 200.00, steps = 200
00:03:12 [INFO] train episode 2828: reward = 68.00, steps = 68
00:03:12 [INFO] train episode 2829: reward = 163.00, steps = 163
00:03:12 [INFO] train episode 2830: reward = 200.00, steps = 200
00:03:12 [INFO] train episode 2831: reward = 200.00, steps = 200
00:03:12 [INFO] train episode 2832: reward = 200.00, steps = 200
00:03:13 [INFO] train episode 2833: reward = 200.00, steps = 200
00:03:13 [INFO] train episode 2834: reward = 200.00, steps = 200
00:03:13 [INFO] train episode 2835: reward = 200.00, steps = 200
00:03:13 [INFO] train episode 2836: reward = 200.00, steps = 200
00:03:13 [INFO] train episode 2837: reward = 198.00, steps = 198
00:03:13 [INFO] train episode 2838: reward = 200.00, steps = 200
00:03:13 [INFO] train episode 2839: reward = 200.00, steps = 200
00:03:13 [INFO] train episode 2840: reward = 192.00, steps = 192
00:03:13 [INFO] train episode 2841: reward = 171.00, steps = 171
00:03:13 [INFO] train episode 2842: reward = 108.00, steps = 108
00:03:13 [INFO] train episode 2843: reward = 200.00, steps = 200
00:03:13 [INFO] train episode 2844: reward = 159.00, steps = 159
00:03:13 [INFO] train episode 2845: reward = 50.00, steps = 50
00:03:14 [INFO] train episode 2846: reward = 200.00, steps = 200
00:03:14 [INFO] train episode 2847: reward = 200.00, steps = 200
00:03:14 [INFO] train episode 2848: reward = 200.00, steps = 200
00:03:14 [INFO] train episode 2849: reward = 200.00, steps = 200
00:03:14 [INFO] train episode 2850: reward = 200.00, steps = 200
00:03:14 [INFO] train episode 2851: reward = 200.00, steps = 200
00:03:14 [INFO] train episode 2852: reward = 200.00, steps = 200
00:03:14 [INFO] train episode 2853: reward = 167.00, steps = 167
00:03:14 [INFO] train episode 2854: reward = 153.00, steps = 153
00:03:14 [INFO] train episode 2855: reward = 200.00, steps = 200
00:03:14 [INFO] train episode 2856: reward = 200.00, steps = 200
00:03:14 [INFO] train episode 2857: reward = 200.00, steps = 200
00:03:14 [INFO] train episode 2858: reward = 123.00, steps = 123
00:03:15 [INFO] train episode 2859: reward = 200.00, steps = 200
00:03:15 [INFO] train episode 2860: reward = 200.00, steps = 200
00:03:15 [INFO] train episode 2861: reward = 200.00, steps = 200
00:03:15 [INFO] train episode 2862: reward = 200.00, steps = 200
00:03:15 [INFO] train episode 2863: reward = 73.00, steps = 73
00:03:15 [INFO] train episode 2864: reward = 150.00, steps = 150
00:03:15 [INFO] train episode 2865: reward = 200.00, steps = 200
00:03:15 [INFO] train episode 2866: reward = 192.00, steps = 192
00:03:15 [INFO] train episode 2867: reward = 200.00, steps = 200
00:03:15 [INFO] train episode 2868: reward = 200.00, steps = 200
00:03:15 [INFO] train episode 2869: reward = 200.00, steps = 200
00:03:15 [INFO] train episode 2870: reward = 109.00, steps = 109
00:03:15 [INFO] train episode 2871: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2872: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2873: reward = 125.00, steps = 125
00:03:16 [INFO] train episode 2874: reward = 186.00, steps = 186
00:03:16 [INFO] train episode 2875: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2876: reward = 31.00, steps = 31
00:03:16 [INFO] train episode 2877: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2878: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2879: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2880: reward = 133.00, steps = 133
00:03:16 [INFO] train episode 2881: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2882: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2883: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2884: reward = 161.00, steps = 161
00:03:16 [INFO] train episode 2885: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2886: reward = 200.00, steps = 200
00:03:16 [INFO] train episode 2887: reward = 29.00, steps = 29
00:03:17 [INFO] train episode 2888: reward = 200.00, steps = 200
00:03:17 [INFO] train episode 2889: reward = 200.00, steps = 200
00:03:17 [INFO] train episode 2890: reward = 200.00, steps = 200
00:03:17 [INFO] train episode 2891: reward = 200.00, steps = 200
00:03:17 [INFO] train episode 2892: reward = 200.00, steps = 200
00:03:17 [INFO] train episode 2893: reward = 200.00, steps = 200
00:03:17 [INFO] train episode 2894: reward = 200.00, steps = 200
00:03:17 [INFO] train episode 2895: reward = 200.00, steps = 200
00:03:17 [INFO] train episode 2896: reward = 200.00, steps = 200
00:03:17 [INFO] train episode 2897: reward = 101.00, steps = 101
00:03:17 [INFO] train episode 2898: reward = 196.00, steps = 196
00:03:17 [INFO] train episode 2899: reward = 120.00, steps = 120
00:03:17 [INFO] train episode 2900: reward = 194.00, steps = 194
00:03:17 [INFO] train episode 2901: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2902: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2903: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2904: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2905: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2906: reward = 161.00, steps = 161
00:03:18 [INFO] train episode 2907: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2908: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2909: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2910: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2911: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2912: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2913: reward = 200.00, steps = 200
00:03:18 [INFO] train episode 2914: reward = 167.00, steps = 167
00:03:19 [INFO] train episode 2915: reward = 200.00, steps = 200
00:03:19 [INFO] train episode 2916: reward = 200.00, steps = 200
00:03:19 [INFO] train episode 2917: reward = 200.00, steps = 200
00:03:19 [INFO] train episode 2918: reward = 200.00, steps = 200
00:03:19 [INFO] train episode 2919: reward = 200.00, steps = 200
00:03:19 [INFO] train episode 2920: reward = 200.00, steps = 200
00:03:19 [INFO] train episode 2921: reward = 128.00, steps = 128
00:03:19 [INFO] train episode 2922: reward = 200.00, steps = 200
00:03:19 [INFO] train episode 2923: reward = 169.00, steps = 169
00:03:19 [INFO] train episode 2924: reward = 200.00, steps = 200
00:03:19 [INFO] train episode 2925: reward = 200.00, steps = 200
00:03:19 [INFO] train episode 2926: reward = 123.00, steps = 123
00:03:19 [INFO] train episode 2927: reward = 200.00, steps = 200
00:03:20 [INFO] train episode 2928: reward = 178.00, steps = 178
00:03:20 [INFO] train episode 2929: reward = 22.00, steps = 22
00:03:20 [INFO] train episode 2930: reward = 200.00, steps = 200
00:03:20 [INFO] train episode 2931: reward = 200.00, steps = 200
00:03:20 [INFO] train episode 2932: reward = 200.00, steps = 200
00:03:20 [INFO] train episode 2933: reward = 178.00, steps = 178
00:03:20 [INFO] train episode 2934: reward = 200.00, steps = 200
00:03:20 [INFO] train episode 2935: reward = 200.00, steps = 200
00:03:20 [INFO] train episode 2936: reward = 200.00, steps = 200
00:03:20 [INFO] train episode 2937: reward = 100.00, steps = 100
00:03:20 [INFO] train episode 2938: reward = 200.00, steps = 200
00:03:20 [INFO] train episode 2939: reward = 141.00, steps = 141
00:03:20 [INFO] train episode 2940: reward = 94.00, steps = 94
00:03:20 [INFO] train episode 2941: reward = 200.00, steps = 200
00:03:20 [INFO] train episode 2942: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2943: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2944: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2945: reward = 189.00, steps = 189
00:03:21 [INFO] train episode 2946: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2947: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2948: reward = 108.00, steps = 108
00:03:21 [INFO] train episode 2949: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2950: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2951: reward = 116.00, steps = 116
00:03:21 [INFO] train episode 2952: reward = 124.00, steps = 124
00:03:21 [INFO] train episode 2953: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2954: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2955: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2956: reward = 200.00, steps = 200
00:03:21 [INFO] train episode 2957: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2958: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2959: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2960: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2961: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2962: reward = 157.00, steps = 157
00:03:22 [INFO] train episode 2963: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2964: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2965: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2966: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2967: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2968: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2969: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2970: reward = 200.00, steps = 200
00:03:22 [INFO] train episode 2971: reward = 110.00, steps = 110
00:03:23 [INFO] train episode 2972: reward = 200.00, steps = 200
00:03:23 [INFO] train episode 2973: reward = 163.00, steps = 163
00:03:23 [INFO] train episode 2974: reward = 200.00, steps = 200
00:03:23 [INFO] train episode 2975: reward = 179.00, steps = 179
00:03:23 [INFO] train episode 2976: reward = 171.00, steps = 171
00:03:23 [INFO] train episode 2977: reward = 200.00, steps = 200
00:03:23 [INFO] train episode 2978: reward = 200.00, steps = 200
00:03:23 [INFO] train episode 2979: reward = 200.00, steps = 200
00:03:23 [INFO] train episode 2980: reward = 200.00, steps = 200
00:03:23 [INFO] train episode 2981: reward = 200.00, steps = 200
00:03:23 [INFO] train episode 2982: reward = 200.00, steps = 200
00:03:23 [INFO] train episode 2983: reward = 200.00, steps = 200
00:03:23 [INFO] train episode 2984: reward = 200.00, steps = 200
00:03:23 [INFO] train episode 2985: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2986: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2987: reward = 198.00, steps = 198
00:03:24 [INFO] train episode 2988: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2989: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2990: reward = 44.00, steps = 44
00:03:24 [INFO] train episode 2991: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2992: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2993: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2994: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2995: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2996: reward = 111.00, steps = 111
00:03:24 [INFO] train episode 2997: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2998: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 2999: reward = 200.00, steps = 200
00:03:24 [INFO] train episode 3000: reward = 200.00, steps = 200
00:03:25 [INFO] train episode 3001: reward = 200.00, steps = 200
00:03:25 [INFO] train episode 3002: reward = 31.00, steps = 31
00:03:25 [INFO] train episode 3003: reward = 200.00, steps = 200
00:03:25 [INFO] train episode 3004: reward = 200.00, steps = 200
00:03:25 [INFO] train episode 3005: reward = 200.00, steps = 200
00:03:25 [INFO] train episode 3006: reward = 177.00, steps = 177
00:03:25 [INFO] train episode 3007: reward = 200.00, steps = 200
00:03:25 [INFO] train episode 3008: reward = 167.00, steps = 167
00:03:25 [INFO] train episode 3009: reward = 200.00, steps = 200
00:03:25 [INFO] train episode 3010: reward = 200.00, steps = 200
00:03:25 [INFO] train episode 3011: reward = 200.00, steps = 200
00:03:25 [INFO] train episode 3012: reward = 197.00, steps = 197
00:03:25 [INFO] train episode 3013: reward = 200.00, steps = 200
00:03:25 [INFO] train episode 3014: reward = 200.00, steps = 200
00:03:26 [INFO] train episode 3015: reward = 200.00, steps = 200
00:03:26 [INFO] train episode 3016: reward = 22.00, steps = 22
00:03:26 [INFO] train episode 3017: reward = 200.00, steps = 200
00:03:26 [INFO] train episode 3018: reward = 200.00, steps = 200
00:03:26 [INFO] train episode 3019: reward = 178.00, steps = 178
00:03:26 [INFO] train episode 3020: reward = 200.00, steps = 200
00:03:26 [INFO] train episode 3021: reward = 198.00, steps = 198
00:03:26 [INFO] train episode 3022: reward = 200.00, steps = 200
00:03:26 [INFO] train episode 3023: reward = 200.00, steps = 200
00:03:26 [INFO] train episode 3024: reward = 200.00, steps = 200
00:03:26 [INFO] train episode 3025: reward = 200.00, steps = 200
00:03:26 [INFO] train episode 3026: reward = 200.00, steps = 200
00:03:26 [INFO] train episode 3027: reward = 127.00, steps = 127
00:03:26 [INFO] train episode 3028: reward = 164.00, steps = 164
00:03:26 [INFO] train episode 3029: reward = 200.00, steps = 200
00:03:27 [INFO] train episode 3030: reward = 186.00, steps = 186
00:03:27 [INFO] train episode 3031: reward = 200.00, steps = 200
00:03:27 [INFO] train episode 3032: reward = 200.00, steps = 200
00:03:27 [INFO] train episode 3033: reward = 200.00, steps = 200
00:03:27 [INFO] train episode 3034: reward = 200.00, steps = 200
00:03:27 [INFO] train episode 3035: reward = 200.00, steps = 200
00:03:27 [INFO] train episode 3036: reward = 125.00, steps = 125
00:03:27 [INFO] train episode 3037: reward = 190.00, steps = 190
00:03:27 [INFO] train episode 3038: reward = 200.00, steps = 200
00:03:27 [INFO] train episode 3039: reward = 116.00, steps = 116
00:03:27 [INFO] train episode 3040: reward = 200.00, steps = 200
00:03:27 [INFO] train episode 3041: reward = 200.00, steps = 200
00:03:27 [INFO] train episode 3042: reward = 200.00, steps = 200
00:03:27 [INFO] train episode 3043: reward = 155.00, steps = 155
00:03:28 [INFO] train episode 3044: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3045: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3046: reward = 145.00, steps = 145
00:03:28 [INFO] train episode 3047: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3048: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3049: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3050: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3051: reward = 154.00, steps = 154
00:03:28 [INFO] train episode 3052: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3053: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3054: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3055: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3056: reward = 200.00, steps = 200
00:03:28 [INFO] train episode 3057: reward = 200.00, steps = 200
00:03:29 [INFO] train episode 3058: reward = 200.00, steps = 200
00:03:29 [INFO] train episode 3059: reward = 200.00, steps = 200
00:03:29 [INFO] train episode 3060: reward = 200.00, steps = 200
00:03:29 [INFO] train episode 3061: reward = 200.00, steps = 200
00:03:29 [INFO] train episode 3062: reward = 200.00, steps = 200
00:03:29 [INFO] train episode 3063: reward = 200.00, steps = 200
00:03:29 [INFO] train episode 3064: reward = 108.00, steps = 108
00:03:29 [INFO] train episode 3065: reward = 200.00, steps = 200
00:03:29 [INFO] train episode 3066: reward = 177.00, steps = 177
00:03:29 [INFO] train episode 3067: reward = 200.00, steps = 200
00:03:29 [INFO] train episode 3068: reward = 200.00, steps = 200
00:03:29 [INFO] train episode 3069: reward = 165.00, steps = 165
00:03:29 [INFO] train episode 3070: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3071: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3072: reward = 149.00, steps = 149
00:03:30 [INFO] train episode 3073: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3074: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3075: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3076: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3077: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3078: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3079: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3080: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3081: reward = 198.00, steps = 198
00:03:30 [INFO] train episode 3082: reward = 77.00, steps = 77
00:03:30 [INFO] train episode 3083: reward = 200.00, steps = 200
00:03:30 [INFO] train episode 3084: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3085: reward = 183.00, steps = 183
00:03:31 [INFO] train episode 3086: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3087: reward = 142.00, steps = 142
00:03:31 [INFO] train episode 3088: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3089: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3090: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3091: reward = 104.00, steps = 104
00:03:31 [INFO] train episode 3092: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3093: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3094: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3095: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3096: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3097: reward = 200.00, steps = 200
00:03:31 [INFO] train episode 3098: reward = 200.00, steps = 200
00:03:32 [INFO] train episode 3099: reward = 200.00, steps = 200
00:03:32 [INFO] train episode 3100: reward = 200.00, steps = 200
00:03:32 [INFO] train episode 3101: reward = 158.00, steps = 158
00:03:32 [INFO] train episode 3102: reward = 198.00, steps = 198
00:03:32 [INFO] train episode 3103: reward = 198.00, steps = 198
00:03:32 [INFO] train episode 3104: reward = 200.00, steps = 200
00:03:32 [INFO] train episode 3105: reward = 200.00, steps = 200
00:03:32 [INFO] train episode 3106: reward = 180.00, steps = 180
00:03:32 [INFO] train episode 3107: reward = 153.00, steps = 153
00:03:32 [INFO] train episode 3108: reward = 200.00, steps = 200
00:03:32 [INFO] train episode 3109: reward = 200.00, steps = 200
00:03:32 [INFO] train episode 3110: reward = 200.00, steps = 200
00:03:32 [INFO] train episode 3111: reward = 200.00, steps = 200
00:03:32 [INFO] train episode 3112: reward = 135.00, steps = 135
00:03:33 [INFO] train episode 3113: reward = 200.00, steps = 200
00:03:33 [INFO] train episode 3114: reward = 200.00, steps = 200
00:03:33 [INFO] train episode 3115: reward = 180.00, steps = 180
00:03:33 [INFO] train episode 3116: reward = 29.00, steps = 29
00:03:33 [INFO] train episode 3117: reward = 200.00, steps = 200
00:03:33 [INFO] train episode 3118: reward = 200.00, steps = 200
00:03:33 [INFO] train episode 3119: reward = 200.00, steps = 200
00:03:33 [INFO] train episode 3120: reward = 151.00, steps = 151
00:03:33 [INFO] train episode 3121: reward = 200.00, steps = 200
00:03:33 [INFO] train episode 3122: reward = 200.00, steps = 200
00:03:33 [INFO] train episode 3123: reward = 200.00, steps = 200
00:03:33 [INFO] train episode 3124: reward = 200.00, steps = 200
00:03:33 [INFO] train episode 3125: reward = 200.00, steps = 200
00:03:33 [INFO] train episode 3126: reward = 123.00, steps = 123
00:03:33 [INFO] train episode 3127: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3128: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3129: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3130: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3131: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3132: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3133: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3134: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3135: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3136: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3137: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3138: reward = 105.00, steps = 105
00:03:34 [INFO] train episode 3139: reward = 200.00, steps = 200
00:03:34 [INFO] train episode 3140: reward = 144.00, steps = 144
00:03:34 [INFO] train episode 3141: reward = 55.00, steps = 55
00:03:35 [INFO] train episode 3142: reward = 200.00, steps = 200
00:03:35 [INFO] train episode 3143: reward = 161.00, steps = 161
00:03:35 [INFO] train episode 3144: reward = 200.00, steps = 200
00:03:35 [INFO] train episode 3145: reward = 144.00, steps = 144
00:03:35 [INFO] train episode 3146: reward = 163.00, steps = 163
00:03:35 [INFO] train episode 3147: reward = 200.00, steps = 200
00:03:35 [INFO] train episode 3148: reward = 200.00, steps = 200
00:03:35 [INFO] train episode 3149: reward = 200.00, steps = 200
00:03:35 [INFO] train episode 3150: reward = 200.00, steps = 200
00:03:35 [INFO] train episode 3151: reward = 200.00, steps = 200
00:03:35 [INFO] train episode 3152: reward = 31.00, steps = 31
00:03:35 [INFO] train episode 3153: reward = 200.00, steps = 200
00:03:35 [INFO] train episode 3154: reward = 180.00, steps = 180
00:03:35 [INFO] train episode 3155: reward = 136.00, steps = 136
00:03:35 [INFO] train episode 3156: reward = 160.00, steps = 160
00:03:36 [INFO] train episode 3157: reward = 200.00, steps = 200
00:03:36 [INFO] train episode 3158: reward = 200.00, steps = 200
00:03:36 [INFO] train episode 3159: reward = 146.00, steps = 146
00:03:36 [INFO] train episode 3160: reward = 200.00, steps = 200
00:03:36 [INFO] train episode 3161: reward = 200.00, steps = 200
00:03:36 [INFO] train episode 3162: reward = 66.00, steps = 66
00:03:36 [INFO] train episode 3163: reward = 103.00, steps = 103
00:03:36 [INFO] train episode 3164: reward = 158.00, steps = 158
00:03:36 [INFO] train episode 3165: reward = 200.00, steps = 200
00:03:36 [INFO] train episode 3166: reward = 200.00, steps = 200
00:03:36 [INFO] train episode 3167: reward = 200.00, steps = 200
00:03:36 [INFO] train episode 3168: reward = 200.00, steps = 200
00:03:36 [INFO] train episode 3169: reward = 200.00, steps = 200
00:03:36 [INFO] train episode 3170: reward = 200.00, steps = 200
00:03:37 [INFO] train episode 3171: reward = 200.00, steps = 200
00:03:37 [INFO] train episode 3172: reward = 156.00, steps = 156
00:03:37 [INFO] train episode 3173: reward = 200.00, steps = 200
00:03:37 [INFO] train episode 3174: reward = 191.00, steps = 191
00:03:37 [INFO] train episode 3175: reward = 200.00, steps = 200
00:03:37 [INFO] train episode 3176: reward = 141.00, steps = 141
00:03:37 [INFO] train episode 3177: reward = 69.00, steps = 69
00:03:37 [INFO] train episode 3178: reward = 200.00, steps = 200
00:03:37 [INFO] train episode 3179: reward = 105.00, steps = 105
00:03:37 [INFO] train episode 3180: reward = 80.00, steps = 80
00:03:37 [INFO] train episode 3181: reward = 200.00, steps = 200
00:03:37 [INFO] train episode 3182: reward = 134.00, steps = 134
00:03:37 [INFO] train episode 3183: reward = 162.00, steps = 162
00:03:37 [INFO] train episode 3184: reward = 200.00, steps = 200
00:03:37 [INFO] train episode 3185: reward = 143.00, steps = 143
00:03:37 [INFO] train episode 3186: reward = 125.00, steps = 125
00:03:38 [INFO] train episode 3187: reward = 200.00, steps = 200
00:03:38 [INFO] train episode 3188: reward = 200.00, steps = 200
00:03:38 [INFO] train episode 3189: reward = 200.00, steps = 200
00:03:38 [INFO] train episode 3190: reward = 165.00, steps = 165
00:03:38 [INFO] train episode 3191: reward = 200.00, steps = 200
00:03:38 [INFO] train episode 3192: reward = 200.00, steps = 200
00:03:38 [INFO] train episode 3193: reward = 145.00, steps = 145
00:03:38 [INFO] train episode 3194: reward = 190.00, steps = 190
00:03:38 [INFO] train episode 3195: reward = 200.00, steps = 200
00:03:38 [INFO] train episode 3196: reward = 142.00, steps = 142
00:03:38 [INFO] train episode 3197: reward = 200.00, steps = 200
00:03:38 [INFO] train episode 3198: reward = 159.00, steps = 159
00:03:38 [INFO] train episode 3199: reward = 200.00, steps = 200
00:03:38 [INFO] train episode 3200: reward = 200.00, steps = 200
00:03:38 [INFO] train episode 3201: reward = 200.00, steps = 200
00:03:39 [INFO] train episode 3202: reward = 171.00, steps = 171
00:03:39 [INFO] train episode 3203: reward = 183.00, steps = 183
00:03:39 [INFO] train episode 3204: reward = 177.00, steps = 177
00:03:39 [INFO] train episode 3205: reward = 183.00, steps = 183
00:03:39 [INFO] train episode 3206: reward = 170.00, steps = 170
00:03:39 [INFO] train episode 3207: reward = 137.00, steps = 137
00:03:39 [INFO] train episode 3208: reward = 145.00, steps = 145
00:03:39 [INFO] train episode 3209: reward = 159.00, steps = 159
00:03:39 [INFO] train episode 3210: reward = 178.00, steps = 178
00:03:39 [INFO] train episode 3211: reward = 200.00, steps = 200
00:03:39 [INFO] train episode 3212: reward = 170.00, steps = 170
00:03:39 [INFO] train episode 3213: reward = 177.00, steps = 177
00:03:39 [INFO] train episode 3214: reward = 174.00, steps = 174
00:03:39 [INFO] train episode 3215: reward = 200.00, steps = 200
00:03:39 [INFO] train episode 3216: reward = 200.00, steps = 200
00:03:40 [INFO] train episode 3217: reward = 200.00, steps = 200
00:03:40 [INFO] train episode 3218: reward = 200.00, steps = 200
00:03:40 [INFO] train episode 3219: reward = 200.00, steps = 200
00:03:40 [INFO] train episode 3220: reward = 200.00, steps = 200
00:03:40 [INFO] train episode 3221: reward = 132.00, steps = 132
00:03:40 [INFO] train episode 3222: reward = 180.00, steps = 180
00:03:40 [INFO] train episode 3223: reward = 158.00, steps = 158
00:03:40 [INFO] train episode 3224: reward = 200.00, steps = 200
00:03:40 [INFO] train episode 3225: reward = 200.00, steps = 200
00:03:40 [INFO] train episode 3226: reward = 127.00, steps = 127
00:03:40 [INFO] train episode 3227: reward = 200.00, steps = 200
00:03:40 [INFO] train episode 3228: reward = 200.00, steps = 200
00:03:40 [INFO] train episode 3229: reward = 146.00, steps = 146
00:03:40 [INFO] train episode 3230: reward = 122.00, steps = 122
00:03:40 [INFO] train episode 3231: reward = 200.00, steps = 200
00:03:40 [INFO] train episode 3232: reward = 124.00, steps = 124
00:03:41 [INFO] train episode 3233: reward = 191.00, steps = 191
00:03:41 [INFO] train episode 3234: reward = 200.00, steps = 200
00:03:41 [INFO] train episode 3235: reward = 193.00, steps = 193
00:03:41 [INFO] train episode 3236: reward = 171.00, steps = 171
00:03:41 [INFO] train episode 3237: reward = 158.00, steps = 158
00:03:41 [INFO] train episode 3238: reward = 200.00, steps = 200
00:03:41 [INFO] train episode 3239: reward = 200.00, steps = 200
00:03:41 [INFO] train episode 3240: reward = 200.00, steps = 200
00:03:41 [INFO] train episode 3241: reward = 200.00, steps = 200
00:03:41 [INFO] train episode 3242: reward = 200.00, steps = 200
00:03:41 [INFO] train episode 3243: reward = 194.00, steps = 194
00:03:41 [INFO] train episode 3244: reward = 143.00, steps = 143
00:03:41 [INFO] train episode 3245: reward = 200.00, steps = 200
00:03:41 [INFO] train episode 3246: reward = 200.00, steps = 200
00:03:42 [INFO] train episode 3247: reward = 200.00, steps = 200
00:03:42 [INFO] train episode 3248: reward = 200.00, steps = 200
00:03:42 [INFO] train episode 3249: reward = 130.00, steps = 130
00:03:42 [INFO] train episode 3250: reward = 129.00, steps = 129
00:03:42 [INFO] train episode 3251: reward = 93.00, steps = 93
00:03:42 [INFO] train episode 3252: reward = 190.00, steps = 190
00:03:42 [INFO] train episode 3253: reward = 91.00, steps = 91
00:03:42 [INFO] train episode 3254: reward = 135.00, steps = 135
00:03:42 [INFO] train episode 3255: reward = 200.00, steps = 200
00:03:42 [INFO] train episode 3256: reward = 200.00, steps = 200
00:03:42 [INFO] train episode 3257: reward = 200.00, steps = 200
00:03:42 [INFO] train episode 3258: reward = 200.00, steps = 200
00:03:42 [INFO] train episode 3259: reward = 168.00, steps = 168
00:03:42 [INFO] train episode 3260: reward = 200.00, steps = 200
00:03:42 [INFO] train episode 3261: reward = 200.00, steps = 200
00:03:43 [INFO] train episode 3262: reward = 200.00, steps = 200
00:03:43 [INFO] train episode 3263: reward = 200.00, steps = 200
00:03:43 [INFO] train episode 3264: reward = 200.00, steps = 200
00:03:43 [INFO] train episode 3265: reward = 162.00, steps = 162
00:03:43 [INFO] train episode 3266: reward = 157.00, steps = 157
00:03:43 [INFO] train episode 3267: reward = 200.00, steps = 200
00:03:43 [INFO] train episode 3268: reward = 135.00, steps = 135
00:03:43 [INFO] train episode 3269: reward = 178.00, steps = 178
00:03:43 [INFO] train episode 3270: reward = 189.00, steps = 189
00:03:43 [INFO] train episode 3271: reward = 200.00, steps = 200
00:03:43 [INFO] train episode 3272: reward = 200.00, steps = 200
00:03:43 [INFO] train episode 3273: reward = 200.00, steps = 200
00:03:43 [INFO] train episode 3274: reward = 200.00, steps = 200
00:03:43 [INFO] train episode 3275: reward = 200.00, steps = 200
00:03:44 [INFO] train episode 3276: reward = 200.00, steps = 200
00:03:44 [INFO] train episode 3277: reward = 200.00, steps = 200
00:03:44 [INFO] train episode 3278: reward = 200.00, steps = 200
00:03:44 [INFO] train episode 3279: reward = 141.00, steps = 141
00:03:44 [INFO] train episode 3280: reward = 200.00, steps = 200
00:03:44 [INFO] train episode 3281: reward = 200.00, steps = 200
00:03:44 [INFO] train episode 3282: reward = 175.00, steps = 175
00:03:44 [INFO] train episode 3283: reward = 164.00, steps = 164
00:03:44 [INFO] train episode 3284: reward = 54.00, steps = 54
00:03:44 [INFO] train episode 3285: reward = 162.00, steps = 162
00:03:44 [INFO] train episode 3286: reward = 200.00, steps = 200
00:03:44 [INFO] train episode 3287: reward = 163.00, steps = 163
00:03:44 [INFO] train episode 3288: reward = 99.00, steps = 99
00:03:44 [INFO] train episode 3289: reward = 200.00, steps = 200
00:03:44 [INFO] train episode 3290: reward = 200.00, steps = 200
00:03:44 [INFO] train episode 3291: reward = 200.00, steps = 200
00:03:45 [INFO] train episode 3292: reward = 198.00, steps = 198
00:03:45 [INFO] train episode 3293: reward = 200.00, steps = 200
00:03:45 [INFO] train episode 3294: reward = 165.00, steps = 165
00:03:45 [INFO] train episode 3295: reward = 175.00, steps = 175
00:03:45 [INFO] train episode 3296: reward = 129.00, steps = 129
00:03:45 [INFO] train episode 3297: reward = 200.00, steps = 200
00:03:45 [INFO] train episode 3298: reward = 121.00, steps = 121
00:03:45 [INFO] train episode 3299: reward = 200.00, steps = 200
00:03:45 [INFO] train episode 3300: reward = 200.00, steps = 200
00:03:45 [INFO] train episode 3301: reward = 200.00, steps = 200
00:03:45 [INFO] train episode 3302: reward = 200.00, steps = 200
00:03:45 [INFO] train episode 3303: reward = 189.00, steps = 189
00:03:45 [INFO] train episode 3304: reward = 200.00, steps = 200
00:03:45 [INFO] train episode 3305: reward = 200.00, steps = 200
00:03:46 [INFO] train episode 3306: reward = 160.00, steps = 160
00:03:46 [INFO] train episode 3307: reward = 91.00, steps = 91
00:03:46 [INFO] train episode 3308: reward = 66.00, steps = 66
00:03:46 [INFO] train episode 3309: reward = 166.00, steps = 166
00:03:46 [INFO] train episode 3310: reward = 140.00, steps = 140
00:03:46 [INFO] train episode 3311: reward = 200.00, steps = 200
00:03:46 [INFO] train episode 3312: reward = 200.00, steps = 200
00:03:46 [INFO] train episode 3313: reward = 200.00, steps = 200
00:03:46 [INFO] train episode 3314: reward = 200.00, steps = 200
00:03:46 [INFO] train episode 3315: reward = 200.00, steps = 200
00:03:46 [INFO] train episode 3316: reward = 200.00, steps = 200
00:03:46 [INFO] train episode 3317: reward = 139.00, steps = 139
00:03:46 [INFO] train episode 3318: reward = 200.00, steps = 200
00:03:46 [INFO] train episode 3319: reward = 200.00, steps = 200
00:03:46 [INFO] train episode 3320: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3321: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3322: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3323: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3324: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3325: reward = 149.00, steps = 149
00:03:47 [INFO] train episode 3326: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3327: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3328: reward = 83.00, steps = 83
00:03:47 [INFO] train episode 3329: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3330: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3331: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3332: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3333: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3334: reward = 200.00, steps = 200
00:03:47 [INFO] train episode 3335: reward = 146.00, steps = 146
00:03:48 [INFO] train episode 3336: reward = 200.00, steps = 200
00:03:48 [INFO] train episode 3337: reward = 128.00, steps = 128
00:03:48 [INFO] train episode 3338: reward = 183.00, steps = 183
00:03:48 [INFO] train episode 3339: reward = 200.00, steps = 200
00:03:48 [INFO] train episode 3340: reward = 200.00, steps = 200
00:03:48 [INFO] train episode 3341: reward = 120.00, steps = 120
00:03:48 [INFO] train episode 3342: reward = 200.00, steps = 200
00:03:48 [INFO] train episode 3343: reward = 200.00, steps = 200
00:03:48 [INFO] train episode 3344: reward = 160.00, steps = 160
00:03:48 [INFO] train episode 3345: reward = 150.00, steps = 150
00:03:48 [INFO] train episode 3346: reward = 200.00, steps = 200
00:03:48 [INFO] train episode 3347: reward = 200.00, steps = 200
00:03:48 [INFO] train episode 3348: reward = 185.00, steps = 185
00:03:48 [INFO] train episode 3349: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3350: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3351: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3352: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3353: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3354: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3355: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3356: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3357: reward = 159.00, steps = 159
00:03:49 [INFO] train episode 3358: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3359: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3360: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3361: reward = 200.00, steps = 200
00:03:49 [INFO] train episode 3362: reward = 192.00, steps = 192
00:03:50 [INFO] train episode 3363: reward = 180.00, steps = 180
00:03:50 [INFO] train episode 3364: reward = 200.00, steps = 200
00:03:50 [INFO] train episode 3365: reward = 200.00, steps = 200
00:03:50 [INFO] train episode 3366: reward = 200.00, steps = 200
00:03:50 [INFO] train episode 3367: reward = 200.00, steps = 200
00:03:50 [INFO] train episode 3368: reward = 188.00, steps = 188
00:03:50 [INFO] train episode 3369: reward = 200.00, steps = 200
00:03:50 [INFO] train episode 3370: reward = 200.00, steps = 200
00:03:50 [INFO] train episode 3371: reward = 148.00, steps = 148
00:03:50 [INFO] train episode 3372: reward = 200.00, steps = 200
00:03:50 [INFO] train episode 3373: reward = 110.00, steps = 110
00:03:50 [INFO] train episode 3374: reward = 200.00, steps = 200
00:03:50 [INFO] train episode 3375: reward = 167.00, steps = 167
00:03:50 [INFO] train episode 3376: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3377: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3378: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3379: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3380: reward = 164.00, steps = 164
00:03:51 [INFO] train episode 3381: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3382: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3383: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3384: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3385: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3386: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3387: reward = 200.00, steps = 200
00:03:51 [INFO] train episode 3388: reward = 186.00, steps = 186
00:03:51 [INFO] train episode 3389: reward = 157.00, steps = 157
00:03:51 [INFO] train episode 3390: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3391: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3392: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3393: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3394: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3395: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3396: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3397: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3398: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3399: reward = 131.00, steps = 131
00:03:52 [INFO] train episode 3400: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3401: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3402: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3403: reward = 200.00, steps = 200
00:03:52 [INFO] train episode 3404: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3405: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3406: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3407: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3408: reward = 73.00, steps = 73
00:03:53 [INFO] train episode 3409: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3410: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3411: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3412: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3413: reward = 179.00, steps = 179
00:03:53 [INFO] train episode 3414: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3415: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3416: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3417: reward = 200.00, steps = 200
00:03:53 [INFO] train episode 3418: reward = 200.00, steps = 200
00:03:54 [INFO] train episode 3419: reward = 200.00, steps = 200
00:03:54 [INFO] train episode 3420: reward = 122.00, steps = 122
00:03:54 [INFO] train episode 3421: reward = 184.00, steps = 184
00:03:54 [INFO] train episode 3422: reward = 197.00, steps = 197
00:03:54 [INFO] train episode 3423: reward = 200.00, steps = 200
00:03:54 [INFO] train episode 3424: reward = 200.00, steps = 200
00:03:54 [INFO] train episode 3425: reward = 200.00, steps = 200
00:03:54 [INFO] train episode 3426: reward = 193.00, steps = 193
00:03:54 [INFO] train episode 3427: reward = 31.00, steps = 31
00:03:54 [INFO] train episode 3428: reward = 200.00, steps = 200
00:03:54 [INFO] train episode 3429: reward = 200.00, steps = 200
00:03:54 [INFO] train episode 3430: reward = 160.00, steps = 160
00:03:54 [INFO] train episode 3431: reward = 200.00, steps = 200
00:03:54 [INFO] train episode 3432: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3433: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3434: reward = 73.00, steps = 73
00:03:55 [INFO] train episode 3435: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3436: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3437: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3438: reward = 154.00, steps = 154
00:03:55 [INFO] train episode 3439: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3440: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3441: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3442: reward = 146.00, steps = 146
00:03:55 [INFO] train episode 3443: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3444: reward = 193.00, steps = 193
00:03:55 [INFO] train episode 3445: reward = 24.00, steps = 24
00:03:55 [INFO] train episode 3446: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3447: reward = 200.00, steps = 200
00:03:55 [INFO] train episode 3448: reward = 200.00, steps = 200
00:03:56 [INFO] train episode 3449: reward = 200.00, steps = 200
00:03:56 [INFO] train episode 3450: reward = 200.00, steps = 200
00:03:56 [INFO] train episode 3451: reward = 186.00, steps = 186
00:03:56 [INFO] train episode 3452: reward = 200.00, steps = 200
00:03:56 [INFO] train episode 3453: reward = 200.00, steps = 200
00:03:56 [INFO] train episode 3454: reward = 200.00, steps = 200
00:03:56 [INFO] train episode 3455: reward = 186.00, steps = 186
00:03:56 [INFO] train episode 3456: reward = 200.00, steps = 200
00:03:56 [INFO] train episode 3457: reward = 200.00, steps = 200
00:03:56 [INFO] train episode 3458: reward = 144.00, steps = 144
00:03:56 [INFO] train episode 3459: reward = 151.00, steps = 151
00:03:56 [INFO] train episode 3460: reward = 105.00, steps = 105
00:03:56 [INFO] train episode 3461: reward = 200.00, steps = 200
00:03:56 [INFO] train episode 3462: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3463: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3464: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3465: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3466: reward = 184.00, steps = 184
00:03:57 [INFO] train episode 3467: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3468: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3469: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3470: reward = 142.00, steps = 142
00:03:57 [INFO] train episode 3471: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3472: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3473: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3474: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3475: reward = 200.00, steps = 200
00:03:57 [INFO] train episode 3476: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3477: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3478: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3479: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3480: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3481: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3482: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3483: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3484: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3485: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3486: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3487: reward = 99.00, steps = 99
00:03:58 [INFO] train episode 3488: reward = 200.00, steps = 200
00:03:58 [INFO] train episode 3489: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3490: reward = 186.00, steps = 186
00:03:59 [INFO] train episode 3491: reward = 62.00, steps = 62
00:03:59 [INFO] train episode 3492: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3493: reward = 151.00, steps = 151
00:03:59 [INFO] train episode 3494: reward = 158.00, steps = 158
00:03:59 [INFO] train episode 3495: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3496: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3497: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3498: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3499: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3500: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3501: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3502: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3503: reward = 200.00, steps = 200
00:03:59 [INFO] train episode 3504: reward = 200.00, steps = 200
00:04:00 [INFO] train episode 3505: reward = 126.00, steps = 126
00:04:00 [INFO] train episode 3506: reward = 200.00, steps = 200
00:04:00 [INFO] train episode 3507: reward = 200.00, steps = 200
00:04:00 [INFO] train episode 3508: reward = 148.00, steps = 148
00:04:00 [INFO] train episode 3509: reward = 200.00, steps = 200
00:04:00 [INFO] train episode 3510: reward = 200.00, steps = 200
00:04:00 [INFO] train episode 3511: reward = 144.00, steps = 144
00:04:00 [INFO] train episode 3512: reward = 200.00, steps = 200
00:04:00 [INFO] train episode 3513: reward = 200.00, steps = 200
00:04:00 [INFO] train episode 3514: reward = 200.00, steps = 200
00:04:00 [INFO] train episode 3515: reward = 138.00, steps = 138
00:04:00 [INFO] train episode 3516: reward = 200.00, steps = 200
00:04:00 [INFO] train episode 3517: reward = 200.00, steps = 200
00:04:01 [INFO] train episode 3518: reward = 200.00, steps = 200
00:04:01 [INFO] train episode 3519: reward = 153.00, steps = 153
00:04:01 [INFO] train episode 3520: reward = 200.00, steps = 200
00:04:01 [INFO] train episode 3521: reward = 173.00, steps = 173
00:04:01 [INFO] train episode 3522: reward = 200.00, steps = 200
00:04:01 [INFO] train episode 3523: reward = 200.00, steps = 200
00:04:01 [INFO] train episode 3524: reward = 200.00, steps = 200
00:04:01 [INFO] train episode 3525: reward = 200.00, steps = 200
00:04:01 [INFO] train episode 3526: reward = 200.00, steps = 200
00:04:01 [INFO] train episode 3527: reward = 200.00, steps = 200
00:04:01 [INFO] train episode 3528: reward = 200.00, steps = 200
00:04:01 [INFO] train episode 3529: reward = 174.00, steps = 174
00:04:01 [INFO] train episode 3530: reward = 154.00, steps = 154
00:04:01 [INFO] train episode 3531: reward = 133.00, steps = 133
00:04:02 [INFO] train episode 3532: reward = 109.00, steps = 109
00:04:02 [INFO] train episode 3533: reward = 200.00, steps = 200
00:04:02 [INFO] train episode 3534: reward = 129.00, steps = 129
00:04:02 [INFO] train episode 3535: reward = 200.00, steps = 200
00:04:02 [INFO] train episode 3536: reward = 195.00, steps = 195
00:04:02 [INFO] train episode 3537: reward = 200.00, steps = 200
00:04:02 [INFO] train episode 3538: reward = 174.00, steps = 174
00:04:02 [INFO] train episode 3539: reward = 200.00, steps = 200
00:04:02 [INFO] train episode 3540: reward = 200.00, steps = 200
00:04:02 [INFO] train episode 3541: reward = 200.00, steps = 200
00:04:02 [INFO] train episode 3542: reward = 200.00, steps = 200
00:04:02 [INFO] train episode 3543: reward = 145.00, steps = 145
00:04:02 [INFO] train episode 3544: reward = 200.00, steps = 200
00:04:02 [INFO] train episode 3545: reward = 172.00, steps = 172
00:04:02 [INFO] train episode 3546: reward = 200.00, steps = 200
00:04:03 [INFO] train episode 3547: reward = 200.00, steps = 200
00:04:03 [INFO] train episode 3548: reward = 190.00, steps = 190
00:04:03 [INFO] train episode 3549: reward = 200.00, steps = 200
00:04:03 [INFO] train episode 3550: reward = 165.00, steps = 165
00:04:03 [INFO] train episode 3551: reward = 200.00, steps = 200
00:04:03 [INFO] train episode 3552: reward = 200.00, steps = 200
00:04:03 [INFO] train episode 3553: reward = 193.00, steps = 193
00:04:03 [INFO] train episode 3554: reward = 140.00, steps = 140
00:04:03 [INFO] train episode 3555: reward = 200.00, steps = 200
00:04:03 [INFO] train episode 3556: reward = 200.00, steps = 200
00:04:03 [INFO] train episode 3557: reward = 200.00, steps = 200
00:04:03 [INFO] train episode 3558: reward = 183.00, steps = 183
00:04:03 [INFO] train episode 3559: reward = 200.00, steps = 200
00:04:04 [INFO] train episode 3560: reward = 200.00, steps = 200
00:04:04 [INFO] train episode 3561: reward = 200.00, steps = 200
00:04:04 [INFO] train episode 3562: reward = 200.00, steps = 200
00:04:04 [INFO] train episode 3563: reward = 200.00, steps = 200
00:04:04 [INFO] train episode 3564: reward = 136.00, steps = 136
00:04:04 [INFO] train episode 3565: reward = 170.00, steps = 170
00:04:04 [INFO] train episode 3566: reward = 200.00, steps = 200
00:04:04 [INFO] train episode 3567: reward = 200.00, steps = 200
00:04:04 [INFO] train episode 3568: reward = 195.00, steps = 195
00:04:04 [INFO] train episode 3569: reward = 136.00, steps = 136
00:04:04 [INFO] train episode 3570: reward = 200.00, steps = 200
00:04:04 [INFO] train episode 3571: reward = 200.00, steps = 200
00:04:04 [INFO] train episode 3572: reward = 200.00, steps = 200
00:04:04 [INFO] train episode 3573: reward = 200.00, steps = 200
00:04:05 [INFO] train episode 3574: reward = 200.00, steps = 200
00:04:05 [INFO] train episode 3575: reward = 200.00, steps = 200
00:04:05 [INFO] train episode 3576: reward = 147.00, steps = 147
00:04:05 [INFO] train episode 3577: reward = 44.00, steps = 44
00:04:05 [INFO] train episode 3578: reward = 200.00, steps = 200
00:04:05 [INFO] train episode 3579: reward = 186.00, steps = 186
00:04:05 [INFO] train episode 3580: reward = 200.00, steps = 200
00:04:05 [INFO] train episode 3581: reward = 200.00, steps = 200
00:04:05 [INFO] train episode 3582: reward = 200.00, steps = 200
00:04:05 [INFO] train episode 3583: reward = 151.00, steps = 151
00:04:05 [INFO] train episode 3584: reward = 200.00, steps = 200
00:04:05 [INFO] train episode 3585: reward = 199.00, steps = 199
00:04:05 [INFO] train episode 3586: reward = 200.00, steps = 200
00:04:05 [INFO] train episode 3587: reward = 200.00, steps = 200
00:04:05 [INFO] train episode 3588: reward = 200.00, steps = 200
00:04:06 [INFO] train episode 3589: reward = 200.00, steps = 200
00:04:06 [INFO] train episode 3590: reward = 45.00, steps = 45
00:04:06 [INFO] train episode 3591: reward = 173.00, steps = 173
00:04:06 [INFO] train episode 3592: reward = 182.00, steps = 182
00:04:06 [INFO] train episode 3593: reward = 200.00, steps = 200
00:04:06 [INFO] train episode 3594: reward = 107.00, steps = 107
00:04:06 [INFO] train episode 3595: reward = 200.00, steps = 200
00:04:06 [INFO] train episode 3596: reward = 137.00, steps = 137
00:04:06 [INFO] train episode 3597: reward = 145.00, steps = 145
00:04:06 [INFO] train episode 3598: reward = 29.00, steps = 29
00:04:06 [INFO] train episode 3599: reward = 200.00, steps = 200
00:04:06 [INFO] train episode 3600: reward = 200.00, steps = 200
00:04:06 [INFO] train episode 3601: reward = 200.00, steps = 200
00:04:06 [INFO] train episode 3602: reward = 200.00, steps = 200
00:04:06 [INFO] train episode 3603: reward = 120.00, steps = 120
00:04:06 [INFO] train episode 3604: reward = 200.00, steps = 200
00:04:07 [INFO] train episode 3605: reward = 199.00, steps = 199
00:04:07 [INFO] train episode 3606: reward = 200.00, steps = 200
00:04:07 [INFO] train episode 3607: reward = 200.00, steps = 200
00:04:07 [INFO] train episode 3608: reward = 200.00, steps = 200
00:04:07 [INFO] train episode 3609: reward = 200.00, steps = 200
00:04:07 [INFO] train episode 3610: reward = 200.00, steps = 200
00:04:07 [INFO] train episode 3611: reward = 200.00, steps = 200
00:04:07 [INFO] train episode 3612: reward = 200.00, steps = 200
00:04:07 [INFO] train episode 3613: reward = 200.00, steps = 200
00:04:07 [INFO] train episode 3614: reward = 200.00, steps = 200
00:04:07 [INFO] train episode 3615: reward = 149.00, steps = 149
00:04:07 [INFO] train episode 3616: reward = 191.00, steps = 191
00:04:07 [INFO] train episode 3617: reward = 173.00, steps = 173
00:04:08 [INFO] train episode 3618: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3619: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3620: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3621: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3622: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3623: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3624: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3625: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3626: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3627: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3628: reward = 200.00, steps = 200
00:04:08 [INFO] train episode 3629: reward = 158.00, steps = 158
00:04:08 [INFO] train episode 3630: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3631: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3632: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3633: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3634: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3635: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3636: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3637: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3638: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3639: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3640: reward = 142.00, steps = 142
00:04:09 [INFO] train episode 3641: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3642: reward = 200.00, steps = 200
00:04:09 [INFO] train episode 3643: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3644: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3645: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3646: reward = 192.00, steps = 192
00:04:10 [INFO] train episode 3647: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3648: reward = 169.00, steps = 169
00:04:10 [INFO] train episode 3649: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3650: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3651: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3652: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3653: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3654: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3655: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3656: reward = 200.00, steps = 200
00:04:10 [INFO] train episode 3657: reward = 200.00, steps = 200
00:04:11 [INFO] train episode 3658: reward = 165.00, steps = 165
00:04:11 [INFO] train episode 3659: reward = 186.00, steps = 186
00:04:11 [INFO] train episode 3660: reward = 200.00, steps = 200
00:04:11 [INFO] train episode 3661: reward = 200.00, steps = 200
00:04:11 [INFO] train episode 3662: reward = 200.00, steps = 200
00:04:11 [INFO] train episode 3663: reward = 200.00, steps = 200
00:04:11 [INFO] train episode 3664: reward = 200.00, steps = 200
00:04:11 [INFO] train episode 3665: reward = 182.00, steps = 182
00:04:11 [INFO] train episode 3666: reward = 200.00, steps = 200
00:04:11 [INFO] train episode 3667: reward = 200.00, steps = 200
00:04:11 [INFO] train episode 3668: reward = 200.00, steps = 200
00:04:11 [INFO] train episode 3669: reward = 34.00, steps = 34
00:04:11 [INFO] train episode 3670: reward = 200.00, steps = 200
00:04:11 [INFO] train episode 3671: reward = 200.00, steps = 200
00:04:12 [INFO] train episode 3672: reward = 200.00, steps = 200
00:04:12 [INFO] train episode 3673: reward = 132.00, steps = 132
00:04:12 [INFO] train episode 3674: reward = 188.00, steps = 188
00:04:12 [INFO] train episode 3675: reward = 200.00, steps = 200
00:04:12 [INFO] train episode 3676: reward = 200.00, steps = 200
00:04:12 [INFO] train episode 3677: reward = 200.00, steps = 200
00:04:12 [INFO] train episode 3678: reward = 200.00, steps = 200
00:04:12 [INFO] train episode 3679: reward = 200.00, steps = 200
00:04:12 [INFO] train episode 3680: reward = 200.00, steps = 200
00:04:12 [INFO] train episode 3681: reward = 178.00, steps = 178
00:04:12 [INFO] train episode 3682: reward = 200.00, steps = 200
00:04:12 [INFO] train episode 3683: reward = 165.00, steps = 165
00:04:12 [INFO] train episode 3684: reward = 118.00, steps = 118
00:04:12 [INFO] train episode 3685: reward = 182.00, steps = 182
00:04:13 [INFO] train episode 3686: reward = 200.00, steps = 200
00:04:13 [INFO] train episode 3687: reward = 200.00, steps = 200
00:04:13 [INFO] train episode 3688: reward = 200.00, steps = 200
00:04:13 [INFO] train episode 3689: reward = 178.00, steps = 178
00:04:13 [INFO] train episode 3690: reward = 200.00, steps = 200
00:04:13 [INFO] train episode 3691: reward = 163.00, steps = 163
00:04:13 [INFO] train episode 3692: reward = 139.00, steps = 139
00:04:13 [INFO] train episode 3693: reward = 154.00, steps = 154
00:04:13 [INFO] train episode 3694: reward = 200.00, steps = 200
00:04:13 [INFO] train episode 3695: reward = 200.00, steps = 200
00:04:13 [INFO] train episode 3696: reward = 130.00, steps = 130
00:04:13 [INFO] train episode 3697: reward = 200.00, steps = 200
00:04:13 [INFO] train episode 3698: reward = 135.00, steps = 135
00:04:13 [INFO] train episode 3699: reward = 200.00, steps = 200
00:04:13 [INFO] train episode 3700: reward = 200.00, steps = 200
00:04:14 [INFO] train episode 3701: reward = 200.00, steps = 200
00:04:14 [INFO] train episode 3702: reward = 134.00, steps = 134
00:04:14 [INFO] train episode 3703: reward = 182.00, steps = 182
00:04:14 [INFO] train episode 3704: reward = 200.00, steps = 200
00:04:14 [INFO] train episode 3705: reward = 164.00, steps = 164
00:04:14 [INFO] train episode 3706: reward = 200.00, steps = 200
00:04:14 [INFO] train episode 3707: reward = 200.00, steps = 200
00:04:14 [INFO] train episode 3708: reward = 200.00, steps = 200
00:04:14 [INFO] train episode 3709: reward = 200.00, steps = 200
00:04:14 [INFO] train episode 3710: reward = 200.00, steps = 200
00:04:14 [INFO] train episode 3711: reward = 200.00, steps = 200
00:04:14 [INFO] train episode 3712: reward = 200.00, steps = 200
00:04:14 [INFO] train episode 3713: reward = 200.00, steps = 200
00:04:15 [INFO] train episode 3714: reward = 200.00, steps = 200
00:04:15 [INFO] train episode 3715: reward = 200.00, steps = 200
00:04:15 [INFO] train episode 3716: reward = 59.00, steps = 59
00:04:15 [INFO] train episode 3717: reward = 179.00, steps = 179
00:04:15 [INFO] train episode 3718: reward = 147.00, steps = 147
00:04:15 [INFO] train episode 3719: reward = 200.00, steps = 200
00:04:15 [INFO] train episode 3720: reward = 187.00, steps = 187
00:04:15 [INFO] train episode 3721: reward = 148.00, steps = 148
00:04:15 [INFO] train episode 3722: reward = 200.00, steps = 200
00:04:15 [INFO] train episode 3723: reward = 195.00, steps = 195
00:04:15 [INFO] train episode 3724: reward = 184.00, steps = 184
00:04:15 [INFO] train episode 3725: reward = 200.00, steps = 200
00:04:15 [INFO] train episode 3726: reward = 133.00, steps = 133
00:04:15 [INFO] train episode 3727: reward = 156.00, steps = 156
00:04:15 [INFO] train episode 3728: reward = 178.00, steps = 178
00:04:15 [INFO] train episode 3729: reward = 200.00, steps = 200
00:04:16 [INFO] train episode 3730: reward = 200.00, steps = 200
00:04:16 [INFO] train episode 3731: reward = 200.00, steps = 200
00:04:16 [INFO] train episode 3732: reward = 200.00, steps = 200
00:04:16 [INFO] train episode 3733: reward = 178.00, steps = 178
00:04:16 [INFO] train episode 3734: reward = 200.00, steps = 200
00:04:16 [INFO] train episode 3735: reward = 139.00, steps = 139
00:04:16 [INFO] train episode 3736: reward = 156.00, steps = 156
00:04:16 [INFO] train episode 3737: reward = 200.00, steps = 200
00:04:16 [INFO] train episode 3738: reward = 200.00, steps = 200
00:04:16 [INFO] train episode 3739: reward = 130.00, steps = 130
00:04:16 [INFO] train episode 3740: reward = 200.00, steps = 200
00:04:16 [INFO] train episode 3741: reward = 115.00, steps = 115
00:04:16 [INFO] train episode 3742: reward = 175.00, steps = 175
00:04:16 [INFO] train episode 3743: reward = 200.00, steps = 200
00:04:16 [INFO] train episode 3744: reward = 131.00, steps = 131
00:04:17 [INFO] train episode 3745: reward = 164.00, steps = 164
00:04:17 [INFO] train episode 3746: reward = 200.00, steps = 200
00:04:17 [INFO] train episode 3747: reward = 175.00, steps = 175
00:04:17 [INFO] train episode 3748: reward = 158.00, steps = 158
00:04:17 [INFO] train episode 3749: reward = 200.00, steps = 200
00:04:17 [INFO] train episode 3750: reward = 200.00, steps = 200
00:04:17 [INFO] train episode 3751: reward = 200.00, steps = 200
00:04:17 [INFO] train episode 3752: reward = 175.00, steps = 175
00:04:17 [INFO] train episode 3753: reward = 200.00, steps = 200
00:04:17 [INFO] train episode 3754: reward = 128.00, steps = 128
00:04:17 [INFO] train episode 3755: reward = 191.00, steps = 191
00:04:17 [INFO] train episode 3756: reward = 117.00, steps = 117
00:04:17 [INFO] train episode 3757: reward = 175.00, steps = 175
00:04:17 [INFO] train episode 3758: reward = 182.00, steps = 182
00:04:17 [INFO] train episode 3759: reward = 200.00, steps = 200
00:04:18 [INFO] train episode 3760: reward = 174.00, steps = 174
00:04:18 [INFO] train episode 3761: reward = 172.00, steps = 172
00:04:18 [INFO] train episode 3762: reward = 170.00, steps = 170
00:04:18 [INFO] train episode 3763: reward = 200.00, steps = 200
00:04:18 [INFO] train episode 3764: reward = 181.00, steps = 181
00:04:18 [INFO] train episode 3765: reward = 182.00, steps = 182
00:04:18 [INFO] train episode 3766: reward = 200.00, steps = 200
00:04:18 [INFO] train episode 3767: reward = 154.00, steps = 154
00:04:18 [INFO] train episode 3768: reward = 200.00, steps = 200
00:04:18 [INFO] train episode 3769: reward = 189.00, steps = 189
00:04:18 [INFO] train episode 3770: reward = 200.00, steps = 200
00:04:18 [INFO] train episode 3771: reward = 163.00, steps = 163
00:04:18 [INFO] train episode 3772: reward = 200.00, steps = 200
00:04:18 [INFO] train episode 3773: reward = 183.00, steps = 183
00:04:19 [INFO] train episode 3774: reward = 139.00, steps = 139
00:04:19 [INFO] train episode 3775: reward = 200.00, steps = 200
00:04:19 [INFO] train episode 3776: reward = 141.00, steps = 141
00:04:19 [INFO] train episode 3777: reward = 125.00, steps = 125
00:04:19 [INFO] train episode 3778: reward = 200.00, steps = 200
00:04:19 [INFO] train episode 3779: reward = 187.00, steps = 187
00:04:19 [INFO] train episode 3780: reward = 200.00, steps = 200
00:04:19 [INFO] train episode 3781: reward = 200.00, steps = 200
00:04:19 [INFO] train episode 3782: reward = 200.00, steps = 200
00:04:19 [INFO] train episode 3783: reward = 200.00, steps = 200
00:04:19 [INFO] train episode 3784: reward = 200.00, steps = 200
00:04:19 [INFO] train episode 3785: reward = 200.00, steps = 200
00:04:19 [INFO] train episode 3786: reward = 188.00, steps = 188
00:04:19 [INFO] train episode 3787: reward = 200.00, steps = 200
00:04:19 [INFO] train episode 3788: reward = 116.00, steps = 116
00:04:20 [INFO] train episode 3789: reward = 160.00, steps = 160
00:04:20 [INFO] train episode 3790: reward = 165.00, steps = 165
00:04:20 [INFO] train episode 3791: reward = 150.00, steps = 150
00:04:20 [INFO] train episode 3792: reward = 176.00, steps = 176
00:04:20 [INFO] train episode 3793: reward = 200.00, steps = 200
00:04:20 [INFO] train episode 3794: reward = 169.00, steps = 169
00:04:20 [INFO] train episode 3795: reward = 118.00, steps = 118
00:04:20 [INFO] train episode 3796: reward = 118.00, steps = 118
00:04:20 [INFO] train episode 3797: reward = 115.00, steps = 115
00:04:20 [INFO] train episode 3798: reward = 200.00, steps = 200
00:04:20 [INFO] train episode 3799: reward = 200.00, steps = 200
00:04:20 [INFO] train episode 3800: reward = 144.00, steps = 144
00:04:20 [INFO] train episode 3801: reward = 200.00, steps = 200
00:04:20 [INFO] train episode 3802: reward = 146.00, steps = 146
00:04:20 [INFO] train episode 3803: reward = 200.00, steps = 200
00:04:20 [INFO] train episode 3804: reward = 200.00, steps = 200
00:04:21 [INFO] train episode 3805: reward = 189.00, steps = 189
00:04:21 [INFO] train episode 3806: reward = 162.00, steps = 162
00:04:21 [INFO] train episode 3807: reward = 144.00, steps = 144
00:04:21 [INFO] train episode 3808: reward = 49.00, steps = 49
00:04:21 [INFO] train episode 3809: reward = 169.00, steps = 169
00:04:21 [INFO] train episode 3810: reward = 148.00, steps = 148
00:04:21 [INFO] train episode 3811: reward = 200.00, steps = 200
00:04:21 [INFO] train episode 3812: reward = 149.00, steps = 149
00:04:21 [INFO] train episode 3813: reward = 171.00, steps = 171
00:04:21 [INFO] train episode 3814: reward = 132.00, steps = 132
00:04:21 [INFO] train episode 3815: reward = 158.00, steps = 158
00:04:21 [INFO] train episode 3816: reward = 159.00, steps = 159
00:04:21 [INFO] train episode 3817: reward = 200.00, steps = 200
00:04:21 [INFO] train episode 3818: reward = 164.00, steps = 164
00:04:21 [INFO] train episode 3819: reward = 188.00, steps = 188
00:04:21 [INFO] train episode 3820: reward = 180.00, steps = 180
00:04:21 [INFO] train episode 3821: reward = 168.00, steps = 168
00:04:21 [INFO] train episode 3822: reward = 166.00, steps = 166
00:04:22 [INFO] train episode 3823: reward = 162.00, steps = 162
00:04:22 [INFO] train episode 3824: reward = 200.00, steps = 200
00:04:22 [INFO] train episode 3825: reward = 164.00, steps = 164
00:04:22 [INFO] train episode 3826: reward = 200.00, steps = 200
00:04:22 [INFO] train episode 3827: reward = 200.00, steps = 200
00:04:22 [INFO] train episode 3828: reward = 167.00, steps = 167
00:04:22 [INFO] train episode 3829: reward = 200.00, steps = 200
00:04:22 [INFO] train episode 3830: reward = 193.00, steps = 193
00:04:22 [INFO] train episode 3831: reward = 139.00, steps = 139
00:04:22 [INFO] train episode 3832: reward = 72.00, steps = 72
00:04:22 [INFO] train episode 3833: reward = 189.00, steps = 189
00:04:22 [INFO] train episode 3834: reward = 176.00, steps = 176
00:04:22 [INFO] train episode 3835: reward = 116.00, steps = 116
00:04:22 [INFO] train episode 3836: reward = 27.00, steps = 27
00:04:22 [INFO] train episode 3837: reward = 160.00, steps = 160
00:04:22 [INFO] train episode 3838: reward = 152.00, steps = 152
00:04:22 [INFO] train episode 3839: reward = 200.00, steps = 200
00:04:23 [INFO] train episode 3840: reward = 200.00, steps = 200
00:04:23 [INFO] train episode 3841: reward = 200.00, steps = 200
00:04:23 [INFO] train episode 3842: reward = 128.00, steps = 128
00:04:23 [INFO] train episode 3843: reward = 200.00, steps = 200
00:04:23 [INFO] train episode 3844: reward = 131.00, steps = 131
00:04:23 [INFO] train episode 3845: reward = 161.00, steps = 161
00:04:23 [INFO] train episode 3846: reward = 148.00, steps = 148
00:04:23 [INFO] train episode 3847: reward = 172.00, steps = 172
00:04:23 [INFO] train episode 3848: reward = 173.00, steps = 173
00:04:23 [INFO] train episode 3849: reward = 200.00, steps = 200
00:04:23 [INFO] train episode 3850: reward = 142.00, steps = 142
00:04:23 [INFO] train episode 3851: reward = 177.00, steps = 177
00:04:23 [INFO] train episode 3852: reward = 176.00, steps = 176
00:04:23 [INFO] train episode 3853: reward = 200.00, steps = 200
00:04:23 [INFO] train episode 3854: reward = 190.00, steps = 190
00:04:23 [INFO] train episode 3855: reward = 200.00, steps = 200
00:04:24 [INFO] train episode 3856: reward = 131.00, steps = 131
00:04:24 [INFO] train episode 3857: reward = 200.00, steps = 200
00:04:24 [INFO] train episode 3858: reward = 144.00, steps = 144
00:04:24 [INFO] train episode 3859: reward = 200.00, steps = 200
00:04:24 [INFO] train episode 3860: reward = 128.00, steps = 128
00:04:24 [INFO] train episode 3861: reward = 156.00, steps = 156
00:04:24 [INFO] train episode 3862: reward = 200.00, steps = 200
00:04:24 [INFO] train episode 3863: reward = 104.00, steps = 104
00:04:24 [INFO] train episode 3864: reward = 180.00, steps = 180
00:04:24 [INFO] train episode 3865: reward = 200.00, steps = 200
00:04:24 [INFO] train episode 3866: reward = 171.00, steps = 171
00:04:24 [INFO] train episode 3867: reward = 199.00, steps = 199
00:04:24 [INFO] train episode 3868: reward = 200.00, steps = 200
00:04:24 [INFO] train episode 3869: reward = 200.00, steps = 200
00:04:25 [INFO] train episode 3870: reward = 199.00, steps = 199
00:04:25 [INFO] train episode 3871: reward = 200.00, steps = 200
00:04:25 [INFO] train episode 3872: reward = 185.00, steps = 185
00:04:25 [INFO] train episode 3873: reward = 109.00, steps = 109
00:04:25 [INFO] train episode 3874: reward = 200.00, steps = 200
00:04:25 [INFO] train episode 3875: reward = 200.00, steps = 200
00:04:25 [INFO] train episode 3876: reward = 189.00, steps = 189
00:04:25 [INFO] train episode 3877: reward = 200.00, steps = 200
00:04:25 [INFO] train episode 3878: reward = 200.00, steps = 200
00:04:25 [INFO] train episode 3879: reward = 167.00, steps = 167
00:04:25 [INFO] train episode 3880: reward = 192.00, steps = 192
00:04:25 [INFO] train episode 3881: reward = 200.00, steps = 200
00:04:25 [INFO] train episode 3882: reward = 163.00, steps = 163
00:04:25 [INFO] train episode 3883: reward = 138.00, steps = 138
00:04:25 [INFO] train episode 3884: reward = 170.00, steps = 170
00:04:26 [INFO] train episode 3885: reward = 200.00, steps = 200
00:04:26 [INFO] train episode 3886: reward = 189.00, steps = 189
00:04:26 [INFO] train episode 3887: reward = 200.00, steps = 200
00:04:26 [INFO] train episode 3888: reward = 123.00, steps = 123
00:04:26 [INFO] train episode 3889: reward = 200.00, steps = 200
00:04:26 [INFO] train episode 3890: reward = 145.00, steps = 145
00:04:26 [INFO] train episode 3891: reward = 150.00, steps = 150
00:04:26 [INFO] train episode 3892: reward = 200.00, steps = 200
00:04:26 [INFO] train episode 3893: reward = 109.00, steps = 109
00:04:26 [INFO] train episode 3894: reward = 200.00, steps = 200
00:04:26 [INFO] train episode 3895: reward = 200.00, steps = 200
00:04:26 [INFO] train episode 3896: reward = 179.00, steps = 179
00:04:26 [INFO] train episode 3897: reward = 200.00, steps = 200
00:04:26 [INFO] train episode 3898: reward = 200.00, steps = 200
00:04:26 [INFO] train episode 3899: reward = 200.00, steps = 200
00:04:27 [INFO] train episode 3900: reward = 200.00, steps = 200
00:04:27 [INFO] train episode 3901: reward = 180.00, steps = 180
00:04:27 [INFO] train episode 3902: reward = 139.00, steps = 139
00:04:27 [INFO] train episode 3903: reward = 180.00, steps = 180
00:04:27 [INFO] train episode 3904: reward = 200.00, steps = 200
00:04:27 [INFO] train episode 3905: reward = 193.00, steps = 193
00:04:27 [INFO] train episode 3906: reward = 200.00, steps = 200
00:04:27 [INFO] train episode 3907: reward = 176.00, steps = 176
00:04:27 [INFO] train episode 3908: reward = 200.00, steps = 200
00:04:27 [INFO] train episode 3909: reward = 200.00, steps = 200
00:04:27 [INFO] train episode 3910: reward = 192.00, steps = 192
00:04:27 [INFO] train episode 3911: reward = 188.00, steps = 188
00:04:27 [INFO] train episode 3912: reward = 200.00, steps = 200
00:04:27 [INFO] train episode 3913: reward = 200.00, steps = 200
00:04:28 [INFO] train episode 3914: reward = 130.00, steps = 130
00:04:28 [INFO] train episode 3915: reward = 125.00, steps = 125
00:04:28 [INFO] train episode 3916: reward = 142.00, steps = 142
00:04:28 [INFO] train episode 3917: reward = 38.00, steps = 38
00:04:28 [INFO] train episode 3918: reward = 200.00, steps = 200
00:04:28 [INFO] train episode 3919: reward = 200.00, steps = 200
00:04:28 [INFO] train episode 3920: reward = 200.00, steps = 200
00:04:28 [INFO] train episode 3921: reward = 200.00, steps = 200
00:04:28 [INFO] train episode 3922: reward = 170.00, steps = 170
00:04:28 [INFO] train episode 3923: reward = 186.00, steps = 186
00:04:28 [INFO] train episode 3924: reward = 176.00, steps = 176
00:04:28 [INFO] train episode 3925: reward = 169.00, steps = 169
00:04:28 [INFO] train episode 3926: reward = 142.00, steps = 142
00:04:28 [INFO] train episode 3927: reward = 200.00, steps = 200
00:04:28 [INFO] train episode 3928: reward = 200.00, steps = 200
00:04:28 [INFO] train episode 3929: reward = 144.00, steps = 144
00:04:29 [INFO] train episode 3930: reward = 200.00, steps = 200
00:04:29 [INFO] train episode 3931: reward = 200.00, steps = 200
00:04:29 [INFO] train episode 3932: reward = 200.00, steps = 200
00:04:29 [INFO] train episode 3933: reward = 158.00, steps = 158
00:04:29 [INFO] train episode 3934: reward = 200.00, steps = 200
00:04:29 [INFO] train episode 3935: reward = 200.00, steps = 200
00:04:29 [INFO] train episode 3936: reward = 200.00, steps = 200
00:04:29 [INFO] train episode 3937: reward = 200.00, steps = 200
00:04:29 [INFO] train episode 3938: reward = 200.00, steps = 200
00:04:29 [INFO] train episode 3939: reward = 148.00, steps = 148
00:04:29 [INFO] train episode 3940: reward = 200.00, steps = 200
00:04:29 [INFO] train episode 3941: reward = 189.00, steps = 189
00:04:29 [INFO] train episode 3942: reward = 136.00, steps = 136
00:04:29 [INFO] train episode 3943: reward = 166.00, steps = 166
00:04:29 [INFO] train episode 3944: reward = 200.00, steps = 200
00:04:30 [INFO] train episode 3945: reward = 116.00, steps = 116
00:04:30 [INFO] train episode 3946: reward = 200.00, steps = 200
00:04:30 [INFO] train episode 3947: reward = 200.00, steps = 200
00:04:30 [INFO] train episode 3948: reward = 130.00, steps = 130
00:04:30 [INFO] train episode 3949: reward = 200.00, steps = 200
00:04:30 [INFO] train episode 3950: reward = 200.00, steps = 200
00:04:30 [INFO] train episode 3951: reward = 200.00, steps = 200
00:04:30 [INFO] train episode 3952: reward = 200.00, steps = 200
00:04:30 [INFO] train episode 3953: reward = 200.00, steps = 200
00:04:30 [INFO] train episode 3954: reward = 166.00, steps = 166
00:04:30 [INFO] train episode 3955: reward = 195.00, steps = 195
00:04:30 [INFO] train episode 3956: reward = 188.00, steps = 188
00:04:30 [INFO] train episode 3957: reward = 200.00, steps = 200
00:04:30 [INFO] train episode 3958: reward = 200.00, steps = 200
00:04:30 [INFO] train episode 3959: reward = 194.00, steps = 194
00:04:31 [INFO] train episode 3960: reward = 200.00, steps = 200
00:04:31 [INFO] train episode 3961: reward = 200.00, steps = 200
00:04:31 [INFO] train episode 3962: reward = 146.00, steps = 146
00:04:31 [INFO] train episode 3963: reward = 200.00, steps = 200
00:04:31 [INFO] train episode 3964: reward = 200.00, steps = 200
00:04:31 [INFO] train episode 3965: reward = 200.00, steps = 200
00:04:31 [INFO] train episode 3966: reward = 200.00, steps = 200
00:04:31 [INFO] train episode 3967: reward = 200.00, steps = 200
00:04:31 [INFO] train episode 3968: reward = 200.00, steps = 200
00:04:31 [INFO] train episode 3969: reward = 200.00, steps = 200
00:04:31 [INFO] train episode 3970: reward = 153.00, steps = 153
00:04:31 [INFO] train episode 3971: reward = 200.00, steps = 200
00:04:31 [INFO] train episode 3972: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3973: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3974: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3975: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3976: reward = 155.00, steps = 155
00:04:32 [INFO] train episode 3977: reward = 169.00, steps = 169
00:04:32 [INFO] train episode 3978: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3979: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3980: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3981: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3982: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3983: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3984: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3985: reward = 200.00, steps = 200
00:04:32 [INFO] train episode 3986: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3987: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3988: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3989: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3990: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3991: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3992: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3993: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3994: reward = 150.00, steps = 150
00:04:33 [INFO] train episode 3995: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3996: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3997: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 3998: reward = 112.00, steps = 112
00:04:33 [INFO] train episode 3999: reward = 200.00, steps = 200
00:04:33 [INFO] train episode 4000: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4001: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4002: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4003: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4004: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4005: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4006: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4007: reward = 178.00, steps = 178
00:04:34 [INFO] train episode 4008: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4009: reward = 156.00, steps = 156
00:04:34 [INFO] train episode 4010: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4011: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4012: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4013: reward = 200.00, steps = 200
00:04:34 [INFO] train episode 4014: reward = 147.00, steps = 147
00:04:35 [INFO] train episode 4015: reward = 143.00, steps = 143
00:04:35 [INFO] train episode 4016: reward = 135.00, steps = 135
00:04:35 [INFO] train episode 4017: reward = 200.00, steps = 200
00:04:35 [INFO] train episode 4018: reward = 126.00, steps = 126
00:04:35 [INFO] train episode 4019: reward = 200.00, steps = 200
00:04:35 [INFO] train episode 4020: reward = 114.00, steps = 114
00:04:35 [INFO] train episode 4021: reward = 200.00, steps = 200
00:04:35 [INFO] train episode 4022: reward = 200.00, steps = 200
00:04:35 [INFO] train episode 4023: reward = 150.00, steps = 150
00:04:35 [INFO] train episode 4024: reward = 200.00, steps = 200
00:04:35 [INFO] train episode 4025: reward = 200.00, steps = 200
00:04:35 [INFO] train episode 4026: reward = 168.00, steps = 168
00:04:35 [INFO] train episode 4027: reward = 200.00, steps = 200
00:04:35 [INFO] train episode 4028: reward = 200.00, steps = 200
00:04:36 [INFO] train episode 4029: reward = 200.00, steps = 200
00:04:36 [INFO] train episode 4030: reward = 178.00, steps = 178
00:04:36 [INFO] train episode 4031: reward = 33.00, steps = 33
00:04:36 [INFO] train episode 4032: reward = 200.00, steps = 200
00:04:36 [INFO] train episode 4033: reward = 200.00, steps = 200
00:04:36 [INFO] train episode 4034: reward = 150.00, steps = 150
00:04:36 [INFO] train episode 4035: reward = 195.00, steps = 195
00:04:36 [INFO] train episode 4036: reward = 57.00, steps = 57
00:04:36 [INFO] train episode 4037: reward = 175.00, steps = 175
00:04:36 [INFO] train episode 4038: reward = 200.00, steps = 200
00:04:36 [INFO] train episode 4039: reward = 200.00, steps = 200
00:04:36 [INFO] train episode 4040: reward = 181.00, steps = 181
00:04:36 [INFO] train episode 4041: reward = 200.00, steps = 200
00:04:36 [INFO] train episode 4042: reward = 179.00, steps = 179
00:04:36 [INFO] train episode 4043: reward = 200.00, steps = 200
00:04:36 [INFO] train episode 4044: reward = 39.00, steps = 39
00:04:37 [INFO] train episode 4045: reward = 200.00, steps = 200
00:04:37 [INFO] train episode 4046: reward = 200.00, steps = 200
00:04:37 [INFO] train episode 4047: reward = 178.00, steps = 178
00:04:37 [INFO] train episode 4048: reward = 200.00, steps = 200
00:04:37 [INFO] train episode 4049: reward = 200.00, steps = 200
00:04:37 [INFO] train episode 4050: reward = 200.00, steps = 200
00:04:37 [INFO] train episode 4051: reward = 186.00, steps = 186
00:04:37 [INFO] train episode 4052: reward = 200.00, steps = 200
00:04:37 [INFO] train episode 4053: reward = 131.00, steps = 131
00:04:37 [INFO] train episode 4054: reward = 200.00, steps = 200
00:04:37 [INFO] train episode 4055: reward = 200.00, steps = 200
00:04:37 [INFO] train episode 4056: reward = 200.00, steps = 200
00:04:37 [INFO] train episode 4057: reward = 200.00, steps = 200
00:04:37 [INFO] train episode 4058: reward = 174.00, steps = 174
00:04:38 [INFO] train episode 4059: reward = 200.00, steps = 200
00:04:38 [INFO] train episode 4060: reward = 200.00, steps = 200
00:04:38 [INFO] train episode 4061: reward = 124.00, steps = 124
00:04:38 [INFO] train episode 4062: reward = 173.00, steps = 173
00:04:38 [INFO] train episode 4063: reward = 200.00, steps = 200
00:04:38 [INFO] train episode 4064: reward = 200.00, steps = 200
00:04:38 [INFO] train episode 4065: reward = 200.00, steps = 200
00:04:38 [INFO] train episode 4066: reward = 200.00, steps = 200
00:04:38 [INFO] train episode 4067: reward = 200.00, steps = 200
00:04:38 [INFO] train episode 4068: reward = 200.00, steps = 200
00:04:38 [INFO] train episode 4069: reward = 175.00, steps = 175
00:04:38 [INFO] train episode 4070: reward = 200.00, steps = 200
00:04:38 [INFO] train episode 4071: reward = 200.00, steps = 200
00:04:38 [INFO] train episode 4072: reward = 183.00, steps = 183
00:04:39 [INFO] train episode 4073: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4074: reward = 146.00, steps = 146
00:04:39 [INFO] train episode 4075: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4076: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4077: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4078: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4079: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4080: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4081: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4082: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4083: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4084: reward = 200.00, steps = 200
00:04:39 [INFO] train episode 4085: reward = 200.00, steps = 200
00:04:40 [INFO] train episode 4086: reward = 155.00, steps = 155
00:04:40 [INFO] train episode 4087: reward = 179.00, steps = 179
00:04:40 [INFO] train episode 4088: reward = 185.00, steps = 185
00:04:40 [INFO] train episode 4089: reward = 200.00, steps = 200
00:04:40 [INFO] train episode 4090: reward = 158.00, steps = 158
00:04:40 [INFO] train episode 4091: reward = 200.00, steps = 200
00:04:40 [INFO] train episode 4092: reward = 200.00, steps = 200
00:04:40 [INFO] train episode 4093: reward = 200.00, steps = 200
00:04:40 [INFO] train episode 4094: reward = 200.00, steps = 200
00:04:40 [INFO] train episode 4095: reward = 199.00, steps = 199
00:04:40 [INFO] train episode 4096: reward = 145.00, steps = 145
00:04:40 [INFO] train episode 4097: reward = 200.00, steps = 200
00:04:40 [INFO] train episode 4098: reward = 167.00, steps = 167
00:04:40 [INFO] train episode 4099: reward = 86.00, steps = 86
00:04:40 [INFO] train episode 4100: reward = 153.00, steps = 153
00:04:41 [INFO] train episode 4101: reward = 171.00, steps = 171
00:04:41 [INFO] train episode 4102: reward = 200.00, steps = 200
00:04:41 [INFO] train episode 4103: reward = 200.00, steps = 200
00:04:41 [INFO] train episode 4104: reward = 200.00, steps = 200
00:04:41 [INFO] train episode 4105: reward = 200.00, steps = 200
00:04:41 [INFO] train episode 4106: reward = 200.00, steps = 200
00:04:41 [INFO] train episode 4107: reward = 164.00, steps = 164
00:04:41 [INFO] train episode 4108: reward = 118.00, steps = 118
00:04:41 [INFO] train episode 4109: reward = 131.00, steps = 131
00:04:41 [INFO] train episode 4110: reward = 200.00, steps = 200
00:04:41 [INFO] train episode 4111: reward = 123.00, steps = 123
00:04:41 [INFO] train episode 4112: reward = 200.00, steps = 200
00:04:41 [INFO] train episode 4113: reward = 200.00, steps = 200
00:04:41 [INFO] train episode 4114: reward = 200.00, steps = 200
00:04:41 [INFO] train episode 4115: reward = 200.00, steps = 200
00:04:42 [INFO] train episode 4116: reward = 200.00, steps = 200
00:04:42 [INFO] train episode 4117: reward = 139.00, steps = 139
00:04:42 [INFO] train episode 4118: reward = 200.00, steps = 200
00:04:42 [INFO] train episode 4119: reward = 200.00, steps = 200
00:04:42 [INFO] train episode 4120: reward = 200.00, steps = 200
00:04:42 [INFO] train episode 4121: reward = 136.00, steps = 136
00:04:42 [INFO] train episode 4122: reward = 123.00, steps = 123
00:04:42 [INFO] train episode 4123: reward = 145.00, steps = 145
00:04:42 [INFO] train episode 4124: reward = 200.00, steps = 200
00:04:42 [INFO] train episode 4125: reward = 200.00, steps = 200
00:04:42 [INFO] train episode 4126: reward = 200.00, steps = 200
00:04:42 [INFO] train episode 4127: reward = 199.00, steps = 199
00:04:42 [INFO] train episode 4128: reward = 200.00, steps = 200
00:04:42 [INFO] train episode 4129: reward = 135.00, steps = 135
00:04:43 [INFO] train episode 4130: reward = 197.00, steps = 197
00:04:43 [INFO] train episode 4131: reward = 200.00, steps = 200
00:04:43 [INFO] train episode 4132: reward = 200.00, steps = 200
00:04:43 [INFO] train episode 4133: reward = 159.00, steps = 159
00:04:43 [INFO] train episode 4134: reward = 200.00, steps = 200
00:04:43 [INFO] train episode 4135: reward = 188.00, steps = 188
00:04:43 [INFO] train episode 4136: reward = 193.00, steps = 193
00:04:43 [INFO] train episode 4137: reward = 200.00, steps = 200
00:04:43 [INFO] train episode 4138: reward = 158.00, steps = 158
00:04:43 [INFO] train episode 4139: reward = 200.00, steps = 200
00:04:43 [INFO] train episode 4140: reward = 200.00, steps = 200
00:04:43 [INFO] train episode 4141: reward = 200.00, steps = 200
00:04:43 [INFO] train episode 4142: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4143: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4144: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4145: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4146: reward = 145.00, steps = 145
00:04:44 [INFO] train episode 4147: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4148: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4149: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4150: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4151: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4152: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4153: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4154: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4155: reward = 200.00, steps = 200
00:04:44 [INFO] train episode 4156: reward = 128.00, steps = 128
00:04:45 [INFO] train episode 4157: reward = 198.00, steps = 198
00:04:45 [INFO] train episode 4158: reward = 200.00, steps = 200
00:04:45 [INFO] train episode 4159: reward = 158.00, steps = 158
00:04:45 [INFO] train episode 4160: reward = 191.00, steps = 191
00:04:45 [INFO] train episode 4161: reward = 200.00, steps = 200
00:04:45 [INFO] train episode 4162: reward = 200.00, steps = 200
00:04:45 [INFO] train episode 4163: reward = 152.00, steps = 152
00:04:45 [INFO] train episode 4164: reward = 200.00, steps = 200
00:04:45 [INFO] train episode 4165: reward = 183.00, steps = 183
00:04:45 [INFO] train episode 4166: reward = 163.00, steps = 163
00:04:45 [INFO] train episode 4167: reward = 200.00, steps = 200
00:04:45 [INFO] train episode 4168: reward = 45.00, steps = 45
00:04:45 [INFO] train episode 4169: reward = 200.00, steps = 200
00:04:45 [INFO] train episode 4170: reward = 200.00, steps = 200
00:04:45 [INFO] train episode 4171: reward = 172.00, steps = 172
00:04:46 [INFO] train episode 4172: reward = 200.00, steps = 200
00:04:46 [INFO] train episode 4173: reward = 200.00, steps = 200
00:04:46 [INFO] train episode 4174: reward = 154.00, steps = 154
00:04:46 [INFO] train episode 4175: reward = 152.00, steps = 152
00:04:46 [INFO] train episode 4176: reward = 133.00, steps = 133
00:04:46 [INFO] train episode 4177: reward = 200.00, steps = 200
00:04:46 [INFO] train episode 4178: reward = 200.00, steps = 200
00:04:46 [INFO] train episode 4179: reward = 200.00, steps = 200
00:04:46 [INFO] train episode 4180: reward = 185.00, steps = 185
00:04:46 [INFO] train episode 4181: reward = 200.00, steps = 200
00:04:46 [INFO] train episode 4182: reward = 200.00, steps = 200
00:04:46 [INFO] train episode 4183: reward = 200.00, steps = 200
00:04:46 [INFO] train episode 4184: reward = 128.00, steps = 128
00:04:46 [INFO] train episode 4185: reward = 200.00, steps = 200
00:04:47 [INFO] train episode 4186: reward = 200.00, steps = 200
00:04:47 [INFO] train episode 4187: reward = 132.00, steps = 132
00:04:47 [INFO] train episode 4188: reward = 120.00, steps = 120
00:04:47 [INFO] train episode 4189: reward = 171.00, steps = 171
00:04:47 [INFO] train episode 4190: reward = 200.00, steps = 200
00:04:47 [INFO] train episode 4191: reward = 200.00, steps = 200
00:04:47 [INFO] train episode 4192: reward = 195.00, steps = 195
00:04:47 [INFO] train episode 4193: reward = 200.00, steps = 200
00:04:47 [INFO] train episode 4194: reward = 200.00, steps = 200
00:04:47 [INFO] train episode 4195: reward = 200.00, steps = 200
00:04:47 [INFO] train episode 4196: reward = 200.00, steps = 200
00:04:47 [INFO] train episode 4197: reward = 174.00, steps = 174
00:04:47 [INFO] train episode 4198: reward = 200.00, steps = 200
00:04:47 [INFO] train episode 4199: reward = 200.00, steps = 200
00:04:47 [INFO] train episode 4200: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4201: reward = 123.00, steps = 123
00:04:48 [INFO] train episode 4202: reward = 137.00, steps = 137
00:04:48 [INFO] train episode 4203: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4204: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4205: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4206: reward = 176.00, steps = 176
00:04:48 [INFO] train episode 4207: reward = 149.00, steps = 149
00:04:48 [INFO] train episode 4208: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4209: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4210: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4211: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4212: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4213: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4214: reward = 200.00, steps = 200
00:04:48 [INFO] train episode 4215: reward = 166.00, steps = 166
00:04:49 [INFO] train episode 4216: reward = 200.00, steps = 200
00:04:49 [INFO] train episode 4217: reward = 133.00, steps = 133
00:04:49 [INFO] train episode 4218: reward = 197.00, steps = 197
00:04:49 [INFO] train episode 4219: reward = 68.00, steps = 68
00:04:49 [INFO] train episode 4220: reward = 200.00, steps = 200
00:04:49 [INFO] train episode 4221: reward = 200.00, steps = 200
00:04:49 [INFO] train episode 4222: reward = 200.00, steps = 200
00:04:49 [INFO] train episode 4223: reward = 200.00, steps = 200
00:04:49 [INFO] train episode 4224: reward = 125.00, steps = 125
00:04:49 [INFO] train episode 4225: reward = 144.00, steps = 144
00:04:49 [INFO] train episode 4226: reward = 200.00, steps = 200
00:04:49 [INFO] train episode 4227: reward = 200.00, steps = 200
00:04:49 [INFO] train episode 4228: reward = 66.00, steps = 66
00:04:49 [INFO] train episode 4229: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4230: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4231: reward = 179.00, steps = 179
00:04:50 [INFO] train episode 4232: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4233: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4234: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4235: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4236: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4237: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4238: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4239: reward = 192.00, steps = 192
00:04:50 [INFO] train episode 4240: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4241: reward = 200.00, steps = 200
00:04:50 [INFO] train episode 4242: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4243: reward = 148.00, steps = 148
00:04:51 [INFO] train episode 4244: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4245: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4246: reward = 161.00, steps = 161
00:04:51 [INFO] train episode 4247: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4248: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4249: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4250: reward = 155.00, steps = 155
00:04:51 [INFO] train episode 4251: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4252: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4253: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4254: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4255: reward = 200.00, steps = 200
00:04:51 [INFO] train episode 4256: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4257: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4258: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4259: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4260: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4261: reward = 127.00, steps = 127
00:04:52 [INFO] train episode 4262: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4263: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4264: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4265: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4266: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4267: reward = 200.00, steps = 200
00:04:52 [INFO] train episode 4268: reward = 195.00, steps = 195
00:04:52 [INFO] train episode 4269: reward = 168.00, steps = 168
00:04:53 [INFO] train episode 4270: reward = 200.00, steps = 200
00:04:53 [INFO] train episode 4271: reward = 32.00, steps = 32
00:04:53 [INFO] train episode 4272: reward = 181.00, steps = 181
00:04:53 [INFO] train episode 4273: reward = 200.00, steps = 200
00:04:53 [INFO] train episode 4274: reward = 200.00, steps = 200
00:04:53 [INFO] train episode 4275: reward = 200.00, steps = 200
00:04:53 [INFO] train episode 4276: reward = 145.00, steps = 145
00:04:53 [INFO] train episode 4277: reward = 176.00, steps = 176
00:04:53 [INFO] train episode 4278: reward = 125.00, steps = 125
00:04:53 [INFO] train episode 4279: reward = 200.00, steps = 200
00:04:53 [INFO] train episode 4280: reward = 200.00, steps = 200
00:04:53 [INFO] train episode 4281: reward = 200.00, steps = 200
00:04:53 [INFO] train episode 4282: reward = 200.00, steps = 200
00:04:53 [INFO] train episode 4283: reward = 200.00, steps = 200
00:04:53 [INFO] train episode 4284: reward = 200.00, steps = 200
00:04:54 [INFO] train episode 4285: reward = 200.00, steps = 200
00:04:54 [INFO] train episode 4286: reward = 200.00, steps = 200
00:04:54 [INFO] train episode 4287: reward = 162.00, steps = 162
00:04:54 [INFO] train episode 4288: reward = 200.00, steps = 200
00:04:54 [INFO] train episode 4289: reward = 160.00, steps = 160
00:04:54 [INFO] train episode 4290: reward = 138.00, steps = 138
00:04:54 [INFO] train episode 4291: reward = 111.00, steps = 111
00:04:54 [INFO] train episode 4292: reward = 140.00, steps = 140
00:04:54 [INFO] train episode 4293: reward = 200.00, steps = 200
00:04:54 [INFO] train episode 4294: reward = 168.00, steps = 168
00:04:54 [INFO] train episode 4295: reward = 200.00, steps = 200
00:04:54 [INFO] train episode 4296: reward = 200.00, steps = 200
00:04:54 [INFO] train episode 4297: reward = 200.00, steps = 200
00:04:54 [INFO] train episode 4298: reward = 200.00, steps = 200
00:04:54 [INFO] train episode 4299: reward = 200.00, steps = 200
00:04:55 [INFO] train episode 4300: reward = 180.00, steps = 180
00:04:55 [INFO] train episode 4301: reward = 200.00, steps = 200
00:04:55 [INFO] train episode 4302: reward = 200.00, steps = 200
00:04:55 [INFO] train episode 4303: reward = 200.00, steps = 200
00:04:55 [INFO] train episode 4304: reward = 200.00, steps = 200
00:04:55 [INFO] train episode 4305: reward = 138.00, steps = 138
00:04:55 [INFO] train episode 4306: reward = 200.00, steps = 200
00:04:55 [INFO] train episode 4307: reward = 175.00, steps = 175
00:04:55 [INFO] train episode 4308: reward = 200.00, steps = 200
00:04:55 [INFO] train episode 4309: reward = 200.00, steps = 200
00:04:55 [INFO] train episode 4310: reward = 200.00, steps = 200
00:04:55 [INFO] train episode 4311: reward = 193.00, steps = 193
00:04:55 [INFO] train episode 4312: reward = 200.00, steps = 200
00:04:56 [INFO] train episode 4313: reward = 163.00, steps = 163
00:04:56 [INFO] train episode 4314: reward = 184.00, steps = 184
00:04:56 [INFO] train episode 4315: reward = 200.00, steps = 200
00:04:56 [INFO] train episode 4316: reward = 200.00, steps = 200
00:04:56 [INFO] train episode 4317: reward = 142.00, steps = 142
00:04:56 [INFO] train episode 4318: reward = 200.00, steps = 200
00:04:56 [INFO] train episode 4319: reward = 151.00, steps = 151
00:04:56 [INFO] train episode 4320: reward = 200.00, steps = 200
00:04:56 [INFO] train episode 4321: reward = 141.00, steps = 141
00:04:56 [INFO] train episode 4322: reward = 200.00, steps = 200
00:04:56 [INFO] train episode 4323: reward = 200.00, steps = 200
00:04:56 [INFO] train episode 4324: reward = 200.00, steps = 200
00:04:56 [INFO] train episode 4325: reward = 200.00, steps = 200
00:04:56 [INFO] train episode 4326: reward = 200.00, steps = 200
00:04:56 [INFO] train episode 4327: reward = 143.00, steps = 143
00:04:57 [INFO] train episode 4328: reward = 200.00, steps = 200
00:04:57 [INFO] train episode 4329: reward = 157.00, steps = 157
00:04:57 [INFO] train episode 4330: reward = 200.00, steps = 200
00:04:57 [INFO] train episode 4331: reward = 200.00, steps = 200
00:04:57 [INFO] train episode 4332: reward = 200.00, steps = 200
00:04:57 [INFO] train episode 4333: reward = 200.00, steps = 200
00:04:57 [INFO] train episode 4334: reward = 151.00, steps = 151
00:04:57 [INFO] train episode 4335: reward = 200.00, steps = 200
00:04:57 [INFO] train episode 4336: reward = 200.00, steps = 200
00:04:57 [INFO] train episode 4337: reward = 200.00, steps = 200
00:04:57 [INFO] train episode 4338: reward = 165.00, steps = 165
00:04:57 [INFO] train episode 4339: reward = 200.00, steps = 200
00:04:57 [INFO] train episode 4340: reward = 200.00, steps = 200
00:04:57 [INFO] train episode 4341: reward = 148.00, steps = 148
00:04:57 [INFO] train episode 4342: reward = 138.00, steps = 138
00:04:58 [INFO] train episode 4343: reward = 200.00, steps = 200
00:04:58 [INFO] train episode 4344: reward = 200.00, steps = 200
00:04:58 [INFO] train episode 4345: reward = 200.00, steps = 200
00:04:58 [INFO] train episode 4346: reward = 127.00, steps = 127
00:04:58 [INFO] train episode 4347: reward = 158.00, steps = 158
00:04:58 [INFO] train episode 4348: reward = 200.00, steps = 200
00:04:58 [INFO] train episode 4349: reward = 200.00, steps = 200
00:04:58 [INFO] train episode 4350: reward = 200.00, steps = 200
00:04:58 [INFO] train episode 4351: reward = 147.00, steps = 147
00:04:58 [INFO] train episode 4352: reward = 164.00, steps = 164
00:04:58 [INFO] train episode 4353: reward = 200.00, steps = 200
00:04:58 [INFO] train episode 4354: reward = 200.00, steps = 200
00:04:58 [INFO] train episode 4355: reward = 176.00, steps = 176
00:04:58 [INFO] train episode 4356: reward = 161.00, steps = 161
00:04:59 [INFO] train episode 4357: reward = 195.00, steps = 195
00:04:59 [INFO] train episode 4358: reward = 200.00, steps = 200
00:04:59 [INFO] train episode 4359: reward = 200.00, steps = 200
00:04:59 [INFO] train episode 4360: reward = 200.00, steps = 200
00:04:59 [INFO] train episode 4361: reward = 200.00, steps = 200
00:04:59 [INFO] train episode 4362: reward = 173.00, steps = 173
00:04:59 [INFO] train episode 4363: reward = 168.00, steps = 168
00:04:59 [INFO] train episode 4364: reward = 137.00, steps = 137
00:04:59 [INFO] train episode 4365: reward = 200.00, steps = 200
00:04:59 [INFO] train episode 4366: reward = 200.00, steps = 200
00:04:59 [INFO] train episode 4367: reward = 200.00, steps = 200
00:04:59 [INFO] train episode 4368: reward = 184.00, steps = 184
00:04:59 [INFO] train episode 4369: reward = 200.00, steps = 200
00:04:59 [INFO] train episode 4370: reward = 58.00, steps = 58
00:04:59 [INFO] train episode 4371: reward = 200.00, steps = 200
00:04:59 [INFO] train episode 4372: reward = 200.00, steps = 200
00:05:00 [INFO] train episode 4373: reward = 187.00, steps = 187
00:05:00 [INFO] train episode 4374: reward = 115.00, steps = 115
00:05:00 [INFO] train episode 4375: reward = 148.00, steps = 148
00:05:00 [INFO] train episode 4376: reward = 200.00, steps = 200
00:05:00 [INFO] train episode 4377: reward = 200.00, steps = 200
00:05:00 [INFO] train episode 4378: reward = 200.00, steps = 200
00:05:00 [INFO] train episode 4379: reward = 200.00, steps = 200
00:05:00 [INFO] train episode 4380: reward = 200.00, steps = 200
00:05:00 [INFO] train episode 4381: reward = 200.00, steps = 200
00:05:00 [INFO] train episode 4382: reward = 86.00, steps = 86
00:05:00 [INFO] train episode 4383: reward = 200.00, steps = 200
00:05:00 [INFO] train episode 4384: reward = 188.00, steps = 188
00:05:00 [INFO] train episode 4385: reward = 160.00, steps = 160
00:05:00 [INFO] train episode 4386: reward = 200.00, steps = 200
00:05:00 [INFO] train episode 4387: reward = 62.00, steps = 62
00:05:00 [INFO] train episode 4388: reward = 174.00, steps = 174
00:05:01 [INFO] train episode 4389: reward = 200.00, steps = 200
00:05:01 [INFO] train episode 4390: reward = 200.00, steps = 200
00:05:01 [INFO] train episode 4391: reward = 200.00, steps = 200
00:05:01 [INFO] train episode 4392: reward = 200.00, steps = 200
00:05:01 [INFO] train episode 4393: reward = 200.00, steps = 200
00:05:01 [INFO] train episode 4394: reward = 139.00, steps = 139
00:05:01 [INFO] train episode 4395: reward = 200.00, steps = 200
00:05:01 [INFO] train episode 4396: reward = 193.00, steps = 193
00:05:01 [INFO] train episode 4397: reward = 200.00, steps = 200
00:05:01 [INFO] train episode 4398: reward = 200.00, steps = 200
00:05:01 [INFO] train episode 4399: reward = 200.00, steps = 200
00:05:01 [INFO] train episode 4400: reward = 200.00, steps = 200
00:05:01 [INFO] train episode 4401: reward = 184.00, steps = 184
00:05:01 [INFO] train episode 4402: reward = 192.00, steps = 192
00:05:02 [INFO] train episode 4403: reward = 103.00, steps = 103
00:05:02 [INFO] train episode 4404: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4405: reward = 145.00, steps = 145
00:05:02 [INFO] train episode 4406: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4407: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4408: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4409: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4410: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4411: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4412: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4413: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4414: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4415: reward = 200.00, steps = 200
00:05:02 [INFO] train episode 4416: reward = 200.00, steps = 200
00:05:03 [INFO] train episode 4417: reward = 192.00, steps = 192
00:05:03 [INFO] train episode 4418: reward = 200.00, steps = 200
00:05:03 [INFO] train episode 4419: reward = 200.00, steps = 200
00:05:03 [INFO] train episode 4420: reward = 200.00, steps = 200
00:05:03 [INFO] train episode 4421: reward = 200.00, steps = 200
00:05:03 [INFO] train episode 4422: reward = 151.00, steps = 151
00:05:03 [INFO] train episode 4423: reward = 146.00, steps = 146
00:05:03 [INFO] train episode 4424: reward = 198.00, steps = 198
00:05:03 [INFO] train episode 4425: reward = 160.00, steps = 160
00:05:03 [INFO] train episode 4426: reward = 200.00, steps = 200
00:05:03 [INFO] train episode 4427: reward = 143.00, steps = 143
00:05:03 [INFO] train episode 4428: reward = 200.00, steps = 200
00:05:03 [INFO] train episode 4429: reward = 198.00, steps = 198
00:05:04 [INFO] train episode 4430: reward = 183.00, steps = 183
00:05:04 [INFO] train episode 4431: reward = 200.00, steps = 200
00:05:04 [INFO] train episode 4432: reward = 200.00, steps = 200
00:05:04 [INFO] train episode 4433: reward = 159.00, steps = 159
00:05:04 [INFO] train episode 4434: reward = 200.00, steps = 200
00:05:04 [INFO] train episode 4435: reward = 147.00, steps = 147
00:05:04 [INFO] train episode 4436: reward = 200.00, steps = 200
00:05:04 [INFO] train episode 4437: reward = 200.00, steps = 200
00:05:04 [INFO] train episode 4438: reward = 199.00, steps = 199
00:05:04 [INFO] train episode 4439: reward = 200.00, steps = 200
00:05:04 [INFO] train episode 4440: reward = 200.00, steps = 200
00:05:04 [INFO] train episode 4441: reward = 200.00, steps = 200
00:05:04 [INFO] train episode 4442: reward = 200.00, steps = 200
00:05:04 [INFO] train episode 4443: reward = 200.00, steps = 200
00:05:05 [INFO] train episode 4444: reward = 200.00, steps = 200
00:05:05 [INFO] train episode 4445: reward = 200.00, steps = 200
00:05:05 [INFO] train episode 4446: reward = 27.00, steps = 27
00:05:05 [INFO] train episode 4447: reward = 154.00, steps = 154
00:05:05 [INFO] train episode 4448: reward = 200.00, steps = 200
00:05:05 [INFO] train episode 4449: reward = 200.00, steps = 200
00:05:05 [INFO] train episode 4450: reward = 200.00, steps = 200
00:05:05 [INFO] train episode 4451: reward = 200.00, steps = 200
00:05:05 [INFO] train episode 4452: reward = 200.00, steps = 200
00:05:05 [INFO] train episode 4453: reward = 122.00, steps = 122
00:05:05 [INFO] train episode 4454: reward = 143.00, steps = 143
00:05:05 [INFO] train episode 4455: reward = 192.00, steps = 192
00:05:05 [INFO] train episode 4456: reward = 200.00, steps = 200
00:05:05 [INFO] train episode 4457: reward = 195.00, steps = 195
00:05:06 [INFO] train episode 4458: reward = 200.00, steps = 200
00:05:06 [INFO] train episode 4459: reward = 200.00, steps = 200
00:05:06 [INFO] train episode 4460: reward = 200.00, steps = 200
00:05:06 [INFO] train episode 4461: reward = 200.00, steps = 200
00:05:06 [INFO] train episode 4462: reward = 200.00, steps = 200
00:05:06 [INFO] train episode 4463: reward = 200.00, steps = 200
00:05:06 [INFO] train episode 4464: reward = 200.00, steps = 200
00:05:06 [INFO] train episode 4465: reward = 152.00, steps = 152
00:05:06 [INFO] train episode 4466: reward = 196.00, steps = 196
00:05:06 [INFO] train episode 4467: reward = 200.00, steps = 200
00:05:06 [INFO] train episode 4468: reward = 44.00, steps = 44
00:05:06 [INFO] train episode 4469: reward = 200.00, steps = 200
00:05:06 [INFO] train episode 4470: reward = 200.00, steps = 200
00:05:06 [INFO] train episode 4471: reward = 158.00, steps = 158
00:05:06 [INFO] train episode 4472: reward = 196.00, steps = 196
00:05:07 [INFO] train episode 4473: reward = 200.00, steps = 200
00:05:07 [INFO] train episode 4474: reward = 200.00, steps = 200
00:05:07 [INFO] train episode 4475: reward = 171.00, steps = 171
00:05:07 [INFO] train episode 4476: reward = 200.00, steps = 200
00:05:07 [INFO] train episode 4477: reward = 200.00, steps = 200
00:05:07 [INFO] train episode 4478: reward = 200.00, steps = 200
00:05:07 [INFO] train episode 4479: reward = 136.00, steps = 136
00:05:07 [INFO] train episode 4480: reward = 112.00, steps = 112
00:05:07 [INFO] train episode 4481: reward = 33.00, steps = 33
00:05:07 [INFO] train episode 4482: reward = 143.00, steps = 143
00:05:07 [INFO] train episode 4483: reward = 164.00, steps = 164
00:05:07 [INFO] train episode 4484: reward = 200.00, steps = 200
00:05:07 [INFO] train episode 4485: reward = 200.00, steps = 200
00:05:07 [INFO] train episode 4486: reward = 162.00, steps = 162
00:05:07 [INFO] train episode 4487: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4488: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4489: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4490: reward = 139.00, steps = 139
00:05:08 [INFO] train episode 4491: reward = 196.00, steps = 196
00:05:08 [INFO] train episode 4492: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4493: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4494: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4495: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4496: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4497: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4498: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4499: reward = 200.00, steps = 200
00:05:08 [INFO] train episode 4500: reward = 200.00, steps = 200
00:05:09 [INFO] train episode 4501: reward = 200.00, steps = 200
00:05:09 [INFO] train episode 4502: reward = 200.00, steps = 200
00:05:09 [INFO] train episode 4503: reward = 200.00, steps = 200
00:05:09 [INFO] train episode 4504: reward = 200.00, steps = 200
00:05:09 [INFO] train episode 4505: reward = 171.00, steps = 171
00:05:09 [INFO] train episode 4506: reward = 200.00, steps = 200
00:05:09 [INFO] train episode 4507: reward = 140.00, steps = 140
00:05:09 [INFO] train episode 4508: reward = 200.00, steps = 200
00:05:09 [INFO] train episode 4509: reward = 200.00, steps = 200
00:05:09 [INFO] train episode 4510: reward = 81.00, steps = 81
00:05:09 [INFO] train episode 4511: reward = 198.00, steps = 198
00:05:09 [INFO] train episode 4512: reward = 169.00, steps = 169
00:05:09 [INFO] train episode 4513: reward = 200.00, steps = 200
00:05:09 [INFO] train episode 4514: reward = 200.00, steps = 200
00:05:10 [INFO] train episode 4515: reward = 200.00, steps = 200
00:05:10 [INFO] train episode 4516: reward = 200.00, steps = 200
00:05:10 [INFO] train episode 4517: reward = 200.00, steps = 200
00:05:10 [INFO] train episode 4518: reward = 196.00, steps = 196
00:05:10 [INFO] train episode 4519: reward = 200.00, steps = 200
00:05:10 [INFO] train episode 4520: reward = 200.00, steps = 200
00:05:10 [INFO] train episode 4521: reward = 200.00, steps = 200
00:05:10 [INFO] train episode 4522: reward = 200.00, steps = 200
00:05:10 [INFO] train episode 4523: reward = 200.00, steps = 200
00:05:10 [INFO] train episode 4524: reward = 190.00, steps = 190
00:05:10 [INFO] train episode 4525: reward = 125.00, steps = 125
00:05:10 [INFO] train episode 4526: reward = 63.00, steps = 63
00:05:10 [INFO] train episode 4527: reward = 200.00, steps = 200
00:05:10 [INFO] train episode 4528: reward = 187.00, steps = 187
00:05:11 [INFO] train episode 4529: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4530: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4531: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4532: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4533: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4534: reward = 162.00, steps = 162
00:05:11 [INFO] train episode 4535: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4536: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4537: reward = 162.00, steps = 162
00:05:11 [INFO] train episode 4538: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4539: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4540: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4541: reward = 200.00, steps = 200
00:05:11 [INFO] train episode 4542: reward = 200.00, steps = 200
00:05:12 [INFO] train episode 4543: reward = 200.00, steps = 200
00:05:12 [INFO] train episode 4544: reward = 200.00, steps = 200
00:05:12 [INFO] train episode 4545: reward = 188.00, steps = 188
00:05:12 [INFO] train episode 4546: reward = 200.00, steps = 200
00:05:12 [INFO] train episode 4547: reward = 200.00, steps = 200
00:05:12 [INFO] train episode 4548: reward = 177.00, steps = 177
00:05:12 [INFO] train episode 4549: reward = 131.00, steps = 131
00:05:12 [INFO] train episode 4550: reward = 200.00, steps = 200
00:05:12 [INFO] train episode 4551: reward = 189.00, steps = 189
00:05:12 [INFO] train episode 4552: reward = 200.00, steps = 200
00:05:12 [INFO] train episode 4553: reward = 200.00, steps = 200
00:05:12 [INFO] train episode 4554: reward = 200.00, steps = 200
00:05:12 [INFO] train episode 4555: reward = 200.00, steps = 200
00:05:12 [INFO] train episode 4556: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4557: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4558: reward = 189.00, steps = 189
00:05:13 [INFO] train episode 4559: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4560: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4561: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4562: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4563: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4564: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4565: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4566: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4567: reward = 167.00, steps = 167
00:05:13 [INFO] train episode 4568: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4569: reward = 200.00, steps = 200
00:05:13 [INFO] train episode 4570: reward = 196.00, steps = 196
00:05:14 [INFO] train episode 4571: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4572: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4573: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4574: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4575: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4576: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4577: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4578: reward = 73.00, steps = 73
00:05:14 [INFO] train episode 4579: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4580: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4581: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4582: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4583: reward = 200.00, steps = 200
00:05:14 [INFO] train episode 4584: reward = 200.00, steps = 200
00:05:15 [INFO] train episode 4585: reward = 200.00, steps = 200
00:05:15 [INFO] train episode 4586: reward = 198.00, steps = 198
00:05:15 [INFO] train episode 4587: reward = 86.00, steps = 86
00:05:15 [INFO] train episode 4588: reward = 200.00, steps = 200
00:05:15 [INFO] train episode 4589: reward = 67.00, steps = 67
00:05:15 [INFO] train episode 4590: reward = 142.00, steps = 142
00:05:15 [INFO] train episode 4591: reward = 54.00, steps = 54
00:05:15 [INFO] train episode 4592: reward = 200.00, steps = 200
00:05:15 [INFO] train episode 4593: reward = 166.00, steps = 166
00:05:15 [INFO] train episode 4594: reward = 200.00, steps = 200
00:05:15 [INFO] train episode 4595: reward = 200.00, steps = 200
00:05:15 [INFO] train episode 4596: reward = 200.00, steps = 200
00:05:15 [INFO] train episode 4597: reward = 200.00, steps = 200
00:05:15 [INFO] train episode 4598: reward = 200.00, steps = 200
00:05:15 [INFO] train episode 4599: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4600: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4601: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4602: reward = 137.00, steps = 137
00:05:16 [INFO] train episode 4603: reward = 163.00, steps = 163
00:05:16 [INFO] train episode 4604: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4605: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4606: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4607: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4608: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4609: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4610: reward = 86.00, steps = 86
00:05:16 [INFO] train episode 4611: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4612: reward = 200.00, steps = 200
00:05:16 [INFO] train episode 4613: reward = 200.00, steps = 200
00:05:17 [INFO] train episode 4614: reward = 180.00, steps = 180
00:05:17 [INFO] train episode 4615: reward = 59.00, steps = 59
00:05:17 [INFO] train episode 4616: reward = 200.00, steps = 200
00:05:17 [INFO] train episode 4617: reward = 179.00, steps = 179
00:05:17 [INFO] train episode 4618: reward = 200.00, steps = 200
00:05:17 [INFO] train episode 4619: reward = 200.00, steps = 200
00:05:17 [INFO] train episode 4620: reward = 200.00, steps = 200
00:05:17 [INFO] train episode 4621: reward = 197.00, steps = 197
00:05:17 [INFO] train episode 4622: reward = 200.00, steps = 200
00:05:17 [INFO] train episode 4623: reward = 133.00, steps = 133
00:05:17 [INFO] train episode 4624: reward = 200.00, steps = 200
00:05:17 [INFO] train episode 4625: reward = 200.00, steps = 200
00:05:17 [INFO] train episode 4626: reward = 120.00, steps = 120
00:05:17 [INFO] train episode 4627: reward = 200.00, steps = 200
00:05:17 [INFO] train episode 4628: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4629: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4630: reward = 120.00, steps = 120
00:05:18 [INFO] train episode 4631: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4632: reward = 95.00, steps = 95
00:05:18 [INFO] train episode 4633: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4634: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4635: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4636: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4637: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4638: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4639: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4640: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4641: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4642: reward = 200.00, steps = 200
00:05:18 [INFO] train episode 4643: reward = 172.00, steps = 172
00:05:19 [INFO] train episode 4644: reward = 200.00, steps = 200
00:05:19 [INFO] train episode 4645: reward = 172.00, steps = 172
00:05:19 [INFO] train episode 4646: reward = 184.00, steps = 184
00:05:19 [INFO] train episode 4647: reward = 140.00, steps = 140
00:05:19 [INFO] train episode 4648: reward = 200.00, steps = 200
00:05:19 [INFO] train episode 4649: reward = 200.00, steps = 200
00:05:19 [INFO] train episode 4650: reward = 200.00, steps = 200
00:05:19 [INFO] train episode 4651: reward = 200.00, steps = 200
00:05:19 [INFO] train episode 4652: reward = 200.00, steps = 200
00:05:19 [INFO] train episode 4653: reward = 111.00, steps = 111
00:05:19 [INFO] train episode 4654: reward = 200.00, steps = 200
00:05:19 [INFO] train episode 4655: reward = 200.00, steps = 200
00:05:19 [INFO] train episode 4656: reward = 193.00, steps = 193
00:05:20 [INFO] train episode 4657: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4658: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4659: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4660: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4661: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4662: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4663: reward = 169.00, steps = 169
00:05:20 [INFO] train episode 4664: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4665: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4666: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4667: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4668: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4669: reward = 200.00, steps = 200
00:05:20 [INFO] train episode 4670: reward = 200.00, steps = 200
00:05:21 [INFO] train episode 4671: reward = 200.00, steps = 200
00:05:21 [INFO] train episode 4672: reward = 200.00, steps = 200
00:05:21 [INFO] train episode 4673: reward = 200.00, steps = 200
00:05:21 [INFO] train episode 4674: reward = 200.00, steps = 200
00:05:21 [INFO] train episode 4675: reward = 200.00, steps = 200
00:05:21 [INFO] train episode 4676: reward = 167.00, steps = 167
00:05:21 [INFO] train episode 4677: reward = 182.00, steps = 182
00:05:21 [INFO] train episode 4678: reward = 200.00, steps = 200
00:05:21 [INFO] train episode 4679: reward = 200.00, steps = 200
00:05:21 [INFO] train episode 4680: reward = 200.00, steps = 200
00:05:21 [INFO] train episode 4681: reward = 177.00, steps = 177
00:05:21 [INFO] train episode 4682: reward = 182.00, steps = 182
00:05:21 [INFO] train episode 4683: reward = 35.00, steps = 35
00:05:21 [INFO] train episode 4684: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4685: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4686: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4687: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4688: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4689: reward = 123.00, steps = 123
00:05:22 [INFO] train episode 4690: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4691: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4692: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4693: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4694: reward = 194.00, steps = 194
00:05:22 [INFO] train episode 4695: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4696: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4697: reward = 200.00, steps = 200
00:05:22 [INFO] train episode 4698: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4699: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4700: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4701: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4702: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4703: reward = 120.00, steps = 120
00:05:23 [INFO] train episode 4704: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4705: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4706: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4707: reward = 101.00, steps = 101
00:05:23 [INFO] train episode 4708: reward = 66.00, steps = 66
00:05:23 [INFO] train episode 4709: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4710: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4711: reward = 200.00, steps = 200
00:05:23 [INFO] train episode 4712: reward = 151.00, steps = 151
00:05:23 [INFO] train episode 4713: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4714: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4715: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4716: reward = 173.00, steps = 173
00:05:24 [INFO] train episode 4717: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4718: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4719: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4720: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4721: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4722: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4723: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4724: reward = 134.00, steps = 134
00:05:24 [INFO] train episode 4725: reward = 190.00, steps = 190
00:05:24 [INFO] train episode 4726: reward = 200.00, steps = 200
00:05:24 [INFO] train episode 4727: reward = 200.00, steps = 200
00:05:25 [INFO] train episode 4728: reward = 200.00, steps = 200
00:05:25 [INFO] train episode 4729: reward = 200.00, steps = 200
00:05:25 [INFO] train episode 4730: reward = 200.00, steps = 200
00:05:25 [INFO] train episode 4731: reward = 200.00, steps = 200
00:05:25 [INFO] train episode 4732: reward = 200.00, steps = 200
00:05:25 [INFO] train episode 4733: reward = 200.00, steps = 200
00:05:25 [INFO] train episode 4734: reward = 200.00, steps = 200
00:05:25 [INFO] train episode 4735: reward = 200.00, steps = 200
00:05:25 [INFO] train episode 4736: reward = 200.00, steps = 200
00:05:25 [INFO] train episode 4737: reward = 182.00, steps = 182
00:05:25 [INFO] train episode 4738: reward = 110.00, steps = 110
00:05:25 [INFO] train episode 4739: reward = 61.00, steps = 61
00:05:25 [INFO] train episode 4740: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4741: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4742: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4743: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4744: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4745: reward = 120.00, steps = 120
00:05:26 [INFO] train episode 4746: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4747: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4748: reward = 132.00, steps = 132
00:05:26 [INFO] train episode 4749: reward = 97.00, steps = 97
00:05:26 [INFO] train episode 4750: reward = 159.00, steps = 159
00:05:26 [INFO] train episode 4751: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4752: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4753: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4754: reward = 200.00, steps = 200
00:05:26 [INFO] train episode 4755: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4756: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4757: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4758: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4759: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4760: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4761: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4762: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4763: reward = 146.00, steps = 146
00:05:27 [INFO] train episode 4764: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4765: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4766: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4767: reward = 200.00, steps = 200
00:05:27 [INFO] train episode 4768: reward = 63.00, steps = 63
00:05:27 [INFO] train episode 4769: reward = 200.00, steps = 200
00:05:28 [INFO] train episode 4770: reward = 200.00, steps = 200
00:05:28 [INFO] train episode 4771: reward = 200.00, steps = 200
00:05:28 [INFO] train episode 4772: reward = 200.00, steps = 200
00:05:28 [INFO] train episode 4773: reward = 200.00, steps = 200
00:05:28 [INFO] train episode 4774: reward = 50.00, steps = 50
00:05:28 [INFO] train episode 4775: reward = 200.00, steps = 200
00:05:28 [INFO] train episode 4776: reward = 129.00, steps = 129
00:05:28 [INFO] train episode 4777: reward = 200.00, steps = 200
00:05:28 [INFO] train episode 4778: reward = 188.00, steps = 188
00:05:28 [INFO] train episode 4779: reward = 200.00, steps = 200
00:05:28 [INFO] train episode 4780: reward = 200.00, steps = 200
00:05:28 [INFO] train episode 4781: reward = 159.00, steps = 159
00:05:28 [INFO] train episode 4782: reward = 120.00, steps = 120
00:05:28 [INFO] train episode 4783: reward = 200.00, steps = 200
00:05:28 [INFO] train episode 4784: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4785: reward = 116.00, steps = 116
00:05:29 [INFO] train episode 4786: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4787: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4788: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4789: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4790: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4791: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4792: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4793: reward = 173.00, steps = 173
00:05:29 [INFO] train episode 4794: reward = 176.00, steps = 176
00:05:29 [INFO] train episode 4795: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4796: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4797: reward = 200.00, steps = 200
00:05:29 [INFO] train episode 4798: reward = 200.00, steps = 200
00:05:30 [INFO] train episode 4799: reward = 200.00, steps = 200
00:05:30 [INFO] train episode 4800: reward = 200.00, steps = 200
00:05:30 [INFO] train episode 4801: reward = 200.00, steps = 200
00:05:30 [INFO] train episode 4802: reward = 178.00, steps = 178
00:05:30 [INFO] train episode 4803: reward = 190.00, steps = 190
00:05:30 [INFO] train episode 4804: reward = 134.00, steps = 134
00:05:30 [INFO] train episode 4805: reward = 200.00, steps = 200
00:05:30 [INFO] train episode 4806: reward = 200.00, steps = 200
00:05:30 [INFO] train episode 4807: reward = 157.00, steps = 157
00:05:30 [INFO] train episode 4808: reward = 200.00, steps = 200
00:05:30 [INFO] train episode 4809: reward = 200.00, steps = 200
00:05:30 [INFO] train episode 4810: reward = 113.00, steps = 113
00:05:30 [INFO] train episode 4811: reward = 200.00, steps = 200
00:05:30 [INFO] train episode 4812: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4813: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4814: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4815: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4816: reward = 88.00, steps = 88
00:05:31 [INFO] train episode 4817: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4818: reward = 122.00, steps = 122
00:05:31 [INFO] train episode 4819: reward = 71.00, steps = 71
00:05:31 [INFO] train episode 4820: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4821: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4822: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4823: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4824: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4825: reward = 200.00, steps = 200
00:05:31 [INFO] train episode 4826: reward = 148.00, steps = 148
00:05:31 [INFO] train episode 4827: reward = 200.00, steps = 200
00:05:32 [INFO] train episode 4828: reward = 200.00, steps = 200
00:05:32 [INFO] train episode 4829: reward = 200.00, steps = 200
00:05:32 [INFO] train episode 4830: reward = 200.00, steps = 200
00:05:32 [INFO] train episode 4831: reward = 200.00, steps = 200
00:05:32 [INFO] train episode 4832: reward = 195.00, steps = 195
00:05:32 [INFO] train episode 4833: reward = 200.00, steps = 200
00:05:32 [INFO] train episode 4834: reward = 200.00, steps = 200
00:05:32 [INFO] train episode 4835: reward = 85.00, steps = 85
00:05:32 [INFO] train episode 4836: reward = 162.00, steps = 162
00:05:32 [INFO] train episode 4837: reward = 124.00, steps = 124
00:05:32 [INFO] train episode 4838: reward = 200.00, steps = 200
00:05:32 [INFO] train episode 4839: reward = 200.00, steps = 200
00:05:32 [INFO] train episode 4840: reward = 145.00, steps = 145
00:05:32 [INFO] train episode 4841: reward = 200.00, steps = 200
00:05:32 [INFO] train episode 4842: reward = 188.00, steps = 188
00:05:33 [INFO] train episode 4843: reward = 200.00, steps = 200
00:05:33 [INFO] train episode 4844: reward = 200.00, steps = 200
00:05:33 [INFO] train episode 4845: reward = 192.00, steps = 192
00:05:33 [INFO] train episode 4846: reward = 200.00, steps = 200
00:05:33 [INFO] train episode 4847: reward = 196.00, steps = 196
00:05:33 [INFO] train episode 4848: reward = 200.00, steps = 200
00:05:33 [INFO] train episode 4849: reward = 200.00, steps = 200
00:05:33 [INFO] train episode 4850: reward = 200.00, steps = 200
00:05:33 [INFO] train episode 4851: reward = 200.00, steps = 200
00:05:33 [INFO] train episode 4852: reward = 200.00, steps = 200
00:05:33 [INFO] train episode 4853: reward = 200.00, steps = 200
00:05:33 [INFO] train episode 4854: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4855: reward = 196.00, steps = 196
00:05:34 [INFO] train episode 4856: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4857: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4858: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4859: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4860: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4861: reward = 22.00, steps = 22
00:05:34 [INFO] train episode 4862: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4863: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4864: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4865: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4866: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4867: reward = 200.00, steps = 200
00:05:34 [INFO] train episode 4868: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4869: reward = 184.00, steps = 184
00:05:35 [INFO] train episode 4870: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4871: reward = 84.00, steps = 84
00:05:35 [INFO] train episode 4872: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4873: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4874: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4875: reward = 175.00, steps = 175
00:05:35 [INFO] train episode 4876: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4877: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4878: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4879: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4880: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4881: reward = 200.00, steps = 200
00:05:35 [INFO] train episode 4882: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4883: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4884: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4885: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4886: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4887: reward = 109.00, steps = 109
00:05:36 [INFO] train episode 4888: reward = 143.00, steps = 143
00:05:36 [INFO] train episode 4889: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4890: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4891: reward = 130.00, steps = 130
00:05:36 [INFO] train episode 4892: reward = 19.00, steps = 19
00:05:36 [INFO] train episode 4893: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4894: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4895: reward = 69.00, steps = 69
00:05:36 [INFO] train episode 4896: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4897: reward = 200.00, steps = 200
00:05:36 [INFO] train episode 4898: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4899: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4900: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4901: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4902: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4903: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4904: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4905: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4906: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4907: reward = 186.00, steps = 186
00:05:37 [INFO] train episode 4908: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4909: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4910: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4911: reward = 200.00, steps = 200
00:05:37 [INFO] train episode 4912: reward = 169.00, steps = 169
00:05:38 [INFO] train episode 4913: reward = 170.00, steps = 170
00:05:38 [INFO] train episode 4914: reward = 200.00, steps = 200
00:05:38 [INFO] train episode 4915: reward = 200.00, steps = 200
00:05:38 [INFO] train episode 4916: reward = 184.00, steps = 184
00:05:38 [INFO] train episode 4917: reward = 200.00, steps = 200
00:05:38 [INFO] train episode 4918: reward = 200.00, steps = 200
00:05:38 [INFO] train episode 4919: reward = 200.00, steps = 200
00:05:38 [INFO] train episode 4920: reward = 186.00, steps = 186
00:05:38 [INFO] train episode 4921: reward = 200.00, steps = 200
00:05:38 [INFO] train episode 4922: reward = 173.00, steps = 173
00:05:38 [INFO] train episode 4923: reward = 183.00, steps = 183
00:05:38 [INFO] train episode 4924: reward = 200.00, steps = 200
00:05:38 [INFO] train episode 4925: reward = 183.00, steps = 183
00:05:39 [INFO] train episode 4926: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4927: reward = 192.00, steps = 192
00:05:39 [INFO] train episode 4928: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4929: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4930: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4931: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4932: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4933: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4934: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4935: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4936: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4937: reward = 200.00, steps = 200
00:05:39 [INFO] train episode 4938: reward = 200.00, steps = 200
00:05:40 [INFO] train episode 4939: reward = 180.00, steps = 180
00:05:40 [INFO] train episode 4940: reward = 200.00, steps = 200
00:05:40 [INFO] train episode 4941: reward = 200.00, steps = 200
00:05:40 [INFO] train episode 4942: reward = 108.00, steps = 108
00:05:40 [INFO] train episode 4943: reward = 200.00, steps = 200
00:05:40 [INFO] train episode 4944: reward = 178.00, steps = 178
00:05:40 [INFO] train episode 4945: reward = 200.00, steps = 200
00:05:40 [INFO] train episode 4946: reward = 160.00, steps = 160
00:05:40 [INFO] train episode 4947: reward = 200.00, steps = 200
00:05:40 [INFO] train episode 4948: reward = 200.00, steps = 200
00:05:40 [INFO] train episode 4949: reward = 200.00, steps = 200
00:05:40 [INFO] train episode 4950: reward = 176.00, steps = 176
00:05:40 [INFO] train episode 4951: reward = 200.00, steps = 200
00:05:40 [INFO] train episode 4952: reward = 200.00, steps = 200
00:05:41 [INFO] train episode 4953: reward = 200.00, steps = 200
00:05:41 [INFO] train episode 4954: reward = 200.00, steps = 200
00:05:41 [INFO] train episode 4955: reward = 122.00, steps = 122
00:05:41 [INFO] train episode 4956: reward = 175.00, steps = 175
00:05:41 [INFO] train episode 4957: reward = 200.00, steps = 200
00:05:41 [INFO] train episode 4958: reward = 171.00, steps = 171
00:05:41 [INFO] train episode 4959: reward = 200.00, steps = 200
00:05:41 [INFO] train episode 4960: reward = 200.00, steps = 200
00:05:41 [INFO] train episode 4961: reward = 200.00, steps = 200
00:05:41 [INFO] train episode 4962: reward = 200.00, steps = 200
00:05:41 [INFO] train episode 4963: reward = 200.00, steps = 200
00:05:41 [INFO] train episode 4964: reward = 189.00, steps = 189
00:05:41 [INFO] train episode 4965: reward = 200.00, steps = 200
00:05:41 [INFO] train episode 4966: reward = 146.00, steps = 146
00:05:42 [INFO] train episode 4967: reward = 200.00, steps = 200
00:05:42 [INFO] train episode 4968: reward = 200.00, steps = 200
00:05:42 [INFO] train episode 4969: reward = 200.00, steps = 200
00:05:42 [INFO] train episode 4970: reward = 200.00, steps = 200
00:05:42 [INFO] train episode 4971: reward = 200.00, steps = 200
00:05:42 [INFO] train episode 4972: reward = 200.00, steps = 200
00:05:42 [INFO] train episode 4973: reward = 200.00, steps = 200
00:05:42 [INFO] train episode 4974: reward = 117.00, steps = 117
00:05:42 [INFO] train episode 4975: reward = 178.00, steps = 178
00:05:42 [INFO] train episode 4976: reward = 200.00, steps = 200
00:05:42 [INFO] train episode 4977: reward = 200.00, steps = 200
00:05:42 [INFO] train episode 4978: reward = 200.00, steps = 200
00:05:42 [INFO] train episode 4979: reward = 180.00, steps = 180
00:05:43 [INFO] train episode 4980: reward = 200.00, steps = 200
00:05:43 [INFO] train episode 4981: reward = 200.00, steps = 200
00:05:43 [INFO] train episode 4982: reward = 200.00, steps = 200
00:05:43 [INFO] train episode 4983: reward = 200.00, steps = 200
00:05:43 [INFO] train episode 4984: reward = 200.00, steps = 200
00:05:43 [INFO] train episode 4985: reward = 200.00, steps = 200
00:05:43 [INFO] train episode 4986: reward = 144.00, steps = 144
00:05:43 [INFO] train episode 4987: reward = 200.00, steps = 200
00:05:43 [INFO] train episode 4988: reward = 200.00, steps = 200
00:05:43 [INFO] train episode 4989: reward = 140.00, steps = 140
00:05:43 [INFO] train episode 4990: reward = 200.00, steps = 200
00:05:43 [INFO] train episode 4991: reward = 200.00, steps = 200
00:05:43 [INFO] train episode 4992: reward = 194.00, steps = 194
00:05:44 [INFO] train episode 4993: reward = 200.00, steps = 200
00:05:44 [INFO] train episode 4994: reward = 200.00, steps = 200
00:05:44 [INFO] train episode 4995: reward = 200.00, steps = 200
00:05:44 [INFO] train episode 4996: reward = 117.00, steps = 117
00:05:44 [INFO] train episode 4997: reward = 198.00, steps = 198
00:05:44 [INFO] train episode 4998: reward = 200.00, steps = 200
00:05:44 [INFO] train episode 4999: reward = 200.00, steps = 200
00:05:44 [INFO] train episode 5000: reward = 173.00, steps = 173
00:05:44 [INFO] train episode 5001: reward = 200.00, steps = 200
00:05:44 [INFO] train episode 5002: reward = 200.00, steps = 200
00:05:44 [INFO] train episode 5003: reward = 200.00, steps = 200
00:05:44 [INFO] train episode 5004: reward = 200.00, steps = 200
00:05:44 [INFO] train episode 5005: reward = 200.00, steps = 200
00:05:44 [INFO] train episode 5006: reward = 200.00, steps = 200
00:05:45 [INFO] train episode 5007: reward = 70.00, steps = 70
00:05:45 [INFO] train episode 5008: reward = 134.00, steps = 134
00:05:45 [INFO] train episode 5009: reward = 200.00, steps = 200
00:05:45 [INFO] train episode 5010: reward = 169.00, steps = 169
00:05:45 [INFO] train episode 5011: reward = 200.00, steps = 200
00:05:45 [INFO] train episode 5012: reward = 200.00, steps = 200
00:05:45 [INFO] train episode 5013: reward = 200.00, steps = 200
00:05:45 [INFO] train episode 5014: reward = 200.00, steps = 200
00:05:45 [INFO] train episode 5015: reward = 200.00, steps = 200
00:05:45 [INFO] train episode 5016: reward = 200.00, steps = 200
00:05:45 [INFO] train episode 5017: reward = 200.00, steps = 200
00:05:45 [INFO] train episode 5018: reward = 200.00, steps = 200
00:05:45 [INFO] train episode 5019: reward = 171.00, steps = 171
00:05:46 [INFO] train episode 5020: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5021: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5022: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5023: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5024: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5025: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5026: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5027: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5028: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5029: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5030: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5031: reward = 190.00, steps = 190
00:05:46 [INFO] train episode 5032: reward = 200.00, steps = 200
00:05:46 [INFO] train episode 5033: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5034: reward = 159.00, steps = 159
00:05:47 [INFO] train episode 5035: reward = 196.00, steps = 196
00:05:47 [INFO] train episode 5036: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5037: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5038: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5039: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5040: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5041: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5042: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5043: reward = 40.00, steps = 40
00:05:47 [INFO] train episode 5044: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5045: reward = 176.00, steps = 176
00:05:47 [INFO] train episode 5046: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5047: reward = 200.00, steps = 200
00:05:47 [INFO] train episode 5048: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5049: reward = 83.00, steps = 83
00:05:48 [INFO] train episode 5050: reward = 52.00, steps = 52
00:05:48 [INFO] train episode 5051: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5052: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5053: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5054: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5055: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5056: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5057: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5058: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5059: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5060: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5061: reward = 200.00, steps = 200
00:05:48 [INFO] train episode 5062: reward = 200.00, steps = 200
00:05:49 [INFO] train episode 5063: reward = 200.00, steps = 200
00:05:49 [INFO] train episode 5064: reward = 200.00, steps = 200
00:05:49 [INFO] train episode 5065: reward = 200.00, steps = 200
00:05:49 [INFO] train episode 5066: reward = 200.00, steps = 200
00:05:49 [INFO] train episode 5067: reward = 200.00, steps = 200
00:05:49 [INFO] train episode 5068: reward = 200.00, steps = 200
00:05:49 [INFO] train episode 5069: reward = 200.00, steps = 200
00:05:49 [INFO] train episode 5070: reward = 183.00, steps = 183
00:05:49 [INFO] ==== test ====
00:05:49 [INFO] test episode 0: reward = 200.00, steps = 200
00:05:49 [INFO] test episode 1: reward = 98.00, steps = 98
00:05:49 [INFO] test episode 2: reward = 200.00, steps = 200
00:05:49 [INFO] test episode 3: reward = 200.00, steps = 200
00:05:49 [INFO] test episode 4: reward = 200.00, steps = 200
00:05:49 [INFO] test episode 5: reward = 200.00, steps = 200
00:05:49 [INFO] test episode 6: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 7: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 8: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 9: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 10: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 11: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 12: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 13: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 14: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 15: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 16: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 17: reward = 189.00, steps = 189
00:05:50 [INFO] test episode 18: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 19: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 20: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 21: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 22: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 23: reward = 200.00, steps = 200
00:05:50 [INFO] test episode 24: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 25: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 26: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 27: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 28: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 29: reward = 185.00, steps = 185
00:05:51 [INFO] test episode 30: reward = 197.00, steps = 197
00:05:51 [INFO] test episode 31: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 32: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 33: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 34: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 35: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 36: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 37: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 38: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 39: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 40: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 41: reward = 200.00, steps = 200
00:05:51 [INFO] test episode 42: reward = 162.00, steps = 162
00:05:51 [INFO] test episode 43: reward = 17.00, steps = 17
00:05:52 [INFO] test episode 44: reward = 187.00, steps = 187
00:05:52 [INFO] test episode 45: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 46: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 47: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 48: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 49: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 50: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 51: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 52: reward = 171.00, steps = 171
00:05:52 [INFO] test episode 53: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 54: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 55: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 56: reward = 112.00, steps = 112
00:05:52 [INFO] test episode 57: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 58: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 59: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 60: reward = 200.00, steps = 200
00:05:52 [INFO] test episode 61: reward = 146.00, steps = 146
00:05:52 [INFO] test episode 62: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 63: reward = 152.00, steps = 152
00:05:53 [INFO] test episode 64: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 65: reward = 150.00, steps = 150
00:05:53 [INFO] test episode 66: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 67: reward = 189.00, steps = 189
00:05:53 [INFO] test episode 68: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 69: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 70: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 71: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 72: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 73: reward = 176.00, steps = 176
00:05:53 [INFO] test episode 74: reward = 166.00, steps = 166
00:05:53 [INFO] test episode 75: reward = 144.00, steps = 144
00:05:53 [INFO] test episode 76: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 77: reward = 148.00, steps = 148
00:05:53 [INFO] test episode 78: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 79: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 80: reward = 152.00, steps = 152
00:05:53 [INFO] test episode 81: reward = 200.00, steps = 200
00:05:53 [INFO] test episode 82: reward = 174.00, steps = 174
00:05:54 [INFO] test episode 83: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 84: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 85: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 86: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 87: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 88: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 89: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 90: reward = 191.00, steps = 191
00:05:54 [INFO] test episode 91: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 92: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 93: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 94: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 95: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 96: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 97: reward = 200.00, steps = 200
00:05:54 [INFO] test episode 98: reward = 183.00, steps = 183
00:05:54 [INFO] test episode 99: reward = 133.00, steps = 133
00:05:54 [INFO] average episode reward = 190.22 ± 26.10

env.close()