| 2023-04-02 22:31:54 - r - INFO: - Hyperparameters: | |
| 2023-04-02 22:31:54 - r - INFO: - ================================================================================ | |
| 2023-04-02 22:31:54 - r - INFO: - Name Value Type | |
| 2023-04-02 22:31:54 - r - INFO: - env_name LunarLander-v2 <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - new_step_api 1 <class 'bool'> | |
| 2023-04-02 22:31:54 - r - INFO: - wrapper None <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - render 0 <class 'bool'> | |
| 2023-04-02 22:31:54 - r - INFO: - algo_name PPO <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - mode train <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - mp_backend mp <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - seed 1 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - device cpu <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - train_eps 600 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - test_eps 20 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - eval_eps 10 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - eval_per_episode 5 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - max_steps 1000 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - load_checkpoint 0 <class 'bool'> | |
| 2023-04-02 22:31:54 - r - INFO: - load_path tasks <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - show_fig 0 <class 'bool'> | |
| 2023-04-02 22:31:54 - r - INFO: - save_fig 1 <class 'bool'> | |
| 2023-04-02 22:31:54 - r - INFO: - ppo_type clip <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - continuous 0 <class 'bool'> | |
| 2023-04-02 22:31:54 - r - INFO: - gamma 0.99 <class 'float'> | |
| 2023-04-02 22:31:54 - r - INFO: - k_epochs 4 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - actor_lr 0.0003 <class 'float'> | |
| 2023-04-02 22:31:54 - r - INFO: - critic_lr 0.001 <class 'float'> | |
| 2023-04-02 22:31:54 - r - INFO: - eps_clip 0.2 <class 'float'> | |
| 2023-04-02 22:31:54 - r - INFO: - entropy_coef 0.01 <class 'float'> | |
| 2023-04-02 22:31:54 - r - INFO: - train_batch_size 256 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - sgd_batch_size 32 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - actor_hidden_dim 256 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - critic_hidden_dim 256 <class 'int'> | |
| 2023-04-02 22:31:54 - r - INFO: - task_dir /home/zf/Documents/Python/joyrl-offline/tasks/Train_LunarLander-v2_PPO_20230402-223154 <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - res_dir /home/zf/Documents/Python/joyrl-offline/tasks/Train_LunarLander-v2_PPO_20230402-223154/results <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - log_dir /home/zf/Documents/Python/joyrl-offline/tasks/Train_LunarLander-v2_PPO_20230402-223154/logs <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - traj_dir /home/zf/Documents/Python/joyrl-offline/tasks/Train_LunarLander-v2_PPO_20230402-223154/traj <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - tb_dir /home/zf/Documents/Python/joyrl-offline/tasks/Train_LunarLander-v2_PPO_20230402-223154/tb_logs <class 'str'> | |
| 2023-04-02 22:31:54 - r - INFO: - ================================================================================ | |
| 2023-04-02 22:31:54 - r - INFO: - n_states: 8, n_actions: 4 | |
| 2023-04-02 22:31:54 - r - INFO: - Start training! | |
| 2023-04-02 22:31:54 - r - INFO: - Env: LunarLander-v2, Algorithm: PPO, Device: cpu | |
| 2023-04-02 22:31:54 - r - INFO: - Episode: 1/600, Reward: -121.444, Step: 114 | |
| 2023-04-02 22:31:54 - r - INFO: - Episode: 2/600, Reward: -277.234, Step: 118 | |
| 2023-04-02 22:31:55 - r - INFO: - Episode: 3/600, Reward: -115.896, Step: 118 | |
| 2023-04-02 22:31:55 - r - INFO: - Episode: 4/600, Reward: -369.750, Step: 103 | |
| 2023-04-02 22:31:55 - r - INFO: - Episode: 5/600, Reward: -337.845, Step: 104 | |
| 2023-04-02 22:31:55 - r - INFO: - Current episode 5 has the best eval reward: -133.460 | |
| 2023-04-02 22:31:55 - r - INFO: - Episode: 6/600, Reward: -153.433, Step: 104 | |
| 2023-04-02 22:31:55 - r - INFO: - Episode: 7/600, Reward: -97.777, Step: 106 | |
| 2023-04-02 22:31:55 - r - INFO: - Episode: 8/600, Reward: -14.116, Step: 106 | |
| 2023-04-02 22:31:56 - r - INFO: - Episode: 9/600, Reward: -281.984, Step: 119 | |
| 2023-04-02 22:31:56 - r - INFO: - Episode: 10/600, Reward: -115.022, Step: 113 | |
| 2023-04-02 22:31:56 - r - INFO: - Episode: 11/600, Reward: -104.564, Step: 117 | |
| 2023-04-02 22:31:56 - r - INFO: - Episode: 12/600, Reward: -96.841, Step: 105 | |
| 2023-04-02 22:31:56 - r - INFO: - Episode: 13/600, Reward: -174.983, Step: 104 | |
| 2023-04-02 22:31:56 - r - INFO: - Episode: 14/600, Reward: -107.475, Step: 107 | |
| 2023-04-02 22:31:56 - r - INFO: - Episode: 15/600, Reward: -196.714, Step: 109 | |
| 2023-04-02 22:31:57 - r - INFO: - Episode: 16/600, Reward: -216.498, Step: 98 | |
| 2023-04-02 22:31:57 - r - INFO: - Episode: 17/600, Reward: -255.592, Step: 115 | |
| 2023-04-02 22:31:57 - r - INFO: - Episode: 18/600, Reward: -241.319, Step: 116 | |
| 2023-04-02 22:31:57 - r - INFO: - Episode: 19/600, Reward: -135.709, Step: 129 | |
| 2023-04-02 22:31:57 - r - INFO: - Episode: 20/600, Reward: -239.036, Step: 118 | |
| 2023-04-02 22:31:58 - r - INFO: - Episode: 21/600, Reward: -35.755, Step: 135 | |
| 2023-04-02 22:31:58 - r - INFO: - Episode: 22/600, Reward: -323.152, Step: 114 | |
| 2023-04-02 22:31:58 - r - INFO: - Episode: 23/600, Reward: -219.333, Step: 147 | |
| 2023-04-02 22:31:58 - r - INFO: - Episode: 24/600, Reward: -88.332, Step: 124 | |
| 2023-04-02 22:31:58 - r - INFO: - Episode: 25/600, Reward: -203.773, Step: 132 | |
| 2023-04-02 22:31:59 - r - INFO: - Episode: 26/600, Reward: -294.652, Step: 152 | |
| 2023-04-02 22:31:59 - r - INFO: - Episode: 27/600, Reward: -296.472, Step: 128 | |
| 2023-04-02 22:31:59 - r - INFO: - Episode: 28/600, Reward: -79.829, Step: 146 | |
| 2023-04-02 22:31:59 - r - INFO: - Episode: 29/600, Reward: -540.169, Step: 116 | |
| 2023-04-02 22:31:59 - r - INFO: - Episode: 30/600, Reward: -581.587, Step: 98 | |
| 2023-04-02 22:32:00 - r - INFO: - Episode: 31/600, Reward: -517.071, Step: 110 | |
| 2023-04-02 22:32:00 - r - INFO: - Episode: 32/600, Reward: -421.562, Step: 111 | |
| 2023-04-02 22:32:00 - r - INFO: - Episode: 33/600, Reward: -314.088, Step: 120 | |
| 2023-04-02 22:32:00 - r - INFO: - Episode: 34/600, Reward: -207.563, Step: 114 | |
| 2023-04-02 22:32:00 - r - INFO: - Episode: 35/600, Reward: -100.580, Step: 101 | |
| 2023-04-02 22:32:00 - r - INFO: - Episode: 36/600, Reward: -316.158, Step: 108 | |
| 2023-04-02 22:32:00 - r - INFO: - Episode: 37/600, Reward: -312.437, Step: 107 | |
| 2023-04-02 22:32:00 - r - INFO: - Episode: 38/600, Reward: -358.396, Step: 110 | |
| 2023-04-02 22:32:00 - r - INFO: - Episode: 39/600, Reward: -124.137, Step: 108 | |
| 2023-04-02 22:32:01 - r - INFO: - Episode: 40/600, Reward: -156.087, Step: 109 | |
| 2023-04-02 22:32:02 - r - INFO: - Episode: 41/600, Reward: -201.888, Step: 127 | |
| 2023-04-02 22:32:02 - r - INFO: - Episode: 42/600, Reward: -75.112, Step: 134 | |
| 2023-04-02 22:32:02 - r - INFO: - Episode: 43/600, Reward: -294.268, Step: 125 | |
| 2023-04-02 22:32:02 - r - INFO: - Episode: 44/600, Reward: -449.123, Step: 147 | |
| 2023-04-02 22:32:02 - r - INFO: - Episode: 45/600, Reward: -251.930, Step: 146 | |
| 2023-04-02 22:32:03 - r - INFO: - Episode: 46/600, Reward: -363.396, Step: 151 | |
| 2023-04-02 22:32:03 - r - INFO: - Episode: 47/600, Reward: -121.840, Step: 135 | |
| 2023-04-02 22:32:03 - r - INFO: - Episode: 48/600, Reward: -586.513, Step: 173 | |
| 2023-04-02 22:32:03 - r - INFO: - Episode: 49/600, Reward: -430.392, Step: 138 | |
| 2023-04-02 22:32:03 - r - INFO: - Episode: 50/600, Reward: -322.294, Step: 140 | |
| 2023-04-02 22:32:04 - r - INFO: - Episode: 51/600, Reward: -266.473, Step: 134 | |
| 2023-04-02 22:32:04 - r - INFO: - Episode: 52/600, Reward: -290.379, Step: 109 | |
| 2023-04-02 22:32:04 - r - INFO: - Episode: 53/600, Reward: -564.944, Step: 115 | |
| 2023-04-02 22:32:04 - r - INFO: - Episode: 54/600, Reward: -161.722, Step: 138 | |
| 2023-04-02 22:32:04 - r - INFO: - Episode: 55/600, Reward: -218.362, Step: 132 | |
| 2023-04-02 22:32:05 - r - INFO: - Episode: 56/600, Reward: -90.506, Step: 135 | |
| 2023-04-02 22:32:05 - r - INFO: - Episode: 57/600, Reward: -48.795, Step: 115 | |
| 2023-04-02 22:32:05 - r - INFO: - Episode: 58/600, Reward: -239.578, Step: 110 | |
| 2023-04-02 22:32:05 - r - INFO: - Episode: 59/600, Reward: -148.223, Step: 113 | |
| 2023-04-02 22:32:05 - r - INFO: - Episode: 60/600, Reward: -102.341, Step: 107 | |
| 2023-04-02 22:32:05 - r - INFO: - Episode: 61/600, Reward: -90.720, Step: 116 | |
| 2023-04-02 22:32:06 - r - INFO: - Episode: 62/600, Reward: -126.898, Step: 119 | |
| 2023-04-02 22:32:06 - r - INFO: - Episode: 63/600, Reward: -405.098, Step: 140 | |
| 2023-04-02 22:32:06 - r - INFO: - Episode: 64/600, Reward: -409.668, Step: 114 | |
| 2023-04-02 22:32:06 - r - INFO: - Episode: 65/600, Reward: -59.205, Step: 115 | |
| 2023-04-02 22:32:06 - r - INFO: - Episode: 66/600, Reward: -212.760, Step: 120 | |
| 2023-04-02 22:32:07 - r - INFO: - Episode: 67/600, Reward: -83.135, Step: 121 | |
| 2023-04-02 22:32:07 - r - INFO: - Episode: 68/600, Reward: -93.160, Step: 113 | |
| 2023-04-02 22:32:07 - r - INFO: - Episode: 69/600, Reward: -115.493, Step: 116 | |
| 2023-04-02 22:32:07 - r - INFO: - Episode: 70/600, Reward: -101.286, Step: 107 | |
| 2023-04-02 22:32:07 - r - INFO: - Current episode 70 has the best eval reward: -112.992 | |
| 2023-04-02 22:32:07 - r - INFO: - Episode: 71/600, Reward: -6.531, Step: 161 | |
| 2023-04-02 22:32:08 - r - INFO: - Episode: 72/600, Reward: -195.514, Step: 127 | |
| 2023-04-02 22:32:08 - r - INFO: - Episode: 73/600, Reward: -105.655, Step: 117 | |
| 2023-04-02 22:32:08 - r - INFO: - Episode: 74/600, Reward: -208.326, Step: 131 | |
| 2023-04-02 22:32:08 - r - INFO: - Episode: 75/600, Reward: -92.113, Step: 126 | |
| 2023-04-02 22:32:08 - r - INFO: - Current episode 75 has the best eval reward: -74.040 | |
| 2023-04-02 22:32:08 - r - INFO: - Episode: 76/600, Reward: -108.639, Step: 135 | |
| 2023-04-02 22:32:09 - r - INFO: - Episode: 77/600, Reward: -235.689, Step: 141 | |
| 2023-04-02 22:32:09 - r - INFO: - Episode: 78/600, Reward: -115.349, Step: 130 | |
| 2023-04-02 22:32:09 - r - INFO: - Episode: 79/600, Reward: -66.639, Step: 117 | |
| 2023-04-02 22:32:09 - r - INFO: - Episode: 80/600, Reward: -84.450, Step: 124 | |
| 2023-04-02 22:32:09 - r - INFO: - Episode: 81/600, Reward: -75.365, Step: 110 | |
| 2023-04-02 22:32:09 - r - INFO: - Episode: 82/600, Reward: -70.921, Step: 132 | |
| 2023-04-02 22:32:10 - r - INFO: - Episode: 83/600, Reward: -87.512, Step: 113 | |
| 2023-04-02 22:32:10 - r - INFO: - Episode: 84/600, Reward: -78.195, Step: 111 | |
| 2023-04-02 22:32:10 - r - INFO: - Episode: 85/600, Reward: -200.101, Step: 117 | |
| 2023-04-02 22:32:10 - r - INFO: - Episode: 86/600, Reward: -310.614, Step: 134 | |
| 2023-04-02 22:32:10 - r - INFO: - Episode: 87/600, Reward: -315.094, Step: 122 | |
| 2023-04-02 22:32:10 - r - INFO: - Episode: 88/600, Reward: -76.644, Step: 137 | |
| 2023-04-02 22:32:11 - r - INFO: - Episode: 89/600, Reward: -116.261, Step: 123 | |
| 2023-04-02 22:32:11 - r - INFO: - Episode: 90/600, Reward: -34.352, Step: 140 | |
| 2023-04-02 22:32:11 - r - INFO: - Episode: 91/600, Reward: -80.778, Step: 153 | |
| 2023-04-02 22:32:11 - r - INFO: - Episode: 92/600, Reward: -217.031, Step: 142 | |
| 2023-04-02 22:32:12 - r - INFO: - Episode: 93/600, Reward: -24.960, Step: 162 | |
| 2023-04-02 22:32:12 - r - INFO: - Episode: 94/600, Reward: -60.824, Step: 158 | |
| 2023-04-02 22:32:12 - r - INFO: - Episode: 95/600, Reward: -340.600, Step: 136 | |
| 2023-04-02 22:32:13 - r - INFO: - Episode: 96/600, Reward: -277.215, Step: 126 | |
| 2023-04-02 22:32:13 - r - INFO: - Episode: 97/600, Reward: -125.626, Step: 131 | |
| 2023-04-02 22:32:13 - r - INFO: - Episode: 98/600, Reward: -45.416, Step: 124 | |
| 2023-04-02 22:32:13 - r - INFO: - Episode: 99/600, Reward: -67.034, Step: 142 | |
| 2023-04-02 22:32:13 - r - INFO: - Episode: 100/600, Reward: -88.193, Step: 130 | |
| 2023-04-02 22:32:14 - r - INFO: - Current episode 100 has the best eval reward: -50.244 | |
| 2023-04-02 22:32:14 - r - INFO: - Episode: 101/600, Reward: -58.403, Step: 133 | |
| 2023-04-02 22:32:14 - r - INFO: - Episode: 102/600, Reward: -76.792, Step: 122 | |
| 2023-04-02 22:32:14 - r - INFO: - Episode: 103/600, Reward: -79.530, Step: 122 | |
| 2023-04-02 22:32:14 - r - INFO: - Episode: 104/600, Reward: -76.829, Step: 138 | |
| 2023-04-02 22:32:14 - r - INFO: - Episode: 105/600, Reward: -74.573, Step: 162 | |
| 2023-04-02 22:32:15 - r - INFO: - Episode: 106/600, Reward: -94.756, Step: 126 | |
| 2023-04-02 22:32:15 - r - INFO: - Episode: 107/600, Reward: -57.446, Step: 135 | |
| 2023-04-02 22:32:15 - r - INFO: - Episode: 108/600, Reward: -30.263, Step: 153 | |
| 2023-04-02 22:32:15 - r - INFO: - Episode: 109/600, Reward: -15.612, Step: 126 | |
| 2023-04-02 22:32:15 - r - INFO: - Episode: 110/600, Reward: -42.464, Step: 112 | |
| 2023-04-02 22:32:16 - r - INFO: - Episode: 111/600, Reward: -53.891, Step: 131 | |
| 2023-04-02 22:32:16 - r - INFO: - Episode: 112/600, Reward: -47.279, Step: 135 | |
| 2023-04-02 22:32:16 - r - INFO: - Episode: 113/600, Reward: -28.310, Step: 171 | |
| 2023-04-02 22:32:16 - r - INFO: - Episode: 114/600, Reward: -71.555, Step: 161 | |
| 2023-04-02 22:32:16 - r - INFO: - Episode: 115/600, Reward: -46.645, Step: 165 | |
| 2023-04-02 22:32:17 - r - INFO: - Episode: 116/600, Reward: -110.328, Step: 176 | |
| 2023-04-02 22:32:17 - r - INFO: - Episode: 117/600, Reward: -1.405, Step: 193 | |
| 2023-04-02 22:32:17 - r - INFO: - Episode: 118/600, Reward: -80.805, Step: 228 | |
| 2023-04-02 22:32:19 - r - INFO: - Episode: 119/600, Reward: -431.340, Step: 790 | |
| 2023-04-02 22:32:19 - r - INFO: - Episode: 120/600, Reward: -148.612, Step: 161 | |
| 2023-04-02 22:32:20 - r - INFO: - Episode: 121/600, Reward: -176.688, Step: 170 | |
| 2023-04-02 22:32:20 - r - INFO: - Episode: 122/600, Reward: -75.354, Step: 159 | |
| 2023-04-02 22:32:21 - r - INFO: - Episode: 123/600, Reward: -377.815, Step: 350 | |
| 2023-04-02 22:32:21 - r - INFO: - Episode: 124/600, Reward: -226.834, Step: 395 | |
| 2023-04-02 22:32:21 - r - INFO: - Episode: 125/600, Reward: -55.800, Step: 198 | |
| 2023-04-02 22:32:23 - r - INFO: - Episode: 126/600, Reward: -145.402, Step: 236 | |
| 2023-04-02 22:32:23 - r - INFO: - Episode: 127/600, Reward: -132.791, Step: 168 | |
| 2023-04-02 22:32:23 - r - INFO: - Episode: 128/600, Reward: -363.342, Step: 259 | |
| 2023-04-02 22:32:23 - r - INFO: - Episode: 129/600, Reward: -1.090, Step: 155 | |
| 2023-04-02 22:32:23 - r - INFO: - Episode: 130/600, Reward: -67.628, Step: 193 | |
| 2023-04-02 22:32:24 - r - INFO: - Episode: 131/600, Reward: -117.421, Step: 138 | |
| 2023-04-02 22:32:24 - r - INFO: - Episode: 132/600, Reward: 9.361, Step: 167 | |
| 2023-04-02 22:32:24 - r - INFO: - Episode: 133/600, Reward: -418.884, Step: 161 | |
| 2023-04-02 22:32:24 - r - INFO: - Episode: 134/600, Reward: 7.493, Step: 161 | |
| 2023-04-02 22:32:25 - r - INFO: - Episode: 135/600, Reward: -271.478, Step: 536 | |
| 2023-04-02 22:32:28 - r - INFO: - Episode: 136/600, Reward: 34.584, Step: 1000 | |
| 2023-04-02 22:32:28 - r - INFO: - Episode: 137/600, Reward: -11.470, Step: 147 | |
| 2023-04-02 22:32:28 - r - INFO: - Episode: 138/600, Reward: -75.408, Step: 132 | |
| 2023-04-02 22:32:28 - r - INFO: - Episode: 139/600, Reward: -181.785, Step: 144 | |
| 2023-04-02 22:32:29 - r - INFO: - Episode: 140/600, Reward: -45.557, Step: 176 | |
| 2023-04-02 22:32:30 - r - INFO: - Current episode 140 has the best eval reward: -37.770 | |
| 2023-04-02 22:32:30 - r - INFO: - Episode: 141/600, Reward: -203.110, Step: 165 | |
| 2023-04-02 22:32:30 - r - INFO: - Episode: 142/600, Reward: -254.859, Step: 190 | |
| 2023-04-02 22:32:31 - r - INFO: - Episode: 143/600, Reward: 9.829, Step: 160 | |
| 2023-04-02 22:32:31 - r - INFO: - Episode: 144/600, Reward: 17.705, Step: 150 | |
| 2023-04-02 22:32:31 - r - INFO: - Episode: 145/600, Reward: 8.250, Step: 139 | |
| 2023-04-02 22:32:34 - r - INFO: - Episode: 146/600, Reward: -21.816, Step: 180 | |
| 2023-04-02 22:32:34 - r - INFO: - Episode: 147/600, Reward: -29.650, Step: 213 | |
| 2023-04-02 22:32:34 - r - INFO: - Episode: 148/600, Reward: 10.789, Step: 179 | |
| 2023-04-02 22:32:34 - r - INFO: - Episode: 149/600, Reward: -216.825, Step: 321 | |
| 2023-04-02 22:32:35 - r - INFO: - Episode: 150/600, Reward: -62.803, Step: 448 | |
| 2023-04-02 22:32:39 - r - INFO: - Episode: 151/600, Reward: 27.057, Step: 302 | |
| 2023-04-02 22:32:40 - r - INFO: - Episode: 152/600, Reward: -20.970, Step: 253 | |
| 2023-04-02 22:32:40 - r - INFO: - Episode: 153/600, Reward: -188.575, Step: 319 | |
| 2023-04-02 22:32:41 - r - INFO: - Episode: 154/600, Reward: -105.422, Step: 346 | |
| 2023-04-02 22:32:41 - r - INFO: - Episode: 155/600, Reward: -147.773, Step: 232 | |
| 2023-04-02 22:32:43 - r - INFO: - Episode: 156/600, Reward: -98.581, Step: 222 | |
| 2023-04-02 22:32:43 - r - INFO: - Episode: 157/600, Reward: -204.741, Step: 437 | |
| 2023-04-02 22:32:44 - r - INFO: - Episode: 158/600, Reward: 31.711, Step: 1000 | |
| 2023-04-02 22:32:46 - r - INFO: - Episode: 159/600, Reward: 33.317, Step: 1000 | |
| 2023-04-02 22:32:46 - r - INFO: - Episode: 160/600, Reward: 3.771, Step: 136 | |
| 2023-04-02 22:32:47 - r - INFO: - Current episode 160 has the best eval reward: -9.279 | |
| 2023-04-02 22:32:47 - r - INFO: - Episode: 161/600, Reward: 9.814, Step: 123 | |
| 2023-04-02 22:32:47 - r - INFO: - Episode: 162/600, Reward: 8.625, Step: 129 | |
| 2023-04-02 22:32:47 - r - INFO: - Episode: 163/600, Reward: -5.854, Step: 129 | |
| 2023-04-02 22:32:48 - r - INFO: - Episode: 164/600, Reward: 23.973, Step: 132 | |
| 2023-04-02 22:32:48 - r - INFO: - Episode: 165/600, Reward: -15.441, Step: 137 | |
| 2023-04-02 22:32:49 - r - INFO: - Current episode 165 has the best eval reward: 0.221 | |
| 2023-04-02 22:32:49 - r - INFO: - Episode: 166/600, Reward: -24.959, Step: 142 | |
| 2023-04-02 22:32:49 - r - INFO: - Episode: 167/600, Reward: -55.740, Step: 176 | |
| 2023-04-02 22:32:50 - r - INFO: - Episode: 168/600, Reward: 54.055, Step: 1000 | |
| 2023-04-02 22:32:52 - r - INFO: - Episode: 169/600, Reward: 60.755, Step: 1000 | |
| 2023-04-02 22:32:52 - r - INFO: - Episode: 170/600, Reward: -180.272, Step: 143 | |
| 2023-04-02 22:32:53 - r - INFO: - Episode: 171/600, Reward: -184.921, Step: 148 | |
| 2023-04-02 22:32:53 - r - INFO: - Episode: 172/600, Reward: -171.919, Step: 140 | |
| 2023-04-02 22:32:54 - r - INFO: - Episode: 173/600, Reward: -183.949, Step: 142 | |
| 2023-04-02 22:32:55 - r - INFO: - Episode: 174/600, Reward: 53.447, Step: 1000 | |
| 2023-04-02 22:32:56 - r - INFO: - Episode: 175/600, Reward: 79.824, Step: 1000 | |
| 2023-04-02 22:32:58 - r - INFO: - Episode: 176/600, Reward: -106.806, Step: 144 | |
| 2023-04-02 22:32:58 - r - INFO: - Episode: 177/600, Reward: -58.712, Step: 138 | |
| 2023-04-02 22:32:58 - r - INFO: - Episode: 178/600, Reward: -56.982, Step: 140 | |
| 2023-04-02 22:32:59 - r - INFO: - Episode: 179/600, Reward: 77.983, Step: 1000 | |
| 2023-04-02 22:33:00 - r - INFO: - Episode: 180/600, Reward: 18.476, Step: 166 | |
| 2023-04-02 22:33:01 - r - INFO: - Episode: 181/600, Reward: -17.921, Step: 153 | |
| 2023-04-02 22:33:01 - r - INFO: - Episode: 182/600, Reward: 4.517, Step: 149 | |
| 2023-04-02 22:33:02 - r - INFO: - Episode: 183/600, Reward: 93.140, Step: 1000 | |
| 2023-04-02 22:33:02 - r - INFO: - Episode: 184/600, Reward: -61.875, Step: 108 | |
| 2023-04-02 22:33:02 - r - INFO: - Episode: 185/600, Reward: -45.813, Step: 104 | |
| 2023-04-02 22:33:03 - r - INFO: - Episode: 186/600, Reward: -26.910, Step: 118 | |
| 2023-04-02 22:33:03 - r - INFO: - Episode: 187/600, Reward: -46.781, Step: 106 | |
| 2023-04-02 22:33:03 - r - INFO: - Episode: 188/600, Reward: -20.429, Step: 130 | |
| 2023-04-02 22:33:03 - r - INFO: - Episode: 189/600, Reward: -18.215, Step: 142 | |
| 2023-04-02 22:33:03 - r - INFO: - Episode: 190/600, Reward: -33.297, Step: 110 | |
| 2023-04-02 22:33:03 - r - INFO: - Episode: 191/600, Reward: -55.212, Step: 112 | |
| 2023-04-02 22:33:04 - r - INFO: - Episode: 192/600, Reward: -3.684, Step: 127 | |
| 2023-04-02 22:33:04 - r - INFO: - Episode: 193/600, Reward: -56.040, Step: 116 | |
| 2023-04-02 22:33:05 - r - INFO: - Episode: 194/600, Reward: 94.817, Step: 1000 | |
| 2023-04-02 22:33:05 - r - INFO: - Episode: 195/600, Reward: -39.891, Step: 130 | |
| 2023-04-02 22:33:08 - r - INFO: - Current episode 195 has the best eval reward: 3.858 | |
| 2023-04-02 22:33:09 - r - INFO: - Episode: 196/600, Reward: 68.629, Step: 1000 | |
| 2023-04-02 22:33:09 - r - INFO: - Episode: 197/600, Reward: -74.193, Step: 128 | |
| 2023-04-02 22:33:10 - r - INFO: - Episode: 198/600, Reward: 86.340, Step: 1000 | |
| 2023-04-02 22:33:11 - r - INFO: - Episode: 199/600, Reward: 89.574, Step: 1000 | |
| 2023-04-02 22:33:13 - r - INFO: - Episode: 200/600, Reward: 89.497, Step: 1000 | |
| 2023-04-02 22:33:15 - r - INFO: - Episode: 201/600, Reward: -37.336, Step: 136 | |
| 2023-04-02 22:33:15 - r - INFO: - Episode: 202/600, Reward: -99.698, Step: 131 | |
| 2023-04-02 22:33:15 - r - INFO: - Episode: 203/600, Reward: -63.996, Step: 162 | |
| 2023-04-02 22:33:16 - r - INFO: - Episode: 204/600, Reward: -74.190, Step: 155 | |
| 2023-04-02 22:33:16 - r - INFO: - Episode: 205/600, Reward: 209.337, Step: 736 | |
| 2023-04-02 22:33:19 - r - INFO: - Episode: 206/600, Reward: 188.765, Step: 757 | |
| 2023-04-02 22:33:19 - r - INFO: - Episode: 207/600, Reward: 5.051, Step: 148 | |
| 2023-04-02 22:33:19 - r - INFO: - Episode: 208/600, Reward: -40.342, Step: 179 | |
| 2023-04-02 22:33:19 - r - INFO: - Episode: 209/600, Reward: -70.096, Step: 244 | |
| 2023-04-02 22:33:21 - r - INFO: - Episode: 210/600, Reward: 75.045, Step: 1000 | |
| 2023-04-02 22:33:22 - r - INFO: - Episode: 211/600, Reward: -29.003, Step: 201 | |
| 2023-04-02 22:33:23 - r - INFO: - Episode: 212/600, Reward: 73.286, Step: 1000 | |
| 2023-04-02 22:33:23 - r - INFO: - Episode: 213/600, Reward: -216.103, Step: 168 | |
| 2023-04-02 22:33:24 - r - INFO: - Episode: 214/600, Reward: -86.516, Step: 221 | |
| 2023-04-02 22:33:24 - r - INFO: - Episode: 215/600, Reward: -143.634, Step: 182 | |
| 2023-04-02 22:33:27 - r - INFO: - Current episode 215 has the best eval reward: 18.498 | |
| 2023-04-02 22:33:27 - r - INFO: - Episode: 216/600, Reward: -146.850, Step: 169 | |
| 2023-04-02 22:33:27 - r - INFO: - Episode: 217/600, Reward: -43.835, Step: 188 | |
| 2023-04-02 22:33:27 - r - INFO: - Episode: 218/600, Reward: -40.004, Step: 207 | |
| 2023-04-02 22:33:28 - r - INFO: - Episode: 219/600, Reward: -44.306, Step: 189 | |
| 2023-04-02 22:33:28 - r - INFO: - Episode: 220/600, Reward: -3.133, Step: 135 | |
| 2023-04-02 22:33:31 - r - INFO: - Episode: 221/600, Reward: 85.608, Step: 1000 | |
| 2023-04-02 22:33:31 - r - INFO: - Episode: 222/600, Reward: -34.164, Step: 239 | |
| 2023-04-02 22:33:32 - r - INFO: - Episode: 223/600, Reward: 222.201, Step: 309 | |
| 2023-04-02 22:33:33 - r - INFO: - Episode: 224/600, Reward: 179.929, Step: 837 | |
| 2023-04-02 22:33:34 - r - INFO: - Episode: 225/600, Reward: 82.515, Step: 1000 | |
| 2023-04-02 22:33:36 - r - INFO: - Current episode 225 has the best eval reward: 24.103 | |
| 2023-04-02 22:33:38 - r - INFO: - Episode: 226/600, Reward: 72.611, Step: 1000 | |
| 2023-04-02 22:33:38 - r - INFO: - Episode: 227/600, Reward: 3.218, Step: 192 | |
| 2023-04-02 22:33:38 - r - INFO: - Episode: 228/600, Reward: 27.043, Step: 170 | |
| 2023-04-02 22:33:38 - r - INFO: - Episode: 229/600, Reward: 22.643, Step: 174 | |
| 2023-04-02 22:33:38 - r - INFO: - Episode: 230/600, Reward: -14.321, Step: 197 | |
| 2023-04-02 22:33:39 - r - INFO: - Current episode 230 has the best eval reward: 57.269 | |
| 2023-04-02 22:33:40 - r - INFO: - Episode: 231/600, Reward: 30.397, Step: 170 | |
| 2023-04-02 22:33:40 - r - INFO: - Episode: 232/600, Reward: 25.974, Step: 193 | |
| 2023-04-02 22:33:40 - r - INFO: - Episode: 233/600, Reward: 30.080, Step: 171 | |
| 2023-04-02 22:33:40 - r - INFO: - Episode: 234/600, Reward: -29.671, Step: 222 | |
| 2023-04-02 22:33:40 - r - INFO: - Episode: 235/600, Reward: 207.325, Step: 305 | |
| 2023-04-02 22:33:41 - r - INFO: - Episode: 236/600, Reward: 8.052, Step: 181 | |
| 2023-04-02 22:33:41 - r - INFO: - Episode: 237/600, Reward: 31.976, Step: 185 | |
| 2023-04-02 22:33:42 - r - INFO: - Episode: 238/600, Reward: 13.269, Step: 210 | |
| 2023-04-02 22:33:42 - r - INFO: - Episode: 239/600, Reward: 7.470, Step: 231 | |
| 2023-04-02 22:33:42 - r - INFO: - Episode: 240/600, Reward: -26.022, Step: 334 | |
| 2023-04-02 22:33:44 - r - INFO: - Episode: 241/600, Reward: 25.707, Step: 228 | |
| 2023-04-02 22:33:44 - r - INFO: - Episode: 242/600, Reward: -22.355, Step: 210 | |
| 2023-04-02 22:33:44 - r - INFO: - Episode: 243/600, Reward: 16.928, Step: 210 | |
| 2023-04-02 22:33:44 - r - INFO: - Episode: 244/600, Reward: 0.225, Step: 204 | |
| 2023-04-02 22:33:45 - r - INFO: - Episode: 245/600, Reward: 191.807, Step: 454 | |
| 2023-04-02 22:33:48 - r - INFO: - Episode: 246/600, Reward: -42.903, Step: 223 | |
| 2023-04-02 22:33:48 - r - INFO: - Episode: 247/600, Reward: -113.874, Step: 281 | |
| 2023-04-02 22:33:50 - r - INFO: - Episode: 248/600, Reward: 16.974, Step: 1000 | |
| 2023-04-02 22:33:50 - r - INFO: - Episode: 249/600, Reward: 214.347, Step: 310 | |
| 2023-04-02 22:33:50 - r - INFO: - Episode: 250/600, Reward: -156.822, Step: 288 | |
| 2023-04-02 22:33:53 - r - INFO: - Episode: 251/600, Reward: 182.684, Step: 412 | |
| 2023-04-02 22:33:54 - r - INFO: - Episode: 252/600, Reward: 174.696, Step: 959 | |
| 2023-04-02 22:33:55 - r - INFO: - Episode: 253/600, Reward: 199.880, Step: 314 | |
| 2023-04-02 22:33:55 - r - INFO: - Episode: 254/600, Reward: 189.431, Step: 395 | |
| 2023-04-02 22:33:56 - r - INFO: - Episode: 255/600, Reward: 189.496, Step: 369 | |
| 2023-04-02 22:33:57 - r - INFO: - Episode: 256/600, Reward: -34.829, Step: 216 | |
| 2023-04-02 22:33:57 - r - INFO: - Episode: 257/600, Reward: -63.171, Step: 241 | |
| 2023-04-02 22:33:57 - r - INFO: - Episode: 258/600, Reward: -62.713, Step: 239 | |
| 2023-04-02 22:33:58 - r - INFO: - Episode: 259/600, Reward: 188.234, Step: 485 | |
| 2023-04-02 22:33:58 - r - INFO: - Episode: 260/600, Reward: -40.356, Step: 194 | |
| 2023-04-02 22:33:59 - r - INFO: - Current episode 260 has the best eval reward: 80.901 | |
| 2023-04-02 22:33:59 - r - INFO: - Episode: 261/600, Reward: -8.431, Step: 197 | |
| 2023-04-02 22:34:00 - r - INFO: - Episode: 262/600, Reward: 164.231, Step: 385 | |
| 2023-04-02 22:34:00 - r - INFO: - Episode: 263/600, Reward: 179.970, Step: 350 | |
| 2023-04-02 22:34:01 - r - INFO: - Episode: 264/600, Reward: -172.766, Step: 298 | |
| 2023-04-02 22:34:01 - r - INFO: - Episode: 265/600, Reward: -148.916, Step: 257 | |
| 2023-04-02 22:34:03 - r - INFO: - Episode: 266/600, Reward: -184.392, Step: 377 | |
| 2023-04-02 22:34:03 - r - INFO: - Episode: 267/600, Reward: -148.969, Step: 396 | |
| 2023-04-02 22:34:03 - r - INFO: - Episode: 268/600, Reward: -109.250, Step: 314 | |
| 2023-04-02 22:34:04 - r - INFO: - Episode: 269/600, Reward: 13.637, Step: 256 | |
| 2023-04-02 22:34:04 - r - INFO: - Episode: 270/600, Reward: 28.715, Step: 256 | |
| 2023-04-02 22:34:06 - r - INFO: - Episode: 271/600, Reward: -46.103, Step: 284 | |
| 2023-04-02 22:34:07 - r - INFO: - Episode: 272/600, Reward: 249.831, Step: 339 | |
| 2023-04-02 22:34:07 - r - INFO: - Episode: 273/600, Reward: -8.305, Step: 262 | |
| 2023-04-02 22:34:07 - r - INFO: - Episode: 274/600, Reward: 244.855, Step: 399 | |
| 2023-04-02 22:34:08 - r - INFO: - Episode: 275/600, Reward: -23.199, Step: 229 | |
| 2023-04-02 22:34:09 - r - INFO: - Episode: 276/600, Reward: -18.049, Step: 200 | |
| 2023-04-02 22:34:09 - r - INFO: - Episode: 277/600, Reward: -132.946, Step: 248 | |
| 2023-04-02 22:34:09 - r - INFO: - Episode: 278/600, Reward: -29.598, Step: 206 | |
| 2023-04-02 22:34:10 - r - INFO: - Episode: 279/600, Reward: -126.089, Step: 193 | |
| 2023-04-02 22:34:10 - r - INFO: - Episode: 280/600, Reward: -80.033, Step: 217 | |
| 2023-04-02 22:34:12 - r - INFO: - Episode: 281/600, Reward: -37.706, Step: 250 | |
| 2023-04-02 22:34:12 - r - INFO: - Episode: 282/600, Reward: -15.304, Step: 254 | |
| 2023-04-02 22:34:12 - r - INFO: - Episode: 283/600, Reward: -47.292, Step: 270 | |
| 2023-04-02 22:34:13 - r - INFO: - Episode: 284/600, Reward: 224.679, Step: 397 | |
| 2023-04-02 22:34:13 - r - INFO: - Episode: 285/600, Reward: 13.596, Step: 283 | |
| 2023-04-02 22:34:16 - r - INFO: - Episode: 286/600, Reward: 250.095, Step: 344 | |
| 2023-04-02 22:34:16 - r - INFO: - Episode: 287/600, Reward: 5.143, Step: 235 | |
| 2023-04-02 22:34:16 - r - INFO: - Episode: 288/600, Reward: -213.223, Step: 484 | |
| 2023-04-02 22:34:17 - r - INFO: - Episode: 289/600, Reward: -33.505, Step: 229 | |
| 2023-04-02 22:34:17 - r - INFO: - Episode: 290/600, Reward: 144.377, Step: 480 | |
| 2023-04-02 22:34:20 - r - INFO: - Current episode 290 has the best eval reward: 208.309 | |
| 2023-04-02 22:34:20 - r - INFO: - Episode: 291/600, Reward: 186.786, Step: 474 | |
| 2023-04-02 22:34:20 - r - INFO: - Episode: 292/600, Reward: -8.561, Step: 272 | |
| 2023-04-02 22:34:21 - r - INFO: - Episode: 293/600, Reward: -38.962, Step: 264 | |
| 2023-04-02 22:34:21 - r - INFO: - Episode: 294/600, Reward: 156.429, Step: 393 | |
| 2023-04-02 22:34:21 - r - INFO: - Episode: 295/600, Reward: -11.140, Step: 266 | |
| 2023-04-02 22:34:24 - r - INFO: - Episode: 296/600, Reward: 165.346, Step: 487 | |
| 2023-04-02 22:34:25 - r - INFO: - Episode: 297/600, Reward: 152.515, Step: 773 | |
| 2023-04-02 22:34:26 - r - INFO: - Episode: 298/600, Reward: 136.377, Step: 531 | |
| 2023-04-02 22:34:27 - r - INFO: - Episode: 299/600, Reward: 126.601, Step: 763 | |
| 2023-04-02 22:34:28 - r - INFO: - Episode: 300/600, Reward: 126.580, Step: 791 | |
| 2023-04-02 22:34:32 - r - INFO: - Episode: 301/600, Reward: 147.956, Step: 704 | |
| 2023-04-02 22:34:33 - r - INFO: - Episode: 302/600, Reward: 227.980, Step: 411 | |
| 2023-04-02 22:34:33 - r - INFO: - Episode: 303/600, Reward: 235.315, Step: 437 | |
| 2023-04-02 22:34:34 - r - INFO: - Episode: 304/600, Reward: 5.183, Step: 263 | |
| 2023-04-02 22:34:34 - r - INFO: - Episode: 305/600, Reward: 16.238, Step: 267 | |
| 2023-04-02 22:34:36 - r - INFO: - Episode: 306/600, Reward: -3.761, Step: 272 | |
| 2023-04-02 22:34:36 - r - INFO: - Episode: 307/600, Reward: 250.964, Step: 342 | |
| 2023-04-02 22:34:36 - r - INFO: - Episode: 308/600, Reward: 245.651, Step: 314 | |
| 2023-04-02 22:34:37 - r - INFO: - Episode: 309/600, Reward: 255.293, Step: 306 | |
| 2023-04-02 22:34:37 - r - INFO: - Episode: 310/600, Reward: -62.482, Step: 371 | |
| 2023-04-02 22:34:39 - r - INFO: - Episode: 311/600, Reward: -24.992, Step: 338 | |
| 2023-04-02 22:34:41 - r - INFO: - Episode: 312/600, Reward: -173.280, Step: 891 | |
| 2023-04-02 22:34:41 - r - INFO: - Episode: 313/600, Reward: -86.008, Step: 510 | |
| 2023-04-02 22:34:42 - r - INFO: - Episode: 314/600, Reward: 251.627, Step: 365 | |
| 2023-04-02 22:34:42 - r - INFO: - Episode: 315/600, Reward: 235.291, Step: 359 | |
| 2023-04-02 22:34:44 - r - INFO: - Current episode 315 has the best eval reward: 209.267 | |
| 2023-04-02 22:34:44 - r - INFO: - Episode: 316/600, Reward: 242.802, Step: 384 | |
| 2023-04-02 22:34:45 - r - INFO: - Episode: 317/600, Reward: 238.875, Step: 400 | |
| 2023-04-02 22:34:45 - r - INFO: - Episode: 318/600, Reward: 13.820, Step: 246 | |
| 2023-04-02 22:34:46 - r - INFO: - Episode: 319/600, Reward: 243.893, Step: 366 | |
| 2023-04-02 22:34:46 - r - INFO: - Episode: 320/600, Reward: 247.083, Step: 329 | |
| 2023-04-02 22:34:49 - r - INFO: - Episode: 321/600, Reward: 149.406, Step: 550 | |
| 2023-04-02 22:34:50 - r - INFO: - Episode: 322/600, Reward: 239.891, Step: 407 | |
| 2023-04-02 22:34:50 - r - INFO: - Episode: 323/600, Reward: 234.083, Step: 413 | |
| 2023-04-02 22:34:51 - r - INFO: - Episode: 324/600, Reward: 246.263, Step: 363 | |
| 2023-04-02 22:34:51 - r - INFO: - Episode: 325/600, Reward: 246.975, Step: 343 | |
| 2023-04-02 22:34:53 - r - INFO: - Current episode 325 has the best eval reward: 214.499 | |
| 2023-04-02 22:34:53 - r - INFO: - Episode: 326/600, Reward: 181.409, Step: 390 | |
| 2023-04-02 22:34:53 - r - INFO: - Episode: 327/600, Reward: 245.080, Step: 344 | |
| 2023-04-02 22:34:54 - r - INFO: - Episode: 328/600, Reward: 233.944, Step: 455 | |
| 2023-04-02 22:34:55 - r - INFO: - Episode: 329/600, Reward: 213.536, Step: 461 | |
| 2023-04-02 22:34:55 - r - INFO: - Episode: 330/600, Reward: 224.410, Step: 397 | |
| 2023-04-02 22:34:57 - r - INFO: - Episode: 331/600, Reward: 233.005, Step: 364 | |
| 2023-04-02 22:34:58 - r - INFO: - Episode: 332/600, Reward: 8.840, Step: 217 | |
| 2023-04-02 22:34:58 - r - INFO: - Episode: 333/600, Reward: -3.008, Step: 218 | |
| 2023-04-02 22:34:58 - r - INFO: - Episode: 334/600, Reward: 12.239, Step: 250 | |
| 2023-04-02 22:34:58 - r - INFO: - Episode: 335/600, Reward: 8.395, Step: 235 | |
| 2023-04-02 22:35:00 - r - INFO: - Episode: 336/600, Reward: 226.148, Step: 291 | |
| 2023-04-02 22:35:00 - r - INFO: - Episode: 337/600, Reward: 247.587, Step: 320 | |
| 2023-04-02 22:35:01 - r - INFO: - Episode: 338/600, Reward: 244.383, Step: 390 | |
| 2023-04-02 22:35:01 - r - INFO: - Episode: 339/600, Reward: 240.439, Step: 399 | |
| 2023-04-02 22:35:02 - r - INFO: - Episode: 340/600, Reward: 176.350, Step: 407 | |
| 2023-04-02 22:35:05 - r - INFO: - Episode: 341/600, Reward: -37.625, Step: 348 | |
| 2023-04-02 22:35:05 - r - INFO: - Episode: 342/600, Reward: 239.805, Step: 386 | |
| 2023-04-02 22:35:06 - r - INFO: - Episode: 343/600, Reward: 236.588, Step: 375 | |
| 2023-04-02 22:35:06 - r - INFO: - Episode: 344/600, Reward: 212.320, Step: 420 | |
| 2023-04-02 22:35:07 - r - INFO: - Episode: 345/600, Reward: 239.345, Step: 327 | |
| 2023-04-02 22:35:09 - r - INFO: - Episode: 346/600, Reward: 245.970, Step: 357 | |
| 2023-04-02 22:35:09 - r - INFO: - Episode: 347/600, Reward: 243.653, Step: 352 | |
| 2023-04-02 22:35:10 - r - INFO: - Episode: 348/600, Reward: 225.001, Step: 333 | |
| 2023-04-02 22:35:10 - r - INFO: - Episode: 349/600, Reward: 242.180, Step: 305 | |
| 2023-04-02 22:35:10 - r - INFO: - Episode: 350/600, Reward: 13.432, Step: 265 | |
| 2023-04-02 22:35:13 - r - INFO: - Episode: 351/600, Reward: 240.129, Step: 398 | |
| 2023-04-02 22:35:13 - r - INFO: - Episode: 352/600, Reward: -9.537, Step: 353 | |
| 2023-04-02 22:35:14 - r - INFO: - Episode: 353/600, Reward: 142.987, Step: 795 | |
| 2023-04-02 22:35:15 - r - INFO: - Episode: 354/600, Reward: 229.011, Step: 381 | |
| 2023-04-02 22:35:15 - r - INFO: - Episode: 355/600, Reward: 239.234, Step: 394 | |
| 2023-04-02 22:35:17 - r - INFO: - Current episode 355 has the best eval reward: 231.954 | |
| 2023-04-02 22:35:17 - r - INFO: - Episode: 356/600, Reward: 244.898, Step: 346 | |
| 2023-04-02 22:35:18 - r - INFO: - Episode: 357/600, Reward: 245.168, Step: 352 | |
| 2023-04-02 22:35:18 - r - INFO: - Episode: 358/600, Reward: 247.098, Step: 319 | |
| 2023-04-02 22:35:19 - r - INFO: - Episode: 359/600, Reward: 242.512, Step: 419 | |
| 2023-04-02 22:35:19 - r - INFO: - Episode: 360/600, Reward: 24.758, Step: 265 | |
| 2023-04-02 22:35:21 - r - INFO: - Episode: 361/600, Reward: 184.121, Step: 324 | |
| 2023-04-02 22:35:22 - r - INFO: - Episode: 362/600, Reward: 209.176, Step: 395 | |
| 2023-04-02 22:35:22 - r - INFO: - Episode: 363/600, Reward: -12.265, Step: 221 | |
| 2023-04-02 22:35:22 - r - INFO: - Episode: 364/600, Reward: 32.635, Step: 239 | |
| 2023-04-02 22:35:22 - r - INFO: - Episode: 365/600, Reward: 7.066, Step: 286 | |
| 2023-04-02 22:35:25 - r - INFO: - Episode: 366/600, Reward: -57.704, Step: 356 | |
| 2023-04-02 22:35:26 - r - INFO: - Episode: 367/600, Reward: 119.182, Step: 654 | |
| 2023-04-02 22:35:27 - r - INFO: - Episode: 368/600, Reward: 156.614, Step: 717 | |
| 2023-04-02 22:35:27 - r - INFO: - Episode: 369/600, Reward: 241.747, Step: 423 | |
| 2023-04-02 22:35:28 - r - INFO: - Episode: 370/600, Reward: 234.864, Step: 366 | |
| 2023-04-02 22:35:31 - r - INFO: - Episode: 371/600, Reward: 222.284, Step: 447 | |
| 2023-04-02 22:35:31 - r - INFO: - Episode: 372/600, Reward: -19.122, Step: 335 | |
| 2023-04-02 22:35:32 - r - INFO: - Episode: 373/600, Reward: 225.110, Step: 428 | |
| 2023-04-02 22:35:33 - r - INFO: - Episode: 374/600, Reward: 240.094, Step: 415 | |
| 2023-04-02 22:35:33 - r - INFO: - Episode: 375/600, Reward: 174.815, Step: 545 | |
| 2023-04-02 22:35:37 - r - INFO: - Episode: 376/600, Reward: 192.837, Step: 461 | |
| 2023-04-02 22:35:37 - r - INFO: - Episode: 377/600, Reward: 242.377, Step: 361 | |
| 2023-04-02 22:35:38 - r - INFO: - Episode: 378/600, Reward: 241.636, Step: 388 | |
| 2023-04-02 22:35:38 - r - INFO: - Episode: 379/600, Reward: -4.094, Step: 318 | |
| 2023-04-02 22:35:39 - r - INFO: - Episode: 380/600, Reward: 224.748, Step: 349 | |
| 2023-04-02 22:35:42 - r - INFO: - Episode: 381/600, Reward: 237.187, Step: 367 | |
| 2023-04-02 22:35:42 - r - INFO: - Episode: 382/600, Reward: 241.407, Step: 397 | |
| 2023-04-02 22:35:43 - r - INFO: - Episode: 383/600, Reward: 239.651, Step: 367 | |
| 2023-04-02 22:35:43 - r - INFO: - Episode: 384/600, Reward: 241.749, Step: 362 | |
| 2023-04-02 22:35:44 - r - INFO: - Episode: 385/600, Reward: 191.455, Step: 415 | |
| 2023-04-02 22:35:47 - r - INFO: - Episode: 386/600, Reward: -17.334, Step: 312 | |
| 2023-04-02 22:35:47 - r - INFO: - Episode: 387/600, Reward: 252.577, Step: 356 | |
| 2023-04-02 22:35:47 - r - INFO: - Episode: 388/600, Reward: 251.911, Step: 314 | |
| 2023-04-02 22:35:48 - r - INFO: - Episode: 389/600, Reward: 252.396, Step: 341 | |
| 2023-04-02 22:35:48 - r - INFO: - Episode: 390/600, Reward: 248.863, Step: 311 | |
| 2023-04-02 22:35:51 - r - INFO: - Episode: 391/600, Reward: 202.274, Step: 395 | |
| 2023-04-02 22:35:51 - r - INFO: - Episode: 392/600, Reward: 241.861, Step: 318 | |
| 2023-04-02 22:35:52 - r - INFO: - Episode: 393/600, Reward: 255.668, Step: 322 | |
| 2023-04-02 22:35:52 - r - INFO: - Episode: 394/600, Reward: 248.078, Step: 298 | |
| 2023-04-02 22:35:52 - r - INFO: - Episode: 395/600, Reward: 255.693, Step: 296 | |
| 2023-04-02 22:35:54 - r - INFO: - Current episode 395 has the best eval reward: 252.299 | |
| 2023-04-02 22:35:54 - r - INFO: - Episode: 396/600, Reward: 253.226, Step: 318 | |
| 2023-04-02 22:35:55 - r - INFO: - Episode: 397/600, Reward: 236.214, Step: 491 | |
| 2023-04-02 22:35:55 - r - INFO: - Episode: 398/600, Reward: 244.976, Step: 324 | |
| 2023-04-02 22:35:55 - r - INFO: - Episode: 399/600, Reward: 249.893, Step: 301 | |
| 2023-04-02 22:35:56 - r - INFO: - Episode: 400/600, Reward: 242.053, Step: 348 | |
| 2023-04-02 22:35:58 - r - INFO: - Episode: 401/600, Reward: 237.409, Step: 340 | |
| 2023-04-02 22:35:59 - r - INFO: - Episode: 402/600, Reward: 248.976, Step: 322 | |
| 2023-04-02 22:35:59 - r - INFO: - Episode: 403/600, Reward: 240.694, Step: 333 | |
| 2023-04-02 22:36:00 - r - INFO: - Episode: 404/600, Reward: 236.968, Step: 380 | |
| 2023-04-02 22:36:00 - r - INFO: - Episode: 405/600, Reward: 225.875, Step: 320 | |
| 2023-04-02 22:36:03 - r - INFO: - Episode: 406/600, Reward: 220.762, Step: 735 | |
| 2023-04-02 22:36:03 - r - INFO: - Episode: 407/600, Reward: 234.115, Step: 497 | |
| 2023-04-02 22:36:04 - r - INFO: - Episode: 408/600, Reward: 228.883, Step: 397 | |
| 2023-04-02 22:36:05 - r - INFO: - Episode: 409/600, Reward: 237.333, Step: 386 | |
| 2023-04-02 22:36:05 - r - INFO: - Episode: 410/600, Reward: 235.915, Step: 354 | |
| 2023-04-02 22:36:07 - r - INFO: - Episode: 411/600, Reward: 238.182, Step: 343 | |
| 2023-04-02 22:36:08 - r - INFO: - Episode: 412/600, Reward: 157.924, Step: 518 | |
| 2023-04-02 22:36:08 - r - INFO: - Episode: 413/600, Reward: 15.345, Step: 270 | |
| 2023-04-02 22:36:08 - r - INFO: - Episode: 414/600, Reward: 242.835, Step: 304 | |
| 2023-04-02 22:36:09 - r - INFO: - Episode: 415/600, Reward: 10.263, Step: 241 | |
| 2023-04-02 22:36:11 - r - INFO: - Episode: 416/600, Reward: 240.273, Step: 301 | |
| 2023-04-02 22:36:11 - r - INFO: - Episode: 417/600, Reward: 247.024, Step: 301 | |
| 2023-04-02 22:36:12 - r - INFO: - Episode: 418/600, Reward: 248.339, Step: 308 | |
| 2023-04-02 22:36:12 - r - INFO: - Episode: 419/600, Reward: 250.754, Step: 294 | |
| 2023-04-02 22:36:12 - r - INFO: - Episode: 420/600, Reward: 260.319, Step: 272 | |
| 2023-04-02 22:36:14 - r - INFO: - Episode: 421/600, Reward: 258.923, Step: 269 | |
| 2023-04-02 22:36:14 - r - INFO: - Episode: 422/600, Reward: 10.691, Step: 229 | |
| 2023-04-02 22:36:15 - r - INFO: - Episode: 423/600, Reward: 248.147, Step: 263 | |
| 2023-04-02 22:36:15 - r - INFO: - Episode: 424/600, Reward: 251.983, Step: 295 | |
| 2023-04-02 22:36:15 - r - INFO: - Episode: 425/600, Reward: 258.080, Step: 284 | |
| 2023-04-02 22:36:17 - r - INFO: - Episode: 426/600, Reward: 259.407, Step: 268 | |
| 2023-04-02 22:36:17 - r - INFO: - Episode: 427/600, Reward: 47.025, Step: 219 | |
| 2023-04-02 22:36:18 - r - INFO: - Episode: 428/600, Reward: 260.112, Step: 249 | |
| 2023-04-02 22:36:18 - r - INFO: - Episode: 429/600, Reward: 262.850, Step: 272 | |
| 2023-04-02 22:36:18 - r - INFO: - Episode: 430/600, Reward: 258.350, Step: 275 | |
| 2023-04-02 22:36:20 - r - INFO: - Episode: 431/600, Reward: 16.468, Step: 245 | |
| 2023-04-02 22:36:20 - r - INFO: - Episode: 432/600, Reward: 234.909, Step: 275 | |
| 2023-04-02 22:36:20 - r - INFO: - Episode: 433/600, Reward: 223.706, Step: 297 | |
| 2023-04-02 22:36:21 - r - INFO: - Episode: 434/600, Reward: 247.155, Step: 293 | |
| 2023-04-02 22:36:21 - r - INFO: - Episode: 435/600, Reward: 249.757, Step: 288 | |
| 2023-04-02 22:36:23 - r - INFO: - Episode: 436/600, Reward: 239.382, Step: 282 | |
| 2023-04-02 22:36:23 - r - INFO: - Episode: 437/600, Reward: 262.216, Step: 261 | |
| 2023-04-02 22:36:23 - r - INFO: - Episode: 438/600, Reward: 260.980, Step: 280 | |
| 2023-04-02 22:36:24 - r - INFO: - Episode: 439/600, Reward: 262.113, Step: 282 | |
| 2023-04-02 22:36:24 - r - INFO: - Episode: 440/600, Reward: 259.490, Step: 264 | |
| 2023-04-02 22:36:25 - r - INFO: - Episode: 441/600, Reward: 257.432, Step: 297 | |
| 2023-04-02 22:36:26 - r - INFO: - Episode: 442/600, Reward: 264.151, Step: 263 | |
| 2023-04-02 22:36:26 - r - INFO: - Episode: 443/600, Reward: 193.695, Step: 415 | |
| 2023-04-02 22:36:26 - r - INFO: - Episode: 444/600, Reward: 264.278, Step: 240 | |
| 2023-04-02 22:36:27 - r - INFO: - Episode: 445/600, Reward: 262.986, Step: 250 | |
| 2023-04-02 22:36:28 - r - INFO: - Episode: 446/600, Reward: 261.351, Step: 238 | |
| 2023-04-02 22:36:28 - r - INFO: - Episode: 447/600, Reward: 45.025, Step: 219 | |
| 2023-04-02 22:36:29 - r - INFO: - Episode: 448/600, Reward: 261.015, Step: 267 | |
| 2023-04-02 22:36:29 - r - INFO: - Episode: 449/600, Reward: 263.976, Step: 263 | |
| 2023-04-02 22:36:29 - r - INFO: - Episode: 450/600, Reward: 243.877, Step: 296 | |
| 2023-04-02 22:36:31 - r - INFO: - Episode: 451/600, Reward: 260.750, Step: 273 | |
| 2023-04-02 22:36:31 - r - INFO: - Episode: 452/600, Reward: 256.636, Step: 258 | |
| 2023-04-02 22:36:31 - r - INFO: - Episode: 453/600, Reward: 256.439, Step: 254 | |
| 2023-04-02 22:36:32 - r - INFO: - Episode: 454/600, Reward: 265.349, Step: 255 | |
| 2023-04-02 22:36:32 - r - INFO: - Episode: 455/600, Reward: 264.665, Step: 266 | |
| 2023-04-02 22:36:33 - r - INFO: - Episode: 456/600, Reward: 253.014, Step: 253 | |
| 2023-04-02 22:36:33 - r - INFO: - Episode: 457/600, Reward: 32.262, Step: 194 | |
| 2023-04-02 22:36:34 - r - INFO: - Episode: 458/600, Reward: 264.128, Step: 232 | |
| 2023-04-02 22:36:34 - r - INFO: - Episode: 459/600, Reward: 265.752, Step: 255 | |
| 2023-04-02 22:36:34 - r - INFO: - Episode: 460/600, Reward: 263.110, Step: 237 | |
| 2023-04-02 22:36:35 - r - INFO: - Current episode 460 has the best eval reward: 266.538 | |
| 2023-04-02 22:36:35 - r - INFO: - Episode: 461/600, Reward: 30.295, Step: 162 | |
| 2023-04-02 22:36:35 - r - INFO: - Episode: 462/600, Reward: 271.226, Step: 214 | |
| 2023-04-02 22:36:36 - r - INFO: - Episode: 463/600, Reward: 13.384, Step: 181 | |
| 2023-04-02 22:36:36 - r - INFO: - Episode: 464/600, Reward: 174.842, Step: 395 | |
| 2023-04-02 22:36:36 - r - INFO: - Episode: 465/600, Reward: 1.168, Step: 187 | |
| 2023-04-02 22:36:37 - r - INFO: - Episode: 466/600, Reward: 13.686, Step: 206 | |
| 2023-04-02 22:36:38 - r - INFO: - Episode: 467/600, Reward: 257.603, Step: 271 | |
| 2023-04-02 22:36:38 - r - INFO: - Episode: 468/600, Reward: -6.680, Step: 203 | |
| 2023-04-02 22:36:38 - r - INFO: - Episode: 469/600, Reward: -28.242, Step: 229 | |
| 2023-04-02 22:36:39 - r - INFO: - Episode: 470/600, Reward: -25.970, Step: 237 | |
| 2023-04-02 22:36:40 - r - INFO: - Episode: 471/600, Reward: 196.133, Step: 301 | |
| 2023-04-02 22:36:40 - r - INFO: - Episode: 472/600, Reward: 206.873, Step: 298 | |
| 2023-04-02 22:36:40 - r - INFO: - Episode: 473/600, Reward: 11.522, Step: 197 | |
| 2023-04-02 22:36:41 - r - INFO: - Episode: 474/600, Reward: 0.357, Step: 201 | |
| 2023-04-02 22:36:41 - r - INFO: - Episode: 475/600, Reward: 195.312, Step: 344 | |
| 2023-04-02 22:36:42 - r - INFO: - Episode: 476/600, Reward: -54.742, Step: 194 | |
| 2023-04-02 22:36:42 - r - INFO: - Episode: 477/600, Reward: 4.921, Step: 173 | |
| 2023-04-02 22:36:43 - r - INFO: - Episode: 478/600, Reward: 196.359, Step: 253 | |
| 2023-04-02 22:36:43 - r - INFO: - Episode: 479/600, Reward: 175.233, Step: 287 | |
| 2023-04-02 22:36:43 - r - INFO: - Episode: 480/600, Reward: 178.848, Step: 287 | |
| 2023-04-02 22:36:44 - r - INFO: - Episode: 481/600, Reward: -48.507, Step: 179 | |
| 2023-04-02 22:36:44 - r - INFO: - Episode: 482/600, Reward: 6.498, Step: 174 | |
| 2023-04-02 22:36:44 - r - INFO: - Episode: 483/600, Reward: 261.715, Step: 216 | |
| 2023-04-02 22:36:45 - r - INFO: - Episode: 484/600, Reward: 203.306, Step: 366 | |
| 2023-04-02 22:36:45 - r - INFO: - Episode: 485/600, Reward: 261.610, Step: 212 | |
| 2023-04-02 22:36:46 - r - INFO: - Episode: 486/600, Reward: -60.526, Step: 200 | |
| 2023-04-02 22:36:47 - r - INFO: - Episode: 487/600, Reward: -50.410, Step: 246 | |
| 2023-04-02 22:36:47 - r - INFO: - Episode: 488/600, Reward: 262.397, Step: 274 | |
| 2023-04-02 22:36:47 - r - INFO: - Episode: 489/600, Reward: 257.958, Step: 265 | |
| 2023-04-02 22:36:48 - r - INFO: - Episode: 490/600, Reward: 259.685, Step: 293 | |
| 2023-04-02 22:36:49 - r - INFO: - Episode: 491/600, Reward: 259.445, Step: 242 | |
| 2023-04-02 22:36:50 - r - INFO: - Episode: 492/600, Reward: 246.089, Step: 326 | |
| 2023-04-02 22:36:50 - r - INFO: - Episode: 493/600, Reward: 250.200, Step: 372 | |
| 2023-04-02 22:36:51 - r - INFO: - Episode: 494/600, Reward: 162.818, Step: 496 | |
| 2023-04-02 22:36:51 - r - INFO: - Episode: 495/600, Reward: 253.942, Step: 298 | |
| 2023-04-02 22:36:53 - r - INFO: - Episode: 496/600, Reward: 258.923, Step: 255 | |
| 2023-04-02 22:36:54 - r - INFO: - Episode: 497/600, Reward: 260.284, Step: 265 | |
| 2023-04-02 22:36:54 - r - INFO: - Episode: 498/600, Reward: 251.429, Step: 285 | |
| 2023-04-02 22:36:54 - r - INFO: - Episode: 499/600, Reward: 263.885, Step: 257 | |
| 2023-04-02 22:36:54 - r - INFO: - Episode: 500/600, Reward: 260.733, Step: 234 | |
| 2023-04-02 22:36:56 - r - INFO: - Episode: 501/600, Reward: 249.684, Step: 235 | |
| 2023-04-02 22:36:56 - r - INFO: - Episode: 502/600, Reward: 260.315, Step: 234 | |
| 2023-04-02 22:36:56 - r - INFO: - Episode: 503/600, Reward: -11.048, Step: 214 | |
| 2023-04-02 22:36:57 - r - INFO: - Episode: 504/600, Reward: 258.626, Step: 241 | |
| 2023-04-02 22:36:57 - r - INFO: - Episode: 505/600, Reward: 15.664, Step: 219 | |
| 2023-04-02 22:36:59 - r - INFO: - Episode: 506/600, Reward: 258.389, Step: 295 | |
| 2023-04-02 22:36:59 - r - INFO: - Episode: 507/600, Reward: -186.030, Step: 412 | |
| 2023-04-02 22:37:00 - r - INFO: - Episode: 508/600, Reward: 188.378, Step: 480 | |
| 2023-04-02 22:37:00 - r - INFO: - Episode: 509/600, Reward: 256.534, Step: 294 | |
| 2023-04-02 22:37:02 - r - INFO: - Episode: 510/600, Reward: 187.044, Step: 922 | |
| 2023-04-02 22:37:09 - r - INFO: - Episode: 511/600, Reward: 263.852, Step: 232 | |
| 2023-04-02 22:37:09 - r - INFO: - Episode: 512/600, Reward: 248.015, Step: 241 | |
| 2023-04-02 22:37:10 - r - INFO: - Episode: 513/600, Reward: 249.355, Step: 227 | |
| 2023-04-02 22:37:10 - r - INFO: - Episode: 514/600, Reward: -22.340, Step: 176 | |
| 2023-04-02 22:37:11 - r - INFO: - Episode: 515/600, Reward: -5.522, Step: 1000 | |
| 2023-04-02 22:37:14 - r - INFO: - Episode: 516/600, Reward: -115.527, Step: 583 | |
| 2023-04-02 22:37:14 - r - INFO: - Episode: 517/600, Reward: 14.921, Step: 173 | |
| 2023-04-02 22:37:16 - r - INFO: - Episode: 518/600, Reward: -75.088, Step: 1000 | |
| 2023-04-02 22:37:16 - r - INFO: - Episode: 519/600, Reward: 243.402, Step: 322 | |
| 2023-04-02 22:37:18 - r - INFO: - Episode: 520/600, Reward: -92.877, Step: 1000 | |
| 2023-04-02 22:37:26 - r - INFO: - Episode: 521/600, Reward: -48.260, Step: 438 | |
| 2023-04-02 22:37:27 - r - INFO: - Episode: 522/600, Reward: 137.752, Step: 554 | |
| 2023-04-02 22:37:28 - r - INFO: - Episode: 523/600, Reward: -52.636, Step: 1000 | |
| 2023-04-02 22:37:30 - r - INFO: - Episode: 524/600, Reward: -85.157, Step: 1000 | |
| 2023-04-02 22:37:30 - r - INFO: - Episode: 525/600, Reward: -143.406, Step: 270 | |
| 2023-04-02 22:37:38 - r - INFO: - Episode: 526/600, Reward: -125.846, Step: 291 | |
| 2023-04-02 22:37:38 - r - INFO: - Episode: 527/600, Reward: -116.227, Step: 272 | |
| 2023-04-02 22:37:39 - r - INFO: - Episode: 528/600, Reward: -32.613, Step: 1000 | |
| 2023-04-02 22:37:40 - r - INFO: - Episode: 529/600, Reward: -26.567, Step: 216 | |
| 2023-04-02 22:37:40 - r - INFO: - Episode: 530/600, Reward: 219.599, Step: 645 | |
| 2023-04-02 22:37:46 - r - INFO: - Episode: 531/600, Reward: 244.029, Step: 498 | |
| 2023-04-02 22:37:46 - r - INFO: - Episode: 532/600, Reward: 255.433, Step: 257 | |
| 2023-04-02 22:37:46 - r - INFO: - Episode: 533/600, Reward: 254.793, Step: 323 | |
| 2023-04-02 22:37:47 - r - INFO: - Episode: 534/600, Reward: 256.517, Step: 268 | |
| 2023-04-02 22:37:47 - r - INFO: - Episode: 535/600, Reward: 260.777, Step: 257 | |
| 2023-04-02 22:37:49 - r - INFO: - Episode: 536/600, Reward: 236.733, Step: 304 | |
| 2023-04-02 22:37:51 - r - INFO: - Episode: 537/600, Reward: -73.740, Step: 1000 | |
| 2023-04-02 22:37:52 - r - INFO: - Episode: 538/600, Reward: -57.553, Step: 1000 | |
| 2023-04-02 22:37:54 - r - INFO: - Episode: 539/600, Reward: -77.619, Step: 1000 | |
| 2023-04-02 22:37:56 - r - INFO: - Episode: 540/600, Reward: -87.691, Step: 1000 | |
| 2023-04-02 22:37:58 - r - INFO: - Episode: 541/600, Reward: 104.132, Step: 812 | |
| 2023-04-02 22:37:59 - r - INFO: - Episode: 542/600, Reward: 256.767, Step: 275 | |
| 2023-04-02 22:37:59 - r - INFO: - Episode: 543/600, Reward: 8.147, Step: 232 | |
| 2023-04-02 22:38:00 - r - INFO: - Episode: 544/600, Reward: 155.294, Step: 615 | |
| 2023-04-02 22:38:00 - r - INFO: - Episode: 545/600, Reward: 229.551, Step: 337 | |
| 2023-04-02 22:38:04 - r - INFO: - Episode: 546/600, Reward: 156.560, Step: 466 | |
| 2023-04-02 22:38:04 - r - INFO: - Episode: 547/600, Reward: 238.245, Step: 243 | |
| 2023-04-02 22:38:04 - r - INFO: - Episode: 548/600, Reward: 248.843, Step: 274 | |
| 2023-04-02 22:38:05 - r - INFO: - Episode: 549/600, Reward: 254.527, Step: 251 | |
| 2023-04-02 22:38:05 - r - INFO: - Episode: 550/600, Reward: 267.225, Step: 228 | |
| 2023-04-02 22:38:06 - r - INFO: - Episode: 551/600, Reward: 264.262, Step: 265 | |
| 2023-04-02 22:38:06 - r - INFO: - Episode: 552/600, Reward: 243.735, Step: 269 | |
| 2023-04-02 22:38:07 - r - INFO: - Episode: 553/600, Reward: 42.273, Step: 165 | |
| 2023-04-02 22:38:07 - r - INFO: - Episode: 554/600, Reward: 248.316, Step: 246 | |
| 2023-04-02 22:38:07 - r - INFO: - Episode: 555/600, Reward: 40.931, Step: 173 | |
| 2023-04-02 22:38:08 - r - INFO: - Episode: 556/600, Reward: 16.317, Step: 161 | |
| 2023-04-02 22:38:08 - r - INFO: - Episode: 557/600, Reward: 46.279, Step: 171 | |
| 2023-04-02 22:38:08 - r - INFO: - Episode: 558/600, Reward: 258.548, Step: 245 | |
| 2023-04-02 22:38:08 - r - INFO: - Episode: 559/600, Reward: 256.210, Step: 227 | |
| 2023-04-02 22:38:09 - r - INFO: - Episode: 560/600, Reward: 24.411, Step: 159 | |
| 2023-04-02 22:38:09 - r - INFO: - Episode: 561/600, Reward: 269.466, Step: 204 | |
| 2023-04-02 22:38:10 - r - INFO: - Episode: 562/600, Reward: 45.629, Step: 165 | |
| 2023-04-02 22:38:10 - r - INFO: - Episode: 563/600, Reward: 267.713, Step: 215 | |
| 2023-04-02 22:38:10 - r - INFO: - Episode: 564/600, Reward: 261.260, Step: 254 | |
| 2023-04-02 22:38:10 - r - INFO: - Episode: 565/600, Reward: 28.404, Step: 152 | |
| 2023-04-02 22:38:11 - r - INFO: - Episode: 566/600, Reward: 29.313, Step: 149 | |
| 2023-04-02 22:38:12 - r - INFO: - Episode: 567/600, Reward: 261.192, Step: 504 | |
| 2023-04-02 22:38:12 - r - INFO: - Episode: 568/600, Reward: 258.287, Step: 217 | |
| 2023-04-02 22:38:12 - r - INFO: - Episode: 569/600, Reward: 269.920, Step: 240 | |
| 2023-04-02 22:38:12 - r - INFO: - Episode: 570/600, Reward: 37.344, Step: 167 | |
| 2023-04-02 22:38:14 - r - INFO: - Episode: 571/600, Reward: 268.270, Step: 244 | |
| 2023-04-02 22:38:14 - r - INFO: - Episode: 572/600, Reward: 264.803, Step: 274 | |
| 2023-04-02 22:38:14 - r - INFO: - Episode: 573/600, Reward: 270.073, Step: 223 | |
| 2023-04-02 22:38:14 - r - INFO: - Episode: 574/600, Reward: 270.384, Step: 237 | |
| 2023-04-02 22:38:15 - r - INFO: - Episode: 575/600, Reward: 259.619, Step: 250 | |
| 2023-04-02 22:38:16 - r - INFO: - Episode: 576/600, Reward: 270.013, Step: 213 | |
| 2023-04-02 22:38:16 - r - INFO: - Episode: 577/600, Reward: -2.147, Step: 160 | |
| 2023-04-02 22:38:17 - r - INFO: - Episode: 578/600, Reward: 243.889, Step: 229 | |
| 2023-04-02 22:38:17 - r - INFO: - Episode: 579/600, Reward: 202.207, Step: 488 | |
| 2023-04-02 22:38:18 - r - INFO: - Episode: 580/600, Reward: 269.916, Step: 281 | |
| 2023-04-02 22:38:20 - r - INFO: - Episode: 581/600, Reward: 241.754, Step: 263 | |
| 2023-04-02 22:38:20 - r - INFO: - Episode: 582/600, Reward: 250.112, Step: 209 | |
| 2023-04-02 22:38:20 - r - INFO: - Episode: 583/600, Reward: 251.388, Step: 324 | |
| 2023-04-02 22:38:21 - r - INFO: - Episode: 584/600, Reward: 234.244, Step: 368 | |
| 2023-04-02 22:38:21 - r - INFO: - Episode: 585/600, Reward: 252.416, Step: 245 | |
| 2023-04-02 22:38:22 - r - INFO: - Episode: 586/600, Reward: 237.838, Step: 311 | |
| 2023-04-02 22:38:23 - r - INFO: - Episode: 587/600, Reward: 266.629, Step: 270 | |
| 2023-04-02 22:38:23 - r - INFO: - Episode: 588/600, Reward: 240.826, Step: 256 | |
| 2023-04-02 22:38:23 - r - INFO: - Episode: 589/600, Reward: 236.912, Step: 239 | |
| 2023-04-02 22:38:23 - r - INFO: - Episode: 590/600, Reward: 32.451, Step: 216 | |
| 2023-04-02 22:38:25 - r - INFO: - Episode: 591/600, Reward: 259.219, Step: 247 | |
| 2023-04-02 22:38:25 - r - INFO: - Episode: 592/600, Reward: 248.622, Step: 226 | |
| 2023-04-02 22:38:25 - r - INFO: - Episode: 593/600, Reward: 267.273, Step: 219 | |
| 2023-04-02 22:38:26 - r - INFO: - Episode: 594/600, Reward: 268.889, Step: 225 | |
| 2023-04-02 22:38:26 - r - INFO: - Episode: 595/600, Reward: -9.316, Step: 223 | |
| 2023-04-02 22:38:27 - r - INFO: - Episode: 596/600, Reward: 267.592, Step: 233 | |
| 2023-04-02 22:38:28 - r - INFO: - Episode: 597/600, Reward: 253.772, Step: 287 | |
| 2023-04-02 22:38:28 - r - INFO: - Episode: 598/600, Reward: 270.646, Step: 280 | |
| 2023-04-02 22:38:28 - r - INFO: - Episode: 599/600, Reward: -12.607, Step: 218 | |
| 2023-04-02 22:38:28 - r - INFO: - Episode: 600/600, Reward: -33.086, Step: 172 | |
| 2023-04-02 22:38:29 - r - INFO: - Finish training! | |