| 2023-04-08 18:36:52 - r - INFO: - Hyperparameters: | |
| 2023-04-08 18:36:52 - r - INFO: - ================================================================================ | |
| 2023-04-08 18:36:52 - r - INFO: - Name Value Type | |
| 2023-04-08 18:36:52 - r - INFO: - env_name CartPole-v1 <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - new_step_api 1 <class 'bool'> | |
| 2023-04-08 18:36:52 - r - INFO: - wrapper None <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - render 0 <class 'bool'> | |
| 2023-04-08 18:36:52 - r - INFO: - algo_name CQL <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - mode train <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - seed 1 <class 'int'> | |
| 2023-04-08 18:36:52 - r - INFO: - device cpu <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - train_eps 300 <class 'int'> | |
| 2023-04-08 18:36:52 - r - INFO: - test_eps 20 <class 'int'> | |
| 2023-04-08 18:36:52 - r - INFO: - eval_eps 10 <class 'int'> | |
| 2023-04-08 18:36:52 - r - INFO: - eval_per_episode 5 <class 'int'> | |
| 2023-04-08 18:36:52 - r - INFO: - max_steps 200 <class 'int'> | |
| 2023-04-08 18:36:52 - r - INFO: - load_checkpoint 0 <class 'bool'> | |
| 2023-04-08 18:36:52 - r - INFO: - load_path tasks <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - show_fig 1 <class 'bool'> | |
| 2023-04-08 18:36:52 - r - INFO: - save_fig 1 <class 'bool'> | |
| 2023-04-08 18:36:52 - r - INFO: - epsilon_start 0.95 <class 'float'> | |
| 2023-04-08 18:36:52 - r - INFO: - epsilon_end 0.01 <class 'float'> | |
| 2023-04-08 18:36:52 - r - INFO: - epsilon_decay 500 <class 'int'> | |
| 2023-04-08 18:36:52 - r - INFO: - gamma 0.99 <class 'float'> | |
| 2023-04-08 18:36:52 - r - INFO: - tau 0.001 <class 'float'> | |
| 2023-04-08 18:36:52 - r - INFO: - lr 0.001 <class 'float'> | |
| 2023-04-08 18:36:52 - r - INFO: - buffer_size 100000 <class 'int'> | |
| 2023-04-08 18:36:52 - r - INFO: - batch_size 64 <class 'int'> | |
| 2023-04-08 18:36:52 - r - INFO: - target_update 4 <class 'int'> | |
| 2023-04-08 18:36:52 - r - INFO: - value_layers [{'layer_type': 'linear', 'layer_dim': ['n_states', 256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_dim': [256, 256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_dim': [256, 'n_actions'], 'activation': 'none'}] <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - task_dir D:\MyDoc\joyrl\rl-tutorials-master-newest\rl-tutorials-master\joyrl/tasks/Train_CartPole-v1_CQL_20230408-183652 <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - model_dir D:\MyDoc\joyrl\rl-tutorials-master-newest\rl-tutorials-master\joyrl/tasks/Train_CartPole-v1_CQL_20230408-183652/models <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - res_dir D:\MyDoc\joyrl\rl-tutorials-master-newest\rl-tutorials-master\joyrl/tasks/Train_CartPole-v1_CQL_20230408-183652/results <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - log_dir D:\MyDoc\joyrl\rl-tutorials-master-newest\rl-tutorials-master\joyrl/tasks/Train_CartPole-v1_CQL_20230408-183652/logs <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - traj_dir D:\MyDoc\joyrl\rl-tutorials-master-newest\rl-tutorials-master\joyrl/tasks/Train_CartPole-v1_CQL_20230408-183652/traj <class 'str'> | |
| 2023-04-08 18:36:52 - r - INFO: - ================================================================================ | |
| 2023-04-08 18:36:52 - r - INFO: - n_states: 4, n_actions: 2 | |
| 2023-04-08 18:36:52 - r - INFO: - Start training! | |
| 2023-04-08 18:36:52 - r - INFO: - Env: CartPole-v1, Algorithm: CQL, Device: cpu | |
| 2023-04-08 18:36:52 - r - INFO: - Episode: 1/300, Reward: 18.000, Step: 18 | |
| 2023-04-08 18:36:52 - r - INFO: - Episode: 2/300, Reward: 28.000, Step: 28 | |
| 2023-04-08 18:36:52 - r - INFO: - Episode: 3/300, Reward: 15.000, Step: 15 | |
| 2023-04-08 18:36:52 - r - INFO: - Episode: 4/300, Reward: 15.000, Step: 15 | |
| 2023-04-08 18:36:52 - r - INFO: - Episode: 5/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:36:52 - r - INFO: - Current episode 5 has the best eval reward: 10.000 | |
| 2023-04-08 18:36:52 - r - INFO: - Episode: 6/300, Reward: 35.000, Step: 35 | |
| 2023-04-08 18:36:52 - r - INFO: - Episode: 7/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:36:53 - r - INFO: - Episode: 8/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:36:53 - r - INFO: - Episode: 9/300, Reward: 17.000, Step: 17 | |
| 2023-04-08 18:36:53 - r - INFO: - Episode: 10/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:36:53 - r - INFO: - Episode: 11/300, Reward: 13.000, Step: 13 | |
| 2023-04-08 18:36:53 - r - INFO: - Episode: 12/300, Reward: 22.000, Step: 22 | |
| 2023-04-08 18:36:53 - r - INFO: - Episode: 13/300, Reward: 29.000, Step: 29 | |
| 2023-04-08 18:36:53 - r - INFO: - Episode: 14/300, Reward: 25.000, Step: 25 | |
| 2023-04-08 18:36:53 - r - INFO: - Episode: 15/300, Reward: 16.000, Step: 16 | |
| 2023-04-08 18:36:54 - r - INFO: - Episode: 16/300, Reward: 25.000, Step: 25 | |
| 2023-04-08 18:36:54 - r - INFO: - Episode: 17/300, Reward: 19.000, Step: 19 | |
| 2023-04-08 18:36:54 - r - INFO: - Episode: 18/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:36:54 - r - INFO: - Episode: 19/300, Reward: 28.000, Step: 28 | |
| 2023-04-08 18:36:54 - r - INFO: - Episode: 20/300, Reward: 22.000, Step: 22 | |
| 2023-04-08 18:36:54 - r - INFO: - Current episode 20 has the best eval reward: 10.000 | |
| 2023-04-08 18:36:54 - r - INFO: - Episode: 21/300, Reward: 18.000, Step: 18 | |
| 2023-04-08 18:36:54 - r - INFO: - Episode: 22/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:36:54 - r - INFO: - Episode: 23/300, Reward: 21.000, Step: 21 | |
| 2023-04-08 18:36:54 - r - INFO: - Episode: 24/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:36:54 - r - INFO: - Episode: 25/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:36:54 - r - INFO: - Current episode 25 has the best eval reward: 10.000 | |
| 2023-04-08 18:36:55 - r - INFO: - Episode: 26/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:36:55 - r - INFO: - Episode: 27/300, Reward: 17.000, Step: 17 | |
| 2023-04-08 18:36:55 - r - INFO: - Episode: 28/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:36:55 - r - INFO: - Episode: 29/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:36:55 - r - INFO: - Episode: 30/300, Reward: 14.000, Step: 14 | |
| 2023-04-08 18:36:55 - r - INFO: - Episode: 31/300, Reward: 28.000, Step: 28 | |
| 2023-04-08 18:36:55 - r - INFO: - Episode: 32/300, Reward: 15.000, Step: 15 | |
| 2023-04-08 18:36:55 - r - INFO: - Episode: 33/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:36:55 - r - INFO: - Episode: 34/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:36:56 - r - INFO: - Episode: 35/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:36:56 - r - INFO: - Episode: 36/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:36:56 - r - INFO: - Episode: 37/300, Reward: 16.000, Step: 16 | |
| 2023-04-08 18:36:56 - r - INFO: - Episode: 38/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:36:56 - r - INFO: - Episode: 39/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:36:56 - r - INFO: - Episode: 40/300, Reward: 30.000, Step: 30 | |
| 2023-04-08 18:36:56 - r - INFO: - Current episode 40 has the best eval reward: 10.000 | |
| 2023-04-08 18:36:56 - r - INFO: - Episode: 41/300, Reward: 15.000, Step: 15 | |
| 2023-04-08 18:36:56 - r - INFO: - Episode: 42/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:36:56 - r - INFO: - Episode: 43/300, Reward: 33.000, Step: 33 | |
| 2023-04-08 18:36:56 - r - INFO: - Episode: 44/300, Reward: 18.000, Step: 18 | |
| 2023-04-08 18:36:57 - r - INFO: - Episode: 45/300, Reward: 13.000, Step: 13 | |
| 2023-04-08 18:36:57 - r - INFO: - Current episode 45 has the best eval reward: 10.000 | |
| 2023-04-08 18:36:57 - r - INFO: - Episode: 46/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:36:57 - r - INFO: - Episode: 47/300, Reward: 26.000, Step: 26 | |
| 2023-04-08 18:36:57 - r - INFO: - Episode: 48/300, Reward: 15.000, Step: 15 | |
| 2023-04-08 18:36:57 - r - INFO: - Episode: 49/300, Reward: 14.000, Step: 14 | |
| 2023-04-08 18:36:57 - r - INFO: - Episode: 50/300, Reward: 18.000, Step: 18 | |
| 2023-04-08 18:36:57 - r - INFO: - Current episode 50 has the best eval reward: 10.000 | |
| 2023-04-08 18:36:57 - r - INFO: - Episode: 51/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:36:57 - r - INFO: - Episode: 52/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:36:58 - r - INFO: - Episode: 53/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:36:58 - r - INFO: - Episode: 54/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:36:58 - r - INFO: - Episode: 55/300, Reward: 23.000, Step: 23 | |
| 2023-04-08 18:36:58 - r - INFO: - Episode: 56/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:36:58 - r - INFO: - Episode: 57/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:36:58 - r - INFO: - Episode: 58/300, Reward: 13.000, Step: 13 | |
| 2023-04-08 18:36:58 - r - INFO: - Episode: 59/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:36:58 - r - INFO: - Episode: 60/300, Reward: 34.000, Step: 34 | |
| 2023-04-08 18:36:58 - r - INFO: - Episode: 61/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 62/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 63/300, Reward: 14.000, Step: 14 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 64/300, Reward: 14.000, Step: 14 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 65/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 66/300, Reward: 13.000, Step: 13 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 67/300, Reward: 17.000, Step: 17 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 68/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 69/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 70/300, Reward: 28.000, Step: 28 | |
| 2023-04-08 18:36:59 - r - INFO: - Current episode 70 has the best eval reward: 10.000 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 71/300, Reward: 13.000, Step: 13 | |
| 2023-04-08 18:36:59 - r - INFO: - Episode: 72/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:00 - r - INFO: - Episode: 73/300, Reward: 26.000, Step: 26 | |
| 2023-04-08 18:37:00 - r - INFO: - Episode: 74/300, Reward: 20.000, Step: 20 | |
| 2023-04-08 18:37:00 - r - INFO: - Episode: 75/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:37:00 - r - INFO: - Current episode 75 has the best eval reward: 10.000 | |
| 2023-04-08 18:37:00 - r - INFO: - Episode: 76/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:00 - r - INFO: - Episode: 77/300, Reward: 39.000, Step: 39 | |
| 2023-04-08 18:37:00 - r - INFO: - Episode: 78/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:00 - r - INFO: - Episode: 79/300, Reward: 23.000, Step: 23 | |
| 2023-04-08 18:37:00 - r - INFO: - Episode: 80/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:00 - r - INFO: - Episode: 81/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:37:00 - r - INFO: - Episode: 82/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 83/300, Reward: 14.000, Step: 14 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 84/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 85/300, Reward: 18.000, Step: 18 | |
| 2023-04-08 18:37:01 - r - INFO: - Current episode 85 has the best eval reward: 10.000 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 86/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 87/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 88/300, Reward: 14.000, Step: 14 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 89/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 90/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:01 - r - INFO: - Current episode 90 has the best eval reward: 10.000 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 91/300, Reward: 22.000, Step: 22 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 92/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:01 - r - INFO: - Episode: 93/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:37:02 - r - INFO: - Episode: 94/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:37:02 - r - INFO: - Episode: 95/300, Reward: 19.000, Step: 19 | |
| 2023-04-08 18:37:02 - r - INFO: - Current episode 95 has the best eval reward: 10.000 | |
| 2023-04-08 18:37:02 - r - INFO: - Episode: 96/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:02 - r - INFO: - Episode: 97/300, Reward: 25.000, Step: 25 | |
| 2023-04-08 18:37:02 - r - INFO: - Episode: 98/300, Reward: 31.000, Step: 31 | |
| 2023-04-08 18:37:02 - r - INFO: - Episode: 99/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:37:02 - r - INFO: - Episode: 100/300, Reward: 18.000, Step: 18 | |
| 2023-04-08 18:37:02 - r - INFO: - Episode: 101/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:37:03 - r - INFO: - Episode: 102/300, Reward: 15.000, Step: 15 | |
| 2023-04-08 18:37:03 - r - INFO: - Episode: 103/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:03 - r - INFO: - Episode: 104/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:03 - r - INFO: - Episode: 105/300, Reward: 21.000, Step: 21 | |
| 2023-04-08 18:37:03 - r - INFO: - Current episode 105 has the best eval reward: 10.000 | |
| 2023-04-08 18:37:03 - r - INFO: - Episode: 106/300, Reward: 26.000, Step: 26 | |
| 2023-04-08 18:37:03 - r - INFO: - Episode: 107/300, Reward: 22.000, Step: 22 | |
| 2023-04-08 18:37:03 - r - INFO: - Episode: 108/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:03 - r - INFO: - Episode: 109/300, Reward: 13.000, Step: 13 | |
| 2023-04-08 18:37:03 - r - INFO: - Episode: 110/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:03 - r - INFO: - Current episode 110 has the best eval reward: 10.000 | |
| 2023-04-08 18:37:04 - r - INFO: - Episode: 111/300, Reward: 23.000, Step: 23 | |
| 2023-04-08 18:37:04 - r - INFO: - Episode: 112/300, Reward: 20.000, Step: 20 | |
| 2023-04-08 18:37:04 - r - INFO: - Episode: 113/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:04 - r - INFO: - Episode: 114/300, Reward: 14.000, Step: 14 | |
| 2023-04-08 18:37:04 - r - INFO: - Episode: 115/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:04 - r - INFO: - Current episode 115 has the best eval reward: 10.000 | |
| 2023-04-08 18:37:04 - r - INFO: - Episode: 116/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:04 - r - INFO: - Episode: 117/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:04 - r - INFO: - Episode: 118/300, Reward: 65.000, Step: 65 | |
| 2023-04-08 18:37:04 - r - INFO: - Episode: 119/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 120/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 121/300, Reward: 30.000, Step: 30 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 122/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 123/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 124/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 125/300, Reward: 31.000, Step: 31 | |
| 2023-04-08 18:37:05 - r - INFO: - Current episode 125 has the best eval reward: 12.000 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 126/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 127/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 128/300, Reward: 17.000, Step: 17 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 129/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:05 - r - INFO: - Episode: 130/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:06 - r - INFO: - Current episode 130 has the best eval reward: 15.000 | |
| 2023-04-08 18:37:06 - r - INFO: - Episode: 131/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:06 - r - INFO: - Episode: 132/300, Reward: 17.000, Step: 17 | |
| 2023-04-08 18:37:06 - r - INFO: - Episode: 133/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:06 - r - INFO: - Episode: 134/300, Reward: 51.000, Step: 51 | |
| 2023-04-08 18:37:06 - r - INFO: - Episode: 135/300, Reward: 25.000, Step: 25 | |
| 2023-04-08 18:37:06 - r - INFO: - Episode: 136/300, Reward: 15.000, Step: 15 | |
| 2023-04-08 18:37:06 - r - INFO: - Episode: 137/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 138/300, Reward: 27.000, Step: 27 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 139/300, Reward: 21.000, Step: 21 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 140/300, Reward: 17.000, Step: 17 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 141/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 142/300, Reward: 17.000, Step: 17 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 143/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 144/300, Reward: 23.000, Step: 23 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 145/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 146/300, Reward: 20.000, Step: 20 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 147/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:07 - r - INFO: - Episode: 148/300, Reward: 17.000, Step: 17 | |
| 2023-04-08 18:37:08 - r - INFO: - Episode: 149/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:08 - r - INFO: - Episode: 150/300, Reward: 31.000, Step: 31 | |
| 2023-04-08 18:37:08 - r - INFO: - Episode: 151/300, Reward: 27.000, Step: 27 | |
| 2023-04-08 18:37:08 - r - INFO: - Episode: 152/300, Reward: 34.000, Step: 34 | |
| 2023-04-08 18:37:08 - r - INFO: - Episode: 153/300, Reward: 16.000, Step: 16 | |
| 2023-04-08 18:37:08 - r - INFO: - Episode: 154/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:37:09 - r - INFO: - Episode: 155/300, Reward: 41.000, Step: 41 | |
| 2023-04-08 18:37:09 - r - INFO: - Episode: 156/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:37:09 - r - INFO: - Episode: 157/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:37:09 - r - INFO: - Episode: 158/300, Reward: 60.000, Step: 60 | |
| 2023-04-08 18:37:09 - r - INFO: - Episode: 159/300, Reward: 17.000, Step: 17 | |
| 2023-04-08 18:37:09 - r - INFO: - Episode: 160/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:09 - r - INFO: - Episode: 161/300, Reward: 17.000, Step: 17 | |
| 2023-04-08 18:37:09 - r - INFO: - Episode: 162/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:10 - r - INFO: - Episode: 163/300, Reward: 31.000, Step: 31 | |
| 2023-04-08 18:37:10 - r - INFO: - Episode: 164/300, Reward: 65.000, Step: 65 | |
| 2023-04-08 18:37:10 - r - INFO: - Episode: 165/300, Reward: 9.000, Step: 9 | |
| 2023-04-08 18:37:10 - r - INFO: - Episode: 166/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:37:10 - r - INFO: - Episode: 167/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:37:10 - r - INFO: - Episode: 168/300, Reward: 10.000, Step: 10 | |
| 2023-04-08 18:37:11 - r - INFO: - Episode: 169/300, Reward: 71.000, Step: 71 | |
| 2023-04-08 18:37:11 - r - INFO: - Episode: 170/300, Reward: 41.000, Step: 41 | |
| 2023-04-08 18:37:11 - r - INFO: - Episode: 171/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:11 - r - INFO: - Episode: 172/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:37:11 - r - INFO: - Episode: 173/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:11 - r - INFO: - Episode: 174/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:37:11 - r - INFO: - Episode: 175/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:11 - r - INFO: - Episode: 176/300, Reward: 14.000, Step: 14 | |
| 2023-04-08 18:37:11 - r - INFO: - Episode: 177/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:12 - r - INFO: - Episode: 178/300, Reward: 57.000, Step: 57 | |
| 2023-04-08 18:37:12 - r - INFO: - Episode: 179/300, Reward: 13.000, Step: 13 | |
| 2023-04-08 18:37:12 - r - INFO: - Episode: 180/300, Reward: 14.000, Step: 14 | |
| 2023-04-08 18:37:12 - r - INFO: - Episode: 181/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:12 - r - INFO: - Episode: 182/300, Reward: 49.000, Step: 49 | |
| 2023-04-08 18:37:13 - r - INFO: - Episode: 183/300, Reward: 33.000, Step: 33 | |
| 2023-04-08 18:37:13 - r - INFO: - Episode: 184/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:13 - r - INFO: - Episode: 185/300, Reward: 64.000, Step: 64 | |
| 2023-04-08 18:37:13 - r - INFO: - Episode: 186/300, Reward: 40.000, Step: 40 | |
| 2023-04-08 18:37:13 - r - INFO: - Episode: 187/300, Reward: 12.000, Step: 12 | |
| 2023-04-08 18:37:13 - r - INFO: - Episode: 188/300, Reward: 14.000, Step: 14 | |
| 2023-04-08 18:37:14 - r - INFO: - Episode: 189/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:14 - r - INFO: - Episode: 190/300, Reward: 64.000, Step: 64 | |
| 2023-04-08 18:37:14 - r - INFO: - Episode: 191/300, Reward: 53.000, Step: 53 | |
| 2023-04-08 18:37:15 - r - INFO: - Episode: 192/300, Reward: 64.000, Step: 64 | |
| 2023-04-08 18:37:15 - r - INFO: - Episode: 193/300, Reward: 54.000, Step: 54 | |
| 2023-04-08 18:37:16 - r - INFO: - Episode: 194/300, Reward: 83.000, Step: 83 | |
| 2023-04-08 18:37:16 - r - INFO: - Episode: 195/300, Reward: 53.000, Step: 53 | |
| 2023-04-08 18:37:16 - r - INFO: - Episode: 196/300, Reward: 27.000, Step: 27 | |
| 2023-04-08 18:37:16 - r - INFO: - Episode: 197/300, Reward: 39.000, Step: 39 | |
| 2023-04-08 18:37:17 - r - INFO: - Episode: 198/300, Reward: 93.000, Step: 93 | |
| 2023-04-08 18:37:17 - r - INFO: - Episode: 199/300, Reward: 11.000, Step: 11 | |
| 2023-04-08 18:37:17 - r - INFO: - Episode: 200/300, Reward: 13.000, Step: 13 | |
| 2023-04-08 18:37:17 - r - INFO: - Current episode 200 has the best eval reward: 18.000 | |
| 2023-04-08 18:37:18 - r - INFO: - Episode: 201/300, Reward: 127.000, Step: 127 | |
| 2023-04-08 18:37:18 - r - INFO: - Episode: 202/300, Reward: 120.000, Step: 120 | |
| 2023-04-08 18:37:19 - r - INFO: - Episode: 203/300, Reward: 60.000, Step: 60 | |
| 2023-04-08 18:37:20 - r - INFO: - Episode: 204/300, Reward: 157.000, Step: 157 | |
| 2023-04-08 18:37:20 - r - INFO: - Episode: 205/300, Reward: 63.000, Step: 63 | |
| 2023-04-08 18:37:20 - r - INFO: - Current episode 205 has the best eval reward: 89.000 | |
| 2023-04-08 18:37:20 - r - INFO: - Episode: 206/300, Reward: 26.000, Step: 26 | |
| 2023-04-08 18:37:21 - r - INFO: - Episode: 207/300, Reward: 45.000, Step: 45 | |
| 2023-04-08 18:37:21 - r - INFO: - Episode: 208/300, Reward: 80.000, Step: 80 | |
| 2023-04-08 18:37:22 - r - INFO: - Episode: 209/300, Reward: 101.000, Step: 101 | |
| 2023-04-08 18:37:22 - r - INFO: - Episode: 210/300, Reward: 96.000, Step: 96 | |
| 2023-04-08 18:37:23 - r - INFO: - Episode: 211/300, Reward: 81.000, Step: 81 | |
| 2023-04-08 18:37:23 - r - INFO: - Episode: 212/300, Reward: 80.000, Step: 80 | |
| 2023-04-08 18:37:24 - r - INFO: - Episode: 213/300, Reward: 193.000, Step: 193 | |
| 2023-04-08 18:37:25 - r - INFO: - Episode: 214/300, Reward: 148.000, Step: 148 | |
| 2023-04-08 18:37:26 - r - INFO: - Episode: 215/300, Reward: 138.000, Step: 138 | |
| 2023-04-08 18:37:27 - r - INFO: - Episode: 216/300, Reward: 152.000, Step: 152 | |
| 2023-04-08 18:37:28 - r - INFO: - Episode: 217/300, Reward: 173.000, Step: 173 | |
| 2023-04-08 18:37:29 - r - INFO: - Episode: 218/300, Reward: 86.000, Step: 86 | |
| 2023-04-08 18:37:29 - r - INFO: - Episode: 219/300, Reward: 107.000, Step: 107 | |
| 2023-04-08 18:37:30 - r - INFO: - Episode: 220/300, Reward: 152.000, Step: 152 | |
| 2023-04-08 18:37:31 - r - INFO: - Episode: 221/300, Reward: 100.000, Step: 100 | |
| 2023-04-08 18:37:31 - r - INFO: - Episode: 222/300, Reward: 97.000, Step: 97 | |
| 2023-04-08 18:37:32 - r - INFO: - Episode: 223/300, Reward: 104.000, Step: 104 | |
| 2023-04-08 18:37:33 - r - INFO: - Episode: 224/300, Reward: 93.000, Step: 93 | |
| 2023-04-08 18:37:33 - r - INFO: - Episode: 225/300, Reward: 138.000, Step: 138 | |
| 2023-04-08 18:37:35 - r - INFO: - Episode: 226/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:37:36 - r - INFO: - Episode: 227/300, Reward: 120.000, Step: 120 | |
| 2023-04-08 18:37:36 - r - INFO: - Episode: 228/300, Reward: 133.000, Step: 133 | |
| 2023-04-08 18:37:37 - r - INFO: - Episode: 229/300, Reward: 105.000, Step: 105 | |
| 2023-04-08 18:37:38 - r - INFO: - Episode: 230/300, Reward: 96.000, Step: 96 | |
| 2023-04-08 18:37:38 - r - INFO: - Current episode 230 has the best eval reward: 91.000 | |
| 2023-04-08 18:37:39 - r - INFO: - Episode: 231/300, Reward: 166.000, Step: 166 | |
| 2023-04-08 18:37:40 - r - INFO: - Episode: 232/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:37:41 - r - INFO: - Episode: 233/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:37:42 - r - INFO: - Episode: 234/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:37:43 - r - INFO: - Episode: 235/300, Reward: 129.000, Step: 129 | |
| 2023-04-08 18:37:43 - r - INFO: - Current episode 235 has the best eval reward: 193.000 | |
| 2023-04-08 18:37:44 - r - INFO: - Episode: 236/300, Reward: 135.000, Step: 135 | |
| 2023-04-08 18:37:45 - r - INFO: - Episode: 237/300, Reward: 128.000, Step: 128 | |
| 2023-04-08 18:37:46 - r - INFO: - Episode: 238/300, Reward: 141.000, Step: 141 | |
| 2023-04-08 18:37:47 - r - INFO: - Episode: 239/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:37:48 - r - INFO: - Episode: 240/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:37:49 - r - INFO: - Episode: 241/300, Reward: 137.000, Step: 137 | |
| 2023-04-08 18:37:50 - r - INFO: - Episode: 242/300, Reward: 172.000, Step: 172 | |
| 2023-04-08 18:37:51 - r - INFO: - Episode: 243/300, Reward: 149.000, Step: 149 | |
| 2023-04-08 18:37:53 - r - INFO: - Episode: 244/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:37:53 - r - INFO: - Episode: 245/300, Reward: 154.000, Step: 154 | |
| 2023-04-08 18:37:55 - r - INFO: - Episode: 246/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:37:56 - r - INFO: - Episode: 247/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:37:57 - r - INFO: - Episode: 248/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:37:59 - r - INFO: - Episode: 249/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:00 - r - INFO: - Episode: 250/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:01 - r - INFO: - Episode: 251/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:03 - r - INFO: - Episode: 252/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:04 - r - INFO: - Episode: 253/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:05 - r - INFO: - Episode: 254/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:06 - r - INFO: - Episode: 255/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:08 - r - INFO: - Episode: 256/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:09 - r - INFO: - Episode: 257/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:10 - r - INFO: - Episode: 258/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:11 - r - INFO: - Episode: 259/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:13 - r - INFO: - Episode: 260/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:14 - r - INFO: - Episode: 261/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:15 - r - INFO: - Episode: 262/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:17 - r - INFO: - Episode: 263/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:18 - r - INFO: - Episode: 264/300, Reward: 195.000, Step: 195 | |
| 2023-04-08 18:38:19 - r - INFO: - Episode: 265/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:21 - r - INFO: - Episode: 266/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:22 - r - INFO: - Episode: 267/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:23 - r - INFO: - Episode: 268/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:24 - r - INFO: - Episode: 269/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:25 - r - INFO: - Episode: 270/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:27 - r - INFO: - Episode: 271/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:28 - r - INFO: - Episode: 272/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:30 - r - INFO: - Episode: 273/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:31 - r - INFO: - Episode: 274/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:33 - r - INFO: - Episode: 275/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:34 - r - INFO: - Episode: 276/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:36 - r - INFO: - Episode: 277/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:37 - r - INFO: - Episode: 278/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:38 - r - INFO: - Episode: 279/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:39 - r - INFO: - Episode: 280/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:40 - r - INFO: - Current episode 280 has the best eval reward: 200.000 | |
| 2023-04-08 18:38:41 - r - INFO: - Episode: 281/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:42 - r - INFO: - Episode: 282/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:43 - r - INFO: - Episode: 283/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:45 - r - INFO: - Episode: 284/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:46 - r - INFO: - Episode: 285/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:46 - r - INFO: - Current episode 285 has the best eval reward: 200.000 | |
| 2023-04-08 18:38:47 - r - INFO: - Episode: 286/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:49 - r - INFO: - Episode: 287/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:50 - r - INFO: - Episode: 288/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:51 - r - INFO: - Episode: 289/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:52 - r - INFO: - Episode: 290/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:53 - r - INFO: - Current episode 290 has the best eval reward: 200.000 | |
| 2023-04-08 18:38:54 - r - INFO: - Episode: 291/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:55 - r - INFO: - Episode: 292/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:57 - r - INFO: - Episode: 293/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:58 - r - INFO: - Episode: 294/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:38:59 - r - INFO: - Episode: 295/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:39:00 - r - INFO: - Episode: 296/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:39:02 - r - INFO: - Episode: 297/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:39:03 - r - INFO: - Episode: 298/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:39:04 - r - INFO: - Episode: 299/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:39:05 - r - INFO: - Episode: 300/300, Reward: 200.000, Step: 200 | |
| 2023-04-08 18:39:06 - r - INFO: - Finish training! | |