| 2023-04-04 21:15:46 - r - INFO: - Hyperparameters: | |
| 2023-04-04 21:15:46 - r - INFO: - ================================================================================ | |
| 2023-04-04 21:15:46 - r - INFO: - Name Value Type | |
| 2023-04-04 21:15:46 - r - INFO: - env_name MountainCar-v0 <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - new_step_api 1 <class 'bool'> | |
| 2023-04-04 21:15:46 - r - INFO: - wrapper None <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - render 0 <class 'bool'> | |
| 2023-04-04 21:15:46 - r - INFO: - algo_name DQN <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - mode train <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - seed 3 <class 'int'> | |
| 2023-04-04 21:15:46 - r - INFO: - device cpu <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - train_eps 200 <class 'int'> | |
| 2023-04-04 21:15:46 - r - INFO: - test_eps 20 <class 'int'> | |
| 2023-04-04 21:15:46 - r - INFO: - eval_eps 10 <class 'int'> | |
| 2023-04-04 21:15:46 - r - INFO: - eval_per_episode 5 <class 'int'> | |
| 2023-04-04 21:15:46 - r - INFO: - max_steps 200 <class 'int'> | |
| 2023-04-04 21:15:46 - r - INFO: - load_checkpoint 0 <class 'bool'> | |
| 2023-04-04 21:15:46 - r - INFO: - load_path tasks <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - show_fig 0 <class 'bool'> | |
| 2023-04-04 21:15:46 - r - INFO: - save_fig 1 <class 'bool'> | |
| 2023-04-04 21:15:46 - r - INFO: - epsilon_start 0.99 <class 'float'> | |
| 2023-04-04 21:15:46 - r - INFO: - epsilon_end 0.01 <class 'float'> | |
| 2023-04-04 21:15:46 - r - INFO: - epsilon_decay 800 <class 'int'> | |
| 2023-04-04 21:15:46 - r - INFO: - gamma 0.99 <class 'float'> | |
| 2023-04-04 21:15:46 - r - INFO: - lr 0.01 <class 'float'> | |
| 2023-04-04 21:15:46 - r - INFO: - buffer_size 40000 <class 'int'> | |
| 2023-04-04 21:15:46 - r - INFO: - batch_size 64 <class 'int'> | |
| 2023-04-04 21:15:46 - r - INFO: - target_update 4 <class 'int'> | |
| 2023-04-04 21:15:46 - 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'> | |
| 2023-04-04 21:15:46 - r - INFO: - task_dir /home/PJLAB/geyuhong/rl-tutorials/joyrl/tasks/Train_MountainCar-v0_DQN_20230404-211546 <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - model_dir /home/PJLAB/geyuhong/rl-tutorials/joyrl/tasks/Train_MountainCar-v0_DQN_20230404-211546/models <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - res_dir /home/PJLAB/geyuhong/rl-tutorials/joyrl/tasks/Train_MountainCar-v0_DQN_20230404-211546/results <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - log_dir /home/PJLAB/geyuhong/rl-tutorials/joyrl/tasks/Train_MountainCar-v0_DQN_20230404-211546/logs <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - traj_dir /home/PJLAB/geyuhong/rl-tutorials/joyrl/tasks/Train_MountainCar-v0_DQN_20230404-211546/traj <class 'str'> | |
| 2023-04-04 21:15:46 - r - INFO: - ================================================================================ | |
| 2023-04-04 21:15:46 - r - INFO: - n_states: 2, n_actions: 3 | |
| 2023-04-04 21:15:46 - r - INFO: - Start training! | |
| 2023-04-04 21:15:46 - r - INFO: - Env: MountainCar-v0, Algorithm: DQN, Device: cpu | |
| 2023-04-04 21:15:47 - r - INFO: - Episode: 1/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:47 - r - INFO: - Episode: 2/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:47 - r - INFO: - Episode: 3/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:47 - r - INFO: - Episode: 4/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:48 - r - INFO: - Episode: 5/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:48 - r - INFO: - Current episode 5 has the best eval reward: -200.000 | |
| 2023-04-04 21:15:48 - r - INFO: - Episode: 6/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:48 - r - INFO: - Episode: 7/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:49 - r - INFO: - Episode: 8/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:49 - r - INFO: - Episode: 9/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:49 - r - INFO: - Episode: 10/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:50 - r - INFO: - Current episode 10 has the best eval reward: -200.000 | |
| 2023-04-04 21:15:50 - r - INFO: - Episode: 11/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:50 - r - INFO: - Episode: 12/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:51 - r - INFO: - Episode: 13/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:51 - r - INFO: - Episode: 14/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:51 - r - INFO: - Episode: 15/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:52 - r - INFO: - Current episode 15 has the best eval reward: -200.000 | |
| 2023-04-04 21:15:52 - r - INFO: - Episode: 16/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:52 - r - INFO: - Episode: 17/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:53 - r - INFO: - Episode: 18/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:53 - r - INFO: - Episode: 19/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:53 - r - INFO: - Episode: 20/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:54 - r - INFO: - Current episode 20 has the best eval reward: -200.000 | |
| 2023-04-04 21:15:54 - r - INFO: - Episode: 21/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:54 - r - INFO: - Episode: 22/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:55 - r - INFO: - Episode: 23/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:55 - r - INFO: - Episode: 24/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:55 - r - INFO: - Episode: 25/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:56 - r - INFO: - Current episode 25 has the best eval reward: -200.000 | |
| 2023-04-04 21:15:56 - r - INFO: - Episode: 26/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:56 - r - INFO: - Episode: 27/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:57 - r - INFO: - Episode: 28/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:57 - r - INFO: - Episode: 29/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:57 - r - INFO: - Episode: 30/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:58 - r - INFO: - Current episode 30 has the best eval reward: -200.000 | |
| 2023-04-04 21:15:58 - r - INFO: - Episode: 31/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:58 - r - INFO: - Episode: 32/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:59 - r - INFO: - Episode: 33/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:59 - r - INFO: - Episode: 34/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:15:59 - r - INFO: - Episode: 35/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:00 - r - INFO: - Current episode 35 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:00 - r - INFO: - Episode: 36/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:00 - r - INFO: - Episode: 37/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:01 - r - INFO: - Episode: 38/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:01 - r - INFO: - Episode: 39/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:02 - r - INFO: - Episode: 40/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:02 - r - INFO: - Current episode 40 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:02 - r - INFO: - Episode: 41/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:03 - r - INFO: - Episode: 42/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:03 - r - INFO: - Episode: 43/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:03 - r - INFO: - Episode: 44/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:04 - r - INFO: - Episode: 45/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:04 - r - INFO: - Current episode 45 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:04 - r - INFO: - Episode: 46/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:05 - r - INFO: - Episode: 47/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:05 - r - INFO: - Episode: 48/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:06 - r - INFO: - Episode: 49/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:06 - r - INFO: - Episode: 50/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:06 - r - INFO: - Current episode 50 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:07 - r - INFO: - Episode: 51/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:07 - r - INFO: - Episode: 52/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:07 - r - INFO: - Episode: 53/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:08 - r - INFO: - Episode: 54/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:08 - r - INFO: - Episode: 55/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:08 - r - INFO: - Current episode 55 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:09 - r - INFO: - Episode: 56/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:09 - r - INFO: - Episode: 57/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:09 - r - INFO: - Episode: 58/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:10 - r - INFO: - Episode: 59/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:10 - r - INFO: - Episode: 60/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:10 - r - INFO: - Current episode 60 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:11 - r - INFO: - Episode: 61/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:11 - r - INFO: - Episode: 62/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:11 - r - INFO: - Episode: 63/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:12 - r - INFO: - Episode: 64/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:12 - r - INFO: - Episode: 65/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:12 - r - INFO: - Current episode 65 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:13 - r - INFO: - Episode: 66/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:13 - r - INFO: - Episode: 67/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:14 - r - INFO: - Episode: 68/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:14 - r - INFO: - Episode: 69/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:15 - r - INFO: - Episode: 70/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:15 - r - INFO: - Current episode 70 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:15 - r - INFO: - Episode: 71/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:16 - r - INFO: - Episode: 72/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:16 - r - INFO: - Episode: 73/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:16 - r - INFO: - Episode: 74/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:17 - r - INFO: - Episode: 75/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:17 - r - INFO: - Current episode 75 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:17 - r - INFO: - Episode: 76/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:18 - r - INFO: - Episode: 77/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:18 - r - INFO: - Episode: 78/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:18 - r - INFO: - Episode: 79/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:19 - r - INFO: - Episode: 80/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:19 - r - INFO: - Current episode 80 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:19 - r - INFO: - Episode: 81/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:20 - r - INFO: - Episode: 82/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:20 - r - INFO: - Episode: 83/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:20 - r - INFO: - Episode: 84/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:21 - r - INFO: - Episode: 85/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:21 - r - INFO: - Current episode 85 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:21 - r - INFO: - Episode: 86/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:22 - r - INFO: - Episode: 87/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:22 - r - INFO: - Episode: 88/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:22 - r - INFO: - Episode: 89/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:23 - r - INFO: - Episode: 90/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:23 - r - INFO: - Current episode 90 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:23 - r - INFO: - Episode: 91/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:24 - r - INFO: - Episode: 92/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:24 - r - INFO: - Episode: 93/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:24 - r - INFO: - Episode: 94/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:25 - r - INFO: - Episode: 95/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:25 - r - INFO: - Current episode 95 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:26 - r - INFO: - Episode: 96/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:26 - r - INFO: - Episode: 97/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:26 - r - INFO: - Episode: 98/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:27 - r - INFO: - Episode: 99/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:27 - r - INFO: - Episode: 100/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:27 - r - INFO: - Current episode 100 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:28 - r - INFO: - Episode: 101/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:28 - r - INFO: - Episode: 102/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:28 - r - INFO: - Episode: 103/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:29 - r - INFO: - Episode: 104/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:29 - r - INFO: - Episode: 105/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:29 - r - INFO: - Current episode 105 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:30 - r - INFO: - Episode: 106/200, Reward: -190.000, Step: 190 | |
| 2023-04-04 21:16:30 - r - INFO: - Episode: 107/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:30 - r - INFO: - Episode: 108/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:31 - r - INFO: - Episode: 109/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:31 - r - INFO: - Episode: 110/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:31 - r - INFO: - Current episode 110 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:32 - r - INFO: - Episode: 111/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:32 - r - INFO: - Episode: 112/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:32 - r - INFO: - Episode: 113/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:33 - r - INFO: - Episode: 114/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:33 - r - INFO: - Episode: 115/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:33 - r - INFO: - Current episode 115 has the best eval reward: -200.000 | |
| 2023-04-04 21:16:34 - r - INFO: - Episode: 116/200, Reward: -149.000, Step: 149 | |
| 2023-04-04 21:16:34 - r - INFO: - Episode: 117/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:34 - r - INFO: - Episode: 118/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:35 - r - INFO: - Episode: 119/200, Reward: -105.000, Step: 105 | |
| 2023-04-04 21:16:35 - r - INFO: - Episode: 120/200, Reward: -162.000, Step: 162 | |
| 2023-04-04 21:16:35 - r - INFO: - Current episode 120 has the best eval reward: -148.000 | |
| 2023-04-04 21:16:36 - r - INFO: - Episode: 121/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:36 - r - INFO: - Episode: 122/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:36 - r - INFO: - Episode: 123/200, Reward: -195.000, Step: 195 | |
| 2023-04-04 21:16:37 - r - INFO: - Episode: 124/200, Reward: -173.000, Step: 173 | |
| 2023-04-04 21:16:37 - r - INFO: - Episode: 125/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:38 - r - INFO: - Episode: 126/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:38 - r - INFO: - Episode: 127/200, Reward: -149.000, Step: 149 | |
| 2023-04-04 21:16:38 - r - INFO: - Episode: 128/200, Reward: -127.000, Step: 127 | |
| 2023-04-04 21:16:38 - r - INFO: - Episode: 129/200, Reward: -132.000, Step: 132 | |
| 2023-04-04 21:16:39 - r - INFO: - Episode: 130/200, Reward: -145.000, Step: 145 | |
| 2023-04-04 21:16:39 - r - INFO: - Episode: 131/200, Reward: -125.000, Step: 125 | |
| 2023-04-04 21:16:39 - r - INFO: - Episode: 132/200, Reward: -127.000, Step: 127 | |
| 2023-04-04 21:16:40 - r - INFO: - Episode: 133/200, Reward: -126.000, Step: 126 | |
| 2023-04-04 21:16:40 - r - INFO: - Episode: 134/200, Reward: -115.000, Step: 115 | |
| 2023-04-04 21:16:40 - r - INFO: - Episode: 135/200, Reward: -168.000, Step: 168 | |
| 2023-04-04 21:16:41 - r - INFO: - Episode: 136/200, Reward: -174.000, Step: 174 | |
| 2023-04-04 21:16:41 - r - INFO: - Episode: 137/200, Reward: -118.000, Step: 118 | |
| 2023-04-04 21:16:41 - r - INFO: - Episode: 138/200, Reward: -153.000, Step: 153 | |
| 2023-04-04 21:16:42 - r - INFO: - Episode: 139/200, Reward: -118.000, Step: 118 | |
| 2023-04-04 21:16:42 - r - INFO: - Episode: 140/200, Reward: -117.000, Step: 117 | |
| 2023-04-04 21:16:42 - r - INFO: - Current episode 140 has the best eval reward: -112.000 | |
| 2023-04-04 21:16:42 - r - INFO: - Episode: 141/200, Reward: -113.000, Step: 113 | |
| 2023-04-04 21:16:42 - r - INFO: - Episode: 142/200, Reward: -114.000, Step: 114 | |
| 2023-04-04 21:16:43 - r - INFO: - Episode: 143/200, Reward: -116.000, Step: 116 | |
| 2023-04-04 21:16:43 - r - INFO: - Episode: 144/200, Reward: -117.000, Step: 117 | |
| 2023-04-04 21:16:43 - r - INFO: - Episode: 145/200, Reward: -117.000, Step: 117 | |
| 2023-04-04 21:16:43 - r - INFO: - Episode: 146/200, Reward: -114.000, Step: 114 | |
| 2023-04-04 21:16:44 - r - INFO: - Episode: 147/200, Reward: -132.000, Step: 132 | |
| 2023-04-04 21:16:44 - r - INFO: - Episode: 148/200, Reward: -124.000, Step: 124 | |
| 2023-04-04 21:16:44 - r - INFO: - Episode: 149/200, Reward: -118.000, Step: 118 | |
| 2023-04-04 21:16:44 - r - INFO: - Episode: 150/200, Reward: -125.000, Step: 125 | |
| 2023-04-04 21:16:45 - r - INFO: - Episode: 151/200, Reward: -111.000, Step: 111 | |
| 2023-04-04 21:16:45 - r - INFO: - Episode: 152/200, Reward: -131.000, Step: 131 | |
| 2023-04-04 21:16:45 - r - INFO: - Episode: 153/200, Reward: -114.000, Step: 114 | |
| 2023-04-04 21:16:45 - r - INFO: - Episode: 154/200, Reward: -125.000, Step: 125 | |
| 2023-04-04 21:16:46 - r - INFO: - Episode: 155/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:46 - r - INFO: - Episode: 156/200, Reward: -107.000, Step: 107 | |
| 2023-04-04 21:16:46 - r - INFO: - Episode: 157/200, Reward: -127.000, Step: 127 | |
| 2023-04-04 21:16:47 - r - INFO: - Episode: 158/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:47 - r - INFO: - Episode: 159/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:47 - r - INFO: - Episode: 160/200, Reward: -113.000, Step: 113 | |
| 2023-04-04 21:16:48 - r - INFO: - Episode: 161/200, Reward: -166.000, Step: 166 | |
| 2023-04-04 21:16:48 - r - INFO: - Episode: 162/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:49 - r - INFO: - Episode: 163/200, Reward: -171.000, Step: 171 | |
| 2023-04-04 21:16:49 - r - INFO: - Episode: 164/200, Reward: -156.000, Step: 156 | |
| 2023-04-04 21:16:49 - r - INFO: - Episode: 165/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:50 - r - INFO: - Episode: 166/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:50 - r - INFO: - Episode: 167/200, Reward: -128.000, Step: 128 | |
| 2023-04-04 21:16:50 - r - INFO: - Episode: 168/200, Reward: -171.000, Step: 171 | |
| 2023-04-04 21:16:51 - r - INFO: - Episode: 169/200, Reward: -123.000, Step: 123 | |
| 2023-04-04 21:16:51 - r - INFO: - Episode: 170/200, Reward: -173.000, Step: 173 | |
| 2023-04-04 21:16:51 - r - INFO: - Current episode 170 has the best eval reward: -111.000 | |
| 2023-04-04 21:16:51 - r - INFO: - Episode: 171/200, Reward: -157.000, Step: 157 | |
| 2023-04-04 21:16:52 - r - INFO: - Episode: 172/200, Reward: -122.000, Step: 122 | |
| 2023-04-04 21:16:52 - r - INFO: - Episode: 173/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:52 - r - INFO: - Episode: 174/200, Reward: -123.000, Step: 123 | |
| 2023-04-04 21:16:52 - r - INFO: - Episode: 175/200, Reward: -152.000, Step: 152 | |
| 2023-04-04 21:16:53 - r - INFO: - Episode: 176/200, Reward: -116.000, Step: 116 | |
| 2023-04-04 21:16:53 - r - INFO: - Episode: 177/200, Reward: -141.000, Step: 141 | |
| 2023-04-04 21:16:53 - r - INFO: - Episode: 178/200, Reward: -158.000, Step: 158 | |
| 2023-04-04 21:16:54 - r - INFO: - Episode: 179/200, Reward: -153.000, Step: 153 | |
| 2023-04-04 21:16:54 - r - INFO: - Episode: 180/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:55 - r - INFO: - Episode: 181/200, Reward: -199.000, Step: 199 | |
| 2023-04-04 21:16:55 - r - INFO: - Episode: 182/200, Reward: -194.000, Step: 194 | |
| 2023-04-04 21:16:55 - r - INFO: - Episode: 183/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:56 - r - INFO: - Episode: 184/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:56 - r - INFO: - Episode: 185/200, Reward: -149.000, Step: 149 | |
| 2023-04-04 21:16:57 - r - INFO: - Episode: 186/200, Reward: -162.000, Step: 162 | |
| 2023-04-04 21:16:57 - r - INFO: - Episode: 187/200, Reward: -191.000, Step: 191 | |
| 2023-04-04 21:16:57 - r - INFO: - Episode: 188/200, Reward: -196.000, Step: 196 | |
| 2023-04-04 21:16:58 - r - INFO: - Episode: 189/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:58 - r - INFO: - Episode: 190/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:59 - r - INFO: - Episode: 191/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:16:59 - r - INFO: - Episode: 192/200, Reward: -191.000, Step: 191 | |
| 2023-04-04 21:16:59 - r - INFO: - Episode: 193/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:17:00 - r - INFO: - Episode: 194/200, Reward: -198.000, Step: 198 | |
| 2023-04-04 21:17:00 - r - INFO: - Episode: 195/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:17:00 - r - INFO: - Current episode 195 has the best eval reward: -109.000 | |
| 2023-04-04 21:17:01 - r - INFO: - Episode: 196/200, Reward: -181.000, Step: 181 | |
| 2023-04-04 21:17:01 - r - INFO: - Episode: 197/200, Reward: -181.000, Step: 181 | |
| 2023-04-04 21:17:01 - r - INFO: - Episode: 198/200, Reward: -187.000, Step: 187 | |
| 2023-04-04 21:17:02 - r - INFO: - Episode: 199/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:17:02 - r - INFO: - Episode: 200/200, Reward: -200.000, Step: 200 | |
| 2023-04-04 21:17:02 - r - INFO: - Finish training! | |