| 2023-02-04 22:31:46 - r - INFO: - Hyperparameters: | |
| 2023-02-04 22:31:46 - r - INFO: - ================================================================================ | |
| 2023-02-04 22:31:46 - r - INFO: - Name Value Type | |
| 2023-02-04 22:31:46 - r - INFO: - env_name CartPole-v1 <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - new_step_api 1 <class 'bool'> | |
| 2023-02-04 22:31:46 - r - INFO: - wrapper None <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - render 0 <class 'bool'> | |
| 2023-02-04 22:31:46 - r - INFO: - algo_name DRQN <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - mode train <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - seed 1 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - device cuda <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - train_eps 200 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - test_eps 10 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - eval_eps 10 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - eval_per_episode 5 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - max_steps 200 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - load_checkpoint 0 <class 'bool'> | |
| 2023-02-04 22:31:46 - r - INFO: - load_path Train_CartPole-v1_ <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - show_fig 0 <class 'bool'> | |
| 2023-02-04 22:31:46 - r - INFO: - save_fig 1 <class 'bool'> | |
| 2023-02-04 22:31:46 - r - INFO: - epsilon_start 0.1 <class 'float'> | |
| 2023-02-04 22:31:46 - r - INFO: - epsilon_end 0.001 <class 'float'> | |
| 2023-02-04 22:31:46 - r - INFO: - epsilon_decay 0.995 <class 'float'> | |
| 2023-02-04 22:31:46 - r - INFO: - hidden_dim 64 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - gamma 0.99 <class 'float'> | |
| 2023-02-04 22:31:46 - r - INFO: - lr 0.001 <class 'float'> | |
| 2023-02-04 22:31:46 - r - INFO: - buffer_size 100000 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - batch_size 8 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - target_update 4 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - lookup_step 10 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - min_epi_num 16 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - max_epi_len 100 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - max_epi_num 100 <class 'int'> | |
| 2023-02-04 22:31:46 - r - INFO: - value_layers [{'layer_type': 'linear', 'layer_dim': ['n_states', 64], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_dim': [64, 64], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_dim': [64, 'n_actions'], 'activation': 'none'}] <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - task_dir /home/dingli/rl-tutorials/joyrl/tasks/Train_CartPole-v1_DRQN_20230204-223146 <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - model_dir /home/dingli/rl-tutorials/joyrl/tasks/Train_CartPole-v1_DRQN_20230204-223146/models <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - res_dir /home/dingli/rl-tutorials/joyrl/tasks/Train_CartPole-v1_DRQN_20230204-223146/results <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - log_dir /home/dingli/rl-tutorials/joyrl/tasks/Train_CartPole-v1_DRQN_20230204-223146/logs <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - traj_dir /home/dingli/rl-tutorials/joyrl/tasks/Train_CartPole-v1_DRQN_20230204-223146/traj <class 'str'> | |
| 2023-02-04 22:31:46 - r - INFO: - ================================================================================ | |
| 2023-02-04 22:31:46 - r - INFO: - n_states: 4, n_actions: 2 | |
| 2023-02-04 22:31:48 - r - INFO: - Start training! | |
| 2023-02-04 22:31:48 - r - INFO: - Env: CartPole-v1, Algorithm: DRQN, Device: cuda | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 1/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 2/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 3/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 4/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 5/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Current episode 5 has the best eval reward: 10.000 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 6/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 7/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 8/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 9/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 10/200, Reward: 12.000, Step: 12 | |
| 2023-02-04 22:31:49 - r - INFO: - Current episode 10 has the best eval reward: 10.000 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 11/200, Reward: 11.000, Step: 11 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 12/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 13/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 14/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:49 - r - INFO: - Episode: 15/200, Reward: 11.000, Step: 11 | |
| 2023-02-04 22:31:50 - r - INFO: - Current episode 15 has the best eval reward: 10.000 | |
| 2023-02-04 22:31:50 - r - INFO: - Episode: 16/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:31:50 - r - INFO: - Episode: 17/200, Reward: 13.000, Step: 13 | |
| 2023-02-04 22:31:50 - r - INFO: - Episode: 18/200, Reward: 14.000, Step: 14 | |
| 2023-02-04 22:31:50 - r - INFO: - Episode: 19/200, Reward: 18.000, Step: 18 | |
| 2023-02-04 22:31:51 - r - INFO: - Episode: 20/200, Reward: 13.000, Step: 13 | |
| 2023-02-04 22:31:51 - r - INFO: - Current episode 20 has the best eval reward: 11.000 | |
| 2023-02-04 22:31:51 - r - INFO: - Episode: 21/200, Reward: 12.000, Step: 12 | |
| 2023-02-04 22:31:51 - r - INFO: - Episode: 22/200, Reward: 12.000, Step: 12 | |
| 2023-02-04 22:31:51 - r - INFO: - Episode: 23/200, Reward: 14.000, Step: 14 | |
| 2023-02-04 22:31:51 - r - INFO: - Episode: 24/200, Reward: 11.000, Step: 11 | |
| 2023-02-04 22:31:51 - r - INFO: - Episode: 25/200, Reward: 9.000, Step: 9 | |
| 2023-02-04 22:31:52 - r - INFO: - Episode: 26/200, Reward: 20.000, Step: 20 | |
| 2023-02-04 22:31:52 - r - INFO: - Episode: 27/200, Reward: 19.000, Step: 19 | |
| 2023-02-04 22:31:52 - r - INFO: - Episode: 28/200, Reward: 13.000, Step: 13 | |
| 2023-02-04 22:31:52 - r - INFO: - Episode: 29/200, Reward: 16.000, Step: 16 | |
| 2023-02-04 22:31:53 - r - INFO: - Episode: 30/200, Reward: 17.000, Step: 17 | |
| 2023-02-04 22:31:54 - r - INFO: - Current episode 30 has the best eval reward: 102.000 | |
| 2023-02-04 22:31:55 - r - INFO: - Episode: 31/200, Reward: 74.000, Step: 74 | |
| 2023-02-04 22:31:56 - r - INFO: - Episode: 32/200, Reward: 87.000, Step: 87 | |
| 2023-02-04 22:31:58 - r - INFO: - Episode: 33/200, Reward: 142.000, Step: 142 | |
| 2023-02-04 22:31:58 - r - INFO: - Episode: 34/200, Reward: 53.000, Step: 53 | |
| 2023-02-04 22:31:59 - r - INFO: - Episode: 35/200, Reward: 56.000, Step: 56 | |
| 2023-02-04 22:32:00 - r - INFO: - Episode: 36/200, Reward: 57.000, Step: 57 | |
| 2023-02-04 22:32:01 - r - INFO: - Episode: 37/200, Reward: 24.000, Step: 24 | |
| 2023-02-04 22:32:01 - r - INFO: - Episode: 38/200, Reward: 56.000, Step: 56 | |
| 2023-02-04 22:32:03 - r - INFO: - Episode: 39/200, Reward: 110.000, Step: 110 | |
| 2023-02-04 22:32:03 - r - INFO: - Episode: 40/200, Reward: 35.000, Step: 35 | |
| 2023-02-04 22:32:04 - r - INFO: - Episode: 41/200, Reward: 27.000, Step: 27 | |
| 2023-02-04 22:32:04 - r - INFO: - Episode: 42/200, Reward: 31.000, Step: 31 | |
| 2023-02-04 22:32:05 - r - INFO: - Episode: 43/200, Reward: 28.000, Step: 28 | |
| 2023-02-04 22:32:05 - r - INFO: - Episode: 44/200, Reward: 27.000, Step: 27 | |
| 2023-02-04 22:32:05 - r - INFO: - Episode: 45/200, Reward: 38.000, Step: 38 | |
| 2023-02-04 22:32:06 - r - INFO: - Episode: 46/200, Reward: 27.000, Step: 27 | |
| 2023-02-04 22:32:07 - r - INFO: - Episode: 47/200, Reward: 30.000, Step: 30 | |
| 2023-02-04 22:32:07 - r - INFO: - Episode: 48/200, Reward: 25.000, Step: 25 | |
| 2023-02-04 22:32:07 - r - INFO: - Episode: 49/200, Reward: 22.000, Step: 22 | |
| 2023-02-04 22:32:08 - r - INFO: - Episode: 50/200, Reward: 30.000, Step: 30 | |
| 2023-02-04 22:32:08 - r - INFO: - Episode: 51/200, Reward: 26.000, Step: 26 | |
| 2023-02-04 22:32:09 - r - INFO: - Episode: 52/200, Reward: 29.000, Step: 29 | |
| 2023-02-04 22:32:09 - r - INFO: - Episode: 53/200, Reward: 34.000, Step: 34 | |
| 2023-02-04 22:32:10 - r - INFO: - Episode: 54/200, Reward: 30.000, Step: 30 | |
| 2023-02-04 22:32:10 - r - INFO: - Episode: 55/200, Reward: 30.000, Step: 30 | |
| 2023-02-04 22:32:11 - r - INFO: - Episode: 56/200, Reward: 25.000, Step: 25 | |
| 2023-02-04 22:32:12 - r - INFO: - Episode: 57/200, Reward: 78.000, Step: 78 | |
| 2023-02-04 22:32:12 - r - INFO: - Episode: 58/200, Reward: 23.000, Step: 23 | |
| 2023-02-04 22:32:13 - r - INFO: - Episode: 59/200, Reward: 53.000, Step: 53 | |
| 2023-02-04 22:32:13 - r - INFO: - Episode: 60/200, Reward: 46.000, Step: 46 | |
| 2023-02-04 22:32:14 - r - INFO: - Episode: 61/200, Reward: 39.000, Step: 39 | |
| 2023-02-04 22:32:15 - r - INFO: - Episode: 62/200, Reward: 33.000, Step: 33 | |
| 2023-02-04 22:32:15 - r - INFO: - Episode: 63/200, Reward: 31.000, Step: 31 | |
| 2023-02-04 22:32:16 - r - INFO: - Episode: 64/200, Reward: 34.000, Step: 34 | |
| 2023-02-04 22:32:16 - r - INFO: - Episode: 65/200, Reward: 57.000, Step: 57 | |
| 2023-02-04 22:32:17 - r - INFO: - Episode: 66/200, Reward: 52.000, Step: 52 | |
| 2023-02-04 22:32:18 - r - INFO: - Episode: 67/200, Reward: 90.000, Step: 90 | |
| 2023-02-04 22:32:19 - r - INFO: - Episode: 68/200, Reward: 22.000, Step: 22 | |
| 2023-02-04 22:32:19 - r - INFO: - Episode: 69/200, Reward: 21.000, Step: 21 | |
| 2023-02-04 22:32:19 - r - INFO: - Episode: 70/200, Reward: 39.000, Step: 39 | |
| 2023-02-04 22:32:20 - r - INFO: - Episode: 71/200, Reward: 21.000, Step: 21 | |
| 2023-02-04 22:32:20 - r - INFO: - Episode: 72/200, Reward: 25.000, Step: 25 | |
| 2023-02-04 22:32:21 - r - INFO: - Episode: 73/200, Reward: 18.000, Step: 18 | |
| 2023-02-04 22:32:21 - r - INFO: - Episode: 74/200, Reward: 18.000, Step: 18 | |
| 2023-02-04 22:32:22 - r - INFO: - Episode: 75/200, Reward: 69.000, Step: 69 | |
| 2023-02-04 22:32:22 - r - INFO: - Episode: 76/200, Reward: 28.000, Step: 28 | |
| 2023-02-04 22:32:23 - r - INFO: - Episode: 77/200, Reward: 28.000, Step: 28 | |
| 2023-02-04 22:32:23 - r - INFO: - Episode: 78/200, Reward: 18.000, Step: 18 | |
| 2023-02-04 22:32:23 - r - INFO: - Episode: 79/200, Reward: 18.000, Step: 18 | |
| 2023-02-04 22:32:23 - r - INFO: - Episode: 80/200, Reward: 20.000, Step: 20 | |
| 2023-02-04 22:32:24 - r - INFO: - Episode: 81/200, Reward: 41.000, Step: 41 | |
| 2023-02-04 22:32:25 - r - INFO: - Episode: 82/200, Reward: 69.000, Step: 69 | |
| 2023-02-04 22:32:25 - r - INFO: - Episode: 83/200, Reward: 18.000, Step: 18 | |
| 2023-02-04 22:32:26 - r - INFO: - Episode: 84/200, Reward: 27.000, Step: 27 | |
| 2023-02-04 22:32:26 - r - INFO: - Episode: 85/200, Reward: 30.000, Step: 30 | |
| 2023-02-04 22:32:27 - r - INFO: - Episode: 86/200, Reward: 28.000, Step: 28 | |
| 2023-02-04 22:32:29 - r - INFO: - Episode: 87/200, Reward: 131.000, Step: 131 | |
| 2023-02-04 22:32:30 - r - INFO: - Episode: 88/200, Reward: 83.000, Step: 83 | |
| 2023-02-04 22:32:31 - r - INFO: - Episode: 89/200, Reward: 103.000, Step: 103 | |
| 2023-02-04 22:32:32 - r - INFO: - Episode: 90/200, Reward: 30.000, Step: 30 | |
| 2023-02-04 22:32:32 - r - INFO: - Episode: 91/200, Reward: 30.000, Step: 30 | |
| 2023-02-04 22:32:33 - r - INFO: - Episode: 92/200, Reward: 31.000, Step: 31 | |
| 2023-02-04 22:32:34 - r - INFO: - Episode: 93/200, Reward: 115.000, Step: 115 | |
| 2023-02-04 22:32:36 - r - INFO: - Episode: 94/200, Reward: 160.000, Step: 160 | |
| 2023-02-04 22:32:37 - r - INFO: - Episode: 95/200, Reward: 64.000, Step: 64 | |
| 2023-02-04 22:32:39 - r - INFO: - Episode: 96/200, Reward: 143.000, Step: 143 | |
| 2023-02-04 22:32:41 - r - INFO: - Episode: 97/200, Reward: 88.000, Step: 88 | |
| 2023-02-04 22:32:42 - r - INFO: - Episode: 98/200, Reward: 111.000, Step: 111 | |
| 2023-02-04 22:32:43 - r - INFO: - Episode: 99/200, Reward: 103.000, Step: 103 | |
| 2023-02-04 22:32:45 - r - INFO: - Episode: 100/200, Reward: 120.000, Step: 120 | |
| 2023-02-04 22:32:46 - r - INFO: - Current episode 100 has the best eval reward: 118.000 | |
| 2023-02-04 22:32:48 - r - INFO: - Episode: 101/200, Reward: 112.000, Step: 112 | |
| 2023-02-04 22:32:49 - r - INFO: - Episode: 102/200, Reward: 98.000, Step: 98 | |
| 2023-02-04 22:32:51 - r - INFO: - Episode: 103/200, Reward: 100.000, Step: 100 | |
| 2023-02-04 22:32:52 - r - INFO: - Episode: 104/200, Reward: 91.000, Step: 91 | |
| 2023-02-04 22:32:53 - r - INFO: - Episode: 105/200, Reward: 112.000, Step: 112 | |
| 2023-02-04 22:32:56 - r - INFO: - Episode: 106/200, Reward: 107.000, Step: 107 | |
| 2023-02-04 22:32:57 - r - INFO: - Episode: 107/200, Reward: 123.000, Step: 123 | |
| 2023-02-04 22:32:59 - r - INFO: - Episode: 108/200, Reward: 174.000, Step: 174 | |
| 2023-02-04 22:33:01 - r - INFO: - Episode: 109/200, Reward: 121.000, Step: 121 | |
| 2023-02-04 22:33:02 - r - INFO: - Episode: 110/200, Reward: 82.000, Step: 82 | |
| 2023-02-04 22:33:03 - r - INFO: - Episode: 111/200, Reward: 19.000, Step: 19 | |
| 2023-02-04 22:33:03 - r - INFO: - Episode: 112/200, Reward: 36.000, Step: 36 | |
| 2023-02-04 22:33:03 - r - INFO: - Episode: 113/200, Reward: 10.000, Step: 10 | |
| 2023-02-04 22:33:03 - r - INFO: - Episode: 114/200, Reward: 12.000, Step: 12 | |
| 2023-02-04 22:33:05 - r - INFO: - Episode: 115/200, Reward: 83.000, Step: 83 | |
| 2023-02-04 22:33:06 - r - INFO: - Episode: 116/200, Reward: 71.000, Step: 71 | |
| 2023-02-04 22:33:07 - r - INFO: - Episode: 117/200, Reward: 78.000, Step: 78 | |
| 2023-02-04 22:33:09 - r - INFO: - Episode: 118/200, Reward: 102.000, Step: 102 | |
| 2023-02-04 22:33:11 - r - INFO: - Episode: 119/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:33:14 - r - INFO: - Episode: 120/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:33:16 - r - INFO: - Current episode 120 has the best eval reward: 181.000 | |
| 2023-02-04 22:33:18 - r - INFO: - Episode: 121/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:33:21 - r - INFO: - Episode: 122/200, Reward: 158.000, Step: 158 | |
| 2023-02-04 22:33:23 - r - INFO: - Episode: 123/200, Reward: 153.000, Step: 153 | |
| 2023-02-04 22:33:24 - r - INFO: - Episode: 124/200, Reward: 141.000, Step: 141 | |
| 2023-02-04 22:33:27 - r - INFO: - Episode: 125/200, Reward: 178.000, Step: 178 | |
| 2023-02-04 22:33:30 - r - INFO: - Episode: 126/200, Reward: 158.000, Step: 158 | |
| 2023-02-04 22:33:32 - r - INFO: - Episode: 127/200, Reward: 147.000, Step: 147 | |
| 2023-02-04 22:33:35 - r - INFO: - Episode: 128/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:33:37 - r - INFO: - Episode: 129/200, Reward: 168.000, Step: 168 | |
| 2023-02-04 22:33:40 - r - INFO: - Episode: 130/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:33:42 - r - INFO: - Current episode 130 has the best eval reward: 200.000 | |
| 2023-02-04 22:33:45 - r - INFO: - Episode: 131/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:33:47 - r - INFO: - Episode: 132/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:33:50 - r - INFO: - Episode: 133/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:33:53 - r - INFO: - Episode: 134/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:33:55 - r - INFO: - Episode: 135/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:33:58 - r - INFO: - Current episode 135 has the best eval reward: 200.000 | |
| 2023-02-04 22:33:58 - r - INFO: - Episode: 136/200, Reward: 30.000, Step: 30 | |
| 2023-02-04 22:34:01 - r - INFO: - Episode: 137/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:03 - r - INFO: - Episode: 138/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:06 - r - INFO: - Episode: 139/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:08 - r - INFO: - Episode: 140/200, Reward: 115.000, Step: 115 | |
| 2023-02-04 22:34:10 - r - INFO: - Current episode 140 has the best eval reward: 200.000 | |
| 2023-02-04 22:34:12 - r - INFO: - Episode: 141/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:15 - r - INFO: - Episode: 142/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:18 - r - INFO: - Episode: 143/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:19 - r - INFO: - Episode: 144/200, Reward: 53.000, Step: 53 | |
| 2023-02-04 22:34:19 - r - INFO: - Episode: 145/200, Reward: 58.000, Step: 58 | |
| 2023-02-04 22:34:24 - r - INFO: - Episode: 146/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:27 - r - INFO: - Episode: 147/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:28 - r - INFO: - Episode: 148/200, Reward: 113.000, Step: 113 | |
| 2023-02-04 22:34:30 - r - INFO: - Episode: 149/200, Reward: 102.000, Step: 102 | |
| 2023-02-04 22:34:31 - r - INFO: - Episode: 150/200, Reward: 111.000, Step: 111 | |
| 2023-02-04 22:34:33 - r - INFO: - Episode: 151/200, Reward: 54.000, Step: 54 | |
| 2023-02-04 22:34:33 - r - INFO: - Episode: 152/200, Reward: 48.000, Step: 48 | |
| 2023-02-04 22:34:36 - r - INFO: - Episode: 153/200, Reward: 188.000, Step: 188 | |
| 2023-02-04 22:34:39 - r - INFO: - Episode: 154/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:41 - r - INFO: - Episode: 155/200, Reward: 172.000, Step: 172 | |
| 2023-02-04 22:34:45 - r - INFO: - Episode: 156/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:48 - r - INFO: - Episode: 157/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:34:49 - r - INFO: - Episode: 158/200, Reward: 93.000, Step: 93 | |
| 2023-02-04 22:34:52 - r - INFO: - Episode: 159/200, Reward: 183.000, Step: 183 | |
| 2023-02-04 22:34:53 - r - INFO: - Episode: 160/200, Reward: 81.000, Step: 81 | |
| 2023-02-04 22:34:55 - r - INFO: - Current episode 160 has the best eval reward: 200.000 | |
| 2023-02-04 22:34:56 - r - INFO: - Episode: 161/200, Reward: 85.000, Step: 85 | |
| 2023-02-04 22:34:57 - r - INFO: - Episode: 162/200, Reward: 47.000, Step: 47 | |
| 2023-02-04 22:34:59 - r - INFO: - Episode: 163/200, Reward: 136.000, Step: 136 | |
| 2023-02-04 22:35:01 - r - INFO: - Episode: 164/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:03 - r - INFO: - Episode: 165/200, Reward: 130.000, Step: 130 | |
| 2023-02-04 22:35:07 - r - INFO: - Episode: 166/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:10 - r - INFO: - Episode: 167/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:12 - r - INFO: - Episode: 168/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:15 - r - INFO: - Episode: 169/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:18 - r - INFO: - Episode: 170/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:19 - r - INFO: - Episode: 171/200, Reward: 37.000, Step: 37 | |
| 2023-02-04 22:35:20 - r - INFO: - Episode: 172/200, Reward: 129.000, Step: 129 | |
| 2023-02-04 22:35:23 - r - INFO: - Episode: 173/200, Reward: 153.000, Step: 153 | |
| 2023-02-04 22:35:24 - r - INFO: - Episode: 174/200, Reward: 133.000, Step: 133 | |
| 2023-02-04 22:35:26 - r - INFO: - Episode: 175/200, Reward: 106.000, Step: 106 | |
| 2023-02-04 22:35:29 - r - INFO: - Episode: 176/200, Reward: 122.000, Step: 122 | |
| 2023-02-04 22:35:30 - r - INFO: - Episode: 177/200, Reward: 78.000, Step: 78 | |
| 2023-02-04 22:35:32 - r - INFO: - Episode: 178/200, Reward: 147.000, Step: 147 | |
| 2023-02-04 22:35:34 - r - INFO: - Episode: 179/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:37 - r - INFO: - Episode: 180/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:39 - r - INFO: - Current episode 180 has the best eval reward: 200.000 | |
| 2023-02-04 22:35:42 - r - INFO: - Episode: 181/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:45 - r - INFO: - Episode: 182/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:47 - r - INFO: - Episode: 183/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:50 - r - INFO: - Episode: 184/200, Reward: 163.000, Step: 163 | |
| 2023-02-04 22:35:52 - r - INFO: - Episode: 185/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:35:54 - r - INFO: - Current episode 185 has the best eval reward: 200.000 | |
| 2023-02-04 22:35:57 - r - INFO: - Episode: 186/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:36:00 - r - INFO: - Episode: 187/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:36:02 - r - INFO: - Episode: 188/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:36:05 - r - INFO: - Episode: 189/200, Reward: 177.000, Step: 177 | |
| 2023-02-04 22:36:07 - r - INFO: - Episode: 190/200, Reward: 159.000, Step: 159 | |
| 2023-02-04 22:36:09 - r - INFO: - Current episode 190 has the best eval reward: 200.000 | |
| 2023-02-04 22:36:12 - r - INFO: - Episode: 191/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:36:13 - r - INFO: - Episode: 192/200, Reward: 44.000, Step: 44 | |
| 2023-02-04 22:36:15 - r - INFO: - Episode: 193/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:36:18 - r - INFO: - Episode: 194/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:36:21 - r - INFO: - Episode: 195/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:36:26 - r - INFO: - Episode: 196/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:36:28 - r - INFO: - Episode: 197/200, Reward: 199.000, Step: 199 | |
| 2023-02-04 22:36:29 - r - INFO: - Episode: 198/200, Reward: 13.000, Step: 13 | |
| 2023-02-04 22:36:29 - r - INFO: - Episode: 199/200, Reward: 15.000, Step: 15 | |
| 2023-02-04 22:36:31 - r - INFO: - Episode: 200/200, Reward: 200.000, Step: 200 | |
| 2023-02-04 22:36:33 - r - INFO: - Current episode 200 has the best eval reward: 200.000 | |
| 2023-02-04 22:36:33 - r - INFO: - Finish training! | |