johnjim0816's picture
update CartPole-v1 NoisyDQN
54d82df
raw
history blame
20.5 kB
2023-03-05 11:28:49 - r - INFO: - Hyperparameters:
2023-03-05 11:28:49 - r - INFO: - ================================================================================
2023-03-05 11:28:49 - r - INFO: - Name Value Type
2023-03-05 11:28:49 - r - INFO: - env_name CartPole-v1 <class 'str'>
2023-03-05 11:28:49 - r - INFO: - new_step_api 1 <class 'bool'>
2023-03-05 11:28:49 - r - INFO: - wrapper None <class 'str'>
2023-03-05 11:28:49 - r - INFO: - render 0 <class 'bool'>
2023-03-05 11:28:49 - r - INFO: - algo_name SAC_D <class 'str'>
2023-03-05 11:28:49 - r - INFO: - mode train <class 'str'>
2023-03-05 11:28:49 - r - INFO: - seed 0 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - device cuda <class 'str'>
2023-03-05 11:28:49 - r - INFO: - train_eps 200 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - test_eps 10 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - eval_eps 10 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - eval_per_episode 5 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - max_steps 200 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - load_checkpoint 0 <class 'bool'>
2023-03-05 11:28:49 - r - INFO: - load_path Train_CartPole-v1_DQN_20221026-054757 <class 'str'>
2023-03-05 11:28:49 - r - INFO: - show_fig 0 <class 'bool'>
2023-03-05 11:28:49 - r - INFO: - save_fig 1 <class 'bool'>
2023-03-05 11:28:49 - r - INFO: - epsilon_start 0.95 <class 'float'>
2023-03-05 11:28:49 - r - INFO: - epsilon_end 0.01 <class 'float'>
2023-03-05 11:28:49 - r - INFO: - epsilon_decay 500 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - lr 0.0001 <class 'float'>
2023-03-05 11:28:49 - r - INFO: - gamma 0.95 <class 'float'>
2023-03-05 11:28:49 - r - INFO: - tau 0.005 <class 'float'>
2023-03-05 11:28:49 - r - INFO: - alpha 0.2 <class 'float'>
2023-03-05 11:28:49 - r - INFO: - automatic_entropy_tuning 0 <class 'bool'>
2023-03-05 11:28:49 - r - INFO: - batch_size 64 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - hidden_dim 256 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - n_epochs 1 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - target_update 1 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - buffer_size 1000000 <class 'int'>
2023-03-05 11:28:49 - r - INFO: - task_dir /home/dingli/joyrl_offline/tasks/Train_CartPole-v1_SAC_D_20230305-112849 <class 'str'>
2023-03-05 11:28:49 - r - INFO: - model_dir /home/dingli/joyrl_offline/tasks/Train_CartPole-v1_SAC_D_20230305-112849/models <class 'str'>
2023-03-05 11:28:49 - r - INFO: - res_dir /home/dingli/joyrl_offline/tasks/Train_CartPole-v1_SAC_D_20230305-112849/results <class 'str'>
2023-03-05 11:28:49 - r - INFO: - log_dir /home/dingli/joyrl_offline/tasks/Train_CartPole-v1_SAC_D_20230305-112849/logs <class 'str'>
2023-03-05 11:28:49 - r - INFO: - traj_dir /home/dingli/joyrl_offline/tasks/Train_CartPole-v1_SAC_D_20230305-112849/traj <class 'str'>
2023-03-05 11:28:49 - r - INFO: - ================================================================================
2023-03-05 11:28:49 - r - INFO: - n_states: 4, n_actions: 2
2023-03-05 11:28:51 - r - INFO: - Start training!
2023-03-05 11:28:51 - r - INFO: - Env: CartPole-v1, Algorithm: SAC_D, Device: cuda
2023-03-05 11:28:51 - r - INFO: - Episode: 1/200, Reward: 17.000, Step: 17
2023-03-05 11:28:52 - r - INFO: - Episode: 2/200, Reward: 77.000, Step: 77
2023-03-05 11:28:52 - r - INFO: - Episode: 3/200, Reward: 33.000, Step: 33
2023-03-05 11:28:52 - r - INFO: - Episode: 4/200, Reward: 25.000, Step: 25
2023-03-05 11:28:53 - r - INFO: - Episode: 5/200, Reward: 49.000, Step: 49
2023-03-05 11:28:53 - r - INFO: - Current episode 5 has the best eval reward: 63.300
2023-03-05 11:28:53 - r - INFO: - Episode: 6/200, Reward: 31.000, Step: 31
2023-03-05 11:28:53 - r - INFO: - Episode: 7/200, Reward: 35.000, Step: 35
2023-03-05 11:28:54 - r - INFO: - Episode: 8/200, Reward: 15.000, Step: 15
2023-03-05 11:28:54 - r - INFO: - Episode: 9/200, Reward: 10.000, Step: 10
2023-03-05 11:28:54 - r - INFO: - Episode: 10/200, Reward: 11.000, Step: 11
2023-03-05 11:28:54 - r - INFO: - Episode: 11/200, Reward: 16.000, Step: 16
2023-03-05 11:28:54 - r - INFO: - Episode: 12/200, Reward: 10.000, Step: 10
2023-03-05 11:28:54 - r - INFO: - Episode: 13/200, Reward: 16.000, Step: 16
2023-03-05 11:28:54 - r - INFO: - Episode: 14/200, Reward: 8.000, Step: 8
2023-03-05 11:28:54 - r - INFO: - Episode: 15/200, Reward: 11.000, Step: 11
2023-03-05 11:28:54 - r - INFO: - Episode: 16/200, Reward: 14.000, Step: 14
2023-03-05 11:28:54 - r - INFO: - Episode: 17/200, Reward: 11.000, Step: 11
2023-03-05 11:28:55 - r - INFO: - Episode: 18/200, Reward: 10.000, Step: 10
2023-03-05 11:28:55 - r - INFO: - Episode: 19/200, Reward: 14.000, Step: 14
2023-03-05 11:28:55 - r - INFO: - Episode: 20/200, Reward: 14.000, Step: 14
2023-03-05 11:28:55 - r - INFO: - Episode: 21/200, Reward: 15.000, Step: 15
2023-03-05 11:28:55 - r - INFO: - Episode: 22/200, Reward: 9.000, Step: 9
2023-03-05 11:28:55 - r - INFO: - Episode: 23/200, Reward: 13.000, Step: 13
2023-03-05 11:28:55 - r - INFO: - Episode: 24/200, Reward: 12.000, Step: 12
2023-03-05 11:28:55 - r - INFO: - Episode: 25/200, Reward: 14.000, Step: 14
2023-03-05 11:28:55 - r - INFO: - Episode: 26/200, Reward: 9.000, Step: 9
2023-03-05 11:28:55 - r - INFO: - Episode: 27/200, Reward: 10.000, Step: 10
2023-03-05 11:28:55 - r - INFO: - Episode: 28/200, Reward: 10.000, Step: 10
2023-03-05 11:28:56 - r - INFO: - Episode: 29/200, Reward: 12.000, Step: 12
2023-03-05 11:28:56 - r - INFO: - Episode: 30/200, Reward: 9.000, Step: 9
2023-03-05 11:28:56 - r - INFO: - Episode: 31/200, Reward: 9.000, Step: 9
2023-03-05 11:28:56 - r - INFO: - Episode: 32/200, Reward: 9.000, Step: 9
2023-03-05 11:28:56 - r - INFO: - Episode: 33/200, Reward: 10.000, Step: 10
2023-03-05 11:28:56 - r - INFO: - Episode: 34/200, Reward: 9.000, Step: 9
2023-03-05 11:28:56 - r - INFO: - Episode: 35/200, Reward: 9.000, Step: 9
2023-03-05 11:28:56 - r - INFO: - Episode: 36/200, Reward: 9.000, Step: 9
2023-03-05 11:28:56 - r - INFO: - Episode: 37/200, Reward: 10.000, Step: 10
2023-03-05 11:28:56 - r - INFO: - Episode: 38/200, Reward: 9.000, Step: 9
2023-03-05 11:28:56 - r - INFO: - Episode: 39/200, Reward: 9.000, Step: 9
2023-03-05 11:28:56 - r - INFO: - Episode: 40/200, Reward: 12.000, Step: 12
2023-03-05 11:28:56 - r - INFO: - Episode: 41/200, Reward: 10.000, Step: 10
2023-03-05 11:28:57 - r - INFO: - Episode: 42/200, Reward: 9.000, Step: 9
2023-03-05 11:28:57 - r - INFO: - Episode: 43/200, Reward: 10.000, Step: 10
2023-03-05 11:28:57 - r - INFO: - Episode: 44/200, Reward: 10.000, Step: 10
2023-03-05 11:28:57 - r - INFO: - Episode: 45/200, Reward: 12.000, Step: 12
2023-03-05 11:28:57 - r - INFO: - Episode: 46/200, Reward: 12.000, Step: 12
2023-03-05 11:28:57 - r - INFO: - Episode: 47/200, Reward: 11.000, Step: 11
2023-03-05 11:28:57 - r - INFO: - Episode: 48/200, Reward: 13.000, Step: 13
2023-03-05 11:28:57 - r - INFO: - Episode: 49/200, Reward: 10.000, Step: 10
2023-03-05 11:28:57 - r - INFO: - Episode: 50/200, Reward: 12.000, Step: 12
2023-03-05 11:28:57 - r - INFO: - Episode: 51/200, Reward: 12.000, Step: 12
2023-03-05 11:28:58 - r - INFO: - Episode: 52/200, Reward: 24.000, Step: 24
2023-03-05 11:28:58 - r - INFO: - Episode: 53/200, Reward: 68.000, Step: 68
2023-03-05 11:28:58 - r - INFO: - Episode: 54/200, Reward: 12.000, Step: 12
2023-03-05 11:28:59 - r - INFO: - Episode: 55/200, Reward: 16.000, Step: 16
2023-03-05 11:28:59 - r - INFO: - Episode: 56/200, Reward: 83.000, Step: 83
2023-03-05 11:29:00 - r - INFO: - Episode: 57/200, Reward: 122.000, Step: 122
2023-03-05 11:29:00 - r - INFO: - Episode: 58/200, Reward: 28.000, Step: 28
2023-03-05 11:29:01 - r - INFO: - Episode: 59/200, Reward: 55.000, Step: 55
2023-03-05 11:29:01 - r - INFO: - Episode: 60/200, Reward: 32.000, Step: 32
2023-03-05 11:29:02 - r - INFO: - Episode: 61/200, Reward: 41.000, Step: 41
2023-03-05 11:29:02 - r - INFO: - Episode: 62/200, Reward: 33.000, Step: 33
2023-03-05 11:29:02 - r - INFO: - Episode: 63/200, Reward: 21.000, Step: 21
2023-03-05 11:29:02 - r - INFO: - Episode: 64/200, Reward: 19.000, Step: 19
2023-03-05 11:29:02 - r - INFO: - Episode: 65/200, Reward: 19.000, Step: 19
2023-03-05 11:29:03 - r - INFO: - Episode: 66/200, Reward: 27.000, Step: 27
2023-03-05 11:29:03 - r - INFO: - Episode: 67/200, Reward: 30.000, Step: 30
2023-03-05 11:29:03 - r - INFO: - Episode: 68/200, Reward: 25.000, Step: 25
2023-03-05 11:29:03 - r - INFO: - Episode: 69/200, Reward: 23.000, Step: 23
2023-03-05 11:29:04 - r - INFO: - Episode: 70/200, Reward: 27.000, Step: 27
2023-03-05 11:29:04 - r - INFO: - Episode: 71/200, Reward: 26.000, Step: 26
2023-03-05 11:29:04 - r - INFO: - Episode: 72/200, Reward: 26.000, Step: 26
2023-03-05 11:29:05 - r - INFO: - Episode: 73/200, Reward: 33.000, Step: 33
2023-03-05 11:29:05 - r - INFO: - Episode: 74/200, Reward: 43.000, Step: 43
2023-03-05 11:29:05 - r - INFO: - Episode: 75/200, Reward: 26.000, Step: 26
2023-03-05 11:29:05 - r - INFO: - Episode: 76/200, Reward: 25.000, Step: 25
2023-03-05 11:29:06 - r - INFO: - Episode: 77/200, Reward: 23.000, Step: 23
2023-03-05 11:29:06 - r - INFO: - Episode: 78/200, Reward: 41.000, Step: 41
2023-03-05 11:29:06 - r - INFO: - Episode: 79/200, Reward: 36.000, Step: 36
2023-03-05 11:29:07 - r - INFO: - Episode: 80/200, Reward: 36.000, Step: 36
2023-03-05 11:29:07 - r - INFO: - Episode: 81/200, Reward: 31.000, Step: 31
2023-03-05 11:29:07 - r - INFO: - Episode: 82/200, Reward: 27.000, Step: 27
2023-03-05 11:29:07 - r - INFO: - Episode: 83/200, Reward: 27.000, Step: 27
2023-03-05 11:29:08 - r - INFO: - Episode: 84/200, Reward: 28.000, Step: 28
2023-03-05 11:29:08 - r - INFO: - Episode: 85/200, Reward: 27.000, Step: 27
2023-03-05 11:29:08 - r - INFO: - Episode: 86/200, Reward: 29.000, Step: 29
2023-03-05 11:29:09 - r - INFO: - Episode: 87/200, Reward: 25.000, Step: 25
2023-03-05 11:29:09 - r - INFO: - Episode: 88/200, Reward: 59.000, Step: 59
2023-03-05 11:29:09 - r - INFO: - Episode: 89/200, Reward: 30.000, Step: 30
2023-03-05 11:29:10 - r - INFO: - Episode: 90/200, Reward: 91.000, Step: 91
2023-03-05 11:29:10 - r - INFO: - Episode: 91/200, Reward: 33.000, Step: 33
2023-03-05 11:29:11 - r - INFO: - Episode: 92/200, Reward: 77.000, Step: 77
2023-03-05 11:29:11 - r - INFO: - Episode: 93/200, Reward: 42.000, Step: 42
2023-03-05 11:29:12 - r - INFO: - Episode: 94/200, Reward: 57.000, Step: 57
2023-03-05 11:29:13 - r - INFO: - Episode: 95/200, Reward: 75.000, Step: 75
2023-03-05 11:29:13 - r - INFO: - Episode: 96/200, Reward: 55.000, Step: 55
2023-03-05 11:29:14 - r - INFO: - Episode: 97/200, Reward: 42.000, Step: 42
2023-03-05 11:29:14 - r - INFO: - Episode: 98/200, Reward: 43.000, Step: 43
2023-03-05 11:29:15 - r - INFO: - Episode: 99/200, Reward: 92.000, Step: 92
2023-03-05 11:29:15 - r - INFO: - Episode: 100/200, Reward: 41.000, Step: 41
2023-03-05 11:29:16 - r - INFO: - Episode: 101/200, Reward: 72.000, Step: 72
2023-03-05 11:29:18 - r - INFO: - Episode: 102/200, Reward: 200.000, Step: 200
2023-03-05 11:29:19 - r - INFO: - Episode: 103/200, Reward: 115.000, Step: 115
2023-03-05 11:29:20 - r - INFO: - Episode: 104/200, Reward: 90.000, Step: 90
2023-03-05 11:29:21 - r - INFO: - Episode: 105/200, Reward: 97.000, Step: 97
2023-03-05 11:29:21 - r - INFO: - Current episode 105 has the best eval reward: 145.500
2023-03-05 11:29:22 - r - INFO: - Episode: 106/200, Reward: 143.000, Step: 143
2023-03-05 11:29:23 - r - INFO: - Episode: 107/200, Reward: 109.000, Step: 109
2023-03-05 11:29:25 - r - INFO: - Episode: 108/200, Reward: 200.000, Step: 200
2023-03-05 11:29:26 - r - INFO: - Episode: 109/200, Reward: 168.000, Step: 168
2023-03-05 11:29:28 - r - INFO: - Episode: 110/200, Reward: 158.000, Step: 158
2023-03-05 11:29:28 - r - INFO: - Current episode 110 has the best eval reward: 150.100
2023-03-05 11:29:30 - r - INFO: - Episode: 111/200, Reward: 200.000, Step: 200
2023-03-05 11:29:31 - r - INFO: - Episode: 112/200, Reward: 133.000, Step: 133
2023-03-05 11:29:32 - r - INFO: - Episode: 113/200, Reward: 123.000, Step: 123
2023-03-05 11:29:33 - r - INFO: - Episode: 114/200, Reward: 135.000, Step: 135
2023-03-05 11:29:34 - r - INFO: - Episode: 115/200, Reward: 133.000, Step: 133
2023-03-05 11:29:35 - r - INFO: - Current episode 115 has the best eval reward: 181.400
2023-03-05 11:29:36 - r - INFO: - Episode: 116/200, Reward: 136.000, Step: 136
2023-03-05 11:29:37 - r - INFO: - Episode: 117/200, Reward: 141.000, Step: 141
2023-03-05 11:29:38 - r - INFO: - Episode: 118/200, Reward: 120.000, Step: 120
2023-03-05 11:29:39 - r - INFO: - Episode: 119/200, Reward: 156.000, Step: 156
2023-03-05 11:29:41 - r - INFO: - Episode: 120/200, Reward: 200.000, Step: 200
2023-03-05 11:29:41 - r - INFO: - Current episode 120 has the best eval reward: 192.200
2023-03-05 11:29:43 - r - INFO: - Episode: 121/200, Reward: 174.000, Step: 174
2023-03-05 11:29:44 - r - INFO: - Episode: 122/200, Reward: 158.000, Step: 158
2023-03-05 11:29:45 - r - INFO: - Episode: 123/200, Reward: 124.000, Step: 124
2023-03-05 11:29:47 - r - INFO: - Episode: 124/200, Reward: 200.000, Step: 200
2023-03-05 11:29:48 - r - INFO: - Episode: 125/200, Reward: 162.000, Step: 162
2023-03-05 11:29:51 - r - INFO: - Episode: 126/200, Reward: 200.000, Step: 200
2023-03-05 11:29:52 - r - INFO: - Episode: 127/200, Reward: 141.000, Step: 141
2023-03-05 11:29:53 - r - INFO: - Episode: 128/200, Reward: 192.000, Step: 192
2023-03-05 11:29:55 - r - INFO: - Episode: 129/200, Reward: 176.000, Step: 176
2023-03-05 11:29:56 - r - INFO: - Episode: 130/200, Reward: 127.000, Step: 127
2023-03-05 11:29:58 - r - INFO: - Episode: 131/200, Reward: 200.000, Step: 200
2023-03-05 11:29:59 - r - INFO: - Episode: 132/200, Reward: 200.000, Step: 200
2023-03-05 11:30:01 - r - INFO: - Episode: 133/200, Reward: 200.000, Step: 200
2023-03-05 11:30:02 - r - INFO: - Episode: 134/200, Reward: 150.000, Step: 150
2023-03-05 11:30:03 - r - INFO: - Episode: 135/200, Reward: 139.000, Step: 139
2023-03-05 11:30:05 - r - INFO: - Episode: 136/200, Reward: 171.000, Step: 171
2023-03-05 11:30:07 - r - INFO: - Episode: 137/200, Reward: 200.000, Step: 200
2023-03-05 11:30:09 - r - INFO: - Episode: 138/200, Reward: 179.000, Step: 179
2023-03-05 11:30:10 - r - INFO: - Episode: 139/200, Reward: 200.000, Step: 200
2023-03-05 11:30:12 - r - INFO: - Episode: 140/200, Reward: 187.000, Step: 187
2023-03-05 11:30:14 - r - INFO: - Episode: 141/200, Reward: 200.000, Step: 200
2023-03-05 11:30:16 - r - INFO: - Episode: 142/200, Reward: 170.000, Step: 170
2023-03-05 11:30:17 - r - INFO: - Episode: 143/200, Reward: 200.000, Step: 200
2023-03-05 11:30:19 - r - INFO: - Episode: 144/200, Reward: 182.000, Step: 182
2023-03-05 11:30:20 - r - INFO: - Episode: 145/200, Reward: 117.000, Step: 117
2023-03-05 11:30:22 - r - INFO: - Episode: 146/200, Reward: 200.000, Step: 200
2023-03-05 11:30:24 - r - INFO: - Episode: 147/200, Reward: 149.000, Step: 149
2023-03-05 11:30:25 - r - INFO: - Episode: 148/200, Reward: 158.000, Step: 158
2023-03-05 11:30:27 - r - INFO: - Episode: 149/200, Reward: 196.000, Step: 196
2023-03-05 11:30:29 - r - INFO: - Episode: 150/200, Reward: 198.000, Step: 198
2023-03-05 11:30:31 - r - INFO: - Episode: 151/200, Reward: 200.000, Step: 200
2023-03-05 11:30:33 - r - INFO: - Episode: 152/200, Reward: 200.000, Step: 200
2023-03-05 11:30:34 - r - INFO: - Episode: 153/200, Reward: 198.000, Step: 198
2023-03-05 11:30:36 - r - INFO: - Episode: 154/200, Reward: 176.000, Step: 176
2023-03-05 11:30:38 - r - INFO: - Episode: 155/200, Reward: 200.000, Step: 200
2023-03-05 11:30:40 - r - INFO: - Episode: 156/200, Reward: 195.000, Step: 195
2023-03-05 11:30:41 - r - INFO: - Episode: 157/200, Reward: 168.000, Step: 168
2023-03-05 11:30:42 - r - INFO: - Episode: 158/200, Reward: 167.000, Step: 167
2023-03-05 11:30:44 - r - INFO: - Episode: 159/200, Reward: 195.000, Step: 195
2023-03-05 11:30:46 - r - INFO: - Episode: 160/200, Reward: 196.000, Step: 196
2023-03-05 11:30:48 - r - INFO: - Episode: 161/200, Reward: 195.000, Step: 195
2023-03-05 11:30:49 - r - INFO: - Episode: 162/200, Reward: 172.000, Step: 172
2023-03-05 11:30:51 - r - INFO: - Episode: 163/200, Reward: 142.000, Step: 142
2023-03-05 11:30:52 - r - INFO: - Episode: 164/200, Reward: 167.000, Step: 167
2023-03-05 11:30:54 - r - INFO: - Episode: 165/200, Reward: 191.000, Step: 191
2023-03-05 11:30:56 - r - INFO: - Episode: 166/200, Reward: 173.000, Step: 173
2023-03-05 11:30:57 - r - INFO: - Episode: 167/200, Reward: 181.000, Step: 181
2023-03-05 11:30:59 - r - INFO: - Episode: 168/200, Reward: 200.000, Step: 200
2023-03-05 11:31:01 - r - INFO: - Episode: 169/200, Reward: 180.000, Step: 180
2023-03-05 11:31:02 - r - INFO: - Episode: 170/200, Reward: 200.000, Step: 200
2023-03-05 11:31:03 - r - INFO: - Current episode 170 has the best eval reward: 198.500
2023-03-05 11:31:04 - r - INFO: - Episode: 171/200, Reward: 200.000, Step: 200
2023-03-05 11:31:06 - r - INFO: - Episode: 172/200, Reward: 174.000, Step: 174
2023-03-05 11:31:07 - r - INFO: - Episode: 173/200, Reward: 189.000, Step: 189
2023-03-05 11:31:09 - r - INFO: - Episode: 174/200, Reward: 200.000, Step: 200
2023-03-05 11:31:11 - r - INFO: - Episode: 175/200, Reward: 195.000, Step: 195
2023-03-05 11:31:13 - r - INFO: - Episode: 176/200, Reward: 200.000, Step: 200
2023-03-05 11:31:15 - r - INFO: - Episode: 177/200, Reward: 200.000, Step: 200
2023-03-05 11:31:16 - r - INFO: - Episode: 178/200, Reward: 200.000, Step: 200
2023-03-05 11:31:18 - r - INFO: - Episode: 179/200, Reward: 200.000, Step: 200
2023-03-05 11:31:20 - r - INFO: - Episode: 180/200, Reward: 200.000, Step: 200
2023-03-05 11:31:22 - r - INFO: - Episode: 181/200, Reward: 200.000, Step: 200
2023-03-05 11:31:24 - r - INFO: - Episode: 182/200, Reward: 200.000, Step: 200
2023-03-05 11:31:25 - r - INFO: - Episode: 183/200, Reward: 184.000, Step: 184
2023-03-05 11:31:27 - r - INFO: - Episode: 184/200, Reward: 200.000, Step: 200
2023-03-05 11:31:29 - r - INFO: - Episode: 185/200, Reward: 200.000, Step: 200
2023-03-05 11:31:29 - r - INFO: - Current episode 185 has the best eval reward: 200.000
2023-03-05 11:31:31 - r - INFO: - Episode: 186/200, Reward: 200.000, Step: 200
2023-03-05 11:31:33 - r - INFO: - Episode: 187/200, Reward: 200.000, Step: 200
2023-03-05 11:31:34 - r - INFO: - Episode: 188/200, Reward: 200.000, Step: 200
2023-03-05 11:31:36 - r - INFO: - Episode: 189/200, Reward: 200.000, Step: 200
2023-03-05 11:31:38 - r - INFO: - Episode: 190/200, Reward: 200.000, Step: 200
2023-03-05 11:31:40 - r - INFO: - Episode: 191/200, Reward: 200.000, Step: 200
2023-03-05 11:31:42 - r - INFO: - Episode: 192/200, Reward: 200.000, Step: 200
2023-03-05 11:31:44 - r - INFO: - Episode: 193/200, Reward: 200.000, Step: 200
2023-03-05 11:31:45 - r - INFO: - Episode: 194/200, Reward: 200.000, Step: 200
2023-03-05 11:31:47 - r - INFO: - Episode: 195/200, Reward: 200.000, Step: 200
2023-03-05 11:31:47 - r - INFO: - Current episode 195 has the best eval reward: 200.000
2023-03-05 11:31:49 - r - INFO: - Episode: 196/200, Reward: 200.000, Step: 200
2023-03-05 11:31:51 - r - INFO: - Episode: 197/200, Reward: 200.000, Step: 200
2023-03-05 11:31:53 - r - INFO: - Episode: 198/200, Reward: 200.000, Step: 200
2023-03-05 11:31:55 - r - INFO: - Episode: 199/200, Reward: 200.000, Step: 200
2023-03-05 11:31:56 - r - INFO: - Episode: 200/200, Reward: 200.000, Step: 200
2023-03-05 11:31:57 - r - INFO: - Finish training!