2023-02-20 21:29:59 - r - INFO: - Hyperparameters:
2023-02-20 21:29:59 - r - INFO: - ================================================================================
2023-02-20 21:29:59 - r - INFO: -         Name        	       Value        	        Type        
2023-02-20 21:29:59 - r - INFO: -       env_name      	    CartPole-v1     	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -     new_step_api    	         1          	   <class 'bool'>   
2023-02-20 21:29:59 - r - INFO: -       wrapper       	        None        	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -        render       	         0          	   <class 'bool'>   
2023-02-20 21:29:59 - r - INFO: -      algo_name      	        PPO         	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -         mode        	       train        	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -         seed        	         1          	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -        device       	        cuda        	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -      train_eps      	        200         	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -       test_eps      	         10         	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -       eval_eps      	         10         	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -   eval_per_episode  	         5          	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -      max_steps      	        200         	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -   load_checkpoint   	         0          	   <class 'bool'>   
2023-02-20 21:29:59 - r - INFO: -      load_path      	Train_CartPole-v1_DQN_20221026-054757	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -       show_fig      	         0          	   <class 'bool'>   
2023-02-20 21:29:59 - r - INFO: -       save_fig      	         1          	   <class 'bool'>   
2023-02-20 21:29:59 - r - INFO: -       ppo_type      	        clip        	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -      continuous     	         0          	   <class 'bool'>   
2023-02-20 21:29:59 - r - INFO: -        gamma        	        0.99        	  <class 'float'>   
2023-02-20 21:29:59 - r - INFO: -       k_epochs      	         4          	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -       actor_lr      	       0.0003       	  <class 'float'>   
2023-02-20 21:29:59 - r - INFO: -      critic_lr      	       0.001        	  <class 'float'>   
2023-02-20 21:29:59 - r - INFO: -       eps_clip      	        0.2         	  <class 'float'>   
2023-02-20 21:29:59 - r - INFO: -     entropy_coef    	        0.01        	  <class 'float'>   
2023-02-20 21:29:59 - r - INFO: -   train_batch_size  	        256         	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -    sgd_batch_size   	        128         	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -   actor_hidden_dim  	        256         	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -  critic_hidden_dim  	        256         	   <class 'int'>    
2023-02-20 21:29:59 - r - INFO: -       task_dir      	C:\Users\24438\Desktop\rl-tutorials\joyrl/tasks/Train_CartPole-v1_PPO_20230220-212959	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -      model_dir      	C:\Users\24438\Desktop\rl-tutorials\joyrl/tasks/Train_CartPole-v1_PPO_20230220-212959/models	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -       res_dir       	C:\Users\24438\Desktop\rl-tutorials\joyrl/tasks/Train_CartPole-v1_PPO_20230220-212959/results	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -       log_dir       	C:\Users\24438\Desktop\rl-tutorials\joyrl/tasks/Train_CartPole-v1_PPO_20230220-212959/logs	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: -       traj_dir      	C:\Users\24438\Desktop\rl-tutorials\joyrl/tasks/Train_CartPole-v1_PPO_20230220-212959/traj	   <class 'str'>    
2023-02-20 21:29:59 - r - INFO: - ================================================================================
2023-02-20 21:29:59 - r - INFO: - n_states: 4, n_actions: 2
2023-02-20 21:29:59 - r - INFO: - Start training!
2023-02-20 21:29:59 - r - INFO: - Env: CartPole-v1, Algorithm: PPO, Device: cuda
2023-02-20 21:30:01 - r - INFO: - Episode: 1/200, Reward: 25.000, Step: 25
2023-02-20 21:30:01 - r - INFO: - Episode: 2/200, Reward: 15.000, Step: 15
2023-02-20 21:30:01 - r - INFO: - Episode: 3/200, Reward: 13.000, Step: 13
2023-02-20 21:30:01 - r - INFO: - Episode: 4/200, Reward: 14.000, Step: 14
2023-02-20 21:30:01 - r - INFO: - Episode: 5/200, Reward: 25.000, Step: 25
2023-02-20 21:30:01 - r - INFO: - Current episode 5 has the best eval reward: 23.900
2023-02-20 21:30:01 - r - INFO: - Episode: 6/200, Reward: 41.000, Step: 41
2023-02-20 21:30:01 - r - INFO: - Episode: 7/200, Reward: 33.000, Step: 33
2023-02-20 21:30:01 - r - INFO: - Episode: 8/200, Reward: 12.000, Step: 12
2023-02-20 21:30:01 - r - INFO: - Episode: 9/200, Reward: 20.000, Step: 20
2023-02-20 21:30:01 - r - INFO: - Episode: 10/200, Reward: 33.000, Step: 33
2023-02-20 21:30:02 - r - INFO: - Current episode 10 has the best eval reward: 27.400
2023-02-20 21:30:02 - r - INFO: - Episode: 11/200, Reward: 19.000, Step: 19
2023-02-20 21:30:02 - r - INFO: - Episode: 12/200, Reward: 35.000, Step: 35
2023-02-20 21:30:02 - r - INFO: - Episode: 13/200, Reward: 35.000, Step: 35
2023-02-20 21:30:02 - r - INFO: - Episode: 14/200, Reward: 9.000, Step: 9
2023-02-20 21:30:02 - r - INFO: - Episode: 15/200, Reward: 32.000, Step: 32
2023-02-20 21:30:02 - r - INFO: - Current episode 15 has the best eval reward: 37.600
2023-02-20 21:30:02 - r - INFO: - Episode: 16/200, Reward: 29.000, Step: 29
2023-02-20 21:30:02 - r - INFO: - Episode: 17/200, Reward: 17.000, Step: 17
2023-02-20 21:30:02 - r - INFO: - Episode: 18/200, Reward: 17.000, Step: 17
2023-02-20 21:30:02 - r - INFO: - Episode: 19/200, Reward: 17.000, Step: 17
2023-02-20 21:30:02 - r - INFO: - Episode: 20/200, Reward: 20.000, Step: 20
2023-02-20 21:30:03 - r - INFO: - Episode: 21/200, Reward: 24.000, Step: 24
2023-02-20 21:30:03 - r - INFO: - Episode: 22/200, Reward: 44.000, Step: 44
2023-02-20 21:30:03 - r - INFO: - Episode: 23/200, Reward: 39.000, Step: 39
2023-02-20 21:30:03 - r - INFO: - Episode: 24/200, Reward: 48.000, Step: 48
2023-02-20 21:30:03 - r - INFO: - Episode: 25/200, Reward: 52.000, Step: 52
2023-02-20 21:30:03 - r - INFO: - Episode: 26/200, Reward: 32.000, Step: 32
2023-02-20 21:30:03 - r - INFO: - Episode: 27/200, Reward: 45.000, Step: 45
2023-02-20 21:30:04 - r - INFO: - Episode: 28/200, Reward: 68.000, Step: 68
2023-02-20 21:30:04 - r - INFO: - Episode: 29/200, Reward: 45.000, Step: 45
2023-02-20 21:30:04 - r - INFO: - Episode: 30/200, Reward: 16.000, Step: 16
2023-02-20 21:30:04 - r - INFO: - Current episode 30 has the best eval reward: 45.300
2023-02-20 21:30:04 - r - INFO: - Episode: 31/200, Reward: 38.000, Step: 38
2023-02-20 21:30:04 - r - INFO: - Episode: 32/200, Reward: 17.000, Step: 17
2023-02-20 21:30:04 - r - INFO: - Episode: 33/200, Reward: 35.000, Step: 35
2023-02-20 21:30:04 - r - INFO: - Episode: 34/200, Reward: 12.000, Step: 12
2023-02-20 21:30:04 - r - INFO: - Episode: 35/200, Reward: 56.000, Step: 56
2023-02-20 21:30:05 - r - INFO: - Episode: 36/200, Reward: 36.000, Step: 36
2023-02-20 21:30:05 - r - INFO: - Episode: 37/200, Reward: 15.000, Step: 15
2023-02-20 21:30:05 - r - INFO: - Episode: 38/200, Reward: 25.000, Step: 25
2023-02-20 21:30:05 - r - INFO: - Episode: 39/200, Reward: 28.000, Step: 28
2023-02-20 21:30:05 - r - INFO: - Episode: 40/200, Reward: 56.000, Step: 56
2023-02-20 21:30:05 - r - INFO: - Episode: 41/200, Reward: 18.000, Step: 18
2023-02-20 21:30:05 - r - INFO: - Episode: 42/200, Reward: 33.000, Step: 33
2023-02-20 21:30:05 - r - INFO: - Episode: 43/200, Reward: 30.000, Step: 30
2023-02-20 21:30:05 - r - INFO: - Episode: 44/200, Reward: 30.000, Step: 30
2023-02-20 21:30:06 - r - INFO: - Episode: 45/200, Reward: 28.000, Step: 28
2023-02-20 21:30:06 - r - INFO: - Episode: 46/200, Reward: 38.000, Step: 38
2023-02-20 21:30:06 - r - INFO: - Episode: 47/200, Reward: 70.000, Step: 70
2023-02-20 21:30:06 - r - INFO: - Episode: 48/200, Reward: 18.000, Step: 18
2023-02-20 21:30:06 - r - INFO: - Episode: 49/200, Reward: 16.000, Step: 16
2023-02-20 21:30:06 - r - INFO: - Episode: 50/200, Reward: 36.000, Step: 36
2023-02-20 21:30:07 - r - INFO: - Current episode 50 has the best eval reward: 48.700
2023-02-20 21:30:07 - r - INFO: - Episode: 51/200, Reward: 26.000, Step: 26
2023-02-20 21:30:07 - r - INFO: - Episode: 52/200, Reward: 34.000, Step: 34
2023-02-20 21:30:07 - r - INFO: - Episode: 53/200, Reward: 70.000, Step: 70
2023-02-20 21:30:07 - r - INFO: - Episode: 54/200, Reward: 39.000, Step: 39
2023-02-20 21:30:07 - r - INFO: - Episode: 55/200, Reward: 87.000, Step: 87
2023-02-20 21:30:08 - r - INFO: - Episode: 56/200, Reward: 75.000, Step: 75
2023-02-20 21:30:08 - r - INFO: - Episode: 57/200, Reward: 21.000, Step: 21
2023-02-20 21:30:08 - r - INFO: - Episode: 58/200, Reward: 72.000, Step: 72
2023-02-20 21:30:08 - r - INFO: - Episode: 59/200, Reward: 43.000, Step: 43
2023-02-20 21:30:08 - r - INFO: - Episode: 60/200, Reward: 48.000, Step: 48
2023-02-20 21:30:09 - r - INFO: - Episode: 61/200, Reward: 64.000, Step: 64
2023-02-20 21:30:09 - r - INFO: - Episode: 62/200, Reward: 135.000, Step: 135
2023-02-20 21:30:09 - r - INFO: - Episode: 63/200, Reward: 108.000, Step: 108
2023-02-20 21:30:09 - r - INFO: - Episode: 64/200, Reward: 38.000, Step: 38
2023-02-20 21:30:09 - r - INFO: - Episode: 65/200, Reward: 22.000, Step: 22
2023-02-20 21:30:10 - r - INFO: - Current episode 65 has the best eval reward: 68.000
2023-02-20 21:30:10 - r - INFO: - Episode: 66/200, Reward: 60.000, Step: 60
2023-02-20 21:30:10 - r - INFO: - Episode: 67/200, Reward: 74.000, Step: 74
2023-02-20 21:30:10 - r - INFO: - Episode: 68/200, Reward: 93.000, Step: 93
2023-02-20 21:30:10 - r - INFO: - Episode: 69/200, Reward: 55.000, Step: 55
2023-02-20 21:30:10 - r - INFO: - Episode: 70/200, Reward: 48.000, Step: 48
2023-02-20 21:30:11 - r - INFO: - Episode: 71/200, Reward: 29.000, Step: 29
2023-02-20 21:30:11 - r - INFO: - Episode: 72/200, Reward: 59.000, Step: 59
2023-02-20 21:30:11 - r - INFO: - Episode: 73/200, Reward: 35.000, Step: 35
2023-02-20 21:30:11 - r - INFO: - Episode: 74/200, Reward: 40.000, Step: 40
2023-02-20 21:30:11 - r - INFO: - Episode: 75/200, Reward: 113.000, Step: 113
2023-02-20 21:30:12 - r - INFO: - Episode: 76/200, Reward: 114.000, Step: 114
2023-02-20 21:30:12 - r - INFO: - Episode: 77/200, Reward: 52.000, Step: 52
2023-02-20 21:30:13 - r - INFO: - Episode: 78/200, Reward: 139.000, Step: 139
2023-02-20 21:30:13 - r - INFO: - Episode: 79/200, Reward: 138.000, Step: 138
2023-02-20 21:30:13 - r - INFO: - Episode: 80/200, Reward: 54.000, Step: 54
2023-02-20 21:30:14 - r - INFO: - Current episode 80 has the best eval reward: 110.900
2023-02-20 21:30:14 - r - INFO: - Episode: 81/200, Reward: 156.000, Step: 156
2023-02-20 21:30:15 - r - INFO: - Episode: 82/200, Reward: 140.000, Step: 140
2023-02-20 21:30:15 - r - INFO: - Episode: 83/200, Reward: 144.000, Step: 144
2023-02-20 21:30:15 - r - INFO: - Episode: 84/200, Reward: 118.000, Step: 118
2023-02-20 21:30:15 - r - INFO: - Episode: 85/200, Reward: 156.000, Step: 156
2023-02-20 21:30:16 - r - INFO: - Episode: 86/200, Reward: 135.000, Step: 135
2023-02-20 21:30:17 - r - INFO: - Episode: 87/200, Reward: 144.000, Step: 144
2023-02-20 21:30:17 - r - INFO: - Episode: 88/200, Reward: 160.000, Step: 160
2023-02-20 21:30:17 - r - INFO: - Episode: 89/200, Reward: 30.000, Step: 30
2023-02-20 21:30:17 - r - INFO: - Episode: 90/200, Reward: 194.000, Step: 194
2023-02-20 21:30:19 - r - INFO: - Current episode 90 has the best eval reward: 169.300
2023-02-20 21:30:20 - r - INFO: - Episode: 91/200, Reward: 200.000, Step: 200
2023-02-20 21:30:20 - r - INFO: - Episode: 92/200, Reward: 200.000, Step: 200
2023-02-20 21:30:20 - r - INFO: - Episode: 93/200, Reward: 160.000, Step: 160
2023-02-20 21:30:21 - r - INFO: - Episode: 94/200, Reward: 200.000, Step: 200
2023-02-20 21:30:21 - r - INFO: - Episode: 95/200, Reward: 59.000, Step: 59
2023-02-20 21:30:23 - r - INFO: - Episode: 96/200, Reward: 200.000, Step: 200
2023-02-20 21:30:23 - r - INFO: - Episode: 97/200, Reward: 182.000, Step: 182
2023-02-20 21:30:23 - r - INFO: - Episode: 98/200, Reward: 125.000, Step: 125
2023-02-20 21:30:23 - r - INFO: - Episode: 99/200, Reward: 140.000, Step: 140
2023-02-20 21:30:24 - r - INFO: - Episode: 100/200, Reward: 146.000, Step: 146
2023-02-20 21:30:25 - r - INFO: - Episode: 101/200, Reward: 130.000, Step: 130
2023-02-20 21:30:26 - r - INFO: - Episode: 102/200, Reward: 74.000, Step: 74
2023-02-20 21:30:26 - r - INFO: - Episode: 103/200, Reward: 167.000, Step: 167
2023-02-20 21:30:26 - r - INFO: - Episode: 104/200, Reward: 171.000, Step: 171
2023-02-20 21:30:26 - r - INFO: - Episode: 105/200, Reward: 150.000, Step: 150
2023-02-20 21:30:28 - r - INFO: - Episode: 106/200, Reward: 105.000, Step: 105
2023-02-20 21:30:28 - r - INFO: - Episode: 107/200, Reward: 65.000, Step: 65
2023-02-20 21:30:28 - r - INFO: - Episode: 108/200, Reward: 170.000, Step: 170
2023-02-20 21:30:29 - r - INFO: - Episode: 109/200, Reward: 172.000, Step: 172
2023-02-20 21:30:29 - r - INFO: - Episode: 110/200, Reward: 164.000, Step: 164
2023-02-20 21:30:30 - r - INFO: - Current episode 110 has the best eval reward: 180.000
2023-02-20 21:30:31 - r - INFO: - Episode: 111/200, Reward: 148.000, Step: 148
2023-02-20 21:30:31 - r - INFO: - Episode: 112/200, Reward: 116.000, Step: 116
2023-02-20 21:30:31 - r - INFO: - Episode: 113/200, Reward: 59.000, Step: 59
2023-02-20 21:30:31 - r - INFO: - Episode: 114/200, Reward: 200.000, Step: 200
2023-02-20 21:30:31 - r - INFO: - Episode: 115/200, Reward: 36.000, Step: 36
2023-02-20 21:30:33 - r - INFO: - Episode: 116/200, Reward: 200.000, Step: 200
2023-02-20 21:30:34 - r - INFO: - Episode: 117/200, Reward: 200.000, Step: 200
2023-02-20 21:30:34 - r - INFO: - Episode: 118/200, Reward: 158.000, Step: 158
2023-02-20 21:30:34 - r - INFO: - Episode: 119/200, Reward: 200.000, Step: 200
2023-02-20 21:30:34 - r - INFO: - Episode: 120/200, Reward: 200.000, Step: 200
2023-02-20 21:30:37 - r - INFO: - Current episode 120 has the best eval reward: 200.000
2023-02-20 21:30:37 - r - INFO: - Episode: 121/200, Reward: 200.000, Step: 200
2023-02-20 21:30:38 - r - INFO: - Episode: 122/200, Reward: 172.000, Step: 172
2023-02-20 21:30:38 - r - INFO: - Episode: 123/200, Reward: 137.000, Step: 137
2023-02-20 21:30:38 - r - INFO: - Episode: 124/200, Reward: 189.000, Step: 189
2023-02-20 21:30:38 - r - INFO: - Episode: 125/200, Reward: 200.000, Step: 200
2023-02-20 21:30:40 - r - INFO: - Episode: 126/200, Reward: 200.000, Step: 200
2023-02-20 21:30:41 - r - INFO: - Episode: 127/200, Reward: 197.000, Step: 197
2023-02-20 21:30:41 - r - INFO: - Episode: 128/200, Reward: 125.000, Step: 125
2023-02-20 21:30:41 - r - INFO: - Episode: 129/200, Reward: 194.000, Step: 194
2023-02-20 21:30:41 - r - INFO: - Episode: 130/200, Reward: 167.000, Step: 167
2023-02-20 21:30:43 - r - INFO: - Episode: 131/200, Reward: 135.000, Step: 135
2023-02-20 21:30:43 - r - INFO: - Episode: 132/200, Reward: 200.000, Step: 200
2023-02-20 21:30:44 - r - INFO: - Episode: 133/200, Reward: 200.000, Step: 200
2023-02-20 21:30:44 - r - INFO: - Episode: 134/200, Reward: 170.000, Step: 170
2023-02-20 21:30:44 - r - INFO: - Episode: 135/200, Reward: 195.000, Step: 195
2023-02-20 21:30:47 - r - INFO: - Episode: 136/200, Reward: 150.000, Step: 150
2023-02-20 21:30:47 - r - INFO: - Episode: 137/200, Reward: 187.000, Step: 187
2023-02-20 21:30:47 - r - INFO: - Episode: 138/200, Reward: 172.000, Step: 172
2023-02-20 21:30:47 - r - INFO: - Episode: 139/200, Reward: 124.000, Step: 124
2023-02-20 21:30:47 - r - INFO: - Episode: 140/200, Reward: 105.000, Step: 105
2023-02-20 21:30:49 - r - INFO: - Episode: 141/200, Reward: 49.000, Step: 49
2023-02-20 21:30:49 - r - INFO: - Episode: 142/200, Reward: 108.000, Step: 108
2023-02-20 21:30:49 - r - INFO: - Episode: 143/200, Reward: 117.000, Step: 117
2023-02-20 21:30:50 - r - INFO: - Episode: 144/200, Reward: 136.000, Step: 136
2023-02-20 21:30:50 - r - INFO: - Episode: 145/200, Reward: 120.000, Step: 120
2023-02-20 21:30:52 - r - INFO: - Episode: 146/200, Reward: 172.000, Step: 172
2023-02-20 21:30:52 - r - INFO: - Episode: 147/200, Reward: 134.000, Step: 134
2023-02-20 21:30:52 - r - INFO: - Episode: 148/200, Reward: 200.000, Step: 200
2023-02-20 21:30:53 - r - INFO: - Episode: 149/200, Reward: 200.000, Step: 200
2023-02-20 21:30:53 - r - INFO: - Episode: 150/200, Reward: 150.000, Step: 150
2023-02-20 21:30:55 - r - INFO: - Episode: 151/200, Reward: 190.000, Step: 190
2023-02-20 21:30:55 - r - INFO: - Episode: 152/200, Reward: 200.000, Step: 200
2023-02-20 21:30:56 - r - INFO: - Episode: 153/200, Reward: 200.000, Step: 200
2023-02-20 21:30:56 - r - INFO: - Episode: 154/200, Reward: 200.000, Step: 200
2023-02-20 21:30:56 - r - INFO: - Episode: 155/200, Reward: 179.000, Step: 179
2023-02-20 21:30:59 - r - INFO: - Episode: 156/200, Reward: 200.000, Step: 200
2023-02-20 21:30:59 - r - INFO: - Episode: 157/200, Reward: 200.000, Step: 200
2023-02-20 21:30:59 - r - INFO: - Episode: 158/200, Reward: 200.000, Step: 200
2023-02-20 21:31:00 - r - INFO: - Episode: 159/200, Reward: 200.000, Step: 200
2023-02-20 21:31:00 - r - INFO: - Episode: 160/200, Reward: 195.000, Step: 195
2023-02-20 21:31:02 - r - INFO: - Episode: 161/200, Reward: 195.000, Step: 195
2023-02-20 21:31:02 - r - INFO: - Episode: 162/200, Reward: 142.000, Step: 142
2023-02-20 21:31:03 - r - INFO: - Episode: 163/200, Reward: 200.000, Step: 200
2023-02-20 21:31:03 - r - INFO: - Episode: 164/200, Reward: 108.000, Step: 108
2023-02-20 21:31:03 - r - INFO: - Episode: 165/200, Reward: 200.000, Step: 200
2023-02-20 21:31:05 - r - INFO: - Episode: 166/200, Reward: 165.000, Step: 165
2023-02-20 21:31:05 - r - INFO: - Episode: 167/200, Reward: 153.000, Step: 153
2023-02-20 21:31:05 - r - INFO: - Episode: 168/200, Reward: 85.000, Step: 85
2023-02-20 21:31:05 - r - INFO: - Episode: 169/200, Reward: 139.000, Step: 139
2023-02-20 21:31:06 - r - INFO: - Episode: 170/200, Reward: 155.000, Step: 155
2023-02-20 21:31:08 - r - INFO: - Episode: 171/200, Reward: 166.000, Step: 166
2023-02-20 21:31:08 - r - INFO: - Episode: 172/200, Reward: 182.000, Step: 182
2023-02-20 21:31:08 - r - INFO: - Episode: 173/200, Reward: 190.000, Step: 190
2023-02-20 21:31:08 - r - INFO: - Episode: 174/200, Reward: 35.000, Step: 35
2023-02-20 21:31:09 - r - INFO: - Episode: 175/200, Reward: 124.000, Step: 124
2023-02-20 21:31:11 - r - INFO: - Episode: 176/200, Reward: 114.000, Step: 114
2023-02-20 21:31:11 - r - INFO: - Episode: 177/200, Reward: 200.000, Step: 200
2023-02-20 21:31:11 - r - INFO: - Episode: 178/200, Reward: 200.000, Step: 200
2023-02-20 21:31:12 - r - INFO: - Episode: 179/200, Reward: 200.000, Step: 200
2023-02-20 21:31:12 - r - INFO: - Episode: 180/200, Reward: 200.000, Step: 200
2023-02-20 21:31:14 - r - INFO: - Episode: 181/200, Reward: 110.000, Step: 110
2023-02-20 21:31:14 - r - INFO: - Episode: 182/200, Reward: 128.000, Step: 128
2023-02-20 21:31:14 - r - INFO: - Episode: 183/200, Reward: 107.000, Step: 107
2023-02-20 21:31:15 - r - INFO: - Episode: 184/200, Reward: 192.000, Step: 192
2023-02-20 21:31:15 - r - INFO: - Episode: 185/200, Reward: 106.000, Step: 106
2023-02-20 21:31:16 - r - INFO: - Episode: 186/200, Reward: 32.000, Step: 32
2023-02-20 21:31:16 - r - INFO: - Episode: 187/200, Reward: 107.000, Step: 107
2023-02-20 21:31:17 - r - INFO: - Episode: 188/200, Reward: 129.000, Step: 129
2023-02-20 21:31:17 - r - INFO: - Episode: 189/200, Reward: 122.000, Step: 122
2023-02-20 21:31:17 - r - INFO: - Episode: 190/200, Reward: 126.000, Step: 126
2023-02-20 21:31:18 - r - INFO: - Episode: 191/200, Reward: 120.000, Step: 120
2023-02-20 21:31:19 - r - INFO: - Episode: 192/200, Reward: 127.000, Step: 127
2023-02-20 21:31:19 - r - INFO: - Episode: 193/200, Reward: 132.000, Step: 132
2023-02-20 21:31:19 - r - INFO: - Episode: 194/200, Reward: 128.000, Step: 128
2023-02-20 21:31:19 - r - INFO: - Episode: 195/200, Reward: 142.000, Step: 142
2023-02-20 21:31:21 - r - INFO: - Episode: 196/200, Reward: 137.000, Step: 137
2023-02-20 21:31:21 - r - INFO: - Episode: 197/200, Reward: 125.000, Step: 125
2023-02-20 21:31:21 - r - INFO: - Episode: 198/200, Reward: 118.000, Step: 118
2023-02-20 21:31:22 - r - INFO: - Episode: 199/200, Reward: 158.000, Step: 158
2023-02-20 21:31:22 - r - INFO: - Episode: 200/200, Reward: 144.000, Step: 144
2023-02-20 21:31:23 - r - INFO: - Finish training!