2023-03-31 22:58:15 - r - INFO: - Hyperparameters:
2023-03-31 22:58:15 - r - INFO: - ================================================================================
2023-03-31 22:58:15 - r - INFO: -         Name        	       Value        	        Type        
2023-03-31 22:58:15 - r - INFO: -       env_name      	    CartPole-v1     	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: -     new_step_api    	         1          	   <class 'bool'>   
2023-03-31 22:58:15 - r - INFO: -       wrapper       	        None        	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: -        render       	         0          	   <class 'bool'>   
2023-03-31 22:58:15 - r - INFO: -      algo_name      	      PER_DQN       	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: -         mode        	       train        	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: -         seed        	         1          	   <class 'int'>    
2023-03-31 22:58:15 - r - INFO: -        device       	        cuda        	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: -      train_eps      	        200         	   <class 'int'>    
2023-03-31 22:58:15 - r - INFO: -       test_eps      	         10         	   <class 'int'>    
2023-03-31 22:58:15 - r - INFO: -       eval_eps      	         10         	   <class 'int'>    
2023-03-31 22:58:15 - r - INFO: -   eval_per_episode  	         5          	   <class 'int'>    
2023-03-31 22:58:15 - r - INFO: -      max_steps      	        200         	   <class 'int'>    
2023-03-31 22:58:15 - r - INFO: -   load_checkpoint   	         0          	   <class 'bool'>   
2023-03-31 22:58:15 - r - INFO: -      load_path      	Train_CartPole-v1_PER_DQN	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: -       show_fig      	         0          	   <class 'bool'>   
2023-03-31 22:58:15 - r - INFO: -       save_fig      	         1          	   <class 'bool'>   
2023-03-31 22:58:15 - r - INFO: -    epsilon_start    	        0.95        	  <class 'float'>   
2023-03-31 22:58:15 - r - INFO: -     epsilon_end     	        0.01        	  <class 'float'>   
2023-03-31 22:58:15 - r - INFO: -    epsilon_decay    	        500         	   <class 'int'>    
2023-03-31 22:58:15 - r - INFO: -      hidden_dim     	        256         	   <class 'int'>    
2023-03-31 22:58:15 - r - INFO: -        gamma        	        0.99        	  <class 'float'>   
2023-03-31 22:58:15 - r - INFO: -          lr         	       0.0001       	  <class 'float'>   
2023-03-31 22:58:15 - r - INFO: -     buffer_size     	       100000       	   <class 'int'>    
2023-03-31 22:58:15 - r - INFO: -      per_alpha      	        0.6         	  <class 'float'>   
2023-03-31 22:58:15 - r - INFO: -       per_beta      	        0.4         	  <class 'float'>   
2023-03-31 22:58:15 - r - INFO: -  per_beta_annealing 	       0.001        	  <class 'float'>   
2023-03-31 22:58:15 - r - INFO: -     per_epsilon     	        0.01        	  <class 'float'>   
2023-03-31 22:58:15 - r - INFO: -      batch_size     	         64         	   <class 'int'>    
2023-03-31 22:58:15 - r - INFO: -    target_update    	         4          	   <class 'int'>    
2023-03-31 22:58:15 - 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'>    
2023-03-31 22:58:15 - r - INFO: -       task_dir      	C:\Users\24438\Desktop\joyrl-offline/tasks/Train_CartPole-v1_PER_DQN_20230331-225815	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: -       res_dir       	C:\Users\24438\Desktop\joyrl-offline/tasks/Train_CartPole-v1_PER_DQN_20230331-225815/results	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: -       log_dir       	C:\Users\24438\Desktop\joyrl-offline/tasks/Train_CartPole-v1_PER_DQN_20230331-225815/logs	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: -       traj_dir      	C:\Users\24438\Desktop\joyrl-offline/tasks/Train_CartPole-v1_PER_DQN_20230331-225815/traj	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: -        tb_dir       	C:\Users\24438\Desktop\joyrl-offline/tasks/Train_CartPole-v1_PER_DQN_20230331-225815/tb_logs	   <class 'str'>    
2023-03-31 22:58:15 - r - INFO: - ================================================================================
2023-03-31 22:58:15 - r - INFO: - n_states: 4, n_actions: 2
2023-03-31 22:58:16 - r - INFO: - Start training!
2023-03-31 22:58:16 - r - INFO: - Env: CartPole-v1, Algorithm: PER_DQN, Device: cuda
2023-03-31 22:58:17 - r - INFO: - Episode: 1/200, Reward: 15.000, Step: 15
2023-03-31 22:58:17 - r - INFO: - Episode: 2/200, Reward: 29.000, Step: 29
2023-03-31 22:58:17 - r - INFO: - Episode: 3/200, Reward: 13.000, Step: 13
2023-03-31 22:58:17 - r - INFO: - Episode: 4/200, Reward: 14.000, Step: 14
2023-03-31 22:58:17 - r - INFO: - Episode: 5/200, Reward: 11.000, Step: 11
2023-03-31 22:58:17 - r - INFO: - Current episode 5 has the best eval reward: 9.600
2023-03-31 22:58:17 - r - INFO: - Episode: 6/200, Reward: 39.000, Step: 39
2023-03-31 22:58:18 - r - INFO: - Episode: 7/200, Reward: 35.000, Step: 35
2023-03-31 22:58:18 - r - INFO: - Episode: 8/200, Reward: 16.000, Step: 16
2023-03-31 22:58:18 - r - INFO: - Episode: 9/200, Reward: 13.000, Step: 13
2023-03-31 22:58:18 - r - INFO: - Episode: 10/200, Reward: 12.000, Step: 12
2023-03-31 22:58:18 - r - INFO: - Episode: 11/200, Reward: 11.000, Step: 11
2023-03-31 22:58:18 - r - INFO: - Episode: 12/200, Reward: 34.000, Step: 34
2023-03-31 22:58:18 - r - INFO: - Episode: 13/200, Reward: 15.000, Step: 15
2023-03-31 22:58:18 - r - INFO: - Episode: 14/200, Reward: 23.000, Step: 23
2023-03-31 22:58:18 - r - INFO: - Episode: 15/200, Reward: 9.000, Step: 9
2023-03-31 22:58:19 - r - INFO: - Episode: 16/200, Reward: 19.000, Step: 19
2023-03-31 22:58:19 - r - INFO: - Episode: 17/200, Reward: 9.000, Step: 9
2023-03-31 22:58:19 - r - INFO: - Episode: 18/200, Reward: 10.000, Step: 10
2023-03-31 22:58:19 - r - INFO: - Episode: 19/200, Reward: 16.000, Step: 16
2023-03-31 22:58:19 - r - INFO: - Episode: 20/200, Reward: 19.000, Step: 19
2023-03-31 22:58:19 - r - INFO: - Current episode 20 has the best eval reward: 9.700
2023-03-31 22:58:19 - r - INFO: - Episode: 21/200, Reward: 11.000, Step: 11
2023-03-31 22:58:19 - r - INFO: - Episode: 22/200, Reward: 10.000, Step: 10
2023-03-31 22:58:19 - r - INFO: - Episode: 23/200, Reward: 14.000, Step: 14
2023-03-31 22:58:19 - r - INFO: - Episode: 24/200, Reward: 12.000, Step: 12
2023-03-31 22:58:19 - r - INFO: - Episode: 25/200, Reward: 16.000, Step: 16
2023-03-31 22:58:19 - r - INFO: - Episode: 26/200, Reward: 11.000, Step: 11
2023-03-31 22:58:19 - r - INFO: - Episode: 27/200, Reward: 10.000, Step: 10
2023-03-31 22:58:19 - r - INFO: - Episode: 28/200, Reward: 16.000, Step: 16
2023-03-31 22:58:19 - r - INFO: - Episode: 29/200, Reward: 12.000, Step: 12
2023-03-31 22:58:20 - r - INFO: - Episode: 30/200, Reward: 16.000, Step: 16
2023-03-31 22:58:20 - r - INFO: - Episode: 31/200, Reward: 11.000, Step: 11
2023-03-31 22:58:20 - r - INFO: - Episode: 32/200, Reward: 8.000, Step: 8
2023-03-31 22:58:20 - r - INFO: - Episode: 33/200, Reward: 8.000, Step: 8
2023-03-31 22:58:20 - r - INFO: - Episode: 34/200, Reward: 12.000, Step: 12
2023-03-31 22:58:20 - r - INFO: - Episode: 35/200, Reward: 10.000, Step: 10
2023-03-31 22:58:20 - r - INFO: - Episode: 36/200, Reward: 9.000, Step: 9
2023-03-31 22:58:20 - r - INFO: - Episode: 37/200, Reward: 11.000, Step: 11
2023-03-31 22:58:20 - r - INFO: - Episode: 38/200, Reward: 10.000, Step: 10
2023-03-31 22:58:20 - r - INFO: - Episode: 39/200, Reward: 11.000, Step: 11
2023-03-31 22:58:20 - r - INFO: - Episode: 40/200, Reward: 10.000, Step: 10
2023-03-31 22:58:20 - r - INFO: - Episode: 41/200, Reward: 10.000, Step: 10
2023-03-31 22:58:20 - r - INFO: - Episode: 42/200, Reward: 10.000, Step: 10
2023-03-31 22:58:20 - r - INFO: - Episode: 43/200, Reward: 10.000, Step: 10
2023-03-31 22:58:20 - r - INFO: - Episode: 44/200, Reward: 9.000, Step: 9
2023-03-31 22:58:20 - r - INFO: - Episode: 45/200, Reward: 11.000, Step: 11
2023-03-31 22:58:21 - r - INFO: - Current episode 45 has the best eval reward: 10.600
2023-03-31 22:58:21 - r - INFO: - Episode: 46/200, Reward: 10.000, Step: 10
2023-03-31 22:58:21 - r - INFO: - Episode: 47/200, Reward: 10.000, Step: 10
2023-03-31 22:58:21 - r - INFO: - Episode: 48/200, Reward: 11.000, Step: 11
2023-03-31 22:58:21 - r - INFO: - Episode: 49/200, Reward: 10.000, Step: 10
2023-03-31 22:58:21 - r - INFO: - Episode: 50/200, Reward: 13.000, Step: 13
2023-03-31 22:58:21 - r - INFO: - Episode: 51/200, Reward: 18.000, Step: 18
2023-03-31 22:58:21 - r - INFO: - Episode: 52/200, Reward: 12.000, Step: 12
2023-03-31 22:58:21 - r - INFO: - Episode: 53/200, Reward: 10.000, Step: 10
2023-03-31 22:58:21 - r - INFO: - Episode: 54/200, Reward: 10.000, Step: 10
2023-03-31 22:58:21 - r - INFO: - Episode: 55/200, Reward: 11.000, Step: 11
2023-03-31 22:58:21 - r - INFO: - Episode: 56/200, Reward: 8.000, Step: 8
2023-03-31 22:58:21 - r - INFO: - Episode: 57/200, Reward: 16.000, Step: 16
2023-03-31 22:58:21 - r - INFO: - Episode: 58/200, Reward: 11.000, Step: 11
2023-03-31 22:58:21 - r - INFO: - Episode: 59/200, Reward: 9.000, Step: 9
2023-03-31 22:58:22 - r - INFO: - Episode: 60/200, Reward: 9.000, Step: 9
2023-03-31 22:58:22 - r - INFO: - Episode: 61/200, Reward: 10.000, Step: 10
2023-03-31 22:58:22 - r - INFO: - Episode: 62/200, Reward: 10.000, Step: 10
2023-03-31 22:58:22 - r - INFO: - Episode: 63/200, Reward: 9.000, Step: 9
2023-03-31 22:58:22 - r - INFO: - Episode: 64/200, Reward: 8.000, Step: 8
2023-03-31 22:58:22 - r - INFO: - Episode: 65/200, Reward: 10.000, Step: 10
2023-03-31 22:58:22 - r - INFO: - Episode: 66/200, Reward: 9.000, Step: 9
2023-03-31 22:58:22 - r - INFO: - Episode: 67/200, Reward: 10.000, Step: 10
2023-03-31 22:58:22 - r - INFO: - Episode: 68/200, Reward: 12.000, Step: 12
2023-03-31 22:58:22 - r - INFO: - Episode: 69/200, Reward: 12.000, Step: 12
2023-03-31 22:58:22 - r - INFO: - Episode: 70/200, Reward: 12.000, Step: 12
2023-03-31 22:58:22 - r - INFO: - Current episode 70 has the best eval reward: 12.500
2023-03-31 22:58:22 - r - INFO: - Episode: 71/200, Reward: 10.000, Step: 10
2023-03-31 22:58:22 - r - INFO: - Episode: 72/200, Reward: 13.000, Step: 13
2023-03-31 22:58:22 - r - INFO: - Episode: 73/200, Reward: 20.000, Step: 20
2023-03-31 22:58:23 - r - INFO: - Episode: 74/200, Reward: 12.000, Step: 12
2023-03-31 22:58:23 - r - INFO: - Episode: 75/200, Reward: 13.000, Step: 13
2023-03-31 22:58:23 - r - INFO: - Current episode 75 has the best eval reward: 13.000
2023-03-31 22:58:23 - r - INFO: - Episode: 76/200, Reward: 15.000, Step: 15
2023-03-31 22:58:23 - r - INFO: - Episode: 77/200, Reward: 13.000, Step: 13
2023-03-31 22:58:23 - r - INFO: - Episode: 78/200, Reward: 19.000, Step: 19
2023-03-31 22:58:23 - r - INFO: - Episode: 79/200, Reward: 14.000, Step: 14
2023-03-31 22:58:23 - r - INFO: - Episode: 80/200, Reward: 12.000, Step: 12
2023-03-31 22:58:23 - r - INFO: - Current episode 80 has the best eval reward: 15.400
2023-03-31 22:58:23 - r - INFO: - Episode: 81/200, Reward: 13.000, Step: 13
2023-03-31 22:58:24 - r - INFO: - Episode: 82/200, Reward: 14.000, Step: 14
2023-03-31 22:58:24 - r - INFO: - Episode: 83/200, Reward: 13.000, Step: 13
2023-03-31 22:58:24 - r - INFO: - Episode: 84/200, Reward: 13.000, Step: 13
2023-03-31 22:58:24 - r - INFO: - Episode: 85/200, Reward: 14.000, Step: 14
2023-03-31 22:58:24 - r - INFO: - Current episode 85 has the best eval reward: 16.000
2023-03-31 22:58:24 - r - INFO: - Episode: 86/200, Reward: 18.000, Step: 18
2023-03-31 22:58:24 - r - INFO: - Episode: 87/200, Reward: 23.000, Step: 23
2023-03-31 22:58:24 - r - INFO: - Episode: 88/200, Reward: 13.000, Step: 13
2023-03-31 22:58:24 - r - INFO: - Episode: 89/200, Reward: 13.000, Step: 13
2023-03-31 22:58:25 - r - INFO: - Episode: 90/200, Reward: 21.000, Step: 21
2023-03-31 22:58:25 - r - INFO: - Current episode 90 has the best eval reward: 18.800
2023-03-31 22:58:25 - r - INFO: - Episode: 91/200, Reward: 17.000, Step: 17
2023-03-31 22:58:25 - r - INFO: - Episode: 92/200, Reward: 23.000, Step: 23
2023-03-31 22:58:25 - r - INFO: - Episode: 93/200, Reward: 16.000, Step: 16
2023-03-31 22:58:25 - r - INFO: - Episode: 94/200, Reward: 22.000, Step: 22
2023-03-31 22:58:25 - r - INFO: - Episode: 95/200, Reward: 23.000, Step: 23
2023-03-31 22:58:26 - r - INFO: - Current episode 95 has the best eval reward: 22.000
2023-03-31 22:58:26 - r - INFO: - Episode: 96/200, Reward: 14.000, Step: 14
2023-03-31 22:58:26 - r - INFO: - Episode: 97/200, Reward: 20.000, Step: 20
2023-03-31 22:58:26 - r - INFO: - Episode: 98/200, Reward: 24.000, Step: 24
2023-03-31 22:58:26 - r - INFO: - Episode: 99/200, Reward: 21.000, Step: 21
2023-03-31 22:58:26 - r - INFO: - Episode: 100/200, Reward: 22.000, Step: 22
2023-03-31 22:58:27 - r - INFO: - Episode: 101/200, Reward: 21.000, Step: 21
2023-03-31 22:58:27 - r - INFO: - Episode: 102/200, Reward: 19.000, Step: 19
2023-03-31 22:58:27 - r - INFO: - Episode: 103/200, Reward: 18.000, Step: 18
2023-03-31 22:58:27 - r - INFO: - Episode: 104/200, Reward: 18.000, Step: 18
2023-03-31 22:58:27 - r - INFO: - Episode: 105/200, Reward: 23.000, Step: 23
2023-03-31 22:58:27 - r - INFO: - Episode: 106/200, Reward: 16.000, Step: 16
2023-03-31 22:58:27 - r - INFO: - Episode: 107/200, Reward: 19.000, Step: 19
2023-03-31 22:58:28 - r - INFO: - Episode: 108/200, Reward: 18.000, Step: 18
2023-03-31 22:58:28 - r - INFO: - Episode: 109/200, Reward: 21.000, Step: 21
2023-03-31 22:58:28 - r - INFO: - Episode: 110/200, Reward: 24.000, Step: 24
2023-03-31 22:58:28 - r - INFO: - Current episode 110 has the best eval reward: 23.300
2023-03-31 22:58:28 - r - INFO: - Episode: 111/200, Reward: 24.000, Step: 24
2023-03-31 22:58:28 - r - INFO: - Episode: 112/200, Reward: 27.000, Step: 27
2023-03-31 22:58:29 - r - INFO: - Episode: 113/200, Reward: 35.000, Step: 35
2023-03-31 22:58:29 - r - INFO: - Episode: 114/200, Reward: 23.000, Step: 23
2023-03-31 22:58:29 - r - INFO: - Episode: 115/200, Reward: 29.000, Step: 29
2023-03-31 22:58:29 - r - INFO: - Current episode 115 has the best eval reward: 24.100
2023-03-31 22:58:29 - r - INFO: - Episode: 116/200, Reward: 25.000, Step: 25
2023-03-31 22:58:29 - r - INFO: - Episode: 117/200, Reward: 20.000, Step: 20
2023-03-31 22:58:30 - r - INFO: - Episode: 118/200, Reward: 23.000, Step: 23
2023-03-31 22:58:30 - r - INFO: - Episode: 119/200, Reward: 21.000, Step: 21
2023-03-31 22:58:30 - r - INFO: - Episode: 120/200, Reward: 23.000, Step: 23
2023-03-31 22:58:30 - r - INFO: - Current episode 120 has the best eval reward: 24.500
2023-03-31 22:58:30 - r - INFO: - Episode: 121/200, Reward: 17.000, Step: 17
2023-03-31 22:58:30 - r - INFO: - Episode: 122/200, Reward: 19.000, Step: 19
2023-03-31 22:58:30 - r - INFO: - Episode: 123/200, Reward: 19.000, Step: 19
2023-03-31 22:58:31 - r - INFO: - Episode: 124/200, Reward: 21.000, Step: 21
2023-03-31 22:58:31 - r - INFO: - Episode: 125/200, Reward: 24.000, Step: 24
2023-03-31 22:58:31 - r - INFO: - Current episode 125 has the best eval reward: 25.600
2023-03-31 22:58:31 - r - INFO: - Episode: 126/200, Reward: 23.000, Step: 23
2023-03-31 22:58:31 - r - INFO: - Episode: 127/200, Reward: 22.000, Step: 22
2023-03-31 22:58:31 - r - INFO: - Episode: 128/200, Reward: 23.000, Step: 23
2023-03-31 22:58:31 - r - INFO: - Episode: 129/200, Reward: 22.000, Step: 22
2023-03-31 22:58:32 - r - INFO: - Episode: 130/200, Reward: 28.000, Step: 28
2023-03-31 22:58:32 - r - INFO: - Current episode 130 has the best eval reward: 29.800
2023-03-31 22:58:32 - r - INFO: - Episode: 131/200, Reward: 32.000, Step: 32
2023-03-31 22:58:32 - r - INFO: - Episode: 132/200, Reward: 35.000, Step: 35
2023-03-31 22:58:32 - r - INFO: - Episode: 133/200, Reward: 27.000, Step: 27
2023-03-31 22:58:33 - r - INFO: - Episode: 134/200, Reward: 24.000, Step: 24
2023-03-31 22:58:33 - r - INFO: - Episode: 135/200, Reward: 37.000, Step: 37
2023-03-31 22:58:33 - r - INFO: - Current episode 135 has the best eval reward: 35.700
2023-03-31 22:58:33 - r - INFO: - Episode: 136/200, Reward: 33.000, Step: 33
2023-03-31 22:58:34 - r - INFO: - Episode: 137/200, Reward: 39.000, Step: 39
2023-03-31 22:58:34 - r - INFO: - Episode: 138/200, Reward: 24.000, Step: 24
2023-03-31 22:58:34 - r - INFO: - Episode: 139/200, Reward: 24.000, Step: 24
2023-03-31 22:58:34 - r - INFO: - Episode: 140/200, Reward: 40.000, Step: 40
2023-03-31 22:58:35 - r - INFO: - Current episode 140 has the best eval reward: 40.200
2023-03-31 22:58:35 - r - INFO: - Episode: 141/200, Reward: 31.000, Step: 31
2023-03-31 22:58:35 - r - INFO: - Episode: 142/200, Reward: 30.000, Step: 30
2023-03-31 22:58:35 - r - INFO: - Episode: 143/200, Reward: 25.000, Step: 25
2023-03-31 22:58:35 - r - INFO: - Episode: 144/200, Reward: 23.000, Step: 23
2023-03-31 22:58:35 - r - INFO: - Episode: 145/200, Reward: 29.000, Step: 29
2023-03-31 22:58:36 - r - INFO: - Current episode 145 has the best eval reward: 58.500
2023-03-31 22:58:36 - r - INFO: - Episode: 146/200, Reward: 51.000, Step: 51
2023-03-31 22:58:37 - r - INFO: - Episode: 147/200, Reward: 73.000, Step: 73
2023-03-31 22:58:37 - r - INFO: - Episode: 148/200, Reward: 38.000, Step: 38
2023-03-31 22:58:37 - r - INFO: - Episode: 149/200, Reward: 37.000, Step: 37
2023-03-31 22:58:37 - r - INFO: - Episode: 150/200, Reward: 32.000, Step: 32
2023-03-31 22:58:38 - r - INFO: - Episode: 151/200, Reward: 43.000, Step: 43
2023-03-31 22:58:38 - r - INFO: - Episode: 152/200, Reward: 29.000, Step: 29
2023-03-31 22:58:38 - r - INFO: - Episode: 153/200, Reward: 33.000, Step: 33
2023-03-31 22:58:38 - r - INFO: - Episode: 154/200, Reward: 31.000, Step: 31
2023-03-31 22:58:39 - r - INFO: - Episode: 155/200, Reward: 41.000, Step: 41
2023-03-31 22:58:39 - r - INFO: - Episode: 156/200, Reward: 79.000, Step: 79
2023-03-31 22:58:40 - r - INFO: - Episode: 157/200, Reward: 47.000, Step: 47
2023-03-31 22:58:40 - r - INFO: - Episode: 158/200, Reward: 32.000, Step: 32
2023-03-31 22:58:40 - r - INFO: - Episode: 159/200, Reward: 36.000, Step: 36
2023-03-31 22:58:41 - r - INFO: - Episode: 160/200, Reward: 76.000, Step: 76
2023-03-31 22:58:41 - r - INFO: - Current episode 160 has the best eval reward: 75.000
2023-03-31 22:58:41 - r - INFO: - Episode: 161/200, Reward: 73.000, Step: 73
2023-03-31 22:58:42 - r - INFO: - Episode: 162/200, Reward: 59.000, Step: 59
2023-03-31 22:58:42 - r - INFO: - Episode: 163/200, Reward: 102.000, Step: 102
2023-03-31 22:58:43 - r - INFO: - Episode: 164/200, Reward: 87.000, Step: 87
2023-03-31 22:58:44 - r - INFO: - Episode: 165/200, Reward: 94.000, Step: 94
2023-03-31 22:58:44 - r - INFO: - Current episode 165 has the best eval reward: 143.300
2023-03-31 22:58:45 - r - INFO: - Episode: 166/200, Reward: 116.000, Step: 116
2023-03-31 22:58:46 - r - INFO: - Episode: 167/200, Reward: 135.000, Step: 135
2023-03-31 22:58:47 - r - INFO: - Episode: 168/200, Reward: 140.000, Step: 140
2023-03-31 22:58:48 - r - INFO: - Episode: 169/200, Reward: 167.000, Step: 167
2023-03-31 22:58:49 - r - INFO: - Episode: 170/200, Reward: 128.000, Step: 128
2023-03-31 22:58:50 - r - INFO: - Current episode 170 has the best eval reward: 157.400
2023-03-31 22:58:51 - r - INFO: - Episode: 171/200, Reward: 200.000, Step: 200
2023-03-31 22:58:52 - r - INFO: - Episode: 172/200, Reward: 135.000, Step: 135
2023-03-31 22:58:53 - r - INFO: - Episode: 173/200, Reward: 163.000, Step: 163
2023-03-31 22:58:54 - r - INFO: - Episode: 174/200, Reward: 180.000, Step: 180
2023-03-31 22:58:56 - r - INFO: - Episode: 175/200, Reward: 185.000, Step: 185
2023-03-31 22:58:56 - r - INFO: - Current episode 175 has the best eval reward: 165.700
2023-03-31 22:58:57 - r - INFO: - Episode: 176/200, Reward: 200.000, Step: 200
2023-03-31 22:58:59 - r - INFO: - Episode: 177/200, Reward: 200.000, Step: 200
2023-03-31 22:59:00 - r - INFO: - Episode: 178/200, Reward: 200.000, Step: 200
2023-03-31 22:59:01 - r - INFO: - Episode: 179/200, Reward: 200.000, Step: 200
2023-03-31 22:59:03 - r - INFO: - Episode: 180/200, Reward: 200.000, Step: 200
2023-03-31 22:59:04 - r - INFO: - Current episode 180 has the best eval reward: 200.000
2023-03-31 22:59:05 - r - INFO: - Episode: 181/200, Reward: 200.000, Step: 200
2023-03-31 22:59:06 - r - INFO: - Episode: 182/200, Reward: 200.000, Step: 200
2023-03-31 22:59:08 - r - INFO: - Episode: 183/200, Reward: 200.000, Step: 200
2023-03-31 22:59:09 - r - INFO: - Episode: 184/200, Reward: 200.000, Step: 200
2023-03-31 22:59:10 - r - INFO: - Episode: 185/200, Reward: 200.000, Step: 200
2023-03-31 22:59:12 - r - INFO: - Episode: 186/200, Reward: 200.000, Step: 200
2023-03-31 22:59:18 - r - INFO: - Episode: 187/200, Reward: 200.000, Step: 200
2023-03-31 22:59:22 - r - INFO: - Episode: 188/200, Reward: 200.000, Step: 200
2023-03-31 22:59:24 - r - INFO: - Episode: 189/200, Reward: 200.000, Step: 200
2023-03-31 22:59:26 - r - INFO: - Episode: 190/200, Reward: 200.000, Step: 200
2023-03-31 22:59:28 - r - INFO: - Episode: 191/200, Reward: 200.000, Step: 200
2023-03-31 22:59:29 - r - INFO: - Episode: 192/200, Reward: 200.000, Step: 200
2023-03-31 22:59:30 - r - INFO: - Episode: 193/200, Reward: 200.000, Step: 200
2023-03-31 22:59:32 - r - INFO: - Episode: 194/200, Reward: 200.000, Step: 200
2023-03-31 22:59:33 - r - INFO: - Episode: 195/200, Reward: 200.000, Step: 200
2023-03-31 22:59:35 - r - INFO: - Episode: 196/200, Reward: 200.000, Step: 200
2023-03-31 22:59:37 - r - INFO: - Episode: 197/200, Reward: 200.000, Step: 200
2023-03-31 22:59:38 - r - INFO: - Episode: 198/200, Reward: 200.000, Step: 200
2023-03-31 22:59:39 - r - INFO: - Episode: 199/200, Reward: 200.000, Step: 200
2023-03-31 22:59:40 - r - INFO: - Episode: 200/200, Reward: 200.000, Step: 200
2023-03-31 22:59:41 - r - INFO: - Current episode 200 has the best eval reward: 200.000
2023-03-31 22:59:41 - r - INFO: - Finish training!