2023-04-15 22:05:40 - r - INFO: - Hyperparameters:
2023-04-15 22:05:40 - r - INFO: - ================================================================================
2023-04-15 22:05:40 - r - INFO: -         Name        	       Value        	        Type        
2023-04-15 22:05:40 - r - INFO: -       env_name      	        gym         	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -     new_step_api    	         1          	   <class 'bool'>   
2023-04-15 22:05:40 - r - INFO: -       wrapper       	        None        	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -        render       	         0          	   <class 'bool'>   
2023-04-15 22:05:40 - r - INFO: -     render_mode     	        None        	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -      algo_name      	      PER_DQN       	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -         mode        	        test        	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -      mp_backend     	        ray         	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -         seed        	         1          	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -        device       	        cpu         	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -      train_eps      	        250         	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -       test_eps      	         10         	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -       eval_eps      	         10         	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -   eval_per_episode  	         5          	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -      max_steps      	        200         	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -   load_checkpoint   	         1          	   <class 'bool'>   
2023-04-15 22:05:40 - r - INFO: -      load_path      	Train_CartPole-v1_PER_DQN_ray_20230415-215738	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -       show_fig      	         0          	   <class 'bool'>   
2023-04-15 22:05:40 - r - INFO: -       save_fig      	         1          	   <class 'bool'>   
2023-04-15 22:05:40 - r - INFO: -      n_workers      	         1          	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -    epsilon_start    	        0.95        	  <class 'float'>   
2023-04-15 22:05:40 - r - INFO: -     epsilon_end     	        0.01        	  <class 'float'>   
2023-04-15 22:05:40 - r - INFO: -    epsilon_decay    	        500         	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -      hidden_dim     	        256         	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -        gamma        	        0.99        	  <class 'float'>   
2023-04-15 22:05:40 - r - INFO: -          lr         	       0.0001       	  <class 'float'>   
2023-04-15 22:05:40 - r - INFO: -     buffer_size     	       100000       	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -      per_alpha      	        0.6         	  <class 'float'>   
2023-04-15 22:05:40 - r - INFO: -       per_beta      	        0.4         	  <class 'float'>   
2023-04-15 22:05:40 - r - INFO: -  per_beta_annealing 	       0.001        	  <class 'float'>   
2023-04-15 22:05:40 - r - INFO: -     per_epsilon     	        0.01        	  <class 'float'>   
2023-04-15 22:05:40 - r - INFO: -      batch_size     	         64         	   <class 'int'>    
2023-04-15 22:05:40 - r - INFO: -    target_update    	         4          	   <class 'int'>    
2023-04-15 22:05:40 - 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'>    
2023-04-15 22:05:40 - r - INFO: -          id         	    CartPole-v1     	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -       task_dir      	/media/disk/gsc/joyrl-offline/tasks/Test_gym_PER_DQN_20230415-220540	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -       res_dir       	/media/disk/gsc/joyrl-offline/tasks/Test_gym_PER_DQN_20230415-220540/results	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -       log_dir       	/media/disk/gsc/joyrl-offline/tasks/Test_gym_PER_DQN_20230415-220540/logs	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -       traj_dir      	/media/disk/gsc/joyrl-offline/tasks/Test_gym_PER_DQN_20230415-220540/traj	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: -      video_dir      	/media/disk/gsc/joyrl-offline/tasks/Test_gym_PER_DQN_20230415-220540/videos	   <class 'str'>    
2023-04-15 22:05:40 - r - INFO: - ================================================================================
2023-04-15 22:05:40 - r - INFO: - n_states: 4, n_actions: 2
2023-04-15 22:05:40 - r - INFO: - Start testing!
2023-04-15 22:05:40 - r - INFO: - Env: gym, Algorithm: PER_DQN, Device: cpu
2023-04-15 22:05:40 - r - INFO: - Episode: 1/10, Reward: 200.000, Step: 200
2023-04-15 22:05:40 - r - INFO: - Episode: 2/10, Reward: 199.000, Step: 199
2023-04-15 22:05:40 - r - INFO: - Episode: 3/10, Reward: 200.000, Step: 200
2023-04-15 22:05:40 - r - INFO: - Episode: 4/10, Reward: 200.000, Step: 200
2023-04-15 22:05:40 - r - INFO: - Episode: 5/10, Reward: 200.000, Step: 200
2023-04-15 22:05:40 - r - INFO: - Episode: 6/10, Reward: 200.000, Step: 200
2023-04-15 22:05:40 - r - INFO: - Episode: 7/10, Reward: 200.000, Step: 200
2023-04-15 22:05:40 - r - INFO: - Episode: 8/10, Reward: 200.000, Step: 200
2023-04-15 22:05:41 - r - INFO: - Episode: 9/10, Reward: 200.000, Step: 200
2023-04-15 22:05:41 - r - INFO: - Episode: 10/10, Reward: 200.000, Step: 200
2023-04-15 22:05:41 - r - INFO: - Finish testing!