ClassControl/Pendulum-v1/Test_Pendulum-v1_DDPG_HER_20230414-151611/logs/log.txt

2023-04-14 15:16:11 - r - INFO: - Hyperparameters:
2023-04-14 15:16:11 - r - INFO: - ================================================================================
2023-04-14 15:16:11 - r - INFO: -         Name        	       Value        	        Type        
2023-04-14 15:16:11 - r - INFO: -       env_name      	    Pendulum-v1     	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -     new_step_api    	         1          	   <class 'bool'>   
2023-04-14 15:16:11 - r - INFO: -       wrapper       	        None        	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -        render       	         0          	   <class 'bool'>   
2023-04-14 15:16:11 - r - INFO: -     render_mode     	       human        	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -      algo_name      	      DDPG_HER      	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -         mode        	        test        	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -      mp_backend     	         mp         	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -         seed        	         0          	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -        device       	        cpu         	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -    her_sample_num   	         4          	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -     update_every    	        100         	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -      train_eps      	        150         	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -       test_eps      	         20         	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -       eval_eps      	         10         	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -   eval_per_episode  	         5          	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -      max_steps      	        200         	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -   load_checkpoint   	         1          	   <class 'bool'>   
2023-04-14 15:16:11 - r - INFO: -      load_path      	       tasks        	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -       show_fig      	         0          	   <class 'bool'>   
2023-04-14 15:16:11 - r - INFO: -       save_fig      	         1          	   <class 'bool'>   
2023-04-14 15:16:11 - r - INFO: -        gamma        	        0.99        	  <class 'float'>   
2023-04-14 15:16:11 - r - INFO: -      critic_lr      	       0.001        	  <class 'float'>   
2023-04-14 15:16:11 - r - INFO: -       actor_lr      	       0.0001       	  <class 'float'>   
2023-04-14 15:16:11 - r - INFO: -     buffer_size     	        8000        	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -      batch_size     	        128         	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -         tau         	       0.001        	  <class 'float'>   
2023-04-14 15:16:11 - r - INFO: -  critic_hidden_dim  	        256         	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -   actor_hidden_dim  	        256         	   <class 'int'>    
2023-04-14 15:16:11 - r - INFO: -       task_dir      	D:\MyDoc\joyrl\joyrl-offline/tasks/Test_Pendulum-v1_DDPG_HER_20230414-151611	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -       res_dir       	D:\MyDoc\joyrl\joyrl-offline/tasks/Test_Pendulum-v1_DDPG_HER_20230414-151611/results	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -       log_dir       	D:\MyDoc\joyrl\joyrl-offline/tasks/Test_Pendulum-v1_DDPG_HER_20230414-151611/logs	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -       traj_dir      	D:\MyDoc\joyrl\joyrl-offline/tasks/Test_Pendulum-v1_DDPG_HER_20230414-151611/traj	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: -      video_dir      	D:\MyDoc\joyrl\joyrl-offline/tasks/Test_Pendulum-v1_DDPG_HER_20230414-151611/videos	   <class 'str'>    
2023-04-14 15:16:11 - r - INFO: - ================================================================================
2023-04-14 15:16:11 - r - INFO: - action_bound: 2.0
2023-04-14 15:16:11 - r - INFO: - n_states: 3, n_actions: 1
2023-04-14 15:16:11 - r - INFO: - Start testing!
2023-04-14 15:16:11 - r - INFO: - Env: Pendulum-v1, Algorithm: DDPG_HER, Device: cpu
2023-04-14 15:16:11 - r - INFO: - Episode: 1/20, Reward: -119.619, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 2/20, Reward: -125.829, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 3/20, Reward: -311.731, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 4/20, Reward: -122.448, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 5/20, Reward: -123.622, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 6/20, Reward: -255.851, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 7/20, Reward: -135.118, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 8/20, Reward: -131.147, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 9/20, Reward: -128.532, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 10/20, Reward: -237.524, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 11/20, Reward: -127.244, Step: 200
2023-04-14 15:16:11 - r - INFO: - Episode: 12/20, Reward: -124.922, Step: 200
2023-04-14 15:16:12 - r - INFO: - Episode: 13/20, Reward: -115.935, Step: 200
2023-04-14 15:16:12 - r - INFO: - Episode: 14/20, Reward: -129.591, Step: 200
2023-04-14 15:16:12 - r - INFO: - Episode: 15/20, Reward: -124.751, Step: 200
2023-04-14 15:16:12 - r - INFO: - Episode: 16/20, Reward: -132.203, Step: 200
2023-04-14 15:16:12 - r - INFO: - Episode: 17/20, Reward: -2.005, Step: 200
2023-04-14 15:16:12 - r - INFO: - Episode: 18/20, Reward: -129.287, Step: 200
2023-04-14 15:16:12 - r - INFO: - Episode: 19/20, Reward: -129.070, Step: 200
2023-04-14 15:16:12 - r - INFO: - Episode: 20/20, Reward: -123.223, Step: 200
2023-04-14 15:16:12 - r - INFO: - Finish testing!