update Cartpole-v1 DuelingDQN

CartPole-v1/Test_CartPole-v1_DuelingDQN_20221122-125455/config.yaml

@@ -1,41 +0,0 @@
-general_cfg:
-  algo_name: DuelingDQN
-  device: cuda
-  env_name: CartPole-v1
-  eval_eps: 10
-  eval_per_episode: 5
-  load_checkpoint: true
-  load_path: Train_CartPole-v1_DuelingDQN_20221122-125403
-  max_steps: 200
-  mode: test
-  save_fig: true
-  seed: 1
-  show_fig: false
-  test_eps: 10
-  train_eps: 100
-algo_cfg:
-  batch_size: 64
-  buffer_size: 100000
-  epsilon_decay: 500
-  epsilon_end: 0.01
-  epsilon_start: 0.95
-  gamma: 0.99
-  hidden_dim: 256
-  lr: 0.0001
-  target_update: 4
-  value_layers:
-  - activation: relu
-    layer_dim:
-    - n_states
-    - 256
-    layer_type: linear
-  - activation: relu
-    layer_dim:
-    - 256
-    - 256
-    layer_type: linear
-  - activation: none
-    layer_dim:
-    - 256
-    - n_actions
-    layer_type: linear

CartPole-v1/Test_CartPole-v1_DuelingDQN_20221122-125455/logs/log.txt

@@ -1,14 +0,0 @@
-2022-11-22 12:54:55 - r - INFO: - n_states: 4, n_actions: 2
-2022-11-22 12:54:58 - r - INFO: - Start testing!
-2022-11-22 12:54:58 - r - INFO: - Env: CartPole-v1, Algorithm: DuelingDQN, Device: cuda
-2022-11-22 12:54:58 - r - INFO: - Episode: 1/10, Reward: 200.000, Step: 200
-2022-11-22 12:54:58 - r - INFO: - Episode: 2/10, Reward: 200.000, Step: 200
-2022-11-22 12:54:58 - r - INFO: - Episode: 3/10, Reward: 200.000, Step: 200
-2022-11-22 12:54:58 - r - INFO: - Episode: 4/10, Reward: 200.000, Step: 200
-2022-11-22 12:54:58 - r - INFO: - Episode: 5/10, Reward: 200.000, Step: 200
-2022-11-22 12:54:58 - r - INFO: - Episode: 6/10, Reward: 200.000, Step: 200
-2022-11-22 12:54:58 - r - INFO: - Episode: 7/10, Reward: 200.000, Step: 200
-2022-11-22 12:54:58 - r - INFO: - Episode: 8/10, Reward: 200.000, Step: 200
-2022-11-22 12:54:58 - r - INFO: - Episode: 9/10, Reward: 200.000, Step: 200
-2022-11-22 12:54:58 - r - INFO: - Episode: 10/10, Reward: 200.000, Step: 200
-2022-11-22 12:54:58 - r - INFO: - Finish testing!

CartPole-v1/Test_CartPole-v1_DuelingDQN_20221122-125455/results/res.csv

@@ -1,11 +0,0 @@
-episodes,rewards,steps
-0,200.0,200
-1,200.0,200
-2,200.0,200
-3,200.0,200
-4,200.0,200
-5,200.0,200
-6,200.0,200
-7,200.0,200
-8,200.0,200
-9,200.0,200

CartPole-v1/Test_CartPole-v1_DuelingDQN_mp_20230407-171120/config.yaml

@@ -1,47 +0,0 @@
-general_cfg:
-  algo_name: DuelingDQN
-  device: cpu
-  env_name: CartPole-v1
-  eval_eps: 10
-  eval_per_episode: 5
-  load_checkpoint: true
-  load_path: Train_CartPole-v1_DuelingDQN_mp_20230407-170853
-  max_steps: 200
-  mode: test
-  mp_backend: mp
-  n_workers: 1
-  new_step_api: true
-  render: false
-  render_mode: human
-  save_fig: true
-  seed: 1
-  show_fig: false
-  test_eps: 10
-  train_eps: 200
-  wrapper: null
-algo_cfg:
-  batch_size: 64
-  buffer_size: 100000
-  epsilon_decay: 500
-  epsilon_end: 0.01
-  epsilon_start: 0.95
-  gamma: 0.99
-  hidden_dim: 256
-  lr: 0.0001
-  target_update: 4
-  value_layers:
-  - activation: relu
-    layer_dim:
-    - n_states
-    - 256
-    layer_type: linear
-  - activation: relu
-    layer_dim:
-    - 256
-    - 256
-    layer_type: linear
-  - activation: none
-    layer_dim:
-    - 256
-    - n_actions
-    layer_type: linear

CartPole-v1/Test_CartPole-v1_DuelingDQN_mp_20230407-171120/logs/log.txt

@@ -1,53 +0,0 @@
-2023-04-07 17:11:20 - r - INFO: - Hyperparameters:
-2023-04-07 17:11:20 - r - INFO: - ================================================================================
-2023-04-07 17:11:20 - r - INFO: -         Name        	       Value        	        Type        
-2023-04-07 17:11:20 - r - INFO: -       env_name      	    CartPole-v1     	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -     new_step_api    	         1          	   <class 'bool'>   
-2023-04-07 17:11:20 - r - INFO: -       wrapper       	        None        	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -        render       	         0          	   <class 'bool'>   
-2023-04-07 17:11:20 - r - INFO: -     render_mode     	       human        	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -      algo_name      	     DuelingDQN     	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -         mode        	        test        	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -      mp_backend     	         mp         	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -         seed        	         1          	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -        device       	        cpu         	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -      train_eps      	        200         	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -       test_eps      	         10         	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -       eval_eps      	         10         	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -   eval_per_episode  	         5          	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -      max_steps      	        200         	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -   load_checkpoint   	         1          	   <class 'bool'>   
-2023-04-07 17:11:20 - r - INFO: -      load_path      	Train_CartPole-v1_DuelingDQN_mp_20230407-170853	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -       show_fig      	         0          	   <class 'bool'>   
-2023-04-07 17:11:20 - r - INFO: -       save_fig      	         1          	   <class 'bool'>   
-2023-04-07 17:11:20 - r - INFO: -      n_workers      	         1          	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -    epsilon_start    	        0.95        	  <class 'float'>   
-2023-04-07 17:11:20 - r - INFO: -     epsilon_end     	        0.01        	  <class 'float'>   
-2023-04-07 17:11:20 - r - INFO: -    epsilon_decay    	        500         	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -        gamma        	        0.99        	  <class 'float'>   
-2023-04-07 17:11:20 - r - INFO: -          lr         	       0.0001       	  <class 'float'>   
-2023-04-07 17:11:20 - r - INFO: -     buffer_size     	       100000       	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -      batch_size     	         64         	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -    target_update    	         4          	   <class 'int'>    
-2023-04-07 17:11:20 - 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'>    
-2023-04-07 17:11:20 - r - INFO: -      hidden_dim     	        256         	   <class 'int'>    
-2023-04-07 17:11:20 - r - INFO: -       task_dir      	/media/disk/gsc/joyrl-offline/tasks/Test_CartPole-v1_DuelingDQN_20230407-171120	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -       res_dir       	/media/disk/gsc/joyrl-offline/tasks/Test_CartPole-v1_DuelingDQN_20230407-171120/results	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -       log_dir       	/media/disk/gsc/joyrl-offline/tasks/Test_CartPole-v1_DuelingDQN_20230407-171120/logs	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -       traj_dir      	/media/disk/gsc/joyrl-offline/tasks/Test_CartPole-v1_DuelingDQN_20230407-171120/traj	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: -      video_dir      	/media/disk/gsc/joyrl-offline/tasks/Test_CartPole-v1_DuelingDQN_20230407-171120/videos	   <class 'str'>    
-2023-04-07 17:11:20 - r - INFO: - ================================================================================
-2023-04-07 17:11:20 - r - INFO: - n_states: 4, n_actions: 2
-2023-04-07 17:11:20 - r - INFO: - Start testing!
-2023-04-07 17:11:20 - r - INFO: - Env: CartPole-v1, Algorithm: DuelingDQN, Device: cpu
-2023-04-07 17:11:20 - r - INFO: - Episode: 1/10, Reward: 200.000, Step: 200
-2023-04-07 17:11:21 - r - INFO: - Episode: 2/10, Reward: 200.000, Step: 200
-2023-04-07 17:11:21 - r - INFO: - Episode: 3/10, Reward: 190.000, Step: 190
-2023-04-07 17:11:21 - r - INFO: - Episode: 4/10, Reward: 200.000, Step: 200
-2023-04-07 17:11:21 - r - INFO: - Episode: 5/10, Reward: 187.000, Step: 187
-2023-04-07 17:11:21 - r - INFO: - Episode: 6/10, Reward: 182.000, Step: 182
-2023-04-07 17:11:21 - r - INFO: - Episode: 7/10, Reward: 200.000, Step: 200
-2023-04-07 17:11:21 - r - INFO: - Episode: 8/10, Reward: 200.000, Step: 200
-2023-04-07 17:11:21 - r - INFO: - Episode: 9/10, Reward: 196.000, Step: 196
-2023-04-07 17:11:21 - r - INFO: - Episode: 10/10, Reward: 200.000, Step: 200
-2023-04-07 17:11:21 - r - INFO: - Finish testing!

CartPole-v1/Test_CartPole-v1_DuelingDQN_mp_20230407-171120/results/res.csv

@@ -1,11 +0,0 @@
-episodes,rewards,steps
-0,200.0,200
-1,200.0,200
-2,190.0,190
-3,200.0,200
-4,187.0,187
-5,182.0,182
-6,200.0,200
-7,200.0,200
-8,196.0,196
-9,200.0,200

CartPole-v1/Test_CartPole-v1_DuelingDQN_ray_20230407-165208/config.yaml

@@ -1,47 +0,0 @@
-general_cfg:
-  algo_name: DuelingDQN
-  device: cpu
-  env_name: CartPole-v1
-  eval_eps: 10
-  eval_per_episode: 5
-  load_checkpoint: true
-  load_path: Train_CartPole-v1_DuelingDQN_20230407-153236
-  max_steps: 200
-  mode: test
-  mp_backend: ray
-  n_workers: 1
-  new_step_api: true
-  render: false
-  render_mode: human
-  save_fig: true
-  seed: 1
-  show_fig: false
-  test_eps: 10
-  train_eps: 400
-  wrapper: null
-algo_cfg:
-  batch_size: 64
-  buffer_size: 100000
-  epsilon_decay: 500
-  epsilon_end: 0.01
-  epsilon_start: 0.95
-  gamma: 0.99
-  hidden_dim: 256
-  lr: 0.0001
-  target_update: 4
-  value_layers:
-  - activation: relu
-    layer_dim:
-    - n_states
-    - 256
-    layer_type: linear
-  - activation: relu
-    layer_dim:
-    - 256
-    - 256
-    layer_type: linear
-  - activation: none
-    layer_dim:
-    - 256
-    - n_actions
-    layer_type: linear

CartPole-v1/Test_CartPole-v1_DuelingDQN_ray_20230407-165208/logs/log.txt

@@ -1,53 +0,0 @@
-2023-04-07 16:52:08 - r - INFO: - Hyperparameters:
-2023-04-07 16:52:08 - r - INFO: - ================================================================================
-2023-04-07 16:52:08 - r - INFO: -         Name        	       Value        	        Type        
-2023-04-07 16:52:08 - r - INFO: -       env_name      	    CartPole-v1     	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -     new_step_api    	         1          	   <class 'bool'>   
-2023-04-07 16:52:08 - r - INFO: -       wrapper       	        None        	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -        render       	         0          	   <class 'bool'>   
-2023-04-07 16:52:08 - r - INFO: -     render_mode     	       human        	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -      algo_name      	     DuelingDQN     	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -         mode        	        test        	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -      mp_backend     	        ray         	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -         seed        	         1          	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -        device       	        cpu         	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -      train_eps      	        400         	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -       test_eps      	         10         	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -       eval_eps      	         10         	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -   eval_per_episode  	         5          	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -      max_steps      	        200         	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -   load_checkpoint   	         1          	   <class 'bool'>   
-2023-04-07 16:52:08 - r - INFO: -      load_path      	Train_CartPole-v1_DuelingDQN_20230407-153236	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -       show_fig      	         0          	   <class 'bool'>   
-2023-04-07 16:52:08 - r - INFO: -       save_fig      	         1          	   <class 'bool'>   
-2023-04-07 16:52:08 - r - INFO: -      n_workers      	         1          	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -    epsilon_start    	        0.95        	  <class 'float'>   
-2023-04-07 16:52:08 - r - INFO: -     epsilon_end     	        0.01        	  <class 'float'>   
-2023-04-07 16:52:08 - r - INFO: -    epsilon_decay    	        500         	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -        gamma        	        0.99        	  <class 'float'>   
-2023-04-07 16:52:08 - r - INFO: -          lr         	       0.0001       	  <class 'float'>   
-2023-04-07 16:52:08 - r - INFO: -     buffer_size     	       100000       	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -      batch_size     	         64         	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -    target_update    	         4          	   <class 'int'>    
-2023-04-07 16:52:08 - 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'>    
-2023-04-07 16:52:08 - r - INFO: -      hidden_dim     	        256         	   <class 'int'>    
-2023-04-07 16:52:08 - r - INFO: -       task_dir      	/media/disk/gsc/joyrl-offline/tasks/Test_CartPole-v1_DuelingDQN_20230407-165208	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -       res_dir       	/media/disk/gsc/joyrl-offline/tasks/Test_CartPole-v1_DuelingDQN_20230407-165208/results	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -       log_dir       	/media/disk/gsc/joyrl-offline/tasks/Test_CartPole-v1_DuelingDQN_20230407-165208/logs	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -       traj_dir      	/media/disk/gsc/joyrl-offline/tasks/Test_CartPole-v1_DuelingDQN_20230407-165208/traj	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: -      video_dir      	/media/disk/gsc/joyrl-offline/tasks/Test_CartPole-v1_DuelingDQN_20230407-165208/videos	   <class 'str'>    
-2023-04-07 16:52:08 - r - INFO: - ================================================================================
-2023-04-07 16:52:08 - r - INFO: - n_states: 4, n_actions: 2
-2023-04-07 16:52:08 - r - INFO: - Start testing!
-2023-04-07 16:52:08 - r - INFO: - Env: CartPole-v1, Algorithm: DuelingDQN, Device: cpu
-2023-04-07 16:52:08 - r - INFO: - Episode: 1/10, Reward: 171.000, Step: 171
-2023-04-07 16:52:08 - r - INFO: - Episode: 2/10, Reward: 185.000, Step: 185
-2023-04-07 16:52:08 - r - INFO: - Episode: 3/10, Reward: 159.000, Step: 159
-2023-04-07 16:52:08 - r - INFO: - Episode: 4/10, Reward: 155.000, Step: 155
-2023-04-07 16:52:08 - r - INFO: - Episode: 5/10, Reward: 200.000, Step: 200
-2023-04-07 16:52:08 - r - INFO: - Episode: 6/10, Reward: 120.000, Step: 120
-2023-04-07 16:52:08 - r - INFO: - Episode: 7/10, Reward: 200.000, Step: 200
-2023-04-07 16:52:08 - r - INFO: - Episode: 8/10, Reward: 187.000, Step: 187
-2023-04-07 16:52:08 - r - INFO: - Episode: 9/10, Reward: 154.000, Step: 154
-2023-04-07 16:52:08 - r - INFO: - Episode: 10/10, Reward: 200.000, Step: 200
-2023-04-07 16:52:08 - r - INFO: - Finish testing!

CartPole-v1/Test_CartPole-v1_DuelingDQN_ray_20230407-165208/results/res.csv

@@ -1,11 +0,0 @@
-episodes,rewards,steps
-0,171.0,171
-1,185.0,185
-2,159.0,159
-3,155.0,155
-4,200.0,200
-5,120.0,120
-6,200.0,200
-7,187.0,187
-8,154.0,154
-9,200.0,200

CartPole-v1/Train_CartPole-v1_DuelingDQN_20221122-125403/config.yaml

@@ -1,41 +0,0 @@
-general_cfg:
-  algo_name: DuelingDQN
-  device: cuda
-  env_name: CartPole-v1
-  eval_eps: 10
-  eval_per_episode: 5
-  load_checkpoint: false
-  load_path: Train_CartPole-v1_DQN_20221026-054757
-  max_steps: 200
-  mode: train
-  save_fig: true
-  seed: 1
-  show_fig: false
-  test_eps: 10
-  train_eps: 100
-algo_cfg:
-  batch_size: 64
-  buffer_size: 100000
-  epsilon_decay: 500
-  epsilon_end: 0.01
-  epsilon_start: 0.95
-  gamma: 0.99
-  hidden_dim: 256
-  lr: 0.0001
-  target_update: 4
-  value_layers:
-  - activation: relu
-    layer_dim:
-    - n_states
-    - 256
-    layer_type: linear
-  - activation: relu
-    layer_dim:
-    - 256
-    - 256
-    layer_type: linear
-  - activation: none
-    layer_dim:
-    - 256
-    - n_actions
-    layer_type: linear

CartPole-v1/Train_CartPole-v1_DuelingDQN_20221122-125403/logs/log.txt

@@ -1,119 +0,0 @@
-2022-11-22 12:54:03 - r - INFO: - n_states: 4, n_actions: 2
-2022-11-22 12:54:06 - r - INFO: - Start training!
-2022-11-22 12:54:06 - r - INFO: - Env: CartPole-v1, Algorithm: DuelingDQN, Device: cuda
-2022-11-22 12:54:06 - r - INFO: - Episode: 1/100, Reward: 18.000, Step: 18
-2022-11-22 12:54:06 - r - INFO: - Episode: 2/100, Reward: 35.000, Step: 35
-2022-11-22 12:54:06 - r - INFO: - Episode: 3/100, Reward: 13.000, Step: 13
-2022-11-22 12:54:06 - r - INFO: - Episode: 4/100, Reward: 32.000, Step: 32
-2022-11-22 12:54:06 - r - INFO: - Episode: 5/100, Reward: 16.000, Step: 16
-2022-11-22 12:54:06 - r - INFO: - Current episode 5 has the best eval reward: 9.100
-2022-11-22 12:54:06 - r - INFO: - Episode: 6/100, Reward: 9.000, Step: 9
-2022-11-22 12:54:06 - r - INFO: - Episode: 7/100, Reward: 12.000, Step: 12
-2022-11-22 12:54:06 - r - INFO: - Episode: 8/100, Reward: 16.000, Step: 16
-2022-11-22 12:54:06 - r - INFO: - Episode: 9/100, Reward: 14.000, Step: 14
-2022-11-22 12:54:06 - r - INFO: - Episode: 10/100, Reward: 12.000, Step: 12
-2022-11-22 12:54:06 - r - INFO: - Current episode 10 has the best eval reward: 9.200
-2022-11-22 12:54:06 - r - INFO: - Episode: 11/100, Reward: 13.000, Step: 13
-2022-11-22 12:54:06 - r - INFO: - Episode: 12/100, Reward: 14.000, Step: 14
-2022-11-22 12:54:06 - r - INFO: - Episode: 13/100, Reward: 19.000, Step: 19
-2022-11-22 12:54:06 - r - INFO: - Episode: 14/100, Reward: 9.000, Step: 9
-2022-11-22 12:54:06 - r - INFO: - Episode: 15/100, Reward: 15.000, Step: 15
-2022-11-22 12:54:06 - r - INFO: - Current episode 15 has the best eval reward: 9.300
-2022-11-22 12:54:06 - r - INFO: - Episode: 16/100, Reward: 12.000, Step: 12
-2022-11-22 12:54:06 - r - INFO: - Episode: 17/100, Reward: 11.000, Step: 11
-2022-11-22 12:54:06 - r - INFO: - Episode: 18/100, Reward: 9.000, Step: 9
-2022-11-22 12:54:07 - r - INFO: - Episode: 19/100, Reward: 13.000, Step: 13
-2022-11-22 12:54:07 - r - INFO: - Episode: 20/100, Reward: 17.000, Step: 17
-2022-11-22 12:54:07 - r - INFO: - Current episode 20 has the best eval reward: 9.900
-2022-11-22 12:54:07 - r - INFO: - Episode: 21/100, Reward: 14.000, Step: 14
-2022-11-22 12:54:07 - r - INFO: - Episode: 22/100, Reward: 20.000, Step: 20
-2022-11-22 12:54:07 - r - INFO: - Episode: 23/100, Reward: 11.000, Step: 11
-2022-11-22 12:54:07 - r - INFO: - Episode: 24/100, Reward: 24.000, Step: 24
-2022-11-22 12:54:07 - r - INFO: - Episode: 25/100, Reward: 11.000, Step: 11
-2022-11-22 12:54:07 - r - INFO: - Episode: 26/100, Reward: 11.000, Step: 11
-2022-11-22 12:54:07 - r - INFO: - Episode: 27/100, Reward: 11.000, Step: 11
-2022-11-22 12:54:07 - r - INFO: - Episode: 28/100, Reward: 13.000, Step: 13
-2022-11-22 12:54:07 - r - INFO: - Episode: 29/100, Reward: 11.000, Step: 11
-2022-11-22 12:54:07 - r - INFO: - Episode: 30/100, Reward: 8.000, Step: 8
-2022-11-22 12:54:07 - r - INFO: - Episode: 31/100, Reward: 13.000, Step: 13
-2022-11-22 12:54:07 - r - INFO: - Episode: 32/100, Reward: 9.000, Step: 9
-2022-11-22 12:54:07 - r - INFO: - Episode: 33/100, Reward: 34.000, Step: 34
-2022-11-22 12:54:07 - r - INFO: - Episode: 34/100, Reward: 10.000, Step: 10
-2022-11-22 12:54:07 - r - INFO: - Episode: 35/100, Reward: 10.000, Step: 10
-2022-11-22 12:54:07 - r - INFO: - Episode: 36/100, Reward: 10.000, Step: 10
-2022-11-22 12:54:07 - r - INFO: - Episode: 37/100, Reward: 34.000, Step: 34
-2022-11-22 12:54:07 - r - INFO: - Episode: 38/100, Reward: 35.000, Step: 35
-2022-11-22 12:54:07 - r - INFO: - Episode: 39/100, Reward: 32.000, Step: 32
-2022-11-22 12:54:08 - r - INFO: - Episode: 40/100, Reward: 37.000, Step: 37
-2022-11-22 12:54:08 - r - INFO: - Current episode 40 has the best eval reward: 27.500
-2022-11-22 12:54:08 - r - INFO: - Episode: 41/100, Reward: 29.000, Step: 29
-2022-11-22 12:54:08 - r - INFO: - Episode: 42/100, Reward: 52.000, Step: 52
-2022-11-22 12:54:08 - r - INFO: - Episode: 43/100, Reward: 54.000, Step: 54
-2022-11-22 12:54:08 - r - INFO: - Episode: 44/100, Reward: 90.000, Step: 90
-2022-11-22 12:54:08 - r - INFO: - Episode: 45/100, Reward: 91.000, Step: 91
-2022-11-22 12:54:09 - r - INFO: - Current episode 45 has the best eval reward: 87.500
-2022-11-22 12:54:09 - r - INFO: - Episode: 46/100, Reward: 51.000, Step: 51
-2022-11-22 12:54:09 - r - INFO: - Episode: 47/100, Reward: 101.000, Step: 101
-2022-11-22 12:54:09 - r - INFO: - Episode: 48/100, Reward: 67.000, Step: 67
-2022-11-22 12:54:09 - r - INFO: - Episode: 49/100, Reward: 103.000, Step: 103
-2022-11-22 12:54:10 - r - INFO: - Episode: 50/100, Reward: 45.000, Step: 45
-2022-11-22 12:54:10 - r - INFO: - Episode: 51/100, Reward: 137.000, Step: 137
-2022-11-22 12:54:10 - r - INFO: - Episode: 52/100, Reward: 47.000, Step: 47
-2022-11-22 12:54:10 - r - INFO: - Episode: 53/100, Reward: 89.000, Step: 89
-2022-11-22 12:54:11 - r - INFO: - Episode: 54/100, Reward: 95.000, Step: 95
-2022-11-22 12:54:11 - r - INFO: - Episode: 55/100, Reward: 55.000, Step: 55
-2022-11-22 12:54:11 - r - INFO: - Episode: 56/100, Reward: 92.000, Step: 92
-2022-11-22 12:54:12 - r - INFO: - Episode: 57/100, Reward: 155.000, Step: 155
-2022-11-22 12:54:12 - r - INFO: - Episode: 58/100, Reward: 125.000, Step: 125
-2022-11-22 12:54:12 - r - INFO: - Episode: 59/100, Reward: 152.000, Step: 152
-2022-11-22 12:54:13 - r - INFO: - Episode: 60/100, Reward: 199.000, Step: 199
-2022-11-22 12:54:13 - r - INFO: - Current episode 60 has the best eval reward: 179.100
-2022-11-22 12:54:14 - r - INFO: - Episode: 61/100, Reward: 88.000, Step: 88
-2022-11-22 12:54:14 - r - INFO: - Episode: 62/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:14 - r - INFO: - Episode: 63/100, Reward: 176.000, Step: 176
-2022-11-22 12:54:15 - r - INFO: - Episode: 64/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:15 - r - INFO: - Episode: 65/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:16 - r - INFO: - Current episode 65 has the best eval reward: 198.700
-2022-11-22 12:54:16 - r - INFO: - Episode: 66/100, Reward: 193.000, Step: 193
-2022-11-22 12:54:17 - r - INFO: - Episode: 67/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:17 - r - INFO: - Episode: 68/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:18 - r - INFO: - Episode: 69/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:18 - r - INFO: - Episode: 70/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:19 - r - INFO: - Current episode 70 has the best eval reward: 200.000
-2022-11-22 12:54:20 - r - INFO: - Episode: 71/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:20 - r - INFO: - Episode: 72/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:20 - r - INFO: - Episode: 73/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:21 - r - INFO: - Episode: 74/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:21 - r - INFO: - Episode: 75/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:22 - r - INFO: - Current episode 75 has the best eval reward: 200.000
-2022-11-22 12:54:23 - r - INFO: - Episode: 76/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:23 - r - INFO: - Episode: 77/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:24 - r - INFO: - Episode: 78/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:24 - r - INFO: - Episode: 79/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:24 - r - INFO: - Episode: 80/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:25 - r - INFO: - Current episode 80 has the best eval reward: 200.000
-2022-11-22 12:54:26 - r - INFO: - Episode: 81/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:26 - r - INFO: - Episode: 82/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:27 - r - INFO: - Episode: 83/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:27 - r - INFO: - Episode: 84/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:27 - r - INFO: - Episode: 85/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:28 - r - INFO: - Current episode 85 has the best eval reward: 200.000
-2022-11-22 12:54:29 - r - INFO: - Episode: 86/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:29 - r - INFO: - Episode: 87/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:30 - r - INFO: - Episode: 88/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:30 - r - INFO: - Episode: 89/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:30 - r - INFO: - Episode: 90/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:31 - r - INFO: - Current episode 90 has the best eval reward: 200.000
-2022-11-22 12:54:32 - r - INFO: - Episode: 91/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:32 - r - INFO: - Episode: 92/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:33 - r - INFO: - Episode: 93/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:33 - r - INFO: - Episode: 94/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:34 - r - INFO: - Episode: 95/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:34 - r - INFO: - Current episode 95 has the best eval reward: 200.000
-2022-11-22 12:54:35 - r - INFO: - Episode: 96/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:35 - r - INFO: - Episode: 97/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:36 - r - INFO: - Episode: 98/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:36 - r - INFO: - Episode: 99/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:37 - r - INFO: - Episode: 100/100, Reward: 200.000, Step: 200
-2022-11-22 12:54:37 - r - INFO: - Current episode 100 has the best eval reward: 200.000
-2022-11-22 12:54:37 - r - INFO: - Finish training!

CartPole-v1/Train_CartPole-v1_DuelingDQN_20221122-125403/results/res.csv

@@ -1,101 +0,0 @@
-episodes,rewards,steps
-0,18.0,18
-1,35.0,35
-2,13.0,13
-3,32.0,32
-4,16.0,16
-5,9.0,9
-6,12.0,12
-7,16.0,16
-8,14.0,14
-9,12.0,12
-10,13.0,13
-11,14.0,14
-12,19.0,19
-13,9.0,9
-14,15.0,15
-15,12.0,12
-16,11.0,11
-17,9.0,9
-18,13.0,13
-19,17.0,17
-20,14.0,14
-21,20.0,20
-22,11.0,11
-23,24.0,24
-24,11.0,11
-25,11.0,11
-26,11.0,11
-27,13.0,13
-28,11.0,11
-29,8.0,8
-30,13.0,13
-31,9.0,9
-32,34.0,34
-33,10.0,10
-34,10.0,10
-35,10.0,10
-36,34.0,34
-37,35.0,35
-38,32.0,32
-39,37.0,37
-40,29.0,29
-41,52.0,52
-42,54.0,54
-43,90.0,90
-44,91.0,91
-45,51.0,51
-46,101.0,101
-47,67.0,67
-48,103.0,103
-49,45.0,45
-50,137.0,137
-51,47.0,47
-52,89.0,89
-53,95.0,95
-54,55.0,55
-55,92.0,92
-56,155.0,155
-57,125.0,125
-58,152.0,152
-59,199.0,199
-60,88.0,88
-61,200.0,200
-62,176.0,176
-63,200.0,200
-64,200.0,200
-65,193.0,193
-66,200.0,200
-67,200.0,200
-68,200.0,200
-69,200.0,200
-70,200.0,200
-71,200.0,200
-72,200.0,200
-73,200.0,200
-74,200.0,200
-75,200.0,200
-76,200.0,200
-77,200.0,200
-78,200.0,200
-79,200.0,200
-80,200.0,200
-81,200.0,200
-82,200.0,200
-83,200.0,200
-84,200.0,200
-85,200.0,200
-86,200.0,200
-87,200.0,200
-88,200.0,200
-89,200.0,200
-90,200.0,200
-91,200.0,200
-92,200.0,200
-93,200.0,200
-94,200.0,200
-95,200.0,200
-96,200.0,200
-97,200.0,200
-98,200.0,200
-99,200.0,200

CartPole-v1/Train_CartPole-v1_DuelingDQN_mp_20230407-170853/logs/log.txt

@@ -1,43 +0,0 @@
-2023-04-07 17:08:53 - r - INFO: - Hyperparameters:
-2023-04-07 17:08:53 - r - INFO: - ================================================================================
-2023-04-07 17:08:53 - r - INFO: -         Name        	       Value        	        Type        
-2023-04-07 17:08:53 - r - INFO: -       env_name      	    CartPole-v1     	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -     new_step_api    	         1          	   <class 'bool'>   
-2023-04-07 17:08:53 - r - INFO: -       wrapper       	        None        	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -        render       	         0          	   <class 'bool'>   
-2023-04-07 17:08:53 - r - INFO: -     render_mode     	       human        	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -      algo_name      	     DuelingDQN     	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -         mode        	       train        	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -      mp_backend     	         mp         	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -         seed        	         1          	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -        device       	        cpu         	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -      train_eps      	        200         	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -       test_eps      	         10         	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -       eval_eps      	         10         	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -   eval_per_episode  	         5          	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -      max_steps      	        200         	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -   load_checkpoint   	         0          	   <class 'bool'>   
-2023-04-07 17:08:53 - r - INFO: -      load_path      	Train_CartPole-v1_DQN_20221026-054757	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -       show_fig      	         0          	   <class 'bool'>   
-2023-04-07 17:08:53 - r - INFO: -       save_fig      	         1          	   <class 'bool'>   
-2023-04-07 17:08:53 - r - INFO: -      n_workers      	         4          	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -    epsilon_start    	        0.95        	  <class 'float'>   
-2023-04-07 17:08:53 - r - INFO: -     epsilon_end     	        0.01        	  <class 'float'>   
-2023-04-07 17:08:53 - r - INFO: -    epsilon_decay    	        500         	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -        gamma        	        0.99        	  <class 'float'>   
-2023-04-07 17:08:53 - r - INFO: -          lr         	       0.0001       	  <class 'float'>   
-2023-04-07 17:08:53 - r - INFO: -     buffer_size     	       100000       	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -      batch_size     	         64         	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -    target_update    	         4          	   <class 'int'>    
-2023-04-07 17:08:53 - 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'>    
-2023-04-07 17:08:53 - r - INFO: -      hidden_dim     	        256         	   <class 'int'>    
-2023-04-07 17:08:53 - r - INFO: -       task_dir      	/media/disk/gsc/joyrl-offline/tasks/Train_CartPole-v1_DuelingDQN_20230407-170853	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -       res_dir       	/media/disk/gsc/joyrl-offline/tasks/Train_CartPole-v1_DuelingDQN_20230407-170853/results	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -       log_dir       	/media/disk/gsc/joyrl-offline/tasks/Train_CartPole-v1_DuelingDQN_20230407-170853/logs	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -       traj_dir      	/media/disk/gsc/joyrl-offline/tasks/Train_CartPole-v1_DuelingDQN_20230407-170853/traj	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: -      video_dir      	/media/disk/gsc/joyrl-offline/tasks/Train_CartPole-v1_DuelingDQN_20230407-170853/videos	   <class 'str'>    
-2023-04-07 17:08:53 - r - INFO: - ================================================================================
-2023-04-07 17:08:53 - r - INFO: - n_states: 4, n_actions: 2
-2023-04-07 17:08:53 - r - INFO: - Start training!
-2023-04-07 17:08:53 - r - INFO: - Env: CartPole-v1, Algorithm: DuelingDQN, Device: cpu
-2023-04-07 17:10:11 - r - INFO: - Finish training!

CartPole-v1/Train_CartPole-v1_DuelingDQN_mp_20230407-170853/models/checkpoint.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:87aab291b33d6423c3c54eced436183398700a290427c1913be9d65f5503b5ae
-size 537607

CartPole-v1/Train_CartPole-v1_DuelingDQN_mp_20230407-170853/results/res.csv

@@ -1,202 +0,0 @@
-episodes,rewards
-0,17.0
-1,16.0
-2,24.0
-3,38.0
-4,18.0
-5,18.0
-6,19.0
-7,17.0
-8,27.0
-9,16.0
-10,15.0
-11,31.0
-12,33.0
-13,13.0
-14,9.0
-15,34.0
-16,32.0
-17,34.0
-18,12.0
-19,13.0
-20,11.0
-21,9.0
-22,9.0
-23,11.0
-24,38.0
-25,13.0
-26,20.0
-27,10.0
-28,33.0
-29,15.0
-30,32.0
-31,11.0
-32,13.0
-33,12.0
-34,9.0
-35,13.0
-36,14.0
-37,21.0
-38,48.0
-39,19.0
-40,65.0
-41,28.0
-42,15.0
-43,11.0
-44,54.0
-45,26.0
-46,37.0
-47,40.0
-48,54.0
-49,54.0
-50,50.0
-51,84.0
-52,55.0
-53,43.0
-54,45.0
-55,48.0
-56,88.0
-57,41.0
-58,46.0
-59,61.0
-60,32.0
-61,53.0
-62,59.0
-63,49.0
-64,60.0
-65,35.0
-66,82.0
-67,50.0
-68,108.0
-69,121.0
-70,113.0
-71,67.0
-72,87.0
-73,96.0
-74,181.0
-75,62.0
-76,137.0
-77,175.0
-78,123.0
-79,149.0
-80,172.0
-81,200.0
-82,156.0
-83,146.0
-84,200.0
-85,200.0
-86,200.0
-87,128.0
-88,188.0
-89,200.0
-90,200.0
-91,200.0
-92,200.0
-93,200.0
-94,200.0
-95,200.0
-96,200.0
-97,200.0
-98,195.0
-99,200.0
-100,200.0
-101,196.0
-102,200.0
-103,200.0
-104,192.0
-105,200.0
-106,190.0
-107,200.0
-108,200.0
-109,200.0
-110,197.0
-111,200.0
-112,200.0
-113,200.0
-114,200.0
-115,200.0
-116,200.0
-117,200.0
-118,200.0
-119,200.0
-120,200.0
-121,200.0
-122,200.0
-123,200.0
-124,200.0
-125,200.0
-126,200.0
-127,200.0
-128,200.0
-129,200.0
-130,200.0
-131,200.0
-132,200.0
-133,200.0
-134,200.0
-135,200.0
-136,200.0
-137,197.0
-138,200.0
-139,200.0
-140,200.0
-141,200.0
-142,200.0
-143,200.0
-144,21.0
-145,193.0
-146,123.0
-147,194.0
-148,9.0
-149,9.0
-150,48.0
-151,200.0
-152,200.0
-153,200.0
-154,200.0
-155,200.0
-156,200.0
-157,200.0
-158,200.0
-159,200.0
-160,200.0
-161,200.0
-162,200.0
-163,200.0
-164,200.0
-165,200.0
-166,200.0
-167,200.0
-168,200.0
-169,200.0
-170,200.0
-171,200.0
-172,200.0
-173,200.0
-174,200.0
-175,200.0
-176,200.0
-177,200.0
-178,200.0
-179,200.0
-180,200.0
-181,200.0
-182,200.0
-183,200.0
-184,200.0
-185,200.0
-186,200.0
-187,200.0
-188,200.0
-189,200.0
-190,200.0
-191,200.0
-192,200.0
-193,200.0
-194,200.0
-195,200.0
-196,200.0
-197,200.0
-198,200.0
-199,200.0
-200,200.0

CartPole-v1/Train_CartPole-v1_DuelingDQN_ray_20230407-153236/logs/log.txt

@@ -1,43 +0,0 @@
-2023-04-07 15:32:36 - r - INFO: - Hyperparameters:
-2023-04-07 15:32:36 - r - INFO: - ================================================================================
-2023-04-07 15:32:36 - r - INFO: -         Name        	       Value        	        Type        
-2023-04-07 15:32:36 - r - INFO: -       env_name      	    CartPole-v1     	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -     new_step_api    	         1          	   <class 'bool'>   
-2023-04-07 15:32:36 - r - INFO: -       wrapper       	        None        	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -        render       	         0          	   <class 'bool'>   
-2023-04-07 15:32:36 - r - INFO: -     render_mode     	       human        	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -      algo_name      	     DuelingDQN     	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -         mode        	       train        	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -      mp_backend     	        ray         	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -         seed        	         1          	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -        device       	        cpu         	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -      train_eps      	        400         	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -       test_eps      	         10         	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -       eval_eps      	         10         	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -   eval_per_episode  	         5          	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -      max_steps      	        200         	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -   load_checkpoint   	         0          	   <class 'bool'>   
-2023-04-07 15:32:36 - r - INFO: -      load_path      	Train_CartPole-v1_DQN_20221026-054757	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -       show_fig      	         0          	   <class 'bool'>   
-2023-04-07 15:32:36 - r - INFO: -       save_fig      	         1          	   <class 'bool'>   
-2023-04-07 15:32:36 - r - INFO: -      n_workers      	         2          	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -    epsilon_start    	        0.95        	  <class 'float'>   
-2023-04-07 15:32:36 - r - INFO: -     epsilon_end     	        0.01        	  <class 'float'>   
-2023-04-07 15:32:36 - r - INFO: -    epsilon_decay    	        500         	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -        gamma        	        0.99        	  <class 'float'>   
-2023-04-07 15:32:36 - r - INFO: -          lr         	       0.0001       	  <class 'float'>   
-2023-04-07 15:32:36 - r - INFO: -     buffer_size     	       100000       	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -      batch_size     	         64         	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -    target_update    	         4          	   <class 'int'>    
-2023-04-07 15:32:36 - 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'>    
-2023-04-07 15:32:36 - r - INFO: -      hidden_dim     	        256         	   <class 'int'>    
-2023-04-07 15:32:36 - r - INFO: -       task_dir      	/media/disk/gsc/joyrl-offline/tasks/Train_CartPole-v1_DuelingDQN_20230407-153236	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -       res_dir       	/media/disk/gsc/joyrl-offline/tasks/Train_CartPole-v1_DuelingDQN_20230407-153236/results	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -       log_dir       	/media/disk/gsc/joyrl-offline/tasks/Train_CartPole-v1_DuelingDQN_20230407-153236/logs	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -       traj_dir      	/media/disk/gsc/joyrl-offline/tasks/Train_CartPole-v1_DuelingDQN_20230407-153236/traj	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: -      video_dir      	/media/disk/gsc/joyrl-offline/tasks/Train_CartPole-v1_DuelingDQN_20230407-153236/videos	   <class 'str'>    
-2023-04-07 15:32:36 - r - INFO: - ================================================================================
-2023-04-07 15:32:39 - r - INFO: - n_states: 4, n_actions: 2
-2023-04-07 15:32:39 - r - INFO: - Start training!
-2023-04-07 15:32:39 - r - INFO: - Env: CartPole-v1, Algorithm: DuelingDQN, Device: cpu
-2023-04-07 15:40:31 - r - INFO: - Finish training!

CartPole-v1/Train_CartPole-v1_DuelingDQN_ray_20230407-153236/models/checkpoint.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:03f1262598e3d636dd22e3b2fc0dfe52bf7a55348d54f51f02a8410682ec5a18
-size 537607

CartPole-v1/Train_CartPole-v1_DuelingDQN_ray_20230407-153236/results/res.csv

@@ -1,401 +0,0 @@
-episodes,rewards
-0,18.0
-1,18.0
-2,19.0
-3,28.0
-4,17.0
-5,15.0
-6,13.0
-7,15.0
-8,38.0
-9,31.0
-10,11.0
-11,31.0
-12,10.0
-13,17.0
-14,14.0
-15,13.0
-16,21.0
-17,15.0
-18,9.0
-19,10.0
-20,22.0
-21,19.0
-22,11.0
-23,13.0
-24,20.0
-25,15.0
-26,14.0
-27,12.0
-28,10.0
-29,11.0
-30,12.0
-31,14.0
-32,9.0
-33,10.0
-34,16.0
-35,13.0
-36,15.0
-37,12.0
-38,14.0
-39,10.0
-40,14.0
-41,10.0
-42,11.0
-43,16.0
-44,16.0
-45,12.0
-46,15.0
-47,19.0
-48,15.0
-49,20.0
-50,15.0
-51,11.0
-52,13.0
-53,12.0
-54,12.0
-55,12.0
-56,12.0
-57,12.0
-58,11.0
-59,10.0
-60,13.0
-61,11.0
-62,12.0
-63,9.0
-64,11.0
-65,11.0
-66,10.0
-67,9.0
-68,11.0
-69,11.0
-70,11.0
-71,12.0
-72,10.0
-73,12.0
-74,9.0
-75,10.0
-76,9.0
-77,10.0
-78,9.0
-79,10.0
-80,11.0
-81,9.0
-82,12.0
-83,11.0
-84,12.0
-85,10.0
-86,9.0
-87,11.0
-88,9.0
-89,9.0
-90,10.0
-91,15.0
-92,11.0
-93,9.0
-94,10.0
-95,16.0
-96,13.0
-97,9.0
-98,10.0
-99,10.0
-100,13.0
-101,11.0
-102,10.0
-103,9.0
-104,13.0
-105,16.0
-106,12.0
-107,9.0
-108,11.0
-109,9.0
-110,13.0
-111,11.0
-112,18.0
-113,13.0
-114,9.0
-115,12.0
-116,10.0
-117,10.0
-118,10.0
-119,13.0
-120,10.0
-121,11.0
-122,10.0
-123,10.0
-124,9.0
-125,10.0
-126,11.0
-127,14.0
-128,12.0
-129,9.0
-130,11.0
-131,14.0
-132,11.0
-133,10.0
-134,13.0
-135,9.0
-136,11.0
-137,11.0
-138,11.0
-139,9.0
-140,10.0
-141,9.0
-142,9.0
-143,12.0
-144,9.0
-145,10.0
-146,9.0
-147,10.0
-148,9.0
-149,10.0
-150,9.0
-151,12.0
-152,9.0
-153,9.0
-154,10.0
-155,9.0
-156,10.0
-157,13.0
-158,14.0
-159,10.0
-160,12.0
-161,11.0
-162,10.0
-163,11.0
-164,11.0
-165,9.0
-166,31.0
-167,39.0
-168,18.0
-169,24.0
-170,18.0
-171,18.0
-172,24.0
-173,16.0
-174,25.0
-175,23.0
-176,26.0
-177,23.0
-178,26.0
-179,21.0
-180,28.0
-181,20.0
-182,22.0
-183,30.0
-184,27.0
-185,34.0
-186,31.0
-187,39.0
-188,29.0
-189,29.0
-190,37.0
-191,27.0
-192,36.0
-193,34.0
-194,46.0
-195,35.0
-196,52.0
-197,32.0
-198,30.0
-199,69.0
-200,38.0
-201,39.0
-202,57.0
-203,38.0
-204,68.0
-205,47.0
-206,45.0
-207,63.0
-208,47.0
-209,86.0
-210,67.0
-211,60.0
-212,48.0
-213,55.0
-214,95.0
-215,58.0
-216,70.0
-217,58.0
-218,42.0
-219,69.0
-220,47.0
-221,109.0
-222,70.0
-223,80.0
-224,77.0
-225,61.0
-226,72.0
-227,55.0
-228,77.0
-229,61.0
-230,79.0
-231,66.0
-232,68.0
-233,99.0
-234,143.0
-235,82.0
-236,85.0
-237,103.0
-238,99.0
-239,93.0
-240,100.0
-241,101.0
-242,151.0
-243,195.0
-244,100.0
-245,99.0
-246,127.0
-247,105.0
-248,127.0
-249,142.0
-250,169.0
-251,108.0
-252,128.0
-253,123.0
-254,134.0
-255,126.0
-256,114.0
-257,200.0
-258,123.0
-259,159.0
-260,125.0
-261,142.0
-262,178.0
-263,96.0
-264,200.0
-265,200.0
-266,113.0
-267,90.0
-268,200.0
-269,122.0
-270,140.0
-271,116.0
-272,128.0
-273,190.0
-274,170.0
-275,96.0
-276,126.0
-277,200.0
-278,88.0
-279,76.0
-280,74.0
-281,84.0
-282,130.0
-283,200.0
-284,86.0
-285,153.0
-286,200.0
-287,59.0
-288,135.0
-289,62.0
-290,200.0
-291,182.0
-292,138.0
-293,200.0
-294,118.0
-295,50.0
-296,74.0
-297,62.0
-298,200.0
-299,124.0
-300,111.0
-301,61.0
-302,132.0
-303,200.0
-304,80.0
-305,60.0
-306,77.0
-307,47.0
-308,80.0
-309,64.0
-310,96.0
-311,200.0
-312,200.0
-313,133.0
-314,200.0
-315,188.0
-316,132.0
-317,150.0
-318,135.0
-319,184.0
-320,138.0
-321,176.0
-322,200.0
-323,161.0
-324,158.0
-325,142.0
-326,133.0
-327,151.0
-328,143.0
-329,160.0
-330,150.0
-331,134.0
-332,147.0
-333,132.0
-334,143.0
-335,137.0
-336,155.0
-337,138.0
-338,138.0
-339,130.0
-340,148.0
-341,146.0
-342,152.0
-343,135.0
-344,175.0
-345,153.0
-346,155.0
-347,131.0
-348,156.0
-349,138.0
-350,151.0
-351,162.0
-352,200.0
-353,175.0
-354,156.0
-355,145.0
-356,168.0
-357,200.0
-358,181.0
-359,145.0
-360,189.0
-361,200.0
-362,144.0
-363,200.0
-364,178.0
-365,200.0
-366,179.0
-367,200.0
-368,177.0
-369,200.0
-370,185.0
-371,195.0
-372,200.0
-373,200.0
-374,190.0
-375,200.0
-376,200.0
-377,200.0
-378,200.0
-379,200.0
-380,200.0
-381,200.0
-382,170.0
-383,173.0
-384,162.0
-385,162.0
-386,149.0
-387,173.0
-388,200.0
-389,200.0
-390,200.0
-391,156.0
-392,157.0
-393,169.0
-394,182.0
-395,154.0
-396,200.0
-397,200.0
-398,200.0
-399,200.0

CartPole-v1/{Train_CartPole-v1_DuelingDQN_ray_20230407-153236 → Train_ray_CartPole-v1_DuelingDQN_20230517-224129}/config.yaml

@@ -1,47 +1,44 @@
 general_cfg:
   algo_name: DuelingDQN
+  collect_traj: false
   device: cpu
-  env_name: CartPole-v1
-  eval_eps: 10
-  eval_per_episode: 5
+  env_name: gym
   load_checkpoint: false
-  load_path: Train_CartPole-v1_DQN_20221026-054757
-  max_steps: 200
+  load_model_step: best
+  load_path: Train_single_CartPole-v1_DQN_20230515-211721
+  max_episode: 100
+  max_step: 200
   mode: train
+  model_save_fre: 500
   mp_backend: ray
   n_workers: 2
-  new_step_api: true
-  render: false
-  render_mode: human
-  save_fig: true
+  online_eval: true
+  online_eval_episode: 10
   seed: 1
-  show_fig: false
-  test_eps: 10
-  train_eps: 400
-  wrapper: null
 algo_cfg:
   batch_size: 64
   buffer_size: 100000
+  buffer_type: REPLAY_QUE
+  dueling: true
   epsilon_decay: 500
   epsilon_end: 0.01
   epsilon_start: 0.95
-  gamma: 0.99
-  hidden_dim: 256
+  gamma: 0.95
   lr: 0.0001
   target_update: 4
   value_layers:
   - activation: relu
     layer_dim:
-    - n_states
     - 256
     layer_type: linear
   - activation: relu
     layer_dim:
     - 256
-    - 256
-    layer_type: linear
-  - activation: none
-    layer_dim:
-    - 256
-    - n_actions
     layer_type: linear
+env_cfg:
+  id: CartPole-v1
+  ignore_params:
+  - wrapper
+  - ignore_params
+  render_mode: null
+  wrapper: null

CartPole-v1/Train_ray_CartPole-v1_DuelingDQN_20230517-224129/logs/log.txt

@@ -0,0 +1,169 @@
+2023-05-17 22:41:29 - SimpleLog - INFO: - General Configs:
+2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================
+2023-05-17 22:41:29 - SimpleLog - INFO: -         Name        	       Value        	        Type        
+2023-05-17 22:41:29 - SimpleLog - INFO: -       env_name      	        gym         	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -      algo_name      	     DuelingDQN     	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -         mode        	       train        	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -        device       	        cpu         	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -         seed        	         1          	   <class 'int'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -     max_episode     	        100         	   <class 'int'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -       max_step      	        200         	   <class 'int'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -     collect_traj    	         0          	   <class 'bool'>   
+2023-05-17 22:41:29 - SimpleLog - INFO: -      mp_backend     	        ray         	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -      n_workers      	         2          	   <class 'int'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -     online_eval     	         1          	   <class 'bool'>   
+2023-05-17 22:41:29 - SimpleLog - INFO: - online_eval_episode 	         10         	   <class 'int'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -    model_save_fre   	        500         	   <class 'int'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -   load_checkpoint   	         0          	   <class 'bool'>   
+2023-05-17 22:41:29 - SimpleLog - INFO: -      load_path      	Train_single_CartPole-v1_DQN_20230515-211721	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -   load_model_step   	        best        	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================
+2023-05-17 22:41:29 - SimpleLog - INFO: - Algo Configs:
+2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================
+2023-05-17 22:41:29 - SimpleLog - INFO: -         Name        	       Value        	        Type        
+2023-05-17 22:41:29 - SimpleLog - INFO: -       dueling       	         1          	   <class 'bool'>   
+2023-05-17 22:41:29 - SimpleLog - INFO: -    epsilon_start    	        0.95        	  <class 'float'>   
+2023-05-17 22:41:29 - SimpleLog - INFO: -     epsilon_end     	        0.01        	  <class 'float'>   
+2023-05-17 22:41:29 - SimpleLog - INFO: -    epsilon_decay    	        500         	   <class 'int'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -        gamma        	        0.95        	  <class 'float'>   
+2023-05-17 22:41:29 - SimpleLog - INFO: -          lr         	       0.0001       	  <class 'float'>   
+2023-05-17 22:41:29 - SimpleLog - INFO: -     buffer_size     	       100000       	   <class 'int'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -      batch_size     	         64         	   <class 'int'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -    target_update    	         4          	   <class 'int'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -     value_layers    	[{'layer_type': 'linear', 'layer_dim': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_dim': [256], 'activation': 'relu'}]	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -     buffer_type     	     REPLAY_QUE     	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================
+2023-05-17 22:41:29 - SimpleLog - INFO: - Env Configs:
+2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================
+2023-05-17 22:41:29 - SimpleLog - INFO: -         Name        	       Value        	        Type        
+2023-05-17 22:41:29 - SimpleLog - INFO: -          id         	    CartPole-v1     	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -     render_mode     	        None        	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -       wrapper       	        None        	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: -    ignore_params    	['wrapper', 'ignore_params']	   <class 'str'>    
+2023-05-17 22:41:29 - SimpleLog - INFO: - ================================================================================
+2023-05-17 22:41:35 - SimpleLog - INFO: - obs_space: Box([-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38], [4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38], (4,), float32), n_actions: Discrete(2)
+2023-05-17 22:41:38 - RayLog - INFO: - Worker 1 finished episode 0 with reward 22.0 in 22 steps
+2023-05-17 22:41:38 - RayLog - INFO: - Worker 0 finished episode 0 with reward 23.0 in 23 steps
+2023-05-17 22:41:38 - RayLog - INFO: - Worker 0 finished episode 2 with reward 10.0 in 10 steps
+2023-05-17 22:41:38 - RayLog - INFO: - Worker 0 finished episode 3 with reward 9.0 in 9 steps
+2023-05-17 22:41:38 - RayLog - INFO: - Worker 1 finished episode 2 with reward 29.0 in 29 steps
+2023-05-17 22:41:38 - RayLog - INFO: - Worker 0 finished episode 4 with reward 11.0 in 11 steps
+2023-05-17 22:41:39 - RayLog - INFO: - Worker 0 finished episode 6 with reward 15.0 in 15 steps
+2023-05-17 22:41:39 - RayLog - INFO: - Worker 1 finished episode 5 with reward 18.0 in 18 steps
+2023-05-17 22:41:39 - RayLog - INFO: - Worker 0 finished episode 7 with reward 9.0 in 9 steps
+2023-05-17 22:41:39 - RayLog - INFO: - Worker 1 finished episode 8 with reward 11.0 in 11 steps
+2023-05-17 22:41:39 - RayLog - INFO: - Worker 1 finished episode 10 with reward 13.0 in 13 steps
+2023-05-17 22:41:39 - RayLog - INFO: - Worker 0 finished episode 9 with reward 25.0 in 25 steps
+2023-05-17 22:41:40 - RayLog - INFO: - Worker 0 finished episode 12 with reward 12.0 in 12 steps
+2023-05-17 22:41:40 - RayLog - INFO: - Worker 0 finished episode 13 with reward 10.0 in 10 steps
+2023-05-17 22:41:40 - RayLog - INFO: - Worker 1 finished episode 11 with reward 33.0 in 33 steps
+2023-05-17 22:41:40 - RayLog - INFO: - Worker 0 finished episode 14 with reward 9.0 in 9 steps
+2023-05-17 22:41:40 - RayLog - INFO: - Worker 1 finished episode 15 with reward 10.0 in 10 steps
+2023-05-17 22:41:40 - RayLog - INFO: - Worker 0 finished episode 16 with reward 13.0 in 13 steps
+2023-05-17 22:41:40 - RayLog - INFO: - Worker 1 finished episode 17 with reward 16.0 in 16 steps
+2023-05-17 22:41:40 - RayLog - INFO: - Worker 0 finished episode 18 with reward 9.0 in 9 steps
+2023-05-17 22:41:41 - RayLog - INFO: - Worker 0 finished episode 20 with reward 11.0 in 11 steps
+2023-05-17 22:41:41 - RayLog - INFO: - Worker 1 finished episode 19 with reward 16.0 in 16 steps
+2023-05-17 22:41:41 - RayLog - INFO: - Worker 0 finished episode 21 with reward 18.0 in 18 steps
+2023-05-17 22:41:41 - RayLog - INFO: - Worker 1 finished episode 22 with reward 18.0 in 18 steps
+2023-05-17 22:41:41 - RayLog - INFO: - Worker 0 finished episode 23 with reward 11.0 in 11 steps
+2023-05-17 22:41:41 - RayLog - INFO: - Worker 1 finished episode 24 with reward 9.0 in 9 steps
+2023-05-17 22:41:41 - RayLog - INFO: - Worker 1 finished episode 26 with reward 9.0 in 9 steps
+2023-05-17 22:41:41 - RayLog - INFO: - Worker 0 finished episode 25 with reward 10.0 in 10 steps
+2023-05-17 22:41:42 - RayLog - INFO: - Worker 0 finished episode 28 with reward 11.0 in 11 steps
+2023-05-17 22:41:42 - RayLog - INFO: - Worker 1 finished episode 27 with reward 12.0 in 12 steps
+2023-05-17 22:41:42 - RayLog - INFO: - Worker 0 finished episode 29 with reward 15.0 in 15 steps
+2023-05-17 22:41:42 - RayLog - INFO: - Worker 1 finished episode 30 with reward 19.0 in 19 steps
+2023-05-17 22:41:42 - RayLog - INFO: - Worker 0 finished episode 31 with reward 10.0 in 10 steps
+2023-05-17 22:41:42 - RayLog - INFO: - Worker 1 finished episode 32 with reward 13.0 in 13 steps
+2023-05-17 22:41:44 - RayLog - INFO: - update_step: 500, online_eval_reward: 200.000
+2023-05-17 22:41:44 - RayLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
+2023-05-17 22:41:45 - RayLog - INFO: - Worker 0 finished episode 33 with reward 97.0 in 97 steps
+2023-05-17 22:41:45 - RayLog - INFO: - Worker 1 finished episode 34 with reward 96.0 in 96 steps
+2023-05-17 22:41:46 - RayLog - INFO: - Worker 1 finished episode 36 with reward 24.0 in 24 steps
+2023-05-17 22:41:46 - RayLog - INFO: - Worker 0 finished episode 35 with reward 34.0 in 34 steps
+2023-05-17 22:41:46 - RayLog - INFO: - Worker 1 finished episode 37 with reward 17.0 in 17 steps
+2023-05-17 22:41:46 - RayLog - INFO: - Worker 0 finished episode 38 with reward 23.0 in 23 steps
+2023-05-17 22:41:46 - RayLog - INFO: - Worker 1 finished episode 39 with reward 16.0 in 16 steps
+2023-05-17 22:41:47 - RayLog - INFO: - Worker 1 finished episode 41 with reward 17.0 in 17 steps
+2023-05-17 22:41:47 - RayLog - INFO: - Worker 0 finished episode 40 with reward 24.0 in 24 steps
+2023-05-17 22:41:47 - RayLog - INFO: - Worker 1 finished episode 42 with reward 21.0 in 21 steps
+2023-05-17 22:41:47 - RayLog - INFO: - Worker 0 finished episode 43 with reward 29.0 in 29 steps
+2023-05-17 22:41:47 - RayLog - INFO: - Worker 1 finished episode 44 with reward 22.0 in 22 steps
+2023-05-17 22:41:49 - RayLog - INFO: - update_step: 1000, online_eval_reward: 100.000
+2023-05-17 22:41:49 - RayLog - INFO: - Worker 0 finished episode 45 with reward 84.0 in 84 steps
+2023-05-17 22:41:49 - RayLog - INFO: - Worker 1 finished episode 46 with reward 75.0 in 75 steps
+2023-05-17 22:41:50 - RayLog - INFO: - Worker 1 finished episode 48 with reward 52.0 in 52 steps
+2023-05-17 22:41:50 - RayLog - INFO: - Worker 0 finished episode 47 with reward 66.0 in 66 steps
+2023-05-17 22:41:51 - RayLog - INFO: - Worker 1 finished episode 49 with reward 63.0 in 63 steps
+2023-05-17 22:41:52 - RayLog - INFO: - Worker 0 finished episode 50 with reward 94.0 in 94 steps
+2023-05-17 22:41:53 - RayLog - INFO: - Worker 1 finished episode 51 with reward 75.0 in 75 steps
+2023-05-17 22:41:54 - RayLog - INFO: - update_step: 1500, online_eval_reward: 120.000
+2023-05-17 22:41:54 - RayLog - INFO: - Worker 0 finished episode 52 with reward 102.0 in 102 steps
+2023-05-17 22:41:55 - RayLog - INFO: - Worker 1 finished episode 53 with reward 93.0 in 93 steps
+2023-05-17 22:41:57 - RayLog - INFO: - Worker 1 finished episode 55 with reward 126.0 in 126 steps
+2023-05-17 22:41:58 - RayLog - INFO: - Worker 0 finished episode 54 with reward 200.0 in 200 steps
+2023-05-17 22:41:59 - RayLog - INFO: - update_step: 2000, online_eval_reward: 200.000
+2023-05-17 22:42:01 - RayLog - INFO: - Worker 1 finished episode 56 with reward 200.0 in 200 steps
+2023-05-17 22:42:02 - RayLog - INFO: - Worker 0 finished episode 57 with reward 200.0 in 200 steps
+2023-05-17 22:42:04 - RayLog - INFO: - update_step: 2500, online_eval_reward: 167.000
+2023-05-17 22:42:05 - RayLog - INFO: - Worker 1 finished episode 58 with reward 200.0 in 200 steps
+2023-05-17 22:42:06 - RayLog - INFO: - Worker 0 finished episode 59 with reward 168.0 in 168 steps
+2023-05-17 22:42:09 - RayLog - INFO: - Worker 0 finished episode 61 with reward 164.0 in 164 steps
+2023-05-17 22:42:09 - RayLog - INFO: - update_step: 3000, online_eval_reward: 145.000
+2023-05-17 22:42:09 - RayLog - INFO: - Worker 1 finished episode 60 with reward 189.0 in 189 steps
+2023-05-17 22:42:12 - RayLog - INFO: - Worker 0 finished episode 62 with reward 152.0 in 152 steps
+2023-05-17 22:42:12 - RayLog - INFO: - Worker 1 finished episode 63 with reward 162.0 in 162 steps
+2023-05-17 22:42:14 - RayLog - INFO: - update_step: 3500, online_eval_reward: 151.000
+2023-05-17 22:42:15 - RayLog - INFO: - Worker 0 finished episode 64 with reward 143.0 in 143 steps
+2023-05-17 22:42:16 - RayLog - INFO: - Worker 1 finished episode 65 with reward 163.0 in 163 steps
+2023-05-17 22:42:19 - RayLog - INFO: - Worker 0 finished episode 66 with reward 187.0 in 187 steps
+2023-05-17 22:42:19 - RayLog - INFO: - update_step: 4000, online_eval_reward: 189.000
+2023-05-17 22:42:20 - RayLog - INFO: - Worker 1 finished episode 67 with reward 200.0 in 200 steps
+2023-05-17 22:42:22 - RayLog - INFO: - Worker 0 finished episode 68 with reward 173.0 in 173 steps
+2023-05-17 22:42:23 - RayLog - INFO: - Worker 1 finished episode 69 with reward 170.0 in 170 steps
+2023-05-17 22:42:24 - RayLog - INFO: - update_step: 4500, online_eval_reward: 178.000
+2023-05-17 22:42:26 - RayLog - INFO: - Worker 0 finished episode 70 with reward 200.0 in 200 steps
+2023-05-17 22:42:27 - RayLog - INFO: - Worker 1 finished episode 71 with reward 200.0 in 200 steps
+2023-05-17 22:42:30 - RayLog - INFO: - update_step: 5000, online_eval_reward: 197.000
+2023-05-17 22:42:30 - RayLog - INFO: - Worker 0 finished episode 72 with reward 200.0 in 200 steps
+2023-05-17 22:42:31 - RayLog - INFO: - Worker 1 finished episode 73 with reward 200.0 in 200 steps
+2023-05-17 22:42:35 - RayLog - INFO: - Worker 0 finished episode 74 with reward 197.0 in 197 steps
+2023-05-17 22:42:35 - RayLog - INFO: - update_step: 5500, online_eval_reward: 200.000
+2023-05-17 22:42:36 - RayLog - INFO: - Worker 1 finished episode 75 with reward 200.0 in 200 steps
+2023-05-17 22:42:39 - RayLog - INFO: - Worker 0 finished episode 76 with reward 200.0 in 200 steps
+2023-05-17 22:42:40 - RayLog - INFO: - Worker 1 finished episode 77 with reward 200.0 in 200 steps
+2023-05-17 22:42:40 - RayLog - INFO: - update_step: 6000, online_eval_reward: 200.000
+2023-05-17 22:42:43 - RayLog - INFO: - Worker 0 finished episode 78 with reward 200.0 in 200 steps
+2023-05-17 22:42:44 - RayLog - INFO: - Worker 1 finished episode 79 with reward 200.0 in 200 steps
+2023-05-17 22:42:45 - RayLog - INFO: - update_step: 6500, online_eval_reward: 200.000
+2023-05-17 22:42:47 - RayLog - INFO: - Worker 0 finished episode 80 with reward 200.0 in 200 steps
+2023-05-17 22:42:48 - RayLog - INFO: - Worker 1 finished episode 81 with reward 200.0 in 200 steps
+2023-05-17 22:42:51 - RayLog - INFO: - update_step: 7000, online_eval_reward: 200.000
+2023-05-17 22:42:52 - RayLog - INFO: - Worker 0 finished episode 82 with reward 200.0 in 200 steps
+2023-05-17 22:42:53 - RayLog - INFO: - Worker 1 finished episode 83 with reward 200.0 in 200 steps
+2023-05-17 22:42:56 - RayLog - INFO: - Worker 0 finished episode 84 with reward 200.0 in 200 steps
+2023-05-17 22:42:56 - RayLog - INFO: - update_step: 7500, online_eval_reward: 200.000
+2023-05-17 22:42:57 - RayLog - INFO: - Worker 1 finished episode 85 with reward 200.0 in 200 steps
+2023-05-17 22:43:00 - RayLog - INFO: - Worker 0 finished episode 86 with reward 200.0 in 200 steps
+2023-05-17 22:43:01 - RayLog - INFO: - Worker 1 finished episode 87 with reward 200.0 in 200 steps
+2023-05-17 22:43:02 - RayLog - INFO: - update_step: 8000, online_eval_reward: 200.000
+2023-05-17 22:43:05 - RayLog - INFO: - Worker 0 finished episode 88 with reward 200.0 in 200 steps
+2023-05-17 22:43:06 - RayLog - INFO: - Worker 1 finished episode 89 with reward 200.0 in 200 steps
+2023-05-17 22:43:07 - RayLog - INFO: - update_step: 8500, online_eval_reward: 200.000
+2023-05-17 22:43:09 - RayLog - INFO: - Worker 0 finished episode 90 with reward 200.0 in 200 steps
+2023-05-17 22:43:10 - RayLog - INFO: - Worker 1 finished episode 91 with reward 200.0 in 200 steps
+2023-05-17 22:43:12 - RayLog - INFO: - update_step: 9000, online_eval_reward: 200.000
+2023-05-17 22:43:13 - RayLog - INFO: - Worker 0 finished episode 92 with reward 200.0 in 200 steps
+2023-05-17 22:43:14 - RayLog - INFO: - Worker 1 finished episode 93 with reward 200.0 in 200 steps
+2023-05-17 22:43:18 - RayLog - INFO: - Worker 0 finished episode 94 with reward 200.0 in 200 steps
+2023-05-17 22:43:18 - RayLog - INFO: - update_step: 9500, online_eval_reward: 200.000
+2023-05-17 22:43:19 - RayLog - INFO: - Worker 1 finished episode 95 with reward 200.0 in 200 steps
+2023-05-17 22:43:22 - RayLog - INFO: - Worker 0 finished episode 96 with reward 200.0 in 200 steps
+2023-05-17 22:43:23 - RayLog - INFO: - Worker 1 finished episode 97 with reward 200.0 in 200 steps
+2023-05-17 22:43:23 - RayLog - INFO: - update_step: 10000, online_eval_reward: 200.000
+2023-05-17 22:43:26 - RayLog - INFO: - Worker 0 finished episode 98 with reward 200.0 in 200 steps
+2023-05-17 22:43:27 - RayLog - INFO: - Worker 1 finished episode 99 with reward 200.0 in 200 steps
+2023-05-17 22:43:29 - RayLog - INFO: - update_step: 10500, online_eval_reward: 200.000
+2023-05-17 22:43:30 - RayLog - INFO: - Worker 0 finished episode 100 with reward 200.0 in 200 steps
+2023-05-17 22:43:32 - SimpleLog - INFO: - Finish training! total time consumed: 122.69s

CartPole-v1/{Test_CartPole-v1_DuelingDQN_mp_20230407-171120/models/checkpoint.pt → Train_ray_CartPole-v1_DuelingDQN_20230517-224129/tb_logs/interact/events.out.tfevents.1684334489.DESKTOP-H34HQIQ.80856.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87aab291b33d6423c3c54eced436183398700a290427c1913be9d65f5503b5ae
-size 537607
+oid sha256:1c9b4a566642bacd5610c3e7b42d10f1feb9704e2a4cb2c004a7d85f75a0aba9
+size 40

CartPole-v1/{Test_CartPole-v1_DuelingDQN_ray_20230407-165208/models/checkpoint.pt → Train_ray_CartPole-v1_DuelingDQN_20230517-224129/tb_logs/interact/events.out.tfevents.1684334497.DESKTOP-H34HQIQ.84100.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f1262598e3d636dd22e3b2fc0dfe52bf7a55348d54f51f02a8410682ec5a18
-size 537607
+oid sha256:9867609ac2d205c8c66fe7bc380a67b26f152a046fb5e97d523f5b2bf1c147fd
+size 10028