Hugging Face's logo

joyrl
/
joyrl-benchmarks

TensorBoard
Model card Files Metrics Community
15

Train_CartPole-v1_SAC

#6
by gsc579 - opened
base: refs/heads/main
←
from: refs/pr/6
Discussion Files changed
+624
-0
Files changed (40) hide show
  1. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/config.yaml +81 -0
  2. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/logs/log.txt +429 -0
  3. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/100 +3 -0
  4. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/1000 +3 -0
  5. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/1600 +3 -0
  6. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/1700 +3 -0
  7. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/1800 +3 -0
  8. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/1900 +3 -0
  9. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/200 +3 -0
  10. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/2000 +3 -0
  11. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/2100 +3 -0
  12. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/2900 +3 -0
  13. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/300 +3 -0
  14. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/3000 +3 -0
  15. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/3200 +3 -0
  16. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/3900 +3 -0
  17. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/400 +3 -0
  18. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/4000 +3 -0
  19. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/4200 +3 -0
  20. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/4600 +3 -0
  21. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/500 +3 -0
  22. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/5000 +3 -0
  23. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/5700 +3 -0
  24. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/5800 +3 -0
  25. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/5900 +3 -0
  26. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/600 +3 -0
  27. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/6000 +3 -0
  28. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/6300 +3 -0
  29. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/6400 +3 -0
  30. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/6900 +3 -0
  31. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/700 +3 -0
  32. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/7100 +3 -0
  33. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/7200 +3 -0
  34. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/7900 +3 -0
  35. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/800 +3 -0
  36. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/8700 +3 -0
  37. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/900 +3 -0
  38. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/best +3 -0
  39. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/tb_logs/interact/events.out.tfevents.1687076822.ML3090.327748.0 +3 -0
  40. ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/tb_logs/policy/events.out.tfevents.1687076822.ML3090.327748.1 +3 -0
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/config.yaml ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ general_cfg:
2
+ algo_name: SAC
3
+ collect_traj: false
4
+ device: cpu
5
+ env_name: gym
6
+ interact_summary_fre: 1
7
+ load_checkpoint: false
8
+ load_model_step: best
9
+ load_path: Train_single_CartPole-v1_DQN_20230515-211721
10
+ max_episode: 200
11
+ max_step: 200
12
+ mode: train
13
+ model_save_fre: 100
14
+ model_summary_fre: 1
15
+ mp_backend: single
16
+ n_learners: 1
17
+ n_workers: 2
18
+ online_eval: true
19
+ online_eval_episode: 10
20
+ seed: 1
21
+ share_buffer: true
22
+ algo_cfg:
23
+ action_type: discrete
24
+ actor_layers:
25
+ - activation: relu
26
+ layer_size:
27
+ - 256
28
+ layer_type: linear
29
+ - activation: relu
30
+ layer_size:
31
+ - 256
32
+ layer_type: linear
33
+ actor_lr: 0.0003
34
+ alpha: 0.1
35
+ alpha_lr: 0.0001
36
+ automatic_entropy_tuning: false
37
+ batch_size: 64
38
+ buffer_size: 1000000
39
+ buffer_type: REPLAY_QUE
40
+ critic1_lr: 0.001
41
+ critic2_lr: 0.001
42
+ critic_layers:
43
+ - activation: relu
44
+ layer_size:
45
+ - 256
46
+ layer_type: linear
47
+ - activation: relu
48
+ layer_size:
49
+ - 256
50
+ layer_type: linear
51
+ epsilon_decay: 500
52
+ epsilon_end: 0.01
53
+ epsilon_start: 0.95
54
+ gamma: 0.95
55
+ hidden_dim: 64
56
+ independ_actor: true
57
+ lr: 0.0001
58
+ min_policy: 0
59
+ n_epochs: 1
60
+ n_steps_per_learn: 1
61
+ share_optimizer: false
62
+ start_steps: 10000
63
+ target_update: 1
64
+ target_update_fre: 1
65
+ tau: 0.005
66
+ value_layers:
67
+ - activation: relu
68
+ layer_size:
69
+ - 256
70
+ layer_type: linear
71
+ - activation: relu
72
+ layer_size:
73
+ - 256
74
+ layer_type: linear
75
+ env_cfg:
76
+ id: CartPole-v1
77
+ ignore_params:
78
+ - wrapper
79
+ - ignore_params
80
+ render_mode: null
81
+ wrapper: null
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/logs/log.txt ADDED
@@ -0,0 +1,429 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - General Configs:
2
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - ================================================================================
3
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - Name Value Type
4
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - env_name gym <class 'str'>
5
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - algo_name SAC <class 'str'>
6
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - mode train <class 'str'>
7
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - device cpu <class 'str'>
8
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - seed 1 <class 'int'>
9
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - max_episode 200 <class 'int'>
10
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - max_step 200 <class 'int'>
11
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
12
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - mp_backend single <class 'str'>
13
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - n_workers 2 <class 'int'>
14
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - n_learners 1 <class 'int'>
15
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
16
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
17
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'>
18
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - model_save_fre 100 <class 'int'>
19
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - load_checkpoint 0 <class 'bool'>
20
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - load_path Train_single_CartPole-v1_DQN_20230515-211721 <class 'str'>
21
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - load_model_step best <class 'str'>
22
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - interact_summary_fre 1 <class 'int'>
23
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - model_summary_fre 1 <class 'int'>
24
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - ================================================================================
25
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - Algo Configs:
26
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - ================================================================================
27
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - Name Value Type
28
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - critic1_lr 0.001 <class 'float'>
29
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - critic2_lr 0.001 <class 'float'>
30
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - actor_lr 0.0003 <class 'float'>
31
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - gamma 0.95 <class 'float'>
32
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - tau 0.005 <class 'float'>
33
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - alpha 0.1 <class 'float'>
34
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - automatic_entropy_tuning 0 <class 'bool'>
35
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - batch_size 64 <class 'int'>
36
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - hidden_dim 64 <class 'int'>
37
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - n_epochs 1 <class 'int'>
38
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - start_steps 10000 <class 'int'>
39
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - target_update_fre 1 <class 'int'>
40
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - buffer_size 1000000 <class 'int'>
41
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - min_policy 0 <class 'int'>
42
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - alpha_lr 0.0001 <class 'float'>
43
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - n_steps_per_learn 1 <class 'int'>
44
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - action_type discrete <class 'str'>
45
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - independ_actor 1 <class 'bool'>
46
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - share_optimizer 0 <class 'bool'>
47
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - actor_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
48
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - critic_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
49
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - value_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
50
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - buffer_type REPLAY_QUE <class 'str'>
51
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - epsilon_decay 500 <class 'int'>
52
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - epsilon_end 0.01 <class 'float'>
53
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - epsilon_start 0.95 <class 'float'>
54
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - lr 0.0001 <class 'float'>
55
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - target_update 1 <class 'int'>
56
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - ================================================================================
57
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - Env Configs:
58
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - ================================================================================
59
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - Name Value Type
60
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - id CartPole-v1 <class 'str'>
61
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - render_mode None <class 'str'>
62
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - wrapper None <class 'str'>
63
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
64
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - ================================================================================
65
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - Start training!
66
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - Interactor 1 finished episode 1 with reward 13.000 in 13 steps
67
+ 2023-06-18 16:27:02 - SimpleLog - INFO: - Interactor 0 finished episode 2 with reward 29.000 in 29 steps
68
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 0 finished episode 3 with reward 18.000 in 18 steps
69
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 1 finished episode 4 with reward 34.000 in 34 steps
70
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward 28.000 in 28 steps
71
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 1 finished episode 6 with reward 35.000 in 35 steps
72
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 0 finished episode 7 with reward 18.000 in 18 steps
73
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 1 finished episode 8 with reward 16.000 in 16 steps
74
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 0 finished episode 9 with reward 21.000 in 21 steps
75
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 1 finished episode 10 with reward 26.000 in 26 steps
76
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 0 finished episode 11 with reward 14.000 in 14 steps
77
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - update_step: 100, online_eval_reward: 26.000
78
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 26.000, save the best model!
79
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 1 finished episode 12 with reward 11.000 in 11 steps
80
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 0 finished episode 13 with reward 12.000 in 12 steps
81
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 1 finished episode 14 with reward 16.000 in 16 steps
82
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 0 finished episode 15 with reward 12.000 in 12 steps
83
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 0 finished episode 16 with reward 13.000 in 13 steps
84
+ 2023-06-18 16:27:03 - SimpleLog - INFO: - Interactor 1 finished episode 17 with reward 20.000 in 20 steps
85
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 0 finished episode 18 with reward 31.000 in 31 steps
86
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 1 finished episode 19 with reward 37.000 in 37 steps
87
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 0 finished episode 20 with reward 18.000 in 18 steps
88
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 0 finished episode 21 with reward 14.000 in 14 steps
89
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 1 finished episode 22 with reward 23.000 in 23 steps
90
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - update_step: 200, online_eval_reward: 10.000
91
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 0 finished episode 23 with reward 10.000 in 10 steps
92
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 0 finished episode 24 with reward 12.000 in 12 steps
93
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 1 finished episode 25 with reward 22.000 in 22 steps
94
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 1 finished episode 26 with reward 18.000 in 18 steps
95
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 0 finished episode 27 with reward 26.000 in 26 steps
96
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 0 finished episode 28 with reward 16.000 in 16 steps
97
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward 11.000 in 11 steps
98
+ 2023-06-18 16:27:04 - SimpleLog - INFO: - Interactor 1 finished episode 30 with reward 38.000 in 38 steps
99
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 0 finished episode 31 with reward 11.000 in 11 steps
100
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - update_step: 300, online_eval_reward: 10.000
101
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 0 finished episode 32 with reward 22.000 in 22 steps
102
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 1 finished episode 33 with reward 45.000 in 45 steps
103
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 1 finished episode 34 with reward 13.000 in 13 steps
104
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 0 finished episode 35 with reward 36.000 in 36 steps
105
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 1 finished episode 36 with reward 12.000 in 12 steps
106
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 0 finished episode 37 with reward 12.000 in 12 steps
107
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 0 finished episode 38 with reward 14.000 in 14 steps
108
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 1 finished episode 39 with reward 24.000 in 24 steps
109
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 1 finished episode 40 with reward 16.000 in 16 steps
110
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 0 finished episode 41 with reward 31.000 in 31 steps
111
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - update_step: 400, online_eval_reward: 11.000
112
+ 2023-06-18 16:27:05 - SimpleLog - INFO: - Interactor 1 finished episode 42 with reward 14.000 in 14 steps
113
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 0 finished episode 43 with reward 23.000 in 23 steps
114
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 1 finished episode 44 with reward 26.000 in 26 steps
115
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 0 finished episode 45 with reward 11.000 in 11 steps
116
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 0 finished episode 46 with reward 11.000 in 11 steps
117
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward 17.000 in 17 steps
118
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 0 finished episode 48 with reward 15.000 in 15 steps
119
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 0 finished episode 49 with reward 17.000 in 17 steps
120
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 1 finished episode 50 with reward 70.000 in 70 steps
121
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - update_step: 500, online_eval_reward: 14.000
122
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 1 finished episode 51 with reward 15.000 in 15 steps
123
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 1 finished episode 52 with reward 11.000 in 11 steps
124
+ 2023-06-18 16:27:06 - SimpleLog - INFO: - Interactor 1 finished episode 53 with reward 12.000 in 12 steps
125
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 0 finished episode 54 with reward 61.000 in 61 steps
126
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 1 finished episode 55 with reward 18.000 in 18 steps
127
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 1 finished episode 56 with reward 15.000 in 15 steps
128
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 0 finished episode 57 with reward 17.000 in 17 steps
129
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 1 finished episode 58 with reward 17.000 in 17 steps
130
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 0 finished episode 59 with reward 18.000 in 18 steps
131
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - update_step: 600, online_eval_reward: 13.000
132
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 0 finished episode 60 with reward 26.000 in 26 steps
133
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 1 finished episode 61 with reward 32.000 in 32 steps
134
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 0 finished episode 62 with reward 14.000 in 14 steps
135
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 1 finished episode 63 with reward 19.000 in 19 steps
136
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 0 finished episode 64 with reward 12.000 in 12 steps
137
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 0 finished episode 65 with reward 12.000 in 12 steps
138
+ 2023-06-18 16:27:07 - SimpleLog - INFO: - Interactor 1 finished episode 66 with reward 15.000 in 15 steps
139
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 0 finished episode 67 with reward 22.000 in 22 steps
140
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 1 finished episode 68 with reward 24.000 in 24 steps
141
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 1 finished episode 69 with reward 12.000 in 12 steps
142
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - update_step: 700, online_eval_reward: 41.000
143
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 41.000, save the best model!
144
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 0 finished episode 70 with reward 27.000 in 27 steps
145
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 1 finished episode 71 with reward 18.000 in 18 steps
146
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 0 finished episode 72 with reward 15.000 in 15 steps
147
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 1 finished episode 73 with reward 12.000 in 12 steps
148
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward 14.000 in 14 steps
149
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 1 finished episode 75 with reward 19.000 in 19 steps
150
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 0 finished episode 76 with reward 48.000 in 48 steps
151
+ 2023-06-18 16:27:08 - SimpleLog - INFO: - Interactor 1 finished episode 77 with reward 22.000 in 22 steps
152
+ 2023-06-18 16:27:09 - SimpleLog - INFO: - Interactor 0 finished episode 78 with reward 14.000 in 14 steps
153
+ 2023-06-18 16:27:09 - SimpleLog - INFO: - Interactor 0 finished episode 79 with reward 17.000 in 17 steps
154
+ 2023-06-18 16:27:09 - SimpleLog - INFO: - update_step: 800, online_eval_reward: 42.000
155
+ 2023-06-18 16:27:09 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 42.000, save the best model!
156
+ 2023-06-18 16:27:09 - SimpleLog - INFO: - Interactor 1 finished episode 80 with reward 30.000 in 30 steps
157
+ 2023-06-18 16:27:09 - SimpleLog - INFO: - Interactor 0 finished episode 81 with reward 20.000 in 20 steps
158
+ 2023-06-18 16:27:09 - SimpleLog - INFO: - Interactor 0 finished episode 82 with reward 15.000 in 15 steps
159
+ 2023-06-18 16:27:09 - SimpleLog - INFO: - Interactor 1 finished episode 83 with reward 28.000 in 28 steps
160
+ 2023-06-18 16:27:09 - SimpleLog - INFO: - Interactor 0 finished episode 84 with reward 33.000 in 33 steps
161
+ 2023-06-18 16:27:09 - SimpleLog - INFO: - Interactor 0 finished episode 85 with reward 16.000 in 16 steps
162
+ 2023-06-18 16:27:10 - SimpleLog - INFO: - Interactor 1 finished episode 86 with reward 60.000 in 60 steps
163
+ 2023-06-18 16:27:10 - SimpleLog - INFO: - Interactor 0 finished episode 87 with reward 21.000 in 21 steps
164
+ 2023-06-18 16:27:10 - SimpleLog - INFO: - update_step: 900, online_eval_reward: 200.000
165
+ 2023-06-18 16:27:10 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
166
+ 2023-06-18 16:27:10 - SimpleLog - INFO: - Interactor 0 finished episode 88 with reward 21.000 in 21 steps
167
+ 2023-06-18 16:27:10 - SimpleLog - INFO: - Interactor 1 finished episode 89 with reward 44.000 in 44 steps
168
+ 2023-06-18 16:27:10 - SimpleLog - INFO: - Interactor 1 finished episode 90 with reward 14.000 in 14 steps
169
+ 2023-06-18 16:27:10 - SimpleLog - INFO: - Interactor 0 finished episode 91 with reward 30.000 in 30 steps
170
+ 2023-06-18 16:27:11 - SimpleLog - INFO: - Interactor 0 finished episode 92 with reward 30.000 in 30 steps
171
+ 2023-06-18 16:27:11 - SimpleLog - INFO: - Interactor 0 finished episode 93 with reward 14.000 in 14 steps
172
+ 2023-06-18 16:27:11 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: 200.000
173
+ 2023-06-18 16:27:11 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
174
+ 2023-06-18 16:27:11 - SimpleLog - INFO: - Interactor 0 finished episode 94 with reward 42.000 in 42 steps
175
+ 2023-06-18 16:27:11 - SimpleLog - INFO: - Interactor 1 finished episode 95 with reward 88.000 in 88 steps
176
+ 2023-06-18 16:27:12 - SimpleLog - INFO: - Interactor 1 finished episode 96 with reward 28.000 in 28 steps
177
+ 2023-06-18 16:27:12 - SimpleLog - INFO: - update_step: 1100, online_eval_reward: 200.000
178
+ 2023-06-18 16:27:12 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
179
+ 2023-06-18 16:27:13 - SimpleLog - INFO: - Interactor 0 finished episode 97 with reward 81.000 in 81 steps
180
+ 2023-06-18 16:27:13 - SimpleLog - INFO: - Interactor 1 finished episode 98 with reward 68.000 in 68 steps
181
+ 2023-06-18 16:27:13 - SimpleLog - INFO: - Interactor 0 finished episode 99 with reward 26.000 in 26 steps
182
+ 2023-06-18 16:27:13 - SimpleLog - INFO: - Interactor 1 finished episode 100 with reward 40.000 in 40 steps
183
+ 2023-06-18 16:27:13 - SimpleLog - INFO: - Interactor 0 finished episode 101 with reward 33.000 in 33 steps
184
+ 2023-06-18 16:27:14 - SimpleLog - INFO: - update_step: 1200, online_eval_reward: 200.000
185
+ 2023-06-18 16:27:14 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
186
+ 2023-06-18 16:27:14 - SimpleLog - INFO: - Interactor 0 finished episode 102 with reward 27.000 in 27 steps
187
+ 2023-06-18 16:27:14 - SimpleLog - INFO: - Interactor 1 finished episode 103 with reward 41.000 in 41 steps
188
+ 2023-06-18 16:27:14 - SimpleLog - INFO: - Interactor 0 finished episode 104 with reward 39.000 in 39 steps
189
+ 2023-06-18 16:27:14 - SimpleLog - INFO: - Interactor 0 finished episode 105 with reward 11.000 in 11 steps
190
+ 2023-06-18 16:27:14 - SimpleLog - INFO: - Interactor 0 finished episode 106 with reward 29.000 in 29 steps
191
+ 2023-06-18 16:27:14 - SimpleLog - INFO: - Interactor 1 finished episode 107 with reward 84.000 in 84 steps
192
+ 2023-06-18 16:27:15 - SimpleLog - INFO: - update_step: 1300, online_eval_reward: 200.000
193
+ 2023-06-18 16:27:15 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
194
+ 2023-06-18 16:27:15 - SimpleLog - INFO: - Interactor 0 finished episode 108 with reward 41.000 in 41 steps
195
+ 2023-06-18 16:27:15 - SimpleLog - INFO: - Interactor 1 finished episode 109 with reward 31.000 in 31 steps
196
+ 2023-06-18 16:27:15 - SimpleLog - INFO: - Interactor 1 finished episode 110 with reward 21.000 in 21 steps
197
+ 2023-06-18 16:27:15 - SimpleLog - INFO: - Interactor 0 finished episode 111 with reward 35.000 in 35 steps
198
+ 2023-06-18 16:27:16 - SimpleLog - INFO: - update_step: 1400, online_eval_reward: 153.000
199
+ 2023-06-18 16:27:16 - SimpleLog - INFO: - Interactor 0 finished episode 112 with reward 49.000 in 49 steps
200
+ 2023-06-18 16:27:16 - SimpleLog - INFO: - Interactor 1 finished episode 113 with reward 114.000 in 114 steps
201
+ 2023-06-18 16:27:17 - SimpleLog - INFO: - Interactor 1 finished episode 114 with reward 23.000 in 23 steps
202
+ 2023-06-18 16:27:17 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: 200.000
203
+ 2023-06-18 16:27:17 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
204
+ 2023-06-18 16:27:17 - SimpleLog - INFO: - Interactor 0 finished episode 115 with reward 101.000 in 101 steps
205
+ 2023-06-18 16:27:18 - SimpleLog - INFO: - Interactor 1 finished episode 116 with reward 67.000 in 67 steps
206
+ 2023-06-18 16:27:18 - SimpleLog - INFO: - Interactor 0 finished episode 117 with reward 88.000 in 88 steps
207
+ 2023-06-18 16:27:18 - SimpleLog - INFO: - update_step: 1600, online_eval_reward: 158.000
208
+ 2023-06-18 16:27:18 - SimpleLog - INFO: - Interactor 1 finished episode 118 with reward 77.000 in 77 steps
209
+ 2023-06-18 16:27:19 - SimpleLog - INFO: - Interactor 1 finished episode 119 with reward 63.000 in 63 steps
210
+ 2023-06-18 16:27:20 - SimpleLog - INFO: - update_step: 1700, online_eval_reward: 200.000
211
+ 2023-06-18 16:27:20 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
212
+ 2023-06-18 16:27:20 - SimpleLog - INFO: - Interactor 0 finished episode 120 with reward 115.000 in 115 steps
213
+ 2023-06-18 16:27:20 - SimpleLog - INFO: - Interactor 1 finished episode 121 with reward 102.000 in 102 steps
214
+ 2023-06-18 16:27:21 - SimpleLog - INFO: - update_step: 1800, online_eval_reward: 171.000
215
+ 2023-06-18 16:27:21 - SimpleLog - INFO: - Interactor 0 finished episode 122 with reward 98.000 in 98 steps
216
+ 2023-06-18 16:27:21 - SimpleLog - INFO: - Interactor 0 finished episode 123 with reward 74.000 in 74 steps
217
+ 2023-06-18 16:27:21 - SimpleLog - INFO: - Interactor 1 finished episode 124 with reward 91.000 in 91 steps
218
+ 2023-06-18 16:27:22 - SimpleLog - INFO: - update_step: 1900, online_eval_reward: 165.000
219
+ 2023-06-18 16:27:23 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: 200.000
220
+ 2023-06-18 16:27:23 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
221
+ 2023-06-18 16:27:24 - SimpleLog - INFO: - Interactor 0 finished episode 125 with reward 171.000 in 171 steps
222
+ 2023-06-18 16:27:24 - SimpleLog - INFO: - Interactor 1 finished episode 126 with reward 168.000 in 168 steps
223
+ 2023-06-18 16:27:24 - SimpleLog - INFO: - update_step: 2100, online_eval_reward: 200.000
224
+ 2023-06-18 16:27:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
225
+ 2023-06-18 16:27:25 - SimpleLog - INFO: - Interactor 0 finished episode 127 with reward 95.000 in 95 steps
226
+ 2023-06-18 16:27:25 - SimpleLog - INFO: - Interactor 1 finished episode 128 with reward 109.000 in 109 steps
227
+ 2023-06-18 16:27:25 - SimpleLog - INFO: - update_step: 2200, online_eval_reward: 168.000
228
+ 2023-06-18 16:27:26 - SimpleLog - INFO: - Interactor 0 finished episode 129 with reward 128.000 in 128 steps
229
+ 2023-06-18 16:27:27 - SimpleLog - INFO: - update_step: 2300, online_eval_reward: 200.000
230
+ 2023-06-18 16:27:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
231
+ 2023-06-18 16:27:27 - SimpleLog - INFO: - Interactor 1 finished episode 130 with reward 168.000 in 168 steps
232
+ 2023-06-18 16:27:28 - SimpleLog - INFO: - update_step: 2400, online_eval_reward: 187.000
233
+ 2023-06-18 16:27:28 - SimpleLog - INFO: - Interactor 0 finished episode 131 with reward 144.000 in 144 steps
234
+ 2023-06-18 16:27:29 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: 200.000
235
+ 2023-06-18 16:27:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
236
+ 2023-06-18 16:27:29 - SimpleLog - INFO: - Interactor 1 finished episode 132 with reward 200.000 in 200 steps
237
+ 2023-06-18 16:27:30 - SimpleLog - INFO: - Interactor 0 finished episode 133 with reward 156.000 in 156 steps
238
+ 2023-06-18 16:27:30 - SimpleLog - INFO: - update_step: 2600, online_eval_reward: 200.000
239
+ 2023-06-18 16:27:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
240
+ 2023-06-18 16:27:31 - SimpleLog - INFO: - update_step: 2700, online_eval_reward: 200.000
241
+ 2023-06-18 16:27:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
242
+ 2023-06-18 16:27:32 - SimpleLog - INFO: - Interactor 1 finished episode 134 with reward 200.000 in 200 steps
243
+ 2023-06-18 16:27:32 - SimpleLog - INFO: - Interactor 0 finished episode 135 with reward 183.000 in 183 steps
244
+ 2023-06-18 16:27:33 - SimpleLog - INFO: - update_step: 2800, online_eval_reward: 200.000
245
+ 2023-06-18 16:27:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
246
+ 2023-06-18 16:27:34 - SimpleLog - INFO: - update_step: 2900, online_eval_reward: 200.000
247
+ 2023-06-18 16:27:34 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
248
+ 2023-06-18 16:27:34 - SimpleLog - INFO: - Interactor 1 finished episode 136 with reward 200.000 in 200 steps
249
+ 2023-06-18 16:27:34 - SimpleLog - INFO: - Interactor 0 finished episode 137 with reward 200.000 in 200 steps
250
+ 2023-06-18 16:27:35 - SimpleLog - INFO: - update_step: 3000, online_eval_reward: 200.000
251
+ 2023-06-18 16:27:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
252
+ 2023-06-18 16:27:36 - SimpleLog - INFO: - Interactor 1 finished episode 138 with reward 140.000 in 140 steps
253
+ 2023-06-18 16:27:36 - SimpleLog - INFO: - update_step: 3100, online_eval_reward: 200.000
254
+ 2023-06-18 16:27:36 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
255
+ 2023-06-18 16:27:37 - SimpleLog - INFO: - Interactor 0 finished episode 139 with reward 200.000 in 200 steps
256
+ 2023-06-18 16:27:38 - SimpleLog - INFO: - update_step: 3200, online_eval_reward: 200.000
257
+ 2023-06-18 16:27:38 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
258
+ 2023-06-18 16:27:38 - SimpleLog - INFO: - Interactor 1 finished episode 140 with reward 200.000 in 200 steps
259
+ 2023-06-18 16:27:39 - SimpleLog - INFO: - update_step: 3300, online_eval_reward: 200.000
260
+ 2023-06-18 16:27:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
261
+ 2023-06-18 16:27:39 - SimpleLog - INFO: - Interactor 0 finished episode 141 with reward 144.000 in 144 steps
262
+ 2023-06-18 16:27:40 - SimpleLog - INFO: - update_step: 3400, online_eval_reward: 200.000
263
+ 2023-06-18 16:27:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
264
+ 2023-06-18 16:27:41 - SimpleLog - INFO: - Interactor 1 finished episode 142 with reward 200.000 in 200 steps
265
+ 2023-06-18 16:27:41 - SimpleLog - INFO: - update_step: 3500, online_eval_reward: 200.000
266
+ 2023-06-18 16:27:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
267
+ 2023-06-18 16:27:41 - SimpleLog - INFO: - Interactor 0 finished episode 143 with reward 200.000 in 200 steps
268
+ 2023-06-18 16:27:42 - SimpleLog - INFO: - update_step: 3600, online_eval_reward: 200.000
269
+ 2023-06-18 16:27:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
270
+ 2023-06-18 16:27:43 - SimpleLog - INFO: - Interactor 1 finished episode 144 with reward 178.000 in 178 steps
271
+ 2023-06-18 16:27:44 - SimpleLog - INFO: - update_step: 3700, online_eval_reward: 200.000
272
+ 2023-06-18 16:27:44 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
273
+ 2023-06-18 16:27:44 - SimpleLog - INFO: - Interactor 0 finished episode 145 with reward 200.000 in 200 steps
274
+ 2023-06-18 16:27:45 - SimpleLog - INFO: - update_step: 3800, online_eval_reward: 200.000
275
+ 2023-06-18 16:27:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
276
+ 2023-06-18 16:27:45 - SimpleLog - INFO: - Interactor 1 finished episode 146 with reward 200.000 in 200 steps
277
+ 2023-06-18 16:27:46 - SimpleLog - INFO: - Interactor 0 finished episode 147 with reward 186.000 in 186 steps
278
+ 2023-06-18 16:27:46 - SimpleLog - INFO: - update_step: 3900, online_eval_reward: 200.000
279
+ 2023-06-18 16:27:46 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
280
+ 2023-06-18 16:27:47 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: 200.000
281
+ 2023-06-18 16:27:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
282
+ 2023-06-18 16:27:48 - SimpleLog - INFO: - Interactor 1 finished episode 148 with reward 200.000 in 200 steps
283
+ 2023-06-18 16:27:48 - SimpleLog - INFO: - Interactor 0 finished episode 149 with reward 200.000 in 200 steps
284
+ 2023-06-18 16:27:49 - SimpleLog - INFO: - update_step: 4100, online_eval_reward: 200.000
285
+ 2023-06-18 16:27:49 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
286
+ 2023-06-18 16:27:50 - SimpleLog - INFO: - update_step: 4200, online_eval_reward: 200.000
287
+ 2023-06-18 16:27:50 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
288
+ 2023-06-18 16:27:50 - SimpleLog - INFO: - Interactor 1 finished episode 150 with reward 200.000 in 200 steps
289
+ 2023-06-18 16:27:50 - SimpleLog - INFO: - Interactor 0 finished episode 151 with reward 192.000 in 192 steps
290
+ 2023-06-18 16:27:51 - SimpleLog - INFO: - update_step: 4300, online_eval_reward: 200.000
291
+ 2023-06-18 16:27:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
292
+ 2023-06-18 16:27:52 - SimpleLog - INFO: - update_step: 4400, online_eval_reward: 200.000
293
+ 2023-06-18 16:27:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
294
+ 2023-06-18 16:27:53 - SimpleLog - INFO: - Interactor 1 finished episode 152 with reward 200.000 in 200 steps
295
+ 2023-06-18 16:27:53 - SimpleLog - INFO: - Interactor 0 finished episode 153 with reward 200.000 in 200 steps
296
+ 2023-06-18 16:27:53 - SimpleLog - INFO: - update_step: 4500, online_eval_reward: 200.000
297
+ 2023-06-18 16:27:53 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
298
+ 2023-06-18 16:27:55 - SimpleLog - INFO: - update_step: 4600, online_eval_reward: 200.000
299
+ 2023-06-18 16:27:55 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
300
+ 2023-06-18 16:27:55 - SimpleLog - INFO: - Interactor 1 finished episode 154 with reward 156.000 in 156 steps
301
+ 2023-06-18 16:27:55 - SimpleLog - INFO: - Interactor 0 finished episode 155 with reward 200.000 in 200 steps
302
+ 2023-06-18 16:27:56 - SimpleLog - INFO: - update_step: 4700, online_eval_reward: 200.000
303
+ 2023-06-18 16:27:56 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
304
+ 2023-06-18 16:27:56 - SimpleLog - INFO: - Interactor 1 finished episode 156 with reward 177.000 in 177 steps
305
+ 2023-06-18 16:27:57 - SimpleLog - INFO: - update_step: 4800, online_eval_reward: 200.000
306
+ 2023-06-18 16:27:57 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
307
+ 2023-06-18 16:27:58 - SimpleLog - INFO: - Interactor 0 finished episode 157 with reward 200.000 in 200 steps
308
+ 2023-06-18 16:27:58 - SimpleLog - INFO: - update_step: 4900, online_eval_reward: 200.000
309
+ 2023-06-18 16:27:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
310
+ 2023-06-18 16:27:59 - SimpleLog - INFO: - Interactor 1 finished episode 158 with reward 200.000 in 200 steps
311
+ 2023-06-18 16:27:59 - SimpleLog - INFO: - update_step: 5000, online_eval_reward: 200.000
312
+ 2023-06-18 16:27:59 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
313
+ 2023-06-18 16:28:00 - SimpleLog - INFO: - Interactor 0 finished episode 159 with reward 200.000 in 200 steps
314
+ 2023-06-18 16:28:01 - SimpleLog - INFO: - update_step: 5100, online_eval_reward: 200.000
315
+ 2023-06-18 16:28:01 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
316
+ 2023-06-18 16:28:01 - SimpleLog - INFO: - Interactor 1 finished episode 160 with reward 196.000 in 196 steps
317
+ 2023-06-18 16:28:02 - SimpleLog - INFO: - update_step: 5200, online_eval_reward: 200.000
318
+ 2023-06-18 16:28:02 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
319
+ 2023-06-18 16:28:02 - SimpleLog - INFO: - Interactor 0 finished episode 161 with reward 200.000 in 200 steps
320
+ 2023-06-18 16:28:03 - SimpleLog - INFO: - update_step: 5300, online_eval_reward: 200.000
321
+ 2023-06-18 16:28:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
322
+ 2023-06-18 16:28:04 - SimpleLog - INFO: - Interactor 1 finished episode 162 with reward 200.000 in 200 steps
323
+ 2023-06-18 16:28:04 - SimpleLog - INFO: - update_step: 5400, online_eval_reward: 200.000
324
+ 2023-06-18 16:28:04 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
325
+ 2023-06-18 16:28:05 - SimpleLog - INFO: - Interactor 0 finished episode 163 with reward 200.000 in 200 steps
326
+ 2023-06-18 16:28:05 - SimpleLog - INFO: - update_step: 5500, online_eval_reward: 200.000
327
+ 2023-06-18 16:28:05 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
328
+ 2023-06-18 16:28:06 - SimpleLog - INFO: - Interactor 1 finished episode 164 with reward 200.000 in 200 steps
329
+ 2023-06-18 16:28:07 - SimpleLog - INFO: - update_step: 5600, online_eval_reward: 200.000
330
+ 2023-06-18 16:28:07 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
331
+ 2023-06-18 16:28:07 - SimpleLog - INFO: - Interactor 0 finished episode 165 with reward 200.000 in 200 steps
332
+ 2023-06-18 16:28:08 - SimpleLog - INFO: - update_step: 5700, online_eval_reward: 200.000
333
+ 2023-06-18 16:28:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
334
+ 2023-06-18 16:28:08 - SimpleLog - INFO: - Interactor 1 finished episode 166 with reward 179.000 in 179 steps
335
+ 2023-06-18 16:28:09 - SimpleLog - INFO: - update_step: 5800, online_eval_reward: 200.000
336
+ 2023-06-18 16:28:09 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
337
+ 2023-06-18 16:28:10 - SimpleLog - INFO: - Interactor 0 finished episode 167 with reward 200.000 in 200 steps
338
+ 2023-06-18 16:28:11 - SimpleLog - INFO: - update_step: 5900, online_eval_reward: 200.000
339
+ 2023-06-18 16:28:11 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
340
+ 2023-06-18 16:28:11 - SimpleLog - INFO: - Interactor 1 finished episode 168 with reward 148.000 in 148 steps
341
+ 2023-06-18 16:28:12 - SimpleLog - INFO: - update_step: 6000, online_eval_reward: 200.000
342
+ 2023-06-18 16:28:12 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
343
+ 2023-06-18 16:28:13 - SimpleLog - INFO: - Interactor 0 finished episode 169 with reward 186.000 in 186 steps
344
+ 2023-06-18 16:28:13 - SimpleLog - INFO: - Interactor 1 finished episode 170 with reward 181.000 in 181 steps
345
+ 2023-06-18 16:28:14 - SimpleLog - INFO: - update_step: 6100, online_eval_reward: 200.000
346
+ 2023-06-18 16:28:14 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
347
+ 2023-06-18 16:28:15 - SimpleLog - INFO: - update_step: 6200, online_eval_reward: 200.000
348
+ 2023-06-18 16:28:15 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
349
+ 2023-06-18 16:28:16 - SimpleLog - INFO: - Interactor 1 finished episode 171 with reward 141.000 in 141 steps
350
+ 2023-06-18 16:28:16 - SimpleLog - INFO: - Interactor 0 finished episode 172 with reward 177.000 in 177 steps
351
+ 2023-06-18 16:28:17 - SimpleLog - INFO: - update_step: 6300, online_eval_reward: 200.000
352
+ 2023-06-18 16:28:17 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
353
+ 2023-06-18 16:28:18 - SimpleLog - INFO: - update_step: 6400, online_eval_reward: 200.000
354
+ 2023-06-18 16:28:18 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
355
+ 2023-06-18 16:28:19 - SimpleLog - INFO: - Interactor 1 finished episode 173 with reward 200.000 in 200 steps
356
+ 2023-06-18 16:28:19 - SimpleLog - INFO: - Interactor 0 finished episode 174 with reward 197.000 in 197 steps
357
+ 2023-06-18 16:28:20 - SimpleLog - INFO: - update_step: 6500, online_eval_reward: 200.000
358
+ 2023-06-18 16:28:20 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
359
+ 2023-06-18 16:28:20 - SimpleLog - INFO: - Interactor 1 finished episode 175 with reward 170.000 in 170 steps
360
+ 2023-06-18 16:28:21 - SimpleLog - INFO: - update_step: 6600, online_eval_reward: 200.000
361
+ 2023-06-18 16:28:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
362
+ 2023-06-18 16:28:21 - SimpleLog - INFO: - Interactor 0 finished episode 176 with reward 192.000 in 192 steps
363
+ 2023-06-18 16:28:22 - SimpleLog - INFO: - update_step: 6700, online_eval_reward: 200.000
364
+ 2023-06-18 16:28:22 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
365
+ 2023-06-18 16:28:23 - SimpleLog - INFO: - Interactor 0 finished episode 177 with reward 148.000 in 148 steps
366
+ 2023-06-18 16:28:23 - SimpleLog - INFO: - Interactor 1 finished episode 178 with reward 200.000 in 200 steps
367
+ 2023-06-18 16:28:24 - SimpleLog - INFO: - update_step: 6800, online_eval_reward: 200.000
368
+ 2023-06-18 16:28:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
369
+ 2023-06-18 16:28:25 - SimpleLog - INFO: - update_step: 6900, online_eval_reward: 200.000
370
+ 2023-06-18 16:28:25 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
371
+ 2023-06-18 16:28:25 - SimpleLog - INFO: - Interactor 0 finished episode 179 with reward 131.000 in 131 steps
372
+ 2023-06-18 16:28:25 - SimpleLog - INFO: - Interactor 1 finished episode 180 with reward 149.000 in 149 steps
373
+ 2023-06-18 16:28:26 - SimpleLog - INFO: - update_step: 7000, online_eval_reward: 200.000
374
+ 2023-06-18 16:28:26 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
375
+ 2023-06-18 16:28:27 - SimpleLog - INFO: - Interactor 0 finished episode 181 with reward 176.000 in 176 steps
376
+ 2023-06-18 16:28:27 - SimpleLog - INFO: - update_step: 7100, online_eval_reward: 200.000
377
+ 2023-06-18 16:28:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
378
+ 2023-06-18 16:28:28 - SimpleLog - INFO: - Interactor 1 finished episode 182 with reward 200.000 in 200 steps
379
+ 2023-06-18 16:28:29 - SimpleLog - INFO: - update_step: 7200, online_eval_reward: 200.000
380
+ 2023-06-18 16:28:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
381
+ 2023-06-18 16:28:29 - SimpleLog - INFO: - Interactor 0 finished episode 183 with reward 162.000 in 162 steps
382
+ 2023-06-18 16:28:30 - SimpleLog - INFO: - update_step: 7300, online_eval_reward: 200.000
383
+ 2023-06-18 16:28:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
384
+ 2023-06-18 16:28:30 - SimpleLog - INFO: - Interactor 1 finished episode 184 with reward 200.000 in 200 steps
385
+ 2023-06-18 16:28:31 - SimpleLog - INFO: - update_step: 7400, online_eval_reward: 200.000
386
+ 2023-06-18 16:28:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
387
+ 2023-06-18 16:28:31 - SimpleLog - INFO: - Interactor 0 finished episode 185 with reward 188.000 in 188 steps
388
+ 2023-06-18 16:28:32 - SimpleLog - INFO: - update_step: 7500, online_eval_reward: 200.000
389
+ 2023-06-18 16:28:32 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
390
+ 2023-06-18 16:28:33 - SimpleLog - INFO: - Interactor 1 finished episode 186 with reward 200.000 in 200 steps
391
+ 2023-06-18 16:28:33 - SimpleLog - INFO: - update_step: 7600, online_eval_reward: 200.000
392
+ 2023-06-18 16:28:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
393
+ 2023-06-18 16:28:34 - SimpleLog - INFO: - Interactor 0 finished episode 187 with reward 189.000 in 189 steps
394
+ 2023-06-18 16:28:35 - SimpleLog - INFO: - update_step: 7700, online_eval_reward: 200.000
395
+ 2023-06-18 16:28:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
396
+ 2023-06-18 16:28:35 - SimpleLog - INFO: - Interactor 1 finished episode 188 with reward 200.000 in 200 steps
397
+ 2023-06-18 16:28:36 - SimpleLog - INFO: - update_step: 7800, online_eval_reward: 200.000
398
+ 2023-06-18 16:28:36 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
399
+ 2023-06-18 16:28:36 - SimpleLog - INFO: - Interactor 0 finished episode 189 with reward 175.000 in 175 steps
400
+ 2023-06-18 16:28:36 - SimpleLog - INFO: - Interactor 1 finished episode 190 with reward 133.000 in 133 steps
401
+ 2023-06-18 16:28:37 - SimpleLog - INFO: - update_step: 7900, online_eval_reward: 200.000
402
+ 2023-06-18 16:28:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
403
+ 2023-06-18 16:28:38 - SimpleLog - INFO: - Interactor 0 finished episode 191 with reward 191.000 in 191 steps
404
+ 2023-06-18 16:28:38 - SimpleLog - INFO: - update_step: 8000, online_eval_reward: 200.000
405
+ 2023-06-18 16:28:38 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
406
+ 2023-06-18 16:28:39 - SimpleLog - INFO: - Interactor 1 finished episode 192 with reward 163.000 in 163 steps
407
+ 2023-06-18 16:28:40 - SimpleLog - INFO: - update_step: 8100, online_eval_reward: 200.000
408
+ 2023-06-18 16:28:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
409
+ 2023-06-18 16:28:40 - SimpleLog - INFO: - Interactor 0 finished episode 193 with reward 200.000 in 200 steps
410
+ 2023-06-18 16:28:41 - SimpleLog - INFO: - update_step: 8200, online_eval_reward: 200.000
411
+ 2023-06-18 16:28:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
412
+ 2023-06-18 16:28:41 - SimpleLog - INFO: - Interactor 1 finished episode 194 with reward 168.000 in 168 steps
413
+ 2023-06-18 16:28:42 - SimpleLog - INFO: - update_step: 8300, online_eval_reward: 200.000
414
+ 2023-06-18 16:28:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
415
+ 2023-06-18 16:28:43 - SimpleLog - INFO: - Interactor 1 finished episode 195 with reward 179.000 in 179 steps
416
+ 2023-06-18 16:28:43 - SimpleLog - INFO: - Interactor 0 finished episode 196 with reward 200.000 in 200 steps
417
+ 2023-06-18 16:28:43 - SimpleLog - INFO: - update_step: 8400, online_eval_reward: 200.000
418
+ 2023-06-18 16:28:43 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
419
+ 2023-06-18 16:28:45 - SimpleLog - INFO: - update_step: 8500, online_eval_reward: 200.000
420
+ 2023-06-18 16:28:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
421
+ 2023-06-18 16:28:45 - SimpleLog - INFO: - Interactor 1 finished episode 197 with reward 200.000 in 200 steps
422
+ 2023-06-18 16:28:45 - SimpleLog - INFO: - Interactor 0 finished episode 198 with reward 200.000 in 200 steps
423
+ 2023-06-18 16:28:46 - SimpleLog - INFO: - update_step: 8600, online_eval_reward: 200.000
424
+ 2023-06-18 16:28:46 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
425
+ 2023-06-18 16:28:47 - SimpleLog - INFO: - update_step: 8700, online_eval_reward: 200.000
426
+ 2023-06-18 16:28:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
427
+ 2023-06-18 16:28:48 - SimpleLog - INFO: - Interactor 0 finished episode 199 with reward 155.000 in 155 steps
428
+ 2023-06-18 16:28:48 - SimpleLog - INFO: - Interactor 1 finished episode 200 with reward 200.000 in 200 steps
429
+ 2023-06-18 16:28:48 - SimpleLog - INFO: - Finish training! Time cost: 105.571 s
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:585592996f4be38915cb427294b1d2023bfe29ce1555b9c9579c2f430fc370c6
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/1000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:784523ef3b2de6b079c5d792206b56efc56d09da37c785c6a85e62fadd161cf1
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/1600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e4ece772fcb0da915320c39ec1ab6fdb5c37ba45aa375cbc8754298089d8f6a
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/1700 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c75d4787fc6f33680307d402c4c72db2846f91c74b1d0fb06003b0cb5176dce1
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/1800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38faee3e44dbe454255a8daf382899007814d4fe65e74d3262e4dcb67bd93791
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/1900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74a409847aaa26af05e88a076a391ff5017cb2ca504247a0fafa60bacebfc69c
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1118ee1a1b171197df8e687d062c7219fedbaab026e1896e58a73059485104ff
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/2000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37d39a43e9df4af5a0d8a6cc6da7d6b15f5281ed3e9adda98b50a0ab4440012f
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/2100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7299911938f7303ec6f260f0e8444f335b41e21eee4107aac01c5e32da96f7aa
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/2900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14a2af22bd910457587a8e40f64e8355f59c4feb4c3a11cd81ae91f6ca6d6cd
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/300 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fc54983c79de4f0e7e8169712da917645324b63837d783ccd5c0a6db0124b8a
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/3000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d7936cfb1a27cccf6fb605e684f7813f134019eba1f4e87997ab660d8897725
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/3200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8179f29344faa18e16d1e43a66936207b52ae3cd9937673c60cc792fd05c5632
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/3900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0eda97974f6f7866b69d029f2ab0bbb00456e06fc0541021b84f8a62cf962d
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/400 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ef987a10e0b8140d372d6de0a39913d8303b23c055726c3595107b04987c1f
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/4000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e3f8cbad42e7f1a60e31d44dccc564d79a15587f9ef2f39495ada7b21d3557a
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/4200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe3249c4c4210aed5f690974cd681c42c87c230d9c8f8f40cdd8fe214a9dd804
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/4600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71b9daa3b8fd48e9d34a2c10e1d1e0bcea07e2f2d32be7e4b05ed75a942b493d
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbf13e116e7f0a3f0f0ccf8b5a0e4f4bde3dbcd5d82990ab11576847060f524b
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/5000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de71efe99914249401b89f0a5eeb580479e7ccccead386c9eb5515ec06d8af67
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/5700 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029023aab60632c1ec493c4134b402d2c178e1774615933a1351f37e565457fd
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/5800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa68e086143f5857daf34dd674ef6d44c77121f48cbb74d1bd08ea8af05d10de
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/5900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57b26b5e2aab0f1bf1890f56d0976bc622313aba7e3cca806035537fec1034f6
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:480163a42f4b17ef28a2d796b012daa4966de754e1d7dbab7f08cd2cda4576e3
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/6000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8542382bde4cc229421878b846259bcfd28564bdeb6a72ae74910bbd2351db67
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/6300 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b66d4cf3d81efde1f33b70d5d2a512644d0f9bb22cc4b3de787e2eea7e4d94
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/6400 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e73b3b6396dd643f10c26ca10885662ba581ad73b1dc17505658da1fcc2c0722
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/6900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f7e32dd0fb244cffae59636ea39e10f7f07bd98fe648151f38cc33ebe822ab8
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/700 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52aa41878d15cdd1e4fbe60a980bac1b1bb5ed5567bb1c2a59ffab80072041b8
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/7100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf209affc398b5e0866f7e0d03c4264effaffa525dbed8427c89bab275c88540
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/7200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b2ec8c1e97ad15f761f85956af25304c8e01802c986653d62c00ba4e4a9d852
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/7900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b52618275aeae5220abb70a03c584427ef97184a178d3c4c2fdbee08286831
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab8f2bf67a3ea3a681f89def2c607982528058a3ee282e84e34177530e52f76
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/8700 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24738476e4b24fbd41c025a4fa02666e6aedd2a9f53d4e061936e9613da45da7
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0040ac0a927f5730a8308757d1afb31346feb712ec8884fadf6128dd8cd2b4ab
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/models/best ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24738476e4b24fbd41c025a4fa02666e6aedd2a9f53d4e061936e9613da45da7
3
+ size 1362571
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/tb_logs/interact/events.out.tfevents.1687076822.ML3090.327748.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d8de034c3eb07d75b5a32b1e99dfa9e98709a4202d8eda2dab011e01c889781
3
+ size 19786
ClassControl/Pendulum-v1/Train_CartPole-v1_SAC_20230618-162702/tb_logs/policy/events.out.tfevents.1687076822.ML3090.327748.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f2c9fdecd455043f5d2bbdbfa2572586fcb3624ec8fe4ba3adf327a64f78bb
3
+ size 2439660