Hugging Face's logo

joyrl
/
joyrl-benchmarks

TensorBoard
Model card Files
xet
Metrics Community
15

Test_CartPole-v1_SAC

#7
by gsc579 - opened
base: refs/heads/main
←
from: refs/pr/7
Discussion Files changed
+867
-0
This view is limited to 50 files because it contains too many changes.  See the raw diff here.
Files changed (50) hide show
  1. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/config.yaml +81 -0
  2. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/logs/log.txt +639 -0
  3. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/100 +3 -0
  4. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1000 +3 -0
  5. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10000 +3 -0
  6. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10300 +3 -0
  7. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10900 +3 -0
  8. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1100 +3 -0
  9. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11000 +3 -0
  10. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11600 +3 -0
  11. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11700 +3 -0
  12. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11800 +3 -0
  13. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11900 +3 -0
  14. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1200 +3 -0
  15. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/12100 +3 -0
  16. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13000 +3 -0
  17. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13100 +3 -0
  18. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13200 +3 -0
  19. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13900 +3 -0
  20. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1400 +3 -0
  21. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14000 +3 -0
  22. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14100 +3 -0
  23. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14200 +3 -0
  24. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14300 +3 -0
  25. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14900 +3 -0
  26. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1500 +3 -0
  27. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15000 +3 -0
  28. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15100 +3 -0
  29. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15800 +3 -0
  30. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15900 +3 -0
  31. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1600 +3 -0
  32. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16000 +3 -0
  33. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16100 +3 -0
  34. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16800 +3 -0
  35. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1700 +3 -0
  36. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17000 +3 -0
  37. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17100 +3 -0
  38. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17200 +3 -0
  39. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17300 +3 -0
  40. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17600 +3 -0
  41. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17700 +3 -0
  42. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17900 +3 -0
  43. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1800 +3 -0
  44. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18000 +3 -0
  45. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18400 +3 -0
  46. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18600 +3 -0
  47. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18700 +3 -0
  48. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1900 +3 -0
  49. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/200 +3 -0
  50. ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/tb_logs/interact/events.out.tfevents.1687077139.ML3090.328984.0 +3 -0
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/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: true
8
+ load_model_step: best
9
+ load_path: Train_CartPole-v1_SAC_20230618-162702
10
+ max_episode: 200
11
+ max_step: 200
12
+ mode: test
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/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/logs/log.txt ADDED
@@ -0,0 +1,639 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - General Configs:
2
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================
3
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - Name Value Type
4
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - env_name gym <class 'str'>
5
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - algo_name SAC <class 'str'>
6
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - mode test <class 'str'>
7
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - device cpu <class 'str'>
8
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - seed 1 <class 'int'>
9
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - max_episode 200 <class 'int'>
10
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - max_step 200 <class 'int'>
11
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
12
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - mp_backend single <class 'str'>
13
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - n_workers 2 <class 'int'>
14
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - n_learners 1 <class 'int'>
15
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
16
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
17
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'>
18
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - model_save_fre 100 <class 'int'>
19
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - load_checkpoint 1 <class 'bool'>
20
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - load_path Train_CartPole-v1_SAC_20230618-162702 <class 'str'>
21
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - load_model_step best <class 'str'>
22
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - interact_summary_fre 1 <class 'int'>
23
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - model_summary_fre 1 <class 'int'>
24
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================
25
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - Algo Configs:
26
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================
27
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - Name Value Type
28
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - critic1_lr 0.001 <class 'float'>
29
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - critic2_lr 0.001 <class 'float'>
30
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - actor_lr 0.0003 <class 'float'>
31
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - gamma 0.95 <class 'float'>
32
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - tau 0.005 <class 'float'>
33
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - alpha 0.1 <class 'float'>
34
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - automatic_entropy_tuning 0 <class 'bool'>
35
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - batch_size 64 <class 'int'>
36
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - hidden_dim 64 <class 'int'>
37
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - n_epochs 1 <class 'int'>
38
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - start_steps 10000 <class 'int'>
39
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - target_update_fre 1 <class 'int'>
40
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - buffer_size 1000000 <class 'int'>
41
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - min_policy 0 <class 'int'>
42
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - alpha_lr 0.0001 <class 'float'>
43
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - n_steps_per_learn 1 <class 'int'>
44
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - action_type discrete <class 'str'>
45
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - independ_actor 1 <class 'bool'>
46
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - share_optimizer 0 <class 'bool'>
47
+ 2023-06-18 16:32:19 - 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 16:32:19 - 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 16:32:19 - 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 16:32:19 - SimpleLog - INFO: - buffer_type REPLAY_QUE <class 'str'>
51
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - epsilon_decay 500 <class 'int'>
52
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - epsilon_end 0.01 <class 'float'>
53
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - epsilon_start 0.95 <class 'float'>
54
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - lr 0.0001 <class 'float'>
55
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - target_update 1 <class 'int'>
56
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================
57
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - Env Configs:
58
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================
59
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - Name Value Type
60
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - id CartPole-v1 <class 'str'>
61
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - render_mode None <class 'str'>
62
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - wrapper None <class 'str'>
63
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
64
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - ================================================================================
65
+ 2023-06-18 16:32:19 - SimpleLog - INFO: - Start testing!
66
+ 2023-06-18 16:32:21 - SimpleLog - INFO: - update_step: 100, online_eval_reward: 200.000
67
+ 2023-06-18 16:32:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
68
+ 2023-06-18 16:32:21 - SimpleLog - INFO: - Interactor 0 finished episode 1 with reward 199.000 in 199 steps
69
+ 2023-06-18 16:32:21 - SimpleLog - INFO: - Interactor 1 finished episode 2 with reward 200.000 in 200 steps
70
+ 2023-06-18 16:32:22 - SimpleLog - INFO: - update_step: 200, online_eval_reward: 200.000
71
+ 2023-06-18 16:32:22 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
72
+ 2023-06-18 16:32:23 - SimpleLog - INFO: - update_step: 300, online_eval_reward: 200.000
73
+ 2023-06-18 16:32:23 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
74
+ 2023-06-18 16:32:23 - SimpleLog - INFO: - Interactor 1 finished episode 3 with reward 149.000 in 149 steps
75
+ 2023-06-18 16:32:23 - SimpleLog - INFO: - Interactor 0 finished episode 4 with reward 167.000 in 167 steps
76
+ 2023-06-18 16:32:24 - SimpleLog - INFO: - update_step: 400, online_eval_reward: 184.000
77
+ 2023-06-18 16:32:25 - SimpleLog - INFO: - update_step: 500, online_eval_reward: 200.000
78
+ 2023-06-18 16:32:25 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
79
+ 2023-06-18 16:32:25 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward 169.000 in 169 steps
80
+ 2023-06-18 16:32:26 - SimpleLog - INFO: - Interactor 1 finished episode 6 with reward 200.000 in 200 steps
81
+ 2023-06-18 16:32:27 - SimpleLog - INFO: - update_step: 600, online_eval_reward: 200.000
82
+ 2023-06-18 16:32:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
83
+ 2023-06-18 16:32:27 - SimpleLog - INFO: - Interactor 0 finished episode 7 with reward 111.000 in 111 steps
84
+ 2023-06-18 16:32:28 - SimpleLog - INFO: - update_step: 700, online_eval_reward: 200.000
85
+ 2023-06-18 16:32:28 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
86
+ 2023-06-18 16:32:28 - SimpleLog - INFO: - Interactor 1 finished episode 8 with reward 200.000 in 200 steps
87
+ 2023-06-18 16:32:28 - SimpleLog - INFO: - Interactor 0 finished episode 9 with reward 129.000 in 129 steps
88
+ 2023-06-18 16:32:29 - SimpleLog - INFO: - update_step: 800, online_eval_reward: 200.000
89
+ 2023-06-18 16:32:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
90
+ 2023-06-18 16:32:30 - SimpleLog - INFO: - update_step: 900, online_eval_reward: 200.000
91
+ 2023-06-18 16:32:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
92
+ 2023-06-18 16:32:30 - SimpleLog - INFO: - Interactor 1 finished episode 10 with reward 200.000 in 200 steps
93
+ 2023-06-18 16:32:30 - SimpleLog - INFO: - Interactor 0 finished episode 11 with reward 200.000 in 200 steps
94
+ 2023-06-18 16:32:31 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: 200.000
95
+ 2023-06-18 16:32:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
96
+ 2023-06-18 16:32:32 - SimpleLog - INFO: - Interactor 1 finished episode 12 with reward 137.000 in 137 steps
97
+ 2023-06-18 16:32:33 - SimpleLog - INFO: - update_step: 1100, online_eval_reward: 200.000
98
+ 2023-06-18 16:32:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
99
+ 2023-06-18 16:32:33 - SimpleLog - INFO: - Interactor 0 finished episode 13 with reward 182.000 in 182 steps
100
+ 2023-06-18 16:32:34 - SimpleLog - INFO: - update_step: 1200, online_eval_reward: 200.000
101
+ 2023-06-18 16:32:34 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
102
+ 2023-06-18 16:32:34 - SimpleLog - INFO: - Interactor 1 finished episode 14 with reward 163.000 in 163 steps
103
+ 2023-06-18 16:32:34 - SimpleLog - INFO: - Interactor 0 finished episode 15 with reward 157.000 in 157 steps
104
+ 2023-06-18 16:32:35 - SimpleLog - INFO: - update_step: 1300, online_eval_reward: 200.000
105
+ 2023-06-18 16:32:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
106
+ 2023-06-18 16:32:36 - SimpleLog - INFO: - update_step: 1400, online_eval_reward: 200.000
107
+ 2023-06-18 16:32:36 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
108
+ 2023-06-18 16:32:36 - SimpleLog - INFO: - Interactor 0 finished episode 16 with reward 131.000 in 131 steps
109
+ 2023-06-18 16:32:36 - SimpleLog - INFO: - Interactor 1 finished episode 17 with reward 200.000 in 200 steps
110
+ 2023-06-18 16:32:37 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: 200.000
111
+ 2023-06-18 16:32:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
112
+ 2023-06-18 16:32:39 - SimpleLog - INFO: - update_step: 1600, online_eval_reward: 200.000
113
+ 2023-06-18 16:32:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
114
+ 2023-06-18 16:32:39 - SimpleLog - INFO: - Interactor 0 finished episode 18 with reward 200.000 in 200 steps
115
+ 2023-06-18 16:32:39 - SimpleLog - INFO: - Interactor 1 finished episode 19 with reward 200.000 in 200 steps
116
+ 2023-06-18 16:32:40 - SimpleLog - INFO: - update_step: 1700, online_eval_reward: 200.000
117
+ 2023-06-18 16:32:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
118
+ 2023-06-18 16:32:41 - SimpleLog - INFO: - Interactor 1 finished episode 20 with reward 173.000 in 173 steps
119
+ 2023-06-18 16:32:41 - SimpleLog - INFO: - update_step: 1800, online_eval_reward: 200.000
120
+ 2023-06-18 16:32:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
121
+ 2023-06-18 16:32:41 - SimpleLog - INFO: - Interactor 0 finished episode 21 with reward 200.000 in 200 steps
122
+ 2023-06-18 16:32:42 - SimpleLog - INFO: - update_step: 1900, online_eval_reward: 200.000
123
+ 2023-06-18 16:32:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
124
+ 2023-06-18 16:32:43 - SimpleLog - INFO: - Interactor 1 finished episode 22 with reward 170.000 in 170 steps
125
+ 2023-06-18 16:32:43 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: 200.000
126
+ 2023-06-18 16:32:43 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
127
+ 2023-06-18 16:32:44 - SimpleLog - INFO: - Interactor 0 finished episode 23 with reward 196.000 in 196 steps
128
+ 2023-06-18 16:32:45 - SimpleLog - INFO: - update_step: 2100, online_eval_reward: 200.000
129
+ 2023-06-18 16:32:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
130
+ 2023-06-18 16:32:45 - SimpleLog - INFO: - Interactor 1 finished episode 24 with reward 153.000 in 153 steps
131
+ 2023-06-18 16:32:45 - SimpleLog - INFO: - Interactor 0 finished episode 25 with reward 186.000 in 186 steps
132
+ 2023-06-18 16:32:46 - SimpleLog - INFO: - update_step: 2200, online_eval_reward: 200.000
133
+ 2023-06-18 16:32:46 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
134
+ 2023-06-18 16:32:47 - SimpleLog - INFO: - Interactor 1 finished episode 26 with reward 178.000 in 178 steps
135
+ 2023-06-18 16:32:47 - SimpleLog - INFO: - update_step: 2300, online_eval_reward: 200.000
136
+ 2023-06-18 16:32:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
137
+ 2023-06-18 16:32:48 - SimpleLog - INFO: - Interactor 0 finished episode 27 with reward 182.000 in 182 steps
138
+ 2023-06-18 16:32:48 - SimpleLog - INFO: - update_step: 2400, online_eval_reward: 200.000
139
+ 2023-06-18 16:32:48 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
140
+ 2023-06-18 16:32:49 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward 200.000 in 200 steps
141
+ 2023-06-18 16:32:49 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: 200.000
142
+ 2023-06-18 16:32:49 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
143
+ 2023-06-18 16:32:50 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward 162.000 in 162 steps
144
+ 2023-06-18 16:32:51 - SimpleLog - INFO: - update_step: 2600, online_eval_reward: 200.000
145
+ 2023-06-18 16:32:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
146
+ 2023-06-18 16:32:51 - SimpleLog - INFO: - Interactor 1 finished episode 30 with reward 140.000 in 140 steps
147
+ 2023-06-18 16:32:52 - SimpleLog - INFO: - update_step: 2700, online_eval_reward: 200.000
148
+ 2023-06-18 16:32:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
149
+ 2023-06-18 16:32:52 - SimpleLog - INFO: - Interactor 0 finished episode 31 with reward 200.000 in 200 steps
150
+ 2023-06-18 16:32:53 - SimpleLog - INFO: - update_step: 2800, online_eval_reward: 200.000
151
+ 2023-06-18 16:32:53 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
152
+ 2023-06-18 16:32:53 - SimpleLog - INFO: - Interactor 1 finished episode 32 with reward 200.000 in 200 steps
153
+ 2023-06-18 16:32:54 - SimpleLog - INFO: - update_step: 2900, online_eval_reward: 200.000
154
+ 2023-06-18 16:32:54 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
155
+ 2023-06-18 16:32:55 - SimpleLog - INFO: - Interactor 0 finished episode 33 with reward 200.000 in 200 steps
156
+ 2023-06-18 16:32:55 - SimpleLog - INFO: - update_step: 3000, online_eval_reward: 200.000
157
+ 2023-06-18 16:32:55 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
158
+ 2023-06-18 16:32:56 - SimpleLog - INFO: - Interactor 1 finished episode 34 with reward 200.000 in 200 steps
159
+ 2023-06-18 16:32:57 - SimpleLog - INFO: - update_step: 3100, online_eval_reward: 200.000
160
+ 2023-06-18 16:32:57 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
161
+ 2023-06-18 16:32:57 - SimpleLog - INFO: - Interactor 0 finished episode 35 with reward 200.000 in 200 steps
162
+ 2023-06-18 16:32:58 - SimpleLog - INFO: - Interactor 1 finished episode 36 with reward 166.000 in 166 steps
163
+ 2023-06-18 16:32:58 - SimpleLog - INFO: - update_step: 3200, online_eval_reward: 200.000
164
+ 2023-06-18 16:32:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
165
+ 2023-06-18 16:32:59 - SimpleLog - INFO: - update_step: 3300, online_eval_reward: 200.000
166
+ 2023-06-18 16:32:59 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
167
+ 2023-06-18 16:32:59 - SimpleLog - INFO: - Interactor 0 finished episode 37 with reward 168.000 in 168 steps
168
+ 2023-06-18 16:33:00 - SimpleLog - INFO: - Interactor 1 finished episode 38 with reward 160.000 in 160 steps
169
+ 2023-06-18 16:33:00 - SimpleLog - INFO: - update_step: 3400, online_eval_reward: 200.000
170
+ 2023-06-18 16:33:00 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
171
+ 2023-06-18 16:33:02 - SimpleLog - INFO: - update_step: 3500, online_eval_reward: 200.000
172
+ 2023-06-18 16:33:02 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
173
+ 2023-06-18 16:33:02 - SimpleLog - INFO: - Interactor 0 finished episode 39 with reward 200.000 in 200 steps
174
+ 2023-06-18 16:33:02 - SimpleLog - INFO: - Interactor 1 finished episode 40 with reward 165.000 in 165 steps
175
+ 2023-06-18 16:33:03 - SimpleLog - INFO: - update_step: 3600, online_eval_reward: 200.000
176
+ 2023-06-18 16:33:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
177
+ 2023-06-18 16:33:04 - SimpleLog - INFO: - update_step: 3700, online_eval_reward: 200.000
178
+ 2023-06-18 16:33:04 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
179
+ 2023-06-18 16:33:04 - SimpleLog - INFO: - Interactor 0 finished episode 41 with reward 200.000 in 200 steps
180
+ 2023-06-18 16:33:04 - SimpleLog - INFO: - Interactor 1 finished episode 42 with reward 185.000 in 185 steps
181
+ 2023-06-18 16:33:05 - SimpleLog - INFO: - update_step: 3800, online_eval_reward: 200.000
182
+ 2023-06-18 16:33:05 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
183
+ 2023-06-18 16:33:06 - SimpleLog - INFO: - Interactor 0 finished episode 43 with reward 131.000 in 131 steps
184
+ 2023-06-18 16:33:07 - SimpleLog - INFO: - update_step: 3900, online_eval_reward: 200.000
185
+ 2023-06-18 16:33:07 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
186
+ 2023-06-18 16:33:07 - SimpleLog - INFO: - Interactor 1 finished episode 44 with reward 200.000 in 200 steps
187
+ 2023-06-18 16:33:08 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: 200.000
188
+ 2023-06-18 16:33:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
189
+ 2023-06-18 16:33:08 - SimpleLog - INFO: - Interactor 0 finished episode 45 with reward 190.000 in 190 steps
190
+ 2023-06-18 16:33:09 - SimpleLog - INFO: - Interactor 1 finished episode 46 with reward 183.000 in 183 steps
191
+ 2023-06-18 16:33:09 - SimpleLog - INFO: - update_step: 4100, online_eval_reward: 200.000
192
+ 2023-06-18 16:33:09 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
193
+ 2023-06-18 16:33:10 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward 127.000 in 127 steps
194
+ 2023-06-18 16:33:10 - SimpleLog - INFO: - update_step: 4200, online_eval_reward: 200.000
195
+ 2023-06-18 16:33:10 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
196
+ 2023-06-18 16:33:11 - SimpleLog - INFO: - Interactor 1 finished episode 48 with reward 200.000 in 200 steps
197
+ 2023-06-18 16:33:12 - SimpleLog - INFO: - update_step: 4300, online_eval_reward: 200.000
198
+ 2023-06-18 16:33:12 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
199
+ 2023-06-18 16:33:12 - SimpleLog - INFO: - Interactor 0 finished episode 49 with reward 188.000 in 188 steps
200
+ 2023-06-18 16:33:13 - SimpleLog - INFO: - update_step: 4400, online_eval_reward: 200.000
201
+ 2023-06-18 16:33:13 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
202
+ 2023-06-18 16:33:13 - SimpleLog - INFO: - Interactor 1 finished episode 50 with reward 159.000 in 159 steps
203
+ 2023-06-18 16:33:14 - SimpleLog - INFO: - update_step: 4500, online_eval_reward: 200.000
204
+ 2023-06-18 16:33:14 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
205
+ 2023-06-18 16:33:14 - SimpleLog - INFO: - Interactor 0 finished episode 51 with reward 200.000 in 200 steps
206
+ 2023-06-18 16:33:15 - SimpleLog - INFO: - Interactor 1 finished episode 52 with reward 137.000 in 137 steps
207
+ 2023-06-18 16:33:15 - SimpleLog - INFO: - update_step: 4600, online_eval_reward: 200.000
208
+ 2023-06-18 16:33:15 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
209
+ 2023-06-18 16:33:16 - SimpleLog - INFO: - update_step: 4700, online_eval_reward: 200.000
210
+ 2023-06-18 16:33:16 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
211
+ 2023-06-18 16:33:17 - SimpleLog - INFO: - Interactor 0 finished episode 53 with reward 200.000 in 200 steps
212
+ 2023-06-18 16:33:17 - SimpleLog - INFO: - Interactor 1 finished episode 54 with reward 190.000 in 190 steps
213
+ 2023-06-18 16:33:18 - SimpleLog - INFO: - update_step: 4800, online_eval_reward: 200.000
214
+ 2023-06-18 16:33:18 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
215
+ 2023-06-18 16:33:19 - SimpleLog - INFO: - update_step: 4900, online_eval_reward: 200.000
216
+ 2023-06-18 16:33:19 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
217
+ 2023-06-18 16:33:19 - SimpleLog - INFO: - Interactor 0 finished episode 55 with reward 200.000 in 200 steps
218
+ 2023-06-18 16:33:19 - SimpleLog - INFO: - Interactor 1 finished episode 56 with reward 200.000 in 200 steps
219
+ 2023-06-18 16:33:20 - SimpleLog - INFO: - update_step: 5000, online_eval_reward: 200.000
220
+ 2023-06-18 16:33:20 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
221
+ 2023-06-18 16:33:21 - SimpleLog - INFO: - update_step: 5100, online_eval_reward: 200.000
222
+ 2023-06-18 16:33:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
223
+ 2023-06-18 16:33:22 - SimpleLog - INFO: - Interactor 0 finished episode 57 with reward 200.000 in 200 steps
224
+ 2023-06-18 16:33:22 - SimpleLog - INFO: - Interactor 1 finished episode 58 with reward 200.000 in 200 steps
225
+ 2023-06-18 16:33:23 - SimpleLog - INFO: - update_step: 5200, online_eval_reward: 200.000
226
+ 2023-06-18 16:33:23 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
227
+ 2023-06-18 16:33:24 - SimpleLog - INFO: - update_step: 5300, online_eval_reward: 200.000
228
+ 2023-06-18 16:33:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
229
+ 2023-06-18 16:33:24 - SimpleLog - INFO: - Interactor 0 finished episode 59 with reward 162.000 in 162 steps
230
+ 2023-06-18 16:33:24 - SimpleLog - INFO: - Interactor 1 finished episode 60 with reward 200.000 in 200 steps
231
+ 2023-06-18 16:33:25 - SimpleLog - INFO: - update_step: 5400, online_eval_reward: 200.000
232
+ 2023-06-18 16:33:25 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
233
+ 2023-06-18 16:33:25 - SimpleLog - INFO: - Interactor 0 finished episode 61 with reward 155.000 in 155 steps
234
+ 2023-06-18 16:33:26 - SimpleLog - INFO: - update_step: 5500, online_eval_reward: 200.000
235
+ 2023-06-18 16:33:26 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
236
+ 2023-06-18 16:33:27 - SimpleLog - INFO: - Interactor 0 finished episode 62 with reward 100.000 in 100 steps
237
+ 2023-06-18 16:33:27 - SimpleLog - INFO: - Interactor 1 finished episode 63 with reward 200.000 in 200 steps
238
+ 2023-06-18 16:33:27 - SimpleLog - INFO: - update_step: 5600, online_eval_reward: 200.000
239
+ 2023-06-18 16:33:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
240
+ 2023-06-18 16:33:29 - SimpleLog - INFO: - update_step: 5700, online_eval_reward: 200.000
241
+ 2023-06-18 16:33:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
242
+ 2023-06-18 16:33:29 - SimpleLog - INFO: - Interactor 1 finished episode 64 with reward 157.000 in 157 steps
243
+ 2023-06-18 16:33:29 - SimpleLog - INFO: - Interactor 0 finished episode 65 with reward 200.000 in 200 steps
244
+ 2023-06-18 16:33:30 - SimpleLog - INFO: - update_step: 5800, online_eval_reward: 200.000
245
+ 2023-06-18 16:33:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
246
+ 2023-06-18 16:33:31 - SimpleLog - INFO: - Interactor 1 finished episode 66 with reward 158.000 in 158 steps
247
+ 2023-06-18 16:33:31 - SimpleLog - INFO: - update_step: 5900, online_eval_reward: 200.000
248
+ 2023-06-18 16:33:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
249
+ 2023-06-18 16:33:32 - SimpleLog - INFO: - Interactor 0 finished episode 67 with reward 189.000 in 189 steps
250
+ 2023-06-18 16:33:32 - SimpleLog - INFO: - update_step: 6000, online_eval_reward: 200.000
251
+ 2023-06-18 16:33:32 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
252
+ 2023-06-18 16:33:33 - SimpleLog - INFO: - Interactor 1 finished episode 68 with reward 185.000 in 185 steps
253
+ 2023-06-18 16:33:34 - SimpleLog - INFO: - update_step: 6100, online_eval_reward: 200.000
254
+ 2023-06-18 16:33:34 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
255
+ 2023-06-18 16:33:34 - SimpleLog - INFO: - Interactor 0 finished episode 69 with reward 200.000 in 200 steps
256
+ 2023-06-18 16:33:35 - SimpleLog - INFO: - update_step: 6200, online_eval_reward: 200.000
257
+ 2023-06-18 16:33:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
258
+ 2023-06-18 16:33:35 - SimpleLog - INFO: - Interactor 1 finished episode 70 with reward 161.000 in 161 steps
259
+ 2023-06-18 16:33:36 - SimpleLog - INFO: - update_step: 6300, online_eval_reward: 200.000
260
+ 2023-06-18 16:33:36 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
261
+ 2023-06-18 16:33:36 - SimpleLog - INFO: - Interactor 0 finished episode 71 with reward 151.000 in 151 steps
262
+ 2023-06-18 16:33:37 - SimpleLog - INFO: - update_step: 6400, online_eval_reward: 200.000
263
+ 2023-06-18 16:33:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
264
+ 2023-06-18 16:33:38 - SimpleLog - INFO: - Interactor 1 finished episode 72 with reward 200.000 in 200 steps
265
+ 2023-06-18 16:33:39 - SimpleLog - INFO: - update_step: 6500, online_eval_reward: 200.000
266
+ 2023-06-18 16:33:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
267
+ 2023-06-18 16:33:39 - SimpleLog - INFO: - Interactor 0 finished episode 73 with reward 200.000 in 200 steps
268
+ 2023-06-18 16:33:40 - SimpleLog - INFO: - update_step: 6600, online_eval_reward: 200.000
269
+ 2023-06-18 16:33:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
270
+ 2023-06-18 16:33:40 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward 185.000 in 185 steps
271
+ 2023-06-18 16:33:41 - SimpleLog - INFO: - update_step: 6700, online_eval_reward: 200.000
272
+ 2023-06-18 16:33:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
273
+ 2023-06-18 16:33:41 - SimpleLog - INFO: - Interactor 0 finished episode 75 with reward 200.000 in 200 steps
274
+ 2023-06-18 16:33:42 - SimpleLog - INFO: - Interactor 1 finished episode 76 with reward 168.000 in 168 steps
275
+ 2023-06-18 16:33:42 - SimpleLog - INFO: - Interactor 0 finished episode 77 with reward 95.000 in 95 steps
276
+ 2023-06-18 16:33:42 - SimpleLog - INFO: - update_step: 6800, online_eval_reward: 200.000
277
+ 2023-06-18 16:33:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
278
+ 2023-06-18 16:33:43 - SimpleLog - INFO: - update_step: 6900, online_eval_reward: 200.000
279
+ 2023-06-18 16:33:43 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
280
+ 2023-06-18 16:33:44 - SimpleLog - INFO: - Interactor 1 finished episode 78 with reward 200.000 in 200 steps
281
+ 2023-06-18 16:33:44 - SimpleLog - INFO: - Interactor 0 finished episode 79 with reward 200.000 in 200 steps
282
+ 2023-06-18 16:33:45 - SimpleLog - INFO: - update_step: 7000, online_eval_reward: 200.000
283
+ 2023-06-18 16:33:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
284
+ 2023-06-18 16:33:46 - SimpleLog - INFO: - update_step: 7100, online_eval_reward: 200.000
285
+ 2023-06-18 16:33:46 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
286
+ 2023-06-18 16:33:47 - SimpleLog - INFO: - Interactor 1 finished episode 80 with reward 200.000 in 200 steps
287
+ 2023-06-18 16:33:47 - SimpleLog - INFO: - Interactor 0 finished episode 81 with reward 199.000 in 199 steps
288
+ 2023-06-18 16:33:47 - SimpleLog - INFO: - update_step: 7200, online_eval_reward: 200.000
289
+ 2023-06-18 16:33:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
290
+ 2023-06-18 16:33:48 - SimpleLog - INFO: - update_step: 7300, online_eval_reward: 200.000
291
+ 2023-06-18 16:33:48 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
292
+ 2023-06-18 16:33:49 - SimpleLog - INFO: - Interactor 1 finished episode 82 with reward 200.000 in 200 steps
293
+ 2023-06-18 16:33:49 - SimpleLog - INFO: - Interactor 0 finished episode 83 with reward 200.000 in 200 steps
294
+ 2023-06-18 16:33:50 - SimpleLog - INFO: - update_step: 7400, online_eval_reward: 200.000
295
+ 2023-06-18 16:33:50 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
296
+ 2023-06-18 16:33:51 - SimpleLog - INFO: - update_step: 7500, online_eval_reward: 200.000
297
+ 2023-06-18 16:33:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
298
+ 2023-06-18 16:33:51 - SimpleLog - INFO: - Interactor 0 finished episode 84 with reward 195.000 in 195 steps
299
+ 2023-06-18 16:33:51 - SimpleLog - INFO: - Interactor 1 finished episode 85 with reward 200.000 in 200 steps
300
+ 2023-06-18 16:33:52 - SimpleLog - INFO: - update_step: 7600, online_eval_reward: 200.000
301
+ 2023-06-18 16:33:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
302
+ 2023-06-18 16:33:53 - SimpleLog - INFO: - update_step: 7700, online_eval_reward: 200.000
303
+ 2023-06-18 16:33:53 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
304
+ 2023-06-18 16:33:54 - SimpleLog - INFO: - Interactor 0 finished episode 86 with reward 182.000 in 182 steps
305
+ 2023-06-18 16:33:54 - SimpleLog - INFO: - Interactor 1 finished episode 87 with reward 200.000 in 200 steps
306
+ 2023-06-18 16:33:54 - SimpleLog - INFO: - update_step: 7800, online_eval_reward: 200.000
307
+ 2023-06-18 16:33:54 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
308
+ 2023-06-18 16:33:56 - SimpleLog - INFO: - update_step: 7900, online_eval_reward: 200.000
309
+ 2023-06-18 16:33:56 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
310
+ 2023-06-18 16:33:56 - SimpleLog - INFO: - Interactor 0 finished episode 88 with reward 194.000 in 194 steps
311
+ 2023-06-18 16:33:56 - SimpleLog - INFO: - Interactor 1 finished episode 89 with reward 200.000 in 200 steps
312
+ 2023-06-18 16:33:57 - SimpleLog - INFO: - update_step: 8000, online_eval_reward: 200.000
313
+ 2023-06-18 16:33:57 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
314
+ 2023-06-18 16:33:58 - SimpleLog - INFO: - update_step: 8100, online_eval_reward: 200.000
315
+ 2023-06-18 16:33:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
316
+ 2023-06-18 16:33:58 - SimpleLog - INFO: - Interactor 0 finished episode 90 with reward 189.000 in 189 steps
317
+ 2023-06-18 16:33:59 - SimpleLog - INFO: - Interactor 1 finished episode 91 with reward 200.000 in 200 steps
318
+ 2023-06-18 16:33:59 - SimpleLog - INFO: - update_step: 8200, online_eval_reward: 200.000
319
+ 2023-06-18 16:33:59 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
320
+ 2023-06-18 16:34:00 - SimpleLog - INFO: - update_step: 8300, online_eval_reward: 200.000
321
+ 2023-06-18 16:34:00 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
322
+ 2023-06-18 16:34:01 - SimpleLog - INFO: - Interactor 0 finished episode 92 with reward 200.000 in 200 steps
323
+ 2023-06-18 16:34:01 - SimpleLog - INFO: - Interactor 1 finished episode 93 with reward 175.000 in 175 steps
324
+ 2023-06-18 16:34:02 - SimpleLog - INFO: - update_step: 8400, online_eval_reward: 200.000
325
+ 2023-06-18 16:34:02 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
326
+ 2023-06-18 16:34:03 - SimpleLog - INFO: - update_step: 8500, online_eval_reward: 200.000
327
+ 2023-06-18 16:34:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
328
+ 2023-06-18 16:34:03 - SimpleLog - INFO: - Interactor 0 finished episode 94 with reward 200.000 in 200 steps
329
+ 2023-06-18 16:34:03 - SimpleLog - INFO: - Interactor 1 finished episode 95 with reward 200.000 in 200 steps
330
+ 2023-06-18 16:34:04 - SimpleLog - INFO: - update_step: 8600, online_eval_reward: 200.000
331
+ 2023-06-18 16:34:04 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
332
+ 2023-06-18 16:34:05 - SimpleLog - INFO: - update_step: 8700, online_eval_reward: 200.000
333
+ 2023-06-18 16:34:05 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
334
+ 2023-06-18 16:34:06 - SimpleLog - INFO: - Interactor 0 finished episode 96 with reward 200.000 in 200 steps
335
+ 2023-06-18 16:34:06 - SimpleLog - INFO: - Interactor 1 finished episode 97 with reward 200.000 in 200 steps
336
+ 2023-06-18 16:34:06 - SimpleLog - INFO: - update_step: 8800, online_eval_reward: 200.000
337
+ 2023-06-18 16:34:06 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
338
+ 2023-06-18 16:34:08 - SimpleLog - INFO: - update_step: 8900, online_eval_reward: 200.000
339
+ 2023-06-18 16:34:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
340
+ 2023-06-18 16:34:08 - SimpleLog - INFO: - Interactor 0 finished episode 98 with reward 175.000 in 175 steps
341
+ 2023-06-18 16:34:08 - SimpleLog - INFO: - Interactor 1 finished episode 99 with reward 200.000 in 200 steps
342
+ 2023-06-18 16:34:09 - SimpleLog - INFO: - update_step: 9000, online_eval_reward: 200.000
343
+ 2023-06-18 16:34:09 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
344
+ 2023-06-18 16:34:10 - SimpleLog - INFO: - update_step: 9100, online_eval_reward: 200.000
345
+ 2023-06-18 16:34:10 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
346
+ 2023-06-18 16:34:10 - SimpleLog - INFO: - Interactor 0 finished episode 100 with reward 180.000 in 180 steps
347
+ 2023-06-18 16:34:11 - SimpleLog - INFO: - Interactor 1 finished episode 101 with reward 200.000 in 200 steps
348
+ 2023-06-18 16:34:11 - SimpleLog - INFO: - update_step: 9200, online_eval_reward: 200.000
349
+ 2023-06-18 16:34:11 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
350
+ 2023-06-18 16:34:13 - SimpleLog - INFO: - update_step: 9300, online_eval_reward: 200.000
351
+ 2023-06-18 16:34:13 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
352
+ 2023-06-18 16:34:13 - SimpleLog - INFO: - Interactor 0 finished episode 102 with reward 200.000 in 200 steps
353
+ 2023-06-18 16:34:13 - SimpleLog - INFO: - Interactor 1 finished episode 103 with reward 200.000 in 200 steps
354
+ 2023-06-18 16:34:14 - SimpleLog - INFO: - update_step: 9400, online_eval_reward: 200.000
355
+ 2023-06-18 16:34:14 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
356
+ 2023-06-18 16:34:14 - SimpleLog - INFO: - Interactor 0 finished episode 104 with reward 179.000 in 179 steps
357
+ 2023-06-18 16:34:15 - SimpleLog - INFO: - update_step: 9500, online_eval_reward: 200.000
358
+ 2023-06-18 16:34:15 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
359
+ 2023-06-18 16:34:15 - SimpleLog - INFO: - Interactor 1 finished episode 105 with reward 191.000 in 191 steps
360
+ 2023-06-18 16:34:16 - SimpleLog - INFO: - update_step: 9600, online_eval_reward: 200.000
361
+ 2023-06-18 16:34:16 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
362
+ 2023-06-18 16:34:17 - SimpleLog - INFO: - Interactor 0 finished episode 106 with reward 186.000 in 186 steps
363
+ 2023-06-18 16:34:17 - SimpleLog - INFO: - update_step: 9700, online_eval_reward: 200.000
364
+ 2023-06-18 16:34:17 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
365
+ 2023-06-18 16:34:18 - SimpleLog - INFO: - Interactor 1 finished episode 107 with reward 186.000 in 186 steps
366
+ 2023-06-18 16:34:19 - SimpleLog - INFO: - update_step: 9800, online_eval_reward: 200.000
367
+ 2023-06-18 16:34:19 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
368
+ 2023-06-18 16:34:19 - SimpleLog - INFO: - Interactor 0 finished episode 108 with reward 200.000 in 200 steps
369
+ 2023-06-18 16:34:20 - SimpleLog - INFO: - update_step: 9900, online_eval_reward: 200.000
370
+ 2023-06-18 16:34:20 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
371
+ 2023-06-18 16:34:20 - SimpleLog - INFO: - Interactor 1 finished episode 109 with reward 200.000 in 200 steps
372
+ 2023-06-18 16:34:21 - SimpleLog - INFO: - update_step: 10000, online_eval_reward: 200.000
373
+ 2023-06-18 16:34:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
374
+ 2023-06-18 16:34:22 - SimpleLog - INFO: - Interactor 0 finished episode 110 with reward 200.000 in 200 steps
375
+ 2023-06-18 16:34:22 - SimpleLog - INFO: - update_step: 10100, online_eval_reward: 200.000
376
+ 2023-06-18 16:34:22 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
377
+ 2023-06-18 16:34:23 - SimpleLog - INFO: - Interactor 1 finished episode 111 with reward 200.000 in 200 steps
378
+ 2023-06-18 16:34:24 - SimpleLog - INFO: - update_step: 10200, online_eval_reward: 200.000
379
+ 2023-06-18 16:34:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
380
+ 2023-06-18 16:34:24 - SimpleLog - INFO: - Interactor 0 finished episode 112 with reward 192.000 in 192 steps
381
+ 2023-06-18 16:34:25 - SimpleLog - INFO: - update_step: 10300, online_eval_reward: 200.000
382
+ 2023-06-18 16:34:25 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
383
+ 2023-06-18 16:34:25 - SimpleLog - INFO: - Interactor 1 finished episode 113 with reward 200.000 in 200 steps
384
+ 2023-06-18 16:34:26 - SimpleLog - INFO: - update_step: 10400, online_eval_reward: 200.000
385
+ 2023-06-18 16:34:26 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
386
+ 2023-06-18 16:34:26 - SimpleLog - INFO: - Interactor 0 finished episode 114 with reward 163.000 in 163 steps
387
+ 2023-06-18 16:34:27 - SimpleLog - INFO: - update_step: 10500, online_eval_reward: 200.000
388
+ 2023-06-18 16:34:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
389
+ 2023-06-18 16:34:28 - SimpleLog - INFO: - Interactor 1 finished episode 115 with reward 200.000 in 200 steps
390
+ 2023-06-18 16:34:29 - SimpleLog - INFO: - update_step: 10600, online_eval_reward: 200.000
391
+ 2023-06-18 16:34:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
392
+ 2023-06-18 16:34:29 - SimpleLog - INFO: - Interactor 0 finished episode 116 with reward 200.000 in 200 steps
393
+ 2023-06-18 16:34:30 - SimpleLog - INFO: - update_step: 10700, online_eval_reward: 200.000
394
+ 2023-06-18 16:34:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
395
+ 2023-06-18 16:34:30 - SimpleLog - INFO: - Interactor 1 finished episode 117 with reward 160.000 in 160 steps
396
+ 2023-06-18 16:34:31 - SimpleLog - INFO: - update_step: 10800, online_eval_reward: 200.000
397
+ 2023-06-18 16:34:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
398
+ 2023-06-18 16:34:31 - SimpleLog - INFO: - Interactor 0 finished episode 118 with reward 200.000 in 200 steps
399
+ 2023-06-18 16:34:32 - SimpleLog - INFO: - update_step: 10900, online_eval_reward: 200.000
400
+ 2023-06-18 16:34:32 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
401
+ 2023-06-18 16:34:32 - SimpleLog - INFO: - Interactor 1 finished episode 119 with reward 200.000 in 200 steps
402
+ 2023-06-18 16:34:33 - SimpleLog - INFO: - update_step: 11000, online_eval_reward: 200.000
403
+ 2023-06-18 16:34:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
404
+ 2023-06-18 16:34:34 - SimpleLog - INFO: - Interactor 0 finished episode 120 with reward 200.000 in 200 steps
405
+ 2023-06-18 16:34:34 - SimpleLog - INFO: - Interactor 1 finished episode 121 with reward 182.000 in 182 steps
406
+ 2023-06-18 16:34:35 - SimpleLog - INFO: - update_step: 11100, online_eval_reward: 200.000
407
+ 2023-06-18 16:34:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
408
+ 2023-06-18 16:34:36 - SimpleLog - INFO: - update_step: 11200, online_eval_reward: 200.000
409
+ 2023-06-18 16:34:36 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
410
+ 2023-06-18 16:34:36 - SimpleLog - INFO: - Interactor 0 finished episode 122 with reward 200.000 in 200 steps
411
+ 2023-06-18 16:34:37 - SimpleLog - INFO: - Interactor 1 finished episode 123 with reward 200.000 in 200 steps
412
+ 2023-06-18 16:34:37 - SimpleLog - INFO: - update_step: 11300, online_eval_reward: 200.000
413
+ 2023-06-18 16:34:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
414
+ 2023-06-18 16:34:39 - SimpleLog - INFO: - update_step: 11400, online_eval_reward: 200.000
415
+ 2023-06-18 16:34:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
416
+ 2023-06-18 16:34:39 - SimpleLog - INFO: - Interactor 0 finished episode 124 with reward 200.000 in 200 steps
417
+ 2023-06-18 16:34:39 - SimpleLog - INFO: - Interactor 1 finished episode 125 with reward 200.000 in 200 steps
418
+ 2023-06-18 16:34:40 - SimpleLog - INFO: - update_step: 11500, online_eval_reward: 200.000
419
+ 2023-06-18 16:34:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
420
+ 2023-06-18 16:34:41 - SimpleLog - INFO: - update_step: 11600, online_eval_reward: 200.000
421
+ 2023-06-18 16:34:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
422
+ 2023-06-18 16:34:41 - SimpleLog - INFO: - Interactor 0 finished episode 126 with reward 200.000 in 200 steps
423
+ 2023-06-18 16:34:41 - SimpleLog - INFO: - Interactor 1 finished episode 127 with reward 146.000 in 146 steps
424
+ 2023-06-18 16:34:42 - SimpleLog - INFO: - update_step: 11700, online_eval_reward: 200.000
425
+ 2023-06-18 16:34:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
426
+ 2023-06-18 16:34:43 - SimpleLog - INFO: - update_step: 11800, online_eval_reward: 200.000
427
+ 2023-06-18 16:34:43 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
428
+ 2023-06-18 16:34:44 - SimpleLog - INFO: - Interactor 0 finished episode 128 with reward 176.000 in 176 steps
429
+ 2023-06-18 16:34:44 - SimpleLog - INFO: - Interactor 1 finished episode 129 with reward 178.000 in 178 steps
430
+ 2023-06-18 16:34:45 - SimpleLog - INFO: - update_step: 11900, online_eval_reward: 200.000
431
+ 2023-06-18 16:34:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
432
+ 2023-06-18 16:34:45 - SimpleLog - INFO: - Interactor 1 finished episode 130 with reward 172.000 in 172 steps
433
+ 2023-06-18 16:34:46 - SimpleLog - INFO: - update_step: 12000, online_eval_reward: 200.000
434
+ 2023-06-18 16:34:46 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
435
+ 2023-06-18 16:34:46 - SimpleLog - INFO: - Interactor 0 finished episode 131 with reward 200.000 in 200 steps
436
+ 2023-06-18 16:34:47 - SimpleLog - INFO: - update_step: 12100, online_eval_reward: 200.000
437
+ 2023-06-18 16:34:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
438
+ 2023-06-18 16:34:48 - SimpleLog - INFO: - Interactor 1 finished episode 132 with reward 200.000 in 200 steps
439
+ 2023-06-18 16:34:48 - SimpleLog - INFO: - update_step: 12200, online_eval_reward: 200.000
440
+ 2023-06-18 16:34:48 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
441
+ 2023-06-18 16:34:48 - SimpleLog - INFO: - Interactor 0 finished episode 133 with reward 200.000 in 200 steps
442
+ 2023-06-18 16:34:50 - SimpleLog - INFO: - update_step: 12300, online_eval_reward: 200.000
443
+ 2023-06-18 16:34:50 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
444
+ 2023-06-18 16:34:50 - SimpleLog - INFO: - Interactor 1 finished episode 134 with reward 200.000 in 200 steps
445
+ 2023-06-18 16:34:51 - SimpleLog - INFO: - update_step: 12400, online_eval_reward: 200.000
446
+ 2023-06-18 16:34:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
447
+ 2023-06-18 16:34:51 - SimpleLog - INFO: - Interactor 0 finished episode 135 with reward 200.000 in 200 steps
448
+ 2023-06-18 16:34:52 - SimpleLog - INFO: - update_step: 12500, online_eval_reward: 200.000
449
+ 2023-06-18 16:34:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
450
+ 2023-06-18 16:34:53 - SimpleLog - INFO: - Interactor 1 finished episode 136 with reward 200.000 in 200 steps
451
+ 2023-06-18 16:34:53 - SimpleLog - INFO: - update_step: 12600, online_eval_reward: 200.000
452
+ 2023-06-18 16:34:53 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
453
+ 2023-06-18 16:34:53 - SimpleLog - INFO: - Interactor 0 finished episode 137 with reward 200.000 in 200 steps
454
+ 2023-06-18 16:34:55 - SimpleLog - INFO: - update_step: 12700, online_eval_reward: 200.000
455
+ 2023-06-18 16:34:55 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
456
+ 2023-06-18 16:34:55 - SimpleLog - INFO: - Interactor 1 finished episode 138 with reward 200.000 in 200 steps
457
+ 2023-06-18 16:34:56 - SimpleLog - INFO: - update_step: 12800, online_eval_reward: 200.000
458
+ 2023-06-18 16:34:56 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
459
+ 2023-06-18 16:34:56 - SimpleLog - INFO: - Interactor 0 finished episode 139 with reward 200.000 in 200 steps
460
+ 2023-06-18 16:34:57 - SimpleLog - INFO: - update_step: 12900, online_eval_reward: 200.000
461
+ 2023-06-18 16:34:57 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
462
+ 2023-06-18 16:34:58 - SimpleLog - INFO: - Interactor 1 finished episode 140 with reward 200.000 in 200 steps
463
+ 2023-06-18 16:34:58 - SimpleLog - INFO: - update_step: 13000, online_eval_reward: 200.000
464
+ 2023-06-18 16:34:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
465
+ 2023-06-18 16:34:59 - SimpleLog - INFO: - Interactor 0 finished episode 141 with reward 200.000 in 200 steps
466
+ 2023-06-18 16:35:00 - SimpleLog - INFO: - update_step: 13100, online_eval_reward: 200.000
467
+ 2023-06-18 16:35:00 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
468
+ 2023-06-18 16:35:00 - SimpleLog - INFO: - Interactor 1 finished episode 142 with reward 200.000 in 200 steps
469
+ 2023-06-18 16:35:01 - SimpleLog - INFO: - update_step: 13200, online_eval_reward: 200.000
470
+ 2023-06-18 16:35:01 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
471
+ 2023-06-18 16:35:01 - SimpleLog - INFO: - Interactor 0 finished episode 143 with reward 200.000 in 200 steps
472
+ 2023-06-18 16:35:02 - SimpleLog - INFO: - update_step: 13300, online_eval_reward: 200.000
473
+ 2023-06-18 16:35:02 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
474
+ 2023-06-18 16:35:03 - SimpleLog - INFO: - Interactor 1 finished episode 144 with reward 200.000 in 200 steps
475
+ 2023-06-18 16:35:03 - SimpleLog - INFO: - update_step: 13400, online_eval_reward: 200.000
476
+ 2023-06-18 16:35:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
477
+ 2023-06-18 16:35:03 - SimpleLog - INFO: - Interactor 0 finished episode 145 with reward 200.000 in 200 steps
478
+ 2023-06-18 16:35:05 - SimpleLog - INFO: - update_step: 13500, online_eval_reward: 200.000
479
+ 2023-06-18 16:35:05 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
480
+ 2023-06-18 16:35:05 - SimpleLog - INFO: - Interactor 1 finished episode 146 with reward 200.000 in 200 steps
481
+ 2023-06-18 16:35:06 - SimpleLog - INFO: - update_step: 13600, online_eval_reward: 200.000
482
+ 2023-06-18 16:35:06 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
483
+ 2023-06-18 16:35:06 - SimpleLog - INFO: - Interactor 0 finished episode 147 with reward 200.000 in 200 steps
484
+ 2023-06-18 16:35:07 - SimpleLog - INFO: - update_step: 13700, online_eval_reward: 200.000
485
+ 2023-06-18 16:35:07 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
486
+ 2023-06-18 16:35:08 - SimpleLog - INFO: - Interactor 1 finished episode 148 with reward 200.000 in 200 steps
487
+ 2023-06-18 16:35:08 - SimpleLog - INFO: - update_step: 13800, online_eval_reward: 200.000
488
+ 2023-06-18 16:35:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
489
+ 2023-06-18 16:35:08 - SimpleLog - INFO: - Interactor 0 finished episode 149 with reward 200.000 in 200 steps
490
+ 2023-06-18 16:35:10 - SimpleLog - INFO: - update_step: 13900, online_eval_reward: 200.000
491
+ 2023-06-18 16:35:10 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
492
+ 2023-06-18 16:35:10 - SimpleLog - INFO: - Interactor 1 finished episode 150 with reward 200.000 in 200 steps
493
+ 2023-06-18 16:35:10 - SimpleLog - INFO: - Interactor 0 finished episode 151 with reward 179.000 in 179 steps
494
+ 2023-06-18 16:35:11 - SimpleLog - INFO: - update_step: 14000, online_eval_reward: 200.000
495
+ 2023-06-18 16:35:11 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
496
+ 2023-06-18 16:35:12 - SimpleLog - INFO: - update_step: 14100, online_eval_reward: 200.000
497
+ 2023-06-18 16:35:12 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
498
+ 2023-06-18 16:35:13 - SimpleLog - INFO: - Interactor 0 finished episode 152 with reward 187.000 in 187 steps
499
+ 2023-06-18 16:35:13 - SimpleLog - INFO: - Interactor 1 finished episode 153 with reward 200.000 in 200 steps
500
+ 2023-06-18 16:35:13 - SimpleLog - INFO: - update_step: 14200, online_eval_reward: 200.000
501
+ 2023-06-18 16:35:13 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
502
+ 2023-06-18 16:35:15 - SimpleLog - INFO: - update_step: 14300, online_eval_reward: 200.000
503
+ 2023-06-18 16:35:15 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
504
+ 2023-06-18 16:35:15 - SimpleLog - INFO: - Interactor 0 finished episode 154 with reward 189.000 in 189 steps
505
+ 2023-06-18 16:35:15 - SimpleLog - INFO: - Interactor 1 finished episode 155 with reward 200.000 in 200 steps
506
+ 2023-06-18 16:35:16 - SimpleLog - INFO: - update_step: 14400, online_eval_reward: 200.000
507
+ 2023-06-18 16:35:16 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
508
+ 2023-06-18 16:35:17 - SimpleLog - INFO: - update_step: 14500, online_eval_reward: 200.000
509
+ 2023-06-18 16:35:17 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
510
+ 2023-06-18 16:35:17 - SimpleLog - INFO: - Interactor 0 finished episode 156 with reward 200.000 in 200 steps
511
+ 2023-06-18 16:35:18 - SimpleLog - INFO: - Interactor 1 finished episode 157 with reward 200.000 in 200 steps
512
+ 2023-06-18 16:35:18 - SimpleLog - INFO: - update_step: 14600, online_eval_reward: 200.000
513
+ 2023-06-18 16:35:18 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
514
+ 2023-06-18 16:35:19 - SimpleLog - INFO: - update_step: 14700, online_eval_reward: 200.000
515
+ 2023-06-18 16:35:19 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
516
+ 2023-06-18 16:35:20 - SimpleLog - INFO: - Interactor 0 finished episode 158 with reward 191.000 in 191 steps
517
+ 2023-06-18 16:35:20 - SimpleLog - INFO: - Interactor 1 finished episode 159 with reward 200.000 in 200 steps
518
+ 2023-06-18 16:35:21 - SimpleLog - INFO: - update_step: 14800, online_eval_reward: 200.000
519
+ 2023-06-18 16:35:21 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
520
+ 2023-06-18 16:35:22 - SimpleLog - INFO: - update_step: 14900, online_eval_reward: 200.000
521
+ 2023-06-18 16:35:22 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
522
+ 2023-06-18 16:35:22 - SimpleLog - INFO: - Interactor 0 finished episode 160 with reward 163.000 in 163 steps
523
+ 2023-06-18 16:35:22 - SimpleLog - INFO: - Interactor 1 finished episode 161 with reward 200.000 in 200 steps
524
+ 2023-06-18 16:35:23 - SimpleLog - INFO: - update_step: 15000, online_eval_reward: 200.000
525
+ 2023-06-18 16:35:23 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
526
+ 2023-06-18 16:35:24 - SimpleLog - INFO: - Interactor 0 finished episode 162 with reward 141.000 in 141 steps
527
+ 2023-06-18 16:35:24 - SimpleLog - INFO: - update_step: 15100, online_eval_reward: 200.000
528
+ 2023-06-18 16:35:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
529
+ 2023-06-18 16:35:25 - SimpleLog - INFO: - Interactor 1 finished episode 163 with reward 154.000 in 154 steps
530
+ 2023-06-18 16:35:25 - SimpleLog - INFO: - update_step: 15200, online_eval_reward: 200.000
531
+ 2023-06-18 16:35:25 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
532
+ 2023-06-18 16:35:26 - SimpleLog - INFO: - Interactor 0 finished episode 164 with reward 200.000 in 200 steps
533
+ 2023-06-18 16:35:27 - SimpleLog - INFO: - update_step: 15300, online_eval_reward: 200.000
534
+ 2023-06-18 16:35:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
535
+ 2023-06-18 16:35:27 - SimpleLog - INFO: - Interactor 1 finished episode 165 with reward 200.000 in 200 steps
536
+ 2023-06-18 16:35:28 - SimpleLog - INFO: - update_step: 15400, online_eval_reward: 200.000
537
+ 2023-06-18 16:35:28 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
538
+ 2023-06-18 16:35:28 - SimpleLog - INFO: - Interactor 0 finished episode 166 with reward 200.000 in 200 steps
539
+ 2023-06-18 16:35:29 - SimpleLog - INFO: - update_step: 15500, online_eval_reward: 200.000
540
+ 2023-06-18 16:35:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
541
+ 2023-06-18 16:35:29 - SimpleLog - INFO: - Interactor 1 finished episode 167 with reward 200.000 in 200 steps
542
+ 2023-06-18 16:35:30 - SimpleLog - INFO: - update_step: 15600, online_eval_reward: 200.000
543
+ 2023-06-18 16:35:30 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
544
+ 2023-06-18 16:35:30 - SimpleLog - INFO: - Interactor 0 finished episode 168 with reward 167.000 in 167 steps
545
+ 2023-06-18 16:35:31 - SimpleLog - INFO: - Interactor 1 finished episode 169 with reward 148.000 in 148 steps
546
+ 2023-06-18 16:35:31 - SimpleLog - INFO: - update_step: 15700, online_eval_reward: 200.000
547
+ 2023-06-18 16:35:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
548
+ 2023-06-18 16:35:32 - SimpleLog - INFO: - Interactor 0 finished episode 170 with reward 168.000 in 168 steps
549
+ 2023-06-18 16:35:33 - SimpleLog - INFO: - update_step: 15800, online_eval_reward: 200.000
550
+ 2023-06-18 16:35:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
551
+ 2023-06-18 16:35:33 - SimpleLog - INFO: - Interactor 1 finished episode 171 with reward 200.000 in 200 steps
552
+ 2023-06-18 16:35:34 - SimpleLog - INFO: - update_step: 15900, online_eval_reward: 200.000
553
+ 2023-06-18 16:35:34 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
554
+ 2023-06-18 16:35:34 - SimpleLog - INFO: - Interactor 0 finished episode 172 with reward 187.000 in 187 steps
555
+ 2023-06-18 16:35:35 - SimpleLog - INFO: - update_step: 16000, online_eval_reward: 200.000
556
+ 2023-06-18 16:35:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
557
+ 2023-06-18 16:35:36 - SimpleLog - INFO: - Interactor 1 finished episode 173 with reward 200.000 in 200 steps
558
+ 2023-06-18 16:35:36 - SimpleLog - INFO: - update_step: 16100, online_eval_reward: 200.000
559
+ 2023-06-18 16:35:36 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
560
+ 2023-06-18 16:35:37 - SimpleLog - INFO: - Interactor 0 finished episode 174 with reward 200.000 in 200 steps
561
+ 2023-06-18 16:35:37 - SimpleLog - INFO: - update_step: 16200, online_eval_reward: 200.000
562
+ 2023-06-18 16:35:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
563
+ 2023-06-18 16:35:38 - SimpleLog - INFO: - Interactor 1 finished episode 175 with reward 149.000 in 149 steps
564
+ 2023-06-18 16:35:39 - SimpleLog - INFO: - update_step: 16300, online_eval_reward: 200.000
565
+ 2023-06-18 16:35:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
566
+ 2023-06-18 16:35:39 - SimpleLog - INFO: - Interactor 0 finished episode 176 with reward 200.000 in 200 steps
567
+ 2023-06-18 16:35:40 - SimpleLog - INFO: - update_step: 16400, online_eval_reward: 200.000
568
+ 2023-06-18 16:35:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
569
+ 2023-06-18 16:35:40 - SimpleLog - INFO: - Interactor 1 finished episode 177 with reward 200.000 in 200 steps
570
+ 2023-06-18 16:35:41 - SimpleLog - INFO: - update_step: 16500, online_eval_reward: 200.000
571
+ 2023-06-18 16:35:41 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
572
+ 2023-06-18 16:35:42 - SimpleLog - INFO: - Interactor 0 finished episode 178 with reward 182.000 in 182 steps
573
+ 2023-06-18 16:35:42 - SimpleLog - INFO: - update_step: 16600, online_eval_reward: 200.000
574
+ 2023-06-18 16:35:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
575
+ 2023-06-18 16:35:42 - SimpleLog - INFO: - Interactor 1 finished episode 179 with reward 175.000 in 175 steps
576
+ 2023-06-18 16:35:44 - SimpleLog - INFO: - update_step: 16700, online_eval_reward: 200.000
577
+ 2023-06-18 16:35:44 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
578
+ 2023-06-18 16:35:44 - SimpleLog - INFO: - Interactor 0 finished episode 180 with reward 200.000 in 200 steps
579
+ 2023-06-18 16:35:45 - SimpleLog - INFO: - update_step: 16800, online_eval_reward: 200.000
580
+ 2023-06-18 16:35:45 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
581
+ 2023-06-18 16:35:45 - SimpleLog - INFO: - Interactor 1 finished episode 181 with reward 200.000 in 200 steps
582
+ 2023-06-18 16:35:46 - SimpleLog - INFO: - update_step: 16900, online_eval_reward: 200.000
583
+ 2023-06-18 16:35:46 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
584
+ 2023-06-18 16:35:46 - SimpleLog - INFO: - Interactor 0 finished episode 182 with reward 200.000 in 200 steps
585
+ 2023-06-18 16:35:47 - SimpleLog - INFO: - update_step: 17000, online_eval_reward: 200.000
586
+ 2023-06-18 16:35:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
587
+ 2023-06-18 16:35:47 - SimpleLog - INFO: - Interactor 1 finished episode 183 with reward 200.000 in 200 steps
588
+ 2023-06-18 16:35:48 - SimpleLog - INFO: - update_step: 17100, online_eval_reward: 200.000
589
+ 2023-06-18 16:35:48 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
590
+ 2023-06-18 16:35:49 - SimpleLog - INFO: - Interactor 0 finished episode 184 with reward 200.000 in 200 steps
591
+ 2023-06-18 16:35:50 - SimpleLog - INFO: - update_step: 17200, online_eval_reward: 200.000
592
+ 2023-06-18 16:35:50 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
593
+ 2023-06-18 16:35:50 - SimpleLog - INFO: - Interactor 1 finished episode 185 with reward 200.000 in 200 steps
594
+ 2023-06-18 16:35:51 - SimpleLog - INFO: - update_step: 17300, online_eval_reward: 200.000
595
+ 2023-06-18 16:35:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
596
+ 2023-06-18 16:35:51 - SimpleLog - INFO: - Interactor 0 finished episode 186 with reward 200.000 in 200 steps
597
+ 2023-06-18 16:35:52 - SimpleLog - INFO: - Interactor 1 finished episode 187 with reward 186.000 in 186 steps
598
+ 2023-06-18 16:35:52 - SimpleLog - INFO: - update_step: 17400, online_eval_reward: 200.000
599
+ 2023-06-18 16:35:52 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
600
+ 2023-06-18 16:35:53 - SimpleLog - INFO: - update_step: 17500, online_eval_reward: 200.000
601
+ 2023-06-18 16:35:53 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
602
+ 2023-06-18 16:35:54 - SimpleLog - INFO: - Interactor 0 finished episode 188 with reward 200.000 in 200 steps
603
+ 2023-06-18 16:35:54 - SimpleLog - INFO: - Interactor 1 finished episode 189 with reward 200.000 in 200 steps
604
+ 2023-06-18 16:35:55 - SimpleLog - INFO: - update_step: 17600, online_eval_reward: 200.000
605
+ 2023-06-18 16:35:55 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
606
+ 2023-06-18 16:35:56 - SimpleLog - INFO: - update_step: 17700, online_eval_reward: 200.000
607
+ 2023-06-18 16:35:56 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
608
+ 2023-06-18 16:35:56 - SimpleLog - INFO: - Interactor 0 finished episode 190 with reward 200.000 in 200 steps
609
+ 2023-06-18 16:35:57 - SimpleLog - INFO: - Interactor 1 finished episode 191 with reward 200.000 in 200 steps
610
+ 2023-06-18 16:35:57 - SimpleLog - INFO: - update_step: 17800, online_eval_reward: 200.000
611
+ 2023-06-18 16:35:57 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
612
+ 2023-06-18 16:35:58 - SimpleLog - INFO: - update_step: 17900, online_eval_reward: 200.000
613
+ 2023-06-18 16:35:58 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
614
+ 2023-06-18 16:35:59 - SimpleLog - INFO: - Interactor 0 finished episode 192 with reward 200.000 in 200 steps
615
+ 2023-06-18 16:35:59 - SimpleLog - INFO: - Interactor 1 finished episode 193 with reward 200.000 in 200 steps
616
+ 2023-06-18 16:36:00 - SimpleLog - INFO: - update_step: 18000, online_eval_reward: 200.000
617
+ 2023-06-18 16:36:00 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
618
+ 2023-06-18 16:36:01 - SimpleLog - INFO: - update_step: 18100, online_eval_reward: 200.000
619
+ 2023-06-18 16:36:01 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
620
+ 2023-06-18 16:36:02 - SimpleLog - INFO: - Interactor 0 finished episode 194 with reward 200.000 in 200 steps
621
+ 2023-06-18 16:36:02 - SimpleLog - INFO: - Interactor 1 finished episode 195 with reward 200.000 in 200 steps
622
+ 2023-06-18 16:36:02 - SimpleLog - INFO: - update_step: 18200, online_eval_reward: 200.000
623
+ 2023-06-18 16:36:02 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
624
+ 2023-06-18 16:36:04 - SimpleLog - INFO: - update_step: 18300, online_eval_reward: 200.000
625
+ 2023-06-18 16:36:04 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
626
+ 2023-06-18 16:36:04 - SimpleLog - INFO: - Interactor 0 finished episode 196 with reward 190.000 in 190 steps
627
+ 2023-06-18 16:36:04 - SimpleLog - INFO: - Interactor 1 finished episode 197 with reward 200.000 in 200 steps
628
+ 2023-06-18 16:36:05 - SimpleLog - INFO: - update_step: 18400, online_eval_reward: 200.000
629
+ 2023-06-18 16:36:05 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
630
+ 2023-06-18 16:36:06 - SimpleLog - INFO: - update_step: 18500, online_eval_reward: 200.000
631
+ 2023-06-18 16:36:06 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
632
+ 2023-06-18 16:36:06 - SimpleLog - INFO: - Interactor 0 finished episode 198 with reward 200.000 in 200 steps
633
+ 2023-06-18 16:36:07 - SimpleLog - INFO: - Interactor 1 finished episode 199 with reward 200.000 in 200 steps
634
+ 2023-06-18 16:36:07 - SimpleLog - INFO: - update_step: 18600, online_eval_reward: 200.000
635
+ 2023-06-18 16:36:07 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
636
+ 2023-06-18 16:36:08 - SimpleLog - INFO: - update_step: 18700, online_eval_reward: 200.000
637
+ 2023-06-18 16:36:08 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
638
+ 2023-06-18 16:36:09 - SimpleLog - INFO: - Interactor 0 finished episode 200 with reward 200.000 in 200 steps
639
+ 2023-06-18 16:36:09 - SimpleLog - INFO: - Finish testing! Time cost: 229.417 s
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add5d0d53b1d79e1812626cb409e21ae8d0b347ce2aebca398412974d3092798
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b4684feeeab8f71a31684e238f2e5d8f678c4a3c7b58443082c47d1d28d9978
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ed2d8a8d547df67abec878af406875d89cdb4903b41e52ac3460b465f1be16d
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10300 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99d0f56697bb3e9f108b3034580de19fb4e7cb705897295d47bf1a98e4c01fb4
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/10900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73a645d4bdb58eed9da819ef63310565f1bf45c755b2b1042a921343a1e8b38
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4994ca255864a58d79d968116ebf58498e29b3cd3edd332eee5b32e46e99a4cc
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f2b11eb37b31349365b2d077435a072d4376b3209ed258e0f60ec9d9165223
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85ffdd23098b67aa11bd1f2a834a5a246ea67ed6fbd7b1289302600ef4bd7a7
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11700 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3589f5bf1f7109d172dbce9e33abc5dcc6c3d5ca58a9201b41a20d80c3606fa
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d11f38c72072b2a5f453d3f5e04de50942848c7b5c4ef63cb65abcbc0b25ce4
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/11900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15446f327abe16f08a2fd4ae6075751e51dd1a4aacc9cac3bd7ec3757db189b
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f66d0dc3d25181c5fbb35abe0015eb08e52eb2580c3a103ce66172945569748
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/12100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b53ab418585ce3e703020b7e606a0de2f45aa0e82efe281621de69b41d92745
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0715db6295848d80e6134a04f22d3a314067d3806e16361444a3e63ab7c35db
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b32798dd921c01efb9fc320c6e6ec83c7b1fe1c6de64f902e6b52ed7a6c03d
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f48101058e77c02328aa36ce6573e9dd654000ac27a022eae23267301c296a7
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/13900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:024e07ed4c94b765288cd4d048dc671f32f265c924dd1fda6a7b50eeae5528f1
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1400 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebe907ad613ee3dfe9582c381ed4568943ffb65683f36560af5e3508b7523bf3
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d024a2338eb3e6723c71e1a4a3b48962c940702cd0deb4fefb574281730194fb
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1429b0352df27acc14c4d1aa722354f1313f9eb76e2ebbec5f8cc571b71475a6
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42fa39c58e4bd8831410e102d4a30516eca012ab25ca28d9af73f03f2a66d6d6
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14300 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e662091f888025b5c6254d45abdd6dee1670d6e4a43cc0f6557627dc919899d9
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/14900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdeab0564c1a1f118c6e221479b77cec2c5b90dbf68899dd259880a5a24ff761
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:804f2b482196318d71884b4e5d731d576c95130e4003b049048b1356a899a587
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed4eb970666b6c2372a82b262ac37ce383312e706f9c99bfaf22df74ece0514e
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc15a1f3ef265e973138d3a3bdeda0e83a2cc5a3bcfa4e0a54b444ab31a424df
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a19d4aa9763c0d1b0a91f5057cf545f8cb912cdcc01d57cd9c7d8b94b9be2b
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/15900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37ad7932f82a86bad4c931339a900f82b9c491233d3fad484140c6b94d726cf
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a46a07579ee4351757949a014da81246e48cfe1094ab337c0b609643b9d535f2
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:122e09fde5d3b301e18bbcae10c4cf547b84d12e182a79b03c24200407aa3170
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb8e131dfd24d6617fb4e68fd4c9657373259d4998464ad2bd686169f9c27bae
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/16800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64e93d92d90d7abb1be17c254e0db2b6dc384c85424ac01a8e23295745e6c6d2
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1700 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02957143fc0d38de232441d8c8cb8052a2070fa396417b21cc9b6e660f51d6a9
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8074d61bd0c6226e4c82b9a7baedd4c829d6419bb1c40a555de75d94ea41aa89
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50da37ff21b597cab80241be3a936a135c151124c8d178d23132db79a0800775
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a49e08a7e07d426e3ce27e17a8ed309b1b69f0d9375caf7deca26d4c036ce2e
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17300 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbcb20cec809eaf1d85071cea502999f60dd6ff73c7d958f874effdf700d70e6
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2d3fcf5e8c5825688529931097a3aeaacd5998dbec1251b97c1f91fcddd7840
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17700 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f548a74453f08f9d26e64ae5c724cb318c5c04ae1f9bd79ca0a37f6805c596ca
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/17900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4541a4a60377a5204c0fce60e9b98db6221cf48f9a00c33233f15950bc612f90
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e79ae7dea899d12054b60c533fc92c84dd6ab36e4d7f0b1134f839853ea1b2f
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d5fa99802f6f7970efca114e078580867f439cab33432320623aa8ce09112d
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18400 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54a27f5c13fa961caab89e7ffb2b5b2b264f91965731c7c3b0433eda222eb001
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b7f34347ce4056945f9308e58d225fcdef0e1ad3324596a3ba14553b8310385
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/18700 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b89a9b6bb7ac83c5084c4cd144e5ed8e306180ccd2a572e35239d978956d347
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/1900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d291d4960503277bcd3eba3c87cb18a5e55a3acb09b6077cc8330c8c5ffcf899
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/models/200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5631d59644656d58fb8b51c6223769b5bc1c43e352e7745ce85195592a24a756
3
+ size 1362571
ClassControl/CartPole-v1/Test_CartPole-v1_SAC_20230618-163219/tb_logs/interact/events.out.tfevents.1687077139.ML3090.328984.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2afc33eb6c50d1d5e1161b1d6e9cf207ab36edcdff724b5495c1838d6eb2d97d
3
+ size 19386