Hugging Face's logo

joyrl
/
joyrl-benchmarks

TensorBoard
Model card Files Metrics Community
15

Test_Pendulum-v1_SAC

#8
by gsc579 - opened
base: refs/heads/main
←
from: refs/pr/8
Discussion Files changed
+689
-0
Files changed (47) hide show
  1. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/config.yaml +81 -0
  2. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/logs/log.txt +473 -0
  3. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/100 +3 -0
  4. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1000 +3 -0
  5. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/10000 +3 -0
  6. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/10800 +3 -0
  7. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/10900 +3 -0
  8. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1100 +3 -0
  9. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/11000 +3 -0
  10. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/11800 +3 -0
  11. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/11900 +3 -0
  12. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1200 +3 -0
  13. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/12000 +3 -0
  14. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/12900 +3 -0
  15. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1300 +3 -0
  16. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/13000 +3 -0
  17. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/13900 +3 -0
  18. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1400 +3 -0
  19. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/14000 +3 -0
  20. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/14100 +3 -0
  21. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/14800 +3 -0
  22. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/14900 +3 -0
  23. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1500 +3 -0
  24. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/15000 +3 -0
  25. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/15900 +3 -0
  26. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1600 +3 -0
  27. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16000 +3 -0
  28. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16100 +3 -0
  29. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16200 +3 -0
  30. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16300 +3 -0
  31. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16400 +3 -0
  32. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16500 +3 -0
  33. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16600 +3 -0
  34. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16900 +3 -0
  35. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1700 +3 -0
  36. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/17000 +3 -0
  37. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/17500 +3 -0
  38. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/17600 +3 -0
  39. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/17900 +3 -0
  40. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1800 +3 -0
  41. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/18000 +3 -0
  42. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/18600 +3 -0
  43. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/18700 +3 -0
  44. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/18800 +3 -0
  45. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/18900 +3 -0
  46. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/tb_logs/interact/events.out.tfevents.1687078982.ML3090.333825.0 +3 -0
  47. ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/tb_logs/policy/events.out.tfevents.1687078982.ML3090.333825.1 +3 -0
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/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_Pendulum-v1_SAC_20230618-165413
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: continuous
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: 256
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: Pendulum-v1
77
+ ignore_params:
78
+ - wrapper
79
+ - ignore_params
80
+ render_mode: null
81
+ wrapper: null
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/logs/log.txt ADDED
@@ -0,0 +1,473 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - General Configs:
2
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - ================================================================================
3
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - Name Value Type
4
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - env_name gym <class 'str'>
5
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - algo_name SAC <class 'str'>
6
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - mode test <class 'str'>
7
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - device cpu <class 'str'>
8
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - seed 1 <class 'int'>
9
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - max_episode 200 <class 'int'>
10
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - max_step 200 <class 'int'>
11
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
12
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - mp_backend single <class 'str'>
13
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - n_workers 2 <class 'int'>
14
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - n_learners 1 <class 'int'>
15
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
16
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
17
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'>
18
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - model_save_fre 100 <class 'int'>
19
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - load_checkpoint 1 <class 'bool'>
20
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - load_path Train_Pendulum-v1_SAC_20230618-165413 <class 'str'>
21
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - load_model_step best <class 'str'>
22
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - interact_summary_fre 1 <class 'int'>
23
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - model_summary_fre 1 <class 'int'>
24
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - ================================================================================
25
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - Algo Configs:
26
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - ================================================================================
27
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - Name Value Type
28
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - critic1_lr 0.001 <class 'float'>
29
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - critic2_lr 0.001 <class 'float'>
30
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - actor_lr 0.0003 <class 'float'>
31
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - gamma 0.95 <class 'float'>
32
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - tau 0.005 <class 'float'>
33
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - alpha 0.1 <class 'float'>
34
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - automatic_entropy_tuning 0 <class 'bool'>
35
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - batch_size 256 <class 'int'>
36
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - hidden_dim 64 <class 'int'>
37
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - n_epochs 1 <class 'int'>
38
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - start_steps 10000 <class 'int'>
39
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - target_update_fre 1 <class 'int'>
40
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - buffer_size 1000000 <class 'int'>
41
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - min_policy 0 <class 'int'>
42
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - alpha_lr 0.0001 <class 'float'>
43
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - n_steps_per_learn 1 <class 'int'>
44
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - action_type continuous <class 'str'>
45
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - independ_actor 1 <class 'bool'>
46
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - share_optimizer 0 <class 'bool'>
47
+ 2023-06-18 17:03:02 - 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 17:03:02 - 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 17:03:02 - 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 17:03:02 - SimpleLog - INFO: - buffer_type REPLAY_QUE <class 'str'>
51
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - epsilon_decay 500 <class 'int'>
52
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - epsilon_end 0.01 <class 'float'>
53
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - epsilon_start 0.95 <class 'float'>
54
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - lr 0.0001 <class 'float'>
55
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - target_update 1 <class 'int'>
56
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - ================================================================================
57
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - Env Configs:
58
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - ================================================================================
59
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - Name Value Type
60
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - id Pendulum-v1 <class 'str'>
61
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - render_mode None <class 'str'>
62
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - wrapper None <class 'str'>
63
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
64
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - ================================================================================
65
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - Start testing!
66
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - Interactor 0 finished episode 1 with reward -136.444 in 200 steps
67
+ 2023-06-18 17:03:02 - SimpleLog - INFO: - Interactor 1 finished episode 2 with reward -127.005 in 200 steps
68
+ 2023-06-18 17:03:03 - SimpleLog - INFO: - update_step: 100, online_eval_reward: -636.118
69
+ 2023-06-18 17:03:03 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -636.118, save the best model!
70
+ 2023-06-18 17:03:05 - SimpleLog - INFO: - update_step: 200, online_eval_reward: -626.424
71
+ 2023-06-18 17:03:05 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -626.424, save the best model!
72
+ 2023-06-18 17:03:05 - SimpleLog - INFO: - Interactor 0 finished episode 3 with reward -127.766 in 200 steps
73
+ 2023-06-18 17:03:05 - SimpleLog - INFO: - Interactor 1 finished episode 4 with reward -249.089 in 200 steps
74
+ 2023-06-18 17:03:06 - SimpleLog - INFO: - update_step: 300, online_eval_reward: -693.215
75
+ 2023-06-18 17:03:08 - SimpleLog - INFO: - update_step: 400, online_eval_reward: -663.382
76
+ 2023-06-18 17:03:08 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward -382.003 in 200 steps
77
+ 2023-06-18 17:03:08 - SimpleLog - INFO: - Interactor 1 finished episode 6 with reward -501.304 in 200 steps
78
+ 2023-06-18 17:03:09 - SimpleLog - INFO: - update_step: 500, online_eval_reward: -648.743
79
+ 2023-06-18 17:03:11 - SimpleLog - INFO: - update_step: 600, online_eval_reward: -625.739
80
+ 2023-06-18 17:03:11 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -625.739, save the best model!
81
+ 2023-06-18 17:03:11 - SimpleLog - INFO: - Interactor 0 finished episode 7 with reward -484.950 in 200 steps
82
+ 2023-06-18 17:03:11 - SimpleLog - INFO: - Interactor 1 finished episode 8 with reward -499.543 in 200 steps
83
+ 2023-06-18 17:03:12 - SimpleLog - INFO: - update_step: 700, online_eval_reward: -626.179
84
+ 2023-06-18 17:03:14 - SimpleLog - INFO: - update_step: 800, online_eval_reward: -625.761
85
+ 2023-06-18 17:03:14 - SimpleLog - INFO: - Interactor 0 finished episode 9 with reward -379.836 in 200 steps
86
+ 2023-06-18 17:03:14 - SimpleLog - INFO: - Interactor 1 finished episode 10 with reward -500.035 in 200 steps
87
+ 2023-06-18 17:03:15 - SimpleLog - INFO: - update_step: 900, online_eval_reward: -627.214
88
+ 2023-06-18 17:03:17 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: -626.435
89
+ 2023-06-18 17:03:17 - SimpleLog - INFO: - Interactor 0 finished episode 11 with reward -126.620 in 200 steps
90
+ 2023-06-18 17:03:17 - SimpleLog - INFO: - Interactor 1 finished episode 12 with reward -374.525 in 200 steps
91
+ 2023-06-18 17:03:18 - SimpleLog - INFO: - update_step: 1100, online_eval_reward: -625.984
92
+ 2023-06-18 17:03:20 - SimpleLog - INFO: - update_step: 1200, online_eval_reward: -626.109
93
+ 2023-06-18 17:03:21 - SimpleLog - INFO: - Interactor 0 finished episode 13 with reward -254.016 in 200 steps
94
+ 2023-06-18 17:03:21 - SimpleLog - INFO: - Interactor 1 finished episode 14 with reward -374.616 in 200 steps
95
+ 2023-06-18 17:03:21 - SimpleLog - INFO: - update_step: 1300, online_eval_reward: -626.158
96
+ 2023-06-18 17:03:23 - SimpleLog - INFO: - update_step: 1400, online_eval_reward: -625.683
97
+ 2023-06-18 17:03:23 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -625.683, save the best model!
98
+ 2023-06-18 17:03:24 - SimpleLog - INFO: - Interactor 0 finished episode 15 with reward -256.294 in 200 steps
99
+ 2023-06-18 17:03:24 - SimpleLog - INFO: - Interactor 1 finished episode 16 with reward -375.215 in 200 steps
100
+ 2023-06-18 17:03:24 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: -502.887
101
+ 2023-06-18 17:03:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -502.887, save the best model!
102
+ 2023-06-18 17:03:26 - SimpleLog - INFO: - update_step: 1600, online_eval_reward: -502.960
103
+ 2023-06-18 17:03:27 - SimpleLog - INFO: - Interactor 0 finished episode 17 with reward -256.581 in 200 steps
104
+ 2023-06-18 17:03:27 - SimpleLog - INFO: - Interactor 1 finished episode 18 with reward -247.272 in 200 steps
105
+ 2023-06-18 17:03:27 - SimpleLog - INFO: - update_step: 1700, online_eval_reward: -626.464
106
+ 2023-06-18 17:03:29 - SimpleLog - INFO: - update_step: 1800, online_eval_reward: -251.186
107
+ 2023-06-18 17:03:29 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -251.186, save the best model!
108
+ 2023-06-18 17:03:30 - SimpleLog - INFO: - Interactor 0 finished episode 19 with reward -135.492 in 200 steps
109
+ 2023-06-18 17:03:30 - SimpleLog - INFO: - Interactor 1 finished episode 20 with reward -254.200 in 200 steps
110
+ 2023-06-18 17:03:30 - SimpleLog - INFO: - update_step: 1900, online_eval_reward: -378.429
111
+ 2023-06-18 17:03:32 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: -627.004
112
+ 2023-06-18 17:03:33 - SimpleLog - INFO: - Interactor 0 finished episode 21 with reward -134.371 in 200 steps
113
+ 2023-06-18 17:03:33 - SimpleLog - INFO: - Interactor 1 finished episode 22 with reward -253.048 in 200 steps
114
+ 2023-06-18 17:03:33 - SimpleLog - INFO: - update_step: 2100, online_eval_reward: -377.027
115
+ 2023-06-18 17:03:35 - SimpleLog - INFO: - update_step: 2200, online_eval_reward: -377.597
116
+ 2023-06-18 17:03:36 - SimpleLog - INFO: - Interactor 0 finished episode 23 with reward -133.143 in 200 steps
117
+ 2023-06-18 17:03:36 - SimpleLog - INFO: - Interactor 1 finished episode 24 with reward -252.381 in 200 steps
118
+ 2023-06-18 17:03:37 - SimpleLog - INFO: - update_step: 2300, online_eval_reward: -379.799
119
+ 2023-06-18 17:03:38 - SimpleLog - INFO: - update_step: 2400, online_eval_reward: -625.610
120
+ 2023-06-18 17:03:39 - SimpleLog - INFO: - Interactor 0 finished episode 25 with reward -132.652 in 200 steps
121
+ 2023-06-18 17:03:39 - SimpleLog - INFO: - Interactor 1 finished episode 26 with reward -252.240 in 200 steps
122
+ 2023-06-18 17:03:40 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: -607.196
123
+ 2023-06-18 17:03:41 - SimpleLog - INFO: - update_step: 2600, online_eval_reward: -626.740
124
+ 2023-06-18 17:03:42 - SimpleLog - INFO: - Interactor 0 finished episode 27 with reward -132.616 in 200 steps
125
+ 2023-06-18 17:03:42 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward -251.448 in 200 steps
126
+ 2023-06-18 17:03:43 - SimpleLog - INFO: - update_step: 2700, online_eval_reward: -626.690
127
+ 2023-06-18 17:03:44 - SimpleLog - INFO: - update_step: 2800, online_eval_reward: -625.910
128
+ 2023-06-18 17:03:45 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward -132.756 in 200 steps
129
+ 2023-06-18 17:03:45 - SimpleLog - INFO: - Interactor 1 finished episode 30 with reward -251.432 in 200 steps
130
+ 2023-06-18 17:03:46 - SimpleLog - INFO: - update_step: 2900, online_eval_reward: -625.974
131
+ 2023-06-18 17:03:47 - SimpleLog - INFO: - update_step: 3000, online_eval_reward: -378.740
132
+ 2023-06-18 17:03:48 - SimpleLog - INFO: - Interactor 0 finished episode 31 with reward -131.944 in 200 steps
133
+ 2023-06-18 17:03:48 - SimpleLog - INFO: - Interactor 1 finished episode 32 with reward -251.573 in 200 steps
134
+ 2023-06-18 17:03:49 - SimpleLog - INFO: - update_step: 3100, online_eval_reward: -626.400
135
+ 2023-06-18 17:03:50 - SimpleLog - INFO: - update_step: 3200, online_eval_reward: -412.492
136
+ 2023-06-18 17:03:51 - SimpleLog - INFO: - Interactor 0 finished episode 33 with reward -131.532 in 200 steps
137
+ 2023-06-18 17:03:51 - SimpleLog - INFO: - Interactor 1 finished episode 34 with reward -251.657 in 200 steps
138
+ 2023-06-18 17:03:52 - SimpleLog - INFO: - update_step: 3300, online_eval_reward: -451.813
139
+ 2023-06-18 17:03:53 - SimpleLog - INFO: - update_step: 3400, online_eval_reward: -697.842
140
+ 2023-06-18 17:03:54 - SimpleLog - INFO: - Interactor 0 finished episode 35 with reward -132.751 in 200 steps
141
+ 2023-06-18 17:03:54 - SimpleLog - INFO: - Interactor 1 finished episode 36 with reward -252.351 in 200 steps
142
+ 2023-06-18 17:03:55 - SimpleLog - INFO: - update_step: 3500, online_eval_reward: -501.635
143
+ 2023-06-18 17:03:56 - SimpleLog - INFO: - update_step: 3600, online_eval_reward: -746.679
144
+ 2023-06-18 17:03:57 - SimpleLog - INFO: - Interactor 0 finished episode 37 with reward -133.753 in 200 steps
145
+ 2023-06-18 17:03:57 - SimpleLog - INFO: - Interactor 1 finished episode 38 with reward -252.748 in 200 steps
146
+ 2023-06-18 17:03:58 - SimpleLog - INFO: - update_step: 3700, online_eval_reward: -502.816
147
+ 2023-06-18 17:03:59 - SimpleLog - INFO: - update_step: 3800, online_eval_reward: -502.489
148
+ 2023-06-18 17:04:00 - SimpleLog - INFO: - Interactor 0 finished episode 39 with reward -134.706 in 200 steps
149
+ 2023-06-18 17:04:00 - SimpleLog - INFO: - Interactor 1 finished episode 40 with reward -252.406 in 200 steps
150
+ 2023-06-18 17:04:01 - SimpleLog - INFO: - update_step: 3900, online_eval_reward: -734.186
151
+ 2023-06-18 17:04:03 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: -747.067
152
+ 2023-06-18 17:04:03 - SimpleLog - INFO: - Interactor 0 finished episode 41 with reward -135.287 in 200 steps
153
+ 2023-06-18 17:04:03 - SimpleLog - INFO: - Interactor 1 finished episode 42 with reward -253.261 in 200 steps
154
+ 2023-06-18 17:04:04 - SimpleLog - INFO: - update_step: 4100, online_eval_reward: -502.202
155
+ 2023-06-18 17:04:06 - SimpleLog - INFO: - update_step: 4200, online_eval_reward: -502.387
156
+ 2023-06-18 17:04:06 - SimpleLog - INFO: - Interactor 0 finished episode 43 with reward -258.825 in 200 steps
157
+ 2023-06-18 17:04:06 - SimpleLog - INFO: - Interactor 1 finished episode 44 with reward -377.815 in 200 steps
158
+ 2023-06-18 17:04:07 - SimpleLog - INFO: - update_step: 4300, online_eval_reward: -503.666
159
+ 2023-06-18 17:04:09 - SimpleLog - INFO: - update_step: 4400, online_eval_reward: -503.467
160
+ 2023-06-18 17:04:10 - SimpleLog - INFO: - Interactor 0 finished episode 45 with reward -259.453 in 200 steps
161
+ 2023-06-18 17:04:10 - SimpleLog - INFO: - Interactor 1 finished episode 46 with reward -377.560 in 200 steps
162
+ 2023-06-18 17:04:10 - SimpleLog - INFO: - update_step: 4500, online_eval_reward: -747.326
163
+ 2023-06-18 17:04:12 - SimpleLog - INFO: - update_step: 4600, online_eval_reward: -748.833
164
+ 2023-06-18 17:04:13 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward -136.616 in 200 steps
165
+ 2023-06-18 17:04:13 - SimpleLog - INFO: - Interactor 1 finished episode 48 with reward -377.490 in 200 steps
166
+ 2023-06-18 17:04:13 - SimpleLog - INFO: - update_step: 4700, online_eval_reward: -761.474
167
+ 2023-06-18 17:04:15 - SimpleLog - INFO: - update_step: 4800, online_eval_reward: -771.114
168
+ 2023-06-18 17:04:16 - SimpleLog - INFO: - Interactor 0 finished episode 49 with reward -258.114 in 200 steps
169
+ 2023-06-18 17:04:16 - SimpleLog - INFO: - Interactor 1 finished episode 50 with reward -376.747 in 200 steps
170
+ 2023-06-18 17:04:16 - SimpleLog - INFO: - update_step: 4900, online_eval_reward: -756.980
171
+ 2023-06-18 17:04:18 - SimpleLog - INFO: - update_step: 5000, online_eval_reward: -745.851
172
+ 2023-06-18 17:04:19 - SimpleLog - INFO: - Interactor 0 finished episode 51 with reward -253.985 in 200 steps
173
+ 2023-06-18 17:04:19 - SimpleLog - INFO: - Interactor 1 finished episode 52 with reward -372.461 in 200 steps
174
+ 2023-06-18 17:04:20 - SimpleLog - INFO: - update_step: 5100, online_eval_reward: -747.694
175
+ 2023-06-18 17:04:21 - SimpleLog - INFO: - update_step: 5200, online_eval_reward: -746.287
176
+ 2023-06-18 17:04:22 - SimpleLog - INFO: - Interactor 0 finished episode 53 with reward -252.117 in 200 steps
177
+ 2023-06-18 17:04:22 - SimpleLog - INFO: - Interactor 1 finished episode 54 with reward -370.886 in 200 steps
178
+ 2023-06-18 17:04:23 - SimpleLog - INFO: - update_step: 5300, online_eval_reward: -746.609
179
+ 2023-06-18 17:04:24 - SimpleLog - INFO: - update_step: 5400, online_eval_reward: -746.759
180
+ 2023-06-18 17:04:25 - SimpleLog - INFO: - Interactor 0 finished episode 55 with reward -251.893 in 200 steps
181
+ 2023-06-18 17:04:25 - SimpleLog - INFO: - Interactor 1 finished episode 56 with reward -370.721 in 200 steps
182
+ 2023-06-18 17:04:26 - SimpleLog - INFO: - update_step: 5500, online_eval_reward: -745.414
183
+ 2023-06-18 17:04:27 - SimpleLog - INFO: - update_step: 5600, online_eval_reward: -750.942
184
+ 2023-06-18 17:04:28 - SimpleLog - INFO: - Interactor 0 finished episode 57 with reward -252.362 in 200 steps
185
+ 2023-06-18 17:04:28 - SimpleLog - INFO: - Interactor 1 finished episode 58 with reward -371.562 in 200 steps
186
+ 2023-06-18 17:04:29 - SimpleLog - INFO: - update_step: 5700, online_eval_reward: -739.262
187
+ 2023-06-18 17:04:30 - SimpleLog - INFO: - update_step: 5800, online_eval_reward: -777.061
188
+ 2023-06-18 17:04:31 - SimpleLog - INFO: - Interactor 0 finished episode 59 with reward -253.113 in 200 steps
189
+ 2023-06-18 17:04:31 - SimpleLog - INFO: - Interactor 1 finished episode 60 with reward -371.534 in 200 steps
190
+ 2023-06-18 17:04:32 - SimpleLog - INFO: - update_step: 5900, online_eval_reward: -760.010
191
+ 2023-06-18 17:04:34 - SimpleLog - INFO: - update_step: 6000, online_eval_reward: -746.427
192
+ 2023-06-18 17:04:34 - SimpleLog - INFO: - Interactor 0 finished episode 61 with reward -252.634 in 200 steps
193
+ 2023-06-18 17:04:34 - SimpleLog - INFO: - Interactor 1 finished episode 62 with reward -370.496 in 200 steps
194
+ 2023-06-18 17:04:35 - SimpleLog - INFO: - update_step: 6100, online_eval_reward: -751.456
195
+ 2023-06-18 17:04:37 - SimpleLog - INFO: - update_step: 6200, online_eval_reward: -777.795
196
+ 2023-06-18 17:04:37 - SimpleLog - INFO: - Interactor 0 finished episode 63 with reward -253.216 in 200 steps
197
+ 2023-06-18 17:04:37 - SimpleLog - INFO: - Interactor 1 finished episode 64 with reward -370.464 in 200 steps
198
+ 2023-06-18 17:04:38 - SimpleLog - INFO: - update_step: 6300, online_eval_reward: -737.162
199
+ 2023-06-18 17:04:40 - SimpleLog - INFO: - update_step: 6400, online_eval_reward: -740.493
200
+ 2023-06-18 17:04:41 - SimpleLog - INFO: - Interactor 0 finished episode 65 with reward -253.932 in 200 steps
201
+ 2023-06-18 17:04:41 - SimpleLog - INFO: - Interactor 1 finished episode 66 with reward -370.900 in 200 steps
202
+ 2023-06-18 17:04:41 - SimpleLog - INFO: - update_step: 6500, online_eval_reward: -747.373
203
+ 2023-06-18 17:04:43 - SimpleLog - INFO: - update_step: 6600, online_eval_reward: -848.187
204
+ 2023-06-18 17:04:44 - SimpleLog - INFO: - Interactor 0 finished episode 67 with reward -630.252 in 200 steps
205
+ 2023-06-18 17:04:44 - SimpleLog - INFO: - Interactor 1 finished episode 68 with reward -628.687 in 200 steps
206
+ 2023-06-18 17:04:44 - SimpleLog - INFO: - update_step: 6700, online_eval_reward: -749.950
207
+ 2023-06-18 17:04:46 - SimpleLog - INFO: - update_step: 6800, online_eval_reward: -747.891
208
+ 2023-06-18 17:04:47 - SimpleLog - INFO: - Interactor 0 finished episode 69 with reward -517.135 in 200 steps
209
+ 2023-06-18 17:04:47 - SimpleLog - INFO: - Interactor 1 finished episode 70 with reward -623.039 in 200 steps
210
+ 2023-06-18 17:04:48 - SimpleLog - INFO: - update_step: 6900, online_eval_reward: -734.989
211
+ 2023-06-18 17:04:49 - SimpleLog - INFO: - update_step: 7000, online_eval_reward: -747.610
212
+ 2023-06-18 17:04:50 - SimpleLog - INFO: - Interactor 0 finished episode 71 with reward -253.929 in 200 steps
213
+ 2023-06-18 17:04:50 - SimpleLog - INFO: - Interactor 1 finished episode 72 with reward -371.426 in 200 steps
214
+ 2023-06-18 17:04:51 - SimpleLog - INFO: - update_step: 7100, online_eval_reward: -711.361
215
+ 2023-06-18 17:04:52 - SimpleLog - INFO: - update_step: 7200, online_eval_reward: -747.133
216
+ 2023-06-18 17:04:53 - SimpleLog - INFO: - Interactor 0 finished episode 73 with reward -254.455 in 200 steps
217
+ 2023-06-18 17:04:53 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward -372.031 in 200 steps
218
+ 2023-06-18 17:04:54 - SimpleLog - INFO: - update_step: 7300, online_eval_reward: -747.573
219
+ 2023-06-18 17:04:56 - SimpleLog - INFO: - update_step: 7400, online_eval_reward: -746.315
220
+ 2023-06-18 17:04:57 - SimpleLog - INFO: - Interactor 0 finished episode 75 with reward -254.290 in 200 steps
221
+ 2023-06-18 17:04:57 - SimpleLog - INFO: - Interactor 1 finished episode 76 with reward -371.493 in 200 steps
222
+ 2023-06-18 17:04:57 - SimpleLog - INFO: - update_step: 7500, online_eval_reward: -629.045
223
+ 2023-06-18 17:04:59 - SimpleLog - INFO: - update_step: 7600, online_eval_reward: -635.438
224
+ 2023-06-18 17:05:00 - SimpleLog - INFO: - Interactor 0 finished episode 77 with reward -253.799 in 200 steps
225
+ 2023-06-18 17:05:00 - SimpleLog - INFO: - Interactor 1 finished episode 78 with reward -371.591 in 200 steps
226
+ 2023-06-18 17:05:01 - SimpleLog - INFO: - update_step: 7700, online_eval_reward: -747.443
227
+ 2023-06-18 17:05:02 - SimpleLog - INFO: - update_step: 7800, online_eval_reward: -747.871
228
+ 2023-06-18 17:05:03 - SimpleLog - INFO: - Interactor 0 finished episode 79 with reward -253.395 in 200 steps
229
+ 2023-06-18 17:05:03 - SimpleLog - INFO: - Interactor 1 finished episode 80 with reward -371.719 in 200 steps
230
+ 2023-06-18 17:05:04 - SimpleLog - INFO: - update_step: 7900, online_eval_reward: -634.066
231
+ 2023-06-18 17:05:05 - SimpleLog - INFO: - update_step: 8000, online_eval_reward: -626.568
232
+ 2023-06-18 17:05:06 - SimpleLog - INFO: - Interactor 0 finished episode 81 with reward -379.646 in 200 steps
233
+ 2023-06-18 17:05:06 - SimpleLog - INFO: - Interactor 1 finished episode 82 with reward -370.409 in 200 steps
234
+ 2023-06-18 17:05:07 - SimpleLog - INFO: - update_step: 8100, online_eval_reward: -746.212
235
+ 2023-06-18 17:05:08 - SimpleLog - INFO: - update_step: 8200, online_eval_reward: -732.249
236
+ 2023-06-18 17:05:09 - SimpleLog - INFO: - Interactor 0 finished episode 83 with reward -254.146 in 200 steps
237
+ 2023-06-18 17:05:09 - SimpleLog - INFO: - Interactor 1 finished episode 84 with reward -371.660 in 200 steps
238
+ 2023-06-18 17:05:10 - SimpleLog - INFO: - update_step: 8300, online_eval_reward: -635.946
239
+ 2023-06-18 17:05:11 - SimpleLog - INFO: - update_step: 8400, online_eval_reward: -625.884
240
+ 2023-06-18 17:05:12 - SimpleLog - INFO: - Interactor 0 finished episode 85 with reward -254.644 in 200 steps
241
+ 2023-06-18 17:05:12 - SimpleLog - INFO: - Interactor 1 finished episode 86 with reward -496.348 in 200 steps
242
+ 2023-06-18 17:05:13 - SimpleLog - INFO: - update_step: 8500, online_eval_reward: -747.116
243
+ 2023-06-18 17:05:15 - SimpleLog - INFO: - update_step: 8600, online_eval_reward: -631.017
244
+ 2023-06-18 17:05:15 - SimpleLog - INFO: - Interactor 0 finished episode 87 with reward -380.258 in 200 steps
245
+ 2023-06-18 17:05:15 - SimpleLog - INFO: - Interactor 1 finished episode 88 with reward -370.962 in 200 steps
246
+ 2023-06-18 17:05:16 - SimpleLog - INFO: - update_step: 8700, online_eval_reward: -511.448
247
+ 2023-06-18 17:05:18 - SimpleLog - INFO: - update_step: 8800, online_eval_reward: -627.426
248
+ 2023-06-18 17:05:18 - SimpleLog - INFO: - Interactor 0 finished episode 89 with reward -129.067 in 200 steps
249
+ 2023-06-18 17:05:18 - SimpleLog - INFO: - Interactor 1 finished episode 90 with reward -624.422 in 200 steps
250
+ 2023-06-18 17:05:19 - SimpleLog - INFO: - update_step: 8900, online_eval_reward: -697.878
251
+ 2023-06-18 17:05:21 - SimpleLog - INFO: - update_step: 9000, online_eval_reward: -503.100
252
+ 2023-06-18 17:05:22 - SimpleLog - INFO: - Interactor 0 finished episode 91 with reward -506.755 in 200 steps
253
+ 2023-06-18 17:05:22 - SimpleLog - INFO: - Interactor 1 finished episode 92 with reward -371.752 in 200 steps
254
+ 2023-06-18 17:05:22 - SimpleLog - INFO: - update_step: 9100, online_eval_reward: -552.838
255
+ 2023-06-18 17:05:24 - SimpleLog - INFO: - update_step: 9200, online_eval_reward: -624.902
256
+ 2023-06-18 17:05:25 - SimpleLog - INFO: - Interactor 0 finished episode 93 with reward -128.671 in 200 steps
257
+ 2023-06-18 17:05:25 - SimpleLog - INFO: - Interactor 1 finished episode 94 with reward -372.343 in 200 steps
258
+ 2023-06-18 17:05:25 - SimpleLog - INFO: - update_step: 9300, online_eval_reward: -585.368
259
+ 2023-06-18 17:05:27 - SimpleLog - INFO: - update_step: 9400, online_eval_reward: -637.911
260
+ 2023-06-18 17:05:28 - SimpleLog - INFO: - Interactor 0 finished episode 95 with reward -127.988 in 200 steps
261
+ 2023-06-18 17:05:28 - SimpleLog - INFO: - Interactor 1 finished episode 96 with reward -372.189 in 200 steps
262
+ 2023-06-18 17:05:29 - SimpleLog - INFO: - update_step: 9500, online_eval_reward: -626.990
263
+ 2023-06-18 17:05:30 - SimpleLog - INFO: - update_step: 9600, online_eval_reward: -502.545
264
+ 2023-06-18 17:05:31 - SimpleLog - INFO: - Interactor 0 finished episode 97 with reward -508.382 in 200 steps
265
+ 2023-06-18 17:05:31 - SimpleLog - INFO: - Interactor 1 finished episode 98 with reward -666.960 in 200 steps
266
+ 2023-06-18 17:05:32 - SimpleLog - INFO: - update_step: 9700, online_eval_reward: -502.885
267
+ 2023-06-18 17:05:33 - SimpleLog - INFO: - update_step: 9800, online_eval_reward: -628.113
268
+ 2023-06-18 17:05:34 - SimpleLog - INFO: - Interactor 0 finished episode 99 with reward -127.608 in 200 steps
269
+ 2023-06-18 17:05:34 - SimpleLog - INFO: - Interactor 1 finished episode 100 with reward -378.065 in 200 steps
270
+ 2023-06-18 17:05:35 - SimpleLog - INFO: - update_step: 9900, online_eval_reward: -624.142
271
+ 2023-06-18 17:05:36 - SimpleLog - INFO: - update_step: 10000, online_eval_reward: -623.988
272
+ 2023-06-18 17:05:37 - SimpleLog - INFO: - Interactor 0 finished episode 101 with reward -256.093 in 200 steps
273
+ 2023-06-18 17:05:37 - SimpleLog - INFO: - Interactor 1 finished episode 102 with reward -372.639 in 200 steps
274
+ 2023-06-18 17:05:38 - SimpleLog - INFO: - update_step: 10100, online_eval_reward: -626.887
275
+ 2023-06-18 17:05:40 - SimpleLog - INFO: - update_step: 10200, online_eval_reward: -632.886
276
+ 2023-06-18 17:05:40 - SimpleLog - INFO: - Interactor 0 finished episode 103 with reward -128.766 in 200 steps
277
+ 2023-06-18 17:05:40 - SimpleLog - INFO: - Interactor 1 finished episode 104 with reward -320.030 in 200 steps
278
+ 2023-06-18 17:05:41 - SimpleLog - INFO: - update_step: 10300, online_eval_reward: -652.435
279
+ 2023-06-18 17:05:43 - SimpleLog - INFO: - update_step: 10400, online_eval_reward: -648.223
280
+ 2023-06-18 17:05:44 - SimpleLog - INFO: - Interactor 0 finished episode 105 with reward -257.621 in 200 steps
281
+ 2023-06-18 17:05:44 - SimpleLog - INFO: - Interactor 1 finished episode 106 with reward -372.740 in 200 steps
282
+ 2023-06-18 17:05:44 - SimpleLog - INFO: - update_step: 10500, online_eval_reward: -505.940
283
+ 2023-06-18 17:05:46 - SimpleLog - INFO: - update_step: 10600, online_eval_reward: -506.988
284
+ 2023-06-18 17:05:47 - SimpleLog - INFO: - Interactor 0 finished episode 107 with reward -139.789 in 200 steps
285
+ 2023-06-18 17:05:47 - SimpleLog - INFO: - Interactor 1 finished episode 108 with reward -255.972 in 200 steps
286
+ 2023-06-18 17:05:47 - SimpleLog - INFO: - update_step: 10700, online_eval_reward: -566.581
287
+ 2023-06-18 17:05:49 - SimpleLog - INFO: - update_step: 10800, online_eval_reward: -650.279
288
+ 2023-06-18 17:05:50 - SimpleLog - INFO: - Interactor 0 finished episode 109 with reward -137.825 in 200 steps
289
+ 2023-06-18 17:05:50 - SimpleLog - INFO: - Interactor 1 finished episode 110 with reward -255.216 in 200 steps
290
+ 2023-06-18 17:05:51 - SimpleLog - INFO: - update_step: 10900, online_eval_reward: -744.327
291
+ 2023-06-18 17:05:52 - SimpleLog - INFO: - update_step: 11000, online_eval_reward: -660.797
292
+ 2023-06-18 17:05:53 - SimpleLog - INFO: - Interactor 0 finished episode 111 with reward -255.907 in 200 steps
293
+ 2023-06-18 17:05:53 - SimpleLog - INFO: - Interactor 1 finished episode 112 with reward -373.364 in 200 steps
294
+ 2023-06-18 17:05:54 - SimpleLog - INFO: - update_step: 11100, online_eval_reward: -744.080
295
+ 2023-06-18 17:05:55 - SimpleLog - INFO: - update_step: 11200, online_eval_reward: -747.634
296
+ 2023-06-18 17:05:56 - SimpleLog - INFO: - Interactor 0 finished episode 113 with reward -137.575 in 200 steps
297
+ 2023-06-18 17:05:56 - SimpleLog - INFO: - Interactor 1 finished episode 114 with reward -254.991 in 200 steps
298
+ 2023-06-18 17:05:57 - SimpleLog - INFO: - update_step: 11300, online_eval_reward: -737.472
299
+ 2023-06-18 17:05:58 - SimpleLog - INFO: - update_step: 11400, online_eval_reward: -739.587
300
+ 2023-06-18 17:05:59 - SimpleLog - INFO: - Interactor 0 finished episode 115 with reward -137.454 in 200 steps
301
+ 2023-06-18 17:05:59 - SimpleLog - INFO: - Interactor 1 finished episode 116 with reward -254.369 in 200 steps
302
+ 2023-06-18 17:06:00 - SimpleLog - INFO: - update_step: 11500, online_eval_reward: -669.705
303
+ 2023-06-18 17:06:02 - SimpleLog - INFO: - update_step: 11600, online_eval_reward: -716.405
304
+ 2023-06-18 17:06:03 - SimpleLog - INFO: - Interactor 0 finished episode 117 with reward -136.874 in 200 steps
305
+ 2023-06-18 17:06:03 - SimpleLog - INFO: - Interactor 1 finished episode 118 with reward -252.785 in 200 steps
306
+ 2023-06-18 17:06:03 - SimpleLog - INFO: - update_step: 11700, online_eval_reward: -626.797
307
+ 2023-06-18 17:06:05 - SimpleLog - INFO: - update_step: 11800, online_eval_reward: -727.960
308
+ 2023-06-18 17:06:06 - SimpleLog - INFO: - Interactor 0 finished episode 119 with reward -136.063 in 200 steps
309
+ 2023-06-18 17:06:06 - SimpleLog - INFO: - Interactor 1 finished episode 120 with reward -252.348 in 200 steps
310
+ 2023-06-18 17:06:06 - SimpleLog - INFO: - update_step: 11900, online_eval_reward: -745.943
311
+ 2023-06-18 17:06:08 - SimpleLog - INFO: - update_step: 12000, online_eval_reward: -745.982
312
+ 2023-06-18 17:06:09 - SimpleLog - INFO: - Interactor 0 finished episode 121 with reward -127.967 in 200 steps
313
+ 2023-06-18 17:06:09 - SimpleLog - INFO: - Interactor 1 finished episode 122 with reward -252.231 in 200 steps
314
+ 2023-06-18 17:06:10 - SimpleLog - INFO: - update_step: 12100, online_eval_reward: -726.946
315
+ 2023-06-18 17:06:11 - SimpleLog - INFO: - update_step: 12200, online_eval_reward: -747.153
316
+ 2023-06-18 17:06:12 - SimpleLog - INFO: - Interactor 0 finished episode 123 with reward -134.319 in 200 steps
317
+ 2023-06-18 17:06:12 - SimpleLog - INFO: - Interactor 1 finished episode 124 with reward -250.729 in 200 steps
318
+ 2023-06-18 17:06:13 - SimpleLog - INFO: - update_step: 12300, online_eval_reward: -625.867
319
+ 2023-06-18 17:06:14 - SimpleLog - INFO: - update_step: 12400, online_eval_reward: -734.067
320
+ 2023-06-18 17:06:15 - SimpleLog - INFO: - Interactor 0 finished episode 125 with reward -133.822 in 200 steps
321
+ 2023-06-18 17:06:15 - SimpleLog - INFO: - Interactor 1 finished episode 126 with reward -369.726 in 200 steps
322
+ 2023-06-18 17:06:16 - SimpleLog - INFO: - update_step: 12500, online_eval_reward: -612.307
323
+ 2023-06-18 17:06:18 - SimpleLog - INFO: - update_step: 12600, online_eval_reward: -609.807
324
+ 2023-06-18 17:06:18 - SimpleLog - INFO: - Interactor 0 finished episode 127 with reward -127.352 in 200 steps
325
+ 2023-06-18 17:06:18 - SimpleLog - INFO: - Interactor 1 finished episode 128 with reward -249.728 in 200 steps
326
+ 2023-06-18 17:06:19 - SimpleLog - INFO: - update_step: 12700, online_eval_reward: -482.078
327
+ 2023-06-18 17:06:21 - SimpleLog - INFO: - update_step: 12800, online_eval_reward: -631.631
328
+ 2023-06-18 17:06:21 - SimpleLog - INFO: - Interactor 0 finished episode 129 with reward -127.126 in 200 steps
329
+ 2023-06-18 17:06:21 - SimpleLog - INFO: - Interactor 1 finished episode 130 with reward -249.478 in 200 steps
330
+ 2023-06-18 17:06:22 - SimpleLog - INFO: - update_step: 12900, online_eval_reward: -627.272
331
+ 2023-06-18 17:06:24 - SimpleLog - INFO: - update_step: 13000, online_eval_reward: -664.118
332
+ 2023-06-18 17:06:25 - SimpleLog - INFO: - Interactor 0 finished episode 131 with reward -133.073 in 200 steps
333
+ 2023-06-18 17:06:25 - SimpleLog - INFO: - Interactor 1 finished episode 132 with reward -249.471 in 200 steps
334
+ 2023-06-18 17:06:25 - SimpleLog - INFO: - update_step: 13100, online_eval_reward: -666.291
335
+ 2023-06-18 17:06:27 - SimpleLog - INFO: - update_step: 13200, online_eval_reward: -126.603
336
+ 2023-06-18 17:06:27 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -126.603, save the best model!
337
+ 2023-06-18 17:06:28 - SimpleLog - INFO: - Interactor 0 finished episode 133 with reward -132.828 in 200 steps
338
+ 2023-06-18 17:06:28 - SimpleLog - INFO: - Interactor 1 finished episode 134 with reward -249.529 in 200 steps
339
+ 2023-06-18 17:06:28 - SimpleLog - INFO: - update_step: 13300, online_eval_reward: -626.330
340
+ 2023-06-18 17:06:30 - SimpleLog - INFO: - update_step: 13400, online_eval_reward: -735.992
341
+ 2023-06-18 17:06:31 - SimpleLog - INFO: - Interactor 0 finished episode 135 with reward -126.868 in 200 steps
342
+ 2023-06-18 17:06:31 - SimpleLog - INFO: - Interactor 1 finished episode 136 with reward -248.425 in 200 steps
343
+ 2023-06-18 17:06:32 - SimpleLog - INFO: - update_step: 13500, online_eval_reward: -743.216
344
+ 2023-06-18 17:06:33 - SimpleLog - INFO: - update_step: 13600, online_eval_reward: -625.370
345
+ 2023-06-18 17:06:34 - SimpleLog - INFO: - Interactor 0 finished episode 137 with reward -133.082 in 200 steps
346
+ 2023-06-18 17:06:34 - SimpleLog - INFO: - Interactor 1 finished episode 138 with reward -248.855 in 200 steps
347
+ 2023-06-18 17:06:35 - SimpleLog - INFO: - update_step: 13700, online_eval_reward: -626.441
348
+ 2023-06-18 17:06:36 - SimpleLog - INFO: - update_step: 13800, online_eval_reward: -686.595
349
+ 2023-06-18 17:06:37 - SimpleLog - INFO: - Interactor 0 finished episode 139 with reward -127.573 in 200 steps
350
+ 2023-06-18 17:06:37 - SimpleLog - INFO: - Interactor 1 finished episode 140 with reward -244.583 in 200 steps
351
+ 2023-06-18 17:06:38 - SimpleLog - INFO: - update_step: 13900, online_eval_reward: -634.347
352
+ 2023-06-18 17:06:39 - SimpleLog - INFO: - update_step: 14000, online_eval_reward: -126.375
353
+ 2023-06-18 17:06:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -126.375, save the best model!
354
+ 2023-06-18 17:06:40 - SimpleLog - INFO: - Interactor 0 finished episode 141 with reward -126.582 in 200 steps
355
+ 2023-06-18 17:06:40 - SimpleLog - INFO: - Interactor 1 finished episode 142 with reward -245.557 in 200 steps
356
+ 2023-06-18 17:06:41 - SimpleLog - INFO: - update_step: 14100, online_eval_reward: -626.482
357
+ 2023-06-18 17:06:43 - SimpleLog - INFO: - update_step: 14200, online_eval_reward: -126.869
358
+ 2023-06-18 17:06:44 - SimpleLog - INFO: - Interactor 0 finished episode 143 with reward -128.180 in 200 steps
359
+ 2023-06-18 17:06:44 - SimpleLog - INFO: - Interactor 1 finished episode 144 with reward -245.956 in 200 steps
360
+ 2023-06-18 17:06:44 - SimpleLog - INFO: - update_step: 14300, online_eval_reward: -538.085
361
+ 2023-06-18 17:06:46 - SimpleLog - INFO: - update_step: 14400, online_eval_reward: -126.981
362
+ 2023-06-18 17:06:47 - SimpleLog - INFO: - Interactor 0 finished episode 145 with reward -127.003 in 200 steps
363
+ 2023-06-18 17:06:47 - SimpleLog - INFO: - Interactor 1 finished episode 146 with reward -370.454 in 200 steps
364
+ 2023-06-18 17:06:47 - SimpleLog - INFO: - update_step: 14500, online_eval_reward: -594.180
365
+ 2023-06-18 17:06:49 - SimpleLog - INFO: - update_step: 14600, online_eval_reward: -651.184
366
+ 2023-06-18 17:06:50 - SimpleLog - INFO: - Interactor 0 finished episode 147 with reward -133.030 in 200 steps
367
+ 2023-06-18 17:06:50 - SimpleLog - INFO: - Interactor 1 finished episode 148 with reward -250.006 in 200 steps
368
+ 2023-06-18 17:06:51 - SimpleLog - INFO: - update_step: 14700, online_eval_reward: -251.577
369
+ 2023-06-18 17:06:52 - SimpleLog - INFO: - update_step: 14800, online_eval_reward: -626.997
370
+ 2023-06-18 17:06:53 - SimpleLog - INFO: - Interactor 0 finished episode 149 with reward -130.168 in 200 steps
371
+ 2023-06-18 17:06:53 - SimpleLog - INFO: - Interactor 1 finished episode 150 with reward -367.668 in 200 steps
372
+ 2023-06-18 17:06:54 - SimpleLog - INFO: - update_step: 14900, online_eval_reward: -733.004
373
+ 2023-06-18 17:06:56 - SimpleLog - INFO: - update_step: 15000, online_eval_reward: -747.291
374
+ 2023-06-18 17:06:57 - SimpleLog - INFO: - Interactor 0 finished episode 151 with reward -133.304 in 200 steps
375
+ 2023-06-18 17:06:57 - SimpleLog - INFO: - Interactor 1 finished episode 152 with reward -497.832 in 200 steps
376
+ 2023-06-18 17:06:57 - SimpleLog - INFO: - update_step: 15100, online_eval_reward: -904.923
377
+ 2023-06-18 17:06:59 - SimpleLog - INFO: - update_step: 15200, online_eval_reward: -505.224
378
+ 2023-06-18 17:07:00 - SimpleLog - INFO: - Interactor 0 finished episode 153 with reward -638.666 in 200 steps
379
+ 2023-06-18 17:07:00 - SimpleLog - INFO: - Interactor 1 finished episode 154 with reward -497.511 in 200 steps
380
+ 2023-06-18 17:07:00 - SimpleLog - INFO: - update_step: 15300, online_eval_reward: -627.141
381
+ 2023-06-18 17:07:02 - SimpleLog - INFO: - update_step: 15400, online_eval_reward: -251.423
382
+ 2023-06-18 17:07:03 - SimpleLog - INFO: - Interactor 0 finished episode 155 with reward -126.485 in 200 steps
383
+ 2023-06-18 17:07:03 - SimpleLog - INFO: - Interactor 1 finished episode 156 with reward -366.388 in 200 steps
384
+ 2023-06-18 17:07:04 - SimpleLog - INFO: - update_step: 15500, online_eval_reward: -747.579
385
+ 2023-06-18 17:07:05 - SimpleLog - INFO: - update_step: 15600, online_eval_reward: -746.773
386
+ 2023-06-18 17:07:06 - SimpleLog - INFO: - Interactor 0 finished episode 157 with reward -135.656 in 200 steps
387
+ 2023-06-18 17:07:06 - SimpleLog - INFO: - Interactor 1 finished episode 158 with reward -741.409 in 200 steps
388
+ 2023-06-18 17:07:07 - SimpleLog - INFO: - update_step: 15700, online_eval_reward: -126.185
389
+ 2023-06-18 17:07:07 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: -126.185, save the best model!
390
+ 2023-06-18 17:07:08 - SimpleLog - INFO: - update_step: 15800, online_eval_reward: -747.045
391
+ 2023-06-18 17:07:09 - SimpleLog - INFO: - Interactor 0 finished episode 159 with reward -126.398 in 200 steps
392
+ 2023-06-18 17:07:09 - SimpleLog - INFO: - Interactor 1 finished episode 160 with reward -368.797 in 200 steps
393
+ 2023-06-18 17:07:10 - SimpleLog - INFO: - update_step: 15900, online_eval_reward: -747.972
394
+ 2023-06-18 17:07:12 - SimpleLog - INFO: - update_step: 16000, online_eval_reward: -645.710
395
+ 2023-06-18 17:07:13 - SimpleLog - INFO: - Interactor 0 finished episode 161 with reward -126.509 in 200 steps
396
+ 2023-06-18 17:07:13 - SimpleLog - INFO: - Interactor 1 finished episode 162 with reward -497.220 in 200 steps
397
+ 2023-06-18 17:07:13 - SimpleLog - INFO: - update_step: 16100, online_eval_reward: -713.664
398
+ 2023-06-18 17:07:15 - SimpleLog - INFO: - update_step: 16200, online_eval_reward: -126.325
399
+ 2023-06-18 17:07:16 - SimpleLog - INFO: - Interactor 0 finished episode 163 with reward -136.788 in 200 steps
400
+ 2023-06-18 17:07:16 - SimpleLog - INFO: - Interactor 1 finished episode 164 with reward -367.465 in 200 steps
401
+ 2023-06-18 17:07:16 - SimpleLog - INFO: - update_step: 16300, online_eval_reward: -625.428
402
+ 2023-06-18 17:07:18 - SimpleLog - INFO: - update_step: 16400, online_eval_reward: -703.316
403
+ 2023-06-18 17:07:19 - SimpleLog - INFO: - Interactor 0 finished episode 165 with reward -136.234 in 200 steps
404
+ 2023-06-18 17:07:19 - SimpleLog - INFO: - Interactor 1 finished episode 166 with reward -367.381 in 200 steps
405
+ 2023-06-18 17:07:20 - SimpleLog - INFO: - update_step: 16500, online_eval_reward: -627.194
406
+ 2023-06-18 17:07:21 - SimpleLog - INFO: - update_step: 16600, online_eval_reward: -744.325
407
+ 2023-06-18 17:07:22 - SimpleLog - INFO: - Interactor 0 finished episode 167 with reward -135.877 in 200 steps
408
+ 2023-06-18 17:07:22 - SimpleLog - INFO: - Interactor 1 finished episode 168 with reward -367.539 in 200 steps
409
+ 2023-06-18 17:07:23 - SimpleLog - INFO: - update_step: 16700, online_eval_reward: -717.572
410
+ 2023-06-18 17:07:24 - SimpleLog - INFO: - update_step: 16800, online_eval_reward: -629.369
411
+ 2023-06-18 17:07:25 - SimpleLog - INFO: - Interactor 0 finished episode 169 with reward -127.248 in 200 steps
412
+ 2023-06-18 17:07:25 - SimpleLog - INFO: - Interactor 1 finished episode 170 with reward -497.286 in 200 steps
413
+ 2023-06-18 17:07:26 - SimpleLog - INFO: - update_step: 16900, online_eval_reward: -642.603
414
+ 2023-06-18 17:07:28 - SimpleLog - INFO: - update_step: 17000, online_eval_reward: -631.630
415
+ 2023-06-18 17:07:28 - SimpleLog - INFO: - Interactor 0 finished episode 171 with reward -136.446 in 200 steps
416
+ 2023-06-18 17:07:28 - SimpleLog - INFO: - Interactor 1 finished episode 172 with reward -369.549 in 200 steps
417
+ 2023-06-18 17:07:29 - SimpleLog - INFO: - update_step: 17100, online_eval_reward: -251.684
418
+ 2023-06-18 17:07:31 - SimpleLog - INFO: - update_step: 17200, online_eval_reward: -605.021
419
+ 2023-06-18 17:07:32 - SimpleLog - INFO: - Interactor 0 finished episode 173 with reward -138.281 in 200 steps
420
+ 2023-06-18 17:07:32 - SimpleLog - INFO: - Interactor 1 finished episode 174 with reward -366.105 in 200 steps
421
+ 2023-06-18 17:07:32 - SimpleLog - INFO: - update_step: 17300, online_eval_reward: -126.459
422
+ 2023-06-18 17:07:34 - SimpleLog - INFO: - update_step: 17400, online_eval_reward: -626.421
423
+ 2023-06-18 17:07:35 - SimpleLog - INFO: - Interactor 0 finished episode 175 with reward -127.802 in 200 steps
424
+ 2023-06-18 17:07:35 - SimpleLog - INFO: - Interactor 1 finished episode 176 with reward -367.508 in 200 steps
425
+ 2023-06-18 17:07:35 - SimpleLog - INFO: - update_step: 17500, online_eval_reward: -251.493
426
+ 2023-06-18 17:07:37 - SimpleLog - INFO: - update_step: 17600, online_eval_reward: -707.992
427
+ 2023-06-18 17:07:38 - SimpleLog - INFO: - Interactor 0 finished episode 177 with reward -261.253 in 200 steps
428
+ 2023-06-18 17:07:38 - SimpleLog - INFO: - Interactor 1 finished episode 178 with reward -368.799 in 200 steps
429
+ 2023-06-18 17:07:39 - SimpleLog - INFO: - update_step: 17700, online_eval_reward: -620.728
430
+ 2023-06-18 17:07:40 - SimpleLog - INFO: - update_step: 17800, online_eval_reward: -503.678
431
+ 2023-06-18 17:07:41 - SimpleLog - INFO: - Interactor 0 finished episode 179 with reward -253.789 in 200 steps
432
+ 2023-06-18 17:07:41 - SimpleLog - INFO: - Interactor 1 finished episode 180 with reward -366.836 in 200 steps
433
+ 2023-06-18 17:07:42 - SimpleLog - INFO: - update_step: 17900, online_eval_reward: -251.175
434
+ 2023-06-18 17:07:43 - SimpleLog - INFO: - update_step: 18000, online_eval_reward: -597.803
435
+ 2023-06-18 17:07:44 - SimpleLog - INFO: - Interactor 0 finished episode 181 with reward -252.849 in 200 steps
436
+ 2023-06-18 17:07:44 - SimpleLog - INFO: - Interactor 1 finished episode 182 with reward -367.496 in 200 steps
437
+ 2023-06-18 17:07:45 - SimpleLog - INFO: - update_step: 18100, online_eval_reward: -250.703
438
+ 2023-06-18 17:07:46 - SimpleLog - INFO: - update_step: 18200, online_eval_reward: -251.585
439
+ 2023-06-18 17:07:47 - SimpleLog - INFO: - Interactor 0 finished episode 183 with reward -251.684 in 200 steps
440
+ 2023-06-18 17:07:47 - SimpleLog - INFO: - Interactor 1 finished episode 184 with reward -365.909 in 200 steps
441
+ 2023-06-18 17:07:48 - SimpleLog - INFO: - update_step: 18300, online_eval_reward: -252.046
442
+ 2023-06-18 17:07:50 - SimpleLog - INFO: - update_step: 18400, online_eval_reward: -251.152
443
+ 2023-06-18 17:07:51 - SimpleLog - INFO: - Interactor 0 finished episode 185 with reward -252.229 in 200 steps
444
+ 2023-06-18 17:07:51 - SimpleLog - INFO: - Interactor 1 finished episode 186 with reward -364.737 in 200 steps
445
+ 2023-06-18 17:07:51 - SimpleLog - INFO: - update_step: 18500, online_eval_reward: -250.797
446
+ 2023-06-18 17:07:53 - SimpleLog - INFO: - update_step: 18600, online_eval_reward: -747.515
447
+ 2023-06-18 17:07:54 - SimpleLog - INFO: - Interactor 0 finished episode 187 with reward -252.739 in 200 steps
448
+ 2023-06-18 17:07:54 - SimpleLog - INFO: - Interactor 1 finished episode 188 with reward -365.580 in 200 steps
449
+ 2023-06-18 17:07:54 - SimpleLog - INFO: - update_step: 18700, online_eval_reward: -705.736
450
+ 2023-06-18 17:07:56 - SimpleLog - INFO: - update_step: 18800, online_eval_reward: -251.174
451
+ 2023-06-18 17:07:57 - SimpleLog - INFO: - Interactor 0 finished episode 189 with reward -128.201 in 200 steps
452
+ 2023-06-18 17:07:57 - SimpleLog - INFO: - Interactor 1 finished episode 190 with reward -364.734 in 200 steps
453
+ 2023-06-18 17:07:58 - SimpleLog - INFO: - update_step: 18900, online_eval_reward: -251.335
454
+ 2023-06-18 17:07:59 - SimpleLog - INFO: - update_step: 19000, online_eval_reward: -638.485
455
+ 2023-06-18 17:08:00 - SimpleLog - INFO: - Interactor 0 finished episode 191 with reward -253.096 in 200 steps
456
+ 2023-06-18 17:08:00 - SimpleLog - INFO: - Interactor 1 finished episode 192 with reward -614.102 in 200 steps
457
+ 2023-06-18 17:08:01 - SimpleLog - INFO: - update_step: 19100, online_eval_reward: -251.756
458
+ 2023-06-18 17:08:02 - SimpleLog - INFO: - update_step: 19200, online_eval_reward: -251.738
459
+ 2023-06-18 17:08:03 - SimpleLog - INFO: - Interactor 0 finished episode 193 with reward -252.029 in 200 steps
460
+ 2023-06-18 17:08:03 - SimpleLog - INFO: - Interactor 1 finished episode 194 with reward -608.898 in 200 steps
461
+ 2023-06-18 17:08:04 - SimpleLog - INFO: - update_step: 19300, online_eval_reward: -629.103
462
+ 2023-06-18 17:08:06 - SimpleLog - INFO: - update_step: 19400, online_eval_reward: -251.932
463
+ 2023-06-18 17:08:06 - SimpleLog - INFO: - Interactor 0 finished episode 195 with reward -252.844 in 200 steps
464
+ 2023-06-18 17:08:06 - SimpleLog - INFO: - Interactor 1 finished episode 196 with reward -363.399 in 200 steps
465
+ 2023-06-18 17:08:07 - SimpleLog - INFO: - update_step: 19500, online_eval_reward: -251.400
466
+ 2023-06-18 17:08:09 - SimpleLog - INFO: - update_step: 19600, online_eval_reward: -629.244
467
+ 2023-06-18 17:08:10 - SimpleLog - INFO: - Interactor 0 finished episode 197 with reward -251.457 in 200 steps
468
+ 2023-06-18 17:08:10 - SimpleLog - INFO: - Interactor 1 finished episode 198 with reward -364.868 in 200 steps
469
+ 2023-06-18 17:08:11 - SimpleLog - INFO: - update_step: 19700, online_eval_reward: -251.345
470
+ 2023-06-18 17:08:12 - SimpleLog - INFO: - update_step: 19800, online_eval_reward: -762.630
471
+ 2023-06-18 17:08:13 - SimpleLog - INFO: - Interactor 0 finished episode 199 with reward -251.466 in 200 steps
472
+ 2023-06-18 17:08:13 - SimpleLog - INFO: - Interactor 1 finished episode 200 with reward -610.339 in 200 steps
473
+ 2023-06-18 17:08:13 - SimpleLog - INFO: - Finish testing! Time cost: 311.544 s
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecc504ba20896877bf4a2c3277324bada6e89ad28c165de45a3400fd4d6b87a4
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57f0cec7ff383528fc398da847d0eac743b0cadc95ccc84a8a7ce127315e776
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/10000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf5ad469e6b503319abc0756b864a26fa87122a12d45286b71d0453b382d45f
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/10800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb38b429f0d4a892ad14f3f253ffb8bf38f9efc28fb169abf05c6f7c3be11352
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/10900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693b6b8fe5184f9e8e2f313aef74bf72c581fa5185e34ee2a6b049d3bdc7699b
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6f326d7dd4e8c6dc88a7df89cda422e09df11fea598b5ec0df806b86c82b2a
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/11000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd659dd5f5c3d9727df57c79cdf4bf2799e79e0add202a33f5de469208bbfb4b
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/11800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ac1cf0ba29649b21c821cf5b473bb79dc315c9b2ebd6de9efe8195715a1ef46
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/11900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d23d0811191fce7a0e52fcd5430edeaf8b59ed59c61e46ee17eeaf84fd837a8f
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af7711dcc3ebd3f98724c717ae6e1d030daa72fbe836d6cec901c38f53f228d
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/12000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63d47a0dd4eabd247a1602bcbec6df348b1ece5befbde96a165a7025ded9b3a3
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/12900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ea400f661c1396459812e2c88610c8bc2e4634249bf8c92b7ce447e70ad211
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1300 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c25727a2f4839dee37fd1f8a91624f9d4c9cedb4a90edf207662f392978e1fd
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/13000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d23af78158b2159dfd632f94d74655d59428f58f3dfb91f4fe4b6528405ef56
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/13900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c070d8e953ac57bec065d023208786dbe5e8bd435b2bd46d33d43e26a7ce3c
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1400 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fa064549662321afe9b3767492098b3639ef1ce0608d038f8af3a00ef7a0a21
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/14000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46e9183f1c4fc9c97efacaa941d161cc56b88d335cae89a1bba32947e9927f4d
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/14100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c8fdd18771dfb5db2c29c42e3d7f12774f769c5f8ea6515cd9a78775ab78ae6
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/14800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef08700e2c3802d6a8833b1d219fb3bef0b6efe321a06c5657f74c112d380e6
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/14900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9442ad3575440cfd4516b2abf10d828c3e7f4563ece9cba3779de3af91f72c71
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df890a9858929be3792afa155b00cda5a7f2f1ad2da57bdc47ee420757ab7ae
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/15000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6eb773c804839bf9e4f2ad3e32662bbd1cbdebc9163fc763c2b122e007cfc16
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/15900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98bbb62aa911d31f959b75105c6566d0f44cee8fccadeaa7d4e29bd96e807040
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03051f7526a7a60d4269a7ce0c9ed5519171f7ebe345a22d7fbab25fe14b5dd7
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9a52becccf9d3f140f12882de257e014555c2905643e9267ccb1499601e966
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16100 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee977ad747de809e1e1348ef8c739394dc736152072bf65d8f00cfb8aa41da6
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16200 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a393d56ea5d3fbe2a2b2b86500f3c1c6b76f158516ec5179b7a0a396f62d9115
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16300 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d1edcda34a6db06c77f3c3762662a1e32549077db765d82c9e75dd021b0061
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16400 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d7c7108d4bc7a46b4f76322fcc210d272ceb8b4bc32954cb584c44ca34ece3
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c43006baf3cfed977c997b338e84312d9786deb306a931b6d8b78c526bf4f35
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae579c28e9989de0cc5e827b6c6423d021b152583b5845eed1bd7e7da3dac595
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/16900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bded8b3b076987a9d47f55c2cd4500d7849c8a6fbc7923de836f874040486036
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1700 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37bcbb588a2f5690817b438998cd874b578dec249d75eda25c6ede678f01c502
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/17000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69a7ad2c973b966a76ed4de866c3de5d3c8d64e598b40cff4e6c91e4783e6e2f
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/17500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe38c46d7f23ea57e771a5cf77babac9142fbed2c61adac1fb543751dcd6ede
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/17600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e6371e57f9dbb1cd9a9e066c601b68352fe7d912c1dab0f31c10d021f070c97
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/17900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02429f54e1e61420a3b26d8d6d5bda5ad5b89fcbba6667bf1239fe12d25e909c
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/1800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d4802c52e7dae212b31abee02e3afdbcc5d5656e233e802dae3c90123bb2d91
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/18000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d755810054df2eb94861d218b8de8c26550e09166dc587f0acdf2ed257a8b84f
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/18600 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d464529db611d108d5b742e40ef103d6ea505817a1229572179108b6396a0e02
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/18700 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61d4ea6a88aebd8335df82e132d71f56963469eefd93cad143fde8592148164a
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/18800 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd6ee1e06e2b7ce349ed7f3123458a34a00c8eb8cecfaf254243c3440e8587e1
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/models/18900 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408c6380f22f84da16a1b6ea5cb738a1a8b581bb53c136cf85bdea6833a7c8c6
3
+ size 1356936
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/tb_logs/interact/events.out.tfevents.1687078982.ML3090.333825.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78e3c61298eb55b57680acf6c2709f23ab89206e0bd516a20e2d8d5d0e3e0039
3
+ size 19386
ClassControl/Pendulum-v1/Test_Pendulum-v1_SAC_20230618-170302/tb_logs/policy/events.out.tfevents.1687078982.ML3090.333825.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb41e549f785f9607d6d8eedeb8ce1d9d22f585a85062d183fae14990a0098f2
3
+ size 5434566