gsc579 commited on
Commit
f9094e1
1 Parent(s): b179a57

Train_CartPole-v1_SoftQ

Browse files
Files changed (22) hide show
  1. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/config.yaml +49 -0
  2. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/logs/log.txt +284 -0
  3. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/1000 +3 -0
  4. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/1500 +3 -0
  5. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/2000 +3 -0
  6. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/2500 +3 -0
  7. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/3000 +3 -0
  8. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/3500 +3 -0
  9. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/4000 +3 -0
  10. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/4500 +3 -0
  11. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/500 +3 -0
  12. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/5000 +3 -0
  13. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/5500 +3 -0
  14. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/6000 +3 -0
  15. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/6500 +3 -0
  16. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/7000 +3 -0
  17. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/7500 +3 -0
  18. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/8000 +3 -0
  19. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/8500 +3 -0
  20. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/best +0 -0
  21. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/tb_logs/interact/events.out.tfevents.1688565198.LAPTOP-L4C8EI5B.11808.0 +3 -0
  22. ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/tb_logs/policy/events.out.tfevents.1688565198.LAPTOP-L4C8EI5B.11808.1 +3 -0
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/config.yaml ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ general_cfg:
2
+ algo_name: SoftQ
3
+ collect_traj: false
4
+ device: cpu
5
+ env_name: gym
6
+ interact_summary_fre: 1
7
+ load_checkpoint: false
8
+ load_model_step: best
9
+ load_path: Train_CartPole-v1_SoftQ_20230702-191520
10
+ max_episode: 200
11
+ max_step: 200
12
+ mode: train
13
+ model_save_fre: 500
14
+ model_summary_fre: 1
15
+ mp_backend: null
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
+ alpha: 4
24
+ batch_size: 128
25
+ buffer_size: 100000
26
+ buffer_type: REPLAY_QUE
27
+ epsilon_decay: 500
28
+ epsilon_end: 0.01
29
+ epsilon_start: 0.95
30
+ gamma: 0.95
31
+ lr: 0.0001
32
+ n_steps_per_learn: 1
33
+ target_update: 4
34
+ value_layers:
35
+ - activation: relu
36
+ layer_size:
37
+ - 256
38
+ layer_type: linear
39
+ - activation: relu
40
+ layer_size:
41
+ - 256
42
+ layer_type: linear
43
+ env_cfg:
44
+ id: CartPole-v1
45
+ ignore_params:
46
+ - wrapper
47
+ - ignore_params
48
+ render_mode: null
49
+ wrapper: null
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/logs/log.txt ADDED
@@ -0,0 +1,284 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - General Configs:
2
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================
3
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Name Value Type
4
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - env_name gym <class 'str'>
5
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - algo_name SoftQ <class 'str'>
6
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - mode train <class 'str'>
7
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - device cpu <class 'str'>
8
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - seed 1 <class 'int'>
9
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - max_episode 200 <class 'int'>
10
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - max_step 200 <class 'int'>
11
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
12
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - mp_backend None <class 'str'>
13
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - n_workers 2 <class 'int'>
14
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - n_learners 1 <class 'int'>
15
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
16
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
17
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'>
18
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - model_save_fre 500 <class 'int'>
19
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - load_checkpoint 0 <class 'bool'>
20
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - load_path Train_CartPole-v1_SoftQ_20230702-191520 <class 'str'>
21
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - load_model_step best <class 'str'>
22
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - interact_summary_fre 1 <class 'int'>
23
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - model_summary_fre 1 <class 'int'>
24
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================
25
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Algo Configs:
26
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================
27
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Name Value Type
28
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - epsilon_start 0.95 <class 'float'>
29
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - epsilon_end 0.01 <class 'float'>
30
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - epsilon_decay 500 <class 'int'>
31
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - gamma 0.95 <class 'float'>
32
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - lr 0.0001 <class 'float'>
33
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - buffer_type REPLAY_QUE <class 'str'>
34
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - buffer_size 100000 <class 'int'>
35
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - batch_size 128 <class 'int'>
36
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - alpha 4 <class 'int'>
37
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - target_update 4 <class 'int'>
38
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - value_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
39
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - n_steps_per_learn 1 <class 'int'>
40
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================
41
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Env Configs:
42
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================
43
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Name Value Type
44
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - id CartPole-v1 <class 'str'>
45
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - render_mode None <class 'str'>
46
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - wrapper None <class 'str'>
47
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
48
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - ================================================================================
49
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Start training!
50
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 1 with reward 12.000 in 12 steps
51
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 2 with reward 20.000 in 20 steps
52
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 3 with reward 11.000 in 11 steps
53
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 4 with reward 30.000 in 30 steps
54
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward 22.000 in 22 steps
55
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 6 with reward 12.000 in 12 steps
56
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 7 with reward 26.000 in 26 steps
57
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 8 with reward 33.000 in 33 steps
58
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 9 with reward 48.000 in 48 steps
59
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 10 with reward 32.000 in 32 steps
60
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 11 with reward 15.000 in 15 steps
61
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 12 with reward 14.000 in 14 steps
62
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 13 with reward 30.000 in 30 steps
63
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 14 with reward 25.000 in 25 steps
64
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 1 finished episode 15 with reward 11.000 in 11 steps
65
+ 2023-07-05 21:53:18 - SimpleLog - INFO: - Interactor 0 finished episode 16 with reward 16.000 in 16 steps
66
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 17 with reward 25.000 in 25 steps
67
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 18 with reward 27.000 in 27 steps
68
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 19 with reward 14.000 in 14 steps
69
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 20 with reward 42.000 in 42 steps
70
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 21 with reward 10.000 in 10 steps
71
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 22 with reward 40.000 in 40 steps
72
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 23 with reward 24.000 in 24 steps
73
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 24 with reward 19.000 in 19 steps
74
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 25 with reward 15.000 in 15 steps
75
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 26 with reward 27.000 in 27 steps
76
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 27 with reward 12.000 in 12 steps
77
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward 17.000 in 17 steps
78
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward 34.000 in 34 steps
79
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 30 with reward 10.000 in 10 steps
80
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 31 with reward 25.000 in 25 steps
81
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 32 with reward 11.000 in 11 steps
82
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 33 with reward 13.000 in 13 steps
83
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 34 with reward 44.000 in 44 steps
84
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 35 with reward 16.000 in 16 steps
85
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 36 with reward 19.000 in 19 steps
86
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 37 with reward 12.000 in 12 steps
87
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 38 with reward 15.000 in 15 steps
88
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 39 with reward 11.000 in 11 steps
89
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 40 with reward 16.000 in 16 steps
90
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 41 with reward 17.000 in 17 steps
91
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 42 with reward 10.000 in 10 steps
92
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 43 with reward 16.000 in 16 steps
93
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 0 finished episode 44 with reward 28.000 in 28 steps
94
+ 2023-07-05 21:53:19 - SimpleLog - INFO: - Interactor 1 finished episode 45 with reward 9.000 in 9 steps
95
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 46 with reward 19.000 in 19 steps
96
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 47 with reward 26.000 in 26 steps
97
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 48 with reward 9.000 in 9 steps
98
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 49 with reward 10.000 in 10 steps
99
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 50 with reward 18.000 in 18 steps
100
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 51 with reward 12.000 in 12 steps
101
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 52 with reward 14.000 in 14 steps
102
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 53 with reward 13.000 in 13 steps
103
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 54 with reward 21.000 in 21 steps
104
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 55 with reward 11.000 in 11 steps
105
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 56 with reward 17.000 in 17 steps
106
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 57 with reward 11.000 in 11 steps
107
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - update_step: 500, online_eval_reward: 9.000
108
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 9.000, save the best model!
109
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 58 with reward 21.000 in 21 steps
110
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 59 with reward 16.000 in 16 steps
111
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 60 with reward 42.000 in 42 steps
112
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 61 with reward 9.000 in 9 steps
113
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 62 with reward 14.000 in 14 steps
114
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 63 with reward 29.000 in 29 steps
115
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 64 with reward 16.000 in 16 steps
116
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 65 with reward 21.000 in 21 steps
117
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 66 with reward 24.000 in 24 steps
118
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 67 with reward 20.000 in 20 steps
119
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 68 with reward 12.000 in 12 steps
120
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 69 with reward 15.000 in 15 steps
121
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 70 with reward 27.000 in 27 steps
122
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 71 with reward 26.000 in 26 steps
123
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 72 with reward 23.000 in 23 steps
124
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 0 finished episode 73 with reward 22.000 in 22 steps
125
+ 2023-07-05 21:53:20 - SimpleLog - INFO: - Interactor 1 finished episode 74 with reward 18.000 in 18 steps
126
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 75 with reward 18.000 in 18 steps
127
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 76 with reward 17.000 in 17 steps
128
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 77 with reward 9.000 in 9 steps
129
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 78 with reward 28.000 in 28 steps
130
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 79 with reward 19.000 in 19 steps
131
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 80 with reward 39.000 in 39 steps
132
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 81 with reward 26.000 in 26 steps
133
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 82 with reward 53.000 in 53 steps
134
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 83 with reward 28.000 in 28 steps
135
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 84 with reward 12.000 in 12 steps
136
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 85 with reward 52.000 in 52 steps
137
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 86 with reward 20.000 in 20 steps
138
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 87 with reward 66.000 in 66 steps
139
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 88 with reward 22.000 in 22 steps
140
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 89 with reward 15.000 in 15 steps
141
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 1 finished episode 90 with reward 15.000 in 15 steps
142
+ 2023-07-05 21:53:21 - SimpleLog - INFO: - Interactor 0 finished episode 91 with reward 27.000 in 27 steps
143
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 92 with reward 49.000 in 49 steps
144
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 93 with reward 31.000 in 31 steps
145
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: 66.000
146
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 66.000, save the best model!
147
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 0 finished episode 94 with reward 96.000 in 96 steps
148
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 95 with reward 65.000 in 65 steps
149
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 0 finished episode 96 with reward 46.000 in 46 steps
150
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 97 with reward 33.000 in 33 steps
151
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 0 finished episode 98 with reward 25.000 in 25 steps
152
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 99 with reward 34.000 in 34 steps
153
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 0 finished episode 100 with reward 54.000 in 54 steps
154
+ 2023-07-05 21:53:22 - SimpleLog - INFO: - Interactor 1 finished episode 101 with reward 27.000 in 27 steps
155
+ 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 0 finished episode 102 with reward 36.000 in 36 steps
156
+ 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 1 finished episode 103 with reward 36.000 in 36 steps
157
+ 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 1 finished episode 104 with reward 37.000 in 37 steps
158
+ 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 1 finished episode 105 with reward 37.000 in 37 steps
159
+ 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 0 finished episode 106 with reward 107.000 in 107 steps
160
+ 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 1 finished episode 107 with reward 44.000 in 44 steps
161
+ 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 1 finished episode 108 with reward 99.000 in 99 steps
162
+ 2023-07-05 21:53:23 - SimpleLog - INFO: - Interactor 0 finished episode 109 with reward 118.000 in 118 steps
163
+ 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 1 finished episode 110 with reward 68.000 in 68 steps
164
+ 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 0 finished episode 111 with reward 75.000 in 75 steps
165
+ 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 1 finished episode 112 with reward 17.000 in 17 steps
166
+ 2023-07-05 21:53:24 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: 93.000
167
+ 2023-07-05 21:53:24 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 93.000, save the best model!
168
+ 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 0 finished episode 113 with reward 65.000 in 65 steps
169
+ 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 0 finished episode 114 with reward 33.000 in 33 steps
170
+ 2023-07-05 21:53:24 - SimpleLog - INFO: - Interactor 0 finished episode 115 with reward 40.000 in 40 steps
171
+ 2023-07-05 21:53:25 - SimpleLog - INFO: - Interactor 0 finished episode 116 with reward 57.000 in 57 steps
172
+ 2023-07-05 21:53:25 - SimpleLog - INFO: - Interactor 1 finished episode 117 with reward 200.000 in 200 steps
173
+ 2023-07-05 21:53:25 - SimpleLog - INFO: - Interactor 1 finished episode 118 with reward 75.000 in 75 steps
174
+ 2023-07-05 21:53:25 - SimpleLog - INFO: - Interactor 0 finished episode 119 with reward 91.000 in 91 steps
175
+ 2023-07-05 21:53:25 - SimpleLog - INFO: - Interactor 0 finished episode 120 with reward 47.000 in 47 steps
176
+ 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 0 finished episode 121 with reward 76.000 in 76 steps
177
+ 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 1 finished episode 122 with reward 127.000 in 127 steps
178
+ 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 0 finished episode 123 with reward 100.000 in 100 steps
179
+ 2023-07-05 21:53:26 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: 129.000
180
+ 2023-07-05 21:53:26 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 129.000, save the best model!
181
+ 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 0 finished episode 124 with reward 26.000 in 26 steps
182
+ 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 1 finished episode 125 with reward 146.000 in 146 steps
183
+ 2023-07-05 21:53:26 - SimpleLog - INFO: - Interactor 1 finished episode 126 with reward 39.000 in 39 steps
184
+ 2023-07-05 21:53:27 - SimpleLog - INFO: - Interactor 0 finished episode 127 with reward 84.000 in 84 steps
185
+ 2023-07-05 21:53:27 - SimpleLog - INFO: - Interactor 1 finished episode 128 with reward 80.000 in 80 steps
186
+ 2023-07-05 21:53:27 - SimpleLog - INFO: - Interactor 0 finished episode 129 with reward 116.000 in 116 steps
187
+ 2023-07-05 21:53:27 - SimpleLog - INFO: - Interactor 1 finished episode 130 with reward 124.000 in 124 steps
188
+ 2023-07-05 21:53:27 - SimpleLog - INFO: - Interactor 0 finished episode 131 with reward 75.000 in 75 steps
189
+ 2023-07-05 21:53:28 - SimpleLog - INFO: - Interactor 1 finished episode 132 with reward 68.000 in 68 steps
190
+ 2023-07-05 21:53:28 - SimpleLog - INFO: - Interactor 0 finished episode 133 with reward 89.000 in 89 steps
191
+ 2023-07-05 21:53:28 - SimpleLog - INFO: - Interactor 1 finished episode 134 with reward 121.000 in 121 steps
192
+ 2023-07-05 21:53:28 - SimpleLog - INFO: - Interactor 0 finished episode 135 with reward 129.000 in 129 steps
193
+ 2023-07-05 21:53:28 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: 168.000
194
+ 2023-07-05 21:53:28 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 168.000, save the best model!
195
+ 2023-07-05 21:53:29 - SimpleLog - INFO: - Interactor 1 finished episode 136 with reward 90.000 in 90 steps
196
+ 2023-07-05 21:53:29 - SimpleLog - INFO: - Interactor 0 finished episode 137 with reward 77.000 in 77 steps
197
+ 2023-07-05 21:53:29 - SimpleLog - INFO: - Interactor 1 finished episode 138 with reward 188.000 in 188 steps
198
+ 2023-07-05 21:53:29 - SimpleLog - INFO: - Interactor 0 finished episode 139 with reward 200.000 in 200 steps
199
+ 2023-07-05 21:53:30 - SimpleLog - INFO: - Interactor 1 finished episode 140 with reward 200.000 in 200 steps
200
+ 2023-07-05 21:53:30 - SimpleLog - INFO: - Interactor 0 finished episode 141 with reward 200.000 in 200 steps
201
+ 2023-07-05 21:53:30 - SimpleLog - INFO: - Interactor 1 finished episode 142 with reward 49.000 in 49 steps
202
+ 2023-07-05 21:53:31 - SimpleLog - INFO: - update_step: 3000, online_eval_reward: 200.000
203
+ 2023-07-05 21:53:31 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
204
+ 2023-07-05 21:53:31 - SimpleLog - INFO: - Interactor 0 finished episode 143 with reward 200.000 in 200 steps
205
+ 2023-07-05 21:53:31 - SimpleLog - INFO: - Interactor 1 finished episode 144 with reward 195.000 in 195 steps
206
+ 2023-07-05 21:53:32 - SimpleLog - INFO: - Interactor 0 finished episode 145 with reward 200.000 in 200 steps
207
+ 2023-07-05 21:53:32 - SimpleLog - INFO: - Interactor 1 finished episode 146 with reward 200.000 in 200 steps
208
+ 2023-07-05 21:53:33 - SimpleLog - INFO: - update_step: 3500, online_eval_reward: 200.000
209
+ 2023-07-05 21:53:33 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
210
+ 2023-07-05 21:53:33 - SimpleLog - INFO: - Interactor 1 finished episode 147 with reward 167.000 in 167 steps
211
+ 2023-07-05 21:53:33 - SimpleLog - INFO: - Interactor 0 finished episode 148 with reward 200.000 in 200 steps
212
+ 2023-07-05 21:53:34 - SimpleLog - INFO: - Interactor 1 finished episode 149 with reward 133.000 in 133 steps
213
+ 2023-07-05 21:53:34 - SimpleLog - INFO: - Interactor 0 finished episode 150 with reward 135.000 in 135 steps
214
+ 2023-07-05 21:53:34 - SimpleLog - INFO: - Interactor 1 finished episode 151 with reward 200.000 in 200 steps
215
+ 2023-07-05 21:53:35 - SimpleLog - INFO: - Interactor 0 finished episode 152 with reward 200.000 in 200 steps
216
+ 2023-07-05 21:53:35 - SimpleLog - INFO: - update_step: 4000, online_eval_reward: 200.000
217
+ 2023-07-05 21:53:35 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
218
+ 2023-07-05 21:53:35 - SimpleLog - INFO: - Interactor 1 finished episode 153 with reward 129.000 in 129 steps
219
+ 2023-07-05 21:53:35 - SimpleLog - INFO: - Interactor 0 finished episode 154 with reward 114.000 in 114 steps
220
+ 2023-07-05 21:53:36 - SimpleLog - INFO: - Interactor 0 finished episode 155 with reward 143.000 in 143 steps
221
+ 2023-07-05 21:53:36 - SimpleLog - INFO: - Interactor 1 finished episode 156 with reward 200.000 in 200 steps
222
+ 2023-07-05 21:53:37 - SimpleLog - INFO: - Interactor 0 finished episode 157 with reward 200.000 in 200 steps
223
+ 2023-07-05 21:53:37 - SimpleLog - INFO: - Interactor 1 finished episode 158 with reward 200.000 in 200 steps
224
+ 2023-07-05 21:53:38 - SimpleLog - INFO: - update_step: 4500, online_eval_reward: 200.000
225
+ 2023-07-05 21:53:38 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
226
+ 2023-07-05 21:53:38 - SimpleLog - INFO: - Interactor 0 finished episode 159 with reward 200.000 in 200 steps
227
+ 2023-07-05 21:53:38 - SimpleLog - INFO: - Interactor 1 finished episode 160 with reward 200.000 in 200 steps
228
+ 2023-07-05 21:53:39 - SimpleLog - INFO: - Interactor 0 finished episode 161 with reward 200.000 in 200 steps
229
+ 2023-07-05 21:53:39 - SimpleLog - INFO: - Interactor 1 finished episode 162 with reward 200.000 in 200 steps
230
+ 2023-07-05 21:53:39 - SimpleLog - INFO: - Interactor 0 finished episode 163 with reward 200.000 in 200 steps
231
+ 2023-07-05 21:53:40 - SimpleLog - INFO: - update_step: 5000, online_eval_reward: 200.000
232
+ 2023-07-05 21:53:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
233
+ 2023-07-05 21:53:40 - SimpleLog - INFO: - Interactor 1 finished episode 164 with reward 200.000 in 200 steps
234
+ 2023-07-05 21:53:41 - SimpleLog - INFO: - Interactor 0 finished episode 165 with reward 181.000 in 181 steps
235
+ 2023-07-05 21:53:41 - SimpleLog - INFO: - Interactor 1 finished episode 166 with reward 200.000 in 200 steps
236
+ 2023-07-05 21:53:41 - SimpleLog - INFO: - Interactor 0 finished episode 167 with reward 200.000 in 200 steps
237
+ 2023-07-05 21:53:42 - SimpleLog - INFO: - Interactor 1 finished episode 168 with reward 200.000 in 200 steps
238
+ 2023-07-05 21:53:42 - SimpleLog - INFO: - update_step: 5500, online_eval_reward: 200.000
239
+ 2023-07-05 21:53:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
240
+ 2023-07-05 21:53:42 - SimpleLog - INFO: - Interactor 0 finished episode 169 with reward 200.000 in 200 steps
241
+ 2023-07-05 21:53:43 - SimpleLog - INFO: - Interactor 1 finished episode 170 with reward 200.000 in 200 steps
242
+ 2023-07-05 21:53:43 - SimpleLog - INFO: - Interactor 0 finished episode 171 with reward 200.000 in 200 steps
243
+ 2023-07-05 21:53:43 - SimpleLog - INFO: - Interactor 1 finished episode 172 with reward 200.000 in 200 steps
244
+ 2023-07-05 21:53:44 - SimpleLog - INFO: - Interactor 0 finished episode 173 with reward 200.000 in 200 steps
245
+ 2023-07-05 21:53:44 - SimpleLog - INFO: - update_step: 6000, online_eval_reward: 200.000
246
+ 2023-07-05 21:53:44 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
247
+ 2023-07-05 21:53:44 - SimpleLog - INFO: - Interactor 1 finished episode 174 with reward 200.000 in 200 steps
248
+ 2023-07-05 21:53:45 - SimpleLog - INFO: - Interactor 0 finished episode 175 with reward 200.000 in 200 steps
249
+ 2023-07-05 21:53:45 - SimpleLog - INFO: - Interactor 1 finished episode 176 with reward 167.000 in 167 steps
250
+ 2023-07-05 21:53:46 - SimpleLog - INFO: - Interactor 0 finished episode 177 with reward 200.000 in 200 steps
251
+ 2023-07-05 21:53:46 - SimpleLog - INFO: - Interactor 1 finished episode 178 with reward 200.000 in 200 steps
252
+ 2023-07-05 21:53:47 - SimpleLog - INFO: - update_step: 6500, online_eval_reward: 200.000
253
+ 2023-07-05 21:53:47 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
254
+ 2023-07-05 21:53:47 - SimpleLog - INFO: - Interactor 0 finished episode 179 with reward 200.000 in 200 steps
255
+ 2023-07-05 21:53:47 - SimpleLog - INFO: - Interactor 1 finished episode 180 with reward 200.000 in 200 steps
256
+ 2023-07-05 21:53:48 - SimpleLog - INFO: - Interactor 0 finished episode 181 with reward 200.000 in 200 steps
257
+ 2023-07-05 21:53:48 - SimpleLog - INFO: - Interactor 1 finished episode 182 with reward 200.000 in 200 steps
258
+ 2023-07-05 21:53:48 - SimpleLog - INFO: - Interactor 0 finished episode 183 with reward 200.000 in 200 steps
259
+ 2023-07-05 21:53:49 - SimpleLog - INFO: - Interactor 1 finished episode 184 with reward 200.000 in 200 steps
260
+ 2023-07-05 21:53:49 - SimpleLog - INFO: - update_step: 7000, online_eval_reward: 200.000
261
+ 2023-07-05 21:53:49 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
262
+ 2023-07-05 21:53:50 - SimpleLog - INFO: - Interactor 0 finished episode 185 with reward 200.000 in 200 steps
263
+ 2023-07-05 21:53:50 - SimpleLog - INFO: - Interactor 1 finished episode 186 with reward 200.000 in 200 steps
264
+ 2023-07-05 21:53:51 - SimpleLog - INFO: - Interactor 0 finished episode 187 with reward 200.000 in 200 steps
265
+ 2023-07-05 21:53:51 - SimpleLog - INFO: - Interactor 1 finished episode 188 with reward 200.000 in 200 steps
266
+ 2023-07-05 21:53:51 - SimpleLog - INFO: - update_step: 7500, online_eval_reward: 200.000
267
+ 2023-07-05 21:53:51 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
268
+ 2023-07-05 21:53:52 - SimpleLog - INFO: - Interactor 0 finished episode 189 with reward 200.000 in 200 steps
269
+ 2023-07-05 21:53:52 - SimpleLog - INFO: - Interactor 1 finished episode 190 with reward 200.000 in 200 steps
270
+ 2023-07-05 21:53:52 - SimpleLog - INFO: - Interactor 0 finished episode 191 with reward 200.000 in 200 steps
271
+ 2023-07-05 21:53:53 - SimpleLog - INFO: - Interactor 1 finished episode 192 with reward 200.000 in 200 steps
272
+ 2023-07-05 21:53:53 - SimpleLog - INFO: - Interactor 0 finished episode 193 with reward 200.000 in 200 steps
273
+ 2023-07-05 21:53:53 - SimpleLog - INFO: - Interactor 1 finished episode 194 with reward 200.000 in 200 steps
274
+ 2023-07-05 21:53:54 - SimpleLog - INFO: - update_step: 8000, online_eval_reward: 200.000
275
+ 2023-07-05 21:53:54 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
276
+ 2023-07-05 21:53:54 - SimpleLog - INFO: - Interactor 0 finished episode 195 with reward 200.000 in 200 steps
277
+ 2023-07-05 21:53:55 - SimpleLog - INFO: - Interactor 1 finished episode 196 with reward 200.000 in 200 steps
278
+ 2023-07-05 21:53:55 - SimpleLog - INFO: - Interactor 0 finished episode 197 with reward 200.000 in 200 steps
279
+ 2023-07-05 21:53:55 - SimpleLog - INFO: - Interactor 1 finished episode 198 with reward 200.000 in 200 steps
280
+ 2023-07-05 21:53:56 - SimpleLog - INFO: - update_step: 8500, online_eval_reward: 200.000
281
+ 2023-07-05 21:53:56 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
282
+ 2023-07-05 21:53:57 - SimpleLog - INFO: - Interactor 0 finished episode 199 with reward 200.000 in 200 steps
283
+ 2023-07-05 21:53:57 - SimpleLog - INFO: - Interactor 1 finished episode 200 with reward 200.000 in 200 steps
284
+ 2023-07-05 21:53:57 - SimpleLog - INFO: - Finish training! Time cost: 38.512 s
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/1000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b64c2855d8d931637913e414d58ba62809839c0ea7d5b5a8961c6023ca2946a
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/1500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e1253be4612f3f001d626e93a915304b2a6173c7a628ec700c2ad68ea8b2232
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/2000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6159cba88bf3e65ca3cddf47e3b83f9d9eb7902bcd25fb3627d42adebfa2ac1
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/2500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d0a013855361ad9a9cac08c640432811774666ee8f86494168b77475ba707f
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/3000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c20204fdc7bdf90a40fe9a630524253ac13d4a50f91b0d7814f14134c0865ae0
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/3500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c55b028850273939ba2a70c31d90c2171bca89198d65e9e37a07f4c42b640b1
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/4000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:598d72511fd18ca05d5b0e18c58d6ba1234ae28bd29a88e17e4fb93c1d5cb03a
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/4500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928318c42b9708c5b4c4caa92953275e9bf7ca994ce04d84f02a6527ce25cfc8
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455f990e87ec78a5ae8e846367a11a57c37e5a325512294d2a7b9028960cd98a
3
+ size 544713
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/5000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc538822f80548006913284753a33af1ba2d9af5905d3a337915b26e57a81f1d
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/5500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c8d7353ecc69d2889d9ac1ccee56a575da8e4840d187b2e0ca15b4edfd7dd8
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/6000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddff61fd3cafc95fb2a86a6dedf3f669e17d688fe7253c3f896e52bc9e799d67
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/6500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe0138a29dbcb6dd2cb70aac9f2874643e8b0b50b6114b8fb5662a134cde9b08
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/7000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03d5302026c5a8052efc744d7e96abcb9d78c01ef3b3a9ba571a4f4bd6637981
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/7500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d88bf981e21fde94707a25f7962bd1442bde258f828cce1fd3f1cc5f2de8c6
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/8000 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39f1dcb7fcc9634bc4ab0e1c93f48aaabfc9f775c0a966e35de9b281c9ca118
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/8500 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ab4d93045965e2fbc69fc18bd558c0aac8b3b67caa4fd9ac27356a795664fd6
3
+ size 544727
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/models/best ADDED
Binary file (545 kB). View file
 
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/tb_logs/interact/events.out.tfevents.1688565198.LAPTOP-L4C8EI5B.11808.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ccb627b3c3a8669e4b585c22bbe3db305d21e6ed78e877ed943ae534ca8db7
3
+ size 19834
ClassControl/CartPole-v1/Train_CartPole-v1_SoftQ_20230705-215318/tb_logs/policy/events.out.tfevents.1688565198.LAPTOP-L4C8EI5B.11808.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ae98a4b34d8a2ce34b2a974c4ab1b51025ca83a7444ad7fb07e8b9d4b172b25
3
+ size 421158