Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
b501460
·
verified ·
1 Parent(s): 4a4ae5a

Sync latest.state.json (2e5863e6cf97)

Browse files
Files changed (1) hide show
  1. ppo_v82/latest.state.json +9 -9
ppo_v82/latest.state.json CHANGED
@@ -1,52 +1,52 @@
1
  {
2
  "checkpoint_schema_version": 2,
3
  "hidden_reset_policy": "episode_done",
4
- "update": 151,
5
  "stage": 5,
6
  "ent_scale": 1.0,
7
  "lr_now": 0.00025,
8
- "total_env_steps": 309248,
9
  "recent_wins": [
10
  0.0,
11
  0.0,
12
  0.0,
13
  0.0,
14
- 1.0,
15
  0.0,
16
- 1.0,
17
  0.0,
18
  0.0,
19
  0.0,
20
- 1.0,
21
  0.0,
22
  0.0,
23
  0.0,
24
  0.0,
 
 
 
25
  0.0,
26
  0.0,
27
  0.0,
28
  0.0,
29
  0.0,
 
30
  0.0,
31
  0.0,
32
  0.0,
33
  0.0,
34
  1.0,
35
- 0.0,
36
  1.0,
37
  0.0,
38
  0.0,
39
  0.0,
40
  0.0,
41
  0.0,
42
- 1.0,
43
  0.0,
44
  0.0,
 
45
  0.0,
46
  0.0,
47
  1.0,
48
- 1.0,
49
- 1.0
50
  ],
51
  "best_eval_win": null,
52
  "best_eval_score": null,
 
1
  {
2
  "checkpoint_schema_version": 2,
3
  "hidden_reset_policy": "episode_done",
4
+ "update": 156,
5
  "stage": 5,
6
  "ent_scale": 1.0,
7
  "lr_now": 0.00025,
8
+ "total_env_steps": 319488,
9
  "recent_wins": [
10
  0.0,
11
  0.0,
12
  0.0,
13
  0.0,
 
14
  0.0,
 
15
  0.0,
16
  0.0,
17
  0.0,
 
18
  0.0,
19
  0.0,
20
  0.0,
21
  0.0,
22
+ 1.0,
23
+ 0.0,
24
+ 1.0,
25
  0.0,
26
  0.0,
27
  0.0,
28
  0.0,
29
  0.0,
30
+ 1.0,
31
  0.0,
32
  0.0,
33
  0.0,
34
  0.0,
35
  1.0,
36
+ 1.0,
37
  1.0,
38
  0.0,
39
  0.0,
40
  0.0,
41
  0.0,
42
  0.0,
 
43
  0.0,
44
  0.0,
45
+ 1.0,
46
  0.0,
47
  0.0,
48
  1.0,
49
+ 0.0
 
50
  ],
51
  "best_eval_win": null,
52
  "best_eval_score": null,