Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
fa53bf9
·
verified ·
1 Parent(s): fc4f331

Sync latest.state.json (274c091633e5)

Browse files
Files changed (1) hide show
  1. ppo_v84/latest.state.json +12 -8
ppo_v84/latest.state.json CHANGED
@@ -1,51 +1,51 @@
1
  {
2
  "checkpoint_schema_version": 2,
3
  "hidden_reset_policy": "episode_done",
4
- "update": 496,
5
  "stage": 8,
6
  "ent_scale": 1.0,
7
  "lr_now": 0.0000681226312597656,
8
- "total_env_steps": 1143296,
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
  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
- 0.0,
37
  0.0,
38
  0.0,
39
  0.0,
40
- 1.0,
41
  0.0,
42
  0.0,
43
  0.0,
 
44
  0.0,
45
  0.0,
46
- 1.0,
47
  0.0,
48
- 1.0,
49
  0.0
50
  ],
51
  "recent_conversions": [
@@ -75,6 +75,10 @@
75
  1.0,
76
  0.0,
77
  1.0,
 
 
 
 
78
  1.0
79
  ],
80
  "best_eval_win": null,
 
1
  {
2
  "checkpoint_schema_version": 2,
3
  "hidden_reset_policy": "episode_done",
4
+ "update": 501,
5
  "stage": 8,
6
  "ent_scale": 1.0,
7
  "lr_now": 0.0000681226312597656,
8
+ "total_env_steps": 1156096,
9
  "recent_wins": [
10
  0.0,
11
  0.0,
12
  0.0,
13
  0.0,
14
  0.0,
15
+ 1.0,
16
  0.0,
17
  0.0,
18
  0.0,
19
  0.0,
20
  0.0,
21
+ 1.0,
22
  0.0,
23
  0.0,
24
  0.0,
25
  0.0,
26
  0.0,
27
+ 1.0,
28
  0.0,
29
+ 1.0,
30
  0.0,
31
  0.0,
32
+ 1.0,
33
  0.0,
34
  0.0,
35
  0.0,
36
  0.0,
37
  0.0,
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
  0.0,
 
49
  0.0
50
  ],
51
  "recent_conversions": [
 
75
  1.0,
76
  0.0,
77
  1.0,
78
+ 1.0,
79
+ 1.0,
80
+ 0.0,
81
+ 0.0,
82
  1.0
83
  ],
84
  "best_eval_win": null,