Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
b480fb4
·
verified ·
1 Parent(s): d2bf88a

Sync policy_update945.state.json (fc924c00d1eb)

Browse files
Files changed (1) hide show
  1. ppo_v86/policy_update945.state.json +96 -0
ppo_v86/policy_update945.state.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint_schema_version": 2,
3
+ "hidden_reset_policy": "episode_done",
4
+ "update": 946,
5
+ "stage": 8,
6
+ "ent_scale": 1.0,
7
+ "lr_now": 0.0000681226312597656,
8
+ "total_env_steps": 2771968,
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
+ 0.0,
35
+ 0.0,
36
+ 0.0,
37
+ 1.0,
38
+ 0.0,
39
+ 1.0,
40
+ 0.0,
41
+ 0.0,
42
+ 0.0,
43
+ 0.0,
44
+ 0.0,
45
+ 0.0,
46
+ 0.0,
47
+ 0.0,
48
+ 0.0,
49
+ 0.0
50
+ ],
51
+ "recent_conversions": [
52
+ 0.0,
53
+ 0.0,
54
+ 0.0,
55
+ 0.0,
56
+ 1.0,
57
+ 0.0,
58
+ 1.0,
59
+ 0.0,
60
+ 0.0,
61
+ 0.0,
62
+ 0.0,
63
+ 0.0,
64
+ 1.0,
65
+ 0.0,
66
+ 1.0,
67
+ 0.0,
68
+ 0.0,
69
+ 0.0
70
+ ],
71
+ "best_eval_win": null,
72
+ "best_eval_score": null,
73
+ "v81_curriculum": true,
74
+ "curriculum_schedule": "v8.3",
75
+ "reward_profile": "v8.6-attack-fair-v1",
76
+ "return_stats": null,
77
+ "stage_env_targets": [
78
+ 24,
79
+ 24,
80
+ 24,
81
+ 24,
82
+ 24,
83
+ 24,
84
+ 16,
85
+ 12,
86
+ 10,
87
+ 12,
88
+ 10,
89
+ 8,
90
+ 8,
91
+ 8,
92
+ 8
93
+ ],
94
+ "envs_per_shard": 12,
95
+ "requested_env_target": null
96
+ }