Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
773e461
·
verified ·
1 Parent(s): 2e4eeaf

Sync curriculum_advance_u2552_s25_to_26.state.json (df9b6bafcc95)

Browse files
Files changed (1) hide show
  1. ppo_v11/curriculum_advance_u2552_s25_to_26.state.json +89 -0
ppo_v11/curriculum_advance_u2552_s25_to_26.state.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint_schema_version": 3,
3
+ "hidden_reset_policy": "episode_done",
4
+ "update": 2553,
5
+ "stage": 26,
6
+ "ent_scale": 1.0,
7
+ "lr_now": 0.00001,
8
+ "total_env_steps": 16745472,
9
+ "recent_wins": [],
10
+ "recent_conversions": [],
11
+ "recent_deaths": [],
12
+ "best_eval_win": null,
13
+ "best_eval_score": null,
14
+ "curriculum_schedule": "v10",
15
+ "reward_profile": "v10-anti-spiral-v1",
16
+ "return_stats": null,
17
+ "stage_env_targets": [
18
+ 24,
19
+ 24,
20
+ 24,
21
+ 24,
22
+ 24,
23
+ 24,
24
+ 24,
25
+ 24,
26
+ 24,
27
+ 24,
28
+ 24,
29
+ 24,
30
+ 24,
31
+ 24,
32
+ 24,
33
+ 24,
34
+ 24,
35
+ 24,
36
+ 24,
37
+ 24,
38
+ 24,
39
+ 24,
40
+ 24,
41
+ 24,
42
+ 24,
43
+ 24,
44
+ 24,
45
+ 24,
46
+ 20,
47
+ 20,
48
+ 20,
49
+ 16,
50
+ 16,
51
+ 16,
52
+ 12,
53
+ 12,
54
+ 10,
55
+ 10,
56
+ 10,
57
+ 10,
58
+ 10,
59
+ 10,
60
+ 10,
61
+ 10,
62
+ 10,
63
+ 10,
64
+ 10,
65
+ 10,
66
+ 10,
67
+ 10,
68
+ 8,
69
+ 8,
70
+ 8,
71
+ 8,
72
+ 8,
73
+ 8,
74
+ 8,
75
+ 8,
76
+ 8,
77
+ 8,
78
+ 8,
79
+ 8,
80
+ 8,
81
+ 8,
82
+ 8,
83
+ 8,
84
+ 8,
85
+ 8
86
+ ],
87
+ "envs_per_shard": 40,
88
+ "requested_env_target": null
89
+ }