Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
df58677
·
verified ·
1 Parent(s): 6991f0b

Sync policy_update345.state.json (50daea7df607)

Browse files
Files changed (1) hide show
  1. ppo_v83/policy_update345.state.json +102 -0
ppo_v83/policy_update345.state.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint_schema_version": 2,
3
+ "hidden_reset_policy": "episode_done",
4
+ "update": 346,
5
+ "stage": 6,
6
+ "ent_scale": 1.0,
7
+ "lr_now": 0.00009428737890624998,
8
+ "total_env_steps": 749568,
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
+ 1.0,
29
+ 0.0,
30
+ 1.0,
31
+ 0.0,
32
+ 1.0,
33
+ 1.0,
34
+ 0.0,
35
+ 0.0,
36
+ 0.0,
37
+ 1.0,
38
+ 0.0,
39
+ 1.0,
40
+ 0.0,
41
+ 1.0,
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
+ 1.0,
53
+ 1.0,
54
+ 1.0,
55
+ 1.0,
56
+ 1.0,
57
+ 1.0,
58
+ 1.0,
59
+ 1.0,
60
+ 0.0,
61
+ 0.0,
62
+ 0.0,
63
+ 0.0,
64
+ 0.0,
65
+ 0.0,
66
+ 0.0,
67
+ 1.0,
68
+ 1.0,
69
+ 1.0,
70
+ 1.0,
71
+ 1.0,
72
+ 1.0,
73
+ 1.0,
74
+ 1.0,
75
+ 1.0
76
+ ],
77
+ "best_eval_win": null,
78
+ "best_eval_score": null,
79
+ "v81_curriculum": true,
80
+ "curriculum_schedule": "v8.3",
81
+ "reward_profile": "v8.3-closeout-v1",
82
+ "return_stats": null,
83
+ "stage_env_targets": [
84
+ 24,
85
+ 24,
86
+ 24,
87
+ 24,
88
+ 24,
89
+ 24,
90
+ 16,
91
+ 12,
92
+ 10,
93
+ 12,
94
+ 10,
95
+ 8,
96
+ 8,
97
+ 8,
98
+ 8
99
+ ],
100
+ "envs_per_shard": 16,
101
+ "requested_env_target": null
102
+ }