Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
4ad016e
·
verified ·
1 Parent(s): 75b6955

Sync policy_update11625.state.json (54f02e3aa9db)

Browse files
Files changed (1) hide show
  1. ppo_v10/policy_update11625.state.json +163 -0
ppo_v10/policy_update11625.state.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint_schema_version": 2,
3
+ "hidden_reset_policy": "episode_done",
4
+ "update": 11626,
5
+ "stage": 13,
6
+ "ent_scale": 5.0,
7
+ "lr_now": 0.00003022637339143656,
8
+ "total_env_steps": 40936448,
9
+ "recent_wins": [
10
+ 1.0,
11
+ 1.0,
12
+ 1.0,
13
+ 1.0,
14
+ 1.0,
15
+ 1.0,
16
+ 1.0,
17
+ 1.0,
18
+ 1.0,
19
+ 1.0,
20
+ 1.0,
21
+ 1.0,
22
+ 1.0
23
+ ],
24
+ "recent_conversions": [
25
+ 1.0,
26
+ 1.0,
27
+ 1.0,
28
+ 1.0,
29
+ 1.0,
30
+ 1.0,
31
+ 1.0,
32
+ 1.0,
33
+ 1.0,
34
+ 1.0,
35
+ 1.0,
36
+ 1.0,
37
+ 1.0
38
+ ],
39
+ "recent_deaths": [
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
+ 0.0,
51
+ 0.0,
52
+ 0.0
53
+ ],
54
+ "best_eval_win": null,
55
+ "best_eval_score": null,
56
+ "curriculum_schedule": "v10",
57
+ "reward_profile": "v10-anti-spiral-v1",
58
+ "return_stats": null,
59
+ "stage_env_targets": [
60
+ 24,
61
+ 24,
62
+ 24,
63
+ 24,
64
+ 24,
65
+ 24,
66
+ 24,
67
+ 24,
68
+ 24,
69
+ 24,
70
+ 24,
71
+ 24,
72
+ 24,
73
+ 24,
74
+ 24,
75
+ 24,
76
+ 24,
77
+ 24,
78
+ 24,
79
+ 24,
80
+ 24,
81
+ 24,
82
+ 24,
83
+ 24,
84
+ 24,
85
+ 24,
86
+ 24,
87
+ 24,
88
+ 24,
89
+ 24,
90
+ 24,
91
+ 24,
92
+ 24,
93
+ 24,
94
+ 24,
95
+ 24,
96
+ 24,
97
+ 24,
98
+ 24,
99
+ 24,
100
+ 24,
101
+ 24,
102
+ 24,
103
+ 24,
104
+ 24,
105
+ 24,
106
+ 20,
107
+ 20,
108
+ 20,
109
+ 20,
110
+ 20,
111
+ 20,
112
+ 20,
113
+ 20,
114
+ 16,
115
+ 16,
116
+ 16,
117
+ 16,
118
+ 12,
119
+ 12,
120
+ 12,
121
+ 12,
122
+ 12,
123
+ 12,
124
+ 12,
125
+ 12,
126
+ 12,
127
+ 12,
128
+ 10,
129
+ 10,
130
+ 10,
131
+ 10,
132
+ 10,
133
+ 10,
134
+ 10,
135
+ 10,
136
+ 10,
137
+ 10,
138
+ 10,
139
+ 10,
140
+ 10,
141
+ 10,
142
+ 8,
143
+ 8,
144
+ 8,
145
+ 8,
146
+ 8,
147
+ 8,
148
+ 8,
149
+ 8,
150
+ 8,
151
+ 8,
152
+ 8,
153
+ 8,
154
+ 8,
155
+ 8,
156
+ 8,
157
+ 8,
158
+ 8,
159
+ 8
160
+ ],
161
+ "envs_per_shard": 14,
162
+ "requested_env_target": null
163
+ }