Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
2eff9ce
·
verified ·
1 Parent(s): 3466ba5

Sync policy_update2540.state.json (42f557e75af2)

Browse files
Files changed (1) hide show
  1. ppo_v11/policy_update2540.state.json +180 -0
ppo_v11/policy_update2540.state.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint_schema_version": 3,
3
+ "hidden_reset_policy": "episode_done",
4
+ "update": 2541,
5
+ "stage": 25,
6
+ "ent_scale": 1.0,
7
+ "lr_now": 0.00001,
8
+ "total_env_steps": 16660992,
9
+ "recent_wins": [
10
+ 0.0,
11
+ 0.0,
12
+ 1.0,
13
+ 1.0,
14
+ 0.0,
15
+ 1.0,
16
+ 0.0,
17
+ 0.0,
18
+ 1.0,
19
+ 0.0,
20
+ 0.0,
21
+ 0.0,
22
+ 1.0,
23
+ 0.0,
24
+ 0.0,
25
+ 1.0,
26
+ 0.0,
27
+ 0.0,
28
+ 0.0,
29
+ 1.0,
30
+ 1.0,
31
+ 0.0,
32
+ 0.0,
33
+ 0.0,
34
+ 1.0,
35
+ 1.0,
36
+ 0.0,
37
+ 0.0,
38
+ 1.0,
39
+ 0.0,
40
+ 1.0,
41
+ 0.0,
42
+ 0.0,
43
+ 0.0,
44
+ 0.0
45
+ ],
46
+ "recent_conversions": [
47
+ 1.0,
48
+ 1.0,
49
+ 1.0,
50
+ 1.0,
51
+ 1.0,
52
+ 1.0,
53
+ 0.0,
54
+ 1.0,
55
+ 1.0,
56
+ 0.0,
57
+ 1.0,
58
+ 1.0,
59
+ 0.0,
60
+ 0.0,
61
+ 1.0,
62
+ 0.0,
63
+ 1.0,
64
+ 0.0
65
+ ],
66
+ "recent_deaths": [
67
+ 1.0,
68
+ 0.0,
69
+ 0.0,
70
+ 0.0,
71
+ 1.0,
72
+ 0.0,
73
+ 0.0,
74
+ 1.0,
75
+ 0.0,
76
+ 1.0,
77
+ 0.0,
78
+ 1.0,
79
+ 0.0,
80
+ 1.0,
81
+ 1.0,
82
+ 0.0,
83
+ 0.0,
84
+ 1.0,
85
+ 0.0,
86
+ 0.0,
87
+ 0.0,
88
+ 1.0,
89
+ 0.0,
90
+ 1.0,
91
+ 0.0,
92
+ 0.0,
93
+ 0.0,
94
+ 0.0,
95
+ 0.0,
96
+ 0.0,
97
+ 0.0,
98
+ 1.0,
99
+ 1.0,
100
+ 1.0,
101
+ 0.0
102
+ ],
103
+ "best_eval_win": null,
104
+ "best_eval_score": null,
105
+ "curriculum_schedule": "v10",
106
+ "reward_profile": "v10-anti-spiral-v1",
107
+ "return_stats": null,
108
+ "stage_env_targets": [
109
+ 24,
110
+ 24,
111
+ 24,
112
+ 24,
113
+ 24,
114
+ 24,
115
+ 24,
116
+ 24,
117
+ 24,
118
+ 24,
119
+ 24,
120
+ 24,
121
+ 24,
122
+ 24,
123
+ 24,
124
+ 24,
125
+ 24,
126
+ 24,
127
+ 24,
128
+ 24,
129
+ 24,
130
+ 24,
131
+ 24,
132
+ 24,
133
+ 24,
134
+ 24,
135
+ 24,
136
+ 24,
137
+ 20,
138
+ 20,
139
+ 20,
140
+ 16,
141
+ 16,
142
+ 16,
143
+ 12,
144
+ 12,
145
+ 10,
146
+ 10,
147
+ 10,
148
+ 10,
149
+ 10,
150
+ 10,
151
+ 10,
152
+ 10,
153
+ 10,
154
+ 10,
155
+ 10,
156
+ 10,
157
+ 10,
158
+ 10,
159
+ 8,
160
+ 8,
161
+ 8,
162
+ 8,
163
+ 8,
164
+ 8,
165
+ 8,
166
+ 8,
167
+ 8,
168
+ 8,
169
+ 8,
170
+ 8,
171
+ 8,
172
+ 8,
173
+ 8,
174
+ 8,
175
+ 8,
176
+ 8
177
+ ],
178
+ "envs_per_shard": 40,
179
+ "requested_env_target": null
180
+ }