Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
415a171
·
verified ·
1 Parent(s): 1a9506a

Sync policy_update45.state.json (86f941d98d58)

Browse files
Files changed (1) hide show
  1. ppo_v11/policy_update45.state.json +244 -0
ppo_v11/policy_update45.state.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint_schema_version": 3,
3
+ "hidden_reset_policy": "episode_done",
4
+ "update": 46,
5
+ "stage": 0,
6
+ "ent_scale": 1.0,
7
+ "lr_now": 0.00025,
8
+ "total_env_steps": 141312,
9
+ "recent_wins": [
10
+ 1.0,
11
+ 0.0,
12
+ 1.0,
13
+ 0.0,
14
+ 0.0,
15
+ 1.0,
16
+ 0.0,
17
+ 1.0,
18
+ 0.0,
19
+ 1.0,
20
+ 0.0,
21
+ 1.0,
22
+ 1.0,
23
+ 0.0,
24
+ 0.0,
25
+ 0.0,
26
+ 1.0,
27
+ 0.0,
28
+ 1.0,
29
+ 0.0,
30
+ 0.0,
31
+ 1.0,
32
+ 0.0,
33
+ 0.0,
34
+ 0.0,
35
+ 0.0,
36
+ 0.0,
37
+ 0.0,
38
+ 0.0,
39
+ 0.0,
40
+ 0.0,
41
+ 0.0,
42
+ 1.0,
43
+ 0.0,
44
+ 0.0,
45
+ 1.0,
46
+ 1.0,
47
+ 1.0,
48
+ 0.0,
49
+ 1.0
50
+ ],
51
+ "recent_conversions": [
52
+ 0.0,
53
+ 1.0,
54
+ 1.0,
55
+ 0.0,
56
+ 0.0,
57
+ 1.0,
58
+ 0.0,
59
+ 1.0,
60
+ 1.0,
61
+ 1.0,
62
+ 0.0,
63
+ 1.0,
64
+ 0.0,
65
+ 1.0,
66
+ 0.0,
67
+ 1.0,
68
+ 1.0,
69
+ 1.0,
70
+ 0.0,
71
+ 0.0,
72
+ 1.0,
73
+ 1.0,
74
+ 1.0,
75
+ 1.0,
76
+ 1.0,
77
+ 1.0,
78
+ 1.0,
79
+ 0.0,
80
+ 1.0,
81
+ 0.0,
82
+ 0.0,
83
+ 0.0,
84
+ 0.0,
85
+ 0.0,
86
+ 1.0,
87
+ 0.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0
92
+ ],
93
+ "recent_deaths": [
94
+ 0.0,
95
+ 1.0,
96
+ 0.0,
97
+ 0.0,
98
+ 0.0,
99
+ 0.0,
100
+ 0.0,
101
+ 0.0,
102
+ 0.0,
103
+ 0.0,
104
+ 1.0,
105
+ 0.0,
106
+ 0.0,
107
+ 0.0,
108
+ 0.0,
109
+ 1.0,
110
+ 0.0,
111
+ 1.0,
112
+ 0.0,
113
+ 1.0,
114
+ 1.0,
115
+ 0.0,
116
+ 0.0,
117
+ 0.0,
118
+ 0.0,
119
+ 0.0,
120
+ 0.0,
121
+ 1.0,
122
+ 1.0,
123
+ 0.0,
124
+ 0.0,
125
+ 0.0,
126
+ 0.0,
127
+ 0.0,
128
+ 1.0,
129
+ 0.0,
130
+ 0.0,
131
+ 0.0,
132
+ 0.0,
133
+ 0.0
134
+ ],
135
+ "best_eval_win": null,
136
+ "best_eval_score": null,
137
+ "curriculum_schedule": "v10",
138
+ "reward_profile": "v10-anti-spiral-v1",
139
+ "return_stats": null,
140
+ "stage_env_targets": [
141
+ 24,
142
+ 24,
143
+ 24,
144
+ 24,
145
+ 24,
146
+ 24,
147
+ 24,
148
+ 24,
149
+ 24,
150
+ 24,
151
+ 24,
152
+ 24,
153
+ 24,
154
+ 24,
155
+ 24,
156
+ 24,
157
+ 24,
158
+ 24,
159
+ 24,
160
+ 24,
161
+ 24,
162
+ 24,
163
+ 24,
164
+ 24,
165
+ 24,
166
+ 24,
167
+ 24,
168
+ 24,
169
+ 24,
170
+ 24,
171
+ 24,
172
+ 24,
173
+ 24,
174
+ 24,
175
+ 24,
176
+ 24,
177
+ 24,
178
+ 24,
179
+ 24,
180
+ 24,
181
+ 24,
182
+ 24,
183
+ 24,
184
+ 24,
185
+ 24,
186
+ 24,
187
+ 20,
188
+ 20,
189
+ 20,
190
+ 20,
191
+ 20,
192
+ 20,
193
+ 20,
194
+ 20,
195
+ 16,
196
+ 16,
197
+ 16,
198
+ 16,
199
+ 12,
200
+ 12,
201
+ 12,
202
+ 12,
203
+ 12,
204
+ 12,
205
+ 12,
206
+ 12,
207
+ 12,
208
+ 12,
209
+ 10,
210
+ 10,
211
+ 10,
212
+ 10,
213
+ 10,
214
+ 10,
215
+ 10,
216
+ 10,
217
+ 10,
218
+ 10,
219
+ 10,
220
+ 10,
221
+ 10,
222
+ 10,
223
+ 8,
224
+ 8,
225
+ 8,
226
+ 8,
227
+ 8,
228
+ 8,
229
+ 8,
230
+ 8,
231
+ 8,
232
+ 8,
233
+ 8,
234
+ 8,
235
+ 8,
236
+ 8,
237
+ 8,
238
+ 8,
239
+ 8,
240
+ 8
241
+ ],
242
+ "envs_per_shard": 24,
243
+ "requested_env_target": null
244
+ }