Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
djmango commited on
Commit
ef6b0cd
·
verified ·
1 Parent(s): 84a3491

Sync policy_update11895.state.json (811e4349a2b1)

Browse files
Files changed (1) hide show
  1. ppo_v10/policy_update11895.state.json +194 -0
ppo_v10/policy_update11895.state.json ADDED
@@ -0,0 +1,194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "checkpoint_schema_version": 2,
3
+ "hidden_reset_policy": "episode_done",
4
+ "update": 11896,
5
+ "stage": 21,
6
+ "ent_scale": 4.761904761904762,
7
+ "lr_now": 8.236400355459294e-6,
8
+ "total_env_steps": 41904128,
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
+ 0.0,
19
+ 1.0,
20
+ 1.0,
21
+ 1.0,
22
+ 1.0,
23
+ 0.0,
24
+ 1.0,
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
+ ],
35
+ "recent_conversions": [
36
+ 1.0,
37
+ 1.0,
38
+ 1.0,
39
+ 1.0,
40
+ 1.0,
41
+ 1.0,
42
+ 1.0,
43
+ 1.0,
44
+ 1.0,
45
+ 1.0,
46
+ 1.0,
47
+ 1.0,
48
+ 1.0,
49
+ 1.0,
50
+ 1.0,
51
+ 1.0,
52
+ 1.0,
53
+ 1.0,
54
+ 1.0,
55
+ 1.0,
56
+ 1.0,
57
+ 1.0
58
+ ],
59
+ "recent_deaths": [
60
+ 0.0,
61
+ 0.0,
62
+ 0.0,
63
+ 0.0,
64
+ 0.0,
65
+ 0.0,
66
+ 0.0,
67
+ 0.0,
68
+ 0.0,
69
+ 0.0,
70
+ 0.0,
71
+ 0.0,
72
+ 0.0,
73
+ 1.0,
74
+ 0.0,
75
+ 0.0,
76
+ 0.0,
77
+ 0.0,
78
+ 0.0,
79
+ 0.0,
80
+ 0.0,
81
+ 0.0,
82
+ 0.0,
83
+ 0.0
84
+ ],
85
+ "best_eval_win": null,
86
+ "best_eval_score": null,
87
+ "curriculum_schedule": "v10",
88
+ "reward_profile": "v10-anti-spiral-v1",
89
+ "return_stats": null,
90
+ "stage_env_targets": [
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
+ 24,
107
+ 24,
108
+ 24,
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
+ 20,
141
+ 20,
142
+ 20,
143
+ 20,
144
+ 20,
145
+ 16,
146
+ 16,
147
+ 16,
148
+ 16,
149
+ 12,
150
+ 12,
151
+ 12,
152
+ 12,
153
+ 12,
154
+ 12,
155
+ 12,
156
+ 12,
157
+ 12,
158
+ 12,
159
+ 10,
160
+ 10,
161
+ 10,
162
+ 10,
163
+ 10,
164
+ 10,
165
+ 10,
166
+ 10,
167
+ 10,
168
+ 10,
169
+ 10,
170
+ 10,
171
+ 10,
172
+ 10,
173
+ 8,
174
+ 8,
175
+ 8,
176
+ 8,
177
+ 8,
178
+ 8,
179
+ 8,
180
+ 8,
181
+ 8,
182
+ 8,
183
+ 8,
184
+ 8,
185
+ 8,
186
+ 8,
187
+ 8,
188
+ 8,
189
+ 8,
190
+ 8
191
+ ],
192
+ "envs_per_shard": 14,
193
+ "requested_env_target": null
194
+ }