Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
openfront-rl / ppo_v86 /latest.state.json
djmango's picture
djmango
Sync latest.state.json (f4e0f380394e)
464aa80 verified
Raw History Blame Contribute Delete
1.36 kB
{
"checkpoint_schema_version": 2,
"hidden_reset_policy": "episode_done",
"update": 1166,
"stage": 8,
"ent_scale": 1.0375133984838831,
"lr_now": 0.0000681226312597656,
"total_env_steps": 3447808,
"recent_wins": [
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"recent_conversions": [
0.0,
0.0,
0.0,
0.0,
1.0,
0.0,
0.0,
1.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0
],
"best_eval_win": null,
"best_eval_score": null,
"v81_curriculum": true,
"curriculum_schedule": "v8.3",
"reward_profile": "v8.6-attack-fair-v1",
"return_stats": null,
"stage_env_targets": [
24,
24,
24,
24,
24,
24,
16,
12,
10,
12,
10,
8,
8,
8,
8
],
"envs_per_shard": 12,
"requested_env_target": null
}