Hugging Face's logo

djmango
/
openfront-rl

Reinforcement Learning
Safetensors
PyTorch
ppo
openfront
game-ai
Model card Files
xet
 Community
openfront-rl / ppo_v81 /latest.state.json
djmango's picture
djmango
Sync latest.state.json (575bbb039ab1)
fc48332 verified
Raw History Blame Contribute Delete
764 Bytes
{
"update": 1231,
"stage": 5,
"ent_scale": 1.0,
"lr_now": 0.00011092632812499998,
"total_env_steps": 2541824,
"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
],
"best_eval_win": 0.0,
"best_eval_score": 0.9322033898305084,
"v81_curriculum": true,
"stage_env_targets": [
24,
24,
24,
24,
24,
24,
12,
10,
8,
8,
8
],
"envs_per_shard": 24,
"requested_env_target": null
}