openfront-rl / ppo_v10 /curriculum_advance_u9876_s27_to_28.state.json
djmango's picture
Sync curriculum_advance_u9876_s27_to_28.state.json (c2077f001d8e)
36c2500 verified
Raw
History Blame
1.31 kB
{
"checkpoint_schema_version": 2,
"hidden_reset_policy": "episode_done",
"update": 9877,
"stage": 28,
"ent_scale": 5.0,
"lr_now": 2.640401243871792e-6,
"total_env_steps": 34664448,
"recent_wins": [],
"recent_conversions": [],
"recent_deaths": [],
"best_eval_win": null,
"best_eval_score": null,
"v81_curriculum": true,
"curriculum_schedule": "v10",
"reward_profile": "v10-anti-spiral-v1",
"return_stats": null,
"stage_env_targets": [
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
24,
20,
20,
20,
20,
20,
20,
20,
20,
16,
16,
16,
16,
12,
12,
12,
12,
12,
12,
12,
12,
12,
12,
10,
10,
10,
10,
10,
10,
10,
10,
10,
10,
10,
10,
10,
10,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8,
8
],
"envs_per_shard": 14,
"requested_env_target": null
}