openfront-rl / ppo_v10 /curriculum_advance_u11687_s18_to_19.state.json
djmango's picture
Sync curriculum_advance_u11687_s18_to_19.state.json (3c466506306b)
10177ed verified
Raw
History Blame
1.3 kB
{
"checkpoint_schema_version": 2,
"hidden_reset_policy": "episode_done",
"update": 11688,
"stage": 19,
"ent_scale": 3.069566267703796,
"lr_now": 0.000011399862083680684,
"total_env_steps": 41155072,
"recent_wins": [],
"recent_conversions": [],
"recent_deaths": [],
"best_eval_win": null,
"best_eval_score": null,
"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
}