openfront-rl / ppo_v11 /curriculum_advance_u139_s2_to_3.state.json
djmango's picture
Sync curriculum_advance_u139_s2_to_3.state.json (3388fb06beb3)
a9c2eef verified
Raw
History Blame Contribute Delete
1.27 kB
{
"checkpoint_schema_version": 3,
"hidden_reset_policy": "episode_done",
"update": 140,
"stage": 3,
"ent_scale": 1.0,
"lr_now": 0.00015353125,
"total_env_steps": 378240,
"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": 24,
"requested_env_target": null
}