ppo_v11/policy_update115.state.json

{
  "checkpoint_schema_version": 3,
  "hidden_reset_policy": "episode_done",
  "update": 116,
  "stage": 2,
  "ent_scale": 1.0,
  "lr_now": 0.00018062499999999999,
  "total_env_steps": 325248,
  "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
}