ppo_v9/policy_update1060.state.json

{
  "checkpoint_schema_version": 2,
  "hidden_reset_policy": "episode_done",
  "update": 1061,
  "stage": 2,
  "ent_scale": 1.3241592213316957,
  "lr_now": 0.00018062499999999999,
  "total_env_steps": 4074240,
  "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
  ],
  "recent_conversions": [],
  "best_eval_win": null,
  "best_eval_score": null,
  "v81_curriculum": true,
  "curriculum_schedule": "v9",
  "reward_profile": "v9-sparse-win-v1",
  "return_stats": null,
  "stage_env_targets": [
    24,
    24,
    24,
    24,
    24,
    24,
    24,
    24,
    20,
    20,
    16,
    16,
    12,
    12,
    10,
    10,
    10,
    8,
    8,
    10,
    8,
    8,
    8,
    8,
    8
  ],
  "envs_per_shard": 20,
  "requested_env_target": null
}