ppo_v81/policy_update1225.state.json

{
  "update": 1226,
  "stage": 5,
  "ent_scale": 1.0,
  "lr_now": 0.00011092632812499998,
  "total_env_steps": 2530304,
  "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
  ],
  "best_eval_win": 0.0,
  "best_eval_score": 0.9322033898305084,
  "v81_curriculum": true,
  "stage_env_targets": [
    24,
    24,
    24,
    24,
    24,
    24,
    12,
    10,
    8,
    8,
    8
  ],
  "envs_per_shard": 24,
  "requested_env_target": null
}