| {"mean_reward": 262.445672, "std_reward": 18.13287912323087, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-20T06:00:26.894079"} |
| {"mean_reward": 262.445672, "std_reward": 18.13287912323087, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-20T06:00:26.894079"} |