| {"mean_reward": 586.5, "std_reward": 182.68894328885918, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-24T16:24:14.570333"} |
| {"mean_reward": 586.5, "std_reward": 182.68894328885918, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-08-24T16:24:14.570333"} |