| {"mean_reward": 585.0, "std_reward": 130.3648725692623, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-14T21:50:09.415866"} |
| {"mean_reward": 585.0, "std_reward": 130.3648725692623, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-12-14T21:50:09.415866"} |