| {"mean_reward": 283.63471810000004, "std_reward": 11.506741154327297, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-19T03:37:11.894680"} |
| {"mean_reward": 283.63471810000004, "std_reward": 11.506741154327297, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-19T03:37:11.894680"} |