| {"mean_reward": 264.8912344, "std_reward": 17.19159699112602, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-13T14:23:24.290307"} |
| {"mean_reward": 264.8912344, "std_reward": 17.19159699112602, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-13T14:23:24.290307"} |