| {"mean_reward": 278.1844491271801, "std_reward": 19.566739496785324, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-20T07:31:15.697437"} |
| {"mean_reward": 278.1844491271801, "std_reward": 19.566739496785324, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-20T07:31:15.697437"} |