| {"mean_reward": 253.23037320000003, "std_reward": 18.669681943769415, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-25T18:12:23.481148"} |
| {"mean_reward": 253.23037320000003, "std_reward": 18.669681943769415, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-03-25T18:12:23.481148"} |