| {"mean_reward": 215.949307, "std_reward": 20.141450639489463, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-07T19:10:31.486660"} |
| {"mean_reward": 215.949307, "std_reward": 20.141450639489463, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-01-07T19:10:31.486660"} |