| {"mean_reward": 581.0, "std_reward": 211.62230506258078, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-18T22:57:43.856572"} |
| {"mean_reward": 581.0, "std_reward": 211.62230506258078, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-18T22:57:43.856572"} |