| {"mean_reward": 723.0, "std_reward": 362.8167581576132, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-25T19:03:52.645603"} |
| {"mean_reward": 723.0, "std_reward": 362.8167581576132, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-25T19:03:52.645603"} |