| {"mean_reward": 501.0, "std_reward": 131.86735759845953, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-11T03:34:30.412525"} |
| {"mean_reward": 501.0, "std_reward": 131.86735759845953, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-02-11T03:34:30.412525"} |