| {"mean_reward": 582.5, "std_reward": 92.58104557629494, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-04T08:05:35.159158"} |
| {"mean_reward": 582.5, "std_reward": 92.58104557629494, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-03-04T08:05:35.159158"} |