| {"mean_reward": 481.0, "std_reward": 222.09007181771995, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-04T16:58:34.301376"} |
| {"mean_reward": 481.0, "std_reward": 222.09007181771995, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-06-04T16:58:34.301376"} |