| {"mean_reward": 724.0, "std_reward": 157.12733689590746, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-11T13:11:57.598981"} |
| {"mean_reward": 724.0, "std_reward": 157.12733689590746, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-11T13:11:57.598981"} |