| {"mean_reward": 275.0, "std_reward": 7.745966692414834, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-11-30T13:55:43.138159"} |
| {"mean_reward": 275.0, "std_reward": 7.745966692414834, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-11-30T13:55:43.138159"} |