| {"mean_reward": 38.5, "std_reward": 14.5, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-10T08:48:51.856532"} |
| {"mean_reward": 38.5, "std_reward": 14.5, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-09-10T08:48:51.856532"} |