| {"mean_reward": -0.1838437942788005, "std_reward": 0.12156127695105516, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-10T15:07:01.602494"} |
| {"mean_reward": -0.1838437942788005, "std_reward": 0.12156127695105516, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-10T15:07:01.602494"} |