| {"mean_reward": -0.20496069500222802, "std_reward": 0.08090223468818154, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-08T14:33:34.729679"} |
| {"mean_reward": -0.20496069500222802, "std_reward": 0.08090223468818154, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-08T14:33:34.729679"} |