| {"mean_reward": -0.22389308013953269, "std_reward": 0.13283183373124693, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-30T12:39:16.348887"} |
| {"mean_reward": -0.22389308013953269, "std_reward": 0.13283183373124693, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-06-30T12:39:16.348887"} |