| {"mean_reward": -48.5, "std_reward": 8.52936105461599, "is_deterministic": true, "n_eval_episodes": 1000, "eval_datetime": "2025-10-18T14:12:01.492922"} |
| {"mean_reward": -48.5, "std_reward": 8.52936105461599, "is_deterministic": true, "n_eval_episodes": 1000, "eval_datetime": "2025-10-18T14:12:01.492922"} |