| {"mean_reward": 36.9128646, "std_reward": 191.1769651285749, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-29T03:51:35.727900"} |
| {"mean_reward": 36.9128646, "std_reward": 191.1769651285749, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-29T03:51:35.727900"} |