| {"mean_reward": 211.747766, "std_reward": 66.22244548514749, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-15T09:11:17.449655"} |
| {"mean_reward": 211.747766, "std_reward": 66.22244548514749, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-10-15T09:11:17.449655"} |