| {"mean_reward": 227.5, "std_reward": 88.35298523536146, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-11-22T21:34:17.022765"} |
| {"mean_reward": 227.5, "std_reward": 88.35298523536146, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-11-22T21:34:17.022765"} |