| {"mean_reward": 630.5, "std_reward": 154.31218357602228, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-18T09:57:52.396535"} |
| {"mean_reward": 630.5, "std_reward": 154.31218357602228, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-04-18T09:57:52.396535"} |