| {"mean_reward": 553.0, "std_reward": 103.46980235798269, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-25T13:19:56.787013"} |
| {"mean_reward": 553.0, "std_reward": 103.46980235798269, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2025-05-25T13:19:56.787013"} |