| {"mean_reward": 660.0, "std_reward": 139.0323703315167, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-22T10:11:43.028011"} |
| {"mean_reward": 660.0, "std_reward": 139.0323703315167, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-22T10:11:43.028011"} |