| {"mean_reward": 617.0, "std_reward": 134.1118935814419, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-22T17:09:21.544638"} |
| {"mean_reward": 617.0, "std_reward": 134.1118935814419, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-10-22T17:09:21.544638"} |