{"mean_reward": 667.5, "std_reward": 132.7450564051257, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-29T17:28:09.524601"} |
{"mean_reward": 667.5, "std_reward": 132.7450564051257, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-07-29T17:28:09.524601"} |