{"mean_reward": 566.0, "std_reward": 95.83318840568751, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-25T13:21:00.561806"} |
{"mean_reward": 566.0, "std_reward": 95.83318840568751, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-05-25T13:21:00.561806"} |