{"mean_reward": 5.0, "std_reward": 7.0710678118654755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-15T04:37:23.351038"} |
{"mean_reward": 5.0, "std_reward": 7.0710678118654755, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-15T04:37:23.351038"} |