{"mean_reward": 15.5, "std_reward": 12.539936203984453, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-11T12:39:57.880355"} |
{"mean_reward": 15.5, "std_reward": 12.539936203984453, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2022-06-11T12:39:57.880355"} |