{"mean_reward": -0.16893385285511614, "std_reward": 0.1272921477149999, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-22T18:01:13.471313"} |
{"mean_reward": -0.16893385285511614, "std_reward": 0.1272921477149999, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-08-22T18:01:13.471313"} |