{"mean_reward": -0.1738556689582765, "std_reward": 0.07265601479648634, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-04T19:40:51.319652"} |
{"mean_reward": -0.1738556689582765, "std_reward": 0.07265601479648634, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-04T19:40:51.319652"} |