{"mean_reward": 2.7, "std_reward": 4.124318125460256, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-18T00:48:30.983043"} |
{"mean_reward": 2.7, "std_reward": 4.124318125460256, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-18T00:48:30.983043"} |