{"mean_reward": -21.0, "std_reward": 3.0659419433511785, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-29T10:37:42.493999"} |
{"mean_reward": -21.0, "std_reward": 3.0659419433511785, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-09-29T10:37:42.493999"} |