{"mean_reward": 539.0, "std_reward": 190.57544437833536, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-15T07:55:31.770905"} |
{"mean_reward": 539.0, "std_reward": 190.57544437833536, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-15T07:55:31.770905"} |