{"mean_reward": 604.5, "std_reward": 220.92362933828514, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-13T03:14:18.659024"} |
{"mean_reward": 604.5, "std_reward": 220.92362933828514, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-05-13T03:14:18.659024"} |