{"mean_reward": 9.4, "std_reward": 0.8, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-13T03:39:59.484117"} |
{"mean_reward": 9.4, "std_reward": 0.8, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-13T03:39:59.484117"} |