We consider a reinforcement learning setting where the learner is given a set of possible models containing the true model. While there are algorithms that are able to successfully learn optimal behavior in this setting, they do so without trying to identify the underlying true model. Indeed, we show that there are cases in which the attempt to find the true model is doomed to failure.

中文翻译：

---

最佳行为比真相更容易学习

我们考虑一种强化学习设置，其中向学习者提供了一组包含真实模型的可能模型。虽然有些算法能够在此设置中成功学习最佳行为，但它们无需尝试识别潜在的真实模型。事实上，我们表明在某些情况下，寻找真实模型的尝试注定要失败。