论文标题
在协变量下的外部有效性的非政策评估和学习
Off-Policy Evaluation and Learning for External Validity under a Covariate Shift
论文作者
论文摘要
我们考虑使用从其他政策获得的历史数据来评估和培训评估数据的新政策。非政策评估（OPE）的目的是估计评估数据的新政策的预期奖励，而货币学数据（OPL）的目标是找到一项新政策，以最大程度地提高评估数据的预期奖励。尽管标准OPE和OPL假设历史和评估数据之间的协变量分布相同，但协变量转移通常存在，即历史数据的协变量分布与评估数据的分布不同。在本文中，我们得出了协变量转移下OPE的效率界限。然后，我们通过使用历史和评估数据分布之间的密度比的非参数估计器，在协变量转移下对OPE和OPL进行双重稳健有效的估计器。我们还讨论了其他可能的估计器并比较其理论属性。最后，我们通过实验确认了提出的估计器的有效性。
We consider evaluating and training a new policy for the evaluation data by using the historical data obtained from a different policy. The goal of off-policy evaluation (OPE) is to estimate the expected reward of a new policy over the evaluation data, and that of off-policy learning (OPL) is to find a new policy that maximizes the expected reward over the evaluation data. Although the standard OPE and OPL assume the same distribution of covariate between the historical and evaluation data, a covariate shift often exists, i.e., the distribution of the covariate of the historical data is different from that of the evaluation data. In this paper, we derive the efficiency bound of OPE under a covariate shift. Then, we propose doubly robust and efficient estimators for OPE and OPL under a covariate shift by using a nonparametric estimator of the density ratio between the historical and evaluation data distributions. We also discuss other possible estimators and compare their theoretical properties. Finally, we confirm the effectiveness of the proposed estimators through experiments.
