Deeply-Debiased Off-Policy Interval Estimation
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9580-9591, 2021.
Off-policy evaluation learns a target policy’s value with a historical dataset generated by a different behavior policy. In addition to a point estimate, many applications would benefit significantly from having a confidence interval (CI) that quantifies the uncertainty of the point estimate. In this paper, we propose a novel procedure to construct an efficient, robust, and flexible CI on a target policy’s value. Our method is justified by theoretical results and numerical experiments. A Python implementation of the proposed procedure is available at https://github.com/ RunzheStat/D2OPE.