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 deeply-debiasing 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.
@article{arxiv.2105.04646,
title = {Deeply-Debiased Off-Policy Interval Estimation},
author = {Chengchun Shi and Runzhe Wan and Victor Chernozhukov and Rui Song},
journal= {arXiv preprint arXiv:2105.04646},
year = {2021}
}