B1543
Title: Deeply debiased off policy interval estimation
Authors: Chengchun Shi - LSE (United Kingdom) [presenting]
Runzhe Wan - NC State University (United States)
Victor Chernozhukov - MIT (United States)
Rui Song - North Carolina State University (United States)
Abstract: Off-policy evaluation learns a target policy 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. 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 on GitHub.