Timezone: »

Deeply-Debiased Off-Policy Interval Estimation
Chengchun Shi · Runzhe Wan · Victor Chernozhukov · Rui Song

Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @

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.

Author Information

Chengchun Shi (London School of Economics and Political Science)
Runzhe Wan (North Carolina State University)
Victor Chernozhukov (MIT)
Rui Song (North Carolina State University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors