A review of off-policy evaluation in reinforcement learning

Masatoshi Uehara, Chengchun Shi and Nathan Kallus

LSE Research Online Documents on Economics from London School of Economics and Political Science, LSE Library

Abstract: Reinforcement learning (RL) is one of the most vibrant research frontiers in machine learning and has been recently applied to solve a number of challenging problems. In this paper, we primarily focus on off-policy evaluation (OPE), one of the most fundamental topics in RL. In recent years, a number of OPE methods have been developed in the statistics and computer science literature. We provide a discussion on the efficiency bound of OPE, some of the existing state-of-the-art OPE methods, their statistical properties and some other related research directions that are currently actively explored.

Keywords: off-policy evaluation; semiparametric methods; causal inference; dynamic treatment regime; offline reinforcement learning; contextual bandits (search for similar items in EconPapers)
JEL-codes: C1 (search for similar items in EconPapers)
Pages: 21 pages
Date: 2026-08-31
New Economics Papers: this item is included in nep-mac
References: View references in EconPapers View complete reference list from CitEc
Citations:

Published in Statistical Science, 31, August, 2026, 41(3), pp. 561 - 581. ISSN: 0883-4237

Downloads: (external link)
https://researchonline.lse.ac.uk/id/eprint/127940/ Open access version. (application/pdf)
Our link check indicates that this URL is bad, the error code is: 403 Forbidden

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ehl:lserod:127940

Access Statistics for this paper

More papers in LSE Research Online Documents on Economics from London School of Economics and Political Science, LSE Library LSE Library Portugal Street London, WC2A 2HD, U.K.. Contact information at EDIRC.
Bibliographic data for series maintained by LSERO Manager ().