Uehara, Masatoshi, Shi, Chengchun 
ORCID: 0000-0001-7773-2099 and Kallus, Nathan
(2025)
A review of off-policy evaluation in reinforcement learning.
Statistical Science.
ISSN 0883-4237
(In Press)
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.
| Item Type: | Article |
|---|---|
| Additional Information: | © 2025 |
| Divisions: | Statistics |
| Date Deposited: | 14 Apr 2025 14:18 |
| Last Modified: | 15 Apr 2025 13:57 |
| URI: | http://eprints.lse.ac.uk/id/eprint/127940 |
Actions (login required)
 |
View Item |
