Semi-Parametric Efficient Policy Learning with Continuous Actions
Name
NeurIPS-2019-semi-parametric-efficient-policy-learning-with-continuous-actions-Paper.pdf
Description
Published version
Size
212.73 KB
Format
Adobe PDF
Checksum (MD5)
a393d43d0abcc0d0391e1ae180c100df
Author(s)
Chernozhukov, Victor
Lewis, Greg
Syrgkanis, Vasilis
Demirer, Mert
Date Issued
June 12, 2019
Journal
Advances in Neural Information Processing Systems
Publisher
The IFS
Citation
Chernozhukov, Victor, Lewis, Greg, Syrgkanis, Vasilis and Demirer, Mert. 2019. "Semi-Parametric Efficient Policy Learning with Continuous Actions." Advances in Neural Information Processing Systems, 32.
Version
Final published version
Abstract
© 2019 Neural information processing systems foundation. All rights reserved. We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value function takes a known parametric form in the treatment, but we are agnostic on how it depends on the observed contexts. We propose a doubly robust off-policy estimate for this setting and show that off-policy optimization based on this estimate is robust to estimation errors of the policy function or the regression model. Our results also apply if the model does not satisfy our semi-parametric form, but rather we measure regret in terms of the best projection of the true value function to this functional space. Our work extends prior approaches of policy optimization from observational data that only considered discrete actions. We provide an experimental evaluation of our method in a synthetic data example motivated by optimal personalized pricing and costly resource allocation.
MIT Department
Sloan School of Management
Massachusetts Institute of Technology. Department of Economics
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1920/wp.cem.2019.3419
