Abstract

http://ssrn.com/abstract=2326583
 


 



Robust Control of the Multi-Armed Bandit Problem


Felipe Caro


University of California, Los Angeles - Anderson School of Management

Aparupa Das Gupta


University of California, Los Angeles (UCLA) - Decisions, Operations, and Technology Management (DOTM) Area

July 1, 2014


Abstract:     
We study a robust model of the multi-armed bandit (MAB) problem in which the transition probabilities are ambiguous and belong to subsets of the probability simplex. We characterize the optimal policy as a project-by-project retirement policy but we show that arms become dependent so the Gittins index is not optimal. We propose a Lagrangian index policy that is computationally equivalent to evaluating the indices of a non-robust MAB. For a project selection problem we fi nd that it performs near optimal.

Number of Pages in PDF File: 21

working papers series


Download This Paper

Date posted: September 17, 2013 ; Last revised: July 15, 2014

Suggested Citation

Caro, Felipe and Das Gupta, Aparupa, Robust Control of the Multi-Armed Bandit Problem (July 1, 2014). Available at SSRN: http://ssrn.com/abstract=2326583 or http://dx.doi.org/10.2139/ssrn.2326583

Contact Information

Felipe Caro
University of California, Los Angeles - Anderson School of Management ( email )
110 Westwood Plaza
Los Angeles, CA 90095-1481
United States
Aparupa Das Gupta (Contact Author)
University of California, Los Angeles (UCLA) - Decisions, Operations, and Technology Management (DOTM) Area ( email )
Los Angeles, CA
United States
Feedback to SSRN


Paper statistics
Abstract Views: 175
Downloads: 29

© 2014 Social Science Electronic Publishing, Inc. All Rights Reserved.  FAQ   Terms of Use   Privacy Policy   Copyright   Contact Us
This page was processed by apollo4 in 0.391 seconds