Bandit Problems

Bergemann, Dirk; Valimaki, Juuso

Download This Paper

Open PDF in Browser

Add Paper to My Library

Bandit Problems

Cowles Foundation Discussion Paper No. 1551

16 Pages Posted: 19 Jan 2006

See all articles by Dirk Bergemann

Dirk Bergemann

Yale University - Cowles Foundation - Department of Economics; Yale University - Cowles Foundation

Juuso Valimaki

Helsinki School of Economics; University of Southampton - Division of Economics

Date Written: January 2006

Abstract

We survey the literature on multi-armed bandit models and their applications in economics. The multi-armed bandit problem is a statistical decision model of an agent trying to optimize his decisions while improving his information at the same time. This classic problem has received much attention in economics as it concisely models the trade-off between exploration (trying out each arm to find the best one) and exploitation (playing the arm believed to give the best payoff).

Keywords: One-Armed Bandit, Multi-Armed Bandit, Bayesian Learning, Experimentation, Index Policy, Matching, Experience Goods

JEL Classification: C72, C73, D43, D83

Suggested Citation: Suggested Citation

Bergemann, Dirk and Valimaki, Juuso, Bandit Problems (January 2006). Cowles Foundation Discussion Paper No. 1551, Available at SSRN: https://ssrn.com/abstract=877173