Nonparametric bandits with covariates

Philippe Rigollet, Assaf Zeevi

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We consider a bandit problem which involves sequential sampling from two populations (arms). Each arm produces a noisy reward realization which depends on an observable random covariate. The goal is to maximize cumulative expected reward. We derive general lower bounds on the performance of any admissible policy, and develop an algorithm whose performance achieves the order of said lower bound up to logarithmic terms. This is done by decomposing the global problem into suitably "localized" bandit problems. Proofs blend ideas from nonparametric statistics and traditional methods used in the bandit literature.

Original languageEnglish
Title of host publicationCOLT 2010 - The 23rd Conference on Learning Theory
Pages54-66
Number of pages13
StatePublished - 2010
Externally publishedYes
Event23rd Conference on Learning Theory, COLT 2010 - Haifa, Israel
Duration: 27 Jun 201029 Jun 2010

Publication series

NameCOLT 2010 - The 23rd Conference on Learning Theory

Conference

Conference23rd Conference on Learning Theory, COLT 2010
Country/TerritoryIsrael
CityHaifa
Period27/06/1029/06/10

Fingerprint

Dive into the research topics of 'Nonparametric bandits with covariates'. Together they form a unique fingerprint.

Cite this