Nonparametric Bandits with Covariates

Details Nonparametric Bandits with Covariates Nonparametric Bandits with Covariates

2010-03-08

arxiv.org/abs/1003.1630v1

Mathematics

Statistics Theory

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Nonparametric Bandits with Covariates does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Nonparametric Bandits with Covariates, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Nonparametric Bandits with Covariates will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-677223