On Bayesian index policies for sequential resource allocation

Emilie Kaufmann 1
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : This paper is about index policies for minimizing (frequentist) regret in a stochastic multi-armed bandit model, inspired by a Bayesian view on the problem. Our main contribution is to prove that the Bayes-UCB algorithm, which relies on quantiles of posterior distributions, is asymptotically optimal when the reward distributions belong to a one-dimensional exponential family, for a large class of prior distributions. We also show that the Bayesian literature gives new insight on what kind of exploration rates could be used in frequentist, UCB-type algorithms. Indeed, approximations of the Bayesian optimal solution or the Finite Horizon Gittins indices provide a justification for the kl-UCB+ and kl-UCB-H+ algorithms, whose asymptotic optimality is also established.
Document type :
Journal articles
Complete list of metadatas

Cited literature [38 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01251606
Contributor : Emilie Kaufmann <>
Submitted on : Monday, November 6, 2017 - 9:52:16 AM
Last modification on : Tuesday, July 23, 2019 - 1:00:04 PM
Long-term archiving on : Wednesday, February 7, 2018 - 1:19:05 PM

Files

KaufmannSupplement.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01251606, version 3
  • ARXIV : 1601.01190

Citation

Emilie Kaufmann. On Bayesian index policies for sequential resource allocation. Annals of Statistics, Institute of Mathematical Statistics, In press. ⟨hal-01251606v3⟩

Share

Metrics

Record views

366

Files downloads

138