Stochastically constrained best arm identification with Thompson sampling

Le Yang, Siyang Gao*, Cheng Li, Yi Wang

*Corresponding author for this work

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

Abstract

We consider the problem of the best arm identification in the presence of stochastic constraints, where there is a finite number of arms associated with multiple performance measures. The goal is to identify the arm that optimizes the objective measure subject to constraints on the remaining measures. We will explore the popular idea of Thompson sampling (TS) as a means to solve it. To the best of our knowledge, it is the first attempt to extend TS to this problem. We will design a TS-based sampling algorithm, establish its asymptotic optimality in the rate of posterior convergence, and demonstrate its superior performance using numerical examples. © 2025 Published by Elsevier Ltd.
Original languageEnglish
Article number112223
JournalAutomatica
Volume176
Online published28 Feb 2025
DOIs
Publication statusPublished - Jun 2025

Research Keywords

  • Best feasible arm identification
  • Rate of posterior convergence
  • Thompson sampling
  • Top-two algorithm

Fingerprint

Dive into the research topics of 'Stochastically constrained best arm identification with Thompson sampling'. Together they form a unique fingerprint.

Cite this