Stochastically constrained best arm identification with Thompson sampling

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 measure...

Full description

Saved in:
Bibliographic Details
Published inAutomatica (Oxford) Vol. 176; p. 112223
Main Authors Yang, Le, Gao, Siyang, Li, Cheng, Wang, Yi
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.06.2025
Subjects
Best feasible arm identification
Rate of posterior convergence
Thompson sampling
Top-two algorithm
Top-two algorithm
Rate of posterior convergence
Best feasible arm identification
Thompson sampling
Online AccessGet full text
ISSN0005-1098
DOI10.1016/j.automatica.2025.112223

Cover

More Information
Summary: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.
ISSN:0005-1098
DOI:10.1016/j.automatica.2025.112223