TY - JOUR
T1 - Stochastically constrained best arm identification with Thompson sampling
AU - Yang, Le
AU - Gao, Siyang
AU - Li, Cheng
AU - Wang, Yi
PY - 2025/6
Y1 - 2025/6
N2 - 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.
AB - 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.
KW - Best feasible arm identification
KW - Rate of posterior convergence
KW - Thompson sampling
KW - Top-two algorithm
UR - http://www.scopus.com/inward/record.url?scp=85218896760&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85218896760&origin=recordpage
U2 - 10.1016/j.automatica.2025.112223
DO - 10.1016/j.automatica.2025.112223
M3 - RGC 21 - Publication in refereed journal
SN - 0005-1098
VL - 176
JO - Automatica
JF - Automatica
M1 - 112223
ER -