Quantum Best Arm Identification

Xuchuang Wang, Yu-Zhen Janice Chen, Matheus Guedes de Andrade, Mohammad Hajiesmaili, John C. S. Lui, Don Towsley

Abstract: Recent progress on building quantum computers [1] envisages wide applications of quantum algorithms in the near future. With the advantage of quantum computer, one can speed up not only fundamental algorithms, e.g., unstructured search [6] and factoring [11], but recent machine learning algorithms [3] as well. In this paper, we study the quantum speedup on a canonical task of reinforcement learning-best arm identification in multi-armed bandits.