Multiplier Bootstrap-based Exploration
Machine Learning
2023-02-06 v1
Abstract
Despite the great interest in the bandit problem, designing efficient algorithms for complex models remains challenging, as there is typically no analytical way to quantify uncertainty. In this paper, we propose Multiplier Bootstrap-based Exploration (MBE), a novel exploration strategy that is applicable to any reward model amenable to weighted loss minimization. We prove both instance-dependent and instance-independent rate-optimal regret bounds for MBE in sub-Gaussian multi-armed bandits. With extensive simulation and real data experiments, we show the generality and adaptivity of MBE.
Keywords
Cite
@article{arxiv.2302.01543,
title = {Multiplier Bootstrap-based Exploration},
author = {Runzhe Wan and Haoyu Wei and Branislav Kveton and Rui Song},
journal= {arXiv preprint arXiv:2302.01543},
year = {2023}
}