匹配市场中的竞争赌徒

Jun, 2019

Competing Bandits in Matching Markets

Lydia T. Liu, Horia Mania, Michael I. Jordan

TL;DR本研究提出了一种统计学习模型，用于解决双边市场中的稳定匹配问题，其中一方需从随机奖励中学习另一方的偏好，该模型扩展了标准的多臂赌博机框架，并研究了集中式和分散式方法，发现与单人多臂赌博机设置相比，具有令人惊讶的探索-利用权衡。

Abstract

stable matching, a classical model for two-sided markets, has long been studied with little consideration for how each side's preferences are learned. With the advent of massive online markets powered by