BriefGPT.xyz
Jul, 2020
多智体多臂赌博机公平算法
Fair Algorithms for Multi-Agent Multi-Armed Bandits
HTML
PDF
Safwan Hossain, Evi Micha, Nisarg Shah
TL;DR
本文在经典赌博机问题的基础上提出了一个多智能体变种，旨在学会对赌臂进行公平分配并利用纳什社会福利来衡量它的公平性，设计了三个多智能体变种的算法并证明其实现了次线性的损失纳什社会福利， 因此可以对合理的互惠性展现出更大的感受。
Abstract
We propose a
multi-agent
variant of the classical
multi-armed bandit problem
, in which there are N agents and K arms, and pulling an arm generates a (possibly different) stochastic reward to each agent. Unlike th
→