BriefGPT.xyz
Mar, 2022
无遗憾学习匹配: 基于Markov匹配市场的强化学习
Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets
HTML
PDF
Yifei Min, Tianhao Wang, Ruitu Xu, Zhaoran Wang, Michael I. Jordan...
TL;DR
研究马尔可夫匹配市场，提出强化学习框架，结合最大权匹配算法解决序列探索、匹配稳定性和函数逼近等问题，并证明算法可达到次线性的遗憾率。
Abstract
We study a
markov matching market
involving a planner and a set of
strategic agents
on the two sides of the market. At each step, the agents are presented with a
→