BriefGPT.xyz
Feb, 2024
分散学习对斯塔克尔贝格博弈中玩家效用的影响
Impact of Decentralized Learning on Player Utilities in Stackelberg Games
HTML
PDF
Kate Donahue, Nicole Immorlica, Meena Jagadeesan, Brendan Lucier, Aleksandrs Slivkins
TL;DR
探讨了两个学习代理(如推荐系统或聊天机器人)相互交流并独立学习的情况下,每个代理的目标和效用如何受到影响,并提出了一种宽容于小学习误差的放松后的后悔基准,以及相应的学习算法,实现了接近最优水平的后悔率。
Abstract
When deployed in the world, a
learning agent
such as a
recommender system
or a
chatbot
often repeatedly interacts with another
→