BriefGPT.xyz
May, 2023
多智体决策的复杂性:从博弈中的学习到部分监控
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring
HTML
PDF
Dylan J. Foster, Dean P. Foster, Noah Golowich, Alexander Rakhlin
TL;DR
本文研究了多智能体强化学习中的样本效率、均衡计算和统计复杂性等问题,提出了一系列新的结构性结果,并阐述了决策时附带隐藏报酬的统计复杂度。
Abstract
A central problem in the theory of
multi-agent reinforcement learning
(MARL) is to understand what structural conditions and algorithmic principles lead to
sample-efficient learning
guarantees, and how these cons
→