BriefGPT.xyz
Jul, 2023
多智能体学习的稳定性：多人网络博弈中的收敛性
Stability of Multi-Agent Learning: Convergence in Network Games with Many Players
HTML
PDF
Aamal Hussain, Dan Leonte, Francesco Belardinelli, Georgios Piliouras
TL;DR
多智能体学习在网络游戏中表现出复杂的动态特性，通过研究Q学习的动态特性，确定了在任何网络游戏中收敛到唯一均衡的充分条件，并且在适当的网络条件下，可以实现任意数量智能体的稳定学习动态。
Abstract
The behaviour of
multi-agent learning
in many player games has been shown to display complex dynamics outside of restrictive examples such as network zero-sum games. In addition, it has been shown that
convergent behavi
→