BriefGPT.xyz
May, 2022
BRExIt: 关于专家迭代中对手建模的研究
BRExIt: On Opponent Modelling in Expert Iteration
HTML
PDF
Daniel Hernandez, Hendrik Baier, Michael Kaisers
TL;DR
提出了一种名为BRExIt的学习算法,利用对手模型来提高学习的效率和性能,在Connect4游戏中的实验验证,BRExIt算法具有更高的采样效率,能够学习出表现优异的策略。
Abstract
Finding a
best response policy
is a central objective in
game theory
and
multi-agent learning
, with modern population-based training appro
→