BriefGPT.xyz
Feb, 2018
使用软Q学习平衡双人随机博弈
Balancing Two-Player Stochastic Games with Soft Q-Learning
HTML
PDF
Jordi Grau-Moya, Felix Leibfried, Haitham Bou-Ammar
TL;DR
本文将软Q-学习技术应用于随机博弈中的多智能体系统，实现可调的智能体策略，通过理论和实验贡献，证明了软Q-学习可以在各种不同类型的博弈中实现优异表现。
Abstract
Within the context of
video games
the notion of perfectly rational agents can be undesirable as it leads to uninteresting situations, where humans face tough adversarial decision makers. Current frameworks for
stochasti
→