Continuous Time Learning Algorithms in Optimization and Game Theory

被引：0
|
作者：
Sylvain Sorin
机构：
[1] Sorbonne Université,Institut de Mathématiques Jussieu
[2] Campus P.&M. Curie,PRG, CNRS UMR 7586
来源：
Dynamic Games and Applications | 2023年 / 13卷
关键词：
Learning algorithms; Continuous time; Optimization; Game theory;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The purpose of this work is the comparison of learning algorithms in continuous time used in optimization and game theory. The first three are issued from no-regret dynamics and cover in particular “Replicator dynamics” and “Local projection dynamics”. Then we study “Conditional gradient” versus “Global projection” dynamics and finally “Frank-Wolfe” versus “Best reply” dynamics. Important similarities occur when considering potential or dissipative games.
引用
收藏
页码：3 / 24
页数：21
相关论文
共 50 条
12345