Convergent gradient ascent with momentum in general-sum games

Convergent gradient ascent with momentum in general-sum games

We discuss the recent work in policy gradient learning in general-sum games, and address the drawbacks in policy convergence of algorithms such as IGA and WOLF-IGA. We propose a novel learning algorithm M-IGA by adding momentum terms to policy iterations. M-IGA is guaranteed to converge to Nash equi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) 2004-10, Vol.61, p.449-454
Hauptverfasser: Zhang, Huaxiang, Huang, Shangteng
Format: Artikel
Sprache:eng
Schlagworte:
Convergence
Gradient
Policy
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We discuss the recent work in policy gradient learning in general-sum games, and address the drawbacks in policy convergence of algorithms such as IGA and WOLF-IGA. We propose a novel learning algorithm M-IGA by adding momentum terms to policy iterations. M-IGA is guaranteed to converge to Nash equilibrium policies against a M-IGA learner.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2004.04.003