RL in Markov Games with Independent Function Approximation: Improved Sample Complexity Bound under the Local Access Model

Efficiently learning equilibria with large state and action spaces in general-sum Markov games while overcoming the curse of multi-agency is a challenging problem. Recent works have attempted to solve this problem by employing independent linear function classes to approximate the marginal \(Q\)-val...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-03
Hauptverfasser:	Fan, Junyi, Han, Yuxuan, Zeng, Jialin, Jian-Feng, Cai, Wang, Yang, Yang, Xiang, Zhang, Jiheng
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy Algorithms Complexity Game theory Games Iterative methods Linear functions Machine learning Random access
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!