Simplifying communication control: a cooperative multi-agent reinforcement learning framework based on group decision-making

Abstract Multi-agent cooperative systems face fundamental challenges in distributed learning due to environmental non-stationarity and partial observability. While existing approaches employ communication mechanisms or hybrid action spaces to enhance collaboration, they often rely on complex policy...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Quantao Wang, Ziming He, Haobin Shi
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Springer 2025-11-01
Schriftenreihe:	Journal of King Saud University: Computer and Information Sciences
Schlagworte:	Cooperative multi-agent system Reinforcement learning Group decision-making
Online-Zugang:	https://doi.org/10.1007/s44443-025-00326-6
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!