PooL: Pheromone-inspired Communication Framework forLarge Scale Multi-Agent Reinforcement Learning

Being difficult to scale poses great problems in multi-agent coordination. Multi-agent Reinforcement Learning (MARL) algorithms applied in small-scale multi-agent systems are hard to extend to large-scale ones because the latter is far more dynamic and the number of interactions increases exponentia...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-02
Hauptverfasser:	Cao, Zixuan, Shi, Mengzhi, Zhao, Zhanbo, Ma, Xiujun
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Communication Coordination Machine learning Multiagent systems Pheromones Swarm intelligence
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!