Lyapunov-Informed Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks

Multi-Agent Reinforcement Learning (MARL) has shown great potential in solving complex tasks. Despite great success, low training efficiency remains a pervasive and long-standing challenge in MARL. To tackle this issue, it is promising to leverage prior knowledge or environmental properties to infor...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on automation science and engineering Jg. 22; S. 20263 - 20279
Hauptverfasser:	Feng, Pu, Shi, Rongye, Wang, Size, Wu, Qizhen, Yu, Xin, Wu, Wenjun
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	IEEE 2025
Schlagworte:	Artificial intelligence Automation Dynamical systems Games knowledge-informed reinforcement learning Lyapunov methods Lyapunov stability multi-agent reinforcement learning multi-robot cooperation Reinforcement learning Robot kinematics Stability criteria Stochastic systems Training
ISSN:	1545-5955, 1558-3783
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!