Experience Sharing Based Memetic Transfer Learning for Multiagent Reinforcement Learning

In transfer learning (TL) for multiagent reinforcement learning (MARL), most popular methods are based on action advising scheme, in which skilled agents directly transfer actions, i.e., explicit knowledge, to other agents. However, this scheme requires an inquiry-answer process, which quadratically...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Memetic computing 2022-03, Vol.14 (1), p.3-17
Hauptverfasser:	Wang, Tonghao, Peng, Xingguang, Jin, Yaochu, Xu, Demin
Format:	Artikel
Sprache:	eng
Schlagworte:	Acceleration Applications of Mathematics Artificial Intelligence Bioinformatics Complex Systems Control Engineering Explicit knowledge Machine learning Mathematical and Computational Engineering Mechatronics Multiagent systems Regular Research Paper Robotics System effectiveness
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!