Behavior-based Neuroevolutionary Training in Reinforcement Learning

In addition to their undisputed success in solving classical optimization problems, neuroevolutionary and population-based algorithms have become an alternative to standard reinforcement learning methods. However, evolutionary methods often lack the sample efficiency of standard value-based methods...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-05
Hauptverfasser:	Stork, Jörg, Zaefferer, Martin, Eisler, Nils, Tichelmann, Patrick, Bartz-Beielstein, Thomas, Eiben, A E
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Neural and Evolutionary Computing Efficiency Evolutionary algorithms Genetic algorithms Machine learning Optimization Policies Topology optimization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!