SAGE: Generating Symbolic Goals for Myopic Models in Deep Reinforcement Learning

Model-based reinforcement learning algorithms are typically more sample efficient than their model-free counterparts, especially in sparse reward problems. Unfortunately, many interesting domains are too complex to specify the complete models required by traditional model-based approaches. Learning...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-03
Hauptverfasser:	Chester, Andrew, Dann, Michael, Zambetta, Fabio, Thangarajah, John
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Deep learning Domains Hybrid systems Machine learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!