Investigating the Properties of Neural Network Representations in Reinforcement Learning

In this paper we investigate the properties of representations learned by deep reinforcement learning systems. Much of the early work on representations for reinforcement learning focused on designing fixed-basis architectures to achieve properties thought to be desirable, such as orthogonality and...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-05
Hauptverfasser:	Wang, Han, Miahi, Erfan, White, Martha, Machado, Marlos C, Abbas, Zaheer, Kumaraswamy, Raksha, Liu, Vincent, White, Adam
Format:	Artikel
Sprache:	eng
Schlagworte:	Data transmission Deep learning Neural networks Orthogonality Representations Teaching methods Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!