Continual Auxiliary Task Learning

Learning auxiliary tasks, such as multiple predictions about the world, can provide many benefits to reinforcement learning systems. A variety of off-policy learning algorithms have been developed to learn such predictions, but as yet there is little work on how to adapt the behavior to gather usefu...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	McLeod, Matthew, Lo, Chunlok, Schlegel, Matthew, Jacobsen, Andrew, Kumaraswamy, Raksha, White, Martha, White, Adam
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!