IMITATION LEARNING BASED ON PREDICTION OF OUTCOMES

A method is proposed of training a policy model to generate action data for controlling an agent to perform a task in an environment. The method comprises: obtaining, for each of a plurality of performances of the task, a corresponding demonstrator trajectory comprising a plurality of sets of state...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	SULSKY, Yury, JAEGLE, Andrew Coulter, WAYNE, Gregory Duncan, FERGUS, Robert David
Format:	Patent
Sprache:	eng ; fre ; ger
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!