LEARNING ENVIRONMENT REPRESENTATIONS FOR AGENT CONTROL USING PREDICTIONS OF BOOTSTRAPPED LATENTS

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an environment representation neural network of a reinforcement learning system controls an agent to perform a given task. In one aspect, the method includes: receiving a current observati...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	MUNOS, Remi, GRILL, Jean-Bastien François Laurent, GUO, Zhaohan, AZAR, Mohammad Gheshlaghi, ALTCHÉ, Florent, PIOT, Bilal, PIRES, Bernardo Avila
Format:	Patent
Sprache:	eng ; fre
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!