The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jul. 07, 2026

Filed:

Feb. 08, 2021
Applicant:

Gpm Holding Llc, Mountain View, CA (US);

Inventors:

Zhaohan Guo, London, GB;

Mohammad Gheshlaghi Azar, London, GB;

Bernardo Avila Pires, London, GB;

Florent Altché, Paris, FR;

Jean-Bastien François Laurent Grill, Paris, FR;

Bilal Piot, London, GB;

Remi Munos, London, GB;

Assignee:

GDM Holding LLC, Mountain View, CA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06N 3/084 (2023.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01);
U.S. Cl.
CPC ...
G06N 3/084 (2013.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01);
Abstract

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 observation input and a future observation input; generating, from the future observation input, a future latent representation of the future state of the environment; processing, using the environment representation neural network, to generate a current internal representation of the current state of the environment; generating, from the current internal representation, a predicted future latent representation; evaluating an objective function measuring a difference between the future latent representation and the predicted future latent representation; and determining, based on a determined gradient of the objective function, an update to the current values of the environment representation parameters.


Find Patent Forward Citations

Loading…