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. 25, 2023

Filed:

Jan. 22, 2020
Applicant:

Samsung Electronics Co., Ltd., Suwon-si, KR;

Inventors:

Riley Simmons-Edler, Princeton, NJ (US);

Ben Eisner, New York, NY (US);

Eric Mitchell, Stanford, CA (US);

Daniel Dongyuel Lee, Tenafly, NJ (US);

Sebastian Seung, Princeton, NJ (US);

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06V 10/82 (2022.01); G06N 5/043 (2023.01); G06N 3/08 (2023.01); G06N 3/045 (2023.01); G06N 3/006 (2023.01); G06V 10/764 (2022.01); G06V 10/778 (2022.01); G06V 10/80 (2022.01);
U.S. Cl.
CPC ...
G06V 10/82 (2022.01); G06N 3/006 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 5/043 (2013.01); G06V 10/764 (2022.01); G06V 10/7788 (2022.01); G06V 10/811 (2022.01);
Abstract

An apparatus for performing continuous actions includes a memory storing instructions, and a processor configured to execute the instructions to obtain a first action of an agent, based on a current state of the agent, using a cross-entropy guided policy (CGP) neural network, and control to perform the obtained first action. The CGP neural network is trained using a cross-entropy method (CEM) policy neural network for obtaining a second action of the agent based on an input state of the agent, and the CEM policy neural network is trained using a CEM and trained separately from the training of the CGP neural network.


Find Patent Forward Citations

Loading…