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:
May. 16, 2023

Filed:

Oct. 04, 2019
Applicant:

Mitsubishi Electric Research Laboratories, Inc., Cambridge, MA (US);

Inventors:

Devesh Jha, Cambridge, MA (US);

Arvind Raghunathan, Brookline, MA (US);

Diego Romeres, Somerville, MA (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G05B 13/02 (2006.01); G05B 13/04 (2006.01); G06N 20/00 (2019.01); G06N 3/08 (2023.01); G06N 7/01 (2023.01);
U.S. Cl.
CPC ...
G05B 13/029 (2013.01); G05B 13/0265 (2013.01); G05B 13/042 (2013.01); G05B 13/047 (2013.01); G06N 3/08 (2013.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01);
Abstract

A computer-implemented learning method for optimizing a control policy controlling a system is provided. The method includes receiving states of the system being operated for a specific task, initializing the control policy as a function approximator including neural networks, collecting state transition and reward data using a current control policy, estimating an advantage function and a state visitation frequency based on the current control policy, updating the current control policy using the second-order approximation of the objective function, a second-order approximation of the KL-divergence constraint on the permissible change in the policy using a quasi-newton trust region policy optimization, and determining an optimal control policy, for controlling the system, based on the average reward accumulated using the updated current control policy.


Find Patent Forward Citations

Loading…