OpenTechnical
This is a record of a document published elsewhere, first published by the United States Patent and Trademark Office, as US-12552021-B2, on 17 February 2026. OpenTechnical did not first disclose it. The identifier, hashes and timestamps below record what this library served and when, not when the material became public. View the original.

OT-2026-000002833

Techniques for training and implementing reinforcement learning policies for robot control

Published
Permanent URL
Classification
Robotics & Automation › Robot Architectures
Inventors
FOX DIETER, NARANG YASHRAJ SHYAM, TANG BINGJIE, TOZETO RAMOS FABIO
Assignee
NVIDIA CORP
Original source
US-12552021-B2, the United States Patent and Trademark Office, 17 February 2026
Document SHA-256
eef161c4f71e381d346e409e855a3c9d454a08ccc8c184569e8b778f8e327f08

Abstract

One embodiment of a method for training a machine learning model to control a robot includes causing a model of the robot to move within a simulation based on one or more outputs of the machine learning model, computing an error within the simulation, computing at least one of a reward or an observation based on the error, and updating one or more parameters of the machine learning model based on the at least one of a reward or an observation.

Publication information

Plain textMarkdownManifestIntegrity record

Citation

OpenTechnical Publication OT-2026-000002833, “Techniques for training and implementing reinforcement learning policies for robot control,” published September 15, 2026 at 19:15:39 UTC, https://opentechnical.org/p/OT-2026-000002833.

To cite specific content, add the paragraph or figure numbers.

Terms

This record reproduces a document published elsewhere and is provided for reference and study. Rights in the original remain with its owner. See the publication policy.