US Patent Issued to NVIDIA on Feb. 17 for "Techniques for training and implementing reinforcement learning policies for robot control" (California, Washington Inventors)

ALEXANDRIA, Va., Feb. 17 -- United States Patent no. 12,552,021, issued on Feb. 17, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Techniques for training and implementing reinforcement learning policies for robot control" was invented by Bingjie Tang (Los Angeles), Yashraj Shyam Narang (Seattle), Dieter Fox (Seattle) and Fabio Tozeto Ramos (Seattle).

According to the abstract* released by the U.S. Patent & Trademark Office: "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 o...