US Patent Issued to Google on July 7 for "Offline primitive discovery for accelerating data-driven reinforcement learning" (California, Massachusetts Inventors)

ALEXANDRIA, Va., July 7 -- United States Patent no. 12,675,670, issued on July 7, was assigned to Google LLC (Mountain View, Calif.).

"Offline primitive discovery for accelerating data-driven reinforcement learning" was invented by Anurag Ajay (Cambridge, Mass.), Ofir Nachum (San Francisco), Aviral Kumar (Berkeley, Calif.) and Sergey Levine (Berkeley, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes determining a first state associated with a particular task, and determining, by a task policy model, a latent space representation of the first state. The task policy model may have been trained to define, for each respective state of a plurality of possible states associated with the part...