US Patent Issued to Google on March 17 for "Sample-efficient reinforcement learning" (British, American Inventors)

ALEXANDRIA, Va., March 17 -- United States Patent no. 12,579,438, issued on March 17, was assigned to Google LLC (Mountain View, Calif.).

"Sample-efficient reinforcement learning" was invented by Danijar Hafner (London), Jacob Buckman (San Francisco), Honglak Lee (Mountain View, Calif.), Eugene Brevdo (San Bruno, Calif.) and George Jay Tucker (Sunnyvale, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on computer storage media, for sample-efficient reinforcement learning. One of the methods includes maintaining an ensemble of Q networks, an ensemble of transition models, and an ensemble of reward models; obtaining a transition; genera...