US Patent Issued to DeepMind Technologies on July 1 for "Data-efficient reinforcement learning for continuous control tasks" (British, German, Bulgarian Inventors)

ALEXANDRIA, Va., July 3 -- United States Patent no. 12,346,786, issued on July 1, was assigned to DeepMind Technologies Ltd. (London).

"Data-efficient reinforcement learning for continuous control tasks" was invented by Martin Riedmiller (Balgheim, Germany), Roland Hafner (Balgheim, Germany), Mel Vecerik (London), Timothy Paul Lillicrap (London), Thomas Lampe (London), Ivaylo Popov (Ruse, Bulgaria), Gabriel Barth-Maron (London) and Nicolas Manfred Otto Heess (London).

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 data-efficient reinforcement learning. One of the systems is a system for training an actor neural ...