US Patent Issued to DeepMind Technologies on Feb. 24 for "Continuous control with deep reinforcement learning" (British Inventors)

ALEXANDRIA, Va., Feb. 24 -- United States Patent no. 12,561,573, issued on Feb. 24, was assigned to DeepMind Technologies Ltd. (London).

"Continuous control with deep reinforcement learning" was invented by Timothy Paul Lillicrap (London), Jonathan James Hunt (London), Alexander Pritzel (London), Nicolas Manfred Otto Heess (London), Tom Erez (London), Yuval Tassa (London), David Silver (Hitchin, Great Britain) and Daniel Pieter Wierstra (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 training an actor neural network used to select actions to be performed by an agent interacting with an environment. One ...