US Patent Issued to GDM Holding on March 24 for "Training a policy neural network for controlling an agent using best response policy iteration" (British, French Inventors)

ALEXANDRIA, Va., March 24 -- United States Patent no. 12,585,941, issued on March 24, was assigned to GDM Holding LLC (Mountain View, Calif.).

"Training a policy neural network for controlling an agent using best response policy iteration" was invented by Thomas William Anthony (London), Thomas Edward Eccles (London), Andrea Tacchetti (London), Janos Kramar (London), Ian Michael Gemp (London), Thomas Chalmers Hudson (London), Nicolas Pierre Mickael Porcel (London), Marc Lanctot (London), Julien Perolat (Saint Etienne, France), Richard Everett (London), Thore Kurt Hartwig Graepel (Cambridge, Great Britain) and Yoram Bachrach (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems and apparatus...