ALEXANDRIA, Va., Dec. 2 -- United States Patent no. 12,488,278, issued on Dec. 2, was assigned to Microsoft Technology Licensing LLC (Redmond, Wash.).
"Interactive agent and control using reinforcement learning" was invented by Katja Hofmann (Cambridge, Great Britain), Luisa Maria Zintgraf (Oxford, Great Britain), Sam Michael Devlin (Trumpington, Great Britain) and Kamil Andrzej Ciosek (Cambridge, Great Britain).
According to the abstract* released by the U.S. Patent & Trademark Office: "In various examples there is a method performed by a computer-implemented agent in an environment. The method comprises storing a reinforcement learning policy for controlling the computer-implemented agent. The method also comprises storing a distributio...