ALEXANDRIA, Va., May 5 -- United States Patent no. 12,619,911, issued on May 5, was assigned to International Business Machines Corp. (Armonk, N.Y.).
"Computing robust policies in offline reinforcement learning" was invented by Radu Marinescu (Dublin), Parikshit Ram (Atlanta), Djallel Bouneffouf (Poughkeepsie, N.Y.), Tejaswini Pedapati (White Plains, N.Y.) and Paulito Palmes (Dublin).
According to the abstract* released by the U.S. Patent & Trademark Office: "According to one embodiment, a method, computer system, and computer program product for reinforcement learning is provided. The present invention may include training, using an offline dataset, a plurality of diverse reward models, and creating a policy based on an output of the rew...