US Patent Issued to Preferred Networks on Sept. 15 for "Distributed reinforcement learning system and distributed reinforcement learning method" (Japanese Inventors)

ALEXANDRIA, Va., Sept. 15 -- United States Patent no. 12,737,681, issued on Sept. 15, was assigned to Preferred Networks Inc. (Tokyo).

"Distributed reinforcement learning system and distributed reinforcement learning method" was invented by Kota Uenishi (Tokyo) and Yasuhiro Fujita (Tokyo).

According to the abstract* released by the U.S. Patent & Trademark Office: "A distributed reinforcement learning system includes one or more actor devices configured to acquire experience data, the experience data being used for reinforcement learning and corresponding to an action determined based on a model to be trained, a plurality of replay buffers configured to store the experience data acquired from the one or more actor devices, and one or more ...