US Patent Issued to RESEARCH & BUSINESS FOUNDATION SUNGKYUNKWAN UNIVERSITY on June 17 for "Reinforcement learning method and apparatus using task decomposition" (South Korean Inventors)

ALEXANDRIA, Va., June 19 -- United States Patent no. 12,333,441, issued on June 17, was assigned to RESEARCH & BUSINESS FOUNDATION SUNGKYUNKWAN UNIVERSITY (Suwon-si, South Korea).

"Reinforcement learning method and apparatus using task decomposition" was invented by Min Jong Yoo (Suwon-si, South Korea), Gwang Pyo Yoo (Suwon-si, South Korea) and Hong Uk Woo (Suwon-si, South Korea).

According to the abstract* released by the U.S. Patent & Trademark Office: "According to an exemplary embodiment of the present invention, a reinforcement learning method using a task decomposition inference model in a time-variant environment includes selecting a plurality of paired transitions having a time-invariant common characteristic and a time-variant di...