US Patent Issued to Fujitsu on Aug. 4 for "Computer-readable recording medium storing multi-agent reinforcement learning program, information processing apparatus, and multi-agent reinforcement learning method" (Japanese Inventors)

ALEXANDRIA, Va., Aug. 5 -- United States Patent no. 12,699,929, issued on Aug. 4, was assigned to Fujitsu Ltd. (Kawasaki, Japan).

"Computer-readable recording medium storing multi-agent reinforcement learning program, information processing apparatus, and multi-agent reinforcement learning method" was invented by Yoshihiro Okawa (Yokohama, Japan), Hayato Dan (Yokohama, Japan), Natsuki Ishikawa (Yamato, Japan) and Masatoshi Ogawa (Zama, Japan).

According to the abstract* released by the U.S. Patent & Trademark Office: "A process includes obtaining, according to a predetermined update order of a policy parameter of each agent, a degree of influence on a constraint specific to a first agent and a degree of influence on a system-wide constrai...