US Patent Issued to INTERNATIONAL BUSINESS MACHINES on March 25 for "Neuro-symbolic reinforcement learning with first-order logic" (Japanese Inventors)

ALEXANDRIA, Va., March 26 -- United States Patent no. 12,260,328, issued on March 25, was assigned to INTERNATIONAL BUSINESS MACHINES Corp. (Armonk, N.Y.).

"Neuro-symbolic reinforcement learning with first-order logic" was invented by Daiki Kimura (Kanagawa, Japan), Masaki Ono (Tokyo), Subhajit Chaudhury (Kawasaki, Japan) and Michiaki Tatsubori (Oiso, Japan).

According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method for reinforcement learning with Logical Neural Networks (LNNs) is provided including receiving a plurality of observation text sentences from a target environment, extracting one or more propositional logic values from the plurality of observation text sentences, finding a class ...