US Patent Issued to Adobe on Nov. 25 for "Reinforcement learning-based techniques for training a natural media agent" (California, Maryland Inventors)

ALEXANDRIA, Va., Nov. 25 -- United States Patent no. 12,481,884, issued on Nov. 25, was assigned to Adobe Inc. (San Jose, Calif.).

"Reinforcement learning-based techniques for training a natural media agent" was invented by Jonathan Brandt (Santa Cruz, Calif.), Chen Fang (Sunnyvale, Calif.), Byungmoon Kim (Sunnyvale, Calif.) and Biao Jia (College Park, Md.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Some embodiments involve a reinforcement learning based framework for training a natural media agent to learn a rendering policy without human supervision or labeled datasets. The reinforcement learning based framework feeds the natural media agent a training dataset to implicitly learn the rendering policy by...