US Patent Issued to DeepMind Technologies on May 6 for "Reinforcement learning using meta-learned intrinsic rewards" (British, American Inventors)

ALEXANDRIA, Va., June 10 -- United States Patent no. 12,293,283, issued on May 6, was assigned to DeepMind Technologies Ltd. (London).

"Reinforcement learning using meta-learned intrinsic rewards" was invented by Zeyu Zheng (Ann Arbor, Mich.), Junhyuk Oh (London) and Satinder Singh Baveja (Ann Arbor, Mich.).

According to the abstract* released by the U.S. Patent & Trademark Office: "There is described methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a reinforcement learning system. The reinforcement learning system comprises an agent configured to perform actions based upon a policy and an intrinsic reward system configured to generate intrinsic reward values for the agent bas...