ALEXANDRIA, Va., July 9 -- United States Patent no. 12,353,993, issued on July 8, was assigned to DeepMind Technologies Ltd. (London).

"Domain adaptation for robotic control using self-supervised learning" was invented by Rae Chan Jeong (London), Yusuf Aytar (London), David Khosid (London), Yuxiang Zhou (London), Jacqueline Ok-chan Kay (London), Thomas Lampe (London), Konstantinos Bousmalis (London) and Francesco Nori (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a policy neural network for use in controlling a real-world agent in a real-world environment. One of the methods includes training...