ALEXANDRIA, Va., June 12 -- United States Patent no. 12,299,574, issued on May 13, was assigned to DeepMind Technologies Ltd. (London).
"Distributed training using actor-critic reinforcement learning with off-policy correction factors" was invented by Hubert Josef Soyer (London), Lasse Espeholt (Amsterdam), Karen Simonyan (London), Yotam Doron (London), Vlad Firoiu (London), Volodymyr Mnih (Toronto), Koray Kavukcuoglu (London), Remi Munos (London), Thomas Ward (London), Timothy James Alexander Harley (London) and Iain Robert Dunning (New York).
According to the abstract* released by the U.S. Patent & Trademark Office: "Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action...