ALEXANDRIA, Va., Sept. 24 -- United States Patent no. 12,743,627, issued on Sept. 22, was assigned to GDM Holding LLC (Mountain View, Calif.).
"Reinforcement learning with auxiliary tasks" was invented by Volodymyr Mnih (Toronto), Wojciech Czarnecki (London), Maxwell Elliot Jaderberg (London), Tom Schaul (London), David Silver (Hitchin, Great Britain) and Koray Kavukcuoglu (London).
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 a reinforcement learning system. The method includes: training an action selection policy neural network, and during the training of the action selection neural network, trai...