US Patent Issued to GDM Holding on Sept. 8 for "Reinforcement learning using a relational network for generating data encoding relationships between entities in an environment" (British Inventors)

ALEXANDRIA, Va., Sept. 8 -- United States Patent no. 12,731,054, issued on Sept. 8, was assigned to GDM Holding LLC (Mountain View, Calif.).

"Reinforcement learning using a relational network for generating data encoding relationships between entities in an environment" was invented by Yujia Li (London), Victor Constant Bapst (London), Vinicius Zambaldi (London), David Nunes Raposo (London) and Adam Anthony Santoro (London).

According to the abstract* released by the U.S. Patent & Trademark Office: "A neural network system is proposed, including an input network for extracting, from state data, respective entity data for each a plurality of entities which are present, or at least potentially present, in the environment. The entity data de...