Gdm Holding LLC

Deepmind Technologies Limited

Jost Tobias Springenberg

Nicolas Manfred Otto Heess

Raia Thais Hadsell

Martin Riedmiller

Peter William Battaglia

Joshua Merel

Timothy Arthur Mann

Todd Andrew Hester

Alexandre Galashov

Rae Chan Jeong

Abbas Abdolmaleki

Alvaro Sanchez

Francesco Nori

Daniel J Mankowitz

Nir Levine

Jacqueline Ok-Chan Kay

A graph neural network system for processing data representing a physical system is disclosed. The graph neural network system receives physical system data and action data, where the physical system includes bodies coupled by joints. The graph neural network system processes an input graph to provide an output graph, the input and output graphs each having a graph structure including nodes and edges corresponding, respectively, to the bodies and joints of the physical system. The graph processing neural network provides the inferred static property or dynamic state of the physical system. The graph processing neural network is differentiable and may be used for control and/or reinforcement learning.

Graph neural networks representing physical systems

Growing community of inventors

London, United Kingdom

Jost Tobias Springenberg