公开(公告)号：US20210049467A1

公开(公告)日：2021-02-18

申请号：US17046963

申请日：2019-04-12

Applicant: DeepMind Technologies Limited

Inventor： Martin Riedmiller ,  Raia Thais Hadsell ,  Peter William Battaglia ,  Joshua Merel ,  Jost Tobias Springenberg ,  Alvaro Sanchez ,  Nicolas Manfred Otto Heess

IPC: G06N3/08

Abstract: A graph neural network system implementing a learnable physics engine for understanding and controlling a physical system. The physical system is considered to be composed of bodies coupled by joints and is represented by static and dynamic graphs. A graph processing neural network processes an input graph e.g. the static and dynamic graphs, to provide an output graph, e.g. a predicted dynamic graph. The graph processing neural network is differentiable and may be used for control and/or reinforcement learning. The trained graph neural network system can be applied to physical systems with similar but new graph structures (zero-shot learning).

公开(公告)号：US20230359788A1

公开(公告)日：2023-11-09

申请号：US18027174

申请日：2021-10-01

Applicant: DeepMind Technologies Limited

Inventor： Alvaro Sanchez ,  Jonathan William Godwin ,  Rex Ying ,  Tobias Pfaff ,  Meire Fortunato ,  Peter William Battaglia

IPC: G06F30/27

CPC classification number: G06F30/27 ,  G06F2113/08

Abstract: This specification describes a simulation system that performs simulations of physical environments using a graph neural network. At each of one or more time steps in a sequence of time steps, the system can process a representation of a current state of the physical environment at the current time step using the graph neural network to generate a prediction of a next state of the physical environment at the next time step. Some implementations of the system are adapted for hardware GLOBAL acceleration. As well as performing simulations, the system can be used to predict physical quantities based on measured real-world data. Implementations of the system are differentiable and can also be used for design optimization, and for optimal control tasks.

公开(公告)号：US20220366247A1

公开(公告)日：2022-11-17

申请号：US17763920

申请日：2020-09-23

Applicant: DeepMind Technologies Limited

Inventor： Jessica Blake Chandler Hamrick ,  Victor Constant Bapst ,  Alvaro Sanchez ,  Tobias Pfaff ,  Theophane Guillaume Weber ,  Lars Buesing ,  Peter William Battaglia

IPC: G06N3/08 ,  G06N3/04

Abstract: A reinforcement learning system and method that selects actions to be performed by an agent interacting with an environment. The system uses a combination of reinforcement learning and a look ahead search: Reinforcement learning Q-values are used to guide the look ahead search and the search is used in turn to improve the Q-values. The system learns from a combination of real experience and simulated, model-based experience.

公开(公告)号：US20250103776A1

公开(公告)日：2025-03-27

申请号：US18832787

申请日：2023-01-30

Applicant: DeepMind Technologies Limited

Inventor： Kelsey Rebecca Allen ,  Tatiana Lopez Guevara ,  Kimberly Stachenfeld ,  Jessica Blake Chandler Hamrick ,  Alvaro Sanchez ,  Peter William Battaglia ,  Tobias Pfaff

IPC: G06F30/27 ,  G06F30/15 ,  G06N3/042 ,  G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing a set of design parameters. In one aspect, a method includes: obtaining a respective initial value for each design parameter, and iteratively optimizing current values of the design parameters over a sequence of optimization iterations. The method further includes, each optimization iteration: generating a representation of an initial state of an environment using the current values of the design parameters, processing an input including the representation of the initial state of the environment using a simulation neural network to generate an output that defines a simulation of the state of the environment over a sequence of one or more time steps, determining a reward, determining gradients of the reward with respect to the current values of the design parameters, and updating the current values of the design parameters using the gradients.

公开(公告)号：US20240176982A1

公开(公告)日：2024-05-30

申请号：US18283131

申请日：2022-05-30

Applicant: DeepMind Technologies Limited

Inventor： Jonathan William Godwin ,  Peter William Battaglia ,  Kevin Michael Schaarschmidt ,  Alvaro Sanchez

IPC: G06N3/04 ,  G06N3/084

CPC classification number: G06N3/04 ,  G06N3/084

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network that includes one or more graph neural network layers. In one aspect, a method comprises: generating data defining a graph, comprising: generating a respective final feature representation for each node, wherein, for each of one or more of the nodes, the respective final feature representation is a modified feature representation that is generated from a respective feature representation for the node using respective noise; processing the data defining the graph using one or more of the graph neural network layers of the neural network to generate a respective updated node embedding of each node; and processing, for each of one or more of the nodes having modified feature representations, the updated node embedding of the node to generate a respective de-noising prediction for the node.