Deepmind Technologies Limited

Gdm Holding LLC

Peter William Battaglia

Razvan Pascanu

Theophane Guillaume Weber

Nicolas Manfred Otto Heess

Oriol Vinyals

Daniel Pieter Wierstra

Yujia Li

Sebastien Henri Andre Racaniere

Lars Buesing

David Paul Reichert

Danilo Jimenez Rezende

Adrià Puigdomènech Badia

Arthur Clement Guez

Daniel Zorn

Nicholas Watters

Raia Thais Hadsell

Martin Riedmiller

Seyed Mohammadali Eslami

Joshua Merel

Adria Puigdomenech Badia

Hasuk Song

Andrea Tacchetti

Vinicius Zambaldi

Alvaro Sanchez

Charlie Thomas Curtis Nash

Jost Tobias Springenberg

Iaroslav Ganin

Sebastien Henri Racaniere

Danilo Jiminez Rezende

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

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating data specifying a three-dimensional mesh of an object using an auto-regressive neural network.

Autoregressive neural networks for the generation of polygonal meshes of 3D objects

A system implemented by one or more computers comprises a visual encoder component configured to receive as input data representing a sequence of image frames, in particular representing objects in a scene of the sequence, and to output a sequence of corresponding state codes, each state code comprising vectors, one for each of the objects. Each vector represents a respective position and velocity of its corresponding object. The system also comprises a dynamic predictor component configured to take as input a sequence of state codes, for example from the visual encoder, and predict a state code for a next unobserved frame. The system further comprises a state decoder component configured to convert the predicted state code, to a state, the state comprising a respective position and velocity vector for each object in the scene. This state may represent a predicted position and velocity vector for each of the objects.

Making object-level predictions of the future state of a physical system

A neural network system is proposed. The neural network can be trained by model-based reinforcement learning to select actions to be performed by an agent interacting with an environment, to perform a task in an attempt to achieve a specified result. The system may comprise at least one imagination core which receives a current observation characterizing a current state of the environment, and optionally historical observations, and which includes a model of the environment. The imagination core may be configured to output trajectory data in response to the current observation, and/or historical observations. The trajectory data comprising a sequence of future features of the environment imagined by the imagination core. The system may also include a rollout encoder to encode the features, and an output stage to receive data derived from the rollout embedding and to output action policy data for identifying an action based on the current observation.

Imagination-based agent neural networks

A neural network system is proposed to select actions to be performed by an agent interacting with an environment to perform a task in an attempt to achieve a specified result. The system may include a controller to receive state data and context data, and to output action data. The system may also include an imagination module to receive the state and action data, and to output consequent state data. The system may also include a manager to receive the state data and the context data, and to output route data which defines whether the system is to execute an action or to imagine. The system may also include a memory to store the context data.

Growing community of inventors

London, United Kingdom

Peter William Battaglia