Deepmind Technologies Limited

Adam Anthony Santoro

Timothy Paul Lillicrap

Gregory Duncan Wayne

Chia-Chun Hung

David Nunes Raposo

Jack William Rae

Theophane Guillaume Weber

Tobias Markus Pohlen

Peter Conway Humphreys

Mevlana Celaleddin Gemici

Ryan Faulkner

Ivo Danihelka

Yujia Li

Victor Constant Bapst

Joshua Simon Abramson

Mike Chrzanowski

Sergey Bartunov

Arun Ahuja

Federico Javier Carnevale

Petko Ivanov Georgiev

Rui Zhu

Chen Yan

Jessica Paige Landon

Alistair Michael Muldal

Tamara Louise Von Glehn

Daniel Pieter Wiestra

Vinicius Zambaldi

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents. In particular, an interactive agent can be controlled based on multi-modal inputs that include both an observation image and a natural language text sequence.

Controlling interactive agents using multi-modal inputs

A computer-implemented method for controlling a particular computer to execute a task is described. The method includes receiving a control input comprising a visual input, the visual input including one or more screen frames of a computer display that represent at least a current state of the particular computer, processing the control input using a neural network to generate one or more control outputs that are used to control the particular computer to execute the task, in which the one or more control outputs include an action type output that specifies at least one of a pointing device action or a keyboard action to be performed to control the particular computer; determining one or more actions from the one or more control outputs; and executing the one or more actions to control the particular computer.

Learned computer control using pointing device and keyboard actions

A computer-implemented method for controlling a particular computer to execute a task is described. The method includes receiving a control input comprising a visual input, the visual input including one or more screen frames of a computer display that represent at least a current state of the particular computer; processing the control input using a neural network to generate one or more control outputs that are used to control the particular computer to execute the task, in which the one or more control outputs include an action type output that specifies at least one of a pointing device action or a keyboard action to be performed to control the particular computer; determining one or more actions from the one or more control outputs; and executing the one or more actions to control the particular computer.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating sequences of predicted observations, for example images. In one aspect, a system comprises a controller recurrent neural network, and a decoder neural network to process a set of latent variables to generate an observation. An external memory and a memory interface subsystem is configured to, for each of a plurality of time steps, receive an updated hidden state from the controller, generate a memory context vector by reading data from the external memory using the updated hidden state, determine a set of latent variables from the memory context vector, generate a predicted observation by providing the set of latent variables to the decoder neural network, write data to the external memory using the latent variables, the updated hidden state, or both, and generate a controller input for a subsequent time step from the latent variables.

Memory augmented generative temporal models

A system including one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to implement a memory and memory-based neural network is described. The memory is configured to store a respective memory vector at each of a plurality of memory locations in the memory. The memory-based neural network is configured to: at each of a plurality of time steps: receive an input; determine an update to the memory, wherein determining the update comprising applying an attention mechanism over the memory vectors in the memory and the received input; update the memory using the determined update to the memory; and generate an output for the current time step using the updated memory.

Neural networks with relational memory

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 describes the entity. The neural network contains a relational network for parsing this data, which includes one or more attention blocks which may be stacked to perform successive actions on the entity data. The attention blocks each include a respective transform network for each of the entities. The transform network for each entity is able to transform data which the transform network receives for the entity into modified entity data for the entity, based on data for a plurality of the other entities. An output network is arranged to receive data output by the relational network, and use the received data to select a respective action.

Reinforcement learning using a relational network for generating data encoding relationships between entities in an environment

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory. One of the systems includes a controller neural network that includes a Least Recently Used Access (LRUA) subsystem configured to: maintain a respective usage weight for each of a plurality of locations in the external memory, and for each of the plurality of time steps: generate a respective reading weight for each location using a read key, read data from the locations in accordance with the reading weights, generate a respective writing weight for each of the locations from a respective reading weight from a preceding time step and the respective usage weight for the location, write a write vector to the locations in accordance with the writing weights, and update the respective usage weight from the respective reading weight and the respective writing weight.

Augmenting neural networks with external memory

Growing community of inventors

London, United Kingdom

Adam Anthony Santoro