Deepmind Technologies Limited

Sergio Gomez Colmenarejo

Joao Ferdinando Gomes De Freitas

Scott Ellison Reed

Ziyu Wang

Misha Man Ray Denil

Aaron Gerard Antonius Van Den Oord

David Budden

Yusuf Aytar

Alexander Novikov

Nal Emmerich Kalchbrenner

Daniel Belov

Tom Schaul

Mel Vecerik

Jonathan Karl Scholz

Matthew William Hoffman

David Benjamin Pfau

David Barker

Marcin Andrychowicz

Serkan Cabi

Ksenia Konyushkova

Oleg O Sushkov

Oriol Vinyals

Rae Chan Jeong

Tobias Pfaff

Tom Paine

Konrad Zolna

David William Saxton

Joao Ferdinando Freitas

Misha Man Denil

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for data-driven robotic control. One of the methods includes maintaining robot experience data; obtaining annotation data; training, on the annotation data, a reward model; generating task-specific training data for the particular task, comprising, for each experience in a second subset of the experiences in the robot experience data: processing the observation in the experience using the trained reward model to generate a reward prediction, and associating the reward prediction with the experience; and training a policy neural network on the task-specific training data for the particular task, wherein the policy neural network is configured to receive a network input comprising an observation and to generate a policy output that defines a control policy for a robot performing the particular task.

Data-driven robot control

Methods, systems, and apparatus, including computer programs encoded on computer storage media for training machine learning models. One method includes obtaining a machine learning model, wherein the machine learning model comprises one or more model parameters, and the machine learning model is trained using gradient descent techniques to optimize an objective function; determining an update rule for the model parameters using a recurrent neural network (RNN); and applying a determined update rule for a final time step in a sequence of multiple time steps to the model parameters.

Training machine learning models by determining update rules using neural networks

A method of generating an output image having an output resolution of N pixels&#xd7;N pixels, each pixel in the output image having a respective color value for each of a plurality of color channels, the method comprising: obtaining a low-resolution version of the output image; and upscaling the low-resolution version of the output image to generate the output image having the output resolution by repeatedly performing the following operations: obtaining a current version of the output image having a current K&#xd7;K resolution; and processing the current version of the output image using a set of convolutional neural networks that are specific to the current resolution to generate an updated version of the output image having a 2K&#xd7;2K resolution.

Iterative multiscale image generation using neural networks

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an action selection policy neural network, wherein the action selection policy neural network is configured to process an observation characterizing a state of an environment to generate an action selection policy output, wherein the action selection policy output is used to select an action to be performed by an agent interacting with an environment. In one aspect, a method comprises: obtaining an observation characterizing a state of the environment subsequent to the agent performing a selected action; generating a latent representation of the observation; processing the latent representation of the observation using a discriminator neural network to generate an imitation score; determining a reward from the imitation score; and adjusting the current values of the action selection policy neural network parameters based on the reward using a reinforcement learning training technique.

Action selection neural network training using imitation learning in latent space

Training machine learning models by determining update rules using recurrent neural networks

Growing community of inventors

London, United Kingdom

Sergio Gomez Colmenarejo