Deepmind Technologies Limited

Gdm Holding LLC

Rae Chan Jeong

Yusuf Aytar

Joao Ferdinando Gomes De Freitas

Scott Ellison Reed

Mel Vecerik

Konstantinos Bousmalis

David Budden

Ziyu Wang

Sergio Gomez Colmenarejo

Misha Man Ray Denil

Jonathan Karl Scholz

Thomas Lampe

Alexander Novikov

Timothy Arthur Mann

David Barker

Todd Andrew Hester

Serkan Cabi

Ksenia Konyushkova

Oleg O Sushkov

Alexandre Galashov

Abbas Abdolmaleki

Yuxiang Zhou

Jacqueline Ok-chan Kay

Francesco Nori

Jost Tobias Springenberg

Daniel J Mankowitz

David Khosid

Nir Levine

Martin Riedmiller

Jacqueline Ok-Chan Kay

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a policy neural network for use in controlling a real-world agent in a real-world environment. One of the methods includes training the policy neural network by optimizing a first task-specific objective that measures a performance of the policy neural network in controlling a simulated version of the real-world agent; and then training the policy neural network by jointly optimizing (i) a self-supervised objective that measures at least a performance of internal representations generated by the policy neural network on a self-supervised task performed on real-world data and (ii) a second task-specific objective that measures the performance of the policy neural network in controlling the simulated version of the real-world agent.

Domain adaptation for robotic control using self-supervised learning

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

Growing community of inventors

London, United Kingdom

Rae Chan Jeong