Deepmind Technologies Limited

Jacqueline Ok-chan Kay

Konstantinos Bousmalis

Thomas Lampe

Yusuf Aytar

Rae Chan Jeong

Yuxiang Zhou

Francesco Nori

David Khosid

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

Growing community of inventors

London, United Kingdom

Jacqueline Ok-chan Kay