Deepmind Technologies Limited

Gdm Holding LLC

Alexandre Galashov

Joshua Merel

Leonard Hasenclever

Vu Pham

Rae Chan Jeong

Francesco Nori

Jost Tobias Springenberg

Jacqueline Ok-Chan Kay

A computer-implemented method of training a student machine learning system comprises receiving data indicating execution of an expert, determining one or more actions performed by the expert during the execution and a corresponding state-action Jacobian, and training the student machine learning system using a linear-feedback-stabilized policy. The linear-feedback-stabilized policy may be based on the state-action Jacobian. Also a neural network system for representing a space of probabilistic motor primitives, implemented by one or more computers. The neural network system comprises an encoder configured to generate latent variables based on a plurality of inputs, each input comprising a plurality of frames, and a decoder configured to generate an action based on one or more of the latent variables and a state.

Learning motor primitives and training a machine learning system using a linear-feedback-stabilized policy

Growing community of inventors

London, United Kingdom

Alexandre Galashov