Poster
Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
Manuel Watter · Jost Springenberg · Joschka Boedecker · Martin Riedmiller

Thu Dec 10th 11:00 AM -- 03:00 PM @ 210 C #20 #None

We introduce Embed to Control (E2C), a method for model learning and control of non-linear dynamical systems from raw pixel images. E2C consists of a deep generative model, belonging to the family of variational autoencoders, that learns to generate image trajectories from a latent space in which the dynamics is constrained to be locally linear. Our model is derived directly from an optimal control formulation in latent space, supports long-term prediction of image sequences and exhibits strong performance on a variety of complex control problems.

Author Information

Manuel Watter (University of Freiburg)
Jost Springenberg (University of Freiburg)
Joschka Boedecker (University of Freiburg)
Martin Riedmiller (Google DeepMind)

More from the Same Authors