Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images

Part of Advances in Neural Information Processing Systems 28 (NIPS 2015)

Bibtex Metadata Paper Reviews Supplemental


Manuel Watter, Jost Springenberg, Joschka Boedecker, Martin Riedmiller


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.