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


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.


  • The corresponding paper can be found here (arxiv)


  • A video of the E2C algorithm solving the four considered benchmarks can be found here: Video E2C