English

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

Machine Learning 2015-11-23 v3 Computer Vision and Pattern Recognition Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1506.07365,
  title  = {Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images},
  author = {Manuel Watter and Jost Tobias Springenberg and Joschka Boedecker and Martin Riedmiller},
  journal= {arXiv preprint arXiv:1506.07365},
  year   = {2015}
}

Comments

Final NIPS version

R2 v1 2026-06-22T09:59:23.108Z