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

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.

Cite

Text

Watter et al. "Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images." Neural Information Processing Systems, 2015.

Markdown

[Watter et al. "Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images." Neural Information Processing Systems, 2015.](https://mlanthology.org/neurips/2015/watter2015neurips-embed/)

BibTeX

@inproceedings{watter2015neurips-embed,
  title     = {{Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images}},
  author    = {Watter, Manuel and Springenberg, Jost and Boedecker, Joschka and Riedmiller, Martin},
  booktitle = {Neural Information Processing Systems},
  year      = {2015},
  pages     = {2746-2754},
  url       = {https://mlanthology.org/neurips/2015/watter2015neurips-embed/}
}