Learning to Control an Unstable System with Forward Modeling

Abstract

The forward modeling approach is a methodology for learning con(cid:173) trol when data is available in distal coordinate systems. We extend previous work by considering how this methodology can be applied to the optimization of quantities that are distal not only in space but also in time.

Cite

Text

Jordan and Jacobs. "Learning to Control an Unstable System with Forward Modeling." Neural Information Processing Systems, 1989.

Markdown

[Jordan and Jacobs. "Learning to Control an Unstable System with Forward Modeling." Neural Information Processing Systems, 1989.](https://mlanthology.org/neurips/1989/jordan1989neurips-learning/)

BibTeX

@inproceedings{jordan1989neurips-learning,
  title     = {{Learning to Control an Unstable System with Forward Modeling}},
  author    = {Jordan, Michael I. and Jacobs, Robert A.},
  booktitle = {Neural Information Processing Systems},
  year      = {1989},
  pages     = {324-331},
  url       = {https://mlanthology.org/neurips/1989/jordan1989neurips-learning/}
}