Mixtures of Controllers for Jump Linear and Non-Linear Plants

Abstract

We describe an extension to the Mixture of Experts architecture for modelling and controlling dynamical systems which exhibit multi(cid:173) ple modes of behavior. This extension is based on a Markov process model, and suggests a recurrent network for gating a set of linear or non-linear controllers. The new architecture is demonstrated to be capable of learning effective control strategies for jump linear and non-linear plants with multiple modes of behavior.

Cite

Text

Cacciatore and Nowlan. "Mixtures of Controllers for Jump Linear and Non-Linear Plants." Neural Information Processing Systems, 1993.

Markdown

[Cacciatore and Nowlan. "Mixtures of Controllers for Jump Linear and Non-Linear Plants." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/cacciatore1993neurips-mixtures/)

BibTeX

@inproceedings{cacciatore1993neurips-mixtures,
  title     = {{Mixtures of Controllers for Jump Linear and Non-Linear Plants}},
  author    = {Cacciatore, Timothy W. and Nowlan, Steven J.},
  booktitle = {Neural Information Processing Systems},
  year      = {1993},
  pages     = {719-726},
  url       = {https://mlanthology.org/neurips/1993/cacciatore1993neurips-mixtures/}
}