ML Anthology

Representing Systems with Hidden State

Christopher Hundt, Prakash Panangaden, Joelle Pineau, Doina Precup
AAAI 2006 pp. 368-374
/aaai/2006/hundt2006aaai-representing/

Abstract

We discuss the problem of finding a good state repre-sentation in stochastic systems with observations. We develop a duality theory that generalizes existing work in predictive state representations as well as automata theory. We discuss how this theoretical framework can be used to build learning algorithms, approximate plan-ning algorithms as well as to deal with continuous ob-servations.

PDF AAAI Semantic Scholar

Cite

Text

Hundt et al. "Representing Systems with Hidden State." AAAI Conference on Artificial Intelligence, 2006.

Markdown

[Hundt et al. "Representing Systems with Hidden State." AAAI Conference on Artificial Intelligence, 2006.](https://mlanthology.org/aaai/2006/hundt2006aaai-representing/)

BibTeX

@inproceedings{hundt2006aaai-representing,
  title     = {{Representing Systems with Hidden State}},
  author    = {Hundt, Christopher and Panangaden, Prakash and Pineau, Joelle and Precup, Doina},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2006},
  pages     = {368-374},
  url       = {https://mlanthology.org/aaai/2006/hundt2006aaai-representing/}
}