Model minimization by linear PSR

Izadi, Masoumeh T.; Precup, Doina

Model minimization by linear PSR

Download BibTeX Cite

Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1749-1749.

Abstract

Predictive state representation (PSR), proposed by [Littman et al., 2002; Singh et al., 2004], are a general representation for controlled dynamical systems. We present a sufficient condition under which a linear PSR compresses a POMDP representation.

Masoumeh T. Izadi, and Doina Precup. 2005. Model minimization by linear PSR. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05. IJCAI, 1749–1749. https://ijcai.org/proceedings/2005/334

@inproceedings{ijcai2005p334,
  title     = {Model minimization by linear PSR},
  author    = {Izadi, Masoumeh T. and Precup, Doina},
  booktitle = {Proceedings of the Nineteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-05}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  pages     = {1749--1749},
  year      = {2005},
  url       = {https://ijcai.org/proceedings/2005/334},
}

TY  - CPAPER
TI  - Model minimization by linear PSR
AU  - Izadi, Masoumeh T.
AU  - Precup, Doina
T2  - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2005
SP  - 1749
EP  - 1749
UR  - https://ijcai.org/proceedings/2005/334
ER  -