Model minimization by linear PSR

Authors:
Masoumeh T. Izadi;Doina Precup
Affiliations:
McGill University, School of Computer Science;McGill University, School of Computer Science
Venue:
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Year:
2005

Citing 1
Cited 2

Predictive state representations: a new theory for modeling dynamical systems

UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence

Point-based planning for predictive state representations

Canadian AI'08 Proceedings of the Canadian Society for computational studies of intelligence, 21st conference on Advances in artificial intelligence
Sequential decision making under uncertainty

SARA'05 Proceedings of the 6th international conference on Abstraction, Reformulation and Approximation

Quantified Score

Hi-index	0.00

Visualization

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.