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
Hi-index | 0.00 |
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.