Sciweavers

18 search results - page 2 / 4
» Learning and discovery of predictive state representations i...
Sort
View
NIPS
2001
13 years 6 months ago
Predictive Representations of State
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
Michael L. Littman, Richard S. Sutton, Satinder P....
ICMLA
2004
13 years 6 months ago
Planning with predictive state representations
Predictive state representation (PSR) models for controlled dynamical systems have recently been proposed as an alternative to traditional models such as partially observable Mark...
Michael R. James, Satinder P. Singh, Michael L. Li...
ICML
2006
IEEE
14 years 6 months ago
Kernel Predictive Linear Gaussian models for nonlinear stochastic dynamical systems
The recent Predictive Linear Gaussian model (or PLG) improves upon traditional linear dynamical system models by using a predictive representation of state, which makes consistent...
David Wingate, Satinder P. Singh
AAAI
2011
12 years 5 months ago
An Online Spectral Learning Algorithm for Partially Observable Nonlinear Dynamical Systems
Recently, a number of researchers have proposed spectral algorithms for learning models of dynamical systems—for example, Hidden Markov Models (HMMs), Partially Observable Marko...
Byron Boots, Geoffrey J. Gordon
ACSC
2008
IEEE
13 years 7 months ago
An investigation of the state formation and transition limitations for prediction problems in recurrent neural networks
Recurrent neural networks are able to store information about previous as well as current inputs. This "memory" allows them to solve temporal problems such as language r...
Angel Kennedy, Cara MacNish