Sciweavers

111 search results - page 2 / 23
» Predictive State Representations: A New Theory for Modeling ...
Sort
View
AAAI
2006
13 years 7 months ago
Improving Approximate Value Iteration Using Memories and Predictive State Representations
Planning in partially-observable dynamical systems is a challenging problem, and recent developments in point-based techniques such as Perseus significantly improve performance as...
Michael R. James, Ton Wessling, Nikos A. Vlassis
ICML
2008
IEEE
14 years 6 months ago
Efficiently learning linear-linear exponential family predictive representations of state
Exponential Family PSR (EFPSR) models capture stochastic dynamical systems by representing state as the parameters of an exponential family distribution over a shortterm window of...
David Wingate, Satinder P. Singh
ATAL
2008
Springer
13 years 7 months ago
Dynamics based control with PSRs
We present an extension of the Dynamics Based Control (DBC) paradigm to environment models based on Predictive State Representations (PSRs). We show an approximate greedy version ...
Ariel Adam, Zinovi Rabinovich, Jeffrey S. Rosensch...
ICMLA
2004
13 years 7 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...
NIPS
2001
13 years 7 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....