Sciweavers

267 search results - page 40 / 54
» Qualitative Analysis of Partially-Observable Markov Decision...
Sort
View
AAAI
2006
13 years 9 months ago
Incremental Least Squares Policy Iteration for POMDPs
We present a new algorithm, called incremental least squares policy iteration (ILSPI), for finding the infinite-horizon stationary policy for partially observable Markov decision ...
Hui Li, Xuejun Liao, Lawrence Carin
NIPS
2001
13 years 9 months ago
Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
Evan Greensmith, Peter L. Bartlett, Jonathan Baxte...
NIPS
2003
13 years 9 months ago
A Nonlinear Predictive State Representation
Predictive state representations (PSRs) use predictions of a set of tests to represent the state of controlled dynamical systems. One reason why this representation is exciting as...
Matthew R. Rudary, Satinder P. Singh
CSL
2010
Springer
13 years 7 months ago
The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management
This paper explains how Partially Observable Markov Decision Processes (POMDPs) can provide a principled mathematical framework for modelling the inherent uncertainty in spoken di...
Steve Young, Milica Gasic, Simon Keizer, Fran&cced...
JAIR
2010
115views more  JAIR 2010»
13 years 6 months ago
An Investigation into Mathematical Programming for Finite Horizon Decentralized POMDPs
Decentralized planning in uncertain environments is a complex task generally dealt with by using a decision-theoretic approach, mainly through the framework of Decentralized Parti...
Raghav Aras, Alain Dutech