Sciweavers

221 search results - page 8 / 45
» A Linear Decision-Based Approximation Approach to Stochastic...
Sort
View
NIPS
2003
13 years 8 months ago
Linear Program Approximations for Factored Continuous-State Markov Decision Processes
Approximate linear programming (ALP) has emerged recently as one of the most promising methods for solving complex factored MDPs with finite state spaces. In this work we show th...
Milos Hauskrecht, Branislav Kveton
ICML
2009
IEEE
14 years 8 months ago
Constraint relaxation in approximate linear programs
Approximate Linear Programming (ALP) is a reinforcement learning technique with nice theoretical properties, but it often performs poorly in practice. We identify some reasons for...
Marek Petrik, Shlomo Zilberstein
ICML
2010
IEEE
13 years 8 months ago
Feature Selection Using Regularization in Approximate Linear Programs for Markov Decision Processes
Approximate dynamic programming has been used successfully in a large variety of domains, but it relies on a small set of provided approximation features to calculate solutions re...
Marek Petrik, Gavin Taylor, Ronald Parr, Shlomo Zi...
AMAI
2006
Springer
13 years 7 months ago
Symmetric approximate linear programming for factored MDPs with application to constrained problems
A weakness of classical Markov decision processes (MDPs) is that they scale very poorly due to the flat state-space representation. Factored MDPs address this representational pro...
Dmitri A. Dolgov, Edmund H. Durfee
CORR
2011
Springer
220views Education» more  CORR 2011»
13 years 2 months ago
On a linear programming approach to the discrete Willmore boundary value problem and generalizations
We consider the problem of finding (possibly non connected) discrete surfaces spanning a finite set of discrete boundary curves in the three-dimensional space and minimizing (glo...
Thomas Schoenemann, Simon Masnou, Daniel Cremers