Sciweavers

1974 search results - page 12 / 395
» On Unbiased Linear Approximations
Sort
View
UAI
2008
14 years 11 months ago
Partitioned Linear Programming Approximations for MDPs
Approximate linear programming (ALP) is an efficient approach to solving large factored Markov decision processes (MDPs). The main idea of the method is to approximate the optimal...
Branislav Kveton, Milos Hauskrecht
69
Voted
NA
2006
59views more  NA 2006»
14 years 9 months ago
On the fast solution of Toeplitz-block linear systems arising in multivariate approximation theory
When constructing multivariate Pad
Stefan Becuwe, Annie A. M. Cuyt
JACIII
2007
99views more  JACIII 2007»
14 years 9 months ago
Asymptotic Behavior of Linear Approximations of Pseudo-Boolean Functions
We study the problem of approximating pseudoBoolean functions by linear pseudo-Boolean functions. Pseudo-Boolean functions generalize ordinary Boolean functions by allowing the fu...
Guoli Ding, Robert F. Lax, Peter P. Chen, Jianhua ...
ICML
2010
IEEE
14 years 10 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...