369 search results - page 49 / 74 » Global Optimization for Value Function Approximation |
ICCV
2009
IEEE
15 years 1 months ago
2009
IEEE
The concept of graph cuts is by now a standard method
for all sorts of low level vision problems. Its popularity is
largely due to the fact that globally or near globally optimal...
NIPS
1998
13 years 10 months ago
1998
A simple learning rule is derived, the VAPS algorithm, which can be instantiated to generate a wide range of new reinforcementlearning algorithms. These algorithms solve a number ...
ICML
2006
IEEE
14 years 9 months ago
2006
IEEE
Policy evaluation is a critical step in the approximate solution of large Markov decision processes (MDPs), typically requiring O(|S|3 ) to directly solve the Bellman system of |S...
UAI
2008
13 years 10 months ago
2008
Deciding what to sense is a crucial task, made harder by dependencies and by a nonadditive utility function. We develop approximation algorithms for selecting an optimal set of me...
NIPS
2007
13 years 10 months ago
2007
Clustering is often formulated as the maximum likelihood estimation of a mixture model that explains the data. The EM algorithm widely used to solve the resulting optimization pro...