68 search results - page 4 / 14 » Feature-Discovering Approximate Value Iteration Methods |
118
Voted
ICML
1995
IEEE
16 years 3 months ago
1995
IEEE
The success ofreinforcement learninginpractical problems depends on the ability to combine function approximation with temporal di erence methods such as value iteration. Experime...
106
Voted
SIAMSC
2010
15 years 25 days ago
2010
In numerous applications of image processing, e.g. astronomical and medical imaging, data-noise is well-modeled by a Poisson distribution. This motivates the use of the negative-lo...
118
Voted
JAIR
2010
15 years 27 days ago
2010
Domain-specific features are important in representing problem structure throughout machine learning and decision-theoretic planning. In planning, once state features are provide...
114
click to vote
CISS
2008
IEEE
15 years 9 months ago
2008
IEEE
— We consider dual subgradient methods for solving (nonsmooth) convex constrained optimization problems. Our focus is on generating approximate primal solutions with performance ...
151
click to vote
SIAMJO
2010
15 years 25 days ago
2010
This paper introduces a novel algorithm to approximate the matrix with minimum nuclear norm among all matrices obeying a set of convex constraints. This problem may be understood a...