369 search results - page 15 / 74 » Global Optimization for Value Function Approximation |
JC
1998
13 years 8 months ago
1998
The problem of global solution of Fredholm integral equations is studied. This means that one seeks to approximate the full solution function (as opposed to the local problem, whe...
MOC
2002
13 years 8 months ago
2002
Abstract. This article is devoted to the construction of a Hermite-type regularization operator transforming functions that are not necessarily C1 into globally C1 finite-element f...
ICML
1995
IEEE
14 years 9 months ago
1995
IEEE
A number of reinforcement learning algorithms have been developed that are guaranteed to converge to the optimal solution when used with lookup tables. It is shown, however, that ...
UAI
2008
13 years 10 months ago
2008
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...
UAI
2004
13 years 10 months ago
2004
In this paper, we propose a new lower approximation scheme for POMDP with discounted and average cost criterion. The approximating functions are determined by their values at a fi...