Back to Search Start Over

Quasi-random sampling for approximate dynamic programming.

Authors :
Cervellera, Cristiano
Gaggero, Mauro
Maccio, Danilo
Marcialis, Roberto
Source :
2013 International Joint Conference on Neural Networks (IJCNN); 2013, p1-8, 8p
Publication Year :
2013

Abstract

This paper analyzes quasi-random sampling techniques for approximate dynamic programming. Specifically, low-discrepancy sequences and lattice point sets are investigated and compared as efficient schemes for uniform sampling of the state space in high-dimensional settings. The convergence analysis of the approximate solution is provided basing on geometric properties of the two discretization methods. It is also shown that such schemes are able to take advantage of regularities of the value functions, possibly through suitable transformations of the state vector. Simulation results concerning optimal management of a water reservoirs system and inventory control are presented to show the effectiveness of the considered techniques with respect to pure-random sampling. [ABSTRACT FROM PUBLISHER]

Details

Language :
English
ISBNs :
9781467361293
Database :
Complementary Index
Journal :
2013 International Joint Conference on Neural Networks (IJCNN)
Publication Type :
Conference
Accession number :
94558340
Full Text :
https://doi.org/10.1109/IJCNN.2013.6707065