Skip navigation
Skip navigation

Continuous State Dynamic Programming via Nonexpansive Approximation

Stachurski, John

Description

This paper studies fitted value iteration for continuous state numerical dynamic programming using nonexpansive function approximators. A number of approximation schemes are discussed. The main contribution is to provide error bounds for approximate optimal policies generated by the value iteration algorithm.

CollectionsANU Research Publications
Date published: 2008
Type: Journal article
URI: http://hdl.handle.net/1885/29372
Source: Computational Economics
DOI: 10.1007/s10614-007-9111-5

Download

File Description SizeFormat Image
01_Stachurski_Continuous_State_Dynamic_2008.pdf310.9 kBAdobe PDF    Request a copy
02_Stachurski_Continuous_State_Dynamic_2008.pdf234.24 kBAdobe PDF    Request a copy


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator