Skip navigation
Skip navigation

Fitted Value Function Iteration with Probability One Contractions

Pal, Jeno; Stachurski, John

Description

This paper studies a value function iteration algorithm based on nonexpansive function approximation and Monte Carlo integration that can be applied to almost all stationary dynamic programming problems. The method can be represented using a randomized fitted Bellman operator and a corresponding algorithm that is shown to be globally convergent with probability one. When additional restrictions are imposed, an OP(n-1/2) rate of convergence for Monte Carlo error is obtained.

CollectionsANU Research Publications
Date published: 2013
Type: Journal article
URI: http://hdl.handle.net/1885/33643
Source: Journal of Economic Dynamics and Control
DOI: 10.1016/j.jedc.2012.08.003

Download

File Description SizeFormat Image
01_Pal_Fitted_Value_Function_2013.pdf309.49 kBAdobe PDF    Request a copy
02_Pal_Fitted_Value_Function_2013.pdf357.11 kBAdobe PDF    Request a copy
03_Pal_Fitted_Value_Function_2013.pdf673.52 kBAdobe PDF    Request a copy


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

Updated:  20 July 2017/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator