Fitted Value Function Iteration With Probability One Contractions

Jenö Pál and John Stachurski ()

ANU Working Papers in Economics and Econometrics from Australian National University, College of Business and Economics, School of Economics

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

Pages: 22 Pages
Date: 2011-10
New Economics Papers: this item is included in nep-cis and nep-cmp
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.cbe.anu.edu.au/researchpapers/econ/wp560.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:acb:cbeeco:2011-560

Access Statistics for this paper

More papers in ANU Working Papers in Economics and Econometrics from Australian National University, College of Business and Economics, School of Economics Contact information at EDIRC.
Bibliographic data for series maintained by ().