Continuous State Dynamic Programming via Nonexpansive Approximation

John Stachurski ()

No 961, Department of Economics - Working Papers Series from The University of Melbourne

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

Keywords: Dynamic Programming; Approximation (search for similar items in EconPapers)
JEL-codes: C61 C63 (search for similar items in EconPapers)
Pages: 25 pages
Date: 2006
New Economics Papers: this item is included in nep-bec, nep-cmp and nep-dge
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.economics.unimelb.edu.au/downloads/wpapers-06/961.pdf (application/pdf)
Our link check indicates that this URL is bad, the error code is: 404 Not Found (http://www.economics.unimelb.edu.au/downloads/wpapers-06/961.pdf [301 Moved Permanently]--> http://fbe.unimelb.edu.au/economics/downloads/wpapers-06/961.pdf [301 Moved Permanently]--> https://fbe.unimelb.edu.au/economics/downloads/wpapers-06/961.pdf)

Related works:
Journal Article: Continuous State Dynamic Programming via Nonexpansive Approximation (2008)
Working Paper: Continuous State Dynamic Programming Via Nonexpansive Approximation (2006)
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:mlb:wpaper:961

Access Statistics for this paper

More papers in Department of Economics - Working Papers Series from The University of Melbourne Department of Economics, The University of Melbourne, 4th Floor, FBE Building, Level 4, 111 Barry Street. Victoria, 3010, Australia. Contact information at EDIRC.
Bibliographic data for series maintained by Dandapani Lokanathan ().