Continuous State Dynamic Programming Via Nonexpansive Approximation

John Stachurski ()

No 618, KIER Working Papers from Kyoto University, Institute of Economic Research

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.

Pages: 24pages
Date: 2006-04
New Economics Papers: this item is included in nep-cmp and nep-dge
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.kier.kyoto-u.ac.jp/DP/DP618.pdf (application/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:kyo:wpaper:618

Access Statistics for this paper

More papers in KIER Working Papers from Kyoto University, Institute of Economic Research Contact information at EDIRC.
Bibliographic data for series maintained by Makoto Watanabe ().