Continuous state dynamic programming via nonexpansive approximation

被引：14

作者：

Stachurski, John ^{[1
]}

机构：

[1] Kyoto Univ, Inst Econ Res, Sakyo Ku, Kyoto 6068501, Japan

来源：

COMPUTATIONAL ECONOMICS | 2008年 / 31卷 / 02期

基金：

澳大利亚研究理事会;

关键词：

numerical dynamic programming; nonexpansive approximation;

D O I：

10.1007/s10614-007-9111-5

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

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.

引用

页码：141 / 160

页数：20

共 21 条

[1] Comparing solution methods for dynamic equilibrium economies [J].

Aruoba, S. Boragan ;

Fernandez-Villaverde, Jesus ;

Rubio-Ramirez, Juan F. .

JOURNAL OF ECONOMIC DYNAMICS & CONTROL, 2006, 30 (12) :2477-2508

[2] A theory of commodity price fluctuations [J].

Chambers, MJ ;

Bailey, RE .

JOURNAL OF POLITICAL ECONOMY, 1996, 104 (05) :924-957

[3] Competitive storage and commodity price dynamics [J].

Deaton, A ;

Laroque, G .

JOURNAL OF POLITICAL ECONOMY, 1996, 104 (05) :896-923

[4]

Drummond C, 1996, TR9605 COMP SCI DEP

[5]

Gordon G., 1995, P 12 INT C MACH LEAR

[6]

GUESTRIN C, 2001, IJCAI 01, V1, P673

[7]

Hernandez-Lerma O., 1999, FURTHER TOPICS DISCR

[8]

Judd K. L., 1994, NUMERICAL DYNA UNPUB

[9] PROJECTION METHODS FOR SOLVING AGGREGATE GROWTH-MODELS [J].

JUDD, KL .

JOURNAL OF ECONOMIC THEORY, 1992, 58 (02) :410-452

[10]

M&OSOL

← 1 2 3 →