Using randomization to break the curse of dimensionality.

This paper introduces random versions of successive approximations and multigrid algorithms for computing approximate solutions to a class of finite and infinite horizon Markovian decision problems (MDPs). We prove that these algorithms succeed in breaking the “curse of dimensionality” for a subcla...

Full description

Bibliographic Details

Published in:	Econometrica Vol. 65; pp. 487 - 517
Main Author:	Rust, John
Format:	Article
Published:	Wiley-Blackwell May 1997
Subjects:	Markov processes Mathematical models of decision making Dynamic programming
Online Access:	View this record in EBSCOhost