New error bounds for approximations from projected linear equations

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider linear fixed point equations and their approximations by projection on a low dimensional subspace. We derive new bounds on the approximation error of the solution, which are expressed in terms of low dimensional matrices and can be computed by simulation. When the fixed point mapping is a contraction, as is typically the case in Markovian decision processes (MDP), one of our bounds is always sharper than the standard worst case bounds, and another one is often sharper. Our bounds also apply to the non-contraction case, including policy evaluation in MDP with nonstandard projections that enhance exploration. There are no error bounds currently available for this case to our knowledge.

Original languageEnglish (US)
Title of host publication46th Annual Allerton Conference on Communication, Control, and Computing
Pages1116-1123
Number of pages8
DOIs
StatePublished - 2008
Externally publishedYes
Event46th Annual Allerton Conference on Communication, Control, and Computing - Monticello, IL, United States
Duration: Sep 24 2008Sep 26 2008

Publication series

Name46th Annual Allerton Conference on Communication, Control, and Computing

Other

Other46th Annual Allerton Conference on Communication, Control, and Computing
CountryUnited States
CityMonticello, IL
Period9/24/089/26/08

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software
  • Control and Systems Engineering
  • Communication

Fingerprint Dive into the research topics of 'New error bounds for approximations from projected linear equations'. Together they form a unique fingerprint.

Cite this