CaltechAUTHORS
Published December 2009 | Version Submitted + Published
Book Section - Chapter Open

Approximate dynamic programming using fluid and diffusion approximations with applications to power management

Creators

Abstract

TD learning and its refinements are powerful tools for approximating the solution to dynamic programming problems. However, the techniques provide the approximate solution only within a prescribed finite-dimensional function class. Thus, the question that always arises is how should the function class be chosen? The goal of this paper is to propose an approach for TD learning based on choosing the function class using the solutions to associated fluid and diffusion approximations. In order to illustrate this new approach, the paper focuses on an application to dynamic speed scaling for power management.

Additional Information

© 2009 IEEE. Financial support from the National Science Foundation (ECS-0523620 and CCF-0830511), ITMANET DARPA RK 2006-07284, and Microsoft Research is gratefully acknowledged.

Attached Files

Published - 05399685.pdf

Submitted - 1307.1759.pdf

Files

05399685.pdf

Files (4.2 MB)

Name Size
md5:2d120ae78662e0d0050fcb5f0b3bcda9
1.2 MB Preview Download
md5:f9835f86ad208fdf0563b19284d46a5d
3.0 MB Preview Download

Additional details

Identifiers

Eprint ID
93261
Resolver ID
CaltechAUTHORS:20190226-095816638

Related works

Describes
https://arxiv.org/abs/1307.1759 (URL)

Funding

NSF
ECS-0523620
NSF
CCF-0830511
Defense Advanced Research Projects Agency (DARPA)
RK 2006-07284
Microsoft Research

Dates

Created
2019-02-26
Created from EPrint's datestamp field
Updated
2021-11-16
Created from EPrint's last_modified field