Variability sensitive Markov decision processes

Melike Baykal-Gursoy; Keith W. Ross

Variability sensitive Markov decision processes

Melike Baykal-Gursoy, Keith W. Ross

Research output: Contribution to journal › Conference article › peer-review

Abstract

Time-average Markov decision processes with finite state and action spaces are considered. Several definitions of variability are introduced and compared. It is shown that a stationary policy maximizes one of these criteria, namely, the expected long-run average variability. An algorithm that produces such an optimal stationary policy is given.

Original language	English (US)
Pages (from-to)	1261-1262
Number of pages	2
Journal	Proceedings of the IEEE Conference on Decision and Control
Volume	2
State	Published - 1989
Event	Proceedings of the 28th IEEE Conference on Decision and Control. Part 2 (of 3) - Tampa, FL, USA Duration: Dec 13 1989 → Dec 15 1989

ASJC Scopus subject areas

Control and Systems Engineering
Modeling and Simulation
Control and Optimization

Cite this

@article{a60acd5886604e36b2744ecc34fa5797,

title = "Variability sensitive Markov decision processes",

abstract = "Time-average Markov decision processes with finite state and action spaces are considered. Several definitions of variability are introduced and compared. It is shown that a stationary policy maximizes one of these criteria, namely, the expected long-run average variability. An algorithm that produces such an optimal stationary policy is given.",

author = "Melike Baykal-Gursoy and Ross, {Keith W.}",

year = "1989",

language = "English (US)",

volume = "2",

pages = "1261--1262",

journal = "Proceedings of the IEEE Conference on Decision and Control",

issn = "0191-2216",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "Proceedings of the 28th IEEE Conference on Decision and Control. Part 2 (of 3) ; Conference date: 13-12-1989 Through 15-12-1989",

}

TY - JOUR

T1 - Variability sensitive Markov decision processes

AU - Baykal-Gursoy, Melike

AU - Ross, Keith W.

PY - 1989

Y1 - 1989

N2 - Time-average Markov decision processes with finite state and action spaces are considered. Several definitions of variability are introduced and compared. It is shown that a stationary policy maximizes one of these criteria, namely, the expected long-run average variability. An algorithm that produces such an optimal stationary policy is given.

AB - Time-average Markov decision processes with finite state and action spaces are considered. Several definitions of variability are introduced and compared. It is shown that a stationary policy maximizes one of these criteria, namely, the expected long-run average variability. An algorithm that produces such an optimal stationary policy is given.

UR - http://www.scopus.com/inward/record.url?scp=0024908281&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024908281&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0024908281

SN - 0191-2216

VL - 2

SP - 1261

EP - 1262

JO - Proceedings of the IEEE Conference on Decision and Control

JF - Proceedings of the IEEE Conference on Decision and Control

T2 - Proceedings of the 28th IEEE Conference on Decision and Control. Part 2 (of 3)

Y2 - 13 December 1989 through 15 December 1989

ER -

Variability sensitive Markov decision processes

Abstract

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this