Generalized Markovian decision processes

I. Brosh; E. Shlifer; P. J. Schweitzer

doi:10.1007/BF01965715

Generalized Markovian decision processes

I. Brosh^*, E. Shlifer, P. J. Schweitzer

^*Corresponding author for this work

Coller School of Management

Research output: Contribution to journal › Article › peer-review

Abstract

A general discrete decision process is formulated which includes both undiscounted and discounted semi-Markovian decision processes as special cases. A policy-iteration algorithm is presented and shown to converge to an optimal policy. Properties of the coupled functional equations are derived. Primal and dual linear programming formulations of the optimization problem are also given. An application is given to Markov ratio decision process.

Original language	English
Pages (from-to)	173-186
Number of pages	14
Journal	Mathematical Methods of Operations Research
Volume	21
Issue number	5
DOIs	https://doi.org/10.1007/BF01965715
State	Published - Oct 1977

Access to Document

10.1007/BF01965715

Cite this

@article{4d1de20e7488436791ea0782e4bfa5dd,

title = "Generalized Markovian decision processes",

abstract = "A general discrete decision process is formulated which includes both undiscounted and discounted semi-Markovian decision processes as special cases. A policy-iteration algorithm is presented and shown to converge to an optimal policy. Properties of the coupled functional equations are derived. Primal and dual linear programming formulations of the optimization problem are also given. An application is given to Markov ratio decision process.",

author = "I. Brosh and E. Shlifer and Schweitzer, {P. J.}",

year = "1977",

month = oct,

doi = "10.1007/BF01965715",

language = "אנגלית",

volume = "21",

pages = "173--186",

journal = "Mathematical Methods of Operations Research",

issn = "1432-2994",

publisher = "Physica-Verlag",

number = "5",

}

TY - JOUR

T1 - Generalized Markovian decision processes

AU - Brosh, I.

AU - Shlifer, E.

AU - Schweitzer, P. J.

PY - 1977/10

Y1 - 1977/10

N2 - A general discrete decision process is formulated which includes both undiscounted and discounted semi-Markovian decision processes as special cases. A policy-iteration algorithm is presented and shown to converge to an optimal policy. Properties of the coupled functional equations are derived. Primal and dual linear programming formulations of the optimization problem are also given. An application is given to Markov ratio decision process.

AB - A general discrete decision process is formulated which includes both undiscounted and discounted semi-Markovian decision processes as special cases. A policy-iteration algorithm is presented and shown to converge to an optimal policy. Properties of the coupled functional equations are derived. Primal and dual linear programming formulations of the optimization problem are also given. An application is given to Markov ratio decision process.

UR - http://www.scopus.com/inward/record.url?scp=34250302077&partnerID=8YFLogxK

U2 - 10.1007/BF01965715

DO - 10.1007/BF01965715

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:34250302077

SN - 1432-2994

VL - 21

SP - 173

EP - 186

JO - Mathematical Methods of Operations Research

JF - Mathematical Methods of Operations Research

IS - 5

ER -

Generalized Markovian decision processes

Abstract

Access to Document

Other files and links

Fingerprint

Cite this