Mutually dependent Markov decision processes

Toshiharu Fujita, Akifumi Kira

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we introduce a basic framework for mutually dependent Markov decision processes (MDMDP) showing recursive mutual dependence. Our model is structured upon two types of finite-stage Markov decision processes. At each stage, the reward in one process is given by the optimal value of the alternative process problem, whose initial state is determined by the current state and decision in the original process. We formulate the MDMDP model and derive mutually dependent recursive equations by dynamic programming. Furthermore, MDMDP is illustrated in a numerical example. The model enables easier treatment of some classes of complex multi-stage decision processes.

Original languageEnglish
Pages (from-to)992-998
Number of pages7
JournalJournal of Advanced Computational Intelligence and Intelligent Informatics
Volume18
Issue number6
DOIs
Publication statusPublished - Nov 1 2014

Fingerprint

Dynamic programming

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

Mutually dependent Markov decision processes. / Fujita, Toshiharu; Kira, Akifumi.

In: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol. 18, No. 6, 01.11.2014, p. 992-998.

Research output: Contribution to journalArticle

Fujita, Toshiharu ; Kira, Akifumi. / Mutually dependent Markov decision processes. In: Journal of Advanced Computational Intelligence and Intelligent Informatics. 2014 ; Vol. 18, No. 6. pp. 992-998.
@article{100c9072185c4631b50f5336a0aa61e0,
title = "Mutually dependent Markov decision processes",
abstract = "In this paper, we introduce a basic framework for mutually dependent Markov decision processes (MDMDP) showing recursive mutual dependence. Our model is structured upon two types of finite-stage Markov decision processes. At each stage, the reward in one process is given by the optimal value of the alternative process problem, whose initial state is determined by the current state and decision in the original process. We formulate the MDMDP model and derive mutually dependent recursive equations by dynamic programming. Furthermore, MDMDP is illustrated in a numerical example. The model enables easier treatment of some classes of complex multi-stage decision processes.",
author = "Toshiharu Fujita and Akifumi Kira",
year = "2014",
month = "11",
day = "1",
doi = "10.20965/jaciii.2014.p0992",
language = "English",
volume = "18",
pages = "992--998",
journal = "Journal of Advanced Computational Intelligence and Intelligent Informatics",
issn = "1343-0130",
publisher = "Fuji Technology Press",
number = "6",

}

TY - JOUR

T1 - Mutually dependent Markov decision processes

AU - Fujita, Toshiharu

AU - Kira, Akifumi

PY - 2014/11/1

Y1 - 2014/11/1

N2 - In this paper, we introduce a basic framework for mutually dependent Markov decision processes (MDMDP) showing recursive mutual dependence. Our model is structured upon two types of finite-stage Markov decision processes. At each stage, the reward in one process is given by the optimal value of the alternative process problem, whose initial state is determined by the current state and decision in the original process. We formulate the MDMDP model and derive mutually dependent recursive equations by dynamic programming. Furthermore, MDMDP is illustrated in a numerical example. The model enables easier treatment of some classes of complex multi-stage decision processes.

AB - In this paper, we introduce a basic framework for mutually dependent Markov decision processes (MDMDP) showing recursive mutual dependence. Our model is structured upon two types of finite-stage Markov decision processes. At each stage, the reward in one process is given by the optimal value of the alternative process problem, whose initial state is determined by the current state and decision in the original process. We formulate the MDMDP model and derive mutually dependent recursive equations by dynamic programming. Furthermore, MDMDP is illustrated in a numerical example. The model enables easier treatment of some classes of complex multi-stage decision processes.

UR - http://www.scopus.com/inward/record.url?scp=84912095308&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84912095308&partnerID=8YFLogxK

U2 - 10.20965/jaciii.2014.p0992

DO - 10.20965/jaciii.2014.p0992

M3 - Article

AN - SCOPUS:84912095308

VL - 18

SP - 992

EP - 998

JO - Journal of Advanced Computational Intelligence and Intelligent Informatics

JF - Journal of Advanced Computational Intelligence and Intelligent Informatics

SN - 1343-0130

IS - 6

ER -