Markov decision processes and stochastic games with total effective payoff

Markov decision processes and stochastic games with total effective payoff Ann Oper Res https://doi.org/10.1007/s10479-018-2898-8 S.I.: STOCHASTIC MODELING AND OPTIMIZATION, IN MEMORY OF ANDRÁS PRÉKOPA Markov decision processes and stochastic games with total effective payoff 1 2 Endre Boros · Khaled Elbassioni · 3 4 Vladimir Gurvich · Kazuhisa Makino © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract We consider finite Markov decision processes with undiscounted total effective payoff. We show that there exist uniformly optimal pure and stationary strategies that can be computed by solving a polynomial number of linear programs. This implies that in a two- player zero-sum stochastic game with perfect information and with total effective payoff there exists a stationary best response to any stationary strategy of the opponent. From this, we derive the existence of a uniformly optimal pure and stationary saddle point. Finally we show that mean payoff can be viewed as a special case of total payoff. Keywords Markov decision processes · Stochastic games · Linear programming · Optimal stationary strategies · Equilibrium computation This research was partially supported by the Scientific Grant-in-Aid from Ministry of Education, Science, Sports and Culture of Japan. The first author also thanks for partial support the National Science Foundation (Grant and IIS-1161476). The research http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Annals of Operations Research Springer Journals

Markov decision processes and stochastic games with total effective payoff

Loading next page...
 
/lp/springer_journal/markov-decision-processes-and-stochastic-games-with-total-effective-6sDWSmQCQs
Publisher
Springer Journals
Copyright
Copyright © 2018 by Springer Science+Business Media, LLC, part of Springer Nature
Subject
Business and Management; Operations Research/Decision Theory; Combinatorics; Theory of Computation
ISSN
0254-5330
eISSN
1572-9338
D.O.I.
10.1007/s10479-018-2898-8
Publisher site
See Article on Publisher Site

Abstract

Ann Oper Res https://doi.org/10.1007/s10479-018-2898-8 S.I.: STOCHASTIC MODELING AND OPTIMIZATION, IN MEMORY OF ANDRÁS PRÉKOPA Markov decision processes and stochastic games with total effective payoff 1 2 Endre Boros · Khaled Elbassioni · 3 4 Vladimir Gurvich · Kazuhisa Makino © Springer Science+Business Media, LLC, part of Springer Nature 2018 Abstract We consider finite Markov decision processes with undiscounted total effective payoff. We show that there exist uniformly optimal pure and stationary strategies that can be computed by solving a polynomial number of linear programs. This implies that in a two- player zero-sum stochastic game with perfect information and with total effective payoff there exists a stationary best response to any stationary strategy of the opponent. From this, we derive the existence of a uniformly optimal pure and stationary saddle point. Finally we show that mean payoff can be viewed as a special case of total payoff. Keywords Markov decision processes · Stochastic games · Linear programming · Optimal stationary strategies · Equilibrium computation This research was partially supported by the Scientific Grant-in-Aid from Ministry of Education, Science, Sports and Culture of Japan. The first author also thanks for partial support the National Science Foundation (Grant and IIS-1161476). The research

Journal

Annals of Operations ResearchSpringer Journals

Published: May 28, 2018

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off