Sporadic Overtaking Optimality in Markov Decision Problems

János Flesch; Arkadi Predtetchinski; Eilon Solan

doi:10.1007/s13235-016-0186-2

Sporadic Overtaking Optimality in Markov Decision Problems

János Flesch, Arkadi Predtetchinski, Eilon Solan

School of Mathematical Sciences

Tel Aviv University

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

Abstract

This paper examines a notion of sporadic overtaking optimality in the context of Markov decision problems (MDP). For the class of deterministic MDPs, we prove the existence of pure stationary sporadic overtaking optimal strategies under both the discounted and the average payoff evaluations. Moreover, we examine logical connections between sporadic overtaking optimality and Blackwell optimality. In the class of nondeterministic MDPs, we give examples that admit no sporadic overtaking optimal strategy and discuss a number of alternative definitions of this concept.

Original language	English
Pages (from-to)	212-228
Number of pages	17
Journal	Dynamic Games and Applications
Volume	7
Issue number	2
DOIs	https://doi.org/10.1007/s13235-016-0186-2
State	Published - 1 Jun 2017

Keywords

Blackwell optimality
Markov decision problems
Overtaking optimality
Sporadic overtaking optimality

All Science Journal Classification (ASJC) codes

Computational Mathematics
Applied Mathematics
Economics and Econometrics
Statistics and Probability
Computer Science Applications
Computational Theory and Mathematics
Computer Graphics and Computer-Aided Design

Access to Document

10.1007/s13235-016-0186-2

Cite this

@article{a959aa933bd84a069ea51d1f6be49ced,

title = "Sporadic Overtaking Optimality in Markov Decision Problems",

abstract = "This paper examines a notion of sporadic overtaking optimality in the context of Markov decision problems (MDP). For the class of deterministic MDPs, we prove the existence of pure stationary sporadic overtaking optimal strategies under both the discounted and the average payoff evaluations. Moreover, we examine logical connections between sporadic overtaking optimality and Blackwell optimality. In the class of nondeterministic MDPs, we give examples that admit no sporadic overtaking optimal strategy and discuss a number of alternative definitions of this concept.",

keywords = "Blackwell optimality, Markov decision problems, Overtaking optimality, Sporadic overtaking optimality",

author = "J{\'a}nos Flesch and Arkadi Predtetchinski and Eilon Solan",

note = "Publisher Copyright: {\textcopyright} 2016, The Author(s).",

year = "2017",

month = jun,

day = "1",

doi = "10.1007/s13235-016-0186-2",

language = "الإنجليزيّة",

volume = "7",

pages = "212--228",

journal = "Dynamic Games and Applications",

issn = "2153-0785",

publisher = "Springer Science + Business Media",

number = "2",

}

TY - JOUR

T1 - Sporadic Overtaking Optimality in Markov Decision Problems

AU - Flesch, János

AU - Predtetchinski, Arkadi

AU - Solan, Eilon

PY - 2017/6/1

Y1 - 2017/6/1

N2 - This paper examines a notion of sporadic overtaking optimality in the context of Markov decision problems (MDP). For the class of deterministic MDPs, we prove the existence of pure stationary sporadic overtaking optimal strategies under both the discounted and the average payoff evaluations. Moreover, we examine logical connections between sporadic overtaking optimality and Blackwell optimality. In the class of nondeterministic MDPs, we give examples that admit no sporadic overtaking optimal strategy and discuss a number of alternative definitions of this concept.

AB - This paper examines a notion of sporadic overtaking optimality in the context of Markov decision problems (MDP). For the class of deterministic MDPs, we prove the existence of pure stationary sporadic overtaking optimal strategies under both the discounted and the average payoff evaluations. Moreover, we examine logical connections between sporadic overtaking optimality and Blackwell optimality. In the class of nondeterministic MDPs, we give examples that admit no sporadic overtaking optimal strategy and discuss a number of alternative definitions of this concept.

KW - Blackwell optimality

KW - Markov decision problems

KW - Overtaking optimality

KW - Sporadic overtaking optimality

UR - http://www.scopus.com/inward/record.url?scp=85017177854&partnerID=8YFLogxK

U2 - 10.1007/s13235-016-0186-2

DO - 10.1007/s13235-016-0186-2

M3 - مقالة

SN - 2153-0785

VL - 7

SP - 212

EP - 228

JO - Dynamic Games and Applications

JF - Dynamic Games and Applications

IS - 2

ER -

Sporadic Overtaking Optimality in Markov Decision Problems

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this