Multiple Mean-Payoff Optimization Under Local Stability Constraints

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F25%3A00141698" target="_blank" >RIV/00216224:14330/25:00141698 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1609/aaai.v39i25.34856" target="_blank" >http://dx.doi.org/10.1609/aaai.v39i25.34856</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1609/aaai.v39i25.34856" target="_blank" >10.1609/aaai.v39i25.34856</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Multiple Mean-Payoff Optimization Under Local Stability Constraints

Popis výsledku v původním jazyce

The long-run average payoff per transition (mean payoff) is the main tool for specifying the performance and dependability properties of discrete systems. The problem of constructing a controller (strategy) simultaneously optimizing several mean payoffs has been deeply studied for stochastic and game-theoretic models. One common issue of the constructed controllers is the instability of the mean payoffs, measured by the deviations of the average rewards per transition computed in a finite "window" sliding along a run. Unfortunately, the problem of simultaneously optimizing the mean payoffs under local stability constraints is computationally hard, and the existing works do not provide a practically usable algorithm even for non-stochastic models such as two-player games. In this paper, we design and evaluate the first efficient and scalable solution to this problem applicable to Markov decision processes.

Název v anglickém jazyce

Multiple Mean-Payoff Optimization Under Local Stability Constraints

Popis výsledku anglicky

The long-run average payoff per transition (mean payoff) is the main tool for specifying the performance and dependability properties of discrete systems. The problem of constructing a controller (strategy) simultaneously optimizing several mean payoffs has been deeply studied for stochastic and game-theoretic models. One common issue of the constructed controllers is the instability of the mean payoffs, measured by the deviations of the average rewards per transition computed in a finite "window" sliding along a run. Unfortunately, the problem of simultaneously optimizing the mean payoffs under local stability constraints is computationally hard, and the existing works do not provide a practically usable algorithm even for non-stochastic models such as two-player games. In this paper, we design and evaluate the first efficient and scalable solution to this problem applicable to Markov decision processes.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39 No. 25: AAAI-25 Technical Tracks 25

ISBN

9781577358978

ISSN

2159-5399

e-ISSN

2374-3468

Počet stran výsledku

8

Strana od-do

26551-26558

Název nakladatele

AAAI

Místo vydání

Palo Alto

Místo konání akce

Philadelphia, PA

Datum konání akce

1. 8. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001477487000040