Strategy Representation by Decision Trees with Linear Classifiers

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F19%3A00108295" target="_blank" >RIV/00216224:14330/19:00108295 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-030-30281-8_7" target="_blank" >http://dx.doi.org/10.1007/978-3-030-30281-8_7</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-30281-8_7" target="_blank" >10.1007/978-3-030-30281-8_7</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Strategy Representation by Decision Trees with Linear Classifiers

Popis výsledku v původním jazyce

Graph games and Markov decision processes (MDPs) are standard models in reactive synthesis and verification of probabilistic systems with nondeterminism. The class of omega-regular winning conditions; e.g., safety, reachability, liveness, parity conditions; provides a robust and expressive specification formalism for properties that arise in analysis of reactive systems. The resolutions of nondeterminism in games and MDPs are represented as strategies, and we consider succinct representation of such strategies. The decision-tree data structure from machine learning retains the flavor of decisions of strategies and allows entropy-based minimization to obtain succinct trees. However, in contrast to traditional machine-learning problems where small errors are allowed, for winning strategies in graph games and MDPs no error is allowed, and the decision tree must represent the entire strategy. In this work we propose decision trees with linear classifiers for representation of strategies in graph games and MDPs. We have implemented strategy representation using this data structure and we present experimental results for problems on graph games and MDPs, which show that this new data structure presents a much more efficient strategy representation as compared to standard decision trees.

Název v anglickém jazyce

Strategy Representation by Decision Trees with Linear Classifiers

Popis výsledku anglicky

Graph games and Markov decision processes (MDPs) are standard models in reactive synthesis and verification of probabilistic systems with nondeterminism. The class of omega-regular winning conditions; e.g., safety, reachability, liveness, parity conditions; provides a robust and expressive specification formalism for properties that arise in analysis of reactive systems. The resolutions of nondeterminism in games and MDPs are represented as strategies, and we consider succinct representation of such strategies. The decision-tree data structure from machine learning retains the flavor of decisions of strategies and allows entropy-based minimization to obtain succinct trees. However, in contrast to traditional machine-learning problems where small errors are allowed, for winning strategies in graph games and MDPs no error is allowed, and the decision tree must represent the entire strategy. In this work we propose decision trees with linear classifiers for representation of strategies in graph games and MDPs. We have implemented strategy representation using this data structure and we present experimental results for problems on graph games and MDPs, which show that this new data structure presents a much more efficient strategy representation as compared to standard decision trees.

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

<a href="/cs/project/GA18-11193S" target="_blank" >GA18-11193S: Algoritmy pro diskrétní systémy a hry s nekonečně mnoha stavy</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Quantitative Evaluation of Systems (QEST 2019)

ISBN

9783030302801

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

20

Strana od-do

109-128

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Cham

Datum konání akce

1. 1. 2019

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

000679281300007