L*-Based Learning of Markov Decision Processes

Martin Tappler, Bernhard Aichernig, Giovanni Bacci, Maria Eichlseder, Kim Guldstrand Larsen

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem Konferenzband

Abstract

Automata learning techniques automatically generate system models from test observations. These techniques usually fall into two categories: passive and active. Passive learning uses a predetermined data set, e.g., system logs. In contrast, active learning actively queries the system under learning, which is considered more efficient.

An influential active learning technique is Angluin’s L∗
algorithm for regular languages which inspired several generalisations from DFAs to other automata-based modelling formalisms. In this work, we study L∗-based learning of deterministic Markov decision processes, first assuming an ideal setting with perfect information. Then, we relax this assumption and present a novel learning algorithm that collects information by sampling system traces via testing. Experiments with the implementation of our sampling-based algorithm suggest that it achieves better accuracy than state-of-the-art passive learning techniques with the same amount of test data. Unlike existing learning algorithms with predefined states, our algorithm learns the complete model structure including the states.
Originalspracheenglisch
TitelFormal Methods - The Next 30 Years
Redakteure/-innenMaurice H. ter Beek, Annabelle McIver, José N. Oliveria
ErscheinungsortCham
Herausgeber (Verlag)Springer
Seiten651 - 669
Seitenumfang19
ISBN (elektronisch)978-3-030-30942-8
ISBN (Print)978-3-030-30941-1
DOIs
PublikationsstatusVeröffentlicht - 2019
Veranstaltung2019 International Symposium on Formal Methods - Porto, Portugal
Dauer: 7 Okt 201911 Okt 2019

Publikationsreihe

NameLecture Notes in Computer Science
Band11800

Konferenz

Konferenz2019 International Symposium on Formal Methods
KurztitelFM 2019
LandPortugal
OrtPorto
Zeitraum7/10/1911/10/19

Fields of Expertise

  • Information, Communication & Computing

Fingerprint Untersuchen Sie die Forschungsthemen von „L*-Based Learning of Markov Decision Processes“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren