L*-Based Learning of Markov Decision Processes

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.
Original languageEnglish
Title of host publicationFormal Methods - The Next 30 Years
EditorsMaurice H. ter Beek, Annabelle McIver, José N. Oliveria
Place of PublicationCham
PublisherSpringer
Pages651 - 669
Number of pages19
ISBN (Electronic)978-3-030-30942-8
ISBN (Print)978-3-030-30941-1
DOIs
Publication statusPublished - 2019
Event2019 International Symposium on Formal Methods - Porto, Portugal
Duration: 7 Oct 201911 Oct 2019

Publication series

NameLecture Notes in Computer Science
Volume11800

Conference

Conference2019 International Symposium on Formal Methods
Abbreviated titleFM 2019
CountryPortugal
CityPorto
Period7/10/1911/10/19

Fields of Expertise

  • Information, Communication & Computing

Fingerprint Dive into the research topics of 'L*-Based Learning of Markov Decision Processes'. Together they form a unique fingerprint.

Cite this