Logo des Repositoriums
 

Formal Verification of Intelligent Hybrid Systems that are modeled with Simulink and the Reinforcement Learning Toolbox

dc.contributor.authorAdelt, Julius
dc.contributor.authorLiebrenz, Timm
dc.contributor.authorHerber, Paula
dc.contributor.editorEngels, Gregor
dc.contributor.editorHebig, Regina
dc.contributor.editorTichy, Matthias
dc.date.accessioned2023-01-18T13:38:51Z
dc.date.available2023-01-18T13:38:51Z
dc.date.issued2023
dc.description.abstractReinforcement Learning (RL) is a powerful technique to control intelligent hybrid systems (HS) in dynamic and uncertain environments. However, formally guaranteeing safe behavior of intelligent HS is hard because formal descriptions are often not available in industrial design processes and hard to obtain for RL. Furthermore, the intertwined discrete and continuous behavior of hybrid systems results in limited scalability of automatic verification methods, such as model checking. This makes deductive verification desirable. In this paper, we summarize our approach for deductive verification of intelligent HS with embedded RL components that are modeled with Simulink and the RL Toolbox. This paper was originally published at the Formal Methods conference 2021 (FM21) [ALH21].en
dc.identifier.isbn978-3-88579-726-5
dc.identifier.pissn1617-5468
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/40113
dc.language.isoen
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofSoftware Engineering 2023
dc.relation.ispartofseriesLecture Notes in Informatics (LNI) - Proceedings, Volume P-332
dc.subjectFormal Verification
dc.subjectTheorem Proving
dc.subjectHybrid Systems
dc.subjectSafe Reinforcement Learning
dc.titleFormal Verification of Intelligent Hybrid Systems that are modeled with Simulink and the Reinforcement Learning Toolboxen
dc.typeText/Conference Paper
gi.citation.endPage30
gi.citation.publisherPlaceBonn
gi.citation.startPage29
gi.conference.date20.–24. Februar 2023
gi.conference.locationPaderborn
gi.conference.sessiontitleWissenschaftliches Hauptprogramm

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
paper1.pdf
Größe:
282.45 KB
Format:
Adobe Portable Document Format