https://www.mdu.se/

mdh.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Model Checking for Reinforcement Learning in Autonomous Driving: One Can Do More Than You Think!
Mälardalens universitet, Akademin för innovation, design och teknik, Inbyggda system. Formal Modelling and Analysis of Embedded Systems.
2024 (engelsk)Inngår i: Proceedings Sixth International Workshop on Formal Methods for Autonomous Systems, 2024, Vol. 411, s. 160-177Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Most reinforcement learning (RL) platforms use high-level programming languages, such as OpenAI Gymnasium using Python. These frameworks provide various API and benchmarks for testing RL algorithms in different domains, such as autonomous driving (AD) and robotics. These platforms often emphasise the design of RL algorithms and the training performance but neglect the correctness of models and reward functions, which can be crucial for the successful application of RL. This paper proposes using formal methods to model AD systems and demonstrates how model checking (MC) can be used in RL for AD. Most studies combining MC and RL focus on safety, such as safety shields. However, this paper shows different facets where MC can strengthen RL. First, an MC-based model pre-analysis can reveal bugs with respect to sensor accuracy and learning step size. This step serves as a preparation of RL, which saves time if bugs exist and deepens users' understanding of the target system. Second, reward automata can benefit the design of reward functions and greatly improve learning performance especially when the learning objectives are multiple. All these findings are supported by experiments. 

sted, utgiver, år, opplag, sider
2024. Vol. 411, s. 160-177
Serie
Electronic Proceedings in Theoretical Computer Science, ISSN 2075-2180
HSV kategori
Identifikatorer
URN: urn:nbn:se:mdh:diva-69356DOI: 10.4204/eptcs.411.11ISI: 001376926700012Scopus ID: 2-s2.0-85211891478OAI: oai:DiVA.org:mdh-69356DiVA, id: diva2:1919306
Konferanse
Sixth International Workshop on Formal Methods for Autonomous Systems (FMAS), Manchester, England, 11/11-13/11, 2024
Tilgjengelig fra: 2024-12-09 Laget: 2024-12-09 Sist oppdatert: 2025-04-09bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Person

Gu, Rong

Søk i DiVA

Av forfatter/redaktør
Gu, Rong
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 22 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf