Simple record

dc.contributor.authorArana-Arexolaleiba, Nestor
dc.contributor.otherOdriozola Olalde, Haritz
dc.contributor.otherZamalloa, Maider
dc.date.accessioned2023-03-02T13:47:20Z
dc.date.available2023-03-02T13:47:20Z
dc.date.issued2023
dc.identifier.isbn979-8-3503-9868-7en
dc.identifier.issn979-8-3503-9868-7en
dc.identifier.otherhttps://katalogoa.mondragon.edu/janium-bin/janium_login_opac.pl?find&ficha_no=170352en
dc.identifier.urihttps://hdl.handle.net/20.500.11984/6031
dc.description.abstractReinforcement Learning (RL) algorithms are showing promising results in simulated environments, but their replication in real physical applications, even more so in safety-critical applications, is not yet guaranteed. Ensuring the functional safety of RL algorithms is not a trivial task since the physical integrity of the target system, also called environment, especially when there is interaction with humans, may depend on it. Among the methods recently developed with the objective of guaranteeing safety, Shielded Reinforcement Learning is defined, which defines an interaction mechanism if the action event proposed by the agent causes a non-safe state. This article provides an overview of the different Shielding Reinforcement Learning approaches. In addition to summarising the techniques used by each of them, their advantages and disadvantages are discussed. Finally, the shortcomings associated with Shielded Reinforcement Learning methods that can lead to risk or unsafe situations are discussed.en
dc.description.sponsorshipGobierno Vasco-Eusko Jaurlaritzaes
dc.description.sponsorshipComisión Europeaes
dc.language.isoengen
dc.publisherIEEEen
dc.rights© 2023 IEEEen
dc.subjectReinforcement learningen
dc.subjectSystem integrationen
dc.subjectControl systemsen
dc.subject3D printingen
dc.subjectRobot sensing systemsen
dc.subjectRobustnessen
dc.subjectSafetyen
dc.titleShielded Reinforcement Learning: A review of reactive methods for safe learningen
dcterms.accessRightshttp://purl.org/coar/access_right/c_f1cfen
dcterms.source2023 IEEE/SICE International Symposium on System Integrations (SII)en
local.contributor.groupRobótica y automatizaciónes
local.description.peerreviewedtrueen
local.identifier.doihttps://doi.org/10.1109/SII55687.2023.10039301en
local.relation.projectIDinfo:eu-repo/grantAgreement/GV/Elkartek 2021/KK-2021-00111/CAPV/Arquitectura embebida para nuevas aplicaciones edge computing/ERTZEANen
local.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/8570617/EU/Networking for research and development of human interactive and sensitive robotics taking advantage of additive manufacturing/R2P2en
local.embargo.enddate2025-02-15
local.contributor.otherinstitutionhttps://ror.org/03hp1m080es
local.source.detailsAtlanta. 17-20 January,en
oaire.format.mimetypeapplication/pdf
oaire.file$DSPACE\assetstore
oaire.resourceTypehttp://purl.org/coar/resource_type/c_c94fen
oaire.versionhttp://purl.org/coar/version/c_ab4af688f83e57aaen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Simple record