Show simple item record

AuthorHihn, Heinkedc.contributor.author
AuthorGottwald, Sebastiandc.contributor.author
AuthorBraun, Daniel-Alexanderdc.contributor.author
Date of accession2020-02-26T12:50:59Zdc.date.accessioned
Available in OPARU since2020-02-26T12:50:59Zdc.date.available
Date of first publication2020-02-26dc.date.issued
AbstractInformation-theoretic bounded rationality describes utility-optimizing decision-makers whose limited information-processing capabilities are formalized by information constraints. One of the consequences of bounded rationality is that resource-limited decision-makers can join together to solve decision-making problems that are beyond the capabilities of each individual. Here, we study an information-theoretic principle that drives division of labor and specialization when decision-makers with information constraints are joined together. We devise an on-line learning rule of this principle that learns a partitioning of the problem space such that it can be solved by specialized linear policies. We demonstrate the approach for decision-making problems whose complexity exceeds the capabilities of individual decision-makers, but can be solved by combining the decision-makers optimally. The strength of the model is that it is abstract and principled, yet has direct applications in classification, regression, reinforcement learning and adaptive control.dc.description.abstract
Languageen_USdc.language.iso
PublisherUniversität Ulmdc.publisher
LicenseStandard (ohne Print-on-Demand)dc.rights
Link to license texthttps://oparu.uni-ulm.de/xmlui/license_opod_v1dc.rights.uri
KeywordBounded rationalitydc.subject
KeywordGain schechudlingdc.subject
Dewey Decimal GroupDDC 004 / Data processing & computer sciencedc.subject.ddc
Dewey Decimal GroupDDC 620 / Engineering & allied operationsdc.subject.ddc
LCSHClassificationdc.subject.lcsh
LCSHDecision makingdc.subject.lcsh
LCSHReinforcement learningdc.subject.lcsh
TitleAn information-theoretic on-line learning principle for specialization in hierarchical decision-making systemsdc.title
Resource typeBeitrag zu einer Konferenzdc.type
VersionacceptedVersiondc.description.version
DOIhttp://dx.doi.org/10.18725/OPARU-25586dc.identifier.doi
URNhttp://nbn-resolving.de/urn:nbn:de:bsz:289-oparu-25649-8dc.identifier.urn
GNDEingeschränkte Rationalitätdc.subject.gnd
GNDKlassifikationdc.subject.gnd
GNDEntscheidungsfindungdc.subject.gnd
GNDBestärkendes Lernen (Künstliche Intelligenz)dc.subject.gnd
GNDGewinnplanungdc.subject.gnd
FacultyFakultät für Ingenieurwissenschaften, Informatik und Psychologieuulm.affiliationGeneral
InstitutionInstitut für Neuroinformatikuulm.affiliationSpecific
Peer reviewjauulm.peerReview
DCMI TypeTextuulm.typeDCMI
CategoryPublikationenuulm.category
arXiv ID of original publicationarXiv:1907.11452v3dc.relation1.arxiv
Source - Volume2019source.volume
EU project uulmBRISC / Bounded Rationality in Sensorimotor Coordination / EC / H2020 / 678082uulm.projectEU
Conference nameIEEE Conference on Decision and Controluulm.conferenceName
Conference placeNiceuulm.conferencePlace
Conference start date2019-12-11uulm.conferenceStartDate
Conference end date2019-12-13uulm.conferenceEndDate
WoS000560779003059uulm.identifier.wos
Bibliographyuulmuulm.bibliographie


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record