Multi-objective bandit algorithms with Chebyshev scalarization.

Simple item page
dc.centroE.T.S.I. Informáticaes_ES
dc.contributor.authorMandow-Andaluz, Lorenzo
dc.contributor.authorMartín-Albo, Sergio
dc.contributor.authorPérez-de-la-Cruz-Molina, José Luis
dc.date.accessioned2023-11-10T07:48:49Z
dc.date.available2023-11-10T07:48:49Z
dc.date.created2023
dc.date.issued2023
dc.departamentoLenguajes y Ciencias de la Computación
dc.description.abstractIn this paper we analyze several alternatives for Chebyshev scalarization in multi-objective bandit problems. The alternatives are evaluated on a reference bi-objective benchmark problem of Pareto frontier approximation. Performance is analyzed according to three measures: probability of selecting an optimal action, regret, and unfairness. The paper presents a new algorithm that improves the speed of convergence over previous proposals at least by one order of magnitude.es_ES
dc.description.sponsorshipFinanciado por Plan Propio de Investigación de la Universidad de Málaga - Campus de Excelencia Internacional Andalucía Tech. L. Mandow supported by project IRIS PID2021-122812OB-I00 (co-financed by FEDER funds). This research is partially supported by the Spanish Ministry of Science and Innovation, the European Regional Development Fund (FEDER), Junta de Andalucía (JA), and Universidad de Málaga (UMA) through the research projects with reference PID2021-122381OB-I00 and UMA20-FEDERJA-065. S. Martín-Albo supported by Beca de Iniciación a la Investigación para estudiantes de grado y máster, I Plan Propio de Investigación y Transferencia de la Universidad de Málaga, España.es_ES
dc.identifier.urihttps://hdl.handle.net/10630/27987
dc.language.isoenges_ES
dc.relation.eventdateOctubre 2023es_ES
dc.relation.eventplaceCracovia (Polonia)es_ES
dc.relation.eventtitleMODeM 2023 (Multi-Objective Decision Making Workshop at ECAI 2023)es_ES
dc.rights.accessRightsopen accesses_ES
dc.subjectProbabilidadeses_ES
dc.subjectToma de decisiones multicriterioes_ES
dc.subject.otherMulti-objective decision makinges_ES
dc.subject.otherChebyshev scalarizationes_ES
dc.subject.otherTchebycheff scalarizationes_ES
dc.subject.otherMulti-armed bandit problemes_ES
dc.titleMulti-objective bandit algorithms with Chebyshev scalarization.es_ES
dc.typeconference outputes_ES
dspace.entity.typePublication
relation.isAuthorOfPublicationb4b11711-73ab-4cd0-854c-8ab2735e829d
relation.isAuthorOfPublicationb7e65043-46cc-445b-8d8f-b4c7ad4f1c06
relation.isAuthorOfPublication.latestForDiscoveryb4b11711-73ab-4cd0-854c-8ab2735e829d

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
2023-modem-prerpint-riuma.pdf
Size:
329.46 KB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Ponencias, Comunicaciones a congresos y Pósteres