{"id":"https://openalex.org/W2032950725","doi":"https://doi.org/10.1007/s10994-014-5458-8","title":"Preference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithm","display_name":"Preference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithm","publication_year":2014,"publication_date":"2014-07-02","ids":{"openalex":"https://openalex.org/W2032950725","doi":"https://doi.org/10.1007/s10994-014-5458-8","mag":"2032950725"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-014-5458-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-014-5458-8","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-014-5458-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-014-5458-8.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047520070","display_name":"R\u00f3bert Busa\u2010Fekete","orcid":"https://orcid.org/0000-0002-3691-650X"},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I4210166048","display_name":"Gesellschaft Fur Mathematik Und Datenverarbeitung","ror":"https://ror.org/02g6d4t03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210166048"]}],"countries":["DE","HU"],"is_corresponding":true,"raw_author_name":"R\u00f3bert Busa-Fekete","raw_affiliation_strings":["Fachbereich Mathematik und Informatik [Marburg] [Dept. of Math and Computer Science] (Fb. 12 - Mathematik und Informatik, Hans-Meerwein-Stra\u00dfe, D-35032 Marburg Germany - Germany)","MTA-SZTE Research Group on Artificial Intelligence (H-6701 Szeged, Postafi\u00f3k 652., Hungary - Hungary)"],"affiliations":[{"raw_affiliation_string":"Fachbereich Mathematik und Informatik [Marburg] [Dept. of Math and Computer Science] (Fb. 12 - Mathematik und Informatik, Hans-Meerwein-Stra\u00dfe, D-35032 Marburg Germany - Germany)","institution_ids":["https://openalex.org/I4210166048"]},{"raw_affiliation_string":"MTA-SZTE Research Group on Artificial Intelligence (H-6701 Szeged, Postafi\u00f3k 652., Hungary - Hungary)","institution_ids":["https://openalex.org/I4210152167"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048258912","display_name":"Bal\u00e1zs Sz\u00f6r\u00e9nyi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]},{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR","HU"],"is_corresponding":false,"raw_author_name":"Bal\u00e1zs Sz\u00f6r\u00e9nyi","raw_affiliation_strings":["MTA-SZTE Research Group on Artificial Intelligence (H-6701 Szeged, Postafi\u00f3k 652., Hungary - Hungary)","SEQUEL - Sequential Learning (Centre Inria de l'Universit\u00e9 de Lille ,170 Av. de Bretagne, 59000 Lille - France)"],"affiliations":[{"raw_affiliation_string":"MTA-SZTE Research Group on Artificial Intelligence (H-6701 Szeged, Postafi\u00f3k 652., Hungary - Hungary)","institution_ids":["https://openalex.org/I4210152167"]},{"raw_affiliation_string":"SEQUEL - Sequential Learning (Centre Inria de l'Universit\u00e9 de Lille ,170 Av. de Bretagne, 59000 Lille - France)","institution_ids":["https://openalex.org/I2279609970"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073106112","display_name":"Paul Weng","orcid":"https://orcid.org/0000-0002-2008-4569"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Weng","raw_affiliation_strings":["DECISION (France)"],"affiliations":[{"raw_affiliation_string":"DECISION (France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043737358","display_name":"Weiwei Cheng","orcid":"https://orcid.org/0000-0002-3381-4188"},"institutions":[{"id":"https://openalex.org/I4210166048","display_name":"Gesellschaft Fur Mathematik Und Datenverarbeitung","ror":"https://ror.org/02g6d4t03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210166048"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Weiwei Cheng","raw_affiliation_strings":["Fachbereich Mathematik und Informatik [Marburg] [Dept. of Math and Computer Science] (Fb. 12 - Mathematik und Informatik, Hans-Meerwein-Stra\u00dfe, D-35032 Marburg Germany - Germany)"],"affiliations":[{"raw_affiliation_string":"Fachbereich Mathematik und Informatik [Marburg] [Dept. of Math and Computer Science] (Fb. 12 - Mathematik und Informatik, Hans-Meerwein-Stra\u00dfe, D-35032 Marburg Germany - Germany)","institution_ids":["https://openalex.org/I4210166048"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059439673","display_name":"Eyke H\u00fcllermeier","orcid":"https://orcid.org/0000-0002-9944-4108"},"institutions":[{"id":"https://openalex.org/I4210166048","display_name":"Gesellschaft Fur Mathematik Und Datenverarbeitung","ror":"https://ror.org/02g6d4t03","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210166048"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eyke H\u00fcllermeier","raw_affiliation_strings":["Fachbereich Mathematik und Informatik [Marburg] [Dept. of Math and Computer Science] (Fb. 12 - Mathematik und Informatik, Hans-Meerwein-Stra\u00dfe, D-35032 Marburg Germany - Germany)"],"affiliations":[{"raw_affiliation_string":"Fachbereich Mathematik und Informatik [Marburg] [Dept. of Math and Computer Science] (Fb. 12 - Mathematik und Informatik, Hans-Meerwein-Stra\u00dfe, D-35032 Marburg Germany - Germany)","institution_ids":["https://openalex.org/I4210166048"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047520070"],"corresponding_institution_ids":["https://openalex.org/I4210152167","https://openalex.org/I4210166048"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":3.3917,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93062794,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"97","issue":"3","first_page":"327","last_page":"351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7683483958244324},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.7678492069244385},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7275839447975159},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.5831488370895386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5679605007171631},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.5544933080673218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5181330442428589},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5148250460624695},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.505408525466919},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4896731674671173},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4521479904651642},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4176374673843384},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37522947788238525},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2983182668685913},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08651599287986755}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7683483958244324},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.7678492069244385},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7275839447975159},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.5831488370895386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5679605007171631},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.5544933080673218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181330442428589},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5148250460624695},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.505408525466919},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4896731674671173},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4521479904651642},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4176374673843384},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37522947788238525},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2983182668685913},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08651599287986755},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10994-014-5458-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-014-5458-8","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-014-5458-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:publicatio.bibl.u-szeged.hu:4795","is_oa":true,"landing_page_url":"http://publicatio.bibl.u-szeged.hu/4795/7/springer2014.97.3.jpg","pdf_url":null,"source":{"id":"https://openalex.org/S4306400436","display_name":"SZTE Publicatio Repozit\u00f3rium (University of Szeged)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I227486990","host_organization_name":"University of Szeged","host_organization_lineage":["https://openalex.org/I227486990"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Cikk"},{"id":"pmh:oai:HAL:hal-01079370v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-01079370","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning, 2014, 97 (3), pp.327-351. ⟨10.1007/s10994-014-5458-8⟩","raw_type":"Journal articles"},{"id":"pmh:oai:epub.ub.uni-muenchen.de:91496","is_oa":false,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bvb:19-epub-91496-7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning","raw_type":"doc-type:article"}],"best_oa_location":{"id":"doi:10.1007/s10994-014-5458-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-014-5458-8","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10994-014-5458-8.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2032950725.pdf","grobid_xml":"https://content.openalex.org/works/W2032950725.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W42649658","https://openalex.org/W122021961","https://openalex.org/W199168817","https://openalex.org/W1484675474","https://openalex.org/W1510052597","https://openalex.org/W1553373771","https://openalex.org/W1576660662","https://openalex.org/W1583155004","https://openalex.org/W1583953806","https://openalex.org/W1585839838","https://openalex.org/W1605438009","https://openalex.org/W1861050369","https://openalex.org/W1965281372","https://openalex.org/W1976503157","https://openalex.org/W1977326596","https://openalex.org/W1985412770","https://openalex.org/W1999874108","https://openalex.org/W2012367441","https://openalex.org/W2027907186","https://openalex.org/W2035720976","https://openalex.org/W2044493620","https://openalex.org/W2057785395","https://openalex.org/W2059654640","https://openalex.org/W2061562262","https://openalex.org/W2066251678","https://openalex.org/W2073384958","https://openalex.org/W2097452095","https://openalex.org/W2101723727","https://openalex.org/W2103012681","https://openalex.org/W2105947986","https://openalex.org/W2113023245","https://openalex.org/W2116671302","https://openalex.org/W2119567691","https://openalex.org/W2119717200","https://openalex.org/W2121863487","https://openalex.org/W2125612430","https://openalex.org/W2128677288","https://openalex.org/W2129297552","https://openalex.org/W2132083787","https://openalex.org/W2132414174","https://openalex.org/W2134282875","https://openalex.org/W2134289401","https://openalex.org/W2143426320","https://openalex.org/W2154023516","https://openalex.org/W2156682402","https://openalex.org/W2161735965","https://openalex.org/W2165060096","https://openalex.org/W2165962877","https://openalex.org/W2168405694","https://openalex.org/W2168810201","https://openalex.org/W2172131460","https://openalex.org/W2241261888","https://openalex.org/W2315464424","https://openalex.org/W2334782222","https://openalex.org/W2486609979","https://openalex.org/W2596585349","https://openalex.org/W2604272474","https://openalex.org/W2735944294","https://openalex.org/W2797333853","https://openalex.org/W2912748147","https://openalex.org/W3139377883","https://openalex.org/W4211221179","https://openalex.org/W4233413206","https://openalex.org/W4292408320","https://openalex.org/W6675498099","https://openalex.org/W6741305981","https://openalex.org/W6792155000"],"related_works":["https://openalex.org/W1968265719","https://openalex.org/W1515481220","https://openalex.org/W2060303324","https://openalex.org/W4206238124","https://openalex.org/W4324116389","https://openalex.org/W2161073979","https://openalex.org/W3126212998","https://openalex.org/W2516425091","https://openalex.org/W3105737538","https://openalex.org/W4389072749"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}