{"id":"https://openalex.org/W2951763655","doi":"https://doi.org/10.1609/aaai.v33i01.33015549","title":"Dueling Bandits with Qualitative Feedback","display_name":"Dueling Bandits with Qualitative Feedback","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2951763655","doi":"https://doi.org/10.1609/aaai.v33i01.33015549","mag":"2951763655"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33015549","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015549","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4496/4374","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4496/4374","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035966558","display_name":"Liyuan Xu","orcid":"https://orcid.org/0000-0001-7416-3871"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Liyuan Xu","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112464181","display_name":"Junya Honda","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junya Honda","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072744508","display_name":"Masashi Sugiyama","orcid":"https://orcid.org/0000-0001-6658-6743"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masashi Sugiyama","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"5549","last_page":"5556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965000152587891,"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/T11182","display_name":"Auction Theory and Applications","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.9472106695175171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6865963935852051},{"id":"https://openalex.org/keywords/qualitative-analysis","display_name":"Qualitative analysis","score":0.5150163173675537},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5149189233779907},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4432779550552368},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.436576783657074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39070603251457214},{"id":"https://openalex.org/keywords/qualitative-research","display_name":"Qualitative research","score":0.38815295696258545},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26548975706100464},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20517393946647644}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9472106695175171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6865963935852051},{"id":"https://openalex.org/C3018587665","wikidata":"https://www.wikidata.org/wiki/Q7268696","display_name":"Qualitative analysis","level":3,"score":0.5150163173675537},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5149189233779907},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4432779550552368},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.436576783657074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39070603251457214},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.38815295696258545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26548975706100464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20517393946647644},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33015549","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015549","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4496/4374","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4496","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4496","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33015549","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33015549","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4496/4374","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1532979674","display_name":"Construction of knowledge discovery algorithms based on information theoretic methods","funder_award_id":"18K17998","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3538458246","display_name":"Theory and Application of Statistical Reinforcement Learning","funder_award_id":"17H00757","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8941621529","display_name":null,"funder_award_id":"KAKENHI 17H00757","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320317743","display_name":"Masason Foundation","ror":null},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951763655.pdf","grobid_xml":"https://content.openalex.org/works/W2951763655.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W50636094","https://openalex.org/W1518788040","https://openalex.org/W1530210183","https://openalex.org/W1553636730","https://openalex.org/W1858303725","https://openalex.org/W1862423129","https://openalex.org/W1909146639","https://openalex.org/W1972789308","https://openalex.org/W1983962754","https://openalex.org/W2007815473","https://openalex.org/W2039522160","https://openalex.org/W2044493620","https://openalex.org/W2045097767","https://openalex.org/W2108114251","https://openalex.org/W2127131211","https://openalex.org/W2141645258","https://openalex.org/W2146759922","https://openalex.org/W2156541733","https://openalex.org/W2343707533","https://openalex.org/W2555426513","https://openalex.org/W3125733173","https://openalex.org/W4234228486","https://openalex.org/W6602052860","https://openalex.org/W6639113721","https://openalex.org/W6661750875","https://openalex.org/W6661917881","https://openalex.org/W6679108983","https://openalex.org/W6704463079"],"related_works":["https://openalex.org/W2046541833","https://openalex.org/W2412051436","https://openalex.org/W1499806064","https://openalex.org/W4240869053","https://openalex.org/W2140472019","https://openalex.org/W2057857755","https://openalex.org/W2261353938","https://openalex.org/W4316090175","https://openalex.org/W2898960644","https://openalex.org/W2591867738"],"abstract_inverted_index":{"We":[0,29],"formulate":[1],"and":[2,123],"study":[3],"a":[4],"novel":[5],"multi-armed":[6],"bandit":[7,13,37],"problem":[8,39],"called":[9],"the":[10,31,35,41,48,61,68,71,74,80,103,111,120,131],"qualitative":[11,23,49,121],"dueling":[12,36],"(QDB)":[14],"problem,":[15,63,73],"where":[16,40],"an":[17],"agent":[18],"observes":[19],"not":[20],"numeric":[21],"but":[22],"feedback":[24],"by":[25,46,118],"pulling":[26],"each":[27],"arm.":[28],"employ":[30],"same":[32],"regret":[33],"as":[34],"(DB)":[38],"duel":[42,81],"is":[43],"carried":[44],"out":[45,91],"comparing":[47],"feedback.":[50],"Although":[51],"we":[52,97],"can":[53,85],"naively":[54],"use":[55],"classic":[56],"DB":[57,116,133],"algorithms":[58,101,113,117],"for":[59,102],"solving":[60],"QDB":[62,72,104],"this":[64,95],"reduction":[65],"significantly":[66,114],"worsens":[67],"performance\u2014actually,":[69],"in":[70],"probability":[75],"that":[76,110],"one":[77],"arm":[78,84],"wins":[79],"over":[82,130],"another":[83],"be":[86],"directly":[87],"estimated":[88],"without":[89],"carrying":[90],"actual":[92],"duels.":[93],"In":[94],"paper1,":[96],"propose":[98],"such":[99],"direct":[100],"problem.":[105],"Our":[106],"theoretical":[107],"analysis":[108],"shows":[109],"proposed":[112],"outperform":[115],"incorporating":[119],"feedback,":[122],"experimental":[124],"results":[125],"also":[126],"demonstrate":[127],"vast":[128],"improvement":[129],"existing":[132],"algorithms.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}