{"id":"https://openalex.org/W2829790400","doi":"https://doi.org/10.24963/ijcai.2018/776","title":"Advancements in Dueling Bandits","display_name":"Advancements in Dueling Bandits","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2829790400","doi":"https://doi.org/10.24963/ijcai.2018/776","mag":"2829790400"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2018/776","doi":"https://doi.org/10.24963/ijcai.2018/776","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/776","pdf_url":"https://www.ijcai.org/proceedings/2018/0776.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2018/0776.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069290448","display_name":"Yanan Sui","orcid":"https://orcid.org/0000-0002-9480-627X","observed_orcids":["https://orcid.org/0000-0002-9480-627X"]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanan Sui","raw_affiliation_strings":["California Institute of Technology","Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066732643","display_name":"Masrour Zoghi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Masrour Zoghi","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027441885","display_name":"Katja Hofmann","orcid":"https://orcid.org/0000-0003-3697-407X","observed_orcids":["https://orcid.org/0000-0003-3697-407X"]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katja Hofmann","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085826758","display_name":"Yisong Yue","orcid":"https://orcid.org/0000-0001-9127-1989","observed_orcids":["https://orcid.org/0000-0001-9127-1989"]},"institutions":[{"id":"https://openalex.org/I122411786","display_name":"California Institute of Technology","ror":"https://ror.org/05dxps055","country_code":"US","type":"education","lineage":["https://openalex.org/I122411786"]},{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yisong Yue","raw_affiliation_strings":["California Institute of Technology","Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California Institute of Technology","institution_ids":["https://openalex.org/I122411786"]},{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.1202,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.98004233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5502","last_page":"5510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":1.0,"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":1.0,"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":0.0,"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/T12288","display_name":"Optimization and Search Problems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/dueling-bandits","display_name":"dueling bandits","score":0.996999979019165},{"id":"https://openalex.org/keywords/e-learning","display_name":"online learning","score":0.8230000138282776},{"id":"https://openalex.org/keywords/preference-feedback","display_name":"preference feedback","score":0.9860000014305115},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"pairwise comparison","score":0.5820000171661377},{"id":"https://openalex.org/keywords/implicit-feedback","display_name":"implicit feedback","score":0.5680000185966492},{"id":"https://openalex.org/keywords/multi-armed-bandits","display_name":"multi-armed bandits","score":0.7200000286102295},{"id":"https://openalex.org/keywords/regret-minimization","display_name":"regret minimization","score":0.546999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7916271686553955},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6293560266494751},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.596528172492981},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5267528891563416},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49131980538368225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48513898253440857},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3688591718673706},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11347696185112},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09241598844528198},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2018/776","doi":"https://doi.org/10.24963/ijcai.2018/776","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/776","pdf_url":"https://www.ijcai.org/proceedings/2018/0776.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2018/776","doi":"https://doi.org/10.24963/ijcai.2018/776","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2018/776","pdf_url":"https://www.ijcai.org/proceedings/2018/0776.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2829790400.pdf","grobid_xml":"https://content.openalex.org/works/W2829790400.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W50636094","https://openalex.org/W1032589285","https://openalex.org/W1518788040","https://openalex.org/W1553636730","https://openalex.org/W1951936954","https://openalex.org/W1964631708","https://openalex.org/W1982530130","https://openalex.org/W1998498767","https://openalex.org/W1998955392","https://openalex.org/W2009979684","https://openalex.org/W2044493620","https://openalex.org/W2077902449","https://openalex.org/W2090589280","https://openalex.org/W2094790959","https://openalex.org/W2104743565","https://openalex.org/W2125735873","https://openalex.org/W2130227799","https://openalex.org/W2147892741","https://openalex.org/W2154023516","https://openalex.org/W2156541733","https://openalex.org/W2163996478","https://openalex.org/W2184294966","https://openalex.org/W2249408652","https://openalex.org/W2272560936","https://openalex.org/W2278024189","https://openalex.org/W2341805565","https://openalex.org/W2346878437","https://openalex.org/W2515978214","https://openalex.org/W2555426513","https://openalex.org/W2604370872","https://openalex.org/W2606602301","https://openalex.org/W2611619034","https://openalex.org/W2626460392","https://openalex.org/W2751686538","https://openalex.org/W2785324569","https://openalex.org/W2950876252","https://openalex.org/W2950929549","https://openalex.org/W2951092852","https://openalex.org/W2962684386","https://openalex.org/W2963878998","https://openalex.org/W2963912524","https://openalex.org/W2964081017","https://openalex.org/W2964168155","https://openalex.org/W3005507814","https://openalex.org/W3006334608","https://openalex.org/W4237910115"],"related_works":["https://openalex.org/W7207421245","https://openalex.org/W2883737864","https://openalex.org/W2130227799","https://openalex.org/W2611619034","https://openalex.org/W4221167361","https://openalex.org/W2809650812","https://openalex.org/W2952775474","https://openalex.org/W4409157911","https://openalex.org/W2044493620","https://openalex.org/W3210467483"],"abstract_inverted_index":{"The":[0,57],"dueling":[1,37,58,96,108],"bandits":[2,38,59,97,109],"problem":[3,60,136],"is":[4,61,74],"an":[5,100,121],"online":[6,26],"learning":[7,10,27],"framework":[8,39],"where":[9],"happens":[11],"``on-the-fly''":[12],"through":[13],"preference":[14,79],"feedback,":[15,72],"i.e.,":[16],"from":[17],"comparisons":[18],"between":[19],"a":[20],"pair":[21,54],"of":[22,44,52,55,94,107,123],"actions.":[23,56],"Unlike":[24],"conventional":[25],"settings":[28,65],"that":[29,66],"require":[30],"absolute":[31],"feedback":[32,47],"for":[33,63],"each":[34,53],"action,":[35],"the":[36,42,49,89,95,103,115],"assumes":[40],"only":[41],"presence":[43],"(noisy)":[45],"binary":[46],"about":[48],"relative":[50],"quality":[51],"well-suited":[62],"modeling":[64],"elicit":[67],"subjective":[68],"or":[69],"implicit":[70],"human":[71],"which":[73],"typically":[75],"more":[76],"reliable":[77],"in":[78,88,147],"form.":[80],"In":[81],"this":[82],"survey,":[83],"we":[84],"review":[85],"recent":[86,124],"results":[87],"theories,":[90],"algorithms,":[91],"and":[92,105,129,138],"applications":[93],"problem.":[98],"As":[99],"emerging":[101],"domain,":[102],"theories":[104],"algorithms":[106],"have":[110],"been":[111],"intensively":[112],"studied":[113],"during":[114],"past":[116],"few":[117],"years.":[118],"We":[119,131],"provide":[120],"overview":[122],"advancements,":[125],"including":[126],"algorithmic":[127],"advances":[128],"applications.":[130],"discuss":[132],"extensions":[133],"to":[134],"standard":[135],"formulation":[137],"novel":[139],"application":[140],"areas,":[141],"highlighting":[142],"key":[143],"open":[144],"research":[145],"questions":[146],"our":[148],"discussion.":[149]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2018-07-19T00:00:00"}
