{"id":"https://openalex.org/W2798369493","doi":"https://doi.org/10.1145/3209978.3210051","title":"Learning Contextual Bandits in a Non-stationary Environment","display_name":"Learning Contextual Bandits in a Non-stationary Environment","publication_year":2018,"publication_date":"2018-06-27","ids":{"openalex":"https://openalex.org/W2798369493","doi":"https://doi.org/10.1145/3209978.3210051","mag":"2798369493"},"language":"en","primary_location":{"id":"doi:10.1145/3209978.3210051","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3209978.3210051","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3209978.3210051","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3209978.3210051","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101992274","display_name":"Qingyun Wu","orcid":"https://orcid.org/0000-0003-1008-516X"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingyun Wu","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021190749","display_name":"Naveen Iyer","orcid":null},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naveen Iyer","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085094109","display_name":"Hongning Wang","orcid":"https://orcid.org/0000-0002-6524-9195"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongning Wang","raw_affiliation_strings":["University of Virginia, Charlottesville, VA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia, Charlottesville, VA, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"495","last_page":"504"},"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":0.9904999732971191,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.940890371799469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8062945604324341},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.7497725486755371},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7291908860206604},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.6000592708587646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5259794592857361},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48883551359176636},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4570150673389435},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.44612187147140503},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32807791233062744},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10049766302108765}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.940890371799469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062945604324341},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.7497725486755371},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7291908860206604},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.6000592708587646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5259794592857361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48883551359176636},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4570150673389435},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.44612187147140503},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32807791233062744},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10049766302108765},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3209978.3210051","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3209978.3210051","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3209978.3210051","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.09365","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.09365","pdf_url":"https://arxiv.org/pdf/1805.09365","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3209978.3210051","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3209978.3210051","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3209978.3210051","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G118577680","display_name":null,"funder_award_id":"IIS-1553568, IIS-1618948","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5245339017","display_name":"CAREER: Human-Centric Knowledge Discovery and Decision Optimization","funder_award_id":"1553568","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7441103298","display_name":null,"funder_award_id":"IIS-1553568","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7888745661","display_name":"III: Small: Collaborative Learning with Incomplete and Noisy Knowledge","funder_award_id":"1618948","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8793715909","display_name":null,"funder_award_id":"IIS-1618948","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798369493.pdf","grobid_xml":"https://content.openalex.org/works/W2798369493.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W172143579","https://openalex.org/W1487320471","https://openalex.org/W1839697241","https://openalex.org/W1944301273","https://openalex.org/W1968049117","https://openalex.org/W2009979684","https://openalex.org/W2108114251","https://openalex.org/W2112420033","https://openalex.org/W2116067849","https://openalex.org/W2119738618","https://openalex.org/W2119850747","https://openalex.org/W2138909795","https://openalex.org/W2149571656","https://openalex.org/W2160163723","https://openalex.org/W2161571887","https://openalex.org/W2168405694","https://openalex.org/W2294582607","https://openalex.org/W2340290367","https://openalex.org/W2394764681","https://openalex.org/W2519411794","https://openalex.org/W2604278489","https://openalex.org/W2604822632","https://openalex.org/W2742393003","https://openalex.org/W2783571795","https://openalex.org/W2950978108","https://openalex.org/W2951573205","https://openalex.org/W2962818688","https://openalex.org/W2963243812","https://openalex.org/W2964132277","https://openalex.org/W3125634603","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3108185025","https://openalex.org/W1850547517","https://openalex.org/W2964125852","https://openalex.org/W3176022311","https://openalex.org/W3048056964","https://openalex.org/W4287690869","https://openalex.org/W3046298489","https://openalex.org/W3015709540","https://openalex.org/W4287816990","https://openalex.org/W4281629038"],"abstract_inverted_index":{"Multi-armed":[0],"bandit":[1,85],"algorithms":[2,28],"have":[3],"become":[4],"a":[5,31,48,83,121,140],"reference":[6],"solution":[7],"for":[8,133],"handling":[9],"the":[10,59,62,112],"explore/exploit":[11],"dilemma":[12],"in":[13,38,119,139],"recommender":[14,49],"systems,":[15],"and":[16,73,99,130],"many":[17],"other":[18],"important":[19],"real-world":[20,131],"problems,":[21],"such":[22,27,120],"as":[23,40],"display":[24],"advertisement.":[25],"However,":[26],"usually":[29],"assume":[30],"stationary":[32],"reward":[33,66,96],"distribution,":[34],"which":[35],"hardly":[36],"holds":[37],"practice":[39],"users'":[41],"preferences":[42],"are":[43],"dynamic.":[44],"This":[45],"inevitably":[46],"costs":[47],"system":[50],"consistent":[51],"suboptimal":[52],"performance.":[53],"In":[54,79],"this":[55],"paper,":[56],"we":[57,81],"consider":[58],"situation":[60],"where":[61],"underlying":[63],"distribution":[64],"of":[65,91,111],"remains":[67],"unchanged":[68],"over":[69],"(possibly":[70],"short)":[71],"epochs":[72],"shifts":[74],"at":[75],"unknown":[76],"time":[77],"instants.":[78],"accordance,":[80],"propose":[82],"contextual":[84],"algorithm":[86,114],"that":[87],"detects":[88],"possible":[89],"changes":[90],"environment":[92],"based":[93],"on":[94,127],"its":[95,101,116,136],"estimation":[97],"confidence":[98],"updates":[100],"arm":[102],"selection":[103],"strategy":[104],"respectively.":[105],"Rigorous":[106],"upper":[107],"regret":[108],"bound":[109],"analysis":[110],"proposed":[113],"demonstrates":[115],"learning":[117],"effectiveness":[118],"non-trivial":[122],"environment.":[123,142],"Extensive":[124],"empirical":[125],"evaluations":[126],"both":[128],"synthetic":[129],"datasets":[132],"recommendation":[134],"confirm":[135],"practical":[137],"utility":[138],"changing":[141]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":7}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}