{"id":"https://openalex.org/W2903290945","doi":"https://doi.org/10.1109/acssc.2018.8645353","title":"Quick Best Action Identification in Linear Bandit Problems","display_name":"Quick Best Action Identification in Linear Bandit Problems","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2903290945","doi":"https://doi.org/10.1109/acssc.2018.8645353","mag":"2903290945"},"language":"en","primary_location":{"id":"doi:10.1109/acssc.2018.8645353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2018.8645353","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100735722","display_name":"Jun Geng","orcid":"https://orcid.org/0000-0002-0024-9848"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Geng","raw_affiliation_strings":["School of Electrical and Information Engineering, Harbin Institute of Technology, Harbin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081715462","display_name":"Lifeng Lai","orcid":"https://orcid.org/0000-0002-9493-8248"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lifeng Lai","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of California, Davis, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of California, Davis, CA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1312","last_page":"1316"},"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":0.9962000250816345,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9926999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8729739189147949},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7232816219329834},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6786982417106628},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6777304410934448},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6735679507255554},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6344075202941895},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5937380790710449},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.5425574779510498},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4349375069141388},{"id":"https://openalex.org/keywords/parameter-identification-problem","display_name":"Parameter identification problem","score":0.4255276024341583},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3490484952926636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2724665105342865},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22539681196212769},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08754894137382507}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8729739189147949},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7232816219329834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6786982417106628},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6777304410934448},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6735679507255554},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6344075202941895},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5937380790710449},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.5425574779510498},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4349375069141388},{"id":"https://openalex.org/C79610928","wikidata":"https://www.wikidata.org/wiki/Q1656743","display_name":"Parameter identification problem","level":3,"score":0.4255276024341583},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3490484952926636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2724665105342865},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22539681196212769},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08754894137382507},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C2983447341","wikidata":"https://www.wikidata.org/wiki/Q1413083","display_name":"Model parameter","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acssc.2018.8645353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2018.8645353","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2018 52nd Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W50486269","https://openalex.org/W966080908","https://openalex.org/W2014482607","https://openalex.org/W2045030310","https://openalex.org/W2103405567","https://openalex.org/W2108114251","https://openalex.org/W2119738618","https://openalex.org/W2126559945","https://openalex.org/W2146025745","https://openalex.org/W2168810201","https://openalex.org/W2222505014","https://openalex.org/W2715423655","https://openalex.org/W2764809058","https://openalex.org/W2797105841","https://openalex.org/W2963736810","https://openalex.org/W6602031475","https://openalex.org/W6675394771","https://openalex.org/W6676576766","https://openalex.org/W6678664249","https://openalex.org/W6684588553","https://openalex.org/W6688923598"],"related_works":["https://openalex.org/W4376155396","https://openalex.org/W1947085858","https://openalex.org/W2101991911","https://openalex.org/W2174986909","https://openalex.org/W2527791220","https://openalex.org/W2155070487","https://openalex.org/W4311589891","https://openalex.org/W3123835761","https://openalex.org/W118270247","https://openalex.org/W2356003845"],"abstract_inverted_index":{"In":[0,21],"this":[1],"paper,":[2],"we":[3],"consider":[4],"a":[5,17,82,101,108,117,130],"best":[6,24],"action":[7,25,54,70],"identification":[8,26],"problem":[9],"in":[10,36,81],"the":[11,22,31,39,48,60,63,76,90,96,121,136,140,144,151],"stochastic":[12],"linear":[13],"bandit":[14],"setup":[15],"with":[16],"fixed":[18],"confident":[19],"constraint.":[20],"considered":[23],"problem,":[27],"instead":[28],"of":[29,47,139,150],"minimizing":[30],"accumulative":[32,97],"regret":[33,98],"as":[34,148],"done":[35],"existing":[37,91],"works,":[38],"learner":[40,64],"aims":[41],"to":[42,67,94],"obtain":[43],"an":[44],"accurate":[45],"estimate":[46],"underlying":[49],"parameter":[50],"based":[51,71],"on":[52,120],"his":[53,69,72],"and":[55,104,133],"reward":[56],"sequences.":[57],"To":[58],"improve":[59],"estimation":[61,122,137],"efficiency,":[62],"is":[65,79,99,106],"allowed":[66],"select":[68],"historical":[73],"information;":[74],"hence":[75,105],"whole":[77],"procedure":[78],"designed":[80,93,141],"sequential":[83],"adaptive":[84],"manner.":[85],"We":[86,114,127],"first":[87],"show":[88,134],"that":[89,135,149],"algorithms":[92],"minimize":[95],"not":[100,107],"consistent":[102],"estimator":[103],"good":[109],"policy":[110,132,142],"for":[111,124],"our":[112],"problem.":[113],"then":[115],"characterize":[116],"lower":[118,153],"bound":[119],"error":[123,138],"any":[125],"policy.":[126],"further":[128],"design":[129],"simple":[131],"achieves":[143],"same":[145],"scaling":[146],"order":[147],"derived":[152],"bound.":[154]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}