{"id":"https://openalex.org/W2909940598","doi":"https://doi.org/10.1109/itw.2018.8613513","title":"Best Arm Identification for Both Stochastic and Adversarial Multi-armed Bandits","display_name":"Best Arm Identification for Both Stochastic and Adversarial Multi-armed Bandits","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2909940598","doi":"https://doi.org/10.1109/itw.2018.8613513","mag":"2909940598"},"language":"en","primary_location":{"id":"doi:10.1109/itw.2018.8613513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itw.2018.8613513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Information Theory Workshop (ITW)","raw_type":"proceedings-article"},"type":"article","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/A5101666192","display_name":"Hantao Zhang","orcid":"https://orcid.org/0000-0002-5342-7951"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hantao Zhang","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016749653","display_name":"Cong Shen","orcid":"https://orcid.org/0000-0002-3148-4453"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Shen","raw_affiliation_strings":["Department of Electronic Engineering and Information Science, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering and Information Science, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.2202,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64137368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"35","issue":null,"first_page":"1","last_page":"5"},"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":0.9965000152587891,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9923999905586243,"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/adversarial-system","display_name":"Adversarial system","score":0.9194059371948242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6970707178115845},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.6237276196479797},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5542944669723511},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45981794595718384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43833106756210327},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.42313212156295776},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4129427671432495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3510572910308838},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18590328097343445},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0737760066986084}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9194059371948242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6970707178115845},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.6237276196479797},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5542944669723511},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45981794595718384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43833106756210327},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.42313212156295776},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4129427671432495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3510572910308838},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18590328097343445},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0737760066986084},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itw.2018.8613513","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itw.2018.8613513","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Information Theory Workshop (ITW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W165458731","https://openalex.org/W1504908594","https://openalex.org/W1553290137","https://openalex.org/W1575029535","https://openalex.org/W2126559945","https://openalex.org/W2168810201","https://openalex.org/W2225232604","https://openalex.org/W2293238857","https://openalex.org/W2402892507","https://openalex.org/W2950361145","https://openalex.org/W2963334428","https://openalex.org/W2963736810","https://openalex.org/W6606658949","https://openalex.org/W6630207868","https://openalex.org/W6632992360","https://openalex.org/W6634542218","https://openalex.org/W6678664249","https://openalex.org/W6684588553","https://openalex.org/W6689117217","https://openalex.org/W6696956927","https://openalex.org/W6712753481"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W2982428536"],"abstract_inverted_index":{"We":[0,30,56],"study":[1],"the":[2,12,26,43,47,58,61,79,87,100,109,120,125,132,149],"problem":[3,48],"of":[4,60,82,144],"best":[5,101,170],"arm":[6,102,133,171],"identification":[7,172],"in":[8],"multi-armed":[9],"bandits,":[10],"where":[11],"underlying":[13],"setting":[14],"can":[15,103],"be":[16,104],"either":[17,166],"stochastic":[18,66,71,138,167],"or":[19,168],"adversarial":[20,53,68,95,140,169],"and":[21,45,50,67,92,139,155],"is":[22,39,54,85,111,128,146,157],"not":[23],"revealed":[24],"to":[25,40,124,131],"forecaster":[27],"a":[28,113],"priori.":[29],"propose":[31],"an":[32,75],"algorithm,":[33],"called":[34],"S3-BA,":[35],"whose":[36],"key":[37],"idea":[38],"simultaneously":[41],"explore":[42],"arms":[44],"learn":[46],"model,":[49],"switch":[51],"when":[52],"declared.":[55],"analyze":[57],"performance":[59,143],"proposed":[62],"algorithm":[63],"for":[64,136,165],"both":[65,137],"bandits.":[69,141],"For":[70,94],"bandits":[72,96],"we":[73,97,117],"prove":[74,118],"upper":[76],"bound":[77],"on":[78,86],"error":[80],"rate":[81],"S3-BA":[83,145],"that":[84,99,119,159],"same":[88],"order":[89],"as":[90,106,108],"UCB-E":[91],"SH.":[93],"show":[98],"guaranteed":[105],"long":[107],"budget":[110],"above":[112],"threshold.":[114],"More":[115],"importantly,":[116],"\u201clearning":[121],"loss\u201d":[122],"due":[123],"formulation":[126],"uncertainty":[127],"negligible":[129],"compared":[130],"selection":[134],"policies,":[135],"The":[142],"evaluated":[147],"using":[148],"real-world":[150],"US":[151],"stock":[152],"market":[153],"dataset,":[154],"it":[156,160],"observed":[158],"outperforms":[161],"existing":[162],"algorithms":[163],"designed":[164],"problems.":[173]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}