{"id":"https://openalex.org/W2886549473","doi":"https://doi.org/10.1109/isit.2018.8437583","title":"Learning in Restless Multi-Armed Bandits using Adaptive Arm Sequencing Rules","display_name":"Learning in Restless Multi-Armed Bandits using Adaptive Arm Sequencing Rules","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2886549473","doi":"https://doi.org/10.1109/isit.2018.8437583","mag":"2886549473"},"language":"en","primary_location":{"id":"doi:10.1109/isit.2018.8437583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2018.8437583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Information Theory (ISIT)","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/A5077036467","display_name":"Tomer Gafni","orcid":"https://orcid.org/0000-0002-5906-1428"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tomer Gafni","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev Beer Sheva, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev Beer Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066085947","display_name":"Kobi Cohen","orcid":"https://orcid.org/0000-0003-0532-009X"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Kobi Cohen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev Beer Sheva, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Ben-Gurion University of the Negev Beer Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2017,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88577821,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1206","last_page":"1210"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9930999875068665,"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":0.9202905893325806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6369624137878418},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.600412130355835},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5116639137268066},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.45644575357437134},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42456483840942383},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4243379235267639},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.4188283085823059},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41124826669692993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3347119688987732},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24520078301429749},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18870416283607483}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9202905893325806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6369624137878418},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.600412130355835},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5116639137268066},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.45644575357437134},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42456483840942383},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4243379235267639},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.4188283085823059},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41124826669692993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3347119688987732},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24520078301429749},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18870416283607483},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isit.2018.8437583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isit.2018.8437583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Symposium on Information Theory (ISIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323051","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1751431909","https://openalex.org/W1905635701","https://openalex.org/W1977509904","https://openalex.org/W1980829002","https://openalex.org/W1981218270","https://openalex.org/W1989239951","https://openalex.org/W2009551863","https://openalex.org/W2023353151","https://openalex.org/W2029199203","https://openalex.org/W2044502527","https://openalex.org/W2056921512","https://openalex.org/W2077902449","https://openalex.org/W2105556121","https://openalex.org/W2125724988","https://openalex.org/W2141515329","https://openalex.org/W2143915371","https://openalex.org/W2150328967","https://openalex.org/W2163863791","https://openalex.org/W2168405694","https://openalex.org/W2170447782","https://openalex.org/W2171671264","https://openalex.org/W2552178850","https://openalex.org/W2612336410","https://openalex.org/W2898754723","https://openalex.org/W2962764550","https://openalex.org/W2964296255","https://openalex.org/W3102381603","https://openalex.org/W3111277265","https://openalex.org/W3125634603","https://openalex.org/W4232620022","https://openalex.org/W6756306824","https://openalex.org/W6763721445"],"related_works":["https://openalex.org/W2947263763","https://openalex.org/W4288373430","https://openalex.org/W4287753704","https://openalex.org/W3036260055","https://openalex.org/W2970347269","https://openalex.org/W3158925485","https://openalex.org/W2996735312","https://openalex.org/W4287863949","https://openalex.org/W4287102143","https://openalex.org/W1850488217"],"abstract_inverted_index":{"We":[0,129],"consider":[1],"a":[2,17,36,40,101,131,140,184,191,204],"class":[3,111],"of":[4,23,43,49,63,112,122,174,243],"restless":[5],"multi-armed":[6],"bandit":[7],"(RMAB)":[8],"problems":[9,114],"with":[10,98,188,208,224],"unknown":[11,57,80],"arm":[12,21,52],"dynamics.":[13],"At":[14],"each":[15],"time,":[16],"player":[18,102],"chooses":[19],"an":[20,31,56,78,86],"out":[22],"N":[24],"arms":[25,65,135],"to":[26,29,55,70,77,100,136,160,226,248],"play,":[27],"referred":[28,159],"as":[30,94,161,246],"active":[32,51],"arm,":[33],"and":[34,125,190,239],"receives":[35],"random":[37,81],"reward":[38,44,47,61,96,157],"from":[39],"finite":[41],"set":[42],"states.":[45],"The":[46,60,83],"state":[48,62],"the":[50,91,95,106,120,145,154,170,175,195,214,221,227,236,244],"transits":[53],"according":[54,76],"Markovian":[58],"dynamic.":[59],"passive":[64],"(which":[66],"are":[67,149],"not":[68],"chosen":[69,176],"play":[71],"at":[72],"time":[73,189,209],"t)":[74],"evolves":[75],"arbitrary":[79],"process.":[82],"objective":[84],"is":[85,197],"arm-selection":[87],"policy":[88],"that":[89,103,133,180],"minimizes":[90],"regret,":[92],"defined":[93],"loss":[97],"respect":[99,225],"always":[104],"plays":[105],"most":[107],"rewarding":[108],"arm.":[109],"This":[110],"RMAB":[113,212],"has":[115],"been":[116],"studied":[117],"recently":[118],"in":[119,139,143,210,220],"context":[121],"communication":[123],"networks":[124],"financial":[126],"investment":[127],"applications.":[128],"develop":[130],"strategy":[132],"selects":[134],"be":[137],"played":[138],"consecutive":[141],"manner":[142],"which":[144],"selection":[146],"sequencing":[147,172],"rules":[148,173],"adaptively":[150],"updated":[151],"controlled":[152],"by":[153],"current":[155],"sample":[156],"means,":[158],"Adaptive":[162],"Sequencing":[163],"Rules":[164],"(ASR)":[165],"algorithm.":[166],"By":[167],"designing":[168],"judiciously":[169],"adaptive":[171],"arms,":[177],"we":[178],"show":[179],"ASR":[181],"algorithm":[182,245],"achieves":[183],"logarithmic":[185,205],"regret":[186,196,206,222],"order":[187,207],"finite-sample":[192],"bound":[193],"on":[194],"established.":[198],"Although":[199],"existing":[200,249],"methods":[201],"have":[202],"shown":[203],"this":[211],"setting,":[213],"theoretical":[215,237],"analysis":[216],"presents":[217],"significant":[218],"improvement":[219],"scaling":[223],"system":[228],"parameters":[229],"under":[230],"ASR.":[231],"Extensive":[232],"simulation":[233],"results":[234],"support":[235],"study":[238],"demonstrate":[240],"strong":[241],"performance":[242],"compared":[247],"methods.":[250]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}