{"id":"https://openalex.org/W2950273845","doi":"https://doi.org/10.1109/tac.2020.3043431","title":"Learning in Restless Multiarmed Bandits via Adaptive Arm Sequencing Rules","display_name":"Learning in Restless Multiarmed Bandits via Adaptive Arm Sequencing Rules","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W2950273845","doi":"https://doi.org/10.1109/tac.2020.3043431","mag":"2950273845"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2020.3043431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2020.3043431","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.08120","any_repository_has_fulltext":true},"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":["School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel","Ben\u2010Gurion University of the Negev"],"raw_orcid":"https://orcid.org/0000-0002-5906-1428","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel","institution_ids":["https://openalex.org/I124227911"]},{"raw_affiliation_string":"Ben\u2010Gurion University of the Negev","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":["School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel"],"raw_orcid":"https://orcid.org/0000-0003-0532-009X","affiliations":[{"raw_affiliation_string":"School 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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00850578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"66","issue":"10","first_page":"5029","last_page":"5036"},"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":0.9955999851226807,"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":0.9950000047683716,"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":0.9374343156814575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6117510199546814},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5952324867248535},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5191537737846375},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4812197983264923},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.4677543640136719},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4572443962097168},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4139742851257324},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4107722043991089},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.38785064220428467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2901337742805481},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20230403542518616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2020891308784485}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9374343156814575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6117510199546814},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5952324867248535},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5191537737846375},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4812197983264923},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.4677543640136719},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4572443962097168},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4139742851257324},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4107722043991089},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38785064220428467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2901337742805481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20230403542518616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2020891308784485},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tac.2020.3043431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2020.3043431","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1906.08120","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.08120","pdf_url":"https://arxiv.org/pdf/1906.08120","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"},{"id":"mag:2950273845","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.08120.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1906.08120","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.08120","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.08120","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.08120","pdf_url":"https://arxiv.org/pdf/1906.08120","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5755329095","display_name":null,"funder_award_id":"2640/20","funder_id":"https://openalex.org/F4320322252","funder_display_name":"Israel Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950273845.pdf","grobid_xml":"https://content.openalex.org/works/W2950273845.grobid-xml"},"referenced_works_count":42,"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/W1985014315","https://openalex.org/W1985380836","https://openalex.org/W1989239951","https://openalex.org/W2009551863","https://openalex.org/W2023353151","https://openalex.org/W2029199203","https://openalex.org/W2044502527","https://openalex.org/W2045026444","https://openalex.org/W2048984153","https://openalex.org/W2056921512","https://openalex.org/W2077902449","https://openalex.org/W2105556121","https://openalex.org/W2125724988","https://openalex.org/W2139964991","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/W2765574662","https://openalex.org/W2793205632","https://openalex.org/W2886549473","https://openalex.org/W2898035736","https://openalex.org/W2898754723","https://openalex.org/W2962677764","https://openalex.org/W2962764550","https://openalex.org/W2963627946","https://openalex.org/W2964296255","https://openalex.org/W2999204576","https://openalex.org/W3100789280","https://openalex.org/W3102381603","https://openalex.org/W3125634603","https://openalex.org/W4232620022"],"related_works":["https://openalex.org/W2886549473","https://openalex.org/W3111277265","https://openalex.org/W3173728037","https://openalex.org/W3028862769","https://openalex.org/W2488721199","https://openalex.org/W2897337230","https://openalex.org/W2950290000","https://openalex.org/W2933394573","https://openalex.org/W2962987366","https://openalex.org/W3173863509","https://openalex.org/W2132479360","https://openalex.org/W3034893468","https://openalex.org/W1854414374","https://openalex.org/W2742723920","https://openalex.org/W343811141","https://openalex.org/W3037755290","https://openalex.org/W3094163526","https://openalex.org/W3175764140","https://openalex.org/W2188785377","https://openalex.org/W2792286966"],"abstract_inverted_index":{"We":[0,136],"consider":[1],"a":[2,17,39,43,108,138,147,191,198,211,225,249],"class":[3,118],"of":[4,23,46,52,66,119,129,252],"restless":[5],"multiarmed":[6],"bandit":[7],"(RMAB)":[8],"problems":[9,121],"with":[10,105,195,215,232],"unknown":[11,60,87],"arm":[12,21,55],"dynamics.":[13,62],"At":[14],"each":[15],"time,":[16,196],"player":[18,109],"chooses":[19],"an":[20,34,59,85,93],"out":[22],"<inline-formula":[24,77],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[25,78],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[26,79],"notation=\"LaTeX\">$N$</tex-math></inline-formula>":[27],"arms":[28,68,142,161],"to":[29,32,58,73,84,107,143,234,257],"play,":[30],"referred":[31],"as":[33,101,255],"active":[35,54],"arm,":[36],"and":[37,132,169,197,247],"receives":[38],"random":[40,88],"reward":[41,47,50,64,103,175],"from":[42],"finite":[44],"set":[45],"states.":[48],"The":[49,63,90,156],"state":[51,65],"the":[53,98,102,113,127,163,172,180,187,202,221,229,235,244,253],"transits":[56],"according":[57,83],"Markovian":[61],"passive":[67],"(which":[69],"are":[70,166],"not":[71],"chosen":[72],"play":[74],"at":[75],"time":[76,216],"notation=\"LaTeX\">$t$</tex-math></inline-formula>":[80],")":[81],"evolves":[82],"arbitrary":[86],"process.":[89],"objective":[91],"is":[92,204],"arm-selection":[94],"policy":[95],"that":[96,110,140,186],"minimizes":[97],"regret,":[99],"defined":[100],"loss":[104],"respect":[106,233],"always":[111],"plays":[112],"most":[114],"rewarding":[115],"arm.":[116],"This":[117],"RMAB":[120,219],"has":[122],"been":[123],"studied":[124],"recently":[125],"in":[126,146,217,228],"context":[128],"communication":[130],"networks":[131],"financial":[133],"investment":[134],"applications.":[135],"develop":[137],"strategy":[139],"selects":[141],"be":[144],"played":[145],"consecutive":[148],"manner,":[149],"dubbed":[150],"adaptive":[151,181],"sequencing":[152,157,182],"rules":[153,158],"(ASR)":[154],"algorithm.":[155],"for":[159],"selecting":[160],"under":[162,238],"ASR":[164,188],"algorithm":[165,189,254],"adaptively":[167],"updated":[168],"controlled":[170],"by":[171],"current":[173],"sample":[174],"means.":[176],"By":[177],"designing":[178],"judiciously":[179],"rules,":[183],"we":[184],"show":[185],"achieves":[190],"logarithmic":[192,212],"regret":[193,203,213,230],"order":[194,214],"finite-sample":[199],"bound":[200],"on":[201],"established.":[205],"Although":[206],"existing":[207,258],"methods":[208],"have":[209],"shown":[210],"this":[218],"setting,":[220],"theoretical":[222,245],"analysis":[223],"shows":[224],"significant":[226],"improvement":[227],"scaling":[231],"system":[236],"parameters":[237],"ASR.":[239],"Extensive":[240],"simulation":[241],"results":[242],"support":[243],"study":[246],"demonstrate":[248],"strong":[250],"performance":[251],"compared":[256],"methods.":[259]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}