{"id":"https://openalex.org/W4313155634","doi":"https://doi.org/10.1109/tsp.2022.3224790","title":"Learning in Restless Bandits Under Exogenous Global Markov Process","display_name":"Learning in Restless Bandits Under Exogenous Global Markov Process","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4313155634","doi":"https://doi.org/10.1109/tsp.2022.3224790"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2022.3224790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2022.3224790","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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 Signal Processing","raw_type":"journal-article"},"type":"preprint","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":true,"raw_author_name":"Tomer Gafni","raw_affiliation_strings":["School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer-Sheva, Israel"],"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074718726","display_name":"Michal Yemini","orcid":"https://orcid.org/0000-0002-2087-1183"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Michal Yemini","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat-Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"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"],"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":3,"corresponding_author_ids":["https://openalex.org/A5077036467"],"corresponding_institution_ids":["https://openalex.org/I124227911"],"apc_list":null,"apc_paid":null,"fwci":1.1833,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.81149871,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"70","issue":null,"first_page":"5679","last_page":"5693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T13553","display_name":"Age of Information Optimization","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9959999918937683,"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":0.9066071510314941},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5731896758079529},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49860548973083496},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4546419382095337},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.4429270923137665},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4332057535648346},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4206363260746002},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.41783300042152405},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4091809391975403},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.144820898771286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1335667371749878},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.09699156880378723}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.9066071510314941},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5731896758079529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49860548973083496},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4546419382095337},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.4429270923137665},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4332057535648346},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4206363260746002},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.41783300042152405},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4091809391975403},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.144820898771286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1335667371749878},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.09699156880378723},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsp.2022.3224790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2022.3224790","pdf_url":null,"source":{"id":"https://openalex.org/S168680287","display_name":"IEEE Transactions on Signal Processing","issn_l":"1053-587X","issn":["1053-587X","1941-0476"],"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 Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W157259654","https://openalex.org/W1751431909","https://openalex.org/W1972707086","https://openalex.org/W1977509904","https://openalex.org/W1980829002","https://openalex.org/W1985014315","https://openalex.org/W1985380836","https://openalex.org/W1989239951","https://openalex.org/W1998039896","https://openalex.org/W2003798390","https://openalex.org/W2009551863","https://openalex.org/W2023353151","https://openalex.org/W2029199203","https://openalex.org/W2044502527","https://openalex.org/W2045026444","https://openalex.org/W2056921512","https://openalex.org/W2077902449","https://openalex.org/W2104389751","https://openalex.org/W2113733815","https://openalex.org/W2130527179","https://openalex.org/W2141515329","https://openalex.org/W2143915371","https://openalex.org/W2150328967","https://openalex.org/W2152902239","https://openalex.org/W2153620960","https://openalex.org/W2161571887","https://openalex.org/W2164599584","https://openalex.org/W2168405694","https://openalex.org/W2170447782","https://openalex.org/W2171671264","https://openalex.org/W2519680108","https://openalex.org/W2725896932","https://openalex.org/W2808233815","https://openalex.org/W2890134435","https://openalex.org/W2962764550","https://openalex.org/W2963561380","https://openalex.org/W2964046129","https://openalex.org/W2964296255","https://openalex.org/W2969447045","https://openalex.org/W2992659141","https://openalex.org/W3028363395","https://openalex.org/W3081812122","https://openalex.org/W3102381603","https://openalex.org/W3110865173","https://openalex.org/W3111277265","https://openalex.org/W3121362365","https://openalex.org/W3124527634","https://openalex.org/W3125634603","https://openalex.org/W3148526481","https://openalex.org/W3197661529","https://openalex.org/W3198738752","https://openalex.org/W3207417986","https://openalex.org/W4225285064","https://openalex.org/W4232620022","https://openalex.org/W4238524517","https://openalex.org/W6606960145","https://openalex.org/W6632992360","https://openalex.org/W6679661297","https://openalex.org/W6697515318","https://openalex.org/W6769089321","https://openalex.org/W7034144617"],"related_works":["https://openalex.org/W2947263763","https://openalex.org/W4288373430","https://openalex.org/W4287753704","https://openalex.org/W3036260055","https://openalex.org/W3158925485","https://openalex.org/W2996735312","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414"],"abstract_inverted_index":{"We":[0,166,178,189],"consider":[1],"an":[2,16,42,58,146],"extension":[3],"to":[4,41,67,114,144],"the":[5,23,33,93,104,109,119,122,133,137,151,158,176,200],"restless":[6],"multi-armed":[7],"bandit":[8],"(RMAB)":[9],"problem":[10],"with":[11,112,187],"unknown":[12,17,43],"arm":[13,38,59,134],"dynamics,":[14],"where":[15],"exogenous":[18],"global":[19,31],"Markov":[20,162],"process":[21,35],"governs":[22],"rewards":[24,34],"distribution":[25],"of":[26,36,61,78,92,121],"each":[27,30,37,53,127],"arm.":[28],"Under":[29],"state,":[32],"evolves":[39,90],"according":[40],"Markovian":[44],"rule,":[45],"which":[46],"is":[47,106,143],"non-identical":[48],"among":[49],"different":[50],"arms.":[51],"At":[52],"time,":[54],"a":[55,71,75,115,172,183],"player":[56,116],"chooses":[57],"out":[60],"<inline-formula":[62,129],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[63,130],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[64,131],"notation=\"LaTeX\">$N$</tex-math></inline-formula>":[65],"arms":[66,82],"play,":[68],"and":[69,124,170,194,203],"receives":[70],"random":[72],"reward":[73,79,110],"from":[74],"finite":[76],"set":[77],"states.":[80],"The":[81,141],"are":[83],"restless,":[84],"that":[85,117,135,149,154,180,198,205],"is,":[86],"their":[87],"local":[88],"state":[89],"regardless":[91],"player's":[94],"actions.":[95],"Motivated":[96],"by":[97],"recent":[98],"studies":[99],"on":[100,175],"related":[101],"RMAB":[102],"settings,":[103],"regret":[105,185],"defined":[107],"as":[108],"loss":[111],"respect":[113],"knows":[118],"dynamics":[120],"problem,":[123],"plays":[125],"at":[126],"time":[128],"notation=\"LaTeX\">$t$</tex-math></inline-formula>":[132],"maximizes":[136],"expected":[138],"immediate":[139],"value.":[140],"objective":[142],"develop":[145,157],"arm-selection":[147],"policy":[148],"minimizes":[150],"regret.":[152,177],"To":[153],"end,":[155],"we":[156],"Learning":[159],"under":[160],"Exogenous":[161],"Process":[163],"(LEMP)":[164],"algorithm.":[165],"analyze":[167,191],"LEMP":[168,181,192,206],"theoretically":[169],"establish":[171],"finite-sample":[173],"bound":[174],"show":[179],"achieves":[182],"logarithmic":[184],"order":[186],"time.":[188],"further":[190],"numerically":[193],"present":[195],"simulation":[196],"results":[197],"support":[199],"theoretical":[201],"findings":[202],"demonstrate":[204],"significantly":[207],"outperforms":[208],"alternative":[209],"algorithms.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}