{"id":"https://openalex.org/W3121876324","doi":"https://doi.org/10.1109/tsp.2021.3054344","title":"The Restless Hidden Markov Bandit With Linear Rewards and Side Information","display_name":"The Restless Hidden Markov Bandit With Linear Rewards and Side Information","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3121876324","doi":"https://doi.org/10.1109/tsp.2021.3054344","mag":"3121876324"},"language":"en","primary_location":{"id":"doi:10.1109/tsp.2021.3054344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2021.3054344","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.10271","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074718726","display_name":"Michal Yemini","orcid":"https://orcid.org/0000-0002-2087-1183"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michal Yemini","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, Stanford, CA, USA","Stanford University ()"],"raw_orcid":"https://orcid.org/0000-0002-2087-1183","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019966334","display_name":"Amir Leshem","orcid":"https://orcid.org/0000-0002-2265-7463"},"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":"Amir Leshem","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel","Faculty of Engineering, Bar\u2013Ilan University, Ramat Gan, Israel"],"raw_orcid":"https://orcid.org/0000-0002-2265-7463","affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Faculty of Engineering, Bar\u2013Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040147387","display_name":"Anelia Somekh-Baruch","orcid":"https://orcid.org/0000-0002-3839-6317"},"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":"Anelia Somekh-Baruch","raw_affiliation_strings":["Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel","Bar-Ilan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan University","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1792,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50420066,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"69","issue":null,"first_page":"1108","last_page":"1123"},"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":0.9977999925613403,"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/T13553","display_name":"Age of Information Optimization","score":0.9940000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8575878143310547},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.6264801621437073},{"id":"https://openalex.org/keywords/polytope","display_name":"Polytope","score":0.5990779399871826},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5629572868347168},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5479561686515808},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5430672764778137},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5220082402229309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5195246338844299},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4712671935558319},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.43909355998039246},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4249623417854309},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41614794731140137},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36467084288597107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2554468512535095},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23396450281143188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14085814356803894},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.1319778561592102}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8575878143310547},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6264801621437073},{"id":"https://openalex.org/C145691206","wikidata":"https://www.wikidata.org/wiki/Q747980","display_name":"Polytope","level":2,"score":0.5990779399871826},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5629572868347168},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5479561686515808},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5430672764778137},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5220082402229309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5195246338844299},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4712671935558319},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43909355998039246},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4249623417854309},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41614794731140137},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36467084288597107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2554468512535095},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23396450281143188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14085814356803894},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.1319778561592102},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tsp.2021.3054344","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsp.2021.3054344","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"},{"id":"pmh:oai:arXiv.org:1910.10271","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10271","pdf_url":"https://arxiv.org/pdf/1910.10271","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:3121876324","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1910.10271","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.1910.10271","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.10271","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:1910.10271","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.10271","pdf_url":"https://arxiv.org/pdf/1910.10271","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8299999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3121876324.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W50486269","https://openalex.org/W1487320471","https://openalex.org/W1600293573","https://openalex.org/W1662803991","https://openalex.org/W1751431909","https://openalex.org/W1850488217","https://openalex.org/W1944205345","https://openalex.org/W1985380836","https://openalex.org/W1998039896","https://openalex.org/W2009754940","https://openalex.org/W2010189695","https://openalex.org/W2028404160","https://openalex.org/W2061753713","https://openalex.org/W2097931172","https://openalex.org/W2104389751","https://openalex.org/W2108114251","https://openalex.org/W2110099400","https://openalex.org/W2112420033","https://openalex.org/W2115519224","https://openalex.org/W2125724988","https://openalex.org/W2133282568","https://openalex.org/W2143621361","https://openalex.org/W2147398813","https://openalex.org/W2152902239","https://openalex.org/W2168359464","https://openalex.org/W2178643644","https://openalex.org/W2397735741","https://openalex.org/W2555652361","https://openalex.org/W2570022719","https://openalex.org/W2885843666","https://openalex.org/W2885981445","https://openalex.org/W2903569780","https://openalex.org/W2912712349","https://openalex.org/W2914335791","https://openalex.org/W2941097477","https://openalex.org/W2951590424","https://openalex.org/W2963465244","https://openalex.org/W2964186085","https://openalex.org/W2964284806","https://openalex.org/W2968743040","https://openalex.org/W3102381603","https://openalex.org/W3102676469","https://openalex.org/W3196847620","https://openalex.org/W4232620022","https://openalex.org/W4238524517","https://openalex.org/W6602031475","https://openalex.org/W6629353124","https://openalex.org/W6637077600","https://openalex.org/W6639039794","https://openalex.org/W6640716383","https://openalex.org/W6657494743","https://openalex.org/W6674777300","https://openalex.org/W6676576766","https://openalex.org/W6679680281","https://openalex.org/W6681556291","https://openalex.org/W6736146505","https://openalex.org/W6743785172","https://openalex.org/W6751959615","https://openalex.org/W6752838982","https://openalex.org/W6753991998","https://openalex.org/W6767544959"],"related_works":["https://openalex.org/W3086984058","https://openalex.org/W2576746119","https://openalex.org/W2949446396","https://openalex.org/W2148250692","https://openalex.org/W1594658837","https://openalex.org/W2157016390","https://openalex.org/W2953067537","https://openalex.org/W3038006069","https://openalex.org/W2952099252","https://openalex.org/W2603526483","https://openalex.org/W3102508570","https://openalex.org/W2808053666","https://openalex.org/W1861297722","https://openalex.org/W1808410902","https://openalex.org/W3124285628","https://openalex.org/W2796393948","https://openalex.org/W3157822308","https://openalex.org/W1945796651","https://openalex.org/W45156998","https://openalex.org/W2257760079"],"abstract_inverted_index":{"In":[0],"this":[1,105],"paper":[2],"we":[3,24,42,108,128,154],"present":[4,98],"a":[5,72,122],"model":[6],"for":[7],"the":[8,29,34,39,48,76,111,119,131,144,150],"hidden":[9,60,112],"Markovian":[10,22,73],"bandit":[11],"problem":[12],"with":[13],"linear":[14],"rewards.":[15],"As":[16],"opposed":[17],"to":[18,33,65,71,80,87,94,104,136],"current":[19],"work":[20],"on":[21,143],"bandits,":[23],"do":[25],"not":[26,141],"assume":[27,43],"that":[28,54,91,130,139],"state":[30],"is":[31,63,78,84,92],"known":[32],"decision":[35,49],"maker":[36,50],"before":[37],"making":[38],"decision.":[40],"Furthermore,":[41,127],"structural":[44,132],"side":[45,133],"information":[46,134],"where":[47],"knows":[51],"in":[52,118,149,159],"advance":[53],"there":[55],"are":[56],"two":[57],"types":[58],"of":[59,121,146],"states;":[61],"one":[62],"common":[64],"all":[66],"arms":[67],"and":[68,75,83,101,114],"evolves":[69],"according":[70,86],"distribution,":[74],"other":[77],"unique":[79,93],"each":[81,95],"arm":[82],"distributed":[85],"an":[88,99],"i.i.d.":[89],"process":[90],"arm.":[96],"We":[97],"algorithm":[100],"regret":[102,117,138],"analysis":[103],"problem.":[106],"Surprisingly,":[107],"can":[109],"recover":[110],"states":[113],"maintain":[115],"logarithmic":[116],"case":[120],"convex":[123],"polytope":[124],"action":[125,151],"set.":[126],"show":[129],"leads":[135],"expected":[137],"does":[140],"depend":[142],"number":[145],"extreme":[147],"points":[148],"space.":[152],"Therefore,":[153],"obtain":[155],"practical":[156],"solutions":[157],"even":[158],"high":[160],"dimensional":[161],"problems.":[162]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}