{"id":"https://openalex.org/W3086984058","doi":"https://doi.org/10.1109/cdc42340.2020.9304511","title":"Restless Hidden Markov Bandit with Linear Rewards","display_name":"Restless Hidden Markov Bandit with Linear Rewards","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3086984058","doi":"https://doi.org/10.1109/cdc42340.2020.9304511","mag":"3086984058"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9304511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","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/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":["Stanford University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, USA","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"],"raw_orcid":null,"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/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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18840132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":null,"first_page":"1183","last_page":"1189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13497","display_name":"Hermeneutics and Narrative Identity","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13497","display_name":"Hermeneutics and Narrative Identity","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1211","display_name":"Philosophy"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13695","display_name":"Aging, Elder Care, and Social Issues","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13099","display_name":"Health, Medicine and Society","score":0.95660001039505,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.8797386884689331},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.616665780544281},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.6098257303237915},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.548895001411438},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5373626351356506},{"id":"https://openalex.org/keywords/polytope","display_name":"Polytope","score":0.5172751545906067},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5003371238708496},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4999561309814453},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.47890129685401917},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4761604964733124},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.47114983201026917},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46806707978248596},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.435497522354126},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.4218718409538269},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.408197283744812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2671222686767578},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22221088409423828},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16369163990020752},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.14343932271003723},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08086839318275452}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8797386884689331},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.616665780544281},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6098257303237915},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.548895001411438},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5373626351356506},{"id":"https://openalex.org/C145691206","wikidata":"https://www.wikidata.org/wiki/Q747980","display_name":"Polytope","level":2,"score":0.5172751545906067},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5003371238708496},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4999561309814453},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.47890129685401917},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4761604964733124},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.47114983201026917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46806707978248596},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.435497522354126},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.4218718409538269},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.408197283744812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2671222686767578},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22221088409423828},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16369163990020752},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.14343932271003723},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08086839318275452},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc42340.2020.9304511","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1751431909","https://openalex.org/W1985380836","https://openalex.org/W1998039896","https://openalex.org/W2009754940","https://openalex.org/W2061753713","https://openalex.org/W2104389751","https://openalex.org/W2110099400","https://openalex.org/W2143621361","https://openalex.org/W2168359464","https://openalex.org/W2178643644","https://openalex.org/W2397735741","https://openalex.org/W2555652361","https://openalex.org/W2570022719","https://openalex.org/W2914335791","https://openalex.org/W2964186085","https://openalex.org/W3119402609","https://openalex.org/W4232620022","https://openalex.org/W6602031475","https://openalex.org/W6637077600","https://openalex.org/W6639039794","https://openalex.org/W6674777300","https://openalex.org/W6676576766","https://openalex.org/W6751959615","https://openalex.org/W6752838982","https://openalex.org/W6753727089","https://openalex.org/W6753991998","https://openalex.org/W6756526481","https://openalex.org/W6761957732"],"related_works":["https://openalex.org/W3121876324","https://openalex.org/W2576746119","https://openalex.org/W1594658837","https://openalex.org/W2949446396","https://openalex.org/W3038006069","https://openalex.org/W2148250692","https://openalex.org/W2603526483","https://openalex.org/W2157016390","https://openalex.org/W2808053666","https://openalex.org/W2952099252","https://openalex.org/W1808410902","https://openalex.org/W2109690147","https://openalex.org/W3124285628","https://openalex.org/W1861297722","https://openalex.org/W3102508570","https://openalex.org/W2796393948","https://openalex.org/W246157401","https://openalex.org/W2914049206","https://openalex.org/W2952117888","https://openalex.org/W3157822308"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"algorithm":[4],"and":[5,39,76,107],"regret":[6,141,160],"analysis":[7],"for":[8],"the":[9,21,25,36,56,62,65,77,85,92,102,105,111,119,143,153,166,172],"restless":[10],"hidden":[11,41,108,124],"Markov":[12],"bandit":[13],"problem":[14,20],"with":[15],"linear":[16,31,97],"rewards.":[17],"In":[18,43],"this":[19,129],"reward":[22,93],"received":[23,78],"by":[24],"decision":[26,57,86,112],"maker":[27,58,87,113],"is":[28,82,94],"a":[29,40,95],"random":[30,96],"function":[32,98],"which":[33,99],"depends":[34,100],"on":[35,48,73,101,165],"arm":[37],"selected":[38,103],"state.":[42],"contrast":[44],"to":[45,158],"previous":[46],"works":[47],"Markovian":[49],"bandits,":[50],"we":[51,127,136,150],"do":[52],"not":[53,115,163],"assume":[54],"that":[55,84,91,152,161],"receives":[59],"information":[60,131,156],"regarding":[61],"state":[63],"of":[64,122,145,168],"system,":[66],"but":[67],"can":[68,137],"only":[69],"infer/estimate":[70],"it":[71,81],"based":[72],"its":[74],"actions":[75],"reward.":[79],"Additionally,":[80],"assumed":[83],"knows":[88],"in":[89,117,142,171],"advance":[90,118],"arm,":[104],"action,":[106],"states.":[109],"However,":[110],"does":[114,162],"know":[116],"probability":[120],"distributions":[121],"these":[123],"states;":[125],"thus":[126],"call":[128],"side":[130,133,155],"structural":[132,154],"information.":[134],"Surprisingly,":[135],"still":[138],"maintain":[139],"logarithmic":[140],"case":[144],"polyhedral":[146],"action":[147,173],"set.":[148],"Furthermore,":[149],"show":[151],"leads":[157],"expected":[159],"depend":[164],"number":[167],"extreme":[169],"points":[170],"space.":[174]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2020-09-21T00:00:00"}