{"id":"https://openalex.org/W2042117588","doi":"https://doi.org/10.1109/globalsip.2014.7032327","title":"Multi-policy posterior sampling for restless Markov bandits","display_name":"Multi-policy posterior sampling for restless Markov bandits","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2042117588","doi":"https://doi.org/10.1109/globalsip.2014.7032327","mag":"2042117588"},"language":"en","primary_location":{"id":"doi:10.1109/globalsip.2014.7032327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2014.7032327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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/A5034452450","display_name":"Suleman Alnatheer","orcid":null},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Suleman Alnatheer","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Stevens Institute of Technology, New Jersey","Department of Electrical and Computer Engineering Stevens Institute of Technology, Hoboken, New Jersey 07030-5991"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Stevens Institute of Technology, New Jersey","institution_ids":["https://openalex.org/I108468826"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering Stevens Institute of Technology, Hoboken, New Jersey 07030-5991","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069857153","display_name":"Hong Man","orcid":"https://orcid.org/0000-0002-8892-3066"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Man","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Stevens Institute of Technology, New Jersey","Department of Electrical and Computer Engineering Stevens Institute of Technology, Hoboken, New Jersey 07030-5991"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Stevens Institute of Technology, New Jersey","institution_ids":["https://openalex.org/I108468826"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering Stevens Institute of Technology, Hoboken, New Jersey 07030-5991","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034452450"],"corresponding_institution_ids":["https://openalex.org/I108468826"],"apc_list":null,"apc_paid":null,"fwci":0.4141,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68814156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1271","last_page":"1275"},"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":0.9983999729156494,"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":0.9944000244140625,"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/computer-science","display_name":"Computer science","score":0.6486057043075562},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.608234167098999},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5734964609146118},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5649713277816772},{"id":"https://openalex.org/keywords/aperiodic-graph","display_name":"Aperiodic graph","score":0.5516737699508667},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5491797924041748},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5112631320953369},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.48888152837753296},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4782496988773346},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34346064925193787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25996631383895874},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21482202410697937},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09444671869277954}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6486057043075562},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.608234167098999},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5734964609146118},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5649713277816772},{"id":"https://openalex.org/C104247578","wikidata":"https://www.wikidata.org/wiki/Q4779368","display_name":"Aperiodic graph","level":2,"score":0.5516737699508667},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5491797924041748},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5112631320953369},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.48888152837753296},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4782496988773346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34346064925193787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25996631383895874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21482202410697937},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09444671869277954},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globalsip.2014.7032327","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globalsip.2014.7032327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","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":11,"referenced_works":["https://openalex.org/W1601485248","https://openalex.org/W2029199203","https://openalex.org/W2039522160","https://openalex.org/W2040774021","https://openalex.org/W2056921512","https://openalex.org/W2105556121","https://openalex.org/W2168405694","https://openalex.org/W2171671264","https://openalex.org/W3102381603","https://openalex.org/W3125634603","https://openalex.org/W6786166493"],"related_works":["https://openalex.org/W2037661079","https://openalex.org/W2339191433","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"This":[0],"paper":[1,138],"considers":[2],"Multi-Arms":[3],"Restless":[4,43],"Bandits":[5,44],"problem,":[6],"where":[7,161],"each":[8,75],"arm":[9,76,109],"have":[10],"time":[11,19,66],"varying":[12],"rewards":[13,102,112],"generated":[14],"from":[15,83],"unknown":[16],"two-states":[17],"discrete":[18],"Markov":[20],"process.":[21],"Each":[22],"chain":[23],"is":[24,68],"assumed":[25],"irreducible,":[26],"aperiodic,":[27],"and":[28,77,165],"non-reactive":[29],"to":[30,39,55,110,151],"agent":[31],"actions.":[32],"Optimal":[33],"solution":[34],"or":[35,92,123],"constant":[36],"value":[37],"approximation":[38],"all":[40,60,145],"instances":[41,146,160],"of":[42,86,103,113,117,136,147,159],"problem":[45,149],"does":[46],"not":[47],"exist;":[48],"in":[49,144],"fact":[50],"it":[51],"has":[52],"been":[53],"proven":[54],"be":[56],"intractable":[57],"even":[58],"if":[59],"parameters":[61,73],"were":[62],"deterministic.":[63],"A":[64],"polynomial":[65],"algorithm":[67,99],"proposed":[69,98],"that":[70,139],"learns":[71],"transitional":[72],"for":[74],"selects":[78],"the":[79,97,134,137,148],"perceived":[80,108],"optimal":[81],"policy":[82],"a":[84,90,156],"set":[85,158],"predefined":[87],"policies":[88],"using":[89,119],"beliefs":[91],"probability":[93,121],"distributions.":[94],"More":[95],"precisely,":[96],"compares":[100],"mean":[101],"consistently":[104],"staying":[105],"with":[106],"best":[107],"means":[111],"Myopically":[114],"accessed":[115],"combination":[116],"arms":[118,162],"randomized":[120],"matching":[122],"better":[124],"known":[125],"as":[126],"Thompson":[127],"Sampling.":[128],"Empirical":[129],"evaluations":[130],"are":[131,163],"presented":[132],"at":[133],"end":[135],"show":[140],"an":[141],"improve":[142],"performance":[143],"compared":[150],"other":[152],"existing":[153],"algorithms":[154],"except":[155],"small":[157],"similar":[164],"bursty.":[166]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}