{"id":"https://openalex.org/W2148250692","doi":"https://doi.org/10.1109/icassp.2011.5946895","title":"Logarithmic weak regret of non-Bayesian restless multi-armed bandit","display_name":"Logarithmic weak regret of non-Bayesian restless multi-armed bandit","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2148250692","doi":"https://doi.org/10.1109/icassp.2011.5946895","mag":"2148250692"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5048855727","display_name":"Haoyang Liu","orcid":"https://orcid.org/0009-0002-8594-4045"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyang Liu","raw_affiliation_strings":["University of California, Davis, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007144865","display_name":"Keqin Liu","orcid":"https://orcid.org/0000-0002-7995-7125"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keqin Liu","raw_affiliation_strings":["University of California, Davis, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013788255","display_name":"Qing Zhao","orcid":"https://orcid.org/0000-0002-9590-4285"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qing Zhao","raw_affiliation_strings":["University of California, Davis, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84218800"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1968","last_page":"1971"},"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/T13553","display_name":"Age of Information Optimization","score":0.9933000206947327,"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":0.9883000254631042,"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":0.962125837802887},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.7001510858535767},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.6227515339851379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5623060464859009},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.49904680252075195},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.4886370301246643},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47799983620643616},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.44498538970947266},{"id":"https://openalex.org/keywords/investment","display_name":"Investment (military)","score":0.4350394606590271},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3035271465778351},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1293310821056366},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10291397571563721}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.962125837802887},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.7001510858535767},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.6227515339851379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5623060464859009},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.49904680252075195},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4886370301246643},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47799983620643616},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.44498538970947266},{"id":"https://openalex.org/C27548731","wikidata":"https://www.wikidata.org/wiki/Q88272","display_name":"Investment (military)","level":3,"score":0.4350394606590271},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3035271465778351},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1293310821056366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10291397571563721},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5946895","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.221.1203","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.221.1203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.ucdavis.edu/%7Eqzhao/LiuEtal11ICASSP.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1945796651","https://openalex.org/W2000080679","https://openalex.org/W2009551863","https://openalex.org/W2044502527","https://openalex.org/W2056921512","https://openalex.org/W2105556121","https://openalex.org/W2113733815","https://openalex.org/W2120125372","https://openalex.org/W2125724988","https://openalex.org/W2139964991","https://openalex.org/W2140571193","https://openalex.org/W2141515329","https://openalex.org/W2157146750","https://openalex.org/W2168405694","https://openalex.org/W2962764550","https://openalex.org/W3125634603","https://openalex.org/W4232620022","https://openalex.org/W6640924194"],"related_works":["https://openalex.org/W2947263763","https://openalex.org/W4288373430","https://openalex.org/W3036260055","https://openalex.org/W4287753704","https://openalex.org/W2970347269","https://openalex.org/W3158925485","https://openalex.org/W2996735312","https://openalex.org/W4287863949","https://openalex.org/W1850488217","https://openalex.org/W4287102143"],"abstract_inverted_index":{"We":[0,118],"consider":[1],"the":[2,33,36,48,58,63,70,92,98,101,108,154,160,170,176,179,185],"restless":[3],"multi-armed":[4],"bandit":[5],"(RMAB)":[6],"problem":[7],"with":[8,95,134],"unknown":[9,61,201],"dynamics.":[10],"At":[11],"each":[12,30],"time,":[13],"a":[14,84,120,132,165],"player":[15,102],"chooses":[16],"K":[17,105,115,186],"out":[18],"of":[19,29,57,83,137,191],"N":[20],"(N":[21],">;":[22],"K)":[23],"arms":[24,59,106],"to":[25,43,62,68,97,123,163,169],"play":[26],"The":[27,54,65,81],"state":[28],"arm":[31,37,49,78],"determines":[32],"reward":[34,73,93,182],"when":[35,139],"is":[38,50,67,86,148,156],"played":[39],"and":[40,111,204],"transits":[41],"according":[42],"Markovian":[44,55],"rules":[45],"no":[46,151],"matter":[47],"engaged":[51],"or":[52],"passive.":[53],"dynamics":[56],"are":[60,107],"player.":[64],"objective":[66],"maximize":[69],"long-term":[71],"expected":[72],"by":[74,88,184],"designing":[75],"an":[76,140],"optimal":[77],"selection":[79],"policy.":[80],"performance":[82],"policy":[85,162],"measured":[87],"regret,":[89],"defined":[90],"as":[91,124],"loss":[94],"respect":[96],"case":[99],"where":[100],"knows":[103],"which":[104],"most":[109],"rewarding":[110],"always":[112],"plays":[113],"these":[114,192],"best":[116,187],"arms.":[117,188],"construct":[119],"policy,":[121],"referred":[122],"Restless":[125],"Upper":[126],"Confidence":[127],"Bound":[128],"(RUCB),":[129],"that":[130],"achieves":[131,178],"regret":[133,166],"logarithmic":[135,171],"order":[136],"time":[138],"arbitrary":[141],"nontrivial":[142],"bound":[143],"on":[144],"certain":[145],"system":[146,155,177],"parameters":[147],"known.":[149],"When":[150],"knowledge":[152],"about":[153],"available,":[157],"we":[158],"extend":[159],"RUCB":[161],"achieve":[164],"arbitrarily":[167],"close":[168],"order.":[172],"In":[173],"both":[174],"cases,":[175],"maximum":[180],"average":[181],"offered":[183],"Potential":[189],"applications":[190],"results":[193],"include":[194],"cognitive":[195],"radio":[196],"networks,":[197],"opportunistic":[198],"communications":[199],"in":[200],"fading":[202],"environments,":[203],"financial":[205],"investment.":[206]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}