{"id":"https://openalex.org/W4389065325","doi":"https://doi.org/10.1109/tac.2023.3336835","title":"Adaptive KL-UCB Based Bandit Algorithms for Markovian and I.I.D. Settings","display_name":"Adaptive KL-UCB Based Bandit Algorithms for Markovian and I.I.D. Settings","publication_year":2023,"publication_date":"2023-11-27","ids":{"openalex":"https://openalex.org/W4389065325","doi":"https://doi.org/10.1109/tac.2023.3336835"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2023.3336835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3336835","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-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/A5018946124","display_name":"Arghyadip Roy","orcid":"https://orcid.org/0000-0001-9955-9514"},"institutions":[{"id":"https://openalex.org/I1317621060","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079","country_code":"IN","type":"education","lineage":["https://openalex.org/I1317621060"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Arghyadip Roy","raw_affiliation_strings":["Mehta Family School of Data Science and Artificial Intelligence, Indian Institute of Technology Guwahati, Guwahati, India"],"affiliations":[{"raw_affiliation_string":"Mehta Family School of Data Science and Artificial Intelligence, Indian Institute of Technology Guwahati, Guwahati, India","institution_ids":["https://openalex.org/I1317621060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028903768","display_name":"Sanjay Shakkottai","orcid":"https://orcid.org/0000-0002-4325-9050"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Shakkottai","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA","Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078518595","display_name":"R. Srikant","orcid":"https://orcid.org/0000-0003-1483-5204"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Srikant","raw_affiliation_strings":["Department of Electrical and Computer Engineering, and Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, and Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018946124"],"corresponding_institution_ids":["https://openalex.org/I1317621060"],"apc_list":null,"apc_paid":null,"fwci":1.2743,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.82356279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"69","issue":"4","first_page":"2637","last_page":"2644"},"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":0.9969000220298767,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9927999973297119,"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":0.8761447072029114},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.64212965965271},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6264261603355408},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5834497213363647},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.5720657110214233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5241346955299377},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5068762898445129},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.46494972705841064},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.42638319730758667},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4209222197532654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39715316891670227},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10689747333526611},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10634076595306396}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8761447072029114},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.64212965965271},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6264261603355408},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5834497213363647},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5720657110214233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5241346955299377},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5068762898445129},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.46494972705841064},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.42638319730758667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4209222197532654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39715316891670227},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10689747333526611},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10634076595306396},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2023.3336835","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2023.3336835","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327457","display_name":"Indian Institute of Technology Guwahati","ror":"https://ror.org/0022nd079"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1570963478","https://openalex.org/W1751431909","https://openalex.org/W1998498767","https://openalex.org/W2000080679","https://openalex.org/W2009551863","https://openalex.org/W2056921512","https://openalex.org/W2077148472","https://openalex.org/W2077902449","https://openalex.org/W2113733815","https://openalex.org/W2120125372","https://openalex.org/W2125724988","https://openalex.org/W2135730283","https://openalex.org/W2146950091","https://openalex.org/W2150328967","https://openalex.org/W2151544200","https://openalex.org/W2153975459","https://openalex.org/W2168405694","https://openalex.org/W2568033804","https://openalex.org/W2796125956","https://openalex.org/W3020125231","https://openalex.org/W3027822437","https://openalex.org/W3100329718","https://openalex.org/W3102381603","https://openalex.org/W3104981656","https://openalex.org/W3154055679","https://openalex.org/W4206530644","https://openalex.org/W4232620022","https://openalex.org/W4234228486","https://openalex.org/W4389065325","https://openalex.org/W6630117878","https://openalex.org/W6639039794","https://openalex.org/W6682110964","https://openalex.org/W6683646410","https://openalex.org/W6736209634","https://openalex.org/W6750652772","https://openalex.org/W6752838982","https://openalex.org/W6773397638"],"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":{"In":[0,23],"the":[1,15,28,39,79,82,92,118,138,172],"regret-based":[2],"formulation":[3],"of":[4,14,30,41,71,101,116,166],"Multi-armed":[5],"Bandit":[6],"(MAB)":[7],"problems,":[8],"except":[9],"in":[10,37,63,179],"rare":[11],"instances,":[12],"much":[13],"literature":[16],"focuses":[17],"on":[18],"arms":[19],"with":[20],"i.i.d.":[21,95,125,147,184],"rewards.":[22],"this":[24,128],"paper,":[25],"we":[26,130],"consider":[27],"problem":[29],"obtaining":[31],"regret":[32,62],"guarantees":[33],"for":[34,91,182],"MAB":[35],"problems":[36,65],"which":[38],"rewards":[40,96,103,139],"each":[42,141],"arm":[43,142,173],"form":[44],"a":[45,53,60,69,98,132,149,159,163],"Markov":[46,102],"chain":[47],"that":[48,112,135,171],"may":[49],"not":[50,67],"belong":[51],"to":[52,108,162],"single":[54],"parameter":[55],"exponential":[56],"family.":[57],"To":[58,126],"achieve":[59],"logarithmic":[61],"such":[64,86],"is":[66,106,121,175],"difficult:":[68],"variation":[70],"standard":[72,160],"Kullback-Leibler":[73],"Upper":[74],"Confidence":[75],"Bound":[76],"(KL-UCB)":[77],"does":[78],"job.":[80],"However,":[81],"constants":[83],"obtained":[84],"from":[85,140,157],"an":[87,110],"analysis":[88],"are":[89,97,143],"poor":[90],"following":[93],"reason:":[94],"special":[99],"case":[100],"and":[104,185],"it":[105,169],"difficult":[107],"design":[109],"algorithm":[111,134,154],"works":[113],"well":[114],"independent":[115],"whether":[117,137],"underlying":[119],"model":[120],"truly":[122,144],"Markovian":[123,145,186],"or":[124,146],"overcome":[127],"issue,":[129],"introduce":[131],"novel":[133],"identifies":[136],"using":[148,158],"TV":[150],"distance-based":[151],"test.":[152],"Our":[153],"then":[155],"switches":[156],"KL-UCB":[161,167],"specialized":[164],"version":[165],"when":[168],"determines":[170],"reward":[174],"Markovian,":[176],"thus":[177],"resulting":[178],"low":[180],"regrets":[181],"both":[183],"settings.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}