{"id":"https://openalex.org/W2096825593","doi":"https://doi.org/10.1109/allerton.2010.5706896","title":"Optimism in reinforcement learning and Kullback-Leibler divergence","display_name":"Optimism in reinforcement learning and Kullback-Leibler divergence","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2096825593","doi":"https://doi.org/10.1109/allerton.2010.5706896","mag":"2096825593"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2010.5706896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2010.5706896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1004.5229","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sarah Filippi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sarah Filippi","raw_affiliation_strings":["LTCI, TELECOM ParisTech and CNRS, Paris, France"],"affiliations":[{"raw_affiliation_string":"LTCI, TELECOM ParisTech and CNRS, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Olivier Cappe","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Cappe","raw_affiliation_strings":["LTCI, TELECOM ParisTech and CNRS, Paris, France"],"affiliations":[{"raw_affiliation_string":"LTCI, TELECOM ParisTech and CNRS, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":null,"display_name":"Aurelien Garivier","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Aurelien Garivier","raw_affiliation_strings":["LTCI, TELECOM ParisTech and CNRS, Paris, France"],"affiliations":[{"raw_affiliation_string":"LTCI, TELECOM ParisTech and CNRS, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":1.2091,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.82742924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"115","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9907000064849854,"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/regret","display_name":"Regret","score":0.704800009727478},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7038999795913696},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6912999749183655},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5874999761581421},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5476999878883362},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.5116999745368958},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5077999830245972},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5005000233650208}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.704800009727478},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7038999795913696},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6912999749183655},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5282999873161316},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5116999745368958},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5005000233650208},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4781999886035919},{"id":"https://openalex.org/C204017024","wikidata":"https://www.wikidata.org/wiki/Q485446","display_name":"Optimism","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4269999861717224},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.32589998841285706},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.30799999833106995},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29120001196861267},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.2773999869823456},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/allerton.2010.5706896","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2010.5706896","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1004.5229","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1004.5229","pdf_url":"https://arxiv.org/pdf/1004.5229","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":"pmh:oai:CiteSeerX.psu:10.1.1.639.6924","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.639.6924","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.stats.ox.ac.uk/__data/assets/pdf_file/0014/10319/KLModelBased_Filippi.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.762.685","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.762.685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1004.5229.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00476116v3","is_oa":true,"landing_page_url":"https://hal.science/hal-00476116","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Communication, Control, and Computing (Allerton), 2010 48th Annual Allerton Conference on, Sep 2010, Monticello (Illinois), United States. pp.115 - 122, ⟨10.1109/ALLERTON.2010.5706896⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1004.5229","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1004.5229","pdf_url":"https://arxiv.org/pdf/1004.5229","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1965878388","https://openalex.org/W1988526405","https://openalex.org/W1998376807","https://openalex.org/W2009551863","https://openalex.org/W2147967768","https://openalex.org/W2334782222","https://openalex.org/W2489939061","https://openalex.org/W6629680116","https://openalex.org/W6637077600","https://openalex.org/W6639039794","https://openalex.org/W6640648879","https://openalex.org/W6647064280","https://openalex.org/W6674777300","https://openalex.org/W6679661297","https://openalex.org/W6683603353"],"related_works":[],"abstract_inverted_index":{"We":[0],"consider":[1],"model-based":[2],"reinforcement":[3],"learning":[4],"in":[5,67,118],"finite":[6],"Markov":[7],"Decision":[8],"Processes":[9],"(MDPs),":[10],"focussing":[11],"on":[12,104,125,154],"so-called":[13],"optimistic":[14],"strategies.":[15],"In":[16,61],"MDPs,":[17],"optimism":[18],"can":[19],"be":[20],"implemented":[21],"by":[22,42],"carrying":[23],"out":[24],"extended":[25,97],"value":[26,98],"iterations":[27],"under":[28,84],"a":[29,129],"constraint":[30],"of":[31,69,120,147],"consistency":[32],"with":[33],"the":[34,71,80,105,113,135,150],"estimated":[35],"model":[36],"transition":[37],"probabilities.":[38],"The":[39],"UCRL2":[40,117],"algorithm":[41],"Auer,":[43],"Jaksch":[44],"and":[45],"Ortner":[46],"(2009),":[47],"which":[48],"follows":[49],"this":[50,62,76,142],"strategy,":[51],"has":[52,137],"recently":[53],"been":[54],"shown":[55],"to":[56],"guarantee":[57],"near-optimal":[58],"regret":[59],"bounds.":[60],"paper,":[63],"we":[64,87,108,144],"strongly":[65],"argue":[66],"favor":[68],"using":[70],"Kullback-Leibler":[72],"(KL)":[73],"divergence":[74],"for":[75,94],"purpose.":[77],"By":[78],"studying":[79],"linear":[81],"maximization":[82],"problem":[83],"KL":[85,106],"constraints,":[86],"provide":[88,145],"an":[89],"efficient":[90],"algorithm,":[91],"termed":[92],"KL-UCRL,":[93],"solving":[95],"KL-optimistic":[96],"iteration.":[99],"Using":[100],"recent":[101],"deviation":[102],"bounds":[103],"divergence,":[107],"prove":[109],"that":[110],"KL-UCRL":[111],"provides":[112],"same":[114],"guarantees":[115],"as":[116],"terms":[119],"regret.":[121],"However,":[122],"numerical":[123],"experiments":[124],"classical":[126],"benchmarks":[127],"show":[128],"significantly":[130],"improved":[131],"behavior,":[132],"particularly":[133],"when":[134],"MDP":[136],"reduced":[138],"connectivity.":[139],"To":[140],"support":[141],"observation,":[143],"elements":[146],"comparison":[148],"between":[149],"two":[151],"algorithms":[152],"based":[153],"geometric":[155],"considerations.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}