{"id":"https://openalex.org/W2903743315","doi":"https://doi.org/10.1007/s10994-018-5767-4","title":"Bayesian optimistic Kullback\u2013Leibler exploration","display_name":"Bayesian optimistic Kullback\u2013Leibler exploration","publication_year":2018,"publication_date":"2018-12-19","ids":{"openalex":"https://openalex.org/W2903743315","doi":"https://doi.org/10.1007/s10994-018-5767-4","mag":"2903743315"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-018-5767-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-018-5767-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5767-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5767-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106407178","display_name":"Kanghoon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kanghoon Lee","raw_affiliation_strings":["School of Computing, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computing, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038564473","display_name":"Geon-Hyeong Kim","orcid":"https://orcid.org/0000-0003-0114-9643"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Geon-Hyeong Kim","raw_affiliation_strings":["School of Computing, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computing, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035060247","display_name":"Pedro A. Ortega","orcid":"https://orcid.org/0000-0003-2261-8453"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210113297","display_name":"Google (United Kingdom)","ror":"https://ror.org/024bc3e07","country_code":"GB","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210113297","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pedro Ortega","raw_affiliation_strings":["Google UK, DeepMind 6th Floor, Six Pancras Square, Kings Cross, London, N1C 4AG, UK"],"affiliations":[{"raw_affiliation_string":"Google UK, DeepMind 6th Floor, Six Pancras Square, Kings Cross, London, N1C 4AG, UK","institution_ids":["https://openalex.org/I4210113297","https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007905483","display_name":"Daniel D. Lee","orcid":"https://orcid.org/0000-0002-2163-2686"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel D. Lee","raw_affiliation_strings":["Cornell Tech, 2 West Loop Road, New York, NY, 10044, USA"],"affiliations":[{"raw_affiliation_string":"Cornell Tech, 2 West Loop Road, New York, NY, 10044, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074569524","display_name":"Kee-Eung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kee-Eung Kim","raw_affiliation_strings":["School of Computing, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"School of Computing, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5106407178"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.1692,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62358618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"108","issue":"5","first_page":"765","last_page":"783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9993000030517578,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9983000159263611,"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/bayesian-probability","display_name":"Bayesian probability","score":0.6648975610733032},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6200380921363831},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6017224788665771},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.5916600823402405},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5654735565185547},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5653950572013855},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4651098847389221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4645082354545593},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4484338164329529},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42772161960601807},{"id":"https://openalex.org/keywords/bayesian-programming","display_name":"Bayesian programming","score":0.4233185648918152},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4104156494140625},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4000054895877838},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33138108253479004},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3116285502910614},{"id":"https://openalex.org/keywords/bayes-factor","display_name":"Bayes factor","score":0.2985526919364929}],"concepts":[{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6648975610733032},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6200380921363831},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6017224788665771},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.5916600823402405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5654735565185547},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5653950572013855},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4651098847389221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4645082354545593},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4484338164329529},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42772161960601807},{"id":"https://openalex.org/C127043819","wikidata":"https://www.wikidata.org/wiki/Q16243608","display_name":"Bayesian programming","level":5,"score":0.4233185648918152},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4104156494140625},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4000054895877838},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33138108253479004},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3116285502910614},{"id":"https://openalex.org/C142291917","wikidata":"https://www.wikidata.org/wiki/Q4165283","display_name":"Bayes factor","level":4,"score":0.2985526919364929},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-018-5767-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-018-5767-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5767-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-018-5767-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-018-5767-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-018-5767-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1446640842","display_name":null,"funder_award_id":"2017-0-01778","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G313390495","display_name":null,"funder_award_id":"UD170018CD","funder_id":"https://openalex.org/F4320324161","funder_display_name":"Korea Advanced Institute of Science and Technology"},{"id":"https://openalex.org/G3953289899","display_name":null,"funder_award_id":"2017-0-01778","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5174525149","display_name":null,"funder_award_id":"UD170018CD","funder_id":"https://openalex.org/F4320334874","funder_display_name":"Defense Acquisition Program Administration"},{"id":"https://openalex.org/G6034860306","display_name":null,"funder_award_id":"UD170018CD","funder_id":"https://openalex.org/F4320323103","funder_display_name":"Agency for Defense Development"},{"id":"https://openalex.org/G6947043535","display_name":null,"funder_award_id":"Contract UD170018CD","funder_id":"https://openalex.org/F4320323103","funder_display_name":"Agency for Defense Development"}],"funders":[{"id":"https://openalex.org/F4320323103","display_name":"Agency for Defense Development","ror":"https://ror.org/05fhe0r85"},{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320334874","display_name":"Defense Acquisition Program Administration","ror":"https://ror.org/04bjg9m96"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903743315.pdf","grobid_xml":"https://content.openalex.org/works/W2903743315.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1497039698","https://openalex.org/W1501823362","https://openalex.org/W1582436621","https://openalex.org/W1591803298","https://openalex.org/W1596778849","https://openalex.org/W1850488217","https://openalex.org/W1988526405","https://openalex.org/W2082691056","https://openalex.org/W2096825593","https://openalex.org/W2111764152","https://openalex.org/W2116459397","https://openalex.org/W2119567691","https://openalex.org/W2124352385","https://openalex.org/W2125710232","https://openalex.org/W2133419240","https://openalex.org/W2142971854","https://openalex.org/W2144794447","https://openalex.org/W2158232074","https://openalex.org/W2159178228","https://openalex.org/W2161966552","https://openalex.org/W2182000050","https://openalex.org/W2296319761","https://openalex.org/W2489939061","https://openalex.org/W2951333509","https://openalex.org/W2951592473","https://openalex.org/W2963214119","https://openalex.org/W3023407077","https://openalex.org/W3101676093","https://openalex.org/W4250589301","https://openalex.org/W4285719527","https://openalex.org/W4298023569","https://openalex.org/W6634907821","https://openalex.org/W6635327058","https://openalex.org/W6681472862","https://openalex.org/W7001894244"],"related_works":["https://openalex.org/W2105321464","https://openalex.org/W2887774187","https://openalex.org/W2388220555","https://openalex.org/W1554844486","https://openalex.org/W1520875569","https://openalex.org/W3048739257","https://openalex.org/W1665563134","https://openalex.org/W2963604926","https://openalex.org/W2199957582","https://openalex.org/W2033178790"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
