{"id":"https://openalex.org/W2052471706","doi":"https://doi.org/10.1007/s10472-010-9190-1","title":"A dynamic programming strategy to balance exploration and exploitation in the bandit problem","display_name":"A dynamic programming strategy to balance exploration and exploitation in the bandit problem","publication_year":2010,"publication_date":"2010-06-09","ids":{"openalex":"https://openalex.org/W2052471706","doi":"https://doi.org/10.1007/s10472-010-9190-1","mag":"2052471706"},"language":"en","primary_location":{"id":"doi:10.1007/s10472-010-9190-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10472-010-9190-1","pdf_url":null,"source":{"id":"https://openalex.org/S90199469","display_name":"Annals of Mathematics and Artificial Intelligence","issn_l":"1012-2443","issn":["1012-2443","1573-7470"],"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":"Annals of Mathematics and Artificial Intelligence","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/A5062257690","display_name":"Olivier Caelen","orcid":"https://orcid.org/0000-0001-6970-9825"},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Olivier Caelen","raw_affiliation_strings":["Computer Science Department, Universit\u00e9 Libre de Bruxelles, Bruxelles, Belgium","Computer Science Department, Universit\u00e9 Libre de Bruxelles, CP 212, Bvd. du Triomphe, 1050, Bruxelles, Belgium","Computer Science Department, Universit\u00e9 Libre de Bruxelles, Bruxelles, Belgium 1050#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Universit\u00e9 Libre de Bruxelles, Bruxelles, Belgium","institution_ids":["https://openalex.org/I132053463"]},{"raw_affiliation_string":"Computer Science Department, Universit\u00e9 Libre de Bruxelles, CP 212, Bvd. du Triomphe, 1050, Bruxelles, Belgium","institution_ids":["https://openalex.org/I132053463"]},{"raw_affiliation_string":"Computer Science Department, Universit\u00e9 Libre de Bruxelles, Bruxelles, Belgium 1050#TAB#","institution_ids":["https://openalex.org/I132053463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072869049","display_name":"Gianluca Bontempi","orcid":"https://orcid.org/0000-0001-8621-316X"},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Gianluca Bontempi","raw_affiliation_strings":["Computer Science Department, Universit\u00e9 Libre de Bruxelles, Bruxelles, Belgium","Computer Science Department, Universit\u00e9 Libre de Bruxelles, CP 212, Bvd. du Triomphe, 1050, Bruxelles, Belgium","Computer Science Department, Universit\u00e9 Libre de Bruxelles, Bruxelles, Belgium 1050#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Universit\u00e9 Libre de Bruxelles, Bruxelles, Belgium","institution_ids":["https://openalex.org/I132053463"]},{"raw_affiliation_string":"Computer Science Department, Universit\u00e9 Libre de Bruxelles, CP 212, Bvd. du Triomphe, 1050, Bruxelles, Belgium","institution_ids":["https://openalex.org/I132053463"]},{"raw_affiliation_string":"Computer Science Department, Universit\u00e9 Libre de Bruxelles, Bruxelles, Belgium 1050#TAB#","institution_ids":["https://openalex.org/I132053463"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5062257690","https://openalex.org/A5072869049"],"corresponding_institution_ids":["https://openalex.org/I132053463"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.6975,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75543401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"60","issue":"1-2","first_page":"3","last_page":"24"},"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":0.9991999864578247,"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/T12288","display_name":"Optimization and Search Problems","score":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6696130037307739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6564649343490601},{"id":"https://openalex.org/keywords/multi-armed-bandit","display_name":"Multi-armed bandit","score":0.6068652868270874},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5992146730422974},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5264462232589722},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.4663642346858978},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4303191900253296},{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.4120887815952301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40685737133026123},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2958061099052429},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2018648386001587},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1490665078163147},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.12052720785140991}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6696130037307739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6564649343490601},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.6068652868270874},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5992146730422974},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5264462232589722},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.4663642346858978},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4303191900253296},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.4120887815952301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40685737133026123},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2958061099052429},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2018648386001587},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1490665078163147},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.12052720785140991},{"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/C99508421","wikidata":"https://www.wikidata.org/wiki/Q2678675","display_name":"Physical medicine and rehabilitation","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10472-010-9190-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10472-010-9190-1","pdf_url":null,"source":{"id":"https://openalex.org/S90199469","display_name":"Annals of Mathematics and Artificial Intelligence","issn_l":"1012-2443","issn":["1012-2443","1573-7470"],"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":"Annals of Mathematics and Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:dipot.ulb.ac.be:2013/71617","is_oa":false,"landing_page_url":"http://hdl.handle.net/2013/ULB-DIPOT:oai:dipot.ulb.ac.be:2013/71617","pdf_url":null,"source":{"id":"https://openalex.org/S4306401063","display_name":"D\u00e9p\u00f4t institutionnel de l'Universit\u00e9 libre de Bruxelles (Universit\u00e9 Libre de Bruxelles)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I132053463","host_organization_name":"Universit\u00e9 Libre de Bruxelles","host_organization_lineage":["https://openalex.org/I132053463"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of mathematics and artificial intelligence","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W100327610","https://openalex.org/W566184825","https://openalex.org/W809822409","https://openalex.org/W1506806321","https://openalex.org/W1515851193","https://openalex.org/W1515933446","https://openalex.org/W1516061453","https://openalex.org/W1545148916","https://openalex.org/W1576452626","https://openalex.org/W1586868336","https://openalex.org/W1601081659","https://openalex.org/W1622484071","https://openalex.org/W1663973292","https://openalex.org/W1983916623","https://openalex.org/W1995945562","https://openalex.org/W1998498767","https://openalex.org/W2002985443","https://openalex.org/W2116067849","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2168405694","https://openalex.org/W2231190415","https://openalex.org/W2293688512","https://openalex.org/W2317700292","https://openalex.org/W2334782222","https://openalex.org/W2487144912","https://openalex.org/W2561675875","https://openalex.org/W3011120880","https://openalex.org/W3106889297","https://openalex.org/W3124770868","https://openalex.org/W3143261911","https://openalex.org/W4214717370","https://openalex.org/W4241387086","https://openalex.org/W4254113915","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2787412873","https://openalex.org/W3209920515","https://openalex.org/W3119536152"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
