{"id":"https://openalex.org/W1862757251","doi":"https://doi.org/10.1007/978-3-642-27645-3_11","title":"Bayesian Reinforcement Learning","display_name":"Bayesian Reinforcement Learning","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1862757251","doi":"https://doi.org/10.1007/978-3-642-27645-3_11","mag":"1862757251"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-27645-3_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_11","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00840479","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082325811","display_name":"Nikos Vlassis","orcid":null},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Nikos Vlassis","raw_affiliation_strings":["Luxembourg Centre for Systems Biomedicine, University of Luxembourg, Luxembourg, Luxembourg","OneTree, Luxembourg, Luxembourg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Luxembourg Centre for Systems Biomedicine, University of Luxembourg, Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]},{"raw_affiliation_string":"OneTree, Luxembourg, Luxembourg","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013843778","display_name":"Mohammad Ghavamzadeh","orcid":"https://orcid.org/0000-0003-0930-8688"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mohammad Ghavamzadeh","raw_affiliation_strings":["INRIA, Sophia Antipolis, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036260775","display_name":"Shie Mannor","orcid":"https://orcid.org/0000-0003-4439-7647"},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Shie Mannor","raw_affiliation_strings":["Technion, Haifa, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion, Haifa, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050467922","display_name":"Pascal Poupart","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pascal Poupart","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7109,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.96577554,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"359","last_page":"386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9987999796867371,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.996399998664856,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8457916378974915},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6853414177894592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5843165516853333},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5561844110488892},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5217493772506714},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4887404441833496},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.45163094997406006},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4361749589443207},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.41781771183013916},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41617852449417114},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4148048758506775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27322638034820557},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.17118263244628906}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8457916378974915},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6853414177894592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5843165516853333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5561844110488892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5217493772506714},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4887404441833496},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.45163094997406006},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4361749589443207},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.41781771183013916},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41617852449417114},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4148048758506775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27322638034820557},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.17118263244628906},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-642-27645-3_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_11","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-00840479v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00840479","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":"Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State of the Art, Springer Verlag, 2012","raw_type":"Book sections"},{"id":"pmh:oai:orbilu.uni.lu:10993/3390","is_oa":true,"landing_page_url":"http://orbilu.uni.lu/handle/10993/3390","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Reinforcement Learning: State of the Art, 359-386 (2012)","raw_type":"peer reviewed"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00840479v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00840479","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":"Marco Wiering and Martijn van Otterlo. Reinforcement Learning: State of the Art, Springer Verlag, 2012","raw_type":"Book sections"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":90,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W342056545","https://openalex.org/W1485515110","https://openalex.org/W1496855202","https://openalex.org/W1497039698","https://openalex.org/W1507852408","https://openalex.org/W1510073064","https://openalex.org/W1512919909","https://openalex.org/W1515933446","https://openalex.org/W1552684655","https://openalex.org/W1564755532","https://openalex.org/W1569296262","https://openalex.org/W1582436621","https://openalex.org/W1591803298","https://openalex.org/W1594783240","https://openalex.org/W1746819321","https://openalex.org/W1922608396","https://openalex.org/W1931792391","https://openalex.org/W1935502388","https://openalex.org/W1965878388","https://openalex.org/W2004030284","https://openalex.org/W2006258746","https://openalex.org/W2039522160","https://openalex.org/W2069045459","https://openalex.org/W2071814471","https://openalex.org/W2091565802","https://openalex.org/W2091735588","https://openalex.org/W2094387729","https://openalex.org/W2098102888","https://openalex.org/W2099089474","https://openalex.org/W2100677568","https://openalex.org/W2100785108","https://openalex.org/W2108682071","https://openalex.org/W2108692343","https://openalex.org/W2110720940","https://openalex.org/W2111833414","https://openalex.org/W2114537044","https://openalex.org/W2116459397","https://openalex.org/W2119678437","https://openalex.org/W2119717200","https://openalex.org/W2123372395","https://openalex.org/W2124352385","https://openalex.org/W2125612430","https://openalex.org/W2125710232","https://openalex.org/W2128643385","https://openalex.org/W2130801532","https://openalex.org/W2132057084","https://openalex.org/W2132849848","https://openalex.org/W2133040789","https://openalex.org/W2133733518","https://openalex.org/W2134197408","https://openalex.org/W2136602922","https://openalex.org/W2136719210","https://openalex.org/W2137509429","https://openalex.org/W2143362857","https://openalex.org/W2144446635","https://openalex.org/W2144794447","https://openalex.org/W2149551746","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2156974606","https://openalex.org/W2158640361","https://openalex.org/W2158907787","https://openalex.org/W2159008857","https://openalex.org/W2162888803","https://openalex.org/W2164294821","https://openalex.org/W2164569010","https://openalex.org/W2165622730","https://openalex.org/W2166473218","https://openalex.org/W2167061265","https://openalex.org/W2168565265","https://openalex.org/W2169743339","https://openalex.org/W2296381616","https://openalex.org/W2325958504","https://openalex.org/W2522381472","https://openalex.org/W2531139068","https://openalex.org/W2595840341","https://openalex.org/W2795693315","https://openalex.org/W2913340405","https://openalex.org/W2964117027","https://openalex.org/W3011120880","https://openalex.org/W3015571647","https://openalex.org/W3101822862","https://openalex.org/W3103182070","https://openalex.org/W3104240813","https://openalex.org/W4211049957","https://openalex.org/W4237171445","https://openalex.org/W4245448682","https://openalex.org/W4254092108","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W2964314781","https://openalex.org/W3006565005","https://openalex.org/W3099153698","https://openalex.org/W4287868071","https://openalex.org/W4389708677","https://openalex.org/W2611832276","https://openalex.org/W69468016"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}