{"id":"https://openalex.org/W2236244207","doi":"https://doi.org/10.1561/2200000049","title":"Bayesian Reinforcement Learning: A Survey","display_name":"Bayesian Reinforcement Learning: A Survey","publication_year":2015,"publication_date":"2015-11-26","ids":{"openalex":"https://openalex.org/W2236244207","doi":"https://doi.org/10.1561/2200000049","mag":"2236244207"},"language":"en","primary_location":{"id":"doi:10.1561/2200000049","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2200000049","pdf_url":null,"source":{"id":"https://openalex.org/S4210188176","display_name":"Foundations and Trends\u00ae in Machine Learning","issn_l":"1935-8237","issn":["1935-8237","1935-8245"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1609.04436","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067540098","display_name":"Mohammed Ghavamzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Mohammad Ghavamzadeh","raw_affiliation_strings":["Adobe Research & INRIA","Adobe Research and INRIA, France"],"affiliations":[{"raw_affiliation_string":"Adobe Research & INRIA","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"Adobe Research and INRIA, 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","Technion, Israel"],"affiliations":[{"raw_affiliation_string":"Technion","institution_ids":["https://openalex.org/I174306211"]},{"raw_affiliation_string":"Technion, Israel","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080591144","display_name":"Jo\u00eblle Pineau","orcid":"https://orcid.org/0000-0003-0747-7250"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joelle Pineau","raw_affiliation_strings":["McGill University","McGill University, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University","institution_ids":["https://openalex.org/I5023651"]},{"raw_affiliation_string":"McGill University, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020699288","display_name":"Aviv Tamar","orcid":"https://orcid.org/0000-0002-1972-854X"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aviv Tamar","raw_affiliation_strings":["University of California, Berkeley","University of California, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5067540098"],"corresponding_institution_ids":["https://openalex.org/I1306409833","https://openalex.org/I1326498283"],"apc_list":null,"apc_paid":null,"fwci":11.5655,"has_fulltext":false,"cited_by_count":211,"citation_normalized_percentile":{"value":0.98441841,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"8","issue":"5-6","first_page":"359","last_page":"483"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.6817228198051453},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6768614649772644},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6477320790290833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6368446350097656},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5668478608131409},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5605416297912598},{"id":"https://openalex.org/keywords/variable-order-bayesian-network","display_name":"Variable-order Bayesian network","score":0.5154348611831665},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.49726441502571106},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49194929003715515},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4136032164096832},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37190043926239014},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.27575382590293884},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20652702450752258}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6817228198051453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6768614649772644},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6477320790290833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6368446350097656},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5668478608131409},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5605416297912598},{"id":"https://openalex.org/C71983512","wikidata":"https://www.wikidata.org/wiki/Q7915687","display_name":"Variable-order Bayesian network","level":4,"score":0.5154348611831665},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.49726441502571106},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49194929003715515},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4136032164096832},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37190043926239014},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27575382590293884},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20652702450752258}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1561/2200000049","is_oa":false,"landing_page_url":"https://doi.org/10.1561/2200000049","pdf_url":null,"source":{"id":"https://openalex.org/S4210188176","display_name":"Foundations and Trends\u00ae in Machine Learning","issn_l":"1935-8237","issn":["1935-8237","1935-8245"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318575","host_organization_name":"Now Publishers","host_organization_lineage":["https://openalex.org/P4310318575"],"host_organization_lineage_names":["Now Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Foundations and Trends\u00ae in Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1609.04436","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.04436","pdf_url":"https://arxiv.org/pdf/1609.04436","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1609.04436","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1609.04436","pdf_url":"https://arxiv.org/pdf/1609.04436","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":143,"referenced_works":["https://openalex.org/W52822972","https://openalex.org/W148122774","https://openalex.org/W1485515110","https://openalex.org/W1496855202","https://openalex.org/W1497039698","https://openalex.org/W1507852408","https://openalex.org/W1510073064","https://openalex.org/W1515308897","https://openalex.org/W1515851193","https://openalex.org/W1526144783","https://openalex.org/W1532688806","https://openalex.org/W1552684655","https://openalex.org/W1567876833","https://openalex.org/W1569296262","https://openalex.org/W1571154989","https://openalex.org/W1582436621","https://openalex.org/W1591675293","https://openalex.org/W1597303641","https://openalex.org/W1625390266","https://openalex.org/W1792865576","https://openalex.org/W1814308503","https://openalex.org/W1869302287","https://openalex.org/W1901083042","https://openalex.org/W1965418165","https://openalex.org/W1965878388","https://openalex.org/W1970837196","https://openalex.org/W1972336342","https://openalex.org/W1973749650","https://openalex.org/W1980035368","https://openalex.org/W1988526405","https://openalex.org/W1999874108","https://openalex.org/W2009551863","https://openalex.org/W2014384147","https://openalex.org/W2028169578","https://openalex.org/W2031571562","https://openalex.org/W2034725503","https://openalex.org/W2041367235","https://openalex.org/W2046727971","https://openalex.org/W2046765929","https://openalex.org/W2049934117","https://openalex.org/W2061226732","https://openalex.org/W2061753713","https://openalex.org/W2071814471","https://openalex.org/W2082691056","https://openalex.org/W2092092836","https://openalex.org/W2094387729","https://openalex.org/W2098102888","https://openalex.org/W2098774185","https://openalex.org/W2099089474","https://openalex.org/W2100785108","https://openalex.org/W2104402102","https://openalex.org/W2108692343","https://openalex.org/W2108734173","https://openalex.org/W2108738385","https://openalex.org/W2110720940","https://openalex.org/W2111764152","https://openalex.org/W2111833414","https://openalex.org/W2112476714","https://openalex.org/W2112925200","https://openalex.org/W2113023245","https://openalex.org/W2113958614","https://openalex.org/W2116459397","https://openalex.org/W2117629901","https://openalex.org/W2119678437","https://openalex.org/W2119914747","https://openalex.org/W2120346334","https://openalex.org/W2122162550","https://openalex.org/W2123372395","https://openalex.org/W2123803235","https://openalex.org/W2124352385","https://openalex.org/W2125710232","https://openalex.org/W2126848223","https://openalex.org/W2131024815","https://openalex.org/W2132057084","https://openalex.org/W2132849848","https://openalex.org/W2132876566","https://openalex.org/W2133733518","https://openalex.org/W2134197408","https://openalex.org/W2136602922","https://openalex.org/W2139053308","https://openalex.org/W2141645258","https://openalex.org/W2143555911","https://openalex.org/W2144088174","https://openalex.org/W2146807381","https://openalex.org/W2149721706","https://openalex.org/W2151268438","https://openalex.org/W2154087138","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2156974606","https://openalex.org/W2158125716","https://openalex.org/W2158232074","https://openalex.org/W2158319693","https://openalex.org/W2158738729","https://openalex.org/W2159008857","https://openalex.org/W2159178228","https://openalex.org/W2159471113","https://openalex.org/W2159810454","https://openalex.org/W2160422981","https://openalex.org/W2161966552","https://openalex.org/W2162979096","https://openalex.org/W2163037893","https://openalex.org/W2163302320","https://openalex.org/W2164569010","https://openalex.org/W2165622730","https://openalex.org/W2166473218","https://openalex.org/W2167999092","https://openalex.org/W2168318917","https://openalex.org/W2168359464","https://openalex.org/W2169498096","https://openalex.org/W2181849516","https://openalex.org/W2182000050","https://openalex.org/W2403303158","https://openalex.org/W2406242985","https://openalex.org/W2407441816","https://openalex.org/W2586680856","https://openalex.org/W2949186496","https://openalex.org/W2950989964","https://openalex.org/W2962974313","https://openalex.org/W2963214119","https://openalex.org/W2965916140","https://openalex.org/W3004707083","https://openalex.org/W3011120880","https://openalex.org/W3023151133","https://openalex.org/W3041202696","https://openalex.org/W3101605325","https://openalex.org/W3101822862","https://openalex.org/W3103182070","https://openalex.org/W3104240813","https://openalex.org/W3125634603","https://openalex.org/W3139377883","https://openalex.org/W4211049957","https://openalex.org/W4230563027","https://openalex.org/W4234228486","https://openalex.org/W4240556612","https://openalex.org/W4241680091","https://openalex.org/W4250248097","https://openalex.org/W4293405734","https://openalex.org/W4298593971","https://openalex.org/W4299286629","https://openalex.org/W4300395467","https://openalex.org/W4301444643","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W2793406240","https://openalex.org/W2164129707","https://openalex.org/W4292122269","https://openalex.org/W2949366006","https://openalex.org/W4328114192","https://openalex.org/W2464065341"],"abstract_inverted_index":{"Bayesian":[0,31,44,86,102,123,151],"methods":[1,11,32,84,103,124],"for":[2,12,33,42,85,104,125],"machine":[3],"learning":[4,36],"have":[5],"been":[6],"widely":[7],"investigated,":[8],"yielding":[9],"principled":[10],"incorporating":[13,43],"prior":[14,74,108],"information":[15,109],"into":[16,76],"inference":[17,87],"algorithms.":[18,78],"In":[19],"this":[20],"survey,":[21],"we":[22],"provide":[23,146],"an":[24,52],"in-depth":[25],"review":[26,96],"of":[27,30,61,116,141],"the":[28,34,62,77,89,97,114,117,133,142],"role":[29],"reinforcement":[35],"(RL)":[37],"paradigm.":[38],"The":[39,139],"major":[40],"incentives":[41],"reasoning":[45],"in":[46,64,88],"RL":[47,152],"are:":[48],"1)":[49],"it":[50,68],"provides":[51,69],"elegant":[53],"approach":[54],"to":[55,72,145],"action-selection":[56],"(exploration/exploitation)":[57],"as":[58],"a":[59,70,147],"function":[60,135],"uncertainty":[63],"learning;":[65],"and":[66,83,154,157],"2)":[67],"machinery":[71],"incorporate":[73],"knowledge":[75],"We":[79,94,120],"first":[80],"discuss":[81],"models":[82],"simple":[90],"single-step":[91],"Bandit":[92],"model.":[93,119],"then":[95],"extensive":[98],"recent":[99],"literature":[100],"on":[101,113,150],"model-based":[105],"RL,":[106,127],"where":[107,128],"can":[110],"be":[111],"expressed":[112,131],"parameters":[115],"Markov":[118],"also":[121],"present":[122],"model-free":[126],"priors":[129],"are":[130],"over":[132],"value":[134],"or":[136],"policy":[137],"class.":[138],"objective":[140],"paper":[143],"is":[144],"comprehensive":[148],"survey":[149],"algorithms":[153],"their":[155],"theoretical":[156],"empirical":[158],"properties.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":40},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2016-06-24T00:00:00"}