{"id":"https://openalex.org/W4308216308","doi":"https://doi.org/10.1109/allerton49937.2022.9929353","title":"An Information-Theoretic Analysis of Bayesian Reinforcement Learning","display_name":"An Information-Theoretic Analysis of Bayesian Reinforcement Learning","publication_year":2022,"publication_date":"2022-09-27","ids":{"openalex":"https://openalex.org/W4308216308","doi":"https://doi.org/10.1109/allerton49937.2022.9929353"},"language":"en","primary_location":{"id":"doi:10.1109/allerton49937.2022.9929353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton49937.2022.9929353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-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/A5010481265","display_name":"Amaury Gouverneur","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Amaury Gouverneur","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041149980","display_name":"Borja Rodr\u00edguez-G\u00e1lvez","orcid":"https://orcid.org/0000-0002-0862-1333"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Borja Rodriguez-Galvez","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079492269","display_name":"Tobias J. Oechtering","orcid":"https://orcid.org/0000-0002-0036-9049"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Tobias J. Oechtering","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041348422","display_name":"Mikael Skoglund","orcid":"https://orcid.org/0000-0002-7926-5081"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Mikael Skoglund","raw_affiliation_strings":["KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KTH Royal Institute of Technology,Division of Information Science and Engineering (ISE)","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Division of Information Science and Engineering (ISE), KTH Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6758,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.73306007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9990000128746033,"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":0.9829999804496765,"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":0.8011730909347534},{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.7989631295204163},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6338191628456116},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6267884969711304},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6003638505935669},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.5235209465026855},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5129775404930115},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5068228840827942},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.48669272661209106},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46984830498695374},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39108794927597046},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3788398802280426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33197933435440063},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11030209064483643}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8011730909347534},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.7989631295204163},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6338191628456116},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6267884969711304},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6003638505935669},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.5235209465026855},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5129775404930115},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5068228840827942},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.48669272661209106},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46984830498695374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39108794927597046},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3788398802280426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33197933435440063},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11030209064483643},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton49937.2022.9929353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton49937.2022.9929353","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.800000011920929,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G7178064093","display_name":null,"funder_award_id":"2019-03606","funder_id":"https://openalex.org/F4320320940","funder_display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning"}],"funders":[{"id":"https://openalex.org/F4320320940","display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning","ror":"https://ror.org/044wr7g58"},{"id":"https://openalex.org/F4320322327","display_name":"Knut och Alice Wallenbergs Stiftelse","ror":"https://ror.org/004hzzk67"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1496462336","https://openalex.org/W1527849298","https://openalex.org/W1618543586","https://openalex.org/W2039522160","https://openalex.org/W2103012681","https://openalex.org/W2108738385","https://openalex.org/W2111764152","https://openalex.org/W2155027007","https://openalex.org/W2158125716","https://openalex.org/W2236244207","https://openalex.org/W2377531001","https://openalex.org/W2400458653","https://openalex.org/W2617539226","https://openalex.org/W2962901934","https://openalex.org/W2976533594","https://openalex.org/W3116959972","https://openalex.org/W3123190877","https://openalex.org/W4233762729","https://openalex.org/W4251333191","https://openalex.org/W4287371499","https://openalex.org/W6633965395","https://openalex.org/W6636178939","https://openalex.org/W6676077707","https://openalex.org/W6676833704","https://openalex.org/W6683204974","https://openalex.org/W6738074204"],"related_works":["https://openalex.org/W2970347269","https://openalex.org/W4287863949","https://openalex.org/W1850488217","https://openalex.org/W4287102143","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W2614538623","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"Building":[0],"on":[1,98,107,120],"the":[2,16,31,37,40,50,56,81,99,108,112,126,132,140,152],"framework":[3],"introduced":[4],"by":[5,47,54,88,156],"Xu":[6],"and":[7,58,83,103,111,131,158],"Raginsky":[8],"[1]":[9],"for":[10,20,94],"supervised":[11],"learning":[12,24,48,67],"problems,":[13],"we":[14,29,143],"study":[15],"best":[17],"achievable":[18],"performance":[19],"model-based":[21],"Bayesian":[22,33],"reinforcement":[23,66],"problems.":[25],"With":[26],"this":[27,63],"purpose,":[28],"define":[30],"minimum":[32],"regret":[34],"(MBR)":[35],"as":[36,70],"difference":[38],"between":[39],"maximum":[41],"expected":[42],"cumulative":[43],"reward":[44],"obtainable":[45],"either":[46],"from":[49,150],"collected":[51],"data":[52],"or":[53],"knowing":[55],"environment":[57],"its":[59],"dynamics.":[60],"We":[61,117],"specialize":[62],"definition":[64],"to":[65,80],"problems":[68],"modeled":[69],"Markov":[71],"decision":[72],"processes":[73],"(MDPs)":[74],"whose":[75,84],"kernel":[76],"parameters":[77],"are":[78,115],"unknown":[79],"agent":[82],"uncertainty":[85],"is":[86,101],"expressed":[87],"a":[89],"prior":[90],"distribution.":[91],"One":[92],"method":[93],"deriving":[95],"upper":[96],"bounds":[97,105,147,155],"MBR":[100],"presented":[102],"specific":[104],"based":[106],"relative":[109],"entropy":[110],"Wasserstein":[113],"distance":[114],"given.":[116],"then":[118],"focus":[119],"two":[121],"particular":[122],"cases":[123],"of":[124],"MDPs,":[125],"multi-armed":[127],"bandit":[128],"problem":[129],"(MAB)":[130],"online":[133],"optimization":[134],"with":[135],"partial":[136],"feedback":[137],"problem.":[138],"For":[139],"latter":[141],"problem,":[142],"show":[144],"that":[145],"our":[146],"can":[148],"recover":[149],"below":[151],"current":[153],"information-theoretic":[154],"Russo":[157],"Van":[159],"Roy":[160],"[2].":[161]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}