{"id":"https://openalex.org/W4224042014","doi":"https://doi.org/10.1109/ciss53076.2022.9751189","title":"The RBMLE method for Reinforcement Learning","display_name":"The RBMLE method for Reinforcement Learning","publication_year":2022,"publication_date":"2022-03-09","ids":{"openalex":"https://openalex.org/W4224042014","doi":"https://doi.org/10.1109/ciss53076.2022.9751189"},"language":"en","primary_location":{"id":"doi:10.1109/ciss53076.2022.9751189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss53076.2022.9751189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","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/A5041563197","display_name":"Akshay Mete","orcid":"https://orcid.org/0009-0009-9176-2265"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Akshay Mete","raw_affiliation_strings":["Texas A & M University,Department of ECE,College Station,TX,USA"],"affiliations":[{"raw_affiliation_string":"Texas A & M University,Department of ECE,College Station,TX,USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055489202","display_name":"Rahul Singh","orcid":"https://orcid.org/0000-0003-0363-3666"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rahul Singh","raw_affiliation_strings":["Indian Institute of Science,Department of ECE,Bengaluru,India","Department of ECE, Indian Institute of Science, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,Department of ECE,Bengaluru,India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Department of ECE, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101852131","display_name":"P. R. Kumar","orcid":"https://orcid.org/0000-0003-0474-080X"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. R. Kumar","raw_affiliation_strings":["Texas A & M University,Department of ECE,College Station,TX,USA"],"affiliations":[{"raw_affiliation_string":"Texas A & M University,Department of ECE,College Station,TX,USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041563197"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":0.1695,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50506969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"107","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9959999918937683,"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":0.9908999800682068,"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/regret","display_name":"Regret","score":0.8171788454055786},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6575247049331665},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6447239518165588},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5611652731895447},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49506011605262756},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48663029074668884},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4532046616077423},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.38778790831565857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3846468925476074},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27872204780578613},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25879642367362976}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.8171788454055786},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6575247049331665},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6447239518165588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5611652731895447},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49506011605262756},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48663029074668884},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4532046616077423},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38778790831565857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3846468925476074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27872204780578613},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25879642367362976},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ciss53076.2022.9751189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss53076.2022.9751189","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 56th Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"},{"id":"pmh:oai::72052","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G271639475","display_name":null,"funder_award_id":"CMMI-2038625","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W53582479","https://openalex.org/W105751747","https://openalex.org/W1487320471","https://openalex.org/W1535136082","https://openalex.org/W1578233523","https://openalex.org/W1901083042","https://openalex.org/W1974508877","https://openalex.org/W1982997797","https://openalex.org/W1998498767","https://openalex.org/W2004487554","https://openalex.org/W2009551863","https://openalex.org/W2031660693","https://openalex.org/W2039522160","https://openalex.org/W2045812400","https://openalex.org/W2055441457","https://openalex.org/W2094826322","https://openalex.org/W2096825593","https://openalex.org/W2097931172","https://openalex.org/W2106164082","https://openalex.org/W2111764152","https://openalex.org/W2112420033","https://openalex.org/W2115447855","https://openalex.org/W2115597380","https://openalex.org/W2123225686","https://openalex.org/W2132908009","https://openalex.org/W2142500134","https://openalex.org/W2168405694","https://openalex.org/W2182000050","https://openalex.org/W2320680700","https://openalex.org/W2415697701","https://openalex.org/W2499002200","https://openalex.org/W2604209058","https://openalex.org/W2753754162","https://openalex.org/W2949186496","https://openalex.org/W2963568654","https://openalex.org/W3001756029","https://openalex.org/W3020125231","https://openalex.org/W3101242211","https://openalex.org/W3101676093","https://openalex.org/W3118201743","https://openalex.org/W3124229194","https://openalex.org/W3137764350","https://openalex.org/W3173921152","https://openalex.org/W4206530644","https://openalex.org/W4206670532","https://openalex.org/W4225435134","https://openalex.org/W4248696375","https://openalex.org/W4250248097","https://openalex.org/W4287863949","https://openalex.org/W6629353124","https://openalex.org/W6639039794","https://openalex.org/W6639904974","https://openalex.org/W6640015871","https://openalex.org/W6674777300","https://openalex.org/W6675656252","https://openalex.org/W6676833704","https://openalex.org/W6679661297","https://openalex.org/W6686227676","https://openalex.org/W6736527823","https://openalex.org/W6743825324","https://openalex.org/W6764988152","https://openalex.org/W6772593463","https://openalex.org/W6774554500","https://openalex.org/W6784412824","https://openalex.org/W6785000746","https://openalex.org/W6785291173","https://openalex.org/W6810325554"],"related_works":["https://openalex.org/W2465145931","https://openalex.org/W2132908009","https://openalex.org/W2512014291","https://openalex.org/W2945119207","https://openalex.org/W2803304514","https://openalex.org/W3091875946","https://openalex.org/W2966613056","https://openalex.org/W3092949629","https://openalex.org/W2985982678","https://openalex.org/W2128957716"],"abstract_inverted_index":{"The":[0],"Reward":[1],"Biased":[2],"Maximum":[3,45],"Likelihood":[4,46],"Estimate":[5,47],"(RBMLE)":[6],"method":[7,161],"was":[8],"proposed":[9],"about":[10],"four":[11],"decades":[12],"ago":[13],"for":[14,26,66,110,142,162],"the":[15,44,74,82,102,117,124,133,159],"adaptive":[16],"control":[17],"of":[18,50,84,119,126,158],"unknown":[19],"Markov":[20],"Decision":[21],"Processes,":[22],"and":[23,32,89,128,148],"later":[24],"studied":[25],"more":[27],"general":[28],"Controlled":[29],"Markovian":[30],"Systems":[31],"Linear":[33],"Quadratic":[34],"Gaussian":[35],"systems.":[36],"It":[37,62,105,121],"showed":[38],"that":[39,76,137],"if":[40],"one":[41,56,78],"could":[42,57],"bias":[43],"in":[48,116,132,149],"favor":[49],"parameters":[51,68],"with":[52,69],"larger":[53,70],"rewards":[54,71],"then":[55],"obtain":[58],"long-term":[59],"average":[60],"optimality.":[61],"provided":[63,107],"a":[64,85,108],"reason":[65,109],"preferring":[67],"based":[72],"on":[73],"fact":[75],"generally":[77],"can":[79],"only":[80,131],"identify":[81],"behavior":[83],"system":[86],"under":[87],"closed-loop,":[88],"therefore":[90],"any":[91],"limiting":[92],"parameter":[93],"estimate":[94],"has":[95,139],"to":[96],"necessarily":[97],"have":[98],"lower":[99],"reward":[100],"than":[101],"true":[103],"parameter.":[104],"thereby":[106],"what":[111],"his":[112],"now":[113],"called":[114],"\u201coptimism":[115],"face":[118],"uncertainty\u201d.":[120],"similarly":[122],"preceded":[123],"definition":[125],"\u201cregret\u201d,":[127],"it":[129,138],"is":[130],"last":[134],"three":[135],"years":[136],"been":[140],"analyzed":[141],"its":[143],"regret":[144],"performance,":[145],"both":[146],"analytically,":[147],"comparative":[150],"simulation":[151],"testing.":[152],"This":[153],"paper":[154],"provides":[155],"an":[156],"account":[157],"RBMLE":[160],"reinforcement":[163],"learning.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}