{"id":"https://openalex.org/W2105078254","doi":"https://doi.org/10.1162/0899766053011528","title":"Robust Reinforcement Learning","display_name":"Robust Reinforcement Learning","publication_year":2005,"publication_date":"2005-02-01","ids":{"openalex":"https://openalex.org/W2105078254","doi":"https://doi.org/10.1162/0899766053011528","mag":"2105078254","pmid":"https://pubmed.ncbi.nlm.nih.gov/15720771"},"language":"en","primary_location":{"id":"doi:10.1162/0899766053011528","is_oa":false,"landing_page_url":"https://doi.org/10.1162/0899766053011528","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5025458882","display_name":"Jun Morimoto","orcid":"https://orcid.org/0000-0002-4115-1919"},"institutions":[{"id":"https://openalex.org/I4210104143","display_name":"Advanced Telecommunications Research Institute International","ror":"https://ror.org/01pe1d703","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210104143"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Jun Morimoto","raw_affiliation_strings":["Computational Brain Project, ICORP, JST, Sora Ku-gun, Kyoto, 619-0288, Japan; ATR Computational Neuroscience Laboratories, Soraku-gun, Kyoto 619-0288, Japan,","ATR Computational Neuroscience Laboratories, Soraku-gun, Kyoto 619-0288, Japan,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Brain Project, ICORP, JST, Sora Ku-gun, Kyoto, 619-0288, Japan; ATR Computational Neuroscience Laboratories, Soraku-gun, Kyoto 619-0288, Japan,","institution_ids":["https://openalex.org/I4210104143"]},{"raw_affiliation_string":"ATR Computational Neuroscience Laboratories, Soraku-gun, Kyoto 619-0288, Japan,","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004840638","display_name":"Kenji Doya","orcid":"https://orcid.org/0000-0002-2446-6820"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kenji Doya","raw_affiliation_strings":["ATR Computational Neuroscience Laboratories, Soraku-gun, Kyoto 619-0288, Japan; Initial Research Project, OIST, Gushikawa, Okinawa, 904-2234, Japan; and CREST, JST, Soraku-gun, Kyoto 619-0288, Japan,","Initial Research Project, OIST, Gushikawa, Okinawa, 904-2234, Japan","CREST, JST, Soraku-gun, Kyoto 619-0288, Japan,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ATR Computational Neuroscience Laboratories, Soraku-gun, Kyoto 619-0288, Japan; Initial Research Project, OIST, Gushikawa, Okinawa, 904-2234, Japan; and CREST, JST, Soraku-gun, Kyoto 619-0288, Japan,","institution_ids":[]},{"raw_affiliation_string":"Initial Research Project, OIST, Gushikawa, Okinawa, 904-2234, Japan","institution_ids":[]},{"raw_affiliation_string":"CREST, JST, Soraku-gun, Kyoto 619-0288, Japan,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004840638","https://openalex.org/A5025458882"],"corresponding_institution_ids":["https://openalex.org/I4210104143"],"apc_list":null,"apc_paid":null,"fwci":3.2153,"has_fulltext":false,"cited_by_count":232,"citation_normalized_percentile":{"value":0.92364732,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"17","issue":"2","first_page":"335","last_page":"359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.9968000054359436,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9207000136375427,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9165999889373779,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8492034077644348},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.7453792095184326},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5858005881309509},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.584394633769989},{"id":"https://openalex.org/keywords/describing-function","display_name":"Describing function","score":0.5356743931770325},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5277740955352783},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.521630585193634},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5211034417152405},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.49292898178100586},{"id":"https://openalex.org/keywords/swing","display_name":"Swing","score":0.4578576982021332},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45167794823646545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3729333281517029},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.33095988631248474},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3135821223258972},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2907865047454834},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27428948879241943},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11269432306289673}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8492034077644348},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.7453792095184326},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5858005881309509},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.584394633769989},{"id":"https://openalex.org/C147317941","wikidata":"https://www.wikidata.org/wiki/Q1925419","display_name":"Describing function","level":3,"score":0.5356743931770325},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5277740955352783},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.521630585193634},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5211034417152405},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.49292898178100586},{"id":"https://openalex.org/C65655974","wikidata":"https://www.wikidata.org/wiki/Q14867674","display_name":"Swing","level":2,"score":0.4578576982021332},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45167794823646545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3729333281517029},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33095988631248474},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3135821223258972},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2907865047454834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27428948879241943},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11269432306289673},{"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1162/0899766053011528","is_oa":false,"landing_page_url":"https://doi.org/10.1162/0899766053011528","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:15720771","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15720771","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computation","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.20.895","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.895","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/Web/Groups/NIPS/00papers-pub-on-web/MorimotoDoya.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1551923895","https://openalex.org/W1585575029","https://openalex.org/W1973039793","https://openalex.org/W2060248504","https://openalex.org/W2080759927","https://openalex.org/W2091565802","https://openalex.org/W2099767582","https://openalex.org/W2103626435","https://openalex.org/W2113501460","https://openalex.org/W2121832485","https://openalex.org/W2124215603","https://openalex.org/W2149398074","https://openalex.org/W2167647761"],"related_works":["https://openalex.org/W2614575562","https://openalex.org/W2372645633","https://openalex.org/W2689391174","https://openalex.org/W1501190258","https://openalex.org/W4256087190","https://openalex.org/W4240668504","https://openalex.org/W2788366696","https://openalex.org/W3188865574","https://openalex.org/W2569146624","https://openalex.org/W2125074935"],"abstract_inverted_index":{"This":[0],"letter":[1],"proposes":[2],"a":[3,69,74,85,101,105,194,212,233],"new":[4],"reinforcement":[5,157,214],"learning":[6,34,126,158,215],"(RL)":[7],"paradigm":[8],"that":[9,108],"explicitly":[10],"takes":[11,109],"into":[12,110],"account":[13,111],"input":[14],"disturbance":[15,83,138],"as":[16,18,99],"well":[17],"modeling":[19],"errors.":[20],"The":[21,95],"use":[22],"of":[23,64,104,114,120,164],"environmental":[24],"models":[25],"in":[26,72,143,205],"RL":[27],"is":[28,97],"quite":[29],"popular":[30],"for":[31,38,128,134],"both":[32],"offline":[33],"using":[35],"simulations":[36],"and":[37,48,56,117,133,139,174,209,232],"online":[39,125,180],"action":[40],"planning.":[41],"However,":[42],"the":[43,46,49,62,80,91,112,115,118,121,130,136,140,146,151,161,169,172,175,188,206,228],"difference":[44],"between":[45],"model":[47],"real":[50],"environment":[51],"can":[52],"lead":[53],"to":[54,78,89,145,227],"unpredictable,":[55],"often":[57],"unwanted,":[58],"results.":[59],"Based":[60],"on":[61,160],"theory":[63],"H(infinity)":[65,190],"control,":[66],"we":[67,154],"consider":[68],"differential":[70],"game":[71],"which":[73,153],"\"disturbing\"":[75],"agent":[76,87],"tries":[77,88],"make":[79,90],"worst":[81,137],"possible":[82],"while":[84,211],"\"control\"":[86],"best":[92,141],"control":[93,142,162,191],"input.":[94],"problem":[96],"formulated":[98],"finding":[100],"min-max":[102],"solution":[103],"value":[106,131,147,176],"function":[107,132,177],"amount":[113],"reward":[116],"norm":[119],"disturbance.":[122],"We":[123,149,223],"derive":[124],"algorithms":[127,181],"estimating":[129],"calculating":[135],"reference":[144],"function.":[148],"tested":[150],"paradigm,":[152],"call":[155],"robust":[156,201,234],"(RRL),":[159],"task":[163],"an":[165],"inverted":[166],"pendulum.":[167],"In":[168],"linear":[170,189],"domain,":[171],"policy":[173,236],"learned":[178],"by":[179,187],"coincided":[182],"with":[183,203,220],"those":[184],"derived":[185],"analytically":[186],"theory.":[192],"For":[193],"fully":[195],"nonlinear":[196],"swing-up":[197,230,235],"task,":[198,231],"RRL":[199,226],"achieved":[200],"performance":[202],"changes":[204],"pendulum":[207],"weight":[208],"friction,":[210],"standard":[213],"algorithm":[216],"could":[217],"not":[218],"deal":[219],"these":[221],"changes.":[222],"also":[224],"applied":[225],"cart-pole":[229],"was":[237],"acquired.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":26},{"year":2022,"cited_by_count":27},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}