{"id":"https://openalex.org/W2163859348","doi":"https://doi.org/10.1109/fuzz.2001.1009030","title":"On convergence of fuzzy reinforcement learning","display_name":"On convergence of fuzzy reinforcement learning","publication_year":2005,"publication_date":"2005-08-25","ids":{"openalex":"https://openalex.org/W2163859348","doi":"https://doi.org/10.1109/fuzz.2001.1009030","mag":"2163859348"},"language":"en","primary_location":{"id":"doi:10.1109/fuzz.2001.1009030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzz.2001.1009030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297)","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/A5089401517","display_name":"H.R. Berenji","orcid":null},"institutions":[{"id":"https://openalex.org/I1280536761","display_name":"Ames Research Center","ror":"https://ror.org/02acart68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280536761","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"H.R. Berenji","raw_affiliation_strings":["Computational Sciences Division, NASA Ames Research Center, Intelligent Inference Systems Corporation, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computational Sciences Division, NASA Ames Research Center, Intelligent Inference Systems Corporation, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1280536761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021283042","display_name":"David Vengerov","orcid":null},"institutions":[{"id":"https://openalex.org/I1280536761","display_name":"Ames Research Center","ror":"https://ror.org/02acart68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280536761","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Vengerov","raw_affiliation_strings":["Computational Sciences Division, NASA Ames Research Center, Intelligent Inference Systems Corporation, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Computational Sciences Division, NASA Ames Research Center, Intelligent Inference Systems Corporation, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1280536761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5089401517"],"corresponding_institution_ids":["https://openalex.org/I1280536761"],"apc_list":null,"apc_paid":null,"fwci":3.0713,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92211592,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"618","last_page":"621"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9785000085830688,"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"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.967199981212616,"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/convergence","display_name":"Convergence (economics)","score":0.7198367714881897},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.644324779510498},{"id":"https://openalex.org/keywords/fuzzy-rule","display_name":"Fuzzy rule","score":0.640439510345459},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5731393098831177},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.558630108833313},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5561832189559937},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5154934525489807},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4400617480278015},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4314040541648865},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4191461205482483},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.40163737535476685},{"id":"https://openalex.org/keywords/fuzzy-set","display_name":"Fuzzy set","score":0.3680642545223236},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23677104711532593}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7198367714881897},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.644324779510498},{"id":"https://openalex.org/C2780049643","wikidata":"https://www.wikidata.org/wiki/Q5511139","display_name":"Fuzzy rule","level":4,"score":0.640439510345459},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5731393098831177},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.558630108833313},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5561832189559937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5154934525489807},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4400617480278015},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4314040541648865},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4191461205482483},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40163737535476685},{"id":"https://openalex.org/C42011625","wikidata":"https://www.wikidata.org/wiki/Q1055058","display_name":"Fuzzy set","level":3,"score":0.3680642545223236},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23677104711532593},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fuzz.2001.1009030","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzz.2001.1009030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W748403231","https://openalex.org/W1576452626","https://openalex.org/W1594871463","https://openalex.org/W1967981236","https://openalex.org/W1980056622","https://openalex.org/W2040598998","https://openalex.org/W2046738003","https://openalex.org/W2079325629","https://openalex.org/W2091565802","https://openalex.org/W2102634648","https://openalex.org/W2103269436","https://openalex.org/W2120405980","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2158316397","https://openalex.org/W2164056559","https://openalex.org/W6635431665","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6684199269"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W1494268238","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W1976468483","https://openalex.org/W2480116122","https://openalex.org/W2563912921","https://openalex.org/W2594336854","https://openalex.org/W2083536291"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"the":[3,13,43,48,62],"first":[4],"convergence":[5,49],"proof":[6],"for":[7,26],"fuzzy":[8,38,58],"reinforcement":[9],"learning.":[10],"We":[11],"extend":[12],"work":[14,33],"of":[15,50],"Konda":[16],"and":[17,68],"Tsitsiklis":[18],"(2000),":[19],"who":[20],"presented":[21],"a":[22,27,37,54],"convergent":[23],"actor-critic":[24],"algorithm":[25],"general":[28],"parameterized":[29],"actor.":[30],"In":[31],"our":[32],"we":[34],"prove":[35],"that":[36,46],"rule":[39,59],"base":[40,60],"actor":[41],"satisfies":[42],"necessary":[44],"conditions":[45],"guarantee":[47],"its":[51],"parameters":[52],"to":[53],"local":[55],"optimum.":[56],"Our":[57],"uses":[61],"Takagi-Sugeno-Kang":[63],"rules,":[64],"Gaussian":[65],"membership":[66],"functions":[67],"product":[69],"inference.":[70]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}