{"id":"https://openalex.org/W2126085481","doi":"https://doi.org/10.1109/fuzzy.2008.4630417","title":"Consistency of fuzzy model-based reinforcement learning","display_name":"Consistency of fuzzy model-based reinforcement learning","publication_year":2008,"publication_date":"2008-06-01","ids":{"openalex":"https://openalex.org/W2126085481","doi":"https://doi.org/10.1109/fuzzy.2008.4630417","mag":"2126085481"},"language":"en","primary_location":{"id":"doi:10.1109/fuzzy.2008.4630417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzzy.2008.4630417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.uliege.be/handle/2268/13578","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lucian Busoniu","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technnology, Netherlands","Delft Center for Systems and Control, Delft University of Technology, Delft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technnology, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077011518","display_name":"Damien Ernst","orcid":"https://orcid.org/0000-0002-3035-8260"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Damien Ernst","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technnology, Netherlands","Systems and Modeling Unit of the University of Li\u00e8ge, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technnology, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Systems and Modeling Unit of the University of Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026547410","display_name":"Bart De Schutter","orcid":"https://orcid.org/0000-0001-9867-6196"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["BE","NL"],"is_corresponding":false,"raw_author_name":"Bart De Schutter","raw_affiliation_strings":["Research Associate of the Belgian FNRS, Systems and Modeling Unit of University of Li\u00e8ge, Belgium","Delft Center for Systems and Control of the Delft University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Associate of the Belgian FNRS, Systems and Modeling Unit of University of Li\u00e8ge, Belgium","institution_ids":["https://openalex.org/I157674565"]},{"raw_affiliation_string":"Delft Center for Systems and Control of the Delft University of Technology, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technnology, Netherlands","Delft Center for Systems and Control of the Delft University of Technology, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technnology, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control of the Delft University of Technology, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"518","last_page":"524"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9793000221252441,"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":0.9782999753952026,"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":0.8054838180541992},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.7245797514915466},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6307951211929321},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.6055263876914978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5533968806266785},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5514234900474548},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.49351418018341064},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49247750639915466},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4292396306991577},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.41063395142555237},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36696407198905945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32335570454597473},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10908138751983643}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8054838180541992},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.7245797514915466},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6307951211929321},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.6055263876914978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5533968806266785},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5514234900474548},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.49351418018341064},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49247750639915466},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4292396306991577},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.41063395142555237},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36696407198905945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32335570454597473},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10908138751983643},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/fuzzy.2008.4630417","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fuzzy.2008.4630417","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.907.6866","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.907.6866","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Lucian_Busoniu/publication/4375811_Consistency_of_fuzzy_model-based_reinforcement_learning/links/0c960526110b0974a1000000.pdf","raw_type":"text"},{"id":"pmh:oai:orbi.ulg.ac.be:2268/13578","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/13578","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2008 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE-08), 518-524 (2008); 2008 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE-08), Hong-Kong, China [CN], 1-6 June 2008","raw_type":"http://purl.org/coar/resource_type/c_5794"}],"best_oa_location":{"id":"pmh:oai:orbi.ulg.ac.be:2268/13578","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/13578","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2008 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE-08), 518-524 (2008); 2008 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE-08), Hong-Kong, China [CN], 1-6 June 2008","raw_type":"http://purl.org/coar/resource_type/c_5794"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1544598807","https://openalex.org/W1547105496","https://openalex.org/W1550698229","https://openalex.org/W1590631717","https://openalex.org/W1777239053","https://openalex.org/W1820996291","https://openalex.org/W1982650427","https://openalex.org/W2004283713","https://openalex.org/W2098432798","https://openalex.org/W2104335146","https://openalex.org/W2107977784","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2122689259","https://openalex.org/W2125510930","https://openalex.org/W2143490508","https://openalex.org/W2146290970","https://openalex.org/W2150999967","https://openalex.org/W2152520382","https://openalex.org/W2158316397","https://openalex.org/W2169982856","https://openalex.org/W2266260776","https://openalex.org/W2305205647","https://openalex.org/W4214717370","https://openalex.org/W4245296547","https://openalex.org/W6638088447","https://openalex.org/W6677737365","https://openalex.org/W6678900246","https://openalex.org/W6693743473"],"related_works":["https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W3009457412","https://openalex.org/W2992629954","https://openalex.org/W3021988786","https://openalex.org/W3099311996"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,9],"(RL)":[2],"is":[3,15,85,92,109],"a":[4,28,51,60,105,113],"widely":[5],"used":[6],"paradigm":[7],"for":[8,112],"control.":[10],"Computing":[11],"exact":[12],"RL":[13],"solutions":[14],"generally":[16],"only":[17],"possible":[18],"when":[19],"process":[20],"states":[21],"and":[22,58,74],"control":[23],"actions":[24],"take":[25],"values":[26],"in":[27,116],"small":[29],"discrete":[30],"set.":[31],"In":[32,38],"practice,":[33],"approximate":[34],"algorithms":[35],"are":[36],"necessary.":[37],"this":[39],"paper,":[40],"we":[41,79],"propose":[42],"an":[43],"approximate,":[44],"model-based":[45],"Q-iteration":[46],"algorithm":[47,84],"that":[48,81,88,104],"relies":[49],"on":[50,59,68],"fuzzy":[52],"partition":[53],"of":[54,62,71,75],"the":[55,63,69,72,76,82,89,96,119],"state":[56],"space,":[57],"discretization":[61],"action":[64],"space.":[65],"Using":[66],"assumptions":[67],"continuity":[70],"dynamics":[73],"reward":[77,107],"function,":[78],"show":[80],"resulting":[83],"consistent,":[86],"i.e.,":[87],"optimal":[90],"solution":[91],"obtained":[93],"asymptotically":[94],"as":[95,118],"approximation":[97,120],"accuracy":[98,121],"increases.":[99,122],"An":[100],"experimental":[101],"study":[102],"indicates":[103],"continuous":[106],"function":[108],"also":[110],"important":[111],"predictable":[114],"improvement":[115],"performance":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
