{"id":"https://openalex.org/W2084123874","doi":"https://doi.org/10.1109/icnsc.2012.6204912","title":"Fuzzy C-means method for representation policy iteration in reinforcement learning","display_name":"Fuzzy C-means method for representation policy iteration in reinforcement learning","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W2084123874","doi":"https://doi.org/10.1109/icnsc.2012.6204912","mag":"2084123874"},"language":"en","primary_location":{"id":"doi:10.1109/icnsc.2012.6204912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc.2012.6204912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2012 9th IEEE International Conference on Networking, Sensing and Control","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/A5103082016","display_name":"Zhenhua Huang","orcid":"https://orcid.org/0000-0003-3178-9721"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenhua Huang","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","College of Mechatronics and Automation, National University of Defense Technology, Changsha, 410073, P.R China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, 410073, P.R China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053112608","display_name":"Xin Xu","orcid":"https://orcid.org/0000-0003-3238-745X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Xu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","College of Mechatronics and Automation, National University of Defense Technology, Changsha, 410073, P.R China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, 410073, P.R China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021284542","display_name":"Jun Wu","orcid":"https://orcid.org/0000-0002-1388-7451"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wu","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","College of Mechatronics and Automation, National University of Defense Technology, Changsha, 410073, P.R China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, 410073, P.R China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057599028","display_name":"Lei Zuo","orcid":"https://orcid.org/0000-0002-9938-7449"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zuo","raw_affiliation_strings":["College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","College of Mechatronics and Automation, National University of Defense Technology, Changsha, 410073, P.R China"],"affiliations":[{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"College of Mechatronics and Automation, National University of Defense Technology, Changsha, 410073, P.R China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103082016"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.4281,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72540802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","issue":null,"first_page":"175","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9970999956130981,"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":0.9815000295639038,"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":0.6656156182289124},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.555390477180481},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5261473059654236},{"id":"https://openalex.org/keywords/laplace-operator","display_name":"Laplace operator","score":0.5056777000427246},{"id":"https://openalex.org/keywords/eigenfunction","display_name":"Eigenfunction","score":0.5051959156990051},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5051565766334534},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.470449835062027},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43869102001190186},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.43578147888183594},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4166116714477539},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4116383194923401},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.389404833316803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.377154141664505},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34728285670280457},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.21008354425430298},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18509197235107422}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6656156182289124},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555390477180481},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5261473059654236},{"id":"https://openalex.org/C165700671","wikidata":"https://www.wikidata.org/wiki/Q203484","display_name":"Laplace operator","level":2,"score":0.5056777000427246},{"id":"https://openalex.org/C128803854","wikidata":"https://www.wikidata.org/wiki/Q1307821","display_name":"Eigenfunction","level":3,"score":0.5051959156990051},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5051565766334534},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.470449835062027},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43869102001190186},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.43578147888183594},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4166116714477539},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4116383194923401},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.389404833316803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.377154141664505},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34728285670280457},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.21008354425430298},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18509197235107422},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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":1,"locations":[{"id":"doi:10.1109/icnsc.2012.6204912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icnsc.2012.6204912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of 2012 9th IEEE International Conference on Networking, Sensing and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1594387031","https://openalex.org/W1920714059","https://openalex.org/W1941358455","https://openalex.org/W2072931156","https://openalex.org/W2118556122","https://openalex.org/W2121863487","https://openalex.org/W2143958939","https://openalex.org/W2161795906","https://openalex.org/W3027095131","https://openalex.org/W4214717370","https://openalex.org/W4239890145","https://openalex.org/W4242606736","https://openalex.org/W4285719527","https://openalex.org/W6640233130","https://openalex.org/W6683841269"],"related_works":["https://openalex.org/W4302419125","https://openalex.org/W2766128145","https://openalex.org/W4300623652","https://openalex.org/W121031341","https://openalex.org/W2038878154","https://openalex.org/W4290982745","https://openalex.org/W2464780829","https://openalex.org/W2963746646","https://openalex.org/W3217737408","https://openalex.org/W4285669519"],"abstract_inverted_index":{"This":[0],"paper":[1,38],"introduces":[2],"a":[3,21,53],"Fuzzy":[4,71],"C-means":[5,72],"method":[6,10,74,117,144,148],"as":[7,46,75,113,145],"the":[8,39,42,64,70,76,91,94,104,108,114,137,142,146,152],"subsampling":[9,77,147,154],"for":[11,120],"Representation":[12],"Policy":[13],"Iteration":[14],"(RPI)":[15],"in":[16],"Reinforcement":[17],"Learning.":[18],"RPI":[19,43,140],"is":[20,118],"new":[22],"class":[23],"of":[24,41,93,139],"algorithm":[25,44],"that":[26,150],"automatically":[27],"learns":[28],"both":[29],"basis":[30,81],"functions":[31,82,85],"and":[32],"approximately":[33,123],"optimal":[34,124],"policy.":[35,57,125],"In":[36],"this":[37],"procedures":[40],"are":[45,50,61,87],"follows.":[47],"Firstly":[48],"samples":[49,60],"collected":[51],"using":[52,69,90,141,151],"random":[54],"or":[55],"guided":[56],"The":[58],"subset":[59,105],"obtained":[62],"from":[63,103],"original":[65],"ones":[66],"subsequently":[67],"by":[68,89],"(FCM)":[73],"method.":[78,155],"Then":[79],"global":[80],"called":[83],"proto-value":[84],"(PVFs)":[86],"formed":[88],"eigenfunctions":[92],"graph":[95,101],"Laplacian":[96],"operator":[97],"on":[98,128],"an":[99,122,129],"undirected":[100],"constructed":[102],"samples.":[106],"Finally,":[107],"least-square":[109],"policy":[110],"iteration":[111],"(LSPI)":[112],"parameter":[115],"estimation":[116],"used":[119],"learning":[121],"Illustrative":[126],"experiments":[127],"Inverted":[130],"Pendulum":[131],"problem":[132],"were":[133],"accomplished":[134],"to":[135],"compare":[136],"performance":[138],"FCM":[143],"with":[149],"previous":[153]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}