{"id":"https://openalex.org/W2046460325","doi":"https://doi.org/10.1109/ijcnn.2014.6889756","title":"Online learning control based on projected gradient temporal difference and advanced heuristic dynamic programming","display_name":"Online learning control based on projected gradient temporal difference and advanced heuristic dynamic programming","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W2046460325","doi":"https://doi.org/10.1109/ijcnn.2014.6889756","mag":"2046460325"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2014.6889756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2014.6889756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://digitalcommons.uri.edu/ele_facpubs/536","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101891348","display_name":"Jian Fu","orcid":"https://orcid.org/0000-0001-7044-5302"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Fu","raw_affiliation_strings":["School of Automation, Wuhan University of Technology, Wuhan, Hubei, China 430070","School of Automation Wuhan University of Technology  Wuhan China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Wuhan University of Technology, Wuhan, Hubei, China 430070","institution_ids":["https://openalex.org/I196699116","https://openalex.org/I43922553"]},{"raw_affiliation_string":"School of Automation Wuhan University of Technology  Wuhan China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019080184","display_name":"Sujuan Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]},{"id":"https://openalex.org/I43922553","display_name":"Wuhan University of Science and Technology","ror":"https://ror.org/00e4hrk88","country_code":"CN","type":"education","lineage":["https://openalex.org/I43922553"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sujuan Wei","raw_affiliation_strings":["School of Automation, Wuhan University of Technology, Wuhan, Hubei, China 430070","School of Automation Wuhan University of Technology  Wuhan China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Wuhan University of Technology, Wuhan, Hubei, China 430070","institution_ids":["https://openalex.org/I196699116","https://openalex.org/I43922553"]},{"raw_affiliation_string":"School of Automation Wuhan University of Technology  Wuhan China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100411297","display_name":"Haibo He","orcid":"https://orcid.org/0000-0002-5247-9370"},"institutions":[{"id":"https://openalex.org/I17626003","display_name":"University of Rhode Island","ror":"https://ror.org/013ckk937","country_code":"US","type":"education","lineage":["https://openalex.org/I17626003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haibo He","raw_affiliation_strings":["Department of Electrical, Computer and Biomedical Engineering University of Rhode Island, Kingston, Rhode Island, USA 02881","Dept of Electr., Comput., & Biomed. Eng., Univ. of Rhode Island, Kingston, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Biomedical Engineering University of Rhode Island, Kingston, Rhode Island, USA 02881","institution_ids":["https://openalex.org/I17626003"]},{"raw_affiliation_string":"Dept of Electr., Comput., & Biomed. Eng., Univ. of Rhode Island, Kingston, RI, USA","institution_ids":["https://openalex.org/I17626003"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017090828","display_name":"Shengyong Wang","orcid":"https://orcid.org/0009-0009-7040-6712"},"institutions":[{"id":"https://openalex.org/I4210100789","display_name":"Wuhan College","ror":"https://ror.org/01dashf18","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210100789"]},{"id":"https://openalex.org/I4210101015","display_name":"Wuhan Municipal Engineering Design & Research Institute","ror":"https://ror.org/00ycq1k13","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210101015"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengyong Wang","raw_affiliation_strings":["WISDRI(WuHan) Automation Co., Ltd, Wuhan, Hubei, China 430070","WISDRI(WuHan) Autom. Co. Ltd., Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"WISDRI(WuHan) Automation Co., Ltd, Wuhan, Hubei, China 430070","institution_ids":["https://openalex.org/I4210100789"]},{"raw_affiliation_string":"WISDRI(WuHan) Autom. Co. Ltd., Wuhan, China","institution_ids":["https://openalex.org/I4210101015"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3649","last_page":"3656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9911999702453613,"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.9433000087738037,"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/temporal-difference-learning","display_name":"Temporal difference learning","score":0.8347840309143066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7546260356903076},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7326182126998901},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6413975954055786},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6412258148193359},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6347830295562744},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6061763167381287},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6012762784957886},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.569878339767456},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5569611191749573},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4851835370063782},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4834340810775757},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4760986566543579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43557441234588623},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34890180826187134},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.30714306235313416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24393147230148315},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12827780842781067}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.8347840309143066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7546260356903076},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7326182126998901},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6413975954055786},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6412258148193359},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6347830295562744},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6061763167381287},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6012762784957886},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.569878339767456},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5569611191749573},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4851835370063782},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4834340810775757},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4760986566543579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43557441234588623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34890180826187134},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.30714306235313416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24393147230148315},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12827780842781067},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2014.6889756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2014.6889756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:digitalcommons.uri.edu:ele_facpubs-1535","is_oa":true,"landing_page_url":"https://digitalcommons.uri.edu/ele_facpubs/536","pdf_url":null,"source":{"id":"https://openalex.org/S2764761010","display_name":"Journal of Media Literacy Education","issn_l":"2167-8715","issn":["2167-8715"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310316378","host_organization_name":"National Association for Media Literacy Education","host_organization_lineage":["https://openalex.org/P4310316378"],"host_organization_lineage_names":["National Association for Media Literacy Education"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical, Computer, and Biomedical Engineering Faculty Publications","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:digitalcommons.uri.edu:ele_facpubs-1535","is_oa":true,"landing_page_url":"https://digitalcommons.uri.edu/ele_facpubs/536","pdf_url":null,"source":{"id":"https://openalex.org/S2764761010","display_name":"Journal of Media Literacy Education","issn_l":"2167-8715","issn":["2167-8715"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310316378","host_organization_name":"National Association for Media Literacy Education","host_organization_lineage":["https://openalex.org/P4310316378"],"host_organization_lineage_names":["National Association for Media Literacy Education"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Electrical, Computer, and Biomedical Engineering Faculty Publications","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W253794995","https://openalex.org/W603852980","https://openalex.org/W1646707810","https://openalex.org/W1981950047","https://openalex.org/W1983523797","https://openalex.org/W1999213690","https://openalex.org/W2044287460","https://openalex.org/W2050838777","https://openalex.org/W2060605484","https://openalex.org/W2105004188","https://openalex.org/W2108286682","https://openalex.org/W2113921460","https://openalex.org/W2124829859","https://openalex.org/W2134042548","https://openalex.org/W2139418546","https://openalex.org/W2145952809","https://openalex.org/W2165501837","https://openalex.org/W2165726932","https://openalex.org/W6650387702","https://openalex.org/W7065010408"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W2145363145","https://openalex.org/W2386410636","https://openalex.org/W2952594763","https://openalex.org/W2341346307","https://openalex.org/W4285537323","https://openalex.org/W2025663273","https://openalex.org/W1932159282","https://openalex.org/W3038962357"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,51,109],"novel":[3],"online":[4,61,105],"learning":[5,38,62,106],"control":[6,107,115],"algorithm":[7],"(OLCPA)":[8],"which":[9,85],"comprises":[10],"projected":[11],"gradient":[12],"temporal":[13,35,72],"difference":[14,73],"for":[15,55],"action-value":[16,41],"function":[17,42],"(PGTDAVF)":[18],"and":[19,99,117],"advanced":[20],"heuristic":[21],"dynamic":[22],"programming":[23],"with":[24,39,68],"one":[25],"step":[26],"delay":[27],"(AHD-POSD).":[28],"PGTDAVF":[29,57,77],"can":[30],"guarantee":[31],"the":[32,69,93,97,120],"convergence":[33],"of":[34,71,104,119],"difference(TD)-based":[36],"policy":[37,83],"smooth":[40],"approximators,":[43],"such":[44],"as":[45],"neural":[46],"networks.":[47],"Meanwhile,":[48],"AHDPOSD":[49],"is":[50],"specially":[52],"designed":[53],"framework":[54],"embedding":[56],"in":[58,87],"to":[59,78],"conduct":[60],"control.":[63],"It":[64],"not":[65],"only":[66],"coincides":[67],"intention":[70],"but":[74],"also":[75],"enables":[76],"be":[79],"effective":[80],"under":[81],"nonidentical":[82],"environment,":[84],"results":[86],"more":[88],"practicality.":[89],"In":[90],"this":[91],"way,":[92],"proposed":[94],"algorithms":[95],"achieve":[96],"stability":[98],"practicability":[100],"simultaneously.":[101],"Finally,":[102],"simulation":[103],"on":[108],"cart":[110],"pole":[111],"benchmark":[112],"demonstrates":[113],"practical":[114],"capability":[116],"efficiency":[118],"presented":[121],"method.":[122]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}