{"id":"https://openalex.org/W3128043489","doi":"https://doi.org/10.1155/2021/8839391","title":"Online Optimal Control of Robotic Systems with Single Critic NN\u2010Based Reinforcement Learning","display_name":"Online Optimal Control of Robotic Systems with Single Critic NN\u2010Based Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3128043489","doi":"https://doi.org/10.1155/2021/8839391","mag":"3128043489"},"language":"en","primary_location":{"id":"doi:10.1155/2021/8839391","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/8839391","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/8839391.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://downloads.hindawi.com/journals/complexity/2021/8839391.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065038302","display_name":"Xiaoyi Long","orcid":"https://orcid.org/0000-0001-7810-2697"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyi Long","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan 430072, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034648573","display_name":"Zheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng He","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan 430072, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyuan Wang","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan 430072, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan 430072, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034648573"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":{"value":2300,"currency":"USD","value_usd":2300},"apc_paid":{"value":2300,"currency":"USD","value_usd":2300},"fwci":1.0602,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79734809,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2021","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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/T12047","display_name":"Viral Infections and Vectors","score":0.9621000289916992,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9178000092506409,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8684381246566772},{"id":"https://openalex.org/keywords/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.8447521924972534},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.7079147100448608},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6997779607772827},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.642005205154419},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6419873833656311},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6002274751663208},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.5997053980827332},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5745805501937866},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5384561419487},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5198705196380615},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.517196536064148},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4912514090538025},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4629114270210266},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4367738366127014},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.39583438634872437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3171856105327606},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2032662332057953},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18444666266441345}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8684381246566772},{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.8447521924972534},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.7079147100448608},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6997779607772827},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.642005205154419},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6419873833656311},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6002274751663208},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.5997053980827332},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5745805501937866},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5384561419487},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5198705196380615},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.517196536064148},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4912514090538025},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4629114270210266},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4367738366127014},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.39583438634872437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3171856105327606},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2032662332057953},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18444666266441345},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1155/2021/8839391","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/8839391","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/8839391.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:hin:complx:8839391","is_oa":false,"landing_page_url":"http://downloads.hindawi.com/journals/complexity/2021/8839391.xml","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:c6ffdbea93a74f06b51aed4f3d066232","is_oa":true,"landing_page_url":"https://doaj.org/article/c6ffdbea93a74f06b51aed4f3d066232","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complexity, Vol 2021 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1155/2021/8839391","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2021/8839391","pdf_url":"https://downloads.hindawi.com/journals/complexity/2021/8839391.pdf","source":{"id":"https://openalex.org/S207319443","display_name":"Complexity","issn_l":"1076-2787","issn":["1076-2787","1099-0526"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complexity","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2396767952","display_name":null,"funder_award_id":"U1736206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2506566822","display_name":null,"funder_award_id":"U1903214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3825263882","display_name":null,"funder_award_id":"2019AAA049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4872122564","display_name":null,"funder_award_id":"616713","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6346682572","display_name":null,"funder_award_id":"61671332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G769530383","display_name":null,"funder_award_id":"62071339","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8433026972","display_name":null,"funder_award_id":"2019AAA049","funder_id":"https://openalex.org/F4320335792","funder_display_name":"Hubei Technological Innovation Special Fund"},{"id":"https://openalex.org/G8955107213","display_name":null,"funder_award_id":"Major","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335792","display_name":"Hubei Technological Innovation Special Fund","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3128043489.pdf","grobid_xml":"https://content.openalex.org/works/W3128043489.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W560518094","https://openalex.org/W1484889203","https://openalex.org/W1527736490","https://openalex.org/W1584101032","https://openalex.org/W1595516097","https://openalex.org/W1597554859","https://openalex.org/W1599132769","https://openalex.org/W1968908471","https://openalex.org/W1972243698","https://openalex.org/W1988523476","https://openalex.org/W2081514674","https://openalex.org/W2085194340","https://openalex.org/W2087063454","https://openalex.org/W2103676119","https://openalex.org/W2104843094","https://openalex.org/W2107937876","https://openalex.org/W2108286682","https://openalex.org/W2148439597","https://openalex.org/W2331370928","https://openalex.org/W2475651303","https://openalex.org/W2487144912","https://openalex.org/W2762171542","https://openalex.org/W2885522335","https://openalex.org/W2908498619","https://openalex.org/W2964330577","https://openalex.org/W2966813522","https://openalex.org/W2968532797","https://openalex.org/W3004605473","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2921905705","https://openalex.org/W118270679","https://openalex.org/W4255265352","https://openalex.org/W1632524629","https://openalex.org/W4239477580","https://openalex.org/W2052286527","https://openalex.org/W3103991047","https://openalex.org/W3144229288","https://openalex.org/W2545178307","https://openalex.org/W2160996072"],"abstract_inverted_index":{"This":[0],"paper":[1],"suggests":[2],"an":[3,61,78],"online":[4,111,127],"solution":[5],"for":[6],"the":[7,31,42,51,71,83,88,95,102,115,119,136,139],"optimal":[8,45,63,79,85],"tracking":[9,46,52,64,72,104],"control":[10,47,56,65,86],"of":[11,44,90,138],"robotic":[12,32],"systems":[13],"based":[14],"on":[15],"a":[16,36,54,123],"single":[17],"critic":[18,124],"neural":[19],"network":[20],"(NN)\u2010based":[21],"reinforcement":[22],"learning":[23,128],"(RL)":[24],"method.":[25,141],"To":[26,49,81],"this":[27],"end,":[28],"we":[29],"rewrite":[30],"system":[33],"model":[34],"as":[35],"state\u2010space":[37],"form,":[38],"which":[39],"will":[40],"facilitate":[41],"realization":[43],"synthesis.":[48],"maintain":[50],"response,":[53],"steady\u2010state":[55],"is":[57,66,114],"designed,":[58],"and":[59,101],"then":[60],"adaptive":[62,91],"used":[67],"to":[68,98,117,134],"ensure":[69],"that":[70],"error":[73],"can":[74],"achieve":[75],"convergence":[76],"in":[77],"sense.":[80],"solve":[82],"obtained":[84],"via":[87],"framework":[89],"dynamic":[92],"programming":[93],"(ADP),":[94],"command":[96],"trajectory":[97],"be":[99],"tracked":[100],"modified":[103],"Hamilton\u2010Jacobi\u2010Bellman":[105],"(HJB)":[106],"are":[107,132],"all":[108],"formulated.":[109],"An":[110],"RL":[112],"algorithm":[113],"developed":[116],"address":[118],"HJB":[120],"equation":[121],"using":[122],"NN":[125],"with":[126],"algorithm.":[129],"Simulation":[130],"results":[131],"given":[133],"verify":[135],"effectiveness":[137],"proposed":[140]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}