{"id":"https://openalex.org/W3080747787","doi":"https://doi.org/10.1109/tnnls.2020.3015767","title":"A Parallel Framework of Adaptive Dynamic Programming Algorithm With Off-Policy Learning","display_name":"A Parallel Framework of Adaptive Dynamic Programming Algorithm With Off-Policy Learning","publication_year":2020,"publication_date":"2020-08-24","ids":{"openalex":"https://openalex.org/W3080747787","doi":"https://doi.org/10.1109/tnnls.2020.3015767","mag":"3080747787","pmid":"https://pubmed.ncbi.nlm.nih.gov/32833647"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.3015767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3015767","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["Key Laboratory of Measurement and Control of Complex System of Engineering, Ministry of Education, Southeast University, Nanjing, China","School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9269-334X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Measurement and Control of Complex System of Engineering, Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100347697","display_name":"Xiaofeng Li","orcid":"https://orcid.org/0000-0002-8447-9279"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Li","raw_affiliation_strings":["Key Laboratory of Measurement and Control of Complex System of Engineering, Ministry of Education, Southeast University, Nanjing, China","School of Automation, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Measurement and Control of Complex System of Engineering, Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103266231","display_name":"Yuewen Sun","orcid":"https://orcid.org/0000-0001-7534-1297"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewen Sun","raw_affiliation_strings":["Key Laboratory of Measurement and Control of Complex System of Engineering, Ministry of Education, Southeast University, Nanjing, China","School of Automation, Southeast University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Measurement and Control of Complex System of Engineering, Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76569877"],"apc_list":null,"apc_paid":null,"fwci":1.9024,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.88847123,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"32","issue":"8","first_page":"3578","last_page":"3587"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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":0.991100013256073,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9672999978065491,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.7879270315170288},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6837818622589111},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6835050582885742},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6525160670280457},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5989336371421814},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5915759801864624},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5828530192375183},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5797192454338074},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.551393985748291},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5133091807365417},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4982566833496094},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4912371039390564},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41253986954689026},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26899993419647217},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2246851623058319},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20622524619102478},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15167102217674255}],"concepts":[{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.7879270315170288},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6837818622589111},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6835050582885742},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6525160670280457},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5989336371421814},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5915759801864624},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5828530192375183},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5797192454338074},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.551393985748291},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5133091807365417},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4982566833496094},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4912371039390564},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41253986954689026},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26899993419647217},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2246851623058319},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20622524619102478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15167102217674255},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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":2,"locations":[{"id":"doi:10.1109/tnnls.2020.3015767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.3015767","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:32833647","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32833647","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G1654982242","display_name":null,"funder_award_id":"U1713209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2249051953","display_name":null,"funder_award_id":"61942301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5033343354","display_name":null,"funder_award_id":"61921004","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1510124874","https://openalex.org/W1589747210","https://openalex.org/W1601081659","https://openalex.org/W1757796397","https://openalex.org/W1991509378","https://openalex.org/W2005675298","https://openalex.org/W2048687352","https://openalex.org/W2086808696","https://openalex.org/W2093831009","https://openalex.org/W2110040537","https://openalex.org/W2121863487","https://openalex.org/W2136064843","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2160561608","https://openalex.org/W2165150801","https://openalex.org/W2165501837","https://openalex.org/W2165726932","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2245501338","https://openalex.org/W2257979135","https://openalex.org/W2319074362","https://openalex.org/W2329769476","https://openalex.org/W2332672415","https://openalex.org/W2342662072","https://openalex.org/W2400458653","https://openalex.org/W2509783950","https://openalex.org/W2550394442","https://openalex.org/W2580175322","https://openalex.org/W2580629550","https://openalex.org/W2727279496","https://openalex.org/W2745868649","https://openalex.org/W2761873684","https://openalex.org/W2766447205","https://openalex.org/W2766502495","https://openalex.org/W2771641782","https://openalex.org/W2887344203","https://openalex.org/W2950268955","https://openalex.org/W2951799221","https://openalex.org/W2962974451","https://openalex.org/W2963477884","https://openalex.org/W2963641140","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964291307","https://openalex.org/W2990022244","https://openalex.org/W3100789280","https://openalex.org/W3103559770","https://openalex.org/W4213251304","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6637967152","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6704571135","https://openalex.org/W6732665253","https://openalex.org/W6744838376","https://openalex.org/W6754615820","https://openalex.org/W6771136596"],"related_works":["https://openalex.org/W4239477580","https://openalex.org/W4255265352","https://openalex.org/W2921905705","https://openalex.org/W1632524629","https://openalex.org/W4292330635","https://openalex.org/W2902017027","https://openalex.org/W2766998270","https://openalex.org/W2950982235","https://openalex.org/W2052286527","https://openalex.org/W4306892756"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"a":[3],"model-free":[4],"online":[5],"adaptive":[6],"dynamic":[7],"programming":[8],"(ADP)":[9],"approach":[10],"is":[11,94,114,120,128,150,172],"developed":[12],"for":[13,96],"solving":[14],"the":[15,24,29,38,43,48,54,61,74,79,82,86,101,108,117,125,135,138,144,146,159,162,166,169],"optimal":[16],"control":[17,112,163],"problem":[18],"of":[19,50,107,137,168],"nonaffine":[20],"nonlinear":[21],"systems.":[22],"Combining":[23],"off-policy":[25],"learning":[26],"mechanism":[27],"with":[28,42,63,152],"parallel":[30],"paradigm,":[31],"multithread":[32],"agents":[33],"are":[34],"employed":[35],"to":[36,122,134,157],"collect":[37],"transitions":[39],"by":[40,174],"interacting":[41],"environment":[44,62],"that":[45,72,124],"significantly":[46],"augments":[47],"number":[49],"sampled":[51,83],"data.":[52,84],"On":[53],"other":[55],"hand,":[56],"each":[57],"thread":[58],"agent":[59],"explores":[60],"different":[64],"initial":[65],"states":[66],"under":[67,110],"its":[68],"own":[69],"behavior":[70],"policy":[71,87,97,102],"enhances":[73],"exploration":[75],"capability":[76],"and":[77,131,161],"alleviates":[78],"correlation":[80],"between":[81],"After":[85],"evaluation":[88],"process,":[89],"only":[90],"one":[91],"step":[92],"update":[93],"required":[95],"improvement":[98],"based":[99],"on":[100],"gradient":[103],"method.":[104],"The":[105],"stability":[106],"system":[109],"iterative":[111,126],"laws":[113],"guaranteed.":[115],"Moreover,":[116],"convergence":[118],"analysis":[119],"given":[121],"prove":[123],"Q-function":[127,160],"monotonically":[129],"nonincreasing":[130],"finally":[132],"converges":[133],"solution":[136],"Hamilton-Jacobi-Bellman":[139],"(HJB)":[140],"equation.":[141],"For":[142],"implementing":[143],"algorithm,":[145],"actor-critic":[147],"(AC)":[148],"structure":[149],"utilized":[151],"two":[153,175],"neural":[154],"networks":[155],"(NNs)":[156],"approximate":[158],"policy.":[164],"Finally,":[165],"effectiveness":[167],"proposed":[170],"algorithm":[171],"verified":[173],"numerical":[176],"examples.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}