{"id":"https://openalex.org/W2796202072","doi":"https://doi.org/10.1109/tnnls.2018.2808203","title":"Actor-Critic Learning Control Based on <inline-formula> <tex-math notation=\"LaTeX\">$\\ell_{2}$ </tex-math> </inline-formula>-Regularized Temporal-Difference Prediction With Gradient Correction","display_name":"Actor-Critic Learning Control Based on <inline-formula> <tex-math notation=\"LaTeX\">$\\ell_{2}$ </tex-math> </inline-formula>-Regularized Temporal-Difference Prediction With Gradient Correction","publication_year":2018,"publication_date":"2018-04-05","ids":{"openalex":"https://openalex.org/W2796202072","doi":"https://doi.org/10.1109/tnnls.2018.2808203","mag":"2796202072","pmid":"https://pubmed.ncbi.nlm.nih.gov/29993664"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2018.2808203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2808203","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/A5077743639","display_name":"Luntong Li","orcid":"https://orcid.org/0000-0002-5299-4858"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Luntong Li","raw_affiliation_strings":["Department of Automation, Beijing University of Chemical Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064212043","display_name":"Dazi Li","orcid":"https://orcid.org/0000-0003-1610-6558"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dazi Li","raw_affiliation_strings":["Department of Automation, Beijing University of Chemical Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102884128","display_name":"Tianheng Song","orcid":"https://orcid.org/0000-0001-8275-5535"},"institutions":[{"id":"https://openalex.org/I75390827","display_name":"Beijing University of Chemical Technology","ror":"https://ror.org/00df5yc52","country_code":"CN","type":"education","lineage":["https://openalex.org/I75390827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianheng Song","raw_affiliation_strings":["Department of Automation, Beijing University of Chemical Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Beijing University of Chemical Technology, Beijing, China","institution_ids":["https://openalex.org/I75390827"]}]},{"author_position":"last","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":["Institute of Unmanned Systems, College of Mechatronics and Automation, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"Institute of Unmanned Systems, College of Mechatronics and Automation, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077743639"],"corresponding_institution_ids":["https://openalex.org/I75390827"],"apc_list":null,"apc_paid":null,"fwci":1.2823,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.81769991,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"29","issue":"12","first_page":"5899","last_page":"5909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9955999851226807,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9538000226020813,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6125149726867676},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5256772637367249},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.36186695098876953},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.3359258770942688},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.33028537034988403}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6125149726867676},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5256772637367249},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.36186695098876953},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3359258770942688},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.33028537034988403}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2018.2808203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2808203","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:29993664","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29993664","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":[],"awards":[{"id":"https://openalex.org/G3469485582","display_name":null,"funder_award_id":"4182045","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G5320757814","display_name":null,"funder_award_id":"U1564214","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7223810382","display_name":null,"funder_award_id":"ZY1839","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7457541925","display_name":null,"funder_award_id":"61751311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G861959819","display_name":null,"funder_award_id":"61573052","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/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1460549585","https://openalex.org/W1566185995","https://openalex.org/W1594783240","https://openalex.org/W2009303086","https://openalex.org/W2014729048","https://openalex.org/W2024390895","https://openalex.org/W2032736119","https://openalex.org/W2048687352","https://openalex.org/W2052305027","https://openalex.org/W2072931156","https://openalex.org/W2073384958","https://openalex.org/W2075268401","https://openalex.org/W2088542838","https://openalex.org/W2094387729","https://openalex.org/W2100677568","https://openalex.org/W2102988084","https://openalex.org/W2118556122","https://openalex.org/W2132011051","https://openalex.org/W2132351269","https://openalex.org/W2132858840","https://openalex.org/W2134882417","https://openalex.org/W2142620596","https://openalex.org/W2143490508","https://openalex.org/W2149174281","https://openalex.org/W2150999967","https://openalex.org/W2155027007","https://openalex.org/W2156321584","https://openalex.org/W2158738729","https://openalex.org/W2160284799","https://openalex.org/W2165905123","https://openalex.org/W2172968643","https://openalex.org/W2177967097","https://openalex.org/W2317814600","https://openalex.org/W2344093208","https://openalex.org/W2345038028","https://openalex.org/W2399553461","https://openalex.org/W2405551631","https://openalex.org/W2550394442","https://openalex.org/W2586680856","https://openalex.org/W2768907917","https://openalex.org/W2768933283","https://openalex.org/W2953189830","https://openalex.org/W3041202696","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4285719527","https://openalex.org/W4299401133","https://openalex.org/W6635508374","https://openalex.org/W6675256285","https://openalex.org/W6677370284","https://openalex.org/W6683204974","https://openalex.org/W6683356630","https://openalex.org/W6684488654","https://openalex.org/W6745810992"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2504004674","https://openalex.org/W2061531152","https://openalex.org/W3002753104","https://openalex.org/W2077600819","https://openalex.org/W2142036596","https://openalex.org/W2072657027","https://openalex.org/W2962838298"],"abstract_inverted_index":{"Actor-critic":[0],"based":[1],"on":[2,35],"the":[3,22,29,57,79,95,104,120,135,147,153,174,184,188,195],"policy":[4,46,64,76,125,148,156],"gradient":[5,132],"(PG-based":[6],"AC)":[7],"methods":[8],"have":[9,48],"been":[10,49],"widely":[11],"studied":[12],"to":[13,20,37,92,94,173],"solve":[14],"learning":[15,26,100,196,202,211],"control":[16,212],"problems.":[17],"In":[18,54],"order":[19],"increase":[21],"data":[23],"efficiency":[24,203],"of":[25,31,69,99,123,137,168,176,190],"prediction":[27],"in":[28,51,126,134,187],"critic":[30,58,88,189],"PG-based":[32],"AC,":[33],"studies":[34],"how":[36],"use":[38],"recursive":[39],"least-squares":[40],"temporal":[41],"difference":[42],"(RLS-TD)":[43],"algorithms":[44],"for":[45],"evaluation":[47],"conducted":[50],"recent":[52],"years.":[53],"such":[55],"contexts,":[56],"RLS-TD":[59,87,159,177],"evaluates":[60,152],"an":[61,127],"unknown":[62],"mixed":[63],"generated":[65,77],"by":[66,78,157],"a":[67,110],"series":[68],"different":[70],"actors,":[71],"but":[72],"not":[73],"one":[74],"fixed":[75,97,150,155],"current":[80,124],"actor.":[81],"Therefore,":[82],"this":[83,107],"AC":[84,112,210],"framework":[85,113],"with":[86,170],"cannot":[89],"be":[90],"proved":[91],"converge":[93],"optimal":[96],"point":[98],"problem.":[101],"To":[102],"address":[103],"above":[105],"problem,":[106],"paper":[108],"proposes":[109],"new":[111],"named":[114],"critic-iteration":[115],"PG":[116,169],"(CIPG),":[117],"which":[118],"learns":[119],"state-value":[121],"function":[122,171],"on-policy":[128],"way":[129],"and":[130,151,198,204],"performs":[131],"ascent":[133],"direction":[136],"improving":[138],"discounted":[139],"total":[140],"reward.":[141],"During":[142],"each":[143],"iteration,":[144],"CIPG":[145,191,199],"keeps":[146],"parameters":[149],"resulting":[154],"-regularized":[158],"critic.":[160,178],"Our":[161],"convergence":[162,166,206],"analysis":[163,167],"extends":[164],"previous":[165],"approximation":[172],"case":[175],"The":[179],"simulation":[180],"results":[181],"demonstrate":[182],"that":[183],"-regularization":[185],"term":[186],"is":[192],"undamped":[193],"during":[194],"process,":[197],"has":[200],"better":[201],"faster":[205],"rate":[207],"than":[208],"conventional":[209],"methods.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2018-04-13T00:00:00"}