{"id":"https://openalex.org/W4393188243","doi":"https://doi.org/10.1109/tsmc.2024.3373456","title":"Parallel Cross Entropy Policy Gradient Adaptive Dynamic Programming for Optimal Tracking Control of Discrete-Time Nonlinear Systems","display_name":"Parallel Cross Entropy Policy Gradient Adaptive Dynamic Programming for Optimal Tracking Control of Discrete-Time Nonlinear Systems","publication_year":2024,"publication_date":"2024-03-26","ids":{"openalex":"https://openalex.org/W4393188243","doi":"https://doi.org/10.1109/tsmc.2024.3373456"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2024.3373456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3373456","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-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/A5058905701","display_name":"Jiahui Xu","orcid":"https://orcid.org/0000-0002-4058-0447"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Xu","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4058-0447","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777024","display_name":"Jingcheng Wang","orcid":"https://orcid.org/0000-0002-4277-1263"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingcheng Wang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4277-1263","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018604914","display_name":"Jun Rao","orcid":"https://orcid.org/0000-0002-7467-4898"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Rao","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7467-4898","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000872966","display_name":"Yanjiu Zhong","orcid":"https://orcid.org/0000-0002-4361-9378"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjiu Zhong","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4361-9378","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087893108","display_name":"Shunyu Wu","orcid":"https://orcid.org/0000-0001-9856-2148"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunyu Wu","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9856-2148","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026545800","display_name":"Qifang Sun","orcid":"https://orcid.org/0000-0001-6568-6718"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qifang Sun","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6568-6718","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.6252,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68387177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"54","issue":"6","first_page":"3809","last_page":"3821"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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":0.9995999932289124,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9526000022888184,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9447000026702881,"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/dynamic-programming","display_name":"Dynamic programming","score":0.6565070748329163},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5925325751304626},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5702813267707825},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.525407075881958},{"id":"https://openalex.org/keywords/monotonic-function","display_name":"Monotonic function","score":0.5138145089149475},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.494538277387619},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.4647858142852783},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.445008248090744},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4179422855377197},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.41586968302726746},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3359956443309784},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2735106945037842},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2688932418823242},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2614211440086365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15525087714195251}],"concepts":[{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6565070748329163},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5925325751304626},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5702813267707825},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.525407075881958},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.5138145089149475},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.494538277387619},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4647858142852783},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.445008248090744},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4179422855377197},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.41586968302726746},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3359956443309784},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2735106945037842},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2688932418823242},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2614211440086365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15525087714195251},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2024.3373456","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2024.3373456","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4341435642","display_name":null,"funder_award_id":"62273234","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":47,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1592601589","https://openalex.org/W1707845830","https://openalex.org/W2056653303","https://openalex.org/W2137092694","https://openalex.org/W2342031891","https://openalex.org/W2568019971","https://openalex.org/W2770616710","https://openalex.org/W2801701639","https://openalex.org/W2802164917","https://openalex.org/W2891435172","https://openalex.org/W2949510088","https://openalex.org/W2972143761","https://openalex.org/W2996785115","https://openalex.org/W3008245684","https://openalex.org/W3010946901","https://openalex.org/W3013679533","https://openalex.org/W3035700320","https://openalex.org/W3036186095","https://openalex.org/W3037622062","https://openalex.org/W3042179604","https://openalex.org/W3045014914","https://openalex.org/W3045509383","https://openalex.org/W3094514670","https://openalex.org/W3097662863","https://openalex.org/W3124981469","https://openalex.org/W3162945727","https://openalex.org/W3166673355","https://openalex.org/W3167122789","https://openalex.org/W3197308516","https://openalex.org/W3215003840","https://openalex.org/W4200038771","https://openalex.org/W4200152604","https://openalex.org/W4200325667","https://openalex.org/W4210243935","https://openalex.org/W4214717370","https://openalex.org/W4254041323","https://openalex.org/W4292086994","https://openalex.org/W4294891444","https://openalex.org/W4364375123","https://openalex.org/W4388579581","https://openalex.org/W4390829281","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6704939968","https://openalex.org/W6748839928","https://openalex.org/W6779282036"],"related_works":["https://openalex.org/W1932159282","https://openalex.org/W4285537323","https://openalex.org/W2379312070","https://openalex.org/W2136173754","https://openalex.org/W2110050003","https://openalex.org/W2133851133","https://openalex.org/W2953025626","https://openalex.org/W2499081552","https://openalex.org/W2366053282","https://openalex.org/W1653644965"],"abstract_inverted_index":{"Policy":[0],"gradient":[1],"adaptive":[2],"dynamic":[3],"programming":[4],"(PGADP)":[5],"is":[6,70,115,151,178],"a":[7,23,45,73,78,131,166,183],"recently":[8],"acclaimed":[9],"control":[10,15,99,134],"technique":[11],"for":[12,63,136],"the":[13,30,55,83,86,94,98,102,109,112,122,140,143,149,156,171,174],"optimal":[14,60,113],"design":[16],"of":[17,26,57,85,142,148,173],"nonlinear":[18,65],"systems.":[19,66],"Nevertheless,":[20],"it":[21],"demands":[22],"substantial":[24],"amount":[25],"interaction":[27],"data":[28],"with":[29,54],"controlled":[31],"system,":[32],"which":[33],"can":[34],"prove":[35],"costly":[36],"or":[37],"perilous":[38],"in":[39],"certain":[40],"scenarios.":[41],"This":[42],"article":[43],"introduces":[44],"parallel":[46,123],"cross":[47,124],"entropy":[48,125],"optimization":[49,126],"method-based":[50],"PGADP":[51],"(PCEOM-PGADP)":[52],"algorithm,":[53],"objective":[56],"devising":[58],"an":[59,90],"tracking":[61,68,79,187],"controller":[62],"discrete-time":[64],"The":[67,118],"problem":[69,75],"transformed":[71],"into":[72],"regulation":[74],"by":[76,153],"constructing":[77],"error":[80],"system.":[81,188],"Furthermore,":[82],"implementation":[84],"proposed":[87,175],"algorithm":[88,150,177],"employs":[89],"actor\u2013critic":[91],"structure,":[92],"where":[93],"actor":[95],"network":[96,104],"represents":[97],"policy":[100,114,135],"and":[101],"critic":[103],"assesses":[105],"its":[106],"performance.":[107],"Through":[108],"iterative":[110],"interaction,":[111],"ultimately":[116],"derived.":[117],"approach":[119],"also":[120],"leverages":[121],"method":[127],"(PCEOM)":[128],"to":[129],"acquire":[130],"reasonable":[132],"initial":[133],"PGADP,":[137],"thereby":[138],"accelerating":[139],"efficiency":[141],"learning":[144],"process.":[145],"Convergence":[146],"analysis":[147],"conducted":[152],"demonstrating":[154],"that":[155],"generated":[157],"<inline-formula":[158],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[159],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[160],"<tex-math":[161],"notation=\"LaTeX\">$Q$</tex-math>":[162],"</inline-formula>":[163],"function":[164],"constitutes":[165],"monotonically":[167],"nonincreasing":[168],"sequence.":[169],"Finally,":[170],"effectiveness":[172],"PCEOM-PGADP":[176],"verified":[179],"through":[180],"simulation":[181],"on":[182],"complex":[184],"automated":[185],"driving":[186]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
