{"id":"https://openalex.org/W3040370673","doi":"https://doi.org/10.1177/0142331220932634","title":"Off-policy integral reinforcement learning algorithm in dealing with nonzero sum game for nonlinear distributed parameter systems","display_name":"Off-policy integral reinforcement learning algorithm in dealing with nonzero sum game for nonlinear distributed parameter systems","publication_year":2020,"publication_date":"2020-07-06","ids":{"openalex":"https://openalex.org/W3040370673","doi":"https://doi.org/10.1177/0142331220932634","mag":"3040370673"},"language":"en","primary_location":{"id":"doi:10.1177/0142331220932634","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0142331220932634","pdf_url":null,"source":{"id":"https://openalex.org/S24148485","display_name":"Transactions of the Institute of Measurement and Control","issn_l":"0142-3312","issn":["0142-3312","1477-0369"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Institute of Measurement and Control","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/A5049088654","display_name":"He Ren","orcid":"https://orcid.org/0000-0002-7237-8032"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Ren","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101958099","display_name":"Jing Dai","orcid":"https://orcid.org/0000-0002-3273-8881"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jing Dai","raw_affiliation_strings":["Department of Electrical Engineering, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625792","display_name":"Huaguang Zhang","orcid":"https://orcid.org/0000-0002-2375-9824"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaguang Zhang","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, China"],"raw_orcid":"https://orcid.org/0000-0002-2375-9824","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100342397","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0003-4527-6847"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, China"],"raw_orcid":"https://orcid.org/0000-0003-4527-6847","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101958099"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.5073,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71337132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"42","issue":"15","first_page":"2919","last_page":"2928"},"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":0.9513000249862671,"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/T12277","display_name":"Frequency Control in Power Systems","score":0.9176999926567078,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.782538652420044},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.7476747632026672},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.6435914039611816},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6081628203392029},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5888074040412903},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5533193349838257},{"id":"https://openalex.org/keywords/ordinary-differential-equation","display_name":"Ordinary differential equation","score":0.5488718748092651},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5246620178222656},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.5178297162055969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47864830493927},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4716550409793854},{"id":"https://openalex.org/keywords/partial-differential-equation","display_name":"Partial differential equation","score":0.4317706823348999},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42756080627441406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41801977157592773},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.41505166888237},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.3663714528083801},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.30106598138809204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1606491208076477},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10574844479560852}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.782538652420044},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.7476747632026672},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.6435914039611816},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6081628203392029},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5888074040412903},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5533193349838257},{"id":"https://openalex.org/C51544822","wikidata":"https://www.wikidata.org/wiki/Q465274","display_name":"Ordinary differential equation","level":3,"score":0.5488718748092651},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5246620178222656},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.5178297162055969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47864830493927},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4716550409793854},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.4317706823348999},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42756080627441406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41801977157592773},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.41505166888237},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.3663714528083801},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.30106598138809204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1606491208076477},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10574844479560852},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0142331220932634","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0142331220932634","pdf_url":null,"source":{"id":"https://openalex.org/S24148485","display_name":"Transactions of the Institute of Measurement and Control","issn_l":"0142-3312","issn":["0142-3312","1477-0369"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Institute of Measurement and Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1683018794","display_name":null,"funder_award_id":"61,627,809","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4629068781","display_name":null,"funder_award_id":"61433004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G664227649","display_name":null,"funder_award_id":"61,621,004","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":41,"referenced_works":["https://openalex.org/W1479707688","https://openalex.org/W1538686203","https://openalex.org/W1584101032","https://openalex.org/W1912694276","https://openalex.org/W1971361435","https://openalex.org/W1986957722","https://openalex.org/W1989664626","https://openalex.org/W1989855774","https://openalex.org/W1991119064","https://openalex.org/W1997603681","https://openalex.org/W2005229381","https://openalex.org/W2008626900","https://openalex.org/W2011310556","https://openalex.org/W2011581571","https://openalex.org/W2013579823","https://openalex.org/W2019338681","https://openalex.org/W2027851563","https://openalex.org/W2029382655","https://openalex.org/W2037677278","https://openalex.org/W2040278456","https://openalex.org/W2045283962","https://openalex.org/W2055367674","https://openalex.org/W2081264254","https://openalex.org/W2082283639","https://openalex.org/W2085632315","https://openalex.org/W2100276679","https://openalex.org/W2110357265","https://openalex.org/W2144044658","https://openalex.org/W2151966330","https://openalex.org/W2165726932","https://openalex.org/W2586495351","https://openalex.org/W2740962288","https://openalex.org/W2767784613","https://openalex.org/W2790671014","https://openalex.org/W2897975793","https://openalex.org/W2908707124","https://openalex.org/W2947142458","https://openalex.org/W2947686700","https://openalex.org/W2968481051","https://openalex.org/W2982321573","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W3082668976","https://openalex.org/W2517973022","https://openalex.org/W1543121148","https://openalex.org/W1580703421","https://openalex.org/W2618518959","https://openalex.org/W2231364979","https://openalex.org/W4295745414","https://openalex.org/W4382202915","https://openalex.org/W2489516236","https://openalex.org/W4297273858"],"abstract_inverted_index":{"Benefitting":[0],"from":[1],"the":[2,8,24,39,53,61,65,71,77,81,92,95,100,108,122,129,141,144],"technology":[3,56],"of":[4,26,143],"integral":[5],"reinforcement":[6],"learning,":[7],"nonzero":[9],"sum":[10],"(NZS)":[11],"game":[12],"for":[13,64],"distributed":[14],"parameter":[15],"systems":[16,44],"is":[17,35,57,88,104,137],"effectively":[18],"solved":[19],"in":[20,128],"this":[21],"paper":[22],"when":[23],"information":[25],"system":[27],"dynamics":[28],"are":[29,118],"unavailable.":[30],"The":[31],"Karhunen-Lo\u00e8ve":[32],"decomposition":[33],"(KLD)":[34],"employed":[36],"to":[37,59,76,120,139],"convert":[38],"partial":[40],"differential":[41,48],"equation":[42,49],"(PDE)":[43],"into":[45],"high-order":[46],"ordinary":[47],"(ODE)":[50],"systems.":[51],"Moreover,":[52],"off-policy":[54,102,110,146],"IRL":[55,111],"introduced":[58],"design":[60],"optimal":[62,78],"strategies":[63,127],"NZS":[66],"game.":[67],"To":[68],"confirm":[69],"that":[70],"presented":[72,101,109],"algorithm":[73],"will":[74],"converge":[75],"value":[79,123],"functions,":[80],"traditional":[82,96],"adaptive":[83],"dynamic":[84],"programming":[85],"(ADP)":[86],"method":[87,98,103],"first":[89],"discussed.":[90],"Then,":[91],"equivalence":[93],"between":[94],"ADP":[97],"and":[99,114,125],"proved.":[105],"For":[106],"implementing":[107],"method,":[112],"actor":[113],"critic":[115],"neural":[116],"networks":[117],"utilized":[119],"approach":[121],"functions":[124],"control":[126],"iteration":[130],"process,":[131],"individually.":[132],"Finally,":[133],"a":[134],"numerical":[135],"simulation":[136],"shown":[138],"illustrate":[140],"effectiveness":[142],"proposal":[145],"algorithm.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}