{"id":"https://openalex.org/W3008282592","doi":"https://doi.org/10.1109/tnnls.2020.2969215","title":"Adaptive Optimal Control for Stochastic Multiplayer Differential Games Using On-Policy and Off-Policy Reinforcement Learning","display_name":"Adaptive Optimal Control for Stochastic Multiplayer Differential Games Using On-Policy and Off-Policy Reinforcement Learning","publication_year":2020,"publication_date":"2020-02-27","ids":{"openalex":"https://openalex.org/W3008282592","doi":"https://doi.org/10.1109/tnnls.2020.2969215","mag":"3008282592","pmid":"https://pubmed.ncbi.nlm.nih.gov/32142455"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2020.2969215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2969215","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/A5059355181","display_name":"Mushuang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mushuang Liu","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-2678-4678","affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029213376","display_name":"Yan Wan","orcid":"https://orcid.org/0000-0002-7508-5833"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Wan","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-7508-5833","affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-4074-1615","affiliations":[{"raw_affiliation_string":"UTA Research Institute, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059736491","display_name":"Victor G. Lopez","orcid":"https://orcid.org/0000-0003-3989-4091"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor G. Lopez","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-3989-4091","affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":4.8191,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.95870499,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"31","issue":"12","first_page":"5522","last_page":"5533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"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":0.9998000264167786,"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/T12485","display_name":"Optimism, Hope, and Well-being","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9725000262260437,"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":0.6613852977752686},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.6250267028808594},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6249462366104126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6217358112335205},{"id":"https://openalex.org/keywords/stochastic-differential-equation","display_name":"Stochastic differential equation","score":0.5661776065826416},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5080170631408691},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.47973647713661194},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4650036096572876},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4377739727497101},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.41966211795806885},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3527596592903137},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.2875790596008301},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.1660425364971161},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.137473464012146}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6613852977752686},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.6250267028808594},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6249462366104126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6217358112335205},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.5661776065826416},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5080170631408691},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.47973647713661194},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4650036096572876},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4377739727497101},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.41966211795806885},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3527596592903137},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2875790596008301},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.1660425364971161},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.137473464012146},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2020.2969215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2020.2969215","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:32142455","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32142455","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/G3384580025","display_name":null,"funder_award_id":"N00014-18-1- 2221","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G5771986312","display_name":"CAREER: Co-Design of Networking and Decentralized Control to Enable Aerial Networks in an Uncertain Airspace","funder_award_id":"1714519","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8430057035","display_name":"EAGER: Real-Time: Collaborative Research: Unified Theory of Model-based and Data-driven Real-time Optimization and Control for Uncertain Networked Systems","funder_award_id":"1839804","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W560518094","https://openalex.org/W578295231","https://openalex.org/W1243097926","https://openalex.org/W1488674906","https://openalex.org/W1514436360","https://openalex.org/W1529558080","https://openalex.org/W1579118835","https://openalex.org/W1613865483","https://openalex.org/W1614417283","https://openalex.org/W1640156699","https://openalex.org/W1689629105","https://openalex.org/W1835030294","https://openalex.org/W1969959431","https://openalex.org/W1972910244","https://openalex.org/W1983523797","https://openalex.org/W2005437559","https://openalex.org/W2012626098","https://openalex.org/W2013895638","https://openalex.org/W2024303516","https://openalex.org/W2027448788","https://openalex.org/W2038669746","https://openalex.org/W2044221688","https://openalex.org/W2055140741","https://openalex.org/W2055891887","https://openalex.org/W2081514674","https://openalex.org/W2087018957","https://openalex.org/W2088246243","https://openalex.org/W2102933137","https://openalex.org/W2108383324","https://openalex.org/W2113288858","https://openalex.org/W2113794357","https://openalex.org/W2134627749","https://openalex.org/W2139416664","https://openalex.org/W2141198542","https://openalex.org/W2156835128","https://openalex.org/W2165726932","https://openalex.org/W2168758461","https://openalex.org/W2475651303","https://openalex.org/W2484646121","https://openalex.org/W2579592432","https://openalex.org/W2618993261","https://openalex.org/W2785604277","https://openalex.org/W2899654523","https://openalex.org/W2967135054","https://openalex.org/W2988676628","https://openalex.org/W3150098721","https://openalex.org/W4236158019","https://openalex.org/W4243645092","https://openalex.org/W4285719527","https://openalex.org/W6638758238"],"related_works":["https://openalex.org/W4287869118","https://openalex.org/W3005585050","https://openalex.org/W1984343254","https://openalex.org/W3126195429","https://openalex.org/W4210735314","https://openalex.org/W2092374696","https://openalex.org/W2228513190","https://openalex.org/W4283371013","https://openalex.org/W4386821009","https://openalex.org/W2962927879"],"abstract_inverted_index":{"Control-theoretic":[0],"differential":[1,18,52,68,121,179],"games":[2,19,69,122],"have":[3],"been":[4],"used":[5],"to":[6,117],"solve":[7,118],"optimal":[8,89],"control":[9,90],"problems":[10],"in":[11,40],"multiplayer":[12,51,82,178],"systems.":[13],"Most":[14],"existing":[15],"studies":[16],"on":[17],"either":[20],"assume":[21],"deterministic":[22],"dynamics":[23,25,39,57],"or":[24],"corrupted":[26],"with":[27],"additive":[28],"noise.":[29],"In":[30,45,115],"realistic":[31],"environments,":[32],"multidimensional":[33],"environmental":[34],"uncertainties":[35],"often":[36],"modulate":[37],"system":[38],"a":[41],"more":[42],"complicated":[43],"fashion.":[44],"this":[46],"article,":[47],"we":[48,124],"study":[49],"stochastic":[50,120,177],"games,":[53,159],"where":[54],"the":[55,78,94,102,110,119,136,146,157,164,171,176],"players'":[56],"are":[58,154],"modulated":[59],"by":[60],"randomly":[61],"time-varying":[62],"parameters.":[63],"We":[64,85,161],"first":[65],"formulate":[66],"two":[67],"for":[70,156,175],"systems":[71],"of":[72,113],"general":[73],"uncertain":[74],"linear":[75],"dynamics,":[76],"including":[77,145],"two-player":[79],"zero-sum":[80],"and":[81,129,151],"nonzero-sum":[83],"games.":[84,180],"then":[86],"show":[87,162],"that":[88,163],"policies,":[91],"which":[92],"constitute":[93],"Nash":[95,172],"equilibrium":[96,173],"solutions,":[97],"can":[98,168],"be":[99],"derived":[100],"from":[101],"corresponding":[103],"Hamiltonian":[104],"functions.":[105],"Stability":[106],"is":[107],"proven":[108],"using":[109],"Lyapunov":[111],"type":[112],"analysis.":[114],"order":[116],"online,":[123],"integrate":[125],"reinforcement":[126],"learning":[127,143,166],"(RL)":[128],"an":[130],"effective":[131],"uncertainty":[132],"sampling":[133],"method":[134,140],"called":[135],"multivariate":[137],"probabilistic":[138],"collocation":[139],"(MPCM).":[141],"Two":[142],"algorithms,":[144],"on-policy":[147],"integral":[148],"RL":[149],"(IRL)":[150],"off-policy":[152],"IRL,":[153],"designed":[155],"formulated":[158],"respectively.":[160],"proposed":[165],"algorithms":[167],"effectively":[169],"find":[170],"solutions":[174]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}