{"id":"https://openalex.org/W3108085704","doi":"https://doi.org/10.1109/icca51439.2020.9264554","title":"Multi-player H<sub>\u221e</sub> Differential Game using On-Policy and Off-Policy Reinforcement Learning","display_name":"Multi-player H<sub>\u221e</sub> Differential Game using On-Policy and Off-Policy Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3108085704","doi":"https://doi.org/10.1109/icca51439.2020.9264554","mag":"3108085704"},"language":"en","primary_location":{"id":"doi:10.1109/icca51439.2020.9264554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control &amp; Automation (ICCA)","raw_type":"proceedings-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/A5054463573","display_name":"Peiliang An","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":true,"raw_author_name":"Peiliang An","raw_affiliation_strings":["Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","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":["Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, 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":["Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Fort Worth, Texas, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, Texas, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054463573"],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":0.5629,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73880007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1137","last_page":"1142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":1.0,"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":0.9900000095367432,"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/T12047","display_name":"Viral Infections and Vectors","score":0.9585000276565552,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.77674400806427},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.7254610061645508},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7025133371353149},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.6117340326309204},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6008923053741455},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.46890130639076233},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4650477170944214},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42698273062705994},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3870853781700134},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.34914731979370117},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3115152418613434},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27388760447502136},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08586692810058594}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.77674400806427},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.7254610061645508},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.7025133371353149},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.6117340326309204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6008923053741455},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.46890130639076233},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4650477170944214},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42698273062705994},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3870853781700134},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.34914731979370117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3115152418613434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27388760447502136},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08586692810058594},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icca51439.2020.9264554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control &amp; Automation (ICCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1579118835","https://openalex.org/W1614417283","https://openalex.org/W1969959431","https://openalex.org/W1983523797","https://openalex.org/W2013895638","https://openalex.org/W2024303516","https://openalex.org/W2055300044","https://openalex.org/W2055891887","https://openalex.org/W2081514674","https://openalex.org/W2088246243","https://openalex.org/W2092289967","https://openalex.org/W2102933137","https://openalex.org/W2139416664","https://openalex.org/W2165726932","https://openalex.org/W2475651303","https://openalex.org/W2484646121","https://openalex.org/W2579592432","https://openalex.org/W2590583874","https://openalex.org/W2608634483","https://openalex.org/W2798534591","https://openalex.org/W2800584559","https://openalex.org/W2983873455","https://openalex.org/W3008282592","https://openalex.org/W3150098721","https://openalex.org/W6774523736"],"related_works":["https://openalex.org/W4312141693","https://openalex.org/W4283371013","https://openalex.org/W1969185016","https://openalex.org/W1536009559","https://openalex.org/W2111030377","https://openalex.org/W2037619003","https://openalex.org/W2601906167","https://openalex.org/W2103821767","https://openalex.org/W3144554261","https://openalex.org/W2801573479"],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2,117],"a":[3,66],"multi-player":[4,102],"H":[5,103],"<sub":[6,104],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[7,105],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u221e</sub>":[8,106],"differential":[9,90,107],"game":[10,91,108],"for":[11],"systems":[12],"of":[13,34,129],"general":[14],"linear":[15],"dynamics.":[16],"In":[17],"this":[18],"game,":[19],"multiple":[20],"players":[21],"design":[22],"their":[23,28],"control":[24,42],"inputs":[25],"to":[26,49,87,120],"minimize":[27],"cost":[29],"functions":[30],"in":[31],"the":[32,40,47,57,62,78,89,96,101,122,127,130],"presence":[33],"worst-case":[35],"disturbances.":[36],"We":[37,53,93],"first":[38],"derive":[39],"optimal":[41,59],"and":[43,64,82,125],"disturbance":[44],"policies":[45,60],"using":[46,111],"solutions":[48],"Hamilton-Jacobi-Isaacs":[50],"(HJI)":[51],"equations.":[52],"then":[54],"prove":[55],"that":[56,95],"derived":[58],"stabilize":[61],"system":[63,113],"constitute":[65],"Nash":[67],"equilibrium":[68],"solution.":[69],"Two":[70],"integral":[71],"reinforcement":[72],"learning":[73,132],"(IRL)":[74],"-based":[75],"algorithms,":[76],"including":[77],"policy":[79],"iteration":[80],"IRL":[81,98],"off-policy":[83,97],"IRL,":[84],"are":[85,118],"developed":[86,131],"solve":[88,100],"online.":[92],"show":[94],"can":[99],"online":[109],"without":[110],"any":[112],"dynamics":[114],"information.":[115],"Simulation":[116],"conducted":[119],"validate":[121],"theoretical":[123],"analysis":[124],"demonstrate":[126],"effectiveness":[128],"algorithms.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}