{"id":"https://openalex.org/W3150098721","doi":"https://doi.org/10.1109/cdc.2010.5718152","title":"Integral Reinforcement Learning for online computation of feedback Nash strategies of nonzero-sum differential games","display_name":"Integral Reinforcement Learning for online computation of feedback Nash strategies of nonzero-sum differential games","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W3150098721","doi":"https://doi.org/10.1109/cdc.2010.5718152","mag":"3150098721"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2010.5718152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2010.5718152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th IEEE Conference on Decision and Control (CDC)","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/A5047724723","display_name":"Draguna Vrabie","orcid":"https://orcid.org/0000-0002-1547-2049"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Draguna Vrabie","raw_affiliation_strings":["Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Lewis","raw_affiliation_strings":["Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I4210116723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047724723"],"corresponding_institution_ids":["https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":0.6691,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.74270341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3066","last_page":"3071"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9746000170707703,"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/T12277","display_name":"Frequency Control in Power Systems","score":0.9433000087738037,"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":0.7956169843673706},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7012823224067688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6464667320251465},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6107267141342163},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.5828022360801697},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5766525268554688},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49561941623687744},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4908972382545471},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4907613694667816},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.46729376912117004},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.4617784917354584},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.45881539583206177},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.4499649405479431},{"id":"https://openalex.org/keywords/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.4475730061531067},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.42878830432891846},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.4263409376144409},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.42028355598449707},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3754110336303711},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.3172440528869629},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3136145770549774},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.2949482202529907},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26586687564849854},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.2242211401462555},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.18389028310775757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18045717477798462},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15737080574035645}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7956169843673706},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.7012823224067688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464667320251465},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6107267141342163},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.5828022360801697},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5766525268554688},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49561941623687744},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4908972382545471},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4907613694667816},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.46729376912117004},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.4617784917354584},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.45881539583206177},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.4499649405479431},{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.4475730061531067},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.42878830432891846},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.4263409376144409},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.42028355598449707},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3754110336303711},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.3172440528869629},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3136145770549774},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.2949482202529907},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26586687564849854},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2242211401462555},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.18389028310775757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18045717477798462},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15737080574035645},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2010.5718152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2010.5718152","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1583799131","https://openalex.org/W1594802219","https://openalex.org/W1983224847","https://openalex.org/W2024303516","https://openalex.org/W2037025184","https://openalex.org/W2047090868","https://openalex.org/W2055300044","https://openalex.org/W2063445935","https://openalex.org/W2095590702","https://openalex.org/W2117588008","https://openalex.org/W2123130671","https://openalex.org/W2125256511","https://openalex.org/W2131030156","https://openalex.org/W2136064843","https://openalex.org/W2156506338","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3213472335","https://openalex.org/W4302033101","https://openalex.org/W4307347247","https://openalex.org/W6634494593","https://openalex.org/W6634528131","https://openalex.org/W6635685794","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W2800356679","https://openalex.org/W2983873455","https://openalex.org/W4234292432","https://openalex.org/W1987479130","https://openalex.org/W2964933021","https://openalex.org/W2093412621","https://openalex.org/W2896500802","https://openalex.org/W2897095542","https://openalex.org/W2025705427","https://openalex.org/W3128398222"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,73,119],"Approximate/Adaptive":[4],"Dynamic":[5],"Programming":[6],"(ADP)":[7],"algorithm":[8,68,162],"that":[9,50,65,82,181],"finds":[10],"online":[11,44,67,120,155,178],"the":[12,30,35,45,66,80,84,93,100,107,112,115,123,129,136,145,159,174,179,200,204,217],"Nash":[13,147],"equilibrium":[14],"for":[15],"two-player":[16],"nonzero-sum":[17],"differential":[18,138],"games":[19],"with":[20,53,184],"linear":[21],"dynamics":[22],"and":[23,144,191],"infinite":[24,46],"horizon":[25,47],"quadratic":[26],"cost.":[27,208],"Each":[28],"of":[29,37,57,86,114,125,128,173,188,199,206,216],"game":[31,94,139],"players":[32,175,210],"is":[33,69,163,176,220],"using":[34,96],"procedure":[36],"Integral":[38],"Reinforcement":[39],"Learning":[40],"(IRL)":[41],"to":[42,72],"calculate":[43],"value":[48,180,205],"function":[49],"it":[51],"associates":[52],"every":[54],"given":[55,186],"set":[56,85,187],"feedback":[58,146],"control":[59,148],"policies.":[60],"It":[61],"will":[62,110,150],"be":[63,151],"shown":[64],"mathematically":[70],"equivalent":[71],"offline":[74,116],"iterative":[75],"method,":[76],"previously":[77],"introduced":[78],"in":[79,135,142,222],"literature,":[81],"solves":[83],"coupled":[87],"algebraic":[88],"Riccati":[89],"equations":[90],"(ARE)":[91],"underlying":[92],"problem":[95],"complete":[97,126],"knowledge":[98,127],"on":[99,154,165],"system":[101,130],"dynamics.":[102,131],"Here":[103],"we":[104],"show":[105],"how":[106],"ADP":[108,218],"techniques":[109],"enhance":[111],"capabilities":[113],"method":[117],"allowing":[118],"solution":[121],"without":[122],"requirement":[124],"The":[132,161,209,214],"two":[133],"participants":[134],"continuous-time":[137],"are":[140,211],"competing":[141],"real-time":[143],"strategies":[149],"determined":[152],"based":[153],"measured":[156],"data":[157],"from":[158],"system.":[160],"built":[164],"interplay":[166],"between":[167],"a":[168,185,192],"learning":[169,177,212],"phase,":[170],"where":[171],"each":[172,198],"they":[182],"associate":[183],"play":[189],"policies,":[190],"policy":[193],"update":[194],"step,":[195],"performed":[196],"by":[197],"payers":[201],"towards":[202],"decreasing":[203],"their":[207],"concurrently.":[213],"feasibility":[215],"scheme":[219],"demonstrated":[221],"simulation.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}