{"id":"https://openalex.org/W2125755055","doi":"https://doi.org/10.1109/ijcnn.2010.5596754","title":"Adaptive Dynamic Programming algorithm for finding online the equilibrium solution of the two-player zero-sum differential game","display_name":"Adaptive Dynamic Programming algorithm for finding online the equilibrium solution of the two-player zero-sum differential game","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2125755055","doi":"https://doi.org/10.1109/ijcnn.2010.5596754","mag":"2125755055"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2010.5596754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2010.5596754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2010 International Joint Conference on Neural Networks (IJCNN)","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/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]},{"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","Automation and Robotics Research Institute, University of Texas at Arlington, 7300 Jack Newell Blvd. S. Fort Worth, 76118 USA"],"affiliations":[{"raw_affiliation_string":"Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I4210116723"]},{"raw_affiliation_string":"Automation and Robotics Research Institute, University of Texas at Arlington, 7300 Jack Newell Blvd. S. Fort Worth, 76118 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":[{"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"]},{"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 Lewis","raw_affiliation_strings":["Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA","Automation and Robotics Research Institute, University of Texas at Arlington, 7300 Jack Newell Blvd. S. Fort Worth, 76118 USA"],"affiliations":[{"raw_affiliation_string":"Automation and Robotics Research Institute, University of Texas, Arlington, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I4210116723"]},{"raw_affiliation_string":"Automation and Robotics Research Institute, University of Texas at Arlington, 7300 Jack Newell Blvd. S. Fort Worth, 76118 USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047724723"],"corresponding_institution_ids":["https://openalex.org/I189196454","https://openalex.org/I4210116723"],"apc_list":null,"apc_paid":null,"fwci":2.6762,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.90148641,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9904999732971191,"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/T12277","display_name":"Frequency Control in Power Systems","score":0.9819999933242798,"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/dynamic-programming","display_name":"Dynamic programming","score":0.677428126335144},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6689556837081909},{"id":"https://openalex.org/keywords/differential-dynamic-programming","display_name":"Differential dynamic programming","score":0.6456208229064941},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.6092692017555237},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.603649377822876},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5907307863235474},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5877679586410522},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5774681568145752},{"id":"https://openalex.org/keywords/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.572685182094574},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.5271841287612915},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.5260857343673706},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5094812512397766},{"id":"https://openalex.org/keywords/differential-game","display_name":"Differential game","score":0.507318913936615},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4662111699581146},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.42111143469810486},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.39367911219596863},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.36648499965667725},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.33662062883377075},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32170259952545166},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3153609037399292},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.2448306679725647},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20379233360290527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11948588490486145},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.08616399765014648}],"concepts":[{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.677428126335144},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6689556837081909},{"id":"https://openalex.org/C92292787","wikidata":"https://www.wikidata.org/wiki/Q5275342","display_name":"Differential dynamic programming","level":3,"score":0.6456208229064941},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.6092692017555237},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.603649377822876},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5907307863235474},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5877679586410522},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5774681568145752},{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.572685182094574},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5271841287612915},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.5260857343673706},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5094812512397766},{"id":"https://openalex.org/C2779006483","wikidata":"https://www.wikidata.org/wiki/Q1973196","display_name":"Differential game","level":2,"score":0.507318913936615},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4662111699581146},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.42111143469810486},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.39367911219596863},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.36648499965667725},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.33662062883377075},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32170259952545166},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3153609037399292},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.2448306679725647},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20379233360290527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11948588490486145},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.08616399765014648},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2010.5596754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2010.5596754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2010 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W651734400","https://openalex.org/W802531997","https://openalex.org/W1578630563","https://openalex.org/W1979772489","https://openalex.org/W1990401127","https://openalex.org/W2024303516","https://openalex.org/W2042106612","https://openalex.org/W2063358594","https://openalex.org/W2092783757","https://openalex.org/W2095590702","https://openalex.org/W2109640889","https://openalex.org/W2116479681","https://openalex.org/W2117588008","https://openalex.org/W2134582887","https://openalex.org/W2158776408","https://openalex.org/W2498694880","https://openalex.org/W2798534591"],"related_works":["https://openalex.org/W640273602","https://openalex.org/W2800356679","https://openalex.org/W1987479130","https://openalex.org/W2964933021","https://openalex.org/W2983873455","https://openalex.org/W2884690177","https://openalex.org/W2896500802","https://openalex.org/W2043688128","https://openalex.org/W2088246243","https://openalex.org/W2575378351"],"abstract_inverted_index":{"This":[0],"paper":[1],"will":[2,70,101,124,186,202,237],"present":[3],"an":[4,36,79,240],"Approximate/Adaptive":[5],"Dynamic":[6],"Programming":[7],"(ADP)":[8],"algorithm":[9,32,143],"for":[10,17,48,189,192],"determining":[11],"online":[12,80,129,205],"the":[13,18,44,50,60,67,72,75,83,89,95,105,120,133,154,172,183,216,232,243],"Nash":[14],"equilibrium":[15,121],"solution":[16,81,122],"two-player":[19],"zero-sum":[20],"differential":[21],"game":[22,52,61],"with":[23],"linear":[24],"dynamics":[25],"and":[26,110,119,165],"infinite":[27],"horizon":[28],"quadratic":[29],"cost.":[30],"The":[31,135,142,180,199,213,227],"is":[33,58,144,157,175,219,229],"built":[34,145],"around":[35],"iterative":[37],"method":[38,77],"that":[39,57,156,174,236],"has":[40],"been":[41],"developed":[42],"in":[43,94,116,159,221,239],"control":[45,98,200,234],"engineering":[46],"community":[47],"solving":[49],"continuous-time":[51,208],"algebraic":[53],"Riccati":[54],"equation":[55],"(CT-GARE)":[56],"underlying":[59],"problem.":[62],"We":[63],"here":[64],"show":[65],"how":[66],"ADP":[68,217],"techniques":[69],"enhance":[71],"capabilities":[73],"of":[74,85,88,97,182,215],"offline":[76],"allowing":[78],"without":[82],"requirement":[84],"complete":[86],"knowledge":[87],"system":[90],"dynamics.":[91],"While":[92],"working":[93],"framework":[96],"applications":[99],"we":[100],"be":[102,125,203],"referring":[103],"to":[104,161,230],"two":[106,136],"players":[107,113,137],"as":[108],"controller":[109,155,197],"disturbance.":[111,246],"Both":[112],"are":[114,138],"competing":[115],"real":[117],"time":[118],"policies":[123],"determined":[126],"based":[127],"on":[128,146,223],"measured":[130],"data":[131],"from":[132],"system.":[134,226],"not":[139],"learning":[140,150,158],"concurrently.":[141],"interplay":[147],"between":[148],"a":[149,166,207,224],"phase,":[151],"performed":[152,170],"by":[153,171],"order":[160],"optimize":[162],"its":[163,177],"behavior,":[164],"policy":[167,185,201,235],"update":[168,181],"step,":[169],"disturbance":[173,184],"increasing":[176],"detrimental":[178],"effect.":[179],"give":[187],"way":[188],"further":[190],"improvement":[191],"the,":[193],"no":[194],"longer":[195],"optimal,":[196],"policy.":[198],"learned":[204],"using":[206],"heuristic":[209],"dynamic":[210],"programming":[211],"procedure.":[212],"feasibility":[214],"scheme":[218],"demonstrated":[220],"simulation":[222],"power":[225],"goal":[228],"determine":[231],"best":[233],"face":[238],"optimal":[241],"manner":[242],"highest":[244],"load":[245]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}