{"id":"https://openalex.org/W2046888764","doi":"https://doi.org/10.1109/cdc.2011.6160778","title":"Nonlinear two-player zero-sum game approximate solution using a Policy Iteration algorithm","display_name":"Nonlinear two-player zero-sum game approximate solution using a Policy Iteration algorithm","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W2046888764","doi":"https://doi.org/10.1109/cdc.2011.6160778","mag":"2046888764"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2011.6160778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2011.6160778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Conference on Decision and Control and European Control Conference","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/A5110418596","display_name":"M. Johnson","orcid":null},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"M. Johnson","raw_affiliation_strings":["Department of Mechanical and AeroSpace Engineering, University of Florida, Gainesville, FL, USA","Department of Mechanical And Aerospace Engineering, University of Florida, Gainesville, 32611, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and AeroSpace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"Department of Mechanical And Aerospace Engineering, University of Florida, Gainesville, 32611, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034219830","display_name":"Shubhendu Bhasin","orcid":"https://orcid.org/0000-0002-8002-9684"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Bhasin","raw_affiliation_strings":["Department of Mechanical and AeroSpace Engineering, University of Florida, Gainesville, FL, USA","Department of Mechanical And Aerospace Engineering, University of Florida, Gainesville, 32611, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and AeroSpace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"Department of Mechanical And Aerospace Engineering, University of Florida, Gainesville, 32611, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032651215","display_name":"Warren E. Dixon","orcid":"https://orcid.org/0000-0002-5091-181X"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. E. Dixon","raw_affiliation_strings":["Department of Mechanical and AeroSpace Engineering, University of Florida, Gainesville, FL, USA","Department of Mechanical And Aerospace Engineering, University of Florida, Gainesville, 32611, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and AeroSpace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"Department of Mechanical And Aerospace Engineering, University of Florida, Gainesville, 32611, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110418596"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":4.3937,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.94793502,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"147"},"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":0.9896000027656555,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/nonlinear-system","display_name":"Nonlinear system","score":0.5545058250427246},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5441691279411316},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5290759205818176},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5260317921638489},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5161662697792053},{"id":"https://openalex.org/keywords/saddle-point","display_name":"Saddle point","score":0.5118541121482849},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5064796209335327},{"id":"https://openalex.org/keywords/identifier","display_name":"Identifier","score":0.5021412372589111},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49310800433158875},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4905042052268982},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4447929859161377},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.44065800309181213},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43785449862480164},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.42869603633880615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.39158427715301514},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3810339868068695},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3758637309074402},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15088927745819092},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.14721888303756714}],"concepts":[{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5545058250427246},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5441691279411316},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5290759205818176},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5260317921638489},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5161662697792053},{"id":"https://openalex.org/C2681867","wikidata":"https://www.wikidata.org/wiki/Q690935","display_name":"Saddle point","level":2,"score":0.5118541121482849},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5064796209335327},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5021412372589111},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49310800433158875},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4905042052268982},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4447929859161377},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.44065800309181213},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43785449862480164},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.42869603633880615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.39158427715301514},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3810339868068695},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3758637309074402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15088927745819092},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.14721888303756714},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/cdc.2011.6160778","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2011.6160778","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Conference on Decision and Control and European Control Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W567213340","https://openalex.org/W1483858097","https://openalex.org/W1487127700","https://openalex.org/W1574514837","https://openalex.org/W1576452626","https://openalex.org/W1578630563","https://openalex.org/W1581842928","https://openalex.org/W1602326725","https://openalex.org/W1749408314","https://openalex.org/W1990005421","https://openalex.org/W2005437559","https://openalex.org/W2013184330","https://openalex.org/W2016360498","https://openalex.org/W2047090868","https://openalex.org/W2081514674","https://openalex.org/W2091565802","https://openalex.org/W2093831009","https://openalex.org/W2098301654","https://openalex.org/W2100677568","https://openalex.org/W2103496339","https://openalex.org/W2104017958","https://openalex.org/W2107674817","https://openalex.org/W2108286682","https://openalex.org/W2108794258","https://openalex.org/W2109640889","https://openalex.org/W2111034649","https://openalex.org/W2112103082","https://openalex.org/W2112246162","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2136064843","https://openalex.org/W2136909257","https://openalex.org/W2160561608","https://openalex.org/W2162845328","https://openalex.org/W2177721432","https://openalex.org/W2498694880","https://openalex.org/W2798534591","https://openalex.org/W3041202696","https://openalex.org/W3213472335","https://openalex.org/W4214717370","https://openalex.org/W4237810884","https://openalex.org/W4241521318","https://openalex.org/W4285719527","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W1859185863","https://openalex.org/W2978731891","https://openalex.org/W4285537323","https://openalex.org/W2964126589","https://openalex.org/W1932159282","https://openalex.org/W4307691181","https://openalex.org/W3016225735","https://openalex.org/W3022588902","https://openalex.org/W1518875602","https://openalex.org/W2017412075"],"abstract_inverted_index":{"An":[0],"approximate":[1,59],"online":[2],"solution":[3],"is":[4,28,44,56,85],"developed":[5],"for":[6,67],"a":[7,38,53,74,79],"two-player":[8],"zero-sum":[9],"game":[10],"subject":[11],"to":[12,30,46,58],"continuous-time":[13],"nonlinear":[14],"uncertain":[15,50],"dynamics":[16],"and":[17,52,100,115,119,133,141],"an":[18],"infinite":[19],"horizon":[20],"quadratic":[21],"cost.":[22],"A":[23],"novel":[24],"actor-critic-identifier":[25],"(ACI)":[26],"structure":[27],"used":[29,45,57],"implement":[31],"the":[32,49,60,68,88,96,101,112,116,127],"Policy":[33],"Iteration":[34],"(PI)":[35],"algorithm,":[36],"wherein":[37],"robust":[39],"dynamic":[40],"neural":[41],"network":[42],"(DNN)":[43],"asymptotically":[47],"identify":[48],"system,":[51],"critic":[54,69,113,132],"NN":[55,70,114],"value":[61,98],"function.":[62],"The":[63,130],"weight":[64],"update":[65],"laws":[66],"are":[71,109,136],"generated":[72],"using":[73,111],"gradient-descent":[75],"method":[76,92],"based":[77],"on":[78],"modified":[80],"temporal":[81],"difference":[82],"error,":[83],"which":[84],"independent":[86],"of":[87,95,126],"system":[89],"dynamics.":[90],"This":[91],"finds":[93],"approximations":[94],"optimal":[97],"function,":[99],"saddle":[102],"point":[103],"feedback":[104],"control":[105],"policies.":[106],"These":[107],"policies":[108],"computed":[110],"identifier":[117,134],"DNN":[118],"guarantee":[120],"uniformly":[121],"ultimately":[122],"bounded":[123],"(UUB)":[124],"stability":[125],"closed-loop":[128],"system.":[129],"actor,":[131],"structures":[135],"implemented":[137],"in":[138],"real-time,":[139],"continuously":[140],"simultaneously.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}