{"id":"https://openalex.org/W1974949216","doi":"https://doi.org/10.1109/acc.2014.6859092","title":"Model-based reinforcement learning for on-line feedback-Nash equilibrium solution of N-player nonzero-sum differential games","display_name":"Model-based reinforcement learning for on-line feedback-Nash equilibrium solution of N-player nonzero-sum differential games","publication_year":2014,"publication_date":"2014-06-01","ids":{"openalex":"https://openalex.org/W1974949216","doi":"https://doi.org/10.1109/acc.2014.6859092","mag":"1974949216"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2014.6859092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2014.6859092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 American Control Conference","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071224574","display_name":"Rushikesh Kamalapurkar","orcid":"https://orcid.org/0000-0001-9963-5361"},"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":"Rushikesh Kamalapurkar","raw_affiliation_strings":["University of Florida, Gainesville, FL, US","[Dept. of Mech. & Aerosp. Eng., Univ. of Florida, Gainesville, FL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, US","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"[Dept. of Mech. & Aerosp. Eng., Univ. of Florida, Gainesville, FL, USA]","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066598060","display_name":"Justin R. Klotz","orcid":"https://orcid.org/0000-0001-8393-7488"},"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":"Justin Klotz","raw_affiliation_strings":["University of Florida, Gainesville, FL, US","[Dept. of Mech. & Aerosp. Eng., Univ. of Florida, Gainesville, FL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, US","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"[Dept. of Mech. & Aerosp. Eng., Univ. of Florida, Gainesville, FL, 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":"Warren E. Dixon","raw_affiliation_strings":["University of Florida, Gainesville, FL, US","[Dept. of Mech. & Aerosp. Eng., Univ. of Florida, Gainesville, FL, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, US","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"[Dept. of Mech. & Aerosp. Eng., Univ. of Florida, Gainesville, FL, USA]","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"49","issue":null,"first_page":"3000","last_page":"3005"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9944000244140625,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9742000102996826,"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/nash-equilibrium","display_name":"Nash equilibrium","score":0.8204714059829712},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7569437026977539},{"id":"https://openalex.org/keywords/epsilon-equilibrium","display_name":"Epsilon-equilibrium","score":0.5951693058013916},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5445715188980103},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.5318593382835388},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5316365957260132},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45156481862068176},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.4276065528392792},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.4275360703468323},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4270699918270111},{"id":"https://openalex.org/keywords/correlated-equilibrium","display_name":"Correlated equilibrium","score":0.4211660623550415},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.39367204904556274},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36415839195251465},{"id":"https://openalex.org/keywords/equilibrium-selection","display_name":"Equilibrium selection","score":0.3609234094619751},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3349418044090271},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3118683397769928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12870252132415771},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.09720566868782043}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.8204714059829712},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7569437026977539},{"id":"https://openalex.org/C141824439","wikidata":"https://www.wikidata.org/wiki/Q307521","display_name":"Epsilon-equilibrium","level":4,"score":0.5951693058013916},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5445715188980103},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.5318593382835388},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5316365957260132},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45156481862068176},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.4276065528392792},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.4275360703468323},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4270699918270111},{"id":"https://openalex.org/C163630976","wikidata":"https://www.wikidata.org/wiki/Q964667","display_name":"Correlated equilibrium","level":5,"score":0.4211660623550415},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.39367204904556274},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36415839195251465},{"id":"https://openalex.org/C164407509","wikidata":"https://www.wikidata.org/wiki/Q5384490","display_name":"Equilibrium selection","level":4,"score":0.3609234094619751},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3349418044090271},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3118683397769928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12870252132415771},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.09720566868782043},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acc.2014.6859092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2014.6859092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 American Control Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W5108103","https://openalex.org/W1576452626","https://openalex.org/W1578630563","https://openalex.org/W1581842928","https://openalex.org/W1602326725","https://openalex.org/W1606998818","https://openalex.org/W1914756871","https://openalex.org/W1973039793","https://openalex.org/W1979772489","https://openalex.org/W2019338681","https://openalex.org/W2021161853","https://openalex.org/W2046888764","https://openalex.org/W2052369206","https://openalex.org/W2062697270","https://openalex.org/W2067603665","https://openalex.org/W2084063650","https://openalex.org/W2100276679","https://openalex.org/W2102933137","https://openalex.org/W2104843094","https://openalex.org/W2117588008","https://openalex.org/W2121863487","https://openalex.org/W2160698719","https://openalex.org/W2330024298","https://openalex.org/W2888914392","https://openalex.org/W3150098721","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4234761190","https://openalex.org/W6600197225","https://openalex.org/W6677331018"],"related_works":["https://openalex.org/W2013767790","https://openalex.org/W4315489088","https://openalex.org/W4301347782","https://openalex.org/W4299551322","https://openalex.org/W1853631319","https://openalex.org/W4365460918","https://openalex.org/W2038156579","https://openalex.org/W2153002690","https://openalex.org/W2797291350","https://openalex.org/W1498818016"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,16,52],"concurrent":[4],"learning-based":[5],"actor-critic-identifier":[6],"architecture":[7],"to":[8,15,42,60],"obtain":[9],"an":[10],"approximate":[11],"feedback-Nash":[12,46],"equilibrium":[13,47],"solution":[14],"deterministic,":[17],"continuous-time,":[18],"and":[19],"infinite-horizon":[20],"N-player":[21],"nonzero-sum":[22],"differential":[23],"game":[24],"on-line,":[25],"without":[26],"requiring":[27],"persistence":[28],"of":[29,37,44,64],"excitation":[30],"(PE),":[31],"for":[32],"non-linear":[33],"control-affine":[34],"systems.":[35],"Convergence":[36],"the":[38,45,62,65],"developed":[39,66],"control":[40],"policies":[41,48],"neighborhoods":[43],"is":[49],"established":[50],"under":[51],"sufficient":[53],"rank":[54],"condition.":[55],"Simulation":[56],"results":[57],"are":[58],"presented":[59],"demonstrate":[61],"performance":[63],"technique.":[67]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}