{"id":"https://openalex.org/W4392905255","doi":"https://doi.org/10.1109/acit58888.2023.10453794","title":"Reinforcement Learning for Nash Noncoperative and Pareto Cooperative Optimal Linear Systems","display_name":"Reinforcement Learning for Nash Noncoperative and Pareto Cooperative Optimal Linear Systems","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4392905255","doi":"https://doi.org/10.1109/acit58888.2023.10453794"},"language":"en","primary_location":{"id":"doi:10.1109/acit58888.2023.10453794","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/acit58888.2023.10453794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 24th International Arab Conference on Information Technology (ACIT)","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/A5031375377","display_name":"Zoran Gaji\u0107","orcid":"https://orcid.org/0000-0002-0187-6181"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zoran Gajic","raw_affiliation_strings":["Rutgers University,Department of Electrical and Computer Engineering,Piscataway,USA","Department of Electrical and Computer Engineering, Rutgers University, Piscataway, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,Department of Electrical and Computer Engineering,Piscataway,USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rutgers University, Piscataway, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041127915","display_name":"Zulfiqar Ali Memon","orcid":"https://orcid.org/0000-0001-7403-7576"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zulfiqar Memon","raw_affiliation_strings":["Rutgers University,Department of Electrical and Computer Engineering,Piscataway,USA","Department of Electrical and Computer Engineering, Rutgers University, Piscataway, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,Department of Electrical and Computer Engineering,Piscataway,USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rutgers University, Piscataway, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081615294","display_name":"Ahmed Bilal Awan","orcid":"https://orcid.org/0000-0002-5373-2999"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmed Bilal Awan","raw_affiliation_strings":["Rutgers University,Department of Electrical and Computer Engineering,Piscataway,USA","Department of Electrical and Computer Engineering, Rutgers University, Piscataway, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University,Department of Electrical and Computer Engineering,Piscataway,USA","institution_ids":["https://openalex.org/I102322142"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Rutgers University, Piscataway, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27577714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"38","issue":null,"first_page":"1","last_page":"6"},"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":0.9805999994277954,"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":0.9631999731063843,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7964064478874207},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6662453413009644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6097148060798645},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.5476686954498291},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5392142534255981},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.5200961828231812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2673276662826538},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.2619919776916504},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21709606051445007}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7964064478874207},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6662453413009644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6097148060798645},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.5476686954498291},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5392142534255981},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.5200961828231812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2673276662826538},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.2619919776916504},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21709606051445007}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acit58888.2023.10453794","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/acit58888.2023.10453794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 24th International Arab Conference on Information Technology (ACIT)","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":19,"referenced_works":["https://openalex.org/W1519369336","https://openalex.org/W1533225923","https://openalex.org/W1578630563","https://openalex.org/W1583799131","https://openalex.org/W1793264465","https://openalex.org/W2019338681","https://openalex.org/W2073499686","https://openalex.org/W2102933137","https://openalex.org/W2120421730","https://openalex.org/W2165726932","https://openalex.org/W2214884926","https://openalex.org/W2380269368","https://openalex.org/W2579592432","https://openalex.org/W2772589676","https://openalex.org/W2792150900","https://openalex.org/W2936756261","https://openalex.org/W3006882295","https://openalex.org/W3105688066","https://openalex.org/W3134387361"],"related_works":["https://openalex.org/W1963790170","https://openalex.org/W2073298047","https://openalex.org/W2033790662","https://openalex.org/W2586328217","https://openalex.org/W2049264236","https://openalex.org/W2080708212","https://openalex.org/W2337862504","https://openalex.org/W2043126582","https://openalex.org/W317165722","https://openalex.org/W2728870795"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"use":[4],"the":[5,58,67,75],"reinforcement":[6,40],"learning":[7,41,87],"techniques":[8],"for":[9,90],"optimal":[10,37,60,88],"control":[11,38],"of":[12,42,93,103],"linear-quadratic":[13],"systems,":[14],"and":[15,24,39,51,78],"consider":[16],"two":[17],"situations:":[18],"when":[19,25],"controllers":[20,89],"cooperate":[21,29],"(Pareto":[22],"strategies)":[23],"they":[26],"do":[27],"not":[28],"(Nash":[30],"strategies).":[31],"These":[32],"situations":[33],"are":[34,71,98],"encountered":[35],"in":[36,47,52,86],"several":[43],"engineering":[44],"systems":[45],"(especially":[46],"energy":[48],"systems),":[49],"economics,":[50],"general":[53],"machine":[54],"learning.":[55],"We":[56],"compare":[57],"corresponding":[59],"costs":[61],"using":[62],"normalized":[63],"data":[64],"assuming":[65],"that":[66],"system":[68],"initial":[69],"conditions":[70],"uniformly":[72],"distributed":[73],"on":[74,100],"unit":[76],"sphere,":[77],"provide":[79],"an":[80,101,104],"estimate":[81],"how":[82],"much":[83],"cooperation":[84],"helps":[85],"these":[91],"kind":[92],"problems.":[94],"The":[95],"theoretical":[96],"results":[97],"demonstrated":[99],"example":[102],"electric":[105],"power":[106],"system.":[107]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
