{"id":"https://openalex.org/W3184076597","doi":"https://doi.org/10.23919/acc50511.2021.9483047","title":"Cooperative Model-Based Reinforcement Learning for Approximate Optimal Tracking","display_name":"Cooperative Model-Based Reinforcement Learning for Approximate Optimal Tracking","publication_year":2021,"publication_date":"2021-05-25","ids":{"openalex":"https://openalex.org/W3184076597","doi":"https://doi.org/10.23919/acc50511.2021.9483047","mag":"3184076597"},"language":"en","primary_location":{"id":"doi:10.23919/acc50511.2021.9483047","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","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/A5027840499","display_name":"Max L. Greene","orcid":"https://orcid.org/0000-0003-2733-0344"},"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":"Max L. Greene","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017779570","display_name":"Zachary I. Bell","orcid":"https://orcid.org/0000-0002-9574-8104"},"institutions":[{"id":"https://openalex.org/I2801461044","display_name":"Eglin Air Force Base","ror":"https://ror.org/002c7zk35","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796","https://openalex.org/I2801461044","https://openalex.org/I4210089612","https://openalex.org/I4210102105"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary I. Bell","raw_affiliation_strings":["Munitions Directorate, Air Force Research Laboratory, Eglin AFB, FL, USA"],"affiliations":[{"raw_affiliation_string":"Munitions Directorate, Air Force Research Laboratory, Eglin AFB, FL, USA","institution_ids":["https://openalex.org/I2801461044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045042598","display_name":"Scott Nivison","orcid":"https://orcid.org/0000-0002-5738-2535"},"institutions":[{"id":"https://openalex.org/I2801461044","display_name":"Eglin Air Force Base","ror":"https://ror.org/002c7zk35","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796","https://openalex.org/I2801461044","https://openalex.org/I4210089612","https://openalex.org/I4210102105"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Scott A. Nivison","raw_affiliation_strings":["Munitions Directorate, Air Force Research Laboratory, Eglin AFB, FL, USA"],"affiliations":[{"raw_affiliation_string":"Munitions Directorate, Air Force Research Laboratory, Eglin AFB, FL, USA","institution_ids":["https://openalex.org/I2801461044"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011665886","display_name":"Jonathan P. How","orcid":"https://orcid.org/0000-0001-8576-1930"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]},{"id":"https://openalex.org/I46020346","display_name":"American Institute of Aeronautics and Astronautics","ror":"https://ror.org/00a1rzv11","country_code":"US","type":"other","lineage":["https://openalex.org/I46020346"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan P. How","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I46020346","https://openalex.org/I63966007"]}]},{"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":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027840499"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.1515,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51700254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1973","last_page":"1978"},"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":0.9843000173568726,"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":0.958899974822998,"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":0.7994619607925415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6737501621246338},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5906763672828674},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5647715926170349},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5408421754837036},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5407784581184387},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5123785734176636},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.49469491839408875},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.4757927656173706},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4722672700881958},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4660433828830719},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.4402020573616028},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43403488397598267},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4283342957496643},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24561139941215515},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.20363885164260864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19467473030090332},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13984018564224243},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.08099931478500366}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7994619607925415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6737501621246338},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5906763672828674},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5647715926170349},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5408421754837036},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5407784581184387},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5123785734176636},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.49469491839408875},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.4757927656173706},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4722672700881958},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4660433828830719},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4402020573616028},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43403488397598267},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4283342957496643},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24561139941215515},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.20363885164260864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19467473030090332},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13984018564224243},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.08099931478500366},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc50511.2021.9483047","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9483047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.46000000834465027,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G28741391","display_name":null,"funder_award_id":"FA9550-18-1-0109","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4297280941","display_name":null,"funder_award_id":"N00014-13-1-0151","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6191118875","display_name":null,"funder_award_id":"FA9550-19-1-0169","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W44157068","https://openalex.org/W560518094","https://openalex.org/W1483858097","https://openalex.org/W1540245649","https://openalex.org/W1574514837","https://openalex.org/W1578936488","https://openalex.org/W1592648094","https://openalex.org/W1977237536","https://openalex.org/W1977671496","https://openalex.org/W1983523797","https://openalex.org/W2048687352","https://openalex.org/W2086975818","https://openalex.org/W2097253853","https://openalex.org/W2098432798","https://openalex.org/W2104843094","https://openalex.org/W2109987654","https://openalex.org/W2111034649","https://openalex.org/W2116479681","https://openalex.org/W2121863487","https://openalex.org/W2162999890","https://openalex.org/W2620645529","https://openalex.org/W2790688051","https://openalex.org/W2800330509","https://openalex.org/W2887138972","https://openalex.org/W2962814013","https://openalex.org/W3003498399","https://openalex.org/W3009484445","https://openalex.org/W3016201194","https://openalex.org/W3098486933","https://openalex.org/W3132069826","https://openalex.org/W4214717370","https://openalex.org/W4238000550","https://openalex.org/W4301747304","https://openalex.org/W6774209130"],"related_works":["https://openalex.org/W4320719302","https://openalex.org/W1892002403","https://openalex.org/W4309005041","https://openalex.org/W2962746246","https://openalex.org/W1989531755","https://openalex.org/W1967384683","https://openalex.org/W2892237068","https://openalex.org/W1901119619","https://openalex.org/W4283708569","https://openalex.org/W3153646294"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"an":[3],"approximate":[4,77],"online":[5],"adaptive":[6],"solution":[7,78],"to":[8,79,116,136,146],"the":[9,34,39,52,76,80,87,90,95,105,118,122,137,143,147,150],"infinite-horizon":[10,81],"optimal":[11,82,151],"tracking":[12,24,83,131],"problem":[13,84],"for":[14,75],"a":[15,69,108,125,156],"set":[16],"of":[17,41,132,142,149],"agents":[18,106,123],"with":[19,68,89,99],"homogeneous":[20],"dynamics":[21],"and":[22,44,59,64,85,107,124,140],"common":[23],"objectives.":[25],"Model-based":[26],"reinforcement":[27],"learning":[28],"is":[29,102,114,153],"implemented":[30],"by":[31],"simultaneously":[32],"evaluating":[33],"Bellman":[35],"error":[36],"(BE)":[37],"at":[38],"state":[40,53,135,139],"each":[42,133],"agent":[43,56],"on":[45,63],"nearby":[46],"off-trajectory":[47,65],"points,":[48],"as":[49],"needed,":[50],"throughout":[51],"space.":[54],"Each":[55],"will":[57],"calculate":[58],"share":[60,117],"their":[61],"respective":[62],"BE":[66,100],"information":[67],"centralized":[70,109,126],"estimator,":[71],"which":[72],"computes":[73],"updates":[74],"shares":[86],"estimate":[88],"agents.":[91],"In":[92],"doing":[93],"so,":[94],"computational":[96,119],"burden":[97],"associated":[98],"extrapolation":[101],"shared":[103],"between":[104,121],"updating":[110],"resource.":[111,127],"Edge":[112],"computing":[113],"leveraged":[115],"load":[120],"Uniformly":[128],"ultimately":[129],"bounded":[130],"agent's":[134],"desired":[138],"convergence":[141],"control":[144],"policy":[145,152],"neighborhood":[148],"proven":[154],"via":[155],"Lyapunov-like":[157],"stability":[158],"analysis.":[159]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}