{"id":"https://openalex.org/W2997987223","doi":"https://doi.org/10.1109/anzcc47194.2019.8945719","title":"Distributed Nonlinear Model Predictive Control and Reinforcement Learning","display_name":"Distributed Nonlinear Model Predictive Control and Reinforcement Learning","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2997987223","doi":"https://doi.org/10.1109/anzcc47194.2019.8945719","mag":"2997987223"},"language":"en","primary_location":{"id":"doi:10.1109/anzcc47194.2019.8945719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/anzcc47194.2019.8945719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Australian & New Zealand Control Conference (ANZCC)","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/A5110803897","display_name":"Ifrah Saeed","orcid":"https://orcid.org/0000-0002-0556-1080"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]},{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU","PK"],"is_corresponding":false,"raw_author_name":"Ifrah Saeed","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Melbourne, Australia, University of Engineering and Technology, Lahore, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Melbourne, Australia, University of Engineering and Technology, Lahore, Pakistan","institution_ids":["https://openalex.org/I142732210","https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060997326","display_name":"Tansu Alpcan","orcid":"https://orcid.org/0000-0002-7434-3239"},"institutions":[{"id":"https://openalex.org/I142732210","display_name":"University of Engineering and Technology Lahore","ror":"https://ror.org/0051w2v06","country_code":"PK","type":"education","lineage":["https://openalex.org/I142732210"]},{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU","PK"],"is_corresponding":false,"raw_author_name":"Tansu Alpcan","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, University of Melbourne, Australia, University of Engineering and Technology, Lahore, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Melbourne, Australia, University of Engineering and Technology, Lahore, Pakistan","institution_ids":["https://openalex.org/I142732210","https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070030398","display_name":"Sarah Erfani","orcid":"https://orcid.org/0000-0003-0885-0643"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sarah M. Erfani","raw_affiliation_strings":["School of Computing and Information Systems, University of Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076294504","display_name":"Mustafa Berkay Y\u0131lmaz","orcid":"https://orcid.org/0000-0003-0320-3957"},"institutions":[{"id":"https://openalex.org/I197907453","display_name":"Akdeniz University","ror":"https://ror.org/01m59r132","country_code":"TR","type":"education","lineage":["https://openalex.org/I197907453"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"M. Berkay Yilmaz","raw_affiliation_strings":["Department of Computer Engineering, Akdeniz University, Antalya, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Akdeniz University, Antalya, Turkey","institution_ids":["https://openalex.org/I197907453"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9969000220298767,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9969000220298767,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9919000267982483,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9754999876022339,"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":0.8193095922470093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7673471570014954},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.7366624474525452},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.521430253982544},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.512537956237793},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4868566393852234},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.4523119628429413},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4417263865470886},{"id":"https://openalex.org/keywords/nonlinear-model","display_name":"Nonlinear model","score":0.43889251351356506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4171265661716461},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.36006417870521545},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2757568955421448},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10740262269973755}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8193095922470093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7673471570014954},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.7366624474525452},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.521430253982544},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.512537956237793},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4868566393852234},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.4523119628429413},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4417263865470886},{"id":"https://openalex.org/C2984755018","wikidata":"https://www.wikidata.org/wiki/Q17118374","display_name":"Nonlinear model","level":3,"score":0.43889251351356506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4171265661716461},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.36006417870521545},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2757568955421448},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10740262269973755},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/anzcc47194.2019.8945719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/anzcc47194.2019.8945719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Australian & New Zealand Control Conference (ANZCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1498097330","https://openalex.org/W1631623342","https://openalex.org/W2066425650","https://openalex.org/W2121863487","https://openalex.org/W2145339207","https://openalex.org/W2592001929","https://openalex.org/W2761873684","https://openalex.org/W2964043796","https://openalex.org/W2964291307","https://openalex.org/W3037207827","https://openalex.org/W4292078458","https://openalex.org/W6692846177"],"related_works":["https://openalex.org/W1631623342","https://openalex.org/W1779399219","https://openalex.org/W648378158","https://openalex.org/W3083517787","https://openalex.org/W1839440842","https://openalex.org/W4251946813","https://openalex.org/W2885820669","https://openalex.org/W1981727740","https://openalex.org/W2368407738","https://openalex.org/W2143511391"],"abstract_inverted_index":{"Coordinating":[0],"two":[1,87],"or":[2,10],"more":[3],"dynamic":[4],"systems":[5,91],"such":[6,44],"as":[7,45],"autonomous":[8],"vehicles":[9],"satellites":[11],"in":[12,39],"a":[13,117,131,165],"distributed":[14,75],"manner":[15],"poses":[16],"an":[17],"important":[18],"research":[19],"challenge.":[20],"Multiple":[21],"approaches":[22],"to":[23,53,136,148,174],"this":[24],"problem":[25,82],"have":[26,147],"been":[27],"proposed":[28],"including":[29],"Nonlinear":[30],"Model":[31],"Predictive":[32],"Control":[33],"(NMPC)":[34],"and":[35,55,85,100,108],"its":[36,150],"model-free":[37,70],"counterparts":[38],"reinforcement":[40],"learning":[41],"(RL)":[42],"literature":[43],"Deep":[46],"QNetwork":[47],"(DQN).":[48],"This":[49,161],"initial":[50],"study":[51],"aims":[52],"compare":[54],"contrast":[56],"the":[57,63,68,80,153],"optimal":[58,154],"control":[59],"technique,":[60],"NMPC,":[61],"where":[62],"model":[64,107],"is":[65,142],"known,":[66],"with":[67],"popular":[69],"RL":[71],"method,":[72],"DQN.":[73],"Simple":[74],"variants":[76],"of":[77,83,133],"these":[78],"for":[79,167],"specific":[81],"balancing":[84],"synchronising":[86],"highly":[88],"unstable":[89],"cart-pole":[90],"are":[92],"investigated":[93],"numerically.":[94],"We":[95],"found":[96],"that":[97],"both":[98],"NMPC":[99,113],"trained":[101,138],"DQN":[102,120,129],"work":[103],"optimally":[104],"under":[105,116],"ideal":[106],"small":[109],"communication":[110],"delays.":[111],"While":[112],"performs":[114],"sub-optimally":[115],"model-mismatch":[118],"scenario,":[119],"performance":[121],"naturally":[122],"does":[123,145],"not":[124,146],"suffer":[125],"from":[126],"this.":[127],"Distributed":[128],"needs":[130],"lot":[132],"realworld":[134],"experience":[135],"be":[137,172],"but":[139],"once":[140],"it":[141,144],"trained,":[143],"spend":[149],"time":[151],"finding":[152],"action":[155],"at":[156],"every":[157],"time-step":[158],"like":[159],"NMPC.":[160],"illustrative":[162],"comparison":[163],"lays":[164],"foundation":[166],"hybrid":[168],"approaches,":[169],"which":[170],"can":[171],"applied":[173],"complex":[175],"multi-agent":[176],"scenarios.":[177]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}