{"id":"https://openalex.org/W2913981879","doi":"https://doi.org/10.1109/cdc.2018.8619022","title":"On Model-Free Reinforcement Learning of Reduced-Order Optimal Control for Singularly Perturbed Systems","display_name":"On Model-Free Reinforcement Learning of Reduced-Order Optimal Control for Singularly Perturbed Systems","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913981879","doi":"https://doi.org/10.1109/cdc.2018.8619022","mag":"2913981879"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2018.8619022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2018.8619022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Decision and Control (CDC)","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/A5101731714","display_name":"Sayak Mukherjee","orcid":"https://orcid.org/0000-0001-8184-4755"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sayak Mukherjee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040513070","display_name":"He Bai","orcid":"https://orcid.org/0000-0002-4247-0698"},"institutions":[{"id":"https://openalex.org/I4210131712","display_name":"Oklahoma State University Oklahoma City","ror":"https://ror.org/03y1zyv86","country_code":"US","type":"education","lineage":["https://openalex.org/I4210131712"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Bai","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, OK, USA"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, OK, USA","institution_ids":["https://openalex.org/I4210131712"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055360778","display_name":"Aranya Chakrabortty","orcid":"https://orcid.org/0000-0002-3474-8215"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aranya Chakrabortty","raw_affiliation_strings":["Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101731714"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":6.8658,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97596976,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5288","last_page":"5293"},"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/T12277","display_name":"Frequency Control in Power Systems","score":0.9484999775886536,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.8230865001678467},{"id":"https://openalex.org/keywords/singular-perturbation","display_name":"Singular perturbation","score":0.7427124977111816},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6335747838020325},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5387616157531738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5358703136444092},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.524630606174469},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.5136250853538513},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.49642521142959595},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.4937354028224945},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4846068322658539},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.432143896818161},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.42457345128059387},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3741350769996643},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2676064372062683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1743311882019043}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8230865001678467},{"id":"https://openalex.org/C165160513","wikidata":"https://www.wikidata.org/wiki/Q7524249","display_name":"Singular perturbation","level":2,"score":0.7427124977111816},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6335747838020325},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5387616157531738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5358703136444092},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.524630606174469},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.5136250853538513},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.49642521142959595},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.4937354028224945},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4846068322658539},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.432143896818161},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.42457345128059387},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3741350769996643},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2676064372062683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1743311882019043},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2018.8619022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2018.8619022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Conference on Decision and Control (CDC)","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":17,"referenced_works":["https://openalex.org/W601351931","https://openalex.org/W1481652330","https://openalex.org/W1515224583","https://openalex.org/W2024303516","https://openalex.org/W2030205386","https://openalex.org/W2037025184","https://openalex.org/W2062361291","https://openalex.org/W2121764658","https://openalex.org/W2121863487","https://openalex.org/W2148437632","https://openalex.org/W2148439597","https://openalex.org/W2487144912","https://openalex.org/W2501280881","https://openalex.org/W2564717627","https://openalex.org/W2772589676","https://openalex.org/W4214717370","https://openalex.org/W4301886962"],"related_works":["https://openalex.org/W1932159282","https://openalex.org/W4285537323","https://openalex.org/W2379312070","https://openalex.org/W2136173754","https://openalex.org/W2110050003","https://openalex.org/W2953025626","https://openalex.org/W2499081552","https://openalex.org/W2366053282","https://openalex.org/W2128788708","https://openalex.org/W2097061373"],"abstract_inverted_index":{"We":[0,53,100,120],"propose":[1,54],"a":[2,44,50,55,74,131],"model-free":[3],"reduced-order":[4,75],"optimal":[5,77],"control":[6,92],"design":[7],"for":[8,89],"linear":[9],"time-invariant":[10],"singularly":[11,133],"perturbed":[12,134],"(SP)":[13],"systems":[14],"using":[15,124],"reinforcement":[16],"learning":[17,84],"(RL).":[18],"Both":[19,144],"the":[20,26,41,65,83,90,112,137,153],"state":[21],"and":[22,86,115,136,150],"input":[23],"matrices":[24],"of":[25,57,68,96,111,152],"plant":[27],"model":[28,42,71,98],"are":[29],"assumed":[30],"to":[31,72,108,116],"be":[32],"completely":[33],"unknown.":[34],"The":[35,79],"only":[36,64],"assumption":[37],"imposed":[38],"is":[39],"that":[40,47,62],"admits":[43],"similarity":[45],"transformation":[46],"results":[48,123],"in":[49],"SP":[51,70],"representation.":[52],"variant":[56],"Adaptive":[58],"Dynamic":[59],"Programming":[60],"(ADP)":[61],"employs":[63],"slow":[66],"states":[67],"this":[69,97],"learn":[73],"adaptive":[76],"controller.":[78],"method":[80],"significantly":[81],"reduces":[82],"time,":[85],"complexity":[87],"required":[88],"feedback":[91],"by":[93],"taking":[94],"advantage":[95],"reduction.":[99],"use":[101],"approximation":[102],"theorems":[103],"from":[104],"singular":[105],"perturbation":[106],"theory":[107],"establish":[109],"sub-optimality":[110],"learned":[113],"controller,":[114],"guarantee":[117],"closed-loop":[118],"stability.":[119],"validate":[121],"our":[122],"two":[125],"representative":[126],"examples":[127,145],"-":[128],"one":[129],"with":[130,139],"standard":[132],"dynamics,":[135],"other":[138],"clustered":[140],"multi-agent":[141],"consensus":[142],"dynamics.":[143],"highlight":[146],"various":[147],"implementation":[148],"details":[149],"effectiveness":[151],"proposed":[154],"approach.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}