{"id":"https://openalex.org/W3045738582","doi":"https://doi.org/10.23919/acc45564.2020.9147523","title":"On Robust Model-Free Reduced-Dimensional Reinforcement Learning Control for Singularly Perturbed Systems","display_name":"On Robust Model-Free Reduced-Dimensional Reinforcement Learning Control for Singularly Perturbed Systems","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3045738582","doi":"https://doi.org/10.23919/acc45564.2020.9147523","mag":"3045738582"},"language":"en","primary_location":{"id":"doi:10.23919/acc45564.2020.9147523","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/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/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Bai","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, USA"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"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":0.7036,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.76190476,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3914","last_page":"3919"},"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9678000211715698,"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/T12047","display_name":"Viral Infections and Vectors","score":0.9158999919891357,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8469818234443665},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7571420669555664},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.7288281917572021},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6180657148361206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5646994113922119},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5280663967132568},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5188683271408081},{"id":"https://openalex.org/keywords/robust-control","display_name":"Robust control","score":0.5052433609962463},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.48834678530693054},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4627656042575836},{"id":"https://openalex.org/keywords/exponential-stability","display_name":"Exponential stability","score":0.4436858594417572},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4425002932548523},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4376859664916992},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.43152594566345215},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.38045522570610046},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.349724680185318},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3131370544433594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18750125169754028},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18615153431892395},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1663476824760437},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.07855433225631714}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8469818234443665},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7571420669555664},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.7288281917572021},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6180657148361206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5646994113922119},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5280663967132568},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5188683271408081},{"id":"https://openalex.org/C31531917","wikidata":"https://www.wikidata.org/wiki/Q915157","display_name":"Robust control","level":3,"score":0.5052433609962463},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.48834678530693054},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4627656042575836},{"id":"https://openalex.org/C167964875","wikidata":"https://www.wikidata.org/wiki/Q17011487","display_name":"Exponential stability","level":3,"score":0.4436858594417572},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4425002932548523},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4376859664916992},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.43152594566345215},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38045522570610046},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.349724680185318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3131370544433594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18750125169754028},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18615153431892395},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1663476824760437},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.07855433225631714},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc45564.2020.9147523","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1481652330","https://openalex.org/W1994266622","https://openalex.org/W2036826525","https://openalex.org/W2037025184","https://openalex.org/W2144151364","https://openalex.org/W2148437632","https://openalex.org/W2148439597","https://openalex.org/W2165626406","https://openalex.org/W2487144912","https://openalex.org/W2913981879","https://openalex.org/W4214717370","https://openalex.org/W4301382568","https://openalex.org/W4301886962"],"related_works":["https://openalex.org/W2108470770","https://openalex.org/W1512021029","https://openalex.org/W1972862722","https://openalex.org/W2281732014","https://openalex.org/W2063351494","https://openalex.org/W2319803529","https://openalex.org/W1562326332","https://openalex.org/W1550017747","https://openalex.org/W2152839317","https://openalex.org/W2913641967"],"abstract_inverted_index":{"We":[0,27,91],"present":[1],"a":[2,54,65,98,103],"robust":[3],"design":[4,94],"for":[5],"reinforcement":[6],"learning":[7,89],"(RL)":[8],"based":[9],"optimal":[10],"control":[11],"of":[12,24,32,56,70,75,97,102],"continuous-time":[13],"linear":[14],"time-invariant":[15],"singularly":[16],"perturbed":[17],"(SP)":[18],"dynamic":[19,25,30,59],"systems":[20],"in":[21],"the":[22,29,34,37,44,57,72,76],"presence":[23],"uncertainties.":[26],"consider":[28],"model":[31],"both":[33],"plant":[35],"and":[36,86,101],"uncertainty":[38,45],"to":[39],"be":[40],"unknown.":[41],"Assuming":[42],"that":[43,63],"satisfies":[46],"an":[47],"input-to-state":[48],"stability":[49],"(ISS)":[50],"condition,":[51],"we":[52],"propose":[53],"variant":[55],"adaptive":[58],"programming":[60],"(ADP)":[61],"method":[62],"learns":[64],"sub-optimal":[66],"controller":[67,81],"using":[68],"measurements":[69],"only":[71],"slow":[73],"states":[74],"plant.":[77],"The":[78],"resulting":[79],"RL":[80],"is,":[82],"therefore,":[83],"significantly":[84],"reduced-dimensional,":[85],"enjoys":[87],"reduced":[88],"time.":[90],"illustrate":[92],"our":[93],"with":[95],"simulations":[96],"SP":[99],"system":[100],"clustered":[104],"multi-agent":[105],"consensus":[106],"network.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}