{"id":"https://openalex.org/W4382936036","doi":"https://doi.org/10.23919/acc55779.2023.10156057","title":"Reinforcement Learning based Approximate Optimal Control of Nonlinear Systems using Carleman Linearization","display_name":"Reinforcement Learning based Approximate Optimal Control of Nonlinear Systems using Carleman Linearization","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4382936036","doi":"https://doi.org/10.23919/acc55779.2023.10156057"},"language":"en","primary_location":{"id":"doi:10.23919/acc55779.2023.10156057","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc55779.2023.10156057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5062293547","display_name":"Jishnudeep Kar","orcid":null},"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":"Jishnudeep Kar","raw_affiliation_strings":["North Carolina State University,Department of Electrical and Computer Engineering,Raleigh,NC,USA","Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Electrical and Computer Engineering,Raleigh,NC,USA","institution_ids":["https://openalex.org/I137902535"]},{"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":["Oklahoma State University,Department of Mechanical Engineering,Stillwater,OK,USA","Department of Mechanical Engineering, Oklahoma State University, Stillwater, OK, USA"],"affiliations":[{"raw_affiliation_string":"Oklahoma State University,Department of Mechanical Engineering,Stillwater,OK,USA","institution_ids":["https://openalex.org/I115475287"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Oklahoma State University, Stillwater, OK, 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":["North Carolina State University,Department of Electrical and Computer Engineering,Raleigh,NC,USA","Department of Electrical and Computer Engineering, North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Electrical and Computer Engineering,Raleigh,NC,USA","institution_ids":["https://openalex.org/I137902535"]},{"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/A5062293547"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":0.4034,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63830148,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3362","last_page":"3367"},"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":0.9781000018119812,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9714999794960022,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8003722429275513},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7599952816963196},{"id":"https://openalex.org/keywords/linearization","display_name":"Linearization","score":0.7372636198997498},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.7096396684646606},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6091727018356323},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.567158579826355},{"id":"https://openalex.org/keywords/feedback-linearization","display_name":"Feedback linearization","score":0.5532238483428955},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5404554009437561},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.5400958061218262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.515389084815979},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.4466370642185211},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.43536484241485596},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4241911470890045},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.41543954610824585},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2823202311992645},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.24420246481895447},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17943349480628967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13548165559768677},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.09190553426742554}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8003722429275513},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7599952816963196},{"id":"https://openalex.org/C11210021","wikidata":"https://www.wikidata.org/wiki/Q1520713","display_name":"Linearization","level":3,"score":0.7372636198997498},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.7096396684646606},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6091727018356323},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.567158579826355},{"id":"https://openalex.org/C85736874","wikidata":"https://www.wikidata.org/wiki/Q672139","display_name":"Feedback linearization","level":3,"score":0.5532238483428955},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5404554009437561},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.5400958061218262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.515389084815979},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.4466370642185211},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.43536484241485596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4241911470890045},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.41543954610824585},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2823202311992645},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.24420246481895447},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17943349480628967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13548165559768677},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09190553426742554},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc55779.2023.10156057","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc55779.2023.10156057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1520892678","https://openalex.org/W1723433682","https://openalex.org/W1973265903","https://openalex.org/W1990063866","https://openalex.org/W2024303516","https://openalex.org/W2078543085","https://openalex.org/W2084504497","https://openalex.org/W2135637601","https://openalex.org/W2148439597","https://openalex.org/W2997318655","https://openalex.org/W3023262556","https://openalex.org/W3046112840","https://openalex.org/W3106496844","https://openalex.org/W3202264307","https://openalex.org/W4214717370","https://openalex.org/W4224232484","https://openalex.org/W4321592870","https://openalex.org/W6671715414"],"related_works":["https://openalex.org/W1998462347","https://openalex.org/W2349527210","https://openalex.org/W1836713364","https://openalex.org/W2141603307","https://openalex.org/W4300511988","https://openalex.org/W2131265573","https://openalex.org/W2899783744","https://openalex.org/W2317650444","https://openalex.org/W130230158","https://openalex.org/W2913529325"],"abstract_inverted_index":{"We":[0,108],"develop":[1],"a":[2,19],"policy":[3],"iteration-based":[4],"model-free":[5],"reinforcement":[6],"learning":[7,124],"(RL)":[8],"control":[9,101],"for":[10],"nonlinear":[11,33,77],"systems":[12],"with":[13],"single":[14],"input.":[15],"First,":[16],"Carleman":[17,38,106],"linearization,":[18],"commonly":[20],"used":[21],"linearization":[22],"technique":[23],"in":[24,55,120],"the":[25,32,60,71,76,99,104],"Hilbert":[26],"space,":[27],"is":[28,79],"applied":[29],"to":[30,98,113],"express":[31],"system":[34],"as":[35],"an":[36,45],"infinite-dimensional":[37,57],"state-space":[39],"model,":[40],"followed":[41],"by":[42],"derivation":[43],"of":[44,62,67,75,122],"online":[46],"state-feedback":[47],"RL":[48],"controller":[49,112],"using":[50,63,84],"state":[51],"and":[52,70],"input":[53],"data":[54],"this":[56,68],"space.":[58],"Next,":[59],"practicality":[61],"any":[64],"finite-order":[65],"truncation":[66],"controller,":[69],"corresponding":[72],"closed-loop":[73],"stability":[74],"plant":[78],"established.":[80],"Results":[81],"are":[82],"validated":[83],"two":[85],"numerical":[86],"examples,":[87],"where":[88],"we":[89],"show":[90],"how":[91],"our":[92,111],"proposed":[93],"method":[94],"provides":[95],"solutions":[96],"close":[97],"optimal":[100],"resulting":[102],"from":[103],"model-based":[105],"controllers.":[107],"also":[109],"compare":[110],"alternative":[114],"data-driven":[115],"methods,":[116],"showing":[117],"its":[118],"advantage":[119],"terms":[121],"shorter":[123],"time.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}