{"id":"https://openalex.org/W4396817420","doi":"https://doi.org/10.1109/tnnls.2024.3392237","title":"Continuous-Time Reinforcement Learning: New Design Algorithms With Theoretical Insights and Performance Guarantees","display_name":"Continuous-Time Reinforcement Learning: New Design Algorithms With Theoretical Insights and Performance Guarantees","publication_year":2024,"publication_date":"2024-05-10","ids":{"openalex":"https://openalex.org/W4396817420","doi":"https://doi.org/10.1109/tnnls.2024.3392237","pmid":"https://pubmed.ncbi.nlm.nih.gov/38728125"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3392237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3392237","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5054618972","display_name":"Brent Wallace","orcid":"https://orcid.org/0000-0001-8145-8539"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brent A. Wallace","raw_affiliation_strings":["Department of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0001-8145-8539","affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085653399","display_name":"Jennie Si","orcid":"https://orcid.org/0000-0002-0374-7404"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jennie Si","raw_affiliation_strings":["Department of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-0374-7404","affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5054618972"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":1.3828,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82168712,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"36","issue":"4","first_page":"6940","last_page":"6954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9919999837875366,"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":0.9919999837875366,"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":0.9315000176429749,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7387065887451172},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6772180795669556},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6008106470108032},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.47207143902778625},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.4701649844646454},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.46472078561782837},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.46065258979797363},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3993673026561737},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3625091314315796},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.35455137491226196},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2839462161064148},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24001461267471313},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21714144945144653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18485799431800842}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7387065887451172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6772180795669556},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6008106470108032},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.47207143902778625},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.4701649844646454},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.46472078561782837},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.46065258979797363},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3993673026561737},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3625091314315796},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35455137491226196},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2839462161064148},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24001461267471313},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21714144945144653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18485799431800842},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3392237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3392237","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38728125","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38728125","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":81,"referenced_works":["https://openalex.org/W814391925","https://openalex.org/W1595516097","https://openalex.org/W1613039631","https://openalex.org/W1854776945","https://openalex.org/W1887006513","https://openalex.org/W1972809999","https://openalex.org/W1983089547","https://openalex.org/W1983523797","https://openalex.org/W1984777330","https://openalex.org/W1985691328","https://openalex.org/W1993626705","https://openalex.org/W2002122824","https://openalex.org/W2005675298","https://openalex.org/W2011310556","https://openalex.org/W2022349444","https://openalex.org/W2037025184","https://openalex.org/W2046971659","https://openalex.org/W2048687352","https://openalex.org/W2060686658","https://openalex.org/W2063054322","https://openalex.org/W2076104664","https://openalex.org/W2081514674","https://openalex.org/W2091565802","https://openalex.org/W2093831009","https://openalex.org/W2095590702","https://openalex.org/W2106813881","https://openalex.org/W2113501460","https://openalex.org/W2120624705","https://openalex.org/W2132858840","https://openalex.org/W2135176411","https://openalex.org/W2140140805","https://openalex.org/W2148439597","https://openalex.org/W2152161277","https://openalex.org/W2166310857","https://openalex.org/W2168586100","https://openalex.org/W2188644438","https://openalex.org/W2315895028","https://openalex.org/W2326903506","https://openalex.org/W2334250148","https://openalex.org/W2343912161","https://openalex.org/W2424242071","https://openalex.org/W2490084223","https://openalex.org/W2490234001","https://openalex.org/W2538885760","https://openalex.org/W2575417362","https://openalex.org/W2589677408","https://openalex.org/W2605603065","https://openalex.org/W2623884029","https://openalex.org/W2772589676","https://openalex.org/W2884730950","https://openalex.org/W2897058770","https://openalex.org/W2909711564","https://openalex.org/W2910910508","https://openalex.org/W2958962467","https://openalex.org/W2998147193","https://openalex.org/W3034289395","https://openalex.org/W3091575680","https://openalex.org/W3103446998","https://openalex.org/W3120441334","https://openalex.org/W3128350768","https://openalex.org/W3159667783","https://openalex.org/W3198869922","https://openalex.org/W3201820699","https://openalex.org/W3213705378","https://openalex.org/W4210910856","https://openalex.org/W4285263112","https://openalex.org/W4291910408","https://openalex.org/W4322706663","https://openalex.org/W4388918052","https://openalex.org/W6607741635","https://openalex.org/W6650454089","https://openalex.org/W6651016379","https://openalex.org/W6654649663","https://openalex.org/W6671526328","https://openalex.org/W6675149523","https://openalex.org/W6703064167","https://openalex.org/W6743398442","https://openalex.org/W6784829994","https://openalex.org/W6794802532","https://openalex.org/W6796214582","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W567560085"],"abstract_inverted_index":{"Continuous-time":[0],"reinforcement":[1,55],"learning":[2,37,56],"(CT-RL)":[3],"methods":[4,27,103,123],"hold":[5],"great":[6,23],"promise":[7],"in":[8,112],"real-world":[9],"applications.":[10],"Adaptive":[11],"dynamic":[12],"programming":[13],"(ADP)-based":[14],"CT-RL":[15],"algorithms,":[16],"especially":[17],"their":[18],"theoretical":[19],"developments,":[20],"have":[21,28],"achieved":[22],"successes.":[24],"However,":[25],"these":[26,149],"not":[29],"been":[30],"demonstrated":[31],"for":[32,59],"solving":[33],"realistic":[34],"or":[35],"meaningful":[36],"control":[38,60,106],"problems.":[39],"Thus,":[40],"the":[41,90,101,105,117,122,143],"goal":[42],"of":[43,51,61,76,142,156],"this":[44],"work":[45,67,133],"is":[46],"to":[47,73],"introduce":[48],"a":[49,69,94,152],"suite":[50],"new":[52,70],"excitable":[53],"integral":[54],"(EIRL)":[57],"algorithms":[58],"CT":[62],"affine":[63,119],"nonlinear":[64,120],"systems.":[65],"This":[66],"develops":[68],"excitation":[71,77],"framework":[72],"improve":[74],"persistence":[75],"(PE)":[78],"and":[79,128,138,146],"numerical":[80],"performance":[81],"via":[82],"input/output":[83],"insights":[84],"from":[85],"classical":[86],"control.":[87],"Furthermore,":[88],"when":[89],"system":[91,126],"dynamics":[92],"afford":[93],"physically-motivated":[95],"partition":[96],"into":[97,108],"distinct":[98],"dynamical":[99],"loops,":[100],"proposed":[102,144],"break":[104],"problem":[107,155],"smaller":[109],"subproblems,":[110],"resulting":[111],"reduced":[113],"complexity.":[114],"By":[115],"leveraging":[116],"known":[118],"dynamics,":[121],"achieve":[124],"well-behaved":[125],"responses":[127],"considerable":[129],"data":[130],"efficiency.":[131],"The":[132],"provides":[134],"convergence,":[135],"solution":[136],"optimality,":[137],"closed-loop":[139],"stability":[140],"guarantees":[141,150],"methods,":[145],"it":[147],"demonstrates":[148],"on":[151],"significant":[153],"application":[154],"controlling":[157],"an":[158],"unstable,":[159],"nonminimum":[160],"phase":[161],"hypersonic":[162],"vehicle":[163],"(HSV).":[164]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}