{"id":"https://openalex.org/W3119164477","doi":"https://doi.org/10.1109/cdc42340.2020.9304400","title":"Model-Based Reinforcement Learning for Optimal Feedback Control of Switched Systems","display_name":"Model-Based Reinforcement Learning for Optimal Feedback Control of Switched Systems","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3119164477","doi":"https://doi.org/10.1109/cdc42340.2020.9304400","mag":"3119164477"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9304400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","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/A5027840499","display_name":"Max L. Greene","orcid":"https://orcid.org/0000-0003-2733-0344"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max L. Greene","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060269730","display_name":"Moad Abudia","orcid":"https://orcid.org/0009-0003-4316-5382"},"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":"Moad Abudia","raw_affiliation_strings":["Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071224574","display_name":"Rushikesh Kamalapurkar","orcid":"https://orcid.org/0000-0001-9963-5361"},"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":"Rushikesh Kamalapurkar","raw_affiliation_strings":["Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032651215","display_name":"Warren E. Dixon","orcid":"https://orcid.org/0000-0002-5091-181X"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Warren E. Dixon","raw_affiliation_strings":["University of Florida, Gainesville, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"162","last_page":"167"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.991599977016449,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9480000138282776,"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/dwell-time","display_name":"Dwell time","score":0.8127394914627075},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8045558929443359},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7378198504447937},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6829769015312195},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.660102367401123},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6242371797561646},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6092522144317627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5279737114906311},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5262084603309631},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5136377215385437},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4737313985824585},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44421863555908203},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.42086294293403625},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38285887241363525},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3808208107948303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11161348223686218},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.08883029222488403},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.05979207158088684}],"concepts":[{"id":"https://openalex.org/C151637689","wikidata":"https://www.wikidata.org/wiki/Q5318064","display_name":"Dwell time","level":2,"score":0.8127394914627075},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8045558929443359},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7378198504447937},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6829769015312195},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.660102367401123},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6242371797561646},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6092522144317627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5279737114906311},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5262084603309631},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5136377215385437},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4737313985824585},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44421863555908203},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42086294293403625},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38285887241363525},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3808208107948303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11161348223686218},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.08883029222488403},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.05979207158088684},{"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C70410870","wikidata":"https://www.wikidata.org/wiki/Q199906","display_name":"Clinical psychology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc42340.2020.9304400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9304400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1540245649","https://openalex.org/W1574514837","https://openalex.org/W1578936488","https://openalex.org/W1584101032","https://openalex.org/W1965442989","https://openalex.org/W1977237536","https://openalex.org/W1983523797","https://openalex.org/W2003183707","https://openalex.org/W2010152647","https://openalex.org/W2013895638","https://openalex.org/W2033030672","https://openalex.org/W2048687352","https://openalex.org/W2055846441","https://openalex.org/W2058616897","https://openalex.org/W2060578001","https://openalex.org/W2086975818","https://openalex.org/W2090167557","https://openalex.org/W2104843094","https://openalex.org/W2111034649","https://openalex.org/W2116479681","https://openalex.org/W2117271243","https://openalex.org/W2121863487","https://openalex.org/W2138131694","https://openalex.org/W2145030746","https://openalex.org/W2158625202","https://openalex.org/W2160698719","https://openalex.org/W2165726932","https://openalex.org/W2476930474","https://openalex.org/W2606555964","https://openalex.org/W2762061748","https://openalex.org/W2772589676","https://openalex.org/W2800330509","https://openalex.org/W2887138972","https://openalex.org/W3016201194","https://openalex.org/W4214717370","https://openalex.org/W4301747304","https://openalex.org/W6746329953"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W2967346707","https://openalex.org/W3099153698","https://openalex.org/W1859185863","https://openalex.org/W4285537323","https://openalex.org/W2964126589","https://openalex.org/W1932159282","https://openalex.org/W4307691181"],"abstract_inverted_index":{"This":[0],"paper":[1],"examines":[2],"the":[3,40,72,81,85,91,102],"use":[4],"of":[5,14,17,39,58,71,80,84,90],"reinforcement":[6],"learning-based":[7],"controllers":[8],"to":[9,55,62,68],"approximate":[10],"multiple":[11],"value":[12,86],"functions":[13],"specific":[15],"classes":[16],"subsystems":[18,60],"while":[19],"following":[20],"a":[21,64],"switching":[22,42,74,99],"sequence.":[23,75],"Each":[24],"subsystem":[25],"may":[26],"have":[27],"varying":[28],"characteristics,":[29],"such":[30],"as":[31],"different":[32,35],"cost":[33],"or":[34],"system":[36],"dynamics.":[37],"Stability":[38],"overall":[41,73],"sequence":[43],"is":[44,95,106],"proven":[45],"using":[46],"Lyapunov-based":[47,51],"analysis":[48],"techniques.":[49],"Specifically,":[50],"methods":[52],"are":[53],"developed":[54],"prove":[56],"boundedness":[57],"individual":[59],"and":[61,88],"determine":[63],"minimum":[65,103],"dwell-time":[66,104],"condition":[67,105],"ensure":[69],"stability":[70],"Uniformly":[76],"ultimately":[77],"bounded":[78],"regulation":[79],"states,":[82],"approximation":[83,89],"function,":[87],"optimal":[92],"control":[93],"policy":[94],"achieved":[96],"for":[97],"arbitrary":[98],"sequences":[100],"provided":[101],"satisfied.":[107]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}