{"id":"https://openalex.org/W2932301621","doi":"https://doi.org/10.23919/acc.2019.8814910","title":"Model-based reinforcement learning for output-feedback optimal control of a class of nonlinear systems","display_name":"Model-based reinforcement learning for output-feedback optimal control of a class of nonlinear systems","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2932301621","doi":"https://doi.org/10.23919/acc.2019.8814910","mag":"2932301621"},"language":"en","primary_location":{"id":"doi:10.23919/acc.2019.8814910","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2019.8814910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.02078","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110720587","display_name":"Ryan Self","orcid":null},"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":"Ryan Self","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071780845","display_name":"Michael Harlan","orcid":null},"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":"Michael Harlan","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"last","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":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I115475287"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2378","last_page":"2383"},"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":0.9764999747276306,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9715999960899353,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.911795973777771},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6886277198791504},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6820558905601501},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.634933590888977},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6308643817901611},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5951283574104309},{"id":"https://openalex.org/keywords/state-estimator","display_name":"State estimator","score":0.5319253206253052},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.505690336227417},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4408486485481262},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38525089621543884},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.3539479374885559},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19219768047332764},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1822662353515625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1309162676334381}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.911795973777771},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6886277198791504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820558905601501},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.634933590888977},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6308643817901611},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5951283574104309},{"id":"https://openalex.org/C2984536560","wikidata":"https://www.wikidata.org/wiki/Q818544","display_name":"State estimator","level":3,"score":0.5319253206253052},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.505690336227417},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4408486485481262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38525089621543884},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3539479374885559},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19219768047332764},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1822662353515625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1309162676334381},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/acc.2019.8814910","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2019.8814910","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.02078","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1903.02078","pdf_url":"https://arxiv.org/pdf/1903.02078","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.02078","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1903.02078","pdf_url":"https://arxiv.org/pdf/1903.02078","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2932301621.pdf","grobid_xml":"https://content.openalex.org/works/W2932301621.grobid-xml"},"referenced_works_count":72,"referenced_works":["https://openalex.org/W5108103","https://openalex.org/W364367221","https://openalex.org/W1505937442","https://openalex.org/W1540245649","https://openalex.org/W1560580936","https://openalex.org/W1578936488","https://openalex.org/W1747856733","https://openalex.org/W1770312810","https://openalex.org/W1964375638","https://openalex.org/W1968908471","https://openalex.org/W1977070092","https://openalex.org/W1977671496","https://openalex.org/W1982262386","https://openalex.org/W1983523797","https://openalex.org/W1986944783","https://openalex.org/W1988115241","https://openalex.org/W2005127705","https://openalex.org/W2010152647","https://openalex.org/W2013895638","https://openalex.org/W2019338681","https://openalex.org/W2024315375","https://openalex.org/W2027197837","https://openalex.org/W2032100464","https://openalex.org/W2052305027","https://openalex.org/W2073990179","https://openalex.org/W2081514674","https://openalex.org/W2085194340","https://openalex.org/W2086975818","https://openalex.org/W2087063454","https://openalex.org/W2089434629","https://openalex.org/W2097253853","https://openalex.org/W2102933137","https://openalex.org/W2104843094","https://openalex.org/W2106907982","https://openalex.org/W2108286682","https://openalex.org/W2108383324","https://openalex.org/W2114384389","https://openalex.org/W2132602063","https://openalex.org/W2134540127","https://openalex.org/W2135836059","https://openalex.org/W2140135625","https://openalex.org/W2142620596","https://openalex.org/W2150841368","https://openalex.org/W2154208977","https://openalex.org/W2155836220","https://openalex.org/W2160698719","https://openalex.org/W2161966552","https://openalex.org/W2165726932","https://openalex.org/W2484646121","https://openalex.org/W2488247662","https://openalex.org/W2489939061","https://openalex.org/W2523345745","https://openalex.org/W2531648764","https://openalex.org/W2559655401","https://openalex.org/W2597289420","https://openalex.org/W2604371190","https://openalex.org/W2767784613","https://openalex.org/W2800330509","https://openalex.org/W2932301621","https://openalex.org/W2964006217","https://openalex.org/W3021669587","https://openalex.org/W3103127108","https://openalex.org/W3150098721","https://openalex.org/W4212774754","https://openalex.org/W4285719527","https://openalex.org/W4301747304","https://openalex.org/W6600197225","https://openalex.org/W6637888334","https://openalex.org/W6639949747","https://openalex.org/W6675945767","https://openalex.org/W6677185582","https://openalex.org/W6680657880"],"related_works":["https://openalex.org/W4287880334","https://openalex.org/W4306904969","https://openalex.org/W4366700029","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W4285230481","https://openalex.org/W2024136090","https://openalex.org/W4391331176"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"an":[3],"output-feedback":[4,40],"model-based":[5,34],"reinforcement":[6,35],"learning":[7,36],"(MBRL)":[8],"method":[9],"for":[10],"a":[11,28],"class":[12],"of":[13,47],"second-order":[14],"nonlinear":[15],"systems":[16],"is":[17],"developed.":[18],"The":[19],"control":[20],"technique":[21],"uses":[22],"exact":[23],"model":[24],"knowledge":[25],"and":[26],"integrates":[27],"dynamic":[29],"state":[30],"estimator":[31],"within":[32],"the":[33,45,48],"framework":[37],"to":[38],"achieve":[39],"MBRL.":[41],"Simulation":[42],"results":[43],"demonstrate":[44],"efficacy":[46],"developed":[49],"method.":[50]},"counts_by_year":[{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2019-04-11T00:00:00"}