{"id":"https://openalex.org/W3009702296","doi":"https://doi.org/10.23919/acc45564.2020.9147344","title":"Online inverse reinforcement learning for systems with disturbances","display_name":"Online inverse reinforcement learning for systems with disturbances","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3009702296","doi":"https://doi.org/10.23919/acc45564.2020.9147344","mag":"3009702296"},"language":"en","primary_location":{"id":"doi:10.23919/acc45564.2020.9147344","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147344","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.03912","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070632557","display_name":"Ryan Self","orcid":"https://orcid.org/0000-0001-8752-6299"},"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/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":["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":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1118","last_page":"1123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9990000128746033,"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":0.9990000128746033,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9933000206947327,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9861000180244446,"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":0.8074766397476196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6457434296607971},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5942758321762085},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5578488111495972},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5545298457145691},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5467721819877625},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5004761219024658},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.45680612325668335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4293055236339569},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.4197945296764374},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.331520140171051},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24669280648231506},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.147040456533432}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8074766397476196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6457434296607971},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5942758321762085},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5578488111495972},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5545298457145691},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5467721819877625},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5004761219024658},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.45680612325668335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4293055236339569},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.4197945296764374},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.331520140171051},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24669280648231506},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.147040456533432},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/acc45564.2020.9147344","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147344","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"},{"id":"pmh:oai:arXiv.org:2003.03912","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.03912","pdf_url":"https://arxiv.org/pdf/2003.03912","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:2003.03912","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.03912","pdf_url":"https://arxiv.org/pdf/2003.03912","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1970916399","https://openalex.org/W1983523797","https://openalex.org/W1996625075","https://openalex.org/W1999874108","https://openalex.org/W2031571562","https://openalex.org/W2037997802","https://openalex.org/W2061562262","https://openalex.org/W2067603665","https://openalex.org/W2070469928","https://openalex.org/W2098774185","https://openalex.org/W2107122393","https://openalex.org/W2113023245","https://openalex.org/W2116442740","https://openalex.org/W2117675763","https://openalex.org/W2157577161","https://openalex.org/W2162009473","https://openalex.org/W2169498096","https://openalex.org/W2340995602","https://openalex.org/W2604371190","https://openalex.org/W2784661720","https://openalex.org/W2886235386","https://openalex.org/W2912564980","https://openalex.org/W2950989964","https://openalex.org/W2992598248","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6677555207","https://openalex.org/W6677631742","https://openalex.org/W6684097133","https://openalex.org/W6910669261"],"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/W2331917905","https://openalex.org/W3155039083"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,20,23,31,43,47,65,73,77,84],"problem":[4],"of":[5,30,76],"online":[6],"inverse":[7,58],"reinforcement":[8,59],"learning":[9,60],"for":[10,53,90],"nonlinear":[11],"systems":[12],"with":[13,83],"modeling":[14],"uncertainties":[15],"and":[16,27,33,68],"additive":[17],"disturbances.":[18],"In":[19],"developed":[21],"approach,":[22],"learner":[24,63],"measures":[25],"state":[26],"input":[28],"trajectories":[29,45,87],"demonstrator":[32],"identifies":[34],"its":[35],"unknown":[36,48],"reward":[37,91],"function":[38,92],"online.":[39],"Sub-optimality":[40],"introduced":[41],"in":[42],"measured":[44],"by":[46],"external":[49,66],"disturbance":[50],"is":[51],"compensated":[52],"using":[54],"a":[55],"novel":[56],"model-based":[57],"approach.":[61],"The":[62,79],"estimates":[64],"disturbances":[67],"uses":[69],"them":[70],"to":[71],"identify":[72],"dynamic":[74],"model":[75,81],"demonstrator.":[78],"learned":[80],"along":[82],"observed":[85],"sub-optimal":[86],"are":[88],"used":[89],"estimation.":[93]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-03-13T00:00:00"}