{"id":"https://openalex.org/W3095316834","doi":"https://doi.org/10.1109/lcsys.2020.3046527","title":"Online Observer-Based Inverse Reinforcement Learning","display_name":"Online Observer-Based Inverse Reinforcement Learning","publication_year":2020,"publication_date":"2020-12-22","ids":{"openalex":"https://openalex.org/W3095316834","doi":"https://doi.org/10.1109/lcsys.2020.3046527","mag":"3095316834"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2020.3046527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2020.3046527","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.02057","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":true,"raw_author_name":"Ryan Self","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109504130","display_name":"Kevin Coleman","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":"Kevin Coleman","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK","institution_ids":["https://openalex.org/I115475287"]}]},{"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":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK","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"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK","institution_ids":["https://openalex.org/I115475287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070632557"],"corresponding_institution_ids":["https://openalex.org/I115475287"],"apc_list":null,"apc_paid":null,"fwci":2.4546,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.91527008,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"5","issue":"6","first_page":"1922","last_page":"1927"},"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9905999898910522,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9846000075340271,"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/robustness","display_name":"Robustness (evolution)","score":0.6444152593612671},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.62492835521698},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5900153517723083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5653296709060669},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5403457283973694},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5122684836387634},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.5068455338478088},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4341808259487152},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.41934069991111755},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3243024945259094},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31730830669403076},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.305210143327713}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6444152593612671},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.62492835521698},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5900153517723083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5653296709060669},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5403457283973694},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5122684836387634},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.5068455338478088},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4341808259487152},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.41934069991111755},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3243024945259094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31730830669403076},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.305210143327713},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lcsys.2020.3046527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2020.3046527","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2011.02057","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02057","pdf_url":"https://arxiv.org/pdf/2011.02057","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:2011.02057","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02057","pdf_url":"https://arxiv.org/pdf/2011.02057","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":[{"id":"https://openalex.org/G765302217","display_name":null,"funder_award_id":"1925147","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095316834.pdf","grobid_xml":"https://content.openalex.org/works/W3095316834.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W52822972","https://openalex.org/W130083205","https://openalex.org/W1494902192","https://openalex.org/W1578936488","https://openalex.org/W1929981607","https://openalex.org/W1970916399","https://openalex.org/W1983523797","https://openalex.org/W2031571562","https://openalex.org/W2047993072","https://openalex.org/W2061562262","https://openalex.org/W2096871511","https://openalex.org/W2098774185","https://openalex.org/W2117675763","https://openalex.org/W2148112459","https://openalex.org/W2162009473","https://openalex.org/W2169498096","https://openalex.org/W2202743478","https://openalex.org/W2340995602","https://openalex.org/W2522472850","https://openalex.org/W2604371190","https://openalex.org/W2610857016","https://openalex.org/W2784661720","https://openalex.org/W2800330509","https://openalex.org/W2886235386","https://openalex.org/W2912564980","https://openalex.org/W2962937519","https://openalex.org/W2963712524","https://openalex.org/W2963797805","https://openalex.org/W2964098908","https://openalex.org/W2992598248","https://openalex.org/W3009702296","https://openalex.org/W3011519113","https://openalex.org/W3095316834","https://openalex.org/W3103355199","https://openalex.org/W3120930765","https://openalex.org/W4285526177","https://openalex.org/W4300463161","https://openalex.org/W4301747304","https://openalex.org/W4313387916","https://openalex.org/W6629585730","https://openalex.org/W6674884181","https://openalex.org/W6677555207","https://openalex.org/W6684097133","https://openalex.org/W6747901993","https://openalex.org/W6781590896"],"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/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2331917905","https://openalex.org/W3155039083"],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"a":[3,29,41],"novel":[4,42],"approach":[5],"to":[6],"the":[7,18,67,70],"output-feedback":[8],"inverse":[9],"reinforcement":[10],"learning":[11],"(IRL)":[12],"problem":[13],"is":[14],"developed":[15,71],"by":[16],"casting":[17],"IRL":[19,37],"problem,":[20],"for":[21,36,55],"linear":[22],"systems":[23],"with":[24],"quadratic":[25],"cost":[26],"functions,":[27],"as":[28],"state":[30,48],"estimation":[31],"problem.":[32],"Two":[33],"observer-based":[34],"techniques":[35],"are":[38,59],"developed,":[39],"including":[40],"observer":[43],"method":[44],"that":[45],"re-uses":[46],"previous":[47],"estimates":[49],"via":[50],"history":[51],"stacks.":[52],"Theoretical":[53],"guarantees":[54],"convergence":[56],"and":[57,73,77],"robustness":[58],"established":[60],"under":[61,75],"appropriate":[62],"excitation":[63],"conditions.":[64],"Simulations":[65],"demonstrate":[66],"performance":[68],"of":[69],"observers":[72],"filters":[74],"noisy":[76],"noise-free":[78],"measurements.":[79]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
