{"id":"https://openalex.org/W3186019740","doi":"https://doi.org/10.23919/acc50511.2021.9482906","title":"Online Observer-Based Inverse Reinforcement Learning","display_name":"Online Observer-Based Inverse Reinforcement Learning","publication_year":2021,"publication_date":"2021-05-25","ids":{"openalex":"https://openalex.org/W3186019740","doi":"https://doi.org/10.23919/acc50511.2021.9482906","mag":"3186019740"},"language":"en","primary_location":{"id":"doi:10.23919/acc50511.2021.9482906","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9482906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"article","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/A5070632557","display_name":"Ryan Self","orcid":"https://orcid.org/0000-0001-8752-6299"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ryan Self","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109504130","display_name":"Kevin Coleman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Coleman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040513070","display_name":"He Bai","orcid":"https://orcid.org/0000-0002-4247-0698"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He Bai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5071224574","display_name":"Rushikesh Kamalapurkar","orcid":"https://orcid.org/0000-0001-9963-5361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rushikesh Kamalapurkar","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5070632557"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.148,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.50959031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1959","last_page":"1964"},"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":0.989799976348877,"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":0.9812999963760376,"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":0.6826150417327881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6158832311630249},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.6026171445846558},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5891737937927246},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5613033175468445},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.5415350198745728},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5212814807891846},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4262215495109558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33889371156692505},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.330607533454895},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32669776678085327},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25052595138549805},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.07487481832504272}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6826150417327881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6158832311630249},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.6026171445846558},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5891737937927246},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5613033175468445},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.5415350198745728},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5212814807891846},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4262215495109558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33889371156692505},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.330607533454895},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32669776678085327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25052595138549805},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.07487481832504272},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc50511.2021.9482906","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc50511.2021.9482906","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"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/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/W2784661720","https://openalex.org/W2800330509","https://openalex.org/W2886235386","https://openalex.org/W2912564980","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/W3054411520","https://openalex.org/W3095316834","https://openalex.org/W3103355199","https://openalex.org/W3120930765","https://openalex.org/W4301142652","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/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2024136090","https://openalex.org/W2964765435","https://openalex.org/W2972892860"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[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":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}