{"id":"https://openalex.org/W2886235386","doi":"https://doi.org/10.23919/acc.2018.8431430","title":"Linear inverse reinforcement learning in continuous time and space","display_name":"Linear inverse reinforcement learning in continuous time and space","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2886235386","doi":"https://doi.org/10.23919/acc.2018.8431430","mag":"2886235386"},"language":"en","primary_location":{"id":"doi:10.23919/acc.2018.8431430","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2018.8431430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Annual American Control Conference (ACC)","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/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":true,"raw_author_name":"Rushikesh Kamalapurkar","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University","institution_ids":["https://openalex.org/I115475287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071224574"],"corresponding_institution_ids":["https://openalex.org/I115475287"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1683","last_page":"1688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983999729156494,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9610000252723694,"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":0.7915760278701782},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6638283729553223},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.629141092300415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6073541045188904},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.5919001698493958},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5188642740249634},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.48970654606819153},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4873143136501312},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4859274923801422},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47178885340690613},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4503815770149231},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4379563629627228},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43381983041763306},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.42918661236763},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37233489751815796},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34159067273139954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29873305559158325},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12622153759002686},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10943901538848877},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09571221470832825},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.0946553647518158},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.07161235809326172}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7915760278701782},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6638283729553223},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.629141092300415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6073541045188904},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5919001698493958},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5188642740249634},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.48970654606819153},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4873143136501312},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4859274923801422},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47178885340690613},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4503815770149231},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4379563629627228},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43381983041763306},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.42918661236763},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37233489751815796},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34159067273139954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29873305559158325},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12622153759002686},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10943901538848877},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09571221470832825},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0946553647518158},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.07161235809326172},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc.2018.8431430","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc.2018.8431430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Annual American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W52822972","https://openalex.org/W1591675293","https://openalex.org/W1801976851","https://openalex.org/W1968908471","https://openalex.org/W1970916399","https://openalex.org/W1983523797","https://openalex.org/W1996625075","https://openalex.org/W1999874108","https://openalex.org/W2024315375","https://openalex.org/W2032558547","https://openalex.org/W2037997802","https://openalex.org/W2061562262","https://openalex.org/W2067603665","https://openalex.org/W2073990179","https://openalex.org/W2086975818","https://openalex.org/W2098774185","https://openalex.org/W2105156548","https://openalex.org/W2113023245","https://openalex.org/W2116442740","https://openalex.org/W2117675763","https://openalex.org/W2133068870","https://openalex.org/W2147544021","https://openalex.org/W2162009473","https://openalex.org/W2169498096","https://openalex.org/W2340995602","https://openalex.org/W2522472850","https://openalex.org/W2950989964","https://openalex.org/W3103355199","https://openalex.org/W3210839039","https://openalex.org/W6635261211","https://openalex.org/W6638440308","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6677555207","https://openalex.org/W6677631742","https://openalex.org/W6679958247","https://openalex.org/W6681478256","https://openalex.org/W6684097133"],"related_works":["https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W3009457412","https://openalex.org/W3021988786","https://openalex.org/W3099311996","https://openalex.org/W2963971282"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"a":[3,10,51],"data-driven":[4],"inverse":[5,38],"reinforcement":[6,39],"learning":[7],"technique":[8],"for":[9],"class":[11],"of":[12,20],"linear":[13],"systems":[14],"to":[15,35,48],"estimate":[16],"the":[17],"cost":[18,42],"function":[19,43],"an":[21],"agent":[22],"online,":[23],"using":[24],"input-output":[25],"measurements.":[26],"A":[27],"simultaneous":[28],"state":[29],"and":[30,41],"parameter":[31],"estimator":[32],"is":[33,45],"utilized":[34],"facilitate":[36],"output-feedback":[37],"learning,":[40],"estimation":[44],"achieved":[46],"up":[47],"multiplication":[49],"by":[50],"constant.":[52]},"counts_by_year":[{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}