{"id":"https://openalex.org/W3054411520","doi":"https://doi.org/10.1109/cdc42340.2020.9303883","title":"Online inverse reinforcement learning with limited data","display_name":"Online inverse reinforcement learning with limited data","publication_year":2020,"publication_date":"2020-12-14","ids":{"openalex":"https://openalex.org/W3054411520","doi":"https://doi.org/10.1109/cdc42340.2020.9303883","mag":"3054411520"},"language":"en","primary_location":{"id":"doi:10.1109/cdc42340.2020.9303883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.08972","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","Oklahoma State University, School of Mechanical and Aerospace Engineering, 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"]},{"raw_affiliation_string":"Oklahoma State University, School of Mechanical and Aerospace Engineering, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057917967","display_name":"S M Nahid Mahmud","orcid":"https://orcid.org/0000-0003-3378-1133"},"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":"S M Nahid Mahmud","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA","Oklahoma State University, School of Mechanical and Aerospace Engineering, 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"]},{"raw_affiliation_string":"Oklahoma State University, School of Mechanical and Aerospace Engineering, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020869372","display_name":"Katrine Hareland","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":"Katrine Hareland","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA","Oklahoma State University, School of Mechanical and Aerospace Engineering, 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"]},{"raw_affiliation_string":"Oklahoma State University, School of Mechanical and Aerospace Engineering, 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"]},{"id":"https://openalex.org/I4210131712","display_name":"Oklahoma State University Oklahoma City","ror":"https://ror.org/03y1zyv86","country_code":"US","type":"education","lineage":["https://openalex.org/I4210131712"]}],"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","Oklahoma State University*"],"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"]},{"raw_affiliation_string":"Oklahoma State University*","institution_ids":["https://openalex.org/I4210131712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"603","last_page":"608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9976000189781189,"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":0.995199978351593,"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":0.8414788246154785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6864880919456482},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6214439868927002},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5599048733711243},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5225721597671509},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4529033601284027},{"id":"https://openalex.org/keywords/inverse-dynamics","display_name":"Inverse dynamics","score":0.44543224573135376},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42728307843208313},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3946469724178314},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3883754014968872},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3412977457046509},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14383289217948914},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13447114825248718}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8414788246154785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6864880919456482},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6214439868927002},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5599048733711243},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5225721597671509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4529033601284027},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.44543224573135376},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42728307843208313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3946469724178314},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3883754014968872},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3412977457046509},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14383289217948914},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13447114825248718},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/cdc42340.2020.9303883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc42340.2020.9303883","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 59th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.08972","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.08972","pdf_url":"https://arxiv.org/pdf/2008.08972","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2008.08972","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.08972","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3054411520","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2008.08972","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.08972","pdf_url":"https://arxiv.org/pdf/2008.08972","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":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6200000047683716,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3054411520.pdf","grobid_xml":"https://content.openalex.org/works/W3054411520.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1578936488","https://openalex.org/W1977671496","https://openalex.org/W1988115241","https://openalex.org/W1996625075","https://openalex.org/W1999874108","https://openalex.org/W2031571562","https://openalex.org/W2061562262","https://openalex.org/W2067603665","https://openalex.org/W2070469928","https://openalex.org/W2086975818","https://openalex.org/W2097253853","https://openalex.org/W2098774185","https://openalex.org/W2113023245","https://openalex.org/W2116442740","https://openalex.org/W2117675763","https://openalex.org/W2137983211","https://openalex.org/W2162009473","https://openalex.org/W2169498096","https://openalex.org/W2522472850","https://openalex.org/W2784661720","https://openalex.org/W2886235386","https://openalex.org/W2912564980","https://openalex.org/W2992598248","https://openalex.org/W3009702296","https://openalex.org/W3103355199","https://openalex.org/W3120930765","https://openalex.org/W3146803896","https://openalex.org/W4301747304","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6677555207","https://openalex.org/W6677631742","https://openalex.org/W6684097133"],"related_works":["https://openalex.org/W3120930765","https://openalex.org/W2886235386","https://openalex.org/W2156163138","https://openalex.org/W2841148035","https://openalex.org/W2117675763","https://openalex.org/W2031067035","https://openalex.org/W2962997838","https://openalex.org/W69730760","https://openalex.org/W3106008061","https://openalex.org/W1997816436","https://openalex.org/W2762483932","https://openalex.org/W3130800560","https://openalex.org/W2980805049","https://openalex.org/W2947612938","https://openalex.org/W3153408412","https://openalex.org/W3209524531","https://openalex.org/W2102576345","https://openalex.org/W3145401136","https://openalex.org/W3195322794","https://openalex.org/W2083963846"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,19,22,63,78],"problem":[4],"of":[5],"online":[6,29],"inverse":[7,48],"reinforcement":[8,49],"learning":[9,50],"for":[10,60],"systems":[11],"with":[12],"limited":[13],"data":[14,93],"and":[15,24,37],"uncertain":[16],"dynamics.":[17,65],"In":[18],"developed":[20],"approach,":[21],"state":[23],"control":[25],"trajectories":[26],"are":[27],"recorded":[28],"by":[30,70],"observing":[31],"an":[32],"agent":[33],"perform":[34],"a":[35,46,72],"task,":[36],"reward":[38,96],"function":[39,97],"estimation":[40,53],"is":[41,54,68],"performed":[42,55],"in":[43,62],"real-time":[44],"using":[45],"novel":[47],"approach.":[51],"Parameter":[52],"concurrently":[56],"to":[57,76,89,94],"help":[58],"compensate":[59],"uncertainties":[61],"agent's":[64],"Data":[66],"insufficiency":[67],"resolved":[69],"developing":[71],"data-driven":[73],"update":[74],"law":[75],"estimate":[77],"optimal":[79],"feedback":[80],"controller.":[81],"The":[82],"estimated":[83],"controller":[84],"can":[85],"then":[86],"be":[87],"queried":[88],"artificially":[90],"create":[91],"additional":[92],"drive":[95],"estimation.":[98]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}