{"id":"https://openalex.org/W2784661720","doi":"https://doi.org/10.1109/ccta.2019.8920458","title":"Online inverse reinforcement learning for nonlinear systems","display_name":"Online inverse reinforcement learning for nonlinear systems","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2784661720","doi":"https://doi.org/10.1109/ccta.2019.8920458","mag":"2784661720"},"language":"en","primary_location":{"id":"doi:10.1109/ccta.2019.8920458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccta.2019.8920458","pdf_url":null,"source":{"id":"https://openalex.org/S4306498490","display_name":"2019 IEEE Conference on Control Technology and Applications (CCTA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Conference on Control Technology and Applications (CCTA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1801.07663","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ryan Self","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":true,"raw_author_name":"Ryan Self","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Still-water, OK, USA"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Still-water, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Michael Harlan","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":"Michael Harlan","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Still-water, OK, USA"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Still-water, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"last","author":{"id":null,"display_name":"Rushikesh Kamalapurkar","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":"Rushikesh Kamalapurkar","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Oklahoma State University, Still-water, OK, USA"],"affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Still-water, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I115475287"],"apc_list":null,"apc_paid":null,"fwci":2.2932,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.87601958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.8977000117301941,"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":0.8977000117301941,"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":0.057999998331069946,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6489999890327454},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.646399974822998},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6370999813079834},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5760999917984009},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.42820000648498535},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.42669999599456787},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.3725999891757965},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.3718999922275543}],"concepts":[{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6489999890327454},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.646399974822998},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6370999813079834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6165000200271606},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5760999917984009},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.42820000648498535},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3752000033855438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3734000027179718},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.3718999922275543},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C140528856","wikidata":"https://www.wikidata.org/wiki/Q191884","display_name":"Inverse function","level":3,"score":0.3431999981403351},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3321000039577484},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ccta.2019.8920458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccta.2019.8920458","pdf_url":null,"source":{"id":"https://openalex.org/S4306498490","display_name":"2019 IEEE Conference on Control Technology and Applications (CCTA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Conference on Control Technology and Applications (CCTA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1801.07663","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1801.07663","pdf_url":"https://arxiv.org/pdf/1801.07663","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:1801.07663","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1801.07663","pdf_url":"https://arxiv.org/pdf/1801.07663","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":18,"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/W2070469928","https://openalex.org/W2157577161","https://openalex.org/W2169498096","https://openalex.org/W2340995602","https://openalex.org/W2604371190","https://openalex.org/W2886235386","https://openalex.org/W6640443443","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6677555207","https://openalex.org/W6677631742","https://openalex.org/W6684097133"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"focuses":[2],"on":[3],"the":[4,31,36,51,55,65,78,81],"development":[5],"of":[6,17,50,57,64,80],"an":[7],"online":[8],"inverse":[9],"reinforcement":[10],"learning":[11],"(IRL)":[12],"technique":[13,44],"for":[14,62],"a":[15],"class":[16],"nonlinear":[18],"systems.":[19],"The":[20],"developed":[21,82],"approach":[22],"utilizes":[23],"observed":[24],"state":[25],"and":[26,29,35,71],"input":[27],"trajectories,":[28],"determines":[30],"unknown":[32,37,58],"reward":[33,52,66],"function":[34,39,53,67],"value":[38],"online.":[40],"A":[41],"parameter":[42],"estimation":[43,49],"is":[45],"utilized":[46],"to":[47,76],"facilitate":[48],"in":[54],"presence":[56],"dynamics.":[59],"Theoretical":[60],"guarantees":[61],"convergence":[63],"estimates":[68],"are":[69,74],"established,":[70],"simulation":[72],"results":[73],"presented":[75],"demonstrate":[77],"performance":[79],"technique.":[83]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2018-02-02T00:00:00"}