{"id":"https://openalex.org/W4382936355","doi":"https://doi.org/10.23919/acc55779.2023.10156188","title":"Nonuniqueness and Convergence to Equivalent Solutions in Observer-based Inverse Reinforcement Learning","display_name":"Nonuniqueness and Convergence to Equivalent Solutions in Observer-based Inverse Reinforcement Learning","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4382936355","doi":"https://doi.org/10.23919/acc55779.2023.10156188"},"language":"en","primary_location":{"id":"doi:10.23919/acc55779.2023.10156188","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc55779.2023.10156188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 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/A5046898662","display_name":"Jared Town","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":"Jared Town","raw_affiliation_strings":["Oklahoma State University,School of Mechanical and Aerospace Engineering,Stillwater,OK,USA","School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oklahoma State University,School of Mechanical and Aerospace Engineering,Stillwater,OK,USA","institution_ids":["https://openalex.org/I115475287"]},{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011744291","display_name":"Zachary Morrison","orcid":"https://orcid.org/0000-0001-9282-7248"},"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":"Zachary Morrison","raw_affiliation_strings":["Oklahoma State University,School of Mechanical and Aerospace Engineering,Stillwater,OK,USA","School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oklahoma State University,School of Mechanical and Aerospace Engineering,Stillwater,OK,USA","institution_ids":["https://openalex.org/I115475287"]},{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, 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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rushikesh Kamalapurkar","raw_affiliation_strings":["Oklahoma State University,School of Mechanical and Aerospace Engineering,Stillwater,OK,USA","School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oklahoma State University,School of Mechanical and Aerospace Engineering,Stillwater,OK,USA","institution_ids":["https://openalex.org/I115475287"]},{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I115475287"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3989","last_page":"3994"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9980999827384949,"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":0.9980999827384949,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9901999831199646,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9851999878883362,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7957932353019714},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6042354106903076},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5306455492973328},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.5291961431503296},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5046993494033813},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.4498162567615509},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.42854586243629456},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4264592230319977},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42350202798843384},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.40014901757240295},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3423754870891571},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2572665512561798},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08334776759147644}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7957932353019714},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6042354106903076},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5306455492973328},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.5291961431503296},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5046993494033813},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.4498162567615509},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.42854586243629456},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4264592230319977},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42350202798843384},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40014901757240295},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3423754870891571},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2572665512561798},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08334776759147644},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc55779.2023.10156188","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/acc55779.2023.10156188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1574928409","https://openalex.org/W1996625075","https://openalex.org/W1999874108","https://openalex.org/W2031571562","https://openalex.org/W2037997802","https://openalex.org/W2070469928","https://openalex.org/W2070832112","https://openalex.org/W2098774185","https://openalex.org/W2113023245","https://openalex.org/W2117675763","https://openalex.org/W2135046866","https://openalex.org/W2162009473","https://openalex.org/W2169498096","https://openalex.org/W2794108217","https://openalex.org/W2895649888","https://openalex.org/W2950989964","https://openalex.org/W3095316834","https://openalex.org/W3156476459","https://openalex.org/W3170519291","https://openalex.org/W3203504876","https://openalex.org/W4221041364","https://openalex.org/W4256202811","https://openalex.org/W4283835015","https://openalex.org/W6674884181","https://openalex.org/W6676728370","https://openalex.org/W6677555207","https://openalex.org/W6677631742","https://openalex.org/W6684097133","https://openalex.org/W6794270814","https://openalex.org/W7014182912","https://openalex.org/W7039619599"],"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/W2331917905","https://openalex.org/W3155039083","https://openalex.org/W1543136835","https://openalex.org/W1970914699"],"abstract_inverted_index":{"A":[0],"key":[1],"challenge":[2],"in":[3,13,41,49],"solving":[4],"the":[5,16,23,26,50,85,94,97],"deterministic":[6],"inverse":[7],"reinforcement":[8],"learning":[9],"problem":[10],"online":[11],"and":[12,31,87],"real-time":[14,53],"is":[15,69],"existence":[17],"of":[18,25,28,96],"non-unique":[19],"solutions.":[20,35],"Nonuniqueness":[21],"necessitates":[22],"study":[24],"notion":[27],"equivalent":[29,44],"solutions":[30,45,73],"convergence":[32,42],"to":[33,43,71,83,92],"such":[34],"While":[36],"offline":[37],"algorithms":[38],"that":[39,55,74],"result":[40],"have":[46],"been":[47],"developed":[48,70,82,98],"literature,":[51],"online,":[52],"techniques":[54],"address":[56],"nonuniqueness":[57],"are":[58,75,81,90],"not":[59],"available.":[60],"In":[61],"this":[62],"paper,":[63],"a":[64],"regularized":[65],"history":[66],"stack":[67],"observer":[68],"generate":[72],"approximately":[76],"equivalent.":[77],"Novel":[78],"data-richness":[79],"conditions":[80],"facilitate":[84],"analysis":[86],"simulation":[88],"results":[89],"provided":[91],"demonstrate":[93],"effectiveness":[95],"technique.":[99]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}