{"id":"https://openalex.org/W4399768031","doi":"https://doi.org/10.1109/tnnls.2024.3409182","title":"Inverse Value Iteration and <i>Q</i>-Learning: Algorithms, Stability, and Robustness","display_name":"Inverse Value Iteration and <i>Q</i>-Learning: Algorithms, Stability, and Robustness","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4399768031","doi":"https://doi.org/10.1109/tnnls.2024.3409182","pmid":"https://pubmed.ncbi.nlm.nih.gov/38889021"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3409182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3409182","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5001862814","display_name":"Bosen Lian","orcid":"https://orcid.org/0000-0002-3275-9551"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bosen Lian","raw_affiliation_strings":["Electrical and Computer Engineering Department, Auburn University, Auburn, AL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3275-9551","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Auburn University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102973745","display_name":"Wenqian Xue","orcid":"https://orcid.org/0000-0002-3670-3854"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenqian Xue","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of Florida, Gainesville, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3670-3854","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["The University of Texas at Arlington Research Institute, Fort Worth, TX, USA","The University of Texas, Arlington Research Institute, Fort Worth, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-4074-1615","affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington Research Institute, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"The University of Texas, Arlington Research Institute, Fort Worth, TX, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053089078","display_name":"Ali Davoudi","orcid":"https://orcid.org/0000-0003-2951-442X"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ali Davoudi","raw_affiliation_strings":["The University of Texas at Arlington Research Institute, Fort Worth, TX, USA","The University of Texas, Arlington Research Institute, Fort Worth, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-2951-442X","affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington Research Institute, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I189196454"]},{"raw_affiliation_string":"The University of Texas, Arlington Research Institute, Fort Worth, TX, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8338,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.9126718,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"36","issue":"4","first_page":"6970","last_page":"6980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.9921000003814697,"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"}},"topics":[{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.9921000003814697,"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":0.9751999974250793,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9685999751091003,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7707018852233887},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6286394000053406},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.6138601899147034},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.568118691444397},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5626219511032104},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49551475048065186},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.46961599588394165},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.44201403856277466},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.43276089429855347},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35994505882263184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19288313388824463},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14981356263160706}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7707018852233887},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6286394000053406},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.6138601899147034},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.568118691444397},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5626219511032104},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49551475048065186},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.46961599588394165},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.44201403856277466},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.43276089429855347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35994505882263184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19288313388824463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14981356263160706},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3409182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3409182","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38889021","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38889021","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1742339193","display_name":null,"funder_award_id":"W911NF-20-1-0132","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1616818660","https://openalex.org/W1970916399","https://openalex.org/W1978884435","https://openalex.org/W2015569921","https://openalex.org/W2037025184","https://openalex.org/W2058966437","https://openalex.org/W2063358594","https://openalex.org/W2148439597","https://openalex.org/W2784079428","https://openalex.org/W2802441085","https://openalex.org/W2810171094","https://openalex.org/W2886235386","https://openalex.org/W2897702175","https://openalex.org/W2917945410","https://openalex.org/W2950438991","https://openalex.org/W2966348706","https://openalex.org/W3016893731","https://openalex.org/W3037298378","https://openalex.org/W3095316834","https://openalex.org/W3121634745","https://openalex.org/W3121683757","https://openalex.org/W3137642493","https://openalex.org/W3138984732","https://openalex.org/W3156476459","https://openalex.org/W3157204454","https://openalex.org/W3161299873","https://openalex.org/W3168011924","https://openalex.org/W3195322794","https://openalex.org/W3203504876","https://openalex.org/W4221041364","https://openalex.org/W4318604516","https://openalex.org/W4361765877","https://openalex.org/W4381198967","https://openalex.org/W4383652256","https://openalex.org/W4386702747","https://openalex.org/W4388712152","https://openalex.org/W4390120077","https://openalex.org/W6640443443","https://openalex.org/W6674884181","https://openalex.org/W6677555207","https://openalex.org/W6685962732","https://openalex.org/W6781315541","https://openalex.org/W6798405520","https://openalex.org/W7024761944"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"This":[0,36],"article":[1,37],"proposes":[2],"a":[3,40],"data-driven":[4],"model-free":[5,54],"inverse":[6,42,55,78],"Q-learning":[7,56],"algorithm":[8,26,57],"for":[9,104],"continuous-time":[10],"linear":[11],"quadratic":[12],"regulators":[13],"(LQRs).":[14],"Using":[15],"an":[16,52],"agent's":[17,48,63],"trajectories":[18],"of":[19,127],"states":[20],"and":[21,102,113,119,125],"optimal":[22],"control":[23,100],"inputs,":[24],"the":[25,33,47,62,68,76,86,123,128],"reconstructs":[27],"its":[28],"cost":[29,64],"function":[30,65],"that":[31],"captures":[32],"same":[34],"trajectories.":[35,70],"first":[38],"poses":[39],"model-based":[41],"value":[43],"iteration":[44],"scheme":[45],"using":[46,67],"system":[49],"dynamics.":[50],"Then,":[51],"online":[53],"is":[58,72],"developed":[59],"to":[60],"recover":[61],"only":[66],"demonstrated":[69],"It":[71],"more":[73],"efficient":[74],"than":[75],"existing":[77],"reinforcement":[79],"learning":[80],"(RL)":[81],"algorithms":[82,94],"as":[83],"it":[84],"avoids":[85],"repetitive":[87],"RL":[88],"in":[89],"inner":[90],"loops.":[91],"The":[92,107],"proposed":[93,108,129],"do":[95],"not":[96],"need":[97],"initial":[98],"stabilizing":[99],"policies":[101],"solve":[103],"unbiased":[105],"solutions.":[106],"algorithm's":[109],"asymptotic":[110],"stability,":[111],"convergence,":[112],"robustness":[114],"are":[115],"guaranteed.":[116],"Theoretical":[117],"analysis":[118],"simulation":[120],"examples":[121],"show":[122],"effectiveness":[124],"advantages":[126],"algorithms.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}