{"id":"https://openalex.org/W4388052875","doi":"https://doi.org/10.1109/tcyb.2023.3324601","title":"Data-Efficient Reinforcement Learning for Complex Nonlinear Systems","display_name":"Data-Efficient Reinforcement Learning for Complex Nonlinear Systems","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388052875","doi":"https://doi.org/10.1109/tcyb.2023.3324601","pmid":"https://pubmed.ncbi.nlm.nih.gov/37906478"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2023.3324601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2023.3324601","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","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/A5080358912","display_name":"Vrushabh S. Donge","orcid":"https://orcid.org/0000-0003-0606-2803"},"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":"Vrushabh S. Donge","raw_affiliation_strings":["Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-0606-2803","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","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":["Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3275-9551","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Auburn University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]}]},{"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":["Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-4074-1615","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"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":["Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-2951-442X","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8081,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.93799426,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"54","issue":"3","first_page":"1391","last_page":"1402"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":1.0,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":1.0,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10305","display_name":"Power System Optimization and Stability","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10928","display_name":"Probabilistic and Robust Engineering Design","score":0.9793000221252441,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8783926367759705},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.6954731941223145},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6854674816131592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6320668458938599},{"id":"https://openalex.org/keywords/eigenfunction","display_name":"Eigenfunction","score":0.5715062022209167},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4687143862247467},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.40786972641944885},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40711331367492676},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.32294875383377075},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29959845542907715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28597313165664673},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15434062480926514},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.10432133078575134}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8783926367759705},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.6954731941223145},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6854674816131592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6320668458938599},{"id":"https://openalex.org/C128803854","wikidata":"https://www.wikidata.org/wiki/Q1307821","display_name":"Eigenfunction","level":3,"score":0.5715062022209167},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4687143862247467},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.40786972641944885},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40711331367492676},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32294875383377075},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29959845542907715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28597313165664673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15434062480926514},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.10432133078575134},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":2,"locations":[{"id":"doi:10.1109/tcyb.2023.3324601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2023.3324601","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:37906478","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37906478","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 cybernetics","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1410907832","https://openalex.org/W1591018827","https://openalex.org/W1612466322","https://openalex.org/W1616818660","https://openalex.org/W1723433682","https://openalex.org/W1997054581","https://openalex.org/W2004026774","https://openalex.org/W2006749870","https://openalex.org/W2011866373","https://openalex.org/W2012451615","https://openalex.org/W2014356541","https://openalex.org/W2059316647","https://openalex.org/W2064733273","https://openalex.org/W2078898317","https://openalex.org/W2131684723","https://openalex.org/W2164954534","https://openalex.org/W2414431373","https://openalex.org/W2484646121","https://openalex.org/W2547247639","https://openalex.org/W2561027863","https://openalex.org/W2772589676","https://openalex.org/W2777417212","https://openalex.org/W2889834506","https://openalex.org/W2911792890","https://openalex.org/W2912832158","https://openalex.org/W2966348706","https://openalex.org/W2998579696","https://openalex.org/W3006550916","https://openalex.org/W3038118776","https://openalex.org/W3082482838","https://openalex.org/W3094377013","https://openalex.org/W3098172061","https://openalex.org/W3099803807","https://openalex.org/W3106039153","https://openalex.org/W3118303791","https://openalex.org/W3122575011","https://openalex.org/W3124444594","https://openalex.org/W3126334423","https://openalex.org/W3136945292","https://openalex.org/W3161299873","https://openalex.org/W3196755144","https://openalex.org/W4200574011","https://openalex.org/W4206184777","https://openalex.org/W4210274507","https://openalex.org/W4210727699","https://openalex.org/W4214717370","https://openalex.org/W4220727796","https://openalex.org/W4229057997","https://openalex.org/W4256433147","https://openalex.org/W4283835015","https://openalex.org/W4284675915","https://openalex.org/W4285156565","https://openalex.org/W4286781802","https://openalex.org/W4291653018","https://openalex.org/W4307776787","https://openalex.org/W4316496288","https://openalex.org/W4328007490","https://openalex.org/W4381162568","https://openalex.org/W6602152948","https://openalex.org/W6681190598","https://openalex.org/W6756754374"],"related_works":["https://openalex.org/W2245403906","https://openalex.org/W2393344178","https://openalex.org/W2495930062","https://openalex.org/W2051796801","https://openalex.org/W2057370678","https://openalex.org/W4206553170","https://openalex.org/W2089206232","https://openalex.org/W3120985700","https://openalex.org/W4221121299","https://openalex.org/W2068693753"],"abstract_inverted_index":{"This":[0,68],"article":[1],"proposes":[2],"a":[3,38,63],"data-efficient":[4,56,99],"model-free":[5,98],"reinforcement":[6],"learning":[7],"(RL)":[8],"algorithm":[9,69],"using":[10],"Koopman":[11,88],"operators":[12],"for":[13,78,90],"complex":[14],"nonlinear":[15,24],"systems.":[16],"A":[17],"high-dimensional":[18],"data-driven":[19,39],"optimal":[20,79],"control":[21,80,109],"of":[22,86,110],"the":[23,32,55,75,87,96,107,111],"system":[25,34,66],"is":[26],"developed":[27],"by":[28],"lifting":[29],"it":[30],"into":[31],"linear":[33,65],"model.":[35,67],"We":[36,102],"use":[37],"model-based":[40],"RL":[41,57,100],"framework":[42,105],"to":[43],"derive":[44],"an":[45],"off-policy":[46],"Bellman":[47],"equation.":[48],"Building":[49],"upon":[50],"this":[51],"equation,":[52],"we":[53],"deduce":[54],"algorithm,":[58],"which":[59],"does":[60],"not":[61],"need":[62],"Koopman-built":[64],"preserves":[70],"dynamic":[71],"information":[72],"while":[73],"reducing":[74],"required":[76],"data":[77],"learning.":[81],"Numerical":[82],"and":[83],"theoretical":[84],"analyses":[85],"eigenfunctions":[89],"dataset":[91],"truncation":[92],"are":[93],"discussed":[94],"in":[95],"proposed":[97],"algorithm.":[101],"validate":[103],"our":[104],"on":[106],"excitation":[108],"power":[112],"system.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":8}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}