{"id":"https://openalex.org/W2104017958","doi":"https://doi.org/10.1109/cdc.2010.5717295","title":"A model-free robust policy iteration algorithm for optimal control of nonlinear systems","display_name":"A model-free robust policy iteration algorithm for optimal control of nonlinear systems","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W2104017958","doi":"https://doi.org/10.1109/cdc.2010.5717295","mag":"2104017958"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2010.5717295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2010.5717295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","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/A5034219830","display_name":"Shubhendu Bhasin","orcid":"https://orcid.org/0000-0002-8002-9684"},"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":true,"raw_author_name":"S. Bhasin","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, 32611-6250 USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, 32611-6250 USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110418596","display_name":"M. Johnson","orcid":null},"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":"M. Johnson","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, 32611-6250 USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, 32611-6250 USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032651215","display_name":"Warren E. Dixon","orcid":"https://orcid.org/0000-0002-5091-181X"},"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":"W. E. Dixon","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, 32611-6250 USA"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]},{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, University of Florida, Gainesville, 32611-6250 USA","institution_ids":["https://openalex.org/I33213144"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5034219830"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":4.1015,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.93989273,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3060","last_page":"3065"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":1.0,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9957000017166138,"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":0.9782000184059143,"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/identifier","display_name":"Identifier","score":0.7370531558990479},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6559329032897949},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6018602848052979},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.5976670384407043},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5893743634223938},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5585176944732666},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5540555715560913},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.45413076877593994},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4459279477596283},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4439302384853363},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4400154650211334},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4360577166080475},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34424105286598206},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3398430347442627},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.22369787096977234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1747172474861145}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.7370531558990479},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6559329032897949},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6018602848052979},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.5976670384407043},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5893743634223938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5585176944732666},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5540555715560913},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.45413076877593994},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4459279477596283},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4439302384853363},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4400154650211334},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4360577166080475},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34424105286598206},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3398430347442627},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.22369787096977234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1747172474861145},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2010.5717295","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2010.5717295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"49th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W18322812","https://openalex.org/W92805021","https://openalex.org/W120139811","https://openalex.org/W567213340","https://openalex.org/W1487127700","https://openalex.org/W1515851193","https://openalex.org/W1542432808","https://openalex.org/W1574514837","https://openalex.org/W1576452626","https://openalex.org/W1749408314","https://openalex.org/W1854776945","https://openalex.org/W1990005421","https://openalex.org/W2013184330","https://openalex.org/W2016360498","https://openalex.org/W2047090868","https://openalex.org/W2081514674","https://openalex.org/W2084378698","https://openalex.org/W2090167557","https://openalex.org/W2091565802","https://openalex.org/W2093831009","https://openalex.org/W2098301654","https://openalex.org/W2100677568","https://openalex.org/W2103496339","https://openalex.org/W2107674817","https://openalex.org/W2108286682","https://openalex.org/W2108794258","https://openalex.org/W2111034649","https://openalex.org/W2112246162","https://openalex.org/W2113501460","https://openalex.org/W2131030156","https://openalex.org/W2136064843","https://openalex.org/W2136909257","https://openalex.org/W2160561608","https://openalex.org/W2177721432","https://openalex.org/W3041202696","https://openalex.org/W3213472335","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W4244977694","https://openalex.org/W6629040409","https://openalex.org/W6634206955","https://openalex.org/W6634528131","https://openalex.org/W6673047230","https://openalex.org/W6804409665","https://openalex.org/W6823096664"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W1859185863","https://openalex.org/W3099153698","https://openalex.org/W4285537323","https://openalex.org/W2964126589","https://openalex.org/W1932159282","https://openalex.org/W4307691181","https://openalex.org/W3016225735"],"abstract_inverted_index":{"An":[0],"online":[1],"model-free":[2],"solution":[3],"is":[4,21,83,96,115],"developed":[5],"for":[6,12,65],"the":[7,25,46,58,66,86,94,99,103,112],"infinite-horizon":[8],"optimal":[9,90],"control":[10,91],"problem":[11],"continuous-time":[13],"nonlinear":[14],"systems.":[15],"A":[16],"novel":[17],"actor-critic-identifier":[18],"(ACI)":[19],"structure":[20],"used":[22,35],"to":[23,43,56],"implement":[24],"Policy":[26],"Iteration":[27],"algorithm,":[28],"wherein":[29],"two":[30],"neural":[31,40],"network":[32,41],"structures":[33,122],"are":[34,69,123],"-":[36],"a":[37,53,72,77],"robust":[38],"dynamic":[39],"(DNN)":[42],"asymptotically":[44],"identify":[45],"uncertain":[47],"system":[48,87,114],"with":[49],"additive":[50],"disturbances,":[51],"and":[52,102,120,128],"critic":[54,67,100,119],"NN":[55,68,101],"approximate":[57],"value":[59],"function.":[60],"The":[61,89,117],"weight":[62],"update":[63],"laws":[64],"generated":[70],"using":[71,98],"gradient-descent":[73],"method":[74],"based":[75],"on":[76],"modified":[78],"temporal":[79],"difference":[80],"error,":[81],"which":[82],"independent":[84],"of":[85,111],"dynamics.":[88],"law":[92],"(or":[93],"actor)":[95],"computed":[97],"identifier":[104,121],"DNN.":[105],"Uniformly":[106],"ultimately":[107],"bounded":[108],"(UUB)":[109],"stability":[110],"closed-loop":[113],"guaranteed.":[116],"actor,":[118],"implemented":[124],"in":[125],"real-time,":[126],"continuously":[127],"simultaneously.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}