{"id":"https://openalex.org/W2108051346","doi":"https://doi.org/10.1109/tsmcb.2010.2050586","title":"Cross-Entropy Optimization of Control Policies With Adaptive Basis Functions","display_name":"Cross-Entropy Optimization of Control Policies With Adaptive Basis Functions","publication_year":2010,"publication_date":"2010-06-25","ids":{"openalex":"https://openalex.org/W2108051346","doi":"https://doi.org/10.1109/tsmcb.2010.2050586","mag":"2108051346","pmid":"https://pubmed.ncbi.nlm.nih.gov/20570774"},"language":"en","primary_location":{"id":"doi:10.1109/tsmcb.2010.2050586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcb.2010.2050586","pdf_url":null,"source":{"id":"https://openalex.org/S4210170378","display_name":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","issn_l":"1083-4419","issn":["1083-4419","1941-0492"],"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 Systems, Man, and Cybernetics, Part B (Cybernetics)","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://orbi.uliege.be/handle/2268/84092","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lucian Busoniu","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, 2628 CD Delft, The Netherlands. i.l.busoniu@tudelft.nl","Delft Center of Systems and Control, Delft University of Technnology, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, 2628 CD Delft, The Netherlands. i.l.busoniu@tudelft.nl","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center of Systems and Control, Delft University of Technnology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077011518","display_name":"Damien Ernst","orcid":"https://orcid.org/0000-0002-3035-8260"},"institutions":[{"id":"https://openalex.org/I157674565","display_name":"University of Li\u00e8ge","ror":"https://ror.org/00afp2z80","country_code":"BE","type":"education","lineage":["https://openalex.org/I157674565"]},{"id":"https://openalex.org/I17653759","display_name":"Fund for Scientific Research","ror":"https://ror.org/03q83t159","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I17653759"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Damien Ernst","raw_affiliation_strings":["Belgian National Fund of Scientific Research, FRS-FNRS, Brussels, Belgium","Systems and Modeling Research Unit, University of Li\u00e8ge, Liege, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Belgian National Fund of Scientific Research, FRS-FNRS, Brussels, Belgium","institution_ids":["https://openalex.org/I17653759"]},{"raw_affiliation_string":"Systems and Modeling Research Unit, University of Li\u00e8ge, Liege, Belgium","institution_ids":["https://openalex.org/I157674565"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026547410","display_name":"Bart De Schutter","orcid":"https://orcid.org/0000-0001-9867-6196"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bart De Schutter","raw_affiliation_strings":["Marine and Transport Technology Department, Delft University of Technnology, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Marine and Transport Technology Department, Delft University of Technnology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Delft Center of Systems and Control, Delft University of Technnology, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center of Systems and Control, Delft University of Technnology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.2656,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.97499269,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"41","issue":"1","first_page":"196","last_page":"209"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9984999895095825,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.995199978351593,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9868999719619751,"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/mathematical-optimization","display_name":"Mathematical optimization","score":0.6778900027275085},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5003118515014648},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.48666244745254517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4744908809661865},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.47019800543785095},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4547441005706787},{"id":"https://openalex.org/keywords/equidistant","display_name":"Equidistant","score":0.4501849412918091},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41198965907096863},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.3877711594104767},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2888021469116211},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13902336359024048}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6778900027275085},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5003118515014648},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.48666244745254517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4744908809661865},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.47019800543785095},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4547441005706787},{"id":"https://openalex.org/C158245278","wikidata":"https://www.wikidata.org/wiki/Q4386982","display_name":"Equidistant","level":2,"score":0.4501849412918091},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41198965907096863},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3877711594104767},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2888021469116211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13902336359024048},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tsmcb.2010.2050586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcb.2010.2050586","pdf_url":null,"source":{"id":"https://openalex.org/S4210170378","display_name":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","issn_l":"1083-4419","issn":["1083-4419","1941-0492"],"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 Systems, Man, and Cybernetics, Part B (Cybernetics)","raw_type":"journal-article"},{"id":"pmid:20570774","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20570774","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 systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.384.2704","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.384.2704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcsc.tudelft.nl/~bdeschutter/pub/rep/10_004.pdf","raw_type":"text"},{"id":"pmh:oai:orbi.ulg.ac.be:2268/84092","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/84092","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Systems, Man and Cybernetics. Part B, Cybernetics, 41 (1), 196-209 (2011-02)","raw_type":"http://purl.org/coar/resource_type/c_6501"}],"best_oa_location":{"id":"pmh:oai:orbi.ulg.ac.be:2268/84092","is_oa":true,"landing_page_url":"https://orbi.uliege.be/handle/2268/84092","pdf_url":null,"source":{"id":"https://openalex.org/S4306400651","display_name":"Open Repository and Bibliography (University of Li\u00e8ge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I157674565","host_organization_name":"University of Li\u00e8ge","host_organization_lineage":["https://openalex.org/I157674565"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Systems, Man and Cybernetics. Part B, Cybernetics, 41 (1), 196-209 (2011-02)","raw_type":"http://purl.org/coar/resource_type/c_6501"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W111165306","https://openalex.org/W1499408472","https://openalex.org/W1502364872","https://openalex.org/W1544598807","https://openalex.org/W1550698229","https://openalex.org/W1552830313","https://openalex.org/W1554366315","https://openalex.org/W1576452626","https://openalex.org/W1601974704","https://openalex.org/W1604314819","https://openalex.org/W1986984034","https://openalex.org/W1998172110","https://openalex.org/W2009303086","https://openalex.org/W2027968610","https://openalex.org/W2098432798","https://openalex.org/W2100857832","https://openalex.org/W2104921316","https://openalex.org/W2107726111","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2130094217","https://openalex.org/W2131490088","https://openalex.org/W2131653110","https://openalex.org/W2133615895","https://openalex.org/W2134289401","https://openalex.org/W2134569556","https://openalex.org/W2135721773","https://openalex.org/W2135826251","https://openalex.org/W2137093764","https://openalex.org/W2143803054","https://openalex.org/W2146737184","https://openalex.org/W2155027007","https://openalex.org/W2161795906","https://openalex.org/W2163302320","https://openalex.org/W2169982856","https://openalex.org/W2172968643","https://openalex.org/W2333635821","https://openalex.org/W3027095131","https://openalex.org/W3099235411","https://openalex.org/W3125826253","https://openalex.org/W4214717370","https://openalex.org/W4230722622","https://openalex.org/W4242606736","https://openalex.org/W4245296547","https://openalex.org/W4251751827","https://openalex.org/W4285719527","https://openalex.org/W6630125228","https://openalex.org/W6635991215","https://openalex.org/W6646985475","https://openalex.org/W6677737365","https://openalex.org/W6679703492","https://openalex.org/W6680509635","https://openalex.org/W6681183203","https://openalex.org/W6683841269","https://openalex.org/W6684126333"],"related_works":["https://openalex.org/W2055230676","https://openalex.org/W2373708349","https://openalex.org/W2370379095","https://openalex.org/W2385837322","https://openalex.org/W3041490575","https://openalex.org/W2970690932","https://openalex.org/W4321135767","https://openalex.org/W2069619724","https://openalex.org/W2086372684","https://openalex.org/W2994927414"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"an":[3],"algorithm":[4,18,121,178],"for":[5,20,109,122,140],"direct":[6],"search":[7,125,159,173],"of":[8,33,48,62,75,104,152],"control":[9],"policies":[10,95,146],"in":[11,56,132],"continuous-state":[12],"discrete-action":[13],"Markov":[14],"decision":[15],"processes.":[16],"The":[17,46,83,107,119],"looks":[19],"the":[21,49,60,63,71,76,80,89,94],"best":[22],"closed-loop":[23],"policy":[24,124,158,172],"that":[25],"can":[26],"be":[27],"represented":[28],"using":[29,115],"a":[30,38,101,149,175],"given":[31],"number":[32,53,151],"basis":[34],"functions":[35],"(BFs),":[36],"where":[37],"discrete":[39],"action":[40,81],"is":[41,67,85,113,129],"assigned":[42],"to":[43,136],"each":[44,110],"BF.":[45],"type":[47],"BFs":[50,128,163],"and":[51,58,73,92,170],"their":[52,97],"are":[54],"specified":[55],"advance":[57],"determine":[59],"complexity":[61],"representation.":[64],"Considerable":[65],"flexibility":[66],"achieved":[68],"by":[69,96],"optimizing":[70],"locations":[72],"shapes":[74],"BFs,":[77,169],"together":[78],"with":[79,88,126,134,147,167,174],"assignments.":[82],"optimization":[84,177],"carried":[86],"out":[87],"cross-entropy":[90,123,157],"method":[91],"evaluates":[93],"empirical":[98],"return":[99,108],"from":[100],"representative":[102,111],"set":[103],"initial":[105],"states.":[106],"state":[112,138],"estimated":[114],"Monte":[116],"Carlo":[117],"simulations.":[118],"resulting":[120],"adaptive":[127],"extensively":[130],"evaluated":[131],"problems":[133],"two":[135],"six":[137],"variables,":[139],"which":[141],"it":[142],"reliably":[143],"obtains":[144],"good":[145],"only":[148],"small":[150],"BFs.":[153],"In":[154],"these":[155],"experiments,":[156],"requires":[160],"vastly":[161],"fewer":[162],"than":[164],"value-function":[165],"techniques":[166],"equidistant":[168],"outperforms":[171],"competing":[176],"called":[179],"DIRECT.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":5}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}