{"id":"https://openalex.org/W2036110640","doi":"https://doi.org/10.1109/cdc.2013.6761042","title":"Reinforcement learning for sequential composition control","display_name":"Reinforcement learning for sequential composition control","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2036110640","doi":"https://doi.org/10.1109/cdc.2013.6761042","mag":"2036110640"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2013.6761042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2013.6761042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"52nd IEEE Conference on Decision and Control","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/A5038810887","display_name":"Esmaeil Najafi","orcid":"https://orcid.org/0000-0001-8719-5143"},"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":"Esmaeil Najafi","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","Delft Center for Systems and Control, Delft University of Technology Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046652464","display_name":"Gabriel A. D. Lopes","orcid":"https://orcid.org/0000-0002-2406-9489"},"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":"Gabriel A. D. Lopes","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","Delft Center for Systems and Control, Delft University of Technology Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology, Delft, CD, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology 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/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]},{"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":["IR","NL"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Department of Mechatronics Engineering, University of Tehran, Iran","Delft Center for Systems and Control, Delft University of Technology Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechatronics Engineering, University of Tehran, Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"Delft Center for Systems and Control, Delft University of Technology Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7265","last_page":"7270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9986000061035156,"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/T10142","display_name":"Formal Methods in Verification","score":0.9986000061035156,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9763000011444092,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8366461992263794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7695801854133606},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.5933140516281128},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5811951160430908},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5174870491027832},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.5093754529953003},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4349175691604614},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4266262352466583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38874560594558716},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.22520270943641663},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1252700388431549}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8366461992263794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7695801854133606},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.5933140516281128},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5811951160430908},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5174870491027832},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.5093754529953003},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4349175691604614},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4266262352466583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38874560594558716},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.22520270943641663},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1252700388431549},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2013.6761042","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2013.6761042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"52nd IEEE Conference on Decision and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W258022877","https://openalex.org/W1503973138","https://openalex.org/W1530240157","https://openalex.org/W1850243376","https://openalex.org/W1990388487","https://openalex.org/W2004463571","https://openalex.org/W2037635833","https://openalex.org/W2046376809","https://openalex.org/W2052843966","https://openalex.org/W2066126065","https://openalex.org/W2069522844","https://openalex.org/W2073384958","https://openalex.org/W2079042739","https://openalex.org/W2079497341","https://openalex.org/W2095487261","https://openalex.org/W2117795877","https://openalex.org/W2118937343","https://openalex.org/W2121863487","https://openalex.org/W2130578594","https://openalex.org/W2132714442","https://openalex.org/W2159461839","https://openalex.org/W2962709723","https://openalex.org/W4211221179","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4210912933","https://openalex.org/W1562959674","https://openalex.org/W2923653485","https://openalex.org/W2952472710","https://openalex.org/W3209094908","https://openalex.org/W4255994452","https://openalex.org/W4206669594","https://openalex.org/W3037422413","https://openalex.org/W2890179775","https://openalex.org/W2043161588"],"abstract_inverted_index":{"Sequential":[0],"composition":[1,25,49,72,82],"is":[2],"an":[3,85],"effective":[4],"strategy":[5,65],"for":[6,109],"addressing":[7],"complex":[8,12],"control":[9,32],"specifications":[10],"and":[11,21,34,56,89,106],"dynamical":[13],"systems":[14],"by":[15],"partitioning":[16],"the":[17,46,80,93],"problem":[18],"in":[19,92],"time":[20,54],"space.":[22],"Traditionally,":[23],"sequential":[24,48,71,81],"controllers":[26],"are":[27],"synthesized":[28],"offline":[29],"given":[30],"a":[31,35,63,69,110],"task":[33],"static":[36],"environment":[37],"with":[38],"possible":[39],"constraints.":[40],"Dynamical":[41],"environments":[42],"may":[43,52],"require":[44],"redesigning":[45],"entire":[47],"controller,":[50],"which":[51],"be":[53],"costly":[55],"inefficient.":[57],"In":[58],"this":[59],"paper":[60],"we":[61,87],"introduce":[62],"learning":[64],"to":[66],"augment":[67],"online":[68],"pre-designed":[70],"controller":[73,83],"based":[74,96],"on":[75,97],"reinforcement":[76],"learning.":[77,102],"By":[78],"interpreting":[79],"as":[84],"automaton,":[86],"add":[88],"delete":[90],"nodes":[91],"graph":[94],"online,":[95],"newly":[98],"acquired":[99],"knowledge":[100],"via":[101],"We":[103],"present":[104],"simulation":[105],"experimental":[107],"results":[108],"nonlinear":[111],"motion-control":[112],"system.":[113]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}