{"id":"https://openalex.org/W2086297186","doi":"https://doi.org/10.1109/ijcnn.2013.6706755","title":"Solutions to finite horizon cost problems using actor-critic reinforcement learning","display_name":"Solutions to finite horizon cost problems using actor-critic reinforcement learning","publication_year":2013,"publication_date":"2013-08-01","ids":{"openalex":"https://openalex.org/W2086297186","doi":"https://doi.org/10.1109/ijcnn.2013.6706755","mag":"2086297186"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2013.6706755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2013.6706755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2013 International Joint Conference on Neural Networks (IJCNN)","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/A5028459687","display_name":"I. Grondman","orcid":null},"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":"Ivo Grondman","raw_affiliation_strings":["Delft Center for Systems and Control, Delft University of Technology, Delft, 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, 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/A5100717012","display_name":"Hao Xu","orcid":"https://orcid.org/0000-0003-4130-7925"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Xu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, USA","Dept. of Electr. & Comput. Eng., Missouri Univ. of Sci. & Technol., Rolla, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, USA","institution_ids":["https://openalex.org/I20382870"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Missouri Univ. of Sci. & Technol., Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078910343","display_name":"S. Jagannathan","orcid":"https://orcid.org/0000-0002-2310-3737"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarangapani Jagannathan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, USA","Dept. of Electr. & Comput. Eng., Missouri Univ. of Sci. & Technol., Rolla, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, USA","institution_ids":["https://openalex.org/I20382870"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Missouri Univ. of Sci. & Technol., Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"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 for Systems and Control, Delft University of Technology, Delft, 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, 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"]}]}],"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":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9987999796867371,"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":0.9987999796867371,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976999759674072,"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":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.873607873916626},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7674060463905334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.643401026725769},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6023193001747131},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5490449666976929},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5356898307800293},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5006155967712402},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.49383601546287537},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.46360576152801514},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.4552310109138489},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4481635093688965},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42928147315979004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.373300701379776},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24037283658981323},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09801608324050903}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.873607873916626},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7674060463905334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.643401026725769},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6023193001747131},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5490449666976929},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5356898307800293},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5006155967712402},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.49383601546287537},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.46360576152801514},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.4552310109138489},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4481635093688965},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42928147315979004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.373300701379776},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24037283658981323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09801608324050903},{"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/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},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2013.6706755","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2013.6706755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2013 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W35083779","https://openalex.org/W368265031","https://openalex.org/W1576452626","https://openalex.org/W1601081659","https://openalex.org/W1966086707","https://openalex.org/W1979638690","https://openalex.org/W2009303086","https://openalex.org/W2016211524","https://openalex.org/W2024780670","https://openalex.org/W2049474031","https://openalex.org/W2057484415","https://openalex.org/W2125944702","https://openalex.org/W2155027007","https://openalex.org/W2160522427","https://openalex.org/W2400458653","https://openalex.org/W2551230555","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W2906267174","https://openalex.org/W134501823","https://openalex.org/W2615656344","https://openalex.org/W2282793296","https://openalex.org/W187740018","https://openalex.org/W2013239059","https://openalex.org/W2295626654","https://openalex.org/W2162286586","https://openalex.org/W4286622840","https://openalex.org/W2536121351"],"abstract_inverted_index":{"Actor-critic":[0],"reinforcement":[1,38],"learning":[2,12,39,126,181],"algorithms":[3,111,162],"have":[4,73],"shown":[5],"to":[6,43,72,102,117,125],"be":[7,33,97],"a":[8,17,55,74,86,127,130,150,179],"successful":[9],"tool":[10],"in":[11],"the":[13,37,50,77,80,92,113,118,140,167,175],"optimal":[14,93,172],"control":[15,94,154],"for":[16,76],"range":[18],"of":[19,36,165,170,177],"(repetitive)":[20],"tasks":[21],"on":[22,129,149],"systems":[23],"with":[24,48,59],"(partially)":[25],"unknown":[26],"dynamics,":[27,142],"which":[28,89],"may":[29,31],"or":[30,137],"not":[32],"nonlinear.":[34],"Most":[35],"literature":[40],"published":[41],"up":[42],"this":[44],"point":[45],"only":[46],"deals":[47],"modeling":[49],"task":[51,128],"at":[52],"hand":[53],"as":[54],"Markov":[56],"decision":[57],"process":[58],"an":[60],"infinite":[61,114],"horizon":[62,115,120],"cost":[63,81],"function.":[64],"In":[65],"practice,":[66],"however,":[67],"it":[68],"is":[69,83,183],"sometimes":[70],"desired":[71],"solution":[75],"case":[78],"where":[79],"function":[82,146],"defined":[84],"over":[85],"finite":[87,119],"horizon,":[88],"means":[90],"that":[91,160],"problem":[95,155,169],"will":[96],"time-varying":[98,171],"and":[99,122],"thus":[100],"harder":[101],"solve.":[103],"This":[104],"paper":[105],"adapts":[106],"two":[107],"previously":[108],"introduced":[109],"actor-critic":[110,161],"from":[112],"setting":[116,121],"applies":[123],"them":[124],"nonlinear":[131,152],"system,":[132],"without":[133],"needing":[134],"any":[135],"assumptions":[136],"knowledge":[138],"about":[139],"system":[141],"using":[143,178],"radial":[144],"basis":[145],"networks.":[147],"Simulations":[148],"typical":[151],"motion":[153],"are":[156,163],"carried":[157],"out,":[158],"showing":[159],"capable":[164],"solving":[166],"difficult":[168],"control.":[173],"Moreover,":[174],"benefit":[176],"model":[180],"technique":[182],"shown.":[184]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}