{"id":"https://openalex.org/W2046376809","doi":"https://doi.org/10.1109/tsmcc.2012.2218595","title":"A Survey of Actor-Critic Reinforcement Learning: Standard and Natural Policy Gradients","display_name":"A Survey of Actor-Critic Reinforcement Learning: Standard and Natural Policy Gradients","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2046376809","doi":"https://doi.org/10.1109/tsmcc.2012.2218595","mag":"2046376809"},"language":"en","primary_location":{"id":"doi:10.1109/tsmcc.2012.2218595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcc.2012.2218595","pdf_url":null,"source":{"id":"https://openalex.org/S4210227557","display_name":"IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)","issn_l":"1094-6977","issn":["1094-6977","1558-2442"],"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 C (Applications and Reviews)","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-00756747","any_repository_has_fulltext":true},"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, Netherlands"],"raw_orcid":null,"affiliations":[{"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/A5058935509","display_name":"Lucian Bu\u015foniu","orcid":"https://orcid.org/0000-0001-8017-1296"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I158333966","display_name":"Technical University of Cluj-Napoca","ror":"https://ror.org/03r8nwp71","country_code":"RO","type":"education","lineage":["https://openalex.org/I158333966"]},{"id":"https://openalex.org/I4210110792","display_name":"Centre de Recherche en Automatique de Nancy","ror":"https://ror.org/022r5hc56","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210099203","https://openalex.org/I4210100260","https://openalex.org/I4210110792","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR","RO"],"is_corresponding":false,"raw_author_name":"Lucian Busoniu","raw_affiliation_strings":["CRAN, UMR 7039 and CNRS, Universit\u00e9 de Lorraine, Vandoeuvre-les-Nancy, France","Department of Automation, Technical University of Cluj-Napoca, Cluj-Napoca, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRAN, UMR 7039 and CNRS, Universit\u00e9 de Lorraine, Vandoeuvre-les-Nancy, France","institution_ids":["https://openalex.org/I90183372","https://openalex.org/I1294671590","https://openalex.org/I4210110792"]},{"raw_affiliation_string":"Department of Automation, Technical University of Cluj-Napoca, Cluj-Napoca, Romania","institution_ids":["https://openalex.org/I158333966"]}]},{"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, Netherlands"],"raw_orcid":null,"affiliations":[{"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/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, Netherlands"],"raw_orcid":null,"affiliations":[{"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":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":22.515,"has_fulltext":false,"cited_by_count":1047,"citation_normalized_percentile":{"value":0.99474415,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"42","issue":"6","first_page":"1291","last_page":"1307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9936000108718872,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.9442999958992004,"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":0.9117099046707153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6518586277961731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5997880697250366},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4943089485168457},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.48315709829330444},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46732062101364136},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.42245250940322876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39524906873703003},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.30653780698776245},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.096996009349823}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9117099046707153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6518586277961731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5997880697250366},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4943089485168457},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.48315709829330444},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46732062101364136},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.42245250940322876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39524906873703003},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.30653780698776245},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.096996009349823},{"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tsmcc.2012.2218595","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmcc.2012.2218595","pdf_url":null,"source":{"id":"https://openalex.org/S4210227557","display_name":"IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)","issn_l":"1094-6977","issn":["1094-6977","1558-2442"],"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 C (Applications and Reviews)","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-00756747v1","is_oa":true,"landing_page_url":"https://hal.science/hal-00756747","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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 C: Applications and Reviews, 2012, 42 (6), pp.1291-1307. ⟨10.1109/TSMCC.2012.2218595⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00756747v1","is_oa":true,"landing_page_url":"https://hal.science/hal-00756747","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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 C: Applications and Reviews, 2012, 42 (6), pp.1291-1307. ⟨10.1109/TSMCC.2012.2218595⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/12","display_name":"Responsible consumption and production"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":107,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W263682811","https://openalex.org/W1499669280","https://openalex.org/W1547105496","https://openalex.org/W1550946783","https://openalex.org/W1564755532","https://openalex.org/W1566185995","https://openalex.org/W1570704007","https://openalex.org/W1578205364","https://openalex.org/W1594783240","https://openalex.org/W1600532803","https://openalex.org/W1616818660","https://openalex.org/W1626155273","https://openalex.org/W1646707810","https://openalex.org/W1751034982","https://openalex.org/W1967459934","https://openalex.org/W1970789124","https://openalex.org/W1983523797","https://openalex.org/W1984986877","https://openalex.org/W1990437501","https://openalex.org/W1994923984","https://openalex.org/W2006036383","https://openalex.org/W2009303086","https://openalex.org/W2012392077","https://openalex.org/W2039091159","https://openalex.org/W2054940200","https://openalex.org/W2062706881","https://openalex.org/W2072931156","https://openalex.org/W2073384958","https://openalex.org/W2077891204","https://openalex.org/W2080759927","https://openalex.org/W2082261506","https://openalex.org/W2091565802","https://openalex.org/W2094387729","https://openalex.org/W2095487261","https://openalex.org/W2095773380","https://openalex.org/W2098432798","https://openalex.org/W2099196192","https://openalex.org/W2099602914","https://openalex.org/W2100677568","https://openalex.org/W2102988084","https://openalex.org/W2103451687","https://openalex.org/W2106432400","https://openalex.org/W2106471678","https://openalex.org/W2107726111","https://openalex.org/W2109330238","https://openalex.org/W2119717200","https://openalex.org/W2120070743","https://openalex.org/W2121863487","https://openalex.org/W2124144580","https://openalex.org/W2124289529","https://openalex.org/W2125612430","https://openalex.org/W2125922627","https://openalex.org/W2126330148","https://openalex.org/W2130801532","https://openalex.org/W2131030156","https://openalex.org/W2132011051","https://openalex.org/W2132351269","https://openalex.org/W2136602922","https://openalex.org/W2139418546","https://openalex.org/W2140135625","https://openalex.org/W2143490508","https://openalex.org/W2144446635","https://openalex.org/W2144801703","https://openalex.org/W2146737184","https://openalex.org/W2149174281","https://openalex.org/W2150999967","https://openalex.org/W2151661095","https://openalex.org/W2153733100","https://openalex.org/W2155027007","https://openalex.org/W2156321584","https://openalex.org/W2157580235","https://openalex.org/W2157701998","https://openalex.org/W2158462832","https://openalex.org/W2161270100","https://openalex.org/W2164056559","https://openalex.org/W2169982856","https://openalex.org/W2172968643","https://openalex.org/W2173945562","https://openalex.org/W2259289169","https://openalex.org/W2764902300","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W3103182070","https://openalex.org/W3139377883","https://openalex.org/W3198350258","https://openalex.org/W4211221179","https://openalex.org/W4214717370","https://openalex.org/W4243489454","https://openalex.org/W4365806715","https://openalex.org/W6629881138","https://openalex.org/W6633018774","https://openalex.org/W6633472939","https://openalex.org/W6635508374","https://openalex.org/W6674743605","https://openalex.org/W6674876905","https://openalex.org/W6675256285","https://openalex.org/W6676422638","https://openalex.org/W6678573530","https://openalex.org/W6679257226","https://openalex.org/W6680194329","https://openalex.org/W6680657880","https://openalex.org/W6682939520","https://openalex.org/W6683204974","https://openalex.org/W6684199269","https://openalex.org/W6792155000","https://openalex.org/W6824966504"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W1508899372"],"abstract_inverted_index":{"Policy-gradient-based":[0],"actor-critic":[1,58,72,115,133,147],"algorithms":[2,8,59,134,148],"are":[3],"amongst":[4],"the":[5,10,66,69,106,112,120,123,136,152],"most":[6],"popular":[7],"in":[9,32,60,82,90],"reinforcement":[11,47,109],"learning":[12,48,110],"framework.":[13],"Their":[14],"advantage":[15],"of":[16,68,71,108,114,122,142,158],"being":[17],"able":[18],"to":[19,57,92],"search":[20],"for":[21],"optimal":[22],"policies":[23],"using":[24],"low-variance":[25],"gradient":[26],"estimates":[27],"has":[28,127],"made":[29,128],"them":[30],"useful":[31],"several":[33,143],"real-life":[34],"applications,":[35],"such":[36],"as":[37],"robotics,":[38],"power":[39],"control,":[40],"and":[41,86,97,111,145,151,161],"finance.":[42],"Although":[43],"general":[44],"surveys":[45],"on":[46,77,105,164],"techniques":[49],"already":[50],"exist,":[51],"no":[52],"survey":[53],"is":[54,149],"specifically":[55],"dedicated":[56],"particular.":[61],"This":[62],"paper,":[63],"therefore,":[64],"describes":[65,119],"state":[67,96],"art":[70],"algorithms,":[73,116],"with":[74,94,102,155],"a":[75,103,162],"focus":[76],"methods":[78],"that":[79],"can":[80],"work":[81],"an":[83,156],"online":[84],"setting":[85],"use":[87],"function":[88],"approximation":[89],"order":[91],"deal":[93],"continuous":[95],"action":[98],"spaces.":[99],"After":[100],"starting":[101],"discussion":[104,163],"concepts":[107],"origins":[113],"this":[117],"paper":[118,153],"workings":[121],"natural":[124,146],"gradient,":[125],"which":[126],"its":[129],"way":[130],"into":[131],"many":[132],"over":[135],"past":[137],"few":[138],"years.":[139],"A":[140],"review":[141],"standard":[144],"given,":[150],"concludes":[154],"overview":[157],"application":[159],"areas":[160],"open":[165],"issues.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":34},{"year":2025,"cited_by_count":117},{"year":2024,"cited_by_count":138},{"year":2023,"cited_by_count":156},{"year":2022,"cited_by_count":111},{"year":2021,"cited_by_count":128},{"year":2020,"cited_by_count":124},{"year":2019,"cited_by_count":86},{"year":2018,"cited_by_count":52},{"year":2017,"cited_by_count":34},{"year":2016,"cited_by_count":18},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":23},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}