{"id":"https://openalex.org/W2566089760","doi":null,"title":"Actor-citic agorithms","display_name":"Actor-citic agorithms","publication_year":1999,"publication_date":"1999-11-29","ids":{"openalex":"https://openalex.org/W2566089760","mag":"2566089760"},"language":"en","primary_location":{"id":"mag:2566089760","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=3009657.3009799","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5034972143","display_name":"Vijay R. Konda","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijay R. Konda","raw_affiliation_strings":["Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, Cambridge, MA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, Cambridge, MA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108523422","display_name":"John N. Tsitsiklis","orcid":"https://orcid.org/0000-0003-2658-8239","observed_orcids":["https://orcid.org/0000-0003-2658-8239"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John N. Tsitsiklis","raw_affiliation_strings":["Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, Cambridge, MA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, Cambridge, MA#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.35917952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1008","last_page":"1014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8705999851226807,"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":0.8705999851226807,"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":0.1234000027179718,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.004600000102072954,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/actor-critic-algorithms","display_name":"actor-critic algorithms","score":0.996999979019165},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8659999966621399},{"id":"https://openalex.org/keywords/simulation-optimization","display_name":"simulation-based optimization","score":0.8629999756813049},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.7889999747276306},{"id":"https://openalex.org/keywords/linearization","display_name":"linearization","score":0.8809999823570251},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.656000018119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6520915031433105},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6452572345733643},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.63680100440979},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6187567710876465},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6157259345054626},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5414751172065735},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47570547461509705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4492076337337494},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41676467657089233},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2630612552165985},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2417527735233307},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2566089760","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=3009657.3009799","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1576452626","https://openalex.org/W2082261506","https://openalex.org/W2094364653","https://openalex.org/W2119717200","https://openalex.org/W2139418546","https://openalex.org/W2155027007","https://openalex.org/W2160067530","https://openalex.org/W2171033527","https://openalex.org/W2173945562","https://openalex.org/W2561625472","https://openalex.org/W4246388106"],"related_works":["https://openalex.org/W7095298065","https://openalex.org/W2009303086","https://openalex.org/W2156737235","https://openalex.org/W2047364871","https://openalex.org/W2082261506","https://openalex.org/W7100996738","https://openalex.org/W2063123975","https://openalex.org/W7100180512","https://openalex.org/W2256989395","https://openalex.org/W2962840509"],"abstract_inverted_index":{"We":[0,58,79],"propose":[1],"and":[2,41,85],"analyze":[3],"a":[4,13,18,37,68],"class":[5],"of":[6,12,21,74,76],"actor-critic":[7],"algorithms":[8,28],"for":[9,63],"simulation-based":[10],"optimization":[11],"Markov":[14],"decision":[15],"process":[16],"over":[17],"parameterized":[19],"family":[20],"randomized":[22],"stationary":[23],"policies.":[24],"These":[25],"are":[26],"two-time-scale":[27],"in":[29,46],"which":[30],"the":[31,42,56,61,64,72,77],"critic":[32,65],"uses":[33],"TD":[34],"learning":[35],"with":[36],"linear":[38],"approximation":[39],"architecture":[40],"actor":[43],"is":[44],"updated":[45],"an":[47],"approximate":[48],"gradient":[49],"direction":[50],"based":[51],"on":[52],"information":[53],"provided":[54],"by":[55,71,81],"critic.":[57],"show":[59],"that":[60],"features":[62],"should":[66],"span":[67],"subspace":[69],"prescribed":[70],"choice":[73],"parameterization":[75],"actor.":[78],"conclude":[80],"discussing":[82],"convergence":[83],"properties":[84],"some":[86],"open":[87],"problems.":[88]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2017-01-06T00:00:00"}