{"id":"https://openalex.org/W2082261506","doi":"https://doi.org/10.1137/s036301299731669x","title":"Actor-Critic--Type Learning Algorithms for Markov Decision Processes","display_name":"Actor-Critic--Type Learning Algorithms for Markov Decision Processes","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W2082261506","doi":"https://doi.org/10.1137/s036301299731669x","mag":"2082261506"},"language":"en","primary_location":{"id":"doi:10.1137/s036301299731669x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/s036301299731669x","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"},"type":"article","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/A5019535240","display_name":"Vijaymohan R. Konda","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vijaymohan R. Konda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018541798","display_name":"Vivek S. Borkar","orcid":"https://orcid.org/0000-0003-0756-5402"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vivek S. Borkar","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019535240"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.5114,"has_fulltext":false,"cited_by_count":238,"citation_normalized_percentile":{"value":0.98777964,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"38","issue":"1","first_page":"94","last_page":"123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9912999868392944,"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":0.9912999868392944,"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":0.9467999935150146,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9438999891281128,"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/markov-decision-process","display_name":"Markov decision process","score":0.8468878865242004},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5723925232887268},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5304450392723083},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5004076957702637},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4923661947250366},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.48175787925720215},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.464286208152771},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4502134919166565},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.43689629435539246},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4354623556137085},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4200612008571625},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41526028513908386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.386172354221344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34256595373153687}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8468878865242004},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5723925232887268},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5304450392723083},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5004076957702637},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4923661947250366},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.48175787925720215},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.464286208152771},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4502134919166565},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.43689629435539246},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4354623556137085},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4200612008571625},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41526028513908386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.386172354221344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34256595373153687},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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":1,"locations":[{"id":"doi:10.1137/s036301299731669x","is_oa":false,"landing_page_url":"https://doi.org/10.1137/s036301299731669x","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Control and Optimization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W649943522","https://openalex.org/W1595277102","https://openalex.org/W1967530463","https://openalex.org/W2014157641","https://openalex.org/W2015836240","https://openalex.org/W2047364871","https://openalex.org/W2059287472","https://openalex.org/W2065134213","https://openalex.org/W2073519119","https://openalex.org/W2080631849","https://openalex.org/W2081287319","https://openalex.org/W2081947709","https://openalex.org/W2082261506","https://openalex.org/W2090089645","https://openalex.org/W2094364653","https://openalex.org/W2102982586","https://openalex.org/W2103406407","https://openalex.org/W2104830490","https://openalex.org/W2123195862","https://openalex.org/W2147750403","https://openalex.org/W2169982856","https://openalex.org/W2235056388","https://openalex.org/W2329479259","https://openalex.org/W2334782222","https://openalex.org/W4231022371"],"related_works":["https://openalex.org/W4297819361","https://openalex.org/W1491017262","https://openalex.org/W1494824878","https://openalex.org/W4294338060","https://openalex.org/W2096013579","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609"],"abstract_inverted_index":{"Algorithms":[0],"for":[1],"learning":[2],"the":[3,24,32],"optimal":[4],"policy":[5],"of":[6,23],"a":[7],"Markov":[8],"decision":[9],"process":[10],"(MDP)":[11],"based":[12],"on":[13],"simulated":[14],"transitions":[15],"are":[16,21,39],"formulated":[17],"and":[18],"analyzed.":[19],"These":[20],"variants":[22],"well-known":[25],"\"actor-critic\"":[26],"(or":[27],"\"adaptive":[28],"critic\")":[29],"algorithm":[30],"in":[31],"artificial":[33],"intelligence":[34],"literature.":[35],"Distributed":[36],"asynchronous":[37],"implementations":[38],"considered.":[40],"The":[41],"analysis":[42],"involves":[43],"two":[44],"time":[45],"scale":[46],"stochastic":[47],"approximations.":[48]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}